diff options
617 files changed, 32331 insertions, 5525 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 99983e6..da95513 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -162,7 +162,7 @@ Description: Discover CPUs in the same CPU frequency coordination domain What: /sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1} Date: August 2008 KernelVersion: 2.6.27 -Contact: discuss@x86-64.org +Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Disable L3 cache indices These files exist in every CPU's cache/index3 directory. Each diff --git a/Documentation/devicetree/bindings/net/ipq806x-dwmac.txt b/Documentation/devicetree/bindings/net/ipq806x-dwmac.txt new file mode 100644 index 0000000..6d7ab4e --- /dev/null +++ b/Documentation/devicetree/bindings/net/ipq806x-dwmac.txt @@ -0,0 +1,35 @@ +* IPQ806x DWMAC Ethernet controller + +The device inherits all the properties of the dwmac/stmmac devices +described in the file net/stmmac.txt with the following changes. + +Required properties: + +- compatible: should be "qcom,ipq806x-gmac" along with "snps,dwmac" + and any applicable more detailed version number + described in net/stmmac.txt + +- qcom,nss-common: should contain a phandle to a syscon device mapping the + nss-common registers. + +- qcom,qsgmii-csr: should contain a phandle to a syscon device mapping the + qsgmii-csr registers. + +Example: + + gmac: ethernet@37000000 { + device_type = "network"; + compatible = "qcom,ipq806x-gmac"; + reg = <0x37000000 0x200000>; + interrupts = <GIC_SPI 220 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + + qcom,nss-common = <&nss_common>; + qcom,qsgmii-csr = <&qsgmii_csr>; + + clocks = <&gcc GMAC_CORE1_CLK>; + clock-names = "stmmaceth"; + + resets = <&gcc GMAC_CORE1_RESET>; + reset-names = "stmmaceth"; + }; diff --git a/Documentation/devicetree/bindings/net/ti,dp83867.txt b/Documentation/devicetree/bindings/net/ti,dp83867.txt new file mode 100644 index 0000000..46bb67a --- /dev/null +++ b/Documentation/devicetree/bindings/net/ti,dp83867.txt @@ -0,0 +1,19 @@ +* Texas Instruments - dp83867 Giga bit ethernet phy + +Required properties: + - reg - The ID number for the phy, usually a small integer + - ti,rx_int_delay - RGMII Recieve Clock Delay - see dt-bindings/net/ti-dp83867.h + for applicable values + - ti,tx_int_delay - RGMII Transmit Clock Delay - see dt-bindings/net/ti-dp83867.h + for applicable values + - ti,fifo_depth - Transmitt FIFO depth- see dt-bindings/net/ti-dp83867.h + for applicable values + +Example: + + ethernet-phy@0 { + reg = <0>; + ti,rx_int_delay = <DP83867_RGMIIDCTL_2_25_NS>; + ti,tx_int_delay = <DP83867_RGMIIDCTL_2_75_NS>; + ti,fifo_depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>; + }; diff --git a/Documentation/hwmon/tmp401 b/Documentation/hwmon/tmp401 index 8eb88e9..711f75e 100644 --- a/Documentation/hwmon/tmp401 +++ b/Documentation/hwmon/tmp401 @@ -20,7 +20,7 @@ Supported chips: Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp432.html * Texas Instruments TMP435 Prefix: 'tmp435' - Addresses scanned: I2C 0x37, 0x48 - 0x4f + Addresses scanned: I2C 0x48 - 0x4f Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp435.html Authors: diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt index 22bbc72..1700756 100644 --- a/Documentation/networking/ieee802154.txt +++ b/Documentation/networking/ieee802154.txt @@ -30,8 +30,8 @@ int sd = socket(PF_IEEE802154, SOCK_DGRAM, 0); The address family, socket addresses etc. are defined in the include/net/af_ieee802154.h header or in the special header -in our userspace package (see either linux-zigbee sourceforge download page -or git tree at git://linux-zigbee.git.sourceforge.net/gitroot/linux-zigbee). +in the userspace package (see either http://wpan.cakelab.org/ or the +git tree at https://github.com/linux-wpan/wpan-tools). One can use SOCK_RAW for passing raw data towards device xmit function. YMMV. @@ -49,15 +49,6 @@ Like with WiFi, there are several types of devices implementing IEEE 802.15.4. Those types of devices require different approach to be hooked into Linux kernel. -MLME - MAC Level Management -============================ - -Most of IEEE 802.15.4 MLME interfaces are directly mapped on netlink commands. -See the include/net/nl802154.h header. Our userspace tools package -(see above) provides CLI configuration utility for radio interfaces and simple -coordinator for IEEE 802.15.4 networks as an example users of MLME protocol. - - HardMAC ======= @@ -75,8 +66,6 @@ net_device with a pointer to struct ieee802154_mlme_ops instance. The fields assoc_req, assoc_resp, disassoc_req, start_req, and scan_req are optional. All other fields are required. -We provide an example of simple HardMAC driver at drivers/ieee802154/fakehard.c - SoftMAC ======= @@ -89,7 +78,8 @@ stack interface for network sniffers (e.g. WireShark). This layer is going to be extended soon. -See header include/net/mac802154.h and several drivers in drivers/ieee802154/. +See header include/net/mac802154.h and several drivers in +drivers/net/ieee802154/. Device drivers API @@ -114,18 +104,17 @@ Moreover IEEE 802.15.4 device operations structure should be filled. Fake drivers ============ -In addition there are two drivers available which simulate real devices with -HardMAC (fakehard) and SoftMAC (fakelb - IEEE 802.15.4 loopback driver) -interfaces. This option provides possibility to test and debug stack without -usage of real hardware. +In addition there is a driver available which simulates a real device with +SoftMAC (fakelb - IEEE 802.15.4 loopback driver) interface. This option +provides possibility to test and debug stack without usage of real hardware. -See sources in drivers/ieee802154 folder for more details. +See sources in drivers/net/ieee802154 folder for more details. 6LoWPAN Linux implementation ============================ -The IEEE 802.15.4 standard specifies an MTU of 128 bytes, yielding about 80 +The IEEE 802.15.4 standard specifies an MTU of 127 bytes, yielding about 80 octets of actual MAC payload once security is turned on, on a wireless link with a link throughput of 250 kbps or less. The 6LoWPAN adaptation format [RFC4944] was specified to carry IPv6 datagrams over such constrained links, @@ -140,7 +129,8 @@ In Semptember 2011 the standard update was published - [RFC6282]. It deprecates HC1 and HC2 compression and defines IPHC encoding format which is used in this Linux implementation. -All the code related to 6lowpan you may find in files: net/ieee802154/6lowpan.* +All the code related to 6lowpan you may find in files: net/6lowpan/* +and net/ieee802154/6lowpan/* To setup 6lowpan interface you need (busybox release > 1.17.0): 1. Add IEEE802.15.4 interface and initialize PANid; diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index cb083e0..5fae770 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -751,8 +751,10 @@ IP Variables: ip_local_port_range - 2 INTEGERS Defines the local port range that is used by TCP and UDP to choose the local port. The first number is the first, the - second the last local port number. The default values are - 32768 and 61000 respectively. + second the last local port number. + If possible, it is better these numbers have different parity. + (one even and one odd values) + The default values are 32768 and 60999 respectively. ip_local_reserved_ports - list of comma separated ranges Specify the ports which are reserved for known third-party @@ -775,7 +777,7 @@ ip_local_reserved_ports - list of comma separated ranges ip_local_port_range, e.g.: $ cat /proc/sys/net/ipv4/ip_local_port_range - 32000 61000 + 32000 60999 $ cat /proc/sys/net/ipv4/ip_local_reserved_ports 8080,9148 diff --git a/Documentation/target/tcmu-design.txt b/Documentation/target/tcmu-design.txt index 43e94ea..263b907 100644 --- a/Documentation/target/tcmu-design.txt +++ b/Documentation/target/tcmu-design.txt @@ -15,8 +15,7 @@ Contents: a) Discovering and configuring TCMU uio devices b) Waiting for events on the device(s) c) Managing the command ring -3) Command filtering and pass_level -4) A final note +3) A final note TCM Userspace Design @@ -324,7 +323,7 @@ int handle_device_events(int fd, void *map) /* Process events from cmd ring until we catch up with cmd_head */ while (ent != (void *)mb + mb->cmdr_off + mb->cmd_head) { - if (tcmu_hdr_get_op(&ent->hdr) == TCMU_OP_CMD) { + if (tcmu_hdr_get_op(ent->hdr.len_op) == TCMU_OP_CMD) { uint8_t *cdb = (void *)mb + ent->req.cdb_off; bool success = true; @@ -339,8 +338,12 @@ int handle_device_events(int fd, void *map) ent->rsp.scsi_status = SCSI_CHECK_CONDITION; } } + else if (tcmu_hdr_get_op(ent->hdr.len_op) != TCMU_OP_PAD) { + /* Tell the kernel we didn't handle unknown opcodes */ + ent->hdr.uflags |= TCMU_UFLAG_UNKNOWN_OP; + } else { - /* Do nothing for PAD entries */ + /* Do nothing for PAD entries except update cmd_tail */ } /* update cmd_tail */ @@ -360,28 +363,6 @@ int handle_device_events(int fd, void *map) } -Command filtering and pass_level --------------------------------- - -TCMU supports a "pass_level" option with valid values of 0 or 1. When -the value is 0 (the default), nearly all SCSI commands received for -the device are passed through to the handler. This allows maximum -flexibility but increases the amount of code required by the handler, -to support all mandatory SCSI commands. If pass_level is set to 1, -then only IO-related commands are presented, and the rest are handled -by LIO's in-kernel command emulation. The commands presented at level -1 include all versions of: - -READ -WRITE -WRITE_VERIFY -XDWRITEREAD -WRITE_SAME -COMPARE_AND_WRITE -SYNCHRONIZE_CACHE -UNMAP - - A final note ------------ diff --git a/MAINTAINERS b/MAINTAINERS index c6f4576..3a4b7cb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -921,6 +921,13 @@ M: Krzysztof Halasa <khalasa@piap.pl> S: Maintained F: arch/arm/mach-cns3xxx/ +ARM/CAVIUM THUNDER NETWORK DRIVER +M: Sunil Goutham <sgoutham@cavium.com> +M: Robert Richter <rric@kernel.org> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Supported +F: drivers/net/ethernet/cavium/ + ARM/CIRRUS LOGIC CLPS711X ARM ARCHITECTURE M: Alexander Shiyan <shc_work@mail.ru> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -2426,7 +2433,6 @@ L: linux-security-module@vger.kernel.org S: Supported F: include/linux/capability.h F: include/uapi/linux/capability.h -F: security/capability.c F: security/commoncap.c F: kernel/capability.c @@ -3824,10 +3830,11 @@ M: David Woodhouse <dwmw2@infradead.org> L: linux-embedded@vger.kernel.org S: Maintained -EMULEX LPFC FC SCSI DRIVER -M: James Smart <james.smart@emulex.com> +EMULEX/AVAGO LPFC FC/FCOE SCSI DRIVER +M: James Smart <james.smart@avagotech.com> +M: Dick Kennedy <dick.kennedy@avagotech.com> L: linux-scsi@vger.kernel.org -W: http://sourceforge.net/projects/lpfcxxxx +W: http://www.avagotech.com S: Supported F: drivers/scsi/lpfc/ @@ -8834,9 +8841,11 @@ F: drivers/misc/phantom.c F: include/uapi/linux/phantom.h SERVER ENGINES 10Gbps iSCSI - BladeEngine 2 DRIVER -M: Jayamohan Kallickal <jayamohan.kallickal@emulex.com> +M: Jayamohan Kallickal <jayamohan.kallickal@avagotech.com> +M: Minh Tran <minh.tran@avagotech.com> +M: John Soni Jose <sony.john-n@avagotech.com> L: linux-scsi@vger.kernel.org -W: http://www.emulex.com +W: http://www.avagotech.com S: Supported F: drivers/scsi/be2iscsi/ @@ -10590,8 +10599,7 @@ F: drivers/virtio/virtio_input.c F: include/uapi/linux/virtio_input.h VIA RHINE NETWORK DRIVER -M: Roger Luethi <rl@hellgate.ch> -S: Maintained +S: Orphan F: drivers/net/ethernet/via/via-rhine.c VIA SD/MMC CARD CONTROLLER DRIVER @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc6 NAME = Hurr durr I'ma sheep # *DOCUMENTATION* diff --git a/arch/alpha/boot/Makefile b/arch/alpha/boot/Makefile index cd14388..8399bd0 100644 --- a/arch/alpha/boot/Makefile +++ b/arch/alpha/boot/Makefile @@ -14,6 +14,9 @@ targets := vmlinux.gz vmlinux \ tools/bootpzh bootloader bootpheader bootpzheader OBJSTRIP := $(obj)/tools/objstrip +HOSTCFLAGS := -Wall -I$(objtree)/usr/include +BOOTCFLAGS += -I$(obj) -I$(srctree)/$(obj) + # SRM bootable image. Copy to offset 512 of a partition. $(obj)/bootimage: $(addprefix $(obj)/tools/,mkbb lxboot bootlx) $(obj)/vmlinux.nh ( cat $(obj)/tools/lxboot $(obj)/tools/bootlx $(obj)/vmlinux.nh ) > $@ @@ -96,13 +99,14 @@ $(obj)/tools/bootph: $(obj)/bootpheader $(OBJSTRIP) FORCE $(obj)/tools/bootpzh: $(obj)/bootpzheader $(OBJSTRIP) FORCE $(call if_changed,objstrip) -LDFLAGS_bootloader := -static -uvsprintf -T #-N -relax -LDFLAGS_bootpheader := -static -uvsprintf -T #-N -relax -LDFLAGS_bootpzheader := -static -uvsprintf -T #-N -relax +LDFLAGS_bootloader := -static -T # -N -relax +LDFLAGS_bootloader := -static -T # -N -relax +LDFLAGS_bootpheader := -static -T # -N -relax +LDFLAGS_bootpzheader := -static -T # -N -relax -OBJ_bootlx := $(obj)/head.o $(obj)/main.o -OBJ_bootph := $(obj)/head.o $(obj)/bootp.o -OBJ_bootpzh := $(obj)/head.o $(obj)/bootpz.o $(obj)/misc.o +OBJ_bootlx := $(obj)/head.o $(obj)/stdio.o $(obj)/main.o +OBJ_bootph := $(obj)/head.o $(obj)/stdio.o $(obj)/bootp.o +OBJ_bootpzh := $(obj)/head.o $(obj)/stdio.o $(obj)/bootpz.o $(obj)/misc.o $(obj)/bootloader: $(obj)/bootloader.lds $(OBJ_bootlx) $(LIBS_Y) FORCE $(call if_changed,ld) diff --git a/arch/alpha/boot/main.c b/arch/alpha/boot/main.c index 3baf2d1..dd6eb4a 100644 --- a/arch/alpha/boot/main.c +++ b/arch/alpha/boot/main.c @@ -19,7 +19,6 @@ #include "ksize.h" -extern int vsprintf(char *, const char *, va_list); extern unsigned long switch_to_osf_pal(unsigned long nr, struct pcb_struct * pcb_va, struct pcb_struct * pcb_pa, unsigned long *vptb); diff --git a/arch/alpha/boot/stdio.c b/arch/alpha/boot/stdio.c new file mode 100644 index 0000000..f844dae --- /dev/null +++ b/arch/alpha/boot/stdio.c @@ -0,0 +1,306 @@ +/* + * Copyright (C) Paul Mackerras 1997. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <stdarg.h> +#include <stddef.h> + +size_t strnlen(const char * s, size_t count) +{ + const char *sc; + + for (sc = s; count-- && *sc != '\0'; ++sc) + /* nothing */; + return sc - s; +} + +# define do_div(n, base) ({ \ + unsigned int __base = (base); \ + unsigned int __rem; \ + __rem = ((unsigned long long)(n)) % __base; \ + (n) = ((unsigned long long)(n)) / __base; \ + __rem; \ +}) + + +static int skip_atoi(const char **s) +{ + int i, c; + + for (i = 0; '0' <= (c = **s) && c <= '9'; ++*s) + i = i*10 + c - '0'; + return i; +} + +#define ZEROPAD 1 /* pad with zero */ +#define SIGN 2 /* unsigned/signed long */ +#define PLUS 4 /* show plus */ +#define SPACE 8 /* space if plus */ +#define LEFT 16 /* left justified */ +#define SPECIAL 32 /* 0x */ +#define LARGE 64 /* use 'ABCDEF' instead of 'abcdef' */ + +static char * number(char * str, unsigned long long num, int base, int size, int precision, int type) +{ + char c,sign,tmp[66]; + const char *digits="0123456789abcdefghijklmnopqrstuvwxyz"; + int i; + + if (type & LARGE) + digits = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"; + if (type & LEFT) + type &= ~ZEROPAD; + if (base < 2 || base > 36) + return 0; + c = (type & ZEROPAD) ? '0' : ' '; + sign = 0; + if (type & SIGN) { + if ((signed long long)num < 0) { + sign = '-'; + num = - (signed long long)num; + size--; + } else if (type & PLUS) { + sign = '+'; + size--; + } else if (type & SPACE) { + sign = ' '; + size--; + } + } + if (type & SPECIAL) { + if (base == 16) + size -= 2; + else if (base == 8) + size--; + } + i = 0; + if (num == 0) + tmp[i++]='0'; + else while (num != 0) { + tmp[i++] = digits[do_div(num, base)]; + } + if (i > precision) + precision = i; + size -= precision; + if (!(type&(ZEROPAD+LEFT))) + while(size-->0) + *str++ = ' '; + if (sign) + *str++ = sign; + if (type & SPECIAL) { + if (base==8) + *str++ = '0'; + else if (base==16) { + *str++ = '0'; + *str++ = digits[33]; + } + } + if (!(type & LEFT)) + while (size-- > 0) + *str++ = c; + while (i < precision--) + *str++ = '0'; + while (i-- > 0) + *str++ = tmp[i]; + while (size-- > 0) + *str++ = ' '; + return str; +} + +int vsprintf(char *buf, const char *fmt, va_list args) +{ + int len; + unsigned long long num; + int i, base; + char * str; + const char *s; + + int flags; /* flags to number() */ + + int field_width; /* width of output field */ + int precision; /* min. # of digits for integers; max + number of chars for from string */ + int qualifier; /* 'h', 'l', or 'L' for integer fields */ + /* 'z' support added 23/7/1999 S.H. */ + /* 'z' changed to 'Z' --davidm 1/25/99 */ + + + for (str=buf ; *fmt ; ++fmt) { + if (*fmt != '%') { + *str++ = *fmt; + continue; + } + + /* process flags */ + flags = 0; + repeat: + ++fmt; /* this also skips first '%' */ + switch (*fmt) { + case '-': flags |= LEFT; goto repeat; + case '+': flags |= PLUS; goto repeat; + case ' ': flags |= SPACE; goto repeat; + case '#': flags |= SPECIAL; goto repeat; + case '0': flags |= ZEROPAD; goto repeat; + } + + /* get field width */ + field_width = -1; + if ('0' <= *fmt && *fmt <= '9') + field_width = skip_atoi(&fmt); + else if (*fmt == '*') { + ++fmt; + /* it's the next argument */ + field_width = va_arg(args, int); + if (field_width < 0) { + field_width = -field_width; + flags |= LEFT; + } + } + + /* get the precision */ + precision = -1; + if (*fmt == '.') { + ++fmt; + if ('0' <= *fmt && *fmt <= '9') + precision = skip_atoi(&fmt); + else if (*fmt == '*') { + ++fmt; + /* it's the next argument */ + precision = va_arg(args, int); + } + if (precision < 0) + precision = 0; + } + + /* get the conversion qualifier */ + qualifier = -1; + if (*fmt == 'l' && *(fmt + 1) == 'l') { + qualifier = 'q'; + fmt += 2; + } else if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' + || *fmt == 'Z') { + qualifier = *fmt; + ++fmt; + } + + /* default base */ + base = 10; + + switch (*fmt) { + case 'c': + if (!(flags & LEFT)) + while (--field_width > 0) + *str++ = ' '; + *str++ = (unsigned char) va_arg(args, int); + while (--field_width > 0) + *str++ = ' '; + continue; + + case 's': + s = va_arg(args, char *); + if (!s) + s = "<NULL>"; + + len = strnlen(s, precision); + + if (!(flags & LEFT)) + while (len < field_width--) + *str++ = ' '; + for (i = 0; i < len; ++i) + *str++ = *s++; + while (len < field_width--) + *str++ = ' '; + continue; + + case 'p': + if (field_width == -1) { + field_width = 2*sizeof(void *); + flags |= ZEROPAD; + } + str = number(str, + (unsigned long) va_arg(args, void *), 16, + field_width, precision, flags); + continue; + + + case 'n': + if (qualifier == 'l') { + long * ip = va_arg(args, long *); + *ip = (str - buf); + } else if (qualifier == 'Z') { + size_t * ip = va_arg(args, size_t *); + *ip = (str - buf); + } else { + int * ip = va_arg(args, int *); + *ip = (str - buf); + } + continue; + + case '%': + *str++ = '%'; + continue; + + /* integer number formats - set up the flags and "break" */ + case 'o': + base = 8; + break; + + case 'X': + flags |= LARGE; + case 'x': + base = 16; + break; + + case 'd': + case 'i': + flags |= SIGN; + case 'u': + break; + + default: + *str++ = '%'; + if (*fmt) + *str++ = *fmt; + else + --fmt; + continue; + } + if (qualifier == 'l') { + num = va_arg(args, unsigned long); + if (flags & SIGN) + num = (signed long) num; + } else if (qualifier == 'q') { + num = va_arg(args, unsigned long long); + if (flags & SIGN) + num = (signed long long) num; + } else if (qualifier == 'Z') { + num = va_arg(args, size_t); + } else if (qualifier == 'h') { + num = (unsigned short) va_arg(args, int); + if (flags & SIGN) + num = (signed short) num; + } else { + num = va_arg(args, unsigned int); + if (flags & SIGN) + num = (signed int) num; + } + str = number(str, num, base, field_width, precision, flags); + } + *str = '\0'; + return str-buf; +} + +int sprintf(char * buf, const char *fmt, ...) +{ + va_list args; + int i; + + va_start(args, fmt); + i=vsprintf(buf,fmt,args); + va_end(args); + return i; +} diff --git a/arch/alpha/boot/tools/objstrip.c b/arch/alpha/boot/tools/objstrip.c index 367d53d..dee8269 100644 --- a/arch/alpha/boot/tools/objstrip.c +++ b/arch/alpha/boot/tools/objstrip.c @@ -27,6 +27,9 @@ #include <linux/param.h> #ifdef __ELF__ # include <linux/elf.h> +# define elfhdr elf64_hdr +# define elf_phdr elf64_phdr +# define elf_check_arch(x) ((x)->e_machine == EM_ALPHA) #endif /* bootfile size must be multiple of BLOCK_SIZE: */ diff --git a/arch/alpha/include/asm/types.h b/arch/alpha/include/asm/types.h index f61e1a5..4cb4b6d 100644 --- a/arch/alpha/include/asm/types.h +++ b/arch/alpha/include/asm/types.h @@ -2,6 +2,5 @@ #define _ALPHA_TYPES_H #include <asm-generic/int-ll64.h> -#include <uapi/asm/types.h> #endif /* _ALPHA_TYPES_H */ diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h index c509d30..a56e608 100644 --- a/arch/alpha/include/asm/unistd.h +++ b/arch/alpha/include/asm/unistd.h @@ -3,7 +3,7 @@ #include <uapi/asm/unistd.h> -#define NR_SYSCALLS 511 +#define NR_SYSCALLS 514 #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_STAT64 diff --git a/arch/alpha/include/uapi/asm/unistd.h b/arch/alpha/include/uapi/asm/unistd.h index d214a035..aa33bf5 100644 --- a/arch/alpha/include/uapi/asm/unistd.h +++ b/arch/alpha/include/uapi/asm/unistd.h @@ -472,5 +472,8 @@ #define __NR_sched_setattr 508 #define __NR_sched_getattr 509 #define __NR_renameat2 510 +#define __NR_getrandom 511 +#define __NR_memfd_create 512 +#define __NR_execveat 513 #endif /* _UAPI_ALPHA_UNISTD_H */ diff --git a/arch/alpha/kernel/err_ev6.c b/arch/alpha/kernel/err_ev6.c index 253cf1a..51267ac 100644 --- a/arch/alpha/kernel/err_ev6.c +++ b/arch/alpha/kernel/err_ev6.c @@ -6,7 +6,6 @@ * Error handling code supporting Alpha systems */ -#include <linux/init.h> #include <linux/sched.h> #include <asm/io.h> diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index 7b2be25..51f2c86 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -19,7 +19,6 @@ #include <linux/ptrace.h> #include <linux/interrupt.h> #include <linux/random.h> -#include <linux/init.h> #include <linux/irq.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index e51f578..36dc91a 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1019,14 +1019,13 @@ SYSCALL_DEFINE2(osf_settimeofday, struct timeval32 __user *, tv, if (tv) { if (get_tv32((struct timeval *)&kts, tv)) return -EFAULT; + kts.tv_nsec *= 1000; } if (tz) { if (copy_from_user(&ktz, tz, sizeof(*tz))) return -EFAULT; } - kts.tv_nsec *= 1000; - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); } diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 1941a07..84d1326 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -236,12 +236,11 @@ release_thread(struct task_struct *dead_task) } /* - * Copy an alpha thread.. + * Copy architecture-specific thread state */ - int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, + unsigned long kthread_arg, struct task_struct *p) { extern void ret_from_fork(void); @@ -262,7 +261,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp, sizeof(struct switch_stack) + sizeof(struct pt_regs)); childstack->r26 = (unsigned long) ret_from_kernel_thread; childstack->r9 = usp; /* function */ - childstack->r10 = arg; + childstack->r10 = kthread_arg; childregs->hae = alpha_mv.hae_cache, childti->pcb.usp = 0; return 0; diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 99ac36d..2f24447f 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -63,7 +63,6 @@ static struct { enum ipi_message_type { IPI_RESCHEDULE, IPI_CALL_FUNC, - IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, }; @@ -506,7 +505,6 @@ setup_profiling_timer(unsigned int multiplier) return -EINVAL; } - static void send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation) { @@ -552,10 +550,6 @@ handle_ipi(struct pt_regs *regs) generic_smp_call_function_interrupt(); break; - case IPI_CALL_FUNC_SINGLE: - generic_smp_call_function_single_interrupt(); - break; - case IPI_CPU_STOP: halt(); @@ -606,7 +600,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) void arch_send_call_function_single_ipi(int cpu) { - send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); + send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC); } static void diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c index 6f01d9a..72b5951 100644 --- a/arch/alpha/kernel/srmcons.c +++ b/arch/alpha/kernel/srmcons.c @@ -237,8 +237,7 @@ srmcons_init(void) return -ENODEV; } - -module_init(srmcons_init); +device_initcall(srmcons_init); /* diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c index f21d61f..24e41bd 100644 --- a/arch/alpha/kernel/sys_marvel.c +++ b/arch/alpha/kernel/sys_marvel.c @@ -331,7 +331,7 @@ marvel_map_irq(const struct pci_dev *cdev, u8 slot, u8 pin) pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &intline); irq = intline; - msi_loc = pci_find_capability(dev, PCI_CAP_ID_MSI); + msi_loc = dev->msi_cap; msg_ctl = 0; if (msi_loc) pci_read_config_word(dev, msi_loc + PCI_MSI_FLAGS, &msg_ctl); diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S index 24789713..9b62e3f 100644 --- a/arch/alpha/kernel/systbls.S +++ b/arch/alpha/kernel/systbls.S @@ -529,6 +529,9 @@ sys_call_table: .quad sys_sched_setattr .quad sys_sched_getattr .quad sys_renameat2 /* 510 */ + .quad sys_getrandom + .quad sys_memfd_create + .quad sys_execveat .size sys_call_table, . - sys_call_table .type sys_call_table, @object diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 9c4c189..74aceea 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -14,7 +14,6 @@ #include <linux/tty.h> #include <linux/delay.h> #include <linux/module.h> -#include <linux/init.h> #include <linux/kallsyms.h> #include <linux/ratelimit.h> diff --git a/arch/alpha/oprofile/op_model_ev4.c b/arch/alpha/oprofile/op_model_ev4.c index 18aa9b4..086a0d5 100644 --- a/arch/alpha/oprofile/op_model_ev4.c +++ b/arch/alpha/oprofile/op_model_ev4.c @@ -8,7 +8,6 @@ */ #include <linux/oprofile.h> -#include <linux/init.h> #include <linux/smp.h> #include <asm/ptrace.h> diff --git a/arch/alpha/oprofile/op_model_ev5.c b/arch/alpha/oprofile/op_model_ev5.c index c32f8a0..c300f5e 100644 --- a/arch/alpha/oprofile/op_model_ev5.c +++ b/arch/alpha/oprofile/op_model_ev5.c @@ -8,7 +8,6 @@ */ #include <linux/oprofile.h> -#include <linux/init.h> #include <linux/smp.h> #include <asm/ptrace.h> diff --git a/arch/alpha/oprofile/op_model_ev6.c b/arch/alpha/oprofile/op_model_ev6.c index 1c84cc2..02edf59 100644 --- a/arch/alpha/oprofile/op_model_ev6.c +++ b/arch/alpha/oprofile/op_model_ev6.c @@ -8,7 +8,6 @@ */ #include <linux/oprofile.h> -#include <linux/init.h> #include <linux/smp.h> #include <asm/ptrace.h> diff --git a/arch/alpha/oprofile/op_model_ev67.c b/arch/alpha/oprofile/op_model_ev67.c index 34a57a1..adb1744 100644 --- a/arch/alpha/oprofile/op_model_ev67.c +++ b/arch/alpha/oprofile/op_model_ev67.c @@ -9,7 +9,6 @@ */ #include <linux/oprofile.h> -#include <linux/init.h> #include <linux/smp.h> #include <asm/ptrace.h> diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 86217db..992736b 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -223,7 +223,7 @@ dtb-$(CONFIG_SOC_IMX25) += \ imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dtb \ imx25-karo-tx25.dtb \ imx25-pdk.dtb -dtb-$(CONFIG_SOC_IMX31) += \ +dtb-$(CONFIG_SOC_IMX27) += \ imx27-apf27.dtb \ imx27-apf27dev.dtb \ imx27-eukrea-mbimxsd27-baseboard.dtb \ diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts index 5c42d25..901739f 100644 --- a/arch/arm/boot/dts/am335x-boneblack.dts +++ b/arch/arm/boot/dts/am335x-boneblack.dts @@ -80,7 +80,3 @@ status = "okay"; }; }; - -&rtc { - system-power-controller; -}; diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 87fc7a3..156d05e 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -654,7 +654,7 @@ wlcore: wlcore@2 { compatible = "ti,wl1271"; reg = <2>; - interrupt-parent = <&gpio1>; + interrupt-parent = <&gpio0>; interrupts = <31 IRQ_TYPE_LEVEL_HIGH>; /* gpio 31 */ ref-clock-frequency = <38400000>; }; diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts index 173ffa4..792394d 100644 --- a/arch/arm/boot/dts/exynos4412-trats2.dts +++ b/arch/arm/boot/dts/exynos4412-trats2.dts @@ -736,7 +736,7 @@ display-timings { timing-0 { - clock-frequency = <0>; + clock-frequency = <57153600>; hactive = <720>; vactive = <1280>; hfront-porch = <5>; diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index 6951b66..bc215e4 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -533,7 +533,7 @@ fec: ethernet@1002b000 { compatible = "fsl,imx27-fec"; - reg = <0x1002b000 0x4000>; + reg = <0x1002b000 0x1000>; interrupts = <50>; clocks = <&clks IMX27_CLK_FEC_IPG_GATE>, <&clks IMX27_CLK_FEC_AHB_GATE>; diff --git a/arch/arm/boot/dts/omap3-devkit8000.dts b/arch/arm/boot/dts/omap3-devkit8000.dts index 134d3f2..921de66 100644 --- a/arch/arm/boot/dts/omap3-devkit8000.dts +++ b/arch/arm/boot/dts/omap3-devkit8000.dts @@ -110,6 +110,8 @@ nand@0,0 { reg = <0 0 4>; /* CS0, offset 0, IO size 4 */ nand-bus-width = <16>; + gpmc,device-width = <2>; + ti,nand-ecc-opt = "sw"; gpmc,sync-clk-ps = <0>; gpmc,cs-on-ns = <0>; diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 0ca4a3e..fbbb191 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -429,7 +429,7 @@ CONFIG_USB_EHCI_EXYNOS=y CONFIG_USB_EHCI_TEGRA=y CONFIG_USB_EHCI_HCD_STI=y CONFIG_USB_EHCI_HCD_PLATFORM=y -CONFIG_USB_ISP1760_HCD=y +CONFIG_USB_ISP1760=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_STI=y CONFIG_USB_OHCI_HCD_PLATFORM=y diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index f8ccc21..4e7f40c 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -33,7 +33,9 @@ ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq @ disable interrupts - ldr r1, [tsk, #TI_FLAGS] + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing + tst r1, #_TIF_SYSCALL_WORK + bne __sys_trace_return tst r1, #_TIF_WORK_MASK bne fast_work_pending asm_trace_hardirqs_on diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 213919b..3b8c283 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -304,16 +304,17 @@ static int probe_current_pmu(struct arm_pmu *pmu) static int of_pmu_irq_cfg(struct platform_device *pdev) { int i, irq; - int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); - - if (!irqs) - return -ENOMEM; + int *irqs; /* Don't bother with PPIs; they're already affine */ irq = platform_get_irq(pdev, 0); if (irq >= 0 && irq_is_percpu(irq)) return 0; + irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); + if (!irqs) + return -ENOMEM; + for (i = 0; i < pdev->num_resources; ++i) { struct device_node *dn; int cpu; diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c index 4d60005..6d0893a 100644 --- a/arch/arm/mach-imx/gpc.c +++ b/arch/arm/mach-imx/gpc.c @@ -280,9 +280,15 @@ void __init imx_gpc_check_dt(void) struct device_node *np; np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpc"); - if (WARN_ON(!np || - !of_find_property(np, "interrupt-controller", NULL))) - pr_warn("Outdated DT detected, system is about to crash!!!\n"); + if (WARN_ON(!np)) + return; + + if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) { + pr_warn("Outdated DT detected, suspend/resume will NOT work\n"); + + /* map GPC, so that at least CPUidle and WARs keep working */ + gpc_base = of_iomap(np, 0); + } } #ifdef CONFIG_PM_GENERIC_DOMAINS @@ -443,6 +449,10 @@ static int imx_gpc_probe(struct platform_device *pdev) struct regulator *pu_reg; int ret; + /* bail out if DT too old and doesn't provide the necessary info */ + if (!of_property_read_bool(pdev->dev.of_node, "#power-domain-cells")) + return 0; + pu_reg = devm_regulator_get_optional(&pdev->dev, "pu"); if (PTR_ERR(pu_reg) == -ENODEV) pu_reg = NULL; diff --git a/arch/arm/mach-pxa/pxa_cplds_irqs.c b/arch/arm/mach-pxa/pxa_cplds_irqs.c index f1aeb54..2385052 100644 --- a/arch/arm/mach-pxa/pxa_cplds_irqs.c +++ b/arch/arm/mach-pxa/pxa_cplds_irqs.c @@ -107,7 +107,7 @@ static int cplds_probe(struct platform_device *pdev) struct resource *res; struct cplds *fpga; int ret; - unsigned int base_irq = 0; + int base_irq; unsigned long irqflags = 0; fpga = devm_kzalloc(&pdev->dev, sizeof(*fpga), GFP_KERNEL); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4e6ef89..7186382 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1112,22 +1112,22 @@ void __init sanity_check_meminfo(void) } /* - * Find the first non-section-aligned page, and point + * Find the first non-pmd-aligned page, and point * memblock_limit at it. This relies on rounding the - * limit down to be section-aligned, which happens at - * the end of this function. + * limit down to be pmd-aligned, which happens at the + * end of this function. * * With this algorithm, the start or end of almost any - * bank can be non-section-aligned. The only exception - * is that the start of the bank 0 must be section- + * bank can be non-pmd-aligned. The only exception is + * that the start of the bank 0 must be section- * aligned, since otherwise memory would need to be * allocated when mapping the start of bank 0, which * occurs before any free memory is mapped. */ if (!memblock_limit) { - if (!IS_ALIGNED(block_start, SECTION_SIZE)) + if (!IS_ALIGNED(block_start, PMD_SIZE)) memblock_limit = block_start; - else if (!IS_ALIGNED(block_end, SECTION_SIZE)) + else if (!IS_ALIGNED(block_end, PMD_SIZE)) memblock_limit = arm_lowmem_limit; } @@ -1137,12 +1137,12 @@ void __init sanity_check_meminfo(void) high_memory = __va(arm_lowmem_limit - 1) + 1; /* - * Round the memblock limit down to a section size. This + * Round the memblock limit down to a pmd size. This * helps to ensure that we will allocate memory from the - * last full section, which should be mapped. + * last full pmd, which should be mapped. */ if (memblock_limit) - memblock_limit = round_down(memblock_limit, SECTION_SIZE); + memblock_limit = round_down(memblock_limit, PMD_SIZE); if (!memblock_limit) memblock_limit = arm_lowmem_limit; diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index d4e162d..7cc3be9 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -478,9 +478,16 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) { - struct pci_controller *controller = bridge->bus->sysdata; - - ACPI_COMPANION_SET(&bridge->dev, controller->companion); + /* + * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL + * here, pci_create_root_bus() has been called by someone else and + * sysdata is likely to be different from what we expect. Let it go in + * that case. + */ + if (!bridge->dev.parent) { + struct pci_controller *controller = bridge->bus->sysdata; + ACPI_COMPANION_SET(&bridge->dev, controller->companion); + } return 0; } diff --git a/arch/mips/ath79/prom.c b/arch/mips/ath79/prom.c index e1fe630..597899a 100644 --- a/arch/mips/ath79/prom.c +++ b/arch/mips/ath79/prom.c @@ -1,6 +1,7 @@ /* * Atheros AR71XX/AR724X/AR913X specific prom routines * + * Copyright (C) 2015 Laurent Fasnacht <l@libres.ch> * Copyright (C) 2008-2010 Gabor Juhos <juhosg@openwrt.org> * Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org> * @@ -25,12 +26,14 @@ void __init prom_init(void) { fw_init_cmdline(); +#ifdef CONFIG_BLK_DEV_INITRD /* Read the initrd address from the firmware environment */ initrd_start = fw_getenvl("initrd_start"); if (initrd_start) { initrd_start = KSEG0ADDR(initrd_start); initrd_end = initrd_start + fw_getenvl("initrd_size"); } +#endif } void __init prom_free_prom_memory(void) diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig index 0026806..b2a577e 100644 --- a/arch/mips/configs/fuloong2e_defconfig +++ b/arch/mips/configs/fuloong2e_defconfig @@ -194,7 +194,7 @@ CONFIG_USB_WUSB_CBAF=m CONFIG_USB_C67X00_HCD=m CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_ROOT_HUB_TT=y -CONFIG_USB_ISP1760_HCD=m +CONFIG_USB_ISP1760=m CONFIG_USB_OHCI_HCD=y CONFIG_USB_UHCI_HCD=m CONFIG_USB_R8A66597_HCD=m diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c index d2bfbc2..51f57d8 100644 --- a/arch/mips/kernel/irq.c +++ b/arch/mips/kernel/irq.c @@ -29,7 +29,7 @@ int kgdb_early_setup; #endif -static unsigned long irq_map[NR_IRQS / BITS_PER_LONG]; +static DECLARE_BITMAP(irq_map, NR_IRQS); int allocate_irqno(void) { diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index fd528d7..336708a 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -444,7 +444,7 @@ struct plat_smp_ops bmips5000_smp_ops = { static void bmips_wr_vec(unsigned long dst, char *start, char *end) { memcpy((void *)dst, start, end - start); - dma_cache_wback((unsigned long)start, end - start); + dma_cache_wback(dst, end - start); local_flush_icache_range(dst, dst + (end - start)); instruction_hazard(); } diff --git a/arch/mips/lib/strnlen_user.S b/arch/mips/lib/strnlen_user.S index 7d12c0d..77e6494 100644 --- a/arch/mips/lib/strnlen_user.S +++ b/arch/mips/lib/strnlen_user.S @@ -34,7 +34,12 @@ LEAF(__strnlen_\func\()_asm) FEXPORT(__strnlen_\func\()_nocheck_asm) move v0, a0 PTR_ADDU a1, a0 # stop pointer -1: beq v0, a1, 1f # limit reached? +1: +#ifdef CONFIG_CPU_DADDI_WORKAROUNDS + .set noat + li AT, 1 +#endif + beq v0, a1, 1f # limit reached? .ifeqs "\func", "kernel" EX(lb, t0, (v0), .Lfault\@) .else @@ -42,7 +47,13 @@ FEXPORT(__strnlen_\func\()_nocheck_asm) .endif .set noreorder bnez t0, 1b -1: PTR_ADDIU v0, 1 +1: +#ifndef CONFIG_CPU_DADDI_WORKAROUNDS + PTR_ADDIU v0, 1 +#else + PTR_ADDU v0, AT + .set at +#endif .set reorder PTR_SUBU v0, a0 jr ra diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h index a6e424d..a6cfdab 100644 --- a/arch/sparc/include/asm/cpudata_64.h +++ b/arch/sparc/include/asm/cpudata_64.h @@ -24,7 +24,8 @@ typedef struct { unsigned int icache_line_size; unsigned int ecache_size; unsigned int ecache_line_size; - int core_id; + unsigned short sock_id; + unsigned short core_id; int proc_id; } cpuinfo_sparc; diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index dc165eb..2a52c91 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -308,12 +308,26 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot) " sllx %1, 32, %1\n" " or %0, %1, %0\n" " .previous\n" + " .section .sun_m7_2insn_patch, \"ax\"\n" + " .word 661b\n" + " sethi %%uhi(%4), %1\n" + " sethi %%hi(%4), %0\n" + " .word 662b\n" + " or %1, %%ulo(%4), %1\n" + " or %0, %%lo(%4), %0\n" + " .word 663b\n" + " sllx %1, 32, %1\n" + " or %0, %1, %0\n" + " .previous\n" : "=r" (mask), "=r" (tmp) : "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U | _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U), "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V | _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | + _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V), + "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V | + _PAGE_CP_4V | _PAGE_E_4V | _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V)); return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask)); @@ -342,9 +356,15 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot) " andn %0, %4, %0\n" " or %0, %5, %0\n" " .previous\n" + " .section .sun_m7_2insn_patch, \"ax\"\n" + " .word 661b\n" + " andn %0, %6, %0\n" + " or %0, %5, %0\n" + " .previous\n" : "=r" (val) : "0" (val), "i" (_PAGE_CP_4U | _PAGE_CV_4U), "i" (_PAGE_E_4U), - "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V)); + "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V), + "i" (_PAGE_CP_4V)); return __pgprot(val); } diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h index ed8f071..d1761df 100644 --- a/arch/sparc/include/asm/topology_64.h +++ b/arch/sparc/include/asm/topology_64.h @@ -40,11 +40,12 @@ static inline int pcibus_to_node(struct pci_bus *pbus) #ifdef CONFIG_SMP #define topology_physical_package_id(cpu) (cpu_data(cpu).proc_id) #define topology_core_id(cpu) (cpu_data(cpu).core_id) -#define topology_core_cpumask(cpu) (&cpu_core_map[cpu]) +#define topology_core_cpumask(cpu) (&cpu_core_sib_map[cpu]) #define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) #endif /* CONFIG_SMP */ extern cpumask_t cpu_core_map[NR_CPUS]; +extern cpumask_t cpu_core_sib_map[NR_CPUS]; static inline const struct cpumask *cpu_coregroup_mask(int cpu) { return &cpu_core_map[cpu]; diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h index 6fd4436..ec9c04d 100644 --- a/arch/sparc/include/asm/trap_block.h +++ b/arch/sparc/include/asm/trap_block.h @@ -79,6 +79,8 @@ struct sun4v_2insn_patch_entry { }; extern struct sun4v_2insn_patch_entry __sun4v_2insn_patch, __sun4v_2insn_patch_end; +extern struct sun4v_2insn_patch_entry __sun_m7_2insn_patch, + __sun_m7_2insn_patch_end; #endif /* !(__ASSEMBLY__) */ diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h index 07cc49e5..0f67942 100644 --- a/arch/sparc/kernel/entry.h +++ b/arch/sparc/kernel/entry.h @@ -69,6 +69,8 @@ void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *, struct sun4v_1insn_patch_entry *); void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *, struct sun4v_2insn_patch_entry *); +void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *, + struct sun4v_2insn_patch_entry *); extern unsigned int dcache_parity_tl1_occurred; extern unsigned int icache_parity_tl1_occurred; diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c index 94e392b..814fb17 100644 --- a/arch/sparc/kernel/leon_pci_grpci2.c +++ b/arch/sparc/kernel/leon_pci_grpci2.c @@ -723,7 +723,6 @@ static int grpci2_of_probe(struct platform_device *ofdev) err = -ENOMEM; goto err1; } - memset(grpci2priv, 0, sizeof(*grpci2priv)); priv->regs = regs; priv->irq = ofdev->archdata.irqs[0]; /* BASE IRQ */ priv->irq_mode = (capability & STS_IRQMODE) >> STS_IRQMODE_BIT; diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 26c80e1..6f80936 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -614,45 +614,68 @@ static void fill_in_one_cache(cpuinfo_sparc *c, struct mdesc_handle *hp, u64 mp) } } -static void mark_core_ids(struct mdesc_handle *hp, u64 mp, int core_id) +static void find_back_node_value(struct mdesc_handle *hp, u64 node, + char *srch_val, + void (*func)(struct mdesc_handle *, u64, int), + u64 val, int depth) { - u64 a; - - mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_BACK) { - u64 t = mdesc_arc_target(hp, a); - const char *name; - const u64 *id; + u64 arc; - name = mdesc_node_name(hp, t); - if (!strcmp(name, "cpu")) { - id = mdesc_get_property(hp, t, "id", NULL); - if (*id < NR_CPUS) - cpu_data(*id).core_id = core_id; - } else { - u64 j; + /* Since we have an estimate of recursion depth, do a sanity check. */ + if (depth == 0) + return; - mdesc_for_each_arc(j, hp, t, MDESC_ARC_TYPE_BACK) { - u64 n = mdesc_arc_target(hp, j); - const char *n_name; + mdesc_for_each_arc(arc, hp, node, MDESC_ARC_TYPE_BACK) { + u64 n = mdesc_arc_target(hp, arc); + const char *name = mdesc_node_name(hp, n); - n_name = mdesc_node_name(hp, n); - if (strcmp(n_name, "cpu")) - continue; + if (!strcmp(srch_val, name)) + (*func)(hp, n, val); - id = mdesc_get_property(hp, n, "id", NULL); - if (*id < NR_CPUS) - cpu_data(*id).core_id = core_id; - } - } + find_back_node_value(hp, n, srch_val, func, val, depth-1); } } +static void __mark_core_id(struct mdesc_handle *hp, u64 node, + int core_id) +{ + const u64 *id = mdesc_get_property(hp, node, "id", NULL); + + if (*id < num_possible_cpus()) + cpu_data(*id).core_id = core_id; +} + +static void __mark_sock_id(struct mdesc_handle *hp, u64 node, + int sock_id) +{ + const u64 *id = mdesc_get_property(hp, node, "id", NULL); + + if (*id < num_possible_cpus()) + cpu_data(*id).sock_id = sock_id; +} + +static void mark_core_ids(struct mdesc_handle *hp, u64 mp, + int core_id) +{ + find_back_node_value(hp, mp, "cpu", __mark_core_id, core_id, 10); +} + +static void mark_sock_ids(struct mdesc_handle *hp, u64 mp, + int sock_id) +{ + find_back_node_value(hp, mp, "cpu", __mark_sock_id, sock_id, 10); +} + static void set_core_ids(struct mdesc_handle *hp) { int idx; u64 mp; idx = 1; + + /* Identify unique cores by looking for cpus backpointed to by + * level 1 instruction caches. + */ mdesc_for_each_node_by_name(hp, mp, "cache") { const u64 *level; const char *type; @@ -667,11 +690,72 @@ static void set_core_ids(struct mdesc_handle *hp) continue; mark_core_ids(hp, mp, idx); + idx++; + } +} + +static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level) +{ + u64 mp; + int idx = 1; + int fnd = 0; + + /* Identify unique sockets by looking for cpus backpointed to by + * shared level n caches. + */ + mdesc_for_each_node_by_name(hp, mp, "cache") { + const u64 *cur_lvl; + + cur_lvl = mdesc_get_property(hp, mp, "level", NULL); + if (*cur_lvl != level) + continue; + + mark_sock_ids(hp, mp, idx); + idx++; + fnd = 1; + } + return fnd; +} + +static void set_sock_ids_by_socket(struct mdesc_handle *hp, u64 mp) +{ + int idx = 1; + mdesc_for_each_node_by_name(hp, mp, "socket") { + u64 a; + + mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_FWD) { + u64 t = mdesc_arc_target(hp, a); + const char *name; + const u64 *id; + + name = mdesc_node_name(hp, t); + if (strcmp(name, "cpu")) + continue; + + id = mdesc_get_property(hp, t, "id", NULL); + if (*id < num_possible_cpus()) + cpu_data(*id).sock_id = idx; + } idx++; } } +static void set_sock_ids(struct mdesc_handle *hp) +{ + u64 mp; + + /* If machine description exposes sockets data use it. + * Otherwise fallback to use shared L3 or L2 caches. + */ + mp = mdesc_node_by_name(hp, MDESC_NODE_NULL, "sockets"); + if (mp != MDESC_NODE_NULL) + return set_sock_ids_by_socket(hp, mp); + + if (!set_sock_ids_by_cache(hp, 3)) + set_sock_ids_by_cache(hp, 2); +} + static void mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id) { u64 a; @@ -707,7 +791,6 @@ static void __set_proc_ids(struct mdesc_handle *hp, const char *exec_unit_name) continue; mark_proc_ids(hp, mp, idx); - idx++; } } @@ -900,6 +983,7 @@ void mdesc_fill_in_cpu_data(cpumask_t *mask) set_core_ids(hp); set_proc_ids(hp); + set_sock_ids(hp); mdesc_release(hp); diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 6f7251f..c928bc6 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -1002,6 +1002,38 @@ static int __init pcibios_init(void) subsys_initcall(pcibios_init); #ifdef CONFIG_SYSFS + +#define SLOT_NAME_SIZE 11 /* Max decimal digits + null in u32 */ + +static void pcie_bus_slot_names(struct pci_bus *pbus) +{ + struct pci_dev *pdev; + struct pci_bus *bus; + + list_for_each_entry(pdev, &pbus->devices, bus_list) { + char name[SLOT_NAME_SIZE]; + struct pci_slot *pci_slot; + const u32 *slot_num; + int len; + + slot_num = of_get_property(pdev->dev.of_node, + "physical-slot#", &len); + + if (slot_num == NULL || len != 4) + continue; + + snprintf(name, sizeof(name), "%u", slot_num[0]); + pci_slot = pci_create_slot(pbus, slot_num[0], name, NULL); + + if (IS_ERR(pci_slot)) + pr_err("PCI: pci_create_slot returned %ld.\n", + PTR_ERR(pci_slot)); + } + + list_for_each_entry(bus, &pbus->children, node) + pcie_bus_slot_names(bus); +} + static void pci_bus_slot_names(struct device_node *node, struct pci_bus *bus) { const struct pci_slot_names { @@ -1053,18 +1085,29 @@ static int __init of_pci_slot_init(void) while ((pbus = pci_find_next_bus(pbus)) != NULL) { struct device_node *node; + struct pci_dev *pdev; + + pdev = list_first_entry(&pbus->devices, struct pci_dev, + bus_list); - if (pbus->self) { - /* PCI->PCI bridge */ - node = pbus->self->dev.of_node; + if (pdev && pci_is_pcie(pdev)) { + pcie_bus_slot_names(pbus); } else { - struct pci_pbm_info *pbm = pbus->sysdata; - /* Host PCI controller */ - node = pbm->op->dev.of_node; - } + if (pbus->self) { + + /* PCI->PCI bridge */ + node = pbus->self->dev.of_node; + + } else { + struct pci_pbm_info *pbm = pbus->sysdata; - pci_bus_slot_names(node, pbus); + /* Host PCI controller */ + node = pbm->op->dev.of_node; + } + + pci_bus_slot_names(node, pbus); + } } return 0; diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index c38d19f..f7b2617 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -255,6 +255,24 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start, } } +void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *start, + struct sun4v_2insn_patch_entry *end) +{ + while (start < end) { + unsigned long addr = start->addr; + + *(unsigned int *) (addr + 0) = start->insns[0]; + wmb(); + __asm__ __volatile__("flush %0" : : "r" (addr + 0)); + + *(unsigned int *) (addr + 4) = start->insns[1]; + wmb(); + __asm__ __volatile__("flush %0" : : "r" (addr + 4)); + + start++; + } +} + static void __init sun4v_patch(void) { extern void sun4v_hvapi_init(void); @@ -267,6 +285,9 @@ static void __init sun4v_patch(void) sun4v_patch_2insn_range(&__sun4v_2insn_patch, &__sun4v_2insn_patch_end); + if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7) + sun_m7_patch_2insn_range(&__sun_m7_2insn_patch, + &__sun_m7_2insn_patch_end); sun4v_hvapi_init(); } diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 61139d9..19cd08d 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -60,8 +60,12 @@ DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE; cpumask_t cpu_core_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = CPU_MASK_NONE }; +cpumask_t cpu_core_sib_map[NR_CPUS] __read_mostly = { + [0 ... NR_CPUS-1] = CPU_MASK_NONE }; + EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); EXPORT_SYMBOL(cpu_core_map); +EXPORT_SYMBOL(cpu_core_sib_map); static cpumask_t smp_commenced_mask; @@ -1243,6 +1247,15 @@ void smp_fill_in_sib_core_maps(void) } } + for_each_present_cpu(i) { + unsigned int j; + + for_each_present_cpu(j) { + if (cpu_data(i).sock_id == cpu_data(j).sock_id) + cpumask_set_cpu(j, &cpu_core_sib_map[i]); + } + } + for_each_present_cpu(i) { unsigned int j; diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 0924305..f1a2f68 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -138,6 +138,11 @@ SECTIONS *(.pause_3insn_patch) __pause_3insn_patch_end = .; } + .sun_m7_2insn_patch : { + __sun_m7_2insn_patch = .; + *(.sun_m7_2insn_patch) + __sun_m7_2insn_patch_end = .; + } PERCPU_SECTION(SMP_CACHE_BYTES) . = ALIGN(PAGE_SIZE); diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 4ca0d6b..559cb744 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -54,6 +54,7 @@ #include "init_64.h" unsigned long kern_linear_pte_xor[4] __read_mostly; +static unsigned long page_cache4v_flag; /* A bitmap, two bits for every 256MB of physical memory. These two * bits determine what page size we use for kernel linear @@ -1909,11 +1910,24 @@ static void __init sun4u_linear_pte_xor_finalize(void) static void __init sun4v_linear_pte_xor_finalize(void) { + unsigned long pagecv_flag; + + /* Bit 9 of TTE is no longer CV bit on M7 processor and it instead + * enables MCD error. Do not set bit 9 on M7 processor. + */ + switch (sun4v_chip_type) { + case SUN4V_CHIP_SPARC_M7: + pagecv_flag = 0x00; + break; + default: + pagecv_flag = _PAGE_CV_4V; + break; + } #ifndef CONFIG_DEBUG_PAGEALLOC if (cpu_pgsz_mask & HV_PGSZ_MASK_256MB) { kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^ PAGE_OFFSET; - kern_linear_pte_xor[1] |= (_PAGE_CP_4V | _PAGE_CV_4V | + kern_linear_pte_xor[1] |= (_PAGE_CP_4V | pagecv_flag | _PAGE_P_4V | _PAGE_W_4V); } else { kern_linear_pte_xor[1] = kern_linear_pte_xor[0]; @@ -1922,7 +1936,7 @@ static void __init sun4v_linear_pte_xor_finalize(void) if (cpu_pgsz_mask & HV_PGSZ_MASK_2GB) { kern_linear_pte_xor[2] = (_PAGE_VALID | _PAGE_SZ2GB_4V) ^ PAGE_OFFSET; - kern_linear_pte_xor[2] |= (_PAGE_CP_4V | _PAGE_CV_4V | + kern_linear_pte_xor[2] |= (_PAGE_CP_4V | pagecv_flag | _PAGE_P_4V | _PAGE_W_4V); } else { kern_linear_pte_xor[2] = kern_linear_pte_xor[1]; @@ -1931,7 +1945,7 @@ static void __init sun4v_linear_pte_xor_finalize(void) if (cpu_pgsz_mask & HV_PGSZ_MASK_16GB) { kern_linear_pte_xor[3] = (_PAGE_VALID | _PAGE_SZ16GB_4V) ^ PAGE_OFFSET; - kern_linear_pte_xor[3] |= (_PAGE_CP_4V | _PAGE_CV_4V | + kern_linear_pte_xor[3] |= (_PAGE_CP_4V | pagecv_flag | _PAGE_P_4V | _PAGE_W_4V); } else { kern_linear_pte_xor[3] = kern_linear_pte_xor[2]; @@ -1958,6 +1972,13 @@ static phys_addr_t __init available_memory(void) return available; } +#define _PAGE_CACHE_4U (_PAGE_CP_4U | _PAGE_CV_4U) +#define _PAGE_CACHE_4V (_PAGE_CP_4V | _PAGE_CV_4V) +#define __DIRTY_BITS_4U (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U) +#define __DIRTY_BITS_4V (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V) +#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R) +#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R) + /* We need to exclude reserved regions. This exclusion will include * vmlinux and initrd. To be more precise the initrd size could be used to * compute a new lower limit because it is freed later during initialization. @@ -2034,6 +2055,25 @@ void __init paging_init(void) memset(swapper_4m_tsb, 0x40, sizeof(swapper_4m_tsb)); #endif + /* TTE.cv bit on sparc v9 occupies the same position as TTE.mcde + * bit on M7 processor. This is a conflicting usage of the same + * bit. Enabling TTE.cv on M7 would turn on Memory Corruption + * Detection error on all pages and this will lead to problems + * later. Kernel does not run with MCD enabled and hence rest + * of the required steps to fully configure memory corruption + * detection are not taken. We need to ensure TTE.mcde is not + * set on M7 processor. Compute the value of cacheability + * flag for use later taking this into consideration. + */ + switch (sun4v_chip_type) { + case SUN4V_CHIP_SPARC_M7: + page_cache4v_flag = _PAGE_CP_4V; + break; + default: + page_cache4v_flag = _PAGE_CACHE_4V; + break; + } + if (tlb_type == hypervisor) sun4v_pgprot_init(); else @@ -2274,13 +2314,6 @@ void free_initrd_mem(unsigned long start, unsigned long end) } #endif -#define _PAGE_CACHE_4U (_PAGE_CP_4U | _PAGE_CV_4U) -#define _PAGE_CACHE_4V (_PAGE_CP_4V | _PAGE_CV_4V) -#define __DIRTY_BITS_4U (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U) -#define __DIRTY_BITS_4V (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V) -#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R) -#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R) - pgprot_t PAGE_KERNEL __read_mostly; EXPORT_SYMBOL(PAGE_KERNEL); @@ -2312,8 +2345,7 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, _PAGE_P_4U | _PAGE_W_4U); if (tlb_type == hypervisor) pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V | - _PAGE_CP_4V | _PAGE_CV_4V | - _PAGE_P_4V | _PAGE_W_4V); + page_cache4v_flag | _PAGE_P_4V | _PAGE_W_4V); pte_base |= _PAGE_PMD_HUGE; @@ -2450,14 +2482,14 @@ static void __init sun4v_pgprot_init(void) int i; PAGE_KERNEL = __pgprot (_PAGE_PRESENT_4V | _PAGE_VALID | - _PAGE_CACHE_4V | _PAGE_P_4V | + page_cache4v_flag | _PAGE_P_4V | __ACCESS_BITS_4V | __DIRTY_BITS_4V | _PAGE_EXEC_4V); PAGE_KERNEL_LOCKED = PAGE_KERNEL; _PAGE_IE = _PAGE_IE_4V; _PAGE_E = _PAGE_E_4V; - _PAGE_CACHE = _PAGE_CACHE_4V; + _PAGE_CACHE = page_cache4v_flag; #ifdef CONFIG_DEBUG_PAGEALLOC kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET; @@ -2465,8 +2497,8 @@ static void __init sun4v_pgprot_init(void) kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^ PAGE_OFFSET; #endif - kern_linear_pte_xor[0] |= (_PAGE_CP_4V | _PAGE_CV_4V | - _PAGE_P_4V | _PAGE_W_4V); + kern_linear_pte_xor[0] |= (page_cache4v_flag | _PAGE_P_4V | + _PAGE_W_4V); for (i = 1; i < 4; i++) kern_linear_pte_xor[i] = kern_linear_pte_xor[0]; @@ -2479,12 +2511,12 @@ static void __init sun4v_pgprot_init(void) _PAGE_SZ4MB_4V | _PAGE_SZ512K_4V | _PAGE_SZ64K_4V | _PAGE_SZ8K_4V); - page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | _PAGE_CACHE_4V; - page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V | + page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | page_cache4v_flag; + page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag | __ACCESS_BITS_4V | _PAGE_WRITE_4V | _PAGE_EXEC_4V); - page_copy = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V | + page_copy = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag | __ACCESS_BITS_4V | _PAGE_EXEC_4V); - page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V | + page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag | __ACCESS_BITS_4V | _PAGE_EXEC_4V); page_exec_bit = _PAGE_EXEC_4V; @@ -2542,7 +2574,7 @@ static unsigned long kern_large_tte(unsigned long paddr) _PAGE_EXEC_4U | _PAGE_L_4U | _PAGE_W_4U); if (tlb_type == hypervisor) val = (_PAGE_VALID | _PAGE_SZ4MB_4V | - _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V | + page_cache4v_flag | _PAGE_P_4V | _PAGE_EXEC_4V | _PAGE_W_4V); return val | paddr; diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index c469490..3c6bb34 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -140,6 +140,7 @@ #define MSR_CORE_C3_RESIDENCY 0x000003fc #define MSR_CORE_C6_RESIDENCY 0x000003fd #define MSR_CORE_C7_RESIDENCY 0x000003fe +#define MSR_KNL_CORE_C6_RESIDENCY 0x000003ff #define MSR_PKG_C2_RESIDENCY 0x0000060d #define MSR_PKG_C8_RESIDENCY 0x00000630 #define MSR_PKG_C9_RESIDENCY 0x00000631 diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index e535533..20190bd 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -708,6 +708,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, struct pt_regs *regs) { int i, ret = 0; + char *tmp; for (i = 0; i < mca_cfg.banks; i++) { m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); @@ -716,9 +717,11 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); } - if (mce_severity(m, mca_cfg.tolerant, msg, true) >= - MCE_PANIC_SEVERITY) + + if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + *msg = tmp; ret = 1; + } } return ret; } diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 00918327..6185d31 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -173,6 +173,21 @@ static void init_thread_xstate(void) xstate_size = sizeof(struct i387_fxsave_struct); else xstate_size = sizeof(struct i387_fsave_struct); + + /* + * Quirk: we don't yet handle the XSAVES* instructions + * correctly, as we don't correctly convert between + * standard and compacted format when interfacing + * with user-space - so disable it for now. + * + * The difference is small: with recent CPUs the + * compacted format is only marginally smaller than + * the standard FPU state format. + * + * ( This is easy to backport while we are fixing + * XSAVES* support. ) + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); } /* diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 2ca7776..579a8fd 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1068,7 +1068,12 @@ void bpf_int_jit_compile(struct bpf_prog *prog) } ctx.cleanup_addr = proglen; - for (pass = 0; pass < 10; pass++) { + /* JITed image shrinks with every pass and the loop iterates + * until the image stops shrinking. Very large bpf programs + * may converge on the last pass. In such case do one more + * pass to emit the final image + */ + for (pass = 0; pass < 10 || image; pass++) { proglen = do_jit(prog, addrs, image, oldproglen, &ctx); if (proglen <= 0) { image = NULL; diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index d939633..14a63ed 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -482,9 +482,16 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) { - struct pci_sysdata *sd = bridge->bus->sysdata; - - ACPI_COMPANION_SET(&bridge->dev, sd->companion); + /* + * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL + * here, pci_create_root_bus() has been called by someone else and + * sysdata is likely to be different from what we expect. Let it go in + * that case. + */ + if (!bridge->dev.parent) { + struct pci_sysdata *sd = bridge->bus->sysdata; + ACPI_COMPANION_SET(&bridge->dev, sd->companion); + } return 0; } diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h index 172a02a..ba78ccf 100644 --- a/arch/xtensa/include/asm/dma-mapping.h +++ b/arch/xtensa/include/asm/dma-mapping.h @@ -185,4 +185,17 @@ static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt, return -EINVAL; } +static inline void *dma_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag, + struct dma_attrs *attrs) +{ + return NULL; +} + +static inline void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ +} + #endif /* _XTENSA_DMA_MAPPING_H */ diff --git a/crypto/Kconfig b/crypto/Kconfig index 8aaf298..362905e 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -1512,15 +1512,6 @@ config CRYPTO_USER_API_RNG This option enables the user-spaces interface for random number generator algorithms. -config CRYPTO_USER_API_AEAD - tristate "User-space interface for AEAD cipher algorithms" - depends on NET - select CRYPTO_AEAD - select CRYPTO_USER_API - help - This option enables the user-spaces interface for AEAD - cipher algorithms. - config CRYPTO_HASH_INFO bool diff --git a/drivers/atm/he.c b/drivers/atm/he.c index 93dca2e..0237271 100644 --- a/drivers/atm/he.c +++ b/drivers/atm/he.c @@ -116,7 +116,7 @@ static bool disable64; static short nvpibits = -1; static short nvcibits = -1; static short rx_skb_reserve = 16; -static bool irq_coalesce = 1; +static bool irq_coalesce = true; static bool sdh = 0; /* Read from EEPROM = 0000 0011b */ diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig index ed5c273..2e77707 100644 --- a/drivers/bluetooth/Kconfig +++ b/drivers/bluetooth/Kconfig @@ -9,6 +9,10 @@ config BT_BCM tristate select FW_LOADER +config BT_RTL + tristate + select FW_LOADER + config BT_HCIBTUSB tristate "HCI USB driver" depends on USB @@ -32,6 +36,17 @@ config BT_HCIBTUSB_BCM Say Y here to compile support for Broadcom protocol. +config BT_HCIBTUSB_RTL + bool "Realtek protocol support" + depends on BT_HCIBTUSB + select BT_RTL + default y + help + The Realtek protocol support enables firmware and configuration + download support for Realtek Bluetooth controllers. + + Say Y here to compile support for Realtek protocol. + config BT_HCIBTSDIO tristate "HCI SDIO driver" depends on MMC diff --git a/drivers/bluetooth/Makefile b/drivers/bluetooth/Makefile index dd0d9c4..f40e194 100644 --- a/drivers/bluetooth/Makefile +++ b/drivers/bluetooth/Makefile @@ -21,6 +21,7 @@ obj-$(CONFIG_BT_MRVL) += btmrvl.o obj-$(CONFIG_BT_MRVL_SDIO) += btmrvl_sdio.o obj-$(CONFIG_BT_WILINK) += btwilink.o obj-$(CONFIG_BT_BCM) += btbcm.o +obj-$(CONFIG_BT_RTL) += btrtl.o btmrvl-y := btmrvl_main.o btmrvl-$(CONFIG_DEBUG_FS) += btmrvl_debugfs.o diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index 4bba866..728fce3 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -55,12 +55,6 @@ int btbcm_check_bdaddr(struct hci_dev *hdev) } bda = (struct hci_rp_read_bd_addr *)skb->data; - if (bda->status) { - BT_ERR("%s: BCM: Device address result failed (%02x)", - hdev->name, bda->status); - kfree_skb(skb); - return -bt_to_errno(bda->status); - } /* The address 00:20:70:02:A0:00 indicates a BCM20702A0 controller * with no configured address. diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 2d43d42..828f2f8 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -53,12 +53,6 @@ int btintel_check_bdaddr(struct hci_dev *hdev) } bda = (struct hci_rp_read_bd_addr *)skb->data; - if (bda->status) { - BT_ERR("%s: Intel device address result failed (%02x)", - hdev->name, bda->status); - kfree_skb(skb); - return -bt_to_errno(bda->status); - } /* For some Intel based controllers, the default Bluetooth device * address 00:03:19:9E:8B:00 can be found. These controllers are diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index 01d6da5..b9a8119 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -1217,7 +1217,7 @@ static void btmrvl_sdio_dump_firmware(struct btmrvl_private *priv) unsigned int reg, reg_start, reg_end; enum rdwr_status stat; u8 *dbg_ptr, *end_ptr, *fw_dump_data, *fw_dump_ptr; - u8 dump_num, idx, i, read_reg, doneflag = 0; + u8 dump_num = 0, idx, i, read_reg, doneflag = 0; u32 memory_size, fw_dump_len = 0; /* dump sdio register first */ diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c new file mode 100644 index 0000000..8428893 --- /dev/null +++ b/drivers/bluetooth/btrtl.c @@ -0,0 +1,390 @@ +/* + * Bluetooth support for Realtek devices + * + * Copyright (C) 2015 Endless Mobile, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/module.h> +#include <linux/firmware.h> +#include <asm/unaligned.h> +#include <linux/usb.h> + +#include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci_core.h> + +#include "btrtl.h" + +#define VERSION "0.1" + +#define RTL_EPATCH_SIGNATURE "Realtech" +#define RTL_ROM_LMP_3499 0x3499 +#define RTL_ROM_LMP_8723A 0x1200 +#define RTL_ROM_LMP_8723B 0x8723 +#define RTL_ROM_LMP_8821A 0x8821 +#define RTL_ROM_LMP_8761A 0x8761 + +static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version) +{ + struct rtl_rom_version_evt *rom_version; + struct sk_buff *skb; + + /* Read RTL ROM version command */ + skb = __hci_cmd_sync(hdev, 0xfc6d, 0, NULL, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + BT_ERR("%s: Read ROM version failed (%ld)", + hdev->name, PTR_ERR(skb)); + return PTR_ERR(skb); + } + + if (skb->len != sizeof(*rom_version)) { + BT_ERR("%s: RTL version event length mismatch", hdev->name); + kfree_skb(skb); + return -EIO; + } + + rom_version = (struct rtl_rom_version_evt *)skb->data; + BT_INFO("%s: rom_version status=%x version=%x", + hdev->name, rom_version->status, rom_version->version); + + *version = rom_version->version; + + kfree_skb(skb); + return 0; +} + +static int rtl8723b_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, + const struct firmware *fw, + unsigned char **_buf) +{ + const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 }; + struct rtl_epatch_header *epatch_info; + unsigned char *buf; + int i, ret, len; + size_t min_size; + u8 opcode, length, data, rom_version = 0; + int project_id = -1; + const unsigned char *fwptr, *chip_id_base; + const unsigned char *patch_length_base, *patch_offset_base; + u32 patch_offset = 0; + u16 patch_length, num_patches; + const u16 project_id_to_lmp_subver[] = { + RTL_ROM_LMP_8723A, + RTL_ROM_LMP_8723B, + RTL_ROM_LMP_8821A, + RTL_ROM_LMP_8761A + }; + + ret = rtl_read_rom_version(hdev, &rom_version); + if (ret) + return ret; + + min_size = sizeof(struct rtl_epatch_header) + sizeof(extension_sig) + 3; + if (fw->size < min_size) + return -EINVAL; + + fwptr = fw->data + fw->size - sizeof(extension_sig); + if (memcmp(fwptr, extension_sig, sizeof(extension_sig)) != 0) { + BT_ERR("%s: extension section signature mismatch", hdev->name); + return -EINVAL; + } + + /* Loop from the end of the firmware parsing instructions, until + * we find an instruction that identifies the "project ID" for the + * hardware supported by this firwmare file. + * Once we have that, we double-check that that project_id is suitable + * for the hardware we are working with. + */ + while (fwptr >= fw->data + (sizeof(struct rtl_epatch_header) + 3)) { + opcode = *--fwptr; + length = *--fwptr; + data = *--fwptr; + + BT_DBG("check op=%x len=%x data=%x", opcode, length, data); + + if (opcode == 0xff) /* EOF */ + break; + + if (length == 0) { + BT_ERR("%s: found instruction with length 0", + hdev->name); + return -EINVAL; + } + + if (opcode == 0 && length == 1) { + project_id = data; + break; + } + + fwptr -= length; + } + + if (project_id < 0) { + BT_ERR("%s: failed to find version instruction", hdev->name); + return -EINVAL; + } + + if (project_id >= ARRAY_SIZE(project_id_to_lmp_subver)) { + BT_ERR("%s: unknown project id %d", hdev->name, project_id); + return -EINVAL; + } + + if (lmp_subver != project_id_to_lmp_subver[project_id]) { + BT_ERR("%s: firmware is for %x but this is a %x", hdev->name, + project_id_to_lmp_subver[project_id], lmp_subver); + return -EINVAL; + } + + epatch_info = (struct rtl_epatch_header *)fw->data; + if (memcmp(epatch_info->signature, RTL_EPATCH_SIGNATURE, 8) != 0) { + BT_ERR("%s: bad EPATCH signature", hdev->name); + return -EINVAL; + } + + num_patches = le16_to_cpu(epatch_info->num_patches); + BT_DBG("fw_version=%x, num_patches=%d", + le32_to_cpu(epatch_info->fw_version), num_patches); + + /* After the rtl_epatch_header there is a funky patch metadata section. + * Assuming 2 patches, the layout is: + * ChipID1 ChipID2 PatchLength1 PatchLength2 PatchOffset1 PatchOffset2 + * + * Find the right patch for this chip. + */ + min_size += 8 * num_patches; + if (fw->size < min_size) + return -EINVAL; + + chip_id_base = fw->data + sizeof(struct rtl_epatch_header); + patch_length_base = chip_id_base + (sizeof(u16) * num_patches); + patch_offset_base = patch_length_base + (sizeof(u16) * num_patches); + for (i = 0; i < num_patches; i++) { + u16 chip_id = get_unaligned_le16(chip_id_base + + (i * sizeof(u16))); + if (chip_id == rom_version + 1) { + patch_length = get_unaligned_le16(patch_length_base + + (i * sizeof(u16))); + patch_offset = get_unaligned_le32(patch_offset_base + + (i * sizeof(u32))); + break; + } + } + + if (!patch_offset) { + BT_ERR("%s: didn't find patch for chip id %d", + hdev->name, rom_version); + return -EINVAL; + } + + BT_DBG("length=%x offset=%x index %d", patch_length, patch_offset, i); + min_size = patch_offset + patch_length; + if (fw->size < min_size) + return -EINVAL; + + /* Copy the firmware into a new buffer and write the version at + * the end. + */ + len = patch_length; + buf = kmemdup(fw->data + patch_offset, patch_length, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + memcpy(buf + patch_length - 4, &epatch_info->fw_version, 4); + + *_buf = buf; + return len; +} + +static int rtl_download_firmware(struct hci_dev *hdev, + const unsigned char *data, int fw_len) +{ + struct rtl_download_cmd *dl_cmd; + int frag_num = fw_len / RTL_FRAG_LEN + 1; + int frag_len = RTL_FRAG_LEN; + int ret = 0; + int i; + + dl_cmd = kmalloc(sizeof(struct rtl_download_cmd), GFP_KERNEL); + if (!dl_cmd) + return -ENOMEM; + + for (i = 0; i < frag_num; i++) { + struct sk_buff *skb; + + BT_DBG("download fw (%d/%d)", i, frag_num); + + dl_cmd->index = i; + if (i == (frag_num - 1)) { + dl_cmd->index |= 0x80; /* data end */ + frag_len = fw_len % RTL_FRAG_LEN; + } + memcpy(dl_cmd->data, data, frag_len); + + /* Send download command */ + skb = __hci_cmd_sync(hdev, 0xfc20, frag_len + 1, dl_cmd, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + BT_ERR("%s: download fw command failed (%ld)", + hdev->name, PTR_ERR(skb)); + ret = -PTR_ERR(skb); + goto out; + } + + if (skb->len != sizeof(struct rtl_download_response)) { + BT_ERR("%s: download fw event length mismatch", + hdev->name); + kfree_skb(skb); + ret = -EIO; + goto out; + } + + kfree_skb(skb); + data += RTL_FRAG_LEN; + } + +out: + kfree(dl_cmd); + return ret; +} + +static int btrtl_setup_rtl8723a(struct hci_dev *hdev) +{ + const struct firmware *fw; + int ret; + + BT_INFO("%s: rtl: loading rtl_bt/rtl8723a_fw.bin", hdev->name); + ret = request_firmware(&fw, "rtl_bt/rtl8723a_fw.bin", &hdev->dev); + if (ret < 0) { + BT_ERR("%s: Failed to load rtl_bt/rtl8723a_fw.bin", hdev->name); + return ret; + } + + if (fw->size < 8) { + ret = -EINVAL; + goto out; + } + + /* Check that the firmware doesn't have the epatch signature + * (which is only for RTL8723B and newer). + */ + if (!memcmp(fw->data, RTL_EPATCH_SIGNATURE, 8)) { + BT_ERR("%s: unexpected EPATCH signature!", hdev->name); + ret = -EINVAL; + goto out; + } + + ret = rtl_download_firmware(hdev, fw->data, fw->size); + +out: + release_firmware(fw); + return ret; +} + +static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver, + const char *fw_name) +{ + unsigned char *fw_data = NULL; + const struct firmware *fw; + int ret; + + BT_INFO("%s: rtl: loading %s", hdev->name, fw_name); + ret = request_firmware(&fw, fw_name, &hdev->dev); + if (ret < 0) { + BT_ERR("%s: Failed to load %s", hdev->name, fw_name); + return ret; + } + + ret = rtl8723b_parse_firmware(hdev, lmp_subver, fw, &fw_data); + if (ret < 0) + goto out; + + ret = rtl_download_firmware(hdev, fw_data, ret); + kfree(fw_data); + if (ret < 0) + goto out; + +out: + release_firmware(fw); + return ret; +} + +static struct sk_buff *btrtl_read_local_version(struct hci_dev *hdev) +{ + struct sk_buff *skb; + + skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION failed (%ld)", + hdev->name, PTR_ERR(skb)); + return skb; + } + + if (skb->len != sizeof(struct hci_rp_read_local_version)) { + BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION event length mismatch", + hdev->name); + kfree_skb(skb); + return ERR_PTR(-EIO); + } + + return skb; +} + +int btrtl_setup_realtek(struct hci_dev *hdev) +{ + struct sk_buff *skb; + struct hci_rp_read_local_version *resp; + u16 lmp_subver; + + skb = btrtl_read_local_version(hdev); + if (IS_ERR(skb)) + return -PTR_ERR(skb); + + resp = (struct hci_rp_read_local_version *)skb->data; + BT_INFO("%s: rtl: examining hci_ver=%02x hci_rev=%04x lmp_ver=%02x " + "lmp_subver=%04x", hdev->name, resp->hci_ver, resp->hci_rev, + resp->lmp_ver, resp->lmp_subver); + + lmp_subver = le16_to_cpu(resp->lmp_subver); + kfree_skb(skb); + + /* Match a set of subver values that correspond to stock firmware, + * which is not compatible with standard btusb. + * If matched, upload an alternative firmware that does conform to + * standard btusb. Once that firmware is uploaded, the subver changes + * to a different value. + */ + switch (lmp_subver) { + case RTL_ROM_LMP_8723A: + case RTL_ROM_LMP_3499: + return btrtl_setup_rtl8723a(hdev); + case RTL_ROM_LMP_8723B: + return btrtl_setup_rtl8723b(hdev, lmp_subver, + "rtl_bt/rtl8723b_fw.bin"); + case RTL_ROM_LMP_8821A: + return btrtl_setup_rtl8723b(hdev, lmp_subver, + "rtl_bt/rtl8821a_fw.bin"); + case RTL_ROM_LMP_8761A: + return btrtl_setup_rtl8723b(hdev, lmp_subver, + "rtl_bt/rtl8761a_fw.bin"); + default: + BT_INFO("rtl: assuming no firmware upload needed."); + return 0; + } +} +EXPORT_SYMBOL_GPL(btrtl_setup_realtek); + +MODULE_AUTHOR("Daniel Drake <drake@endlessm.com>"); +MODULE_DESCRIPTION("Bluetooth support for Realtek devices ver " VERSION); +MODULE_VERSION(VERSION); +MODULE_LICENSE("GPL"); diff --git a/drivers/bluetooth/btrtl.h b/drivers/bluetooth/btrtl.h new file mode 100644 index 0000000..38ffe48 --- /dev/null +++ b/drivers/bluetooth/btrtl.h @@ -0,0 +1,52 @@ +/* + * Bluetooth support for Realtek devices + * + * Copyright (C) 2015 Endless Mobile, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#define RTL_FRAG_LEN 252 + +struct rtl_download_cmd { + __u8 index; + __u8 data[RTL_FRAG_LEN]; +} __packed; + +struct rtl_download_response { + __u8 status; + __u8 index; +} __packed; + +struct rtl_rom_version_evt { + __u8 status; + __u8 version; +} __packed; + +struct rtl_epatch_header { + __u8 signature[8]; + __le32 fw_version; + __le16 num_patches; +} __packed; + +#if IS_ENABLED(CONFIG_BT_RTL) + +int btrtl_setup_realtek(struct hci_dev *hdev); + +#else + +static inline int btrtl_setup_realtek(struct hci_dev *hdev) +{ + return -EOPNOTSUPP; +} + +#endif diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 3c10d4d..94c6c04 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -31,13 +31,14 @@ #include "btintel.h" #include "btbcm.h" +#include "btrtl.h" #define VERSION "0.8" static bool disable_scofix; static bool force_scofix; -static bool reset = 1; +static bool reset = true; static struct usb_driver btusb_driver; @@ -330,6 +331,7 @@ static const struct usb_device_id blacklist_table[] = { #define BTUSB_FIRMWARE_LOADED 7 #define BTUSB_FIRMWARE_FAILED 8 #define BTUSB_BOOTING 9 +#define BTUSB_RESET_RESUME 10 struct btusb_data { struct hci_dev *hdev; @@ -1372,378 +1374,6 @@ static int btusb_setup_csr(struct hci_dev *hdev) return ret; } -#define RTL_FRAG_LEN 252 - -struct rtl_download_cmd { - __u8 index; - __u8 data[RTL_FRAG_LEN]; -} __packed; - -struct rtl_download_response { - __u8 status; - __u8 index; -} __packed; - -struct rtl_rom_version_evt { - __u8 status; - __u8 version; -} __packed; - -struct rtl_epatch_header { - __u8 signature[8]; - __le32 fw_version; - __le16 num_patches; -} __packed; - -#define RTL_EPATCH_SIGNATURE "Realtech" -#define RTL_ROM_LMP_3499 0x3499 -#define RTL_ROM_LMP_8723A 0x1200 -#define RTL_ROM_LMP_8723B 0x8723 -#define RTL_ROM_LMP_8821A 0x8821 -#define RTL_ROM_LMP_8761A 0x8761 - -static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version) -{ - struct rtl_rom_version_evt *rom_version; - struct sk_buff *skb; - int ret; - - /* Read RTL ROM version command */ - skb = __hci_cmd_sync(hdev, 0xfc6d, 0, NULL, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - BT_ERR("%s: Read ROM version failed (%ld)", - hdev->name, PTR_ERR(skb)); - return PTR_ERR(skb); - } - - if (skb->len != sizeof(*rom_version)) { - BT_ERR("%s: RTL version event length mismatch", hdev->name); - kfree_skb(skb); - return -EIO; - } - - rom_version = (struct rtl_rom_version_evt *)skb->data; - BT_INFO("%s: rom_version status=%x version=%x", - hdev->name, rom_version->status, rom_version->version); - - ret = rom_version->status; - if (ret == 0) - *version = rom_version->version; - - kfree_skb(skb); - return ret; -} - -static int rtl8723b_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, - const struct firmware *fw, - unsigned char **_buf) -{ - const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 }; - struct rtl_epatch_header *epatch_info; - unsigned char *buf; - int i, ret, len; - size_t min_size; - u8 opcode, length, data, rom_version = 0; - int project_id = -1; - const unsigned char *fwptr, *chip_id_base; - const unsigned char *patch_length_base, *patch_offset_base; - u32 patch_offset = 0; - u16 patch_length, num_patches; - const u16 project_id_to_lmp_subver[] = { - RTL_ROM_LMP_8723A, - RTL_ROM_LMP_8723B, - RTL_ROM_LMP_8821A, - RTL_ROM_LMP_8761A - }; - - ret = rtl_read_rom_version(hdev, &rom_version); - if (ret) - return -bt_to_errno(ret); - - min_size = sizeof(struct rtl_epatch_header) + sizeof(extension_sig) + 3; - if (fw->size < min_size) - return -EINVAL; - - fwptr = fw->data + fw->size - sizeof(extension_sig); - if (memcmp(fwptr, extension_sig, sizeof(extension_sig)) != 0) { - BT_ERR("%s: extension section signature mismatch", hdev->name); - return -EINVAL; - } - - /* Loop from the end of the firmware parsing instructions, until - * we find an instruction that identifies the "project ID" for the - * hardware supported by this firwmare file. - * Once we have that, we double-check that that project_id is suitable - * for the hardware we are working with. - */ - while (fwptr >= fw->data + (sizeof(struct rtl_epatch_header) + 3)) { - opcode = *--fwptr; - length = *--fwptr; - data = *--fwptr; - - BT_DBG("check op=%x len=%x data=%x", opcode, length, data); - - if (opcode == 0xff) /* EOF */ - break; - - if (length == 0) { - BT_ERR("%s: found instruction with length 0", - hdev->name); - return -EINVAL; - } - - if (opcode == 0 && length == 1) { - project_id = data; - break; - } - - fwptr -= length; - } - - if (project_id < 0) { - BT_ERR("%s: failed to find version instruction", hdev->name); - return -EINVAL; - } - - if (project_id >= ARRAY_SIZE(project_id_to_lmp_subver)) { - BT_ERR("%s: unknown project id %d", hdev->name, project_id); - return -EINVAL; - } - - if (lmp_subver != project_id_to_lmp_subver[project_id]) { - BT_ERR("%s: firmware is for %x but this is a %x", hdev->name, - project_id_to_lmp_subver[project_id], lmp_subver); - return -EINVAL; - } - - epatch_info = (struct rtl_epatch_header *)fw->data; - if (memcmp(epatch_info->signature, RTL_EPATCH_SIGNATURE, 8) != 0) { - BT_ERR("%s: bad EPATCH signature", hdev->name); - return -EINVAL; - } - - num_patches = le16_to_cpu(epatch_info->num_patches); - BT_DBG("fw_version=%x, num_patches=%d", - le32_to_cpu(epatch_info->fw_version), num_patches); - - /* After the rtl_epatch_header there is a funky patch metadata section. - * Assuming 2 patches, the layout is: - * ChipID1 ChipID2 PatchLength1 PatchLength2 PatchOffset1 PatchOffset2 - * - * Find the right patch for this chip. - */ - min_size += 8 * num_patches; - if (fw->size < min_size) - return -EINVAL; - - chip_id_base = fw->data + sizeof(struct rtl_epatch_header); - patch_length_base = chip_id_base + (sizeof(u16) * num_patches); - patch_offset_base = patch_length_base + (sizeof(u16) * num_patches); - for (i = 0; i < num_patches; i++) { - u16 chip_id = get_unaligned_le16(chip_id_base + - (i * sizeof(u16))); - if (chip_id == rom_version + 1) { - patch_length = get_unaligned_le16(patch_length_base + - (i * sizeof(u16))); - patch_offset = get_unaligned_le32(patch_offset_base + - (i * sizeof(u32))); - break; - } - } - - if (!patch_offset) { - BT_ERR("%s: didn't find patch for chip id %d", - hdev->name, rom_version); - return -EINVAL; - } - - BT_DBG("length=%x offset=%x index %d", patch_length, patch_offset, i); - min_size = patch_offset + patch_length; - if (fw->size < min_size) - return -EINVAL; - - /* Copy the firmware into a new buffer and write the version at - * the end. - */ - len = patch_length; - buf = kmemdup(fw->data + patch_offset, patch_length, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - memcpy(buf + patch_length - 4, &epatch_info->fw_version, 4); - - *_buf = buf; - return len; -} - -static int rtl_download_firmware(struct hci_dev *hdev, - const unsigned char *data, int fw_len) -{ - struct rtl_download_cmd *dl_cmd; - int frag_num = fw_len / RTL_FRAG_LEN + 1; - int frag_len = RTL_FRAG_LEN; - int ret = 0; - int i; - - dl_cmd = kmalloc(sizeof(struct rtl_download_cmd), GFP_KERNEL); - if (!dl_cmd) - return -ENOMEM; - - for (i = 0; i < frag_num; i++) { - struct rtl_download_response *dl_resp; - struct sk_buff *skb; - - BT_DBG("download fw (%d/%d)", i, frag_num); - - dl_cmd->index = i; - if (i == (frag_num - 1)) { - dl_cmd->index |= 0x80; /* data end */ - frag_len = fw_len % RTL_FRAG_LEN; - } - memcpy(dl_cmd->data, data, frag_len); - - /* Send download command */ - skb = __hci_cmd_sync(hdev, 0xfc20, frag_len + 1, dl_cmd, - HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - BT_ERR("%s: download fw command failed (%ld)", - hdev->name, PTR_ERR(skb)); - ret = -PTR_ERR(skb); - goto out; - } - - if (skb->len != sizeof(*dl_resp)) { - BT_ERR("%s: download fw event length mismatch", - hdev->name); - kfree_skb(skb); - ret = -EIO; - goto out; - } - - dl_resp = (struct rtl_download_response *)skb->data; - if (dl_resp->status != 0) { - kfree_skb(skb); - ret = bt_to_errno(dl_resp->status); - goto out; - } - - kfree_skb(skb); - data += RTL_FRAG_LEN; - } - -out: - kfree(dl_cmd); - return ret; -} - -static int btusb_setup_rtl8723a(struct hci_dev *hdev) -{ - struct btusb_data *data = dev_get_drvdata(&hdev->dev); - struct usb_device *udev = interface_to_usbdev(data->intf); - const struct firmware *fw; - int ret; - - BT_INFO("%s: rtl: loading rtl_bt/rtl8723a_fw.bin", hdev->name); - ret = request_firmware(&fw, "rtl_bt/rtl8723a_fw.bin", &udev->dev); - if (ret < 0) { - BT_ERR("%s: Failed to load rtl_bt/rtl8723a_fw.bin", hdev->name); - return ret; - } - - if (fw->size < 8) { - ret = -EINVAL; - goto out; - } - - /* Check that the firmware doesn't have the epatch signature - * (which is only for RTL8723B and newer). - */ - if (!memcmp(fw->data, RTL_EPATCH_SIGNATURE, 8)) { - BT_ERR("%s: unexpected EPATCH signature!", hdev->name); - ret = -EINVAL; - goto out; - } - - ret = rtl_download_firmware(hdev, fw->data, fw->size); - -out: - release_firmware(fw); - return ret; -} - -static int btusb_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver, - const char *fw_name) -{ - struct btusb_data *data = dev_get_drvdata(&hdev->dev); - struct usb_device *udev = interface_to_usbdev(data->intf); - unsigned char *fw_data = NULL; - const struct firmware *fw; - int ret; - - BT_INFO("%s: rtl: loading %s", hdev->name, fw_name); - ret = request_firmware(&fw, fw_name, &udev->dev); - if (ret < 0) { - BT_ERR("%s: Failed to load %s", hdev->name, fw_name); - return ret; - } - - ret = rtl8723b_parse_firmware(hdev, lmp_subver, fw, &fw_data); - if (ret < 0) - goto out; - - ret = rtl_download_firmware(hdev, fw_data, ret); - kfree(fw_data); - if (ret < 0) - goto out; - -out: - release_firmware(fw); - return ret; -} - -static int btusb_setup_realtek(struct hci_dev *hdev) -{ - struct sk_buff *skb; - struct hci_rp_read_local_version *resp; - u16 lmp_subver; - - skb = btusb_read_local_version(hdev); - if (IS_ERR(skb)) - return -PTR_ERR(skb); - - resp = (struct hci_rp_read_local_version *)skb->data; - BT_INFO("%s: rtl: examining hci_ver=%02x hci_rev=%04x lmp_ver=%02x " - "lmp_subver=%04x", hdev->name, resp->hci_ver, resp->hci_rev, - resp->lmp_ver, resp->lmp_subver); - - lmp_subver = le16_to_cpu(resp->lmp_subver); - kfree_skb(skb); - - /* Match a set of subver values that correspond to stock firmware, - * which is not compatible with standard btusb. - * If matched, upload an alternative firmware that does conform to - * standard btusb. Once that firmware is uploaded, the subver changes - * to a different value. - */ - switch (lmp_subver) { - case RTL_ROM_LMP_8723A: - case RTL_ROM_LMP_3499: - return btusb_setup_rtl8723a(hdev); - case RTL_ROM_LMP_8723B: - return btusb_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8723b_fw.bin"); - case RTL_ROM_LMP_8821A: - return btusb_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8821a_fw.bin"); - case RTL_ROM_LMP_8761A: - return btusb_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8761a_fw.bin"); - default: - BT_INFO("rtl: assuming no firmware upload needed."); - return 0; - } -} - static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev, struct intel_version *ver) { @@ -1951,12 +1581,6 @@ static int btusb_setup_intel(struct hci_dev *hdev) } ver = (struct intel_version *)skb->data; - if (ver->status) { - BT_ERR("%s Intel fw version event failed (%02x)", hdev->name, - ver->status); - kfree_skb(skb); - return -bt_to_errno(ver->status); - } BT_INFO("%s: read Intel version: %02x%02x%02x%02x%02x%02x%02x%02x%02x", hdev->name, ver->hw_platform, ver->hw_variant, @@ -2004,15 +1628,6 @@ static int btusb_setup_intel(struct hci_dev *hdev) return PTR_ERR(skb); } - if (skb->data[0]) { - u8 evt_status = skb->data[0]; - - BT_ERR("%s enable Intel manufacturer mode event failed (%02x)", - hdev->name, evt_status); - kfree_skb(skb); - release_firmware(fw); - return -bt_to_errno(evt_status); - } kfree_skb(skb); disable_patch = 1; @@ -2358,13 +1973,6 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) } ver = (struct intel_version *)skb->data; - if (ver->status) { - BT_ERR("%s: Intel version command failure (%02x)", - hdev->name, ver->status); - err = -bt_to_errno(ver->status); - kfree_skb(skb); - return err; - } /* The hardware platform number has a fixed value of 0x37 and * for now only accept this single value. @@ -2439,13 +2047,6 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) } params = (struct intel_boot_params *)skb->data; - if (params->status) { - BT_ERR("%s: Intel boot parameters command failure (%02x)", - hdev->name, params->status); - err = -bt_to_errno(params->status); - kfree_skb(skb); - return err; - } BT_INFO("%s: Device revision is %u", hdev->name, le16_to_cpu(params->dev_revid)); @@ -2678,13 +2279,6 @@ static void btusb_hw_error_intel(struct hci_dev *hdev, u8 code) return; } - if (skb->data[0] != 0x00) { - BT_ERR("%s: Exception info command failure (%02x)", - hdev->name, skb->data[0]); - kfree_skb(skb); - return; - } - BT_ERR("%s: Exception info %s", hdev->name, (char *)(skb->data + 1)); kfree_skb(skb); @@ -2792,6 +2386,7 @@ struct qca_device_info { static const struct qca_device_info qca_devices_table[] = { { 0x00000100, 20, 4, 10 }, /* Rome 1.0 */ { 0x00000101, 20, 4, 10 }, /* Rome 1.1 */ + { 0x00000200, 28, 4, 18 }, /* Rome 2.0 */ { 0x00000201, 28, 4, 18 }, /* Rome 2.1 */ { 0x00000300, 28, 4, 18 }, /* Rome 3.0 */ { 0x00000302, 28, 4, 18 }, /* Rome 3.2 */ @@ -3175,8 +2770,17 @@ static int btusb_probe(struct usb_interface *intf, hdev->set_bdaddr = btusb_set_bdaddr_ath3012; } - if (id->driver_info & BTUSB_REALTEK) - hdev->setup = btusb_setup_realtek; +#ifdef CONFIG_BT_HCIBTUSB_RTL + if (id->driver_info & BTUSB_REALTEK) { + hdev->setup = btrtl_setup_realtek; + + /* Realtek devices lose their updated firmware over suspend, + * but the USB hub doesn't notice any status change. + * Explicitly request a device reset on resume. + */ + set_bit(BTUSB_RESET_RESUME, &data->flags); + } +#endif if (id->driver_info & BTUSB_AMP) { /* AMP controllers do not support SCO packets */ @@ -3308,6 +2912,14 @@ static int btusb_suspend(struct usb_interface *intf, pm_message_t message) btusb_stop_traffic(data); usb_kill_anchored_urbs(&data->tx_anchor); + /* Optionally request a device reset on resume, but only when + * wakeups are disabled. If wakeups are enabled we assume the + * device will stay powered up throughout suspend. + */ + if (test_bit(BTUSB_RESET_RESUME, &data->flags) && + !device_may_wakeup(&data->udev->dev)) + data->udev->reset_resume = 1; + return 0; } diff --git a/drivers/bluetooth/btwilink.c b/drivers/bluetooth/btwilink.c index 55c135b..7a722df 100644 --- a/drivers/bluetooth/btwilink.c +++ b/drivers/bluetooth/btwilink.c @@ -22,7 +22,7 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * */ -#define DEBUG + #include <linux/platform_device.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c index dc8e3d4..fc0056a 100644 --- a/drivers/bluetooth/hci_bcsp.c +++ b/drivers/bluetooth/hci_bcsp.c @@ -47,8 +47,8 @@ #include "hci_uart.h" -static bool txcrc = 1; -static bool hciextn = 1; +static bool txcrc = true; +static bool hciextn = true; #define BCSP_TXWINSIZE 4 diff --git a/drivers/bus/mips_cdmm.c b/drivers/bus/mips_cdmm.c index 5bd792c..ab3bde1 100644 --- a/drivers/bus/mips_cdmm.c +++ b/drivers/bus/mips_cdmm.c @@ -453,7 +453,7 @@ void __iomem *mips_cdmm_early_probe(unsigned int dev_type) /* Look for a specific device type */ for (; drb < bus->drbs; drb += size + 1) { - acsr = readl(cdmm + drb * CDMM_DRB_SIZE); + acsr = __raw_readl(cdmm + drb * CDMM_DRB_SIZE); type = (acsr & CDMM_ACSR_DEVTYPE) >> CDMM_ACSR_DEVTYPE_SHIFT; if (type == dev_type) return cdmm + drb * CDMM_DRB_SIZE; @@ -500,7 +500,7 @@ static void mips_cdmm_bus_discover(struct mips_cdmm_bus *bus) bus->discovered = true; pr_info("cdmm%u discovery (%u blocks)\n", cpu, bus->drbs); for (; drb < bus->drbs; drb += size + 1) { - acsr = readl(cdmm + drb * CDMM_DRB_SIZE); + acsr = __raw_readl(cdmm + drb * CDMM_DRB_SIZE); type = (acsr & CDMM_ACSR_DEVTYPE) >> CDMM_ACSR_DEVTYPE_SHIFT; size = (acsr & CDMM_ACSR_DEVSIZE) >> CDMM_ACSR_DEVSIZE_SHIFT; rev = (acsr & CDMM_ACSR_DEVREV) >> CDMM_ACSR_DEVREV_SHIFT; diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c index a50936a..5639699 100644 --- a/drivers/clk/qcom/gcc-ipq806x.c +++ b/drivers/clk/qcom/gcc-ipq806x.c @@ -140,12 +140,47 @@ static struct clk_regmap pll14_vote = { }, }; +#define NSS_PLL_RATE(f, _l, _m, _n, i) \ + { \ + .freq = f, \ + .l = _l, \ + .m = _m, \ + .n = _n, \ + .ibits = i, \ + } + +static struct pll_freq_tbl pll18_freq_tbl[] = { + NSS_PLL_RATE(550000000, 44, 0, 1, 0x01495625), + NSS_PLL_RATE(733000000, 58, 16, 25, 0x014b5625), +}; + +static struct clk_pll pll18 = { + .l_reg = 0x31a4, + .m_reg = 0x31a8, + .n_reg = 0x31ac, + .config_reg = 0x31b4, + .mode_reg = 0x31a0, + .status_reg = 0x31b8, + .status_bit = 16, + .post_div_shift = 16, + .post_div_width = 1, + .freq_tbl = pll18_freq_tbl, + .clkr.hw.init = &(struct clk_init_data){ + .name = "pll18", + .parent_names = (const char *[]){ "pxo" }, + .num_parents = 1, + .ops = &clk_pll_ops, + }, +}; + enum { P_PXO, P_PLL8, P_PLL3, P_PLL0, P_CXO, + P_PLL14, + P_PLL18, }; static const struct parent_map gcc_pxo_pll8_map[] = { @@ -197,6 +232,22 @@ static const char *gcc_pxo_pll8_pll0_map[] = { "pll0_vote", }; +static const struct parent_map gcc_pxo_pll8_pll14_pll18_pll0_map[] = { + { P_PXO, 0 }, + { P_PLL8, 4 }, + { P_PLL0, 2 }, + { P_PLL14, 5 }, + { P_PLL18, 1 } +}; + +static const char *gcc_pxo_pll8_pll14_pll18_pll0[] = { + "pxo", + "pll8_vote", + "pll0_vote", + "pll14", + "pll18", +}; + static struct freq_tbl clk_tbl_gsbi_uart[] = { { 1843200, P_PLL8, 2, 6, 625 }, { 3686400, P_PLL8, 2, 12, 625 }, @@ -2202,6 +2253,472 @@ static struct clk_branch ebi2_aon_clk = { }, }; +static const struct freq_tbl clk_tbl_gmac[] = { + { 133000000, P_PLL0, 1, 50, 301 }, + { 266000000, P_PLL0, 1, 127, 382 }, + { } +}; + +static struct clk_dyn_rcg gmac_core1_src = { + .ns_reg[0] = 0x3cac, + .ns_reg[1] = 0x3cb0, + .md_reg[0] = 0x3ca4, + .md_reg[1] = 0x3ca8, + .bank_reg = 0x3ca0, + .mn[0] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .mn[1] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .s[0] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .s[1] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .p[0] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .p[1] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .mux_sel_bit = 0, + .freq_tbl = clk_tbl_gmac, + .clkr = { + .enable_reg = 0x3ca0, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "gmac_core1_src", + .parent_names = gcc_pxo_pll8_pll14_pll18_pll0, + .num_parents = 5, + .ops = &clk_dyn_rcg_ops, + }, + }, +}; + +static struct clk_branch gmac_core1_clk = { + .halt_reg = 0x3c20, + .halt_bit = 4, + .hwcg_reg = 0x3cb4, + .hwcg_bit = 6, + .clkr = { + .enable_reg = 0x3cb4, + .enable_mask = BIT(4), + .hw.init = &(struct clk_init_data){ + .name = "gmac_core1_clk", + .parent_names = (const char *[]){ + "gmac_core1_src", + }, + .num_parents = 1, + .ops = &clk_branch_ops, + .flags = CLK_SET_RATE_PARENT, + }, + }, +}; + +static struct clk_dyn_rcg gmac_core2_src = { + .ns_reg[0] = 0x3ccc, + .ns_reg[1] = 0x3cd0, + .md_reg[0] = 0x3cc4, + .md_reg[1] = 0x3cc8, + .bank_reg = 0x3ca0, + .mn[0] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .mn[1] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .s[0] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .s[1] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .p[0] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .p[1] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .mux_sel_bit = 0, + .freq_tbl = clk_tbl_gmac, + .clkr = { + .enable_reg = 0x3cc0, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "gmac_core2_src", + .parent_names = gcc_pxo_pll8_pll14_pll18_pll0, + .num_parents = 5, + .ops = &clk_dyn_rcg_ops, + }, + }, +}; + +static struct clk_branch gmac_core2_clk = { + .halt_reg = 0x3c20, + .halt_bit = 5, + .hwcg_reg = 0x3cd4, + .hwcg_bit = 6, + .clkr = { + .enable_reg = 0x3cd4, + .enable_mask = BIT(4), + .hw.init = &(struct clk_init_data){ + .name = "gmac_core2_clk", + .parent_names = (const char *[]){ + "gmac_core2_src", + }, + .num_parents = 1, + .ops = &clk_branch_ops, + .flags = CLK_SET_RATE_PARENT, + }, + }, +}; + +static struct clk_dyn_rcg gmac_core3_src = { + .ns_reg[0] = 0x3cec, + .ns_reg[1] = 0x3cf0, + .md_reg[0] = 0x3ce4, + .md_reg[1] = 0x3ce8, + .bank_reg = 0x3ce0, + .mn[0] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .mn[1] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .s[0] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .s[1] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .p[0] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .p[1] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .mux_sel_bit = 0, + .freq_tbl = clk_tbl_gmac, + .clkr = { + .enable_reg = 0x3ce0, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "gmac_core3_src", + .parent_names = gcc_pxo_pll8_pll14_pll18_pll0, + .num_parents = 5, + .ops = &clk_dyn_rcg_ops, + }, + }, +}; + +static struct clk_branch gmac_core3_clk = { + .halt_reg = 0x3c20, + .halt_bit = 6, + .hwcg_reg = 0x3cf4, + .hwcg_bit = 6, + .clkr = { + .enable_reg = 0x3cf4, + .enable_mask = BIT(4), + .hw.init = &(struct clk_init_data){ + .name = "gmac_core3_clk", + .parent_names = (const char *[]){ + "gmac_core3_src", + }, + .num_parents = 1, + .ops = &clk_branch_ops, + .flags = CLK_SET_RATE_PARENT, + }, + }, +}; + +static struct clk_dyn_rcg gmac_core4_src = { + .ns_reg[0] = 0x3d0c, + .ns_reg[1] = 0x3d10, + .md_reg[0] = 0x3d04, + .md_reg[1] = 0x3d08, + .bank_reg = 0x3d00, + .mn[0] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .mn[1] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .s[0] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .s[1] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .p[0] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .p[1] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .mux_sel_bit = 0, + .freq_tbl = clk_tbl_gmac, + .clkr = { + .enable_reg = 0x3d00, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "gmac_core4_src", + .parent_names = gcc_pxo_pll8_pll14_pll18_pll0, + .num_parents = 5, + .ops = &clk_dyn_rcg_ops, + }, + }, +}; + +static struct clk_branch gmac_core4_clk = { + .halt_reg = 0x3c20, + .halt_bit = 7, + .hwcg_reg = 0x3d14, + .hwcg_bit = 6, + .clkr = { + .enable_reg = 0x3d14, + .enable_mask = BIT(4), + .hw.init = &(struct clk_init_data){ + .name = "gmac_core4_clk", + .parent_names = (const char *[]){ + "gmac_core4_src", + }, + .num_parents = 1, + .ops = &clk_branch_ops, + .flags = CLK_SET_RATE_PARENT, + }, + }, +}; + +static const struct freq_tbl clk_tbl_nss_tcm[] = { + { 266000000, P_PLL0, 3, 0, 0 }, + { 400000000, P_PLL0, 2, 0, 0 }, + { } +}; + +static struct clk_dyn_rcg nss_tcm_src = { + .ns_reg[0] = 0x3dc4, + .ns_reg[1] = 0x3dc8, + .bank_reg = 0x3dc0, + .s[0] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .s[1] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .p[0] = { + .pre_div_shift = 3, + .pre_div_width = 4, + }, + .p[1] = { + .pre_div_shift = 3, + .pre_div_width = 4, + }, + .mux_sel_bit = 0, + .freq_tbl = clk_tbl_nss_tcm, + .clkr = { + .enable_reg = 0x3dc0, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "nss_tcm_src", + .parent_names = gcc_pxo_pll8_pll14_pll18_pll0, + .num_parents = 5, + .ops = &clk_dyn_rcg_ops, + }, + }, +}; + +static struct clk_branch nss_tcm_clk = { + .halt_reg = 0x3c20, + .halt_bit = 14, + .clkr = { + .enable_reg = 0x3dd0, + .enable_mask = BIT(6) | BIT(4), + .hw.init = &(struct clk_init_data){ + .name = "nss_tcm_clk", + .parent_names = (const char *[]){ + "nss_tcm_src", + }, + .num_parents = 1, + .ops = &clk_branch_ops, + .flags = CLK_SET_RATE_PARENT, + }, + }, +}; + +static const struct freq_tbl clk_tbl_nss[] = { + { 110000000, P_PLL18, 1, 1, 5 }, + { 275000000, P_PLL18, 2, 0, 0 }, + { 550000000, P_PLL18, 1, 0, 0 }, + { 733000000, P_PLL18, 1, 0, 0 }, + { } +}; + +static struct clk_dyn_rcg ubi32_core1_src_clk = { + .ns_reg[0] = 0x3d2c, + .ns_reg[1] = 0x3d30, + .md_reg[0] = 0x3d24, + .md_reg[1] = 0x3d28, + .bank_reg = 0x3d20, + .mn[0] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .mn[1] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .s[0] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .s[1] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .p[0] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .p[1] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .mux_sel_bit = 0, + .freq_tbl = clk_tbl_nss, + .clkr = { + .enable_reg = 0x3d20, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "ubi32_core1_src_clk", + .parent_names = gcc_pxo_pll8_pll14_pll18_pll0, + .num_parents = 5, + .ops = &clk_dyn_rcg_ops, + .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, + }, + }, +}; + +static struct clk_dyn_rcg ubi32_core2_src_clk = { + .ns_reg[0] = 0x3d4c, + .ns_reg[1] = 0x3d50, + .md_reg[0] = 0x3d44, + .md_reg[1] = 0x3d48, + .bank_reg = 0x3d40, + .mn[0] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .mn[1] = { + .mnctr_en_bit = 8, + .mnctr_reset_bit = 7, + .mnctr_mode_shift = 5, + .n_val_shift = 16, + .m_val_shift = 16, + .width = 8, + }, + .s[0] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .s[1] = { + .src_sel_shift = 0, + .parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map, + }, + .p[0] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .p[1] = { + .pre_div_shift = 3, + .pre_div_width = 2, + }, + .mux_sel_bit = 0, + .freq_tbl = clk_tbl_nss, + .clkr = { + .enable_reg = 0x3d40, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "ubi32_core2_src_clk", + .parent_names = gcc_pxo_pll8_pll14_pll18_pll0, + .num_parents = 5, + .ops = &clk_dyn_rcg_ops, + .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, + }, + }, +}; + static struct clk_regmap *gcc_ipq806x_clks[] = { [PLL0] = &pll0.clkr, [PLL0_VOTE] = &pll0_vote, @@ -2211,6 +2728,7 @@ static struct clk_regmap *gcc_ipq806x_clks[] = { [PLL8_VOTE] = &pll8_vote, [PLL14] = &pll14.clkr, [PLL14_VOTE] = &pll14_vote, + [PLL18] = &pll18.clkr, [GSBI1_UART_SRC] = &gsbi1_uart_src.clkr, [GSBI1_UART_CLK] = &gsbi1_uart_clk.clkr, [GSBI2_UART_SRC] = &gsbi2_uart_src.clkr, @@ -2307,6 +2825,18 @@ static struct clk_regmap *gcc_ipq806x_clks[] = { [USB_FS1_SYSTEM_CLK] = &usb_fs1_sys_clk.clkr, [EBI2_CLK] = &ebi2_clk.clkr, [EBI2_AON_CLK] = &ebi2_aon_clk.clkr, + [GMAC_CORE1_CLK_SRC] = &gmac_core1_src.clkr, + [GMAC_CORE1_CLK] = &gmac_core1_clk.clkr, + [GMAC_CORE2_CLK_SRC] = &gmac_core2_src.clkr, + [GMAC_CORE2_CLK] = &gmac_core2_clk.clkr, + [GMAC_CORE3_CLK_SRC] = &gmac_core3_src.clkr, + [GMAC_CORE3_CLK] = &gmac_core3_clk.clkr, + [GMAC_CORE4_CLK_SRC] = &gmac_core4_src.clkr, + [GMAC_CORE4_CLK] = &gmac_core4_clk.clkr, + [UBI32_CORE1_CLK_SRC] = &ubi32_core1_src_clk.clkr, + [UBI32_CORE2_CLK_SRC] = &ubi32_core2_src_clk.clkr, + [NSSTCM_CLK_SRC] = &nss_tcm_src.clkr, + [NSSTCM_CLK] = &nss_tcm_clk.clkr, }; static const struct qcom_reset_map gcc_ipq806x_resets[] = { @@ -2425,6 +2955,48 @@ static const struct qcom_reset_map gcc_ipq806x_resets[] = { [USB30_1_PHY_RESET] = { 0x3b58, 0 }, [NSSFB0_RESET] = { 0x3b60, 6 }, [NSSFB1_RESET] = { 0x3b60, 7 }, + [UBI32_CORE1_CLKRST_CLAMP_RESET] = { 0x3d3c, 3}, + [UBI32_CORE1_CLAMP_RESET] = { 0x3d3c, 2 }, + [UBI32_CORE1_AHB_RESET] = { 0x3d3c, 1 }, + [UBI32_CORE1_AXI_RESET] = { 0x3d3c, 0 }, + [UBI32_CORE2_CLKRST_CLAMP_RESET] = { 0x3d5c, 3 }, + [UBI32_CORE2_CLAMP_RESET] = { 0x3d5c, 2 }, + [UBI32_CORE2_AHB_RESET] = { 0x3d5c, 1 }, + [UBI32_CORE2_AXI_RESET] = { 0x3d5c, 0 }, + [GMAC_CORE1_RESET] = { 0x3cbc, 0 }, + [GMAC_CORE2_RESET] = { 0x3cdc, 0 }, + [GMAC_CORE3_RESET] = { 0x3cfc, 0 }, + [GMAC_CORE4_RESET] = { 0x3d1c, 0 }, + [GMAC_AHB_RESET] = { 0x3e24, 0 }, + [NSS_CH0_RST_RX_CLK_N_RESET] = { 0x3b60, 0 }, + [NSS_CH0_RST_TX_CLK_N_RESET] = { 0x3b60, 1 }, + [NSS_CH0_RST_RX_125M_N_RESET] = { 0x3b60, 2 }, + [NSS_CH0_HW_RST_RX_125M_N_RESET] = { 0x3b60, 3 }, + [NSS_CH0_RST_TX_125M_N_RESET] = { 0x3b60, 4 }, + [NSS_CH1_RST_RX_CLK_N_RESET] = { 0x3b60, 5 }, + [NSS_CH1_RST_TX_CLK_N_RESET] = { 0x3b60, 6 }, + [NSS_CH1_RST_RX_125M_N_RESET] = { 0x3b60, 7 }, + [NSS_CH1_HW_RST_RX_125M_N_RESET] = { 0x3b60, 8 }, + [NSS_CH1_RST_TX_125M_N_RESET] = { 0x3b60, 9 }, + [NSS_CH2_RST_RX_CLK_N_RESET] = { 0x3b60, 10 }, + [NSS_CH2_RST_TX_CLK_N_RESET] = { 0x3b60, 11 }, + [NSS_CH2_RST_RX_125M_N_RESET] = { 0x3b60, 12 }, + [NSS_CH2_HW_RST_RX_125M_N_RESET] = { 0x3b60, 13 }, + [NSS_CH2_RST_TX_125M_N_RESET] = { 0x3b60, 14 }, + [NSS_CH3_RST_RX_CLK_N_RESET] = { 0x3b60, 15 }, + [NSS_CH3_RST_TX_CLK_N_RESET] = { 0x3b60, 16 }, + [NSS_CH3_RST_RX_125M_N_RESET] = { 0x3b60, 17 }, + [NSS_CH3_HW_RST_RX_125M_N_RESET] = { 0x3b60, 18 }, + [NSS_CH3_RST_TX_125M_N_RESET] = { 0x3b60, 19 }, + [NSS_RST_RX_250M_125M_N_RESET] = { 0x3b60, 20 }, + [NSS_RST_TX_250M_125M_N_RESET] = { 0x3b60, 21 }, + [NSS_QSGMII_TXPI_RST_N_RESET] = { 0x3b60, 22 }, + [NSS_QSGMII_CDR_RST_N_RESET] = { 0x3b60, 23 }, + [NSS_SGMII2_CDR_RST_N_RESET] = { 0x3b60, 24 }, + [NSS_SGMII3_CDR_RST_N_RESET] = { 0x3b60, 25 }, + [NSS_CAL_PRBS_RST_N_RESET] = { 0x3b60, 26 }, + [NSS_LCKDT_RST_N_RESET] = { 0x3b60, 27 }, + [NSS_SRDS_N_RESET] = { 0x3b60, 28 }, }; static const struct regmap_config gcc_ipq806x_regmap_config = { @@ -2453,6 +3025,8 @@ static int gcc_ipq806x_probe(struct platform_device *pdev) { struct clk *clk; struct device *dev = &pdev->dev; + struct regmap *regmap; + int ret; /* Temporary until RPM clocks supported */ clk = clk_register_fixed_rate(dev, "cxo", NULL, CLK_IS_ROOT, 25000000); @@ -2463,7 +3037,25 @@ static int gcc_ipq806x_probe(struct platform_device *pdev) if (IS_ERR(clk)) return PTR_ERR(clk); - return qcom_cc_probe(pdev, &gcc_ipq806x_desc); + ret = qcom_cc_probe(pdev, &gcc_ipq806x_desc); + if (ret) + return ret; + + regmap = dev_get_regmap(dev, NULL); + if (!regmap) + return -ENODEV; + + /* Setup PLL18 static bits */ + regmap_update_bits(regmap, 0x31a4, 0xffffffc0, 0x40000400); + regmap_write(regmap, 0x31b0, 0x3080); + + /* Set GMAC footswitch sleep/wakeup values */ + regmap_write(regmap, 0x3cb8, 8); + regmap_write(regmap, 0x3cd8, 8); + regmap_write(regmap, 0x3cf8, 8); + regmap_write(regmap, 0x3d18, 8); + + return 0; } static int gcc_ipq806x_remove(struct platform_device *pdev) diff --git a/drivers/gpio/gpio-kempld.c b/drivers/gpio/gpio-kempld.c index 6b8115f..83f281d 100644 --- a/drivers/gpio/gpio-kempld.c +++ b/drivers/gpio/gpio-kempld.c @@ -117,7 +117,7 @@ static int kempld_gpio_get_direction(struct gpio_chip *chip, unsigned offset) = container_of(chip, struct kempld_gpio_data, chip); struct kempld_device_data *pld = gpio->pld; - return kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset); + return !kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset); } static int kempld_gpio_pincount(struct kempld_device_data *pld) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 59eaa23..6bc612b 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -53,6 +53,11 @@ static DEFINE_MUTEX(gpio_lookup_lock); static LIST_HEAD(gpio_lookup_list); LIST_HEAD(gpio_chips); + +static void gpiochip_free_hogs(struct gpio_chip *chip); +static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip); + + static inline void desc_set_label(struct gpio_desc *d, const char *label) { d->label = label; @@ -297,6 +302,7 @@ int gpiochip_add(struct gpio_chip *chip) err_remove_chip: acpi_gpiochip_remove(chip); + gpiochip_free_hogs(chip); of_gpiochip_remove(chip); spin_lock_irqsave(&gpio_lock, flags); list_del(&chip->list); @@ -313,10 +319,6 @@ err_free_descs: } EXPORT_SYMBOL_GPL(gpiochip_add); -/* Forward-declaration */ -static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip); -static void gpiochip_free_hogs(struct gpio_chip *chip); - /** * gpiochip_remove() - unregister a gpio_chip * @chip: the chip to unregister diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c index 40c1db9..2f0ed11 100644 --- a/drivers/gpu/drm/drm_plane_helper.c +++ b/drivers/gpu/drm/drm_plane_helper.c @@ -465,6 +465,9 @@ int drm_plane_helper_commit(struct drm_plane *plane, if (!crtc[i]) continue; + if (crtc[i]->cursor == plane) + continue; + /* There's no other way to figure out whether the crtc is running. */ ret = drm_crtc_vblank_get(crtc[i]); if (ret == 0) { diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h index 0b5af0f..64f8b2f 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/class.h +++ b/drivers/gpu/drm/nouveau/include/nvif/class.h @@ -14,7 +14,7 @@ #define FERMI_TWOD_A 0x0000902d -#define FERMI_MEMORY_TO_MEMORY_FORMAT_A 0x0000903d +#define FERMI_MEMORY_TO_MEMORY_FORMAT_A 0x00009039 #define KEPLER_INLINE_TO_MEMORY_A 0x0000a040 #define KEPLER_INLINE_TO_MEMORY_B 0x0000a140 diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c index 2f5eadd..fdb1dcf 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c @@ -329,7 +329,6 @@ gm204_gr_init(struct nvkm_object *object) nv_mask(priv, 0x419cc0, 0x00000008, 0x00000008); for (gpc = 0; gpc < priv->gpc_nr; gpc++) { - printk(KERN_ERR "ppc %d %d\n", gpc, priv->ppc_nr[gpc]); for (ppc = 0; ppc < priv->ppc_nr[gpc]; ppc++) nv_wr32(priv, PPC_UNIT(gpc, ppc, 0x038), 0xc0000000); nv_wr32(priv, GPC_UNIT(gpc, 0x0420), 0xc0000000); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c index e8778c6..c61102f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c @@ -90,12 +90,14 @@ gf100_devinit_disable(struct nvkm_devinit *devinit) return disable; } -static int +int gf100_devinit_ctor(struct nvkm_object *parent, struct nvkm_object *engine, struct nvkm_oclass *oclass, void *data, u32 size, struct nvkm_object **pobject) { + struct nvkm_devinit_impl *impl = (void *)oclass; struct nv50_devinit_priv *priv; + u64 disable; int ret; ret = nvkm_devinit_create(parent, engine, oclass, &priv); @@ -103,7 +105,8 @@ gf100_devinit_ctor(struct nvkm_object *parent, struct nvkm_object *engine, if (ret) return ret; - if (nv_rd32(priv, 0x022500) & 0x00000001) + disable = impl->disable(&priv->base); + if (disable & (1ULL << NVDEV_ENGINE_DISP)) priv->base.post = true; return 0; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c index b345a53..87ca0ec 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c @@ -48,7 +48,7 @@ struct nvkm_oclass * gm107_devinit_oclass = &(struct nvkm_devinit_impl) { .base.handle = NV_SUBDEV(DEVINIT, 0x07), .base.ofuncs = &(struct nvkm_ofuncs) { - .ctor = nv50_devinit_ctor, + .ctor = gf100_devinit_ctor, .dtor = _nvkm_devinit_dtor, .init = nv50_devinit_init, .fini = _nvkm_devinit_fini, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c index 535172c..1076fcf 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c @@ -161,7 +161,7 @@ struct nvkm_oclass * gm204_devinit_oclass = &(struct nvkm_devinit_impl) { .base.handle = NV_SUBDEV(DEVINIT, 0x07), .base.ofuncs = &(struct nvkm_ofuncs) { - .ctor = nv50_devinit_ctor, + .ctor = gf100_devinit_ctor, .dtor = _nvkm_devinit_dtor, .init = nv50_devinit_init, .fini = _nvkm_devinit_fini, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h index b882b65..9243521c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h @@ -15,6 +15,9 @@ int nv50_devinit_pll_set(struct nvkm_devinit *, u32, u32); int gt215_devinit_pll_set(struct nvkm_devinit *, u32, u32); +int gf100_devinit_ctor(struct nvkm_object *, struct nvkm_object *, + struct nvkm_oclass *, void *, u32, + struct nvkm_object **); int gf100_devinit_pll_set(struct nvkm_devinit *, u32, u32); u64 gm107_devinit_disable(struct nvkm_devinit *); diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 42b2ea3..e597ffc 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1798,7 +1798,9 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc) if ((crtc->mode.clock == test_crtc->mode.clock) && (adjusted_clock == test_adjusted_clock) && (radeon_crtc->ss_enabled == test_radeon_crtc->ss_enabled) && - (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID)) + (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID) && + (drm_detect_monitor_audio(radeon_connector_edid(test_radeon_crtc->connector)) == + drm_detect_monitor_audio(radeon_connector_edid(radeon_crtc->connector)))) return test_radeon_crtc->pll_id; } } diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index a0c35bb..ba50f3c 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -5822,7 +5822,7 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev) L2_CACHE_BIGK_FRAGMENT_SIZE(4)); /* setup context0 */ WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12); - WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1); + WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12); WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12); WREG32(VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR, (u32)(rdev->dummy_page.addr >> 12)); diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 05e6d6e..f848acf 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2485,7 +2485,7 @@ static int evergreen_pcie_gart_enable(struct radeon_device *rdev) WREG32(MC_VM_MB_L1_TLB2_CNTL, tmp); WREG32(MC_VM_MB_L1_TLB3_CNTL, tmp); WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12); - WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1); + WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12); WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12); WREG32(VM_CONTEXT0_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) | RANGE_PROTECTION_FAULT_ENABLE_DEFAULT); diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c index 0926739..9953356 100644 --- a/drivers/gpu/drm/radeon/evergreen_hdmi.c +++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c @@ -400,7 +400,7 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable) if (enable) { struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - if (drm_detect_monitor_audio(radeon_connector_edid(connector))) { + if (connector && drm_detect_monitor_audio(radeon_connector_edid(connector))) { WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset, HDMI_AVI_INFO_SEND | /* enable AVI info frames */ HDMI_AVI_INFO_CONT | /* required for audio info values to be updated */ @@ -438,7 +438,8 @@ void evergreen_dp_enable(struct drm_encoder *encoder, bool enable) if (!dig || !dig->afmt) return; - if (enable && drm_detect_monitor_audio(radeon_connector_edid(connector))) { + if (enable && connector && + drm_detect_monitor_audio(radeon_connector_edid(connector))) { struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); struct radeon_connector *radeon_connector = to_radeon_connector(connector); struct radeon_connector_atom_dig *dig_connector; diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index aba2f42..64d3a77 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -1282,7 +1282,7 @@ static int cayman_pcie_gart_enable(struct radeon_device *rdev) L2_CACHE_BIGK_FRAGMENT_SIZE(6)); /* setup context0 */ WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12); - WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1); + WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12); WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12); WREG32(VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR, (u32)(rdev->dummy_page.addr >> 12)); diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 25b4ac9..8f6d862 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -1112,7 +1112,7 @@ static int r600_pcie_gart_enable(struct radeon_device *rdev) WREG32(MC_VM_L1_TLB_MCB_RD_SEM_CNTL, tmp | ENABLE_SEMAPHORE_MODE); WREG32(MC_VM_L1_TLB_MCB_WR_SEM_CNTL, tmp | ENABLE_SEMAPHORE_MODE); WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12); - WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1); + WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12); WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12); WREG32(VM_CONTEXT0_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) | RANGE_PROTECTION_FAULT_ENABLE_DEFAULT); diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c index dcb7796..25191f1 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.c +++ b/drivers/gpu/drm/radeon/radeon_audio.c @@ -460,9 +460,6 @@ void radeon_audio_detect(struct drm_connector *connector, if (!connector || !connector->encoder) return; - if (!radeon_encoder_is_digital(connector->encoder)) - return; - rdev = connector->encoder->dev->dev_private; if (!radeon_audio_chipset_supported(rdev)) @@ -471,26 +468,26 @@ void radeon_audio_detect(struct drm_connector *connector, radeon_encoder = to_radeon_encoder(connector->encoder); dig = radeon_encoder->enc_priv; - if (!dig->afmt) - return; - if (status == connector_status_connected) { - struct radeon_connector *radeon_connector = to_radeon_connector(connector); + struct radeon_connector *radeon_connector; + int sink_type; + + if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) { + radeon_encoder->audio = NULL; + return; + } + + radeon_connector = to_radeon_connector(connector); + sink_type = radeon_dp_getsinktype(radeon_connector); if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort && - radeon_dp_getsinktype(radeon_connector) == - CONNECTOR_OBJECT_ID_DISPLAYPORT) + sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) radeon_encoder->audio = rdev->audio.dp_funcs; else radeon_encoder->audio = rdev->audio.hdmi_funcs; dig->afmt->pin = radeon_audio_get_pin(connector->encoder); - if (drm_detect_monitor_audio(radeon_connector_edid(connector))) { - radeon_audio_enable(rdev, dig->afmt->pin, 0xf); - } else { - radeon_audio_enable(rdev, dig->afmt->pin, 0); - dig->afmt->pin = NULL; - } + radeon_audio_enable(rdev, dig->afmt->pin, 0xf); } else { radeon_audio_enable(rdev, dig->afmt->pin, 0); dig->afmt->pin = NULL; diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index d17d251..cebb65e 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -1379,10 +1379,8 @@ out: /* updated in get modes as well since we need to know if it's analog or digital */ radeon_connector_update_scratch_regs(connector, ret); - if (radeon_audio != 0) { - radeon_connector_get_edid(connector); + if (radeon_audio != 0) radeon_audio_detect(connector, ret); - } exit: pm_runtime_mark_last_busy(connector->dev->dev); @@ -1719,10 +1717,8 @@ radeon_dp_detect(struct drm_connector *connector, bool force) radeon_connector_update_scratch_regs(connector, ret); - if (radeon_audio != 0) { - radeon_connector_get_edid(connector); + if (radeon_audio != 0) radeon_audio_detect(connector, ret); - } out: pm_runtime_mark_last_busy(connector->dev->dev); diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c index c54d631..01ee96a 100644 --- a/drivers/gpu/drm/radeon/rv770.c +++ b/drivers/gpu/drm/radeon/rv770.c @@ -921,7 +921,7 @@ static int rv770_pcie_gart_enable(struct radeon_device *rdev) WREG32(MC_VM_MB_L1_TLB2_CNTL, tmp); WREG32(MC_VM_MB_L1_TLB3_CNTL, tmp); WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12); - WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1); + WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12); WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12); WREG32(VM_CONTEXT0_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) | RANGE_PROTECTION_FAULT_ENABLE_DEFAULT); diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 5326f75..4c679b8 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -4303,7 +4303,7 @@ static int si_pcie_gart_enable(struct radeon_device *rdev) L2_CACHE_BIGK_FRAGMENT_SIZE(4)); /* setup context0 */ WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12); - WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1); + WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12); WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12); WREG32(VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR, (u32)(rdev->dummy_page.addr >> 12)); diff --git a/drivers/gpu/drm/vgem/Makefile b/drivers/gpu/drm/vgem/Makefile index 1055cb7..3f4c7b8 100644 --- a/drivers/gpu/drm/vgem/Makefile +++ b/drivers/gpu/drm/vgem/Makefile @@ -1,4 +1,4 @@ ccflags-y := -Iinclude/drm -vgem-y := vgem_drv.o vgem_dma_buf.o +vgem-y := vgem_drv.o obj-$(CONFIG_DRM_VGEM) += vgem.o diff --git a/drivers/gpu/drm/vgem/vgem_dma_buf.c b/drivers/gpu/drm/vgem/vgem_dma_buf.c deleted file mode 100644 index 0254438..0000000 --- a/drivers/gpu/drm/vgem/vgem_dma_buf.c +++ /dev/null @@ -1,94 +0,0 @@ -/* - * Copyright © 2012 Intel Corporation - * Copyright © 2014 The Chromium OS Authors - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * - * Authors: - * Ben Widawsky <ben@bwidawsk.net> - * - */ - -#include <linux/dma-buf.h> -#include "vgem_drv.h" - -struct sg_table *vgem_gem_prime_get_sg_table(struct drm_gem_object *gobj) -{ - struct drm_vgem_gem_object *obj = to_vgem_bo(gobj); - BUG_ON(obj->pages == NULL); - - return drm_prime_pages_to_sg(obj->pages, obj->base.size / PAGE_SIZE); -} - -int vgem_gem_prime_pin(struct drm_gem_object *gobj) -{ - struct drm_vgem_gem_object *obj = to_vgem_bo(gobj); - return vgem_gem_get_pages(obj); -} - -void vgem_gem_prime_unpin(struct drm_gem_object *gobj) -{ - struct drm_vgem_gem_object *obj = to_vgem_bo(gobj); - vgem_gem_put_pages(obj); -} - -void *vgem_gem_prime_vmap(struct drm_gem_object *gobj) -{ - struct drm_vgem_gem_object *obj = to_vgem_bo(gobj); - BUG_ON(obj->pages == NULL); - - return vmap(obj->pages, obj->base.size / PAGE_SIZE, 0, PAGE_KERNEL); -} - -void vgem_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr) -{ - vunmap(vaddr); -} - -struct drm_gem_object *vgem_gem_prime_import(struct drm_device *dev, - struct dma_buf *dma_buf) -{ - struct drm_vgem_gem_object *obj = NULL; - int ret; - - obj = kzalloc(sizeof(*obj), GFP_KERNEL); - if (obj == NULL) { - ret = -ENOMEM; - goto fail; - } - - ret = drm_gem_object_init(dev, &obj->base, dma_buf->size); - if (ret) { - ret = -ENOMEM; - goto fail_free; - } - - get_dma_buf(dma_buf); - - obj->base.dma_buf = dma_buf; - obj->use_dma_buf = true; - - return &obj->base; - -fail_free: - kfree(obj); -fail: - return ERR_PTR(ret); -} diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index cb3b435..7a207ca 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -302,22 +302,13 @@ static const struct file_operations vgem_driver_fops = { }; static struct drm_driver vgem_driver = { - .driver_features = DRIVER_GEM | DRIVER_PRIME, + .driver_features = DRIVER_GEM, .gem_free_object = vgem_gem_free_object, .gem_vm_ops = &vgem_gem_vm_ops, .ioctls = vgem_ioctls, .fops = &vgem_driver_fops, .dumb_create = vgem_gem_dumb_create, .dumb_map_offset = vgem_gem_dumb_map, - .prime_handle_to_fd = drm_gem_prime_handle_to_fd, - .prime_fd_to_handle = drm_gem_prime_fd_to_handle, - .gem_prime_export = drm_gem_prime_export, - .gem_prime_import = vgem_gem_prime_import, - .gem_prime_pin = vgem_gem_prime_pin, - .gem_prime_unpin = vgem_gem_prime_unpin, - .gem_prime_get_sg_table = vgem_gem_prime_get_sg_table, - .gem_prime_vmap = vgem_gem_prime_vmap, - .gem_prime_vunmap = vgem_gem_prime_vunmap, .name = DRIVER_NAME, .desc = DRIVER_DESC, .date = DRIVER_DATE, diff --git a/drivers/gpu/drm/vgem/vgem_drv.h b/drivers/gpu/drm/vgem/vgem_drv.h index 57ab4d8..e9f92f7 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.h +++ b/drivers/gpu/drm/vgem/vgem_drv.h @@ -43,15 +43,4 @@ struct drm_vgem_gem_object { extern void vgem_gem_put_pages(struct drm_vgem_gem_object *obj); extern int vgem_gem_get_pages(struct drm_vgem_gem_object *obj); -/* vgem_dma_buf.c */ -extern struct sg_table *vgem_gem_prime_get_sg_table( - struct drm_gem_object *gobj); -extern int vgem_gem_prime_pin(struct drm_gem_object *gobj); -extern void vgem_gem_prime_unpin(struct drm_gem_object *gobj); -extern void *vgem_gem_prime_vmap(struct drm_gem_object *gobj); -extern void vgem_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); -extern struct drm_gem_object *vgem_gem_prime_import(struct drm_device *dev, - struct dma_buf *dma_buf); - - #endif diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c index f3830db..37f0170 100644 --- a/drivers/hwmon/nct6683.c +++ b/drivers/hwmon/nct6683.c @@ -439,6 +439,7 @@ nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg, (*t)->dev_attr.attr.name, tg->base + i); if ((*t)->s2) { a2 = &su->u.a2; + sysfs_attr_init(&a2->dev_attr.attr); a2->dev_attr.attr.name = su->name; a2->nr = (*t)->u.s.nr + i; a2->index = (*t)->u.s.index; @@ -449,6 +450,7 @@ nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg, *attrs = &a2->dev_attr.attr; } else { a = &su->u.a1; + sysfs_attr_init(&a->dev_attr.attr); a->dev_attr.attr.name = su->name; a->index = (*t)->u.index + i; a->dev_attr.attr.mode = diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index 4fcb481..bd1c99d 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -995,6 +995,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg, (*t)->dev_attr.attr.name, tg->base + i); if ((*t)->s2) { a2 = &su->u.a2; + sysfs_attr_init(&a2->dev_attr.attr); a2->dev_attr.attr.name = su->name; a2->nr = (*t)->u.s.nr + i; a2->index = (*t)->u.s.index; @@ -1005,6 +1006,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg, *attrs = &a2->dev_attr.attr; } else { a = &su->u.a1; + sysfs_attr_init(&a->dev_attr.attr); a->dev_attr.attr.name = su->name; a->index = (*t)->u.index + i; a->dev_attr.attr.mode = diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c index 112e4d4..68800115 100644 --- a/drivers/hwmon/ntc_thermistor.c +++ b/drivers/hwmon/ntc_thermistor.c @@ -239,8 +239,10 @@ static struct ntc_thermistor_platform_data * ntc_thermistor_parse_dt(struct platform_device *pdev) { struct iio_channel *chan; + enum iio_chan_type type; struct device_node *np = pdev->dev.of_node; struct ntc_thermistor_platform_data *pdata; + int ret; if (!np) return NULL; @@ -253,6 +255,13 @@ ntc_thermistor_parse_dt(struct platform_device *pdev) if (IS_ERR(chan)) return ERR_CAST(chan); + ret = iio_get_channel_type(chan, &type); + if (ret < 0) + return ERR_PTR(ret); + + if (type != IIO_VOLTAGE) + return ERR_PTR(-EINVAL); + if (of_property_read_u32(np, "pullup-uv", &pdata->pullup_uv)) return ERR_PTR(-ENODEV); if (of_property_read_u32(np, "pullup-ohm", &pdata->pullup_ohm)) diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c index 99664eb..ccf4cff 100644 --- a/drivers/hwmon/tmp401.c +++ b/drivers/hwmon/tmp401.c @@ -44,7 +44,7 @@ #include <linux/sysfs.h> /* Addresses to scan */ -static const unsigned short normal_i2c[] = { 0x37, 0x48, 0x49, 0x4a, 0x4c, 0x4d, +static const unsigned short normal_i2c[] = { 0x48, 0x49, 0x4a, 0x4c, 0x4d, 0x4e, 0x4f, I2C_CLIENT_END }; enum chips { tmp401, tmp411, tmp431, tmp432, tmp435 }; diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 66bd6a2..d95a0c3 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -445,10 +445,10 @@ static int c4iw_get_mib(struct ib_device *ibdev, cxgb4_get_tcp_stats(c4iw_dev->rdev.lldi.pdev, &v4, &v6); memset(stats, 0, sizeof *stats); - stats->iw.tcpInSegs = v4.tcpInSegs + v6.tcpInSegs; - stats->iw.tcpOutSegs = v4.tcpOutSegs + v6.tcpOutSegs; - stats->iw.tcpRetransSegs = v4.tcpRetransSegs + v6.tcpRetransSegs; - stats->iw.tcpOutRsts = v4.tcpOutRsts + v6.tcpOutSegs; + stats->iw.tcpInSegs = v4.tcp_in_segs + v6.tcp_in_segs; + stats->iw.tcpOutSegs = v4.tcp_out_segs + v6.tcp_out_segs; + stats->iw.tcpRetransSegs = v4.tcp_retrans_segs + v6.tcp_retrans_segs; + stats->iw.tcpOutRsts = v4.tcp_out_rsts + v6.tcp_out_rsts; return 0; } diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index cc64400..024b0f7 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1090,7 +1090,7 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att ret = mlx4_cmd_imm(mdev->dev, mailbox->dma, reg_id, size >> 2, 0, MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A, - MLX4_CMD_NATIVE); + MLX4_CMD_WRAPPED); if (ret == -ENOMEM) pr_err("mcg table is full. Fail to register network rule.\n"); else if (ret == -ENXIO) @@ -1107,7 +1107,7 @@ static int __mlx4_ib_destroy_flow(struct mlx4_dev *dev, u64 reg_id) int err; err = mlx4_cmd(dev, reg_id, 0, 0, MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A, - MLX4_CMD_NATIVE); + MLX4_CMD_WRAPPED); if (err) pr_err("Fail to detach network rule. registration id = 0x%llx\n", reg_id); @@ -2041,77 +2041,52 @@ static void init_pkeys(struct mlx4_ib_dev *ibdev) static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) { - char name[80]; - int eq_per_port = 0; - int added_eqs = 0; - int total_eqs = 0; - int i, j, eq; - - /* Legacy mode or comp_pool is not large enough */ - if (dev->caps.comp_pool == 0 || - dev->caps.num_ports > dev->caps.comp_pool) - return; - - eq_per_port = dev->caps.comp_pool / dev->caps.num_ports; - - /* Init eq table */ - added_eqs = 0; - mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) - added_eqs += eq_per_port; - - total_eqs = dev->caps.num_comp_vectors + added_eqs; + int i, j, eq = 0, total_eqs = 0; - ibdev->eq_table = kzalloc(total_eqs * sizeof(int), GFP_KERNEL); + ibdev->eq_table = kcalloc(dev->caps.num_comp_vectors, + sizeof(ibdev->eq_table[0]), GFP_KERNEL); if (!ibdev->eq_table) return; - ibdev->eq_added = added_eqs; - - eq = 0; - mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) { - for (j = 0; j < eq_per_port; j++) { - snprintf(name, sizeof(name), "mlx4-ib-%d-%d@%s", - i, j, dev->persist->pdev->bus->name); - /* Set IRQ for specific name (per ring) */ - if (mlx4_assign_eq(dev, name, NULL, - &ibdev->eq_table[eq])) { - /* Use legacy (same as mlx4_en driver) */ - pr_warn("Can't allocate EQ %d; reverting to legacy\n", eq); - ibdev->eq_table[eq] = - (eq % dev->caps.num_comp_vectors); - } - eq++; + for (i = 1; i <= dev->caps.num_ports; i++) { + for (j = 0; j < mlx4_get_eqs_per_port(dev, i); + j++, total_eqs++) { + if (i > 1 && mlx4_is_eq_shared(dev, total_eqs)) + continue; + ibdev->eq_table[eq] = total_eqs; + if (!mlx4_assign_eq(dev, i, + &ibdev->eq_table[eq])) + eq++; + else + ibdev->eq_table[eq] = -1; } } - /* Fill the reset of the vector with legacy EQ */ - for (i = 0, eq = added_eqs; i < dev->caps.num_comp_vectors; i++) - ibdev->eq_table[eq++] = i; + for (i = eq; i < dev->caps.num_comp_vectors; + ibdev->eq_table[i++] = -1) + ; /* Advertise the new number of EQs to clients */ - ibdev->ib_dev.num_comp_vectors = total_eqs; + ibdev->ib_dev.num_comp_vectors = eq; } static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) { int i; + int total_eqs = ibdev->ib_dev.num_comp_vectors; - /* no additional eqs were added */ + /* no eqs were allocated */ if (!ibdev->eq_table) return; /* Reset the advertised EQ number */ - ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors; + ibdev->ib_dev.num_comp_vectors = 0; - /* Free only the added eqs */ - for (i = 0; i < ibdev->eq_added; i++) { - /* Don't free legacy eqs if used */ - if (ibdev->eq_table[i] <= dev->caps.num_comp_vectors) - continue; + for (i = 0; i < total_eqs; i++) mlx4_release_eq(dev, ibdev->eq_table[i]); - } kfree(ibdev->eq_table); + ibdev->eq_table = NULL; } static void *mlx4_ib_add(struct mlx4_dev *dev) diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index fce39343..ef80e6c 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -523,7 +523,6 @@ struct mlx4_ib_dev { struct mlx4_ib_iboe iboe; int counters[MLX4_MAX_PORTS]; int *eq_table; - int eq_added; struct kobject *iov_parent; struct kobject *ports_parent; struct kobject *dev_ports_parent[MLX4_MFUNC_MAX]; diff --git a/drivers/infiniband/hw/mlx5/Kconfig b/drivers/infiniband/hw/mlx5/Kconfig index 10df386..bce263b 100644 --- a/drivers/infiniband/hw/mlx5/Kconfig +++ b/drivers/infiniband/hw/mlx5/Kconfig @@ -1,8 +1,6 @@ config MLX5_INFINIBAND tristate "Mellanox Connect-IB HCA support" - depends on NETDEVICES && ETHERNET && PCI - select NET_VENDOR_MELLANOX - select MLX5_CORE + depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE ---help--- This driver provides low-level InfiniBand support for Mellanox Connect-IB PCI Express host channel adapters (HCAs). diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 2ee6b10..e2bea9a 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -590,8 +590,7 @@ static int alloc_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf, { int err; - err = mlx5_buf_alloc(dev->mdev, nent * cqe_size, - PAGE_SIZE * 2, &buf->buf); + err = mlx5_buf_alloc(dev->mdev, nent * cqe_size, &buf->buf); if (err) return err; @@ -754,7 +753,7 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries, return ERR_PTR(-EINVAL); entries = roundup_pow_of_two(entries + 1); - if (entries > dev->mdev->caps.gen.max_cqes) + if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) return ERR_PTR(-EINVAL); cq = kzalloc(sizeof(*cq), GFP_KERNEL); @@ -921,7 +920,7 @@ int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period) int err; u32 fsel; - if (!(dev->mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_CQ_MODER)) + if (!MLX5_CAP_GEN(dev->mdev, cq_moderation)) return -ENOSYS; in = kzalloc(sizeof(*in), GFP_KERNEL); @@ -1076,7 +1075,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) int uninitialized_var(cqe_size); unsigned long flags; - if (!(dev->mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_RESIZE_CQ)) { + if (!MLX5_CAP_GEN(dev->mdev, cq_resize)) { pr_info("Firmware does not support resize CQ\n"); return -ENOSYS; } @@ -1085,7 +1084,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) return -EINVAL; entries = roundup_pow_of_two(entries + 1); - if (entries > dev->mdev->caps.gen.max_cqes + 1) + if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1) return -EINVAL; if (entries == ibcq->cqe + 1) diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 9cf9a37..f2d9e70 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -129,7 +129,7 @@ int mlx5_query_ext_port_caps(struct mlx5_ib_dev *dev, u8 port) packet_error = be16_to_cpu(out_mad->status); - dev->mdev->caps.gen.ext_port_cap[port - 1] = (!err && !packet_error) ? + dev->mdev->port_caps[port - 1].ext_port_cap = (!err && !packet_error) ? MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO : 0; out: diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 57c9809..9075649 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -66,15 +66,13 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, struct ib_device_attr *props) { struct mlx5_ib_dev *dev = to_mdev(ibdev); + struct mlx5_core_dev *mdev = dev->mdev; struct ib_smp *in_mad = NULL; struct ib_smp *out_mad = NULL; - struct mlx5_general_caps *gen; int err = -ENOMEM; int max_rq_sg; int max_sq_sg; - u64 flags; - gen = &dev->mdev->caps.gen; in_mad = kzalloc(sizeof(*in_mad), GFP_KERNEL); out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL); if (!in_mad || !out_mad) @@ -96,18 +94,18 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, IB_DEVICE_PORT_ACTIVE_EVENT | IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_RC_RNR_NAK_GEN; - flags = gen->flags; - if (flags & MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR) + + if (MLX5_CAP_GEN(mdev, pkv)) props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR; - if (flags & MLX5_DEV_CAP_FLAG_BAD_QKEY_CNTR) + if (MLX5_CAP_GEN(mdev, qkv)) props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR; - if (flags & MLX5_DEV_CAP_FLAG_APM) + if (MLX5_CAP_GEN(mdev, apm)) props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG; props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY; - if (flags & MLX5_DEV_CAP_FLAG_XRC) + if (MLX5_CAP_GEN(mdev, xrc)) props->device_cap_flags |= IB_DEVICE_XRC; props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS; - if (flags & MLX5_DEV_CAP_FLAG_SIG_HAND_OVER) { + if (MLX5_CAP_GEN(mdev, sho)) { props->device_cap_flags |= IB_DEVICE_SIGNATURE_HANDOVER; /* At this stage no support for signature handover */ props->sig_prot_cap = IB_PROT_T10DIF_TYPE_1 | @@ -116,7 +114,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->sig_guard_cap = IB_GUARD_T10DIF_CRC | IB_GUARD_T10DIF_CSUM; } - if (flags & MLX5_DEV_CAP_FLAG_BLOCK_MCAST) + if (MLX5_CAP_GEN(mdev, block_lb_mc)) props->device_cap_flags |= IB_DEVICE_BLOCK_MULTICAST_LOOPBACK; props->vendor_id = be32_to_cpup((__be32 *)(out_mad->data + 36)) & @@ -126,37 +124,38 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, memcpy(&props->sys_image_guid, out_mad->data + 4, 8); props->max_mr_size = ~0ull; - props->page_size_cap = gen->min_page_sz; - props->max_qp = 1 << gen->log_max_qp; - props->max_qp_wr = gen->max_wqes; - max_rq_sg = gen->max_rq_desc_sz / sizeof(struct mlx5_wqe_data_seg); - max_sq_sg = (gen->max_sq_desc_sz - sizeof(struct mlx5_wqe_ctrl_seg)) / - sizeof(struct mlx5_wqe_data_seg); + props->page_size_cap = 1ull << MLX5_CAP_GEN(mdev, log_pg_sz); + props->max_qp = 1 << MLX5_CAP_GEN(mdev, log_max_qp); + props->max_qp_wr = 1 << MLX5_CAP_GEN(mdev, log_max_qp_sz); + max_rq_sg = MLX5_CAP_GEN(mdev, max_wqe_sz_rq) / + sizeof(struct mlx5_wqe_data_seg); + max_sq_sg = (MLX5_CAP_GEN(mdev, max_wqe_sz_sq) - + sizeof(struct mlx5_wqe_ctrl_seg)) / + sizeof(struct mlx5_wqe_data_seg); props->max_sge = min(max_rq_sg, max_sq_sg); - props->max_cq = 1 << gen->log_max_cq; - props->max_cqe = gen->max_cqes - 1; - props->max_mr = 1 << gen->log_max_mkey; - props->max_pd = 1 << gen->log_max_pd; - props->max_qp_rd_atom = 1 << gen->log_max_ra_req_qp; - props->max_qp_init_rd_atom = 1 << gen->log_max_ra_res_qp; - props->max_srq = 1 << gen->log_max_srq; - props->max_srq_wr = gen->max_srq_wqes - 1; - props->local_ca_ack_delay = gen->local_ca_ack_delay; + props->max_cq = 1 << MLX5_CAP_GEN(mdev, log_max_cq); + props->max_cqe = (1 << MLX5_CAP_GEN(mdev, log_max_eq_sz)) - 1; + props->max_mr = 1 << MLX5_CAP_GEN(mdev, log_max_mkey); + props->max_pd = 1 << MLX5_CAP_GEN(mdev, log_max_pd); + props->max_qp_rd_atom = 1 << MLX5_CAP_GEN(mdev, log_max_ra_req_qp); + props->max_qp_init_rd_atom = 1 << MLX5_CAP_GEN(mdev, log_max_ra_res_qp); + props->max_srq = 1 << MLX5_CAP_GEN(mdev, log_max_srq); + props->max_srq_wr = (1 << MLX5_CAP_GEN(mdev, log_max_srq_sz)) - 1; + props->local_ca_ack_delay = MLX5_CAP_GEN(mdev, local_ca_ack_delay); props->max_res_rd_atom = props->max_qp_rd_atom * props->max_qp; props->max_srq_sge = max_rq_sg - 1; props->max_fast_reg_page_list_len = (unsigned int)-1; - props->local_ca_ack_delay = gen->local_ca_ack_delay; props->atomic_cap = IB_ATOMIC_NONE; props->masked_atomic_cap = IB_ATOMIC_NONE; props->max_pkeys = be16_to_cpup((__be16 *)(out_mad->data + 28)); - props->max_mcast_grp = 1 << gen->log_max_mcg; - props->max_mcast_qp_attach = gen->max_qp_mcg; + props->max_mcast_grp = 1 << MLX5_CAP_GEN(mdev, log_max_mcg); + props->max_mcast_qp_attach = MLX5_CAP_GEN(mdev, max_qp_mcg); props->max_total_mcast_qp_attach = props->max_mcast_qp_attach * props->max_mcast_grp; props->max_map_per_fmr = INT_MAX; /* no limit in ConnectIB */ #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - if (dev->mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_ON_DMND_PG) + if (MLX5_CAP_GEN(mdev, pg)) props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING; props->odp_caps = dev->odp_caps; #endif @@ -172,14 +171,13 @@ int mlx5_ib_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr *props) { struct mlx5_ib_dev *dev = to_mdev(ibdev); + struct mlx5_core_dev *mdev = dev->mdev; struct ib_smp *in_mad = NULL; struct ib_smp *out_mad = NULL; - struct mlx5_general_caps *gen; int ext_active_speed; int err = -ENOMEM; - gen = &dev->mdev->caps.gen; - if (port < 1 || port > gen->num_ports) { + if (port < 1 || port > MLX5_CAP_GEN(mdev, num_ports)) { mlx5_ib_warn(dev, "invalid port number %d\n", port); return -EINVAL; } @@ -210,8 +208,8 @@ int mlx5_ib_query_port(struct ib_device *ibdev, u8 port, props->phys_state = out_mad->data[33] >> 4; props->port_cap_flags = be32_to_cpup((__be32 *)(out_mad->data + 20)); props->gid_tbl_len = out_mad->data[50]; - props->max_msg_sz = 1 << gen->log_max_msg; - props->pkey_tbl_len = gen->port[port - 1].pkey_table_len; + props->max_msg_sz = 1 << MLX5_CAP_GEN(mdev, log_max_msg); + props->pkey_tbl_len = mdev->port_caps[port - 1].pkey_table_len; props->bad_pkey_cntr = be16_to_cpup((__be16 *)(out_mad->data + 46)); props->qkey_viol_cntr = be16_to_cpup((__be16 *)(out_mad->data + 48)); props->active_width = out_mad->data[31] & 0xf; @@ -238,7 +236,7 @@ int mlx5_ib_query_port(struct ib_device *ibdev, u8 port, /* If reported active speed is QDR, check if is FDR-10 */ if (props->active_speed == 4) { - if (gen->ext_port_cap[port - 1] & + if (mdev->port_caps[port - 1].ext_port_cap & MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO) { init_query_mad(in_mad); in_mad->attr_id = MLX5_ATTR_EXTENDED_PORT_INFO; @@ -392,7 +390,6 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, struct mlx5_ib_alloc_ucontext_req_v2 req; struct mlx5_ib_alloc_ucontext_resp resp; struct mlx5_ib_ucontext *context; - struct mlx5_general_caps *gen; struct mlx5_uuar_info *uuari; struct mlx5_uar *uars; int gross_uuars; @@ -403,7 +400,6 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, int i; size_t reqlen; - gen = &dev->mdev->caps.gen; if (!dev->ib_active) return ERR_PTR(-EAGAIN); @@ -436,14 +432,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE; gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE; - resp.qp_tab_size = 1 << gen->log_max_qp; - resp.bf_reg_size = gen->bf_reg_size; - resp.cache_line_size = L1_CACHE_BYTES; - resp.max_sq_desc_sz = gen->max_sq_desc_sz; - resp.max_rq_desc_sz = gen->max_rq_desc_sz; - resp.max_send_wqebb = gen->max_wqes; - resp.max_recv_wr = gen->max_wqes; - resp.max_srq_recv_wr = gen->max_srq_wqes; + resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp); + resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size); + resp.cache_line_size = L1_CACHE_BYTES; + resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq); + resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq); + resp.max_send_wqebb = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz); + resp.max_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz); + resp.max_srq_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz); context = kzalloc(sizeof(*context), GFP_KERNEL); if (!context) @@ -493,7 +489,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, mutex_init(&context->db_page_mutex); resp.tot_uuars = req.total_num_uuars; - resp.num_ports = gen->num_ports; + resp.num_ports = MLX5_CAP_GEN(dev->mdev, num_ports); err = ib_copy_to_udata(udata, &resp, sizeof(resp) - sizeof(resp.reserved)); if (err) @@ -895,11 +891,9 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context, static void get_ext_port_caps(struct mlx5_ib_dev *dev) { - struct mlx5_general_caps *gen; int port; - gen = &dev->mdev->caps.gen; - for (port = 1; port <= gen->num_ports; port++) + for (port = 1; port <= MLX5_CAP_GEN(dev->mdev, num_ports); port++) mlx5_query_ext_port_caps(dev, port); } @@ -907,11 +901,9 @@ static int get_port_caps(struct mlx5_ib_dev *dev) { struct ib_device_attr *dprops = NULL; struct ib_port_attr *pprops = NULL; - struct mlx5_general_caps *gen; int err = -ENOMEM; int port; - gen = &dev->mdev->caps.gen; pprops = kmalloc(sizeof(*pprops), GFP_KERNEL); if (!pprops) goto out; @@ -926,14 +918,17 @@ static int get_port_caps(struct mlx5_ib_dev *dev) goto out; } - for (port = 1; port <= gen->num_ports; port++) { + for (port = 1; port <= MLX5_CAP_GEN(dev->mdev, num_ports); port++) { err = mlx5_ib_query_port(&dev->ib_dev, port, pprops); if (err) { - mlx5_ib_warn(dev, "query_port %d failed %d\n", port, err); + mlx5_ib_warn(dev, "query_port %d failed %d\n", + port, err); break; } - gen->port[port - 1].pkey_table_len = dprops->max_pkeys; - gen->port[port - 1].gid_table_len = pprops->gid_tbl_len; + dev->mdev->port_caps[port - 1].pkey_table_len = + dprops->max_pkeys; + dev->mdev->port_caps[port - 1].gid_table_len = + pprops->gid_tbl_len; mlx5_ib_dbg(dev, "pkey_table_len %d, gid_table_len %d\n", dprops->max_pkeys, pprops->gid_tbl_len); } @@ -1207,8 +1202,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX); dev->ib_dev.owner = THIS_MODULE; dev->ib_dev.node_type = RDMA_NODE_IB_CA; - dev->ib_dev.local_dma_lkey = mdev->caps.gen.reserved_lkey; - dev->num_ports = mdev->caps.gen.num_ports; + dev->ib_dev.local_dma_lkey = 0 /* not supported for now */; + dev->num_ports = MLX5_CAP_GEN(mdev, num_ports); dev->ib_dev.phys_port_cnt = dev->num_ports; dev->ib_dev.num_comp_vectors = dev->mdev->priv.eq_table.num_comp_vectors; @@ -1286,9 +1281,9 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->ib_dev.free_fast_reg_page_list = mlx5_ib_free_fast_reg_page_list; dev->ib_dev.check_mr_status = mlx5_ib_check_mr_status; - mlx5_ib_internal_query_odp_caps(dev); + mlx5_ib_internal_fill_odp_caps(dev); - if (mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_XRC) { + if (MLX5_CAP_GEN(mdev, xrc)) { dev->ib_dev.alloc_xrcd = mlx5_ib_alloc_xrcd; dev->ib_dev.dealloc_xrcd = mlx5_ib_dealloc_xrcd; dev->ib_dev.uverbs_cmd_mask |= diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index dff1cfc..0c441ad 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -617,7 +617,7 @@ int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask, #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING extern struct workqueue_struct *mlx5_ib_page_fault_wq; -int mlx5_ib_internal_query_odp_caps(struct mlx5_ib_dev *dev); +void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev); void mlx5_ib_mr_pfault_handler(struct mlx5_ib_qp *qp, struct mlx5_ib_pfault *pfault); void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp); @@ -631,9 +631,9 @@ void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start, unsigned long end); #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */ -static inline int mlx5_ib_internal_query_odp_caps(struct mlx5_ib_dev *dev) +static inline void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev) { - return 0; + return; } static inline void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp) {} diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 71c5935..bc9a0de 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -975,8 +975,7 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, u64 virt_addr, struct mlx5_ib_mr *mr; int inlen; int err; - bool pg_cap = !!(dev->mdev->caps.gen.flags & - MLX5_DEV_CAP_FLAG_ON_DMND_PG); + bool pg_cap = !!(MLX5_CAP_GEN(dev->mdev, pg)); mr = kzalloc(sizeof(*mr), GFP_KERNEL); if (!mr) diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 5099db0..aa8391e 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -109,40 +109,33 @@ void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start, ib_umem_odp_unmap_dma_pages(umem, start, end); } -#define COPY_ODP_BIT_MLX_TO_IB(reg, ib_caps, field_name, bit_name) do { \ - if (be32_to_cpu(reg.field_name) & MLX5_ODP_SUPPORT_##bit_name) \ - ib_caps->field_name |= IB_ODP_SUPPORT_##bit_name; \ -} while (0) - -int mlx5_ib_internal_query_odp_caps(struct mlx5_ib_dev *dev) +void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev) { - int err; - struct mlx5_odp_caps hw_caps; struct ib_odp_caps *caps = &dev->odp_caps; memset(caps, 0, sizeof(*caps)); - if (!(dev->mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_ON_DMND_PG)) - return 0; - - err = mlx5_query_odp_caps(dev->mdev, &hw_caps); - if (err) - goto out; + if (!MLX5_CAP_GEN(dev->mdev, pg)) + return; caps->general_caps = IB_ODP_SUPPORT; - COPY_ODP_BIT_MLX_TO_IB(hw_caps, caps, per_transport_caps.ud_odp_caps, - SEND); - COPY_ODP_BIT_MLX_TO_IB(hw_caps, caps, per_transport_caps.rc_odp_caps, - SEND); - COPY_ODP_BIT_MLX_TO_IB(hw_caps, caps, per_transport_caps.rc_odp_caps, - RECV); - COPY_ODP_BIT_MLX_TO_IB(hw_caps, caps, per_transport_caps.rc_odp_caps, - WRITE); - COPY_ODP_BIT_MLX_TO_IB(hw_caps, caps, per_transport_caps.rc_odp_caps, - READ); - -out: - return err; + + if (MLX5_CAP_ODP(dev->mdev, ud_odp_caps.send)) + caps->per_transport_caps.ud_odp_caps |= IB_ODP_SUPPORT_SEND; + + if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.send)) + caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_SEND; + + if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.receive)) + caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_RECV; + + if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.write)) + caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_WRITE; + + if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.read)) + caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_READ; + + return; } static struct mlx5_ib_mr *mlx5_ib_odp_find_mr_lkey(struct mlx5_ib_dev *dev, diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index d35f62d..15fd485 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -220,13 +220,11 @@ static void mlx5_ib_qp_event(struct mlx5_core_qp *qp, int type) static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap, int has_rq, struct mlx5_ib_qp *qp, struct mlx5_ib_create_qp *ucmd) { - struct mlx5_general_caps *gen; int wqe_size; int wq_size; - gen = &dev->mdev->caps.gen; /* Sanity check RQ size before proceeding */ - if (cap->max_recv_wr > gen->max_wqes) + if (cap->max_recv_wr > (1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz))) return -EINVAL; if (!has_rq) { @@ -246,10 +244,11 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap, wq_size = roundup_pow_of_two(cap->max_recv_wr) * wqe_size; wq_size = max_t(int, wq_size, MLX5_SEND_WQE_BB); qp->rq.wqe_cnt = wq_size / wqe_size; - if (wqe_size > gen->max_rq_desc_sz) { + if (wqe_size > MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq)) { mlx5_ib_dbg(dev, "wqe_size %d, max %d\n", wqe_size, - gen->max_rq_desc_sz); + MLX5_CAP_GEN(dev->mdev, + max_wqe_sz_rq)); return -EINVAL; } qp->rq.wqe_shift = ilog2(wqe_size); @@ -330,11 +329,9 @@ static int calc_send_wqe(struct ib_qp_init_attr *attr) static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr, struct mlx5_ib_qp *qp) { - struct mlx5_general_caps *gen; int wqe_size; int wq_size; - gen = &dev->mdev->caps.gen; if (!attr->cap.max_send_wr) return 0; @@ -343,9 +340,9 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr, if (wqe_size < 0) return wqe_size; - if (wqe_size > gen->max_sq_desc_sz) { + if (wqe_size > MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq)) { mlx5_ib_dbg(dev, "wqe_size(%d) > max_sq_desc_sz(%d)\n", - wqe_size, gen->max_sq_desc_sz); + wqe_size, MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq)); return -EINVAL; } @@ -358,9 +355,10 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr, wq_size = roundup_pow_of_two(attr->cap.max_send_wr * wqe_size); qp->sq.wqe_cnt = wq_size / MLX5_SEND_WQE_BB; - if (qp->sq.wqe_cnt > gen->max_wqes) { + if (qp->sq.wqe_cnt > (1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz))) { mlx5_ib_dbg(dev, "wqe count(%d) exceeds limits(%d)\n", - qp->sq.wqe_cnt, gen->max_wqes); + qp->sq.wqe_cnt, + 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz)); return -ENOMEM; } qp->sq.wqe_shift = ilog2(MLX5_SEND_WQE_BB); @@ -375,13 +373,11 @@ static int set_user_buf_size(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, struct mlx5_ib_create_qp *ucmd) { - struct mlx5_general_caps *gen; int desc_sz = 1 << qp->sq.wqe_shift; - gen = &dev->mdev->caps.gen; - if (desc_sz > gen->max_sq_desc_sz) { + if (desc_sz > MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq)) { mlx5_ib_warn(dev, "desc_sz %d, max_sq_desc_sz %d\n", - desc_sz, gen->max_sq_desc_sz); + desc_sz, MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq)); return -EINVAL; } @@ -393,9 +389,10 @@ static int set_user_buf_size(struct mlx5_ib_dev *dev, qp->sq.wqe_cnt = ucmd->sq_wqe_count; - if (qp->sq.wqe_cnt > gen->max_wqes) { + if (qp->sq.wqe_cnt > (1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz))) { mlx5_ib_warn(dev, "wqe_cnt %d, max_wqes %d\n", - qp->sq.wqe_cnt, gen->max_wqes); + qp->sq.wqe_cnt, + 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz)); return -EINVAL; } @@ -768,7 +765,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev, qp->sq.offset = qp->rq.wqe_cnt << qp->rq.wqe_shift; qp->buf_size = err + (qp->rq.wqe_cnt << qp->rq.wqe_shift); - err = mlx5_buf_alloc(dev->mdev, qp->buf_size, PAGE_SIZE * 2, &qp->buf); + err = mlx5_buf_alloc(dev->mdev, qp->buf_size, &qp->buf); if (err) { mlx5_ib_dbg(dev, "err %d\n", err); goto err_uuar; @@ -866,22 +863,21 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, struct ib_udata *udata, struct mlx5_ib_qp *qp) { struct mlx5_ib_resources *devr = &dev->devr; + struct mlx5_core_dev *mdev = dev->mdev; struct mlx5_ib_create_qp_resp resp; struct mlx5_create_qp_mbox_in *in; - struct mlx5_general_caps *gen; struct mlx5_ib_create_qp ucmd; int inlen = sizeof(*in); int err; mlx5_ib_odp_create_qp(qp); - gen = &dev->mdev->caps.gen; mutex_init(&qp->mutex); spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK) { - if (!(gen->flags & MLX5_DEV_CAP_FLAG_BLOCK_MCAST)) { + if (!MLX5_CAP_GEN(mdev, block_lb_mc)) { mlx5_ib_dbg(dev, "block multicast loopback isn't supported\n"); return -EINVAL; } else { @@ -914,15 +910,17 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, if (pd) { if (pd->uobject) { + __u32 max_wqes = + 1 << MLX5_CAP_GEN(mdev, log_max_qp_sz); mlx5_ib_dbg(dev, "requested sq_wqe_count (%d)\n", ucmd.sq_wqe_count); if (ucmd.rq_wqe_shift != qp->rq.wqe_shift || ucmd.rq_wqe_count != qp->rq.wqe_cnt) { mlx5_ib_dbg(dev, "invalid rq params\n"); return -EINVAL; } - if (ucmd.sq_wqe_count > gen->max_wqes) { + if (ucmd.sq_wqe_count > max_wqes) { mlx5_ib_dbg(dev, "requested sq_wqe_count (%d) > max allowed (%d)\n", - ucmd.sq_wqe_count, gen->max_wqes); + ucmd.sq_wqe_count, max_wqes); return -EINVAL; } err = create_user_qp(dev, pd, qp, udata, &in, &resp, &inlen); @@ -1226,7 +1224,6 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *init_attr, struct ib_udata *udata) { - struct mlx5_general_caps *gen; struct mlx5_ib_dev *dev; struct mlx5_ib_qp *qp; u16 xrcdn = 0; @@ -1244,12 +1241,11 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd, } dev = to_mdev(to_mxrcd(init_attr->xrcd)->ibxrcd.device); } - gen = &dev->mdev->caps.gen; switch (init_attr->qp_type) { case IB_QPT_XRC_TGT: case IB_QPT_XRC_INI: - if (!(gen->flags & MLX5_DEV_CAP_FLAG_XRC)) { + if (!MLX5_CAP_GEN(dev->mdev, xrc)) { mlx5_ib_dbg(dev, "XRC not supported\n"); return ERR_PTR(-ENOSYS); } @@ -1356,9 +1352,6 @@ enum { static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate) { - struct mlx5_general_caps *gen; - - gen = &dev->mdev->caps.gen; if (rate == IB_RATE_PORT_CURRENT) { return 0; } else if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_300_GBPS) { @@ -1366,7 +1359,7 @@ static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate) } else { while (rate != IB_RATE_2_5_GBPS && !(1 << (rate + MLX5_STAT_RATE_OFFSET) & - gen->stat_rate_support)) + MLX5_CAP_GEN(dev->mdev, stat_rate_support))) --rate; } @@ -1377,10 +1370,8 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, const struct ib_ah_attr *ah, struct mlx5_qp_path *path, u8 port, int attr_mask, u32 path_flags, const struct ib_qp_attr *attr) { - struct mlx5_general_caps *gen; int err; - gen = &dev->mdev->caps.gen; path->fl = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0; path->free_ar = (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x80 : 0; @@ -1391,9 +1382,11 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, const struct ib_ah_attr *ah, path->rlid = cpu_to_be16(ah->dlid); if (ah->ah_flags & IB_AH_GRH) { - if (ah->grh.sgid_index >= gen->port[port - 1].gid_table_len) { + if (ah->grh.sgid_index >= + dev->mdev->port_caps[port - 1].gid_table_len) { pr_err("sgid_index (%u) too large. max is %d\n", - ah->grh.sgid_index, gen->port[port - 1].gid_table_len); + ah->grh.sgid_index, + dev->mdev->port_caps[port - 1].gid_table_len); return -EINVAL; } path->grh_mlid |= 1 << 7; @@ -1570,7 +1563,6 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, struct mlx5_ib_qp *qp = to_mqp(ibqp); struct mlx5_ib_cq *send_cq, *recv_cq; struct mlx5_qp_context *context; - struct mlx5_general_caps *gen; struct mlx5_modify_qp_mbox_in *in; struct mlx5_ib_pd *pd; enum mlx5_qp_state mlx5_cur, mlx5_new; @@ -1579,7 +1571,6 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, int mlx5_st; int err; - gen = &dev->mdev->caps.gen; in = kzalloc(sizeof(*in), GFP_KERNEL); if (!in) return -ENOMEM; @@ -1619,7 +1610,8 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, err = -EINVAL; goto out; } - context->mtu_msgmax = (attr->path_mtu << 5) | gen->log_max_msg; + context->mtu_msgmax = (attr->path_mtu << 5) | + (u8)MLX5_CAP_GEN(dev->mdev, log_max_msg); } if (attr_mask & IB_QP_DEST_QPN) @@ -1777,11 +1769,9 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, struct mlx5_ib_dev *dev = to_mdev(ibqp->device); struct mlx5_ib_qp *qp = to_mqp(ibqp); enum ib_qp_state cur_state, new_state; - struct mlx5_general_caps *gen; int err = -EINVAL; int port; - gen = &dev->mdev->caps.gen; mutex_lock(&qp->mutex); cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state; @@ -1793,21 +1783,25 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, goto out; if ((attr_mask & IB_QP_PORT) && - (attr->port_num == 0 || attr->port_num > gen->num_ports)) + (attr->port_num == 0 || + attr->port_num > MLX5_CAP_GEN(dev->mdev, num_ports))) goto out; if (attr_mask & IB_QP_PKEY_INDEX) { port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port; - if (attr->pkey_index >= gen->port[port - 1].pkey_table_len) + if (attr->pkey_index >= + dev->mdev->port_caps[port - 1].pkey_table_len) goto out; } if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC && - attr->max_rd_atomic > (1 << gen->log_max_ra_res_qp)) + attr->max_rd_atomic > + (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_res_qp))) goto out; if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC && - attr->max_dest_rd_atomic > (1 << gen->log_max_ra_req_qp)) + attr->max_dest_rd_atomic > + (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_req_qp))) goto out; if (cur_state == new_state && cur_state == IB_QPS_RESET) { @@ -3009,7 +3003,7 @@ static void to_ib_ah_attr(struct mlx5_ib_dev *ibdev, struct ib_ah_attr *ib_ah_at ib_ah_attr->port_num = path->port; if (ib_ah_attr->port_num == 0 || - ib_ah_attr->port_num > dev->caps.gen.num_ports) + ib_ah_attr->port_num > MLX5_CAP_GEN(dev, num_ports)) return; ib_ah_attr->sl = path->sl & 0xf; @@ -3135,12 +3129,10 @@ struct ib_xrcd *mlx5_ib_alloc_xrcd(struct ib_device *ibdev, struct ib_udata *udata) { struct mlx5_ib_dev *dev = to_mdev(ibdev); - struct mlx5_general_caps *gen; struct mlx5_ib_xrcd *xrcd; int err; - gen = &dev->mdev->caps.gen; - if (!(gen->flags & MLX5_DEV_CAP_FLAG_XRC)) + if (!MLX5_CAP_GEN(dev->mdev, xrc)) return ERR_PTR(-ENOSYS); xrcd = kmalloc(sizeof(*xrcd), GFP_KERNEL); diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 02d77a2..e8e8e94 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -165,7 +165,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, return err; } - if (mlx5_buf_alloc(dev->mdev, buf_size, PAGE_SIZE * 2, &srq->buf)) { + if (mlx5_buf_alloc(dev->mdev, buf_size, &srq->buf)) { mlx5_ib_dbg(dev, "buf alloc failed\n"); err = -ENOMEM; goto err_db; @@ -236,7 +236,6 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, struct ib_udata *udata) { struct mlx5_ib_dev *dev = to_mdev(pd->device); - struct mlx5_general_caps *gen; struct mlx5_ib_srq *srq; int desc_size; int buf_size; @@ -245,13 +244,13 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, int uninitialized_var(inlen); int is_xrc; u32 flgs, xrcdn; + __u32 max_srq_wqes = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz); - gen = &dev->mdev->caps.gen; /* Sanity check SRQ size before proceeding */ - if (init_attr->attr.max_wr >= gen->max_srq_wqes) { + if (init_attr->attr.max_wr >= max_srq_wqes) { mlx5_ib_dbg(dev, "max_wr %d, cap %d\n", init_attr->attr.max_wr, - gen->max_srq_wqes); + max_srq_wqes); return ERR_PTR(-EINVAL); } diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 327529e..3f40319 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -547,11 +547,11 @@ isert_create_pi_ctx(struct fast_reg_descriptor *desc, return 0; err_prot_mr: - ib_dereg_mr(desc->pi_ctx->prot_mr); + ib_dereg_mr(pi_ctx->prot_mr); err_prot_frpl: - ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl); + ib_free_fast_reg_page_list(pi_ctx->prot_frpl); err_pi_ctx: - kfree(desc->pi_ctx); + kfree(pi_ctx); return ret; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 9687f8a..1b7e155 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -828,7 +828,14 @@ static int its_alloc_tables(struct its_node *its) u64 typer = readq_relaxed(its->base + GITS_TYPER); u32 ids = GITS_TYPER_DEVBITS(typer); - order = get_order((1UL << ids) * entry_size); + /* + * 'order' was initialized earlier to the default page + * granule of the the ITS. We can't have an allocation + * smaller than that. If the requested allocation + * is smaller, round up to the default page granule. + */ + order = max(get_order((1UL << ids) * entry_size), + order); if (order >= MAX_ORDER) { order = MAX_ORDER - 1; pr_warn("%s: Device Table too large, reduce its page order to %u\n", diff --git a/drivers/isdn/capi/capidrv.c b/drivers/isdn/capi/capidrv.c index 1cc6ca8..85cfa4f 100644 --- a/drivers/isdn/capi/capidrv.c +++ b/drivers/isdn/capi/capidrv.c @@ -2264,7 +2264,7 @@ static int capidrv_addcontr(u16 contr, struct capi_profile *profp) return -1; } card->owner = THIS_MODULE; - init_timer(&card->listentimer); + setup_timer(&card->listentimer, listentimerfunc, (unsigned long)card); strcpy(card->name, id); card->contrnr = contr; card->nbchan = profp->nbchannel; @@ -2331,8 +2331,6 @@ static int capidrv_addcontr(u16 contr, struct capi_profile *profp) card->cipmask = 0x1FFF03FF; /* any */ card->cipmask2 = 0; - card->listentimer.data = (unsigned long)card; - card->listentimer.function = listentimerfunc; send_listen(card); mod_timer(&card->listentimer, jiffies + 60 * HZ); diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c index 7dc93aa..312ffd3 100644 --- a/drivers/lguest/core.c +++ b/drivers/lguest/core.c @@ -173,7 +173,7 @@ static void unmap_switcher(void) bool lguest_address_ok(const struct lguest *lg, unsigned long addr, unsigned long len) { - return (addr+len) / PAGE_SIZE < lg->pfn_limit && (addr+len >= addr); + return addr+len <= lg->pfn_limit * PAGE_SIZE && (addr+len >= addr); } /* diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 6395347..eff7bdd 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -429,9 +429,11 @@ static int __multipath_map(struct dm_target *ti, struct request *clone, /* blk-mq request-based interface */ *__clone = blk_get_request(bdev_get_queue(bdev), rq_data_dir(rq), GFP_ATOMIC); - if (IS_ERR(*__clone)) + if (IS_ERR(*__clone)) { /* ENOMEM, requeue */ + clear_mapinfo(m, map_context); return r; + } (*__clone)->bio = (*__clone)->biotail = NULL; (*__clone)->rq_disk = bdev->bd_disk; (*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index d9b00b8..16ba55a 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -820,6 +820,12 @@ void dm_consume_args(struct dm_arg_set *as, unsigned num_args) } EXPORT_SYMBOL(dm_consume_args); +static bool __table_type_request_based(unsigned table_type) +{ + return (table_type == DM_TYPE_REQUEST_BASED || + table_type == DM_TYPE_MQ_REQUEST_BASED); +} + static int dm_table_set_type(struct dm_table *t) { unsigned i; @@ -852,8 +858,7 @@ static int dm_table_set_type(struct dm_table *t) * Determine the type from the live device. * Default to bio-based if device is new. */ - if (live_md_type == DM_TYPE_REQUEST_BASED || - live_md_type == DM_TYPE_MQ_REQUEST_BASED) + if (__table_type_request_based(live_md_type)) request_based = 1; else bio_based = 1; @@ -903,7 +908,7 @@ static int dm_table_set_type(struct dm_table *t) } t->type = DM_TYPE_MQ_REQUEST_BASED; - } else if (hybrid && list_empty(devices) && live_md_type != DM_TYPE_NONE) { + } else if (list_empty(devices) && __table_type_request_based(live_md_type)) { /* inherit live MD type */ t->type = live_md_type; @@ -925,10 +930,7 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t) bool dm_table_request_based(struct dm_table *t) { - unsigned table_type = dm_table_get_type(t); - - return (table_type == DM_TYPE_REQUEST_BASED || - table_type == DM_TYPE_MQ_REQUEST_BASED); + return __table_type_request_based(dm_table_get_type(t)); } bool dm_table_mq_request_based(struct dm_table *t) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index a930b72..2caf492 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1082,13 +1082,11 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue) dm_put(md); } -static void free_rq_clone(struct request *clone, bool must_be_mapped) +static void free_rq_clone(struct request *clone) { struct dm_rq_target_io *tio = clone->end_io_data; struct mapped_device *md = tio->md; - WARN_ON_ONCE(must_be_mapped && !clone->q); - blk_rq_unprep_clone(clone); if (md->type == DM_TYPE_MQ_REQUEST_BASED) @@ -1132,7 +1130,7 @@ static void dm_end_request(struct request *clone, int error) rq->sense_len = clone->sense_len; } - free_rq_clone(clone, true); + free_rq_clone(clone); if (!rq->q->mq_ops) blk_end_request_all(rq, error); else @@ -1151,7 +1149,7 @@ static void dm_unprep_request(struct request *rq) } if (clone) - free_rq_clone(clone, false); + free_rq_clone(clone); } /* @@ -1164,6 +1162,7 @@ static void old_requeue_request(struct request *rq) spin_lock_irqsave(q->queue_lock, flags); blk_requeue_request(q, rq); + blk_run_queue_async(q); spin_unlock_irqrestore(q->queue_lock, flags); } @@ -1724,8 +1723,7 @@ static int dm_merge_bvec(struct request_queue *q, struct mapped_device *md = q->queuedata; struct dm_table *map = dm_get_live_table_fast(md); struct dm_target *ti; - sector_t max_sectors; - int max_size = 0; + sector_t max_sectors, max_size = 0; if (unlikely(!map)) goto out; @@ -1740,8 +1738,16 @@ static int dm_merge_bvec(struct request_queue *q, max_sectors = min(max_io_len(bvm->bi_sector, ti), (sector_t) queue_max_sectors(q)); max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size; - if (unlikely(max_size < 0)) /* this shouldn't _ever_ happen */ - max_size = 0; + + /* + * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t + * to the targets' merge function since it holds sectors not bytes). + * Just doing this as an interim fix for stable@ because the more + * comprehensive cleanup of switching to sector_t will impact every + * DM target that implements a ->merge hook. + */ + if (max_size > INT_MAX) + max_size = INT_MAX; /* * merge_bvec_fn() returns number of bytes @@ -1749,7 +1755,7 @@ static int dm_merge_bvec(struct request_queue *q, * max is precomputed maximal io size */ if (max_size && ti->type->merge) - max_size = ti->type->merge(ti, bvm, biovec, max_size); + max_size = ti->type->merge(ti, bvm, biovec, (int) max_size); /* * If the target doesn't support merge method and some of the devices * provided their merge_bvec method (we know this by looking for the @@ -1971,8 +1977,8 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq, dm_kill_unmapped_request(rq, r); return r; } - if (IS_ERR(clone)) - return DM_MAPIO_REQUEUE; + if (r != DM_MAPIO_REMAPPED) + return r; if (setup_clone(clone, rq, tio, GFP_ATOMIC)) { /* -ENOMEM */ ti->type->release_clone_rq(clone); @@ -2753,13 +2759,15 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, if (dm_table_get_type(map) == DM_TYPE_REQUEST_BASED) { /* clone request is allocated at the end of the pdu */ tio->clone = (void *)blk_mq_rq_to_pdu(rq) + sizeof(struct dm_rq_target_io); - if (!clone_rq(rq, md, tio, GFP_ATOMIC)) - return BLK_MQ_RQ_QUEUE_BUSY; + (void) clone_rq(rq, md, tio, GFP_ATOMIC); queue_kthread_work(&md->kworker, &tio->work); } else { /* Direct call is fine since .queue_rq allows allocations */ - if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) - dm_requeue_unmapped_original_request(md, rq); + if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) { + /* Undo dm_start_request() before requeuing */ + rq_completed(md, rq_data_dir(rq), false); + return BLK_MQ_RQ_QUEUE_BUSY; + } } return BLK_MQ_RQ_QUEUE_OK; diff --git a/drivers/md/md.c b/drivers/md/md.c index 593a024..2750630 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4211,12 +4211,12 @@ action_store(struct mddev *mddev, const char *page, size_t len) if (!mddev->pers || !mddev->pers->sync_request) return -EINVAL; - if (cmd_match(page, "frozen")) - set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - else - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); if (cmd_match(page, "idle") || cmd_match(page, "frozen")) { + if (cmd_match(page, "frozen")) + set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + else + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); flush_workqueue(md_misc_wq); if (mddev->sync_thread) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); @@ -4229,16 +4229,17 @@ action_store(struct mddev *mddev, const char *page, size_t len) test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) return -EBUSY; else if (cmd_match(page, "resync")) - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); else if (cmd_match(page, "recover")) { + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } else if (cmd_match(page, "reshape")) { int err; if (mddev->pers->start_reshape == NULL) return -EINVAL; err = mddev_lock(mddev); if (!err) { + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); err = mddev->pers->start_reshape(mddev); mddev_unlock(mddev); } @@ -4250,6 +4251,7 @@ action_store(struct mddev *mddev, const char *page, size_t len) set_bit(MD_RECOVERY_CHECK, &mddev->recovery); else if (!cmd_match(page, "repair")) return -EINVAL; + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); set_bit(MD_RECOVERY_SYNC, &mddev->recovery); } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index b9f2b9c..553d54b 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -749,6 +749,7 @@ static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) static bool stripe_can_batch(struct stripe_head *sh) { return test_bit(STRIPE_BATCH_READY, &sh->state) && + !test_bit(STRIPE_BITMAP_PENDING, &sh->state) && is_full_stripe_write(sh); } @@ -837,6 +838,15 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh < IO_THRESHOLD) md_wakeup_thread(conf->mddev->thread); + if (test_and_clear_bit(STRIPE_BIT_DELAY, &sh->state)) { + int seq = sh->bm_seq; + if (test_bit(STRIPE_BIT_DELAY, &sh->batch_head->state) && + sh->batch_head->bm_seq > seq) + seq = sh->batch_head->bm_seq; + set_bit(STRIPE_BIT_DELAY, &sh->batch_head->state); + sh->batch_head->bm_seq = seq; + } + atomic_inc(&sh->count); unlock_out: unlock_two_stripes(head, sh); @@ -2987,14 +2997,32 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n", (unsigned long long)(*bip)->bi_iter.bi_sector, (unsigned long long)sh->sector, dd_idx); - spin_unlock_irq(&sh->stripe_lock); if (conf->mddev->bitmap && firstwrite) { + /* Cannot hold spinlock over bitmap_startwrite, + * but must ensure this isn't added to a batch until + * we have added to the bitmap and set bm_seq. + * So set STRIPE_BITMAP_PENDING to prevent + * batching. + * If multiple add_stripe_bio() calls race here they + * much all set STRIPE_BITMAP_PENDING. So only the first one + * to complete "bitmap_startwrite" gets to set + * STRIPE_BIT_DELAY. This is important as once a stripe + * is added to a batch, STRIPE_BIT_DELAY cannot be changed + * any more. + */ + set_bit(STRIPE_BITMAP_PENDING, &sh->state); + spin_unlock_irq(&sh->stripe_lock); bitmap_startwrite(conf->mddev->bitmap, sh->sector, STRIPE_SECTORS, 0); - sh->bm_seq = conf->seq_flush+1; - set_bit(STRIPE_BIT_DELAY, &sh->state); + spin_lock_irq(&sh->stripe_lock); + clear_bit(STRIPE_BITMAP_PENDING, &sh->state); + if (!sh->batch_head) { + sh->bm_seq = conf->seq_flush+1; + set_bit(STRIPE_BIT_DELAY, &sh->state); + } } + spin_unlock_irq(&sh->stripe_lock); if (stripe_can_batch(sh)) stripe_add_to_batch_list(conf, sh); @@ -3392,6 +3420,8 @@ static void handle_stripe_fill(struct stripe_head *sh, set_bit(STRIPE_HANDLE, &sh->state); } +static void break_stripe_batch_list(struct stripe_head *head_sh, + unsigned long handle_flags); /* handle_stripe_clean_event * any written block on an uptodate or failed drive can be returned. * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but @@ -3405,7 +3435,6 @@ static void handle_stripe_clean_event(struct r5conf *conf, int discard_pending = 0; struct stripe_head *head_sh = sh; bool do_endio = false; - int wakeup_nr = 0; for (i = disks; i--; ) if (sh->dev[i].written) { @@ -3494,44 +3523,8 @@ unhash: if (atomic_dec_and_test(&conf->pending_full_writes)) md_wakeup_thread(conf->mddev->thread); - if (!head_sh->batch_head || !do_endio) - return; - for (i = 0; i < head_sh->disks; i++) { - if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags)) - wakeup_nr++; - } - while (!list_empty(&head_sh->batch_list)) { - int i; - sh = list_first_entry(&head_sh->batch_list, - struct stripe_head, batch_list); - list_del_init(&sh->batch_list); - - set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG, - head_sh->state & ~((1 << STRIPE_ACTIVE) | - (1 << STRIPE_PREREAD_ACTIVE) | - STRIPE_EXPAND_SYNC_FLAG)); - sh->check_state = head_sh->check_state; - sh->reconstruct_state = head_sh->reconstruct_state; - for (i = 0; i < sh->disks; i++) { - if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) - wakeup_nr++; - sh->dev[i].flags = head_sh->dev[i].flags; - } - - spin_lock_irq(&sh->stripe_lock); - sh->batch_head = NULL; - spin_unlock_irq(&sh->stripe_lock); - if (sh->state & STRIPE_EXPAND_SYNC_FLAG) - set_bit(STRIPE_HANDLE, &sh->state); - release_stripe(sh); - } - - spin_lock_irq(&head_sh->stripe_lock); - head_sh->batch_head = NULL; - spin_unlock_irq(&head_sh->stripe_lock); - wake_up_nr(&conf->wait_for_overlap, wakeup_nr); - if (head_sh->state & STRIPE_EXPAND_SYNC_FLAG) - set_bit(STRIPE_HANDLE, &head_sh->state); + if (head_sh->batch_head && do_endio) + break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS); } static void handle_stripe_dirtying(struct r5conf *conf, @@ -4172,9 +4165,13 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) static int clear_batch_ready(struct stripe_head *sh) { + /* Return '1' if this is a member of batch, or + * '0' if it is a lone stripe or a head which can now be + * handled. + */ struct stripe_head *tmp; if (!test_and_clear_bit(STRIPE_BATCH_READY, &sh->state)) - return 0; + return (sh->batch_head && sh->batch_head != sh); spin_lock(&sh->stripe_lock); if (!sh->batch_head) { spin_unlock(&sh->stripe_lock); @@ -4202,38 +4199,65 @@ static int clear_batch_ready(struct stripe_head *sh) return 0; } -static void check_break_stripe_batch_list(struct stripe_head *sh) +static void break_stripe_batch_list(struct stripe_head *head_sh, + unsigned long handle_flags) { - struct stripe_head *head_sh, *next; + struct stripe_head *sh, *next; int i; - - if (!test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state)) - return; - - head_sh = sh; + int do_wakeup = 0; list_for_each_entry_safe(sh, next, &head_sh->batch_list, batch_list) { list_del_init(&sh->batch_list); - set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG, - head_sh->state & ~((1 << STRIPE_ACTIVE) | - (1 << STRIPE_PREREAD_ACTIVE) | - (1 << STRIPE_DEGRADED) | - STRIPE_EXPAND_SYNC_FLAG)); + WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) | + (1 << STRIPE_SYNCING) | + (1 << STRIPE_REPLACED) | + (1 << STRIPE_PREREAD_ACTIVE) | + (1 << STRIPE_DELAYED) | + (1 << STRIPE_BIT_DELAY) | + (1 << STRIPE_FULL_WRITE) | + (1 << STRIPE_BIOFILL_RUN) | + (1 << STRIPE_COMPUTE_RUN) | + (1 << STRIPE_OPS_REQ_PENDING) | + (1 << STRIPE_DISCARD) | + (1 << STRIPE_BATCH_READY) | + (1 << STRIPE_BATCH_ERR) | + (1 << STRIPE_BITMAP_PENDING))); + WARN_ON_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) | + (1 << STRIPE_REPLACED))); + + set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS | + (1 << STRIPE_DEGRADED)), + head_sh->state & (1 << STRIPE_INSYNC)); + sh->check_state = head_sh->check_state; sh->reconstruct_state = head_sh->reconstruct_state; - for (i = 0; i < sh->disks; i++) + for (i = 0; i < sh->disks; i++) { + if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) + do_wakeup = 1; sh->dev[i].flags = head_sh->dev[i].flags & (~((1 << R5_WriteError) | (1 << R5_Overlap))); - + } spin_lock_irq(&sh->stripe_lock); sh->batch_head = NULL; spin_unlock_irq(&sh->stripe_lock); - - set_bit(STRIPE_HANDLE, &sh->state); + if (handle_flags == 0 || + sh->state & handle_flags) + set_bit(STRIPE_HANDLE, &sh->state); release_stripe(sh); } + spin_lock_irq(&head_sh->stripe_lock); + head_sh->batch_head = NULL; + spin_unlock_irq(&head_sh->stripe_lock); + for (i = 0; i < head_sh->disks; i++) + if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags)) + do_wakeup = 1; + if (head_sh->state & handle_flags) + set_bit(STRIPE_HANDLE, &head_sh->state); + + if (do_wakeup) + wake_up(&head_sh->raid_conf->wait_for_overlap); } static void handle_stripe(struct stripe_head *sh) @@ -4258,7 +4282,8 @@ static void handle_stripe(struct stripe_head *sh) return; } - check_break_stripe_batch_list(sh); + if (test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state)) + break_stripe_batch_list(sh, 0); if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) { spin_lock(&sh->stripe_lock); @@ -4312,6 +4337,7 @@ static void handle_stripe(struct stripe_head *sh) if (s.failed > conf->max_degraded) { sh->check_state = 0; sh->reconstruct_state = 0; + break_stripe_batch_list(sh, 0); if (s.to_read+s.to_write+s.written) handle_failed_stripe(conf, sh, &s, disks, &s.return_bi); if (s.syncing + s.replacing) diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 7dc0dd8..896d603 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -337,9 +337,12 @@ enum { STRIPE_ON_RELEASE_LIST, STRIPE_BATCH_READY, STRIPE_BATCH_ERR, + STRIPE_BITMAP_PENDING, /* Being added to bitmap, don't add + * to batch yet. + */ }; -#define STRIPE_EXPAND_SYNC_FLAG \ +#define STRIPE_EXPAND_SYNC_FLAGS \ ((1 << STRIPE_EXPAND_SOURCE) |\ (1 << STRIPE_EXPAND_READY) |\ (1 << STRIPE_EXPANDING) |\ diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c index ae498b5..46e3840 100644 --- a/drivers/mfd/da9052-core.c +++ b/drivers/mfd/da9052-core.c @@ -433,6 +433,10 @@ EXPORT_SYMBOL_GPL(da9052_adc_read_temp); static const struct mfd_cell da9052_subdev_info[] = { { .name = "da9052-regulator", + .id = 0, + }, + { + .name = "da9052-regulator", .id = 1, }, { @@ -484,10 +488,6 @@ static const struct mfd_cell da9052_subdev_info[] = { .id = 13, }, { - .name = "da9052-regulator", - .id = 14, - }, - { .name = "da9052-onkey", }, { diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index eadcb05..9a83085 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -34,6 +34,7 @@ source "drivers/net/ethernet/adi/Kconfig" source "drivers/net/ethernet/broadcom/Kconfig" source "drivers/net/ethernet/brocade/Kconfig" source "drivers/net/ethernet/calxeda/Kconfig" +source "drivers/net/ethernet/cavium/Kconfig" source "drivers/net/ethernet/chelsio/Kconfig" source "drivers/net/ethernet/cirrus/Kconfig" source "drivers/net/ethernet/cisco/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 1367afc..4395d99 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_NET_BFIN) += adi/ obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/ obj-$(CONFIG_NET_VENDOR_BROCADE) += brocade/ obj-$(CONFIG_NET_CALXEDA_XGMAC) += calxeda/ +obj-$(CONFIG_NET_VENDOR_CAVIUM) += cavium/ obj-$(CONFIG_NET_VENDOR_CHELSIO) += chelsio/ obj-$(CONFIG_NET_VENDOR_CIRRUS) += cirrus/ obj-$(CONFIG_NET_VENDOR_CISCO) += cisco/ diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 084a50a..909ad7a 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -524,67 +524,70 @@ static void bcm_sysport_free_cb(struct bcm_sysport_cb *cb) dma_unmap_addr_set(cb, dma_addr, 0); } -static int bcm_sysport_rx_refill(struct bcm_sysport_priv *priv, - struct bcm_sysport_cb *cb) +static struct sk_buff *bcm_sysport_rx_refill(struct bcm_sysport_priv *priv, + struct bcm_sysport_cb *cb) { struct device *kdev = &priv->pdev->dev; struct net_device *ndev = priv->netdev; + struct sk_buff *skb, *rx_skb; dma_addr_t mapping; - int ret; - cb->skb = netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH); - if (!cb->skb) { + /* Allocate a new SKB for a new packet */ + skb = netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH); + if (!skb) { + priv->mib.alloc_rx_buff_failed++; netif_err(priv, rx_err, ndev, "SKB alloc failed\n"); - return -ENOMEM; + return NULL; } - mapping = dma_map_single(kdev, cb->skb->data, + mapping = dma_map_single(kdev, skb->data, RX_BUF_LENGTH, DMA_FROM_DEVICE); - ret = dma_mapping_error(kdev, mapping); - if (ret) { + if (dma_mapping_error(kdev, mapping)) { priv->mib.rx_dma_failed++; - bcm_sysport_free_cb(cb); + dev_kfree_skb_any(skb); netif_err(priv, rx_err, ndev, "DMA mapping failure\n"); - return ret; + return NULL; } - dma_unmap_addr_set(cb, dma_addr, mapping); - dma_desc_set_addr(priv, priv->rx_bd_assign_ptr, mapping); + /* Grab the current SKB on the ring */ + rx_skb = cb->skb; + if (likely(rx_skb)) + dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr), + RX_BUF_LENGTH, DMA_FROM_DEVICE); - priv->rx_bd_assign_index++; - priv->rx_bd_assign_index &= (priv->num_rx_bds - 1); - priv->rx_bd_assign_ptr = priv->rx_bds + - (priv->rx_bd_assign_index * DESC_SIZE); + /* Put the new SKB on the ring */ + cb->skb = skb; + dma_unmap_addr_set(cb, dma_addr, mapping); + dma_desc_set_addr(priv, cb->bd_addr, mapping); netif_dbg(priv, rx_status, ndev, "RX refill\n"); - return 0; + /* Return the current SKB to the caller */ + return rx_skb; } static int bcm_sysport_alloc_rx_bufs(struct bcm_sysport_priv *priv) { struct bcm_sysport_cb *cb; - int ret = 0; + struct sk_buff *skb; unsigned int i; for (i = 0; i < priv->num_rx_bds; i++) { - cb = &priv->rx_cbs[priv->rx_bd_assign_index]; - if (cb->skb) - continue; - - ret = bcm_sysport_rx_refill(priv, cb); - if (ret) - break; + cb = &priv->rx_cbs[i]; + skb = bcm_sysport_rx_refill(priv, cb); + if (skb) + dev_kfree_skb(skb); + if (!cb->skb) + return -ENOMEM; } - return ret; + return 0; } /* Poll the hardware for up to budget packets to process */ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv, unsigned int budget) { - struct device *kdev = &priv->pdev->dev; struct net_device *ndev = priv->netdev; unsigned int processed = 0, to_process; struct bcm_sysport_cb *cb; @@ -592,7 +595,6 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv, unsigned int p_index; u16 len, status; struct bcm_rsb *rsb; - int ret; /* Determine how much we should process since last call */ p_index = rdma_readl(priv, RDMA_PROD_INDEX); @@ -610,13 +612,8 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv, while ((processed < to_process) && (processed < budget)) { cb = &priv->rx_cbs[priv->rx_read_ptr]; - skb = cb->skb; + skb = bcm_sysport_rx_refill(priv, cb); - processed++; - priv->rx_read_ptr++; - - if (priv->rx_read_ptr == priv->num_rx_bds) - priv->rx_read_ptr = 0; /* We do not have a backing SKB, so we do not a corresponding * DMA mapping for this incoming packet since @@ -627,12 +624,9 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv, netif_err(priv, rx_err, ndev, "out of memory!\n"); ndev->stats.rx_dropped++; ndev->stats.rx_errors++; - goto refill; + goto next; } - dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr), - RX_BUF_LENGTH, DMA_FROM_DEVICE); - /* Extract the Receive Status Block prepended */ rsb = (struct bcm_rsb *)skb->data; len = (rsb->rx_status_len >> DESC_LEN_SHIFT) & DESC_LEN_MASK; @@ -644,12 +638,20 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv, p_index, priv->rx_c_index, priv->rx_read_ptr, len, status); + if (unlikely(len > RX_BUF_LENGTH)) { + netif_err(priv, rx_status, ndev, "oversized packet\n"); + ndev->stats.rx_length_errors++; + ndev->stats.rx_errors++; + dev_kfree_skb_any(skb); + goto next; + } + if (unlikely(!(status & DESC_EOP) || !(status & DESC_SOP))) { netif_err(priv, rx_status, ndev, "fragmented packet!\n"); ndev->stats.rx_dropped++; ndev->stats.rx_errors++; - bcm_sysport_free_cb(cb); - goto refill; + dev_kfree_skb_any(skb); + goto next; } if (unlikely(status & (RX_STATUS_ERR | RX_STATUS_OVFLOW))) { @@ -658,8 +660,8 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv, ndev->stats.rx_over_errors++; ndev->stats.rx_dropped++; ndev->stats.rx_errors++; - bcm_sysport_free_cb(cb); - goto refill; + dev_kfree_skb_any(skb); + goto next; } skb_put(skb, len); @@ -686,10 +688,12 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv, ndev->stats.rx_bytes += len; napi_gro_receive(&priv->napi, skb); -refill: - ret = bcm_sysport_rx_refill(priv, cb); - if (ret) - priv->mib.alloc_rx_buff_failed++; +next: + processed++; + priv->rx_read_ptr++; + + if (priv->rx_read_ptr == priv->num_rx_bds) + priv->rx_read_ptr = 0; } return processed; @@ -1330,14 +1334,14 @@ static inline int tdma_enable_set(struct bcm_sysport_priv *priv, static int bcm_sysport_init_rx_ring(struct bcm_sysport_priv *priv) { + struct bcm_sysport_cb *cb; u32 reg; int ret; + int i; /* Initialize SW view of the RX ring */ priv->num_rx_bds = NUM_RX_DESC; priv->rx_bds = priv->base + SYS_PORT_RDMA_OFFSET; - priv->rx_bd_assign_ptr = priv->rx_bds; - priv->rx_bd_assign_index = 0; priv->rx_c_index = 0; priv->rx_read_ptr = 0; priv->rx_cbs = kcalloc(priv->num_rx_bds, sizeof(struct bcm_sysport_cb), @@ -1347,6 +1351,11 @@ static int bcm_sysport_init_rx_ring(struct bcm_sysport_priv *priv) return -ENOMEM; } + for (i = 0; i < priv->num_rx_bds; i++) { + cb = priv->rx_cbs + i; + cb->bd_addr = priv->rx_bds + i * DESC_SIZE; + } + ret = bcm_sysport_alloc_rx_bufs(priv); if (ret) { netif_err(priv, hw, priv->netdev, "SKB allocation failed\n"); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 42a4b4a..f28bf54 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -663,8 +663,6 @@ struct bcm_sysport_priv { /* Receive queue */ void __iomem *rx_bds; - void __iomem *rx_bd_assign_ptr; - unsigned int rx_bd_assign_index; struct bcm_sysport_cb *rx_cbs; unsigned int num_rx_bds; unsigned int rx_read_ptr; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index a3b0f7a..7a4aaa3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -357,6 +357,7 @@ struct sw_tx_bd { struct sw_rx_page { struct page *page; DEFINE_DMA_UNMAP_ADDR(mapping); + unsigned int offset; }; union db_prod { @@ -381,9 +382,10 @@ union db_prod { #define PAGES_PER_SGE_SHIFT 0 #define PAGES_PER_SGE (1 << PAGES_PER_SGE_SHIFT) -#define SGE_PAGE_SIZE PAGE_SIZE -#define SGE_PAGE_SHIFT PAGE_SHIFT -#define SGE_PAGE_ALIGN(addr) PAGE_ALIGN((typeof(PAGE_SIZE))(addr)) +#define SGE_PAGE_SHIFT 12 +#define SGE_PAGE_SIZE (1 << SGE_PAGE_SHIFT) +#define SGE_PAGE_MASK (~(SGE_PAGE_SIZE - 1)) +#define SGE_PAGE_ALIGN(addr) (((addr) + SGE_PAGE_SIZE - 1) & SGE_PAGE_MASK) #define SGE_PAGES (SGE_PAGE_SIZE * PAGES_PER_SGE) #define TPA_AGG_SIZE min_t(u32, (min_t(u32, 8, MAX_SKB_FRAGS) * \ SGE_PAGES), 0xffff) @@ -526,6 +528,12 @@ enum bnx2x_tpa_mode_t { TPA_MODE_GRO }; +struct bnx2x_alloc_pool { + struct page *page; + dma_addr_t dma; + unsigned int offset; +}; + struct bnx2x_fastpath { struct bnx2x *bp; /* parent */ @@ -599,6 +607,8 @@ struct bnx2x_fastpath { 4 (for the digits and to make it DWORD aligned) */ #define FP_NAME_SIZE (sizeof(((struct net_device *)0)->name) + 8) char name[FP_NAME_SIZE]; + + struct bnx2x_alloc_pool page_pool; }; #define bnx2x_fp(bp, nr, var) ((bp)->fp[(nr)].var) @@ -1774,7 +1784,7 @@ struct bnx2x { int stats_state; /* used for synchronization of concurrent threads statistics handling */ - struct mutex stats_lock; + struct semaphore stats_lock; /* used by dmae command loader */ struct dmae_command stats_dmae; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 2ef202d..e2a6533 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -544,30 +544,49 @@ static void bnx2x_set_gro_params(struct sk_buff *skb, u16 parsing_flags, static int bnx2x_alloc_rx_sge(struct bnx2x *bp, struct bnx2x_fastpath *fp, u16 index, gfp_t gfp_mask) { - struct page *page = alloc_pages(gfp_mask, PAGES_PER_SGE_SHIFT); struct sw_rx_page *sw_buf = &fp->rx_page_ring[index]; struct eth_rx_sge *sge = &fp->rx_sge_ring[index]; + struct bnx2x_alloc_pool *pool = &fp->page_pool; dma_addr_t mapping; - if (unlikely(page == NULL)) { - BNX2X_ERR("Can't alloc sge\n"); - return -ENOMEM; - } + if (!pool->page || (PAGE_SIZE - pool->offset) < SGE_PAGE_SIZE) { - mapping = dma_map_page(&bp->pdev->dev, page, 0, - SGE_PAGES, DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) { - __free_pages(page, PAGES_PER_SGE_SHIFT); - BNX2X_ERR("Can't map sge\n"); - return -ENOMEM; + /* put page reference used by the memory pool, since we + * won't be using this page as the mempool anymore. + */ + if (pool->page) + put_page(pool->page); + + pool->page = alloc_pages(gfp_mask, PAGES_PER_SGE_SHIFT); + if (unlikely(!pool->page)) { + BNX2X_ERR("Can't alloc sge\n"); + return -ENOMEM; + } + + pool->dma = dma_map_page(&bp->pdev->dev, pool->page, 0, + PAGE_SIZE, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(&bp->pdev->dev, + pool->dma))) { + __free_pages(pool->page, PAGES_PER_SGE_SHIFT); + pool->page = NULL; + BNX2X_ERR("Can't map sge\n"); + return -ENOMEM; + } + pool->offset = 0; } - sw_buf->page = page; + get_page(pool->page); + sw_buf->page = pool->page; + sw_buf->offset = pool->offset; + + mapping = pool->dma + sw_buf->offset; dma_unmap_addr_set(sw_buf, mapping, mapping); sge->addr_hi = cpu_to_le32(U64_HI(mapping)); sge->addr_lo = cpu_to_le32(U64_LO(mapping)); + pool->offset += SGE_PAGE_SIZE; + return 0; } @@ -629,20 +648,22 @@ static int bnx2x_fill_frag_skb(struct bnx2x *bp, struct bnx2x_fastpath *fp, return err; } - /* Unmap the page as we're going to pass it to the stack */ - dma_unmap_page(&bp->pdev->dev, - dma_unmap_addr(&old_rx_pg, mapping), - SGE_PAGES, DMA_FROM_DEVICE); + dma_unmap_single(&bp->pdev->dev, + dma_unmap_addr(&old_rx_pg, mapping), + SGE_PAGE_SIZE, DMA_FROM_DEVICE); /* Add one frag and update the appropriate fields in the skb */ if (fp->mode == TPA_MODE_LRO) - skb_fill_page_desc(skb, j, old_rx_pg.page, 0, frag_len); + skb_fill_page_desc(skb, j, old_rx_pg.page, + old_rx_pg.offset, frag_len); else { /* GRO */ int rem; int offset = 0; for (rem = frag_len; rem > 0; rem -= gro_size) { int len = rem > gro_size ? gro_size : rem; skb_fill_page_desc(skb, frag_id++, - old_rx_pg.page, offset, len); + old_rx_pg.page, + old_rx_pg.offset + offset, + len); if (offset) get_page(old_rx_pg.page); offset += len; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index d7a7175..2b30081 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -804,9 +804,13 @@ static inline void bnx2x_free_rx_sge(struct bnx2x *bp, if (!page) return; - dma_unmap_page(&bp->pdev->dev, dma_unmap_addr(sw_buf, mapping), - SGE_PAGES, DMA_FROM_DEVICE); - __free_pages(page, PAGES_PER_SGE_SHIFT); + /* Since many fragments can share the same page, make sure to + * only unmap and free the page once. + */ + dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(sw_buf, mapping), + SGE_PAGE_SIZE, DMA_FROM_DEVICE); + + put_page(page); sw_buf->page = NULL; sge->addr_hi = 0; @@ -964,6 +968,25 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid, ((u8 *)fw_lo)[1] = mac[4]; } +static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp, + struct bnx2x_alloc_pool *pool) +{ + if (!pool->page) + return; + + /* Page was not fully fragmented. Unmap unused space */ + if (pool->offset < PAGE_SIZE) { + dma_addr_t dma = pool->dma + pool->offset; + int size = PAGE_SIZE - pool->offset; + + dma_unmap_single(&bp->pdev->dev, dma, size, DMA_FROM_DEVICE); + } + + put_page(pool->page); + + pool->page = NULL; +} + static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp, struct bnx2x_fastpath *fp, int last) { @@ -974,6 +997,8 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp, for (i = 0; i < last; i++) bnx2x_free_rx_sge(bp, fp, i); + + bnx2x_free_rx_mem_pool(bp, &fp->page_pool); } static inline void bnx2x_set_next_page_rx_bd(struct bnx2x_fastpath *fp) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index fd52ce9..33501bc 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12054,7 +12054,7 @@ static int bnx2x_init_bp(struct bnx2x *bp) mutex_init(&bp->port.phy_mutex); mutex_init(&bp->fw_mb_mutex); mutex_init(&bp->drv_info_mutex); - mutex_init(&bp->stats_lock); + sema_init(&bp->stats_lock, 1); bp->drv_info_mng_owner = false; INIT_DELAYED_WORK(&bp->sp_task, bnx2x_sp_task); @@ -13690,9 +13690,10 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp) cancel_delayed_work_sync(&bp->sp_task); cancel_delayed_work_sync(&bp->period_task); - mutex_lock(&bp->stats_lock); - bp->stats_state = STATS_STATE_DISABLED; - mutex_unlock(&bp->stats_lock); + if (!down_timeout(&bp->stats_lock, HZ / 10)) { + bp->stats_state = STATS_STATE_DISABLED; + up(&bp->stats_lock); + } bnx2x_save_statistics(bp); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c index 266b055..69d699f0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c @@ -1372,19 +1372,23 @@ void bnx2x_stats_handle(struct bnx2x *bp, enum bnx2x_stats_event event) * that context in case someone is in the middle of a transition. * For other events, wait a bit until lock is taken. */ - if (!mutex_trylock(&bp->stats_lock)) { + if (down_trylock(&bp->stats_lock)) { if (event == STATS_EVENT_UPDATE) return; DP(BNX2X_MSG_STATS, "Unlikely stats' lock contention [event %d]\n", event); - mutex_lock(&bp->stats_lock); + if (unlikely(down_timeout(&bp->stats_lock, HZ / 10))) { + BNX2X_ERR("Failed to take stats lock [event %d]\n", + event); + return; + } } bnx2x_stats_stm[state][event].action(bp); bp->stats_state = bnx2x_stats_stm[state][event].next_state; - mutex_unlock(&bp->stats_lock); + up(&bp->stats_lock); if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp)) DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n", @@ -1970,7 +1974,11 @@ int bnx2x_stats_safe_exec(struct bnx2x *bp, /* Wait for statistics to end [while blocking further requests], * then run supplied function 'safely'. */ - mutex_lock(&bp->stats_lock); + rc = down_timeout(&bp->stats_lock, HZ / 10); + if (unlikely(rc)) { + BNX2X_ERR("Failed to take statistics lock for safe execution\n"); + goto out_no_lock; + } bnx2x_stats_comp(bp); while (bp->stats_pending && cnt--) @@ -1988,7 +1996,7 @@ out: /* No need to restart statistics - if they're enabled, the timer * will restart the statistics. */ - mutex_unlock(&bp->stats_lock); - + up(&bp->stats_lock); +out_no_lock: return rc; } diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c index 594a2ab..68f3c13 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c +++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c @@ -2414,7 +2414,7 @@ bfa_ioc_boot(struct bfa_ioc *ioc, enum bfi_fwboot_type boot_type, if (status == BFA_STATUS_OK) bfa_ioc_lpu_start(ioc); else - bfa_nw_iocpf_timeout(ioc); + bfa_fsm_send_event(&ioc->iocpf, IOCPF_E_TIMEOUT); return status; } @@ -3029,7 +3029,7 @@ bfa_ioc_poll_fwinit(struct bfa_ioc *ioc) } if (ioc->iocpf.poll_time >= BFA_IOC_TOV) { - bfa_nw_iocpf_timeout(ioc); + bfa_fsm_send_event(&ioc->iocpf, IOCPF_E_TIMEOUT); } else { ioc->iocpf.poll_time += BFA_IOC_POLL_TOV; mod_timer(&ioc->iocpf_timer, jiffies + diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 37072a8..caae6cb 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -3701,10 +3701,6 @@ bnad_pci_probe(struct pci_dev *pdev, setup_timer(&bnad->bna.ioceth.ioc.sem_timer, bnad_iocpf_sem_timeout, ((unsigned long)bnad)); - /* Now start the timer before calling IOC */ - mod_timer(&bnad->bna.ioceth.ioc.iocpf_timer, - jiffies + msecs_to_jiffies(BNA_IOC_TIMER_FREQ)); - /* * Start the chip * If the call back comes with error, we bail out. diff --git a/drivers/net/ethernet/brocade/bna/cna_fwimg.c b/drivers/net/ethernet/brocade/bna/cna_fwimg.c index ebf462d..badea36 100644 --- a/drivers/net/ethernet/brocade/bna/cna_fwimg.c +++ b/drivers/net/ethernet/brocade/bna/cna_fwimg.c @@ -30,6 +30,7 @@ cna_read_firmware(struct pci_dev *pdev, u32 **bfi_image, u32 *bfi_image_size, char *fw_name) { const struct firmware *fw; + u32 n; if (request_firmware(&fw, fw_name, &pdev->dev)) { pr_alert("Can't locate firmware %s\n", fw_name); @@ -40,6 +41,12 @@ cna_read_firmware(struct pci_dev *pdev, u32 **bfi_image, *bfi_image_size = fw->size/sizeof(u32); bfi_fw = fw; + /* Convert loaded firmware to host order as it is stored in file + * as sequence of LE32 integers. + */ + for (n = 0; n < *bfi_image_size; n++) + le32_to_cpus(*bfi_image + n); + return *bfi_image; error: return NULL; diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig new file mode 100644 index 0000000..fc3d8e3 --- /dev/null +++ b/drivers/net/ethernet/cavium/Kconfig @@ -0,0 +1,40 @@ +# +# Cavium ethernet device configuration +# + +config NET_VENDOR_CAVIUM + tristate "Cavium ethernet drivers" + depends on PCI && 64BIT + ---help--- + Enable support for the Cavium ThunderX Network Interface + Controller (NIC). The NIC provides the controller and DMA + engines to move network traffic to/from the memory. The NIC + works closely with TNS, BGX and SerDes to implement the + functions replacing and virtualizing those of a typical + standalone PCIe NIC chip. + + If you have a Cavium Thunder board, say Y. + +if NET_VENDOR_CAVIUM + +config THUNDER_NIC_PF + tristate "Thunder Physical function driver" + default NET_VENDOR_CAVIUM + select THUNDER_NIC_BGX + ---help--- + This driver supports Thunder's NIC physical function. + +config THUNDER_NIC_VF + tristate "Thunder Virtual function driver" + default NET_VENDOR_CAVIUM + ---help--- + This driver supports Thunder's NIC virtual function + +config THUNDER_NIC_BGX + tristate "Thunder MAC interface driver (BGX)" + default NET_VENDOR_CAVIUM + ---help--- + This driver supports programming and controlling of MAC + interface from NIC physical function driver. + +endif # NET_VENDOR_CAVIUM diff --git a/drivers/net/ethernet/cavium/Makefile b/drivers/net/ethernet/cavium/Makefile new file mode 100644 index 0000000..7aac478 --- /dev/null +++ b/drivers/net/ethernet/cavium/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the Cavium ethernet device drivers. +# + +obj-$(CONFIG_NET_VENDOR_CAVIUM) += thunder/ diff --git a/drivers/net/ethernet/cavium/thunder/Makefile b/drivers/net/ethernet/cavium/thunder/Makefile new file mode 100644 index 0000000..5c4615c --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/Makefile @@ -0,0 +1,11 @@ +# +# Makefile for Cavium's Thunder ethernet device +# + +obj-$(CONFIG_THUNDER_NIC_BGX) += thunder_bgx.o +obj-$(CONFIG_THUNDER_NIC_PF) += nicpf.o +obj-$(CONFIG_THUNDER_NIC_VF) += nicvf.o + +nicpf-y := nic_main.o +nicvf-y := nicvf_main.o nicvf_queues.o +nicvf-y += nicvf_ethtool.o diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h new file mode 100644 index 0000000..a3b43e5 --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -0,0 +1,422 @@ +/* + * Copyright (C) 2015 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#ifndef NIC_H +#define NIC_H + +#include <linux/netdevice.h> +#include <linux/interrupt.h> +#include <linux/pci.h> +#include "thunder_bgx.h" + +/* PCI device IDs */ +#define PCI_DEVICE_ID_THUNDER_NIC_PF 0xA01E +#define PCI_DEVICE_ID_THUNDER_PASS1_NIC_VF 0x0011 +#define PCI_DEVICE_ID_THUNDER_NIC_VF 0xA034 +#define PCI_DEVICE_ID_THUNDER_BGX 0xA026 + +/* PCI BAR nos */ +#define PCI_CFG_REG_BAR_NUM 0 +#define PCI_MSIX_REG_BAR_NUM 4 + +/* NIC SRIOV VF count */ +#define MAX_NUM_VFS_SUPPORTED 128 +#define DEFAULT_NUM_VF_ENABLED 8 + +#define NIC_TNS_BYPASS_MODE 0 +#define NIC_TNS_MODE 1 + +/* NIC priv flags */ +#define NIC_SRIOV_ENABLED BIT(0) + +/* Min/Max packet size */ +#define NIC_HW_MIN_FRS 64 +#define NIC_HW_MAX_FRS 9200 /* 9216 max packet including FCS */ + +/* Max pkinds */ +#define NIC_MAX_PKIND 16 + +/* Rx Channels */ +/* Receive channel configuration in TNS bypass mode + * Below is configuration in TNS bypass mode + * BGX0-LMAC0-CHAN0 - VNIC CHAN0 + * BGX0-LMAC1-CHAN0 - VNIC CHAN16 + * ... + * BGX1-LMAC0-CHAN0 - VNIC CHAN128 + * ... + * BGX1-LMAC3-CHAN0 - VNIC CHAN174 + */ +#define NIC_INTF_COUNT 2 /* Interfaces btw VNIC and TNS/BGX */ +#define NIC_CHANS_PER_INF 128 +#define NIC_MAX_CHANS (NIC_INTF_COUNT * NIC_CHANS_PER_INF) +#define NIC_CPI_COUNT 2048 /* No of channel parse indices */ + +/* TNS bypass mode: 1-1 mapping between VNIC and BGX:LMAC */ +#define NIC_MAX_BGX MAX_BGX_PER_CN88XX +#define NIC_CPI_PER_BGX (NIC_CPI_COUNT / NIC_MAX_BGX) +#define NIC_MAX_CPI_PER_LMAC 64 /* Max when CPI_ALG is IP diffserv */ +#define NIC_RSSI_PER_BGX (NIC_RSSI_COUNT / NIC_MAX_BGX) + +/* Tx scheduling */ +#define NIC_MAX_TL4 1024 +#define NIC_MAX_TL4_SHAPERS 256 /* 1 shaper for 4 TL4s */ +#define NIC_MAX_TL3 256 +#define NIC_MAX_TL3_SHAPERS 64 /* 1 shaper for 4 TL3s */ +#define NIC_MAX_TL2 64 +#define NIC_MAX_TL2_SHAPERS 2 /* 1 shaper for 32 TL2s */ +#define NIC_MAX_TL1 2 + +/* TNS bypass mode */ +#define NIC_TL2_PER_BGX 32 +#define NIC_TL4_PER_BGX (NIC_MAX_TL4 / NIC_MAX_BGX) +#define NIC_TL4_PER_LMAC (NIC_MAX_TL4 / NIC_CHANS_PER_INF) + +/* NIC VF Interrupts */ +#define NICVF_INTR_CQ 0 +#define NICVF_INTR_SQ 1 +#define NICVF_INTR_RBDR 2 +#define NICVF_INTR_PKT_DROP 3 +#define NICVF_INTR_TCP_TIMER 4 +#define NICVF_INTR_MBOX 5 +#define NICVF_INTR_QS_ERR 6 + +#define NICVF_INTR_CQ_SHIFT 0 +#define NICVF_INTR_SQ_SHIFT 8 +#define NICVF_INTR_RBDR_SHIFT 16 +#define NICVF_INTR_PKT_DROP_SHIFT 20 +#define NICVF_INTR_TCP_TIMER_SHIFT 21 +#define NICVF_INTR_MBOX_SHIFT 22 +#define NICVF_INTR_QS_ERR_SHIFT 23 + +#define NICVF_INTR_CQ_MASK (0xFF << NICVF_INTR_CQ_SHIFT) +#define NICVF_INTR_SQ_MASK (0xFF << NICVF_INTR_SQ_SHIFT) +#define NICVF_INTR_RBDR_MASK (0x03 << NICVF_INTR_RBDR_SHIFT) +#define NICVF_INTR_PKT_DROP_MASK BIT(NICVF_INTR_PKT_DROP_SHIFT) +#define NICVF_INTR_TCP_TIMER_MASK BIT(NICVF_INTR_TCP_TIMER_SHIFT) +#define NICVF_INTR_MBOX_MASK BIT(NICVF_INTR_MBOX_SHIFT) +#define NICVF_INTR_QS_ERR_MASK BIT(NICVF_INTR_QS_ERR_SHIFT) + +/* MSI-X interrupts */ +#define NIC_PF_MSIX_VECTORS 10 +#define NIC_VF_MSIX_VECTORS 20 + +#define NIC_PF_INTR_ID_ECC0_SBE 0 +#define NIC_PF_INTR_ID_ECC0_DBE 1 +#define NIC_PF_INTR_ID_ECC1_SBE 2 +#define NIC_PF_INTR_ID_ECC1_DBE 3 +#define NIC_PF_INTR_ID_ECC2_SBE 4 +#define NIC_PF_INTR_ID_ECC2_DBE 5 +#define NIC_PF_INTR_ID_ECC3_SBE 6 +#define NIC_PF_INTR_ID_ECC3_DBE 7 +#define NIC_PF_INTR_ID_MBOX0 8 +#define NIC_PF_INTR_ID_MBOX1 9 + +/* Global timer for CQ timer thresh interrupts + * Calculated for SCLK of 700Mhz + * value written should be a 1/16th of what is expected + * + * 1 tick per 0.05usec = value of 2.2 + * This 10% would be covered in CQ timer thresh value + */ +#define NICPF_CLK_PER_INT_TICK 2 + +struct nicvf_cq_poll { + u8 cq_idx; /* Completion queue index */ + struct napi_struct napi; +}; + +#define NIC_RSSI_COUNT 4096 /* Total no of RSS indices */ +#define NIC_MAX_RSS_HASH_BITS 8 +#define NIC_MAX_RSS_IDR_TBL_SIZE (1 << NIC_MAX_RSS_HASH_BITS) +#define RSS_HASH_KEY_SIZE 5 /* 320 bit key */ + +struct nicvf_rss_info { + bool enable; +#define RSS_L2_EXTENDED_HASH_ENA BIT(0) +#define RSS_IP_HASH_ENA BIT(1) +#define RSS_TCP_HASH_ENA BIT(2) +#define RSS_TCP_SYN_DIS BIT(3) +#define RSS_UDP_HASH_ENA BIT(4) +#define RSS_L4_EXTENDED_HASH_ENA BIT(5) +#define RSS_ROCE_ENA BIT(6) +#define RSS_L3_BI_DIRECTION_ENA BIT(7) +#define RSS_L4_BI_DIRECTION_ENA BIT(8) + u64 cfg; + u8 hash_bits; + u16 rss_size; + u8 ind_tbl[NIC_MAX_RSS_IDR_TBL_SIZE]; + u64 key[RSS_HASH_KEY_SIZE]; +} ____cacheline_aligned_in_smp; + +enum rx_stats_reg_offset { + RX_OCTS = 0x0, + RX_UCAST = 0x1, + RX_BCAST = 0x2, + RX_MCAST = 0x3, + RX_RED = 0x4, + RX_RED_OCTS = 0x5, + RX_ORUN = 0x6, + RX_ORUN_OCTS = 0x7, + RX_FCS = 0x8, + RX_L2ERR = 0x9, + RX_DRP_BCAST = 0xa, + RX_DRP_MCAST = 0xb, + RX_DRP_L3BCAST = 0xc, + RX_DRP_L3MCAST = 0xd, + RX_STATS_ENUM_LAST, +}; + +enum tx_stats_reg_offset { + TX_OCTS = 0x0, + TX_UCAST = 0x1, + TX_BCAST = 0x2, + TX_MCAST = 0x3, + TX_DROP = 0x4, + TX_STATS_ENUM_LAST, +}; + +struct nicvf_hw_stats { + u64 rx_bytes_ok; + u64 rx_ucast_frames_ok; + u64 rx_bcast_frames_ok; + u64 rx_mcast_frames_ok; + u64 rx_fcs_errors; + u64 rx_l2_errors; + u64 rx_drop_red; + u64 rx_drop_red_bytes; + u64 rx_drop_overrun; + u64 rx_drop_overrun_bytes; + u64 rx_drop_bcast; + u64 rx_drop_mcast; + u64 rx_drop_l3_bcast; + u64 rx_drop_l3_mcast; + u64 tx_bytes_ok; + u64 tx_ucast_frames_ok; + u64 tx_bcast_frames_ok; + u64 tx_mcast_frames_ok; + u64 tx_drops; +}; + +struct nicvf_drv_stats { + /* Rx */ + u64 rx_frames_ok; + u64 rx_frames_64; + u64 rx_frames_127; + u64 rx_frames_255; + u64 rx_frames_511; + u64 rx_frames_1023; + u64 rx_frames_1518; + u64 rx_frames_jumbo; + u64 rx_drops; + /* Tx */ + u64 tx_frames_ok; + u64 tx_drops; + u64 tx_busy; + u64 tx_tso; +}; + +struct nicvf { + struct net_device *netdev; + struct pci_dev *pdev; + u8 vf_id; + u8 node; + u8 tns_mode; + u16 mtu; + struct queue_set *qs; + void __iomem *reg_base; + bool link_up; + u8 duplex; + u32 speed; + struct page *rb_page; + u32 rb_page_offset; + bool rb_alloc_fail; + bool rb_work_scheduled; + struct delayed_work rbdr_work; + struct tasklet_struct rbdr_task; + struct tasklet_struct qs_err_task; + struct tasklet_struct cq_task; + struct nicvf_cq_poll *napi[8]; + struct nicvf_rss_info rss_info; + u8 cpi_alg; + /* Interrupt coalescing settings */ + u32 cq_coalesce_usecs; + + u32 msg_enable; + struct nicvf_hw_stats stats; + struct nicvf_drv_stats drv_stats; + struct bgx_stats bgx_stats; + struct work_struct reset_task; + + /* MSI-X */ + bool msix_enabled; + u8 num_vec; + struct msix_entry msix_entries[NIC_VF_MSIX_VECTORS]; + char irq_name[NIC_VF_MSIX_VECTORS][20]; + bool irq_allocated[NIC_VF_MSIX_VECTORS]; + + bool pf_ready_to_rcv_msg; + bool pf_acked; + bool pf_nacked; + bool bgx_stats_acked; +} ____cacheline_aligned_in_smp; + +/* PF <--> VF Mailbox communication + * Eight 64bit registers are shared between PF and VF. + * Separate set for each VF. + * Writing '1' into last register mbx7 means end of message. + */ + +/* PF <--> VF mailbox communication */ +#define NIC_PF_VF_MAILBOX_SIZE 2 +#define NIC_MBOX_MSG_TIMEOUT 2000 /* ms */ + +/* Mailbox message types */ +#define NIC_MBOX_MSG_READY 0x01 /* Is PF ready to rcv msgs */ +#define NIC_MBOX_MSG_ACK 0x02 /* ACK the message received */ +#define NIC_MBOX_MSG_NACK 0x03 /* NACK the message received */ +#define NIC_MBOX_MSG_QS_CFG 0x04 /* Configure Qset */ +#define NIC_MBOX_MSG_RQ_CFG 0x05 /* Configure receive queue */ +#define NIC_MBOX_MSG_SQ_CFG 0x06 /* Configure Send queue */ +#define NIC_MBOX_MSG_RQ_DROP_CFG 0x07 /* Configure receive queue */ +#define NIC_MBOX_MSG_SET_MAC 0x08 /* Add MAC ID to DMAC filter */ +#define NIC_MBOX_MSG_SET_MAX_FRS 0x09 /* Set max frame size */ +#define NIC_MBOX_MSG_CPI_CFG 0x0A /* Config CPI, RSSI */ +#define NIC_MBOX_MSG_RSS_SIZE 0x0B /* Get RSS indir_tbl size */ +#define NIC_MBOX_MSG_RSS_CFG 0x0C /* Config RSS table */ +#define NIC_MBOX_MSG_RSS_CFG_CONT 0x0D /* RSS config continuation */ +#define NIC_MBOX_MSG_RQ_BP_CFG 0x0E /* RQ backpressure config */ +#define NIC_MBOX_MSG_RQ_SW_SYNC 0x0F /* Flush inflight pkts to RQ */ +#define NIC_MBOX_MSG_BGX_STATS 0x10 /* Get stats from BGX */ +#define NIC_MBOX_MSG_BGX_LINK_CHANGE 0x11 /* BGX:LMAC link status */ +#define NIC_MBOX_MSG_CFG_DONE 0x12 /* VF configuration done */ +#define NIC_MBOX_MSG_SHUTDOWN 0x13 /* VF is being shutdown */ + +struct nic_cfg_msg { + u8 msg; + u8 vf_id; + u8 tns_mode; + u8 node_id; + u8 mac_addr[ETH_ALEN]; +}; + +/* Qset configuration */ +struct qs_cfg_msg { + u8 msg; + u8 num; + u64 cfg; +}; + +/* Receive queue configuration */ +struct rq_cfg_msg { + u8 msg; + u8 qs_num; + u8 rq_num; + u64 cfg; +}; + +/* Send queue configuration */ +struct sq_cfg_msg { + u8 msg; + u8 qs_num; + u8 sq_num; + u64 cfg; +}; + +/* Set VF's MAC address */ +struct set_mac_msg { + u8 msg; + u8 vf_id; + u8 mac_addr[ETH_ALEN]; +}; + +/* Set Maximum frame size */ +struct set_frs_msg { + u8 msg; + u8 vf_id; + u16 max_frs; +}; + +/* Set CPI algorithm type */ +struct cpi_cfg_msg { + u8 msg; + u8 vf_id; + u8 rq_cnt; + u8 cpi_alg; +}; + +/* Get RSS table size */ +struct rss_sz_msg { + u8 msg; + u8 vf_id; + u16 ind_tbl_size; +}; + +/* Set RSS configuration */ +struct rss_cfg_msg { + u8 msg; + u8 vf_id; + u8 hash_bits; + u8 tbl_len; + u8 tbl_offset; +#define RSS_IND_TBL_LEN_PER_MBX_MSG 8 + u8 ind_tbl[RSS_IND_TBL_LEN_PER_MBX_MSG]; +}; + +struct bgx_stats_msg { + u8 msg; + u8 vf_id; + u8 rx; + u8 idx; + u64 stats; +}; + +/* Physical interface link status */ +struct bgx_link_status { + u8 msg; + u8 link_up; + u8 duplex; + u32 speed; +}; + +/* 128 bit shared memory between PF and each VF */ +union nic_mbx { + struct { u8 msg; } msg; + struct nic_cfg_msg nic_cfg; + struct qs_cfg_msg qs; + struct rq_cfg_msg rq; + struct sq_cfg_msg sq; + struct set_mac_msg mac; + struct set_frs_msg frs; + struct cpi_cfg_msg cpi_cfg; + struct rss_sz_msg rss_size; + struct rss_cfg_msg rss_cfg; + struct bgx_stats_msg bgx_stats; + struct bgx_link_status link_status; +}; + +#define NIC_NODE_ID_MASK 0x03 +#define NIC_NODE_ID_SHIFT 44 + +static inline int nic_get_node_id(struct pci_dev *pdev) +{ + u64 addr = pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM); + return ((addr >> NIC_NODE_ID_SHIFT) & NIC_NODE_ID_MASK); +} + +int nicvf_set_real_num_queues(struct net_device *netdev, + int tx_queues, int rx_queues); +int nicvf_open(struct net_device *netdev); +int nicvf_stop(struct net_device *netdev); +int nicvf_send_msg_to_pf(struct nicvf *vf, union nic_mbx *mbx); +void nicvf_config_rss(struct nicvf *nic); +void nicvf_set_rss_key(struct nicvf *nic); +void nicvf_set_ethtool_ops(struct net_device *netdev); +void nicvf_update_stats(struct nicvf *nic); +void nicvf_update_lmac_stats(struct nicvf *nic); + +#endif /* NIC_H */ diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c new file mode 100644 index 0000000..6e0c031 --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -0,0 +1,932 @@ +/* + * Copyright (C) 2015 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/pci.h> +#include <linux/etherdevice.h> +#include <linux/of.h> + +#include "nic_reg.h" +#include "nic.h" +#include "q_struct.h" +#include "thunder_bgx.h" + +#define DRV_NAME "thunder-nic" +#define DRV_VERSION "1.0" + +struct nicpf { + struct pci_dev *pdev; + u8 rev_id; + u8 node; + unsigned int flags; + u8 num_vf_en; /* No of VF enabled */ + bool vf_enabled[MAX_NUM_VFS_SUPPORTED]; + void __iomem *reg_base; /* Register start address */ + struct pkind_cfg pkind; +#define NIC_SET_VF_LMAC_MAP(bgx, lmac) (((bgx & 0xF) << 4) | (lmac & 0xF)) +#define NIC_GET_BGX_FROM_VF_LMAC_MAP(map) ((map >> 4) & 0xF) +#define NIC_GET_LMAC_FROM_VF_LMAC_MAP(map) (map & 0xF) + u8 vf_lmac_map[MAX_LMAC]; + struct delayed_work dwork; + struct workqueue_struct *check_link; + u8 link[MAX_LMAC]; + u8 duplex[MAX_LMAC]; + u32 speed[MAX_LMAC]; + u16 cpi_base[MAX_NUM_VFS_SUPPORTED]; + u16 rss_ind_tbl_size; + bool mbx_lock[MAX_NUM_VFS_SUPPORTED]; + + /* MSI-X */ + bool msix_enabled; + u8 num_vec; + struct msix_entry msix_entries[NIC_PF_MSIX_VECTORS]; + bool irq_allocated[NIC_PF_MSIX_VECTORS]; +}; + +/* Supported devices */ +static const struct pci_device_id nic_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_NIC_PF) }, + { 0, } /* end of table */ +}; + +MODULE_AUTHOR("Sunil Goutham"); +MODULE_DESCRIPTION("Cavium Thunder NIC Physical Function Driver"); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION(DRV_VERSION); +MODULE_DEVICE_TABLE(pci, nic_id_table); + +/* The Cavium ThunderX network controller can *only* be found in SoCs + * containing the ThunderX ARM64 CPU implementation. All accesses to the device + * registers on this platform are implicitly strongly ordered with respect + * to memory accesses. So writeq_relaxed() and readq_relaxed() are safe to use + * with no memory barriers in this driver. The readq()/writeq() functions add + * explicit ordering operation which in this case are redundant, and only + * add overhead. + */ + +/* Register read/write APIs */ +static void nic_reg_write(struct nicpf *nic, u64 offset, u64 val) +{ + writeq_relaxed(val, nic->reg_base + offset); +} + +static u64 nic_reg_read(struct nicpf *nic, u64 offset) +{ + return readq_relaxed(nic->reg_base + offset); +} + +/* PF -> VF mailbox communication APIs */ +static void nic_enable_mbx_intr(struct nicpf *nic) +{ + /* Enable mailbox interrupt for all 128 VFs */ + nic_reg_write(nic, NIC_PF_MAILBOX_ENA_W1S, ~0ull); + nic_reg_write(nic, NIC_PF_MAILBOX_ENA_W1S + sizeof(u64), ~0ull); +} + +static void nic_clear_mbx_intr(struct nicpf *nic, int vf, int mbx_reg) +{ + nic_reg_write(nic, NIC_PF_MAILBOX_INT + (mbx_reg << 3), BIT_ULL(vf)); +} + +static u64 nic_get_mbx_addr(int vf) +{ + return NIC_PF_VF_0_127_MAILBOX_0_1 + (vf << NIC_VF_NUM_SHIFT); +} + +/* Send a mailbox message to VF + * @vf: vf to which this message to be sent + * @mbx: Message to be sent + */ +static void nic_send_msg_to_vf(struct nicpf *nic, int vf, union nic_mbx *mbx) +{ + void __iomem *mbx_addr = nic->reg_base + nic_get_mbx_addr(vf); + u64 *msg = (u64 *)mbx; + + /* In first revision HW, mbox interrupt is triggerred + * when PF writes to MBOX(1), in next revisions when + * PF writes to MBOX(0) + */ + if (nic->rev_id == 0) { + /* see the comment for nic_reg_write()/nic_reg_read() + * functions above + */ + writeq_relaxed(msg[0], mbx_addr); + writeq_relaxed(msg[1], mbx_addr + 8); + } else { + writeq_relaxed(msg[1], mbx_addr + 8); + writeq_relaxed(msg[0], mbx_addr); + } +} + +/* Responds to VF's READY message with VF's + * ID, node, MAC address e.t.c + * @vf: VF which sent READY message + */ +static void nic_mbx_send_ready(struct nicpf *nic, int vf) +{ + union nic_mbx mbx = {}; + int bgx_idx, lmac; + const char *mac; + + mbx.nic_cfg.msg = NIC_MBOX_MSG_READY; + mbx.nic_cfg.vf_id = vf; + + mbx.nic_cfg.tns_mode = NIC_TNS_BYPASS_MODE; + + bgx_idx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + + mac = bgx_get_lmac_mac(nic->node, bgx_idx, lmac); + if (mac) + ether_addr_copy((u8 *)&mbx.nic_cfg.mac_addr, mac); + + mbx.nic_cfg.node_id = nic->node; + nic_send_msg_to_vf(nic, vf, &mbx); +} + +/* ACKs VF's mailbox message + * @vf: VF to which ACK to be sent + */ +static void nic_mbx_send_ack(struct nicpf *nic, int vf) +{ + union nic_mbx mbx = {}; + + mbx.msg.msg = NIC_MBOX_MSG_ACK; + nic_send_msg_to_vf(nic, vf, &mbx); +} + +/* NACKs VF's mailbox message that PF is not able to + * complete the action + * @vf: VF to which ACK to be sent + */ +static void nic_mbx_send_nack(struct nicpf *nic, int vf) +{ + union nic_mbx mbx = {}; + + mbx.msg.msg = NIC_MBOX_MSG_NACK; + nic_send_msg_to_vf(nic, vf, &mbx); +} + +/* Flush all in flight receive packets to memory and + * bring down an active RQ + */ +static int nic_rcv_queue_sw_sync(struct nicpf *nic) +{ + u16 timeout = ~0x00; + + nic_reg_write(nic, NIC_PF_SW_SYNC_RX, 0x01); + /* Wait till sync cycle is finished */ + while (timeout) { + if (nic_reg_read(nic, NIC_PF_SW_SYNC_RX_DONE) & 0x1) + break; + timeout--; + } + nic_reg_write(nic, NIC_PF_SW_SYNC_RX, 0x00); + if (!timeout) { + dev_err(&nic->pdev->dev, "Receive queue software sync failed"); + return 1; + } + return 0; +} + +/* Get BGX Rx/Tx stats and respond to VF's request */ +static void nic_get_bgx_stats(struct nicpf *nic, struct bgx_stats_msg *bgx) +{ + int bgx_idx, lmac; + union nic_mbx mbx = {}; + + bgx_idx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[bgx->vf_id]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[bgx->vf_id]); + + mbx.bgx_stats.msg = NIC_MBOX_MSG_BGX_STATS; + mbx.bgx_stats.vf_id = bgx->vf_id; + mbx.bgx_stats.rx = bgx->rx; + mbx.bgx_stats.idx = bgx->idx; + if (bgx->rx) + mbx.bgx_stats.stats = bgx_get_rx_stats(nic->node, bgx_idx, + lmac, bgx->idx); + else + mbx.bgx_stats.stats = bgx_get_tx_stats(nic->node, bgx_idx, + lmac, bgx->idx); + nic_send_msg_to_vf(nic, bgx->vf_id, &mbx); +} + +/* Update hardware min/max frame size */ +static int nic_update_hw_frs(struct nicpf *nic, int new_frs, int vf) +{ + if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) { + dev_err(&nic->pdev->dev, + "Invalid MTU setting from VF%d rejected, should be between %d and %d\n", + vf, NIC_HW_MIN_FRS, NIC_HW_MAX_FRS); + return 1; + } + new_frs += ETH_HLEN; + if (new_frs <= nic->pkind.maxlen) + return 0; + + nic->pkind.maxlen = new_frs; + nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG, *(u64 *)&nic->pkind); + return 0; +} + +/* Set minimum transmit packet size */ +static void nic_set_tx_pkt_pad(struct nicpf *nic, int size) +{ + int lmac; + u64 lmac_cfg; + + /* Max value that can be set is 60 */ + if (size > 60) + size = 60; + + for (lmac = 0; lmac < (MAX_BGX_PER_CN88XX * MAX_LMAC_PER_BGX); lmac++) { + lmac_cfg = nic_reg_read(nic, NIC_PF_LMAC_0_7_CFG | (lmac << 3)); + lmac_cfg &= ~(0xF << 2); + lmac_cfg |= ((size / 4) << 2); + nic_reg_write(nic, NIC_PF_LMAC_0_7_CFG | (lmac << 3), lmac_cfg); + } +} + +/* Function to check number of LMACs present and set VF::LMAC mapping. + * Mapping will be used while initializing channels. + */ +static void nic_set_lmac_vf_mapping(struct nicpf *nic) +{ + unsigned bgx_map = bgx_get_map(nic->node); + int bgx, next_bgx_lmac = 0; + int lmac, lmac_cnt = 0; + u64 lmac_credit; + + nic->num_vf_en = 0; + + for (bgx = 0; bgx < NIC_MAX_BGX; bgx++) { + if (!(bgx_map & (1 << bgx))) + continue; + lmac_cnt = bgx_get_lmac_count(nic->node, bgx); + for (lmac = 0; lmac < lmac_cnt; lmac++) + nic->vf_lmac_map[next_bgx_lmac++] = + NIC_SET_VF_LMAC_MAP(bgx, lmac); + nic->num_vf_en += lmac_cnt; + + /* Program LMAC credits */ + lmac_credit = (1ull << 1); /* channel credit enable */ + lmac_credit |= (0x1ff << 2); /* Max outstanding pkt count */ + /* 48KB BGX Tx buffer size, each unit is of size 16bytes */ + lmac_credit |= (((((48 * 1024) / lmac_cnt) - + NIC_HW_MAX_FRS) / 16) << 12); + lmac = bgx * MAX_LMAC_PER_BGX; + for (; lmac < lmac_cnt + (bgx * MAX_LMAC_PER_BGX); lmac++) + nic_reg_write(nic, + NIC_PF_LMAC_0_7_CREDIT + (lmac * 8), + lmac_credit); + } +} + +#define BGX0_BLOCK 8 +#define BGX1_BLOCK 9 + +static void nic_init_hw(struct nicpf *nic) +{ + int i; + + /* Reset NIC, in case the driver is repeatedly inserted and removed */ + nic_reg_write(nic, NIC_PF_SOFT_RESET, 1); + + /* Enable NIC HW block */ + nic_reg_write(nic, NIC_PF_CFG, 0x3); + + /* Enable backpressure */ + nic_reg_write(nic, NIC_PF_BP_CFG, (1ULL << 6) | 0x03); + + /* Disable TNS mode on both interfaces */ + nic_reg_write(nic, NIC_PF_INTF_0_1_SEND_CFG, + (NIC_TNS_BYPASS_MODE << 7) | BGX0_BLOCK); + nic_reg_write(nic, NIC_PF_INTF_0_1_SEND_CFG | (1 << 8), + (NIC_TNS_BYPASS_MODE << 7) | BGX1_BLOCK); + nic_reg_write(nic, NIC_PF_INTF_0_1_BP_CFG, + (1ULL << 63) | BGX0_BLOCK); + nic_reg_write(nic, NIC_PF_INTF_0_1_BP_CFG + (1 << 8), + (1ULL << 63) | BGX1_BLOCK); + + /* PKIND configuration */ + nic->pkind.minlen = 0; + nic->pkind.maxlen = NIC_HW_MAX_FRS + ETH_HLEN; + nic->pkind.lenerr_en = 1; + nic->pkind.rx_hdr = 0; + nic->pkind.hdr_sl = 0; + + for (i = 0; i < NIC_MAX_PKIND; i++) + nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG | (i << 3), + *(u64 *)&nic->pkind); + + nic_set_tx_pkt_pad(nic, NIC_HW_MIN_FRS); + + /* Timer config */ + nic_reg_write(nic, NIC_PF_INTR_TIMER_CFG, NICPF_CLK_PER_INT_TICK); +} + +/* Channel parse index configuration */ +static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg) +{ + u32 vnic, bgx, lmac, chan; + u32 padd, cpi_count = 0; + u64 cpi_base, cpi, rssi_base, rssi; + u8 qset, rq_idx = 0; + + vnic = cfg->vf_id; + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]); + + chan = (lmac * MAX_BGX_CHANS_PER_LMAC) + (bgx * NIC_CHANS_PER_INF); + cpi_base = (lmac * NIC_MAX_CPI_PER_LMAC) + (bgx * NIC_CPI_PER_BGX); + rssi_base = (lmac * nic->rss_ind_tbl_size) + (bgx * NIC_RSSI_PER_BGX); + + /* Rx channel configuration */ + nic_reg_write(nic, NIC_PF_CHAN_0_255_RX_BP_CFG | (chan << 3), + (1ull << 63) | (vnic << 0)); + nic_reg_write(nic, NIC_PF_CHAN_0_255_RX_CFG | (chan << 3), + ((u64)cfg->cpi_alg << 62) | (cpi_base << 48)); + + if (cfg->cpi_alg == CPI_ALG_NONE) + cpi_count = 1; + else if (cfg->cpi_alg == CPI_ALG_VLAN) /* 3 bits of PCP */ + cpi_count = 8; + else if (cfg->cpi_alg == CPI_ALG_VLAN16) /* 3 bits PCP + DEI */ + cpi_count = 16; + else if (cfg->cpi_alg == CPI_ALG_DIFF) /* 6bits DSCP */ + cpi_count = NIC_MAX_CPI_PER_LMAC; + + /* RSS Qset, Qidx mapping */ + qset = cfg->vf_id; + rssi = rssi_base; + for (; rssi < (rssi_base + cfg->rq_cnt); rssi++) { + nic_reg_write(nic, NIC_PF_RSSI_0_4097_RQ | (rssi << 3), + (qset << 3) | rq_idx); + rq_idx++; + } + + rssi = 0; + cpi = cpi_base; + for (; cpi < (cpi_base + cpi_count); cpi++) { + /* Determine port to channel adder */ + if (cfg->cpi_alg != CPI_ALG_DIFF) + padd = cpi % cpi_count; + else + padd = cpi % 8; /* 3 bits CS out of 6bits DSCP */ + + /* Leave RSS_SIZE as '0' to disable RSS */ + nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3), + (vnic << 24) | (padd << 16) | (rssi_base + rssi)); + + if ((rssi + 1) >= cfg->rq_cnt) + continue; + + if (cfg->cpi_alg == CPI_ALG_VLAN) + rssi++; + else if (cfg->cpi_alg == CPI_ALG_VLAN16) + rssi = ((cpi - cpi_base) & 0xe) >> 1; + else if (cfg->cpi_alg == CPI_ALG_DIFF) + rssi = ((cpi - cpi_base) & 0x38) >> 3; + } + nic->cpi_base[cfg->vf_id] = cpi_base; +} + +/* Responsds to VF with its RSS indirection table size */ +static void nic_send_rss_size(struct nicpf *nic, int vf) +{ + union nic_mbx mbx = {}; + u64 *msg; + + msg = (u64 *)&mbx; + + mbx.rss_size.msg = NIC_MBOX_MSG_RSS_SIZE; + mbx.rss_size.ind_tbl_size = nic->rss_ind_tbl_size; + nic_send_msg_to_vf(nic, vf, &mbx); +} + +/* Receive side scaling configuration + * configure: + * - RSS index + * - indir table i.e hash::RQ mapping + * - no of hash bits to consider + */ +static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg) +{ + u8 qset, idx = 0; + u64 cpi_cfg, cpi_base, rssi_base, rssi; + + cpi_base = nic->cpi_base[cfg->vf_id]; + cpi_cfg = nic_reg_read(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3)); + rssi_base = (cpi_cfg & 0x0FFF) + cfg->tbl_offset; + + rssi = rssi_base; + qset = cfg->vf_id; + + for (; rssi < (rssi_base + cfg->tbl_len); rssi++) { + nic_reg_write(nic, NIC_PF_RSSI_0_4097_RQ | (rssi << 3), + (qset << 3) | (cfg->ind_tbl[idx] & 0x7)); + idx++; + } + + cpi_cfg &= ~(0xFULL << 20); + cpi_cfg |= (cfg->hash_bits << 20); + nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3), cpi_cfg); +} + +/* 4 level transmit side scheduler configutation + * for TNS bypass mode + * + * Sample configuration for SQ0 + * VNIC0-SQ0 -> TL4(0) -> TL3[0] -> TL2[0] -> TL1[0] -> BGX0 + * VNIC1-SQ0 -> TL4(8) -> TL3[2] -> TL2[0] -> TL1[0] -> BGX0 + * VNIC2-SQ0 -> TL4(16) -> TL3[4] -> TL2[1] -> TL1[0] -> BGX0 + * VNIC3-SQ0 -> TL4(24) -> TL3[6] -> TL2[1] -> TL1[0] -> BGX0 + * VNIC4-SQ0 -> TL4(512) -> TL3[128] -> TL2[32] -> TL1[1] -> BGX1 + * VNIC5-SQ0 -> TL4(520) -> TL3[130] -> TL2[32] -> TL1[1] -> BGX1 + * VNIC6-SQ0 -> TL4(528) -> TL3[132] -> TL2[33] -> TL1[1] -> BGX1 + * VNIC7-SQ0 -> TL4(536) -> TL3[134] -> TL2[33] -> TL1[1] -> BGX1 + */ +static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic, u8 sq_idx) +{ + u32 bgx, lmac, chan; + u32 tl2, tl3, tl4; + u32 rr_quantum; + + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]); + /* 24 bytes for FCS, IPG and preamble */ + rr_quantum = ((NIC_HW_MAX_FRS + 24) / 4); + + tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX); + tl4 += sq_idx; + tl3 = tl4 / (NIC_MAX_TL4 / NIC_MAX_TL3); + nic_reg_write(nic, NIC_PF_QSET_0_127_SQ_0_7_CFG2 | + ((u64)vnic << NIC_QS_ID_SHIFT) | + ((u32)sq_idx << NIC_Q_NUM_SHIFT), tl4); + nic_reg_write(nic, NIC_PF_TL4_0_1023_CFG | (tl4 << 3), + ((u64)vnic << 27) | ((u32)sq_idx << 24) | rr_quantum); + + nic_reg_write(nic, NIC_PF_TL3_0_255_CFG | (tl3 << 3), rr_quantum); + chan = (lmac * MAX_BGX_CHANS_PER_LMAC) + (bgx * NIC_CHANS_PER_INF); + nic_reg_write(nic, NIC_PF_TL3_0_255_CHAN | (tl3 << 3), chan); + /* Enable backpressure on the channel */ + nic_reg_write(nic, NIC_PF_CHAN_0_255_TX_CFG | (chan << 3), 1); + + tl2 = tl3 >> 2; + nic_reg_write(nic, NIC_PF_TL3A_0_63_CFG | (tl2 << 3), tl2); + nic_reg_write(nic, NIC_PF_TL2_0_63_CFG | (tl2 << 3), rr_quantum); + /* No priorities as of now */ + nic_reg_write(nic, NIC_PF_TL2_0_63_PRI | (tl2 << 3), 0x00); +} + +/* Interrupt handler to handle mailbox messages from VFs */ +static void nic_handle_mbx_intr(struct nicpf *nic, int vf) +{ + union nic_mbx mbx = {}; + u64 *mbx_data; + u64 mbx_addr; + u64 reg_addr; + int bgx, lmac; + int i; + int ret = 0; + + nic->mbx_lock[vf] = true; + + mbx_addr = nic_get_mbx_addr(vf); + mbx_data = (u64 *)&mbx; + + for (i = 0; i < NIC_PF_VF_MAILBOX_SIZE; i++) { + *mbx_data = nic_reg_read(nic, mbx_addr); + mbx_data++; + mbx_addr += sizeof(u64); + } + + dev_dbg(&nic->pdev->dev, "%s: Mailbox msg %d from VF%d\n", + __func__, mbx.msg.msg, vf); + switch (mbx.msg.msg) { + case NIC_MBOX_MSG_READY: + nic_mbx_send_ready(nic, vf); + nic->link[vf] = 0; + nic->duplex[vf] = 0; + nic->speed[vf] = 0; + ret = 1; + break; + case NIC_MBOX_MSG_QS_CFG: + reg_addr = NIC_PF_QSET_0_127_CFG | + (mbx.qs.num << NIC_QS_ID_SHIFT); + nic_reg_write(nic, reg_addr, mbx.qs.cfg); + break; + case NIC_MBOX_MSG_RQ_CFG: + reg_addr = NIC_PF_QSET_0_127_RQ_0_7_CFG | + (mbx.rq.qs_num << NIC_QS_ID_SHIFT) | + (mbx.rq.rq_num << NIC_Q_NUM_SHIFT); + nic_reg_write(nic, reg_addr, mbx.rq.cfg); + break; + case NIC_MBOX_MSG_RQ_BP_CFG: + reg_addr = NIC_PF_QSET_0_127_RQ_0_7_BP_CFG | + (mbx.rq.qs_num << NIC_QS_ID_SHIFT) | + (mbx.rq.rq_num << NIC_Q_NUM_SHIFT); + nic_reg_write(nic, reg_addr, mbx.rq.cfg); + break; + case NIC_MBOX_MSG_RQ_SW_SYNC: + ret = nic_rcv_queue_sw_sync(nic); + break; + case NIC_MBOX_MSG_RQ_DROP_CFG: + reg_addr = NIC_PF_QSET_0_127_RQ_0_7_DROP_CFG | + (mbx.rq.qs_num << NIC_QS_ID_SHIFT) | + (mbx.rq.rq_num << NIC_Q_NUM_SHIFT); + nic_reg_write(nic, reg_addr, mbx.rq.cfg); + break; + case NIC_MBOX_MSG_SQ_CFG: + reg_addr = NIC_PF_QSET_0_127_SQ_0_7_CFG | + (mbx.sq.qs_num << NIC_QS_ID_SHIFT) | + (mbx.sq.sq_num << NIC_Q_NUM_SHIFT); + nic_reg_write(nic, reg_addr, mbx.sq.cfg); + nic_tx_channel_cfg(nic, mbx.qs.num, mbx.sq.sq_num); + break; + case NIC_MBOX_MSG_SET_MAC: + lmac = mbx.mac.vf_id; + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[lmac]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[lmac]); + bgx_set_lmac_mac(nic->node, bgx, lmac, mbx.mac.mac_addr); + break; + case NIC_MBOX_MSG_SET_MAX_FRS: + ret = nic_update_hw_frs(nic, mbx.frs.max_frs, + mbx.frs.vf_id); + break; + case NIC_MBOX_MSG_CPI_CFG: + nic_config_cpi(nic, &mbx.cpi_cfg); + break; + case NIC_MBOX_MSG_RSS_SIZE: + nic_send_rss_size(nic, vf); + goto unlock; + case NIC_MBOX_MSG_RSS_CFG: + case NIC_MBOX_MSG_RSS_CFG_CONT: + nic_config_rss(nic, &mbx.rss_cfg); + break; + case NIC_MBOX_MSG_CFG_DONE: + /* Last message of VF config msg sequence */ + nic->vf_enabled[vf] = true; + goto unlock; + case NIC_MBOX_MSG_SHUTDOWN: + /* First msg in VF teardown sequence */ + nic->vf_enabled[vf] = false; + break; + case NIC_MBOX_MSG_BGX_STATS: + nic_get_bgx_stats(nic, &mbx.bgx_stats); + goto unlock; + default: + dev_err(&nic->pdev->dev, + "Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg); + break; + } + + if (!ret) + nic_mbx_send_ack(nic, vf); + else if (mbx.msg.msg != NIC_MBOX_MSG_READY) + nic_mbx_send_nack(nic, vf); +unlock: + nic->mbx_lock[vf] = false; +} + +static void nic_mbx_intr_handler (struct nicpf *nic, int mbx) +{ + u64 intr; + u8 vf, vf_per_mbx_reg = 64; + + intr = nic_reg_read(nic, NIC_PF_MAILBOX_INT + (mbx << 3)); + dev_dbg(&nic->pdev->dev, "PF interrupt Mbox%d 0x%llx\n", mbx, intr); + for (vf = 0; vf < vf_per_mbx_reg; vf++) { + if (intr & (1ULL << vf)) { + dev_dbg(&nic->pdev->dev, "Intr from VF %d\n", + vf + (mbx * vf_per_mbx_reg)); + if ((vf + (mbx * vf_per_mbx_reg)) > nic->num_vf_en) + break; + nic_handle_mbx_intr(nic, vf + (mbx * vf_per_mbx_reg)); + nic_clear_mbx_intr(nic, vf, mbx); + } + } +} + +static irqreturn_t nic_mbx0_intr_handler (int irq, void *nic_irq) +{ + struct nicpf *nic = (struct nicpf *)nic_irq; + + nic_mbx_intr_handler(nic, 0); + + return IRQ_HANDLED; +} + +static irqreturn_t nic_mbx1_intr_handler (int irq, void *nic_irq) +{ + struct nicpf *nic = (struct nicpf *)nic_irq; + + nic_mbx_intr_handler(nic, 1); + + return IRQ_HANDLED; +} + +static int nic_enable_msix(struct nicpf *nic) +{ + int i, ret; + + nic->num_vec = NIC_PF_MSIX_VECTORS; + + for (i = 0; i < nic->num_vec; i++) + nic->msix_entries[i].entry = i; + + ret = pci_enable_msix(nic->pdev, nic->msix_entries, nic->num_vec); + if (ret) { + dev_err(&nic->pdev->dev, + "Request for #%d msix vectors failed\n", + nic->num_vec); + return ret; + } + + nic->msix_enabled = 1; + return 0; +} + +static void nic_disable_msix(struct nicpf *nic) +{ + if (nic->msix_enabled) { + pci_disable_msix(nic->pdev); + nic->msix_enabled = 0; + nic->num_vec = 0; + } +} + +static void nic_free_all_interrupts(struct nicpf *nic) +{ + int irq; + + for (irq = 0; irq < nic->num_vec; irq++) { + if (nic->irq_allocated[irq]) + free_irq(nic->msix_entries[irq].vector, nic); + nic->irq_allocated[irq] = false; + } +} + +static int nic_register_interrupts(struct nicpf *nic) +{ + int ret; + + /* Enable MSI-X */ + ret = nic_enable_msix(nic); + if (ret) + return ret; + + /* Register mailbox interrupt handlers */ + ret = request_irq(nic->msix_entries[NIC_PF_INTR_ID_MBOX0].vector, + nic_mbx0_intr_handler, 0, "NIC Mbox0", nic); + if (ret) + goto fail; + + nic->irq_allocated[NIC_PF_INTR_ID_MBOX0] = true; + + ret = request_irq(nic->msix_entries[NIC_PF_INTR_ID_MBOX1].vector, + nic_mbx1_intr_handler, 0, "NIC Mbox1", nic); + if (ret) + goto fail; + + nic->irq_allocated[NIC_PF_INTR_ID_MBOX1] = true; + + /* Enable mailbox interrupt */ + nic_enable_mbx_intr(nic); + return 0; + +fail: + dev_err(&nic->pdev->dev, "Request irq failed\n"); + nic_free_all_interrupts(nic); + return ret; +} + +static void nic_unregister_interrupts(struct nicpf *nic) +{ + nic_free_all_interrupts(nic); + nic_disable_msix(nic); +} + +static int nic_sriov_init(struct pci_dev *pdev, struct nicpf *nic) +{ + int pos = 0; + int err; + u16 total_vf_cnt; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + if (!pos) { + dev_err(&pdev->dev, "SRIOV capability is not found in PCIe config space\n"); + return -ENODEV; + } + + pci_read_config_word(pdev, (pos + PCI_SRIOV_TOTAL_VF), &total_vf_cnt); + if (total_vf_cnt < nic->num_vf_en) + nic->num_vf_en = total_vf_cnt; + + if (!total_vf_cnt) + return 0; + + err = pci_enable_sriov(pdev, nic->num_vf_en); + if (err) { + dev_err(&pdev->dev, "SRIOV enable failed, num VF is %d\n", + nic->num_vf_en); + nic->num_vf_en = 0; + return err; + } + + dev_info(&pdev->dev, "SRIOV enabled, number of VF available %d\n", + nic->num_vf_en); + + nic->flags |= NIC_SRIOV_ENABLED; + return 0; +} + +/* Poll for BGX LMAC link status and update corresponding VF + * if there is a change, valid only if internal L2 switch + * is not present otherwise VF link is always treated as up + */ +static void nic_poll_for_link(struct work_struct *work) +{ + union nic_mbx mbx = {}; + struct nicpf *nic; + struct bgx_link_status link; + u8 vf, bgx, lmac; + + nic = container_of(work, struct nicpf, dwork.work); + + mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; + + for (vf = 0; vf < nic->num_vf_en; vf++) { + /* Poll only if VF is UP */ + if (!nic->vf_enabled[vf]) + continue; + + /* Get BGX, LMAC indices for the VF */ + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + /* Get interface link status */ + bgx_get_lmac_link_state(nic->node, bgx, lmac, &link); + + /* Inform VF only if link status changed */ + if (nic->link[vf] == link.link_up) + continue; + + if (!nic->mbx_lock[vf]) { + nic->link[vf] = link.link_up; + nic->duplex[vf] = link.duplex; + nic->speed[vf] = link.speed; + + /* Send a mbox message to VF with current link status */ + mbx.link_status.link_up = link.link_up; + mbx.link_status.duplex = link.duplex; + mbx.link_status.speed = link.speed; + nic_send_msg_to_vf(nic, vf, &mbx); + } + } + queue_delayed_work(nic->check_link, &nic->dwork, HZ * 2); +} + +static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct device *dev = &pdev->dev; + struct nicpf *nic; + int err; + + BUILD_BUG_ON(sizeof(union nic_mbx) > 16); + + nic = devm_kzalloc(dev, sizeof(*nic), GFP_KERNEL); + if (!nic) + return -ENOMEM; + + pci_set_drvdata(pdev, nic); + + nic->pdev = pdev; + + err = pci_enable_device(pdev); + if (err) { + dev_err(dev, "Failed to enable PCI device\n"); + pci_set_drvdata(pdev, NULL); + return err; + } + + err = pci_request_regions(pdev, DRV_NAME); + if (err) { + dev_err(dev, "PCI request regions failed 0x%x\n", err); + goto err_disable_device; + } + + err = pci_set_dma_mask(pdev, DMA_BIT_MASK(48)); + if (err) { + dev_err(dev, "Unable to get usable DMA configuration\n"); + goto err_release_regions; + } + + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48)); + if (err) { + dev_err(dev, "Unable to get 48-bit DMA for consistent allocations\n"); + goto err_release_regions; + } + + /* MAP PF's configuration registers */ + nic->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0); + if (!nic->reg_base) { + dev_err(dev, "Cannot map config register space, aborting\n"); + err = -ENOMEM; + goto err_release_regions; + } + + pci_read_config_byte(pdev, PCI_REVISION_ID, &nic->rev_id); + + nic->node = nic_get_node_id(pdev); + + nic_set_lmac_vf_mapping(nic); + + /* Initialize hardware */ + nic_init_hw(nic); + + /* Set RSS TBL size for each VF */ + nic->rss_ind_tbl_size = NIC_MAX_RSS_IDR_TBL_SIZE; + + /* Register interrupts */ + err = nic_register_interrupts(nic); + if (err) + goto err_release_regions; + + /* Configure SRIOV */ + err = nic_sriov_init(pdev, nic); + if (err) + goto err_unregister_interrupts; + + /* Register a physical link status poll fn() */ + nic->check_link = alloc_workqueue("check_link_status", + WQ_UNBOUND | WQ_MEM_RECLAIM, 1); + if (!nic->check_link) { + err = -ENOMEM; + goto err_disable_sriov; + } + + INIT_DELAYED_WORK(&nic->dwork, nic_poll_for_link); + queue_delayed_work(nic->check_link, &nic->dwork, 0); + + return 0; + +err_disable_sriov: + if (nic->flags & NIC_SRIOV_ENABLED) + pci_disable_sriov(pdev); +err_unregister_interrupts: + nic_unregister_interrupts(nic); +err_release_regions: + pci_release_regions(pdev); +err_disable_device: + pci_disable_device(pdev); + pci_set_drvdata(pdev, NULL); + return err; +} + +static void nic_remove(struct pci_dev *pdev) +{ + struct nicpf *nic = pci_get_drvdata(pdev); + + if (nic->flags & NIC_SRIOV_ENABLED) + pci_disable_sriov(pdev); + + if (nic->check_link) { + /* Destroy work Queue */ + cancel_delayed_work(&nic->dwork); + flush_workqueue(nic->check_link); + destroy_workqueue(nic->check_link); + } + + nic_unregister_interrupts(nic); + pci_release_regions(pdev); + pci_disable_device(pdev); + pci_set_drvdata(pdev, NULL); +} + +static struct pci_driver nic_driver = { + .name = DRV_NAME, + .id_table = nic_id_table, + .probe = nic_probe, + .remove = nic_remove, +}; + +static int __init nic_init_module(void) +{ + pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION); + + return pci_register_driver(&nic_driver); +} + +static void __exit nic_cleanup_module(void) +{ + pci_unregister_driver(&nic_driver); +} + +module_init(nic_init_module); +module_exit(nic_cleanup_module); diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h new file mode 100644 index 0000000..58197bb --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -0,0 +1,213 @@ +/* + * Copyright (C) 2015 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#ifndef NIC_REG_H +#define NIC_REG_H + +#define NIC_PF_REG_COUNT 29573 +#define NIC_VF_REG_COUNT 249 + +/* Physical function register offsets */ +#define NIC_PF_CFG (0x0000) +#define NIC_PF_STATUS (0x0010) +#define NIC_PF_INTR_TIMER_CFG (0x0030) +#define NIC_PF_BIST_STATUS (0x0040) +#define NIC_PF_SOFT_RESET (0x0050) +#define NIC_PF_TCP_TIMER (0x0060) +#define NIC_PF_BP_CFG (0x0080) +#define NIC_PF_RRM_CFG (0x0088) +#define NIC_PF_CQM_CF (0x00A0) +#define NIC_PF_CNM_CF (0x00A8) +#define NIC_PF_CNM_STATUS (0x00B0) +#define NIC_PF_CQ_AVG_CFG (0x00C0) +#define NIC_PF_RRM_AVG_CFG (0x00C8) +#define NIC_PF_INTF_0_1_SEND_CFG (0x0200) +#define NIC_PF_INTF_0_1_BP_CFG (0x0208) +#define NIC_PF_INTF_0_1_BP_DIS_0_1 (0x0210) +#define NIC_PF_INTF_0_1_BP_SW_0_1 (0x0220) +#define NIC_PF_RBDR_BP_STATE_0_3 (0x0240) +#define NIC_PF_MAILBOX_INT (0x0410) +#define NIC_PF_MAILBOX_INT_W1S (0x0430) +#define NIC_PF_MAILBOX_ENA_W1C (0x0450) +#define NIC_PF_MAILBOX_ENA_W1S (0x0470) +#define NIC_PF_RX_ETYPE_0_7 (0x0500) +#define NIC_PF_PKIND_0_15_CFG (0x0600) +#define NIC_PF_ECC0_FLIP0 (0x1000) +#define NIC_PF_ECC1_FLIP0 (0x1008) +#define NIC_PF_ECC2_FLIP0 (0x1010) +#define NIC_PF_ECC3_FLIP0 (0x1018) +#define NIC_PF_ECC0_FLIP1 (0x1080) +#define NIC_PF_ECC1_FLIP1 (0x1088) +#define NIC_PF_ECC2_FLIP1 (0x1090) +#define NIC_PF_ECC3_FLIP1 (0x1098) +#define NIC_PF_ECC0_CDIS (0x1100) +#define NIC_PF_ECC1_CDIS (0x1108) +#define NIC_PF_ECC2_CDIS (0x1110) +#define NIC_PF_ECC3_CDIS (0x1118) +#define NIC_PF_BIST0_STATUS (0x1280) +#define NIC_PF_BIST1_STATUS (0x1288) +#define NIC_PF_BIST2_STATUS (0x1290) +#define NIC_PF_BIST3_STATUS (0x1298) +#define NIC_PF_ECC0_SBE_INT (0x2000) +#define NIC_PF_ECC0_SBE_INT_W1S (0x2008) +#define NIC_PF_ECC0_SBE_ENA_W1C (0x2010) +#define NIC_PF_ECC0_SBE_ENA_W1S (0x2018) +#define NIC_PF_ECC0_DBE_INT (0x2100) +#define NIC_PF_ECC0_DBE_INT_W1S (0x2108) +#define NIC_PF_ECC0_DBE_ENA_W1C (0x2110) +#define NIC_PF_ECC0_DBE_ENA_W1S (0x2118) +#define NIC_PF_ECC1_SBE_INT (0x2200) +#define NIC_PF_ECC1_SBE_INT_W1S (0x2208) +#define NIC_PF_ECC1_SBE_ENA_W1C (0x2210) +#define NIC_PF_ECC1_SBE_ENA_W1S (0x2218) +#define NIC_PF_ECC1_DBE_INT (0x2300) +#define NIC_PF_ECC1_DBE_INT_W1S (0x2308) +#define NIC_PF_ECC1_DBE_ENA_W1C (0x2310) +#define NIC_PF_ECC1_DBE_ENA_W1S (0x2318) +#define NIC_PF_ECC2_SBE_INT (0x2400) +#define NIC_PF_ECC2_SBE_INT_W1S (0x2408) +#define NIC_PF_ECC2_SBE_ENA_W1C (0x2410) +#define NIC_PF_ECC2_SBE_ENA_W1S (0x2418) +#define NIC_PF_ECC2_DBE_INT (0x2500) +#define NIC_PF_ECC2_DBE_INT_W1S (0x2508) +#define NIC_PF_ECC2_DBE_ENA_W1C (0x2510) +#define NIC_PF_ECC2_DBE_ENA_W1S (0x2518) +#define NIC_PF_ECC3_SBE_INT (0x2600) +#define NIC_PF_ECC3_SBE_INT_W1S (0x2608) +#define NIC_PF_ECC3_SBE_ENA_W1C (0x2610) +#define NIC_PF_ECC3_SBE_ENA_W1S (0x2618) +#define NIC_PF_ECC3_DBE_INT (0x2700) +#define NIC_PF_ECC3_DBE_INT_W1S (0x2708) +#define NIC_PF_ECC3_DBE_ENA_W1C (0x2710) +#define NIC_PF_ECC3_DBE_ENA_W1S (0x2718) +#define NIC_PF_CPI_0_2047_CFG (0x200000) +#define NIC_PF_RSSI_0_4097_RQ (0x220000) +#define NIC_PF_LMAC_0_7_CFG (0x240000) +#define NIC_PF_LMAC_0_7_SW_XOFF (0x242000) +#define NIC_PF_LMAC_0_7_CREDIT (0x244000) +#define NIC_PF_CHAN_0_255_TX_CFG (0x400000) +#define NIC_PF_CHAN_0_255_RX_CFG (0x420000) +#define NIC_PF_CHAN_0_255_SW_XOFF (0x440000) +#define NIC_PF_CHAN_0_255_CREDIT (0x460000) +#define NIC_PF_CHAN_0_255_RX_BP_CFG (0x480000) +#define NIC_PF_SW_SYNC_RX (0x490000) +#define NIC_PF_SW_SYNC_RX_DONE (0x490008) +#define NIC_PF_TL2_0_63_CFG (0x500000) +#define NIC_PF_TL2_0_63_PRI (0x520000) +#define NIC_PF_TL2_0_63_SH_STATUS (0x580000) +#define NIC_PF_TL3A_0_63_CFG (0x5F0000) +#define NIC_PF_TL3_0_255_CFG (0x600000) +#define NIC_PF_TL3_0_255_CHAN (0x620000) +#define NIC_PF_TL3_0_255_PIR (0x640000) +#define NIC_PF_TL3_0_255_SW_XOFF (0x660000) +#define NIC_PF_TL3_0_255_CNM_RATE (0x680000) +#define NIC_PF_TL3_0_255_SH_STATUS (0x6A0000) +#define NIC_PF_TL4A_0_255_CFG (0x6F0000) +#define NIC_PF_TL4_0_1023_CFG (0x800000) +#define NIC_PF_TL4_0_1023_SW_XOFF (0x820000) +#define NIC_PF_TL4_0_1023_SH_STATUS (0x840000) +#define NIC_PF_TL4A_0_1023_CNM_RATE (0x880000) +#define NIC_PF_TL4A_0_1023_CNM_STATUS (0x8A0000) +#define NIC_PF_VF_0_127_MAILBOX_0_1 (0x20002030) +#define NIC_PF_VNIC_0_127_TX_STAT_0_4 (0x20004000) +#define NIC_PF_VNIC_0_127_RX_STAT_0_13 (0x20004100) +#define NIC_PF_QSET_0_127_LOCK_0_15 (0x20006000) +#define NIC_PF_QSET_0_127_CFG (0x20010000) +#define NIC_PF_QSET_0_127_RQ_0_7_CFG (0x20010400) +#define NIC_PF_QSET_0_127_RQ_0_7_DROP_CFG (0x20010420) +#define NIC_PF_QSET_0_127_RQ_0_7_BP_CFG (0x20010500) +#define NIC_PF_QSET_0_127_RQ_0_7_STAT_0_1 (0x20010600) +#define NIC_PF_QSET_0_127_SQ_0_7_CFG (0x20010C00) +#define NIC_PF_QSET_0_127_SQ_0_7_CFG2 (0x20010C08) +#define NIC_PF_QSET_0_127_SQ_0_7_STAT_0_1 (0x20010D00) + +#define NIC_PF_MSIX_VEC_0_18_ADDR (0x000000) +#define NIC_PF_MSIX_VEC_0_CTL (0x000008) +#define NIC_PF_MSIX_PBA_0 (0x0F0000) + +/* Virtual function register offsets */ +#define NIC_VNIC_CFG (0x000020) +#define NIC_VF_PF_MAILBOX_0_1 (0x000130) +#define NIC_VF_INT (0x000200) +#define NIC_VF_INT_W1S (0x000220) +#define NIC_VF_ENA_W1C (0x000240) +#define NIC_VF_ENA_W1S (0x000260) + +#define NIC_VNIC_RSS_CFG (0x0020E0) +#define NIC_VNIC_RSS_KEY_0_4 (0x002200) +#define NIC_VNIC_TX_STAT_0_4 (0x004000) +#define NIC_VNIC_RX_STAT_0_13 (0x004100) +#define NIC_QSET_RQ_GEN_CFG (0x010010) + +#define NIC_QSET_CQ_0_7_CFG (0x010400) +#define NIC_QSET_CQ_0_7_CFG2 (0x010408) +#define NIC_QSET_CQ_0_7_THRESH (0x010410) +#define NIC_QSET_CQ_0_7_BASE (0x010420) +#define NIC_QSET_CQ_0_7_HEAD (0x010428) +#define NIC_QSET_CQ_0_7_TAIL (0x010430) +#define NIC_QSET_CQ_0_7_DOOR (0x010438) +#define NIC_QSET_CQ_0_7_STATUS (0x010440) +#define NIC_QSET_CQ_0_7_STATUS2 (0x010448) +#define NIC_QSET_CQ_0_7_DEBUG (0x010450) + +#define NIC_QSET_RQ_0_7_CFG (0x010600) +#define NIC_QSET_RQ_0_7_STAT_0_1 (0x010700) + +#define NIC_QSET_SQ_0_7_CFG (0x010800) +#define NIC_QSET_SQ_0_7_THRESH (0x010810) +#define NIC_QSET_SQ_0_7_BASE (0x010820) +#define NIC_QSET_SQ_0_7_HEAD (0x010828) +#define NIC_QSET_SQ_0_7_TAIL (0x010830) +#define NIC_QSET_SQ_0_7_DOOR (0x010838) +#define NIC_QSET_SQ_0_7_STATUS (0x010840) +#define NIC_QSET_SQ_0_7_DEBUG (0x010848) +#define NIC_QSET_SQ_0_7_CNM_CHG (0x010860) +#define NIC_QSET_SQ_0_7_STAT_0_1 (0x010900) + +#define NIC_QSET_RBDR_0_1_CFG (0x010C00) +#define NIC_QSET_RBDR_0_1_THRESH (0x010C10) +#define NIC_QSET_RBDR_0_1_BASE (0x010C20) +#define NIC_QSET_RBDR_0_1_HEAD (0x010C28) +#define NIC_QSET_RBDR_0_1_TAIL (0x010C30) +#define NIC_QSET_RBDR_0_1_DOOR (0x010C38) +#define NIC_QSET_RBDR_0_1_STATUS0 (0x010C40) +#define NIC_QSET_RBDR_0_1_STATUS1 (0x010C48) +#define NIC_QSET_RBDR_0_1_PREFETCH_STATUS (0x010C50) + +#define NIC_VF_MSIX_VECTOR_0_19_ADDR (0x000000) +#define NIC_VF_MSIX_VECTOR_0_19_CTL (0x000008) +#define NIC_VF_MSIX_PBA (0x0F0000) + +/* Offsets within registers */ +#define NIC_MSIX_VEC_SHIFT 4 +#define NIC_Q_NUM_SHIFT 18 +#define NIC_QS_ID_SHIFT 21 +#define NIC_VF_NUM_SHIFT 21 + +/* Port kind configuration register */ +struct pkind_cfg { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 reserved_42_63:22; + u64 hdr_sl:5; /* Header skip length */ + u64 rx_hdr:3; /* TNS Receive header present */ + u64 lenerr_en:1;/* L2 length error check enable */ + u64 reserved_32_32:1; + u64 maxlen:16; /* Max frame size */ + u64 minlen:16; /* Min frame size */ +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 minlen:16; + u64 maxlen:16; + u64 reserved_32_32:1; + u64 lenerr_en:1; + u64 rx_hdr:3; + u64 hdr_sl:5; + u64 reserved_42_63:22; +#endif +}; + +#endif /* NIC_REG_H */ diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c new file mode 100644 index 0000000..16bd2d7 --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -0,0 +1,600 @@ +/* + * Copyright (C) 2015 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +/* ETHTOOL Support for VNIC_VF Device*/ + +#include <linux/pci.h> + +#include "nic_reg.h" +#include "nic.h" +#include "nicvf_queues.h" +#include "q_struct.h" +#include "thunder_bgx.h" + +#define DRV_NAME "thunder-nicvf" +#define DRV_VERSION "1.0" + +struct nicvf_stat { + char name[ETH_GSTRING_LEN]; + unsigned int index; +}; + +#define NICVF_HW_STAT(stat) { \ + .name = #stat, \ + .index = offsetof(struct nicvf_hw_stats, stat) / sizeof(u64), \ +} + +#define NICVF_DRV_STAT(stat) { \ + .name = #stat, \ + .index = offsetof(struct nicvf_drv_stats, stat) / sizeof(u64), \ +} + +static const struct nicvf_stat nicvf_hw_stats[] = { + NICVF_HW_STAT(rx_bytes_ok), + NICVF_HW_STAT(rx_ucast_frames_ok), + NICVF_HW_STAT(rx_bcast_frames_ok), + NICVF_HW_STAT(rx_mcast_frames_ok), + NICVF_HW_STAT(rx_fcs_errors), + NICVF_HW_STAT(rx_l2_errors), + NICVF_HW_STAT(rx_drop_red), + NICVF_HW_STAT(rx_drop_red_bytes), + NICVF_HW_STAT(rx_drop_overrun), + NICVF_HW_STAT(rx_drop_overrun_bytes), + NICVF_HW_STAT(rx_drop_bcast), + NICVF_HW_STAT(rx_drop_mcast), + NICVF_HW_STAT(rx_drop_l3_bcast), + NICVF_HW_STAT(rx_drop_l3_mcast), + NICVF_HW_STAT(tx_bytes_ok), + NICVF_HW_STAT(tx_ucast_frames_ok), + NICVF_HW_STAT(tx_bcast_frames_ok), + NICVF_HW_STAT(tx_mcast_frames_ok), +}; + +static const struct nicvf_stat nicvf_drv_stats[] = { + NICVF_DRV_STAT(rx_frames_ok), + NICVF_DRV_STAT(rx_frames_64), + NICVF_DRV_STAT(rx_frames_127), + NICVF_DRV_STAT(rx_frames_255), + NICVF_DRV_STAT(rx_frames_511), + NICVF_DRV_STAT(rx_frames_1023), + NICVF_DRV_STAT(rx_frames_1518), + NICVF_DRV_STAT(rx_frames_jumbo), + NICVF_DRV_STAT(rx_drops), + NICVF_DRV_STAT(tx_frames_ok), + NICVF_DRV_STAT(tx_busy), + NICVF_DRV_STAT(tx_tso), + NICVF_DRV_STAT(tx_drops), +}; + +static const struct nicvf_stat nicvf_queue_stats[] = { + { "bytes", 0 }, + { "frames", 1 }, +}; + +static const unsigned int nicvf_n_hw_stats = ARRAY_SIZE(nicvf_hw_stats); +static const unsigned int nicvf_n_drv_stats = ARRAY_SIZE(nicvf_drv_stats); +static const unsigned int nicvf_n_queue_stats = ARRAY_SIZE(nicvf_queue_stats); + +static int nicvf_get_settings(struct net_device *netdev, + struct ethtool_cmd *cmd) +{ + struct nicvf *nic = netdev_priv(netdev); + + cmd->supported = 0; + cmd->transceiver = XCVR_EXTERNAL; + if (nic->speed <= 1000) { + cmd->port = PORT_MII; + cmd->autoneg = AUTONEG_ENABLE; + } else { + cmd->port = PORT_FIBRE; + cmd->autoneg = AUTONEG_DISABLE; + } + cmd->duplex = nic->duplex; + ethtool_cmd_speed_set(cmd, nic->speed); + + return 0; +} + +static void nicvf_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *info) +{ + struct nicvf *nic = netdev_priv(netdev); + + strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); + strlcpy(info->version, DRV_VERSION, sizeof(info->version)); + strlcpy(info->bus_info, pci_name(nic->pdev), sizeof(info->bus_info)); +} + +static u32 nicvf_get_msglevel(struct net_device *netdev) +{ + struct nicvf *nic = netdev_priv(netdev); + + return nic->msg_enable; +} + +static void nicvf_set_msglevel(struct net_device *netdev, u32 lvl) +{ + struct nicvf *nic = netdev_priv(netdev); + + nic->msg_enable = lvl; +} + +static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data) +{ + int stats, qidx; + + if (sset != ETH_SS_STATS) + return; + + for (stats = 0; stats < nicvf_n_hw_stats; stats++) { + memcpy(data, nicvf_hw_stats[stats].name, ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + + for (stats = 0; stats < nicvf_n_drv_stats; stats++) { + memcpy(data, nicvf_drv_stats[stats].name, ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + + for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) { + for (stats = 0; stats < nicvf_n_queue_stats; stats++) { + sprintf(data, "rxq%d: %s", qidx, + nicvf_queue_stats[stats].name); + data += ETH_GSTRING_LEN; + } + } + + for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) { + for (stats = 0; stats < nicvf_n_queue_stats; stats++) { + sprintf(data, "txq%d: %s", qidx, + nicvf_queue_stats[stats].name); + data += ETH_GSTRING_LEN; + } + } + + for (stats = 0; stats < BGX_RX_STATS_COUNT; stats++) { + sprintf(data, "bgx_rxstat%d: ", stats); + data += ETH_GSTRING_LEN; + } + + for (stats = 0; stats < BGX_TX_STATS_COUNT; stats++) { + sprintf(data, "bgx_txstat%d: ", stats); + data += ETH_GSTRING_LEN; + } +} + +static int nicvf_get_sset_count(struct net_device *netdev, int sset) +{ + if (sset != ETH_SS_STATS) + return -EINVAL; + + return nicvf_n_hw_stats + nicvf_n_drv_stats + + (nicvf_n_queue_stats * + (MAX_RCV_QUEUES_PER_QS + MAX_SND_QUEUES_PER_QS)) + + BGX_RX_STATS_COUNT + BGX_TX_STATS_COUNT; +} + +static void nicvf_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) +{ + struct nicvf *nic = netdev_priv(netdev); + int stat, qidx; + + nicvf_update_stats(nic); + + /* Update LMAC stats */ + nicvf_update_lmac_stats(nic); + + for (stat = 0; stat < nicvf_n_hw_stats; stat++) + *(data++) = ((u64 *)&nic->stats) + [nicvf_hw_stats[stat].index]; + for (stat = 0; stat < nicvf_n_drv_stats; stat++) + *(data++) = ((u64 *)&nic->drv_stats) + [nicvf_drv_stats[stat].index]; + + for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) { + for (stat = 0; stat < nicvf_n_queue_stats; stat++) + *(data++) = ((u64 *)&nic->qs->rq[qidx].stats) + [nicvf_queue_stats[stat].index]; + } + + for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) { + for (stat = 0; stat < nicvf_n_queue_stats; stat++) + *(data++) = ((u64 *)&nic->qs->sq[qidx].stats) + [nicvf_queue_stats[stat].index]; + } + + for (stat = 0; stat < BGX_RX_STATS_COUNT; stat++) + *(data++) = nic->bgx_stats.rx_stats[stat]; + for (stat = 0; stat < BGX_TX_STATS_COUNT; stat++) + *(data++) = nic->bgx_stats.tx_stats[stat]; +} + +static int nicvf_get_regs_len(struct net_device *dev) +{ + return sizeof(u64) * NIC_VF_REG_COUNT; +} + +static void nicvf_get_regs(struct net_device *dev, + struct ethtool_regs *regs, void *reg) +{ + struct nicvf *nic = netdev_priv(dev); + u64 *p = (u64 *)reg; + u64 reg_offset; + int mbox, key, stat, q; + int i = 0; + + regs->version = 0; + memset(p, 0, NIC_VF_REG_COUNT); + + p[i++] = nicvf_reg_read(nic, NIC_VNIC_CFG); + /* Mailbox registers */ + for (mbox = 0; mbox < NIC_PF_VF_MAILBOX_SIZE; mbox++) + p[i++] = nicvf_reg_read(nic, + NIC_VF_PF_MAILBOX_0_1 | (mbox << 3)); + + p[i++] = nicvf_reg_read(nic, NIC_VF_INT); + p[i++] = nicvf_reg_read(nic, NIC_VF_INT_W1S); + p[i++] = nicvf_reg_read(nic, NIC_VF_ENA_W1C); + p[i++] = nicvf_reg_read(nic, NIC_VF_ENA_W1S); + p[i++] = nicvf_reg_read(nic, NIC_VNIC_RSS_CFG); + + for (key = 0; key < RSS_HASH_KEY_SIZE; key++) + p[i++] = nicvf_reg_read(nic, NIC_VNIC_RSS_KEY_0_4 | (key << 3)); + + /* Tx/Rx statistics */ + for (stat = 0; stat < TX_STATS_ENUM_LAST; stat++) + p[i++] = nicvf_reg_read(nic, + NIC_VNIC_TX_STAT_0_4 | (stat << 3)); + + for (i = 0; i < RX_STATS_ENUM_LAST; i++) + p[i++] = nicvf_reg_read(nic, + NIC_VNIC_RX_STAT_0_13 | (stat << 3)); + + p[i++] = nicvf_reg_read(nic, NIC_QSET_RQ_GEN_CFG); + + /* All completion queue's registers */ + for (q = 0; q < MAX_CMP_QUEUES_PER_QS; q++) { + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_CFG, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_CFG2, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_THRESH, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_BASE, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_TAIL, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_DOOR, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_STATUS, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_STATUS2, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_DEBUG, q); + } + + /* All receive queue's registers */ + for (q = 0; q < MAX_RCV_QUEUES_PER_QS; q++) { + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RQ_0_7_CFG, q); + p[i++] = nicvf_queue_reg_read(nic, + NIC_QSET_RQ_0_7_STAT_0_1, q); + reg_offset = NIC_QSET_RQ_0_7_STAT_0_1 | (1 << 3); + p[i++] = nicvf_queue_reg_read(nic, reg_offset, q); + } + + for (q = 0; q < MAX_SND_QUEUES_PER_QS; q++) { + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CFG, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_THRESH, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_BASE, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_HEAD, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_TAIL, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DOOR, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STATUS, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DEBUG, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CNM_CHG, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STAT_0_1, q); + reg_offset = NIC_QSET_SQ_0_7_STAT_0_1 | (1 << 3); + p[i++] = nicvf_queue_reg_read(nic, reg_offset, q); + } + + for (q = 0; q < MAX_RCV_BUF_DESC_RINGS_PER_QS; q++) { + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_CFG, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_THRESH, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_BASE, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_HEAD, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_TAIL, q); + p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_DOOR, q); + p[i++] = nicvf_queue_reg_read(nic, + NIC_QSET_RBDR_0_1_STATUS0, q); + p[i++] = nicvf_queue_reg_read(nic, + NIC_QSET_RBDR_0_1_STATUS1, q); + reg_offset = NIC_QSET_RBDR_0_1_PREFETCH_STATUS; + p[i++] = nicvf_queue_reg_read(nic, reg_offset, q); + } +} + +static int nicvf_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *cmd) +{ + struct nicvf *nic = netdev_priv(netdev); + + cmd->rx_coalesce_usecs = nic->cq_coalesce_usecs; + return 0; +} + +static void nicvf_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct nicvf *nic = netdev_priv(netdev); + struct queue_set *qs = nic->qs; + + ring->rx_max_pending = MAX_RCV_BUF_COUNT; + ring->rx_pending = qs->rbdr_len; + ring->tx_max_pending = MAX_SND_QUEUE_LEN; + ring->tx_pending = qs->sq_len; +} + +static int nicvf_get_rss_hash_opts(struct nicvf *nic, + struct ethtool_rxnfc *info) +{ + info->data = 0; + + switch (info->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + case UDP_V4_FLOW: + case UDP_V6_FLOW: + case SCTP_V4_FLOW: + case SCTP_V6_FLOW: + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + case IPV4_FLOW: + case IPV6_FLOW: + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int nicvf_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *info, u32 *rules) +{ + struct nicvf *nic = netdev_priv(dev); + int ret = -EOPNOTSUPP; + + switch (info->cmd) { + case ETHTOOL_GRXRINGS: + info->data = nic->qs->rq_cnt; + ret = 0; + break; + case ETHTOOL_GRXFH: + return nicvf_get_rss_hash_opts(nic, info); + default: + break; + } + return ret; +} + +static int nicvf_set_rss_hash_opts(struct nicvf *nic, + struct ethtool_rxnfc *info) +{ + struct nicvf_rss_info *rss = &nic->rss_info; + u64 rss_cfg = nicvf_reg_read(nic, NIC_VNIC_RSS_CFG); + + if (!rss->enable) + netdev_err(nic->netdev, + "RSS is disabled, hash cannot be set\n"); + + netdev_info(nic->netdev, "Set RSS flow type = %d, data = %lld\n", + info->flow_type, info->data); + + if (!(info->data & RXH_IP_SRC) || !(info->data & RXH_IP_DST)) + return -EINVAL; + + switch (info->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + switch (info->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_cfg &= ~(1ULL << RSS_HASH_TCP); + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_cfg |= (1ULL << RSS_HASH_TCP); + break; + default: + return -EINVAL; + } + break; + case UDP_V4_FLOW: + case UDP_V6_FLOW: + switch (info->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_cfg &= ~(1ULL << RSS_HASH_UDP); + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_cfg |= (1ULL << RSS_HASH_UDP); + break; + default: + return -EINVAL; + } + break; + case SCTP_V4_FLOW: + case SCTP_V6_FLOW: + switch (info->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_cfg &= ~(1ULL << RSS_HASH_L4ETC); + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_cfg |= (1ULL << RSS_HASH_L4ETC); + break; + default: + return -EINVAL; + } + break; + case IPV4_FLOW: + case IPV6_FLOW: + rss_cfg = RSS_HASH_IP; + break; + default: + return -EINVAL; + } + + nicvf_reg_write(nic, NIC_VNIC_RSS_CFG, rss_cfg); + return 0; +} + +static int nicvf_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) +{ + struct nicvf *nic = netdev_priv(dev); + + switch (info->cmd) { + case ETHTOOL_SRXFH: + return nicvf_set_rss_hash_opts(nic, info); + default: + break; + } + return -EOPNOTSUPP; +} + +static u32 nicvf_get_rxfh_key_size(struct net_device *netdev) +{ + return RSS_HASH_KEY_SIZE * sizeof(u64); +} + +static u32 nicvf_get_rxfh_indir_size(struct net_device *dev) +{ + struct nicvf *nic = netdev_priv(dev); + + return nic->rss_info.rss_size; +} + +static int nicvf_get_rxfh(struct net_device *dev, u32 *indir, u8 *hkey, + u8 *hfunc) +{ + struct nicvf *nic = netdev_priv(dev); + struct nicvf_rss_info *rss = &nic->rss_info; + int idx; + + if (indir) { + for (idx = 0; idx < rss->rss_size; idx++) + indir[idx] = rss->ind_tbl[idx]; + } + + if (hkey) + memcpy(hkey, rss->key, RSS_HASH_KEY_SIZE * sizeof(u64)); + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + return 0; +} + +static int nicvf_set_rxfh(struct net_device *dev, const u32 *indir, + const u8 *hkey, u8 hfunc) +{ + struct nicvf *nic = netdev_priv(dev); + struct nicvf_rss_info *rss = &nic->rss_info; + int idx; + + if ((nic->qs->rq_cnt <= 1) || (nic->cpi_alg != CPI_ALG_NONE)) { + rss->enable = false; + rss->hash_bits = 0; + return -EIO; + } + + /* We do not allow change in unsupported parameters */ + if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) + return -EOPNOTSUPP; + + rss->enable = true; + if (indir) { + for (idx = 0; idx < rss->rss_size; idx++) + rss->ind_tbl[idx] = indir[idx]; + } + + if (hkey) { + memcpy(rss->key, hkey, RSS_HASH_KEY_SIZE * sizeof(u64)); + nicvf_set_rss_key(nic); + } + + nicvf_config_rss(nic); + return 0; +} + +/* Get no of queues device supports and current queue count */ +static void nicvf_get_channels(struct net_device *dev, + struct ethtool_channels *channel) +{ + struct nicvf *nic = netdev_priv(dev); + + memset(channel, 0, sizeof(*channel)); + + channel->max_rx = MAX_RCV_QUEUES_PER_QS; + channel->max_tx = MAX_SND_QUEUES_PER_QS; + + channel->rx_count = nic->qs->rq_cnt; + channel->tx_count = nic->qs->sq_cnt; +} + +/* Set no of Tx, Rx queues to be used */ +static int nicvf_set_channels(struct net_device *dev, + struct ethtool_channels *channel) +{ + struct nicvf *nic = netdev_priv(dev); + int err = 0; + + if (!channel->rx_count || !channel->tx_count) + return -EINVAL; + if (channel->rx_count > MAX_RCV_QUEUES_PER_QS) + return -EINVAL; + if (channel->tx_count > MAX_SND_QUEUES_PER_QS) + return -EINVAL; + + nic->qs->rq_cnt = channel->rx_count; + nic->qs->sq_cnt = channel->tx_count; + nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt); + + err = nicvf_set_real_num_queues(dev, nic->qs->sq_cnt, nic->qs->rq_cnt); + if (err) + return err; + + if (!netif_running(dev)) + return err; + + nicvf_stop(dev); + nicvf_open(dev); + netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n", + nic->qs->sq_cnt, nic->qs->rq_cnt); + + return err; +} + +static const struct ethtool_ops nicvf_ethtool_ops = { + .get_settings = nicvf_get_settings, + .get_link = ethtool_op_get_link, + .get_drvinfo = nicvf_get_drvinfo, + .get_msglevel = nicvf_get_msglevel, + .set_msglevel = nicvf_set_msglevel, + .get_strings = nicvf_get_strings, + .get_sset_count = nicvf_get_sset_count, + .get_ethtool_stats = nicvf_get_ethtool_stats, + .get_regs_len = nicvf_get_regs_len, + .get_regs = nicvf_get_regs, + .get_coalesce = nicvf_get_coalesce, + .get_ringparam = nicvf_get_ringparam, + .get_rxnfc = nicvf_get_rxnfc, + .set_rxnfc = nicvf_set_rxnfc, + .get_rxfh_key_size = nicvf_get_rxfh_key_size, + .get_rxfh_indir_size = nicvf_get_rxfh_indir_size, + .get_rxfh = nicvf_get_rxfh, + .set_rxfh = nicvf_set_rxfh, + .get_channels = nicvf_get_channels, + .set_channels = nicvf_set_channels, + .get_ts_info = ethtool_op_get_ts_info, +}; + +void nicvf_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &nicvf_ethtool_ops; +} diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c new file mode 100644 index 0000000..02da802 --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -0,0 +1,1331 @@ +/* + * Copyright (C) 2015 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/ethtool.h> +#include <linux/log2.h> +#include <linux/prefetch.h> +#include <linux/irq.h> + +#include "nic_reg.h" +#include "nic.h" +#include "nicvf_queues.h" +#include "thunder_bgx.h" + +#define DRV_NAME "thunder-nicvf" +#define DRV_VERSION "1.0" + +/* Supported devices */ +static const struct pci_device_id nicvf_id_table[] = { + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, + PCI_DEVICE_ID_THUNDER_NIC_VF, + PCI_VENDOR_ID_CAVIUM, 0xA11E) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, + PCI_DEVICE_ID_THUNDER_PASS1_NIC_VF, + PCI_VENDOR_ID_CAVIUM, 0xA11E) }, + { 0, } /* end of table */ +}; + +MODULE_AUTHOR("Sunil Goutham"); +MODULE_DESCRIPTION("Cavium Thunder NIC Virtual Function Driver"); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION(DRV_VERSION); +MODULE_DEVICE_TABLE(pci, nicvf_id_table); + +static int debug = 0x00; +module_param(debug, int, 0644); +MODULE_PARM_DESC(debug, "Debug message level bitmap"); + +static int cpi_alg = CPI_ALG_NONE; +module_param(cpi_alg, int, S_IRUGO); +MODULE_PARM_DESC(cpi_alg, + "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)"); + +static inline void nicvf_set_rx_frame_cnt(struct nicvf *nic, + struct sk_buff *skb) +{ + if (skb->len <= 64) + nic->drv_stats.rx_frames_64++; + else if (skb->len <= 127) + nic->drv_stats.rx_frames_127++; + else if (skb->len <= 255) + nic->drv_stats.rx_frames_255++; + else if (skb->len <= 511) + nic->drv_stats.rx_frames_511++; + else if (skb->len <= 1023) + nic->drv_stats.rx_frames_1023++; + else if (skb->len <= 1518) + nic->drv_stats.rx_frames_1518++; + else + nic->drv_stats.rx_frames_jumbo++; +} + +/* The Cavium ThunderX network controller can *only* be found in SoCs + * containing the ThunderX ARM64 CPU implementation. All accesses to the device + * registers on this platform are implicitly strongly ordered with respect + * to memory accesses. So writeq_relaxed() and readq_relaxed() are safe to use + * with no memory barriers in this driver. The readq()/writeq() functions add + * explicit ordering operation which in this case are redundant, and only + * add overhead. + */ + +/* Register read/write APIs */ +void nicvf_reg_write(struct nicvf *nic, u64 offset, u64 val) +{ + writeq_relaxed(val, nic->reg_base + offset); +} + +u64 nicvf_reg_read(struct nicvf *nic, u64 offset) +{ + return readq_relaxed(nic->reg_base + offset); +} + +void nicvf_queue_reg_write(struct nicvf *nic, u64 offset, + u64 qidx, u64 val) +{ + void __iomem *addr = nic->reg_base + offset; + + writeq_relaxed(val, addr + (qidx << NIC_Q_NUM_SHIFT)); +} + +u64 nicvf_queue_reg_read(struct nicvf *nic, u64 offset, u64 qidx) +{ + void __iomem *addr = nic->reg_base + offset; + + return readq_relaxed(addr + (qidx << NIC_Q_NUM_SHIFT)); +} + +/* VF -> PF mailbox communication */ + +static void nicvf_write_to_mbx(struct nicvf *nic, union nic_mbx *mbx) +{ + u64 *msg = (u64 *)mbx; + + nicvf_reg_write(nic, NIC_VF_PF_MAILBOX_0_1 + 0, msg[0]); + nicvf_reg_write(nic, NIC_VF_PF_MAILBOX_0_1 + 8, msg[1]); +} + +int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx) +{ + int timeout = NIC_MBOX_MSG_TIMEOUT; + int sleep = 10; + + nic->pf_acked = false; + nic->pf_nacked = false; + + nicvf_write_to_mbx(nic, mbx); + + /* Wait for previous message to be acked, timeout 2sec */ + while (!nic->pf_acked) { + if (nic->pf_nacked) + return -EINVAL; + msleep(sleep); + if (nic->pf_acked) + break; + timeout -= sleep; + if (!timeout) { + netdev_err(nic->netdev, + "PF didn't ack to mbox msg %d from VF%d\n", + (mbx->msg.msg & 0xFF), nic->vf_id); + return -EBUSY; + } + } + return 0; +} + +/* Checks if VF is able to comminicate with PF +* and also gets the VNIC number this VF is associated to. +*/ +static int nicvf_check_pf_ready(struct nicvf *nic) +{ + int timeout = 5000, sleep = 20; + union nic_mbx mbx = {}; + + mbx.msg.msg = NIC_MBOX_MSG_READY; + + nic->pf_ready_to_rcv_msg = false; + + nicvf_write_to_mbx(nic, &mbx); + + while (!nic->pf_ready_to_rcv_msg) { + msleep(sleep); + if (nic->pf_ready_to_rcv_msg) + break; + timeout -= sleep; + if (!timeout) { + netdev_err(nic->netdev, + "PF didn't respond to READY msg\n"); + return 0; + } + } + return 1; +} + +static void nicvf_read_bgx_stats(struct nicvf *nic, struct bgx_stats_msg *bgx) +{ + if (bgx->rx) + nic->bgx_stats.rx_stats[bgx->idx] = bgx->stats; + else + nic->bgx_stats.tx_stats[bgx->idx] = bgx->stats; +} + +static void nicvf_handle_mbx_intr(struct nicvf *nic) +{ + union nic_mbx mbx = {}; + u64 *mbx_data; + u64 mbx_addr; + int i; + + mbx_addr = NIC_VF_PF_MAILBOX_0_1; + mbx_data = (u64 *)&mbx; + + for (i = 0; i < NIC_PF_VF_MAILBOX_SIZE; i++) { + *mbx_data = nicvf_reg_read(nic, mbx_addr); + mbx_data++; + mbx_addr += sizeof(u64); + } + + netdev_dbg(nic->netdev, "Mbox message: msg: 0x%x\n", mbx.msg.msg); + switch (mbx.msg.msg) { + case NIC_MBOX_MSG_READY: + nic->pf_ready_to_rcv_msg = true; + nic->vf_id = mbx.nic_cfg.vf_id & 0x7F; + nic->tns_mode = mbx.nic_cfg.tns_mode & 0x7F; + nic->node = mbx.nic_cfg.node_id; + ether_addr_copy(nic->netdev->dev_addr, mbx.nic_cfg.mac_addr); + nic->link_up = false; + nic->duplex = 0; + nic->speed = 0; + break; + case NIC_MBOX_MSG_ACK: + nic->pf_acked = true; + break; + case NIC_MBOX_MSG_NACK: + nic->pf_nacked = true; + break; + case NIC_MBOX_MSG_RSS_SIZE: + nic->rss_info.rss_size = mbx.rss_size.ind_tbl_size; + nic->pf_acked = true; + break; + case NIC_MBOX_MSG_BGX_STATS: + nicvf_read_bgx_stats(nic, &mbx.bgx_stats); + nic->pf_acked = true; + nic->bgx_stats_acked = true; + break; + case NIC_MBOX_MSG_BGX_LINK_CHANGE: + nic->pf_acked = true; + nic->link_up = mbx.link_status.link_up; + nic->duplex = mbx.link_status.duplex; + nic->speed = mbx.link_status.speed; + if (nic->link_up) { + netdev_info(nic->netdev, "%s: Link is Up %d Mbps %s\n", + nic->netdev->name, nic->speed, + nic->duplex == DUPLEX_FULL ? + "Full duplex" : "Half duplex"); + netif_carrier_on(nic->netdev); + netif_tx_wake_all_queues(nic->netdev); + } else { + netdev_info(nic->netdev, "%s: Link is Down\n", + nic->netdev->name); + netif_carrier_off(nic->netdev); + netif_tx_stop_all_queues(nic->netdev); + } + break; + default: + netdev_err(nic->netdev, + "Invalid message from PF, msg 0x%x\n", mbx.msg.msg); + break; + } + nicvf_clear_intr(nic, NICVF_INTR_MBOX, 0); +} + +static int nicvf_hw_set_mac_addr(struct nicvf *nic, struct net_device *netdev) +{ + union nic_mbx mbx = {}; + + mbx.mac.msg = NIC_MBOX_MSG_SET_MAC; + mbx.mac.vf_id = nic->vf_id; + ether_addr_copy(mbx.mac.mac_addr, netdev->dev_addr); + + return nicvf_send_msg_to_pf(nic, &mbx); +} + +static void nicvf_config_cpi(struct nicvf *nic) +{ + union nic_mbx mbx = {}; + + mbx.cpi_cfg.msg = NIC_MBOX_MSG_CPI_CFG; + mbx.cpi_cfg.vf_id = nic->vf_id; + mbx.cpi_cfg.cpi_alg = nic->cpi_alg; + mbx.cpi_cfg.rq_cnt = nic->qs->rq_cnt; + + nicvf_send_msg_to_pf(nic, &mbx); +} + +static void nicvf_get_rss_size(struct nicvf *nic) +{ + union nic_mbx mbx = {}; + + mbx.rss_size.msg = NIC_MBOX_MSG_RSS_SIZE; + mbx.rss_size.vf_id = nic->vf_id; + nicvf_send_msg_to_pf(nic, &mbx); +} + +void nicvf_config_rss(struct nicvf *nic) +{ + union nic_mbx mbx = {}; + struct nicvf_rss_info *rss = &nic->rss_info; + int ind_tbl_len = rss->rss_size; + int i, nextq = 0; + + mbx.rss_cfg.vf_id = nic->vf_id; + mbx.rss_cfg.hash_bits = rss->hash_bits; + while (ind_tbl_len) { + mbx.rss_cfg.tbl_offset = nextq; + mbx.rss_cfg.tbl_len = min(ind_tbl_len, + RSS_IND_TBL_LEN_PER_MBX_MSG); + mbx.rss_cfg.msg = mbx.rss_cfg.tbl_offset ? + NIC_MBOX_MSG_RSS_CFG_CONT : NIC_MBOX_MSG_RSS_CFG; + + for (i = 0; i < mbx.rss_cfg.tbl_len; i++) + mbx.rss_cfg.ind_tbl[i] = rss->ind_tbl[nextq++]; + + nicvf_send_msg_to_pf(nic, &mbx); + + ind_tbl_len -= mbx.rss_cfg.tbl_len; + } +} + +void nicvf_set_rss_key(struct nicvf *nic) +{ + struct nicvf_rss_info *rss = &nic->rss_info; + u64 key_addr = NIC_VNIC_RSS_KEY_0_4; + int idx; + + for (idx = 0; idx < RSS_HASH_KEY_SIZE; idx++) { + nicvf_reg_write(nic, key_addr, rss->key[idx]); + key_addr += sizeof(u64); + } +} + +static int nicvf_rss_init(struct nicvf *nic) +{ + struct nicvf_rss_info *rss = &nic->rss_info; + int idx; + + nicvf_get_rss_size(nic); + + if ((nic->qs->rq_cnt <= 1) || (cpi_alg != CPI_ALG_NONE)) { + rss->enable = false; + rss->hash_bits = 0; + return 0; + } + + rss->enable = true; + + /* Using the HW reset value for now */ + rss->key[0] = 0xFEED0BADFEED0BADULL; + rss->key[1] = 0xFEED0BADFEED0BADULL; + rss->key[2] = 0xFEED0BADFEED0BADULL; + rss->key[3] = 0xFEED0BADFEED0BADULL; + rss->key[4] = 0xFEED0BADFEED0BADULL; + + nicvf_set_rss_key(nic); + + rss->cfg = RSS_IP_HASH_ENA | RSS_TCP_HASH_ENA | RSS_UDP_HASH_ENA; + nicvf_reg_write(nic, NIC_VNIC_RSS_CFG, rss->cfg); + + rss->hash_bits = ilog2(rounddown_pow_of_two(rss->rss_size)); + + for (idx = 0; idx < rss->rss_size; idx++) + rss->ind_tbl[idx] = ethtool_rxfh_indir_default(idx, + nic->qs->rq_cnt); + nicvf_config_rss(nic); + return 1; +} + +int nicvf_set_real_num_queues(struct net_device *netdev, + int tx_queues, int rx_queues) +{ + int err = 0; + + err = netif_set_real_num_tx_queues(netdev, tx_queues); + if (err) { + netdev_err(netdev, + "Failed to set no of Tx queues: %d\n", tx_queues); + return err; + } + + err = netif_set_real_num_rx_queues(netdev, rx_queues); + if (err) + netdev_err(netdev, + "Failed to set no of Rx queues: %d\n", rx_queues); + return err; +} + +static int nicvf_init_resources(struct nicvf *nic) +{ + int err; + union nic_mbx mbx = {}; + + mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; + + /* Enable Qset */ + nicvf_qset_config(nic, true); + + /* Initialize queues and HW for data transfer */ + err = nicvf_config_data_transfer(nic, true); + if (err) { + netdev_err(nic->netdev, + "Failed to alloc/config VF's QSet resources\n"); + return err; + } + + /* Send VF config done msg to PF */ + nicvf_write_to_mbx(nic, &mbx); + + return 0; +} + +static void nicvf_snd_pkt_handler(struct net_device *netdev, + struct cmp_queue *cq, + struct cqe_send_t *cqe_tx, int cqe_type) +{ + struct sk_buff *skb = NULL; + struct nicvf *nic = netdev_priv(netdev); + struct snd_queue *sq; + struct sq_hdr_subdesc *hdr; + + sq = &nic->qs->sq[cqe_tx->sq_idx]; + + hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, cqe_tx->sqe_ptr); + if (hdr->subdesc_type != SQ_DESC_TYPE_HEADER) + return; + + netdev_dbg(nic->netdev, + "%s Qset #%d SQ #%d SQ ptr #%d subdesc count %d\n", + __func__, cqe_tx->sq_qs, cqe_tx->sq_idx, + cqe_tx->sqe_ptr, hdr->subdesc_cnt); + + nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1); + nicvf_check_cqe_tx_errs(nic, cq, cqe_tx); + skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr]; + /* For TSO offloaded packets only one head SKB needs to be freed */ + if (skb) { + prefetch(skb); + dev_consume_skb_any(skb); + } +} + +static void nicvf_rcv_pkt_handler(struct net_device *netdev, + struct napi_struct *napi, + struct cmp_queue *cq, + struct cqe_rx_t *cqe_rx, int cqe_type) +{ + struct sk_buff *skb; + struct nicvf *nic = netdev_priv(netdev); + int err = 0; + + /* Check for errors */ + err = nicvf_check_cqe_rx_errs(nic, cq, cqe_rx); + if (err && !cqe_rx->rb_cnt) + return; + + skb = nicvf_get_rcv_skb(nic, cqe_rx); + if (!skb) { + netdev_dbg(nic->netdev, "Packet not received\n"); + return; + } + + if (netif_msg_pktdata(nic)) { + netdev_info(nic->netdev, "%s: skb 0x%p, len=%d\n", netdev->name, + skb, skb->len); + print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 1, + skb->data, skb->len, true); + } + + nicvf_set_rx_frame_cnt(nic, skb); + + skb_record_rx_queue(skb, cqe_rx->rq_idx); + if (netdev->hw_features & NETIF_F_RXCSUM) { + /* HW by default verifies TCP/UDP/SCTP checksums */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + } else { + skb_checksum_none_assert(skb); + } + + skb->protocol = eth_type_trans(skb, netdev); + + if (napi && (netdev->features & NETIF_F_GRO)) + napi_gro_receive(napi, skb); + else + netif_receive_skb(skb); +} + +static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx, + struct napi_struct *napi, int budget) +{ + int processed_cqe, work_done = 0; + int cqe_count, cqe_head; + struct nicvf *nic = netdev_priv(netdev); + struct queue_set *qs = nic->qs; + struct cmp_queue *cq = &qs->cq[cq_idx]; + struct cqe_rx_t *cq_desc; + + spin_lock_bh(&cq->lock); +loop: + processed_cqe = 0; + /* Get no of valid CQ entries to process */ + cqe_count = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_STATUS, cq_idx); + cqe_count &= CQ_CQE_COUNT; + if (!cqe_count) + goto done; + + /* Get head of the valid CQ entries */ + cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9; + cqe_head &= 0xFFFF; + + netdev_dbg(nic->netdev, "%s cqe_count %d cqe_head %d\n", + __func__, cqe_count, cqe_head); + while (processed_cqe < cqe_count) { + /* Get the CQ descriptor */ + cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head); + cqe_head++; + cqe_head &= (cq->dmem.q_len - 1); + /* Initiate prefetch for next descriptor */ + prefetch((struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head)); + + if ((work_done >= budget) && napi && + (cq_desc->cqe_type != CQE_TYPE_SEND)) { + break; + } + + netdev_dbg(nic->netdev, "cq_desc->cqe_type %d\n", + cq_desc->cqe_type); + switch (cq_desc->cqe_type) { + case CQE_TYPE_RX: + nicvf_rcv_pkt_handler(netdev, napi, cq, + cq_desc, CQE_TYPE_RX); + work_done++; + break; + case CQE_TYPE_SEND: + nicvf_snd_pkt_handler(netdev, cq, + (void *)cq_desc, CQE_TYPE_SEND); + break; + case CQE_TYPE_INVALID: + case CQE_TYPE_RX_SPLIT: + case CQE_TYPE_RX_TCP: + case CQE_TYPE_SEND_PTP: + /* Ignore for now */ + break; + } + processed_cqe++; + } + netdev_dbg(nic->netdev, "%s processed_cqe %d work_done %d budget %d\n", + __func__, processed_cqe, work_done, budget); + + /* Ring doorbell to inform H/W to reuse processed CQEs */ + nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR, + cq_idx, processed_cqe); + + if ((work_done < budget) && napi) + goto loop; + +done: + spin_unlock_bh(&cq->lock); + return work_done; +} + +static int nicvf_poll(struct napi_struct *napi, int budget) +{ + u64 cq_head; + int work_done = 0; + struct net_device *netdev = napi->dev; + struct nicvf *nic = netdev_priv(netdev); + struct nicvf_cq_poll *cq; + struct netdev_queue *txq; + + cq = container_of(napi, struct nicvf_cq_poll, napi); + work_done = nicvf_cq_intr_handler(netdev, cq->cq_idx, napi, budget); + + txq = netdev_get_tx_queue(netdev, cq->cq_idx); + if (netif_tx_queue_stopped(txq)) + netif_tx_wake_queue(txq); + + if (work_done < budget) { + /* Slow packet rate, exit polling */ + napi_complete(napi); + /* Re-enable interrupts */ + cq_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, + cq->cq_idx); + nicvf_clear_intr(nic, NICVF_INTR_CQ, cq->cq_idx); + nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_HEAD, + cq->cq_idx, cq_head); + nicvf_enable_intr(nic, NICVF_INTR_CQ, cq->cq_idx); + } + return work_done; +} + +/* Qset error interrupt handler + * + * As of now only CQ errors are handled + */ +static void nicvf_handle_qs_err(unsigned long data) +{ + struct nicvf *nic = (struct nicvf *)data; + struct queue_set *qs = nic->qs; + int qidx; + u64 status; + + netif_tx_disable(nic->netdev); + + /* Check if it is CQ err */ + for (qidx = 0; qidx < qs->cq_cnt; qidx++) { + status = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_STATUS, + qidx); + if (!(status & CQ_ERR_MASK)) + continue; + /* Process already queued CQEs and reconfig CQ */ + nicvf_disable_intr(nic, NICVF_INTR_CQ, qidx); + nicvf_sq_disable(nic, qidx); + nicvf_cq_intr_handler(nic->netdev, qidx, NULL, 0); + nicvf_cmp_queue_config(nic, qs, qidx, true); + nicvf_sq_free_used_descs(nic->netdev, &qs->sq[qidx], qidx); + nicvf_sq_enable(nic, &qs->sq[qidx], qidx); + + nicvf_enable_intr(nic, NICVF_INTR_CQ, qidx); + } + + netif_tx_start_all_queues(nic->netdev); + /* Re-enable Qset error interrupt */ + nicvf_enable_intr(nic, NICVF_INTR_QS_ERR, 0); +} + +static irqreturn_t nicvf_misc_intr_handler(int irq, void *nicvf_irq) +{ + struct nicvf *nic = (struct nicvf *)nicvf_irq; + u64 intr; + + intr = nicvf_reg_read(nic, NIC_VF_INT); + /* Check for spurious interrupt */ + if (!(intr & NICVF_INTR_MBOX_MASK)) + return IRQ_HANDLED; + + nicvf_handle_mbx_intr(nic); + + return IRQ_HANDLED; +} + +static irqreturn_t nicvf_intr_handler(int irq, void *nicvf_irq) +{ + u64 qidx, intr, clear_intr = 0; + u64 cq_intr, rbdr_intr, qs_err_intr; + struct nicvf *nic = (struct nicvf *)nicvf_irq; + struct queue_set *qs = nic->qs; + struct nicvf_cq_poll *cq_poll = NULL; + + intr = nicvf_reg_read(nic, NIC_VF_INT); + if (netif_msg_intr(nic)) + netdev_info(nic->netdev, "%s: interrupt status 0x%llx\n", + nic->netdev->name, intr); + + qs_err_intr = intr & NICVF_INTR_QS_ERR_MASK; + if (qs_err_intr) { + /* Disable Qset err interrupt and schedule softirq */ + nicvf_disable_intr(nic, NICVF_INTR_QS_ERR, 0); + tasklet_hi_schedule(&nic->qs_err_task); + clear_intr |= qs_err_intr; + } + + /* Disable interrupts and start polling */ + cq_intr = (intr & NICVF_INTR_CQ_MASK) >> NICVF_INTR_CQ_SHIFT; + for (qidx = 0; qidx < qs->cq_cnt; qidx++) { + if (!(cq_intr & (1 << qidx))) + continue; + if (!nicvf_is_intr_enabled(nic, NICVF_INTR_CQ, qidx)) + continue; + + nicvf_disable_intr(nic, NICVF_INTR_CQ, qidx); + clear_intr |= ((1 << qidx) << NICVF_INTR_CQ_SHIFT); + + cq_poll = nic->napi[qidx]; + /* Schedule NAPI */ + if (cq_poll) + napi_schedule(&cq_poll->napi); + } + + /* Handle RBDR interrupts */ + rbdr_intr = (intr & NICVF_INTR_RBDR_MASK) >> NICVF_INTR_RBDR_SHIFT; + if (rbdr_intr) { + /* Disable RBDR interrupt and schedule softirq */ + for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) { + if (!nicvf_is_intr_enabled(nic, NICVF_INTR_RBDR, qidx)) + continue; + nicvf_disable_intr(nic, NICVF_INTR_RBDR, qidx); + tasklet_hi_schedule(&nic->rbdr_task); + clear_intr |= ((1 << qidx) << NICVF_INTR_RBDR_SHIFT); + } + } + + /* Clear interrupts */ + nicvf_reg_write(nic, NIC_VF_INT, clear_intr); + return IRQ_HANDLED; +} + +static int nicvf_enable_msix(struct nicvf *nic) +{ + int ret, vec; + + nic->num_vec = NIC_VF_MSIX_VECTORS; + + for (vec = 0; vec < nic->num_vec; vec++) + nic->msix_entries[vec].entry = vec; + + ret = pci_enable_msix(nic->pdev, nic->msix_entries, nic->num_vec); + if (ret) { + netdev_err(nic->netdev, + "Req for #%d msix vectors failed\n", nic->num_vec); + return 0; + } + nic->msix_enabled = 1; + return 1; +} + +static void nicvf_disable_msix(struct nicvf *nic) +{ + if (nic->msix_enabled) { + pci_disable_msix(nic->pdev); + nic->msix_enabled = 0; + nic->num_vec = 0; + } +} + +static int nicvf_register_interrupts(struct nicvf *nic) +{ + int irq, free, ret = 0; + int vector; + + for_each_cq_irq(irq) + sprintf(nic->irq_name[irq], "NICVF%d CQ%d", + nic->vf_id, irq); + + for_each_sq_irq(irq) + sprintf(nic->irq_name[irq], "NICVF%d SQ%d", + nic->vf_id, irq - NICVF_INTR_ID_SQ); + + for_each_rbdr_irq(irq) + sprintf(nic->irq_name[irq], "NICVF%d RBDR%d", + nic->vf_id, irq - NICVF_INTR_ID_RBDR); + + /* Register all interrupts except mailbox */ + for (irq = 0; irq < NICVF_INTR_ID_SQ; irq++) { + vector = nic->msix_entries[irq].vector; + ret = request_irq(vector, nicvf_intr_handler, + 0, nic->irq_name[irq], nic); + if (ret) + break; + nic->irq_allocated[irq] = true; + } + + for (irq = NICVF_INTR_ID_SQ; irq < NICVF_INTR_ID_MISC; irq++) { + vector = nic->msix_entries[irq].vector; + ret = request_irq(vector, nicvf_intr_handler, + 0, nic->irq_name[irq], nic); + if (ret) + break; + nic->irq_allocated[irq] = true; + } + + sprintf(nic->irq_name[NICVF_INTR_ID_QS_ERR], + "NICVF%d Qset error", nic->vf_id); + if (!ret) { + vector = nic->msix_entries[NICVF_INTR_ID_QS_ERR].vector; + irq = NICVF_INTR_ID_QS_ERR; + ret = request_irq(vector, nicvf_intr_handler, + 0, nic->irq_name[irq], nic); + if (!ret) + nic->irq_allocated[irq] = true; + } + + if (ret) { + netdev_err(nic->netdev, "Request irq failed\n"); + for (free = 0; free < irq; free++) + free_irq(nic->msix_entries[free].vector, nic); + return ret; + } + + return 0; +} + +static void nicvf_unregister_interrupts(struct nicvf *nic) +{ + int irq; + + /* Free registered interrupts */ + for (irq = 0; irq < nic->num_vec; irq++) { + if (nic->irq_allocated[irq]) + free_irq(nic->msix_entries[irq].vector, nic); + nic->irq_allocated[irq] = false; + } + + /* Disable MSI-X */ + nicvf_disable_msix(nic); +} + +/* Initialize MSIX vectors and register MISC interrupt. + * Send READY message to PF to check if its alive + */ +static int nicvf_register_misc_interrupt(struct nicvf *nic) +{ + int ret = 0; + int irq = NICVF_INTR_ID_MISC; + + /* Return if mailbox interrupt is already registered */ + if (nic->msix_enabled) + return 0; + + /* Enable MSI-X */ + if (!nicvf_enable_msix(nic)) + return 1; + + sprintf(nic->irq_name[irq], "%s Mbox", "NICVF"); + /* Register Misc interrupt */ + ret = request_irq(nic->msix_entries[irq].vector, + nicvf_misc_intr_handler, 0, nic->irq_name[irq], nic); + + if (ret) + return ret; + nic->irq_allocated[irq] = true; + + /* Enable mailbox interrupt */ + nicvf_enable_intr(nic, NICVF_INTR_MBOX, 0); + + /* Check if VF is able to communicate with PF */ + if (!nicvf_check_pf_ready(nic)) { + nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0); + nicvf_unregister_interrupts(nic); + return 1; + } + + return 0; +} + +static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + struct nicvf *nic = netdev_priv(netdev); + int qid = skb_get_queue_mapping(skb); + struct netdev_queue *txq = netdev_get_tx_queue(netdev, qid); + + /* Check for minimum packet length */ + if (skb->len <= ETH_HLEN) { + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + + if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) { + netif_tx_stop_queue(txq); + nic->drv_stats.tx_busy++; + if (netif_msg_tx_err(nic)) + netdev_warn(netdev, + "%s: Transmit ring full, stopping SQ%d\n", + netdev->name, qid); + + return NETDEV_TX_BUSY; + } + + return NETDEV_TX_OK; +} + +int nicvf_stop(struct net_device *netdev) +{ + int irq, qidx; + struct nicvf *nic = netdev_priv(netdev); + struct queue_set *qs = nic->qs; + struct nicvf_cq_poll *cq_poll = NULL; + union nic_mbx mbx = {}; + + mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN; + nicvf_send_msg_to_pf(nic, &mbx); + + netif_carrier_off(netdev); + netif_tx_disable(netdev); + + /* Disable RBDR & QS error interrupts */ + for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) { + nicvf_disable_intr(nic, NICVF_INTR_RBDR, qidx); + nicvf_clear_intr(nic, NICVF_INTR_RBDR, qidx); + } + nicvf_disable_intr(nic, NICVF_INTR_QS_ERR, 0); + nicvf_clear_intr(nic, NICVF_INTR_QS_ERR, 0); + + /* Wait for pending IRQ handlers to finish */ + for (irq = 0; irq < nic->num_vec; irq++) + synchronize_irq(nic->msix_entries[irq].vector); + + tasklet_kill(&nic->rbdr_task); + tasklet_kill(&nic->qs_err_task); + if (nic->rb_work_scheduled) + cancel_delayed_work_sync(&nic->rbdr_work); + + for (qidx = 0; qidx < nic->qs->cq_cnt; qidx++) { + cq_poll = nic->napi[qidx]; + if (!cq_poll) + continue; + nic->napi[qidx] = NULL; + napi_synchronize(&cq_poll->napi); + /* CQ intr is enabled while napi_complete, + * so disable it now + */ + nicvf_disable_intr(nic, NICVF_INTR_CQ, qidx); + nicvf_clear_intr(nic, NICVF_INTR_CQ, qidx); + napi_disable(&cq_poll->napi); + netif_napi_del(&cq_poll->napi); + kfree(cq_poll); + } + + /* Free resources */ + nicvf_config_data_transfer(nic, false); + + /* Disable HW Qset */ + nicvf_qset_config(nic, false); + + /* disable mailbox interrupt */ + nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0); + + nicvf_unregister_interrupts(nic); + + return 0; +} + +int nicvf_open(struct net_device *netdev) +{ + int err, qidx; + struct nicvf *nic = netdev_priv(netdev); + struct queue_set *qs = nic->qs; + struct nicvf_cq_poll *cq_poll = NULL; + + nic->mtu = netdev->mtu; + + netif_carrier_off(netdev); + + err = nicvf_register_misc_interrupt(nic); + if (err) + return err; + + /* Register NAPI handler for processing CQEs */ + for (qidx = 0; qidx < qs->cq_cnt; qidx++) { + cq_poll = kzalloc(sizeof(*cq_poll), GFP_KERNEL); + if (!cq_poll) { + err = -ENOMEM; + goto napi_del; + } + cq_poll->cq_idx = qidx; + netif_napi_add(netdev, &cq_poll->napi, nicvf_poll, + NAPI_POLL_WEIGHT); + napi_enable(&cq_poll->napi); + nic->napi[qidx] = cq_poll; + } + + /* Check if we got MAC address from PF or else generate a radom MAC */ + if (is_zero_ether_addr(netdev->dev_addr)) { + eth_hw_addr_random(netdev); + nicvf_hw_set_mac_addr(nic, netdev); + } + + /* Init tasklet for handling Qset err interrupt */ + tasklet_init(&nic->qs_err_task, nicvf_handle_qs_err, + (unsigned long)nic); + + /* Init RBDR tasklet which will refill RBDR */ + tasklet_init(&nic->rbdr_task, nicvf_rbdr_task, + (unsigned long)nic); + INIT_DELAYED_WORK(&nic->rbdr_work, nicvf_rbdr_work); + + /* Configure CPI alorithm */ + nic->cpi_alg = cpi_alg; + nicvf_config_cpi(nic); + + /* Configure receive side scaling */ + nicvf_rss_init(nic); + + err = nicvf_register_interrupts(nic); + if (err) + goto cleanup; + + /* Initialize the queues */ + err = nicvf_init_resources(nic); + if (err) + goto cleanup; + + /* Make sure queue initialization is written */ + wmb(); + + nicvf_reg_write(nic, NIC_VF_INT, -1); + /* Enable Qset err interrupt */ + nicvf_enable_intr(nic, NICVF_INTR_QS_ERR, 0); + + /* Enable completion queue interrupt */ + for (qidx = 0; qidx < qs->cq_cnt; qidx++) + nicvf_enable_intr(nic, NICVF_INTR_CQ, qidx); + + /* Enable RBDR threshold interrupt */ + for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) + nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx); + + netif_carrier_on(netdev); + netif_tx_start_all_queues(netdev); + + return 0; +cleanup: + nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0); + nicvf_unregister_interrupts(nic); +napi_del: + for (qidx = 0; qidx < qs->cq_cnt; qidx++) { + cq_poll = nic->napi[qidx]; + if (!cq_poll) + continue; + napi_disable(&cq_poll->napi); + netif_napi_del(&cq_poll->napi); + kfree(cq_poll); + nic->napi[qidx] = NULL; + } + return err; +} + +static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu) +{ + union nic_mbx mbx = {}; + + mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS; + mbx.frs.max_frs = mtu; + mbx.frs.vf_id = nic->vf_id; + + return nicvf_send_msg_to_pf(nic, &mbx); +} + +static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct nicvf *nic = netdev_priv(netdev); + + if (new_mtu > NIC_HW_MAX_FRS) + return -EINVAL; + + if (new_mtu < NIC_HW_MIN_FRS) + return -EINVAL; + + if (nicvf_update_hw_max_frs(nic, new_mtu)) + return -EINVAL; + netdev->mtu = new_mtu; + nic->mtu = new_mtu; + + return 0; +} + +static int nicvf_set_mac_address(struct net_device *netdev, void *p) +{ + struct sockaddr *addr = p; + struct nicvf *nic = netdev_priv(netdev); + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); + + if (nic->msix_enabled) + if (nicvf_hw_set_mac_addr(nic, netdev)) + return -EBUSY; + + return 0; +} + +void nicvf_update_lmac_stats(struct nicvf *nic) +{ + int stat = 0; + union nic_mbx mbx = {}; + int timeout; + + if (!netif_running(nic->netdev)) + return; + + mbx.bgx_stats.msg = NIC_MBOX_MSG_BGX_STATS; + mbx.bgx_stats.vf_id = nic->vf_id; + /* Rx stats */ + mbx.bgx_stats.rx = 1; + while (stat < BGX_RX_STATS_COUNT) { + nic->bgx_stats_acked = 0; + mbx.bgx_stats.idx = stat; + nicvf_send_msg_to_pf(nic, &mbx); + timeout = 0; + while ((!nic->bgx_stats_acked) && (timeout < 10)) { + msleep(2); + timeout++; + } + stat++; + } + + stat = 0; + + /* Tx stats */ + mbx.bgx_stats.rx = 0; + while (stat < BGX_TX_STATS_COUNT) { + nic->bgx_stats_acked = 0; + mbx.bgx_stats.idx = stat; + nicvf_send_msg_to_pf(nic, &mbx); + timeout = 0; + while ((!nic->bgx_stats_acked) && (timeout < 10)) { + msleep(2); + timeout++; + } + stat++; + } +} + +void nicvf_update_stats(struct nicvf *nic) +{ + int qidx; + struct nicvf_hw_stats *stats = &nic->stats; + struct nicvf_drv_stats *drv_stats = &nic->drv_stats; + struct queue_set *qs = nic->qs; + +#define GET_RX_STATS(reg) \ + nicvf_reg_read(nic, NIC_VNIC_RX_STAT_0_13 | (reg << 3)) +#define GET_TX_STATS(reg) \ + nicvf_reg_read(nic, NIC_VNIC_TX_STAT_0_4 | (reg << 3)) + + stats->rx_bytes_ok = GET_RX_STATS(RX_OCTS); + stats->rx_ucast_frames_ok = GET_RX_STATS(RX_UCAST); + stats->rx_bcast_frames_ok = GET_RX_STATS(RX_BCAST); + stats->rx_mcast_frames_ok = GET_RX_STATS(RX_MCAST); + stats->rx_fcs_errors = GET_RX_STATS(RX_FCS); + stats->rx_l2_errors = GET_RX_STATS(RX_L2ERR); + stats->rx_drop_red = GET_RX_STATS(RX_RED); + stats->rx_drop_overrun = GET_RX_STATS(RX_ORUN); + stats->rx_drop_bcast = GET_RX_STATS(RX_DRP_BCAST); + stats->rx_drop_mcast = GET_RX_STATS(RX_DRP_MCAST); + stats->rx_drop_l3_bcast = GET_RX_STATS(RX_DRP_L3BCAST); + stats->rx_drop_l3_mcast = GET_RX_STATS(RX_DRP_L3MCAST); + + stats->tx_bytes_ok = GET_TX_STATS(TX_OCTS); + stats->tx_ucast_frames_ok = GET_TX_STATS(TX_UCAST); + stats->tx_bcast_frames_ok = GET_TX_STATS(TX_BCAST); + stats->tx_mcast_frames_ok = GET_TX_STATS(TX_MCAST); + stats->tx_drops = GET_TX_STATS(TX_DROP); + + drv_stats->rx_frames_ok = stats->rx_ucast_frames_ok + + stats->rx_bcast_frames_ok + + stats->rx_mcast_frames_ok; + drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok + + stats->tx_bcast_frames_ok + + stats->tx_mcast_frames_ok; + drv_stats->rx_drops = stats->rx_drop_red + + stats->rx_drop_overrun; + drv_stats->tx_drops = stats->tx_drops; + + /* Update RQ and SQ stats */ + for (qidx = 0; qidx < qs->rq_cnt; qidx++) + nicvf_update_rq_stats(nic, qidx); + for (qidx = 0; qidx < qs->sq_cnt; qidx++) + nicvf_update_sq_stats(nic, qidx); +} + +static struct rtnl_link_stats64 *nicvf_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct nicvf *nic = netdev_priv(netdev); + struct nicvf_hw_stats *hw_stats = &nic->stats; + struct nicvf_drv_stats *drv_stats = &nic->drv_stats; + + nicvf_update_stats(nic); + + stats->rx_bytes = hw_stats->rx_bytes_ok; + stats->rx_packets = drv_stats->rx_frames_ok; + stats->rx_dropped = drv_stats->rx_drops; + + stats->tx_bytes = hw_stats->tx_bytes_ok; + stats->tx_packets = drv_stats->tx_frames_ok; + stats->tx_dropped = drv_stats->tx_drops; + + return stats; +} + +static void nicvf_tx_timeout(struct net_device *dev) +{ + struct nicvf *nic = netdev_priv(dev); + + if (netif_msg_tx_err(nic)) + netdev_warn(dev, "%s: Transmit timed out, resetting\n", + dev->name); + + schedule_work(&nic->reset_task); +} + +static void nicvf_reset_task(struct work_struct *work) +{ + struct nicvf *nic; + + nic = container_of(work, struct nicvf, reset_task); + + if (!netif_running(nic->netdev)) + return; + + nicvf_stop(nic->netdev); + nicvf_open(nic->netdev); + nic->netdev->trans_start = jiffies; +} + +static const struct net_device_ops nicvf_netdev_ops = { + .ndo_open = nicvf_open, + .ndo_stop = nicvf_stop, + .ndo_start_xmit = nicvf_xmit, + .ndo_change_mtu = nicvf_change_mtu, + .ndo_set_mac_address = nicvf_set_mac_address, + .ndo_get_stats64 = nicvf_get_stats64, + .ndo_tx_timeout = nicvf_tx_timeout, +}; + +static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct device *dev = &pdev->dev; + struct net_device *netdev; + struct nicvf *nic; + struct queue_set *qs; + int err; + + err = pci_enable_device(pdev); + if (err) { + dev_err(dev, "Failed to enable PCI device\n"); + return err; + } + + err = pci_request_regions(pdev, DRV_NAME); + if (err) { + dev_err(dev, "PCI request regions failed 0x%x\n", err); + goto err_disable_device; + } + + err = pci_set_dma_mask(pdev, DMA_BIT_MASK(48)); + if (err) { + dev_err(dev, "Unable to get usable DMA configuration\n"); + goto err_release_regions; + } + + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48)); + if (err) { + dev_err(dev, "unable to get 48-bit DMA for consistent allocations\n"); + goto err_release_regions; + } + + netdev = alloc_etherdev_mqs(sizeof(struct nicvf), + MAX_RCV_QUEUES_PER_QS, + MAX_SND_QUEUES_PER_QS); + if (!netdev) { + err = -ENOMEM; + goto err_release_regions; + } + + pci_set_drvdata(pdev, netdev); + + SET_NETDEV_DEV(netdev, &pdev->dev); + + nic = netdev_priv(netdev); + nic->netdev = netdev; + nic->pdev = pdev; + + /* MAP VF's configuration registers */ + nic->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0); + if (!nic->reg_base) { + dev_err(dev, "Cannot map config register space, aborting\n"); + err = -ENOMEM; + goto err_free_netdev; + } + + err = nicvf_set_qset_resources(nic); + if (err) + goto err_free_netdev; + + qs = nic->qs; + + err = nicvf_set_real_num_queues(netdev, qs->sq_cnt, qs->rq_cnt); + if (err) + goto err_free_netdev; + + /* Check if PF is alive and get MAC address for this VF */ + err = nicvf_register_misc_interrupt(nic); + if (err) + goto err_free_netdev; + + netdev->features |= (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_SG | + NETIF_F_TSO | NETIF_F_GRO); + netdev->hw_features = netdev->features; + + netdev->netdev_ops = &nicvf_netdev_ops; + + INIT_WORK(&nic->reset_task, nicvf_reset_task); + + err = register_netdev(netdev); + if (err) { + dev_err(dev, "Failed to register netdevice\n"); + goto err_unregister_interrupts; + } + + nic->msg_enable = debug; + + nicvf_set_ethtool_ops(netdev); + + return 0; + +err_unregister_interrupts: + nicvf_unregister_interrupts(nic); +err_free_netdev: + pci_set_drvdata(pdev, NULL); + free_netdev(netdev); +err_release_regions: + pci_release_regions(pdev); +err_disable_device: + pci_disable_device(pdev); + return err; +} + +static void nicvf_remove(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct nicvf *nic = netdev_priv(netdev); + + unregister_netdev(netdev); + nicvf_unregister_interrupts(nic); + pci_set_drvdata(pdev, NULL); + free_netdev(netdev); + pci_release_regions(pdev); + pci_disable_device(pdev); +} + +static struct pci_driver nicvf_driver = { + .name = DRV_NAME, + .id_table = nicvf_id_table, + .probe = nicvf_probe, + .remove = nicvf_remove, +}; + +static int __init nicvf_init_module(void) +{ + pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION); + + return pci_register_driver(&nicvf_driver); +} + +static void __exit nicvf_cleanup_module(void) +{ + pci_unregister_driver(&nicvf_driver); +} + +module_init(nicvf_init_module); +module_exit(nicvf_cleanup_module); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c new file mode 100644 index 0000000..d69d228d --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -0,0 +1,1545 @@ +/* + * Copyright (C) 2015 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/ip.h> +#include <linux/etherdevice.h> +#include <net/ip.h> +#include <net/tso.h> + +#include "nic_reg.h" +#include "nic.h" +#include "q_struct.h" +#include "nicvf_queues.h" + +struct rbuf_info { + struct page *page; + void *data; + u64 offset; +}; + +#define GET_RBUF_INFO(x) ((struct rbuf_info *)(x - NICVF_RCV_BUF_ALIGN_BYTES)) + +/* Poll a register for a specific value */ +static int nicvf_poll_reg(struct nicvf *nic, int qidx, + u64 reg, int bit_pos, int bits, int val) +{ + u64 bit_mask; + u64 reg_val; + int timeout = 10; + + bit_mask = (1ULL << bits) - 1; + bit_mask = (bit_mask << bit_pos); + + while (timeout) { + reg_val = nicvf_queue_reg_read(nic, reg, qidx); + if (((reg_val & bit_mask) >> bit_pos) == val) + return 0; + usleep_range(1000, 2000); + timeout--; + } + netdev_err(nic->netdev, "Poll on reg 0x%llx failed\n", reg); + return 1; +} + +/* Allocate memory for a queue's descriptors */ +static int nicvf_alloc_q_desc_mem(struct nicvf *nic, struct q_desc_mem *dmem, + int q_len, int desc_size, int align_bytes) +{ + dmem->q_len = q_len; + dmem->size = (desc_size * q_len) + align_bytes; + /* Save address, need it while freeing */ + dmem->unalign_base = dma_zalloc_coherent(&nic->pdev->dev, dmem->size, + &dmem->dma, GFP_KERNEL); + if (!dmem->unalign_base) + return -ENOMEM; + + /* Align memory address for 'align_bytes' */ + dmem->phys_base = NICVF_ALIGNED_ADDR((u64)dmem->dma, align_bytes); + dmem->base = dmem->unalign_base + (dmem->phys_base - dmem->dma); + return 0; +} + +/* Free queue's descriptor memory */ +static void nicvf_free_q_desc_mem(struct nicvf *nic, struct q_desc_mem *dmem) +{ + if (!dmem) + return; + + dma_free_coherent(&nic->pdev->dev, dmem->size, + dmem->unalign_base, dmem->dma); + dmem->unalign_base = NULL; + dmem->base = NULL; +} + +/* Allocate buffer for packet reception + * HW returns memory address where packet is DMA'ed but not a pointer + * into RBDR ring, so save buffer address at the start of fragment and + * align the start address to a cache aligned address + */ +static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp, + u32 buf_len, u64 **rbuf) +{ + u64 data; + struct rbuf_info *rinfo; + int order = get_order(buf_len); + + /* Check if request can be accomodated in previous allocated page */ + if (nic->rb_page) { + if ((nic->rb_page_offset + buf_len + buf_len) > + (PAGE_SIZE << order)) { + nic->rb_page = NULL; + } else { + nic->rb_page_offset += buf_len; + get_page(nic->rb_page); + } + } + + /* Allocate a new page */ + if (!nic->rb_page) { + nic->rb_page = alloc_pages(gfp | __GFP_COMP, order); + if (!nic->rb_page) { + netdev_err(nic->netdev, "Failed to allocate new rcv buffer\n"); + return -ENOMEM; + } + nic->rb_page_offset = 0; + } + + data = (u64)page_address(nic->rb_page) + nic->rb_page_offset; + + /* Align buffer addr to cache line i.e 128 bytes */ + rinfo = (struct rbuf_info *)(data + NICVF_RCV_BUF_ALIGN_LEN(data)); + /* Save page address for reference updation */ + rinfo->page = nic->rb_page; + /* Store start address for later retrieval */ + rinfo->data = (void *)data; + /* Store alignment offset */ + rinfo->offset = NICVF_RCV_BUF_ALIGN_LEN(data); + + data += rinfo->offset; + + /* Give next aligned address to hw for DMA */ + *rbuf = (u64 *)(data + NICVF_RCV_BUF_ALIGN_BYTES); + return 0; +} + +/* Retrieve actual buffer start address and build skb for received packet */ +static struct sk_buff *nicvf_rb_ptr_to_skb(struct nicvf *nic, + u64 rb_ptr, int len) +{ + struct sk_buff *skb; + struct rbuf_info *rinfo; + + rb_ptr = (u64)phys_to_virt(rb_ptr); + /* Get buffer start address and alignment offset */ + rinfo = GET_RBUF_INFO(rb_ptr); + + /* Now build an skb to give to stack */ + skb = build_skb(rinfo->data, RCV_FRAG_LEN); + if (!skb) { + put_page(rinfo->page); + return NULL; + } + + /* Set correct skb->data */ + skb_reserve(skb, rinfo->offset + NICVF_RCV_BUF_ALIGN_BYTES); + + prefetch((void *)rb_ptr); + return skb; +} + +/* Allocate RBDR ring and populate receive buffers */ +static int nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr, + int ring_len, int buf_size) +{ + int idx; + u64 *rbuf; + struct rbdr_entry_t *desc; + int err; + + err = nicvf_alloc_q_desc_mem(nic, &rbdr->dmem, ring_len, + sizeof(struct rbdr_entry_t), + NICVF_RCV_BUF_ALIGN_BYTES); + if (err) + return err; + + rbdr->desc = rbdr->dmem.base; + /* Buffer size has to be in multiples of 128 bytes */ + rbdr->dma_size = buf_size; + rbdr->enable = true; + rbdr->thresh = RBDR_THRESH; + + nic->rb_page = NULL; + for (idx = 0; idx < ring_len; idx++) { + err = nicvf_alloc_rcv_buffer(nic, GFP_KERNEL, RCV_FRAG_LEN, + &rbuf); + if (err) + return err; + + desc = GET_RBDR_DESC(rbdr, idx); + desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN; + } + return 0; +} + +/* Free RBDR ring and its receive buffers */ +static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr) +{ + int head, tail; + u64 buf_addr; + struct rbdr_entry_t *desc; + struct rbuf_info *rinfo; + + if (!rbdr) + return; + + rbdr->enable = false; + if (!rbdr->dmem.base) + return; + + head = rbdr->head; + tail = rbdr->tail; + + /* Free SKBs */ + while (head != tail) { + desc = GET_RBDR_DESC(rbdr, head); + buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN; + rinfo = GET_RBUF_INFO((u64)phys_to_virt(buf_addr)); + put_page(rinfo->page); + head++; + head &= (rbdr->dmem.q_len - 1); + } + /* Free SKB of tail desc */ + desc = GET_RBDR_DESC(rbdr, tail); + buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN; + rinfo = GET_RBUF_INFO((u64)phys_to_virt(buf_addr)); + put_page(rinfo->page); + + /* Free RBDR ring */ + nicvf_free_q_desc_mem(nic, &rbdr->dmem); +} + +/* Refill receive buffer descriptors with new buffers. + */ +static void nicvf_refill_rbdr(struct nicvf *nic, gfp_t gfp) +{ + struct queue_set *qs = nic->qs; + int rbdr_idx = qs->rbdr_cnt; + int tail, qcount; + int refill_rb_cnt; + struct rbdr *rbdr; + struct rbdr_entry_t *desc; + u64 *rbuf; + int new_rb = 0; + +refill: + if (!rbdr_idx) + return; + rbdr_idx--; + rbdr = &qs->rbdr[rbdr_idx]; + /* Check if it's enabled */ + if (!rbdr->enable) + goto next_rbdr; + + /* Get no of desc's to be refilled */ + qcount = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_STATUS0, rbdr_idx); + qcount &= 0x7FFFF; + /* Doorbell can be ringed with a max of ring size minus 1 */ + if (qcount >= (qs->rbdr_len - 1)) + goto next_rbdr; + else + refill_rb_cnt = qs->rbdr_len - qcount - 1; + + /* Start filling descs from tail */ + tail = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_TAIL, rbdr_idx) >> 3; + while (refill_rb_cnt) { + tail++; + tail &= (rbdr->dmem.q_len - 1); + + if (nicvf_alloc_rcv_buffer(nic, gfp, RCV_FRAG_LEN, &rbuf)) + break; + + desc = GET_RBDR_DESC(rbdr, tail); + desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN; + refill_rb_cnt--; + new_rb++; + } + + /* make sure all memory stores are done before ringing doorbell */ + smp_wmb(); + + /* Check if buffer allocation failed */ + if (refill_rb_cnt) + nic->rb_alloc_fail = true; + else + nic->rb_alloc_fail = false; + + /* Notify HW */ + nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_DOOR, + rbdr_idx, new_rb); +next_rbdr: + /* Re-enable RBDR interrupts only if buffer allocation is success */ + if (!nic->rb_alloc_fail && rbdr->enable) + nicvf_enable_intr(nic, NICVF_INTR_RBDR, rbdr_idx); + + if (rbdr_idx) + goto refill; +} + +/* Alloc rcv buffers in non-atomic mode for better success */ +void nicvf_rbdr_work(struct work_struct *work) +{ + struct nicvf *nic = container_of(work, struct nicvf, rbdr_work.work); + + nicvf_refill_rbdr(nic, GFP_KERNEL); + if (nic->rb_alloc_fail) + schedule_delayed_work(&nic->rbdr_work, msecs_to_jiffies(10)); + else + nic->rb_work_scheduled = false; +} + +/* In Softirq context, alloc rcv buffers in atomic mode */ +void nicvf_rbdr_task(unsigned long data) +{ + struct nicvf *nic = (struct nicvf *)data; + + nicvf_refill_rbdr(nic, GFP_ATOMIC); + if (nic->rb_alloc_fail) { + nic->rb_work_scheduled = true; + schedule_delayed_work(&nic->rbdr_work, msecs_to_jiffies(10)); + } +} + +/* Initialize completion queue */ +static int nicvf_init_cmp_queue(struct nicvf *nic, + struct cmp_queue *cq, int q_len) +{ + int err; + + err = nicvf_alloc_q_desc_mem(nic, &cq->dmem, q_len, CMP_QUEUE_DESC_SIZE, + NICVF_CQ_BASE_ALIGN_BYTES); + if (err) + return err; + + cq->desc = cq->dmem.base; + cq->thresh = CMP_QUEUE_CQE_THRESH; + nic->cq_coalesce_usecs = (CMP_QUEUE_TIMER_THRESH * 0.05) - 1; + + return 0; +} + +static void nicvf_free_cmp_queue(struct nicvf *nic, struct cmp_queue *cq) +{ + if (!cq) + return; + if (!cq->dmem.base) + return; + + nicvf_free_q_desc_mem(nic, &cq->dmem); +} + +/* Initialize transmit queue */ +static int nicvf_init_snd_queue(struct nicvf *nic, + struct snd_queue *sq, int q_len) +{ + int err; + + err = nicvf_alloc_q_desc_mem(nic, &sq->dmem, q_len, SND_QUEUE_DESC_SIZE, + NICVF_SQ_BASE_ALIGN_BYTES); + if (err) + return err; + + sq->desc = sq->dmem.base; + sq->skbuff = kcalloc(q_len, sizeof(u64), GFP_KERNEL); + if (!sq->skbuff) + return -ENOMEM; + sq->head = 0; + sq->tail = 0; + atomic_set(&sq->free_cnt, q_len - 1); + sq->thresh = SND_QUEUE_THRESH; + + /* Preallocate memory for TSO segment's header */ + sq->tso_hdrs = dma_alloc_coherent(&nic->pdev->dev, + q_len * TSO_HEADER_SIZE, + &sq->tso_hdrs_phys, GFP_KERNEL); + if (!sq->tso_hdrs) + return -ENOMEM; + + return 0; +} + +static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) +{ + if (!sq) + return; + if (!sq->dmem.base) + return; + + if (sq->tso_hdrs) + dma_free_coherent(&nic->pdev->dev, sq->dmem.q_len, + sq->tso_hdrs, sq->tso_hdrs_phys); + + kfree(sq->skbuff); + nicvf_free_q_desc_mem(nic, &sq->dmem); +} + +static void nicvf_reclaim_snd_queue(struct nicvf *nic, + struct queue_set *qs, int qidx) +{ + /* Disable send queue */ + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, 0); + /* Check if SQ is stopped */ + if (nicvf_poll_reg(nic, qidx, NIC_QSET_SQ_0_7_STATUS, 21, 1, 0x01)) + return; + /* Reset send queue */ + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, NICVF_SQ_RESET); +} + +static void nicvf_reclaim_rcv_queue(struct nicvf *nic, + struct queue_set *qs, int qidx) +{ + union nic_mbx mbx = {}; + + /* Make sure all packets in the pipeline are written back into mem */ + mbx.msg.msg = NIC_MBOX_MSG_RQ_SW_SYNC; + nicvf_send_msg_to_pf(nic, &mbx); +} + +static void nicvf_reclaim_cmp_queue(struct nicvf *nic, + struct queue_set *qs, int qidx) +{ + /* Disable timer threshold (doesn't get reset upon CQ reset */ + nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG2, qidx, 0); + /* Disable completion queue */ + nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG, qidx, 0); + /* Reset completion queue */ + nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG, qidx, NICVF_CQ_RESET); +} + +static void nicvf_reclaim_rbdr(struct nicvf *nic, + struct rbdr *rbdr, int qidx) +{ + u64 tmp, fifo_state; + int timeout = 10; + + /* Save head and tail pointers for feeing up buffers */ + rbdr->head = nicvf_queue_reg_read(nic, + NIC_QSET_RBDR_0_1_HEAD, + qidx) >> 3; + rbdr->tail = nicvf_queue_reg_read(nic, + NIC_QSET_RBDR_0_1_TAIL, + qidx) >> 3; + + /* If RBDR FIFO is in 'FAIL' state then do a reset first + * before relaiming. + */ + fifo_state = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_STATUS0, qidx); + if (((fifo_state >> 62) & 0x03) == 0x3) + nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_CFG, + qidx, NICVF_RBDR_RESET); + + /* Disable RBDR */ + nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_CFG, qidx, 0); + if (nicvf_poll_reg(nic, qidx, NIC_QSET_RBDR_0_1_STATUS0, 62, 2, 0x00)) + return; + while (1) { + tmp = nicvf_queue_reg_read(nic, + NIC_QSET_RBDR_0_1_PREFETCH_STATUS, + qidx); + if ((tmp & 0xFFFFFFFF) == ((tmp >> 32) & 0xFFFFFFFF)) + break; + usleep_range(1000, 2000); + timeout--; + if (!timeout) { + netdev_err(nic->netdev, + "Failed polling on prefetch status\n"); + return; + } + } + nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_CFG, + qidx, NICVF_RBDR_RESET); + + if (nicvf_poll_reg(nic, qidx, NIC_QSET_RBDR_0_1_STATUS0, 62, 2, 0x02)) + return; + nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_CFG, qidx, 0x00); + if (nicvf_poll_reg(nic, qidx, NIC_QSET_RBDR_0_1_STATUS0, 62, 2, 0x00)) + return; +} + +/* Configures receive queue */ +static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs, + int qidx, bool enable) +{ + union nic_mbx mbx = {}; + struct rcv_queue *rq; + struct rq_cfg rq_cfg; + + rq = &qs->rq[qidx]; + rq->enable = enable; + + /* Disable receive queue */ + nicvf_queue_reg_write(nic, NIC_QSET_RQ_0_7_CFG, qidx, 0); + + if (!rq->enable) { + nicvf_reclaim_rcv_queue(nic, qs, qidx); + return; + } + + rq->cq_qs = qs->vnic_id; + rq->cq_idx = qidx; + rq->start_rbdr_qs = qs->vnic_id; + rq->start_qs_rbdr_idx = qs->rbdr_cnt - 1; + rq->cont_rbdr_qs = qs->vnic_id; + rq->cont_qs_rbdr_idx = qs->rbdr_cnt - 1; + /* all writes of RBDR data to be loaded into L2 Cache as well*/ + rq->caching = 1; + + /* Send a mailbox msg to PF to config RQ */ + mbx.rq.msg = NIC_MBOX_MSG_RQ_CFG; + mbx.rq.qs_num = qs->vnic_id; + mbx.rq.rq_num = qidx; + mbx.rq.cfg = (rq->caching << 26) | (rq->cq_qs << 19) | + (rq->cq_idx << 16) | (rq->cont_rbdr_qs << 9) | + (rq->cont_qs_rbdr_idx << 8) | + (rq->start_rbdr_qs << 1) | (rq->start_qs_rbdr_idx); + nicvf_send_msg_to_pf(nic, &mbx); + + mbx.rq.msg = NIC_MBOX_MSG_RQ_BP_CFG; + mbx.rq.cfg = (1ULL << 63) | (1ULL << 62) | (qs->vnic_id << 0); + nicvf_send_msg_to_pf(nic, &mbx); + + /* RQ drop config + * Enable CQ drop to reserve sufficient CQEs for all tx packets + */ + mbx.rq.msg = NIC_MBOX_MSG_RQ_DROP_CFG; + mbx.rq.cfg = (1ULL << 62) | (RQ_CQ_DROP << 8); + nicvf_send_msg_to_pf(nic, &mbx); + + nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, qidx, 0x00); + + /* Enable Receive queue */ + rq_cfg.ena = 1; + rq_cfg.tcp_ena = 0; + nicvf_queue_reg_write(nic, NIC_QSET_RQ_0_7_CFG, qidx, *(u64 *)&rq_cfg); +} + +/* Configures completion queue */ +void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs, + int qidx, bool enable) +{ + struct cmp_queue *cq; + struct cq_cfg cq_cfg; + + cq = &qs->cq[qidx]; + cq->enable = enable; + + if (!cq->enable) { + nicvf_reclaim_cmp_queue(nic, qs, qidx); + return; + } + + /* Reset completion queue */ + nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG, qidx, NICVF_CQ_RESET); + + if (!cq->enable) + return; + + spin_lock_init(&cq->lock); + /* Set completion queue base address */ + nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_BASE, + qidx, (u64)(cq->dmem.phys_base)); + + /* Enable Completion queue */ + cq_cfg.ena = 1; + cq_cfg.reset = 0; + cq_cfg.caching = 0; + cq_cfg.qsize = CMP_QSIZE; + cq_cfg.avg_con = 0; + nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG, qidx, *(u64 *)&cq_cfg); + + /* Set threshold value for interrupt generation */ + nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_THRESH, qidx, cq->thresh); + nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG2, + qidx, nic->cq_coalesce_usecs); +} + +/* Configures transmit queue */ +static void nicvf_snd_queue_config(struct nicvf *nic, struct queue_set *qs, + int qidx, bool enable) +{ + union nic_mbx mbx = {}; + struct snd_queue *sq; + struct sq_cfg sq_cfg; + + sq = &qs->sq[qidx]; + sq->enable = enable; + + if (!sq->enable) { + nicvf_reclaim_snd_queue(nic, qs, qidx); + return; + } + + /* Reset send queue */ + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, NICVF_SQ_RESET); + + sq->cq_qs = qs->vnic_id; + sq->cq_idx = qidx; + + /* Send a mailbox msg to PF to config SQ */ + mbx.sq.msg = NIC_MBOX_MSG_SQ_CFG; + mbx.sq.qs_num = qs->vnic_id; + mbx.sq.sq_num = qidx; + mbx.sq.cfg = (sq->cq_qs << 3) | sq->cq_idx; + nicvf_send_msg_to_pf(nic, &mbx); + + /* Set queue base address */ + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_BASE, + qidx, (u64)(sq->dmem.phys_base)); + + /* Enable send queue & set queue size */ + sq_cfg.ena = 1; + sq_cfg.reset = 0; + sq_cfg.ldwb = 0; + sq_cfg.qsize = SND_QSIZE; + sq_cfg.tstmp_bgx_intf = 0; + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, *(u64 *)&sq_cfg); + + /* Set threshold value for interrupt generation */ + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_THRESH, qidx, sq->thresh); + + /* Set queue:cpu affinity for better load distribution */ + if (cpu_online(qidx)) { + cpumask_set_cpu(qidx, &sq->affinity_mask); + netif_set_xps_queue(nic->netdev, + &sq->affinity_mask, qidx); + } +} + +/* Configures receive buffer descriptor ring */ +static void nicvf_rbdr_config(struct nicvf *nic, struct queue_set *qs, + int qidx, bool enable) +{ + struct rbdr *rbdr; + struct rbdr_cfg rbdr_cfg; + + rbdr = &qs->rbdr[qidx]; + nicvf_reclaim_rbdr(nic, rbdr, qidx); + if (!enable) + return; + + /* Set descriptor base address */ + nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_BASE, + qidx, (u64)(rbdr->dmem.phys_base)); + + /* Enable RBDR & set queue size */ + /* Buffer size should be in multiples of 128 bytes */ + rbdr_cfg.ena = 1; + rbdr_cfg.reset = 0; + rbdr_cfg.ldwb = 0; + rbdr_cfg.qsize = RBDR_SIZE; + rbdr_cfg.avg_con = 0; + rbdr_cfg.lines = rbdr->dma_size / 128; + nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_CFG, + qidx, *(u64 *)&rbdr_cfg); + + /* Notify HW */ + nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_DOOR, + qidx, qs->rbdr_len - 1); + + /* Set threshold value for interrupt generation */ + nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_THRESH, + qidx, rbdr->thresh - 1); +} + +/* Requests PF to assign and enable Qset */ +void nicvf_qset_config(struct nicvf *nic, bool enable) +{ + union nic_mbx mbx = {}; + struct queue_set *qs = nic->qs; + struct qs_cfg *qs_cfg; + + if (!qs) { + netdev_warn(nic->netdev, + "Qset is still not allocated, don't init queues\n"); + return; + } + + qs->enable = enable; + qs->vnic_id = nic->vf_id; + + /* Send a mailbox msg to PF to config Qset */ + mbx.qs.msg = NIC_MBOX_MSG_QS_CFG; + mbx.qs.num = qs->vnic_id; + + mbx.qs.cfg = 0; + qs_cfg = (struct qs_cfg *)&mbx.qs.cfg; + if (qs->enable) { + qs_cfg->ena = 1; +#ifdef __BIG_ENDIAN + qs_cfg->be = 1; +#endif + qs_cfg->vnic = qs->vnic_id; + } + nicvf_send_msg_to_pf(nic, &mbx); +} + +static void nicvf_free_resources(struct nicvf *nic) +{ + int qidx; + struct queue_set *qs = nic->qs; + + /* Free receive buffer descriptor ring */ + for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) + nicvf_free_rbdr(nic, &qs->rbdr[qidx]); + + /* Free completion queue */ + for (qidx = 0; qidx < qs->cq_cnt; qidx++) + nicvf_free_cmp_queue(nic, &qs->cq[qidx]); + + /* Free send queue */ + for (qidx = 0; qidx < qs->sq_cnt; qidx++) + nicvf_free_snd_queue(nic, &qs->sq[qidx]); +} + +static int nicvf_alloc_resources(struct nicvf *nic) +{ + int qidx; + struct queue_set *qs = nic->qs; + + /* Alloc receive buffer descriptor ring */ + for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) { + if (nicvf_init_rbdr(nic, &qs->rbdr[qidx], qs->rbdr_len, + DMA_BUFFER_LEN)) + goto alloc_fail; + } + + /* Alloc send queue */ + for (qidx = 0; qidx < qs->sq_cnt; qidx++) { + if (nicvf_init_snd_queue(nic, &qs->sq[qidx], qs->sq_len)) + goto alloc_fail; + } + + /* Alloc completion queue */ + for (qidx = 0; qidx < qs->cq_cnt; qidx++) { + if (nicvf_init_cmp_queue(nic, &qs->cq[qidx], qs->cq_len)) + goto alloc_fail; + } + + return 0; +alloc_fail: + nicvf_free_resources(nic); + return -ENOMEM; +} + +int nicvf_set_qset_resources(struct nicvf *nic) +{ + struct queue_set *qs; + + qs = devm_kzalloc(&nic->pdev->dev, sizeof(*qs), GFP_KERNEL); + if (!qs) + return -ENOMEM; + nic->qs = qs; + + /* Set count of each queue */ + qs->rbdr_cnt = RBDR_CNT; + qs->rq_cnt = RCV_QUEUE_CNT; + qs->sq_cnt = SND_QUEUE_CNT; + qs->cq_cnt = CMP_QUEUE_CNT; + + /* Set queue lengths */ + qs->rbdr_len = RCV_BUF_COUNT; + qs->sq_len = SND_QUEUE_LEN; + qs->cq_len = CMP_QUEUE_LEN; + return 0; +} + +int nicvf_config_data_transfer(struct nicvf *nic, bool enable) +{ + bool disable = false; + struct queue_set *qs = nic->qs; + int qidx; + + if (!qs) + return 0; + + if (enable) { + if (nicvf_alloc_resources(nic)) + return -ENOMEM; + + for (qidx = 0; qidx < qs->sq_cnt; qidx++) + nicvf_snd_queue_config(nic, qs, qidx, enable); + for (qidx = 0; qidx < qs->cq_cnt; qidx++) + nicvf_cmp_queue_config(nic, qs, qidx, enable); + for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) + nicvf_rbdr_config(nic, qs, qidx, enable); + for (qidx = 0; qidx < qs->rq_cnt; qidx++) + nicvf_rcv_queue_config(nic, qs, qidx, enable); + } else { + for (qidx = 0; qidx < qs->rq_cnt; qidx++) + nicvf_rcv_queue_config(nic, qs, qidx, disable); + for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) + nicvf_rbdr_config(nic, qs, qidx, disable); + for (qidx = 0; qidx < qs->sq_cnt; qidx++) + nicvf_snd_queue_config(nic, qs, qidx, disable); + for (qidx = 0; qidx < qs->cq_cnt; qidx++) + nicvf_cmp_queue_config(nic, qs, qidx, disable); + + nicvf_free_resources(nic); + } + + return 0; +} + +/* Get a free desc from SQ + * returns descriptor ponter & descriptor number + */ +static inline int nicvf_get_sq_desc(struct snd_queue *sq, int desc_cnt) +{ + int qentry; + + qentry = sq->tail; + atomic_sub(desc_cnt, &sq->free_cnt); + sq->tail += desc_cnt; + sq->tail &= (sq->dmem.q_len - 1); + + return qentry; +} + +/* Free descriptor back to SQ for future use */ +void nicvf_put_sq_desc(struct snd_queue *sq, int desc_cnt) +{ + atomic_add(desc_cnt, &sq->free_cnt); + sq->head += desc_cnt; + sq->head &= (sq->dmem.q_len - 1); +} + +static inline int nicvf_get_nxt_sqentry(struct snd_queue *sq, int qentry) +{ + qentry++; + qentry &= (sq->dmem.q_len - 1); + return qentry; +} + +void nicvf_sq_enable(struct nicvf *nic, struct snd_queue *sq, int qidx) +{ + u64 sq_cfg; + + sq_cfg = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CFG, qidx); + sq_cfg |= NICVF_SQ_EN; + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, sq_cfg); + /* Ring doorbell so that H/W restarts processing SQEs */ + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR, qidx, 0); +} + +void nicvf_sq_disable(struct nicvf *nic, int qidx) +{ + u64 sq_cfg; + + sq_cfg = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CFG, qidx); + sq_cfg &= ~NICVF_SQ_EN; + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, sq_cfg); +} + +void nicvf_sq_free_used_descs(struct net_device *netdev, struct snd_queue *sq, + int qidx) +{ + u64 head, tail; + struct sk_buff *skb; + struct nicvf *nic = netdev_priv(netdev); + struct sq_hdr_subdesc *hdr; + + head = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_HEAD, qidx) >> 4; + tail = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_TAIL, qidx) >> 4; + while (sq->head != head) { + hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, sq->head); + if (hdr->subdesc_type != SQ_DESC_TYPE_HEADER) { + nicvf_put_sq_desc(sq, 1); + continue; + } + skb = (struct sk_buff *)sq->skbuff[sq->head]; + atomic64_add(1, (atomic64_t *)&netdev->stats.tx_packets); + atomic64_add(hdr->tot_len, + (atomic64_t *)&netdev->stats.tx_bytes); + dev_kfree_skb_any(skb); + nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1); + } +} + +/* Calculate no of SQ subdescriptors needed to transmit all + * segments of this TSO packet. + * Taken from 'Tilera network driver' with a minor modification. + */ +static int nicvf_tso_count_subdescs(struct sk_buff *skb) +{ + struct skb_shared_info *sh = skb_shinfo(skb); + unsigned int sh_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + unsigned int data_len = skb->len - sh_len; + unsigned int p_len = sh->gso_size; + long f_id = -1; /* id of the current fragment */ + long f_size = skb_headlen(skb) - sh_len; /* current fragment size */ + long f_used = 0; /* bytes used from the current fragment */ + long n; /* size of the current piece of payload */ + int num_edescs = 0; + int segment; + + for (segment = 0; segment < sh->gso_segs; segment++) { + unsigned int p_used = 0; + + /* One edesc for header and for each piece of the payload. */ + for (num_edescs++; p_used < p_len; num_edescs++) { + /* Advance as needed. */ + while (f_used >= f_size) { + f_id++; + f_size = skb_frag_size(&sh->frags[f_id]); + f_used = 0; + } + + /* Use bytes from the current fragment. */ + n = p_len - p_used; + if (n > f_size - f_used) + n = f_size - f_used; + f_used += n; + p_used += n; + } + + /* The last segment may be less than gso_size. */ + data_len -= p_len; + if (data_len < p_len) + p_len = data_len; + } + + /* '+ gso_segs' for SQ_HDR_SUDESCs for each segment */ + return num_edescs + sh->gso_segs; +} + +/* Get the number of SQ descriptors needed to xmit this skb */ +static int nicvf_sq_subdesc_required(struct nicvf *nic, struct sk_buff *skb) +{ + int subdesc_cnt = MIN_SQ_DESC_PER_PKT_XMIT; + + if (skb_shinfo(skb)->gso_size) { + subdesc_cnt = nicvf_tso_count_subdescs(skb); + return subdesc_cnt; + } + + if (skb_shinfo(skb)->nr_frags) + subdesc_cnt += skb_shinfo(skb)->nr_frags; + + return subdesc_cnt; +} + +/* Add SQ HEADER subdescriptor. + * First subdescriptor for every send descriptor. + */ +static inline void +nicvf_sq_add_hdr_subdesc(struct snd_queue *sq, int qentry, + int subdesc_cnt, struct sk_buff *skb, int len) +{ + int proto; + struct sq_hdr_subdesc *hdr; + + hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry); + sq->skbuff[qentry] = (u64)skb; + + memset(hdr, 0, SND_QUEUE_DESC_SIZE); + hdr->subdesc_type = SQ_DESC_TYPE_HEADER; + /* Enable notification via CQE after processing SQE */ + hdr->post_cqe = 1; + /* No of subdescriptors following this */ + hdr->subdesc_cnt = subdesc_cnt; + hdr->tot_len = len; + + /* Offload checksum calculation to HW */ + if (skb->ip_summed == CHECKSUM_PARTIAL) { + if (skb->protocol != htons(ETH_P_IP)) + return; + + hdr->csum_l3 = 1; /* Enable IP csum calculation */ + hdr->l3_offset = skb_network_offset(skb); + hdr->l4_offset = skb_transport_offset(skb); + + proto = ip_hdr(skb)->protocol; + switch (proto) { + case IPPROTO_TCP: + hdr->csum_l4 = SEND_L4_CSUM_TCP; + break; + case IPPROTO_UDP: + hdr->csum_l4 = SEND_L4_CSUM_UDP; + break; + case IPPROTO_SCTP: + hdr->csum_l4 = SEND_L4_CSUM_SCTP; + break; + } + } +} + +/* SQ GATHER subdescriptor + * Must follow HDR descriptor + */ +static inline void nicvf_sq_add_gather_subdesc(struct snd_queue *sq, int qentry, + int size, u64 data) +{ + struct sq_gather_subdesc *gather; + + qentry &= (sq->dmem.q_len - 1); + gather = (struct sq_gather_subdesc *)GET_SQ_DESC(sq, qentry); + + memset(gather, 0, SND_QUEUE_DESC_SIZE); + gather->subdesc_type = SQ_DESC_TYPE_GATHER; + gather->ld_type = NIC_SEND_LD_TYPE_E_LDWB; + gather->size = size; + gather->addr = data; +} + +/* Segment a TSO packet into 'gso_size' segments and append + * them to SQ for transfer + */ +static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq, + int qentry, struct sk_buff *skb) +{ + struct tso_t tso; + int seg_subdescs = 0, desc_cnt = 0; + int seg_len, total_len, data_left; + int hdr_qentry = qentry; + int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + + tso_start(skb, &tso); + total_len = skb->len - hdr_len; + while (total_len > 0) { + char *hdr; + + /* Save Qentry for adding HDR_SUBDESC at the end */ + hdr_qentry = qentry; + + data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len); + total_len -= data_left; + + /* Add segment's header */ + qentry = nicvf_get_nxt_sqentry(sq, qentry); + hdr = sq->tso_hdrs + qentry * TSO_HEADER_SIZE; + tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0); + nicvf_sq_add_gather_subdesc(sq, qentry, hdr_len, + sq->tso_hdrs_phys + + qentry * TSO_HEADER_SIZE); + /* HDR_SUDESC + GATHER */ + seg_subdescs = 2; + seg_len = hdr_len; + + /* Add segment's payload fragments */ + while (data_left > 0) { + int size; + + size = min_t(int, tso.size, data_left); + + qentry = nicvf_get_nxt_sqentry(sq, qentry); + nicvf_sq_add_gather_subdesc(sq, qentry, size, + virt_to_phys(tso.data)); + seg_subdescs++; + seg_len += size; + + data_left -= size; + tso_build_data(skb, &tso, size); + } + nicvf_sq_add_hdr_subdesc(sq, hdr_qentry, + seg_subdescs - 1, skb, seg_len); + sq->skbuff[hdr_qentry] = 0; + qentry = nicvf_get_nxt_sqentry(sq, qentry); + + desc_cnt += seg_subdescs; + } + /* Save SKB in the last segment for freeing */ + sq->skbuff[hdr_qentry] = (u64)skb; + + /* make sure all memory stores are done before ringing doorbell */ + smp_wmb(); + + /* Inform HW to xmit all TSO segments */ + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR, + skb_get_queue_mapping(skb), desc_cnt); + return 1; +} + +/* Append an skb to a SQ for packet transfer. */ +int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb) +{ + int i, size; + int subdesc_cnt; + int sq_num, qentry; + struct queue_set *qs = nic->qs; + struct snd_queue *sq; + + sq_num = skb_get_queue_mapping(skb); + sq = &qs->sq[sq_num]; + + subdesc_cnt = nicvf_sq_subdesc_required(nic, skb); + if (subdesc_cnt > atomic_read(&sq->free_cnt)) + goto append_fail; + + qentry = nicvf_get_sq_desc(sq, subdesc_cnt); + + /* Check if its a TSO packet */ + if (skb_shinfo(skb)->gso_size) + return nicvf_sq_append_tso(nic, sq, qentry, skb); + + /* Add SQ header subdesc */ + nicvf_sq_add_hdr_subdesc(sq, qentry, subdesc_cnt - 1, skb, skb->len); + + /* Add SQ gather subdescs */ + qentry = nicvf_get_nxt_sqentry(sq, qentry); + size = skb_is_nonlinear(skb) ? skb_headlen(skb) : skb->len; + nicvf_sq_add_gather_subdesc(sq, qentry, size, virt_to_phys(skb->data)); + + /* Check for scattered buffer */ + if (!skb_is_nonlinear(skb)) + goto doorbell; + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + const struct skb_frag_struct *frag; + + frag = &skb_shinfo(skb)->frags[i]; + + qentry = nicvf_get_nxt_sqentry(sq, qentry); + size = skb_frag_size(frag); + nicvf_sq_add_gather_subdesc(sq, qentry, size, + virt_to_phys( + skb_frag_address(frag))); + } + +doorbell: + /* make sure all memory stores are done before ringing doorbell */ + smp_wmb(); + + /* Inform HW to xmit new packet */ + nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR, + sq_num, subdesc_cnt); + return 1; + +append_fail: + netdev_dbg(nic->netdev, "Not enough SQ descriptors to xmit pkt\n"); + return 0; +} + +static inline unsigned frag_num(unsigned i) +{ +#ifdef __BIG_ENDIAN + return (i & ~3) + 3 - (i & 3); +#else + return i; +#endif +} + +/* Returns SKB for a received packet */ +struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx) +{ + int frag; + int payload_len = 0; + struct sk_buff *skb = NULL; + struct sk_buff *skb_frag = NULL; + struct sk_buff *prev_frag = NULL; + u16 *rb_lens = NULL; + u64 *rb_ptrs = NULL; + + rb_lens = (void *)cqe_rx + (3 * sizeof(u64)); + rb_ptrs = (void *)cqe_rx + (6 * sizeof(u64)); + + netdev_dbg(nic->netdev, "%s rb_cnt %d rb0_ptr %llx rb0_sz %d\n", + __func__, cqe_rx->rb_cnt, cqe_rx->rb0_ptr, cqe_rx->rb0_sz); + + for (frag = 0; frag < cqe_rx->rb_cnt; frag++) { + payload_len = rb_lens[frag_num(frag)]; + if (!frag) { + /* First fragment */ + skb = nicvf_rb_ptr_to_skb(nic, + *rb_ptrs - cqe_rx->align_pad, + payload_len); + if (!skb) + return NULL; + skb_reserve(skb, cqe_rx->align_pad); + skb_put(skb, payload_len); + } else { + /* Add fragments */ + skb_frag = nicvf_rb_ptr_to_skb(nic, *rb_ptrs, + payload_len); + if (!skb_frag) { + dev_kfree_skb(skb); + return NULL; + } + + if (!skb_shinfo(skb)->frag_list) + skb_shinfo(skb)->frag_list = skb_frag; + else + prev_frag->next = skb_frag; + + prev_frag = skb_frag; + skb->len += payload_len; + skb->data_len += payload_len; + skb_frag->len = payload_len; + } + /* Next buffer pointer */ + rb_ptrs++; + } + return skb; +} + +/* Enable interrupt */ +void nicvf_enable_intr(struct nicvf *nic, int int_type, int q_idx) +{ + u64 reg_val; + + reg_val = nicvf_reg_read(nic, NIC_VF_ENA_W1S); + + switch (int_type) { + case NICVF_INTR_CQ: + reg_val |= ((1ULL << q_idx) << NICVF_INTR_CQ_SHIFT); + break; + case NICVF_INTR_SQ: + reg_val |= ((1ULL << q_idx) << NICVF_INTR_SQ_SHIFT); + break; + case NICVF_INTR_RBDR: + reg_val |= ((1ULL << q_idx) << NICVF_INTR_RBDR_SHIFT); + break; + case NICVF_INTR_PKT_DROP: + reg_val |= (1ULL << NICVF_INTR_PKT_DROP_SHIFT); + break; + case NICVF_INTR_TCP_TIMER: + reg_val |= (1ULL << NICVF_INTR_TCP_TIMER_SHIFT); + break; + case NICVF_INTR_MBOX: + reg_val |= (1ULL << NICVF_INTR_MBOX_SHIFT); + break; + case NICVF_INTR_QS_ERR: + reg_val |= (1ULL << NICVF_INTR_QS_ERR_SHIFT); + break; + default: + netdev_err(nic->netdev, + "Failed to enable interrupt: unknown type\n"); + break; + } + + nicvf_reg_write(nic, NIC_VF_ENA_W1S, reg_val); +} + +/* Disable interrupt */ +void nicvf_disable_intr(struct nicvf *nic, int int_type, int q_idx) +{ + u64 reg_val = 0; + + switch (int_type) { + case NICVF_INTR_CQ: + reg_val |= ((1ULL << q_idx) << NICVF_INTR_CQ_SHIFT); + break; + case NICVF_INTR_SQ: + reg_val |= ((1ULL << q_idx) << NICVF_INTR_SQ_SHIFT); + break; + case NICVF_INTR_RBDR: + reg_val |= ((1ULL << q_idx) << NICVF_INTR_RBDR_SHIFT); + break; + case NICVF_INTR_PKT_DROP: + reg_val |= (1ULL << NICVF_INTR_PKT_DROP_SHIFT); + break; + case NICVF_INTR_TCP_TIMER: + reg_val |= (1ULL << NICVF_INTR_TCP_TIMER_SHIFT); + break; + case NICVF_INTR_MBOX: + reg_val |= (1ULL << NICVF_INTR_MBOX_SHIFT); + break; + case NICVF_INTR_QS_ERR: + reg_val |= (1ULL << NICVF_INTR_QS_ERR_SHIFT); + break; + default: + netdev_err(nic->netdev, + "Failed to disable interrupt: unknown type\n"); + break; + } + + nicvf_reg_write(nic, NIC_VF_ENA_W1C, reg_val); +} + +/* Clear interrupt */ +void nicvf_clear_intr(struct nicvf *nic, int int_type, int q_idx) +{ + u64 reg_val = 0; + + switch (int_type) { + case NICVF_INTR_CQ: + reg_val = ((1ULL << q_idx) << NICVF_INTR_CQ_SHIFT); + break; + case NICVF_INTR_SQ: + reg_val = ((1ULL << q_idx) << NICVF_INTR_SQ_SHIFT); + break; + case NICVF_INTR_RBDR: + reg_val = ((1ULL << q_idx) << NICVF_INTR_RBDR_SHIFT); + break; + case NICVF_INTR_PKT_DROP: + reg_val = (1ULL << NICVF_INTR_PKT_DROP_SHIFT); + break; + case NICVF_INTR_TCP_TIMER: + reg_val = (1ULL << NICVF_INTR_TCP_TIMER_SHIFT); + break; + case NICVF_INTR_MBOX: + reg_val = (1ULL << NICVF_INTR_MBOX_SHIFT); + break; + case NICVF_INTR_QS_ERR: + reg_val |= (1ULL << NICVF_INTR_QS_ERR_SHIFT); + break; + default: + netdev_err(nic->netdev, + "Failed to clear interrupt: unknown type\n"); + break; + } + + nicvf_reg_write(nic, NIC_VF_INT, reg_val); +} + +/* Check if interrupt is enabled */ +int nicvf_is_intr_enabled(struct nicvf *nic, int int_type, int q_idx) +{ + u64 reg_val; + u64 mask = 0xff; + + reg_val = nicvf_reg_read(nic, NIC_VF_ENA_W1S); + + switch (int_type) { + case NICVF_INTR_CQ: + mask = ((1ULL << q_idx) << NICVF_INTR_CQ_SHIFT); + break; + case NICVF_INTR_SQ: + mask = ((1ULL << q_idx) << NICVF_INTR_SQ_SHIFT); + break; + case NICVF_INTR_RBDR: + mask = ((1ULL << q_idx) << NICVF_INTR_RBDR_SHIFT); + break; + case NICVF_INTR_PKT_DROP: + mask = NICVF_INTR_PKT_DROP_MASK; + break; + case NICVF_INTR_TCP_TIMER: + mask = NICVF_INTR_TCP_TIMER_MASK; + break; + case NICVF_INTR_MBOX: + mask = NICVF_INTR_MBOX_MASK; + break; + case NICVF_INTR_QS_ERR: + mask = NICVF_INTR_QS_ERR_MASK; + break; + default: + netdev_err(nic->netdev, + "Failed to check interrupt enable: unknown type\n"); + break; + } + + return (reg_val & mask); +} + +void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx) +{ + struct rcv_queue *rq; + +#define GET_RQ_STATS(reg) \ + nicvf_reg_read(nic, NIC_QSET_RQ_0_7_STAT_0_1 |\ + (rq_idx << NIC_Q_NUM_SHIFT) | (reg << 3)) + + rq = &nic->qs->rq[rq_idx]; + rq->stats.bytes = GET_RQ_STATS(RQ_SQ_STATS_OCTS); + rq->stats.pkts = GET_RQ_STATS(RQ_SQ_STATS_PKTS); +} + +void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx) +{ + struct snd_queue *sq; + +#define GET_SQ_STATS(reg) \ + nicvf_reg_read(nic, NIC_QSET_SQ_0_7_STAT_0_1 |\ + (sq_idx << NIC_Q_NUM_SHIFT) | (reg << 3)) + + sq = &nic->qs->sq[sq_idx]; + sq->stats.bytes = GET_SQ_STATS(RQ_SQ_STATS_OCTS); + sq->stats.pkts = GET_SQ_STATS(RQ_SQ_STATS_PKTS); +} + +/* Check for errors in the receive cmp.queue entry */ +int nicvf_check_cqe_rx_errs(struct nicvf *nic, + struct cmp_queue *cq, struct cqe_rx_t *cqe_rx) +{ + struct cmp_queue_stats *stats = &cq->stats; + + if (!cqe_rx->err_level && !cqe_rx->err_opcode) { + stats->rx.errop.good++; + return 0; + } + + if (netif_msg_rx_err(nic)) + netdev_err(nic->netdev, + "%s: RX error CQE err_level 0x%x err_opcode 0x%x\n", + nic->netdev->name, + cqe_rx->err_level, cqe_rx->err_opcode); + + switch (cqe_rx->err_level) { + case CQ_ERRLVL_MAC: + stats->rx.errlvl.mac_errs++; + break; + case CQ_ERRLVL_L2: + stats->rx.errlvl.l2_errs++; + break; + case CQ_ERRLVL_L3: + stats->rx.errlvl.l3_errs++; + break; + case CQ_ERRLVL_L4: + stats->rx.errlvl.l4_errs++; + break; + } + + switch (cqe_rx->err_opcode) { + case CQ_RX_ERROP_RE_PARTIAL: + stats->rx.errop.partial_pkts++; + break; + case CQ_RX_ERROP_RE_JABBER: + stats->rx.errop.jabber_errs++; + break; + case CQ_RX_ERROP_RE_FCS: + stats->rx.errop.fcs_errs++; + break; + case CQ_RX_ERROP_RE_TERMINATE: + stats->rx.errop.terminate_errs++; + break; + case CQ_RX_ERROP_RE_RX_CTL: + stats->rx.errop.bgx_rx_errs++; + break; + case CQ_RX_ERROP_PREL2_ERR: + stats->rx.errop.prel2_errs++; + break; + case CQ_RX_ERROP_L2_FRAGMENT: + stats->rx.errop.l2_frags++; + break; + case CQ_RX_ERROP_L2_OVERRUN: + stats->rx.errop.l2_overruns++; + break; + case CQ_RX_ERROP_L2_PFCS: + stats->rx.errop.l2_pfcs++; + break; + case CQ_RX_ERROP_L2_PUNY: + stats->rx.errop.l2_puny++; + break; + case CQ_RX_ERROP_L2_MAL: + stats->rx.errop.l2_hdr_malformed++; + break; + case CQ_RX_ERROP_L2_OVERSIZE: + stats->rx.errop.l2_oversize++; + break; + case CQ_RX_ERROP_L2_UNDERSIZE: + stats->rx.errop.l2_undersize++; + break; + case CQ_RX_ERROP_L2_LENMISM: + stats->rx.errop.l2_len_mismatch++; + break; + case CQ_RX_ERROP_L2_PCLP: + stats->rx.errop.l2_pclp++; + break; + case CQ_RX_ERROP_IP_NOT: + stats->rx.errop.non_ip++; + break; + case CQ_RX_ERROP_IP_CSUM_ERR: + stats->rx.errop.ip_csum_err++; + break; + case CQ_RX_ERROP_IP_MAL: + stats->rx.errop.ip_hdr_malformed++; + break; + case CQ_RX_ERROP_IP_MALD: + stats->rx.errop.ip_payload_malformed++; + break; + case CQ_RX_ERROP_IP_HOP: + stats->rx.errop.ip_hop_errs++; + break; + case CQ_RX_ERROP_L3_ICRC: + stats->rx.errop.l3_icrc_errs++; + break; + case CQ_RX_ERROP_L3_PCLP: + stats->rx.errop.l3_pclp++; + break; + case CQ_RX_ERROP_L4_MAL: + stats->rx.errop.l4_malformed++; + break; + case CQ_RX_ERROP_L4_CHK: + stats->rx.errop.l4_csum_errs++; + break; + case CQ_RX_ERROP_UDP_LEN: + stats->rx.errop.udp_len_err++; + break; + case CQ_RX_ERROP_L4_PORT: + stats->rx.errop.bad_l4_port++; + break; + case CQ_RX_ERROP_TCP_FLAG: + stats->rx.errop.bad_tcp_flag++; + break; + case CQ_RX_ERROP_TCP_OFFSET: + stats->rx.errop.tcp_offset_errs++; + break; + case CQ_RX_ERROP_L4_PCLP: + stats->rx.errop.l4_pclp++; + break; + case CQ_RX_ERROP_RBDR_TRUNC: + stats->rx.errop.pkt_truncated++; + break; + } + + return 1; +} + +/* Check for errors in the send cmp.queue entry */ +int nicvf_check_cqe_tx_errs(struct nicvf *nic, + struct cmp_queue *cq, struct cqe_send_t *cqe_tx) +{ + struct cmp_queue_stats *stats = &cq->stats; + + switch (cqe_tx->send_status) { + case CQ_TX_ERROP_GOOD: + stats->tx.good++; + return 0; + case CQ_TX_ERROP_DESC_FAULT: + stats->tx.desc_fault++; + break; + case CQ_TX_ERROP_HDR_CONS_ERR: + stats->tx.hdr_cons_err++; + break; + case CQ_TX_ERROP_SUBDC_ERR: + stats->tx.subdesc_err++; + break; + case CQ_TX_ERROP_IMM_SIZE_OFLOW: + stats->tx.imm_size_oflow++; + break; + case CQ_TX_ERROP_DATA_SEQUENCE_ERR: + stats->tx.data_seq_err++; + break; + case CQ_TX_ERROP_MEM_SEQUENCE_ERR: + stats->tx.mem_seq_err++; + break; + case CQ_TX_ERROP_LOCK_VIOL: + stats->tx.lock_viol++; + break; + case CQ_TX_ERROP_DATA_FAULT: + stats->tx.data_fault++; + break; + case CQ_TX_ERROP_TSTMP_CONFLICT: + stats->tx.tstmp_conflict++; + break; + case CQ_TX_ERROP_TSTMP_TIMEOUT: + stats->tx.tstmp_timeout++; + break; + case CQ_TX_ERROP_MEM_FAULT: + stats->tx.mem_fault++; + break; + case CQ_TX_ERROP_CK_OVERLAP: + stats->tx.csum_overlap++; + break; + case CQ_TX_ERROP_CK_OFLOW: + stats->tx.csum_overflow++; + break; + } + + return 1; +} diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h new file mode 100644 index 0000000..8341bdf --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -0,0 +1,381 @@ +/* + * Copyright (C) 2015 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#ifndef NICVF_QUEUES_H +#define NICVF_QUEUES_H + +#include <linux/netdevice.h> +#include "q_struct.h" + +#define MAX_QUEUE_SET 128 +#define MAX_RCV_QUEUES_PER_QS 8 +#define MAX_RCV_BUF_DESC_RINGS_PER_QS 2 +#define MAX_SND_QUEUES_PER_QS 8 +#define MAX_CMP_QUEUES_PER_QS 8 + +/* VF's queue interrupt ranges */ +#define NICVF_INTR_ID_CQ 0 +#define NICVF_INTR_ID_SQ 8 +#define NICVF_INTR_ID_RBDR 16 +#define NICVF_INTR_ID_MISC 18 +#define NICVF_INTR_ID_QS_ERR 19 + +#define for_each_cq_irq(irq) \ + for (irq = NICVF_INTR_ID_CQ; irq < NICVF_INTR_ID_SQ; irq++) +#define for_each_sq_irq(irq) \ + for (irq = NICVF_INTR_ID_SQ; irq < NICVF_INTR_ID_RBDR; irq++) +#define for_each_rbdr_irq(irq) \ + for (irq = NICVF_INTR_ID_RBDR; irq < NICVF_INTR_ID_MISC; irq++) + +#define RBDR_SIZE0 0ULL /* 8K entries */ +#define RBDR_SIZE1 1ULL /* 16K entries */ +#define RBDR_SIZE2 2ULL /* 32K entries */ +#define RBDR_SIZE3 3ULL /* 64K entries */ +#define RBDR_SIZE4 4ULL /* 126K entries */ +#define RBDR_SIZE5 5ULL /* 256K entries */ +#define RBDR_SIZE6 6ULL /* 512K entries */ + +#define SND_QUEUE_SIZE0 0ULL /* 1K entries */ +#define SND_QUEUE_SIZE1 1ULL /* 2K entries */ +#define SND_QUEUE_SIZE2 2ULL /* 4K entries */ +#define SND_QUEUE_SIZE3 3ULL /* 8K entries */ +#define SND_QUEUE_SIZE4 4ULL /* 16K entries */ +#define SND_QUEUE_SIZE5 5ULL /* 32K entries */ +#define SND_QUEUE_SIZE6 6ULL /* 64K entries */ + +#define CMP_QUEUE_SIZE0 0ULL /* 1K entries */ +#define CMP_QUEUE_SIZE1 1ULL /* 2K entries */ +#define CMP_QUEUE_SIZE2 2ULL /* 4K entries */ +#define CMP_QUEUE_SIZE3 3ULL /* 8K entries */ +#define CMP_QUEUE_SIZE4 4ULL /* 16K entries */ +#define CMP_QUEUE_SIZE5 5ULL /* 32K entries */ +#define CMP_QUEUE_SIZE6 6ULL /* 64K entries */ + +/* Default queue count per QS, its lengths and threshold values */ +#define RBDR_CNT 1 +#define RCV_QUEUE_CNT 8 +#define SND_QUEUE_CNT 8 +#define CMP_QUEUE_CNT 8 /* Max of RCV and SND qcount */ + +#define SND_QSIZE SND_QUEUE_SIZE4 +#define SND_QUEUE_LEN (1ULL << (SND_QSIZE + 10)) +#define MAX_SND_QUEUE_LEN (1ULL << (SND_QUEUE_SIZE6 + 10)) +#define SND_QUEUE_THRESH 2ULL +#define MIN_SQ_DESC_PER_PKT_XMIT 2 +/* Since timestamp not enabled, otherwise 2 */ +#define MAX_CQE_PER_PKT_XMIT 1 + +#define CMP_QSIZE CMP_QUEUE_SIZE4 +#define CMP_QUEUE_LEN (1ULL << (CMP_QSIZE + 10)) +#define CMP_QUEUE_CQE_THRESH 0 +#define CMP_QUEUE_TIMER_THRESH 220 /* 10usec */ + +#define RBDR_SIZE RBDR_SIZE0 +#define RCV_BUF_COUNT (1ULL << (RBDR_SIZE + 13)) +#define MAX_RCV_BUF_COUNT (1ULL << (RBDR_SIZE6 + 13)) +#define RBDR_THRESH (RCV_BUF_COUNT / 2) +#define DMA_BUFFER_LEN 2048 /* In multiples of 128bytes */ +#define RCV_FRAG_LEN (SKB_DATA_ALIGN(DMA_BUFFER_LEN + NET_SKB_PAD) + \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + \ + (NICVF_RCV_BUF_ALIGN_BYTES * 2)) +#define RCV_DATA_OFFSET NICVF_RCV_BUF_ALIGN_BYTES + +#define MAX_CQES_FOR_TX ((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \ + MAX_CQE_PER_PKT_XMIT) +#define RQ_CQ_DROP ((CMP_QUEUE_LEN - MAX_CQES_FOR_TX) / 256) + +/* Descriptor size in bytes */ +#define SND_QUEUE_DESC_SIZE 16 +#define CMP_QUEUE_DESC_SIZE 512 + +/* Buffer / descriptor alignments */ +#define NICVF_RCV_BUF_ALIGN 7 +#define NICVF_RCV_BUF_ALIGN_BYTES (1ULL << NICVF_RCV_BUF_ALIGN) +#define NICVF_CQ_BASE_ALIGN_BYTES 512 /* 9 bits */ +#define NICVF_SQ_BASE_ALIGN_BYTES 128 /* 7 bits */ + +#define NICVF_ALIGNED_ADDR(ADDR, ALIGN_BYTES) ALIGN(ADDR, ALIGN_BYTES) +#define NICVF_ADDR_ALIGN_LEN(ADDR, BYTES)\ + (NICVF_ALIGNED_ADDR(ADDR, BYTES) - BYTES) +#define NICVF_RCV_BUF_ALIGN_LEN(X)\ + (NICVF_ALIGNED_ADDR(X, NICVF_RCV_BUF_ALIGN_BYTES) - X) + +/* Queue enable/disable */ +#define NICVF_SQ_EN BIT_ULL(19) + +/* Queue reset */ +#define NICVF_CQ_RESET BIT_ULL(41) +#define NICVF_SQ_RESET BIT_ULL(17) +#define NICVF_RBDR_RESET BIT_ULL(43) + +enum CQ_RX_ERRLVL_E { + CQ_ERRLVL_MAC, + CQ_ERRLVL_L2, + CQ_ERRLVL_L3, + CQ_ERRLVL_L4, +}; + +enum CQ_RX_ERROP_E { + CQ_RX_ERROP_RE_NONE = 0x0, + CQ_RX_ERROP_RE_PARTIAL = 0x1, + CQ_RX_ERROP_RE_JABBER = 0x2, + CQ_RX_ERROP_RE_FCS = 0x7, + CQ_RX_ERROP_RE_TERMINATE = 0x9, + CQ_RX_ERROP_RE_RX_CTL = 0xb, + CQ_RX_ERROP_PREL2_ERR = 0x1f, + CQ_RX_ERROP_L2_FRAGMENT = 0x20, + CQ_RX_ERROP_L2_OVERRUN = 0x21, + CQ_RX_ERROP_L2_PFCS = 0x22, + CQ_RX_ERROP_L2_PUNY = 0x23, + CQ_RX_ERROP_L2_MAL = 0x24, + CQ_RX_ERROP_L2_OVERSIZE = 0x25, + CQ_RX_ERROP_L2_UNDERSIZE = 0x26, + CQ_RX_ERROP_L2_LENMISM = 0x27, + CQ_RX_ERROP_L2_PCLP = 0x28, + CQ_RX_ERROP_IP_NOT = 0x41, + CQ_RX_ERROP_IP_CSUM_ERR = 0x42, + CQ_RX_ERROP_IP_MAL = 0x43, + CQ_RX_ERROP_IP_MALD = 0x44, + CQ_RX_ERROP_IP_HOP = 0x45, + CQ_RX_ERROP_L3_ICRC = 0x46, + CQ_RX_ERROP_L3_PCLP = 0x47, + CQ_RX_ERROP_L4_MAL = 0x61, + CQ_RX_ERROP_L4_CHK = 0x62, + CQ_RX_ERROP_UDP_LEN = 0x63, + CQ_RX_ERROP_L4_PORT = 0x64, + CQ_RX_ERROP_TCP_FLAG = 0x65, + CQ_RX_ERROP_TCP_OFFSET = 0x66, + CQ_RX_ERROP_L4_PCLP = 0x67, + CQ_RX_ERROP_RBDR_TRUNC = 0x70, +}; + +enum CQ_TX_ERROP_E { + CQ_TX_ERROP_GOOD = 0x0, + CQ_TX_ERROP_DESC_FAULT = 0x10, + CQ_TX_ERROP_HDR_CONS_ERR = 0x11, + CQ_TX_ERROP_SUBDC_ERR = 0x12, + CQ_TX_ERROP_IMM_SIZE_OFLOW = 0x80, + CQ_TX_ERROP_DATA_SEQUENCE_ERR = 0x81, + CQ_TX_ERROP_MEM_SEQUENCE_ERR = 0x82, + CQ_TX_ERROP_LOCK_VIOL = 0x83, + CQ_TX_ERROP_DATA_FAULT = 0x84, + CQ_TX_ERROP_TSTMP_CONFLICT = 0x85, + CQ_TX_ERROP_TSTMP_TIMEOUT = 0x86, + CQ_TX_ERROP_MEM_FAULT = 0x87, + CQ_TX_ERROP_CK_OVERLAP = 0x88, + CQ_TX_ERROP_CK_OFLOW = 0x89, + CQ_TX_ERROP_ENUM_LAST = 0x8a, +}; + +struct cmp_queue_stats { + struct rx_stats { + struct { + u64 mac_errs; + u64 l2_errs; + u64 l3_errs; + u64 l4_errs; + } errlvl; + struct { + u64 good; + u64 partial_pkts; + u64 jabber_errs; + u64 fcs_errs; + u64 terminate_errs; + u64 bgx_rx_errs; + u64 prel2_errs; + u64 l2_frags; + u64 l2_overruns; + u64 l2_pfcs; + u64 l2_puny; + u64 l2_hdr_malformed; + u64 l2_oversize; + u64 l2_undersize; + u64 l2_len_mismatch; + u64 l2_pclp; + u64 non_ip; + u64 ip_csum_err; + u64 ip_hdr_malformed; + u64 ip_payload_malformed; + u64 ip_hop_errs; + u64 l3_icrc_errs; + u64 l3_pclp; + u64 l4_malformed; + u64 l4_csum_errs; + u64 udp_len_err; + u64 bad_l4_port; + u64 bad_tcp_flag; + u64 tcp_offset_errs; + u64 l4_pclp; + u64 pkt_truncated; + } errop; + } rx; + struct tx_stats { + u64 good; + u64 desc_fault; + u64 hdr_cons_err; + u64 subdesc_err; + u64 imm_size_oflow; + u64 data_seq_err; + u64 mem_seq_err; + u64 lock_viol; + u64 data_fault; + u64 tstmp_conflict; + u64 tstmp_timeout; + u64 mem_fault; + u64 csum_overlap; + u64 csum_overflow; + } tx; +} ____cacheline_aligned_in_smp; + +enum RQ_SQ_STATS { + RQ_SQ_STATS_OCTS, + RQ_SQ_STATS_PKTS, +}; + +struct rx_tx_queue_stats { + u64 bytes; + u64 pkts; +} ____cacheline_aligned_in_smp; + +struct q_desc_mem { + dma_addr_t dma; + u64 size; + u16 q_len; + dma_addr_t phys_base; + void *base; + void *unalign_base; +}; + +struct rbdr { + bool enable; + u32 dma_size; + u32 frag_len; + u32 thresh; /* Threshold level for interrupt */ + void *desc; + u32 head; + u32 tail; + struct q_desc_mem dmem; +} ____cacheline_aligned_in_smp; + +struct rcv_queue { + bool enable; + struct rbdr *rbdr_start; + struct rbdr *rbdr_cont; + bool en_tcp_reassembly; + u8 cq_qs; /* CQ's QS to which this RQ is assigned */ + u8 cq_idx; /* CQ index (0 to 7) in the QS */ + u8 cont_rbdr_qs; /* Continue buffer ptrs - QS num */ + u8 cont_qs_rbdr_idx; /* RBDR idx in the cont QS */ + u8 start_rbdr_qs; /* First buffer ptrs - QS num */ + u8 start_qs_rbdr_idx; /* RBDR idx in the above QS */ + u8 caching; + struct rx_tx_queue_stats stats; +} ____cacheline_aligned_in_smp; + +struct cmp_queue { + bool enable; + u16 thresh; + spinlock_t lock; /* lock to serialize processing CQEs */ + void *desc; + struct q_desc_mem dmem; + struct cmp_queue_stats stats; +} ____cacheline_aligned_in_smp; + +struct snd_queue { + bool enable; + u8 cq_qs; /* CQ's QS to which this SQ is pointing */ + u8 cq_idx; /* CQ index (0 to 7) in the above QS */ + u16 thresh; + atomic_t free_cnt; + u32 head; + u32 tail; + u64 *skbuff; + void *desc; + +#define TSO_HEADER_SIZE 128 + /* For TSO segment's header */ + char *tso_hdrs; + dma_addr_t tso_hdrs_phys; + + cpumask_t affinity_mask; + struct q_desc_mem dmem; + struct rx_tx_queue_stats stats; +} ____cacheline_aligned_in_smp; + +struct queue_set { + bool enable; + bool be_en; + u8 vnic_id; + u8 rq_cnt; + u8 cq_cnt; + u64 cq_len; + u8 sq_cnt; + u64 sq_len; + u8 rbdr_cnt; + u64 rbdr_len; + struct rcv_queue rq[MAX_RCV_QUEUES_PER_QS]; + struct cmp_queue cq[MAX_CMP_QUEUES_PER_QS]; + struct snd_queue sq[MAX_SND_QUEUES_PER_QS]; + struct rbdr rbdr[MAX_RCV_BUF_DESC_RINGS_PER_QS]; +} ____cacheline_aligned_in_smp; + +#define GET_RBDR_DESC(RING, idx)\ + (&(((struct rbdr_entry_t *)((RING)->desc))[idx])) +#define GET_SQ_DESC(RING, idx)\ + (&(((struct sq_hdr_subdesc *)((RING)->desc))[idx])) +#define GET_CQ_DESC(RING, idx)\ + (&(((union cq_desc_t *)((RING)->desc))[idx])) + +/* CQ status bits */ +#define CQ_WR_FULL BIT(26) +#define CQ_WR_DISABLE BIT(25) +#define CQ_WR_FAULT BIT(24) +#define CQ_CQE_COUNT (0xFFFF << 0) + +#define CQ_ERR_MASK (CQ_WR_FULL | CQ_WR_DISABLE | CQ_WR_FAULT) + +int nicvf_set_qset_resources(struct nicvf *nic); +int nicvf_config_data_transfer(struct nicvf *nic, bool enable); +void nicvf_qset_config(struct nicvf *nic, bool enable); +void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs, + int qidx, bool enable); + +void nicvf_sq_enable(struct nicvf *nic, struct snd_queue *sq, int qidx); +void nicvf_sq_disable(struct nicvf *nic, int qidx); +void nicvf_put_sq_desc(struct snd_queue *sq, int desc_cnt); +void nicvf_sq_free_used_descs(struct net_device *netdev, + struct snd_queue *sq, int qidx); +int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb); + +struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx); +void nicvf_rbdr_task(unsigned long data); +void nicvf_rbdr_work(struct work_struct *work); + +void nicvf_enable_intr(struct nicvf *nic, int int_type, int q_idx); +void nicvf_disable_intr(struct nicvf *nic, int int_type, int q_idx); +void nicvf_clear_intr(struct nicvf *nic, int int_type, int q_idx); +int nicvf_is_intr_enabled(struct nicvf *nic, int int_type, int q_idx); + +/* Register access APIs */ +void nicvf_reg_write(struct nicvf *nic, u64 offset, u64 val); +u64 nicvf_reg_read(struct nicvf *nic, u64 offset); +void nicvf_qset_reg_write(struct nicvf *nic, u64 offset, u64 val); +u64 nicvf_qset_reg_read(struct nicvf *nic, u64 offset); +void nicvf_queue_reg_write(struct nicvf *nic, u64 offset, + u64 qidx, u64 val); +u64 nicvf_queue_reg_read(struct nicvf *nic, + u64 offset, u64 qidx); + +/* Stats */ +void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx); +void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx); +int nicvf_check_cqe_rx_errs(struct nicvf *nic, + struct cmp_queue *cq, struct cqe_rx_t *cqe_rx); +int nicvf_check_cqe_tx_errs(struct nicvf *nic, + struct cmp_queue *cq, struct cqe_send_t *cqe_tx); +#endif /* NICVF_QUEUES_H */ diff --git a/drivers/net/ethernet/cavium/thunder/q_struct.h b/drivers/net/ethernet/cavium/thunder/q_struct.h new file mode 100644 index 0000000..3c1de97 --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/q_struct.h @@ -0,0 +1,701 @@ +/* + * This file contains HW queue descriptor formats, config register + * structures etc + * + * Copyright (C) 2015 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#ifndef Q_STRUCT_H +#define Q_STRUCT_H + +/* Load transaction types for reading segment bytes specified by + * NIC_SEND_GATHER_S[LD_TYPE]. + */ +enum nic_send_ld_type_e { + NIC_SEND_LD_TYPE_E_LDD = 0x0, + NIC_SEND_LD_TYPE_E_LDT = 0x1, + NIC_SEND_LD_TYPE_E_LDWB = 0x2, + NIC_SEND_LD_TYPE_E_ENUM_LAST = 0x3, +}; + +enum ether_type_algorithm { + ETYPE_ALG_NONE = 0x0, + ETYPE_ALG_SKIP = 0x1, + ETYPE_ALG_ENDPARSE = 0x2, + ETYPE_ALG_VLAN = 0x3, + ETYPE_ALG_VLAN_STRIP = 0x4, +}; + +enum layer3_type { + L3TYPE_NONE = 0x00, + L3TYPE_GRH = 0x01, + L3TYPE_IPV4 = 0x04, + L3TYPE_IPV4_OPTIONS = 0x05, + L3TYPE_IPV6 = 0x06, + L3TYPE_IPV6_OPTIONS = 0x07, + L3TYPE_ET_STOP = 0x0D, + L3TYPE_OTHER = 0x0E, +}; + +enum layer4_type { + L4TYPE_NONE = 0x00, + L4TYPE_IPSEC_ESP = 0x01, + L4TYPE_IPFRAG = 0x02, + L4TYPE_IPCOMP = 0x03, + L4TYPE_TCP = 0x04, + L4TYPE_UDP = 0x05, + L4TYPE_SCTP = 0x06, + L4TYPE_GRE = 0x07, + L4TYPE_ROCE_BTH = 0x08, + L4TYPE_OTHER = 0x0E, +}; + +/* CPI and RSSI configuration */ +enum cpi_algorithm_type { + CPI_ALG_NONE = 0x0, + CPI_ALG_VLAN = 0x1, + CPI_ALG_VLAN16 = 0x2, + CPI_ALG_DIFF = 0x3, +}; + +enum rss_algorithm_type { + RSS_ALG_NONE = 0x00, + RSS_ALG_PORT = 0x01, + RSS_ALG_IP = 0x02, + RSS_ALG_TCP_IP = 0x03, + RSS_ALG_UDP_IP = 0x04, + RSS_ALG_SCTP_IP = 0x05, + RSS_ALG_GRE_IP = 0x06, + RSS_ALG_ROCE = 0x07, +}; + +enum rss_hash_cfg { + RSS_HASH_L2ETC = 0x00, + RSS_HASH_IP = 0x01, + RSS_HASH_TCP = 0x02, + RSS_HASH_TCP_SYN_DIS = 0x03, + RSS_HASH_UDP = 0x04, + RSS_HASH_L4ETC = 0x05, + RSS_HASH_ROCE = 0x06, + RSS_L3_BIDI = 0x07, + RSS_L4_BIDI = 0x08, +}; + +/* Completion queue entry types */ +enum cqe_type { + CQE_TYPE_INVALID = 0x0, + CQE_TYPE_RX = 0x2, + CQE_TYPE_RX_SPLIT = 0x3, + CQE_TYPE_RX_TCP = 0x4, + CQE_TYPE_SEND = 0x8, + CQE_TYPE_SEND_PTP = 0x9, +}; + +enum cqe_rx_tcp_status { + CQE_RX_STATUS_VALID_TCP_CNXT = 0x00, + CQE_RX_STATUS_INVALID_TCP_CNXT = 0x0F, +}; + +enum cqe_send_status { + CQE_SEND_STATUS_GOOD = 0x00, + CQE_SEND_STATUS_DESC_FAULT = 0x01, + CQE_SEND_STATUS_HDR_CONS_ERR = 0x11, + CQE_SEND_STATUS_SUBDESC_ERR = 0x12, + CQE_SEND_STATUS_IMM_SIZE_OFLOW = 0x80, + CQE_SEND_STATUS_CRC_SEQ_ERR = 0x81, + CQE_SEND_STATUS_DATA_SEQ_ERR = 0x82, + CQE_SEND_STATUS_MEM_SEQ_ERR = 0x83, + CQE_SEND_STATUS_LOCK_VIOL = 0x84, + CQE_SEND_STATUS_LOCK_UFLOW = 0x85, + CQE_SEND_STATUS_DATA_FAULT = 0x86, + CQE_SEND_STATUS_TSTMP_CONFLICT = 0x87, + CQE_SEND_STATUS_TSTMP_TIMEOUT = 0x88, + CQE_SEND_STATUS_MEM_FAULT = 0x89, + CQE_SEND_STATUS_CSUM_OVERLAP = 0x8A, + CQE_SEND_STATUS_CSUM_OVERFLOW = 0x8B, +}; + +enum cqe_rx_tcp_end_reason { + CQE_RX_TCP_END_FIN_FLAG_DET = 0, + CQE_RX_TCP_END_INVALID_FLAG = 1, + CQE_RX_TCP_END_TIMEOUT = 2, + CQE_RX_TCP_END_OUT_OF_SEQ = 3, + CQE_RX_TCP_END_PKT_ERR = 4, + CQE_RX_TCP_END_QS_DISABLED = 0x0F, +}; + +/* Packet protocol level error enumeration */ +enum cqe_rx_err_level { + CQE_RX_ERRLVL_RE = 0x0, + CQE_RX_ERRLVL_L2 = 0x1, + CQE_RX_ERRLVL_L3 = 0x2, + CQE_RX_ERRLVL_L4 = 0x3, +}; + +/* Packet protocol level error type enumeration */ +enum cqe_rx_err_opcode { + CQE_RX_ERR_RE_NONE = 0x0, + CQE_RX_ERR_RE_PARTIAL = 0x1, + CQE_RX_ERR_RE_JABBER = 0x2, + CQE_RX_ERR_RE_FCS = 0x7, + CQE_RX_ERR_RE_TERMINATE = 0x9, + CQE_RX_ERR_RE_RX_CTL = 0xb, + CQE_RX_ERR_PREL2_ERR = 0x1f, + CQE_RX_ERR_L2_FRAGMENT = 0x20, + CQE_RX_ERR_L2_OVERRUN = 0x21, + CQE_RX_ERR_L2_PFCS = 0x22, + CQE_RX_ERR_L2_PUNY = 0x23, + CQE_RX_ERR_L2_MAL = 0x24, + CQE_RX_ERR_L2_OVERSIZE = 0x25, + CQE_RX_ERR_L2_UNDERSIZE = 0x26, + CQE_RX_ERR_L2_LENMISM = 0x27, + CQE_RX_ERR_L2_PCLP = 0x28, + CQE_RX_ERR_IP_NOT = 0x41, + CQE_RX_ERR_IP_CHK = 0x42, + CQE_RX_ERR_IP_MAL = 0x43, + CQE_RX_ERR_IP_MALD = 0x44, + CQE_RX_ERR_IP_HOP = 0x45, + CQE_RX_ERR_L3_ICRC = 0x46, + CQE_RX_ERR_L3_PCLP = 0x47, + CQE_RX_ERR_L4_MAL = 0x61, + CQE_RX_ERR_L4_CHK = 0x62, + CQE_RX_ERR_UDP_LEN = 0x63, + CQE_RX_ERR_L4_PORT = 0x64, + CQE_RX_ERR_TCP_FLAG = 0x65, + CQE_RX_ERR_TCP_OFFSET = 0x66, + CQE_RX_ERR_L4_PCLP = 0x67, + CQE_RX_ERR_RBDR_TRUNC = 0x70, +}; + +struct cqe_rx_t { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 cqe_type:4; /* W0 */ + u64 stdn_fault:1; + u64 rsvd0:1; + u64 rq_qs:7; + u64 rq_idx:3; + u64 rsvd1:12; + u64 rss_alg:4; + u64 rsvd2:4; + u64 rb_cnt:4; + u64 vlan_found:1; + u64 vlan_stripped:1; + u64 vlan2_found:1; + u64 vlan2_stripped:1; + u64 l4_type:4; + u64 l3_type:4; + u64 l2_present:1; + u64 err_level:3; + u64 err_opcode:8; + + u64 pkt_len:16; /* W1 */ + u64 l2_ptr:8; + u64 l3_ptr:8; + u64 l4_ptr:8; + u64 cq_pkt_len:8; + u64 align_pad:3; + u64 rsvd3:1; + u64 chan:12; + + u64 rss_tag:32; /* W2 */ + u64 vlan_tci:16; + u64 vlan_ptr:8; + u64 vlan2_ptr:8; + + u64 rb3_sz:16; /* W3 */ + u64 rb2_sz:16; + u64 rb1_sz:16; + u64 rb0_sz:16; + + u64 rb7_sz:16; /* W4 */ + u64 rb6_sz:16; + u64 rb5_sz:16; + u64 rb4_sz:16; + + u64 rb11_sz:16; /* W5 */ + u64 rb10_sz:16; + u64 rb9_sz:16; + u64 rb8_sz:16; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 err_opcode:8; + u64 err_level:3; + u64 l2_present:1; + u64 l3_type:4; + u64 l4_type:4; + u64 vlan2_stripped:1; + u64 vlan2_found:1; + u64 vlan_stripped:1; + u64 vlan_found:1; + u64 rb_cnt:4; + u64 rsvd2:4; + u64 rss_alg:4; + u64 rsvd1:12; + u64 rq_idx:3; + u64 rq_qs:7; + u64 rsvd0:1; + u64 stdn_fault:1; + u64 cqe_type:4; /* W0 */ + u64 chan:12; + u64 rsvd3:1; + u64 align_pad:3; + u64 cq_pkt_len:8; + u64 l4_ptr:8; + u64 l3_ptr:8; + u64 l2_ptr:8; + u64 pkt_len:16; /* W1 */ + u64 vlan2_ptr:8; + u64 vlan_ptr:8; + u64 vlan_tci:16; + u64 rss_tag:32; /* W2 */ + u64 rb0_sz:16; + u64 rb1_sz:16; + u64 rb2_sz:16; + u64 rb3_sz:16; /* W3 */ + u64 rb4_sz:16; + u64 rb5_sz:16; + u64 rb6_sz:16; + u64 rb7_sz:16; /* W4 */ + u64 rb8_sz:16; + u64 rb9_sz:16; + u64 rb10_sz:16; + u64 rb11_sz:16; /* W5 */ +#endif + u64 rb0_ptr:64; + u64 rb1_ptr:64; + u64 rb2_ptr:64; + u64 rb3_ptr:64; + u64 rb4_ptr:64; + u64 rb5_ptr:64; + u64 rb6_ptr:64; + u64 rb7_ptr:64; + u64 rb8_ptr:64; + u64 rb9_ptr:64; + u64 rb10_ptr:64; + u64 rb11_ptr:64; +}; + +struct cqe_rx_tcp_err_t { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 cqe_type:4; /* W0 */ + u64 rsvd0:60; + + u64 rsvd1:4; /* W1 */ + u64 partial_first:1; + u64 rsvd2:27; + u64 rbdr_bytes:8; + u64 rsvd3:24; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 rsvd0:60; + u64 cqe_type:4; + + u64 rsvd3:24; + u64 rbdr_bytes:8; + u64 rsvd2:27; + u64 partial_first:1; + u64 rsvd1:4; +#endif +}; + +struct cqe_rx_tcp_t { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 cqe_type:4; /* W0 */ + u64 rsvd0:52; + u64 cq_tcp_status:8; + + u64 rsvd1:32; /* W1 */ + u64 tcp_cntx_bytes:8; + u64 rsvd2:8; + u64 tcp_err_bytes:16; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 cq_tcp_status:8; + u64 rsvd0:52; + u64 cqe_type:4; /* W0 */ + + u64 tcp_err_bytes:16; + u64 rsvd2:8; + u64 tcp_cntx_bytes:8; + u64 rsvd1:32; /* W1 */ +#endif +}; + +struct cqe_send_t { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 cqe_type:4; /* W0 */ + u64 rsvd0:4; + u64 sqe_ptr:16; + u64 rsvd1:4; + u64 rsvd2:10; + u64 sq_qs:7; + u64 sq_idx:3; + u64 rsvd3:8; + u64 send_status:8; + + u64 ptp_timestamp:64; /* W1 */ +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 send_status:8; + u64 rsvd3:8; + u64 sq_idx:3; + u64 sq_qs:7; + u64 rsvd2:10; + u64 rsvd1:4; + u64 sqe_ptr:16; + u64 rsvd0:4; + u64 cqe_type:4; /* W0 */ + + u64 ptp_timestamp:64; /* W1 */ +#endif +}; + +union cq_desc_t { + u64 u[64]; + struct cqe_send_t snd_hdr; + struct cqe_rx_t rx_hdr; + struct cqe_rx_tcp_t rx_tcp_hdr; + struct cqe_rx_tcp_err_t rx_tcp_err_hdr; +}; + +struct rbdr_entry_t { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 rsvd0:15; + u64 buf_addr:42; + u64 cache_align:7; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 cache_align:7; + u64 buf_addr:42; + u64 rsvd0:15; +#endif +}; + +/* TCP reassembly context */ +struct rbe_tcp_cnxt_t { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 tcp_pkt_cnt:12; + u64 rsvd1:4; + u64 align_hdr_bytes:4; + u64 align_ptr_bytes:4; + u64 ptr_bytes:16; + u64 rsvd2:24; + u64 cqe_type:4; + u64 rsvd0:54; + u64 tcp_end_reason:2; + u64 tcp_status:4; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 tcp_status:4; + u64 tcp_end_reason:2; + u64 rsvd0:54; + u64 cqe_type:4; + u64 rsvd2:24; + u64 ptr_bytes:16; + u64 align_ptr_bytes:4; + u64 align_hdr_bytes:4; + u64 rsvd1:4; + u64 tcp_pkt_cnt:12; +#endif +}; + +/* Always Big endian */ +struct rx_hdr_t { + u64 opaque:32; + u64 rss_flow:8; + u64 skip_length:6; + u64 disable_rss:1; + u64 disable_tcp_reassembly:1; + u64 nodrop:1; + u64 dest_alg:2; + u64 rsvd0:2; + u64 dest_rq:11; +}; + +enum send_l4_csum_type { + SEND_L4_CSUM_DISABLE = 0x00, + SEND_L4_CSUM_UDP = 0x01, + SEND_L4_CSUM_TCP = 0x02, + SEND_L4_CSUM_SCTP = 0x03, +}; + +enum send_crc_alg { + SEND_CRCALG_CRC32 = 0x00, + SEND_CRCALG_CRC32C = 0x01, + SEND_CRCALG_ICRC = 0x02, +}; + +enum send_load_type { + SEND_LD_TYPE_LDD = 0x00, + SEND_LD_TYPE_LDT = 0x01, + SEND_LD_TYPE_LDWB = 0x02, +}; + +enum send_mem_alg_type { + SEND_MEMALG_SET = 0x00, + SEND_MEMALG_ADD = 0x08, + SEND_MEMALG_SUB = 0x09, + SEND_MEMALG_ADDLEN = 0x0A, + SEND_MEMALG_SUBLEN = 0x0B, +}; + +enum send_mem_dsz_type { + SEND_MEMDSZ_B64 = 0x00, + SEND_MEMDSZ_B32 = 0x01, + SEND_MEMDSZ_B8 = 0x03, +}; + +enum sq_subdesc_type { + SQ_DESC_TYPE_INVALID = 0x00, + SQ_DESC_TYPE_HEADER = 0x01, + SQ_DESC_TYPE_CRC = 0x02, + SQ_DESC_TYPE_IMMEDIATE = 0x03, + SQ_DESC_TYPE_GATHER = 0x04, + SQ_DESC_TYPE_MEMORY = 0x05, +}; + +struct sq_crc_subdesc { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 rsvd1:32; + u64 crc_ival:32; + u64 subdesc_type:4; + u64 crc_alg:2; + u64 rsvd0:10; + u64 crc_insert_pos:16; + u64 hdr_start:16; + u64 crc_len:16; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 crc_len:16; + u64 hdr_start:16; + u64 crc_insert_pos:16; + u64 rsvd0:10; + u64 crc_alg:2; + u64 subdesc_type:4; + u64 crc_ival:32; + u64 rsvd1:32; +#endif +}; + +struct sq_gather_subdesc { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 subdesc_type:4; /* W0 */ + u64 ld_type:2; + u64 rsvd0:42; + u64 size:16; + + u64 rsvd1:15; /* W1 */ + u64 addr:49; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 size:16; + u64 rsvd0:42; + u64 ld_type:2; + u64 subdesc_type:4; /* W0 */ + + u64 addr:49; + u64 rsvd1:15; /* W1 */ +#endif +}; + +/* SQ immediate subdescriptor */ +struct sq_imm_subdesc { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 subdesc_type:4; /* W0 */ + u64 rsvd0:46; + u64 len:14; + + u64 data:64; /* W1 */ +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 len:14; + u64 rsvd0:46; + u64 subdesc_type:4; /* W0 */ + + u64 data:64; /* W1 */ +#endif +}; + +struct sq_mem_subdesc { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 subdesc_type:4; /* W0 */ + u64 mem_alg:4; + u64 mem_dsz:2; + u64 wmem:1; + u64 rsvd0:21; + u64 offset:32; + + u64 rsvd1:15; /* W1 */ + u64 addr:49; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 offset:32; + u64 rsvd0:21; + u64 wmem:1; + u64 mem_dsz:2; + u64 mem_alg:4; + u64 subdesc_type:4; /* W0 */ + + u64 addr:49; + u64 rsvd1:15; /* W1 */ +#endif +}; + +struct sq_hdr_subdesc { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 subdesc_type:4; + u64 tso:1; + u64 post_cqe:1; /* Post CQE on no error also */ + u64 dont_send:1; + u64 tstmp:1; + u64 subdesc_cnt:8; + u64 csum_l4:2; + u64 csum_l3:1; + u64 rsvd0:5; + u64 l4_offset:8; + u64 l3_offset:8; + u64 rsvd1:4; + u64 tot_len:20; /* W0 */ + + u64 tso_sdc_cont:8; + u64 tso_sdc_first:8; + u64 tso_l4_offset:8; + u64 tso_flags_last:12; + u64 tso_flags_first:12; + u64 rsvd2:2; + u64 tso_max_paysize:14; /* W1 */ +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 tot_len:20; + u64 rsvd1:4; + u64 l3_offset:8; + u64 l4_offset:8; + u64 rsvd0:5; + u64 csum_l3:1; + u64 csum_l4:2; + u64 subdesc_cnt:8; + u64 tstmp:1; + u64 dont_send:1; + u64 post_cqe:1; /* Post CQE on no error also */ + u64 tso:1; + u64 subdesc_type:4; /* W0 */ + + u64 tso_max_paysize:14; + u64 rsvd2:2; + u64 tso_flags_first:12; + u64 tso_flags_last:12; + u64 tso_l4_offset:8; + u64 tso_sdc_first:8; + u64 tso_sdc_cont:8; /* W1 */ +#endif +}; + +/* Queue config register formats */ +struct rq_cfg { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 reserved_2_63:62; + u64 ena:1; + u64 tcp_ena:1; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 tcp_ena:1; + u64 ena:1; + u64 reserved_2_63:62; +#endif +}; + +struct cq_cfg { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 reserved_43_63:21; + u64 ena:1; + u64 reset:1; + u64 caching:1; + u64 reserved_35_39:5; + u64 qsize:3; + u64 reserved_25_31:7; + u64 avg_con:9; + u64 reserved_0_15:16; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 reserved_0_15:16; + u64 avg_con:9; + u64 reserved_25_31:7; + u64 qsize:3; + u64 reserved_35_39:5; + u64 caching:1; + u64 reset:1; + u64 ena:1; + u64 reserved_43_63:21; +#endif +}; + +struct sq_cfg { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 reserved_20_63:44; + u64 ena:1; + u64 reserved_18_18:1; + u64 reset:1; + u64 ldwb:1; + u64 reserved_11_15:5; + u64 qsize:3; + u64 reserved_3_7:5; + u64 tstmp_bgx_intf:3; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 tstmp_bgx_intf:3; + u64 reserved_3_7:5; + u64 qsize:3; + u64 reserved_11_15:5; + u64 ldwb:1; + u64 reset:1; + u64 reserved_18_18:1; + u64 ena:1; + u64 reserved_20_63:44; +#endif +}; + +struct rbdr_cfg { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 reserved_45_63:19; + u64 ena:1; + u64 reset:1; + u64 ldwb:1; + u64 reserved_36_41:6; + u64 qsize:4; + u64 reserved_25_31:7; + u64 avg_con:9; + u64 reserved_12_15:4; + u64 lines:12; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 lines:12; + u64 reserved_12_15:4; + u64 avg_con:9; + u64 reserved_25_31:7; + u64 qsize:4; + u64 reserved_36_41:6; + u64 ldwb:1; + u64 reset:1; + u64 ena: 1; + u64 reserved_45_63:19; +#endif +}; + +struct qs_cfg { +#if defined(__BIG_ENDIAN_BITFIELD) + u64 reserved_32_63:32; + u64 ena:1; + u64 reserved_27_30:4; + u64 sq_ins_ena:1; + u64 sq_ins_pos:6; + u64 lock_ena:1; + u64 lock_viol_cqe_ena:1; + u64 send_tstmp_ena:1; + u64 be:1; + u64 reserved_7_15:9; + u64 vnic:7; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u64 vnic:7; + u64 reserved_7_15:9; + u64 be:1; + u64 send_tstmp_ena:1; + u64 lock_viol_cqe_ena:1; + u64 lock_ena:1; + u64 sq_ins_pos:6; + u64 sq_ins_ena:1; + u64 reserved_27_30:4; + u64 ena:1; + u64 reserved_32_63:32; +#endif +}; + +#endif /* Q_STRUCT_H */ diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c new file mode 100644 index 0000000..633ec05 --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -0,0 +1,966 @@ +/* + * Copyright (C) 2015 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/phy.h> +#include <linux/of.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> + +#include "nic_reg.h" +#include "nic.h" +#include "thunder_bgx.h" + +#define DRV_NAME "thunder-BGX" +#define DRV_VERSION "1.0" + +struct lmac { + struct bgx *bgx; + int dmac; + unsigned char mac[ETH_ALEN]; + bool link_up; + int lmacid; /* ID within BGX */ + int lmacid_bd; /* ID on board */ + struct net_device netdev; + struct phy_device *phydev; + unsigned int last_duplex; + unsigned int last_link; + unsigned int last_speed; + bool is_sgmii; + struct delayed_work dwork; + struct workqueue_struct *check_link; +}; + +struct bgx { + u8 bgx_id; + u8 qlm_mode; + struct lmac lmac[MAX_LMAC_PER_BGX]; + int lmac_count; + int lmac_type; + int lane_to_sds; + int use_training; + void __iomem *reg_base; + struct pci_dev *pdev; +}; + +static struct bgx *bgx_vnic[MAX_BGX_THUNDER]; +static int lmac_count; /* Total no of LMACs in system */ + +static int bgx_xaui_check_link(struct lmac *lmac); + +/* Supported devices */ +static const struct pci_device_id bgx_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_BGX) }, + { 0, } /* end of table */ +}; + +MODULE_AUTHOR("Cavium Inc"); +MODULE_DESCRIPTION("Cavium Thunder BGX/MAC Driver"); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION(DRV_VERSION); +MODULE_DEVICE_TABLE(pci, bgx_id_table); + +/* The Cavium ThunderX network controller can *only* be found in SoCs + * containing the ThunderX ARM64 CPU implementation. All accesses to the device + * registers on this platform are implicitly strongly ordered with respect + * to memory accesses. So writeq_relaxed() and readq_relaxed() are safe to use + * with no memory barriers in this driver. The readq()/writeq() functions add + * explicit ordering operation which in this case are redundant, and only + * add overhead. + */ + +/* Register read/write APIs */ +static u64 bgx_reg_read(struct bgx *bgx, u8 lmac, u64 offset) +{ + void __iomem *addr = bgx->reg_base + ((u32)lmac << 20) + offset; + + return readq_relaxed(addr); +} + +static void bgx_reg_write(struct bgx *bgx, u8 lmac, u64 offset, u64 val) +{ + void __iomem *addr = bgx->reg_base + ((u32)lmac << 20) + offset; + + writeq_relaxed(val, addr); +} + +static void bgx_reg_modify(struct bgx *bgx, u8 lmac, u64 offset, u64 val) +{ + void __iomem *addr = bgx->reg_base + ((u32)lmac << 20) + offset; + + writeq_relaxed(val | readq_relaxed(addr), addr); +} + +static int bgx_poll_reg(struct bgx *bgx, u8 lmac, u64 reg, u64 mask, bool zero) +{ + int timeout = 100; + u64 reg_val; + + while (timeout) { + reg_val = bgx_reg_read(bgx, lmac, reg); + if (zero && !(reg_val & mask)) + return 0; + if (!zero && (reg_val & mask)) + return 0; + usleep_range(1000, 2000); + timeout--; + } + return 1; +} + +/* Return number of BGX present in HW */ +unsigned bgx_get_map(int node) +{ + int i; + unsigned map = 0; + + for (i = 0; i < MAX_BGX_PER_CN88XX; i++) { + if (bgx_vnic[(node * MAX_BGX_PER_CN88XX) + i]) + map |= (1 << i); + } + + return map; +} +EXPORT_SYMBOL(bgx_get_map); + +/* Return number of LMAC configured for this BGX */ +int bgx_get_lmac_count(int node, int bgx_idx) +{ + struct bgx *bgx; + + bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx]; + if (bgx) + return bgx->lmac_count; + + return 0; +} +EXPORT_SYMBOL(bgx_get_lmac_count); + +/* Returns the current link status of LMAC */ +void bgx_get_lmac_link_state(int node, int bgx_idx, int lmacid, void *status) +{ + struct bgx_link_status *link = (struct bgx_link_status *)status; + struct bgx *bgx; + struct lmac *lmac; + + bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx]; + if (!bgx) + return; + + lmac = &bgx->lmac[lmacid]; + link->link_up = lmac->link_up; + link->duplex = lmac->last_duplex; + link->speed = lmac->last_speed; +} +EXPORT_SYMBOL(bgx_get_lmac_link_state); + +const u8 *bgx_get_lmac_mac(int node, int bgx_idx, int lmacid) +{ + struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx]; + + if (bgx) + return bgx->lmac[lmacid].mac; + + return NULL; +} +EXPORT_SYMBOL(bgx_get_lmac_mac); + +void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac) +{ + struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx]; + + if (!bgx) + return; + + ether_addr_copy(bgx->lmac[lmacid].mac, mac); +} +EXPORT_SYMBOL(bgx_set_lmac_mac); + +static void bgx_sgmii_change_link_state(struct lmac *lmac) +{ + struct bgx *bgx = lmac->bgx; + u64 cmr_cfg; + u64 port_cfg = 0; + u64 misc_ctl = 0; + + cmr_cfg = bgx_reg_read(bgx, lmac->lmacid, BGX_CMRX_CFG); + cmr_cfg &= ~CMR_EN; + bgx_reg_write(bgx, lmac->lmacid, BGX_CMRX_CFG, cmr_cfg); + + port_cfg = bgx_reg_read(bgx, lmac->lmacid, BGX_GMP_GMI_PRTX_CFG); + misc_ctl = bgx_reg_read(bgx, lmac->lmacid, BGX_GMP_PCS_MISCX_CTL); + + if (lmac->link_up) { + misc_ctl &= ~PCS_MISC_CTL_GMX_ENO; + port_cfg &= ~GMI_PORT_CFG_DUPLEX; + port_cfg |= (lmac->last_duplex << 2); + } else { + misc_ctl |= PCS_MISC_CTL_GMX_ENO; + } + + switch (lmac->last_speed) { + case 10: + port_cfg &= ~GMI_PORT_CFG_SPEED; /* speed 0 */ + port_cfg |= GMI_PORT_CFG_SPEED_MSB; /* speed_msb 1 */ + port_cfg &= ~GMI_PORT_CFG_SLOT_TIME; /* slottime 0 */ + misc_ctl &= ~PCS_MISC_CTL_SAMP_PT_MASK; + misc_ctl |= 50; /* samp_pt */ + bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_TXX_SLOT, 64); + bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_TXX_BURST, 0); + break; + case 100: + port_cfg &= ~GMI_PORT_CFG_SPEED; /* speed 0 */ + port_cfg &= ~GMI_PORT_CFG_SPEED_MSB; /* speed_msb 0 */ + port_cfg &= ~GMI_PORT_CFG_SLOT_TIME; /* slottime 0 */ + misc_ctl &= ~PCS_MISC_CTL_SAMP_PT_MASK; + misc_ctl |= 5; /* samp_pt */ + bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_TXX_SLOT, 64); + bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_TXX_BURST, 0); + break; + case 1000: + port_cfg |= GMI_PORT_CFG_SPEED; /* speed 1 */ + port_cfg &= ~GMI_PORT_CFG_SPEED_MSB; /* speed_msb 0 */ + port_cfg |= GMI_PORT_CFG_SLOT_TIME; /* slottime 1 */ + misc_ctl &= ~PCS_MISC_CTL_SAMP_PT_MASK; + misc_ctl |= 1; /* samp_pt */ + bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_TXX_SLOT, 512); + if (lmac->last_duplex) + bgx_reg_write(bgx, lmac->lmacid, + BGX_GMP_GMI_TXX_BURST, 0); + else + bgx_reg_write(bgx, lmac->lmacid, + BGX_GMP_GMI_TXX_BURST, 8192); + break; + default: + break; + } + bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_PCS_MISCX_CTL, misc_ctl); + bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_PRTX_CFG, port_cfg); + + port_cfg = bgx_reg_read(bgx, lmac->lmacid, BGX_GMP_GMI_PRTX_CFG); + + /* renable lmac */ + cmr_cfg |= CMR_EN; + bgx_reg_write(bgx, lmac->lmacid, BGX_CMRX_CFG, cmr_cfg); +} + +static void bgx_lmac_handler(struct net_device *netdev) +{ + struct lmac *lmac = container_of(netdev, struct lmac, netdev); + struct phy_device *phydev = lmac->phydev; + int link_changed = 0; + + if (!lmac) + return; + + if (!phydev->link && lmac->last_link) + link_changed = -1; + + if (phydev->link && + (lmac->last_duplex != phydev->duplex || + lmac->last_link != phydev->link || + lmac->last_speed != phydev->speed)) { + link_changed = 1; + } + + lmac->last_link = phydev->link; + lmac->last_speed = phydev->speed; + lmac->last_duplex = phydev->duplex; + + if (!link_changed) + return; + + if (link_changed > 0) + lmac->link_up = true; + else + lmac->link_up = false; + + if (lmac->is_sgmii) + bgx_sgmii_change_link_state(lmac); + else + bgx_xaui_check_link(lmac); +} + +u64 bgx_get_rx_stats(int node, int bgx_idx, int lmac, int idx) +{ + struct bgx *bgx; + + bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx]; + if (!bgx) + return 0; + + if (idx > 8) + lmac = 0; + return bgx_reg_read(bgx, lmac, BGX_CMRX_RX_STAT0 + (idx * 8)); +} +EXPORT_SYMBOL(bgx_get_rx_stats); + +u64 bgx_get_tx_stats(int node, int bgx_idx, int lmac, int idx) +{ + struct bgx *bgx; + + bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx]; + if (!bgx) + return 0; + + return bgx_reg_read(bgx, lmac, BGX_CMRX_TX_STAT0 + (idx * 8)); +} +EXPORT_SYMBOL(bgx_get_tx_stats); + +static void bgx_flush_dmac_addrs(struct bgx *bgx, int lmac) +{ + u64 offset; + + while (bgx->lmac[lmac].dmac > 0) { + offset = ((bgx->lmac[lmac].dmac - 1) * sizeof(u64)) + + (lmac * MAX_DMAC_PER_LMAC * sizeof(u64)); + bgx_reg_write(bgx, 0, BGX_CMR_RX_DMACX_CAM + offset, 0); + bgx->lmac[lmac].dmac--; + } +} + +static int bgx_lmac_sgmii_init(struct bgx *bgx, int lmacid) +{ + u64 cfg; + + bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_THRESH, 0x30); + /* max packet size */ + bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_RXX_JABBER, MAX_FRAME_SIZE); + + /* Disable frame alignment if using preamble */ + cfg = bgx_reg_read(bgx, lmacid, BGX_GMP_GMI_TXX_APPEND); + if (cfg & 1) + bgx_reg_write(bgx, lmacid, BGX_GMP_GMI_TXX_SGMII_CTL, 0); + + /* Enable lmac */ + bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN); + + /* PCS reset */ + bgx_reg_modify(bgx, lmacid, BGX_GMP_PCS_MRX_CTL, PCS_MRX_CTL_RESET); + if (bgx_poll_reg(bgx, lmacid, BGX_GMP_PCS_MRX_CTL, + PCS_MRX_CTL_RESET, true)) { + dev_err(&bgx->pdev->dev, "BGX PCS reset not completed\n"); + return -1; + } + + /* power down, reset autoneg, autoneg enable */ + cfg = bgx_reg_read(bgx, lmacid, BGX_GMP_PCS_MRX_CTL); + cfg &= ~PCS_MRX_CTL_PWR_DN; + cfg |= (PCS_MRX_CTL_RST_AN | PCS_MRX_CTL_AN_EN); + bgx_reg_write(bgx, lmacid, BGX_GMP_PCS_MRX_CTL, cfg); + + if (bgx_poll_reg(bgx, lmacid, BGX_GMP_PCS_MRX_STATUS, + PCS_MRX_STATUS_AN_CPT, false)) { + dev_err(&bgx->pdev->dev, "BGX AN_CPT not completed\n"); + return -1; + } + + return 0; +} + +static int bgx_lmac_xaui_init(struct bgx *bgx, int lmacid, int lmac_type) +{ + u64 cfg; + + /* Reset SPU */ + bgx_reg_modify(bgx, lmacid, BGX_SPUX_CONTROL1, SPU_CTL_RESET); + if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_CONTROL1, SPU_CTL_RESET, true)) { + dev_err(&bgx->pdev->dev, "BGX SPU reset not completed\n"); + return -1; + } + + /* Disable LMAC */ + cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG); + cfg &= ~CMR_EN; + bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg); + + bgx_reg_modify(bgx, lmacid, BGX_SPUX_CONTROL1, SPU_CTL_LOW_POWER); + /* Set interleaved running disparity for RXAUI */ + if (bgx->lmac_type != BGX_MODE_RXAUI) + bgx_reg_modify(bgx, lmacid, + BGX_SPUX_MISC_CONTROL, SPU_MISC_CTL_RX_DIS); + else + bgx_reg_modify(bgx, lmacid, BGX_SPUX_MISC_CONTROL, + SPU_MISC_CTL_RX_DIS | SPU_MISC_CTL_INTLV_RDISP); + + /* clear all interrupts */ + cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_RX_INT); + bgx_reg_write(bgx, lmacid, BGX_SMUX_RX_INT, cfg); + cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_TX_INT); + bgx_reg_write(bgx, lmacid, BGX_SMUX_TX_INT, cfg); + cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_INT); + bgx_reg_write(bgx, lmacid, BGX_SPUX_INT, cfg); + + if (bgx->use_training) { + bgx_reg_write(bgx, lmacid, BGX_SPUX_BR_PMD_LP_CUP, 0x00); + bgx_reg_write(bgx, lmacid, BGX_SPUX_BR_PMD_LD_CUP, 0x00); + bgx_reg_write(bgx, lmacid, BGX_SPUX_BR_PMD_LD_REP, 0x00); + /* training enable */ + bgx_reg_modify(bgx, lmacid, + BGX_SPUX_BR_PMD_CRTL, SPU_PMD_CRTL_TRAIN_EN); + } + + /* Append FCS to each packet */ + bgx_reg_modify(bgx, lmacid, BGX_SMUX_TX_APPEND, SMU_TX_APPEND_FCS_D); + + /* Disable forward error correction */ + cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_FEC_CONTROL); + cfg &= ~SPU_FEC_CTL_FEC_EN; + bgx_reg_write(bgx, lmacid, BGX_SPUX_FEC_CONTROL, cfg); + + /* Disable autoneg */ + cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_AN_CONTROL); + cfg = cfg & ~(SPU_AN_CTL_AN_EN | SPU_AN_CTL_XNP_EN); + bgx_reg_write(bgx, lmacid, BGX_SPUX_AN_CONTROL, cfg); + + cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_AN_ADV); + if (bgx->lmac_type == BGX_MODE_10G_KR) + cfg |= (1 << 23); + else if (bgx->lmac_type == BGX_MODE_40G_KR) + cfg |= (1 << 24); + else + cfg &= ~((1 << 23) | (1 << 24)); + cfg = cfg & (~((1ULL << 25) | (1ULL << 22) | (1ULL << 12))); + bgx_reg_write(bgx, lmacid, BGX_SPUX_AN_ADV, cfg); + + cfg = bgx_reg_read(bgx, 0, BGX_SPU_DBG_CONTROL); + cfg &= ~SPU_DBG_CTL_AN_ARB_LINK_CHK_EN; + bgx_reg_write(bgx, 0, BGX_SPU_DBG_CONTROL, cfg); + + /* Enable lmac */ + bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN); + + cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_CONTROL1); + cfg &= ~SPU_CTL_LOW_POWER; + bgx_reg_write(bgx, lmacid, BGX_SPUX_CONTROL1, cfg); + + cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_TX_CTL); + cfg &= ~SMU_TX_CTL_UNI_EN; + cfg |= SMU_TX_CTL_DIC_EN; + bgx_reg_write(bgx, lmacid, BGX_SMUX_TX_CTL, cfg); + + /* take lmac_count into account */ + bgx_reg_modify(bgx, lmacid, BGX_SMUX_TX_THRESH, (0x100 - 1)); + /* max packet size */ + bgx_reg_modify(bgx, lmacid, BGX_SMUX_RX_JABBER, MAX_FRAME_SIZE); + + return 0; +} + +static int bgx_xaui_check_link(struct lmac *lmac) +{ + struct bgx *bgx = lmac->bgx; + int lmacid = lmac->lmacid; + int lmac_type = bgx->lmac_type; + u64 cfg; + + bgx_reg_modify(bgx, lmacid, BGX_SPUX_MISC_CONTROL, SPU_MISC_CTL_RX_DIS); + if (bgx->use_training) { + cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_INT); + if (!(cfg & (1ull << 13))) { + cfg = (1ull << 13) | (1ull << 14); + bgx_reg_write(bgx, lmacid, BGX_SPUX_INT, cfg); + cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_BR_PMD_CRTL); + cfg |= (1ull << 0); + bgx_reg_write(bgx, lmacid, BGX_SPUX_BR_PMD_CRTL, cfg); + return -1; + } + } + + /* wait for PCS to come out of reset */ + if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_CONTROL1, SPU_CTL_RESET, true)) { + dev_err(&bgx->pdev->dev, "BGX SPU reset not completed\n"); + return -1; + } + + if ((lmac_type == BGX_MODE_10G_KR) || (lmac_type == BGX_MODE_XFI) || + (lmac_type == BGX_MODE_40G_KR) || (lmac_type == BGX_MODE_XLAUI)) { + if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_BR_STATUS1, + SPU_BR_STATUS_BLK_LOCK, false)) { + dev_err(&bgx->pdev->dev, + "SPU_BR_STATUS_BLK_LOCK not completed\n"); + return -1; + } + } else { + if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_BX_STATUS, + SPU_BX_STATUS_RX_ALIGN, false)) { + dev_err(&bgx->pdev->dev, + "SPU_BX_STATUS_RX_ALIGN not completed\n"); + return -1; + } + } + + /* Clear rcvflt bit (latching high) and read it back */ + bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT); + if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) { + dev_err(&bgx->pdev->dev, "Receive fault, retry training\n"); + if (bgx->use_training) { + cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_INT); + if (!(cfg & (1ull << 13))) { + cfg = (1ull << 13) | (1ull << 14); + bgx_reg_write(bgx, lmacid, BGX_SPUX_INT, cfg); + cfg = bgx_reg_read(bgx, lmacid, + BGX_SPUX_BR_PMD_CRTL); + cfg |= (1ull << 0); + bgx_reg_write(bgx, lmacid, + BGX_SPUX_BR_PMD_CRTL, cfg); + return -1; + } + } + return -1; + } + + /* Wait for MAC RX to be ready */ + if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_RX_CTL, + SMU_RX_CTL_STATUS, true)) { + dev_err(&bgx->pdev->dev, "SMU RX link not okay\n"); + return -1; + } + + /* Wait for BGX RX to be idle */ + if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_RX_IDLE, false)) { + dev_err(&bgx->pdev->dev, "SMU RX not idle\n"); + return -1; + } + + /* Wait for BGX TX to be idle */ + if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_TX_IDLE, false)) { + dev_err(&bgx->pdev->dev, "SMU TX not idle\n"); + return -1; + } + + if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) { + dev_err(&bgx->pdev->dev, "Receive fault\n"); + return -1; + } + + /* Receive link is latching low. Force it high and verify it */ + bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK); + if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_STATUS1, + SPU_STATUS1_RCV_LNK, false)) { + dev_err(&bgx->pdev->dev, "SPU receive link down\n"); + return -1; + } + + cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_MISC_CONTROL); + cfg &= ~SPU_MISC_CTL_RX_DIS; + bgx_reg_write(bgx, lmacid, BGX_SPUX_MISC_CONTROL, cfg); + return 0; +} + +static void bgx_poll_for_link(struct work_struct *work) +{ + struct lmac *lmac; + u64 link; + + lmac = container_of(work, struct lmac, dwork.work); + + /* Receive link is latching low. Force it high and verify it */ + bgx_reg_modify(lmac->bgx, lmac->lmacid, + BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK); + bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1, + SPU_STATUS1_RCV_LNK, false); + + link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1); + if (link & SPU_STATUS1_RCV_LNK) { + lmac->link_up = 1; + if (lmac->bgx->lmac_type == BGX_MODE_XLAUI) + lmac->last_speed = 40000; + else + lmac->last_speed = 10000; + lmac->last_duplex = 1; + } else { + lmac->link_up = 0; + } + + if (lmac->last_link != lmac->link_up) { + lmac->last_link = lmac->link_up; + if (lmac->link_up) + bgx_xaui_check_link(lmac); + } + + queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 2); +} + +static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid) +{ + struct lmac *lmac; + u64 cfg; + + lmac = &bgx->lmac[lmacid]; + lmac->bgx = bgx; + + if (bgx->lmac_type == BGX_MODE_SGMII) { + lmac->is_sgmii = 1; + if (bgx_lmac_sgmii_init(bgx, lmacid)) + return -1; + } else { + lmac->is_sgmii = 0; + if (bgx_lmac_xaui_init(bgx, lmacid, bgx->lmac_type)) + return -1; + } + + if (lmac->is_sgmii) { + cfg = bgx_reg_read(bgx, lmacid, BGX_GMP_GMI_TXX_APPEND); + cfg |= ((1ull << 2) | (1ull << 1)); /* FCS and PAD */ + bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_APPEND, cfg); + bgx_reg_write(bgx, lmacid, BGX_GMP_GMI_TXX_MIN_PKT, 60 - 1); + } else { + cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_TX_APPEND); + cfg |= ((1ull << 2) | (1ull << 1)); /* FCS and PAD */ + bgx_reg_modify(bgx, lmacid, BGX_SMUX_TX_APPEND, cfg); + bgx_reg_write(bgx, lmacid, BGX_SMUX_TX_MIN_PKT, 60 + 4); + } + + /* Enable lmac */ + bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, + CMR_EN | CMR_PKT_RX_EN | CMR_PKT_TX_EN); + + /* Restore default cfg, incase low level firmware changed it */ + bgx_reg_write(bgx, lmacid, BGX_CMRX_RX_DMAC_CTL, 0x03); + + if ((bgx->lmac_type != BGX_MODE_XFI) && + (bgx->lmac_type != BGX_MODE_XLAUI) && + (bgx->lmac_type != BGX_MODE_40G_KR) && + (bgx->lmac_type != BGX_MODE_10G_KR)) { + if (!lmac->phydev) + return -ENODEV; + + lmac->phydev->dev_flags = 0; + + if (phy_connect_direct(&lmac->netdev, lmac->phydev, + bgx_lmac_handler, + PHY_INTERFACE_MODE_SGMII)) + return -ENODEV; + + phy_start_aneg(lmac->phydev); + } else { + lmac->check_link = alloc_workqueue("check_link", WQ_UNBOUND | + WQ_MEM_RECLAIM, 1); + if (!lmac->check_link) + return -ENOMEM; + INIT_DELAYED_WORK(&lmac->dwork, bgx_poll_for_link); + queue_delayed_work(lmac->check_link, &lmac->dwork, 0); + } + + return 0; +} + +static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid) +{ + struct lmac *lmac; + u64 cmrx_cfg; + + lmac = &bgx->lmac[lmacid]; + if (lmac->check_link) { + /* Destroy work queue */ + cancel_delayed_work(&lmac->dwork); + flush_workqueue(lmac->check_link); + destroy_workqueue(lmac->check_link); + } + + cmrx_cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG); + cmrx_cfg &= ~(1 << 15); + bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg); + bgx_flush_dmac_addrs(bgx, lmacid); + + if (lmac->phydev) + phy_disconnect(lmac->phydev); + + lmac->phydev = NULL; +} + +static void bgx_set_num_ports(struct bgx *bgx) +{ + u64 lmac_count; + + switch (bgx->qlm_mode) { + case QLM_MODE_SGMII: + bgx->lmac_count = 4; + bgx->lmac_type = BGX_MODE_SGMII; + bgx->lane_to_sds = 0; + break; + case QLM_MODE_XAUI_1X4: + bgx->lmac_count = 1; + bgx->lmac_type = BGX_MODE_XAUI; + bgx->lane_to_sds = 0xE4; + break; + case QLM_MODE_RXAUI_2X2: + bgx->lmac_count = 2; + bgx->lmac_type = BGX_MODE_RXAUI; + bgx->lane_to_sds = 0xE4; + break; + case QLM_MODE_XFI_4X1: + bgx->lmac_count = 4; + bgx->lmac_type = BGX_MODE_XFI; + bgx->lane_to_sds = 0; + break; + case QLM_MODE_XLAUI_1X4: + bgx->lmac_count = 1; + bgx->lmac_type = BGX_MODE_XLAUI; + bgx->lane_to_sds = 0xE4; + break; + case QLM_MODE_10G_KR_4X1: + bgx->lmac_count = 4; + bgx->lmac_type = BGX_MODE_10G_KR; + bgx->lane_to_sds = 0; + bgx->use_training = 1; + break; + case QLM_MODE_40G_KR4_1X4: + bgx->lmac_count = 1; + bgx->lmac_type = BGX_MODE_40G_KR; + bgx->lane_to_sds = 0xE4; + bgx->use_training = 1; + break; + default: + bgx->lmac_count = 0; + break; + } + + /* Check if low level firmware has programmed LMAC count + * based on board type, if yes consider that otherwise + * the default static values + */ + lmac_count = bgx_reg_read(bgx, 0, BGX_CMR_RX_LMACS) & 0x7; + if (lmac_count != 4) + bgx->lmac_count = lmac_count; +} + +static void bgx_init_hw(struct bgx *bgx) +{ + int i; + + bgx_set_num_ports(bgx); + + bgx_reg_modify(bgx, 0, BGX_CMR_GLOBAL_CFG, CMR_GLOBAL_CFG_FCS_STRIP); + if (bgx_reg_read(bgx, 0, BGX_CMR_BIST_STATUS)) + dev_err(&bgx->pdev->dev, "BGX%d BIST failed\n", bgx->bgx_id); + + /* Set lmac type and lane2serdes mapping */ + for (i = 0; i < bgx->lmac_count; i++) { + if (bgx->lmac_type == BGX_MODE_RXAUI) { + if (i) + bgx->lane_to_sds = 0x0e; + else + bgx->lane_to_sds = 0x04; + bgx_reg_write(bgx, i, BGX_CMRX_CFG, + (bgx->lmac_type << 8) | bgx->lane_to_sds); + continue; + } + bgx_reg_write(bgx, i, BGX_CMRX_CFG, + (bgx->lmac_type << 8) | (bgx->lane_to_sds + i)); + bgx->lmac[i].lmacid_bd = lmac_count; + lmac_count++; + } + + bgx_reg_write(bgx, 0, BGX_CMR_TX_LMACS, bgx->lmac_count); + bgx_reg_write(bgx, 0, BGX_CMR_RX_LMACS, bgx->lmac_count); + + /* Set the backpressure AND mask */ + for (i = 0; i < bgx->lmac_count; i++) + bgx_reg_modify(bgx, 0, BGX_CMR_CHAN_MSK_AND, + ((1ULL << MAX_BGX_CHANS_PER_LMAC) - 1) << + (i * MAX_BGX_CHANS_PER_LMAC)); + + /* Disable all MAC filtering */ + for (i = 0; i < RX_DMAC_COUNT; i++) + bgx_reg_write(bgx, 0, BGX_CMR_RX_DMACX_CAM + (i * 8), 0x00); + + /* Disable MAC steering (NCSI traffic) */ + for (i = 0; i < RX_TRAFFIC_STEER_RULE_COUNT; i++) + bgx_reg_write(bgx, 0, BGX_CMR_RX_STREERING + (i * 8), 0x00); +} + +static void bgx_get_qlm_mode(struct bgx *bgx) +{ + struct device *dev = &bgx->pdev->dev; + int lmac_type; + int train_en; + + /* Read LMAC0 type to figure out QLM mode + * This is configured by low level firmware + */ + lmac_type = bgx_reg_read(bgx, 0, BGX_CMRX_CFG); + lmac_type = (lmac_type >> 8) & 0x07; + + train_en = bgx_reg_read(bgx, 0, BGX_SPUX_BR_PMD_CRTL) & + SPU_PMD_CRTL_TRAIN_EN; + + switch (lmac_type) { + case BGX_MODE_SGMII: + bgx->qlm_mode = QLM_MODE_SGMII; + dev_info(dev, "BGX%d QLM mode: SGMII\n", bgx->bgx_id); + break; + case BGX_MODE_XAUI: + bgx->qlm_mode = QLM_MODE_XAUI_1X4; + dev_info(dev, "BGX%d QLM mode: XAUI\n", bgx->bgx_id); + break; + case BGX_MODE_RXAUI: + bgx->qlm_mode = QLM_MODE_RXAUI_2X2; + dev_info(dev, "BGX%d QLM mode: RXAUI\n", bgx->bgx_id); + break; + case BGX_MODE_XFI: + if (!train_en) { + bgx->qlm_mode = QLM_MODE_XFI_4X1; + dev_info(dev, "BGX%d QLM mode: XFI\n", bgx->bgx_id); + } else { + bgx->qlm_mode = QLM_MODE_10G_KR_4X1; + dev_info(dev, "BGX%d QLM mode: 10G_KR\n", bgx->bgx_id); + } + break; + case BGX_MODE_XLAUI: + if (!train_en) { + bgx->qlm_mode = QLM_MODE_XLAUI_1X4; + dev_info(dev, "BGX%d QLM mode: XLAUI\n", bgx->bgx_id); + } else { + bgx->qlm_mode = QLM_MODE_40G_KR4_1X4; + dev_info(dev, "BGX%d QLM mode: 40G_KR4\n", bgx->bgx_id); + } + break; + default: + bgx->qlm_mode = QLM_MODE_SGMII; + dev_info(dev, "BGX%d QLM default mode: SGMII\n", bgx->bgx_id); + } +} + +static void bgx_init_of(struct bgx *bgx, struct device_node *np) +{ + struct device_node *np_child; + u8 lmac = 0; + + for_each_child_of_node(np, np_child) { + struct device_node *phy_np; + const char *mac; + + phy_np = of_parse_phandle(np_child, "phy-handle", 0); + if (phy_np) + bgx->lmac[lmac].phydev = of_phy_find_device(phy_np); + + mac = of_get_mac_address(np_child); + if (mac) + ether_addr_copy(bgx->lmac[lmac].mac, mac); + + SET_NETDEV_DEV(&bgx->lmac[lmac].netdev, &bgx->pdev->dev); + bgx->lmac[lmac].lmacid = lmac; + lmac++; + if (lmac == MAX_LMAC_PER_BGX) + break; + } +} + +static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + int err; + struct device *dev = &pdev->dev; + struct bgx *bgx = NULL; + struct device_node *np; + char bgx_sel[5]; + u8 lmac; + + bgx = devm_kzalloc(dev, sizeof(*bgx), GFP_KERNEL); + if (!bgx) + return -ENOMEM; + bgx->pdev = pdev; + + pci_set_drvdata(pdev, bgx); + + err = pci_enable_device(pdev); + if (err) { + dev_err(dev, "Failed to enable PCI device\n"); + pci_set_drvdata(pdev, NULL); + return err; + } + + err = pci_request_regions(pdev, DRV_NAME); + if (err) { + dev_err(dev, "PCI request regions failed 0x%x\n", err); + goto err_disable_device; + } + + /* MAP configuration registers */ + bgx->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0); + if (!bgx->reg_base) { + dev_err(dev, "BGX: Cannot map CSR memory space, aborting\n"); + err = -ENOMEM; + goto err_release_regions; + } + bgx->bgx_id = (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24) & 1; + bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_CN88XX; + + bgx_vnic[bgx->bgx_id] = bgx; + bgx_get_qlm_mode(bgx); + + snprintf(bgx_sel, 5, "bgx%d", bgx->bgx_id); + np = of_find_node_by_name(NULL, bgx_sel); + if (np) + bgx_init_of(bgx, np); + + bgx_init_hw(bgx); + + /* Enable all LMACs */ + for (lmac = 0; lmac < bgx->lmac_count; lmac++) { + err = bgx_lmac_enable(bgx, lmac); + if (err) { + dev_err(dev, "BGX%d failed to enable lmac%d\n", + bgx->bgx_id, lmac); + goto err_enable; + } + } + + return 0; + +err_enable: + bgx_vnic[bgx->bgx_id] = NULL; +err_release_regions: + pci_release_regions(pdev); +err_disable_device: + pci_disable_device(pdev); + pci_set_drvdata(pdev, NULL); + return err; +} + +static void bgx_remove(struct pci_dev *pdev) +{ + struct bgx *bgx = pci_get_drvdata(pdev); + u8 lmac; + + /* Disable all LMACs */ + for (lmac = 0; lmac < bgx->lmac_count; lmac++) + bgx_lmac_disable(bgx, lmac); + + bgx_vnic[bgx->bgx_id] = NULL; + pci_release_regions(pdev); + pci_disable_device(pdev); + pci_set_drvdata(pdev, NULL); +} + +static struct pci_driver bgx_driver = { + .name = DRV_NAME, + .id_table = bgx_id_table, + .probe = bgx_probe, + .remove = bgx_remove, +}; + +static int __init bgx_init_module(void) +{ + pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION); + + return pci_register_driver(&bgx_driver); +} + +static void __exit bgx_cleanup_module(void) +{ + pci_unregister_driver(&bgx_driver); +} + +module_init(bgx_init_module); +module_exit(bgx_cleanup_module); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h new file mode 100644 index 0000000..ba4f53b --- /dev/null +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -0,0 +1,220 @@ +/* + * Copyright (C) 2015 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#ifndef THUNDER_BGX_H +#define THUNDER_BGX_H + +#define MAX_BGX_THUNDER 8 /* Max 4 nodes, 2 per node */ +#define MAX_BGX_PER_CN88XX 2 +#define MAX_LMAC_PER_BGX 4 +#define MAX_BGX_CHANS_PER_LMAC 16 +#define MAX_DMAC_PER_LMAC 8 +#define MAX_FRAME_SIZE 9216 + +#define MAX_DMAC_PER_LMAC_TNS_BYPASS_MODE 2 + +#define MAX_LMAC (MAX_BGX_PER_CN88XX * MAX_LMAC_PER_BGX) + +/* Registers */ +#define BGX_CMRX_CFG 0x00 +#define CMR_PKT_TX_EN BIT_ULL(13) +#define CMR_PKT_RX_EN BIT_ULL(14) +#define CMR_EN BIT_ULL(15) +#define BGX_CMR_GLOBAL_CFG 0x08 +#define CMR_GLOBAL_CFG_FCS_STRIP BIT_ULL(6) +#define BGX_CMRX_RX_ID_MAP 0x60 +#define BGX_CMRX_RX_STAT0 0x70 +#define BGX_CMRX_RX_STAT1 0x78 +#define BGX_CMRX_RX_STAT2 0x80 +#define BGX_CMRX_RX_STAT3 0x88 +#define BGX_CMRX_RX_STAT4 0x90 +#define BGX_CMRX_RX_STAT5 0x98 +#define BGX_CMRX_RX_STAT6 0xA0 +#define BGX_CMRX_RX_STAT7 0xA8 +#define BGX_CMRX_RX_STAT8 0xB0 +#define BGX_CMRX_RX_STAT9 0xB8 +#define BGX_CMRX_RX_STAT10 0xC0 +#define BGX_CMRX_RX_BP_DROP 0xC8 +#define BGX_CMRX_RX_DMAC_CTL 0x0E8 +#define BGX_CMR_RX_DMACX_CAM 0x200 +#define RX_DMACX_CAM_EN BIT_ULL(48) +#define RX_DMACX_CAM_LMACID(x) (x << 49) +#define RX_DMAC_COUNT 32 +#define BGX_CMR_RX_STREERING 0x300 +#define RX_TRAFFIC_STEER_RULE_COUNT 8 +#define BGX_CMR_CHAN_MSK_AND 0x450 +#define BGX_CMR_BIST_STATUS 0x460 +#define BGX_CMR_RX_LMACS 0x468 +#define BGX_CMRX_TX_STAT0 0x600 +#define BGX_CMRX_TX_STAT1 0x608 +#define BGX_CMRX_TX_STAT2 0x610 +#define BGX_CMRX_TX_STAT3 0x618 +#define BGX_CMRX_TX_STAT4 0x620 +#define BGX_CMRX_TX_STAT5 0x628 +#define BGX_CMRX_TX_STAT6 0x630 +#define BGX_CMRX_TX_STAT7 0x638 +#define BGX_CMRX_TX_STAT8 0x640 +#define BGX_CMRX_TX_STAT9 0x648 +#define BGX_CMRX_TX_STAT10 0x650 +#define BGX_CMRX_TX_STAT11 0x658 +#define BGX_CMRX_TX_STAT12 0x660 +#define BGX_CMRX_TX_STAT13 0x668 +#define BGX_CMRX_TX_STAT14 0x670 +#define BGX_CMRX_TX_STAT15 0x678 +#define BGX_CMRX_TX_STAT16 0x680 +#define BGX_CMRX_TX_STAT17 0x688 +#define BGX_CMR_TX_LMACS 0x1000 + +#define BGX_SPUX_CONTROL1 0x10000 +#define SPU_CTL_LOW_POWER BIT_ULL(11) +#define SPU_CTL_RESET BIT_ULL(15) +#define BGX_SPUX_STATUS1 0x10008 +#define SPU_STATUS1_RCV_LNK BIT_ULL(2) +#define BGX_SPUX_STATUS2 0x10020 +#define SPU_STATUS2_RCVFLT BIT_ULL(10) +#define BGX_SPUX_BX_STATUS 0x10028 +#define SPU_BX_STATUS_RX_ALIGN BIT_ULL(12) +#define BGX_SPUX_BR_STATUS1 0x10030 +#define SPU_BR_STATUS_BLK_LOCK BIT_ULL(0) +#define SPU_BR_STATUS_RCV_LNK BIT_ULL(12) +#define BGX_SPUX_BR_PMD_CRTL 0x10068 +#define SPU_PMD_CRTL_TRAIN_EN BIT_ULL(1) +#define BGX_SPUX_BR_PMD_LP_CUP 0x10078 +#define BGX_SPUX_BR_PMD_LD_CUP 0x10088 +#define BGX_SPUX_BR_PMD_LD_REP 0x10090 +#define BGX_SPUX_FEC_CONTROL 0x100A0 +#define SPU_FEC_CTL_FEC_EN BIT_ULL(0) +#define SPU_FEC_CTL_ERR_EN BIT_ULL(1) +#define BGX_SPUX_AN_CONTROL 0x100C8 +#define SPU_AN_CTL_AN_EN BIT_ULL(12) +#define SPU_AN_CTL_XNP_EN BIT_ULL(13) +#define BGX_SPUX_AN_ADV 0x100D8 +#define BGX_SPUX_MISC_CONTROL 0x10218 +#define SPU_MISC_CTL_INTLV_RDISP BIT_ULL(10) +#define SPU_MISC_CTL_RX_DIS BIT_ULL(12) +#define BGX_SPUX_INT 0x10220 /* +(0..3) << 20 */ +#define BGX_SPUX_INT_W1S 0x10228 +#define BGX_SPUX_INT_ENA_W1C 0x10230 +#define BGX_SPUX_INT_ENA_W1S 0x10238 +#define BGX_SPU_DBG_CONTROL 0x10300 +#define SPU_DBG_CTL_AN_ARB_LINK_CHK_EN BIT_ULL(18) +#define SPU_DBG_CTL_AN_NONCE_MCT_DIS BIT_ULL(29) + +#define BGX_SMUX_RX_INT 0x20000 +#define BGX_SMUX_RX_JABBER 0x20030 +#define BGX_SMUX_RX_CTL 0x20048 +#define SMU_RX_CTL_STATUS (3ull << 0) +#define BGX_SMUX_TX_APPEND 0x20100 +#define SMU_TX_APPEND_FCS_D BIT_ULL(2) +#define BGX_SMUX_TX_MIN_PKT 0x20118 +#define BGX_SMUX_TX_INT 0x20140 +#define BGX_SMUX_TX_CTL 0x20178 +#define SMU_TX_CTL_DIC_EN BIT_ULL(0) +#define SMU_TX_CTL_UNI_EN BIT_ULL(1) +#define SMU_TX_CTL_LNK_STATUS (3ull << 4) +#define BGX_SMUX_TX_THRESH 0x20180 +#define BGX_SMUX_CTL 0x20200 +#define SMU_CTL_RX_IDLE BIT_ULL(0) +#define SMU_CTL_TX_IDLE BIT_ULL(1) + +#define BGX_GMP_PCS_MRX_CTL 0x30000 +#define PCS_MRX_CTL_RST_AN BIT_ULL(9) +#define PCS_MRX_CTL_PWR_DN BIT_ULL(11) +#define PCS_MRX_CTL_AN_EN BIT_ULL(12) +#define PCS_MRX_CTL_RESET BIT_ULL(15) +#define BGX_GMP_PCS_MRX_STATUS 0x30008 +#define PCS_MRX_STATUS_AN_CPT BIT_ULL(5) +#define BGX_GMP_PCS_ANX_AN_RESULTS 0x30020 +#define BGX_GMP_PCS_SGM_AN_ADV 0x30068 +#define BGX_GMP_PCS_MISCX_CTL 0x30078 +#define PCS_MISC_CTL_GMX_ENO BIT_ULL(11) +#define PCS_MISC_CTL_SAMP_PT_MASK 0x7Full +#define BGX_GMP_GMI_PRTX_CFG 0x38020 +#define GMI_PORT_CFG_SPEED BIT_ULL(1) +#define GMI_PORT_CFG_DUPLEX BIT_ULL(2) +#define GMI_PORT_CFG_SLOT_TIME BIT_ULL(3) +#define GMI_PORT_CFG_SPEED_MSB BIT_ULL(8) +#define BGX_GMP_GMI_RXX_JABBER 0x38038 +#define BGX_GMP_GMI_TXX_THRESH 0x38210 +#define BGX_GMP_GMI_TXX_APPEND 0x38218 +#define BGX_GMP_GMI_TXX_SLOT 0x38220 +#define BGX_GMP_GMI_TXX_BURST 0x38228 +#define BGX_GMP_GMI_TXX_MIN_PKT 0x38240 +#define BGX_GMP_GMI_TXX_SGMII_CTL 0x38300 + +#define BGX_MSIX_VEC_0_29_ADDR 0x400000 /* +(0..29) << 4 */ +#define BGX_MSIX_VEC_0_29_CTL 0x400008 +#define BGX_MSIX_PBA_0 0x4F0000 + +/* MSI-X interrupts */ +#define BGX_MSIX_VECTORS 30 +#define BGX_LMAC_VEC_OFFSET 7 +#define BGX_MSIX_VEC_SHIFT 4 + +#define CMRX_INT 0 +#define SPUX_INT 1 +#define SMUX_RX_INT 2 +#define SMUX_TX_INT 3 +#define GMPX_PCS_INT 4 +#define GMPX_GMI_RX_INT 5 +#define GMPX_GMI_TX_INT 6 +#define CMR_MEM_INT 28 +#define SPU_MEM_INT 29 + +#define LMAC_INTR_LINK_UP BIT(0) +#define LMAC_INTR_LINK_DOWN BIT(1) + +/* RX_DMAC_CTL configuration*/ +enum MCAST_MODE { + MCAST_MODE_REJECT, + MCAST_MODE_ACCEPT, + MCAST_MODE_CAM_FILTER, + RSVD +}; + +#define BCAST_ACCEPT 1 +#define CAM_ACCEPT 1 + +void bgx_add_dmac_addr(u64 dmac, int node, int bgx_idx, int lmac); +unsigned bgx_get_map(int node); +int bgx_get_lmac_count(int node, int bgx); +const u8 *bgx_get_lmac_mac(int node, int bgx_idx, int lmacid); +void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac); +void bgx_get_lmac_link_state(int node, int bgx_idx, int lmacid, void *status); +u64 bgx_get_rx_stats(int node, int bgx_idx, int lmac, int idx); +u64 bgx_get_tx_stats(int node, int bgx_idx, int lmac, int idx); +#define BGX_RX_STATS_COUNT 11 +#define BGX_TX_STATS_COUNT 18 + +struct bgx_stats { + u64 rx_stats[BGX_RX_STATS_COUNT]; + u64 tx_stats[BGX_TX_STATS_COUNT]; +}; + +enum LMAC_TYPE { + BGX_MODE_SGMII = 0, /* 1 lane, 1.250 Gbaud */ + BGX_MODE_XAUI = 1, /* 4 lanes, 3.125 Gbaud */ + BGX_MODE_DXAUI = 1, /* 4 lanes, 6.250 Gbaud */ + BGX_MODE_RXAUI = 2, /* 2 lanes, 6.250 Gbaud */ + BGX_MODE_XFI = 3, /* 1 lane, 10.3125 Gbaud */ + BGX_MODE_XLAUI = 4, /* 4 lanes, 10.3125 Gbaud */ + BGX_MODE_10G_KR = 3,/* 1 lane, 10.3125 Gbaud */ + BGX_MODE_40G_KR = 4,/* 4 lanes, 10.3125 Gbaud */ +}; + +enum qlm_mode { + QLM_MODE_SGMII, /* SGMII, each lane independent */ + QLM_MODE_XAUI_1X4, /* 1 XAUI or DXAUI, 4 lanes */ + QLM_MODE_RXAUI_2X2, /* 2 RXAUI, 2 lanes each */ + QLM_MODE_XFI_4X1, /* 4 XFI, 1 lane each */ + QLM_MODE_XLAUI_1X4, /* 1 XLAUI, 4 lanes each */ + QLM_MODE_10G_KR_4X1, /* 4 10GBASE-KR, 1 lane each */ + QLM_MODE_40G_KR4_1X4, /* 1 40GBASE-KR4, 4 lanes each */ +}; + +#endif /* THUNDER_BGX_H */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 3c109d1..bf2b822 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -198,23 +198,45 @@ struct lb_port_stats { }; struct tp_tcp_stats { - u32 tcpOutRsts; - u64 tcpInSegs; - u64 tcpOutSegs; - u64 tcpRetransSegs; + u32 tcp_out_rsts; + u64 tcp_in_segs; + u64 tcp_out_segs; + u64 tcp_retrans_segs; +}; + +struct tp_usm_stats { + u32 frames; + u32 drops; + u64 octets; +}; + +struct tp_fcoe_stats { + u32 frames_ddp; + u32 frames_drop; + u64 octets_ddp; }; struct tp_err_stats { - u32 macInErrs[4]; - u32 hdrInErrs[4]; - u32 tcpInErrs[4]; - u32 tnlCongDrops[4]; - u32 ofldChanDrops[4]; - u32 tnlTxDrops[4]; - u32 ofldVlanDrops[4]; - u32 tcp6InErrs[4]; - u32 ofldNoNeigh; - u32 ofldCongDefer; + u32 mac_in_errs[4]; + u32 hdr_in_errs[4]; + u32 tcp_in_errs[4]; + u32 tnl_cong_drops[4]; + u32 ofld_chan_drops[4]; + u32 tnl_tx_drops[4]; + u32 ofld_vlan_drops[4]; + u32 tcp6_in_errs[4]; + u32 ofld_no_neigh; + u32 ofld_cong_defer; +}; + +struct tp_cpl_stats { + u32 req[4]; + u32 rsp[4]; +}; + +struct tp_rdma_stats { + u32 rqe_dfr_pkt; + u32 rqe_dfr_mod; }; struct sge_params { @@ -224,7 +246,6 @@ struct sge_params { }; struct tp_params { - unsigned int ntxchan; /* # of Tx channels */ unsigned int tre; /* log2 of core clocks per TP tick */ unsigned int la_mask; /* what events are recorded by TP LA */ unsigned short tx_modq_map; /* TX modulation scheduler queue to */ @@ -273,6 +294,7 @@ struct pci_params { #define CHELSIO_T4 0x4 #define CHELSIO_T5 0x5 +#define CHELSIO_T6 0x6 enum chip_type { T4_A1 = CHELSIO_CHIP_CODE(CHELSIO_T4, 1), @@ -284,6 +306,10 @@ enum chip_type { T5_A1 = CHELSIO_CHIP_CODE(CHELSIO_T5, 1), T5_FIRST_REV = T5_A0, T5_LAST_REV = T5_A1, + + T6_A0 = CHELSIO_CHIP_CODE(CHELSIO_T6, 0), + T6_FIRST_REV = T6_A0, + T6_LAST_REV = T6_A0, }; struct devlog_params { @@ -292,6 +318,15 @@ struct devlog_params { u32 size; /* size of log */ }; +/* Stores chip specific parameters */ +struct arch_specific_params { + u8 nchan; + u16 mps_rplc_size; + u16 vfcount; + u32 sge_fl_db; + u16 mps_tcam_size; +}; + struct adapter_params { struct sge_params sge; struct tp_params tp; @@ -317,6 +352,7 @@ struct adapter_params { unsigned char nports; /* # of ethernet ports */ unsigned char portvec; enum chip_type chip; /* chip code */ + struct arch_specific_params arch; /* chip specific params */ unsigned char offload; unsigned char bypass; @@ -432,6 +468,7 @@ struct port_info { u8 rss_mode; struct link_config link_cfg; u16 *rss; + struct port_stats stats_base; #ifdef CONFIG_CHELSIO_T4_DCB struct port_dcb_info dcb; /* Data Center Bridging support */ #endif @@ -650,6 +687,7 @@ struct sge { struct sge_rspq **ingr_map; /* qid->queue ingress queue map */ unsigned long *starving_fl; unsigned long *txq_maperr; + unsigned long *blocked_fl; struct timer_list rx_timer; /* refills starving FLs */ struct timer_list tx_timer; /* checks Tx queues */ }; @@ -671,6 +709,12 @@ struct l2t_data; #endif +struct doorbell_stats { + u32 db_drop; + u32 db_empty; + u32 db_full; +}; + struct adapter { void __iomem *regs; void __iomem *bar2; @@ -678,7 +722,7 @@ struct adapter { struct pci_dev *pdev; struct device *pdev_dev; unsigned int mbox; - unsigned int fn; + unsigned int pf; unsigned int flags; enum chip_type chip; @@ -688,13 +732,12 @@ struct adapter { struct cxgb4_virt_res vres; unsigned int swintr; - unsigned int wol; - struct { unsigned short vec; char desc[IFNAMSIZ + 10]; } msix_info[MAX_INGQ + 1]; + struct doorbell_stats db_stats; struct sge sge; struct net_device *port[MAX_NPORTS]; @@ -849,6 +892,16 @@ enum { VLAN_REWRITE }; +static inline int is_offload(const struct adapter *adap) +{ + return adap->params.offload; +} + +static inline int is_t6(enum chip_type chip) +{ + return CHELSIO_CHIP_VERSION(chip) == CHELSIO_T6; +} + static inline int is_t5(enum chip_type chip) { return CHELSIO_CHIP_VERSION(chip) == CHELSIO_T5; @@ -1220,7 +1273,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info, int t4_prep_adapter(struct adapter *adapter); enum t4_bar2_qtype { T4_BAR2_QTYPE_EGRESS, T4_BAR2_QTYPE_INGRESS }; -int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter, +int t4_bar2_sge_qregs(struct adapter *adapter, unsigned int qid, enum t4_bar2_qtype qtype, u64 *pbar2_qoffset, @@ -1267,13 +1320,23 @@ int t4_cim_read_la(struct adapter *adap, u32 *la_buf, unsigned int *wrptr); void t4_read_cimq_cfg(struct adapter *adap, u16 *base, u16 *size, u16 *thres); const char *t4_get_port_type_description(enum fw_port_type port_type); void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p); +void t4_get_port_stats_offset(struct adapter *adap, int idx, + struct port_stats *stats, + struct port_stats *offset); +void t4_get_lb_stats(struct adapter *adap, int idx, struct lb_port_stats *p); void t4_read_mtu_tbl(struct adapter *adap, u16 *mtus, u8 *mtu_log); void t4_read_cong_tbl(struct adapter *adap, u16 incr[NMTUS][NCCTRL_WIN]); void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr, unsigned int mask, unsigned int val); void t4_tp_read_la(struct adapter *adap, u64 *la_buf, unsigned int *wrptr); +void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st); +void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st); +void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st); +void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st); void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, struct tp_tcp_stats *v6); +void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx, + struct tp_fcoe_stats *st); void t4_load_mtus(struct adapter *adap, const unsigned short *mtus, const unsigned short *alpha, const unsigned short *beta); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 371f75e..3719807 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -1084,41 +1084,89 @@ static inline void tcamxy2valmask(u64 x, u64 y, u8 *addr, u64 *mask) static int mps_tcam_show(struct seq_file *seq, void *v) { - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Idx Ethernet address Mask Vld Ports PF" - " VF Replication " - "P0 P1 P2 P3 ML\n"); - else { + struct adapter *adap = seq->private; + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip); + + if (v == SEQ_START_TOKEN) { + if (adap->params.arch.mps_rplc_size > 128) + seq_puts(seq, "Idx Ethernet address Mask " + "Vld Ports PF VF " + "Replication " + " P0 P1 P2 P3 ML\n"); + else + seq_puts(seq, "Idx Ethernet address Mask " + "Vld Ports PF VF Replication" + " P0 P1 P2 P3 ML\n"); + } else { u64 mask; u8 addr[ETH_ALEN]; - struct adapter *adap = seq->private; + bool replicate; unsigned int idx = (uintptr_t)v - 2; - u64 tcamy = t4_read_reg64(adap, MPS_CLS_TCAM_Y_L(idx)); - u64 tcamx = t4_read_reg64(adap, MPS_CLS_TCAM_X_L(idx)); - u32 cls_lo = t4_read_reg(adap, MPS_CLS_SRAM_L(idx)); - u32 cls_hi = t4_read_reg(adap, MPS_CLS_SRAM_H(idx)); - u32 rplc[4] = {0, 0, 0, 0}; + u64 tcamy, tcamx, val; + u32 cls_lo, cls_hi, ctl; + u32 rplc[8] = {0}; + + if (chip_ver > CHELSIO_T5) { + /* CtlCmdType - 0: Read, 1: Write + * CtlTcamSel - 0: TCAM0, 1: TCAM1 + * CtlXYBitSel- 0: Y bit, 1: X bit + */ + + /* Read tcamy */ + ctl = CTLCMDTYPE_V(0) | CTLXYBITSEL_V(0); + if (idx < 256) + ctl |= CTLTCAMINDEX_V(idx) | CTLTCAMSEL_V(0); + else + ctl |= CTLTCAMINDEX_V(idx - 256) | + CTLTCAMSEL_V(1); + t4_write_reg(adap, MPS_CLS_TCAM_DATA2_CTL_A, ctl); + val = t4_read_reg(adap, MPS_CLS_TCAM_DATA1_A); + tcamy = DMACH_G(val) << 32; + tcamy |= t4_read_reg(adap, MPS_CLS_TCAM_DATA0_A); + + /* Read tcamx. Change the control param */ + ctl |= CTLXYBITSEL_V(1); + t4_write_reg(adap, MPS_CLS_TCAM_DATA2_CTL_A, ctl); + val = t4_read_reg(adap, MPS_CLS_TCAM_DATA1_A); + tcamx = DMACH_G(val) << 32; + tcamx |= t4_read_reg(adap, MPS_CLS_TCAM_DATA0_A); + } else { + tcamy = t4_read_reg64(adap, MPS_CLS_TCAM_Y_L(idx)); + tcamx = t4_read_reg64(adap, MPS_CLS_TCAM_X_L(idx)); + } + + cls_lo = t4_read_reg(adap, MPS_CLS_SRAM_L(idx)); + cls_hi = t4_read_reg(adap, MPS_CLS_SRAM_H(idx)); if (tcamx & tcamy) { seq_printf(seq, "%3u -\n", idx); goto out; } - if (cls_lo & REPLICATE_F) { + rplc[0] = rplc[1] = rplc[2] = rplc[3] = 0; + if (chip_ver > CHELSIO_T5) + replicate = (cls_lo & T6_REPLICATE_F); + else + replicate = (cls_lo & REPLICATE_F); + + if (replicate) { struct fw_ldst_cmd ldst_cmd; int ret; + struct fw_ldst_mps_rplc mps_rplc; + u32 ldst_addrspc; memset(&ldst_cmd, 0, sizeof(ldst_cmd)); + ldst_addrspc = + FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_MPS); ldst_cmd.op_to_addrspace = htonl(FW_CMD_OP_V(FW_LDST_CMD) | FW_CMD_REQUEST_F | FW_CMD_READ_F | - FW_LDST_CMD_ADDRSPACE_V( - FW_LDST_ADDRSPC_MPS)); + ldst_addrspc); ldst_cmd.cycles_to_len16 = htonl(FW_LEN16(ldst_cmd)); - ldst_cmd.u.mps.fid_ctl = + ldst_cmd.u.mps.rplc.fid_idx = htons(FW_LDST_CMD_FID_V(FW_LDST_MPS_RPLC) | - FW_LDST_CMD_CTL_V(idx)); + FW_LDST_CMD_IDX_V(idx)); ret = t4_wr_mbox(adap, adap->mbox, &ldst_cmd, sizeof(ldst_cmd), &ldst_cmd); if (ret) @@ -1126,30 +1174,69 @@ static int mps_tcam_show(struct seq_file *seq, void *v) "replication map for idx %d: %d\n", idx, -ret); else { - rplc[0] = ntohl(ldst_cmd.u.mps.rplc31_0); - rplc[1] = ntohl(ldst_cmd.u.mps.rplc63_32); - rplc[2] = ntohl(ldst_cmd.u.mps.rplc95_64); - rplc[3] = ntohl(ldst_cmd.u.mps.rplc127_96); + mps_rplc = ldst_cmd.u.mps.rplc; + rplc[0] = ntohl(mps_rplc.rplc31_0); + rplc[1] = ntohl(mps_rplc.rplc63_32); + rplc[2] = ntohl(mps_rplc.rplc95_64); + rplc[3] = ntohl(mps_rplc.rplc127_96); + if (adap->params.arch.mps_rplc_size > 128) { + rplc[4] = ntohl(mps_rplc.rplc159_128); + rplc[5] = ntohl(mps_rplc.rplc191_160); + rplc[6] = ntohl(mps_rplc.rplc223_192); + rplc[7] = ntohl(mps_rplc.rplc255_224); + } } } tcamxy2valmask(tcamx, tcamy, addr, &mask); - seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x %012llx" - "%3c %#x%4u%4d", - idx, addr[0], addr[1], addr[2], addr[3], addr[4], - addr[5], (unsigned long long)mask, - (cls_lo & SRAM_VLD_F) ? 'Y' : 'N', PORTMAP_G(cls_hi), - PF_G(cls_lo), - (cls_lo & VF_VALID_F) ? VF_G(cls_lo) : -1); - if (cls_lo & REPLICATE_F) - seq_printf(seq, " %08x %08x %08x %08x", - rplc[3], rplc[2], rplc[1], rplc[0]); + if (chip_ver > CHELSIO_T5) + seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x " + "%012llx%3c %#x%4u%4d", + idx, addr[0], addr[1], addr[2], addr[3], + addr[4], addr[5], (unsigned long long)mask, + (cls_lo & T6_SRAM_VLD_F) ? 'Y' : 'N', + PORTMAP_G(cls_hi), + T6_PF_G(cls_lo), + (cls_lo & T6_VF_VALID_F) ? + T6_VF_G(cls_lo) : -1); else - seq_printf(seq, "%36c", ' '); - seq_printf(seq, "%4u%3u%3u%3u %#x\n", - SRAM_PRIO0_G(cls_lo), SRAM_PRIO1_G(cls_lo), - SRAM_PRIO2_G(cls_lo), SRAM_PRIO3_G(cls_lo), - (cls_lo >> MULTILISTEN0_S) & 0xf); + seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x " + "%012llx%3c %#x%4u%4d", + idx, addr[0], addr[1], addr[2], addr[3], + addr[4], addr[5], (unsigned long long)mask, + (cls_lo & SRAM_VLD_F) ? 'Y' : 'N', + PORTMAP_G(cls_hi), + PF_G(cls_lo), + (cls_lo & VF_VALID_F) ? VF_G(cls_lo) : -1); + + if (replicate) { + if (adap->params.arch.mps_rplc_size > 128) + seq_printf(seq, " %08x %08x %08x %08x " + "%08x %08x %08x %08x", + rplc[7], rplc[6], rplc[5], rplc[4], + rplc[3], rplc[2], rplc[1], rplc[0]); + else + seq_printf(seq, " %08x %08x %08x %08x", + rplc[3], rplc[2], rplc[1], rplc[0]); + } else { + if (adap->params.arch.mps_rplc_size > 128) + seq_printf(seq, "%72c", ' '); + else + seq_printf(seq, "%36c", ' '); + } + + if (chip_ver > CHELSIO_T5) + seq_printf(seq, "%4u%3u%3u%3u %#x\n", + T6_SRAM_PRIO0_G(cls_lo), + T6_SRAM_PRIO1_G(cls_lo), + T6_SRAM_PRIO2_G(cls_lo), + T6_SRAM_PRIO3_G(cls_lo), + (cls_lo >> T6_MULTILISTEN0_S) & 0xf); + else + seq_printf(seq, "%4u%3u%3u%3u %#x\n", + SRAM_PRIO0_G(cls_lo), SRAM_PRIO1_G(cls_lo), + SRAM_PRIO2_G(cls_lo), SRAM_PRIO3_G(cls_lo), + (cls_lo >> MULTILISTEN0_S) & 0xf); } out: return 0; } @@ -1222,7 +1309,7 @@ static int sensors_show(struct seq_file *seq, void *v) param[1] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DIAG) | FW_PARAMS_PARAM_Y_V(FW_PARAM_DEV_DIAG_VDD)); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, param, val); if (ret < 0 || val[0] == 0) @@ -1416,6 +1503,9 @@ static int rss_config_show(struct seq_file *seq, void *v) seq_printf(seq, " HashDelay: %3d\n", HASHDELAY_G(rssconf)); if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) seq_printf(seq, " VfWrAddr: %3d\n", VFWRADDR_G(rssconf)); + else + seq_printf(seq, " VfWrAddr: %3d\n", + T6_VFWRADDR_G(rssconf)); seq_printf(seq, " KeyMode: %s\n", keymode[KEYMODE_G(rssconf)]); seq_printf(seq, " VfWrEn: %3s\n", yesno(rssconf & VFWREN_F)); seq_printf(seq, " KeyWrEn: %3s\n", yesno(rssconf & KEYWREN_F)); @@ -1634,14 +1724,14 @@ static int rss_vf_config_open(struct inode *inode, struct file *file) struct adapter *adapter = inode->i_private; struct seq_tab *p; struct rss_vf_conf *vfconf; - int vf; + int vf, vfcount = adapter->params.arch.vfcount; - p = seq_open_tab(file, 128, sizeof(*vfconf), 1, rss_vf_config_show); + p = seq_open_tab(file, vfcount, sizeof(*vfconf), 1, rss_vf_config_show); if (!p) return -ENOMEM; vfconf = (struct rss_vf_conf *)p->data; - for (vf = 0; vf < 128; vf++) { + for (vf = 0; vf < vfcount; vf++) { t4_read_rss_vf_config(adapter, vf, &vfconf[vf].rss_vf_vfl, &vfconf[vf].rss_vf_vfh); } @@ -1959,6 +2049,61 @@ static void add_debugfs_mem(struct adapter *adap, const char *name, size_mb << 20); } +static int blocked_fl_open(struct inode *inode, struct file *file) +{ + file->private_data = inode->i_private; + return 0; +} + +static ssize_t blocked_fl_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + int len; + const struct adapter *adap = filp->private_data; + char *buf; + ssize_t size = (adap->sge.egr_sz + 3) / 4 + + adap->sge.egr_sz / 32 + 2; /* includes ,/\n/\0 */ + + buf = kzalloc(size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + len = snprintf(buf, size - 1, "%*pb\n", + adap->sge.egr_sz, adap->sge.blocked_fl); + len += sprintf(buf + len, "\n"); + size = simple_read_from_buffer(ubuf, count, ppos, buf, len); + t4_free_mem(buf); + return size; +} + +static ssize_t blocked_fl_write(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + int err; + unsigned long *t; + struct adapter *adap = filp->private_data; + + t = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz), sizeof(long), GFP_KERNEL); + if (!t) + return -ENOMEM; + + err = bitmap_parse_user(ubuf, count, t, adap->sge.egr_sz); + if (err) + return err; + + bitmap_copy(adap->sge.blocked_fl, t, adap->sge.egr_sz); + t4_free_mem(t); + return count; +} + +static const struct file_operations blocked_fl_fops = { + .owner = THIS_MODULE, + .open = blocked_fl_open, + .read = blocked_fl_read, + .write = blocked_fl_write, + .llseek = generic_file_llseek, +}; + /* Add an array of Debug FS files. */ void add_debugfs_files(struct adapter *adap, @@ -1978,7 +2123,7 @@ void add_debugfs_files(struct adapter *adap, int t4_setup_debugfs(struct adapter *adap) { int i; - u32 size; + u32 size = 0; struct dentry *de; static struct t4_debugfs_entry t4_debugfs_files[] = { @@ -2022,6 +2167,7 @@ int t4_setup_debugfs(struct adapter *adap) #if IS_ENABLED(CONFIG_IPV6) { "clip_tbl", &clip_tbl_debugfs_fops, S_IRUSR, 0 }, #endif + { "blocked_fl", &blocked_fl_fops, S_IRUSR | S_IWUSR, 0 }, }; /* Debug FS nodes common to all T5 and later adapters. @@ -2048,12 +2194,7 @@ int t4_setup_debugfs(struct adapter *adap) size = t4_read_reg(adap, MA_EDRAM1_BAR_A); add_debugfs_mem(adap, "edc1", MEM_EDC1, EDRAM1_SIZE_G(size)); } - if (is_t4(adap->params.chip)) { - size = t4_read_reg(adap, MA_EXT_MEMORY_BAR_A); - if (i & EXT_MEM_ENABLE_F) - add_debugfs_mem(adap, "mc", MEM_MC, - EXT_MEM_SIZE_G(size)); - } else { + if (is_t5(adap->params.chip)) { if (i & EXT_MEM0_ENABLE_F) { size = t4_read_reg(adap, MA_EXT_MEMORY0_BAR_A); add_debugfs_mem(adap, "mc0", MEM_MC0, @@ -2064,6 +2205,11 @@ int t4_setup_debugfs(struct adapter *adap) add_debugfs_mem(adap, "mc1", MEM_MC1, EXT_MEM1_SIZE_G(size)); } + } else { + if (i & EXT_MEM_ENABLE_F) + size = t4_read_reg(adap, MA_EXT_MEMORY_BAR_A); + add_debugfs_mem(adap, "mc", MEM_MC, + EXT_MEM_SIZE_G(size)); } de = debugfs_create_file_size("flash", S_IRUSR, adap->debugfs_root, adap, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 401272a..0194c91 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -108,15 +108,82 @@ static const char stats_strings[][ETH_GSTRING_LEN] = { "VLANinsertions ", "GROpackets ", "GROmerged ", - "WriteCoalSuccess ", - "WriteCoalFail ", +}; + +static char adapter_stats_strings[][ETH_GSTRING_LEN] = { + "db_drop ", + "db_full ", + "db_empty ", + "tcp_ipv4_out_rsts ", + "tcp_ipv4_in_segs ", + "tcp_ipv4_out_segs ", + "tcp_ipv4_retrans_segs ", + "tcp_ipv6_out_rsts ", + "tcp_ipv6_in_segs ", + "tcp_ipv6_out_segs ", + "tcp_ipv6_retrans_segs ", + "usm_ddp_frames ", + "usm_ddp_octets ", + "usm_ddp_drops ", + "rdma_no_rqe_mod_defer ", + "rdma_no_rqe_pkt_defer ", + "tp_err_ofld_no_neigh ", + "tp_err_ofld_cong_defer ", + "write_coal_success ", + "write_coal_fail ", +}; + +static char channel_stats_strings[][ETH_GSTRING_LEN] = { + "--------Channel--------- ", + "tp_cpl_requests ", + "tp_cpl_responses ", + "tp_mac_in_errs ", + "tp_hdr_in_errs ", + "tp_tcp_in_errs ", + "tp_tcp6_in_errs ", + "tp_tnl_cong_drops ", + "tp_tnl_tx_drops ", + "tp_ofld_vlan_drops ", + "tp_ofld_chan_drops ", + "fcoe_octets_ddp ", + "fcoe_frames_ddp ", + "fcoe_frames_drop ", +}; + +static char loopback_stats_strings[][ETH_GSTRING_LEN] = { + "-------Loopback----------- ", + "octets_ok ", + "frames_ok ", + "bcast_frames ", + "mcast_frames ", + "ucast_frames ", + "error_frames ", + "frames_64 ", + "frames_65_to_127 ", + "frames_128_to_255 ", + "frames_256_to_511 ", + "frames_512_to_1023 ", + "frames_1024_to_1518 ", + "frames_1519_to_max ", + "frames_dropped ", + "bg0_frames_dropped ", + "bg1_frames_dropped ", + "bg2_frames_dropped ", + "bg3_frames_dropped ", + "bg0_frames_trunc ", + "bg1_frames_trunc ", + "bg2_frames_trunc ", + "bg3_frames_trunc ", }; static int get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: - return ARRAY_SIZE(stats_strings); + return ARRAY_SIZE(stats_strings) + + ARRAY_SIZE(adapter_stats_strings) + + ARRAY_SIZE(channel_stats_strings) + + ARRAY_SIZE(loopback_stats_strings); default: return -EOPNOTSUPP; } @@ -168,8 +235,18 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) static void get_strings(struct net_device *dev, u32 stringset, u8 *data) { - if (stringset == ETH_SS_STATS) + if (stringset == ETH_SS_STATS) { memcpy(data, stats_strings, sizeof(stats_strings)); + data += sizeof(stats_strings); + memcpy(data, adapter_stats_strings, + sizeof(adapter_stats_strings)); + data += sizeof(adapter_stats_strings); + memcpy(data, channel_stats_strings, + sizeof(channel_stats_strings)); + data += sizeof(channel_stats_strings); + memcpy(data, loopback_stats_strings, + sizeof(loopback_stats_strings)); + } } /* port stats maintained per queue of the port. They should be in the same @@ -185,6 +262,45 @@ struct queue_port_stats { u64 gro_merged; }; +struct adapter_stats { + u64 db_drop; + u64 db_full; + u64 db_empty; + u64 tcp_v4_out_rsts; + u64 tcp_v4_in_segs; + u64 tcp_v4_out_segs; + u64 tcp_v4_retrans_segs; + u64 tcp_v6_out_rsts; + u64 tcp_v6_in_segs; + u64 tcp_v6_out_segs; + u64 tcp_v6_retrans_segs; + u64 frames; + u64 octets; + u64 drops; + u64 rqe_dfr_mod; + u64 rqe_dfr_pkt; + u64 ofld_no_neigh; + u64 ofld_cong_defer; + u64 wc_success; + u64 wc_fail; +}; + +struct channel_stats { + u64 cpl_req; + u64 cpl_rsp; + u64 mac_in_errs; + u64 hdr_in_errs; + u64 tcp_in_errs; + u64 tcp6_in_errs; + u64 tnl_cong_drops; + u64 tnl_tx_drops; + u64 ofld_vlan_drops; + u64 ofld_chan_drops; + u64 octets_ddp; + u64 frames_ddp; + u64 frames_drop; +}; + static void collect_sge_port_stats(const struct adapter *adap, const struct port_info *p, struct queue_port_stats *s) @@ -205,30 +321,121 @@ static void collect_sge_port_stats(const struct adapter *adap, } } +static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s) +{ + struct tp_tcp_stats v4, v6; + struct tp_rdma_stats rdma_stats; + struct tp_err_stats err_stats; + struct tp_usm_stats usm_stats; + u64 val1, val2; + + memset(s, 0, sizeof(*s)); + + spin_lock(&adap->stats_lock); + t4_tp_get_tcp_stats(adap, &v4, &v6); + t4_tp_get_rdma_stats(adap, &rdma_stats); + t4_get_usm_stats(adap, &usm_stats); + t4_tp_get_err_stats(adap, &err_stats); + spin_unlock(&adap->stats_lock); + + s->db_drop = adap->db_stats.db_drop; + s->db_full = adap->db_stats.db_full; + s->db_empty = adap->db_stats.db_empty; + + s->tcp_v4_out_rsts = v4.tcp_out_rsts; + s->tcp_v4_in_segs = v4.tcp_in_segs; + s->tcp_v4_out_segs = v4.tcp_out_segs; + s->tcp_v4_retrans_segs = v4.tcp_retrans_segs; + s->tcp_v6_out_rsts = v6.tcp_out_rsts; + s->tcp_v6_in_segs = v6.tcp_in_segs; + s->tcp_v6_out_segs = v6.tcp_out_segs; + s->tcp_v6_retrans_segs = v6.tcp_retrans_segs; + + if (is_offload(adap)) { + s->frames = usm_stats.frames; + s->octets = usm_stats.octets; + s->drops = usm_stats.drops; + s->rqe_dfr_mod = rdma_stats.rqe_dfr_mod; + s->rqe_dfr_pkt = rdma_stats.rqe_dfr_pkt; + } + + s->ofld_no_neigh = err_stats.ofld_no_neigh; + s->ofld_cong_defer = err_stats.ofld_cong_defer; + + if (!is_t4(adap->params.chip)) { + int v; + + v = t4_read_reg(adap, SGE_STAT_CFG_A); + if (STATSOURCE_T5_G(v) == 7) { + val2 = t4_read_reg(adap, SGE_STAT_MATCH_A); + val1 = t4_read_reg(adap, SGE_STAT_TOTAL_A); + s->wc_success = val1 - val2; + s->wc_fail = val2; + } + } +} + +static void collect_channel_stats(struct adapter *adap, struct channel_stats *s, + u8 i) +{ + struct tp_cpl_stats cpl_stats; + struct tp_err_stats err_stats; + struct tp_fcoe_stats fcoe_stats; + + memset(s, 0, sizeof(*s)); + + spin_lock(&adap->stats_lock); + t4_tp_get_cpl_stats(adap, &cpl_stats); + t4_tp_get_err_stats(adap, &err_stats); + t4_get_fcoe_stats(adap, i, &fcoe_stats); + spin_unlock(&adap->stats_lock); + + s->cpl_req = cpl_stats.req[i]; + s->cpl_rsp = cpl_stats.rsp[i]; + s->mac_in_errs = err_stats.mac_in_errs[i]; + s->hdr_in_errs = err_stats.hdr_in_errs[i]; + s->tcp_in_errs = err_stats.tcp_in_errs[i]; + s->tcp6_in_errs = err_stats.tcp6_in_errs[i]; + s->tnl_cong_drops = err_stats.tnl_cong_drops[i]; + s->tnl_tx_drops = err_stats.tnl_tx_drops[i]; + s->ofld_vlan_drops = err_stats.ofld_vlan_drops[i]; + s->ofld_chan_drops = err_stats.ofld_chan_drops[i]; + s->octets_ddp = fcoe_stats.octets_ddp; + s->frames_ddp = fcoe_stats.frames_ddp; + s->frames_drop = fcoe_stats.frames_drop; +} + static void get_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; - u32 val1, val2; + struct lb_port_stats s; + int i; + u64 *p0; - t4_get_port_stats(adapter, pi->tx_chan, (struct port_stats *)data); + t4_get_port_stats_offset(adapter, pi->tx_chan, + (struct port_stats *)data, + &pi->stats_base); data += sizeof(struct port_stats) / sizeof(u64); collect_sge_port_stats(adapter, pi, (struct queue_port_stats *)data); data += sizeof(struct queue_port_stats) / sizeof(u64); - if (!is_t4(adapter->params.chip)) { - t4_write_reg(adapter, SGE_STAT_CFG_A, STATSOURCE_T5_V(7)); - val1 = t4_read_reg(adapter, SGE_STAT_TOTAL_A); - val2 = t4_read_reg(adapter, SGE_STAT_MATCH_A); - *data = val1 - val2; - data++; - *data = val2; - data++; - } else { - memset(data, 0, 2 * sizeof(u64)); - *data += 2; - } + collect_adapter_stats(adapter, (struct adapter_stats *)data); + data += sizeof(struct adapter_stats) / sizeof(u64); + + *data++ = (u64)pi->port_id; + collect_channel_stats(adapter, (struct channel_stats *)data, + pi->port_id); + data += sizeof(struct channel_stats) / sizeof(u64); + + *data++ = (u64)pi->port_id; + memset(&s, 0, sizeof(s)); + t4_get_lb_stats(adapter, pi->port_id, &s); + + p0 = &s.octets; + for (i = 0; i < ARRAY_SIZE(loopback_stats_strings) - 1; i++) + *data++ = (unsigned long long)*p0++; } static void get_regs(struct net_device *dev, struct ethtool_regs *regs, @@ -250,7 +457,7 @@ static int restart_autoneg(struct net_device *dev) return -EAGAIN; if (p->link_cfg.autoneg != AUTONEG_ENABLE) return -EINVAL; - t4_restart_aneg(p->adapter, p->adapter->fn, p->tx_chan); + t4_restart_aneg(p->adapter, p->adapter->pf, p->tx_chan); return 0; } @@ -267,7 +474,7 @@ static int identify_port(struct net_device *dev, else return -EINVAL; - return t4_identify_port(adap, adap->fn, netdev2pinfo(dev)->viid, val); + return t4_identify_port(adap, adap->pf, netdev2pinfo(dev)->viid, val); } static unsigned int from_fw_linkcaps(enum fw_port_type type, unsigned int caps) @@ -439,7 +646,7 @@ static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd) lc->autoneg = cmd->autoneg; if (netif_running(dev)) - return t4_link_start(p->adapter, p->adapter->fn, p->tx_chan, + return t4_link_start(p->adapter, p->adapter->pf, p->tx_chan, lc); return 0; } @@ -472,7 +679,7 @@ static int set_pauseparam(struct net_device *dev, if (epause->tx_pause) lc->requested_fc |= PAUSE_TX; if (netif_running(dev)) - return t4_link_start(p->adapter, p->adapter->fn, p->tx_chan, + return t4_link_start(p->adapter, p->adapter->pf, p->tx_chan, lc); return 0; } @@ -617,7 +824,7 @@ static int eeprom_ptov(unsigned int phys_addr, unsigned int fn, unsigned int sz) */ static int eeprom_rd_phys(struct adapter *adap, unsigned int phys_addr, u32 *v) { - int vaddr = eeprom_ptov(phys_addr, adap->fn, EEPROMPFSIZE); + int vaddr = eeprom_ptov(phys_addr, adap->pf, EEPROMPFSIZE); if (vaddr >= 0) vaddr = pci_read_vpd(adap->pdev, vaddr, sizeof(u32), v); @@ -626,7 +833,7 @@ static int eeprom_rd_phys(struct adapter *adap, unsigned int phys_addr, u32 *v) static int eeprom_wr_phys(struct adapter *adap, unsigned int phys_addr, u32 v) { - int vaddr = eeprom_ptov(phys_addr, adap->fn, EEPROMPFSIZE); + int vaddr = eeprom_ptov(phys_addr, adap->pf, EEPROMPFSIZE); if (vaddr >= 0) vaddr = pci_write_vpd(adap->pdev, vaddr, sizeof(u32), &v); @@ -669,8 +876,8 @@ static int set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, aligned_offset = eeprom->offset & ~3; aligned_len = (eeprom->len + (eeprom->offset & 3) + 3) & ~3; - if (adapter->fn > 0) { - u32 start = 1024 + adapter->fn * EEPROMPFSIZE; + if (adapter->pf > 0) { + u32 start = 1024 + adapter->pf * EEPROMPFSIZE; if (aligned_offset < start || aligned_offset + aligned_len > start + EEPROMPFSIZE) @@ -740,37 +947,6 @@ static int set_flash(struct net_device *netdev, struct ethtool_flash *ef) return ret; } -#define WOL_SUPPORTED (WAKE_BCAST | WAKE_MAGIC) -#define BCAST_CRC 0xa0ccc1a6 - -static void get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) -{ - wol->supported = WAKE_BCAST | WAKE_MAGIC; - wol->wolopts = netdev2adap(dev)->wol; - memset(&wol->sopass, 0, sizeof(wol->sopass)); -} - -static int set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) -{ - int err = 0; - struct port_info *pi = netdev_priv(dev); - - if (wol->wolopts & ~WOL_SUPPORTED) - return -EINVAL; - t4_wol_magic_enable(pi->adapter, pi->tx_chan, - (wol->wolopts & WAKE_MAGIC) ? dev->dev_addr : NULL); - if (wol->wolopts & WAKE_BCAST) { - err = t4_wol_pat_enable(pi->adapter, pi->tx_chan, 0xfe, ~0ULL, - ~0ULL, 0, false); - if (!err) - err = t4_wol_pat_enable(pi->adapter, pi->tx_chan, 1, - ~6ULL, ~0ULL, BCAST_CRC, true); - } else { - t4_wol_pat_enable(pi->adapter, pi->tx_chan, 0, 0, 0, 0, false); - } - return err; -} - static u32 get_rss_table_size(struct net_device *dev) { const struct port_info *pi = netdev_priv(dev); @@ -900,8 +1076,6 @@ static const struct ethtool_ops cxgb_ethtool_ops = { .get_ethtool_stats = get_stats, .get_regs_len = get_regs_len, .get_regs = get_regs, - .get_wol = get_wol, - .set_wol = set_wol, .get_rxnfc = get_rxnfc, .get_rxfh_indir_size = get_rss_table_size, .get_rxfh = get_rss_table, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 73ac153..3057154 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -135,8 +135,10 @@ struct filter_entry { #define FW4_FNAME "cxgb4/t4fw.bin" #define FW5_FNAME "cxgb4/t5fw.bin" +#define FW6_FNAME "cxgb4/t6fw.bin" #define FW4_CFNAME "cxgb4/t4-config.txt" #define FW5_CFNAME "cxgb4/t5-config.txt" +#define FW6_CFNAME "cxgb4/t6-config.txt" #define PHY_AQ1202_FIRMWARE "cxgb4/aq1202_fw.cld" #define PHY_BCM84834_FIRMWARE "cxgb4/bcm8483.bin" #define PHY_AQ1202_DEVICEID 0x4409 @@ -322,7 +324,7 @@ static void dcb_tx_queue_prio_enable(struct net_device *dev, int enable) * level") we need to issue the Set Parameters Commannd * without sleeping (timeout < 0). */ - err = t4_set_params_timeout(adap, adap->mbox, adap->fn, 0, 1, + err = t4_set_params_timeout(adap, adap->mbox, adap->pf, 0, 1, &name, &value, -FW_CMD_MAX_TIMEOUT); @@ -387,7 +389,7 @@ static int set_addr_filters(const struct net_device *dev, bool sleep) int uc_cnt = netdev_uc_count(dev); int mc_cnt = netdev_mc_count(dev); const struct port_info *pi = netdev_priv(dev); - unsigned int mb = pi->adapter->fn; + unsigned int mb = pi->adapter->pf; /* first do the secondary unicast addresses */ netdev_for_each_uc_addr(ha, dev) { @@ -444,7 +446,7 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok) ret = set_addr_filters(dev, sleep_ok); if (ret == 0) - ret = t4_set_rxmode(pi->adapter, pi->adapter->fn, pi->viid, mtu, + ret = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, mtu, (dev->flags & IFF_PROMISC) ? 1 : 0, (dev->flags & IFF_ALLMULTI) ? 1 : 0, 1, -1, sleep_ok); @@ -461,7 +463,7 @@ static int link_start(struct net_device *dev) { int ret; struct port_info *pi = netdev_priv(dev); - unsigned int mb = pi->adapter->fn; + unsigned int mb = pi->adapter->pf; /* * We do not set address filters and promiscuity here, the stack does @@ -879,7 +881,7 @@ int cxgb4_write_rss(const struct port_info *pi, const u16 *queues) for (i = 0; i < pi->rss_size; i++, queues++) rss[i] = rxq[*queues].rspq.abs_id; - err = t4_config_rss_range(adapter, adapter->fn, pi->viid, 0, + err = t4_config_rss_range(adapter, adapter->pf, pi->viid, 0, pi->rss_size, rss, pi->rss_size); /* If Tunnel All Lookup isn't specified in the global RSS * Configuration, then we need to specify a default Ingress @@ -1351,11 +1353,6 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb, return fallback(dev, skb) % dev->real_num_tx_queues; } -static inline int is_offload(const struct adapter *adap) -{ - return adap->params.offload; -} - static int closest_timer(const struct sge *s, int time) { int i, delta, match = 0, min_delta = INT_MAX; @@ -1416,8 +1413,8 @@ int cxgb4_set_rspq_intr_params(struct sge_rspq *q, FW_PARAMS_PARAM_X_V( FW_PARAMS_PARAM_DMAQ_IQ_INTCNTTHRESH) | FW_PARAMS_PARAM_YZ_V(q->cntxt_id); - err = t4_set_params(adap, adap->fn, adap->fn, 0, 1, &v, - &new_idx); + err = t4_set_params(adap, adap->mbox, adap->pf, 0, 1, + &v, &new_idx); if (err) return err; } @@ -1438,7 +1435,7 @@ static int cxgb_set_features(struct net_device *dev, netdev_features_t features) if (!(changed & NETIF_F_HW_VLAN_CTAG_RX)) return 0; - err = t4_set_rxmode(pi->adapter, pi->adapter->fn, pi->viid, -1, + err = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, -1, -1, -1, -1, !!(features & NETIF_F_HW_VLAN_CTAG_RX), true); if (unlikely(err)) @@ -1721,7 +1718,7 @@ static int tid_init(struct tid_info *t) bitmap_zero(t->stid_bmap, t->nstids + t->nsftids); /* Reserve stid 0 for T4/T5 adapters */ if (!t->stid_base && - (is_t4(adap->params.chip) || is_t5(adap->params.chip))) + (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)) __set_bit(0, t->stid_bmap); return 0; @@ -2069,25 +2066,6 @@ out: } EXPORT_SYMBOL(cxgb4_sync_txq_pidx); -void cxgb4_disable_db_coalescing(struct net_device *dev) -{ - struct adapter *adap; - - adap = netdev2adap(dev); - t4_set_reg_field(adap, SGE_DOORBELL_CONTROL_A, NOCOALESCE_F, - NOCOALESCE_F); -} -EXPORT_SYMBOL(cxgb4_disable_db_coalescing); - -void cxgb4_enable_db_coalescing(struct net_device *dev) -{ - struct adapter *adap; - - adap = netdev2adap(dev); - t4_set_reg_field(adap, SGE_DOORBELL_CONTROL_A, NOCOALESCE_F, 0); -} -EXPORT_SYMBOL(cxgb4_enable_db_coalescing); - int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte) { struct adapter *adap; @@ -2127,10 +2105,7 @@ int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte) if (offset < mc0_end) { memtype = MEM_MC0; memaddr = offset - edc1_end; - } else if (is_t4(adap->params.chip)) { - /* T4 only has a single memory channel */ - goto err; - } else { + } else if (is_t5(adap->params.chip)) { size = t4_read_reg(adap, MA_EXT_MEMORY1_BAR_A); mc1_size = EXT_MEM1_SIZE_G(size) << 20; mc1_end = mc0_end + mc1_size; @@ -2141,6 +2116,9 @@ int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte) /* offset beyond the end of any memory */ goto err; } + } else { + /* T4/T6 only has a single memory channel */ + goto err; } } @@ -2175,7 +2153,7 @@ int cxgb4_bar2_sge_qregs(struct net_device *dev, u64 *pbar2_qoffset, unsigned int *pbar2_qid) { - return cxgb4_t4_bar2_sge_qregs(netdev2adap(dev), + return t4_bar2_sge_qregs(netdev2adap(dev), qid, (qtype == CXGB4_BAR2_QTYPE_EGRESS ? T4_BAR2_QTYPE_EGRESS @@ -2305,9 +2283,13 @@ static void process_db_full(struct work_struct *work) drain_db_fifo(adap, dbfifo_drain_delay); enable_dbs(adap); notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY); - t4_set_reg_field(adap, SGE_INT_ENABLE3_A, - DBFIFO_HP_INT_F | DBFIFO_LP_INT_F, - DBFIFO_HP_INT_F | DBFIFO_LP_INT_F); + if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5) + t4_set_reg_field(adap, SGE_INT_ENABLE3_A, + DBFIFO_HP_INT_F | DBFIFO_LP_INT_F, + DBFIFO_HP_INT_F | DBFIFO_LP_INT_F); + else + t4_set_reg_field(adap, SGE_INT_ENABLE3_A, + DBFIFO_LP_INT_F, DBFIFO_LP_INT_F); } static void sync_txq_pidx(struct adapter *adap, struct sge_txq *q) @@ -2369,7 +2351,7 @@ static void process_db_drop(struct work_struct *work) drain_db_fifo(adap, dbfifo_drain_delay); enable_dbs(adap); notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY); - } else { + } else if (is_t5(adap->params.chip)) { u32 dropped_db = t4_read_reg(adap, 0x010ac); u16 qid = (dropped_db >> 15) & 0x1ffff; u16 pidx_inc = dropped_db & 0x1fff; @@ -2377,7 +2359,7 @@ static void process_db_drop(struct work_struct *work) unsigned int bar2_qid; int ret; - ret = cxgb4_t4_bar2_sge_qregs(adap, qid, T4_BAR2_QTYPE_EGRESS, + ret = t4_bar2_sge_qregs(adap, qid, T4_BAR2_QTYPE_EGRESS, &bar2_qoffset, &bar2_qid); if (ret) dev_err(adap->pdev_dev, "doorbell drop recovery: " @@ -2390,7 +2372,8 @@ static void process_db_drop(struct work_struct *work) t4_set_reg_field(adap, 0x10b0, 1<<15, 1<<15); } - t4_set_reg_field(adap, SGE_DOORBELL_CONTROL_A, DROPPED_DB_F, 0); + if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5) + t4_set_reg_field(adap, SGE_DOORBELL_CONTROL_A, DROPPED_DB_F, 0); } void t4_db_full(struct adapter *adap) @@ -2420,7 +2403,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld) unsigned short i; lli.pdev = adap->pdev; - lli.pf = adap->fn; + lli.pf = adap->pf; lli.l2t = adap->l2t; lli.tids = &adap->tids; lli.ports = adap->port; @@ -2757,7 +2740,7 @@ static int cxgb_close(struct net_device *dev) netif_tx_stop_all_queues(dev); netif_carrier_off(dev); - return t4_enable_vi(adapter, adapter->fn, pi->viid, false, false); + return t4_enable_vi(adapter, adapter->pf, pi->viid, false, false); } /* Return an error number if the indicated filter isn't writable ... @@ -2901,7 +2884,8 @@ static struct rtnl_link_stats64 *cxgb_get_stats(struct net_device *dev, spin_unlock(&adapter->stats_lock); return ns; } - t4_get_port_stats(adapter, p->tx_chan, &stats); + t4_get_port_stats_offset(adapter, p->tx_chan, &stats, + &p->stats_base); spin_unlock(&adapter->stats_lock); ns->tx_bytes = stats.tx_octets; @@ -2960,7 +2944,7 @@ static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd) } else return -EINVAL; - mbox = pi->adapter->fn; + mbox = pi->adapter->pf; if (cmd == SIOCGMIIREG) ret = t4_mdio_rd(pi->adapter, mbox, prtad, devad, data->reg_num, &data->val_out); @@ -2987,7 +2971,7 @@ static int cxgb_change_mtu(struct net_device *dev, int new_mtu) if (new_mtu < 81 || new_mtu > MAX_MTU) /* accommodate SACK */ return -EINVAL; - ret = t4_set_rxmode(pi->adapter, pi->adapter->fn, pi->viid, new_mtu, -1, + ret = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, new_mtu, -1, -1, -1, -1, true); if (!ret) dev->mtu = new_mtu; @@ -3003,7 +2987,7 @@ static int cxgb_set_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - ret = t4_change_mac(pi->adapter, pi->adapter->fn, pi->viid, + ret = t4_change_mac(pi->adapter, pi->adapter->pf, pi->viid, pi->xact_addr_filt, addr->sa_data, true, true); if (ret < 0) return ret; @@ -3100,7 +3084,7 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c) c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) | FW_CMD_REQUEST_F | FW_CMD_READ_F); c->cfvalid_to_len16 = htonl(FW_LEN16(*c)); - ret = t4_wr_mbox(adap, adap->fn, c, sizeof(*c), c); + ret = t4_wr_mbox(adap, adap->mbox, c, sizeof(*c), c); if (ret < 0) return ret; @@ -3116,18 +3100,18 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c) } c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) | FW_CMD_REQUEST_F | FW_CMD_WRITE_F); - ret = t4_wr_mbox(adap, adap->fn, c, sizeof(*c), NULL); + ret = t4_wr_mbox(adap, adap->mbox, c, sizeof(*c), NULL); if (ret < 0) return ret; - ret = t4_config_glbl_rss(adap, adap->fn, + ret = t4_config_glbl_rss(adap, adap->pf, FW_RSS_GLB_CONFIG_CMD_MODE_BASICVIRTUAL, FW_RSS_GLB_CONFIG_CMD_TNLMAPEN_F | FW_RSS_GLB_CONFIG_CMD_TNLALLLKP_F); if (ret < 0) return ret; - ret = t4_cfg_pfvf(adap, adap->fn, adap->fn, 0, adap->sge.egr_sz, 64, + ret = t4_cfg_pfvf(adap, adap->mbox, adap->pf, 0, adap->sge.egr_sz, 64, MAX_INGQ, 0, 0, 4, 0xf, 0xf, 16, FW_CMD_CAP_PF, FW_CMD_CAP_PF); if (ret < 0) @@ -3171,7 +3155,7 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c) } /* get basic stuff going */ - return t4_early_init(adap, adap->fn); + return t4_early_init(adap, adap->pf); } /* @@ -3409,6 +3393,9 @@ static int adap_init0_config(struct adapter *adapter, int reset) case CHELSIO_T5: fw_config_file = FW5_CFNAME; break; + case CHELSIO_T6: + fw_config_file = FW6_CFNAME; + break; default: dev_err(adapter->pdev_dev, "Device %d is not supported\n", adapter->pdev->device); @@ -3434,7 +3421,7 @@ static int adap_init0_config(struct adapter *adapter, int reset) params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_CF)); ret = t4_query_params(adapter, adapter->mbox, - adapter->fn, 0, 1, params, val); + adapter->pf, 0, 1, params, val); if (ret == 0) { /* * For t4_memory_rw() below addresses and @@ -3605,7 +3592,24 @@ static struct fw_info fw_info_array[] = { .intfver_iscsi = FW_INTFVER(T5, ISCSI), .intfver_fcoe = FW_INTFVER(T5, FCOE), }, + }, { + .chip = CHELSIO_T6, + .fs_name = FW6_CFNAME, + .fw_mod_name = FW6_FNAME, + .fw_hdr = { + .chip = FW_HDR_CHIP_T6, + .fw_ver = __cpu_to_be32(FW_VERSION(T6)), + .intfver_nic = FW_INTFVER(T6, NIC), + .intfver_vnic = FW_INTFVER(T6, VNIC), + .intfver_ofld = FW_INTFVER(T6, OFLD), + .intfver_ri = FW_INTFVER(T6, RI), + .intfver_iscsipdu = FW_INTFVER(T6, ISCSIPDU), + .intfver_iscsi = FW_INTFVER(T6, ISCSI), + .intfver_fcoepdu = FW_INTFVER(T6, FCOEPDU), + .intfver_fcoe = FW_INTFVER(T6, FCOE), + }, } + }; static struct fw_info *find_fw_info(int chip) @@ -3723,7 +3727,7 @@ static int adap_init0(struct adapter *adap) v = FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PORTVEC); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1, &v, &port_vec); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &v, &port_vec); if (ret < 0) goto bye; @@ -3746,7 +3750,7 @@ static int adap_init0(struct adapter *adap) */ params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_CF)); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1, + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, params, val); /* If the firmware doesn't support Configuration Files, @@ -3805,7 +3809,7 @@ static int adap_init0(struct adapter *adap) params[3] = FW_PARAM_PFVF(FILTER_START); params[4] = FW_PARAM_PFVF(FILTER_END); params[5] = FW_PARAM_PFVF(IQFLINT_START); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, params, val); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6, params, val); if (ret < 0) goto bye; adap->sge.egr_start = val[0]; @@ -3823,7 +3827,7 @@ static int adap_init0(struct adapter *adap) */ params[0] = FW_PARAM_PFVF(EQ_END); params[1] = FW_PARAM_PFVF(IQFLINT_END); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, val); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val); if (ret < 0) goto bye; adap->sge.egr_sz = val[0] - adap->sge.egr_start + 1; @@ -3844,7 +3848,7 @@ static int adap_init0(struct adapter *adap) } /* Allocate the memory for the vaious egress queue bitmaps - * ie starving_fl and txq_maperr. + * ie starving_fl, txq_maperr and blocked_fl. */ adap->sge.starving_fl = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz), sizeof(long), GFP_KERNEL); @@ -3860,9 +3864,18 @@ static int adap_init0(struct adapter *adap) goto bye; } +#ifdef CONFIG_DEBUG_FS + adap->sge.blocked_fl = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz), + sizeof(long), GFP_KERNEL); + if (!adap->sge.blocked_fl) { + ret = -ENOMEM; + goto bye; + } +#endif + params[0] = FW_PARAM_PFVF(CLIP_START); params[1] = FW_PARAM_PFVF(CLIP_END); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, val); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val); if (ret < 0) goto bye; adap->clipt_start = val[0]; @@ -3871,7 +3884,7 @@ static int adap_init0(struct adapter *adap) /* query params related to active filter region */ params[0] = FW_PARAM_PFVF(ACTIVE_FILTER_START); params[1] = FW_PARAM_PFVF(ACTIVE_FILTER_END); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, val); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val); /* If Active filter size is set we enable establishing * offload connection through firmware work request */ @@ -3888,7 +3901,7 @@ static int adap_init0(struct adapter *adap) */ params[0] = FW_PARAM_PFVF(CPLFW4MSG_ENCAP); val[0] = 1; - (void) t4_set_params(adap, adap->mbox, adap->fn, 0, 1, params, val); + (void)t4_set_params(adap, adap->mbox, adap->pf, 0, 1, params, val); /* * Find out whether we're allowed to use the T5+ ULPTX MEMWRITE DSGL @@ -3900,7 +3913,7 @@ static int adap_init0(struct adapter *adap) adap->params.ulptx_memwrite_dsgl = false; } else { params[0] = FW_PARAM_DEV(ULPTX_MEMWRITE_DSGL); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, params, val); adap->params.ulptx_memwrite_dsgl = (ret == 0 && val[0] != 0); } @@ -3926,7 +3939,7 @@ static int adap_init0(struct adapter *adap) params[3] = FW_PARAM_PFVF(TDDP_START); params[4] = FW_PARAM_PFVF(TDDP_END); params[5] = FW_PARAM_DEV(FLOWC_BUFFIFO_SZ); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6, params, val); if (ret < 0) goto bye; @@ -3964,7 +3977,7 @@ static int adap_init0(struct adapter *adap) params[3] = FW_PARAM_PFVF(RQ_END); params[4] = FW_PARAM_PFVF(PBL_START); params[5] = FW_PARAM_PFVF(PBL_END); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6, params, val); if (ret < 0) goto bye; @@ -3981,7 +3994,7 @@ static int adap_init0(struct adapter *adap) params[3] = FW_PARAM_PFVF(CQ_END); params[4] = FW_PARAM_PFVF(OCQ_START); params[5] = FW_PARAM_PFVF(OCQ_END); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, params, + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6, params, val); if (ret < 0) goto bye; @@ -3994,7 +4007,7 @@ static int adap_init0(struct adapter *adap) params[0] = FW_PARAM_DEV(MAXORDIRD_QP); params[1] = FW_PARAM_DEV(MAXIRD_ADAPTER); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val); if (ret < 0) { adap->params.max_ordird_qp = 8; @@ -4012,7 +4025,7 @@ static int adap_init0(struct adapter *adap) if (caps_cmd.iscsicaps) { params[0] = FW_PARAM_PFVF(ISCSI_START); params[1] = FW_PARAM_PFVF(ISCSI_END); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val); if (ret < 0) goto bye; @@ -4072,6 +4085,9 @@ bye: kfree(adap->sge.ingr_map); kfree(adap->sge.starving_fl); kfree(adap->sge.txq_maperr); +#ifdef CONFIG_DEBUG_FS + kfree(adap->sge.blocked_fl); +#endif if (ret != -ETIMEDOUT && ret != -EIO) t4_fw_bye(adap, adap->mbox); return ret; @@ -4139,7 +4155,7 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev) if (t4_wait_dev_ready(adap->regs) < 0) return PCI_ERS_RESULT_DISCONNECT; - if (t4_fw_hello(adap, adap->fn, adap->fn, MASTER_MUST, NULL) < 0) + if (t4_fw_hello(adap, adap->mbox, adap->pf, MASTER_MUST, NULL) < 0) return PCI_ERS_RESULT_DISCONNECT; adap->flags |= FW_OK; if (adap_init1(adap, &c)) @@ -4148,7 +4164,7 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev) for_each_port(adap, i) { struct port_info *p = adap2pinfo(adap, i); - ret = t4_alloc_vi(adap, adap->fn, p->tx_chan, adap->fn, 0, 1, + ret = t4_alloc_vi(adap, adap->mbox, p->tx_chan, adap->pf, 0, 1, NULL, NULL); if (ret < 0) return PCI_ERS_RESULT_DISCONNECT; @@ -4515,6 +4531,9 @@ static void free_some_resources(struct adapter *adapter) kfree(adapter->sge.ingr_map); kfree(adapter->sge.starving_fl); kfree(adapter->sge.txq_maperr); +#ifdef CONFIG_DEBUG_FS + kfree(adapter->sge.blocked_fl); +#endif disable_msi(adapter); for_each_port(adapter, i) @@ -4523,7 +4542,7 @@ static void free_some_resources(struct adapter *adapter) free_netdev(adapter->port[i]); } if (adapter->flags & FW_OK) - t4_fw_bye(adapter, adapter->fn); + t4_fw_bye(adapter, adapter->pf); } #define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN) @@ -4614,7 +4633,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->pdev = pdev; adapter->pdev_dev = &pdev->dev; adapter->mbox = func; - adapter->fn = func; + adapter->pf = func; adapter->msg_enable = dflt_msg_enable; memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map)); @@ -4634,7 +4653,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (!is_t4(adapter->params.chip)) { s_qpp = (QUEUESPERPAGEPF0_S + (QUEUESPERPAGEPF1_S - QUEUESPERPAGEPF0_S) * - adapter->fn); + adapter->pf); qpp = 1 << QUEUESPERPAGEPF0_G(t4_read_reg(adapter, SGE_EGRESS_QUEUES_PER_PAGE_PF_A) >> s_qpp); num_seg = PAGE_SIZE / SEGMENT_SIZE; @@ -4657,10 +4676,15 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) err = -ENOMEM; goto out_free_adapter; } + t4_write_reg(adapter, SGE_STAT_CFG_A, + STATSOURCE_T5_V(7) | STATMODE_V(0)); } setup_memwin(adapter); err = adap_init0(adapter); +#ifdef CONFIG_DEBUG_FS + bitmap_zero(adapter->sge.blocked_fl, adapter->sge.egr_sz); +#endif setup_memwin_rdma(adapter); if (err) goto out_unmap_bar; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h index df34293..14e8110 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h @@ -298,8 +298,6 @@ struct sk_buff *cxgb4_pktgl_to_skb(const struct pkt_gl *gl, unsigned int skb_len, unsigned int pull_len); int cxgb4_sync_txq_pidx(struct net_device *dev, u16 qid, u16 pidx, u16 size); int cxgb4_flush_eq_cache(struct net_device *dev); -void cxgb4_disable_db_coalescing(struct net_device *dev); -void cxgb4_enable_db_coalescing(struct net_device *dev); int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte); u64 cxgb4_read_sge_timestamp(struct net_device *dev); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index dd18fcb..6b7c37fd0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -522,14 +522,13 @@ static void unmap_rx_buf(struct adapter *adap, struct sge_fl *q) static inline void ring_fl_db(struct adapter *adap, struct sge_fl *q) { - u32 val; if (q->pend_cred >= 8) { + u32 val = adap->params.arch.sge_fl_db; + if (is_t4(adap->params.chip)) - val = PIDX_V(q->pend_cred / 8); + val |= PIDX_V(q->pend_cred / 8); else - val = PIDX_T5_V(q->pend_cred / 8) | - DBTYPE_F; - val |= DBPRIO_F; + val |= PIDX_T5_V(q->pend_cred / 8); /* Make sure all memory writes to the Free List queue are * committed before we tell the hardware about them. @@ -588,6 +587,11 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n, struct rx_sw_desc *sd = &q->sdesc[q->pidx]; int node; +#ifdef CONFIG_DEBUG_FS + if (test_bit(q->cntxt_id - adap->sge.egr_start, adap->sge.blocked_fl)) + goto out; +#endif + gfp |= __GFP_NOWARN; node = dev_to_node(adap->pdev_dev); @@ -1029,7 +1033,7 @@ static void inline_tx_skb(const struct sk_buff *skb, const struct sge_txq *q, * Figure out what HW csum a packet wants and return the appropriate control * bits. */ -static u64 hwcsum(const struct sk_buff *skb) +static u64 hwcsum(enum chip_type chip, const struct sk_buff *skb) { int csum_type; const struct iphdr *iph = ip_hdr(skb); @@ -1060,11 +1064,16 @@ nocsum: /* goto nocsum; } - if (likely(csum_type >= TX_CSUM_TCPIP)) - return TXPKT_CSUM_TYPE_V(csum_type) | - TXPKT_IPHDR_LEN_V(skb_network_header_len(skb)) | - TXPKT_ETHHDR_LEN_V(skb_network_offset(skb) - ETH_HLEN); - else { + if (likely(csum_type >= TX_CSUM_TCPIP)) { + u64 hdr_len = TXPKT_IPHDR_LEN_V(skb_network_header_len(skb)); + int eth_hdr_len = skb_network_offset(skb) - ETH_HLEN; + + if (CHELSIO_CHIP_VERSION(chip) <= CHELSIO_T5) + hdr_len |= TXPKT_ETHHDR_LEN_V(eth_hdr_len); + else + hdr_len |= T6_TXPKT_ETHHDR_LEN_V(eth_hdr_len); + return TXPKT_CSUM_TYPE_V(csum_type) | hdr_len; + } else { int start = skb_transport_offset(skb); return TXPKT_CSUM_TYPE_V(csum_type) | @@ -1232,9 +1241,15 @@ out_free: dev_kfree_skb_any(skb); else lso->c.len = htonl(LSO_T5_XFER_SIZE_V(skb->len)); cpl = (void *)(lso + 1); - cntrl = TXPKT_CSUM_TYPE_V(v6 ? TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) | - TXPKT_IPHDR_LEN_V(l3hdr_len) | - TXPKT_ETHHDR_LEN_V(eth_xtra_len); + + if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5) + cntrl = TXPKT_ETHHDR_LEN_V(eth_xtra_len); + else + cntrl = T6_TXPKT_ETHHDR_LEN_V(eth_xtra_len); + + cntrl |= TXPKT_CSUM_TYPE_V(v6 ? + TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) | + TXPKT_IPHDR_LEN_V(l3hdr_len); q->tso++; q->tx_cso += ssi->gso_segs; } else { @@ -1243,7 +1258,8 @@ out_free: dev_kfree_skb_any(skb); FW_WR_IMMDLEN_V(len)); cpl = (void *)(wr + 1); if (skb->ip_summed == CHECKSUM_PARTIAL) { - cntrl = hwcsum(skb) | TXPKT_IPCSUM_DIS_F; + cntrl = hwcsum(adap->params.chip, skb) | + TXPKT_IPCSUM_DIS_F; q->tx_cso++; } } @@ -1260,7 +1276,7 @@ out_free: dev_kfree_skb_any(skb); cpl->ctrl0 = htonl(TXPKT_OPCODE_V(CPL_TX_PKT_XT) | TXPKT_INTF_V(pi->tx_chan) | - TXPKT_PF_V(adap->fn)); + TXPKT_PF_V(adap->pf)); cpl->pack = htons(0); cpl->len = htons(skb->len); cpl->ctrl1 = cpu_to_be64(cntrl); @@ -2385,7 +2401,7 @@ static void __iomem *bar2_address(struct adapter *adapter, u64 bar2_qoffset; int ret; - ret = cxgb4_t4_bar2_sge_qregs(adapter, qid, qtype, + ret = t4_bar2_sge_qregs(adapter, qid, qtype, &bar2_qoffset, pbar2_qid); if (ret) return NULL; @@ -2416,7 +2432,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, memset(&c, 0, sizeof(c)); c.op_to_vfn = htonl(FW_CMD_OP_V(FW_IQ_CMD) | FW_CMD_REQUEST_F | FW_CMD_WRITE_F | FW_CMD_EXEC_F | - FW_IQ_CMD_PFN_V(adap->fn) | FW_IQ_CMD_VFN_V(0)); + FW_IQ_CMD_PFN_V(adap->pf) | FW_IQ_CMD_VFN_V(0)); c.alloc_to_len16 = htonl(FW_IQ_CMD_ALLOC_F | FW_IQ_CMD_IQSTART_F | FW_LEN16(c)); c.type_to_iqandstindex = htonl(FW_IQ_CMD_TYPE_V(FW_IQ_TYPE_FL_INT_CAP) | @@ -2435,6 +2451,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, c.iqns_to_fl0congen = htonl(FW_IQ_CMD_IQFLINTCONGEN_F); if (fl) { + enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip); + /* Allocate the ring for the hardware free list (with space * for its status page) along with the associated software * descriptor ring. The free list size needs to be a multiple @@ -2463,12 +2481,14 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, FW_IQ_CMD_FL0CONGEN_F); c.fl0dcaen_to_fl0cidxfthresh = htons(FW_IQ_CMD_FL0FBMIN_V(FETCHBURSTMIN_64B_X) | - FW_IQ_CMD_FL0FBMAX_V(FETCHBURSTMAX_512B_X)); + FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ? + FETCHBURSTMAX_512B_X : + FETCHBURSTMAX_256B_X)); c.fl0size = htons(flsz); c.fl0addr = cpu_to_be64(fl->addr); } - ret = t4_wr_mbox(adap, adap->fn, &c, sizeof(c), &c); + ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c); if (ret) goto err; @@ -2536,7 +2556,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, CONMCTXT_CNGCHMAP_V(1 << (i << 2)); } } - ret = t4_set_params(adap, adap->mbox, adap->fn, 0, 1, + ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1, ¶m, &val); if (ret) dev_warn(adap->pdev_dev, "Failed to set Congestion" @@ -2601,7 +2621,7 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, memset(&c, 0, sizeof(c)); c.op_to_vfn = htonl(FW_CMD_OP_V(FW_EQ_ETH_CMD) | FW_CMD_REQUEST_F | FW_CMD_WRITE_F | FW_CMD_EXEC_F | - FW_EQ_ETH_CMD_PFN_V(adap->fn) | + FW_EQ_ETH_CMD_PFN_V(adap->pf) | FW_EQ_ETH_CMD_VFN_V(0)); c.alloc_to_len16 = htonl(FW_EQ_ETH_CMD_ALLOC_F | FW_EQ_ETH_CMD_EQSTART_F | FW_LEN16(c)); @@ -2618,7 +2638,7 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, FW_EQ_ETH_CMD_EQSIZE_V(nentries)); c.eqaddr = cpu_to_be64(txq->q.phys_addr); - ret = t4_wr_mbox(adap, adap->fn, &c, sizeof(c), &c); + ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c); if (ret) { kfree(txq->q.sdesc); txq->q.sdesc = NULL; @@ -2656,7 +2676,7 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq, c.op_to_vfn = htonl(FW_CMD_OP_V(FW_EQ_CTRL_CMD) | FW_CMD_REQUEST_F | FW_CMD_WRITE_F | FW_CMD_EXEC_F | - FW_EQ_CTRL_CMD_PFN_V(adap->fn) | + FW_EQ_CTRL_CMD_PFN_V(adap->pf) | FW_EQ_CTRL_CMD_VFN_V(0)); c.alloc_to_len16 = htonl(FW_EQ_CTRL_CMD_ALLOC_F | FW_EQ_CTRL_CMD_EQSTART_F | FW_LEN16(c)); @@ -2673,7 +2693,7 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq, FW_EQ_CTRL_CMD_EQSIZE_V(nentries)); c.eqaddr = cpu_to_be64(txq->q.phys_addr); - ret = t4_wr_mbox(adap, adap->fn, &c, sizeof(c), &c); + ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c); if (ret) { dma_free_coherent(adap->pdev_dev, nentries * sizeof(struct tx_desc), @@ -2711,7 +2731,7 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq, memset(&c, 0, sizeof(c)); c.op_to_vfn = htonl(FW_CMD_OP_V(FW_EQ_OFLD_CMD) | FW_CMD_REQUEST_F | FW_CMD_WRITE_F | FW_CMD_EXEC_F | - FW_EQ_OFLD_CMD_PFN_V(adap->fn) | + FW_EQ_OFLD_CMD_PFN_V(adap->pf) | FW_EQ_OFLD_CMD_VFN_V(0)); c.alloc_to_len16 = htonl(FW_EQ_OFLD_CMD_ALLOC_F | FW_EQ_OFLD_CMD_EQSTART_F | FW_LEN16(c)); @@ -2726,7 +2746,7 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq, FW_EQ_OFLD_CMD_EQSIZE_V(nentries)); c.eqaddr = cpu_to_be64(txq->q.phys_addr); - ret = t4_wr_mbox(adap, adap->fn, &c, sizeof(c), &c); + ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c); if (ret) { kfree(txq->q.sdesc); txq->q.sdesc = NULL; @@ -2765,7 +2785,7 @@ static void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq, unsigned int fl_id = fl ? fl->cntxt_id : 0xffff; adap->sge.ingr_map[rq->cntxt_id - adap->sge.ingr_start] = NULL; - t4_iq_free(adap, adap->fn, adap->fn, 0, FW_IQ_TYPE_FL_INT_CAP, + t4_iq_free(adap, adap->mbox, adap->pf, 0, FW_IQ_TYPE_FL_INT_CAP, rq->cntxt_id, fl_id, 0xffff); dma_free_coherent(adap->pdev_dev, (rq->size + 1) * rq->iqe_len, rq->desc, rq->phys_addr); @@ -2820,7 +2840,7 @@ void t4_free_sge_resources(struct adapter *adap) free_rspq_fl(adap, &eq->rspq, eq->fl.size ? &eq->fl : NULL); if (etq->q.desc) { - t4_eth_eq_free(adap, adap->fn, adap->fn, 0, + t4_eth_eq_free(adap, adap->mbox, adap->pf, 0, etq->q.cntxt_id); free_tx_desc(adap, &etq->q, etq->q.in_use, true); kfree(etq->q.sdesc); @@ -2839,7 +2859,7 @@ void t4_free_sge_resources(struct adapter *adap) if (q->q.desc) { tasklet_kill(&q->qresume_tsk); - t4_ofld_eq_free(adap, adap->fn, adap->fn, 0, + t4_ofld_eq_free(adap, adap->mbox, adap->pf, 0, q->q.cntxt_id); free_tx_desc(adap, &q->q, q->q.in_use, false); kfree(q->q.sdesc); @@ -2854,7 +2874,7 @@ void t4_free_sge_resources(struct adapter *adap) if (cq->q.desc) { tasklet_kill(&cq->qresume_tsk); - t4_ctrl_eq_free(adap, adap->fn, adap->fn, 0, + t4_ctrl_eq_free(adap, adap->mbox, adap->pf, 0, cq->q.cntxt_id); __skb_queue_purge(&cq->sendq); free_txq(adap, &cq->q); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 7b92f0f..c21ab26 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -150,7 +150,12 @@ void t4_write_indirect(struct adapter *adap, unsigned int addr_reg, */ void t4_hw_pci_read_cfg4(struct adapter *adap, int reg, u32 *val) { - u32 req = ENABLE_F | FUNCTION_V(adap->fn) | REGISTER_V(reg); + u32 req = FUNCTION_V(adap->pf) | REGISTER_V(reg); + + if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5) + req |= ENABLE_F; + else + req |= T6_ENABLE_F; if (is_t4(adap->params.chip)) req |= LOCALCFG_F; @@ -381,9 +386,8 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, /* Offset into the region of memory which is being accessed * MEM_EDC0 = 0 * MEM_EDC1 = 1 - * MEM_MC = 2 -- T4 - * MEM_MC0 = 2 -- For T5 - * MEM_MC1 = 3 -- For T5 + * MEM_MC = 2 -- MEM_MC for chips with only 1 memory controller + * MEM_MC1 = 3 -- for chips with 2 memory controllers (e.g. T5) */ edc_size = EDRAM0_SIZE_G(t4_read_reg(adap, MA_EDRAM0_BAR_A)); if (mtype != MEM_MC1) @@ -412,7 +416,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, mem_base = PCIEOFST_G(mem_reg) << PCIEOFST_SHIFT_X; if (is_t4(adap->params.chip)) mem_base -= adap->t4_bar0; - win_pf = is_t4(adap->params.chip) ? 0 : PFNUM_V(adap->fn); + win_pf = is_t4(adap->params.chip) ? 0 : PFNUM_V(adap->pf); /* Calculate our initial PCI-E Memory Window Position and Offset into * that Window. @@ -547,7 +551,7 @@ u32 t4_read_pcie_cfg4(struct adapter *adap, int reg) ldst_cmd.cycles_to_len16 = cpu_to_be32(FW_LEN16(ldst_cmd)); ldst_cmd.u.pcie.select_naccess = FW_LDST_CMD_NACCESS_V(1); ldst_cmd.u.pcie.ctrl_to_fn = - (FW_LDST_CMD_LC_F | FW_LDST_CMD_FN_V(adap->fn)); + (FW_LDST_CMD_LC_F | FW_LDST_CMD_FN_V(adap->pf)); ldst_cmd.u.pcie.r = reg; /* If the LDST Command succeeds, return the result, otherwise @@ -634,6 +638,7 @@ unsigned int t4_get_regs_len(struct adapter *adapter) return T4_REGMAP_SIZE; case CHELSIO_T5: + case CHELSIO_T6: return T5_REGMAP_SIZE; } @@ -1316,6 +1321,344 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x51300, 0x51308, }; + static const unsigned int t6_reg_ranges[] = { + 0x1008, 0x114c, + 0x1180, 0x11b4, + 0x11fc, 0x1250, + 0x1280, 0x133c, + 0x1800, 0x18fc, + 0x3000, 0x302c, + 0x3060, 0x30d8, + 0x30e0, 0x30fc, + 0x3140, 0x357c, + 0x35a8, 0x35cc, + 0x35ec, 0x35ec, + 0x3600, 0x5624, + 0x56cc, 0x575c, + 0x580c, 0x5814, + 0x5890, 0x58bc, + 0x5940, 0x595c, + 0x5980, 0x598c, + 0x59b0, 0x59dc, + 0x59fc, 0x5a18, + 0x5a60, 0x5a6c, + 0x5a80, 0x5a9c, + 0x5b94, 0x5bfc, + 0x5c10, 0x5ec0, + 0x5ec8, 0x5ec8, + 0x6000, 0x6040, + 0x6058, 0x6154, + 0x7700, 0x7798, + 0x77c0, 0x7880, + 0x78cc, 0x78fc, + 0x7b00, 0x7c54, + 0x7d00, 0x7efc, + 0x8dc0, 0x8de0, + 0x8df8, 0x8e84, + 0x8ea0, 0x8f88, + 0x8fb8, 0x911c, + 0x9400, 0x9470, + 0x9600, 0x971c, + 0x9800, 0x9808, + 0x9820, 0x983c, + 0x9850, 0x9864, + 0x9c00, 0x9c6c, + 0x9c80, 0x9cec, + 0x9d00, 0x9d6c, + 0x9d80, 0x9dec, + 0x9e00, 0x9e6c, + 0x9e80, 0x9eec, + 0x9f00, 0x9f6c, + 0x9f80, 0xa020, + 0xd004, 0xd03c, + 0xdfc0, 0xdfe0, + 0xe000, 0xf008, + 0x11000, 0x11014, + 0x11048, 0x11110, + 0x11118, 0x1117c, + 0x11190, 0x11260, + 0x11300, 0x1130c, + 0x12000, 0x1205c, + 0x19040, 0x1906c, + 0x19078, 0x19080, + 0x1908c, 0x19124, + 0x19150, 0x191b0, + 0x191d0, 0x191e8, + 0x19238, 0x192b8, + 0x193f8, 0x19474, + 0x19490, 0x194cc, + 0x194f0, 0x194f8, + 0x19c00, 0x19c80, + 0x19c94, 0x19cbc, + 0x19ce4, 0x19d28, + 0x19d50, 0x19d78, + 0x19d94, 0x19dc8, + 0x19df0, 0x19e10, + 0x19e50, 0x19e6c, + 0x19ea0, 0x19f34, + 0x19f40, 0x19f50, + 0x19f90, 0x19fac, + 0x19fc4, 0x19fe4, + 0x1a000, 0x1a06c, + 0x1a0b0, 0x1a120, + 0x1a128, 0x1a138, + 0x1a190, 0x1a1c4, + 0x1a1fc, 0x1a1fc, + 0x1e008, 0x1e00c, + 0x1e040, 0x1e04c, + 0x1e284, 0x1e290, + 0x1e2c0, 0x1e2c0, + 0x1e2e0, 0x1e2e0, + 0x1e300, 0x1e384, + 0x1e3c0, 0x1e3c8, + 0x1e408, 0x1e40c, + 0x1e440, 0x1e44c, + 0x1e684, 0x1e690, + 0x1e6c0, 0x1e6c0, + 0x1e6e0, 0x1e6e0, + 0x1e700, 0x1e784, + 0x1e7c0, 0x1e7c8, + 0x1e808, 0x1e80c, + 0x1e840, 0x1e84c, + 0x1ea84, 0x1ea90, + 0x1eac0, 0x1eac0, + 0x1eae0, 0x1eae0, + 0x1eb00, 0x1eb84, + 0x1ebc0, 0x1ebc8, + 0x1ec08, 0x1ec0c, + 0x1ec40, 0x1ec4c, + 0x1ee84, 0x1ee90, + 0x1eec0, 0x1eec0, + 0x1eee0, 0x1eee0, + 0x1ef00, 0x1ef84, + 0x1efc0, 0x1efc8, + 0x1f008, 0x1f00c, + 0x1f040, 0x1f04c, + 0x1f284, 0x1f290, + 0x1f2c0, 0x1f2c0, + 0x1f2e0, 0x1f2e0, + 0x1f300, 0x1f384, + 0x1f3c0, 0x1f3c8, + 0x1f408, 0x1f40c, + 0x1f440, 0x1f44c, + 0x1f684, 0x1f690, + 0x1f6c0, 0x1f6c0, + 0x1f6e0, 0x1f6e0, + 0x1f700, 0x1f784, + 0x1f7c0, 0x1f7c8, + 0x1f808, 0x1f80c, + 0x1f840, 0x1f84c, + 0x1fa84, 0x1fa90, + 0x1fac0, 0x1fac0, + 0x1fae0, 0x1fae0, + 0x1fb00, 0x1fb84, + 0x1fbc0, 0x1fbc8, + 0x1fc08, 0x1fc0c, + 0x1fc40, 0x1fc4c, + 0x1fe84, 0x1fe90, + 0x1fec0, 0x1fec0, + 0x1fee0, 0x1fee0, + 0x1ff00, 0x1ff84, + 0x1ffc0, 0x1ffc8, + 0x30000, 0x30070, + 0x30100, 0x3015c, + 0x30190, 0x301d0, + 0x30200, 0x30318, + 0x30400, 0x3052c, + 0x30540, 0x3061c, + 0x30800, 0x3088c, + 0x308c0, 0x30908, + 0x30910, 0x309b8, + 0x30a00, 0x30a04, + 0x30a0c, 0x30a2c, + 0x30a44, 0x30a50, + 0x30a74, 0x30c24, + 0x30d00, 0x30d3c, + 0x30d44, 0x30d7c, + 0x30de0, 0x30de0, + 0x30e00, 0x30ed4, + 0x30f00, 0x30fa4, + 0x30fc0, 0x30fc4, + 0x31000, 0x31004, + 0x31080, 0x310fc, + 0x31208, 0x31220, + 0x3123c, 0x31254, + 0x31300, 0x31300, + 0x31308, 0x3131c, + 0x31338, 0x3133c, + 0x31380, 0x31380, + 0x31388, 0x313a8, + 0x313b4, 0x313b4, + 0x31400, 0x31420, + 0x31438, 0x3143c, + 0x31480, 0x31480, + 0x314a8, 0x314a8, + 0x314b0, 0x314b4, + 0x314c8, 0x314d4, + 0x31a40, 0x31a4c, + 0x31af0, 0x31b20, + 0x31b38, 0x31b3c, + 0x31b80, 0x31b80, + 0x31ba8, 0x31ba8, + 0x31bb0, 0x31bb4, + 0x31bc8, 0x31bd4, + 0x32140, 0x3218c, + 0x321f0, 0x32200, + 0x32218, 0x32218, + 0x32400, 0x32400, + 0x32408, 0x3241c, + 0x32618, 0x32620, + 0x32664, 0x32664, + 0x326a8, 0x326a8, + 0x326ec, 0x326ec, + 0x32a00, 0x32abc, + 0x32b00, 0x32b78, + 0x32c00, 0x32c00, + 0x32c08, 0x32c3c, + 0x32e00, 0x32e2c, + 0x32f00, 0x32f2c, + 0x33000, 0x330ac, + 0x330c0, 0x331ac, + 0x331c0, 0x332c4, + 0x332e4, 0x333c4, + 0x333e4, 0x334ac, + 0x334c0, 0x335ac, + 0x335c0, 0x336c4, + 0x336e4, 0x337c4, + 0x337e4, 0x337fc, + 0x33814, 0x33814, + 0x33854, 0x33868, + 0x33880, 0x3388c, + 0x338c0, 0x338d0, + 0x338e8, 0x338ec, + 0x33900, 0x339ac, + 0x339c0, 0x33ac4, + 0x33ae4, 0x33b10, + 0x33b24, 0x33b50, + 0x33bf0, 0x33c10, + 0x33c24, 0x33c50, + 0x33cf0, 0x33cfc, + 0x34000, 0x34070, + 0x34100, 0x3415c, + 0x34190, 0x341d0, + 0x34200, 0x34318, + 0x34400, 0x3452c, + 0x34540, 0x3461c, + 0x34800, 0x3488c, + 0x348c0, 0x34908, + 0x34910, 0x349b8, + 0x34a00, 0x34a04, + 0x34a0c, 0x34a2c, + 0x34a44, 0x34a50, + 0x34a74, 0x34c24, + 0x34d00, 0x34d3c, + 0x34d44, 0x34d7c, + 0x34de0, 0x34de0, + 0x34e00, 0x34ed4, + 0x34f00, 0x34fa4, + 0x34fc0, 0x34fc4, + 0x35000, 0x35004, + 0x35080, 0x350fc, + 0x35208, 0x35220, + 0x3523c, 0x35254, + 0x35300, 0x35300, + 0x35308, 0x3531c, + 0x35338, 0x3533c, + 0x35380, 0x35380, + 0x35388, 0x353a8, + 0x353b4, 0x353b4, + 0x35400, 0x35420, + 0x35438, 0x3543c, + 0x35480, 0x35480, + 0x354a8, 0x354a8, + 0x354b0, 0x354b4, + 0x354c8, 0x354d4, + 0x35a40, 0x35a4c, + 0x35af0, 0x35b20, + 0x35b38, 0x35b3c, + 0x35b80, 0x35b80, + 0x35ba8, 0x35ba8, + 0x35bb0, 0x35bb4, + 0x35bc8, 0x35bd4, + 0x36140, 0x3618c, + 0x361f0, 0x36200, + 0x36218, 0x36218, + 0x36400, 0x36400, + 0x36408, 0x3641c, + 0x36618, 0x36620, + 0x36664, 0x36664, + 0x366a8, 0x366a8, + 0x366ec, 0x366ec, + 0x36a00, 0x36abc, + 0x36b00, 0x36b78, + 0x36c00, 0x36c00, + 0x36c08, 0x36c3c, + 0x36e00, 0x36e2c, + 0x36f00, 0x36f2c, + 0x37000, 0x370ac, + 0x370c0, 0x371ac, + 0x371c0, 0x372c4, + 0x372e4, 0x373c4, + 0x373e4, 0x374ac, + 0x374c0, 0x375ac, + 0x375c0, 0x376c4, + 0x376e4, 0x377c4, + 0x377e4, 0x377fc, + 0x37814, 0x37814, + 0x37854, 0x37868, + 0x37880, 0x3788c, + 0x378c0, 0x378d0, + 0x378e8, 0x378ec, + 0x37900, 0x379ac, + 0x379c0, 0x37ac4, + 0x37ae4, 0x37b10, + 0x37b24, 0x37b50, + 0x37bf0, 0x37c10, + 0x37c24, 0x37c50, + 0x37cf0, 0x37cfc, + 0x40040, 0x40040, + 0x40080, 0x40084, + 0x40100, 0x40100, + 0x40140, 0x401bc, + 0x40200, 0x40214, + 0x40228, 0x40228, + 0x40240, 0x40258, + 0x40280, 0x40280, + 0x40304, 0x40304, + 0x40330, 0x4033c, + 0x41304, 0x413dc, + 0x41400, 0x4141c, + 0x41480, 0x414d0, + 0x44000, 0x4407c, + 0x440c0, 0x4427c, + 0x442c0, 0x4447c, + 0x444c0, 0x4467c, + 0x446c0, 0x4487c, + 0x448c0, 0x44a7c, + 0x44ac0, 0x44c7c, + 0x44cc0, 0x44e7c, + 0x44ec0, 0x4507c, + 0x450c0, 0x451fc, + 0x45800, 0x45868, + 0x45880, 0x45884, + 0x458a0, 0x458b0, + 0x45a00, 0x45a68, + 0x45a80, 0x45a84, + 0x45aa0, 0x45ab0, + 0x460c0, 0x460e4, + 0x47000, 0x4708c, + 0x47200, 0x47250, + 0x47400, 0x47420, + 0x47600, 0x47618, + 0x47800, 0x4782c, + 0x50000, 0x500cc, + 0x50400, 0x50400, + 0x50800, 0x508cc, + 0x50c00, 0x50c00, + 0x51000, 0x510b0, + 0x51300, 0x51324, + }; + u32 *buf_end = (u32 *)((char *)buf + buf_size); const unsigned int *reg_ranges; int reg_ranges_size, range; @@ -1335,6 +1678,11 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) reg_ranges_size = ARRAY_SIZE(t5_reg_ranges); break; + case CHELSIO_T6: + reg_ranges = t6_reg_ranges; + reg_ranges_size = ARRAY_SIZE(t6_reg_ranges); + break; + default: dev_err(adap->pdev_dev, "Unsupported chip version %d\n", chip_version); @@ -1948,7 +2296,8 @@ static bool t4_fw_matches_chip(const struct adapter *adap, * which will keep us "honest" in the future ... */ if ((is_t4(adap->params.chip) && hdr->chip == FW_HDR_CHIP_T4) || - (is_t5(adap->params.chip) && hdr->chip == FW_HDR_CHIP_T5)) + (is_t5(adap->params.chip) && hdr->chip == FW_HDR_CHIP_T5) || + (is_t6(adap->params.chip) && hdr->chip == FW_HDR_CHIP_T6)) return true; dev_err(adap->pdev_dev, @@ -2062,7 +2411,7 @@ int t4_phy_fw_ver(struct adapter *adap, int *phy_fw_ver) FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PHYFW) | FW_PARAMS_PARAM_Y_V(adap->params.portvec) | FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_PHYFW_VERSION)); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1, + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, ¶m, &val); if (ret < 0) return ret; @@ -2134,7 +2483,7 @@ int t4_load_phy_fw(struct adapter *adap, FW_PARAMS_PARAM_Y_V(adap->params.portvec) | FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_PHYFW_DOWNLOAD)); val = phy_fw_size; - ret = t4_query_params_rw(adap, adap->mbox, adap->fn, 0, 1, + ret = t4_query_params_rw(adap, adap->mbox, adap->pf, 0, 1, ¶m, &val, 1); if (ret < 0) return ret; @@ -2163,7 +2512,7 @@ int t4_load_phy_fw(struct adapter *adap, FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PHYFW) | FW_PARAMS_PARAM_Y_V(adap->params.portvec) | FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_PHYFW_DOWNLOAD)); - ret = t4_set_params_timeout(adap, adap->mbox, adap->fn, 0, 1, + ret = t4_set_params_timeout(adap, adap->mbox, adap->pf, 0, 1, ¶m, &val, 30000); /* If we have version number support, then check to see that the new @@ -2199,7 +2548,7 @@ int t4_fwcache(struct adapter *adap, enum fw_params_param_dev_fwcache op) c.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_PARAMS_CMD) | FW_CMD_REQUEST_F | FW_CMD_WRITE_F | - FW_PARAMS_CMD_PFN_V(adap->fn) | + FW_PARAMS_CMD_PFN_V(adap->pf) | FW_PARAMS_CMD_VFN_V(0)); c.retval_len16 = cpu_to_be32(FW_LEN16(c)); c.param[0].mnem = @@ -2488,6 +2837,7 @@ static void tp_intr_handler(struct adapter *adapter) static void sge_intr_handler(struct adapter *adapter) { u64 v; + u32 err; static const struct intr_info sge_intr_info[] = { { ERR_CPL_EXCEED_IQE_SIZE_F, @@ -2496,8 +2846,6 @@ static void sge_intr_handler(struct adapter *adapter) "SGE GTS CIDX increment too large", -1, 0 }, { ERR_CPL_OPCODE_0_F, "SGE received 0-length CPL", -1, 0 }, { DBFIFO_LP_INT_F, NULL, -1, 0, t4_db_full }, - { DBFIFO_HP_INT_F, NULL, -1, 0, t4_db_full }, - { ERR_DROPPED_DB_F, NULL, -1, 0, t4_db_dropped }, { ERR_DATA_CPL_ON_HIGH_QID1_F | ERR_DATA_CPL_ON_HIGH_QID0_F, "SGE IQID > 1023 received CPL for FL", -1, 0 }, { ERR_BAD_DB_PIDX3_F, "SGE DBP 3 pidx increment too large", -1, @@ -2510,13 +2858,19 @@ static void sge_intr_handler(struct adapter *adapter) 0 }, { ERR_ING_CTXT_PRIO_F, "SGE too many priority ingress contexts", -1, 0 }, - { ERR_EGR_CTXT_PRIO_F, - "SGE too many priority egress contexts", -1, 0 }, { INGRESS_SIZE_ERR_F, "SGE illegal ingress QID", -1, 0 }, { EGRESS_SIZE_ERR_F, "SGE illegal egress QID", -1, 0 }, { 0 } }; + static struct intr_info t4t5_sge_intr_info[] = { + { ERR_DROPPED_DB_F, NULL, -1, 0, t4_db_dropped }, + { DBFIFO_HP_INT_F, NULL, -1, 0, t4_db_full }, + { ERR_EGR_CTXT_PRIO_F, + "SGE too many priority egress contexts", -1, 0 }, + { 0 } + }; + v = (u64)t4_read_reg(adapter, SGE_INT_CAUSE1_A) | ((u64)t4_read_reg(adapter, SGE_INT_CAUSE2_A) << 32); if (v) { @@ -2526,8 +2880,23 @@ static void sge_intr_handler(struct adapter *adapter) t4_write_reg(adapter, SGE_INT_CAUSE2_A, v >> 32); } - if (t4_handle_intr_status(adapter, SGE_INT_CAUSE3_A, sge_intr_info) || - v != 0) + v |= t4_handle_intr_status(adapter, SGE_INT_CAUSE3_A, sge_intr_info); + if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) + v |= t4_handle_intr_status(adapter, SGE_INT_CAUSE3_A, + t4t5_sge_intr_info); + + err = t4_read_reg(adapter, SGE_ERROR_STATS_A); + if (err & ERROR_QID_VALID_F) { + dev_err(adapter->pdev_dev, "SGE error for queue %u\n", + ERROR_QID_G(err)); + if (err & UNCAPTURED_ERROR_F) + dev_err(adapter->pdev_dev, + "SGE UNCAPTURED_ERROR set (clearing)\n"); + t4_write_reg(adapter, SGE_ERROR_STATS_A, ERROR_QID_VALID_F | + UNCAPTURED_ERROR_F); + } + + if (v != 0) t4_fatal_err(adapter); } @@ -2700,6 +3069,7 @@ static void cplsw_intr_handler(struct adapter *adapter) */ static void le_intr_handler(struct adapter *adap) { + enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip); static const struct intr_info le_intr_info[] = { { LIPMISS_F, "LE LIP miss", -1, 0 }, { LIP0_F, "LE 0 LIP error", -1, 0 }, @@ -2709,7 +3079,18 @@ static void le_intr_handler(struct adapter *adap) { 0 } }; - if (t4_handle_intr_status(adap, LE_DB_INT_CAUSE_A, le_intr_info)) + static struct intr_info t6_le_intr_info[] = { + { T6_LIPMISS_F, "LE LIP miss", -1, 0 }, + { T6_LIP0_F, "LE 0 LIP error", -1, 0 }, + { TCAMINTPERR_F, "LE parity error", -1, 1 }, + { T6_UNKNOWNCMD_F, "LE unknown command", -1, 1 }, + { SSRAMINTPERR_F, "LE request queue parity error", -1, 1 }, + { 0 } + }; + + if (t4_handle_intr_status(adap, LE_DB_INT_CAUSE_A, + (chip <= CHELSIO_T5) ? + le_intr_info : t6_le_intr_info)) t4_fatal_err(adap); } @@ -2978,7 +3359,7 @@ int t4_slow_intr_handler(struct adapter *adapter) pcie_intr_handler(adapter); if (cause & MC_F) mem_intr_handler(adapter, MEM_MC); - if (!is_t4(adapter->params.chip) && (cause & MC1_S)) + if (is_t5(adapter->params.chip) && (cause & MC1_F)) mem_intr_handler(adapter, MEM_MC1); if (cause & EDC0_F) mem_intr_handler(adapter, MEM_EDC0); @@ -3024,17 +3405,18 @@ int t4_slow_intr_handler(struct adapter *adapter) */ void t4_intr_enable(struct adapter *adapter) { + u32 val = 0; u32 pf = SOURCEPF_G(t4_read_reg(adapter, PL_WHOAMI_A)); + if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) + val = ERR_DROPPED_DB_F | ERR_EGR_CTXT_PRIO_F | DBFIFO_HP_INT_F; t4_write_reg(adapter, SGE_INT_ENABLE3_A, ERR_CPL_EXCEED_IQE_SIZE_F | ERR_INVALID_CIDX_INC_F | ERR_CPL_OPCODE_0_F | - ERR_DROPPED_DB_F | ERR_DATA_CPL_ON_HIGH_QID1_F | + ERR_DATA_CPL_ON_HIGH_QID1_F | INGRESS_SIZE_ERR_F | ERR_DATA_CPL_ON_HIGH_QID0_F | ERR_BAD_DB_PIDX3_F | ERR_BAD_DB_PIDX2_F | ERR_BAD_DB_PIDX1_F | ERR_BAD_DB_PIDX0_F | ERR_ING_CTXT_PRIO_F | - ERR_EGR_CTXT_PRIO_F | INGRESS_SIZE_ERR_F | - DBFIFO_HP_INT_F | DBFIFO_LP_INT_F | - EGRESS_SIZE_ERR_F); + DBFIFO_LP_INT_F | EGRESS_SIZE_ERR_F | val); t4_write_reg(adapter, MYPF_REG(PL_PF_INT_ENABLE_A), PF_INTR_MASK); t4_set_reg_field(adapter, PL_INT_MAP0_A, 0, 1 << pf); } @@ -3248,11 +3630,29 @@ void t4_read_rss_key(struct adapter *adap, u32 *key) */ void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx) { + u8 rss_key_addr_cnt = 16; + u32 vrt = t4_read_reg(adap, TP_RSS_CONFIG_VRT_A); + + /* T6 and later: for KeyMode 3 (per-vf and per-vf scramble), + * allows access to key addresses 16-63 by using KeyWrAddrX + * as index[5:4](upper 2) into key table + */ + if ((CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) && + (vrt & KEYEXTEND_F) && (KEYMODE_G(vrt) == 3)) + rss_key_addr_cnt = 32; + t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10, TP_RSS_SECRET_KEY0_A); - if (idx >= 0 && idx < 16) - t4_write_reg(adap, TP_RSS_CONFIG_VRT_A, - KEYWRADDR_V(idx) | KEYWREN_F); + + if (idx >= 0 && idx < rss_key_addr_cnt) { + if (rss_key_addr_cnt > 16) + t4_write_reg(adap, TP_RSS_CONFIG_VRT_A, + KEYWRADDRX_V(idx >> 4) | + T6_VFWRADDR_V(idx) | KEYWREN_F); + else + t4_write_reg(adap, TP_RSS_CONFIG_VRT_A, + KEYWRADDR_V(idx) | KEYWREN_F); + } } /** @@ -3286,8 +3686,13 @@ void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index, { u32 vrt, mask, data; - mask = VFWRADDR_V(VFWRADDR_M); - data = VFWRADDR_V(index); + if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) { + mask = VFWRADDR_V(VFWRADDR_M); + data = VFWRADDR_V(index); + } else { + mask = T6_VFWRADDR_V(T6_VFWRADDR_M); + data = T6_VFWRADDR_V(index); + } /* Request that the index'th VF Table values be read into VFL/VFH. */ @@ -3355,18 +3760,18 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, if (v4) { t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, ARRAY_SIZE(val), TP_MIB_TCP_OUT_RST_A); - v4->tcpOutRsts = STAT(OUT_RST); - v4->tcpInSegs = STAT64(IN_SEG); - v4->tcpOutSegs = STAT64(OUT_SEG); - v4->tcpRetransSegs = STAT64(RXT_SEG); + v4->tcp_out_rsts = STAT(OUT_RST); + v4->tcp_in_segs = STAT64(IN_SEG); + v4->tcp_out_segs = STAT64(OUT_SEG); + v4->tcp_retrans_segs = STAT64(RXT_SEG); } if (v6) { t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, ARRAY_SIZE(val), TP_MIB_TCP_V6OUT_RST_A); - v6->tcpOutRsts = STAT(OUT_RST); - v6->tcpInSegs = STAT64(IN_SEG); - v6->tcpOutSegs = STAT64(OUT_SEG); - v6->tcpRetransSegs = STAT64(RXT_SEG); + v6->tcp_out_rsts = STAT(OUT_RST); + v6->tcp_in_segs = STAT64(IN_SEG); + v6->tcp_out_segs = STAT64(OUT_SEG); + v6->tcp_retrans_segs = STAT64(RXT_SEG); } #undef STAT64 #undef STAT @@ -3374,6 +3779,130 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, } /** + * t4_tp_get_err_stats - read TP's error MIB counters + * @adap: the adapter + * @st: holds the counter values + * + * Returns the values of TP's error counters. + */ +void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st) +{ + /* T6 and later has 2 channels */ + if (adap->params.arch.nchan == NCHAN) { + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->mac_in_errs, 12, TP_MIB_MAC_IN_ERR_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tnl_cong_drops, 8, + TP_MIB_TNL_CNG_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tnl_tx_drops, 4, + TP_MIB_TNL_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->ofld_vlan_drops, 4, + TP_MIB_OFD_VLN_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tcp6_in_errs, 4, + TP_MIB_TCP_V6IN_ERR_0_A); + } else { + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->mac_in_errs, 2, TP_MIB_MAC_IN_ERR_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->hdr_in_errs, 2, TP_MIB_HDR_IN_ERR_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tcp_in_errs, 2, TP_MIB_TCP_IN_ERR_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tnl_cong_drops, 2, + TP_MIB_TNL_CNG_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->ofld_chan_drops, 2, + TP_MIB_OFD_CHN_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tnl_tx_drops, 2, TP_MIB_TNL_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->ofld_vlan_drops, 2, + TP_MIB_OFD_VLN_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tcp6_in_errs, 2, TP_MIB_TCP_V6IN_ERR_0_A); + } + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + &st->ofld_no_neigh, 2, TP_MIB_OFD_ARP_DROP_A); +} + +/** + * t4_tp_get_cpl_stats - read TP's CPL MIB counters + * @adap: the adapter + * @st: holds the counter values + * + * Returns the values of TP's CPL counters. + */ +void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st) +{ + /* T6 and later has 2 channels */ + if (adap->params.arch.nchan == NCHAN) { + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->req, + 8, TP_MIB_CPL_IN_REQ_0_A); + } else { + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->req, + 2, TP_MIB_CPL_IN_REQ_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->rsp, + 2, TP_MIB_CPL_OUT_RSP_0_A); + } +} + +/** + * t4_tp_get_rdma_stats - read TP's RDMA MIB counters + * @adap: the adapter + * @st: holds the counter values + * + * Returns the values of TP's RDMA counters. + */ +void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st) +{ + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->rqe_dfr_pkt, + 2, TP_MIB_RQE_DFR_PKT_A); +} + +/** + * t4_get_fcoe_stats - read TP's FCoE MIB counters for a port + * @adap: the adapter + * @idx: the port index + * @st: holds the counter values + * + * Returns the values of TP's FCoE counters for the selected port. + */ +void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx, + struct tp_fcoe_stats *st) +{ + u32 val[2]; + + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->frames_ddp, + 1, TP_MIB_FCOE_DDP_0_A + idx); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->frames_drop, + 1, TP_MIB_FCOE_DROP_0_A + idx); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, + 2, TP_MIB_FCOE_BYTE_0_HI_A + 2 * idx); + st->octets_ddp = ((u64)val[0] << 32) | val[1]; +} + +/** + * t4_get_usm_stats - read TP's non-TCP DDP MIB counters + * @adap: the adapter + * @st: holds the counter values + * + * Returns the values of TP's counters for non-TCP directly-placed packets. + */ +void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st) +{ + u32 val[4]; + + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, 4, + TP_MIB_USM_PKTS_A); + st->frames = val[0]; + st->drops = val[1]; + st->octets = ((u64)val[2] << 32) | val[3]; +} + +/** * t4_read_mtu_tbl - returns the values in the HW path MTU table * @adap: the adapter * @mtus: where to store the MTU values @@ -3630,6 +4159,28 @@ const char *t4_get_port_type_description(enum fw_port_type port_type) } /** + * t4_get_port_stats_offset - collect port stats relative to a previous + * snapshot + * @adap: The adapter + * @idx: The port + * @stats: Current stats to fill + * @offset: Previous stats snapshot + */ +void t4_get_port_stats_offset(struct adapter *adap, int idx, + struct port_stats *stats, + struct port_stats *offset) +{ + u64 *s, *o; + int i; + + t4_get_port_stats(adap, idx, stats); + for (i = 0, s = (u64 *)stats, o = (u64 *)offset; + i < (sizeof(struct port_stats) / sizeof(u64)); + i++, s++, o++) + *s -= *o; +} + +/** * t4_get_port_stats - collect port statistics * @adap: the adapter * @idx: the port index @@ -3713,103 +4264,51 @@ void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p) } /** - * t4_wol_magic_enable - enable/disable magic packet WoL + * t4_get_lb_stats - collect loopback port statistics * @adap: the adapter - * @port: the physical port index - * @addr: MAC address expected in magic packets, %NULL to disable - * - * Enables/disables magic packet wake-on-LAN for the selected port. - */ -void t4_wol_magic_enable(struct adapter *adap, unsigned int port, - const u8 *addr) -{ - u32 mag_id_reg_l, mag_id_reg_h, port_cfg_reg; - - if (is_t4(adap->params.chip)) { - mag_id_reg_l = PORT_REG(port, XGMAC_PORT_MAGIC_MACID_LO); - mag_id_reg_h = PORT_REG(port, XGMAC_PORT_MAGIC_MACID_HI); - port_cfg_reg = PORT_REG(port, XGMAC_PORT_CFG2_A); - } else { - mag_id_reg_l = T5_PORT_REG(port, MAC_PORT_MAGIC_MACID_LO); - mag_id_reg_h = T5_PORT_REG(port, MAC_PORT_MAGIC_MACID_HI); - port_cfg_reg = T5_PORT_REG(port, MAC_PORT_CFG2_A); - } - - if (addr) { - t4_write_reg(adap, mag_id_reg_l, - (addr[2] << 24) | (addr[3] << 16) | - (addr[4] << 8) | addr[5]); - t4_write_reg(adap, mag_id_reg_h, - (addr[0] << 8) | addr[1]); - } - t4_set_reg_field(adap, port_cfg_reg, MAGICEN_F, - addr ? MAGICEN_F : 0); -} - -/** - * t4_wol_pat_enable - enable/disable pattern-based WoL - * @adap: the adapter - * @port: the physical port index - * @map: bitmap of which HW pattern filters to set - * @mask0: byte mask for bytes 0-63 of a packet - * @mask1: byte mask for bytes 64-127 of a packet - * @crc: Ethernet CRC for selected bytes - * @enable: enable/disable switch + * @idx: the loopback port index + * @p: the stats structure to fill * - * Sets the pattern filters indicated in @map to mask out the bytes - * specified in @mask0/@mask1 in received packets and compare the CRC of - * the resulting packet against @crc. If @enable is %true pattern-based - * WoL is enabled, otherwise disabled. + * Return HW statistics for the given loopback port. */ -int t4_wol_pat_enable(struct adapter *adap, unsigned int port, unsigned int map, - u64 mask0, u64 mask1, unsigned int crc, bool enable) +void t4_get_lb_stats(struct adapter *adap, int idx, struct lb_port_stats *p) { - int i; - u32 port_cfg_reg; - - if (is_t4(adap->params.chip)) - port_cfg_reg = PORT_REG(port, XGMAC_PORT_CFG2_A); - else - port_cfg_reg = T5_PORT_REG(port, MAC_PORT_CFG2_A); - - if (!enable) { - t4_set_reg_field(adap, port_cfg_reg, PATEN_F, 0); - return 0; - } - if (map > 0xff) - return -EINVAL; + u32 bgmap = t4_get_mps_bg_map(adap, idx); -#define EPIO_REG(name) \ +#define GET_STAT(name) \ + t4_read_reg64(adap, \ (is_t4(adap->params.chip) ? \ - PORT_REG(port, XGMAC_PORT_EPIO_##name##_A) : \ - T5_PORT_REG(port, MAC_PORT_EPIO_##name##_A)) - - t4_write_reg(adap, EPIO_REG(DATA1), mask0 >> 32); - t4_write_reg(adap, EPIO_REG(DATA2), mask1); - t4_write_reg(adap, EPIO_REG(DATA3), mask1 >> 32); - - for (i = 0; i < NWOL_PAT; i++, map >>= 1) { - if (!(map & 1)) - continue; + PORT_REG(idx, MPS_PORT_STAT_LB_PORT_##name##_L) : \ + T5_PORT_REG(idx, MPS_PORT_STAT_LB_PORT_##name##_L))) +#define GET_STAT_COM(name) t4_read_reg64(adap, MPS_STAT_##name##_L) - /* write byte masks */ - t4_write_reg(adap, EPIO_REG(DATA0), mask0); - t4_write_reg(adap, EPIO_REG(OP), ADDRESS_V(i) | EPIOWR_F); - t4_read_reg(adap, EPIO_REG(OP)); /* flush */ - if (t4_read_reg(adap, EPIO_REG(OP)) & SF_BUSY_F) - return -ETIMEDOUT; - - /* write CRC */ - t4_write_reg(adap, EPIO_REG(DATA0), crc); - t4_write_reg(adap, EPIO_REG(OP), ADDRESS_V(i + 32) | EPIOWR_F); - t4_read_reg(adap, EPIO_REG(OP)); /* flush */ - if (t4_read_reg(adap, EPIO_REG(OP)) & SF_BUSY_F) - return -ETIMEDOUT; - } -#undef EPIO_REG + p->octets = GET_STAT(BYTES); + p->frames = GET_STAT(FRAMES); + p->bcast_frames = GET_STAT(BCAST); + p->mcast_frames = GET_STAT(MCAST); + p->ucast_frames = GET_STAT(UCAST); + p->error_frames = GET_STAT(ERROR); + + p->frames_64 = GET_STAT(64B); + p->frames_65_127 = GET_STAT(65B_127B); + p->frames_128_255 = GET_STAT(128B_255B); + p->frames_256_511 = GET_STAT(256B_511B); + p->frames_512_1023 = GET_STAT(512B_1023B); + p->frames_1024_1518 = GET_STAT(1024B_1518B); + p->frames_1519_max = GET_STAT(1519B_MAX); + p->drop = GET_STAT(DROP_FRAMES); + + p->ovflow0 = (bgmap & 1) ? GET_STAT_COM(RX_BG_0_LB_DROP_FRAME) : 0; + p->ovflow1 = (bgmap & 2) ? GET_STAT_COM(RX_BG_1_LB_DROP_FRAME) : 0; + p->ovflow2 = (bgmap & 4) ? GET_STAT_COM(RX_BG_2_LB_DROP_FRAME) : 0; + p->ovflow3 = (bgmap & 8) ? GET_STAT_COM(RX_BG_3_LB_DROP_FRAME) : 0; + p->trunc0 = (bgmap & 1) ? GET_STAT_COM(RX_BG_0_LB_TRUNC_FRAME) : 0; + p->trunc1 = (bgmap & 2) ? GET_STAT_COM(RX_BG_1_LB_TRUNC_FRAME) : 0; + p->trunc2 = (bgmap & 4) ? GET_STAT_COM(RX_BG_2_LB_TRUNC_FRAME) : 0; + p->trunc3 = (bgmap & 8) ? GET_STAT_COM(RX_BG_3_LB_TRUNC_FRAME) : 0; - t4_set_reg_field(adap, PORT_REG(port, XGMAC_PORT_CFG2_A), 0, PATEN_F); - return 0; +#undef GET_STAT +#undef GET_STAT_COM } /* t4_mk_filtdelwr - create a delete filter WR @@ -4798,45 +5297,71 @@ int t4_alloc_mac_filt(struct adapter *adap, unsigned int mbox, unsigned int viid, bool free, unsigned int naddr, const u8 **addr, u16 *idx, u64 *hash, bool sleep_ok) { - int i, ret; + int offset, ret = 0; struct fw_vi_mac_cmd c; - struct fw_vi_mac_exact *p; - unsigned int max_naddr = is_t4(adap->params.chip) ? - NUM_MPS_CLS_SRAM_L_INSTANCES : - NUM_MPS_T5_CLS_SRAM_L_INSTANCES; + unsigned int nfilters = 0; + unsigned int max_naddr = adap->params.arch.mps_tcam_size; + unsigned int rem = naddr; - if (naddr > 7) + if (naddr > max_naddr) return -EINVAL; - memset(&c, 0, sizeof(c)); - c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) | - FW_CMD_REQUEST_F | FW_CMD_WRITE_F | - (free ? FW_CMD_EXEC_F : 0) | - FW_VI_MAC_CMD_VIID_V(viid)); - c.freemacs_to_len16 = cpu_to_be32(FW_VI_MAC_CMD_FREEMACS_V(free) | - FW_CMD_LEN16_V((naddr + 2) / 2)); - - for (i = 0, p = c.u.exact; i < naddr; i++, p++) { - p->valid_to_idx = - cpu_to_be16(FW_VI_MAC_CMD_VALID_F | - FW_VI_MAC_CMD_IDX_V(FW_VI_MAC_ADD_MAC)); - memcpy(p->macaddr, addr[i], sizeof(p->macaddr)); - } + for (offset = 0; offset < naddr ; /**/) { + unsigned int fw_naddr = (rem < ARRAY_SIZE(c.u.exact) ? + rem : ARRAY_SIZE(c.u.exact)); + size_t len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd, + u.exact[fw_naddr]), 16); + struct fw_vi_mac_exact *p; + int i; - ret = t4_wr_mbox_meat(adap, mbox, &c, sizeof(c), &c, sleep_ok); - if (ret) - return ret; + memset(&c, 0, sizeof(c)); + c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) | + FW_CMD_REQUEST_F | + FW_CMD_WRITE_F | + FW_CMD_EXEC_V(free) | + FW_VI_MAC_CMD_VIID_V(viid)); + c.freemacs_to_len16 = + cpu_to_be32(FW_VI_MAC_CMD_FREEMACS_V(free) | + FW_CMD_LEN16_V(len16)); + + for (i = 0, p = c.u.exact; i < fw_naddr; i++, p++) { + p->valid_to_idx = + cpu_to_be16(FW_VI_MAC_CMD_VALID_F | + FW_VI_MAC_CMD_IDX_V( + FW_VI_MAC_ADD_MAC)); + memcpy(p->macaddr, addr[offset + i], + sizeof(p->macaddr)); + } + + /* It's okay if we run out of space in our MAC address arena. + * Some of the addresses we submit may get stored so we need + * to run through the reply to see what the results were ... + */ + ret = t4_wr_mbox_meat(adap, mbox, &c, sizeof(c), &c, sleep_ok); + if (ret && ret != -FW_ENOMEM) + break; - for (i = 0, p = c.u.exact; i < naddr; i++, p++) { - u16 index = FW_VI_MAC_CMD_IDX_G(be16_to_cpu(p->valid_to_idx)); + for (i = 0, p = c.u.exact; i < fw_naddr; i++, p++) { + u16 index = FW_VI_MAC_CMD_IDX_G( + be16_to_cpu(p->valid_to_idx)); + + if (idx) + idx[offset + i] = (index >= max_naddr ? + 0xffff : index); + if (index < max_naddr) + nfilters++; + else if (hash) + *hash |= (1ULL << + hash_mac_addr(addr[offset + i])); + } - if (idx) - idx[i] = index >= max_naddr ? 0xffff : index; - if (index < max_naddr) - ret++; - else if (hash) - *hash |= (1ULL << hash_mac_addr(addr[i])); + free = false; + offset += fw_naddr; + rem -= fw_naddr; } + + if (ret == 0 || ret == -FW_ENOMEM) + ret = nfilters; return ret; } @@ -4865,9 +5390,7 @@ int t4_change_mac(struct adapter *adap, unsigned int mbox, unsigned int viid, int ret, mode; struct fw_vi_mac_cmd c; struct fw_vi_mac_exact *p = c.u.exact; - unsigned int max_mac_addr = is_t4(adap->params.chip) ? - NUM_MPS_CLS_SRAM_L_INSTANCES : - NUM_MPS_T5_CLS_SRAM_L_INSTANCES; + unsigned int max_mac_addr = adap->params.arch.mps_tcam_size; if (idx < 0) /* new allocation */ idx = persist ? FW_VI_MAC_ADD_PERSIST_MAC : FW_VI_MAC_ADD_MAC; @@ -5276,9 +5799,30 @@ int t4_prep_adapter(struct adapter *adapter) switch (ver) { case CHELSIO_T4: adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T4, pl_rev); + adapter->params.arch.sge_fl_db = DBPRIO_F; + adapter->params.arch.mps_tcam_size = + NUM_MPS_CLS_SRAM_L_INSTANCES; + adapter->params.arch.mps_rplc_size = 128; + adapter->params.arch.nchan = NCHAN; + adapter->params.arch.vfcount = 128; break; case CHELSIO_T5: adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T5, pl_rev); + adapter->params.arch.sge_fl_db = DBPRIO_F | DBTYPE_F; + adapter->params.arch.mps_tcam_size = + NUM_MPS_T5_CLS_SRAM_L_INSTANCES; + adapter->params.arch.mps_rplc_size = 128; + adapter->params.arch.nchan = NCHAN; + adapter->params.arch.vfcount = 128; + break; + case CHELSIO_T6: + adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T6, pl_rev); + adapter->params.arch.sge_fl_db = 0; + adapter->params.arch.mps_tcam_size = + NUM_MPS_T5_CLS_SRAM_L_INSTANCES; + adapter->params.arch.mps_rplc_size = 256; + adapter->params.arch.nchan = 2; + adapter->params.arch.vfcount = 256; break; default: dev_err(adapter->pdev_dev, "Device %d is not supported\n", @@ -5299,7 +5843,7 @@ int t4_prep_adapter(struct adapter *adapter) } /** - * cxgb4_t4_bar2_sge_qregs - return BAR2 SGE Queue register information + * t4_bar2_sge_qregs - return BAR2 SGE Queue register information * @adapter: the adapter * @qid: the Queue ID * @qtype: the Ingress or Egress type for @qid @@ -5323,7 +5867,7 @@ int t4_prep_adapter(struct adapter *adapter) * Write Combining Doorbell Buffer. If the BAR2 Queue ID is not 0, * then these "Inferred Queue ID" register may not be used. */ -int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter, +int t4_bar2_sge_qregs(struct adapter *adapter, unsigned int qid, enum t4_bar2_qtype qtype, u64 *pbar2_qoffset, @@ -5457,13 +6001,13 @@ int t4_init_sge_params(struct adapter *adapter) */ hps = t4_read_reg(adapter, SGE_HOST_PAGE_SIZE_A); s_hps = (HOSTPAGESIZEPF0_S + - (HOSTPAGESIZEPF1_S - HOSTPAGESIZEPF0_S) * adapter->fn); + (HOSTPAGESIZEPF1_S - HOSTPAGESIZEPF0_S) * adapter->pf); sge_params->hps = ((hps >> s_hps) & HOSTPAGESIZEPF0_M); /* Extract the SGE Egress and Ingess Queues Per Page for our PF. */ s_qpp = (QUEUESPERPAGEPF0_S + - (QUEUESPERPAGEPF1_S - QUEUESPERPAGEPF0_S) * adapter->fn); + (QUEUESPERPAGEPF1_S - QUEUESPERPAGEPF0_S) * adapter->pf); qpp = t4_read_reg(adapter, SGE_EGRESS_QUEUES_PER_PAGE_PF_A); sge_params->eq_qpp = ((qpp >> s_qpp) & QUEUESPERPAGEPF0_M); qpp = t4_read_reg(adapter, SGE_INGRESS_QUEUES_PER_PAGE_PF_A); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h index 88067d9..f9a2cb1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h @@ -52,8 +52,6 @@ enum { MBOX_LEN = 64, /* mailbox size in bytes */ TRACE_LEN = 112, /* length of trace data and mask */ FILTER_OPT_LEN = 36, /* filter tuple width for optional components */ - NWOL_PAT = 8, /* # of WoL patterns */ - WOL_PAT_LEN = 128, /* length of WoL patterns */ }; enum { diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index d90f8a0..132cb8f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -686,6 +686,9 @@ struct cpl_tx_pkt { #define TXPKT_ETHHDR_LEN_S 34 #define TXPKT_ETHHDR_LEN_V(x) ((__u64)(x) << TXPKT_ETHHDR_LEN_S) +#define T6_TXPKT_ETHHDR_LEN_S 32 +#define T6_TXPKT_ETHHDR_LEN_V(x) ((__u64)(x) << T6_TXPKT_ETHHDR_LEN_S) + #define TXPKT_CSUM_TYPE_S 40 #define TXPKT_CSUM_TYPE_V(x) ((__u64)(x) << TXPKT_CSUM_TYPE_S) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index 326674b..af3462d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -418,6 +418,20 @@ #define SGE_INGRESS_QUEUES_PER_PAGE_PF_A 0x10f4 #define SGE_INGRESS_QUEUES_PER_PAGE_VF_A 0x10f8 +#define SGE_ERROR_STATS_A 0x1100 + +#define UNCAPTURED_ERROR_S 18 +#define UNCAPTURED_ERROR_V(x) ((x) << UNCAPTURED_ERROR_S) +#define UNCAPTURED_ERROR_F UNCAPTURED_ERROR_V(1U) + +#define ERROR_QID_VALID_S 17 +#define ERROR_QID_VALID_V(x) ((x) << ERROR_QID_VALID_S) +#define ERROR_QID_VALID_F ERROR_QID_VALID_V(1U) + +#define ERROR_QID_S 0 +#define ERROR_QID_M 0x1ffffU +#define ERROR_QID_G(x) (((x) >> ERROR_QID_S) & ERROR_QID_M) + #define HP_INT_THRESH_S 28 #define HP_INT_THRESH_M 0xfU #define HP_INT_THRESH_V(x) ((x) << HP_INT_THRESH_S) @@ -448,8 +462,13 @@ #define SGE_STAT_MATCH_A 0x10e8 #define SGE_STAT_CFG_A 0x10ec +#define STATMODE_S 2 +#define STATMODE_V(x) ((x) << STATMODE_S) + #define STATSOURCE_T5_S 9 +#define STATSOURCE_T5_M 0xfU #define STATSOURCE_T5_V(x) ((x) << STATSOURCE_T5_S) +#define STATSOURCE_T5_G(x) (((x) >> STATSOURCE_T5_S) & STATSOURCE_T5_M) #define SGE_DBFIFO_STATUS2_A 0x1118 @@ -705,6 +724,10 @@ #define REGISTER_S 0 #define REGISTER_V(x) ((x) << REGISTER_S) +#define T6_ENABLE_S 31 +#define T6_ENABLE_V(x) ((x) << T6_ENABLE_S) +#define T6_ENABLE_F T6_ENABLE_V(1U) + #define PFNUM_S 0 #define PFNUM_V(x) ((x) << PFNUM_S) @@ -1399,6 +1422,8 @@ #define CSUM_HAS_PSEUDO_HDR_F CSUM_HAS_PSEUDO_HDR_V(1U) #define TP_MIB_MAC_IN_ERR_0_A 0x0 +#define TP_MIB_HDR_IN_ERR_0_A 0x4 +#define TP_MIB_TCP_IN_ERR_0_A 0x8 #define TP_MIB_TCP_OUT_RST_A 0xc #define TP_MIB_TCP_IN_SEG_HI_A 0x10 #define TP_MIB_TCP_IN_SEG_LO_A 0x11 @@ -1407,11 +1432,19 @@ #define TP_MIB_TCP_RXT_SEG_HI_A 0x14 #define TP_MIB_TCP_RXT_SEG_LO_A 0x15 #define TP_MIB_TNL_CNG_DROP_0_A 0x18 +#define TP_MIB_OFD_CHN_DROP_0_A 0x1c #define TP_MIB_TCP_V6IN_ERR_0_A 0x28 #define TP_MIB_TCP_V6OUT_RST_A 0x2c #define TP_MIB_OFD_ARP_DROP_A 0x36 +#define TP_MIB_CPL_IN_REQ_0_A 0x38 +#define TP_MIB_CPL_OUT_RSP_0_A 0x3c #define TP_MIB_TNL_DROP_0_A 0x44 +#define TP_MIB_FCOE_DDP_0_A 0x48 +#define TP_MIB_FCOE_DROP_0_A 0x4c +#define TP_MIB_FCOE_BYTE_0_HI_A 0x50 #define TP_MIB_OFD_VLN_DROP_0_A 0x58 +#define TP_MIB_USM_PKTS_A 0x5c +#define TP_MIB_RQE_DFR_PKT_A 0x64 #define ULP_TX_INT_CAUSE_A 0x8dcc @@ -1572,6 +1605,7 @@ #define MPS_PORT_STAT_LB_PORT_1519B_MAX_L 0x520 #define MPS_PORT_STAT_LB_PORT_1519B_MAX_H 0x524 #define MPS_PORT_STAT_LB_PORT_DROP_FRAMES 0x528 +#define MPS_PORT_STAT_LB_PORT_DROP_FRAMES_L 0x528 #define MPS_PORT_STAT_RX_PORT_BYTES_L 0x540 #define MPS_PORT_STAT_RX_PORT_BYTES_H 0x544 #define MPS_PORT_STAT_RX_PORT_FRAMES_L 0x548 @@ -2054,6 +2088,11 @@ #define VFLKPIDX_M 0xffU #define VFLKPIDX_G(x) (((x) >> VFLKPIDX_S) & VFLKPIDX_M) +#define T6_VFWRADDR_S 8 +#define T6_VFWRADDR_M 0xffU +#define T6_VFWRADDR_V(x) ((x) << T6_VFWRADDR_S) +#define T6_VFWRADDR_G(x) (((x) >> T6_VFWRADDR_S) & T6_VFWRADDR_M) + #define TP_RSS_CONFIG_CNG_A 0x7e04 #define TP_RSS_SECRET_KEY0_A 0x40 #define TP_RSS_PF0_CONFIG_A 0x30 @@ -2175,7 +2214,28 @@ #define MPS_RX_PERR_INT_CAUSE_A 0x11074 #define MPS_CLS_TCAM_Y_L_A 0xf000 +#define MPS_CLS_TCAM_DATA0_A 0xf000 +#define MPS_CLS_TCAM_DATA1_A 0xf004 + +#define DMACH_S 0 +#define DMACH_M 0xffffU +#define DMACH_G(x) (((x) >> DMACH_S) & DMACH_M) + #define MPS_CLS_TCAM_X_L_A 0xf008 +#define MPS_CLS_TCAM_DATA2_CTL_A 0xf008 + +#define CTLCMDTYPE_S 31 +#define CTLCMDTYPE_V(x) ((x) << CTLCMDTYPE_S) +#define CTLCMDTYPE_F CTLCMDTYPE_V(1U) + +#define CTLTCAMSEL_S 25 +#define CTLTCAMSEL_V(x) ((x) << CTLTCAMSEL_S) + +#define CTLTCAMINDEX_S 17 +#define CTLTCAMINDEX_V(x) ((x) << CTLTCAMINDEX_S) + +#define CTLXYBITSEL_S 16 +#define CTLXYBITSEL_V(x) ((x) << CTLXYBITSEL_S) #define MPS_CLS_TCAM_Y_L(idx) (MPS_CLS_TCAM_Y_L_A + (idx) * 16) #define NUM_MPS_CLS_TCAM_Y_L_INSTANCES 512 @@ -2184,6 +2244,45 @@ #define NUM_MPS_CLS_TCAM_X_L_INSTANCES 512 #define MPS_CLS_SRAM_L_A 0xe000 + +#define T6_MULTILISTEN0_S 26 + +#define T6_SRAM_PRIO3_S 23 +#define T6_SRAM_PRIO3_M 0x7U +#define T6_SRAM_PRIO3_G(x) (((x) >> T6_SRAM_PRIO3_S) & T6_SRAM_PRIO3_M) + +#define T6_SRAM_PRIO2_S 20 +#define T6_SRAM_PRIO2_M 0x7U +#define T6_SRAM_PRIO2_G(x) (((x) >> T6_SRAM_PRIO2_S) & T6_SRAM_PRIO2_M) + +#define T6_SRAM_PRIO1_S 17 +#define T6_SRAM_PRIO1_M 0x7U +#define T6_SRAM_PRIO1_G(x) (((x) >> T6_SRAM_PRIO1_S) & T6_SRAM_PRIO1_M) + +#define T6_SRAM_PRIO0_S 14 +#define T6_SRAM_PRIO0_M 0x7U +#define T6_SRAM_PRIO0_G(x) (((x) >> T6_SRAM_PRIO0_S) & T6_SRAM_PRIO0_M) + +#define T6_SRAM_VLD_S 13 +#define T6_SRAM_VLD_V(x) ((x) << T6_SRAM_VLD_S) +#define T6_SRAM_VLD_F T6_SRAM_VLD_V(1U) + +#define T6_REPLICATE_S 12 +#define T6_REPLICATE_V(x) ((x) << T6_REPLICATE_S) +#define T6_REPLICATE_F T6_REPLICATE_V(1U) + +#define T6_PF_S 9 +#define T6_PF_M 0x7U +#define T6_PF_G(x) (((x) >> T6_PF_S) & T6_PF_M) + +#define T6_VF_VALID_S 8 +#define T6_VF_VALID_V(x) ((x) << T6_VF_VALID_S) +#define T6_VF_VALID_F T6_VF_VALID_V(1U) + +#define T6_VF_S 0 +#define T6_VF_M 0xffU +#define T6_VF_G(x) (((x) >> T6_VF_S) & T6_VF_M) + #define MPS_CLS_SRAM_H_A 0xe004 #define MPS_CLS_SRAM_L(idx) (MPS_CLS_SRAM_L_A + (idx) * 8) @@ -2433,6 +2532,8 @@ #define CIM_F CIM_V(1U) #define MC1_S 31 +#define MC1_V(x) ((x) << MC1_S) +#define MC1_F MC1_V(1U) #define PL_INT_ENABLE_A 0x19410 #define PL_INT_MAP0_A 0x19414 @@ -2463,6 +2564,18 @@ #define REV_V(x) ((x) << REV_S) #define REV_G(x) (((x) >> REV_S) & REV_M) +#define T6_UNKNOWNCMD_S 3 +#define T6_UNKNOWNCMD_V(x) ((x) << T6_UNKNOWNCMD_S) +#define T6_UNKNOWNCMD_F T6_UNKNOWNCMD_V(1U) + +#define T6_LIP0_S 2 +#define T6_LIP0_V(x) ((x) << T6_LIP0_S) +#define T6_LIP0_F T6_LIP0_V(1U) + +#define T6_LIPMISS_S 1 +#define T6_LIPMISS_V(x) ((x) << T6_LIPMISS_S) +#define T6_LIPMISS_F T6_LIPMISS_V(1U) + #define LE_DB_INT_CAUSE_A 0x19c3c #define REQQPARERR_S 16 @@ -2485,6 +2598,14 @@ #define LIP0_V(x) ((x) << LIP0_S) #define LIP0_F LIP0_V(1U) +#define TCAMINTPERR_S 13 +#define TCAMINTPERR_V(x) ((x) << TCAMINTPERR_S) +#define TCAMINTPERR_F TCAMINTPERR_V(1U) + +#define SSRAMINTPERR_S 10 +#define SSRAMINTPERR_V(x) ((x) << SSRAMINTPERR_S) +#define SSRAMINTPERR_F SSRAMINTPERR_V(1U) + #define NCSI_INT_CAUSE_A 0x1a0d8 #define CIM_DM_PRTY_ERR_S 8 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h index 72ec1f9..7bdee3b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h @@ -63,6 +63,7 @@ #define FETCHBURSTMIN_64B_X 2 +#define FETCHBURSTMAX_256B_X 2 #define FETCHBURSTMAX_512B_X 3 #define HOSTFCMODE_STATUS_PAGE_X 2 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 0848317..aceb1e8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -788,15 +788,27 @@ struct fw_ldst_cmd { __be16 vctl; __be16 rval; } mdio; - struct fw_ldst_mps { - __be16 fid_ctl; - __be16 rplcpf_pkd; - __be32 rplc127_96; - __be32 rplc95_64; - __be32 rplc63_32; - __be32 rplc31_0; - __be32 atrb; - __be16 vlan[16]; + union fw_ldst_mps { + struct fw_ldst_mps_rplc { + __be16 fid_idx; + __be16 rplcpf_pkd; + __be32 rplc255_224; + __be32 rplc223_192; + __be32 rplc191_160; + __be32 rplc159_128; + __be32 rplc127_96; + __be32 rplc95_64; + __be32 rplc63_32; + __be32 rplc31_0; + } rplc; + struct fw_ldst_mps_atrb { + __be16 fid_mpsid; + __be16 r2[3]; + __be32 r3[2]; + __be32 r4; + __be32 atrb; + __be16 vlan[16]; + } atrb; } mps; struct fw_ldst_func { u8 access_ctl; @@ -831,8 +843,8 @@ struct fw_ldst_cmd { #define FW_LDST_CMD_FID_S 15 #define FW_LDST_CMD_FID_V(x) ((x) << FW_LDST_CMD_FID_S) -#define FW_LDST_CMD_CTL_S 0 -#define FW_LDST_CMD_CTL_V(x) ((x) << FW_LDST_CMD_CTL_S) +#define FW_LDST_CMD_IDX_S 0 +#define FW_LDST_CMD_IDX_V(x) ((x) << FW_LDST_CMD_IDX_S) #define FW_LDST_CMD_RPLCPF_S 0 #define FW_LDST_CMD_RPLCPF_V(x) ((x) << FW_LDST_CMD_RPLCPF_S) @@ -2536,13 +2548,8 @@ enum fw_port_mod_sub_type { FW_PORT_MOD_SUB_TYPE_TWINAX_7 = 0xC, }; -/* port stats */ -#define FW_NUM_PORT_STATS 50 -#define FW_NUM_PORT_TX_STATS 23 -#define FW_NUM_PORT_RX_STATS 27 - enum fw_port_stats_tx_index { - FW_STAT_TX_PORT_BYTES_IX, + FW_STAT_TX_PORT_BYTES_IX = 0, FW_STAT_TX_PORT_FRAMES_IX, FW_STAT_TX_PORT_BCAST_IX, FW_STAT_TX_PORT_MCAST_IX, @@ -2564,11 +2571,12 @@ enum fw_port_stats_tx_index { FW_STAT_TX_PORT_PPP4_IX, FW_STAT_TX_PORT_PPP5_IX, FW_STAT_TX_PORT_PPP6_IX, - FW_STAT_TX_PORT_PPP7_IX + FW_STAT_TX_PORT_PPP7_IX, + FW_NUM_PORT_TX_STATS }; enum fw_port_stat_rx_index { - FW_STAT_RX_PORT_BYTES_IX, + FW_STAT_RX_PORT_BYTES_IX = 0, FW_STAT_RX_PORT_FRAMES_IX, FW_STAT_RX_PORT_BCAST_IX, FW_STAT_RX_PORT_MCAST_IX, @@ -2594,9 +2602,14 @@ enum fw_port_stat_rx_index { FW_STAT_RX_PORT_PPP5_IX, FW_STAT_RX_PORT_PPP6_IX, FW_STAT_RX_PORT_PPP7_IX, - FW_STAT_RX_PORT_LESS_64B_IX + FW_STAT_RX_PORT_LESS_64B_IX, + FW_STAT_RX_PORT_MAC_ERROR_IX, + FW_NUM_PORT_RX_STATS }; +/* port stats */ +#define FW_NUM_PORT_STATS (FW_NUM_PORT_TX_STATS + FW_NUM_PORT_RX_STATS) + struct fw_port_stats_cmd { __be32 op_to_portid; __be32 retval_len16; @@ -3025,7 +3038,8 @@ struct fw_hdr { enum fw_hdr_chip { FW_HDR_CHIP_T4, - FW_HDR_CHIP_T5 + FW_HDR_CHIP_T5, + FW_HDR_CHIP_T6 }; #define FW_HDR_FW_VER_MAJOR_S 24 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h index b9d1cba..32b2135 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h @@ -45,4 +45,9 @@ #define T5FW_VERSION_MICRO 0x20 #define T5FW_VERSION_BUILD 0x00 +#define T6FW_VERSION_MAJOR 0x01 +#define T6FW_VERSION_MINOR 0x0D +#define T6FW_VERSION_MICRO 0x2D +#define T6FW_VERSION_BUILD 0x00 + #endif diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index 2e41d15..ad53e5a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -524,7 +524,7 @@ static void unmap_rx_buf(struct adapter *adapter, struct sge_fl *fl) */ static inline void ring_fl_db(struct adapter *adapter, struct sge_fl *fl) { - u32 val; + u32 val = adapter->params.arch.sge_fl_db; /* The SGE keeps track of its Producer and Consumer Indices in terms * of Egress Queue Units so we can only tell it about integral numbers @@ -532,11 +532,9 @@ static inline void ring_fl_db(struct adapter *adapter, struct sge_fl *fl) */ if (fl->pend_cred >= FL_PER_EQ_UNIT) { if (is_t4(adapter->params.chip)) - val = PIDX_V(fl->pend_cred / FL_PER_EQ_UNIT); + val |= PIDX_V(fl->pend_cred / FL_PER_EQ_UNIT); else - val = PIDX_T5_V(fl->pend_cred / FL_PER_EQ_UNIT) | - DBTYPE_F; - val |= DBPRIO_F; + val |= PIDX_T5_V(fl->pend_cred / FL_PER_EQ_UNIT); /* Make sure all memory writes to the Free List queue are * committed before we tell the hardware about them. @@ -1084,7 +1082,7 @@ static void inline_tx_skb(const struct sk_buff *skb, const struct sge_txq *tq, * Figure out what HW csum a packet wants and return the appropriate control * bits. */ -static u64 hwcsum(const struct sk_buff *skb) +static u64 hwcsum(enum chip_type chip, const struct sk_buff *skb) { int csum_type; const struct iphdr *iph = ip_hdr(skb); @@ -1116,11 +1114,16 @@ nocsum: goto nocsum; } - if (likely(csum_type >= TX_CSUM_TCPIP)) - return TXPKT_CSUM_TYPE_V(csum_type) | - TXPKT_IPHDR_LEN_V(skb_network_header_len(skb)) | - TXPKT_ETHHDR_LEN_V(skb_network_offset(skb) - ETH_HLEN); - else { + if (likely(csum_type >= TX_CSUM_TCPIP)) { + u64 hdr_len = TXPKT_IPHDR_LEN_V(skb_network_header_len(skb)); + int eth_hdr_len = skb_network_offset(skb) - ETH_HLEN; + + if (chip <= CHELSIO_T5) + hdr_len |= TXPKT_ETHHDR_LEN_V(eth_hdr_len); + else + hdr_len |= T6_TXPKT_ETHHDR_LEN_V(eth_hdr_len); + return TXPKT_CSUM_TYPE_V(csum_type) | hdr_len; + } else { int start = skb_transport_offset(skb); return TXPKT_CSUM_TYPE_V(csum_type) | @@ -1308,10 +1311,15 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev) * accounting. */ cpl = (void *)(lso + 1); - cntrl = (TXPKT_CSUM_TYPE_V(v6 ? + + if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) + cntrl = TXPKT_ETHHDR_LEN_V(eth_xtra_len); + else + cntrl = T6_TXPKT_ETHHDR_LEN_V(eth_xtra_len); + + cntrl |= TXPKT_CSUM_TYPE_V(v6 ? TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) | - TXPKT_IPHDR_LEN_V(l3hdr_len) | - TXPKT_ETHHDR_LEN_V(eth_xtra_len)); + TXPKT_IPHDR_LEN_V(l3hdr_len); txq->tso++; txq->tx_cso += ssi->gso_segs; } else { @@ -1328,7 +1336,8 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev) */ cpl = (void *)(wr + 1); if (skb->ip_summed == CHECKSUM_PARTIAL) { - cntrl = hwcsum(skb) | TXPKT_IPCSUM_DIS_F; + cntrl = hwcsum(adapter->params.chip, skb) | + TXPKT_IPCSUM_DIS_F; txq->tx_cso++; } else cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F; @@ -2162,8 +2171,8 @@ static void __iomem *bar2_address(struct adapter *adapter, u64 bar2_qoffset; int ret; - ret = t4_bar2_sge_qregs(adapter, qid, qtype, - &bar2_qoffset, pbar2_qid); + ret = t4vf_bar2_sge_qregs(adapter, qid, qtype, + &bar2_qoffset, pbar2_qid); if (ret) return NULL; @@ -2247,6 +2256,8 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq, cmd.iqaddr = cpu_to_be64(rspq->phys_addr); if (fl) { + enum chip_type chip = + CHELSIO_CHIP_VERSION(adapter->params.chip); /* * Allocate the ring for the hardware free list (with space * for its status page) along with the associated software @@ -2286,7 +2297,9 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq, cmd.fl0dcaen_to_fl0cidxfthresh = cpu_to_be16( FW_IQ_CMD_FL0FBMIN_V(SGE_FETCHBURSTMIN_64B) | - FW_IQ_CMD_FL0FBMAX_V(SGE_FETCHBURSTMAX_512B)); + FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ? + FETCHBURSTMAX_512B_X : + FETCHBURSTMAX_256B_X)); cmd.fl0size = cpu_to_be16(flsz); cmd.fl0addr = cpu_to_be64(fl->addr); } diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h index b9debb4..88b8981b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h @@ -51,6 +51,7 @@ */ #define CHELSIO_T4 0x4 #define CHELSIO_T5 0x5 +#define CHELSIO_T6 0x6 enum chip_type { T4_A1 = CHELSIO_CHIP_CODE(CHELSIO_T4, 1), @@ -156,6 +157,12 @@ struct vpd_params { u32 cclk; /* Core Clock (KHz) */ }; +/* Stores chip specific parameters */ +struct arch_specific_params { + u32 sge_fl_db; + u16 mps_tcam_size; +}; + /* * Global Receive Side Scaling (RSS) parameters in host-native format. */ @@ -215,6 +222,7 @@ struct adapter_params { struct vpd_params vpd; /* Vital Product Data */ struct rss_params rss; /* Receive Side Scaling */ struct vf_resources vfres; /* Virtual Function Resource limits */ + struct arch_specific_params arch; /* chip specific params */ enum chip_type chip; /* chip code */ u8 nports; /* # of Ethernet "ports" */ }; @@ -284,11 +292,11 @@ int t4vf_fw_reset(struct adapter *); int t4vf_set_params(struct adapter *, unsigned int, const u32 *, const u32 *); enum t4_bar2_qtype { T4_BAR2_QTYPE_EGRESS, T4_BAR2_QTYPE_INGRESS }; -int t4_bar2_sge_qregs(struct adapter *adapter, - unsigned int qid, - enum t4_bar2_qtype qtype, - u64 *pbar2_qoffset, - unsigned int *pbar2_qid); +int t4vf_bar2_sge_qregs(struct adapter *adapter, + unsigned int qid, + enum t4_bar2_qtype qtype, + u64 *pbar2_qoffset, + unsigned int *pbar2_qid); int t4vf_get_sge_params(struct adapter *); int t4vf_get_vpd_params(struct adapter *); diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index 966ee90..0db6dc9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -428,7 +428,7 @@ int t4vf_set_params(struct adapter *adapter, unsigned int nparams, } /** - * t4_bar2_sge_qregs - return BAR2 SGE Queue register information + * t4vf_bar2_sge_qregs - return BAR2 SGE Queue register information * @adapter: the adapter * @qid: the Queue ID * @qtype: the Ingress or Egress type for @qid @@ -452,11 +452,11 @@ int t4vf_set_params(struct adapter *adapter, unsigned int nparams, * Write Combining Doorbell Buffer. If the BAR2 Queue ID is not 0, * then these "Inferred Queue ID" register may not be used. */ -int t4_bar2_sge_qregs(struct adapter *adapter, - unsigned int qid, - enum t4_bar2_qtype qtype, - u64 *pbar2_qoffset, - unsigned int *pbar2_qid) +int t4vf_bar2_sge_qregs(struct adapter *adapter, + unsigned int qid, + enum t4_bar2_qtype qtype, + u64 *pbar2_qoffset, + unsigned int *pbar2_qid) { unsigned int page_shift, page_size, qpp_shift, qpp_mask; u64 bar2_page_offset, bar2_qoffset; @@ -1191,9 +1191,7 @@ int t4vf_alloc_mac_filt(struct adapter *adapter, unsigned int viid, bool free, unsigned nfilters = 0; unsigned int rem = naddr; struct fw_vi_mac_cmd cmd, rpl; - unsigned int max_naddr = is_t4(adapter->params.chip) ? - NUM_MPS_CLS_SRAM_L_INSTANCES : - NUM_MPS_T5_CLS_SRAM_L_INSTANCES; + unsigned int max_naddr = adapter->params.arch.mps_tcam_size; if (naddr > max_naddr) return -EINVAL; @@ -1285,9 +1283,7 @@ int t4vf_change_mac(struct adapter *adapter, unsigned int viid, struct fw_vi_mac_exact *p = &cmd.u.exact[0]; size_t len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd, u.exact[1]), 16); - unsigned int max_naddr = is_t4(adapter->params.chip) ? - NUM_MPS_CLS_SRAM_L_INSTANCES : - NUM_MPS_T5_CLS_SRAM_L_INSTANCES; + unsigned int max_mac_addr = adapter->params.arch.mps_tcam_size; /* * If this is a new allocation, determine whether it should be @@ -1310,7 +1306,7 @@ int t4vf_change_mac(struct adapter *adapter, unsigned int viid, if (ret == 0) { p = &rpl.u.exact[0]; ret = FW_VI_MAC_CMD_IDX_G(be16_to_cpu(p->valid_to_idx)); - if (ret >= max_naddr) + if (ret >= max_mac_addr) ret = -ENOMEM; } return ret; @@ -1590,11 +1586,25 @@ int t4vf_prep_adapter(struct adapter *adapter) switch (CHELSIO_PCI_ID_VER(adapter->pdev->device)) { case CHELSIO_T4: adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T4, 0); + adapter->params.arch.sge_fl_db = DBPRIO_F; + adapter->params.arch.mps_tcam_size = + NUM_MPS_CLS_SRAM_L_INSTANCES; break; case CHELSIO_T5: chipid = REV_G(t4_read_reg(adapter, PL_VF_REV_A)); adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T5, chipid); + adapter->params.arch.sge_fl_db = DBPRIO_F | DBTYPE_F; + adapter->params.arch.mps_tcam_size = + NUM_MPS_T5_CLS_SRAM_L_INSTANCES; + break; + + case CHELSIO_T6: + chipid = REV_G(t4_read_reg(adapter, PL_VF_REV_A)); + adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T6, chipid); + adapter->params.arch.sge_fl_db = 0; + adapter->params.arch.mps_tcam_size = + NUM_MPS_T5_CLS_SRAM_L_INSTANCES; break; } diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index badff18..8966f31 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -5189,16 +5189,16 @@ de4x5_parse_params(struct net_device *dev) if (strstr(p, "fdx") || strstr(p, "FDX")) lp->params.fdx = true; if (strstr(p, "autosense") || strstr(p, "AUTOSENSE")) { - if (strstr(p, "TP")) { - lp->params.autosense = TP; - } else if (strstr(p, "TP_NW")) { + if (strstr(p, "TP_NW")) { lp->params.autosense = TP_NW; + } else if (strstr(p, "TP")) { + lp->params.autosense = TP; + } else if (strstr(p, "BNC_AUI")) { + lp->params.autosense = BNC; } else if (strstr(p, "BNC")) { lp->params.autosense = BNC; } else if (strstr(p, "AUI")) { lp->params.autosense = AUI; - } else if (strstr(p, "BNC_AUI")) { - lp->params.autosense = BNC; } else if (strstr(p, "10Mb")) { lp->params.autosense = _10Mb; } else if (strstr(p, "100Mb")) { diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c index 2c30c0c..447d092 100644 --- a/drivers/net/ethernet/dec/tulip/uli526x.c +++ b/drivers/net/ethernet/dec/tulip/uli526x.c @@ -1115,7 +1115,7 @@ static void uli526x_timer(unsigned long data) netif_carrier_off(dev); } } - db->init=0; + db->init = 0; /* Timer active again */ db->timer.expires = ULI526X_TIMER_WUT; diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 1274b6f..cf0a5fc 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -463,10 +463,8 @@ rio_open (struct net_device *dev) dw32(MACCtrl, dr32(MACCtrl) | AutoVLANuntagging); } - init_timer (&np->timer); + setup_timer(&np->timer, rio_timer, (unsigned long)dev); np->timer.expires = jiffies + 1*HZ; - np->timer.data = (unsigned long) dev; - np->timer.function = rio_timer; add_timer (&np->timer); /* Start Tx/Rx */ diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 75696d4..1365a56 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2593,11 +2593,11 @@ static int be_evt_queues_create(struct be_adapter *adapter) adapter->cfg_num_qs); for_all_evt_queues(adapter, eqo, i) { + int numa_node = dev_to_node(&adapter->pdev->dev); if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL)) return -ENOMEM; - cpumask_set_cpu_local_first(i, dev_to_node(&adapter->pdev->dev), - eqo->affinity_mask); - + cpumask_set_cpu(cpumask_local_spread(i, numa_node), + eqo->affinity_mask); netif_napi_add(adapter->netdev, &eqo->napi, be_poll, BE_NAPI_WEIGHT); napi_hash_add(&eqo->napi); diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index de79193..b9df0cb 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2084,12 +2084,8 @@ static void emac_ethtool_get_pauseparam(struct net_device *ndev, static int emac_get_regs_len(struct emac_instance *dev) { - if (emac_has_feature(dev, EMAC_FTR_EMAC4)) - return sizeof(struct emac_ethtool_regs_subhdr) + - EMAC4_ETHTOOL_REGS_SIZE(dev); - else return sizeof(struct emac_ethtool_regs_subhdr) + - EMAC_ETHTOOL_REGS_SIZE(dev); + sizeof(struct emac_regs); } static int emac_ethtool_get_regs_len(struct net_device *ndev) @@ -2114,15 +2110,15 @@ static void *emac_dump_regs(struct emac_instance *dev, void *buf) struct emac_ethtool_regs_subhdr *hdr = buf; hdr->index = dev->cell_index; - if (emac_has_feature(dev, EMAC_FTR_EMAC4)) { + if (emac_has_feature(dev, EMAC_FTR_EMAC4SYNC)) { + hdr->version = EMAC4SYNC_ETHTOOL_REGS_VER; + } else if (emac_has_feature(dev, EMAC_FTR_EMAC4)) { hdr->version = EMAC4_ETHTOOL_REGS_VER; - memcpy_fromio(hdr + 1, dev->emacp, EMAC4_ETHTOOL_REGS_SIZE(dev)); - return (void *)(hdr + 1) + EMAC4_ETHTOOL_REGS_SIZE(dev); } else { hdr->version = EMAC_ETHTOOL_REGS_VER; - memcpy_fromio(hdr + 1, dev->emacp, EMAC_ETHTOOL_REGS_SIZE(dev)); - return (void *)(hdr + 1) + EMAC_ETHTOOL_REGS_SIZE(dev); } + memcpy_fromio(hdr + 1, dev->emacp, sizeof(struct emac_regs)); + return (void *)(hdr + 1) + sizeof(struct emac_regs); } static void emac_ethtool_get_regs(struct net_device *ndev, diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h index 67f342a..28df374 100644 --- a/drivers/net/ethernet/ibm/emac/core.h +++ b/drivers/net/ethernet/ibm/emac/core.h @@ -461,10 +461,7 @@ struct emac_ethtool_regs_subhdr { }; #define EMAC_ETHTOOL_REGS_VER 0 -#define EMAC_ETHTOOL_REGS_SIZE(dev) ((dev)->rsrc_regs.end - \ - (dev)->rsrc_regs.start + 1) -#define EMAC4_ETHTOOL_REGS_VER 1 -#define EMAC4_ETHTOOL_REGS_SIZE(dev) ((dev)->rsrc_regs.end - \ - (dev)->rsrc_regs.start + 1) +#define EMAC4_ETHTOOL_REGS_VER 1 +#define EMAC4SYNC_ETHTOOL_REGS_VER 2 #endif /* __IBM_NEWEMAC_CORE_H */ diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 35357ae..d2657a4 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2922,9 +2922,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - init_timer(&nic->watchdog); - nic->watchdog.function = e100_watchdog; - nic->watchdog.data = (unsigned long)nic; + setup_timer(&nic->watchdog, e100_watchdog, (unsigned long)nic); INIT_WORK(&nic->tx_timeout_task, e100_tx_timeout_task); diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c index 08f22f3..2af603f 100644 --- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c +++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.h b/drivers/net/ethernet/intel/e1000e/80003es2lan.h index 535a943..a2162e1 100644 --- a/drivers/net/ethernet/intel/e1000e/80003es2lan.h +++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 32e7775..5f70164 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/82571.h b/drivers/net/ethernet/intel/e1000e/82571.h index 2e758f7..abc6a9a 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.h +++ b/drivers/net/ethernet/intel/e1000e/82571.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 0570c66..133d407 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 0abc942..0b748d1 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -98,6 +98,8 @@ struct e1000_info; #define DEFAULT_RADV 8 #define BURST_RDTR 0x20 #define BURST_RADV 0x20 +#define PCICFG_DESC_RING_STATUS 0xe4 +#define FLUSH_DESC_REQUIRED 0x100 /* in the case of WTHRESH, it appears at least the 82571/2 hardware * writes back 4 descriptors when WTHRESH=5, and 3 descriptors when @@ -384,6 +386,10 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca); #define INCVALUE_SHIFT_25MHz 18 #define INCPERIOD_25MHz 1 +#define INCVALUE_24MHz 125 +#define INCVALUE_SHIFT_24MHz 14 +#define INCPERIOD_24MHz 3 + /* Another drawback of scaling the incvalue by a large factor is the * 64-bit SYSTIM register overflows more quickly. This is dealt with * by simply reading the clock before it overflows. diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 11f486e..ad6daa6 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -1516,8 +1516,19 @@ static int e1000_set_es2lan_mac_loopback(struct e1000_adapter *adapter) static int e1000_setup_loopback_test(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; - u32 rctl; - + u32 rctl, fext_nvm11, tarc0; + + if (hw->mac.type == e1000_pch_spt) { + fext_nvm11 = er32(FEXTNVM11); + fext_nvm11 |= E1000_FEXTNVM11_DISABLE_MULR_FIX; + ew32(FEXTNVM11, fext_nvm11); + tarc0 = er32(TARC(0)); + /* clear bits 28 & 29 (control of MULR concurrent requests) */ + tarc0 &= 0xcfffffff; + /* set bit 29 (value of MULR requests is now 2) */ + tarc0 |= 0x20000000; + ew32(TARC(0), tarc0); + } if (hw->phy.media_type == e1000_media_type_fiber || hw->phy.media_type == e1000_media_type_internal_serdes) { switch (hw->mac.type) { @@ -1542,7 +1553,7 @@ static int e1000_setup_loopback_test(struct e1000_adapter *adapter) static void e1000_loopback_cleanup(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; - u32 rctl; + u32 rctl, fext_nvm11, tarc0; u16 phy_reg; rctl = er32(RCTL); @@ -1550,6 +1561,16 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter) ew32(RCTL, rctl); switch (hw->mac.type) { + case e1000_pch_spt: + fext_nvm11 = er32(FEXTNVM11); + fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX; + ew32(FEXTNVM11, fext_nvm11); + tarc0 = er32(TARC(0)); + /* clear bits 28 & 29 (control of MULR concurrent requests) */ + /* set bit 29 (value of MULR requests is now 0) */ + tarc0 &= 0xcfffffff; + ew32(TARC(0), tarc0); + /* fall through */ case e1000_80003es2lan: if (hw->phy.media_type == e1000_media_type_fiber || hw->phy.media_type == e1000_media_type_internal_serdes) { diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 19e8c48..c9da465 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index e18443a..b074b9a 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -1014,7 +1014,6 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) u16 speed, duplex, scale = 0; u16 max_snoop, max_nosnoop; u16 max_ltr_enc; /* max LTR latency encoded */ - s64 lat_ns; /* latency (ns) */ u64 value; u32 rxa; @@ -1040,14 +1039,10 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) * 2^25*(2^10-1) ns. The scale is encoded as 0=2^0ns, * 1=2^5ns, 2=2^10ns,...5=2^25ns. */ - lat_ns = ((s64)rxa * 1024 - - (2 * (s64)hw->adapter->max_frame_size)) * 8 * 1000; - if (lat_ns < 0) { - value = 0; - } else { - value = lat_ns; - do_div(value, speed); - } + rxa *= 512; + value = (rxa > hw->adapter->max_frame_size) ? + (rxa - hw->adapter->max_frame_size) * (16000 / speed) : + 0; while (value > PCI_LTR_VALUE_MASK) { scale++; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 770a573..2645985 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -98,8 +98,15 @@ #define E1000_FEXTNVM6_K1_OFF_ENABLE 0x80000000 /* bit for disabling packet buffer read */ #define E1000_FEXTNVM7_DISABLE_PB_READ 0x00040000 - +#define E1000_FEXTNVM7_SIDE_CLK_UNGATE 0x00000004 #define E1000_FEXTNVM7_DISABLE_SMB_PERST 0x00000020 +#define E1000_FEXTNVM9_IOSFSB_CLKGATE_DIS 0x00000800 +#define E1000_FEXTNVM9_IOSFSB_CLKREQ_DIS 0x00001000 +#define E1000_FEXTNVM11_DISABLE_PB_READ 0x00000200 +#define E1000_FEXTNVM11_DISABLE_MULR_FIX 0x00002000 + +/* bit24: RXDCTL thresholds granularity: 0 - cache lines, 1 - descriptors */ +#define E1000_RXDCTL_THRESH_UNIT_DESC 0x01000000 #define K1_ENTRY_LATENCY 0 #define K1_MIN_TIME 1 diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index 30b74d5..e59d7c2 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/mac.h b/drivers/net/ethernet/intel/e1000e/mac.h index 0513d90..8284618 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.h +++ b/drivers/net/ethernet/intel/e1000e/mac.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/manage.c b/drivers/net/ethernet/intel/e1000e/manage.c index 06edfca..cc9b3be 100644 --- a/drivers/net/ethernet/intel/e1000e/manage.c +++ b/drivers/net/ethernet/intel/e1000e/manage.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/manage.h b/drivers/net/ethernet/intel/e1000e/manage.h index a8c27f9..0b9ea59 100644 --- a/drivers/net/ethernet/intel/e1000e/manage.h +++ b/drivers/net/ethernet/intel/e1000e/manage.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 7dd2c11..e62b9dc 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -48,7 +48,7 @@ #define DRV_EXTRAVERSION "-k" -#define DRV_VERSION "2.3.2" DRV_EXTRAVERSION +#define DRV_VERSION "3.2.5" DRV_EXTRAVERSION char e1000e_driver_name[] = "e1000e"; const char e1000e_driver_version[] = DRV_VERSION; @@ -3525,22 +3525,30 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) switch (hw->mac.type) { case e1000_pch2lan: case e1000_pch_lpt: - case e1000_pch_spt: - /* On I217, I218 and I219, the clock frequency is 25MHz - * or 96MHz as indicated by the System Clock Frequency - * Indication - */ - if (((hw->mac.type != e1000_pch_lpt) && - (hw->mac.type != e1000_pch_spt)) || - (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) { + if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { /* Stable 96MHz frequency */ incperiod = INCPERIOD_96MHz; incvalue = INCVALUE_96MHz; shift = INCVALUE_SHIFT_96MHz; adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHz; + } else { + /* Stable 25MHz frequency */ + incperiod = INCPERIOD_25MHz; + incvalue = INCVALUE_25MHz; + shift = INCVALUE_SHIFT_25MHz; + adapter->cc.shift = shift; + } + break; + case e1000_pch_spt: + if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { + /* Stable 24MHz frequency */ + incperiod = INCPERIOD_24MHz; + incvalue = INCVALUE_24MHz; + shift = INCVALUE_SHIFT_24MHz; + adapter->cc.shift = shift; break; } - /* fall-through */ + return -EINVAL; case e1000_82574: case e1000_82583: /* Stable 25MHz frequency */ @@ -3788,6 +3796,108 @@ static void e1000_power_down_phy(struct e1000_adapter *adapter) } /** + * e1000_flush_tx_ring - remove all descriptors from the tx_ring + * + * We want to clear all pending descriptors from the TX ring. + * zeroing happens when the HW reads the regs. We assign the ring itself as + * the data of the next descriptor. We don't care about the data we are about + * to reset the HW. + */ +static void e1000_flush_tx_ring(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct e1000_ring *tx_ring = adapter->tx_ring; + struct e1000_tx_desc *tx_desc = NULL; + u32 tdt, tctl, txd_lower = E1000_TXD_CMD_IFCS; + u16 size = 512; + + tctl = er32(TCTL); + ew32(TCTL, tctl | E1000_TCTL_EN); + tdt = er32(TDT(0)); + BUG_ON(tdt != tx_ring->next_to_use); + tx_desc = E1000_TX_DESC(*tx_ring, tx_ring->next_to_use); + tx_desc->buffer_addr = tx_ring->dma; + + tx_desc->lower.data = cpu_to_le32(txd_lower | size); + tx_desc->upper.data = 0; + /* flush descriptors to memory before notifying the HW */ + wmb(); + tx_ring->next_to_use++; + if (tx_ring->next_to_use == tx_ring->count) + tx_ring->next_to_use = 0; + ew32(TDT(0), tx_ring->next_to_use); + mmiowb(); + usleep_range(200, 250); +} + +/** + * e1000_flush_rx_ring - remove all descriptors from the rx_ring + * + * Mark all descriptors in the RX ring as consumed and disable the rx ring + */ +static void e1000_flush_rx_ring(struct e1000_adapter *adapter) +{ + u32 rctl, rxdctl; + struct e1000_hw *hw = &adapter->hw; + + rctl = er32(RCTL); + ew32(RCTL, rctl & ~E1000_RCTL_EN); + e1e_flush(); + usleep_range(100, 150); + + rxdctl = er32(RXDCTL(0)); + /* zero the lower 14 bits (prefetch and host thresholds) */ + rxdctl &= 0xffffc000; + + /* update thresholds: prefetch threshold to 31, host threshold to 1 + * and make sure the granularity is "descriptors" and not "cache lines" + */ + rxdctl |= (0x1F | (1 << 8) | E1000_RXDCTL_THRESH_UNIT_DESC); + + ew32(RXDCTL(0), rxdctl); + /* momentarily enable the RX ring for the changes to take effect */ + ew32(RCTL, rctl | E1000_RCTL_EN); + e1e_flush(); + usleep_range(100, 150); + ew32(RCTL, rctl & ~E1000_RCTL_EN); +} + +/** + * e1000_flush_desc_rings - remove all descriptors from the descriptor rings + * + * In i219, the descriptor rings must be emptied before resetting the HW + * or before changing the device state to D3 during runtime (runtime PM). + * + * Failure to do this will cause the HW to enter a unit hang state which can + * only be released by PCI reset on the device + * + */ + +static void e1000_flush_desc_rings(struct e1000_adapter *adapter) +{ + u16 hang_state; + u32 fext_nvm11, tdlen; + struct e1000_hw *hw = &adapter->hw; + + /* First, disable MULR fix in FEXTNVM11 */ + fext_nvm11 = er32(FEXTNVM11); + fext_nvm11 |= E1000_FEXTNVM11_DISABLE_MULR_FIX; + ew32(FEXTNVM11, fext_nvm11); + /* do nothing if we're not in faulty state, or if the queue is empty */ + tdlen = er32(TDLEN(0)); + pci_read_config_word(adapter->pdev, PCICFG_DESC_RING_STATUS, + &hang_state); + if (!(hang_state & FLUSH_DESC_REQUIRED) || !tdlen) + return; + e1000_flush_tx_ring(adapter); + /* recheck, maybe the fault is caused by the rx ring */ + pci_read_config_word(adapter->pdev, PCICFG_DESC_RING_STATUS, + &hang_state); + if (hang_state & FLUSH_DESC_REQUIRED) + e1000_flush_rx_ring(adapter); +} + +/** * e1000e_reset - bring the hardware into a known good state * * This function boots the hardware and enables some settings that @@ -3943,6 +4053,8 @@ void e1000e_reset(struct e1000_adapter *adapter) } } + if (hw->mac.type == e1000_pch_spt) + e1000_flush_desc_rings(adapter); /* Allow time for pending master requests to run */ mac->ops.reset_hw(hw); @@ -4016,6 +4128,20 @@ void e1000e_reset(struct e1000_adapter *adapter) phy_data &= ~IGP02E1000_PM_SPD; e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, phy_data); } + if (hw->mac.type == e1000_pch_spt && adapter->int_mode == 0) { + u32 reg; + + /* Fextnvm7 @ 0xe4[2] = 1 */ + reg = er32(FEXTNVM7); + reg |= E1000_FEXTNVM7_SIDE_CLK_UNGATE; + ew32(FEXTNVM7, reg); + /* Fextnvm9 @ 0x5bb4[13:12] = 11 */ + reg = er32(FEXTNVM9); + reg |= E1000_FEXTNVM9_IOSFSB_CLKGATE_DIS | + E1000_FEXTNVM9_IOSFSB_CLKREQ_DIS; + ew32(FEXTNVM9, reg); + } + } int e1000e_up(struct e1000_adapter *adapter) @@ -4115,8 +4241,6 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset) spin_unlock(&adapter->stats64_lock); e1000e_flush_descriptors(adapter); - e1000_clean_tx_ring(adapter->tx_ring); - e1000_clean_rx_ring(adapter->rx_ring); adapter->link_speed = 0; adapter->link_duplex = 0; @@ -4127,8 +4251,14 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset) e1000_lv_jumbo_workaround_ich8lan(hw, false)) e_dbg("failed to disable jumbo frame workaround mode\n"); - if (reset && !pci_channel_offline(adapter->pdev)) - e1000e_reset(adapter); + if (!pci_channel_offline(adapter->pdev)) { + if (reset) + e1000e_reset(adapter); + else if (hw->mac.type == e1000_pch_spt) + e1000_flush_desc_rings(adapter); + } + e1000_clean_tx_ring(adapter->tx_ring); + e1000_clean_rx_ring(adapter->rx_ring); } void e1000e_reinit_locked(struct e1000_adapter *adapter) @@ -4151,9 +4281,16 @@ static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc) cc); struct e1000_hw *hw = &adapter->hw; cycle_t systim, systim_next; + /* SYSTIMH latching upon SYSTIML read does not work well. To fix that + * we don't want to allow overflow of SYSTIML and a change to SYSTIMH + * to occur between reads, so if we read a vale close to overflow, we + * wait for overflow to occur and read both registers when its safe. + */ + u32 systim_overflow_latch_fix = 0x3FFFFFFF; - /* latch SYSTIMH on read of SYSTIML */ - systim = (cycle_t)er32(SYSTIML); + do { + systim = (cycle_t)er32(SYSTIML); + } while (systim > systim_overflow_latch_fix); systim |= (cycle_t)er32(SYSTIMH) << 32; if ((hw->mac.type == e1000_82574) || (hw->mac.type == e1000_82583)) { @@ -7301,7 +7438,7 @@ static int __init e1000_init_module(void) pr_info("Intel(R) PRO/1000 Network Driver - %s\n", e1000e_driver_version); - pr_info("Copyright(c) 1999 - 2014 Intel Corporation.\n"); + pr_info("Copyright(c) 1999 - 2015 Intel Corporation.\n"); ret = pci_register_driver(&e1000_driver); return ret; diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c index fa6b103..49f205c 100644 --- a/drivers/net/ethernet/intel/e1000e/nvm.c +++ b/drivers/net/ethernet/intel/e1000e/nvm.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/nvm.h b/drivers/net/ethernet/intel/e1000e/nvm.h index 342bf69..5d46967 100644 --- a/drivers/net/ethernet/intel/e1000e/nvm.h +++ b/drivers/net/ethernet/intel/e1000e/nvm.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c index aa1923f..6d8c39a 100644 --- a/drivers/net/ethernet/intel/e1000e/param.c +++ b/drivers/net/ethernet/intel/e1000e/param.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index b2005e1..de13aea 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/phy.h b/drivers/net/ethernet/intel/e1000e/phy.h index 537d278..55bfe47 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.h +++ b/drivers/net/ethernet/intel/e1000e/phy.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 8d7b21d..25a0ad5 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/net/ethernet/intel/e1000e/regs.h b/drivers/net/ethernet/intel/e1000e/regs.h index 85eefc4..b24e5fe 100644 --- a/drivers/net/ethernet/intel/e1000e/regs.h +++ b/drivers/net/ethernet/intel/e1000e/regs.h @@ -1,5 +1,5 @@ /* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. + * Copyright(c) 1999 - 2015 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -38,6 +38,8 @@ #define E1000_FEXTNVM4 0x00024 /* Future Extended NVM 4 - RW */ #define E1000_FEXTNVM6 0x00010 /* Future Extended NVM 6 - RW */ #define E1000_FEXTNVM7 0x000E4 /* Future Extended NVM 7 - RW */ +#define E1000_FEXTNVM9 0x5BB4 /* Future Extended NVM 9 - RW */ +#define E1000_FEXTNVM11 0x5BBC /* Future Extended NVM 11 - RW */ #define E1000_PCIEANACFG 0x00F18 /* PCIE Analog Config */ #define E1000_FCT 0x00030 /* Flow Control Type - RW */ #define E1000_VET 0x00038 /* VLAN Ether Type - RW */ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 33c35d3..aca9cef 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -182,6 +182,7 @@ struct i40e_lump_tracking { enum i40e_fd_stat_idx { I40E_FD_STAT_ATR, I40E_FD_STAT_SB, + I40E_FD_STAT_ATR_TUNNEL, I40E_FD_STAT_PF_COUNT }; #define I40E_FD_STAT_PF_IDX(pf_id) ((pf_id) * I40E_FD_STAT_PF_COUNT) @@ -189,6 +190,8 @@ enum i40e_fd_stat_idx { (I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR) #define I40E_FD_SB_STAT_IDX(pf_id) \ (I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_SB) +#define I40E_FD_ATR_TUNNEL_STAT_IDX(pf_id) \ + (I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR_TUNNEL) struct i40e_fdir_filter { struct hlist_node fdir_node; @@ -263,8 +266,6 @@ struct i40e_pf { struct hlist_head fdir_filter_list; u16 fdir_pf_active_filters; - u16 fd_sb_cnt_idx; - u16 fd_atr_cnt_idx; unsigned long fd_flush_timestamp; u32 fd_flush_cnt; u32 fd_add_err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 4cbaaeb..9a68c65 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -147,6 +147,7 @@ static struct i40e_stats i40e_gstrings_stats[] = { I40E_PF_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared), I40E_PF_STAT("fdir_flush_cnt", fd_flush_cnt), I40E_PF_STAT("fdir_atr_match", stats.fd_atr_match), + I40E_PF_STAT("fdir_atr_tunnel_match", stats.fd_atr_tunnel_match), I40E_PF_STAT("fdir_sb_match", stats.fd_sb_match), /* LPI stats */ @@ -1548,6 +1549,17 @@ static int i40e_loopback_test(struct net_device *netdev, u64 *data) return *data; } +static inline bool i40e_active_vfs(struct i40e_pf *pf) +{ + struct i40e_vf *vfs = pf->vf; + int i; + + for (i = 0; i < pf->num_alloc_vfs; i++) + if (vfs[i].vf_states & I40E_VF_STAT_ACTIVE) + return true; + return false; +} + static void i40e_diag_test(struct net_device *netdev, struct ethtool_test *eth_test, u64 *data) { @@ -1560,6 +1572,20 @@ static void i40e_diag_test(struct net_device *netdev, netif_info(pf, drv, netdev, "offline testing starting\n"); set_bit(__I40E_TESTING, &pf->state); + + if (i40e_active_vfs(pf)) { + dev_warn(&pf->pdev->dev, + "Please take active VFS offline and restart the adapter before running NIC diagnostics\n"); + data[I40E_ETH_TEST_REG] = 1; + data[I40E_ETH_TEST_EEPROM] = 1; + data[I40E_ETH_TEST_INTR] = 1; + data[I40E_ETH_TEST_LOOPBACK] = 1; + data[I40E_ETH_TEST_LINK] = 1; + eth_test->flags |= ETH_TEST_FL_FAILED; + clear_bit(__I40E_TESTING, &pf->state); + goto skip_ol_tests; + } + /* If the device is online then take it offline */ if (if_running) /* indicate we're in test mode */ @@ -1605,6 +1631,8 @@ static void i40e_diag_test(struct net_device *netdev, data[I40E_ETH_TEST_LOOPBACK] = 0; } +skip_ol_tests: + netif_info(pf, drv, netdev, "testing finished\n"); } @@ -2265,7 +2293,7 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, input->pctype = 0; input->dest_vsi = vsi->id; input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID; - input->cnt_index = pf->fd_sb_cnt_idx; + input->cnt_index = I40E_FD_SB_STAT_IDX(pf->hw.pf_id); input->flow_type = fsp->flow_type; input->ip4_proto = fsp->h_u.usr_ip4_spec.proto; diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c index 1803afe..c8b621e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c +++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c @@ -118,7 +118,7 @@ static inline int i40e_fcoe_fc_eof(struct sk_buff *skb, u8 *eof) * * The FC EOF is converted to the value understood by HW for descriptor * programming. Never call this w/o calling i40e_fcoe_eof_is_supported() - * first. + * first and that already checks for all supported valid eof values. **/ static inline u32 i40e_fcoe_ctxt_eof(u8 eof) { @@ -132,9 +132,12 @@ static inline u32 i40e_fcoe_ctxt_eof(u8 eof) case FC_EOF_A: return I40E_TX_DESC_CMD_L4T_EOFT_EOF_A; default: - /* FIXME: still returns 0 */ - pr_err("Unrecognized EOF %x\n", eof); - return 0; + /* Supported valid eof shall be already checked by + * calling i40e_fcoe_eof_is_supported() first, + * therefore this default case shall never hit. + */ + WARN_ON(1); + return -EINVAL; } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index a54c144..0a3e928 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -39,7 +39,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 3 -#define DRV_VERSION_BUILD 2 +#define DRV_VERSION_BUILD 4 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -772,9 +772,8 @@ static void i40e_update_prio_xoff_rx(struct i40e_pf *pf) dcb_cfg = &hw->local_dcbx_config; - /* See if DCB enabled with PFC TC */ - if (!(pf->flags & I40E_FLAG_DCB_ENABLED) || - !(dcb_cfg->pfc.pfcenable)) { + /* Collect Link XOFF stats when PFC is disabled */ + if (!dcb_cfg->pfc.pfcenable) { i40e_update_link_xoff_rx(pf); return; } @@ -1097,12 +1096,18 @@ static void i40e_update_pf_stats(struct i40e_pf *pf) &osd->rx_jabber, &nsd->rx_jabber); /* FDIR stats */ - i40e_stat_update32(hw, I40E_GLQF_PCNT(pf->fd_atr_cnt_idx), + i40e_stat_update32(hw, + I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(pf->hw.pf_id)), pf->stat_offsets_loaded, &osd->fd_atr_match, &nsd->fd_atr_match); - i40e_stat_update32(hw, I40E_GLQF_PCNT(pf->fd_sb_cnt_idx), + i40e_stat_update32(hw, + I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(pf->hw.pf_id)), pf->stat_offsets_loaded, &osd->fd_sb_match, &nsd->fd_sb_match); + i40e_stat_update32(hw, + I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id)), + pf->stat_offsets_loaded, + &osd->fd_atr_tunnel_match, &nsd->fd_atr_tunnel_match); val = rd32(hw, I40E_PRTPM_EEE_STAT); nsd->tx_lpi_status = @@ -4739,7 +4744,8 @@ static int i40e_up_complete(struct i40e_vsi *vsi) pf->fd_add_err = pf->fd_atr_cnt = 0; if (pf->fd_tcp_rule > 0) { pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED; - dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n"); + if (I40E_DEBUG_FD & pf->hw.debug_mask) + dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n"); pf->fd_tcp_rule = 0; } i40e_fdir_filter_restore(vsi); @@ -5428,7 +5434,8 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) && (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) { pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED; - dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n"); + if (I40E_DEBUG_FD & pf->hw.debug_mask) + dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n"); } } /* Wait for some more space to be available to turn on ATR */ @@ -5436,7 +5443,8 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) { pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; - dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table now\n"); + if (I40E_DEBUG_FD & pf->hw.debug_mask) + dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table now\n"); } } } @@ -5469,7 +5477,8 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) if (!(time_after(jiffies, min_flush_time)) && (fd_room < I40E_FDIR_BUFFER_HEAD_ROOM_FOR_ATR)) { - dev_info(&pf->pdev->dev, "ATR disabled, not enough FD filter space.\n"); + if (I40E_DEBUG_FD & pf->hw.debug_mask) + dev_info(&pf->pdev->dev, "ATR disabled, not enough FD filter space.\n"); disable_atr = true; } @@ -5496,7 +5505,8 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) if (!disable_atr) pf->flags |= I40E_FLAG_FD_ATR_ENABLED; clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); - dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n"); + if (I40E_DEBUG_FD & pf->hw.debug_mask) + dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n"); } } } @@ -7676,12 +7686,8 @@ static int i40e_sw_init(struct i40e_pf *pf) (pf->hw.func_caps.fd_filters_best_effort > 0)) { pf->flags |= I40E_FLAG_FD_ATR_ENABLED; pf->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE; - /* Setup a counter for fd_atr per PF */ - pf->fd_atr_cnt_idx = I40E_FD_ATR_STAT_IDX(pf->hw.pf_id); if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) { pf->flags |= I40E_FLAG_FD_SB_ENABLED; - /* Setup a counter for fd_sb per PF */ - pf->fd_sb_cnt_idx = I40E_FD_SB_STAT_IDX(pf->hw.pf_id); } else { dev_info(&pf->pdev->dev, "Flow Director Sideband mode Disabled in MFP mode\n"); @@ -7771,7 +7777,8 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features) pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0; pf->fdir_pf_active_filters = 0; pf->flags |= I40E_FLAG_FD_ATR_ENABLED; - dev_info(&pf->pdev->dev, "ATR re-enabled.\n"); + if (I40E_DEBUG_FD & pf->hw.debug_mask) + dev_info(&pf->pdev->dev, "ATR re-enabled.\n"); /* if ATR was auto disabled it can be re-enabled. */ if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 0b4a7be..cc82a7f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -165,9 +165,6 @@ int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, u8 *raw_packet, tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, 0, I40E_FDIR_MAX_RAW_PACKET_SIZE, 0); - /* set the timestamp */ - tx_buf->time_stamp = jiffies; - /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. */ @@ -283,7 +280,8 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, if (add) { pf->fd_tcp_rule++; if (pf->flags & I40E_FLAG_FD_ATR_ENABLED) { - dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n"); + if (I40E_DEBUG_FD & pf->hw.debug_mask) + dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n"); pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED; } } else { @@ -291,7 +289,8 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, (pf->fd_tcp_rule - 1) : 0; if (pf->fd_tcp_rule == 0) { pf->flags |= I40E_FLAG_FD_ATR_ENABLED; - dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n"); + if (I40E_DEBUG_FD & pf->hw.debug_mask) + dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n"); } } @@ -501,7 +500,8 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) && !(pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) { - dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n"); + if (I40E_DEBUG_FD & pf->hw.debug_mask) + dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n"); pf->auto_disable_flags |= I40E_FLAG_FD_SB_ENABLED; } @@ -807,10 +807,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) tx_ring->vsi->seid, tx_ring->queue_index, tx_ring->next_to_use, i); - dev_info(tx_ring->dev, "tx_bi[next_to_clean]\n" - " time_stamp <%lx>\n" - " jiffies <%lx>\n", - tx_ring->tx_bi[i].time_stamp, jiffies); netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); @@ -1653,9 +1649,6 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget) /* ERR_MASK will only have valid bits if EOP set */ if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) { dev_kfree_skb_any(skb); - /* TODO: shouldn't we increment a counter indicating the - * drop? - */ continue; } @@ -1923,11 +1916,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) * i40e_atr - Add a Flow Director ATR filter * @tx_ring: ring to add programming descriptor to * @skb: send buffer - * @flags: send flags + * @tx_flags: send tx flags * @protocol: wire protocol **/ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, - u32 flags, __be16 protocol) + u32 tx_flags, __be16 protocol) { struct i40e_filter_program_desc *fdir_desc; struct i40e_pf *pf = tx_ring->vsi->back; @@ -1952,25 +1945,38 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, if (!tx_ring->atr_sample_rate) return; - /* snag network header to get L4 type and address */ - hdr.network = skb_network_header(skb); + if (!(tx_flags & (I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6))) + return; - /* Currently only IPv4/IPv6 with TCP is supported */ - if (protocol == htons(ETH_P_IP)) { - if (hdr.ipv4->protocol != IPPROTO_TCP) - return; + if (!(tx_flags & I40E_TX_FLAGS_VXLAN_TUNNEL)) { + /* snag network header to get L4 type and address */ + hdr.network = skb_network_header(skb); - /* access ihl as a u8 to avoid unaligned access on ia64 */ - hlen = (hdr.network[0] & 0x0F) << 2; - } else if (protocol == htons(ETH_P_IPV6)) { - if (hdr.ipv6->nexthdr != IPPROTO_TCP) + /* Currently only IPv4/IPv6 with TCP is supported + * access ihl as u8 to avoid unaligned access on ia64 + */ + if (tx_flags & I40E_TX_FLAGS_IPV4) + hlen = (hdr.network[0] & 0x0F) << 2; + else if (protocol == htons(ETH_P_IPV6)) + hlen = sizeof(struct ipv6hdr); + else return; - - hlen = sizeof(struct ipv6hdr); } else { - return; + hdr.network = skb_inner_network_header(skb); + hlen = skb_inner_network_header_len(skb); } + /* Currently only IPv4/IPv6 with TCP is supported + * Note: tx_flags gets modified to reflect inner protocols in + * tx_enable_csum function if encap is enabled. + */ + if ((tx_flags & I40E_TX_FLAGS_IPV4) && + (hdr.ipv4->protocol != IPPROTO_TCP)) + return; + else if ((tx_flags & I40E_TX_FLAGS_IPV6) && + (hdr.ipv6->nexthdr != IPPROTO_TCP)) + return; + th = (struct tcphdr *)(hdr.network + hlen); /* Due to lack of space, no more new filters can be programmed */ @@ -2020,9 +2026,16 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT; dtype_cmd |= I40E_TXD_FLTR_QW1_CNT_ENA_MASK; - dtype_cmd |= - ((u32)pf->fd_atr_cnt_idx << I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) & - I40E_TXD_FLTR_QW1_CNTINDEX_MASK; + if (!(tx_flags & I40E_TX_FLAGS_VXLAN_TUNNEL)) + dtype_cmd |= + ((u32)I40E_FD_ATR_STAT_IDX(pf->hw.pf_id) << + I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) & + I40E_TXD_FLTR_QW1_CNTINDEX_MASK; + else + dtype_cmd |= + ((u32)I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id) << + I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) & + I40E_TXD_FLTR_QW1_CNTINDEX_MASK; fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype); fdir_desc->rsvd = cpu_to_le32(0); @@ -2043,13 +2056,13 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, * otherwise returns 0 to indicate the flags has been set properly. **/ #ifdef I40E_FCOE -int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, - struct i40e_ring *tx_ring, - u32 *flags) -#else -static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, +inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, struct i40e_ring *tx_ring, u32 *flags) +#else +static inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, + struct i40e_ring *tx_ring, + u32 *flags) #endif { __be16 protocol = skb->protocol; @@ -2117,16 +2130,14 @@ out: * i40e_tso - set up the tso context descriptor * @tx_ring: ptr to the ring to send * @skb: ptr to the skb we're sending - * @tx_flags: the collected send information - * @protocol: the send protocol * @hdr_len: ptr to the size of the packet header * @cd_tunneling: ptr to context descriptor bits * * Returns 0 if no TSO can happen, 1 if tso is going, or error **/ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb, - u32 tx_flags, __be16 protocol, u8 *hdr_len, - u64 *cd_type_cmd_tso_mss, u32 *cd_tunneling) + u8 *hdr_len, u64 *cd_type_cmd_tso_mss, + u32 *cd_tunneling) { u32 cd_cmd, cd_tso_len, cd_mss; struct ipv6hdr *ipv6h; @@ -2218,12 +2229,12 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb, /** * i40e_tx_enable_csum - Enable Tx checksum offloads * @skb: send buffer - * @tx_flags: Tx flags currently set + * @tx_flags: pointer to Tx flags currently set * @td_cmd: Tx descriptor command bits to set * @td_offset: Tx descriptor header offsets to set * @cd_tunneling: ptr to context desc bits **/ -static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, +static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, u32 *td_cmd, u32 *td_offset, struct i40e_ring *tx_ring, u32 *cd_tunneling) @@ -2239,6 +2250,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, switch (ip_hdr(skb)->protocol) { case IPPROTO_UDP: l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING; + *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; break; default: return; @@ -2248,18 +2260,17 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, this_ipv6_hdr = inner_ipv6_hdr(skb); this_tcp_hdrlen = inner_tcp_hdrlen(skb); - if (tx_flags & I40E_TX_FLAGS_IPV4) { - - if (tx_flags & I40E_TX_FLAGS_TSO) { + if (*tx_flags & I40E_TX_FLAGS_IPV4) { + if (*tx_flags & I40E_TX_FLAGS_TSO) { *cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4; ip_hdr(skb)->check = 0; } else { *cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM; } - } else if (tx_flags & I40E_TX_FLAGS_IPV6) { + } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { *cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6; - if (tx_flags & I40E_TX_FLAGS_TSO) + if (*tx_flags & I40E_TX_FLAGS_TSO) ip_hdr(skb)->check = 0; } @@ -2271,8 +2282,8 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, skb_transport_offset(skb)) >> 1) << I40E_TXD_CTX_QW0_NATLEN_SHIFT; if (this_ip_hdr->version == 6) { - tx_flags &= ~I40E_TX_FLAGS_IPV4; - tx_flags |= I40E_TX_FLAGS_IPV6; + *tx_flags &= ~I40E_TX_FLAGS_IPV4; + *tx_flags |= I40E_TX_FLAGS_IPV6; } } else { network_hdr_len = skb_network_header_len(skb); @@ -2282,12 +2293,12 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, } /* Enable IP checksum offloads */ - if (tx_flags & I40E_TX_FLAGS_IPV4) { + if (*tx_flags & I40E_TX_FLAGS_IPV4) { l4_hdr = this_ip_hdr->protocol; /* the stack computes the IP header already, the only time we * need the hardware to recompute it is in the case of TSO. */ - if (tx_flags & I40E_TX_FLAGS_TSO) { + if (*tx_flags & I40E_TX_FLAGS_TSO) { *td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM; this_ip_hdr->check = 0; } else { @@ -2296,7 +2307,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, /* Now set the td_offset for IP header length */ *td_offset = (network_hdr_len >> 2) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT; - } else if (tx_flags & I40E_TX_FLAGS_IPV6) { + } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { l4_hdr = this_ipv6_hdr->nexthdr; *td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6; /* Now set the td_offset for IP header length */ @@ -2394,9 +2405,9 @@ static inline int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) * Returns 0 if stop is not needed **/ #ifdef I40E_FCOE -int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) +inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) #else -static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) +static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) #endif { if (likely(I40E_DESC_UNUSED(tx_ring) >= size)) @@ -2476,13 +2487,13 @@ linearize_chk_done: * @td_offset: offset for checksum or crc **/ #ifdef I40E_FCOE -void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, - struct i40e_tx_buffer *first, u32 tx_flags, - const u8 hdr_len, u32 td_cmd, u32 td_offset) -#else -static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, +inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, struct i40e_tx_buffer *first, u32 tx_flags, const u8 hdr_len, u32 td_cmd, u32 td_offset) +#else +static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, + struct i40e_tx_buffer *first, u32 tx_flags, + const u8 hdr_len, u32 td_cmd, u32 td_offset) #endif { unsigned int data_len = skb->data_len; @@ -2588,9 +2599,6 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_ring->queue_index), first->bytecount); - /* set the timestamp */ - first->time_stamp = jiffies; - /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, @@ -2643,11 +2651,11 @@ dma_error: * one descriptor. **/ #ifdef I40E_FCOE -int i40e_xmit_descriptor_count(struct sk_buff *skb, - struct i40e_ring *tx_ring) -#else -static int i40e_xmit_descriptor_count(struct sk_buff *skb, +inline int i40e_xmit_descriptor_count(struct sk_buff *skb, struct i40e_ring *tx_ring) +#else +static inline int i40e_xmit_descriptor_count(struct sk_buff *skb, + struct i40e_ring *tx_ring) #endif { unsigned int f; @@ -2709,7 +2717,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, else if (protocol == htons(ETH_P_IPV6)) tx_flags |= I40E_TX_FLAGS_IPV6; - tso = i40e_tso(tx_ring, skb, tx_flags, protocol, &hdr_len, + tso = i40e_tso(tx_ring, skb, &hdr_len, &cd_type_cmd_tso_mss, &cd_tunneling); if (tso < 0) @@ -2735,7 +2743,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_PARTIAL) { tx_flags |= I40E_TX_FLAGS_CSUM; - i40e_tx_enable_csum(skb, tx_flags, &td_cmd, &td_offset, + i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset, tx_ring, &cd_tunneling); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 4b0b810..0dc48dc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -139,6 +139,7 @@ enum i40e_dyn_idx_t { #define I40E_TX_FLAGS_FSO (u32)(1 << 7) #define I40E_TX_FLAGS_TSYN (u32)(1 << 8) #define I40E_TX_FLAGS_FD_SB (u32)(1 << 9) +#define I40E_TX_FLAGS_VXLAN_TUNNEL (u32)(1 << 10) #define I40E_TX_FLAGS_VLAN_MASK 0xffff0000 #define I40E_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 #define I40E_TX_FLAGS_VLAN_PRIO_SHIFT 29 @@ -146,7 +147,6 @@ enum i40e_dyn_idx_t { struct i40e_tx_buffer { struct i40e_tx_desc *next_to_watch; - unsigned long time_stamp; union { struct sk_buff *skb; void *raw_buf; diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 568e855..9a5a75b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -1133,6 +1133,7 @@ struct i40e_hw_port_stats { /* flow director stats */ u64 fd_atr_match; u64 fd_sb_match; + u64 fd_atr_tunnel_match; /* EEE LPI */ u32 tx_lpi_status; u32 rx_lpi_status; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 78d1c4f..4653b6e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -980,6 +980,13 @@ static int i40e_pci_sriov_enable(struct pci_dev *pdev, int num_vfs) int pre_existing_vfs = pci_num_vf(pdev); int err = 0; + if (pf->state & __I40E_TESTING) { + dev_warn(&pdev->dev, + "Cannot enable SR-IOV virtual functions while the device is undergoing diagnostic testing\n"); + err = -EPERM; + goto err_out; + } + dev_info(&pdev->dev, "Allocating %d VFs.\n", num_vfs); if (pre_existing_vfs && pre_existing_vfs != num_vfs) i40e_free_vfs(pf); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 3ef2309..ec7e220 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -322,10 +322,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) tx_ring->vsi->seid, tx_ring->queue_index, tx_ring->next_to_use, i); - dev_info(tx_ring->dev, "tx_bi[next_to_clean]\n" - " time_stamp <%lx>\n" - " jiffies <%lx>\n", - tx_ring->tx_bi[i].time_stamp, jiffies); netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); @@ -1128,9 +1124,6 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget) /* ERR_MASK will only have valid bits if EOP set */ if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) { dev_kfree_skb_any(skb); - /* TODO: shouldn't we increment a counter indicating the - * drop? - */ continue; } @@ -1350,7 +1343,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) } /** - * i40e_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW + * i40evf_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW * @skb: send buffer * @tx_ring: ring to send buffer on * @flags: the tx flags to be set @@ -1361,9 +1354,9 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) * Returns error code indicate the frame should be dropped upon error and the * otherwise returns 0 to indicate the flags has been set properly. **/ -static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, - struct i40e_ring *tx_ring, - u32 *flags) +static inline int i40evf_tx_prepare_vlan_flags(struct sk_buff *skb, + struct i40e_ring *tx_ring, + u32 *flags) { __be16 protocol = skb->protocol; u32 tx_flags = 0; @@ -1406,16 +1399,14 @@ out: * i40e_tso - set up the tso context descriptor * @tx_ring: ptr to the ring to send * @skb: ptr to the skb we're sending - * @tx_flags: the collected send information - * @protocol: the send protocol * @hdr_len: ptr to the size of the packet header * @cd_tunneling: ptr to context descriptor bits * * Returns 0 if no TSO can happen, 1 if tso is going, or error **/ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb, - u32 tx_flags, __be16 protocol, u8 *hdr_len, - u64 *cd_type_cmd_tso_mss, u32 *cd_tunneling) + u8 *hdr_len, u64 *cd_type_cmd_tso_mss, + u32 *cd_tunneling) { u32 cd_cmd, cd_tso_len, cd_mss; struct ipv6hdr *ipv6h; @@ -1466,12 +1457,12 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb, /** * i40e_tx_enable_csum - Enable Tx checksum offloads * @skb: send buffer - * @tx_flags: Tx flags currently set + * @tx_flags: pointer to Tx flags currently set * @td_cmd: Tx descriptor command bits to set * @td_offset: Tx descriptor header offsets to set * @cd_tunneling: ptr to context desc bits **/ -static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, +static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, u32 *td_cmd, u32 *td_offset, struct i40e_ring *tx_ring, u32 *cd_tunneling) @@ -1487,6 +1478,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, switch (ip_hdr(skb)->protocol) { case IPPROTO_UDP: l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING; + *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; break; default: return; @@ -1496,18 +1488,17 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, this_ipv6_hdr = inner_ipv6_hdr(skb); this_tcp_hdrlen = inner_tcp_hdrlen(skb); - if (tx_flags & I40E_TX_FLAGS_IPV4) { - - if (tx_flags & I40E_TX_FLAGS_TSO) { + if (*tx_flags & I40E_TX_FLAGS_IPV4) { + if (*tx_flags & I40E_TX_FLAGS_TSO) { *cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4; ip_hdr(skb)->check = 0; } else { *cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM; } - } else if (tx_flags & I40E_TX_FLAGS_IPV6) { + } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { *cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6; - if (tx_flags & I40E_TX_FLAGS_TSO) + if (*tx_flags & I40E_TX_FLAGS_TSO) ip_hdr(skb)->check = 0; } @@ -1519,8 +1510,8 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, skb_transport_offset(skb)) >> 1) << I40E_TXD_CTX_QW0_NATLEN_SHIFT; if (this_ip_hdr->version == 6) { - tx_flags &= ~I40E_TX_FLAGS_IPV4; - tx_flags |= I40E_TX_FLAGS_IPV6; + *tx_flags &= ~I40E_TX_FLAGS_IPV4; + *tx_flags |= I40E_TX_FLAGS_IPV6; } @@ -1532,12 +1523,12 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, } /* Enable IP checksum offloads */ - if (tx_flags & I40E_TX_FLAGS_IPV4) { + if (*tx_flags & I40E_TX_FLAGS_IPV4) { l4_hdr = this_ip_hdr->protocol; /* the stack computes the IP header already, the only time we * need the hardware to recompute it is in the case of TSO. */ - if (tx_flags & I40E_TX_FLAGS_TSO) { + if (*tx_flags & I40E_TX_FLAGS_TSO) { *td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM; this_ip_hdr->check = 0; } else { @@ -1546,7 +1537,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags, /* Now set the td_offset for IP header length */ *td_offset = (network_hdr_len >> 2) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT; - } else if (tx_flags & I40E_TX_FLAGS_IPV6) { + } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { l4_hdr = this_ipv6_hdr->nexthdr; *td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6; /* Now set the td_offset for IP header length */ @@ -1675,7 +1666,44 @@ linearize_chk_done: } /** - * i40e_tx_map - Build the Tx descriptor + * __i40evf_maybe_stop_tx - 2nd level check for tx stop conditions + * @tx_ring: the ring to be checked + * @size: the size buffer we want to assure is available + * + * Returns -EBUSY if a stop is needed, else 0 + **/ +static inline int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) +{ + netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); + /* Memory barrier before checking head and tail */ + smp_mb(); + + /* Check again in a case another CPU has just made room available. */ + if (likely(I40E_DESC_UNUSED(tx_ring) < size)) + return -EBUSY; + + /* A reprieve! - use start_queue because it doesn't call schedule */ + netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index); + ++tx_ring->tx_stats.restart_queue; + return 0; +} + +/** + * i40evf_maybe_stop_tx - 1st level check for tx stop conditions + * @tx_ring: the ring to be checked + * @size: the size buffer we want to assure is available + * + * Returns 0 if stop is not needed + **/ +static inline int i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) +{ + if (likely(I40E_DESC_UNUSED(tx_ring) >= size)) + return 0; + return __i40evf_maybe_stop_tx(tx_ring, size); +} + +/** + * i40evf_tx_map - Build the Tx descriptor * @tx_ring: ring to send buffer on * @skb: send buffer * @first: first buffer info buffer to use @@ -1684,9 +1712,9 @@ linearize_chk_done: * @td_cmd: the command field in the descriptor * @td_offset: offset for checksum or crc **/ -static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, - struct i40e_tx_buffer *first, u32 tx_flags, - const u8 hdr_len, u32 td_cmd, u32 td_offset) +static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, + struct i40e_tx_buffer *first, u32 tx_flags, + const u8 hdr_len, u32 td_cmd, u32 td_offset) { unsigned int data_len = skb->data_len; unsigned int size = skb_headlen(skb); @@ -1792,9 +1820,6 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_ring->queue_index), first->bytecount); - /* set the timestamp */ - first->time_stamp = jiffies; - /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, @@ -1811,8 +1836,12 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_ring->next_to_use = i; + i40evf_maybe_stop_tx(tx_ring, DESC_NEEDED); /* notify HW of packet */ - writel(i, tx_ring->tail); + if (!skb->xmit_more || + netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->queue_index))) + writel(i, tx_ring->tail); return; @@ -1834,44 +1863,7 @@ dma_error: } /** - * __i40e_maybe_stop_tx - 2nd level check for tx stop conditions - * @tx_ring: the ring to be checked - * @size: the size buffer we want to assure is available - * - * Returns -EBUSY if a stop is needed, else 0 - **/ -static inline int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) -{ - netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); - /* Memory barrier before checking head and tail */ - smp_mb(); - - /* Check again in a case another CPU has just made room available. */ - if (likely(I40E_DESC_UNUSED(tx_ring) < size)) - return -EBUSY; - - /* A reprieve! - use start_queue because it doesn't call schedule */ - netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index); - ++tx_ring->tx_stats.restart_queue; - return 0; -} - -/** - * i40e_maybe_stop_tx - 1st level check for tx stop conditions - * @tx_ring: the ring to be checked - * @size: the size buffer we want to assure is available - * - * Returns 0 if stop is not needed - **/ -static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) -{ - if (likely(I40E_DESC_UNUSED(tx_ring) >= size)) - return 0; - return __i40e_maybe_stop_tx(tx_ring, size); -} - -/** - * i40e_xmit_descriptor_count - calculate number of tx descriptors needed + * i40evf_xmit_descriptor_count - calculate number of tx descriptors needed * @skb: send buffer * @tx_ring: ring to send buffer on * @@ -1879,8 +1871,8 @@ static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) * there is not enough descriptors available in this ring since we need at least * one descriptor. **/ -static int i40e_xmit_descriptor_count(struct sk_buff *skb, - struct i40e_ring *tx_ring) +static inline int i40evf_xmit_descriptor_count(struct sk_buff *skb, + struct i40e_ring *tx_ring) { unsigned int f; int count = 0; @@ -1895,7 +1887,7 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb, count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); count += TXD_USE_COUNT(skb_headlen(skb)); - if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) { + if (i40evf_maybe_stop_tx(tx_ring, count + 4 + 1)) { tx_ring->tx_stats.tx_busy++; return 0; } @@ -1921,11 +1913,11 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, u32 td_cmd = 0; u8 hdr_len = 0; int tso; - if (0 == i40e_xmit_descriptor_count(skb, tx_ring)) + if (0 == i40evf_xmit_descriptor_count(skb, tx_ring)) return NETDEV_TX_BUSY; /* prepare the xmit flags */ - if (i40e_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags)) + if (i40evf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags)) goto out_drop; /* obtain protocol of skb */ @@ -1940,7 +1932,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, else if (protocol == htons(ETH_P_IPV6)) tx_flags |= I40E_TX_FLAGS_IPV6; - tso = i40e_tso(tx_ring, skb, tx_flags, protocol, &hdr_len, + tso = i40e_tso(tx_ring, skb, &hdr_len, &cd_type_cmd_tso_mss, &cd_tunneling); if (tso < 0) @@ -1961,17 +1953,15 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_PARTIAL) { tx_flags |= I40E_TX_FLAGS_CSUM; - i40e_tx_enable_csum(skb, tx_flags, &td_cmd, &td_offset, + i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset, tx_ring, &cd_tunneling); } i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss, cd_tunneling, cd_l2tag2); - i40e_tx_map(tx_ring, skb, first, tx_flags, hdr_len, - td_cmd, td_offset); - - i40e_maybe_stop_tx(tx_ring, DESC_NEEDED); + i40evf_tx_map(tx_ring, skb, first, tx_flags, hdr_len, + td_cmd, td_offset); return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 1e49bb1..e7a34f8 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -138,6 +138,7 @@ enum i40e_dyn_idx_t { #define I40E_TX_FLAGS_FCCRC (u32)(1 << 6) #define I40E_TX_FLAGS_FSO (u32)(1 << 7) #define I40E_TX_FLAGS_FD_SB (u32)(1 << 9) +#define I40E_TX_FLAGS_VXLAN_TUNNEL (u32)(1 << 10) #define I40E_TX_FLAGS_VLAN_MASK 0xffff0000 #define I40E_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 #define I40E_TX_FLAGS_VLAN_PRIO_SHIFT 29 @@ -145,7 +146,6 @@ enum i40e_dyn_idx_t { struct i40e_tx_buffer { struct i40e_tx_desc *next_to_watch; - unsigned long time_stamp; union { struct sk_buff *skb; void *raw_buf; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index ec9d83a..c463ec4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -1108,6 +1108,7 @@ struct i40e_hw_port_stats { /* flow director stats */ u64 fd_atr_match; u64 fd_sb_match; + u64 fd_atr_tunnel_match; /* EEE LPI */ u32 tx_lpi_status; u32 rx_lpi_status; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 9f6fb19..9a1d0f1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2594,18 +2594,35 @@ static int ixgbe_add_ethtool_fdir_entry(struct ixgbe_adapter *adapter, struct ixgbe_hw *hw = &adapter->hw; struct ixgbe_fdir_filter *input; union ixgbe_atr_input mask; + u8 queue; int err; if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) return -EOPNOTSUPP; - /* - * Don't allow programming if the action is a queue greater than - * the number of online Rx queues. + /* ring_cookie is a masked into a set of queues and ixgbe pools or + * we use the drop index. */ - if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) && - (fsp->ring_cookie >= adapter->num_rx_queues)) - return -EINVAL; + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) { + queue = IXGBE_FDIR_DROP_QUEUE; + } else { + u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie); + u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie); + + if (!vf && (ring >= adapter->num_rx_queues)) + return -EINVAL; + else if (vf && + ((vf > adapter->num_vfs) || + ring >= adapter->num_rx_queues_per_pool)) + return -EINVAL; + + /* Map the ring onto the absolute queue index */ + if (!vf) + queue = adapter->rx_ring[ring]->reg_idx; + else + queue = ((vf - 1) * + adapter->num_rx_queues_per_pool) + ring; + } /* Don't allow indexes to exist outside of available space */ if (fsp->location >= ((1024 << adapter->fdir_pballoc) - 2)) { @@ -2683,10 +2700,7 @@ static int ixgbe_add_ethtool_fdir_entry(struct ixgbe_adapter *adapter, /* program filters to filter memory */ err = ixgbe_fdir_write_perfect_filter_82599(hw, - &input->filter, input->sw_idx, - (input->action == IXGBE_FDIR_DROP_QUEUE) ? - IXGBE_FDIR_DROP_QUEUE : - adapter->rx_ring[input->action]->reg_idx); + &input->filter, input->sw_idx, queue); if (err) goto err_out_w_lock; diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 1c75829..d52639b 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -3125,9 +3125,8 @@ static int mv643xx_eth_probe(struct platform_device *pdev) mib_counters_clear(mp); - init_timer(&mp->mib_counters_timer); - mp->mib_counters_timer.data = (unsigned long)mp; - mp->mib_counters_timer.function = mib_counters_timer_wrapper; + setup_timer(&mp->mib_counters_timer, mib_counters_timer_wrapper, + (unsigned long)mp); mp->mib_counters_timer.expires = jiffies + 30 * HZ; spin_lock_init(&mp->mib_counters_lock); @@ -3136,9 +3135,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev) netif_napi_add(dev, &mp->napi, mv643xx_eth_poll, NAPI_POLL_WEIGHT); - init_timer(&mp->rx_oom); - mp->rx_oom.data = (unsigned long)mp; - mp->rx_oom.function = oom_timer_wrapper; + setup_timer(&mp->rx_oom, oom_timer_wrapper, (unsigned long)mp); res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 7761045..68ae765 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -714,8 +714,13 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param, msecs_to_jiffies(timeout))) { mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n", op); - err = -EIO; - goto out_reset; + if (op == MLX4_CMD_NOP) { + err = -EBUSY; + goto out; + } else { + err = -EIO; + goto out_reset; + } } err = context->result; @@ -2912,7 +2917,7 @@ int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac) port = mlx4_slaves_closest_port(dev, slave, port); s_info = &priv->mfunc.master.vf_admin[slave].vport[port]; s_info->mac = mac; - mlx4_info(dev, "default mac on vf %d port %d to %llX will take afect only after vf restart\n", + mlx4_info(dev, "default mac on vf %d port %d to %llX will take effect only after vf restart\n", vf, port, s_info->mac); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index e71f313..3348e64 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -292,7 +292,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, u64 mtt_addr; int err; - if (vector > dev->caps.num_comp_vectors + dev->caps.comp_pool) + if (vector >= dev->caps.num_comp_vectors) return -EINVAL; cq->vector = vector; @@ -319,7 +319,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, cq_context->flags |= cpu_to_be32(1 << 19); cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index); - cq_context->comp_eqn = priv->eq_table.eq[vector].eqn; + cq_context->comp_eqn = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn; cq_context->log_page_size = mtt->page_shift - MLX4_ICM_PAGE_SHIFT; mtt_addr = mlx4_mtt_addr(dev, mtt); @@ -339,11 +339,11 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, init_completion(&cq->free); cq->comp = mlx4_add_cq_to_tasklet; cq->tasklet_ctx.priv = - &priv->eq_table.eq[cq->vector].tasklet_ctx; + &priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].tasklet_ctx; INIT_LIST_HEAD(&cq->tasklet_ctx.list); - cq->irq = priv->eq_table.eq[cq->vector].irq; + cq->irq = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].irq; return 0; err_radix: @@ -368,7 +368,10 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq) if (err) mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn); - synchronize_irq(priv->eq_table.eq[cq->vector].irq); + synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq); + if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq != + priv->eq_table.eq[MLX4_EQ_ASYNC].irq) + synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq); spin_lock_irq(&cq_table->lock); radix_tree_delete(&cq_table->tree, cq->cqn); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 22da4d0..63769df 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -66,6 +66,7 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv, cq->ring = ring; cq->is_tx = mode; + cq->vector = mdev->dev->caps.num_comp_vectors; /* Allocate HW buffers on provided NUMA node. * dev->numa_node is used in mtt range allocation flow. @@ -101,12 +102,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, int err = 0; char name[25]; int timestamp_en = 0; - struct cpu_rmap *rmap = -#ifdef CONFIG_RFS_ACCEL - priv->dev->rx_cpu_rmap; -#else - NULL; -#endif + bool assigned_eq = false; cq->dev = mdev->pndev[priv->port]; cq->mcq.set_ci_db = cq->wqres.db.db; @@ -116,23 +112,19 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, memset(cq->buf, 0, cq->buf_size); if (cq->is_tx == RX) { - if (mdev->dev->caps.comp_pool) { - if (!cq->vector) { - sprintf(name, "%s-%d", priv->dev->name, - cq->ring); - /* Set IRQ for specific name (per ring) */ - if (mlx4_assign_eq(mdev->dev, name, rmap, - &cq->vector)) { - cq->vector = (cq->ring + 1 + priv->port) - % mdev->dev->caps.num_comp_vectors; - mlx4_warn(mdev, "Failed assigning an EQ to %s, falling back to legacy EQ's\n", - name); - } - + if (!mlx4_is_eq_vector_valid(mdev->dev, priv->port, + cq->vector)) { + cq->vector = cpumask_first(priv->rx_ring[cq->ring]->affinity_mask); + + err = mlx4_assign_eq(mdev->dev, priv->port, + &cq->vector); + if (err) { + mlx4_err(mdev, "Failed assigning an EQ to %s\n", + name); + goto free_eq; } - } else { - cq->vector = (cq->ring + 1 + priv->port) % - mdev->dev->caps.num_comp_vectors; + + assigned_eq = true; } cq->irq_desc = @@ -159,7 +151,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, &mdev->priv_uar, cq->wqres.db.dma, &cq->mcq, cq->vector, 0, timestamp_en); if (err) - return err; + goto free_eq; cq->mcq.comp = cq->is_tx ? mlx4_en_tx_irq : mlx4_en_rx_irq; cq->mcq.event = mlx4_en_cq_event; @@ -168,13 +160,6 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq, NAPI_POLL_WEIGHT); } else { - struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring]; - - err = irq_set_affinity_hint(cq->mcq.irq, - ring->affinity_mask); - if (err) - mlx4_warn(mdev, "Failed setting affinity hint\n"); - netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq, 64); napi_hash_add(&cq->napi); } @@ -182,6 +167,12 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, napi_enable(&cq->napi); return 0; + +free_eq: + if (assigned_eq) + mlx4_release_eq(mdev->dev, cq->vector); + cq->vector = mdev->dev->caps.num_comp_vectors; + return err; } void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq) @@ -191,9 +182,9 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq) mlx4_en_unmap_buffer(&cq->wqres.buf); mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size); - if (priv->mdev->dev->caps.comp_pool && cq->vector) { + if (mlx4_is_eq_vector_valid(mdev->dev, priv->port, cq->vector) && + cq->is_tx == RX) mlx4_release_eq(priv->mdev->dev, cq->vector); - } cq->vector = 0; cq->buf_size = 0; cq->buf = NULL; @@ -207,7 +198,6 @@ void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq) if (!cq->is_tx) { napi_hash_del(&cq->napi); synchronize_rcu(); - irq_set_affinity_hint(cq->mcq.irq, NULL); } netif_napi_del(&cq->napi); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 32f5ec7..98efb58 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1501,17 +1501,13 @@ static int mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx) { struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx]; int numa_node = priv->mdev->dev->numa_node; - int ret = 0; if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL)) return -ENOMEM; - ret = cpumask_set_cpu_local_first(ring_idx, numa_node, - ring->affinity_mask); - if (ret) - free_cpumask_var(ring->affinity_mask); - - return ret; + cpumask_set_cpu(cpumask_local_spread(ring_idx, numa_node), + ring->affinity_mask); + return 0; } static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx) @@ -1958,7 +1954,6 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv) int i; #ifdef CONFIG_RFS_ACCEL - free_irq_cpu_rmap(priv->dev->rx_cpu_rmap); priv->dev->rx_cpu_rmap = NULL; #endif @@ -2016,11 +2011,7 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv) } #ifdef CONFIG_RFS_ACCEL - if (priv->mdev->dev->caps.comp_pool) { - priv->dev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->mdev->dev->caps.comp_pool); - if (!priv->dev->rx_cpu_rmap) - goto err; - } + priv->dev->rx_cpu_rmap = mlx4_get_cpu_rmap(priv->mdev->dev, priv->port); #endif return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 2a77a6b..35f726c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -337,15 +337,10 @@ void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev) struct mlx4_dev *dev = mdev->dev; mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) { - if (!dev->caps.comp_pool) - num_of_eqs = max_t(int, MIN_RX_RINGS, - min_t(int, - dev->caps.num_comp_vectors, - DEF_RX_RINGS)); - else - num_of_eqs = min_t(int, MAX_MSIX_P_PORT, - dev->caps.comp_pool/ - dev->caps.num_ports) - 1; + num_of_eqs = max_t(int, MIN_RX_RINGS, + min_t(int, + mlx4_get_eqs_per_port(mdev->dev, i), + DEF_RX_RINGS)); num_rx_rings = mlx4_low_memory_profile() ? MIN_RX_RINGS : min_t(int, num_of_eqs, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index f7bf312..7bed3a8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -144,9 +144,9 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, ring->queue_index = queue_index; if (queue_index < priv->num_tx_rings_p_up) - cpumask_set_cpu_local_first(queue_index, - priv->mdev->dev->numa_node, - &ring->affinity_mask); + cpumask_set_cpu(cpumask_local_spread(queue_index, + priv->mdev->dev->numa_node), + &ring->affinity_mask); *pring = ring; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 80bcd64..aae13ad 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -221,6 +221,22 @@ static void mlx4_slave_event(struct mlx4_dev *dev, int slave, slave_event(dev, slave, eqe); } +#if defined(CONFIG_SMP) +static void mlx4_set_eq_affinity_hint(struct mlx4_priv *priv, int vec) +{ + int hint_err; + struct mlx4_dev *dev = &priv->dev; + struct mlx4_eq *eq = &priv->eq_table.eq[vec]; + + if (!eq->affinity_mask || cpumask_empty(eq->affinity_mask)) + return; + + hint_err = irq_set_affinity_hint(eq->irq, eq->affinity_mask); + if (hint_err) + mlx4_warn(dev, "irq_set_affinity_hint failed, err %d\n", hint_err); +} +#endif + int mlx4_gen_pkey_eqe(struct mlx4_dev *dev, int slave, u8 port) { struct mlx4_eqe eqe; @@ -895,8 +911,8 @@ static int mlx4_num_eq_uar(struct mlx4_dev *dev) * we need to map, take the difference of highest index and * the lowest index we'll use and add 1. */ - return (dev->caps.num_comp_vectors + 1 + dev->caps.reserved_eqs + - dev->caps.comp_pool)/4 - dev->caps.reserved_eqs/4 + 1; + return (dev->caps.num_comp_vectors + 1 + dev->caps.reserved_eqs) / 4 - + dev->caps.reserved_eqs / 4 + 1; } static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq) @@ -1085,32 +1101,21 @@ static void mlx4_free_eq(struct mlx4_dev *dev, static void mlx4_free_irqs(struct mlx4_dev *dev) { struct mlx4_eq_table *eq_table = &mlx4_priv(dev)->eq_table; - struct mlx4_priv *priv = mlx4_priv(dev); - int i, vec; + int i; if (eq_table->have_irq) free_irq(dev->persist->pdev->irq, dev); for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) if (eq_table->eq[i].have_irq) { + free_cpumask_var(eq_table->eq[i].affinity_mask); +#if defined(CONFIG_SMP) + irq_set_affinity_hint(eq_table->eq[i].irq, NULL); +#endif free_irq(eq_table->eq[i].irq, eq_table->eq + i); eq_table->eq[i].have_irq = 0; } - for (i = 0; i < dev->caps.comp_pool; i++) { - /* - * Freeing the assigned irq's - * all bits should be 0, but we need to validate - */ - if (priv->msix_ctl.pool_bm & 1ULL << i) { - /* NO need protecting*/ - vec = dev->caps.num_comp_vectors + 1 + i; - free_irq(priv->eq_table.eq[vec].irq, - &priv->eq_table.eq[vec]); - } - } - - kfree(eq_table->irq_names); } @@ -1191,76 +1196,73 @@ int mlx4_init_eq_table(struct mlx4_dev *dev) } priv->eq_table.irq_names = - kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1 + - dev->caps.comp_pool), + kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1), GFP_KERNEL); if (!priv->eq_table.irq_names) { err = -ENOMEM; - goto err_out_bitmap; + goto err_out_clr_int; } - for (i = 0; i < dev->caps.num_comp_vectors; ++i) { - err = mlx4_create_eq(dev, dev->caps.num_cqs - - dev->caps.reserved_cqs + - MLX4_NUM_SPARE_EQE, - (dev->flags & MLX4_FLAG_MSI_X) ? i : 0, - &priv->eq_table.eq[i]); - if (err) { - --i; - goto err_out_unmap; - } - } - - err = mlx4_create_eq(dev, MLX4_NUM_ASYNC_EQE + MLX4_NUM_SPARE_EQE, - (dev->flags & MLX4_FLAG_MSI_X) ? dev->caps.num_comp_vectors : 0, - &priv->eq_table.eq[dev->caps.num_comp_vectors]); - if (err) - goto err_out_comp; - - /*if additional completion vectors poolsize is 0 this loop will not run*/ - for (i = dev->caps.num_comp_vectors + 1; - i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i) { + for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) { + if (i == MLX4_EQ_ASYNC) { + err = mlx4_create_eq(dev, + MLX4_NUM_ASYNC_EQE + MLX4_NUM_SPARE_EQE, + 0, &priv->eq_table.eq[MLX4_EQ_ASYNC]); + } else { + struct mlx4_eq *eq = &priv->eq_table.eq[i]; +#ifdef CONFIG_RFS_ACCEL + int port = find_first_bit(eq->actv_ports.ports, + dev->caps.num_ports) + 1; + + if (port <= dev->caps.num_ports) { + struct mlx4_port_info *info = + &mlx4_priv(dev)->port[port]; + + if (!info->rmap) { + info->rmap = alloc_irq_cpu_rmap( + mlx4_get_eqs_per_port(dev, port)); + if (!info->rmap) { + mlx4_warn(dev, "Failed to allocate cpu rmap\n"); + err = -ENOMEM; + goto err_out_unmap; + } + } - err = mlx4_create_eq(dev, dev->caps.num_cqs - - dev->caps.reserved_cqs + - MLX4_NUM_SPARE_EQE, - (dev->flags & MLX4_FLAG_MSI_X) ? i : 0, - &priv->eq_table.eq[i]); - if (err) { - --i; - goto err_out_unmap; + err = irq_cpu_rmap_add( + info->rmap, eq->irq); + if (err) + mlx4_warn(dev, "Failed adding irq rmap\n"); + } +#endif + err = mlx4_create_eq(dev, dev->caps.num_cqs - + dev->caps.reserved_cqs + + MLX4_NUM_SPARE_EQE, + (dev->flags & MLX4_FLAG_MSI_X) ? + i + 1 - !!(i > MLX4_EQ_ASYNC) : 0, + eq); } + if (err) + goto err_out_unmap; } - if (dev->flags & MLX4_FLAG_MSI_X) { const char *eq_name; - for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) { - if (i < dev->caps.num_comp_vectors) { - snprintf(priv->eq_table.irq_names + - i * MLX4_IRQNAME_SIZE, - MLX4_IRQNAME_SIZE, - "mlx4-comp-%d@pci:%s", i, - pci_name(dev->persist->pdev)); - } else { - snprintf(priv->eq_table.irq_names + - i * MLX4_IRQNAME_SIZE, - MLX4_IRQNAME_SIZE, - "mlx4-async@pci:%s", - pci_name(dev->persist->pdev)); - } + snprintf(priv->eq_table.irq_names + + MLX4_EQ_ASYNC * MLX4_IRQNAME_SIZE, + MLX4_IRQNAME_SIZE, + "mlx4-async@pci:%s", + pci_name(dev->persist->pdev)); + eq_name = priv->eq_table.irq_names + + MLX4_EQ_ASYNC * MLX4_IRQNAME_SIZE; - eq_name = priv->eq_table.irq_names + - i * MLX4_IRQNAME_SIZE; - err = request_irq(priv->eq_table.eq[i].irq, - mlx4_msi_x_interrupt, 0, eq_name, - priv->eq_table.eq + i); - if (err) - goto err_out_async; + err = request_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq, + mlx4_msi_x_interrupt, 0, eq_name, + priv->eq_table.eq + MLX4_EQ_ASYNC); + if (err) + goto err_out_unmap; - priv->eq_table.eq[i].have_irq = 1; - } + priv->eq_table.eq[MLX4_EQ_ASYNC].have_irq = 1; } else { snprintf(priv->eq_table.irq_names, MLX4_IRQNAME_SIZE, @@ -1269,36 +1271,38 @@ int mlx4_init_eq_table(struct mlx4_dev *dev) err = request_irq(dev->persist->pdev->irq, mlx4_interrupt, IRQF_SHARED, priv->eq_table.irq_names, dev); if (err) - goto err_out_async; + goto err_out_unmap; priv->eq_table.have_irq = 1; } err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0, - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn); + priv->eq_table.eq[MLX4_EQ_ASYNC].eqn); if (err) mlx4_warn(dev, "MAP_EQ for async EQ %d failed (%d)\n", - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn, err); + priv->eq_table.eq[MLX4_EQ_ASYNC].eqn, err); - for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) - eq_set_ci(&priv->eq_table.eq[i], 1); + /* arm ASYNC eq */ + eq_set_ci(&priv->eq_table.eq[MLX4_EQ_ASYNC], 1); return 0; -err_out_async: - mlx4_free_eq(dev, &priv->eq_table.eq[dev->caps.num_comp_vectors]); - -err_out_comp: - i = dev->caps.num_comp_vectors - 1; - err_out_unmap: - while (i >= 0) { - mlx4_free_eq(dev, &priv->eq_table.eq[i]); - --i; + while (i >= 0) + mlx4_free_eq(dev, &priv->eq_table.eq[i--]); +#ifdef CONFIG_RFS_ACCEL + for (i = 1; i <= dev->caps.num_ports; i++) { + if (mlx4_priv(dev)->port[i].rmap) { + free_irq_cpu_rmap(mlx4_priv(dev)->port[i].rmap); + mlx4_priv(dev)->port[i].rmap = NULL; + } } +#endif + mlx4_free_irqs(dev); + +err_out_clr_int: if (!mlx4_is_slave(dev)) mlx4_unmap_clr_int(dev); - mlx4_free_irqs(dev); err_out_bitmap: mlx4_unmap_uar(dev); @@ -1316,11 +1320,19 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev) int i; mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 1, - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn); + priv->eq_table.eq[MLX4_EQ_ASYNC].eqn); +#ifdef CONFIG_RFS_ACCEL + for (i = 1; i <= dev->caps.num_ports; i++) { + if (mlx4_priv(dev)->port[i].rmap) { + free_irq_cpu_rmap(mlx4_priv(dev)->port[i].rmap); + mlx4_priv(dev)->port[i].rmap = NULL; + } + } +#endif mlx4_free_irqs(dev); - for (i = 0; i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i) + for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) mlx4_free_eq(dev, &priv->eq_table.eq[i]); if (!mlx4_is_slave(dev)) @@ -1371,87 +1383,169 @@ int mlx4_test_interrupts(struct mlx4_dev *dev) /* Return to default */ mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0, - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn); + priv->eq_table.eq[MLX4_EQ_ASYNC].eqn); return err; } EXPORT_SYMBOL(mlx4_test_interrupts); -int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, - int *vector) +bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + vector = MLX4_CQ_TO_EQ_VECTOR(vector); + if (vector < 0 || (vector >= dev->caps.num_comp_vectors + 1) || + (vector == MLX4_EQ_ASYNC)) + return false; + + return test_bit(port - 1, priv->eq_table.eq[vector].actv_ports.ports); +} +EXPORT_SYMBOL(mlx4_is_eq_vector_valid); + +u32 mlx4_get_eqs_per_port(struct mlx4_dev *dev, u8 port) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + unsigned int i; + unsigned int sum = 0; + + for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) + sum += !!test_bit(port - 1, + priv->eq_table.eq[i].actv_ports.ports); + + return sum; +} +EXPORT_SYMBOL(mlx4_get_eqs_per_port); + +int mlx4_is_eq_shared(struct mlx4_dev *dev, int vector) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + vector = MLX4_CQ_TO_EQ_VECTOR(vector); + if (vector <= 0 || (vector >= dev->caps.num_comp_vectors + 1)) + return -EINVAL; + + return !!(bitmap_weight(priv->eq_table.eq[vector].actv_ports.ports, + dev->caps.num_ports) > 1); +} +EXPORT_SYMBOL(mlx4_is_eq_shared); + +struct cpu_rmap *mlx4_get_cpu_rmap(struct mlx4_dev *dev, int port) { + return mlx4_priv(dev)->port[port].rmap; +} +EXPORT_SYMBOL(mlx4_get_cpu_rmap); +int mlx4_assign_eq(struct mlx4_dev *dev, u8 port, int *vector) +{ struct mlx4_priv *priv = mlx4_priv(dev); - int vec = 0, err = 0, i; + int err = 0, i = 0; + u32 min_ref_count_val = (u32)-1; + int requested_vector = MLX4_CQ_TO_EQ_VECTOR(*vector); + int *prequested_vector = NULL; + mutex_lock(&priv->msix_ctl.pool_lock); - for (i = 0; !vec && i < dev->caps.comp_pool; i++) { - if (~priv->msix_ctl.pool_bm & 1ULL << i) { - priv->msix_ctl.pool_bm |= 1ULL << i; - vec = dev->caps.num_comp_vectors + 1 + i; - snprintf(priv->eq_table.irq_names + - vec * MLX4_IRQNAME_SIZE, - MLX4_IRQNAME_SIZE, "%s", name); -#ifdef CONFIG_RFS_ACCEL - if (rmap) { - err = irq_cpu_rmap_add(rmap, - priv->eq_table.eq[vec].irq); - if (err) - mlx4_warn(dev, "Failed adding irq rmap\n"); + if (requested_vector < (dev->caps.num_comp_vectors + 1) && + (requested_vector >= 0) && + (requested_vector != MLX4_EQ_ASYNC)) { + if (test_bit(port - 1, + priv->eq_table.eq[requested_vector].actv_ports.ports)) { + prequested_vector = &requested_vector; + } else { + struct mlx4_eq *eq; + + for (i = 1; i < port; + requested_vector += mlx4_get_eqs_per_port(dev, i++)) + ; + + eq = &priv->eq_table.eq[requested_vector]; + if (requested_vector < dev->caps.num_comp_vectors + 1 && + test_bit(port - 1, eq->actv_ports.ports)) { + prequested_vector = &requested_vector; } -#endif - err = request_irq(priv->eq_table.eq[vec].irq, - mlx4_msi_x_interrupt, 0, - &priv->eq_table.irq_names[vec<<5], - priv->eq_table.eq + vec); - if (err) { - /*zero out bit by fliping it*/ - priv->msix_ctl.pool_bm ^= 1 << i; - vec = 0; - continue; - /*we dont want to break here*/ + } + } + + if (!prequested_vector) { + requested_vector = -1; + for (i = 0; min_ref_count_val && i < dev->caps.num_comp_vectors + 1; + i++) { + struct mlx4_eq *eq = &priv->eq_table.eq[i]; + + if (min_ref_count_val > eq->ref_count && + test_bit(port - 1, eq->actv_ports.ports)) { + min_ref_count_val = eq->ref_count; + requested_vector = i; } + } + + if (requested_vector < 0) { + err = -ENOSPC; + goto err_unlock; + } + + prequested_vector = &requested_vector; + } + + if (!test_bit(*prequested_vector, priv->msix_ctl.pool_bm) && + dev->flags & MLX4_FLAG_MSI_X) { + set_bit(*prequested_vector, priv->msix_ctl.pool_bm); + snprintf(priv->eq_table.irq_names + + *prequested_vector * MLX4_IRQNAME_SIZE, + MLX4_IRQNAME_SIZE, "mlx4-%d@%s", + *prequested_vector, dev_name(&dev->persist->pdev->dev)); + + err = request_irq(priv->eq_table.eq[*prequested_vector].irq, + mlx4_msi_x_interrupt, 0, + &priv->eq_table.irq_names[*prequested_vector << 5], + priv->eq_table.eq + *prequested_vector); - eq_set_ci(&priv->eq_table.eq[vec], 1); + if (err) { + clear_bit(*prequested_vector, priv->msix_ctl.pool_bm); + *prequested_vector = -1; + } else { +#if defined(CONFIG_SMP) + mlx4_set_eq_affinity_hint(priv, *prequested_vector); +#endif + eq_set_ci(&priv->eq_table.eq[*prequested_vector], 1); + priv->eq_table.eq[*prequested_vector].have_irq = 1; } } + + if (!err && *prequested_vector >= 0) + priv->eq_table.eq[*prequested_vector].ref_count++; + +err_unlock: mutex_unlock(&priv->msix_ctl.pool_lock); - if (vec) { - *vector = vec; - } else { + if (!err && *prequested_vector >= 0) + *vector = MLX4_EQ_TO_CQ_VECTOR(*prequested_vector); + else *vector = 0; - err = (i == dev->caps.comp_pool) ? -ENOSPC : err; - } + return err; } EXPORT_SYMBOL(mlx4_assign_eq); -int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec) +int mlx4_eq_get_irq(struct mlx4_dev *dev, int cq_vec) { struct mlx4_priv *priv = mlx4_priv(dev); - return priv->eq_table.eq[vec].irq; + return priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq_vec)].irq; } EXPORT_SYMBOL(mlx4_eq_get_irq); void mlx4_release_eq(struct mlx4_dev *dev, int vec) { struct mlx4_priv *priv = mlx4_priv(dev); - /*bm index*/ - int i = vec - dev->caps.num_comp_vectors - 1; - - if (likely(i >= 0)) { - /*sanity check , making sure were not trying to free irq's - Belonging to a legacy EQ*/ - mutex_lock(&priv->msix_ctl.pool_lock); - if (priv->msix_ctl.pool_bm & 1ULL << i) { - free_irq(priv->eq_table.eq[vec].irq, - &priv->eq_table.eq[vec]); - priv->msix_ctl.pool_bm &= ~(1ULL << i); - } - mutex_unlock(&priv->msix_ctl.pool_lock); - } + int eq_vec = MLX4_CQ_TO_EQ_VECTOR(vec); + mutex_lock(&priv->msix_ctl.pool_lock); + priv->eq_table.eq[eq_vec].ref_count--; + + /* once we allocated EQ, we don't release it because it might be binded + * to cpu_rmap. + */ + mutex_unlock(&priv->msix_ctl.pool_lock); } EXPORT_SYMBOL(mlx4_release_eq); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 70d33f6..7d57777 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2364,11 +2364,11 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) if (err) { if (dev->flags & MLX4_FLAG_MSI_X) { mlx4_warn(dev, "NOP command failed to generate MSI-X interrupt IRQ %d)\n", - priv->eq_table.eq[dev->caps.num_comp_vectors].irq); + priv->eq_table.eq[MLX4_EQ_ASYNC].irq); mlx4_warn(dev, "Trying again without MSI-X\n"); } else { mlx4_err(dev, "NOP command failed to generate interrupt (IRQ %d), aborting\n", - priv->eq_table.eq[dev->caps.num_comp_vectors].irq); + priv->eq_table.eq[MLX4_EQ_ASYNC].irq); mlx4_err(dev, "BIOS or ACPI interrupt routing problem?\n"); } @@ -2481,14 +2481,45 @@ err_uar_table_free: return err; } +static int mlx4_init_affinity_hint(struct mlx4_dev *dev, int port, int eqn) +{ + int requested_cpu = 0; + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_eq *eq; + int off = 0; + int i; + + if (eqn > dev->caps.num_comp_vectors) + return -EINVAL; + + for (i = 1; i < port; i++) + off += mlx4_get_eqs_per_port(dev, i); + + requested_cpu = eqn - off - !!(eqn > MLX4_EQ_ASYNC); + + /* Meaning EQs are shared, and this call comes from the second port */ + if (requested_cpu < 0) + return 0; + + eq = &priv->eq_table.eq[eqn]; + + if (!zalloc_cpumask_var(&eq->affinity_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_set_cpu(requested_cpu, eq->affinity_mask); + + return 0; +} + static void mlx4_enable_msi_x(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); struct msix_entry *entries; int i; + int port = 0; if (msi_x) { - int nreq = dev->caps.num_ports * num_online_cpus() + MSIX_LEGACY_SZ; + int nreq = dev->caps.num_ports * num_online_cpus() + 1; nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs, nreq); @@ -2503,20 +2534,55 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) nreq = pci_enable_msix_range(dev->persist->pdev, entries, 2, nreq); - if (nreq < 0) { + if (nreq < 0 || nreq < MLX4_EQ_ASYNC) { kfree(entries); goto no_msi; - } else if (nreq < MSIX_LEGACY_SZ + - dev->caps.num_ports * MIN_MSIX_P_PORT) { - /*Working in legacy mode , all EQ's shared*/ - dev->caps.comp_pool = 0; - dev->caps.num_comp_vectors = nreq - 1; - } else { - dev->caps.comp_pool = nreq - MSIX_LEGACY_SZ; - dev->caps.num_comp_vectors = MSIX_LEGACY_SZ - 1; } - for (i = 0; i < nreq; ++i) - priv->eq_table.eq[i].irq = entries[i].vector; + /* 1 is reserved for events (asyncrounous EQ) */ + dev->caps.num_comp_vectors = nreq - 1; + + priv->eq_table.eq[MLX4_EQ_ASYNC].irq = entries[0].vector; + bitmap_zero(priv->eq_table.eq[MLX4_EQ_ASYNC].actv_ports.ports, + dev->caps.num_ports); + + for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) { + if (i == MLX4_EQ_ASYNC) + continue; + + priv->eq_table.eq[i].irq = + entries[i + 1 - !!(i > MLX4_EQ_ASYNC)].vector; + + if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) { + bitmap_fill(priv->eq_table.eq[i].actv_ports.ports, + dev->caps.num_ports); + /* We don't set affinity hint when there + * aren't enough EQs + */ + } else { + set_bit(port, + priv->eq_table.eq[i].actv_ports.ports); + if (mlx4_init_affinity_hint(dev, port + 1, i)) + mlx4_warn(dev, "Couldn't init hint cpumask for EQ %d\n", + i); + } + /* We divide the Eqs evenly between the two ports. + * (dev->caps.num_comp_vectors / dev->caps.num_ports) + * refers to the number of Eqs per port + * (i.e eqs_per_port). Theoretically, we would like to + * write something like (i + 1) % eqs_per_port == 0. + * However, since there's an asynchronous Eq, we have + * to skip over it by comparing this condition to + * !!((i + 1) > MLX4_EQ_ASYNC). + */ + if ((dev->caps.num_comp_vectors > dev->caps.num_ports) && + ((i + 1) % + (dev->caps.num_comp_vectors / dev->caps.num_ports)) == + !!((i + 1) > MLX4_EQ_ASYNC)) + /* If dev->caps.num_comp_vectors < dev->caps.num_ports, + * everything is shared anyway. + */ + port++; + } dev->flags |= MLX4_FLAG_MSI_X; @@ -2526,10 +2592,15 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) no_msi: dev->caps.num_comp_vectors = 1; - dev->caps.comp_pool = 0; - for (i = 0; i < 2; ++i) + BUG_ON(MLX4_EQ_ASYNC >= 2); + for (i = 0; i < 2; ++i) { priv->eq_table.eq[i].irq = dev->persist->pdev->irq; + if (i != MLX4_EQ_ASYNC) { + bitmap_fill(priv->eq_table.eq[i].actv_ports.ports, + dev->caps.num_ports); + } + } } static int mlx4_init_port_info(struct mlx4_dev *dev, int port) @@ -2594,6 +2665,10 @@ static void mlx4_cleanup_port_info(struct mlx4_port_info *info) device_remove_file(&info->dev->persist->pdev->dev, &info->port_attr); device_remove_file(&info->dev->persist->pdev->dev, &info->port_mtu_attr); +#ifdef CONFIG_RFS_ACCEL + free_irq_cpu_rmap(info->rmap); + info->rmap = NULL; +#endif } static int mlx4_init_steering(struct mlx4_dev *dev) @@ -2749,6 +2824,7 @@ disable_sriov: free_mem: dev->persist->num_vfs = 0; kfree(dev->dev_vfs); + dev->dev_vfs = NULL; return dev_flags & ~MLX4_FLAG_MASTER; } @@ -2900,6 +2976,7 @@ slave_start: existing_vfs, reset_flow); + mlx4_close_fw(dev); mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_ALL); dev->flags = dev_flags; if (!SRIOV_VALID_STATE(dev->flags)) { @@ -3024,7 +3101,7 @@ slave_start: if (err) goto err_master_mfunc; - priv->msix_ctl.pool_bm = 0; + bitmap_zero(priv->msix_ctl.pool_bm, MAX_MSIX); mutex_init(&priv->msix_ctl.pool_lock); mlx4_enable_msi_x(dev); @@ -3046,7 +3123,6 @@ slave_start: !mlx4_is_mfunc(dev)) { dev->flags &= ~MLX4_FLAG_MSI_X; dev->caps.num_comp_vectors = 1; - dev->caps.comp_pool = 0; pci_disable_msix(pdev); err = mlx4_setup_hca(dev); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 502d3dd..f424900 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -287,6 +287,12 @@ struct mlx4_icm_table { #define MLX4_CQE_SIZE_MASK_STRIDE 0x3 #define MLX4_EQE_SIZE_MASK_STRIDE 0x30 +#define MLX4_EQ_ASYNC 0 +#define MLX4_EQ_TO_CQ_VECTOR(vector) ((vector) - \ + !!((int)(vector) >= MLX4_EQ_ASYNC)) +#define MLX4_CQ_TO_EQ_VECTOR(vector) ((vector) + \ + !!((int)(vector) >= MLX4_EQ_ASYNC)) + /* * Must be packed because mtt_seg is 64 bits but only aligned to 32 bits. */ @@ -391,6 +397,9 @@ struct mlx4_eq { struct mlx4_buf_list *page_list; struct mlx4_mtt mtt; struct mlx4_eq_tasklet tasklet_ctx; + struct mlx4_active_ports actv_ports; + u32 ref_count; + cpumask_var_t affinity_mask; }; struct mlx4_slave_eqe { @@ -808,6 +817,7 @@ struct mlx4_port_info { struct mlx4_vlan_table vlan_table; struct mlx4_roce_gid_table gid_table; int base_qpn; + struct cpu_rmap *rmap; }; struct mlx4_sense { @@ -818,7 +828,7 @@ struct mlx4_sense { }; struct mlx4_msix_ctl { - u64 pool_bm; + DECLARE_BITMAP(pool_bm, MAX_MSIX); struct mutex pool_lock; }; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index d021f07..edd8fd6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -338,7 +338,7 @@ struct mlx4_en_cq { struct napi_struct napi; int size; int buf_size; - unsigned vector; + int vector; enum cq_type is_tx; u16 moder_time; u16 moder_cnt; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 15ec081..ab48386 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -3973,6 +3973,22 @@ static int validate_eth_header_mac(int slave, struct _rule_hw *eth_header, return 0; } +static void handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl, + struct _rule_hw *eth_header) +{ + if (is_multicast_ether_addr(eth_header->eth.dst_mac) || + is_broadcast_ether_addr(eth_header->eth.dst_mac)) { + struct mlx4_net_trans_rule_hw_eth *eth = + (struct mlx4_net_trans_rule_hw_eth *)eth_header; + struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1); + bool last_rule = next_rule->size == 0 && next_rule->id == 0 && + next_rule->rsvd == 0; + + if (last_rule) + ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC); + } +} + /* * In case of missing eth header, append eth header with a MAC address * assigned to the VF. @@ -4125,6 +4141,12 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, rule_header = (struct _rule_hw *)(ctrl + 1); header_id = map_hw_to_sw_id(be16_to_cpu(rule_header->id)); + if (header_id == MLX4_NET_TRANS_RULE_ID_ETH) + handle_eth_header_mcast_prio(ctrl, rule_header); + + if (slave == dev->caps.function) + goto execute; + switch (header_id) { case MLX4_NET_TRANS_RULE_ID_ETH: if (validate_eth_header_mac(slave, rule_header, rlist)) { @@ -4151,6 +4173,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, goto err_put; } +execute: err = mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param, vhcr->in_modifier, 0, MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 8ff57e8..0d7aef0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -3,6 +3,18 @@ # config MLX5_CORE - tristate + tristate "Mellanox Technologies ConnectX-4 and Connect-IB core driver" depends on PCI default n + ---help--- + Core driver for low level functionality of the ConnectX-4 and + Connect-IB cards by Mellanox Technologies. + +config MLX5_CORE_EN + bool "Mellanox Technologies ConnectX-4 Ethernet support" + depends on MLX5_INFINIBAND=n && NETDEVICES && ETHERNET && PCI && MLX5_CORE + default n + ---help--- + Ethernet support in Mellanox Technologies ConnectX-4 NIC. + Ethernet and Infiniband support in ConnectX-4 are currently mutually + exclusive. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 105780b..87e9e60 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -3,3 +3,6 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \ mad.o +mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o flow_table.o vport.o transobj.o \ + en_main.o en_flow_table.o en_ethtool.o en_tx.o en_rx.o \ + en_txrx.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c index ac0f7bf..0715b49 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c @@ -42,95 +42,36 @@ #include "mlx5_core.h" /* Handling for queue buffers -- we allocate a bunch of memory and - * register it in a memory region at HCA virtual address 0. If the - * requested size is > max_direct, we split the allocation into - * multiple pages, so we don't require too much contiguous memory. + * register it in a memory region at HCA virtual address 0. */ -int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, int max_direct, - struct mlx5_buf *buf) +int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf) { dma_addr_t t; buf->size = size; - if (size <= max_direct) { - buf->nbufs = 1; - buf->npages = 1; - buf->page_shift = (u8)get_order(size) + PAGE_SHIFT; - buf->direct.buf = dma_zalloc_coherent(&dev->pdev->dev, - size, &t, GFP_KERNEL); - if (!buf->direct.buf) - return -ENOMEM; - - buf->direct.map = t; - - while (t & ((1 << buf->page_shift) - 1)) { - --buf->page_shift; - buf->npages *= 2; - } - } else { - int i; - - buf->direct.buf = NULL; - buf->nbufs = (size + PAGE_SIZE - 1) / PAGE_SIZE; - buf->npages = buf->nbufs; - buf->page_shift = PAGE_SHIFT; - buf->page_list = kcalloc(buf->nbufs, sizeof(*buf->page_list), - GFP_KERNEL); - if (!buf->page_list) - return -ENOMEM; - - for (i = 0; i < buf->nbufs; i++) { - buf->page_list[i].buf = - dma_zalloc_coherent(&dev->pdev->dev, PAGE_SIZE, - &t, GFP_KERNEL); - if (!buf->page_list[i].buf) - goto err_free; - - buf->page_list[i].map = t; - } - - if (BITS_PER_LONG == 64) { - struct page **pages; - pages = kmalloc(sizeof(*pages) * buf->nbufs, GFP_KERNEL); - if (!pages) - goto err_free; - for (i = 0; i < buf->nbufs; i++) - pages[i] = virt_to_page(buf->page_list[i].buf); - buf->direct.buf = vmap(pages, buf->nbufs, VM_MAP, PAGE_KERNEL); - kfree(pages); - if (!buf->direct.buf) - goto err_free; - } - } + buf->npages = 1; + buf->page_shift = (u8)get_order(size) + PAGE_SHIFT; + buf->direct.buf = dma_zalloc_coherent(&dev->pdev->dev, + size, &t, GFP_KERNEL); + if (!buf->direct.buf) + return -ENOMEM; - return 0; + buf->direct.map = t; -err_free: - mlx5_buf_free(dev, buf); + while (t & ((1 << buf->page_shift) - 1)) { + --buf->page_shift; + buf->npages *= 2; + } - return -ENOMEM; + return 0; } EXPORT_SYMBOL_GPL(mlx5_buf_alloc); void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf) { - int i; - - if (buf->nbufs == 1) - dma_free_coherent(&dev->pdev->dev, buf->size, buf->direct.buf, - buf->direct.map); - else { - if (BITS_PER_LONG == 64) - vunmap(buf->direct.buf); - - for (i = 0; i < buf->nbufs; i++) - if (buf->page_list[i].buf) - dma_free_coherent(&dev->pdev->dev, PAGE_SIZE, - buf->page_list[i].buf, - buf->page_list[i].map); - kfree(buf->page_list); - } + dma_free_coherent(&dev->pdev->dev, buf->size, buf->direct.buf, + buf->direct.map); } EXPORT_SYMBOL_GPL(mlx5_buf_free); @@ -230,10 +171,7 @@ void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas) int i; for (i = 0; i < buf->npages; i++) { - if (buf->nbufs == 1) - addr = buf->direct.map + (i << buf->page_shift); - else - addr = buf->page_list[i].map; + addr = buf->direct.map + (i << buf->page_shift); pas[i] = cpu_to_be64(addr); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index e3273fa..75ff58d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -75,25 +75,6 @@ enum { MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR = 0x10, }; -enum { - MLX5_CMD_STAT_OK = 0x0, - MLX5_CMD_STAT_INT_ERR = 0x1, - MLX5_CMD_STAT_BAD_OP_ERR = 0x2, - MLX5_CMD_STAT_BAD_PARAM_ERR = 0x3, - MLX5_CMD_STAT_BAD_SYS_STATE_ERR = 0x4, - MLX5_CMD_STAT_BAD_RES_ERR = 0x5, - MLX5_CMD_STAT_RES_BUSY = 0x6, - MLX5_CMD_STAT_LIM_ERR = 0x8, - MLX5_CMD_STAT_BAD_RES_STATE_ERR = 0x9, - MLX5_CMD_STAT_IX_ERR = 0xa, - MLX5_CMD_STAT_NO_RES_ERR = 0xf, - MLX5_CMD_STAT_BAD_INP_LEN_ERR = 0x50, - MLX5_CMD_STAT_BAD_OUTP_LEN_ERR = 0x51, - MLX5_CMD_STAT_BAD_QP_STATE_ERR = 0x10, - MLX5_CMD_STAT_BAD_PKT_ERR = 0x30, - MLX5_CMD_STAT_BAD_SIZE_OUTS_CQES_ERR = 0x40, -}; - static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in, struct mlx5_cmd_msg *out, @@ -390,8 +371,17 @@ const char *mlx5_command_str(int command) case MLX5_CMD_OP_ARM_RQ: return "ARM_RQ"; - case MLX5_CMD_OP_RESIZE_SRQ: - return "RESIZE_SRQ"; + case MLX5_CMD_OP_CREATE_XRC_SRQ: + return "CREATE_XRC_SRQ"; + + case MLX5_CMD_OP_DESTROY_XRC_SRQ: + return "DESTROY_XRC_SRQ"; + + case MLX5_CMD_OP_QUERY_XRC_SRQ: + return "QUERY_XRC_SRQ"; + + case MLX5_CMD_OP_ARM_XRC_SRQ: + return "ARM_XRC_SRQ"; case MLX5_CMD_OP_ALLOC_PD: return "ALLOC_PD"; @@ -408,8 +398,8 @@ const char *mlx5_command_str(int command) case MLX5_CMD_OP_ATTACH_TO_MCG: return "ATTACH_TO_MCG"; - case MLX5_CMD_OP_DETACH_FROM_MCG: - return "DETACH_FROM_MCG"; + case MLX5_CMD_OP_DETTACH_FROM_MCG: + return "DETTACH_FROM_MCG"; case MLX5_CMD_OP_ALLOC_XRCD: return "ALLOC_XRCD"; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index eb0cf81..04ab7e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -219,6 +219,24 @@ int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, } EXPORT_SYMBOL(mlx5_core_modify_cq); +int mlx5_core_modify_cq_moderation(struct mlx5_core_dev *dev, + struct mlx5_core_cq *cq, + u16 cq_period, + u16 cq_max_count) +{ + struct mlx5_modify_cq_mbox_in in; + + memset(&in, 0, sizeof(in)); + + in.cqn = cpu_to_be32(cq->cqn); + in.ctx.cq_period = cpu_to_be16(cq_period); + in.ctx.cq_max_count = cpu_to_be16(cq_max_count); + in.field_select = cpu_to_be32(MLX5_CQ_MODIFY_PERIOD | + MLX5_CQ_MODIFY_COUNT); + + return mlx5_core_modify_cq(dev, cq, &in, sizeof(in)); +} + int mlx5_init_cq_table(struct mlx5_core_dev *dev) { struct mlx5_cq_table *table = &dev->priv.cq_table; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h new file mode 100644 index 0000000..cbb3c7c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -0,0 +1,520 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/if_vlan.h> +#include <linux/etherdevice.h> +#include <linux/mlx5/driver.h> +#include <linux/mlx5/qp.h> +#include <linux/mlx5/cq.h> +#include "vport.h" +#include "wq.h" +#include "transobj.h" +#include "mlx5_core.h" + +#define MLX5E_MAX_NUM_TC 8 + +#define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE 0x7 +#define MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE 0xa +#define MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE 0xd + +#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE 0x7 +#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE 0xa +#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE 0xd + +#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (16 * 1024) +#define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC 0x10 +#define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS 0x20 +#define MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC 0x10 +#define MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS 0x20 +#define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES 0x80 +#define MLX5E_PARAMS_DEFAULT_RX_HASH_LOG_TBL_SZ 0x7 +#define MLX5E_PARAMS_MIN_MTU 46 + +#define MLX5E_TX_CQ_POLL_BUDGET 128 +#define MLX5E_UPDATE_STATS_INTERVAL 200 /* msecs */ + +static const char vport_strings[][ETH_GSTRING_LEN] = { + /* vport statistics */ + "rx_packets", + "rx_bytes", + "tx_packets", + "tx_bytes", + "rx_error_packets", + "rx_error_bytes", + "tx_error_packets", + "tx_error_bytes", + "rx_unicast_packets", + "rx_unicast_bytes", + "tx_unicast_packets", + "tx_unicast_bytes", + "rx_multicast_packets", + "rx_multicast_bytes", + "tx_multicast_packets", + "tx_multicast_bytes", + "rx_broadcast_packets", + "rx_broadcast_bytes", + "tx_broadcast_packets", + "tx_broadcast_bytes", + + /* SW counters */ + "tso_packets", + "tso_bytes", + "lro_packets", + "lro_bytes", + "rx_csum_good", + "rx_csum_none", + "tx_csum_offload", + "tx_queue_stopped", + "tx_queue_wake", + "tx_queue_dropped", + "rx_wqe_err", +}; + +struct mlx5e_vport_stats { + /* HW counters */ + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + u64 rx_error_packets; + u64 rx_error_bytes; + u64 tx_error_packets; + u64 tx_error_bytes; + u64 rx_unicast_packets; + u64 rx_unicast_bytes; + u64 tx_unicast_packets; + u64 tx_unicast_bytes; + u64 rx_multicast_packets; + u64 rx_multicast_bytes; + u64 tx_multicast_packets; + u64 tx_multicast_bytes; + u64 rx_broadcast_packets; + u64 rx_broadcast_bytes; + u64 tx_broadcast_packets; + u64 tx_broadcast_bytes; + + /* SW counters */ + u64 tso_packets; + u64 tso_bytes; + u64 lro_packets; + u64 lro_bytes; + u64 rx_csum_good; + u64 rx_csum_none; + u64 tx_csum_offload; + u64 tx_queue_stopped; + u64 tx_queue_wake; + u64 tx_queue_dropped; + u64 rx_wqe_err; + +#define NUM_VPORT_COUNTERS 31 +}; + +static const char rq_stats_strings[][ETH_GSTRING_LEN] = { + "packets", + "csum_none", + "lro_packets", + "lro_bytes", + "wqe_err" +}; + +struct mlx5e_rq_stats { + u64 packets; + u64 csum_none; + u64 lro_packets; + u64 lro_bytes; + u64 wqe_err; +#define NUM_RQ_STATS 5 +}; + +static const char sq_stats_strings[][ETH_GSTRING_LEN] = { + "packets", + "tso_packets", + "tso_bytes", + "csum_offload_none", + "stopped", + "wake", + "dropped", + "nop" +}; + +struct mlx5e_sq_stats { + u64 packets; + u64 tso_packets; + u64 tso_bytes; + u64 csum_offload_none; + u64 stopped; + u64 wake; + u64 dropped; + u64 nop; +#define NUM_SQ_STATS 8 +}; + +struct mlx5e_stats { + struct mlx5e_vport_stats vport; +}; + +struct mlx5e_params { + u8 log_sq_size; + u8 log_rq_size; + u16 num_channels; + u8 default_vlan_prio; + u8 num_tc; + u16 rx_cq_moderation_usec; + u16 rx_cq_moderation_pkts; + u16 tx_cq_moderation_usec; + u16 tx_cq_moderation_pkts; + u16 min_rx_wqes; + u16 rx_hash_log_tbl_sz; + bool lro_en; + u32 lro_wqe_sz; +}; + +enum { + MLX5E_RQ_STATE_POST_WQES_ENABLE, +}; + +enum cq_flags { + MLX5E_CQ_HAS_CQES = 1, +}; + +struct mlx5e_cq { + /* data path - accessed per cqe */ + struct mlx5_cqwq wq; + void *sqrq; + unsigned long flags; + + /* data path - accessed per napi poll */ + struct napi_struct *napi; + struct mlx5_core_cq mcq; + struct mlx5e_channel *channel; + + /* control */ + struct mlx5_wq_ctrl wq_ctrl; +} ____cacheline_aligned_in_smp; + +struct mlx5e_rq { + /* data path */ + struct mlx5_wq_ll wq; + u32 wqe_sz; + struct sk_buff **skb; + + struct device *pdev; + struct net_device *netdev; + struct mlx5e_rq_stats stats; + struct mlx5e_cq cq; + + unsigned long state; + int ix; + + /* control */ + struct mlx5_wq_ctrl wq_ctrl; + u32 rqn; + struct mlx5e_channel *channel; +} ____cacheline_aligned_in_smp; + +struct mlx5e_tx_skb_cb { + u32 num_bytes; + u8 num_wqebbs; + u8 num_dma; +}; + +#define MLX5E_TX_SKB_CB(__skb) ((struct mlx5e_tx_skb_cb *)__skb->cb) + +struct mlx5e_sq_dma { + dma_addr_t addr; + u32 size; +}; + +enum { + MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, +}; + +struct mlx5e_sq { + /* data path */ + + /* dirtied @completion */ + u16 cc; + u32 dma_fifo_cc; + + /* dirtied @xmit */ + u16 pc ____cacheline_aligned_in_smp; + u32 dma_fifo_pc; + u32 bf_offset; + struct mlx5e_sq_stats stats; + + struct mlx5e_cq cq; + + /* pointers to per packet info: write@xmit, read@completion */ + struct sk_buff **skb; + struct mlx5e_sq_dma *dma_fifo; + + /* read only */ + struct mlx5_wq_cyc wq; + u32 dma_fifo_mask; + void __iomem *uar_map; + struct netdev_queue *txq; + u32 sqn; + u32 bf_buf_size; + struct device *pdev; + __be32 mkey_be; + unsigned long state; + + /* control path */ + struct mlx5_wq_ctrl wq_ctrl; + struct mlx5_uar uar; + struct mlx5e_channel *channel; + int tc; +} ____cacheline_aligned_in_smp; + +static inline bool mlx5e_sq_has_room_for(struct mlx5e_sq *sq, u16 n) +{ + return (((sq->wq.sz_m1 & (sq->cc - sq->pc)) >= n) || + (sq->cc == sq->pc)); +} + +enum channel_flags { + MLX5E_CHANNEL_NAPI_SCHED = 1, +}; + +struct mlx5e_channel { + /* data path */ + struct mlx5e_rq rq; + struct mlx5e_sq sq[MLX5E_MAX_NUM_TC]; + struct napi_struct napi; + struct device *pdev; + struct net_device *netdev; + __be32 mkey_be; + u8 num_tc; + unsigned long flags; + + /* control */ + struct mlx5e_priv *priv; + int ix; + int cpu; +}; + +enum mlx5e_traffic_types { + MLX5E_TT_IPV4_TCP = 0, + MLX5E_TT_IPV6_TCP = 1, + MLX5E_TT_IPV4_UDP = 2, + MLX5E_TT_IPV6_UDP = 3, + MLX5E_TT_IPV4 = 4, + MLX5E_TT_IPV6 = 5, + MLX5E_TT_ANY = 6, + MLX5E_NUM_TT = 7, +}; + +enum { + MLX5E_RQT_SPREADING = 0, + MLX5E_RQT_DEFAULT_RQ = 1, + MLX5E_NUM_RQT = 2, +}; + +struct mlx5e_eth_addr_info { + u8 addr[ETH_ALEN + 2]; + u32 tt_vec; + u32 ft_ix[MLX5E_NUM_TT]; /* flow table index per traffic type */ +}; + +#define MLX5E_ETH_ADDR_HASH_SIZE (1 << BITS_PER_BYTE) + +struct mlx5e_eth_addr_db { + struct hlist_head netdev_uc[MLX5E_ETH_ADDR_HASH_SIZE]; + struct hlist_head netdev_mc[MLX5E_ETH_ADDR_HASH_SIZE]; + struct mlx5e_eth_addr_info broadcast; + struct mlx5e_eth_addr_info allmulti; + struct mlx5e_eth_addr_info promisc; + bool broadcast_enabled; + bool allmulti_enabled; + bool promisc_enabled; +}; + +enum { + MLX5E_STATE_ASYNC_EVENTS_ENABLE, + MLX5E_STATE_OPENED, +}; + +struct mlx5e_vlan_db { + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + u32 active_vlans_ft_ix[VLAN_N_VID]; + u32 untagged_rule_ft_ix; + u32 any_vlan_rule_ft_ix; + bool filter_disabled; +}; + +struct mlx5e_flow_table { + void *vlan; + void *main; +}; + +struct mlx5e_priv { + /* priv data path fields - start */ + int order_base_2_num_channels; + int queue_mapping_channel_mask; + int num_tc; + int default_vlan_prio; + /* priv data path fields - end */ + + unsigned long state; + struct mutex state_lock; /* Protects Interface state */ + struct mlx5_uar cq_uar; + u32 pdn; + struct mlx5_core_mr mr; + + struct mlx5e_channel **channel; + u32 tisn[MLX5E_MAX_NUM_TC]; + u32 rqtn; + u32 tirn[MLX5E_NUM_TT]; + + struct mlx5e_flow_table ft; + struct mlx5e_eth_addr_db eth_addr; + struct mlx5e_vlan_db vlan; + + struct mlx5e_params params; + spinlock_t async_events_spinlock; /* sync hw events */ + struct work_struct update_carrier_work; + struct work_struct set_rx_mode_work; + struct delayed_work update_stats_work; + + struct mlx5_core_dev *mdev; + struct net_device *netdev; + struct mlx5e_stats stats; +}; + +#define MLX5E_NET_IP_ALIGN 2 + +struct mlx5e_tx_wqe { + struct mlx5_wqe_ctrl_seg ctrl; + struct mlx5_wqe_eth_seg eth; +}; + +struct mlx5e_rx_wqe { + struct mlx5_wqe_srq_next_seg next; + struct mlx5_wqe_data_seg data; +}; + +enum mlx5e_link_mode { + MLX5E_1000BASE_CX_SGMII = 0, + MLX5E_1000BASE_KX = 1, + MLX5E_10GBASE_CX4 = 2, + MLX5E_10GBASE_KX4 = 3, + MLX5E_10GBASE_KR = 4, + MLX5E_20GBASE_KR2 = 5, + MLX5E_40GBASE_CR4 = 6, + MLX5E_40GBASE_KR4 = 7, + MLX5E_56GBASE_R4 = 8, + MLX5E_10GBASE_CR = 12, + MLX5E_10GBASE_SR = 13, + MLX5E_10GBASE_ER = 14, + MLX5E_40GBASE_SR4 = 15, + MLX5E_40GBASE_LR4 = 16, + MLX5E_100GBASE_CR4 = 20, + MLX5E_100GBASE_SR4 = 21, + MLX5E_100GBASE_KR4 = 22, + MLX5E_100GBASE_LR4 = 23, + MLX5E_100BASE_TX = 24, + MLX5E_100BASE_T = 25, + MLX5E_10GBASE_T = 26, + MLX5E_25GBASE_CR = 27, + MLX5E_25GBASE_KR = 28, + MLX5E_25GBASE_SR = 29, + MLX5E_50GBASE_CR2 = 30, + MLX5E_50GBASE_KR2 = 31, + MLX5E_LINK_MODES_NUMBER, +}; + +#define MLX5E_PROT_MASK(link_mode) (1 << link_mode) + +u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback); +netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t mlx5e_xmit_multi_tc(struct sk_buff *skb, struct net_device *dev); + +void mlx5e_completion_event(struct mlx5_core_cq *mcq); +void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event); +int mlx5e_napi_poll(struct napi_struct *napi, int budget); +bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq); +bool mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget); +bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); +struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq); + +void mlx5e_update_stats(struct mlx5e_priv *priv); + +int mlx5e_open_flow_table(struct mlx5e_priv *priv); +void mlx5e_close_flow_table(struct mlx5e_priv *priv); +void mlx5e_init_eth_addr(struct mlx5e_priv *priv); +void mlx5e_set_rx_mode_core(struct mlx5e_priv *priv); +void mlx5e_set_rx_mode_work(struct work_struct *work); + +int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto, + u16 vid); +int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, + u16 vid); +void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv); +void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); +int mlx5e_add_all_vlan_rules(struct mlx5e_priv *priv); +void mlx5e_del_all_vlan_rules(struct mlx5e_priv *priv); + +int mlx5e_open_locked(struct net_device *netdev); +int mlx5e_close_locked(struct net_device *netdev); +int mlx5e_update_priv_params(struct mlx5e_priv *priv, + struct mlx5e_params *new_params); + +static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq, + struct mlx5e_tx_wqe *wqe) +{ + /* ensure wqe is visible to device before updating doorbell record */ + dma_wmb(); + + *sq->wq.db = cpu_to_be32(sq->pc); + + /* ensure doorbell record is visible to device before ringing the + * doorbell + */ + wmb(); + + mlx5_write64((__be32 *)&wqe->ctrl, + sq->uar_map + MLX5_BF_OFFSET + sq->bf_offset, + NULL); + + sq->bf_offset ^= sq->bf_buf_size; +} + +static inline void mlx5e_cq_arm(struct mlx5e_cq *cq) +{ + struct mlx5_core_cq *mcq; + + mcq = &cq->mcq; + mlx5_cq_arm(mcq, MLX5_CQ_DB_REQ_NOT, mcq->uar->map, NULL, cq->wq.cc); +} + +extern const struct ethtool_ops mlx5e_ethtool_ops; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c new file mode 100644 index 0000000..de7aec8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -0,0 +1,679 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include "en.h" + +static void mlx5e_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *drvinfo) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_core_dev *mdev = priv->mdev; + + strlcpy(drvinfo->driver, DRIVER_NAME, sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, DRIVER_VERSION " (" DRIVER_RELDATE ")", + sizeof(drvinfo->version)); + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%d", + fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev)); + strlcpy(drvinfo->bus_info, pci_name(mdev->pdev), + sizeof(drvinfo->bus_info)); +} + +static const struct { + u32 supported; + u32 advertised; + u32 speed; +} ptys2ethtool_table[MLX5E_LINK_MODES_NUMBER] = { + [MLX5E_1000BASE_CX_SGMII] = { + .supported = SUPPORTED_1000baseKX_Full, + .advertised = ADVERTISED_1000baseKX_Full, + .speed = 1000, + }, + [MLX5E_1000BASE_KX] = { + .supported = SUPPORTED_1000baseKX_Full, + .advertised = ADVERTISED_1000baseKX_Full, + .speed = 1000, + }, + [MLX5E_10GBASE_CX4] = { + .supported = SUPPORTED_10000baseKX4_Full, + .advertised = ADVERTISED_10000baseKX4_Full, + .speed = 10000, + }, + [MLX5E_10GBASE_KX4] = { + .supported = SUPPORTED_10000baseKX4_Full, + .advertised = ADVERTISED_10000baseKX4_Full, + .speed = 10000, + }, + [MLX5E_10GBASE_KR] = { + .supported = SUPPORTED_10000baseKR_Full, + .advertised = ADVERTISED_10000baseKR_Full, + .speed = 10000, + }, + [MLX5E_20GBASE_KR2] = { + .supported = SUPPORTED_20000baseKR2_Full, + .advertised = ADVERTISED_20000baseKR2_Full, + .speed = 20000, + }, + [MLX5E_40GBASE_CR4] = { + .supported = SUPPORTED_40000baseCR4_Full, + .advertised = ADVERTISED_40000baseCR4_Full, + .speed = 40000, + }, + [MLX5E_40GBASE_KR4] = { + .supported = SUPPORTED_40000baseKR4_Full, + .advertised = ADVERTISED_40000baseKR4_Full, + .speed = 40000, + }, + [MLX5E_56GBASE_R4] = { + .supported = SUPPORTED_56000baseKR4_Full, + .advertised = ADVERTISED_56000baseKR4_Full, + .speed = 56000, + }, + [MLX5E_10GBASE_CR] = { + .supported = SUPPORTED_10000baseKR_Full, + .advertised = ADVERTISED_10000baseKR_Full, + .speed = 10000, + }, + [MLX5E_10GBASE_SR] = { + .supported = SUPPORTED_10000baseKR_Full, + .advertised = ADVERTISED_10000baseKR_Full, + .speed = 10000, + }, + [MLX5E_10GBASE_ER] = { + .supported = SUPPORTED_10000baseKR_Full, + .advertised = ADVERTISED_10000baseKR_Full, + .speed = 10000, + }, + [MLX5E_40GBASE_SR4] = { + .supported = SUPPORTED_40000baseSR4_Full, + .advertised = ADVERTISED_40000baseSR4_Full, + .speed = 40000, + }, + [MLX5E_40GBASE_LR4] = { + .supported = SUPPORTED_40000baseLR4_Full, + .advertised = ADVERTISED_40000baseLR4_Full, + .speed = 40000, + }, + [MLX5E_100GBASE_CR4] = { + .speed = 100000, + }, + [MLX5E_100GBASE_SR4] = { + .speed = 100000, + }, + [MLX5E_100GBASE_KR4] = { + .speed = 100000, + }, + [MLX5E_100GBASE_LR4] = { + .speed = 100000, + }, + [MLX5E_100BASE_TX] = { + .speed = 100, + }, + [MLX5E_100BASE_T] = { + .supported = SUPPORTED_100baseT_Full, + .advertised = ADVERTISED_100baseT_Full, + .speed = 100, + }, + [MLX5E_10GBASE_T] = { + .supported = SUPPORTED_10000baseT_Full, + .advertised = ADVERTISED_10000baseT_Full, + .speed = 1000, + }, + [MLX5E_25GBASE_CR] = { + .speed = 25000, + }, + [MLX5E_25GBASE_KR] = { + .speed = 25000, + }, + [MLX5E_25GBASE_SR] = { + .speed = 25000, + }, + [MLX5E_50GBASE_CR2] = { + .speed = 50000, + }, + [MLX5E_50GBASE_KR2] = { + .speed = 50000, + }, +}; + +static int mlx5e_get_sset_count(struct net_device *dev, int sset) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + switch (sset) { + case ETH_SS_STATS: + return NUM_VPORT_COUNTERS + + priv->params.num_channels * NUM_RQ_STATS + + priv->params.num_channels * priv->num_tc * + NUM_SQ_STATS; + /* fallthrough */ + default: + return -EOPNOTSUPP; + } +} + +static void mlx5e_get_strings(struct net_device *dev, + uint32_t stringset, uint8_t *data) +{ + int i, j, tc, idx = 0; + struct mlx5e_priv *priv = netdev_priv(dev); + + switch (stringset) { + case ETH_SS_PRIV_FLAGS: + break; + + case ETH_SS_TEST: + break; + + case ETH_SS_STATS: + /* VPORT counters */ + for (i = 0; i < NUM_VPORT_COUNTERS; i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + vport_strings[i]); + + /* per channel counters */ + for (i = 0; i < priv->params.num_channels; i++) + for (j = 0; j < NUM_RQ_STATS; j++) + sprintf(data + (idx++) * ETH_GSTRING_LEN, + "rx%d_%s", i, rq_stats_strings[j]); + + for (i = 0; i < priv->params.num_channels; i++) + for (tc = 0; tc < priv->num_tc; tc++) + for (j = 0; j < NUM_SQ_STATS; j++) + sprintf(data + + (idx++) * ETH_GSTRING_LEN, + "tx%d_%d_%s", i, tc, + sq_stats_strings[j]); + break; + } +} + +static void mlx5e_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int i, j, tc, idx = 0; + + if (!data) + return; + + mutex_lock(&priv->state_lock); + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + mlx5e_update_stats(priv); + mutex_unlock(&priv->state_lock); + + for (i = 0; i < NUM_VPORT_COUNTERS; i++) + data[idx++] = ((u64 *)&priv->stats.vport)[i]; + + /* per channel counters */ + for (i = 0; i < priv->params.num_channels; i++) + for (j = 0; j < NUM_RQ_STATS; j++) + data[idx++] = !test_bit(MLX5E_STATE_OPENED, + &priv->state) ? 0 : + ((u64 *)&priv->channel[i]->rq.stats)[j]; + + for (i = 0; i < priv->params.num_channels; i++) + for (tc = 0; tc < priv->num_tc; tc++) + for (j = 0; j < NUM_SQ_STATS; j++) + data[idx++] = !test_bit(MLX5E_STATE_OPENED, + &priv->state) ? 0 : + ((u64 *)&priv->channel[i]->sq[tc].stats)[j]; +} + +static void mlx5e_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *param) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + param->rx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE; + param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE; + param->rx_pending = 1 << priv->params.log_rq_size; + param->tx_pending = 1 << priv->params.log_sq_size; +} + +static int mlx5e_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *param) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_params new_params; + u16 min_rx_wqes; + u8 log_rq_size; + u8 log_sq_size; + int err = 0; + + if (param->rx_jumbo_pending) { + netdev_info(dev, "%s: rx_jumbo_pending not supported\n", + __func__); + return -EINVAL; + } + if (param->rx_mini_pending) { + netdev_info(dev, "%s: rx_mini_pending not supported\n", + __func__); + return -EINVAL; + } + if (param->rx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)) { + netdev_info(dev, "%s: rx_pending (%d) < min (%d)\n", + __func__, param->rx_pending, + 1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE); + return -EINVAL; + } + if (param->rx_pending > (1 << MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE)) { + netdev_info(dev, "%s: rx_pending (%d) > max (%d)\n", + __func__, param->rx_pending, + 1 << MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE); + return -EINVAL; + } + if (param->tx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)) { + netdev_info(dev, "%s: tx_pending (%d) < min (%d)\n", + __func__, param->tx_pending, + 1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE); + return -EINVAL; + } + if (param->tx_pending > (1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE)) { + netdev_info(dev, "%s: tx_pending (%d) > max (%d)\n", + __func__, param->tx_pending, + 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE); + return -EINVAL; + } + + log_rq_size = order_base_2(param->rx_pending); + log_sq_size = order_base_2(param->tx_pending); + min_rx_wqes = min_t(u16, param->rx_pending - 1, + MLX5E_PARAMS_DEFAULT_MIN_RX_WQES); + + if (log_rq_size == priv->params.log_rq_size && + log_sq_size == priv->params.log_sq_size && + min_rx_wqes == priv->params.min_rx_wqes) + return 0; + + mutex_lock(&priv->state_lock); + new_params = priv->params; + new_params.log_rq_size = log_rq_size; + new_params.log_sq_size = log_sq_size; + new_params.min_rx_wqes = min_rx_wqes; + err = mlx5e_update_priv_params(priv, &new_params); + mutex_unlock(&priv->state_lock); + + return err; +} + +static void mlx5e_get_channels(struct net_device *dev, + struct ethtool_channels *ch) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int ncv = priv->mdev->priv.eq_table.num_comp_vectors; + + ch->max_combined = ncv; + ch->combined_count = priv->params.num_channels; +} + +static int mlx5e_set_channels(struct net_device *dev, + struct ethtool_channels *ch) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int ncv = priv->mdev->priv.eq_table.num_comp_vectors; + unsigned int count = ch->combined_count; + struct mlx5e_params new_params; + int err = 0; + + if (!count) { + netdev_info(dev, "%s: combined_count=0 not supported\n", + __func__); + return -EINVAL; + } + if (ch->rx_count || ch->tx_count) { + netdev_info(dev, "%s: separate rx/tx count not supported\n", + __func__); + return -EINVAL; + } + if (count > ncv) { + netdev_info(dev, "%s: count (%d) > max (%d)\n", + __func__, count, ncv); + return -EINVAL; + } + + if (priv->params.num_channels == count) + return 0; + + mutex_lock(&priv->state_lock); + new_params = priv->params; + new_params.num_channels = count; + err = mlx5e_update_priv_params(priv, &new_params); + mutex_unlock(&priv->state_lock); + + return err; +} + +static int mlx5e_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *coal) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + coal->rx_coalesce_usecs = priv->params.rx_cq_moderation_usec; + coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation_pkts; + coal->tx_coalesce_usecs = priv->params.tx_cq_moderation_usec; + coal->tx_max_coalesced_frames = priv->params.tx_cq_moderation_pkts; + + return 0; +} + +static int mlx5e_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *coal) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_channel *c; + int tc; + int i; + + priv->params.tx_cq_moderation_usec = coal->tx_coalesce_usecs; + priv->params.tx_cq_moderation_pkts = coal->tx_max_coalesced_frames; + priv->params.rx_cq_moderation_usec = coal->rx_coalesce_usecs; + priv->params.rx_cq_moderation_pkts = coal->rx_max_coalesced_frames; + + for (i = 0; i < priv->params.num_channels; ++i) { + c = priv->channel[i]; + + for (tc = 0; tc < c->num_tc; tc++) { + mlx5_core_modify_cq_moderation(mdev, + &c->sq[tc].cq.mcq, + coal->tx_coalesce_usecs, + coal->tx_max_coalesced_frames); + } + + mlx5_core_modify_cq_moderation(mdev, &c->rq.cq.mcq, + coal->rx_coalesce_usecs, + coal->rx_max_coalesced_frames); + } + + return 0; +} + +static u32 ptys2ethtool_supported_link(u32 eth_proto_cap) +{ + int i; + u32 supported_modes = 0; + + for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { + if (eth_proto_cap & MLX5E_PROT_MASK(i)) + supported_modes |= ptys2ethtool_table[i].supported; + } + return supported_modes; +} + +static u32 ptys2ethtool_adver_link(u32 eth_proto_cap) +{ + int i; + u32 advertising_modes = 0; + + for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { + if (eth_proto_cap & MLX5E_PROT_MASK(i)) + advertising_modes |= ptys2ethtool_table[i].advertised; + } + return advertising_modes; +} + +static u32 ptys2ethtool_supported_port(u32 eth_proto_cap) +{ + if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR) + | MLX5E_PROT_MASK(MLX5E_10GBASE_SR) + | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4) + | MLX5E_PROT_MASK(MLX5E_40GBASE_SR4) + | MLX5E_PROT_MASK(MLX5E_100GBASE_SR4) + | MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII))) { + return SUPPORTED_FIBRE; + } + + if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_100GBASE_KR4) + | MLX5E_PROT_MASK(MLX5E_40GBASE_KR4) + | MLX5E_PROT_MASK(MLX5E_10GBASE_KR) + | MLX5E_PROT_MASK(MLX5E_10GBASE_KX4) + | MLX5E_PROT_MASK(MLX5E_1000BASE_KX))) { + return SUPPORTED_Backplane; + } + return 0; +} + +static void get_speed_duplex(struct net_device *netdev, + u32 eth_proto_oper, + struct ethtool_cmd *cmd) +{ + int i; + u32 speed = SPEED_UNKNOWN; + u8 duplex = DUPLEX_UNKNOWN; + + if (!netif_carrier_ok(netdev)) + goto out; + + for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { + if (eth_proto_oper & MLX5E_PROT_MASK(i)) { + speed = ptys2ethtool_table[i].speed; + duplex = DUPLEX_FULL; + break; + } + } +out: + ethtool_cmd_speed_set(cmd, speed); + cmd->duplex = duplex; +} + +static void get_supported(u32 eth_proto_cap, u32 *supported) +{ + *supported |= ptys2ethtool_supported_port(eth_proto_cap); + *supported |= ptys2ethtool_supported_link(eth_proto_cap); + *supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; +} + +static void get_advertising(u32 eth_proto_cap, u8 tx_pause, + u8 rx_pause, u32 *advertising) +{ + *advertising |= ptys2ethtool_adver_link(eth_proto_cap); + *advertising |= tx_pause ? ADVERTISED_Pause : 0; + *advertising |= (tx_pause ^ rx_pause) ? ADVERTISED_Asym_Pause : 0; +} + +static u8 get_connector_port(u32 eth_proto) +{ + if (eth_proto & (MLX5E_PROT_MASK(MLX5E_10GBASE_SR) + | MLX5E_PROT_MASK(MLX5E_40GBASE_SR4) + | MLX5E_PROT_MASK(MLX5E_100GBASE_SR4) + | MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII))) { + return PORT_FIBRE; + } + + if (eth_proto & (MLX5E_PROT_MASK(MLX5E_40GBASE_CR4) + | MLX5E_PROT_MASK(MLX5E_10GBASE_CR) + | MLX5E_PROT_MASK(MLX5E_100GBASE_CR4))) { + return PORT_DA; + } + + if (eth_proto & (MLX5E_PROT_MASK(MLX5E_10GBASE_KX4) + | MLX5E_PROT_MASK(MLX5E_10GBASE_KR) + | MLX5E_PROT_MASK(MLX5E_40GBASE_KR4) + | MLX5E_PROT_MASK(MLX5E_100GBASE_KR4))) { + return PORT_NONE; + } + + return PORT_OTHER; +} + +static void get_lp_advertising(u32 eth_proto_lp, u32 *lp_advertising) +{ + *lp_advertising = ptys2ethtool_adver_link(eth_proto_lp); +} + +static int mlx5e_get_settings(struct net_device *netdev, + struct ethtool_cmd *cmd) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + u32 eth_proto_cap; + u32 eth_proto_admin; + u32 eth_proto_lp; + u32 eth_proto_oper; + int err; + + err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN); + + if (err) { + netdev_err(netdev, "%s: query port ptys failed: %d\n", + __func__, err); + goto err_query_ptys; + } + + eth_proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability); + eth_proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin); + eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); + eth_proto_lp = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise); + + cmd->supported = 0; + cmd->advertising = 0; + + get_supported(eth_proto_cap, &cmd->supported); + get_advertising(eth_proto_admin, 0, 0, &cmd->advertising); + get_speed_duplex(netdev, eth_proto_oper, cmd); + + eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; + + cmd->port = get_connector_port(eth_proto_oper); + get_lp_advertising(eth_proto_lp, &cmd->lp_advertising); + + cmd->transceiver = XCVR_INTERNAL; + +err_query_ptys: + return err; +} + +static u32 mlx5e_ethtool2ptys_adver_link(u32 link_modes) +{ + u32 i, ptys_modes = 0; + + for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { + if (ptys2ethtool_table[i].advertised & link_modes) + ptys_modes |= MLX5E_PROT_MASK(i); + } + + return ptys_modes; +} + +static u32 mlx5e_ethtool2ptys_speed_link(u32 speed) +{ + u32 i, speed_links = 0; + + for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { + if (ptys2ethtool_table[i].speed == speed) + speed_links |= MLX5E_PROT_MASK(i); + } + + return speed_links; +} + +static int mlx5e_set_settings(struct net_device *netdev, + struct ethtool_cmd *cmd) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u32 link_modes; + u32 speed; + u32 eth_proto_cap, eth_proto_admin; + u8 port_status; + int err; + + speed = ethtool_cmd_speed(cmd); + + link_modes = cmd->autoneg == AUTONEG_ENABLE ? + mlx5e_ethtool2ptys_adver_link(cmd->advertising) : + mlx5e_ethtool2ptys_speed_link(speed); + + err = mlx5_query_port_proto_cap(mdev, ð_proto_cap, MLX5_PTYS_EN); + if (err) { + netdev_err(netdev, "%s: query port eth proto cap failed: %d\n", + __func__, err); + goto out; + } + + link_modes = link_modes & eth_proto_cap; + if (!link_modes) { + netdev_err(netdev, "%s: Not supported link mode(s) requested", + __func__); + err = -EINVAL; + goto out; + } + + err = mlx5_query_port_proto_admin(mdev, ð_proto_admin, MLX5_PTYS_EN); + if (err) { + netdev_err(netdev, "%s: query port eth proto admin failed: %d\n", + __func__, err); + goto out; + } + + if (link_modes == eth_proto_admin) + goto out; + + err = mlx5_set_port_proto(mdev, link_modes, MLX5_PTYS_EN); + if (err) { + netdev_err(netdev, "%s: set port eth proto admin failed: %d\n", + __func__, err); + goto out; + } + + err = mlx5_query_port_status(mdev, &port_status); + if (err) + goto out; + + if (port_status == MLX5_PORT_DOWN) + return 0; + + err = mlx5_set_port_status(mdev, MLX5_PORT_DOWN); + if (err) + goto out; + err = mlx5_set_port_status(mdev, MLX5_PORT_UP); +out: + return err; +} + +const struct ethtool_ops mlx5e_ethtool_ops = { + .get_drvinfo = mlx5e_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_strings = mlx5e_get_strings, + .get_sset_count = mlx5e_get_sset_count, + .get_ethtool_stats = mlx5e_get_ethtool_stats, + .get_ringparam = mlx5e_get_ringparam, + .set_ringparam = mlx5e_set_ringparam, + .get_channels = mlx5e_get_channels, + .set_channels = mlx5e_set_channels, + .get_coalesce = mlx5e_get_coalesce, + .set_coalesce = mlx5e_set_coalesce, + .get_settings = mlx5e_get_settings, + .set_settings = mlx5e_set_settings, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c b/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c new file mode 100644 index 0000000..6feebda --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c @@ -0,0 +1,858 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/list.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/mlx5/flow_table.h> +#include "en.h" + +enum { + MLX5E_FULLMATCH = 0, + MLX5E_ALLMULTI = 1, + MLX5E_PROMISC = 2, +}; + +enum { + MLX5E_UC = 0, + MLX5E_MC_IPV4 = 1, + MLX5E_MC_IPV6 = 2, + MLX5E_MC_OTHER = 3, +}; + +enum { + MLX5E_ACTION_NONE = 0, + MLX5E_ACTION_ADD = 1, + MLX5E_ACTION_DEL = 2, +}; + +struct mlx5e_eth_addr_hash_node { + struct hlist_node hlist; + u8 action; + struct mlx5e_eth_addr_info ai; +}; + +static inline int mlx5e_hash_eth_addr(u8 *addr) +{ + return addr[5]; +} + +static void mlx5e_add_eth_addr_to_hash(struct hlist_head *hash, u8 *addr) +{ + struct mlx5e_eth_addr_hash_node *hn; + int ix = mlx5e_hash_eth_addr(addr); + int found = 0; + + hlist_for_each_entry(hn, &hash[ix], hlist) + if (ether_addr_equal_64bits(hn->ai.addr, addr)) { + found = 1; + break; + } + + if (found) { + hn->action = MLX5E_ACTION_NONE; + return; + } + + hn = kzalloc(sizeof(*hn), GFP_ATOMIC); + if (!hn) + return; + + ether_addr_copy(hn->ai.addr, addr); + hn->action = MLX5E_ACTION_ADD; + + hlist_add_head(&hn->hlist, &hash[ix]); +} + +static void mlx5e_del_eth_addr_from_hash(struct mlx5e_eth_addr_hash_node *hn) +{ + hlist_del(&hn->hlist); + kfree(hn); +} + +static void mlx5e_del_eth_addr_from_flow_table(struct mlx5e_priv *priv, + struct mlx5e_eth_addr_info *ai) +{ + void *ft = priv->ft.main; + + if (ai->tt_vec & (1 << MLX5E_TT_IPV6_TCP)) + mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV6_TCP]); + + if (ai->tt_vec & (1 << MLX5E_TT_IPV4_TCP)) + mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV4_TCP]); + + if (ai->tt_vec & (1 << MLX5E_TT_IPV6_UDP)) + mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV6_UDP]); + + if (ai->tt_vec & (1 << MLX5E_TT_IPV4_UDP)) + mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV4_UDP]); + + if (ai->tt_vec & (1 << MLX5E_TT_IPV6)) + mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV6]); + + if (ai->tt_vec & (1 << MLX5E_TT_IPV4)) + mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV4]); + + if (ai->tt_vec & (1 << MLX5E_TT_ANY)) + mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_ANY]); +} + +static int mlx5e_get_eth_addr_type(u8 *addr) +{ + if (is_unicast_ether_addr(addr)) + return MLX5E_UC; + + if ((addr[0] == 0x01) && + (addr[1] == 0x00) && + (addr[2] == 0x5e) && + !(addr[3] & 0x80)) + return MLX5E_MC_IPV4; + + if ((addr[0] == 0x33) && + (addr[1] == 0x33)) + return MLX5E_MC_IPV6; + + return MLX5E_MC_OTHER; +} + +static u32 mlx5e_get_tt_vec(struct mlx5e_eth_addr_info *ai, int type) +{ + int eth_addr_type; + u32 ret; + + switch (type) { + case MLX5E_FULLMATCH: + eth_addr_type = mlx5e_get_eth_addr_type(ai->addr); + switch (eth_addr_type) { + case MLX5E_UC: + ret = + (1 << MLX5E_TT_IPV4_TCP) | + (1 << MLX5E_TT_IPV6_TCP) | + (1 << MLX5E_TT_IPV4_UDP) | + (1 << MLX5E_TT_IPV6_UDP) | + (1 << MLX5E_TT_IPV4) | + (1 << MLX5E_TT_IPV6) | + (1 << MLX5E_TT_ANY) | + 0; + break; + + case MLX5E_MC_IPV4: + ret = + (1 << MLX5E_TT_IPV4_UDP) | + (1 << MLX5E_TT_IPV4) | + 0; + break; + + case MLX5E_MC_IPV6: + ret = + (1 << MLX5E_TT_IPV6_UDP) | + (1 << MLX5E_TT_IPV6) | + 0; + break; + + case MLX5E_MC_OTHER: + ret = + (1 << MLX5E_TT_ANY) | + 0; + break; + } + + break; + + case MLX5E_ALLMULTI: + ret = + (1 << MLX5E_TT_IPV4_UDP) | + (1 << MLX5E_TT_IPV6_UDP) | + (1 << MLX5E_TT_IPV4) | + (1 << MLX5E_TT_IPV6) | + (1 << MLX5E_TT_ANY) | + 0; + break; + + default: /* MLX5E_PROMISC */ + ret = + (1 << MLX5E_TT_IPV4_TCP) | + (1 << MLX5E_TT_IPV6_TCP) | + (1 << MLX5E_TT_IPV4_UDP) | + (1 << MLX5E_TT_IPV6_UDP) | + (1 << MLX5E_TT_IPV4) | + (1 << MLX5E_TT_IPV6) | + (1 << MLX5E_TT_ANY) | + 0; + break; + } + + return ret; +} + +static int __mlx5e_add_eth_addr_rule(struct mlx5e_priv *priv, + struct mlx5e_eth_addr_info *ai, int type, + void *flow_context, void *match_criteria) +{ + u8 match_criteria_enable = 0; + void *match_value; + void *dest; + u8 *dmac; + u8 *match_criteria_dmac; + void *ft = priv->ft.main; + u32 *tirn = priv->tirn; + u32 tt_vec; + int err; + + match_value = MLX5_ADDR_OF(flow_context, flow_context, match_value); + dmac = MLX5_ADDR_OF(fte_match_param, match_value, + outer_headers.dmac_47_16); + match_criteria_dmac = MLX5_ADDR_OF(fte_match_param, match_criteria, + outer_headers.dmac_47_16); + dest = MLX5_ADDR_OF(flow_context, flow_context, destination); + + MLX5_SET(flow_context, flow_context, action, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST); + MLX5_SET(flow_context, flow_context, destination_list_size, 1); + MLX5_SET(dest_format_struct, dest, destination_type, + MLX5_FLOW_CONTEXT_DEST_TYPE_TIR); + + switch (type) { + case MLX5E_FULLMATCH: + match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + memset(match_criteria_dmac, 0xff, ETH_ALEN); + ether_addr_copy(dmac, ai->addr); + break; + + case MLX5E_ALLMULTI: + match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + match_criteria_dmac[0] = 0x01; + dmac[0] = 0x01; + break; + + case MLX5E_PROMISC: + break; + } + + tt_vec = mlx5e_get_tt_vec(ai, type); + + if (tt_vec & (1 << MLX5E_TT_ANY)) { + MLX5_SET(dest_format_struct, dest, destination_id, + tirn[MLX5E_TT_ANY]); + err = mlx5_add_flow_table_entry(ft, match_criteria_enable, + match_criteria, flow_context, + &ai->ft_ix[MLX5E_TT_ANY]); + if (err) { + mlx5e_del_eth_addr_from_flow_table(priv, ai); + return err; + } + ai->tt_vec |= (1 << MLX5E_TT_ANY); + } + + match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, match_criteria, + outer_headers.ethertype); + + if (tt_vec & (1 << MLX5E_TT_IPV4)) { + MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + ETH_P_IP); + MLX5_SET(dest_format_struct, dest, destination_id, + tirn[MLX5E_TT_IPV4]); + err = mlx5_add_flow_table_entry(ft, match_criteria_enable, + match_criteria, flow_context, + &ai->ft_ix[MLX5E_TT_IPV4]); + if (err) { + mlx5e_del_eth_addr_from_flow_table(priv, ai); + return err; + } + ai->tt_vec |= (1 << MLX5E_TT_IPV4); + } + + if (tt_vec & (1 << MLX5E_TT_IPV6)) { + MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + ETH_P_IPV6); + MLX5_SET(dest_format_struct, dest, destination_id, + tirn[MLX5E_TT_IPV6]); + err = mlx5_add_flow_table_entry(ft, match_criteria_enable, + match_criteria, flow_context, + &ai->ft_ix[MLX5E_TT_IPV6]); + if (err) { + mlx5e_del_eth_addr_from_flow_table(priv, ai); + return err; + } + ai->tt_vec |= (1 << MLX5E_TT_IPV6); + } + + MLX5_SET_TO_ONES(fte_match_param, match_criteria, + outer_headers.ip_protocol); + MLX5_SET(fte_match_param, match_value, outer_headers.ip_protocol, + IPPROTO_UDP); + + if (tt_vec & (1 << MLX5E_TT_IPV4_UDP)) { + MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + ETH_P_IP); + MLX5_SET(dest_format_struct, dest, destination_id, + tirn[MLX5E_TT_IPV4_UDP]); + err = mlx5_add_flow_table_entry(ft, match_criteria_enable, + match_criteria, flow_context, + &ai->ft_ix[MLX5E_TT_IPV4_UDP]); + if (err) { + mlx5e_del_eth_addr_from_flow_table(priv, ai); + return err; + } + ai->tt_vec |= (1 << MLX5E_TT_IPV4_UDP); + } + + if (tt_vec & (1 << MLX5E_TT_IPV6_UDP)) { + MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + ETH_P_IPV6); + MLX5_SET(dest_format_struct, dest, destination_id, + tirn[MLX5E_TT_IPV6_UDP]); + err = mlx5_add_flow_table_entry(ft, match_criteria_enable, + match_criteria, flow_context, + &ai->ft_ix[MLX5E_TT_IPV6_UDP]); + if (err) { + mlx5e_del_eth_addr_from_flow_table(priv, ai); + return err; + } + ai->tt_vec |= (1 << MLX5E_TT_IPV6_UDP); + } + + MLX5_SET(fte_match_param, match_value, outer_headers.ip_protocol, + IPPROTO_TCP); + + if (tt_vec & (1 << MLX5E_TT_IPV4_TCP)) { + MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + ETH_P_IP); + MLX5_SET(dest_format_struct, dest, destination_id, + tirn[MLX5E_TT_IPV4_TCP]); + err = mlx5_add_flow_table_entry(ft, match_criteria_enable, + match_criteria, flow_context, + &ai->ft_ix[MLX5E_TT_IPV4_TCP]); + if (err) { + mlx5e_del_eth_addr_from_flow_table(priv, ai); + return err; + } + ai->tt_vec |= (1 << MLX5E_TT_IPV4_TCP); + } + + if (tt_vec & (1 << MLX5E_TT_IPV6_TCP)) { + MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, + ETH_P_IPV6); + MLX5_SET(dest_format_struct, dest, destination_id, + tirn[MLX5E_TT_IPV6_TCP]); + err = mlx5_add_flow_table_entry(ft, match_criteria_enable, + match_criteria, flow_context, + &ai->ft_ix[MLX5E_TT_IPV6_TCP]); + if (err) { + mlx5e_del_eth_addr_from_flow_table(priv, ai); + return err; + } + ai->tt_vec |= (1 << MLX5E_TT_IPV6_TCP); + } + + return 0; +} + +static int mlx5e_add_eth_addr_rule(struct mlx5e_priv *priv, + struct mlx5e_eth_addr_info *ai, int type) +{ + u32 *flow_context; + u32 *match_criteria; + int err; + + flow_context = mlx5_vzalloc(MLX5_ST_SZ_BYTES(flow_context) + + MLX5_ST_SZ_BYTES(dest_format_struct)); + match_criteria = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param)); + if (!flow_context || !match_criteria) { + netdev_err(priv->netdev, "%s: alloc failed\n", __func__); + err = -ENOMEM; + goto add_eth_addr_rule_out; + } + + err = __mlx5e_add_eth_addr_rule(priv, ai, type, flow_context, + match_criteria); + if (err) + netdev_err(priv->netdev, "%s: failed\n", __func__); + +add_eth_addr_rule_out: + kvfree(match_criteria); + kvfree(flow_context); + return err; +} + +enum mlx5e_vlan_rule_type { + MLX5E_VLAN_RULE_TYPE_UNTAGGED, + MLX5E_VLAN_RULE_TYPE_ANY_VID, + MLX5E_VLAN_RULE_TYPE_MATCH_VID, +}; + +static int mlx5e_add_vlan_rule(struct mlx5e_priv *priv, + enum mlx5e_vlan_rule_type rule_type, u16 vid) +{ + u8 match_criteria_enable = 0; + u32 *flow_context; + void *match_value; + void *dest; + u32 *match_criteria; + u32 *ft_ix; + int err; + + flow_context = mlx5_vzalloc(MLX5_ST_SZ_BYTES(flow_context) + + MLX5_ST_SZ_BYTES(dest_format_struct)); + match_criteria = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param)); + if (!flow_context || !match_criteria) { + netdev_err(priv->netdev, "%s: alloc failed\n", __func__); + err = -ENOMEM; + goto add_vlan_rule_out; + } + match_value = MLX5_ADDR_OF(flow_context, flow_context, match_value); + dest = MLX5_ADDR_OF(flow_context, flow_context, destination); + + MLX5_SET(flow_context, flow_context, action, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST); + MLX5_SET(flow_context, flow_context, destination_list_size, 1); + MLX5_SET(dest_format_struct, dest, destination_type, + MLX5_FLOW_CONTEXT_DEST_TYPE_FLOW_TABLE); + MLX5_SET(dest_format_struct, dest, destination_id, + mlx5_get_flow_table_id(priv->ft.main)); + + match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, match_criteria, + outer_headers.vlan_tag); + + switch (rule_type) { + case MLX5E_VLAN_RULE_TYPE_UNTAGGED: + ft_ix = &priv->vlan.untagged_rule_ft_ix; + break; + case MLX5E_VLAN_RULE_TYPE_ANY_VID: + ft_ix = &priv->vlan.any_vlan_rule_ft_ix; + MLX5_SET(fte_match_param, match_value, outer_headers.vlan_tag, + 1); + break; + default: /* MLX5E_VLAN_RULE_TYPE_MATCH_VID */ + ft_ix = &priv->vlan.active_vlans_ft_ix[vid]; + MLX5_SET(fte_match_param, match_value, outer_headers.vlan_tag, + 1); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, + outer_headers.first_vid); + MLX5_SET(fte_match_param, match_value, outer_headers.first_vid, + vid); + break; + } + + err = mlx5_add_flow_table_entry(priv->ft.vlan, match_criteria_enable, + match_criteria, flow_context, ft_ix); + if (err) + netdev_err(priv->netdev, "%s: failed\n", __func__); + +add_vlan_rule_out: + kvfree(match_criteria); + kvfree(flow_context); + return err; +} + +static void mlx5e_del_vlan_rule(struct mlx5e_priv *priv, + enum mlx5e_vlan_rule_type rule_type, u16 vid) +{ + switch (rule_type) { + case MLX5E_VLAN_RULE_TYPE_UNTAGGED: + mlx5_del_flow_table_entry(priv->ft.vlan, + priv->vlan.untagged_rule_ft_ix); + break; + case MLX5E_VLAN_RULE_TYPE_ANY_VID: + mlx5_del_flow_table_entry(priv->ft.vlan, + priv->vlan.any_vlan_rule_ft_ix); + break; + case MLX5E_VLAN_RULE_TYPE_MATCH_VID: + mlx5_del_flow_table_entry(priv->ft.vlan, + priv->vlan.active_vlans_ft_ix[vid]); + break; + } +} + +void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv) +{ + WARN_ON(!mutex_is_locked(&priv->state_lock)); + + if (priv->vlan.filter_disabled) { + priv->vlan.filter_disabled = false; + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, + 0); + } +} + +void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv) +{ + WARN_ON(!mutex_is_locked(&priv->state_lock)); + + if (!priv->vlan.filter_disabled) { + priv->vlan.filter_disabled = true; + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, + 0); + } +} + +int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto, + u16 vid) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int err = 0; + + mutex_lock(&priv->state_lock); + + set_bit(vid, priv->vlan.active_vlans); + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + err = mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_VID, + vid); + + mutex_unlock(&priv->state_lock); + + return err; +} + +int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, + u16 vid) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + mutex_lock(&priv->state_lock); + + clear_bit(vid, priv->vlan.active_vlans); + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_VID, vid); + + mutex_unlock(&priv->state_lock); + + return 0; +} + +int mlx5e_add_all_vlan_rules(struct mlx5e_priv *priv) +{ + u16 vid; + int err; + + for_each_set_bit(vid, priv->vlan.active_vlans, VLAN_N_VID) { + err = mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_VID, + vid); + if (err) + return err; + } + + err = mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_UNTAGGED, 0); + if (err) + return err; + + if (priv->vlan.filter_disabled) { + err = mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, + 0); + if (err) + return err; + } + + return 0; +} + +void mlx5e_del_all_vlan_rules(struct mlx5e_priv *priv) +{ + u16 vid; + + if (priv->vlan.filter_disabled) + mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, 0); + + mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_UNTAGGED, 0); + + for_each_set_bit(vid, priv->vlan.active_vlans, VLAN_N_VID) + mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_VID, vid); +} + +#define mlx5e_for_each_hash_node(hn, tmp, hash, i) \ + for (i = 0; i < MLX5E_ETH_ADDR_HASH_SIZE; i++) \ + hlist_for_each_entry_safe(hn, tmp, &hash[i], hlist) + +static void mlx5e_execute_action(struct mlx5e_priv *priv, + struct mlx5e_eth_addr_hash_node *hn) +{ + switch (hn->action) { + case MLX5E_ACTION_ADD: + mlx5e_add_eth_addr_rule(priv, &hn->ai, MLX5E_FULLMATCH); + hn->action = MLX5E_ACTION_NONE; + break; + + case MLX5E_ACTION_DEL: + mlx5e_del_eth_addr_from_flow_table(priv, &hn->ai); + mlx5e_del_eth_addr_from_hash(hn); + break; + } +} + +static void mlx5e_sync_netdev_addr(struct mlx5e_priv *priv) +{ + struct net_device *netdev = priv->netdev; + struct netdev_hw_addr *ha; + + netif_addr_lock_bh(netdev); + + mlx5e_add_eth_addr_to_hash(priv->eth_addr.netdev_uc, + priv->netdev->dev_addr); + + netdev_for_each_uc_addr(ha, netdev) + mlx5e_add_eth_addr_to_hash(priv->eth_addr.netdev_uc, ha->addr); + + netdev_for_each_mc_addr(ha, netdev) + mlx5e_add_eth_addr_to_hash(priv->eth_addr.netdev_mc, ha->addr); + + netif_addr_unlock_bh(netdev); +} + +static void mlx5e_apply_netdev_addr(struct mlx5e_priv *priv) +{ + struct mlx5e_eth_addr_hash_node *hn; + struct hlist_node *tmp; + int i; + + mlx5e_for_each_hash_node(hn, tmp, priv->eth_addr.netdev_uc, i) + mlx5e_execute_action(priv, hn); + + mlx5e_for_each_hash_node(hn, tmp, priv->eth_addr.netdev_mc, i) + mlx5e_execute_action(priv, hn); +} + +static void mlx5e_handle_netdev_addr(struct mlx5e_priv *priv) +{ + struct mlx5e_eth_addr_hash_node *hn; + struct hlist_node *tmp; + int i; + + mlx5e_for_each_hash_node(hn, tmp, priv->eth_addr.netdev_uc, i) + hn->action = MLX5E_ACTION_DEL; + mlx5e_for_each_hash_node(hn, tmp, priv->eth_addr.netdev_mc, i) + hn->action = MLX5E_ACTION_DEL; + + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + mlx5e_sync_netdev_addr(priv); + + mlx5e_apply_netdev_addr(priv); +} + +void mlx5e_set_rx_mode_core(struct mlx5e_priv *priv) +{ + struct mlx5e_eth_addr_db *ea = &priv->eth_addr; + struct net_device *ndev = priv->netdev; + + bool rx_mode_enable = test_bit(MLX5E_STATE_OPENED, &priv->state); + bool promisc_enabled = rx_mode_enable && (ndev->flags & IFF_PROMISC); + bool allmulti_enabled = rx_mode_enable && (ndev->flags & IFF_ALLMULTI); + bool broadcast_enabled = rx_mode_enable; + + bool enable_promisc = !ea->promisc_enabled && promisc_enabled; + bool disable_promisc = ea->promisc_enabled && !promisc_enabled; + bool enable_allmulti = !ea->allmulti_enabled && allmulti_enabled; + bool disable_allmulti = ea->allmulti_enabled && !allmulti_enabled; + bool enable_broadcast = !ea->broadcast_enabled && broadcast_enabled; + bool disable_broadcast = ea->broadcast_enabled && !broadcast_enabled; + + if (enable_promisc) + mlx5e_add_eth_addr_rule(priv, &ea->promisc, MLX5E_PROMISC); + if (enable_allmulti) + mlx5e_add_eth_addr_rule(priv, &ea->allmulti, MLX5E_ALLMULTI); + if (enable_broadcast) + mlx5e_add_eth_addr_rule(priv, &ea->broadcast, MLX5E_FULLMATCH); + + mlx5e_handle_netdev_addr(priv); + + if (disable_broadcast) + mlx5e_del_eth_addr_from_flow_table(priv, &ea->broadcast); + if (disable_allmulti) + mlx5e_del_eth_addr_from_flow_table(priv, &ea->allmulti); + if (disable_promisc) + mlx5e_del_eth_addr_from_flow_table(priv, &ea->promisc); + + ea->promisc_enabled = promisc_enabled; + ea->allmulti_enabled = allmulti_enabled; + ea->broadcast_enabled = broadcast_enabled; +} + +void mlx5e_set_rx_mode_work(struct work_struct *work) +{ + struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, + set_rx_mode_work); + + mutex_lock(&priv->state_lock); + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + mlx5e_set_rx_mode_core(priv); + mutex_unlock(&priv->state_lock); +} + +void mlx5e_init_eth_addr(struct mlx5e_priv *priv) +{ + ether_addr_copy(priv->eth_addr.broadcast.addr, priv->netdev->broadcast); +} + +static int mlx5e_create_main_flow_table(struct mlx5e_priv *priv) +{ + struct mlx5_flow_table_group *g; + u8 *dmac; + + g = kcalloc(9, sizeof(*g), GFP_KERNEL); + + g[0].log_sz = 2; + g[0].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria, + outer_headers.ethertype); + MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria, + outer_headers.ip_protocol); + + g[1].log_sz = 1; + g[1].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, g[1].match_criteria, + outer_headers.ethertype); + + g[2].log_sz = 0; + + g[3].log_sz = 14; + g[3].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + dmac = MLX5_ADDR_OF(fte_match_param, g[3].match_criteria, + outer_headers.dmac_47_16); + memset(dmac, 0xff, ETH_ALEN); + MLX5_SET_TO_ONES(fte_match_param, g[3].match_criteria, + outer_headers.ethertype); + MLX5_SET_TO_ONES(fte_match_param, g[3].match_criteria, + outer_headers.ip_protocol); + + g[4].log_sz = 13; + g[4].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + dmac = MLX5_ADDR_OF(fte_match_param, g[4].match_criteria, + outer_headers.dmac_47_16); + memset(dmac, 0xff, ETH_ALEN); + MLX5_SET_TO_ONES(fte_match_param, g[4].match_criteria, + outer_headers.ethertype); + + g[5].log_sz = 11; + g[5].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + dmac = MLX5_ADDR_OF(fte_match_param, g[5].match_criteria, + outer_headers.dmac_47_16); + memset(dmac, 0xff, ETH_ALEN); + + g[6].log_sz = 2; + g[6].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + dmac = MLX5_ADDR_OF(fte_match_param, g[6].match_criteria, + outer_headers.dmac_47_16); + dmac[0] = 0x01; + MLX5_SET_TO_ONES(fte_match_param, g[6].match_criteria, + outer_headers.ethertype); + MLX5_SET_TO_ONES(fte_match_param, g[6].match_criteria, + outer_headers.ip_protocol); + + g[7].log_sz = 1; + g[7].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + dmac = MLX5_ADDR_OF(fte_match_param, g[7].match_criteria, + outer_headers.dmac_47_16); + dmac[0] = 0x01; + MLX5_SET_TO_ONES(fte_match_param, g[7].match_criteria, + outer_headers.ethertype); + + g[8].log_sz = 0; + g[8].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + dmac = MLX5_ADDR_OF(fte_match_param, g[8].match_criteria, + outer_headers.dmac_47_16); + dmac[0] = 0x01; + priv->ft.main = mlx5_create_flow_table(priv->mdev, 1, + MLX5_FLOW_TABLE_TYPE_NIC_RCV, + 9, g); + kfree(g); + + return priv->ft.main ? 0 : -ENOMEM; +} + +static void mlx5e_destroy_main_flow_table(struct mlx5e_priv *priv) +{ + mlx5_destroy_flow_table(priv->ft.main); +} + +static int mlx5e_create_vlan_flow_table(struct mlx5e_priv *priv) +{ + struct mlx5_flow_table_group *g; + + g = kcalloc(2, sizeof(*g), GFP_KERNEL); + if (!g) + return -ENOMEM; + + g[0].log_sz = 12; + g[0].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria, + outer_headers.vlan_tag); + MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria, + outer_headers.first_vid); + + /* untagged + any vlan id */ + g[1].log_sz = 1; + g[1].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, g[1].match_criteria, + outer_headers.vlan_tag); + + priv->ft.vlan = mlx5_create_flow_table(priv->mdev, 0, + MLX5_FLOW_TABLE_TYPE_NIC_RCV, + 2, g); + + kfree(g); + return priv->ft.vlan ? 0 : -ENOMEM; +} + +static void mlx5e_destroy_vlan_flow_table(struct mlx5e_priv *priv) +{ + mlx5_destroy_flow_table(priv->ft.vlan); +} + +int mlx5e_open_flow_table(struct mlx5e_priv *priv) +{ + int err; + + err = mlx5e_create_main_flow_table(priv); + if (err) + return err; + + err = mlx5e_create_vlan_flow_table(priv); + if (err) + goto err_destroy_main_flow_table; + + return 0; + +err_destroy_main_flow_table: + mlx5e_destroy_main_flow_table(priv); + + return err; +} + +void mlx5e_close_flow_table(struct mlx5e_priv *priv) +{ + mlx5e_destroy_vlan_flow_table(priv); + mlx5e_destroy_main_flow_table(priv); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c new file mode 100644 index 0000000..eee829d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -0,0 +1,1899 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/mlx5/flow_table.h> +#include "en.h" + +struct mlx5e_rq_param { + u32 rqc[MLX5_ST_SZ_DW(rqc)]; + struct mlx5_wq_param wq; +}; + +struct mlx5e_sq_param { + u32 sqc[MLX5_ST_SZ_DW(sqc)]; + struct mlx5_wq_param wq; +}; + +struct mlx5e_cq_param { + u32 cqc[MLX5_ST_SZ_DW(cqc)]; + struct mlx5_wq_param wq; + u16 eq_ix; +}; + +struct mlx5e_channel_param { + struct mlx5e_rq_param rq; + struct mlx5e_sq_param sq; + struct mlx5e_cq_param rx_cq; + struct mlx5e_cq_param tx_cq; +}; + +static void mlx5e_update_carrier(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + u8 port_state; + + port_state = mlx5_query_vport_state(mdev, + MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT); + + if (port_state == VPORT_STATE_UP) + netif_carrier_on(priv->netdev); + else + netif_carrier_off(priv->netdev); +} + +static void mlx5e_update_carrier_work(struct work_struct *work) +{ + struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, + update_carrier_work); + + mutex_lock(&priv->state_lock); + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + mlx5e_update_carrier(priv); + mutex_unlock(&priv->state_lock); +} + +void mlx5e_update_stats(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_vport_stats *s = &priv->stats.vport; + struct mlx5e_rq_stats *rq_stats; + struct mlx5e_sq_stats *sq_stats; + u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)]; + u32 *out; + int outlen = MLX5_ST_SZ_BYTES(query_vport_counter_out); + u64 tx_offload_none; + int i, j; + + out = mlx5_vzalloc(outlen); + if (!out) + return; + + /* Collect firts the SW counters and then HW for consistency */ + s->tso_packets = 0; + s->tso_bytes = 0; + s->tx_queue_stopped = 0; + s->tx_queue_wake = 0; + s->tx_queue_dropped = 0; + tx_offload_none = 0; + s->lro_packets = 0; + s->lro_bytes = 0; + s->rx_csum_none = 0; + s->rx_wqe_err = 0; + for (i = 0; i < priv->params.num_channels; i++) { + rq_stats = &priv->channel[i]->rq.stats; + + s->lro_packets += rq_stats->lro_packets; + s->lro_bytes += rq_stats->lro_bytes; + s->rx_csum_none += rq_stats->csum_none; + s->rx_wqe_err += rq_stats->wqe_err; + + for (j = 0; j < priv->num_tc; j++) { + sq_stats = &priv->channel[i]->sq[j].stats; + + s->tso_packets += sq_stats->tso_packets; + s->tso_bytes += sq_stats->tso_bytes; + s->tx_queue_stopped += sq_stats->stopped; + s->tx_queue_wake += sq_stats->wake; + s->tx_queue_dropped += sq_stats->dropped; + tx_offload_none += sq_stats->csum_offload_none; + } + } + + /* HW counters */ + memset(in, 0, sizeof(in)); + + MLX5_SET(query_vport_counter_in, in, opcode, + MLX5_CMD_OP_QUERY_VPORT_COUNTER); + MLX5_SET(query_vport_counter_in, in, op_mod, 0); + MLX5_SET(query_vport_counter_in, in, other_vport, 0); + + memset(out, 0, outlen); + + if (mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen)) + goto free_out; + +#define MLX5_GET_CTR(p, x) \ + MLX5_GET64(query_vport_counter_out, p, x) + + s->rx_error_packets = + MLX5_GET_CTR(out, received_errors.packets); + s->rx_error_bytes = + MLX5_GET_CTR(out, received_errors.octets); + s->tx_error_packets = + MLX5_GET_CTR(out, transmit_errors.packets); + s->tx_error_bytes = + MLX5_GET_CTR(out, transmit_errors.octets); + + s->rx_unicast_packets = + MLX5_GET_CTR(out, received_eth_unicast.packets); + s->rx_unicast_bytes = + MLX5_GET_CTR(out, received_eth_unicast.octets); + s->tx_unicast_packets = + MLX5_GET_CTR(out, transmitted_eth_unicast.packets); + s->tx_unicast_bytes = + MLX5_GET_CTR(out, transmitted_eth_unicast.octets); + + s->rx_multicast_packets = + MLX5_GET_CTR(out, received_eth_multicast.packets); + s->rx_multicast_bytes = + MLX5_GET_CTR(out, received_eth_multicast.octets); + s->tx_multicast_packets = + MLX5_GET_CTR(out, transmitted_eth_multicast.packets); + s->tx_multicast_bytes = + MLX5_GET_CTR(out, transmitted_eth_multicast.octets); + + s->rx_broadcast_packets = + MLX5_GET_CTR(out, received_eth_broadcast.packets); + s->rx_broadcast_bytes = + MLX5_GET_CTR(out, received_eth_broadcast.octets); + s->tx_broadcast_packets = + MLX5_GET_CTR(out, transmitted_eth_broadcast.packets); + s->tx_broadcast_bytes = + MLX5_GET_CTR(out, transmitted_eth_broadcast.octets); + + s->rx_packets = + s->rx_unicast_packets + + s->rx_multicast_packets + + s->rx_broadcast_packets; + s->rx_bytes = + s->rx_unicast_bytes + + s->rx_multicast_bytes + + s->rx_broadcast_bytes; + s->tx_packets = + s->tx_unicast_packets + + s->tx_multicast_packets + + s->tx_broadcast_packets; + s->tx_bytes = + s->tx_unicast_bytes + + s->tx_multicast_bytes + + s->tx_broadcast_bytes; + + /* Update calculated offload counters */ + s->tx_csum_offload = s->tx_packets - tx_offload_none; + s->rx_csum_good = s->rx_packets - s->rx_csum_none; + +free_out: + kvfree(out); +} + +static void mlx5e_update_stats_work(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct mlx5e_priv *priv = container_of(dwork, struct mlx5e_priv, + update_stats_work); + mutex_lock(&priv->state_lock); + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) { + mlx5e_update_stats(priv); + schedule_delayed_work(dwork, + msecs_to_jiffies( + MLX5E_UPDATE_STATS_INTERVAL)); + } + mutex_unlock(&priv->state_lock); +} + +static void __mlx5e_async_event(struct mlx5e_priv *priv, + enum mlx5_dev_event event) +{ + switch (event) { + case MLX5_DEV_EVENT_PORT_UP: + case MLX5_DEV_EVENT_PORT_DOWN: + schedule_work(&priv->update_carrier_work); + break; + + default: + break; + } +} + +static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, + enum mlx5_dev_event event, unsigned long param) +{ + struct mlx5e_priv *priv = vpriv; + + spin_lock(&priv->async_events_spinlock); + if (test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state)) + __mlx5e_async_event(priv, event); + spin_unlock(&priv->async_events_spinlock); +} + +static void mlx5e_enable_async_events(struct mlx5e_priv *priv) +{ + set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state); +} + +static void mlx5e_disable_async_events(struct mlx5e_priv *priv) +{ + spin_lock_irq(&priv->async_events_spinlock); + clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state); + spin_unlock_irq(&priv->async_events_spinlock); +} + +static void mlx5e_send_nop(struct mlx5e_sq *sq) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + + u16 pi = sq->pc & wq->sz_m1; + struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); + + struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; + + memset(cseg, 0, sizeof(*cseg)); + + cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_NOP); + cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | 0x01); + cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE; + + sq->skb[pi] = NULL; + sq->pc++; + mlx5e_tx_notify_hw(sq, wqe); +} + +static int mlx5e_create_rq(struct mlx5e_channel *c, + struct mlx5e_rq_param *param, + struct mlx5e_rq *rq) +{ + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + void *rqc = param->rqc; + void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq); + int wq_sz; + int err; + int i; + + err = mlx5_wq_ll_create(mdev, ¶m->wq, rqc_wq, &rq->wq, + &rq->wq_ctrl); + if (err) + return err; + + rq->wq.db = &rq->wq.db[MLX5_RCV_DBR]; + + wq_sz = mlx5_wq_ll_get_size(&rq->wq); + rq->skb = kzalloc_node(wq_sz * sizeof(*rq->skb), GFP_KERNEL, + cpu_to_node(c->cpu)); + if (!rq->skb) { + err = -ENOMEM; + goto err_rq_wq_destroy; + } + + rq->wqe_sz = (priv->params.lro_en) ? priv->params.lro_wqe_sz : + priv->netdev->mtu + ETH_HLEN + VLAN_HLEN; + + for (i = 0; i < wq_sz; i++) { + struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i); + + wqe->data.lkey = c->mkey_be; + wqe->data.byte_count = cpu_to_be32(rq->wqe_sz); + } + + rq->pdev = c->pdev; + rq->netdev = c->netdev; + rq->channel = c; + rq->ix = c->ix; + + return 0; + +err_rq_wq_destroy: + mlx5_wq_destroy(&rq->wq_ctrl); + + return err; +} + +static void mlx5e_destroy_rq(struct mlx5e_rq *rq) +{ + kfree(rq->skb); + mlx5_wq_destroy(&rq->wq_ctrl); +} + +static int mlx5e_enable_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param) +{ + struct mlx5e_channel *c = rq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + void *in; + void *rqc; + void *wq; + int inlen; + int err; + + inlen = MLX5_ST_SZ_BYTES(create_rq_in) + + sizeof(u64) * rq->wq_ctrl.buf.npages; + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + rqc = MLX5_ADDR_OF(create_rq_in, in, ctx); + wq = MLX5_ADDR_OF(rqc, rqc, wq); + + memcpy(rqc, param->rqc, sizeof(param->rqc)); + + MLX5_SET(rqc, rqc, cqn, c->rq.cq.mcq.cqn); + MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST); + MLX5_SET(rqc, rqc, flush_in_error_en, 1); + MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST); + MLX5_SET(wq, wq, log_wq_pg_sz, rq->wq_ctrl.buf.page_shift - + PAGE_SHIFT); + MLX5_SET64(wq, wq, dbr_addr, rq->wq_ctrl.db.dma); + + mlx5_fill_page_array(&rq->wq_ctrl.buf, + (__be64 *)MLX5_ADDR_OF(wq, wq, pas)); + + err = mlx5_create_rq(mdev, in, inlen, &rq->rqn); + + kvfree(in); + + return err; +} + +static int mlx5e_modify_rq(struct mlx5e_rq *rq, int curr_state, int next_state) +{ + struct mlx5e_channel *c = rq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + void *in; + void *rqc; + int inlen; + int err; + + inlen = MLX5_ST_SZ_BYTES(modify_rq_in); + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx); + + MLX5_SET(modify_rq_in, in, rq_state, curr_state); + MLX5_SET(rqc, rqc, state, next_state); + + err = mlx5_modify_rq(mdev, rq->rqn, in, inlen); + + kvfree(in); + + return err; +} + +static void mlx5e_disable_rq(struct mlx5e_rq *rq) +{ + struct mlx5e_channel *c = rq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + mlx5_destroy_rq(mdev, rq->rqn); +} + +static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq) +{ + struct mlx5e_channel *c = rq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_wq_ll *wq = &rq->wq; + int i; + + for (i = 0; i < 1000; i++) { + if (wq->cur_sz >= priv->params.min_rx_wqes) + return 0; + + msleep(20); + } + + return -ETIMEDOUT; +} + +static int mlx5e_open_rq(struct mlx5e_channel *c, + struct mlx5e_rq_param *param, + struct mlx5e_rq *rq) +{ + int err; + + err = mlx5e_create_rq(c, param, rq); + if (err) + return err; + + err = mlx5e_enable_rq(rq, param); + if (err) + goto err_destroy_rq; + + err = mlx5e_modify_rq(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY); + if (err) + goto err_disable_rq; + + set_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state); + mlx5e_send_nop(&c->sq[0]); /* trigger mlx5e_post_rx_wqes() */ + + return 0; + +err_disable_rq: + mlx5e_disable_rq(rq); +err_destroy_rq: + mlx5e_destroy_rq(rq); + + return err; +} + +static void mlx5e_close_rq(struct mlx5e_rq *rq) +{ + clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state); + napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ + + mlx5e_modify_rq(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR); + while (!mlx5_wq_ll_is_empty(&rq->wq)) + msleep(20); + + /* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */ + napi_synchronize(&rq->channel->napi); + + mlx5e_disable_rq(rq); + mlx5e_destroy_rq(rq); +} + +static void mlx5e_free_sq_db(struct mlx5e_sq *sq) +{ + kfree(sq->dma_fifo); + kfree(sq->skb); +} + +static int mlx5e_alloc_sq_db(struct mlx5e_sq *sq, int numa) +{ + int wq_sz = mlx5_wq_cyc_get_size(&sq->wq); + int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS; + + sq->skb = kzalloc_node(wq_sz * sizeof(*sq->skb), GFP_KERNEL, numa); + sq->dma_fifo = kzalloc_node(df_sz * sizeof(*sq->dma_fifo), GFP_KERNEL, + numa); + + if (!sq->skb || !sq->dma_fifo) { + mlx5e_free_sq_db(sq); + return -ENOMEM; + } + + sq->dma_fifo_mask = df_sz - 1; + + return 0; +} + +static int mlx5e_create_sq(struct mlx5e_channel *c, + int tc, + struct mlx5e_sq_param *param, + struct mlx5e_sq *sq) +{ + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + void *sqc = param->sqc; + void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq); + int err; + + err = mlx5_alloc_map_uar(mdev, &sq->uar); + if (err) + return err; + + err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, + &sq->wq_ctrl); + if (err) + goto err_unmap_free_uar; + + sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; + sq->uar_map = sq->uar.map; + sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2; + + if (mlx5e_alloc_sq_db(sq, cpu_to_node(c->cpu))) + goto err_sq_wq_destroy; + + sq->txq = netdev_get_tx_queue(priv->netdev, + c->ix + tc * priv->params.num_channels); + + sq->pdev = c->pdev; + sq->mkey_be = c->mkey_be; + sq->channel = c; + sq->tc = tc; + + return 0; + +err_sq_wq_destroy: + mlx5_wq_destroy(&sq->wq_ctrl); + +err_unmap_free_uar: + mlx5_unmap_free_uar(mdev, &sq->uar); + + return err; +} + +static void mlx5e_destroy_sq(struct mlx5e_sq *sq) +{ + struct mlx5e_channel *c = sq->channel; + struct mlx5e_priv *priv = c->priv; + + mlx5e_free_sq_db(sq); + mlx5_wq_destroy(&sq->wq_ctrl); + mlx5_unmap_free_uar(priv->mdev, &sq->uar); +} + +static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param) +{ + struct mlx5e_channel *c = sq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + void *in; + void *sqc; + void *wq; + int inlen; + int err; + + inlen = MLX5_ST_SZ_BYTES(create_sq_in) + + sizeof(u64) * sq->wq_ctrl.buf.npages; + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + sqc = MLX5_ADDR_OF(create_sq_in, in, ctx); + wq = MLX5_ADDR_OF(sqc, sqc, wq); + + memcpy(sqc, param->sqc, sizeof(param->sqc)); + + MLX5_SET(sqc, sqc, user_index, sq->tc); + MLX5_SET(sqc, sqc, tis_num_0, priv->tisn[sq->tc]); + MLX5_SET(sqc, sqc, cqn, c->sq[sq->tc].cq.mcq.cqn); + MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST); + MLX5_SET(sqc, sqc, tis_lst_sz, 1); + MLX5_SET(sqc, sqc, flush_in_error_en, 1); + + MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); + MLX5_SET(wq, wq, uar_page, sq->uar.index); + MLX5_SET(wq, wq, log_wq_pg_sz, sq->wq_ctrl.buf.page_shift - + PAGE_SHIFT); + MLX5_SET64(wq, wq, dbr_addr, sq->wq_ctrl.db.dma); + + mlx5_fill_page_array(&sq->wq_ctrl.buf, + (__be64 *)MLX5_ADDR_OF(wq, wq, pas)); + + err = mlx5_create_sq(mdev, in, inlen, &sq->sqn); + + kvfree(in); + + return err; +} + +static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state, int next_state) +{ + struct mlx5e_channel *c = sq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + void *in; + void *sqc; + int inlen; + int err; + + inlen = MLX5_ST_SZ_BYTES(modify_sq_in); + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx); + + MLX5_SET(modify_sq_in, in, sq_state, curr_state); + MLX5_SET(sqc, sqc, state, next_state); + + err = mlx5_modify_sq(mdev, sq->sqn, in, inlen); + + kvfree(in); + + return err; +} + +static void mlx5e_disable_sq(struct mlx5e_sq *sq) +{ + struct mlx5e_channel *c = sq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + mlx5_destroy_sq(mdev, sq->sqn); +} + +static int mlx5e_open_sq(struct mlx5e_channel *c, + int tc, + struct mlx5e_sq_param *param, + struct mlx5e_sq *sq) +{ + int err; + + err = mlx5e_create_sq(c, tc, param, sq); + if (err) + return err; + + err = mlx5e_enable_sq(sq, param); + if (err) + goto err_destroy_sq; + + err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RST, MLX5_SQC_STATE_RDY); + if (err) + goto err_disable_sq; + + set_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state); + netdev_tx_reset_queue(sq->txq); + netif_tx_start_queue(sq->txq); + + return 0; + +err_disable_sq: + mlx5e_disable_sq(sq); +err_destroy_sq: + mlx5e_destroy_sq(sq); + + return err; +} + +static inline void netif_tx_disable_queue(struct netdev_queue *txq) +{ + __netif_tx_lock_bh(txq); + netif_tx_stop_queue(txq); + __netif_tx_unlock_bh(txq); +} + +static void mlx5e_close_sq(struct mlx5e_sq *sq) +{ + clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state); + napi_synchronize(&sq->channel->napi); /* prevent netif_tx_wake_queue */ + netif_tx_disable_queue(sq->txq); + + /* ensure hw is notified of all pending wqes */ + if (mlx5e_sq_has_room_for(sq, 1)) + mlx5e_send_nop(sq); + + mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR); + while (sq->cc != sq->pc) /* wait till sq is empty */ + msleep(20); + + /* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */ + napi_synchronize(&sq->channel->napi); + + mlx5e_disable_sq(sq); + mlx5e_destroy_sq(sq); +} + +static int mlx5e_create_cq(struct mlx5e_channel *c, + struct mlx5e_cq_param *param, + struct mlx5e_cq *cq) +{ + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_core_cq *mcq = &cq->mcq; + int eqn_not_used; + int irqn; + int err; + u32 i; + + param->wq.numa = cpu_to_node(c->cpu); + param->eq_ix = c->ix; + + err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq, + &cq->wq_ctrl); + if (err) + return err; + + mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn); + + cq->napi = &c->napi; + + mcq->cqe_sz = 64; + mcq->set_ci_db = cq->wq_ctrl.db.db; + mcq->arm_db = cq->wq_ctrl.db.db + 1; + *mcq->set_ci_db = 0; + *mcq->arm_db = 0; + mcq->vector = param->eq_ix; + mcq->comp = mlx5e_completion_event; + mcq->event = mlx5e_cq_error_event; + mcq->irqn = irqn; + mcq->uar = &priv->cq_uar; + + for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) { + struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, i); + + cqe->op_own = 0xf1; + } + + cq->channel = c; + + return 0; +} + +static void mlx5e_destroy_cq(struct mlx5e_cq *cq) +{ + mlx5_wq_destroy(&cq->wq_ctrl); +} + +static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) +{ + struct mlx5e_channel *c = cq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_core_cq *mcq = &cq->mcq; + + void *in; + void *cqc; + int inlen; + int irqn_not_used; + int eqn; + int err; + + inlen = MLX5_ST_SZ_BYTES(create_cq_in) + + sizeof(u64) * cq->wq_ctrl.buf.npages; + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); + + memcpy(cqc, param->cqc, sizeof(param->cqc)); + + mlx5_fill_page_array(&cq->wq_ctrl.buf, + (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas)); + + mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used); + + MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, uar_page, mcq->uar->index); + MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - + PAGE_SHIFT); + MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma); + + err = mlx5_core_create_cq(mdev, mcq, in, inlen); + + kvfree(in); + + if (err) + return err; + + mlx5e_cq_arm(cq); + + return 0; +} + +static void mlx5e_disable_cq(struct mlx5e_cq *cq) +{ + struct mlx5e_channel *c = cq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + mlx5_core_destroy_cq(mdev, &cq->mcq); +} + +static int mlx5e_open_cq(struct mlx5e_channel *c, + struct mlx5e_cq_param *param, + struct mlx5e_cq *cq, + u16 moderation_usecs, + u16 moderation_frames) +{ + int err; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + err = mlx5e_create_cq(c, param, cq); + if (err) + return err; + + err = mlx5e_enable_cq(cq, param); + if (err) + goto err_destroy_cq; + + err = mlx5_core_modify_cq_moderation(mdev, &cq->mcq, + moderation_usecs, + moderation_frames); + if (err) + goto err_destroy_cq; + + return 0; + +err_destroy_cq: + mlx5e_destroy_cq(cq); + + return err; +} + +static void mlx5e_close_cq(struct mlx5e_cq *cq) +{ + mlx5e_disable_cq(cq); + mlx5e_destroy_cq(cq); +} + +static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix) +{ + return cpumask_first(priv->mdev->priv.irq_info[ix].mask); +} + +static int mlx5e_open_tx_cqs(struct mlx5e_channel *c, + struct mlx5e_channel_param *cparam) +{ + struct mlx5e_priv *priv = c->priv; + int err; + int tc; + + for (tc = 0; tc < c->num_tc; tc++) { + err = mlx5e_open_cq(c, &cparam->tx_cq, &c->sq[tc].cq, + priv->params.tx_cq_moderation_usec, + priv->params.tx_cq_moderation_pkts); + if (err) + goto err_close_tx_cqs; + + c->sq[tc].cq.sqrq = &c->sq[tc]; + } + + return 0; + +err_close_tx_cqs: + for (tc--; tc >= 0; tc--) + mlx5e_close_cq(&c->sq[tc].cq); + + return err; +} + +static void mlx5e_close_tx_cqs(struct mlx5e_channel *c) +{ + int tc; + + for (tc = 0; tc < c->num_tc; tc++) + mlx5e_close_cq(&c->sq[tc].cq); +} + +static int mlx5e_open_sqs(struct mlx5e_channel *c, + struct mlx5e_channel_param *cparam) +{ + int err; + int tc; + + for (tc = 0; tc < c->num_tc; tc++) { + err = mlx5e_open_sq(c, tc, &cparam->sq, &c->sq[tc]); + if (err) + goto err_close_sqs; + } + + return 0; + +err_close_sqs: + for (tc--; tc >= 0; tc--) + mlx5e_close_sq(&c->sq[tc]); + + return err; +} + +static void mlx5e_close_sqs(struct mlx5e_channel *c) +{ + int tc; + + for (tc = 0; tc < c->num_tc; tc++) + mlx5e_close_sq(&c->sq[tc]); +} + +static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, + struct mlx5e_channel_param *cparam, + struct mlx5e_channel **cp) +{ + struct net_device *netdev = priv->netdev; + int cpu = mlx5e_get_cpu(priv, ix); + struct mlx5e_channel *c; + int err; + + c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu)); + if (!c) + return -ENOMEM; + + c->priv = priv; + c->ix = ix; + c->cpu = cpu; + c->pdev = &priv->mdev->pdev->dev; + c->netdev = priv->netdev; + c->mkey_be = cpu_to_be32(priv->mr.key); + c->num_tc = priv->num_tc; + + netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64); + + err = mlx5e_open_tx_cqs(c, cparam); + if (err) + goto err_napi_del; + + err = mlx5e_open_cq(c, &cparam->rx_cq, &c->rq.cq, + priv->params.rx_cq_moderation_usec, + priv->params.rx_cq_moderation_pkts); + if (err) + goto err_close_tx_cqs; + c->rq.cq.sqrq = &c->rq; + + napi_enable(&c->napi); + + err = mlx5e_open_sqs(c, cparam); + if (err) + goto err_disable_napi; + + err = mlx5e_open_rq(c, &cparam->rq, &c->rq); + if (err) + goto err_close_sqs; + + netif_set_xps_queue(netdev, get_cpu_mask(c->cpu), ix); + *cp = c; + + return 0; + +err_close_sqs: + mlx5e_close_sqs(c); + +err_disable_napi: + napi_disable(&c->napi); + mlx5e_close_cq(&c->rq.cq); + +err_close_tx_cqs: + mlx5e_close_tx_cqs(c); + +err_napi_del: + netif_napi_del(&c->napi); + kfree(c); + + return err; +} + +static void mlx5e_close_channel(struct mlx5e_channel *c) +{ + mlx5e_close_rq(&c->rq); + mlx5e_close_sqs(c); + napi_disable(&c->napi); + mlx5e_close_cq(&c->rq.cq); + mlx5e_close_tx_cqs(c); + netif_napi_del(&c->napi); + kfree(c); +} + +static void mlx5e_build_rq_param(struct mlx5e_priv *priv, + struct mlx5e_rq_param *param) +{ + void *rqc = param->rqc; + void *wq = MLX5_ADDR_OF(rqc, rqc, wq); + + MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST); + MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN); + MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe))); + MLX5_SET(wq, wq, log_wq_sz, priv->params.log_rq_size); + MLX5_SET(wq, wq, pd, priv->pdn); + + param->wq.numa = dev_to_node(&priv->mdev->pdev->dev); + param->wq.linear = 1; +} + +static void mlx5e_build_sq_param(struct mlx5e_priv *priv, + struct mlx5e_sq_param *param) +{ + void *sqc = param->sqc; + void *wq = MLX5_ADDR_OF(sqc, sqc, wq); + + MLX5_SET(wq, wq, log_wq_sz, priv->params.log_sq_size); + MLX5_SET(wq, wq, log_wq_stride, ilog2(MLX5_SEND_WQE_BB)); + MLX5_SET(wq, wq, pd, priv->pdn); + + param->wq.numa = dev_to_node(&priv->mdev->pdev->dev); +} + +static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv, + struct mlx5e_cq_param *param) +{ + void *cqc = param->cqc; + + MLX5_SET(cqc, cqc, uar_page, priv->cq_uar.index); +} + +static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, + struct mlx5e_cq_param *param) +{ + void *cqc = param->cqc; + + MLX5_SET(cqc, cqc, log_cq_size, priv->params.log_rq_size); + + mlx5e_build_common_cq_param(priv, param); +} + +static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv, + struct mlx5e_cq_param *param) +{ + void *cqc = param->cqc; + + MLX5_SET(cqc, cqc, log_cq_size, priv->params.log_sq_size); + + mlx5e_build_common_cq_param(priv, param); +} + +static void mlx5e_build_channel_param(struct mlx5e_priv *priv, + struct mlx5e_channel_param *cparam) +{ + memset(cparam, 0, sizeof(*cparam)); + + mlx5e_build_rq_param(priv, &cparam->rq); + mlx5e_build_sq_param(priv, &cparam->sq); + mlx5e_build_rx_cq_param(priv, &cparam->rx_cq); + mlx5e_build_tx_cq_param(priv, &cparam->tx_cq); +} + +static int mlx5e_open_channels(struct mlx5e_priv *priv) +{ + struct mlx5e_channel_param cparam; + int err; + int i; + int j; + + priv->channel = kcalloc(priv->params.num_channels, + sizeof(struct mlx5e_channel *), GFP_KERNEL); + if (!priv->channel) + return -ENOMEM; + + mlx5e_build_channel_param(priv, &cparam); + for (i = 0; i < priv->params.num_channels; i++) { + err = mlx5e_open_channel(priv, i, &cparam, &priv->channel[i]); + if (err) + goto err_close_channels; + } + + for (j = 0; j < priv->params.num_channels; j++) { + err = mlx5e_wait_for_min_rx_wqes(&priv->channel[j]->rq); + if (err) + goto err_close_channels; + } + + return 0; + +err_close_channels: + for (i--; i >= 0; i--) + mlx5e_close_channel(priv->channel[i]); + + kfree(priv->channel); + + return err; +} + +static void mlx5e_close_channels(struct mlx5e_priv *priv) +{ + int i; + + for (i = 0; i < priv->params.num_channels; i++) + mlx5e_close_channel(priv->channel[i]); + + kfree(priv->channel); +} + +static int mlx5e_open_tis(struct mlx5e_priv *priv, int tc) +{ + struct mlx5_core_dev *mdev = priv->mdev; + u32 in[MLX5_ST_SZ_DW(create_tis_in)]; + void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); + + memset(in, 0, sizeof(in)); + + MLX5_SET(tisc, tisc, prio, tc); + + return mlx5_create_tis(mdev, in, sizeof(in), &priv->tisn[tc]); +} + +static void mlx5e_close_tis(struct mlx5e_priv *priv, int tc) +{ + mlx5_destroy_tis(priv->mdev, priv->tisn[tc]); +} + +static int mlx5e_open_tises(struct mlx5e_priv *priv) +{ + int num_tc = priv->num_tc; + int err; + int tc; + + for (tc = 0; tc < num_tc; tc++) { + err = mlx5e_open_tis(priv, tc); + if (err) + goto err_close_tises; + } + + return 0; + +err_close_tises: + for (tc--; tc >= 0; tc--) + mlx5e_close_tis(priv, tc); + + return err; +} + +static void mlx5e_close_tises(struct mlx5e_priv *priv) +{ + int num_tc = priv->num_tc; + int tc; + + for (tc = 0; tc < num_tc; tc++) + mlx5e_close_tis(priv, tc); +} + +static int mlx5e_open_rqt(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + u32 *in; + u32 out[MLX5_ST_SZ_DW(create_rqt_out)]; + void *rqtc; + int inlen; + int err; + int sz; + int i; + + sz = 1 << priv->params.rx_hash_log_tbl_sz; + + inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz; + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); + + MLX5_SET(rqtc, rqtc, rqt_actual_size, sz); + MLX5_SET(rqtc, rqtc, rqt_max_size, sz); + + for (i = 0; i < sz; i++) { + int ix = i % priv->params.num_channels; + + MLX5_SET(rqtc, rqtc, rq_num[i], priv->channel[ix]->rq.rqn); + } + + MLX5_SET(create_rqt_in, in, opcode, MLX5_CMD_OP_CREATE_RQT); + + memset(out, 0, sizeof(out)); + err = mlx5_cmd_exec_check_status(mdev, in, inlen, out, sizeof(out)); + if (!err) + priv->rqtn = MLX5_GET(create_rqt_out, out, rqtn); + + kvfree(in); + + return err; +} + +static void mlx5e_close_rqt(struct mlx5e_priv *priv) +{ + u32 in[MLX5_ST_SZ_DW(destroy_rqt_in)]; + u32 out[MLX5_ST_SZ_DW(destroy_rqt_out)]; + + memset(in, 0, sizeof(in)); + + MLX5_SET(destroy_rqt_in, in, opcode, MLX5_CMD_OP_DESTROY_RQT); + MLX5_SET(destroy_rqt_in, in, rqtn, priv->rqtn); + + mlx5_cmd_exec_check_status(priv->mdev, in, sizeof(in), out, + sizeof(out)); +} + +static void mlx5e_build_tir_ctx(struct mlx5e_priv *priv, u32 *tirc, int tt) +{ + void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer); + +#define ROUGH_MAX_L2_L3_HDR_SZ 256 + +#define MLX5_HASH_IP (MLX5_HASH_FIELD_SEL_SRC_IP |\ + MLX5_HASH_FIELD_SEL_DST_IP) + +#define MLX5_HASH_ALL (MLX5_HASH_FIELD_SEL_SRC_IP |\ + MLX5_HASH_FIELD_SEL_DST_IP |\ + MLX5_HASH_FIELD_SEL_L4_SPORT |\ + MLX5_HASH_FIELD_SEL_L4_DPORT) + + if (priv->params.lro_en) { + MLX5_SET(tirc, tirc, lro_enable_mask, + MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO | + MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO); + MLX5_SET(tirc, tirc, lro_max_ip_payload_size, + (priv->params.lro_wqe_sz - + ROUGH_MAX_L2_L3_HDR_SZ) >> 8); + MLX5_SET(tirc, tirc, lro_timeout_period_usecs, + MLX5_CAP_ETH(priv->mdev, + lro_timer_supported_periods[3])); + } + + switch (tt) { + case MLX5E_TT_ANY: + MLX5_SET(tirc, tirc, disp_type, + MLX5_TIRC_DISP_TYPE_DIRECT); + MLX5_SET(tirc, tirc, inline_rqn, + priv->channel[0]->rq.rqn); + break; + default: + MLX5_SET(tirc, tirc, disp_type, + MLX5_TIRC_DISP_TYPE_INDIRECT); + MLX5_SET(tirc, tirc, indirect_table, + priv->rqtn); + MLX5_SET(tirc, tirc, rx_hash_fn, + MLX5_TIRC_RX_HASH_FN_HASH_TOEPLITZ); + MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); + netdev_rss_key_fill(MLX5_ADDR_OF(tirc, tirc, + rx_hash_toeplitz_key), + MLX5_FLD_SZ_BYTES(tirc, + rx_hash_toeplitz_key)); + break; + } + + switch (tt) { + case MLX5E_TT_IPV4_TCP: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV4); + MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, + MLX5_L4_PROT_TYPE_TCP); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_ALL); + break; + + case MLX5E_TT_IPV6_TCP: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV6); + MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, + MLX5_L4_PROT_TYPE_TCP); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_ALL); + break; + + case MLX5E_TT_IPV4_UDP: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV4); + MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, + MLX5_L4_PROT_TYPE_UDP); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_ALL); + break; + + case MLX5E_TT_IPV6_UDP: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV6); + MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, + MLX5_L4_PROT_TYPE_UDP); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_ALL); + break; + + case MLX5E_TT_IPV4: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV4); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP); + break; + + case MLX5E_TT_IPV6: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV6); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP); + break; + } +} + +static int mlx5e_open_tir(struct mlx5e_priv *priv, int tt) +{ + struct mlx5_core_dev *mdev = priv->mdev; + u32 *in; + void *tirc; + int inlen; + int err; + + inlen = MLX5_ST_SZ_BYTES(create_tir_in); + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); + + mlx5e_build_tir_ctx(priv, tirc, tt); + + err = mlx5_create_tir(mdev, in, inlen, &priv->tirn[tt]); + + kvfree(in); + + return err; +} + +static void mlx5e_close_tir(struct mlx5e_priv *priv, int tt) +{ + mlx5_destroy_tir(priv->mdev, priv->tirn[tt]); +} + +static int mlx5e_open_tirs(struct mlx5e_priv *priv) +{ + int err; + int i; + + for (i = 0; i < MLX5E_NUM_TT; i++) { + err = mlx5e_open_tir(priv, i); + if (err) + goto err_close_tirs; + } + + return 0; + +err_close_tirs: + for (i--; i >= 0; i--) + mlx5e_close_tir(priv, i); + + return err; +} + +static void mlx5e_close_tirs(struct mlx5e_priv *priv) +{ + int i; + + for (i = 0; i < MLX5E_NUM_TT; i++) + mlx5e_close_tir(priv, i); +} + +int mlx5e_open_locked(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + int actual_mtu; + int num_txqs; + int err; + + num_txqs = roundup_pow_of_two(priv->params.num_channels) * + priv->params.num_tc; + netif_set_real_num_tx_queues(netdev, num_txqs); + netif_set_real_num_rx_queues(netdev, priv->params.num_channels); + + err = mlx5_set_port_mtu(mdev, netdev->mtu); + if (err) { + netdev_err(netdev, "%s: mlx5_set_port_mtu failed %d\n", + __func__, err); + return err; + } + + err = mlx5_query_port_oper_mtu(mdev, &actual_mtu); + if (err) { + netdev_err(netdev, "%s: mlx5_query_port_oper_mtu failed %d\n", + __func__, err); + return err; + } + + if (actual_mtu != netdev->mtu) + netdev_warn(netdev, "%s: Failed to set MTU to %d\n", + __func__, netdev->mtu); + + netdev->mtu = actual_mtu; + + err = mlx5e_open_tises(priv); + if (err) { + netdev_err(netdev, "%s: mlx5e_open_tises failed, %d\n", + __func__, err); + return err; + } + + err = mlx5e_open_channels(priv); + if (err) { + netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n", + __func__, err); + goto err_close_tises; + } + + err = mlx5e_open_rqt(priv); + if (err) { + netdev_err(netdev, "%s: mlx5e_open_rqt failed, %d\n", + __func__, err); + goto err_close_channels; + } + + err = mlx5e_open_tirs(priv); + if (err) { + netdev_err(netdev, "%s: mlx5e_open_tir failed, %d\n", + __func__, err); + goto err_close_rqls; + } + + err = mlx5e_open_flow_table(priv); + if (err) { + netdev_err(netdev, "%s: mlx5e_open_flow_table failed, %d\n", + __func__, err); + goto err_close_tirs; + } + + err = mlx5e_add_all_vlan_rules(priv); + if (err) { + netdev_err(netdev, "%s: mlx5e_add_all_vlan_rules failed, %d\n", + __func__, err); + goto err_close_flow_table; + } + + mlx5e_init_eth_addr(priv); + + set_bit(MLX5E_STATE_OPENED, &priv->state); + + mlx5e_update_carrier(priv); + mlx5e_set_rx_mode_core(priv); + + schedule_delayed_work(&priv->update_stats_work, 0); + return 0; + +err_close_flow_table: + mlx5e_close_flow_table(priv); + +err_close_tirs: + mlx5e_close_tirs(priv); + +err_close_rqls: + mlx5e_close_rqt(priv); + +err_close_channels: + mlx5e_close_channels(priv); + +err_close_tises: + mlx5e_close_tises(priv); + + return err; +} + +static int mlx5e_open(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + int err; + + mutex_lock(&priv->state_lock); + err = mlx5e_open_locked(netdev); + mutex_unlock(&priv->state_lock); + + return err; +} + +int mlx5e_close_locked(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + clear_bit(MLX5E_STATE_OPENED, &priv->state); + + mlx5e_set_rx_mode_core(priv); + mlx5e_del_all_vlan_rules(priv); + netif_carrier_off(priv->netdev); + mlx5e_close_flow_table(priv); + mlx5e_close_tirs(priv); + mlx5e_close_rqt(priv); + mlx5e_close_channels(priv); + mlx5e_close_tises(priv); + + return 0; +} + +static int mlx5e_close(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + int err; + + mutex_lock(&priv->state_lock); + err = mlx5e_close_locked(netdev); + mutex_unlock(&priv->state_lock); + + return err; +} + +int mlx5e_update_priv_params(struct mlx5e_priv *priv, + struct mlx5e_params *new_params) +{ + int err = 0; + int was_opened; + + WARN_ON(!mutex_is_locked(&priv->state_lock)); + + was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state); + if (was_opened) + mlx5e_close_locked(priv->netdev); + + priv->params = *new_params; + + if (was_opened) + err = mlx5e_open_locked(priv->netdev); + + return err; +} + +static struct rtnl_link_stats64 * +mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_vport_stats *vstats = &priv->stats.vport; + + stats->rx_packets = vstats->rx_packets; + stats->rx_bytes = vstats->rx_bytes; + stats->tx_packets = vstats->tx_packets; + stats->tx_bytes = vstats->tx_bytes; + stats->multicast = vstats->rx_multicast_packets + + vstats->tx_multicast_packets; + stats->tx_errors = vstats->tx_error_packets; + stats->rx_errors = vstats->rx_error_packets; + stats->tx_dropped = vstats->tx_queue_dropped; + stats->rx_crc_errors = 0; + stats->rx_length_errors = 0; + + return stats; +} + +static void mlx5e_set_rx_mode(struct net_device *dev) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + schedule_work(&priv->set_rx_mode_work); +} + +static int mlx5e_set_mac(struct net_device *netdev, void *addr) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct sockaddr *saddr = addr; + + if (!is_valid_ether_addr(saddr->sa_data)) + return -EADDRNOTAVAIL; + + netif_addr_lock_bh(netdev); + ether_addr_copy(netdev->dev_addr, saddr->sa_data); + netif_addr_unlock_bh(netdev); + + schedule_work(&priv->set_rx_mode_work); + + return 0; +} + +static int mlx5e_set_features(struct net_device *netdev, + netdev_features_t features) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + netdev_features_t changes = features ^ netdev->features; + struct mlx5e_params new_params; + bool update_params = false; + + mutex_lock(&priv->state_lock); + new_params = priv->params; + + if (changes & NETIF_F_LRO) { + new_params.lro_en = !!(features & NETIF_F_LRO); + update_params = true; + } + + if (update_params) + mlx5e_update_priv_params(priv, &new_params); + + if (changes & NETIF_F_HW_VLAN_CTAG_FILTER) { + if (features & NETIF_F_HW_VLAN_CTAG_FILTER) + mlx5e_enable_vlan_filter(priv); + else + mlx5e_disable_vlan_filter(priv); + } + + mutex_unlock(&priv->state_lock); + + return 0; +} + +static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + int max_mtu; + int err = 0; + + err = mlx5_query_port_max_mtu(mdev, &max_mtu); + if (err) + return err; + + if (new_mtu > max_mtu || new_mtu < MLX5E_PARAMS_MIN_MTU) { + netdev_err(netdev, "%s: Bad MTU size, mtu must be [%d-%d]\n", + __func__, MLX5E_PARAMS_MIN_MTU, max_mtu); + return -EINVAL; + } + + mutex_lock(&priv->state_lock); + netdev->mtu = new_mtu; + err = mlx5e_update_priv_params(priv, &priv->params); + mutex_unlock(&priv->state_lock); + + return err; +} + +static struct net_device_ops mlx5e_netdev_ops = { + .ndo_open = mlx5e_open, + .ndo_stop = mlx5e_close, + .ndo_start_xmit = mlx5e_xmit, + .ndo_get_stats64 = mlx5e_get_stats, + .ndo_set_rx_mode = mlx5e_set_rx_mode, + .ndo_set_mac_address = mlx5e_set_mac, + .ndo_vlan_rx_add_vid = mlx5e_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = mlx5e_vlan_rx_kill_vid, + .ndo_set_features = mlx5e_set_features, + .ndo_change_mtu = mlx5e_change_mtu, +}; + +static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) +{ + if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) + return -ENOTSUPP; + if (!MLX5_CAP_GEN(mdev, eth_net_offloads) || + !MLX5_CAP_GEN(mdev, nic_flow_table) || + !MLX5_CAP_ETH(mdev, csum_cap) || + !MLX5_CAP_ETH(mdev, max_lso_cap) || + !MLX5_CAP_ETH(mdev, vlan_cap) || + !MLX5_CAP_ETH(mdev, rss_ind_tbl_cap)) { + mlx5_core_warn(mdev, + "Not creating net device, some required device capabilities are missing\n"); + return -ENOTSUPP; + } + return 0; +} + +static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, + struct net_device *netdev, + int num_comp_vectors) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + priv->params.log_sq_size = + MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; + priv->params.log_rq_size = + MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE; + priv->params.rx_cq_moderation_usec = + MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC; + priv->params.rx_cq_moderation_pkts = + MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS; + priv->params.tx_cq_moderation_usec = + MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC; + priv->params.tx_cq_moderation_pkts = + MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS; + priv->params.min_rx_wqes = + MLX5E_PARAMS_DEFAULT_MIN_RX_WQES; + priv->params.rx_hash_log_tbl_sz = + (order_base_2(num_comp_vectors) > + MLX5E_PARAMS_DEFAULT_RX_HASH_LOG_TBL_SZ) ? + order_base_2(num_comp_vectors) : + MLX5E_PARAMS_DEFAULT_RX_HASH_LOG_TBL_SZ; + priv->params.num_tc = 1; + priv->params.default_vlan_prio = 0; + + priv->params.lro_en = false && !!MLX5_CAP_ETH(priv->mdev, lro_cap); + priv->params.lro_wqe_sz = + MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; + + priv->mdev = mdev; + priv->netdev = netdev; + priv->params.num_channels = num_comp_vectors; + priv->order_base_2_num_channels = order_base_2(num_comp_vectors); + priv->queue_mapping_channel_mask = + roundup_pow_of_two(num_comp_vectors) - 1; + priv->num_tc = priv->params.num_tc; + priv->default_vlan_prio = priv->params.default_vlan_prio; + + spin_lock_init(&priv->async_events_spinlock); + mutex_init(&priv->state_lock); + + INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work); + INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work); + INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work); +} + +static void mlx5e_set_netdev_dev_addr(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + mlx5_query_vport_mac_address(priv->mdev, netdev->dev_addr); +} + +static void mlx5e_build_netdev(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + + SET_NETDEV_DEV(netdev, &mdev->pdev->dev); + + if (priv->num_tc > 1) { + mlx5e_netdev_ops.ndo_select_queue = mlx5e_select_queue; + mlx5e_netdev_ops.ndo_start_xmit = mlx5e_xmit_multi_tc; + } + + netdev->netdev_ops = &mlx5e_netdev_ops; + netdev->watchdog_timeo = 15 * HZ; + + netdev->ethtool_ops = &mlx5e_ethtool_ops; + + netdev->vlan_features |= NETIF_F_IP_CSUM; + netdev->vlan_features |= NETIF_F_IPV6_CSUM; + netdev->vlan_features |= NETIF_F_GRO; + netdev->vlan_features |= NETIF_F_TSO; + netdev->vlan_features |= NETIF_F_TSO6; + netdev->vlan_features |= NETIF_F_RXCSUM; + netdev->vlan_features |= NETIF_F_RXHASH; + + if (!!MLX5_CAP_ETH(mdev, lro_cap)) + netdev->vlan_features |= NETIF_F_LRO; + + netdev->hw_features = netdev->vlan_features; + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX; + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + netdev->features = netdev->hw_features; + if (!priv->params.lro_en) + netdev->features &= ~NETIF_F_LRO; + + netdev->features |= NETIF_F_HIGHDMA; + + netdev->priv_flags |= IFF_UNICAST_FLT; + + mlx5e_set_netdev_dev_addr(netdev); +} + +static int mlx5e_create_mkey(struct mlx5e_priv *priv, u32 pdn, + struct mlx5_core_mr *mr) +{ + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_create_mkey_mbox_in *in; + int err; + + in = mlx5_vzalloc(sizeof(*in)); + if (!in) + return -ENOMEM; + + in->seg.flags = MLX5_PERM_LOCAL_WRITE | + MLX5_PERM_LOCAL_READ | + MLX5_ACCESS_MODE_PA; + in->seg.flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64); + in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8); + + err = mlx5_core_create_mkey(mdev, mr, in, sizeof(*in), NULL, NULL, + NULL); + + kvfree(in); + + return err; +} + +static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) +{ + struct net_device *netdev; + struct mlx5e_priv *priv; + int ncv = mdev->priv.eq_table.num_comp_vectors; + int err; + + if (mlx5e_check_required_hca_cap(mdev)) + return NULL; + + netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), + roundup_pow_of_two(ncv) * MLX5E_MAX_NUM_TC, + ncv); + if (!netdev) { + mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n"); + return NULL; + } + + mlx5e_build_netdev_priv(mdev, netdev, ncv); + mlx5e_build_netdev(netdev); + + netif_carrier_off(netdev); + + priv = netdev_priv(netdev); + + err = mlx5_alloc_map_uar(mdev, &priv->cq_uar); + if (err) { + netdev_err(netdev, "%s: mlx5_alloc_map_uar failed, %d\n", + __func__, err); + goto err_free_netdev; + } + + err = mlx5_core_alloc_pd(mdev, &priv->pdn); + if (err) { + netdev_err(netdev, "%s: mlx5_core_alloc_pd failed, %d\n", + __func__, err); + goto err_unmap_free_uar; + } + + err = mlx5e_create_mkey(priv, priv->pdn, &priv->mr); + if (err) { + netdev_err(netdev, "%s: mlx5e_create_mkey failed, %d\n", + __func__, err); + goto err_dealloc_pd; + } + + err = register_netdev(netdev); + if (err) { + netdev_err(netdev, "%s: register_netdev failed, %d\n", + __func__, err); + goto err_destroy_mkey; + } + + mlx5e_enable_async_events(priv); + + return priv; + +err_destroy_mkey: + mlx5_core_destroy_mkey(mdev, &priv->mr); + +err_dealloc_pd: + mlx5_core_dealloc_pd(mdev, priv->pdn); + +err_unmap_free_uar: + mlx5_unmap_free_uar(mdev, &priv->cq_uar); + +err_free_netdev: + free_netdev(netdev); + + return NULL; +} + +static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) +{ + struct mlx5e_priv *priv = vpriv; + struct net_device *netdev = priv->netdev; + + unregister_netdev(netdev); + mlx5_core_destroy_mkey(priv->mdev, &priv->mr); + mlx5_core_dealloc_pd(priv->mdev, priv->pdn); + mlx5_unmap_free_uar(priv->mdev, &priv->cq_uar); + mlx5e_disable_async_events(priv); + flush_scheduled_work(); + free_netdev(netdev); +} + +static void *mlx5e_get_netdev(void *vpriv) +{ + struct mlx5e_priv *priv = vpriv; + + return priv->netdev; +} + +static struct mlx5_interface mlx5e_interface = { + .add = mlx5e_create_netdev, + .remove = mlx5e_destroy_netdev, + .event = mlx5e_async_event, + .protocol = MLX5_INTERFACE_PROTOCOL_ETH, + .get_dev = mlx5e_get_netdev, +}; + +void mlx5e_init(void) +{ + mlx5_register_interface(&mlx5e_interface); +} + +void mlx5e_cleanup(void) +{ + mlx5_unregister_interface(&mlx5e_interface); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c new file mode 100644 index 0000000..ce1317c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -0,0 +1,249 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include "en.h" + +static inline int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, + struct mlx5e_rx_wqe *wqe, u16 ix) +{ + struct sk_buff *skb; + dma_addr_t dma_addr; + + skb = netdev_alloc_skb(rq->netdev, rq->wqe_sz); + if (unlikely(!skb)) + return -ENOMEM; + + skb_reserve(skb, MLX5E_NET_IP_ALIGN); + + dma_addr = dma_map_single(rq->pdev, + /* hw start padding */ + skb->data - MLX5E_NET_IP_ALIGN, + /* hw end padding */ + rq->wqe_sz, + DMA_FROM_DEVICE); + + if (unlikely(dma_mapping_error(rq->pdev, dma_addr))) + goto err_free_skb; + + *((dma_addr_t *)skb->cb) = dma_addr; + wqe->data.addr = cpu_to_be64(dma_addr + MLX5E_NET_IP_ALIGN); + + rq->skb[ix] = skb; + + return 0; + +err_free_skb: + dev_kfree_skb(skb); + + return -ENOMEM; +} + +bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) +{ + struct mlx5_wq_ll *wq = &rq->wq; + + if (unlikely(!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state))) + return false; + + while (!mlx5_wq_ll_is_full(wq)) { + struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head); + + if (unlikely(mlx5e_alloc_rx_wqe(rq, wqe, wq->head))) + break; + + mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index)); + } + + /* ensure wqes are visible to device before updating doorbell record */ + dma_wmb(); + + mlx5_wq_ll_update_db_record(wq); + + return !mlx5_wq_ll_is_full(wq); +} + +static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe) +{ + struct ethhdr *eth = (struct ethhdr *)(skb->data); + struct iphdr *ipv4 = (struct iphdr *)(skb->data + ETH_HLEN); + struct ipv6hdr *ipv6 = (struct ipv6hdr *)(skb->data + ETH_HLEN); + struct tcphdr *tcp; + + u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe); + int tcp_ack = ((CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA == l4_hdr_type) || + (CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA == l4_hdr_type)); + + u16 tot_len = be32_to_cpu(cqe->byte_cnt) - ETH_HLEN; + + if (eth->h_proto == htons(ETH_P_IP)) { + tcp = (struct tcphdr *)(skb->data + ETH_HLEN + + sizeof(struct iphdr)); + ipv6 = NULL; + } else { + tcp = (struct tcphdr *)(skb->data + ETH_HLEN + + sizeof(struct ipv6hdr)); + ipv4 = NULL; + } + + if (get_cqe_lro_tcppsh(cqe)) + tcp->psh = 1; + + if (tcp_ack) { + tcp->ack = 1; + tcp->ack_seq = cqe->lro_ack_seq_num; + tcp->window = cqe->lro_tcp_win; + } + + if (ipv4) { + ipv4->ttl = cqe->lro_min_ttl; + ipv4->tot_len = cpu_to_be16(tot_len); + ipv4->check = 0; + ipv4->check = ip_fast_csum((unsigned char *)ipv4, + ipv4->ihl); + } else { + ipv6->hop_limit = cqe->lro_min_ttl; + ipv6->payload_len = cpu_to_be16(tot_len - + sizeof(struct ipv6hdr)); + } +} + +static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe, + struct sk_buff *skb) +{ + u8 cht = cqe->rss_hash_type; + int ht = (cht & CQE_RSS_HTYPE_L4) ? PKT_HASH_TYPE_L4 : + (cht & CQE_RSS_HTYPE_IP) ? PKT_HASH_TYPE_L3 : + PKT_HASH_TYPE_NONE; + skb_set_hash(skb, be32_to_cpu(cqe->rss_hash_result), ht); +} + +static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, + struct mlx5e_rq *rq, + struct sk_buff *skb) +{ + struct net_device *netdev = rq->netdev; + u32 cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + int lro_num_seg; + + skb_put(skb, cqe_bcnt); + + lro_num_seg = be32_to_cpu(cqe->srqn) >> 24; + if (lro_num_seg > 1) { + mlx5e_lro_update_hdr(skb, cqe); + skb_shinfo(skb)->gso_size = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; + rq->stats.lro_packets++; + rq->stats.lro_bytes += cqe_bcnt; + } + + if (likely(netdev->features & NETIF_F_RXCSUM) && + (cqe->hds_ip_ext & CQE_L2_OK) && + (cqe->hds_ip_ext & CQE_L3_OK) && + (cqe->hds_ip_ext & CQE_L4_OK)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + } else { + skb->ip_summed = CHECKSUM_NONE; + rq->stats.csum_none++; + } + + skb->protocol = eth_type_trans(skb, netdev); + + skb_record_rx_queue(skb, rq->ix); + + if (likely(netdev->features & NETIF_F_RXHASH)) + mlx5e_skb_set_hash(cqe, skb); + + if (cqe_has_vlan(cqe)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + be16_to_cpu(cqe->vlan_info)); +} + +bool mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) +{ + struct mlx5e_rq *rq = cq->sqrq; + int i; + + /* avoid accessing cq (dma coherent memory) if not needed */ + if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags)) + return false; + + for (i = 0; i < budget; i++) { + struct mlx5e_rx_wqe *wqe; + struct mlx5_cqe64 *cqe; + struct sk_buff *skb; + __be16 wqe_counter_be; + u16 wqe_counter; + + cqe = mlx5e_get_cqe(cq); + if (!cqe) + break; + + wqe_counter_be = cqe->wqe_counter; + wqe_counter = be16_to_cpu(wqe_counter_be); + wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter); + skb = rq->skb[wqe_counter]; + rq->skb[wqe_counter] = NULL; + + dma_unmap_single(rq->pdev, + *((dma_addr_t *)skb->cb), + skb_end_offset(skb), + DMA_FROM_DEVICE); + + if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) { + rq->stats.wqe_err++; + dev_kfree_skb(skb); + goto wq_ll_pop; + } + + mlx5e_build_rx_skb(cqe, rq, skb); + rq->stats.packets++; + napi_gro_receive(cq->napi, skb); + +wq_ll_pop: + mlx5_wq_ll_pop(&rq->wq, wqe_counter_be, + &wqe->next.next_wqe_index); + } + + mlx5_cqwq_update_db_record(&cq->wq); + + /* ensure cq space is freed before enabling more cqes */ + wmb(); + + if (i == budget) { + set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); + return true; + } + + return false; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c new file mode 100644 index 0000000..8020986 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -0,0 +1,344 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/tcp.h> +#include <linux/if_vlan.h> +#include "en.h" + +static void mlx5e_dma_pop_last_pushed(struct mlx5e_sq *sq, dma_addr_t *addr, + u32 *size) +{ + sq->dma_fifo_pc--; + *addr = sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr; + *size = sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size; +} + +static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, struct sk_buff *skb) +{ + dma_addr_t addr; + u32 size; + int i; + + for (i = 0; i < MLX5E_TX_SKB_CB(skb)->num_dma; i++) { + mlx5e_dma_pop_last_pushed(sq, &addr, &size); + dma_unmap_single(sq->pdev, addr, size, DMA_TO_DEVICE); + } +} + +static inline void mlx5e_dma_push(struct mlx5e_sq *sq, dma_addr_t addr, + u32 size) +{ + sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr = addr; + sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size = size; + sq->dma_fifo_pc++; +} + +static inline void mlx5e_dma_get(struct mlx5e_sq *sq, u32 i, dma_addr_t *addr, + u32 *size) +{ + *addr = sq->dma_fifo[i & sq->dma_fifo_mask].addr; + *size = sq->dma_fifo[i & sq->dma_fifo_mask].size; +} + +u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int channel_ix = fallback(dev, skb); + int up = skb_vlan_tag_present(skb) ? + skb->vlan_tci >> VLAN_PRIO_SHIFT : + priv->default_vlan_prio; + int tc = netdev_get_prio_tc_map(dev, up); + + return (tc << priv->order_base_2_num_channels) | channel_ix; +} + +static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq, + struct sk_buff *skb) +{ +#define MLX5E_MIN_INLINE 16 /* eth header with vlan (w/o next ethertype) */ + return MLX5E_MIN_INLINE; +} + +static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) +{ + struct vlan_ethhdr *vhdr = (struct vlan_ethhdr *)start; + int cpy1_sz = 2 * ETH_ALEN; + int cpy2_sz = ihs - cpy1_sz - VLAN_HLEN; + + skb_copy_from_linear_data(skb, vhdr, cpy1_sz); + skb_pull_inline(skb, cpy1_sz); + vhdr->h_vlan_proto = skb->vlan_proto; + vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb)); + skb_copy_from_linear_data(skb, &vhdr->h_vlan_encapsulated_proto, + cpy2_sz); + skb_pull_inline(skb, cpy2_sz); +} + +static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + + u16 pi = sq->pc & wq->sz_m1; + struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); + + struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; + struct mlx5_wqe_eth_seg *eseg = &wqe->eth; + struct mlx5_wqe_data_seg *dseg; + + u8 opcode = MLX5_OPCODE_SEND; + dma_addr_t dma_addr = 0; + u16 headlen; + u16 ds_cnt; + u16 ihs; + int i; + + memset(wqe, 0, sizeof(*wqe)); + + if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) + eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM; + else + sq->stats.csum_offload_none++; + + if (skb_is_gso(skb)) { + u32 payload_len; + int num_pkts; + + eseg->mss = cpu_to_be16(skb_shinfo(skb)->gso_size); + opcode = MLX5_OPCODE_LSO; + ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); + payload_len = skb->len - ihs; + num_pkts = (payload_len / skb_shinfo(skb)->gso_size) + + !!(payload_len % skb_shinfo(skb)->gso_size); + MLX5E_TX_SKB_CB(skb)->num_bytes = skb->len + + (num_pkts - 1) * ihs; + sq->stats.tso_packets++; + sq->stats.tso_bytes += payload_len; + } else { + ihs = mlx5e_get_inline_hdr_size(sq, skb); + MLX5E_TX_SKB_CB(skb)->num_bytes = max_t(unsigned int, skb->len, + ETH_ZLEN); + } + + if (skb_vlan_tag_present(skb)) { + mlx5e_insert_vlan(eseg->inline_hdr_start, skb, ihs); + } else { + skb_copy_from_linear_data(skb, eseg->inline_hdr_start, ihs); + skb_pull_inline(skb, ihs); + } + + eseg->inline_hdr_sz = cpu_to_be16(ihs); + + ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS; + ds_cnt += DIV_ROUND_UP(ihs - sizeof(eseg->inline_hdr_start), + MLX5_SEND_WQE_DS); + dseg = (struct mlx5_wqe_data_seg *)cseg + ds_cnt; + + MLX5E_TX_SKB_CB(skb)->num_dma = 0; + + headlen = skb_headlen(skb); + if (headlen) { + dma_addr = dma_map_single(sq->pdev, skb->data, headlen, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(sq->pdev, dma_addr))) + goto dma_unmap_wqe_err; + + dseg->addr = cpu_to_be64(dma_addr); + dseg->lkey = sq->mkey_be; + dseg->byte_count = cpu_to_be32(headlen); + + mlx5e_dma_push(sq, dma_addr, headlen); + MLX5E_TX_SKB_CB(skb)->num_dma++; + + dseg++; + } + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + int fsz = skb_frag_size(frag); + + dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(sq->pdev, dma_addr))) + goto dma_unmap_wqe_err; + + dseg->addr = cpu_to_be64(dma_addr); + dseg->lkey = sq->mkey_be; + dseg->byte_count = cpu_to_be32(fsz); + + mlx5e_dma_push(sq, dma_addr, fsz); + MLX5E_TX_SKB_CB(skb)->num_dma++; + + dseg++; + } + + ds_cnt += MLX5E_TX_SKB_CB(skb)->num_dma; + + cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode); + cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt); + cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE; + + sq->skb[pi] = skb; + + MLX5E_TX_SKB_CB(skb)->num_wqebbs = DIV_ROUND_UP(ds_cnt, + MLX5_SEND_WQEBB_NUM_DS); + sq->pc += MLX5E_TX_SKB_CB(skb)->num_wqebbs; + + netdev_tx_sent_queue(sq->txq, MLX5E_TX_SKB_CB(skb)->num_bytes); + + if (unlikely(!mlx5e_sq_has_room_for(sq, MLX5_SEND_WQE_MAX_WQEBBS))) { + netif_tx_stop_queue(sq->txq); + sq->stats.stopped++; + } + + if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) + mlx5e_tx_notify_hw(sq, wqe); + + sq->stats.packets++; + return NETDEV_TX_OK; + +dma_unmap_wqe_err: + sq->stats.dropped++; + mlx5e_dma_unmap_wqe_err(sq, skb); + + dev_kfree_skb_any(skb); + + return NETDEV_TX_OK; +} + +netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int ix = skb->queue_mapping; + int tc = 0; + struct mlx5e_channel *c = priv->channel[ix]; + struct mlx5e_sq *sq = &c->sq[tc]; + + return mlx5e_sq_xmit(sq, skb); +} + +netdev_tx_t mlx5e_xmit_multi_tc(struct sk_buff *skb, struct net_device *dev) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int ix = skb->queue_mapping & priv->queue_mapping_channel_mask; + int tc = skb->queue_mapping >> priv->order_base_2_num_channels; + struct mlx5e_channel *c = priv->channel[ix]; + struct mlx5e_sq *sq = &c->sq[tc]; + + return mlx5e_sq_xmit(sq, skb); +} + +bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) +{ + struct mlx5e_sq *sq; + u32 dma_fifo_cc; + u32 nbytes; + u16 npkts; + u16 sqcc; + int i; + + /* avoid accessing cq (dma coherent memory) if not needed */ + if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags)) + return false; + + sq = cq->sqrq; + + npkts = 0; + nbytes = 0; + + /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), + * otherwise a cq overrun may occur + */ + sqcc = sq->cc; + + /* avoid dirtying sq cache line every cqe */ + dma_fifo_cc = sq->dma_fifo_cc; + + for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) { + struct mlx5_cqe64 *cqe; + struct sk_buff *skb; + u16 ci; + int j; + + cqe = mlx5e_get_cqe(cq); + if (!cqe) + break; + + ci = sqcc & sq->wq.sz_m1; + skb = sq->skb[ci]; + + if (unlikely(!skb)) { /* nop */ + sq->stats.nop++; + sqcc++; + goto free_skb; + } + + for (j = 0; j < MLX5E_TX_SKB_CB(skb)->num_dma; j++) { + dma_addr_t addr; + u32 size; + + mlx5e_dma_get(sq, dma_fifo_cc, &addr, &size); + dma_fifo_cc++; + dma_unmap_single(sq->pdev, addr, size, DMA_TO_DEVICE); + } + + npkts++; + nbytes += MLX5E_TX_SKB_CB(skb)->num_bytes; + sqcc += MLX5E_TX_SKB_CB(skb)->num_wqebbs; + +free_skb: + dev_kfree_skb(skb); + } + + mlx5_cqwq_update_db_record(&cq->wq); + + /* ensure cq space is freed before enabling more cqes */ + wmb(); + + sq->dma_fifo_cc = dma_fifo_cc; + sq->cc = sqcc; + + netdev_tx_completed_queue(sq->txq, npkts, nbytes); + + if (netif_tx_queue_stopped(sq->txq) && + mlx5e_sq_has_room_for(sq, MLX5_SEND_WQE_MAX_WQEBBS) && + likely(test_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state))) { + netif_tx_wake_queue(sq->txq); + sq->stats.wake++; + } + if (i == MLX5E_TX_CQ_POLL_BUDGET) { + set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); + return true; + } + + return false; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c new file mode 100644 index 0000000..088bc42 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -0,0 +1,107 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include "en.h" + +struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq) +{ + struct mlx5_cqwq *wq = &cq->wq; + u32 ci = mlx5_cqwq_get_ci(wq); + struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(wq, ci); + int cqe_ownership_bit = cqe->op_own & MLX5_CQE_OWNER_MASK; + int sw_ownership_val = mlx5_cqwq_get_wrap_cnt(wq) & 1; + + if (cqe_ownership_bit != sw_ownership_val) + return NULL; + + mlx5_cqwq_pop(wq); + + /* ensure cqe content is read after cqe ownership bit */ + rmb(); + + return cqe; +} + +int mlx5e_napi_poll(struct napi_struct *napi, int budget) +{ + struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel, + napi); + bool busy = false; + int i; + + clear_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags); + + for (i = 0; i < c->num_tc; i++) + busy |= mlx5e_poll_tx_cq(&c->sq[i].cq); + + busy |= mlx5e_poll_rx_cq(&c->rq.cq, budget); + + busy |= mlx5e_post_rx_wqes(c->rq.cq.sqrq); + + if (busy) + return budget; + + napi_complete(napi); + + /* avoid losing completion event during/after polling cqs */ + if (test_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags)) { + napi_schedule(napi); + return 0; + } + + for (i = 0; i < c->num_tc; i++) + mlx5e_cq_arm(&c->sq[i].cq); + mlx5e_cq_arm(&c->rq.cq); + + return 0; +} + +void mlx5e_completion_event(struct mlx5_core_cq *mcq) +{ + struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq); + + set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); + set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags); + barrier(); + napi_schedule(cq->napi); +} + +void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event) +{ + struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq); + struct mlx5e_channel *c = cq->channel; + struct mlx5e_priv *priv = c->priv; + struct net_device *netdev = priv->netdev; + + netdev_err(netdev, "%s: cqn=0x%.6x event=0x%.2x\n", + __func__, mcq->cqn, event); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 58800e4..a40b96d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -339,15 +339,14 @@ static void init_eq_buf(struct mlx5_eq *eq) int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, int nent, u64 mask, const char *name, struct mlx5_uar *uar) { - struct mlx5_eq_table *table = &dev->priv.eq_table; + struct mlx5_priv *priv = &dev->priv; struct mlx5_create_eq_mbox_in *in; struct mlx5_create_eq_mbox_out out; int err; int inlen; eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE); - err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, 2 * PAGE_SIZE, - &eq->buf); + err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, &eq->buf); if (err) return err; @@ -378,14 +377,15 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, goto err_in; } - snprintf(eq->name, MLX5_MAX_EQ_NAME, "%s@pci:%s", + snprintf(priv->irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s", name, pci_name(dev->pdev)); + eq->eqn = out.eq_number; eq->irqn = vecidx; eq->dev = dev; eq->doorbell = uar->map + MLX5_EQ_DOORBEL_OFFSET; - err = request_irq(table->msix_arr[vecidx].vector, mlx5_msix_handler, 0, - eq->name, eq); + err = request_irq(priv->msix_arr[vecidx].vector, mlx5_msix_handler, 0, + priv->irq_info[vecidx].name, eq); if (err) goto err_eq; @@ -401,7 +401,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, return 0; err_irq: - free_irq(table->msix_arr[vecidx].vector, eq); + free_irq(priv->msix_arr[vecidx].vector, eq); err_eq: mlx5_cmd_destroy_eq(dev, eq->eqn); @@ -417,16 +417,15 @@ EXPORT_SYMBOL_GPL(mlx5_create_map_eq); int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq) { - struct mlx5_eq_table *table = &dev->priv.eq_table; int err; mlx5_debug_eq_remove(dev, eq); - free_irq(table->msix_arr[eq->irqn].vector, eq); + free_irq(dev->priv.msix_arr[eq->irqn].vector, eq); err = mlx5_cmd_destroy_eq(dev, eq->eqn); if (err) mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n", eq->eqn); - synchronize_irq(table->msix_arr[eq->irqn].vector); + synchronize_irq(dev->priv.msix_arr[eq->irqn].vector); mlx5_buf_free(dev, &eq->buf); return err; @@ -456,7 +455,7 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev) u32 async_event_mask = MLX5_ASYNC_EVENT_MASK; int err; - if (dev->caps.gen.flags & MLX5_DEV_CAP_FLAG_ON_DMND_PG) + if (MLX5_CAP_GEN(dev, pg)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_PAGE_FAULT); err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD, @@ -479,7 +478,7 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev) err = mlx5_create_map_eq(dev, &table->pages_eq, MLX5_EQ_VEC_PAGES, - dev->caps.gen.max_vf + 1, + /* TODO: sriov max_vf + */ 1, 1 << MLX5_EVENT_TYPE_PAGE_REQUEST, "mlx5_pages_eq", &dev->priv.uuari.uars[0]); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/flow_table.c b/drivers/net/ethernet/mellanox/mlx5/core/flow_table.c new file mode 100644 index 0000000..ca90b9b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/flow_table.c @@ -0,0 +1,422 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/export.h> +#include <linux/mlx5/driver.h> +#include <linux/mlx5/flow_table.h> +#include "mlx5_core.h" + +struct mlx5_ftg { + struct mlx5_flow_table_group g; + u32 id; + u32 start_ix; +}; + +struct mlx5_flow_table { + struct mlx5_core_dev *dev; + u8 level; + u8 type; + u32 id; + struct mutex mutex; /* sync bitmap alloc */ + u16 num_groups; + struct mlx5_ftg *group; + unsigned long *bitmap; + u32 size; +}; + +static int mlx5_set_flow_entry_cmd(struct mlx5_flow_table *ft, u32 group_ix, + u32 flow_index, void *flow_context) +{ + u32 out[MLX5_ST_SZ_DW(set_fte_out)]; + u32 *in; + void *in_flow_context; + int fcdls = + MLX5_GET(flow_context, flow_context, destination_list_size) * + MLX5_ST_SZ_BYTES(dest_format_struct); + int inlen = MLX5_ST_SZ_BYTES(set_fte_in) + fcdls; + int err; + + in = mlx5_vzalloc(inlen); + if (!in) { + mlx5_core_warn(ft->dev, "failed to allocate inbox\n"); + return -ENOMEM; + } + + MLX5_SET(set_fte_in, in, table_type, ft->type); + MLX5_SET(set_fte_in, in, table_id, ft->id); + MLX5_SET(set_fte_in, in, flow_index, flow_index); + MLX5_SET(set_fte_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY); + + in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context); + memcpy(in_flow_context, flow_context, + MLX5_ST_SZ_BYTES(flow_context) + fcdls); + + MLX5_SET(flow_context, in_flow_context, group_id, + ft->group[group_ix].id); + + memset(out, 0, sizeof(out)); + err = mlx5_cmd_exec_check_status(ft->dev, in, inlen, out, + sizeof(out)); + kvfree(in); + + return err; +} + +static void mlx5_del_flow_entry_cmd(struct mlx5_flow_table *ft, u32 flow_index) +{ + u32 in[MLX5_ST_SZ_DW(delete_fte_in)]; + u32 out[MLX5_ST_SZ_DW(delete_fte_out)]; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + +#define MLX5_SET_DFTEI(p, x, v) MLX5_SET(delete_fte_in, p, x, v) + MLX5_SET_DFTEI(in, table_type, ft->type); + MLX5_SET_DFTEI(in, table_id, ft->id); + MLX5_SET_DFTEI(in, flow_index, flow_index); + MLX5_SET_DFTEI(in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY); + + mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, sizeof(out)); +} + +static void mlx5_destroy_flow_group_cmd(struct mlx5_flow_table *ft, int i) +{ + u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)]; + u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)]; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + +#define MLX5_SET_DFGI(p, x, v) MLX5_SET(destroy_flow_group_in, p, x, v) + MLX5_SET_DFGI(in, table_type, ft->type); + MLX5_SET_DFGI(in, table_id, ft->id); + MLX5_SET_DFGI(in, opcode, MLX5_CMD_OP_DESTROY_FLOW_GROUP); + MLX5_SET_DFGI(in, group_id, ft->group[i].id); + mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_create_flow_group_cmd(struct mlx5_flow_table *ft, int i) +{ + u32 out[MLX5_ST_SZ_DW(create_flow_group_out)]; + u32 *in; + void *in_match_criteria; + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_table_group *g = &ft->group[i].g; + u32 start_ix = ft->group[i].start_ix; + u32 end_ix = start_ix + (1 << g->log_sz) - 1; + int err; + + in = mlx5_vzalloc(inlen); + if (!in) { + mlx5_core_warn(ft->dev, "failed to allocate inbox\n"); + return -ENOMEM; + } + in_match_criteria = MLX5_ADDR_OF(create_flow_group_in, in, + match_criteria); + + memset(out, 0, sizeof(out)); + +#define MLX5_SET_CFGI(p, x, v) MLX5_SET(create_flow_group_in, p, x, v) + MLX5_SET_CFGI(in, table_type, ft->type); + MLX5_SET_CFGI(in, table_id, ft->id); + MLX5_SET_CFGI(in, opcode, MLX5_CMD_OP_CREATE_FLOW_GROUP); + MLX5_SET_CFGI(in, start_flow_index, start_ix); + MLX5_SET_CFGI(in, end_flow_index, end_ix); + MLX5_SET_CFGI(in, match_criteria_enable, g->match_criteria_enable); + + memcpy(in_match_criteria, g->match_criteria, + MLX5_ST_SZ_BYTES(fte_match_param)); + + err = mlx5_cmd_exec_check_status(ft->dev, in, inlen, out, + sizeof(out)); + if (!err) + ft->group[i].id = MLX5_GET(create_flow_group_out, out, + group_id); + + kvfree(in); + + return err; +} + +static void mlx5_destroy_flow_table_groups(struct mlx5_flow_table *ft) +{ + int i; + + for (i = 0; i < ft->num_groups; i++) + mlx5_destroy_flow_group_cmd(ft, i); +} + +static int mlx5_create_flow_table_groups(struct mlx5_flow_table *ft) +{ + int err; + int i; + + for (i = 0; i < ft->num_groups; i++) { + err = mlx5_create_flow_group_cmd(ft, i); + if (err) + goto err_destroy_flow_table_groups; + } + + return 0; + +err_destroy_flow_table_groups: + for (i--; i >= 0; i--) + mlx5_destroy_flow_group_cmd(ft, i); + + return err; +} + +static int mlx5_create_flow_table_cmd(struct mlx5_flow_table *ft) +{ + u32 in[MLX5_ST_SZ_DW(create_flow_table_in)]; + u32 out[MLX5_ST_SZ_DW(create_flow_table_out)]; + int err; + + memset(in, 0, sizeof(in)); + + MLX5_SET(create_flow_table_in, in, table_type, ft->type); + MLX5_SET(create_flow_table_in, in, level, ft->level); + MLX5_SET(create_flow_table_in, in, log_size, order_base_2(ft->size)); + + MLX5_SET(create_flow_table_in, in, opcode, + MLX5_CMD_OP_CREATE_FLOW_TABLE); + + memset(out, 0, sizeof(out)); + err = mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, + sizeof(out)); + if (err) + return err; + + ft->id = MLX5_GET(create_flow_table_out, out, table_id); + + return 0; +} + +static void mlx5_destroy_flow_table_cmd(struct mlx5_flow_table *ft) +{ + u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)]; + u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)]; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + +#define MLX5_SET_DFTI(p, x, v) MLX5_SET(destroy_flow_table_in, p, x, v) + MLX5_SET_DFTI(in, table_type, ft->type); + MLX5_SET_DFTI(in, table_id, ft->id); + MLX5_SET_DFTI(in, opcode, MLX5_CMD_OP_DESTROY_FLOW_TABLE); + + mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_find_group(struct mlx5_flow_table *ft, u8 match_criteria_enable, + u32 *match_criteria, int *group_ix) +{ + void *mc_outer = MLX5_ADDR_OF(fte_match_param, match_criteria, + outer_headers); + void *mc_misc = MLX5_ADDR_OF(fte_match_param, match_criteria, + misc_parameters); + void *mc_inner = MLX5_ADDR_OF(fte_match_param, match_criteria, + inner_headers); + int mc_outer_sz = MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4); + int mc_misc_sz = MLX5_ST_SZ_BYTES(fte_match_set_misc); + int mc_inner_sz = MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4); + int i; + + for (i = 0; i < ft->num_groups; i++) { + struct mlx5_flow_table_group *g = &ft->group[i].g; + void *gmc_outer = MLX5_ADDR_OF(fte_match_param, + g->match_criteria, + outer_headers); + void *gmc_misc = MLX5_ADDR_OF(fte_match_param, + g->match_criteria, + misc_parameters); + void *gmc_inner = MLX5_ADDR_OF(fte_match_param, + g->match_criteria, + inner_headers); + + if (g->match_criteria_enable != match_criteria_enable) + continue; + + if (match_criteria_enable & MLX5_MATCH_OUTER_HEADERS) + if (memcmp(mc_outer, gmc_outer, mc_outer_sz)) + continue; + + if (match_criteria_enable & MLX5_MATCH_MISC_PARAMETERS) + if (memcmp(mc_misc, gmc_misc, mc_misc_sz)) + continue; + + if (match_criteria_enable & MLX5_MATCH_INNER_HEADERS) + if (memcmp(mc_inner, gmc_inner, mc_inner_sz)) + continue; + + *group_ix = i; + return 0; + } + + return -EINVAL; +} + +static int alloc_flow_index(struct mlx5_flow_table *ft, int group_ix, u32 *ix) +{ + struct mlx5_ftg *g = &ft->group[group_ix]; + int err = 0; + + mutex_lock(&ft->mutex); + + *ix = find_next_zero_bit(ft->bitmap, ft->size, g->start_ix); + if (*ix >= (g->start_ix + (1 << g->g.log_sz))) + err = -ENOSPC; + else + __set_bit(*ix, ft->bitmap); + + mutex_unlock(&ft->mutex); + + return err; +} + +static void mlx5_free_flow_index(struct mlx5_flow_table *ft, u32 ix) +{ + __clear_bit(ix, ft->bitmap); +} + +int mlx5_add_flow_table_entry(void *flow_table, u8 match_criteria_enable, + void *match_criteria, void *flow_context, + u32 *flow_index) +{ + struct mlx5_flow_table *ft = flow_table; + int group_ix; + int err; + + err = mlx5_find_group(ft, match_criteria_enable, match_criteria, + &group_ix); + if (err) { + mlx5_core_warn(ft->dev, "mlx5_find_group failed\n"); + return err; + } + + err = alloc_flow_index(ft, group_ix, flow_index); + if (err) { + mlx5_core_warn(ft->dev, "alloc_flow_index failed\n"); + return err; + } + + return mlx5_set_flow_entry_cmd(ft, group_ix, *flow_index, flow_context); +} +EXPORT_SYMBOL(mlx5_add_flow_table_entry); + +void mlx5_del_flow_table_entry(void *flow_table, u32 flow_index) +{ + struct mlx5_flow_table *ft = flow_table; + + mlx5_del_flow_entry_cmd(ft, flow_index); + mlx5_free_flow_index(ft, flow_index); +} +EXPORT_SYMBOL(mlx5_del_flow_table_entry); + +void *mlx5_create_flow_table(struct mlx5_core_dev *dev, u8 level, u8 table_type, + u16 num_groups, + struct mlx5_flow_table_group *group) +{ + struct mlx5_flow_table *ft; + u32 start_ix = 0; + u32 ft_size = 0; + void *gr; + void *bm; + int err; + int i; + + for (i = 0; i < num_groups; i++) + ft_size += (1 << group[i].log_sz); + + ft = kzalloc(sizeof(*ft), GFP_KERNEL); + gr = kcalloc(num_groups, sizeof(struct mlx5_ftg), GFP_KERNEL); + bm = kcalloc(BITS_TO_LONGS(ft_size), sizeof(uintptr_t), GFP_KERNEL); + if (!ft || !gr || !bm) + goto err_free_ft; + + ft->group = gr; + ft->bitmap = bm; + ft->num_groups = num_groups; + ft->level = level; + ft->type = table_type; + ft->size = ft_size; + ft->dev = dev; + mutex_init(&ft->mutex); + + for (i = 0; i < ft->num_groups; i++) { + memcpy(&ft->group[i].g, &group[i], sizeof(*group)); + ft->group[i].start_ix = start_ix; + start_ix += 1 << group[i].log_sz; + } + + err = mlx5_create_flow_table_cmd(ft); + if (err) + goto err_free_ft; + + err = mlx5_create_flow_table_groups(ft); + if (err) + goto err_destroy_flow_table_cmd; + + return ft; + +err_destroy_flow_table_cmd: + mlx5_destroy_flow_table_cmd(ft); + +err_free_ft: + mlx5_core_warn(dev, "failed to alloc flow table\n"); + kfree(bm); + kfree(gr); + kfree(ft); + + return NULL; +} +EXPORT_SYMBOL(mlx5_create_flow_table); + +void mlx5_destroy_flow_table(void *flow_table) +{ + struct mlx5_flow_table *ft = flow_table; + + mlx5_destroy_flow_table_groups(ft); + mlx5_destroy_flow_table_cmd(ft); + kfree(ft->bitmap); + kfree(ft->group); + kfree(ft); +} +EXPORT_SYMBOL(mlx5_destroy_flow_table); + +u32 mlx5_get_flow_table_id(void *flow_table) +{ + struct mlx5_flow_table *ft = flow_table; + + return ft->id; +} +EXPORT_SYMBOL(mlx5_get_flow_table_id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 4b4cda3..801ccad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -64,50 +64,74 @@ out_out: return err; } -int mlx5_cmd_query_hca_cap(struct mlx5_core_dev *dev, struct mlx5_caps *caps) +int mlx5_query_hca_caps(struct mlx5_core_dev *dev) { - return mlx5_core_get_caps(dev, caps, HCA_CAP_OPMOD_GET_CUR); -} - -int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *caps) -{ - u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)]; - int out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out); - void *out; int err; - if (!(dev->caps.gen.flags & MLX5_DEV_CAP_FLAG_ON_DMND_PG)) - return -ENOTSUPP; + err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL, HCA_CAP_OPMOD_GET_CUR); + if (err) + return err; - memset(in, 0, sizeof(in)); - out = kzalloc(out_sz, GFP_KERNEL); - if (!out) - return -ENOMEM; - MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP); - MLX5_SET(query_hca_cap_in, in, op_mod, HCA_CAP_OPMOD_GET_ODP_CUR); - err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz); + err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL, HCA_CAP_OPMOD_GET_MAX); if (err) - goto out; + return err; - err = mlx5_cmd_status_to_err_v2(out); - if (err) { - mlx5_core_warn(dev, "query cur hca ODP caps failed, %d\n", err); - goto out; + if (MLX5_CAP_GEN(dev, eth_net_offloads)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS, + HCA_CAP_OPMOD_GET_CUR); + if (err) + return err; + err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS, + HCA_CAP_OPMOD_GET_MAX); + if (err) + return err; } - memcpy(caps, MLX5_ADDR_OF(query_hca_cap_out, out, capability_struct), - sizeof(*caps)); + if (MLX5_CAP_GEN(dev, pg)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_ODP, + HCA_CAP_OPMOD_GET_CUR); + if (err) + return err; + err = mlx5_core_get_caps(dev, MLX5_CAP_ODP, + HCA_CAP_OPMOD_GET_MAX); + if (err) + return err; + } - mlx5_core_dbg(dev, "on-demand paging capabilities:\nrc: %08x\nuc: %08x\nud: %08x\n", - be32_to_cpu(caps->per_transport_caps.rc_odp_caps), - be32_to_cpu(caps->per_transport_caps.uc_odp_caps), - be32_to_cpu(caps->per_transport_caps.ud_odp_caps)); + if (MLX5_CAP_GEN(dev, atomic)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_ATOMIC, + HCA_CAP_OPMOD_GET_CUR); + if (err) + return err; + err = mlx5_core_get_caps(dev, MLX5_CAP_ATOMIC, + HCA_CAP_OPMOD_GET_MAX); + if (err) + return err; + } -out: - kfree(out); - return err; + if (MLX5_CAP_GEN(dev, roce)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE, + HCA_CAP_OPMOD_GET_CUR); + if (err) + return err; + err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE, + HCA_CAP_OPMOD_GET_MAX); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, nic_flow_table)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE, + HCA_CAP_OPMOD_GET_CUR); + if (err) + return err; + err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE, + HCA_CAP_OPMOD_GET_MAX); + if (err) + return err; + } + return 0; } -EXPORT_SYMBOL(mlx5_query_odp_caps); int mlx5_cmd_init_hca(struct mlx5_core_dev *dev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 28425e5..2510fed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -38,6 +38,7 @@ #include <linux/dma-mapping.h> #include <linux/slab.h> #include <linux/io-mapping.h> +#include <linux/interrupt.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/cq.h> #include <linux/mlx5/qp.h> @@ -47,10 +48,6 @@ #include <linux/mlx5/mlx5_ifc.h> #include "mlx5_core.h" -#define DRIVER_NAME "mlx5_core" -#define DRIVER_VERSION "3.0" -#define DRIVER_RELDATE "January 2015" - MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox Connect-IB, ConnectX-4 core driver"); MODULE_LICENSE("Dual BSD/GPL"); @@ -208,24 +205,28 @@ static void release_bar(struct pci_dev *pdev) static int mlx5_enable_msix(struct mlx5_core_dev *dev) { - struct mlx5_eq_table *table = &dev->priv.eq_table; - int num_eqs = 1 << dev->caps.gen.log_max_eq; + struct mlx5_priv *priv = &dev->priv; + struct mlx5_eq_table *table = &priv->eq_table; + int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq); int nvec; int i; - nvec = dev->caps.gen.num_ports * num_online_cpus() + MLX5_EQ_VEC_COMP_BASE; + nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + + MLX5_EQ_VEC_COMP_BASE; nvec = min_t(int, nvec, num_eqs); if (nvec <= MLX5_EQ_VEC_COMP_BASE) return -ENOMEM; - table->msix_arr = kzalloc(nvec * sizeof(*table->msix_arr), GFP_KERNEL); - if (!table->msix_arr) - return -ENOMEM; + priv->msix_arr = kcalloc(nvec, sizeof(*priv->msix_arr), GFP_KERNEL); + + priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL); + if (!priv->msix_arr || !priv->irq_info) + goto err_free_msix; for (i = 0; i < nvec; i++) - table->msix_arr[i].entry = i; + priv->msix_arr[i].entry = i; - nvec = pci_enable_msix_range(dev->pdev, table->msix_arr, + nvec = pci_enable_msix_range(dev->pdev, priv->msix_arr, MLX5_EQ_VEC_COMP_BASE + 1, nvec); if (nvec < 0) return nvec; @@ -233,14 +234,20 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev) table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE; return 0; + +err_free_msix: + kfree(priv->irq_info); + kfree(priv->msix_arr); + return -ENOMEM; } static void mlx5_disable_msix(struct mlx5_core_dev *dev) { - struct mlx5_eq_table *table = &dev->priv.eq_table; + struct mlx5_priv *priv = &dev->priv; pci_disable_msix(dev->pdev); - kfree(table->msix_arr); + kfree(priv->irq_info); + kfree(priv->msix_arr); } struct mlx5_reg_host_endianess { @@ -277,98 +284,28 @@ static u16 to_fw_pkey_sz(u32 size) } } -/* selectively copy writable fields clearing any reserved area - */ -static void copy_rw_fields(void *to, struct mlx5_caps *from) +static u16 to_sw_pkey_sz(int pkey_sz) { - __be64 *flags_off = (__be64 *)MLX5_ADDR_OF(cmd_hca_cap, to, reserved_22); - u64 v64; - - MLX5_SET(cmd_hca_cap, to, log_max_qp, from->gen.log_max_qp); - MLX5_SET(cmd_hca_cap, to, log_max_ra_req_qp, from->gen.log_max_ra_req_qp); - MLX5_SET(cmd_hca_cap, to, log_max_ra_res_qp, from->gen.log_max_ra_res_qp); - MLX5_SET(cmd_hca_cap, to, pkey_table_size, from->gen.pkey_table_size); - MLX5_SET(cmd_hca_cap, to, pkey_table_size, to_fw_pkey_sz(from->gen.pkey_table_size)); - MLX5_SET(cmd_hca_cap, to, log_uar_page_sz, PAGE_SHIFT - 12); - v64 = from->gen.flags & MLX5_CAP_BITS_RW_MASK; - *flags_off = cpu_to_be64(v64); -} - -static u16 get_pkey_table_size(int pkey) -{ - if (pkey > MLX5_MAX_LOG_PKEY_TABLE) + if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE) return 0; - return MLX5_MIN_PKEY_TABLE_SIZE << pkey; + return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz; } -static void fw2drv_caps(struct mlx5_caps *caps, void *out) -{ - struct mlx5_general_caps *gen = &caps->gen; - - gen->max_srq_wqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_srq_sz); - gen->max_wqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_qp_sz); - gen->log_max_qp = MLX5_GET_PR(cmd_hca_cap, out, log_max_qp); - gen->log_max_strq = MLX5_GET_PR(cmd_hca_cap, out, log_max_strq_sz); - gen->log_max_srq = MLX5_GET_PR(cmd_hca_cap, out, log_max_srqs); - gen->max_cqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_cq_sz); - gen->log_max_cq = MLX5_GET_PR(cmd_hca_cap, out, log_max_cq); - gen->max_eqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_eq_sz); - gen->log_max_mkey = MLX5_GET_PR(cmd_hca_cap, out, log_max_mkey); - gen->log_max_eq = MLX5_GET_PR(cmd_hca_cap, out, log_max_eq); - gen->max_indirection = MLX5_GET_PR(cmd_hca_cap, out, max_indirection); - gen->log_max_mrw_sz = MLX5_GET_PR(cmd_hca_cap, out, log_max_mrw_sz); - gen->log_max_bsf_list_size = MLX5_GET_PR(cmd_hca_cap, out, log_max_bsf_list_size); - gen->log_max_klm_list_size = MLX5_GET_PR(cmd_hca_cap, out, log_max_klm_list_size); - gen->log_max_ra_req_dc = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_req_dc); - gen->log_max_ra_res_dc = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_res_dc); - gen->log_max_ra_req_qp = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_req_qp); - gen->log_max_ra_res_qp = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_res_qp); - gen->max_qp_counters = MLX5_GET_PR(cmd_hca_cap, out, max_qp_cnt); - gen->pkey_table_size = get_pkey_table_size(MLX5_GET_PR(cmd_hca_cap, out, pkey_table_size)); - gen->local_ca_ack_delay = MLX5_GET_PR(cmd_hca_cap, out, local_ca_ack_delay); - gen->num_ports = MLX5_GET_PR(cmd_hca_cap, out, num_ports); - gen->log_max_msg = MLX5_GET_PR(cmd_hca_cap, out, log_max_msg); - gen->stat_rate_support = MLX5_GET_PR(cmd_hca_cap, out, stat_rate_support); - gen->flags = be64_to_cpu(*(__be64 *)MLX5_ADDR_OF(cmd_hca_cap, out, reserved_22)); - pr_debug("flags = 0x%llx\n", gen->flags); - gen->uar_sz = MLX5_GET_PR(cmd_hca_cap, out, uar_sz); - gen->min_log_pg_sz = MLX5_GET_PR(cmd_hca_cap, out, log_pg_sz); - gen->bf_reg_size = MLX5_GET_PR(cmd_hca_cap, out, bf); - gen->bf_reg_size = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_bf_reg_size); - gen->max_sq_desc_sz = MLX5_GET_PR(cmd_hca_cap, out, max_wqe_sz_sq); - gen->max_rq_desc_sz = MLX5_GET_PR(cmd_hca_cap, out, max_wqe_sz_rq); - gen->max_dc_sq_desc_sz = MLX5_GET_PR(cmd_hca_cap, out, max_wqe_sz_sq_dc); - gen->max_qp_mcg = MLX5_GET_PR(cmd_hca_cap, out, max_qp_mcg); - gen->log_max_pd = MLX5_GET_PR(cmd_hca_cap, out, log_max_pd); - gen->log_max_xrcd = MLX5_GET_PR(cmd_hca_cap, out, log_max_xrcd); - gen->log_uar_page_sz = MLX5_GET_PR(cmd_hca_cap, out, log_uar_page_sz); -} - -static const char *caps_opmod_str(u16 opmod) -{ - switch (opmod) { - case HCA_CAP_OPMOD_GET_MAX: - return "GET_MAX"; - case HCA_CAP_OPMOD_GET_CUR: - return "GET_CUR"; - default: - return "Invalid"; - } -} - -int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps, - u16 opmod) +int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, + enum mlx5_cap_mode cap_mode) { u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)]; int out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out); - void *out; + void *out, *hca_caps; + u16 opmod = (cap_type << 1) | (cap_mode & 0x01); int err; memset(in, 0, sizeof(in)); out = kzalloc(out_sz, GFP_KERNEL); if (!out) return -ENOMEM; + MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP); MLX5_SET(query_hca_cap_in, in, op_mod, opmod); err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz); @@ -377,12 +314,30 @@ int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps, err = mlx5_cmd_status_to_err_v2(out); if (err) { - mlx5_core_warn(dev, "query max hca cap failed, %d\n", err); + mlx5_core_warn(dev, + "QUERY_HCA_CAP : type(%x) opmode(%x) Failed(%d)\n", + cap_type, cap_mode, err); goto query_ex; } - mlx5_core_dbg(dev, "%s\n", caps_opmod_str(opmod)); - fw2drv_caps(caps, MLX5_ADDR_OF(query_hca_cap_out, out, capability_struct)); + hca_caps = MLX5_ADDR_OF(query_hca_cap_out, out, capability); + + switch (cap_mode) { + case HCA_CAP_OPMOD_GET_MAX: + memcpy(dev->hca_caps_max[cap_type], hca_caps, + MLX5_UN_SZ_BYTES(hca_cap_union)); + break; + case HCA_CAP_OPMOD_GET_CUR: + memcpy(dev->hca_caps_cur[cap_type], hca_caps, + MLX5_UN_SZ_BYTES(hca_cap_union)); + break; + default: + mlx5_core_warn(dev, + "Tried to query dev cap type(%x) with wrong opmode(%x)\n", + cap_type, cap_mode); + err = -EINVAL; + break; + } query_ex: kfree(out); return err; @@ -409,49 +364,45 @@ static int handle_hca_cap(struct mlx5_core_dev *dev) { void *set_ctx = NULL; struct mlx5_profile *prof = dev->profile; - struct mlx5_caps *cur_caps = NULL; - struct mlx5_caps *max_caps = NULL; int err = -ENOMEM; int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + void *set_hca_cap; set_ctx = kzalloc(set_sz, GFP_KERNEL); if (!set_ctx) goto query_ex; - max_caps = kzalloc(sizeof(*max_caps), GFP_KERNEL); - if (!max_caps) - goto query_ex; - - cur_caps = kzalloc(sizeof(*cur_caps), GFP_KERNEL); - if (!cur_caps) - goto query_ex; - - err = mlx5_core_get_caps(dev, max_caps, HCA_CAP_OPMOD_GET_MAX); + err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL, HCA_CAP_OPMOD_GET_MAX); if (err) goto query_ex; - err = mlx5_core_get_caps(dev, cur_caps, HCA_CAP_OPMOD_GET_CUR); + err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL, HCA_CAP_OPMOD_GET_CUR); if (err) goto query_ex; + set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, + capability); + memcpy(set_hca_cap, dev->hca_caps_cur[MLX5_CAP_GENERAL], + MLX5_ST_SZ_BYTES(cmd_hca_cap)); + + mlx5_core_dbg(dev, "Current Pkey table size %d Setting new size %d\n", + to_sw_pkey_sz(MLX5_CAP_GEN(dev, pkey_table_size)), + 128); /* we limit the size of the pkey table to 128 entries for now */ - cur_caps->gen.pkey_table_size = 128; + MLX5_SET(cmd_hca_cap, set_hca_cap, pkey_table_size, + to_fw_pkey_sz(128)); if (prof->mask & MLX5_PROF_MASK_QP_SIZE) - cur_caps->gen.log_max_qp = prof->log_max_qp; + MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp, + prof->log_max_qp); - /* disable checksum */ - cur_caps->gen.flags &= ~MLX5_DEV_CAP_FLAG_CMDIF_CSUM; + /* disable cmdif checksum */ + MLX5_SET(cmd_hca_cap, set_hca_cap, cmdif_checksum, 0); - copy_rw_fields(MLX5_ADDR_OF(set_hca_cap_in, set_ctx, hca_capability_struct), - cur_caps); err = set_caps(dev, set_ctx, set_sz); query_ex: - kfree(cur_caps); - kfree(max_caps); kfree(set_ctx); - return err; } @@ -507,6 +458,74 @@ static int mlx5_core_disable_hca(struct mlx5_core_dev *dev) return 0; } +static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i) +{ + struct mlx5_priv *priv = &mdev->priv; + struct msix_entry *msix = priv->msix_arr; + int irq = msix[i + MLX5_EQ_VEC_COMP_BASE].vector; + int numa_node = dev_to_node(&mdev->pdev->dev); + int err; + + if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) { + mlx5_core_warn(mdev, "zalloc_cpumask_var failed"); + return -ENOMEM; + } + + cpumask_set_cpu(cpumask_local_spread(i, numa_node), + priv->irq_info[i].mask); + + err = irq_set_affinity_hint(irq, priv->irq_info[i].mask); + if (err) { + mlx5_core_warn(mdev, "irq_set_affinity_hint failed,irq 0x%.4x", + irq); + goto err_clear_mask; + } + + return 0; + +err_clear_mask: + free_cpumask_var(priv->irq_info[i].mask); + return err; +} + +static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i) +{ + struct mlx5_priv *priv = &mdev->priv; + struct msix_entry *msix = priv->msix_arr; + int irq = msix[i + MLX5_EQ_VEC_COMP_BASE].vector; + + irq_set_affinity_hint(irq, NULL); + free_cpumask_var(priv->irq_info[i].mask); +} + +static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev) +{ + int err; + int i; + + for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) { + err = mlx5_irq_set_affinity_hint(mdev, i); + if (err) + goto err_out; + } + + return 0; + +err_out: + for (i--; i >= 0; i--) + mlx5_irq_clear_affinity_hint(mdev, i); + + return err; +} + +static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev) +{ + int i; + + for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) + mlx5_irq_clear_affinity_hint(mdev, i); +} + int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn) { struct mlx5_eq_table *table = &dev->priv.eq_table; @@ -549,7 +568,7 @@ static void free_comp_eqs(struct mlx5_core_dev *dev) static int alloc_comp_eqs(struct mlx5_core_dev *dev) { struct mlx5_eq_table *table = &dev->priv.eq_table; - char name[MLX5_MAX_EQ_NAME]; + char name[MLX5_MAX_IRQ_NAME]; struct mlx5_eq *eq; int ncomp_vec; int nent; @@ -566,7 +585,7 @@ static int alloc_comp_eqs(struct mlx5_core_dev *dev) goto clean; } - snprintf(name, MLX5_MAX_EQ_NAME, "mlx5_comp%d", i); + snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i); err = mlx5_create_map_eq(dev, eq, i + MLX5_EQ_VEC_COMP_BASE, nent, 0, name, &dev->priv.uuari.uars[0]); @@ -588,6 +607,61 @@ clean: return err; } +#ifdef CONFIG_MLX5_CORE_EN +static int mlx5_core_set_issi(struct mlx5_core_dev *dev) +{ + u32 query_in[MLX5_ST_SZ_DW(query_issi_in)]; + u32 query_out[MLX5_ST_SZ_DW(query_issi_out)]; + u32 set_in[MLX5_ST_SZ_DW(set_issi_in)]; + u32 set_out[MLX5_ST_SZ_DW(set_issi_out)]; + int err; + u32 sup_issi; + + memset(query_in, 0, sizeof(query_in)); + memset(query_out, 0, sizeof(query_out)); + + MLX5_SET(query_issi_in, query_in, opcode, MLX5_CMD_OP_QUERY_ISSI); + + err = mlx5_cmd_exec_check_status(dev, query_in, sizeof(query_in), + query_out, sizeof(query_out)); + if (err) { + if (((struct mlx5_outbox_hdr *)query_out)->status == + MLX5_CMD_STAT_BAD_OP_ERR) { + pr_debug("Only ISSI 0 is supported\n"); + return 0; + } + + pr_err("failed to query ISSI\n"); + return err; + } + + sup_issi = MLX5_GET(query_issi_out, query_out, supported_issi_dw0); + + if (sup_issi & (1 << 1)) { + memset(set_in, 0, sizeof(set_in)); + memset(set_out, 0, sizeof(set_out)); + + MLX5_SET(set_issi_in, set_in, opcode, MLX5_CMD_OP_SET_ISSI); + MLX5_SET(set_issi_in, set_in, current_issi, 1); + + err = mlx5_cmd_exec_check_status(dev, set_in, sizeof(set_in), + set_out, sizeof(set_out)); + if (err) { + pr_err("failed to set ISSI=1\n"); + return err; + } + + dev->issi = 1; + + return 0; + } else if (sup_issi & (1 << 0)) { + return 0; + } + + return -ENOTSUPP; +} +#endif + static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev) { struct mlx5_priv *priv = &dev->priv; @@ -650,6 +724,14 @@ static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev) goto err_pagealloc_cleanup; } +#ifdef CONFIG_MLX5_CORE_EN + err = mlx5_core_set_issi(dev); + if (err) { + dev_err(&pdev->dev, "failed to set issi\n"); + goto err_disable_hca; + } +#endif + err = mlx5_satisfy_startup_pages(dev, 1); if (err) { dev_err(&pdev->dev, "failed to allocate boot pages\n"); @@ -688,7 +770,7 @@ static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev) mlx5_start_health_poll(dev); - err = mlx5_cmd_query_hca_cap(dev, &dev->caps); + err = mlx5_query_hca_caps(dev); if (err) { dev_err(&pdev->dev, "query hca failed\n"); goto err_stop_poll; @@ -730,6 +812,12 @@ static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev) goto err_stop_eqs; } + err = mlx5_irq_set_affinity_hints(dev); + if (err) { + dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n"); + goto err_free_comp_eqs; + } + MLX5_INIT_DOORBELL_LOCK(&priv->cq_uar_lock); mlx5_init_cq_table(dev); @@ -739,6 +827,9 @@ static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev) return 0; +err_free_comp_eqs: + free_comp_eqs(dev); + err_stop_eqs: mlx5_stop_eqs(dev); @@ -793,6 +884,7 @@ static void mlx5_dev_cleanup(struct mlx5_core_dev *dev) mlx5_cleanup_srq_table(dev); mlx5_cleanup_qp_table(dev); mlx5_cleanup_cq_table(dev); + mlx5_irq_clear_affinity_hints(dev); free_comp_eqs(dev); mlx5_stop_eqs(dev); mlx5_free_uuars(dev, &priv->uuari); @@ -1048,6 +1140,10 @@ static int __init init(void) if (err) goto err_health; +#ifdef CONFIG_MLX5_CORE_EN + mlx5e_init(); +#endif + return 0; err_health: @@ -1060,6 +1156,9 @@ err_debug: static void __exit cleanup(void) { +#ifdef CONFIG_MLX5_CORE_EN + mlx5e_cleanup(); +#endif pci_unregister_driver(&mlx5_core_driver); mlx5_health_cleanup(); destroy_workqueue(mlx5_core_wq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mcg.c b/drivers/net/ethernet/mellanox/mlx5/core/mcg.c index d79fd85..d5a0c2d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mcg.c @@ -91,7 +91,7 @@ int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn) memset(&in, 0, sizeof(in)); memset(&out, 0, sizeof(out)); - in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DETACH_FROM_MCG); + in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DETTACH_FROM_MCG); memcpy(in.gid, mgid, sizeof(*mgid)); in.qpn = cpu_to_be32(qpn); err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index a051b90..6983c10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -37,6 +37,10 @@ #include <linux/kernel.h> #include <linux/sched.h> +#define DRIVER_NAME "mlx5_core" +#define DRIVER_VERSION "3.0-1" +#define DRIVER_RELDATE "January 2015" + extern int mlx5_core_debug_mask; #define mlx5_core_dbg(dev, format, ...) \ @@ -65,11 +69,20 @@ enum { MLX5_CMD_TIME, /* print command execution time */ }; +static inline int mlx5_cmd_exec_check_status(struct mlx5_core_dev *dev, u32 *in, + int in_size, u32 *out, + int out_size) +{ + mlx5_cmd_exec(dev, in, in_size, out, out_size); + return mlx5_cmd_status_to_err((struct mlx5_outbox_hdr *)out); +} -int mlx5_cmd_query_hca_cap(struct mlx5_core_dev *dev, - struct mlx5_caps *caps); +int mlx5_query_hca_caps(struct mlx5_core_dev *dev); int mlx5_cmd_query_adapter(struct mlx5_core_dev *dev); int mlx5_cmd_init_hca(struct mlx5_core_dev *dev); int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev); +void mlx5e_init(void); +void mlx5e_cleanup(void); + #endif /* __MLX5_CORE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 49e90f2..7d3d0f9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -102,3 +102,165 @@ int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps) return err; } EXPORT_SYMBOL_GPL(mlx5_set_port_caps); + +int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, + int ptys_size, int proto_mask) +{ + u32 in[MLX5_ST_SZ_DW(ptys_reg)]; + int err; + + memset(in, 0, sizeof(in)); + MLX5_SET(ptys_reg, in, local_port, 1); + MLX5_SET(ptys_reg, in, proto_mask, proto_mask); + + err = mlx5_core_access_reg(dev, in, sizeof(in), ptys, + ptys_size, MLX5_REG_PTYS, 0, 0); + + return err; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_ptys); + +int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, + u32 *proto_cap, int proto_mask) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + int err; + + err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask); + if (err) + return err; + + if (proto_mask == MLX5_PTYS_EN) + *proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability); + else + *proto_cap = MLX5_GET(ptys_reg, out, ib_proto_capability); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_proto_cap); + +int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, + u32 *proto_admin, int proto_mask) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + int err; + + err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask); + if (err) + return err; + + if (proto_mask == MLX5_PTYS_EN) + *proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin); + else + *proto_admin = MLX5_GET(ptys_reg, out, ib_proto_admin); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_proto_admin); + +int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, + int proto_mask) +{ + u32 in[MLX5_ST_SZ_DW(ptys_reg)]; + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + int err; + + memset(in, 0, sizeof(in)); + + MLX5_SET(ptys_reg, in, local_port, 1); + MLX5_SET(ptys_reg, in, proto_mask, proto_mask); + if (proto_mask == MLX5_PTYS_EN) + MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin); + else + MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PTYS, 0, 1); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_set_port_proto); + +int mlx5_set_port_status(struct mlx5_core_dev *dev, + enum mlx5_port_status status) +{ + u32 in[MLX5_ST_SZ_DW(paos_reg)]; + u32 out[MLX5_ST_SZ_DW(paos_reg)]; + + memset(in, 0, sizeof(in)); + + MLX5_SET(paos_reg, in, admin_status, status); + MLX5_SET(paos_reg, in, ase, 1); + + return mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PAOS, 0, 1); +} + +int mlx5_query_port_status(struct mlx5_core_dev *dev, u8 *status) +{ + u32 in[MLX5_ST_SZ_DW(paos_reg)]; + u32 out[MLX5_ST_SZ_DW(paos_reg)]; + int err; + + memset(in, 0, sizeof(in)); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PAOS, 0, 0); + if (err) + return err; + + *status = MLX5_GET(paos_reg, out, oper_status); + return err; +} + +static int mlx5_query_port_mtu(struct mlx5_core_dev *dev, + int *admin_mtu, int *max_mtu, int *oper_mtu) +{ + u32 in[MLX5_ST_SZ_DW(pmtu_reg)]; + u32 out[MLX5_ST_SZ_DW(pmtu_reg)]; + int err; + + memset(in, 0, sizeof(in)); + + MLX5_SET(pmtu_reg, in, local_port, 1); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PMTU, 0, 0); + if (err) + return err; + + if (max_mtu) + *max_mtu = MLX5_GET(pmtu_reg, out, max_mtu); + if (oper_mtu) + *oper_mtu = MLX5_GET(pmtu_reg, out, oper_mtu); + if (admin_mtu) + *admin_mtu = MLX5_GET(pmtu_reg, out, admin_mtu); + + return 0; +} + +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu) +{ + u32 in[MLX5_ST_SZ_DW(pmtu_reg)]; + u32 out[MLX5_ST_SZ_DW(pmtu_reg)]; + + memset(in, 0, sizeof(in)); + + MLX5_SET(pmtu_reg, in, admin_mtu, mtu); + MLX5_SET(pmtu_reg, in, local_port, 1); + + return mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), + MLX5_REG_PMTU, 0, 1); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_mtu); + +int mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu) +{ + return mlx5_query_port_mtu(dev, NULL, max_mtu, NULL); +} +EXPORT_SYMBOL_GPL(mlx5_query_port_max_mtu); + +int mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu) +{ + return mlx5_query_port_mtu(dev, NULL, NULL, oper_mtu); +} +EXPORT_SYMBOL_GPL(mlx5_query_port_oper_mtu); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c new file mode 100644 index 0000000..3c555d7 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -0,0 +1,169 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/mlx5/driver.h> +#include "mlx5_core.h" +#include "transobj.h" + +int mlx5_create_rq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqn) +{ + u32 out[MLX5_ST_SZ_DW(create_rq_out)]; + int err; + + MLX5_SET(create_rq_in, in, opcode, MLX5_CMD_OP_CREATE_RQ); + + memset(out, 0, sizeof(out)); + err = mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out)); + if (!err) + *rqn = MLX5_GET(create_rq_out, out, rqn); + + return err; +} + +int mlx5_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in, int inlen) +{ + u32 out[MLX5_ST_SZ_DW(modify_rq_out)]; + + MLX5_SET(modify_rq_in, in, rqn, rqn); + MLX5_SET(modify_rq_in, in, opcode, MLX5_CMD_OP_MODIFY_RQ); + + memset(out, 0, sizeof(out)); + return mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out)); +} + +void mlx5_destroy_rq(struct mlx5_core_dev *dev, u32 rqn) +{ + u32 in[MLX5_ST_SZ_DW(destroy_rq_in)]; + u32 out[MLX5_ST_SZ_DW(destroy_rq_out)]; + + memset(in, 0, sizeof(in)); + + MLX5_SET(destroy_rq_in, in, opcode, MLX5_CMD_OP_DESTROY_RQ); + MLX5_SET(destroy_rq_in, in, rqn, rqn); + + mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5_create_sq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *sqn) +{ + u32 out[MLX5_ST_SZ_DW(create_sq_out)]; + int err; + + MLX5_SET(create_sq_in, in, opcode, MLX5_CMD_OP_CREATE_SQ); + + memset(out, 0, sizeof(out)); + err = mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out)); + if (!err) + *sqn = MLX5_GET(create_sq_out, out, sqn); + + return err; +} + +int mlx5_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in, int inlen) +{ + u32 out[MLX5_ST_SZ_DW(modify_sq_out)]; + + MLX5_SET(modify_sq_in, in, sqn, sqn); + MLX5_SET(modify_sq_in, in, opcode, MLX5_CMD_OP_MODIFY_SQ); + + memset(out, 0, sizeof(out)); + return mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out)); +} + +void mlx5_destroy_sq(struct mlx5_core_dev *dev, u32 sqn) +{ + u32 in[MLX5_ST_SZ_DW(destroy_sq_in)]; + u32 out[MLX5_ST_SZ_DW(destroy_sq_out)]; + + memset(in, 0, sizeof(in)); + + MLX5_SET(destroy_sq_in, in, opcode, MLX5_CMD_OP_DESTROY_SQ); + MLX5_SET(destroy_sq_in, in, sqn, sqn); + + mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *tirn) +{ + u32 out[MLX5_ST_SZ_DW(create_tir_out)]; + int err; + + MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR); + + memset(out, 0, sizeof(out)); + err = mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out)); + if (!err) + *tirn = MLX5_GET(create_tir_out, out, tirn); + + return err; +} + +void mlx5_destroy_tir(struct mlx5_core_dev *dev, u32 tirn) +{ + u32 in[MLX5_ST_SZ_DW(destroy_tir_out)]; + u32 out[MLX5_ST_SZ_DW(destroy_tir_out)]; + + memset(in, 0, sizeof(in)); + + MLX5_SET(destroy_tir_in, in, opcode, MLX5_CMD_OP_DESTROY_TIR); + MLX5_SET(destroy_tir_in, in, tirn, tirn); + + mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *tisn) +{ + u32 out[MLX5_ST_SZ_DW(create_tis_out)]; + int err; + + MLX5_SET(create_tis_in, in, opcode, MLX5_CMD_OP_CREATE_TIS); + + memset(out, 0, sizeof(out)); + err = mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out)); + if (!err) + *tisn = MLX5_GET(create_tis_out, out, tisn); + + return err; +} + +void mlx5_destroy_tis(struct mlx5_core_dev *dev, u32 tisn) +{ + u32 in[MLX5_ST_SZ_DW(destroy_tis_out)]; + u32 out[MLX5_ST_SZ_DW(destroy_tis_out)]; + + memset(in, 0, sizeof(in)); + + MLX5_SET(destroy_tis_in, in, opcode, MLX5_CMD_OP_DESTROY_TIS); + MLX5_SET(destroy_tis_in, in, tisn, tisn); + + mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out)); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.h b/drivers/net/ethernet/mellanox/mlx5/core/transobj.h new file mode 100644 index 0000000..1bc898c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.h @@ -0,0 +1,47 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __TRANSOBJ_H__ +#define __TRANSOBJ_H__ + +int mlx5_create_rq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqn); +int mlx5_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in, int inlen); +void mlx5_destroy_rq(struct mlx5_core_dev *dev, u32 rqn); +int mlx5_create_sq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *sqn); +int mlx5_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in, int inlen); +void mlx5_destroy_sq(struct mlx5_core_dev *dev, u32 sqn); +int mlx5_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *tirn); +void mlx5_destroy_tir(struct mlx5_core_dev *dev, u32 tirn); +int mlx5_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *tisn); +void mlx5_destroy_tis(struct mlx5_core_dev *dev, u32 tisn); + +#endif /* __TRANSOBJ_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index 5a89bb1..9ef8587 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -175,12 +175,13 @@ int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari) for (i = 0; i < tot_uuars; i++) { bf = &uuari->bfs[i]; - bf->buf_size = dev->caps.gen.bf_reg_size / 2; + bf->buf_size = (1 << MLX5_CAP_GEN(dev, log_bf_reg_size)) / 2; bf->uar = &uuari->uars[i / MLX5_BF_REGS_PER_PAGE]; bf->regreg = uuari->uars[i / MLX5_BF_REGS_PER_PAGE].map; bf->reg = NULL; /* Add WC support */ - bf->offset = (i % MLX5_BF_REGS_PER_PAGE) * dev->caps.gen.bf_reg_size + - MLX5_BF_OFFSET; + bf->offset = (i % MLX5_BF_REGS_PER_PAGE) * + (1 << MLX5_CAP_GEN(dev, log_bf_reg_size)) + + MLX5_BF_OFFSET; bf->need_lock = need_uuar_lock(i); spin_lock_init(&bf->lock); spin_lock_init(&bf->lock32); @@ -223,3 +224,40 @@ int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari) return 0; } + +int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) +{ + phys_addr_t pfn; + phys_addr_t uar_bar_start; + int err; + + err = mlx5_cmd_alloc_uar(mdev, &uar->index); + if (err) { + mlx5_core_warn(mdev, "mlx5_cmd_alloc_uar() failed, %d\n", err); + return err; + } + + uar_bar_start = pci_resource_start(mdev->pdev, 0); + pfn = (uar_bar_start >> PAGE_SHIFT) + uar->index; + uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!uar->map) { + mlx5_core_warn(mdev, "ioremap() failed, %d\n", err); + err = -ENOMEM; + goto err_free_uar; + } + + return 0; + +err_free_uar: + mlx5_cmd_free_uar(mdev, uar->index); + + return err; +} +EXPORT_SYMBOL(mlx5_alloc_map_uar); + +void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) +{ + iounmap(uar->map); + mlx5_cmd_free_uar(mdev, uar->index); +} +EXPORT_SYMBOL(mlx5_unmap_free_uar); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c new file mode 100644 index 0000000..ba374b9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -0,0 +1,84 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/export.h> +#include <linux/etherdevice.h> +#include <linux/mlx5/driver.h> +#include "vport.h" +#include "mlx5_core.h" + +u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod) +{ + u32 in[MLX5_ST_SZ_DW(query_vport_state_in)]; + u32 out[MLX5_ST_SZ_DW(query_vport_state_out)]; + int err; + + memset(in, 0, sizeof(in)); + + MLX5_SET(query_vport_state_in, in, opcode, + MLX5_CMD_OP_QUERY_VPORT_STATE); + MLX5_SET(query_vport_state_in, in, op_mod, opmod); + + err = mlx5_cmd_exec_check_status(mdev, in, sizeof(in), out, + sizeof(out)); + if (err) + mlx5_core_warn(mdev, "MLX5_CMD_OP_QUERY_VPORT_STATE failed\n"); + + return MLX5_GET(query_vport_state_out, out, state); +} + +void mlx5_query_vport_mac_address(struct mlx5_core_dev *mdev, u8 *addr) +{ + u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)]; + u32 *out; + int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + u8 *out_addr; + + out = mlx5_vzalloc(outlen); + if (!out) + return; + + out_addr = MLX5_ADDR_OF(query_nic_vport_context_out, out, + nic_vport_context.permanent_address); + + memset(in, 0, sizeof(in)); + + MLX5_SET(query_nic_vport_context_in, in, opcode, + MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT); + + memset(out, 0, outlen); + mlx5_cmd_exec_check_status(mdev, in, sizeof(in), out, outlen); + + ether_addr_copy(addr, &out_addr[2]); + + kvfree(out); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.h b/drivers/net/ethernet/mellanox/mlx5/core/vport.h new file mode 100644 index 0000000..c05ca2c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.h @@ -0,0 +1,41 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5_VPORT_H__ +#define __MLX5_VPORT_H__ + +#include <linux/mlx5/driver.h> + +u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod); +void mlx5_query_vport_mac_address(struct mlx5_core_dev *mdev, u8 *addr); + +#endif /* __MLX5_VPORT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c new file mode 100644 index 0000000..8388411 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -0,0 +1,183 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/mlx5/driver.h> +#include "wq.h" +#include "mlx5_core.h" + +u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq) +{ + return (u32)wq->sz_m1 + 1; +} + +u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) +{ + return wq->sz_m1 + 1; +} + +u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq) +{ + return (u32)wq->sz_m1 + 1; +} + +static u32 mlx5_wq_cyc_get_byte_size(struct mlx5_wq_cyc *wq) +{ + return mlx5_wq_cyc_get_size(wq) << wq->log_stride; +} + +static u32 mlx5_cqwq_get_byte_size(struct mlx5_cqwq *wq) +{ + return mlx5_cqwq_get_size(wq) << wq->log_stride; +} + +static u32 mlx5_wq_ll_get_byte_size(struct mlx5_wq_ll *wq) +{ + return mlx5_wq_ll_get_size(wq) << wq->log_stride; +} + +int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, + void *wqc, struct mlx5_wq_cyc *wq, + struct mlx5_wq_ctrl *wq_ctrl) +{ + int err; + + wq->log_stride = MLX5_GET(wq, wqc, log_wq_stride); + wq->sz_m1 = (1 << MLX5_GET(wq, wqc, log_wq_sz)) - 1; + + err = mlx5_db_alloc(mdev, &wq_ctrl->db); + if (err) { + mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err); + return err; + } + + err = mlx5_buf_alloc(mdev, mlx5_wq_cyc_get_byte_size(wq), &wq_ctrl->buf); + if (err) { + mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err); + goto err_db_free; + } + + wq->buf = wq_ctrl->buf.direct.buf; + wq->db = wq_ctrl->db.db; + + wq_ctrl->mdev = mdev; + + return 0; + +err_db_free: + mlx5_db_free(mdev, &wq_ctrl->db); + + return err; +} + +int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, + void *cqc, struct mlx5_cqwq *wq, + struct mlx5_wq_ctrl *wq_ctrl) +{ + int err; + + wq->log_stride = 6 + MLX5_GET(cqc, cqc, cqe_sz); + wq->log_sz = MLX5_GET(cqc, cqc, log_cq_size); + wq->sz_m1 = (1 << wq->log_sz) - 1; + + err = mlx5_db_alloc(mdev, &wq_ctrl->db); + if (err) { + mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err); + return err; + } + + err = mlx5_buf_alloc(mdev, mlx5_cqwq_get_byte_size(wq), &wq_ctrl->buf); + if (err) { + mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err); + goto err_db_free; + } + + wq->buf = wq_ctrl->buf.direct.buf; + wq->db = wq_ctrl->db.db; + + wq_ctrl->mdev = mdev; + + return 0; + +err_db_free: + mlx5_db_free(mdev, &wq_ctrl->db); + + return err; +} + +int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, + void *wqc, struct mlx5_wq_ll *wq, + struct mlx5_wq_ctrl *wq_ctrl) +{ + struct mlx5_wqe_srq_next_seg *next_seg; + int err; + int i; + + wq->log_stride = MLX5_GET(wq, wqc, log_wq_stride); + wq->sz_m1 = (1 << MLX5_GET(wq, wqc, log_wq_sz)) - 1; + + err = mlx5_db_alloc(mdev, &wq_ctrl->db); + if (err) { + mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err); + return err; + } + + err = mlx5_buf_alloc(mdev, mlx5_wq_ll_get_byte_size(wq), &wq_ctrl->buf); + if (err) { + mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err); + goto err_db_free; + } + + wq->buf = wq_ctrl->buf.direct.buf; + wq->db = wq_ctrl->db.db; + + for (i = 0; i < wq->sz_m1; i++) { + next_seg = mlx5_wq_ll_get_wqe(wq, i); + next_seg->next_wqe_index = cpu_to_be16(i + 1); + } + next_seg = mlx5_wq_ll_get_wqe(wq, i); + wq->tail_next = &next_seg->next_wqe_index; + + wq_ctrl->mdev = mdev; + + return 0; + +err_db_free: + mlx5_db_free(mdev, &wq_ctrl->db); + + return err; +} + +void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl) +{ + mlx5_buf_free(wq_ctrl->mdev, &wq_ctrl->buf); + mlx5_db_free(wq_ctrl->mdev, &wq_ctrl->db); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h new file mode 100644 index 0000000..e0ddd69 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -0,0 +1,171 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5_WQ_H__ +#define __MLX5_WQ_H__ + +#include <linux/mlx5/mlx5_ifc.h> + +struct mlx5_wq_param { + int linear; + int numa; +}; + +struct mlx5_wq_ctrl { + struct mlx5_core_dev *mdev; + struct mlx5_buf buf; + struct mlx5_db db; +}; + +struct mlx5_wq_cyc { + void *buf; + __be32 *db; + u16 sz_m1; + u8 log_stride; +}; + +struct mlx5_cqwq { + void *buf; + __be32 *db; + u32 sz_m1; + u32 cc; /* consumer counter */ + u8 log_sz; + u8 log_stride; +}; + +struct mlx5_wq_ll { + void *buf; + __be32 *db; + __be16 *tail_next; + u16 sz_m1; + u16 head; + u16 wqe_ctr; + u16 cur_sz; + u8 log_stride; +}; + +int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, + void *wqc, struct mlx5_wq_cyc *wq, + struct mlx5_wq_ctrl *wq_ctrl); +u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq); + +int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, + void *cqc, struct mlx5_cqwq *wq, + struct mlx5_wq_ctrl *wq_ctrl); +u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq); + +int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, + void *wqc, struct mlx5_wq_ll *wq, + struct mlx5_wq_ctrl *wq_ctrl); +u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq); + +void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl); + +static inline u16 mlx5_wq_cyc_ctr2ix(struct mlx5_wq_cyc *wq, u16 ctr) +{ + return ctr & wq->sz_m1; +} + +static inline void *mlx5_wq_cyc_get_wqe(struct mlx5_wq_cyc *wq, u16 ix) +{ + return wq->buf + (ix << wq->log_stride); +} + +static inline int mlx5_wq_cyc_cc_bigger(u16 cc1, u16 cc2) +{ + int equal = (cc1 == cc2); + int smaller = 0x8000 & (cc1 - cc2); + + return !equal && !smaller; +} + +static inline u32 mlx5_cqwq_get_ci(struct mlx5_cqwq *wq) +{ + return wq->cc & wq->sz_m1; +} + +static inline void *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix) +{ + return wq->buf + (ix << wq->log_stride); +} + +static inline u32 mlx5_cqwq_get_wrap_cnt(struct mlx5_cqwq *wq) +{ + return wq->cc >> wq->log_sz; +} + +static inline void mlx5_cqwq_pop(struct mlx5_cqwq *wq) +{ + wq->cc++; +} + +static inline void mlx5_cqwq_update_db_record(struct mlx5_cqwq *wq) +{ + *wq->db = cpu_to_be32(wq->cc & 0xffffff); +} + +static inline int mlx5_wq_ll_is_full(struct mlx5_wq_ll *wq) +{ + return wq->cur_sz == wq->sz_m1; +} + +static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq) +{ + return !wq->cur_sz; +} + +static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix) +{ + return wq->buf + (ix << wq->log_stride); +} + +static inline void mlx5_wq_ll_push(struct mlx5_wq_ll *wq, u16 head_next) +{ + wq->head = head_next; + wq->wqe_ctr++; + wq->cur_sz++; +} + +static inline void mlx5_wq_ll_pop(struct mlx5_wq_ll *wq, __be16 ix, + __be16 *next_tail_next) +{ + *wq->tail_next = ix; + wq->tail_next = next_tail_next; + wq->cur_sz--; +} + +static inline void mlx5_wq_ll_update_db_record(struct mlx5_wq_ll *wq) +{ + *wq->db = cpu_to_be32(wq->wqe_ctr); +} + +#endif /* __MLX5_WQ_H__ */ diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index 6f332eb..48d2aec 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -6664,7 +6664,7 @@ static void mib_read_work(struct work_struct *work) wake_up_interruptible( &hw_priv->counter[i].counter); } - } else if (jiffies >= hw_priv->counter[i].time) { + } else if (time_after_eq(jiffies, hw_priv->counter[i].time)) { /* Only read MIB counters when the port is connected. */ if (media_connected == mib->state) hw_priv->counter[i].read = 1; diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 1e0f72b..c281117 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -5308,7 +5308,8 @@ static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr) /** * s2io_ethtool_sset - Sets different link parameters. - * @sp : private member of the device structure, which is a pointer to the * s2io_nic structure. + * @sp : private member of the device structure, which is a pointer to the + * s2io_nic structure. * @info: pointer to the structure with parameters given by ethtool to set * link information. * Description: @@ -5793,7 +5794,8 @@ static void s2io_vpd_read(struct s2io_nic *nic) /** * s2io_ethtool_geeprom - reads the value stored in the Eeprom. - * @sp : private member of the device structure, which is a pointer to the * s2io_nic structure. + * @sp : private member of the device structure, which is a pointer to the + * s2io_nic structure. * @eeprom : pointer to the user level structure provided by ethtool, * containing all relevant information. * @data_buf : user defined value to be written into Eeprom. diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index e0c31e3..6409a06 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -3025,9 +3025,9 @@ netxen_sysfs_read_dimm(struct file *filp, struct kobject *kobj, u8 dw, rows, cols, banks, ranks; u32 val; - if (size != sizeof(struct netxen_dimm_cfg)) { + if (size < attr->size) { netdev_err(netdev, "Invalid size\n"); - return -1; + return -EINVAL; } memset(&dimm, 0, sizeof(struct netxen_dimm_cfg)); @@ -3137,7 +3137,7 @@ out: static struct bin_attribute bin_attr_dimm = { .attr = { .name = "dimm", .mode = (S_IRUGO | S_IWUSR) }, - .size = 0, + .size = sizeof(struct netxen_dimm_cfg), .read = netxen_sysfs_read_dimm, }; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index f221126..055f376 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -1326,9 +1326,6 @@ struct qlcnic_eswitch { }; -/* Return codes for Error handling */ -#define QL_STATUS_INVALID_PARAM -1 - #define MAX_BW 100 /* % of link speed */ #define MIN_BW 1 /* % of link speed */ #define MAX_VLAN_ID 4095 diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 367f397..2f6cc42 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -1031,7 +1031,7 @@ int qlcnic_init_pci_info(struct qlcnic_adapter *adapter) pfn = pci_info[i].id; if (pfn >= ahw->max_vnic_func) { - ret = QL_STATUS_INVALID_PARAM; + ret = -EINVAL; dev_err(&adapter->pdev->dev, "%s: Invalid function 0x%x, max 0x%x\n", __func__, pfn, ahw->max_vnic_func); goto err_eswitch; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index 59a721f..05c28f2 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -24,8 +24,6 @@ #include <linux/hwmon-sysfs.h> #endif -#define QLC_STATUS_UNSUPPORTED_CMD -2 - int qlcnicvf_config_bridged_mode(struct qlcnic_adapter *adapter, u32 enable) { return -EOPNOTSUPP; @@ -166,7 +164,7 @@ static int qlcnic_82xx_store_beacon(struct qlcnic_adapter *adapter, u8 b_state, b_rate; if (len != sizeof(u16)) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; memcpy(&beacon, buf, sizeof(u16)); err = qlcnic_validate_beacon(adapter, beacon, &b_state, &b_rate); @@ -383,17 +381,17 @@ static int validate_pm_config(struct qlcnic_adapter *adapter, dest_pci_func = pm_cfg[i].dest_npar; src_index = qlcnic_is_valid_nic_func(adapter, src_pci_func); if (src_index < 0) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; dest_index = qlcnic_is_valid_nic_func(adapter, dest_pci_func); if (dest_index < 0) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; s_esw_id = adapter->npars[src_index].phy_port; d_esw_id = adapter->npars[dest_index].phy_port; if (s_esw_id != d_esw_id) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; } return 0; @@ -414,7 +412,7 @@ static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp, count = size / sizeof(struct qlcnic_pm_func_cfg); rem = size % sizeof(struct qlcnic_pm_func_cfg); if (rem) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; qlcnic_swap32_buffer((u32 *)buf, size / sizeof(u32)); pm_cfg = (struct qlcnic_pm_func_cfg *)buf; @@ -427,7 +425,7 @@ static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp, action = !!pm_cfg[i].action; index = qlcnic_is_valid_nic_func(adapter, pci_func); if (index < 0) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; id = adapter->npars[index].phy_port; ret = qlcnic_config_port_mirroring(adapter, id, @@ -440,7 +438,7 @@ static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp, pci_func = pm_cfg[i].pci_func; index = qlcnic_is_valid_nic_func(adapter, pci_func); if (index < 0) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; id = adapter->npars[index].phy_port; adapter->npars[index].enable_pm = !!pm_cfg[i].action; adapter->npars[index].dest_npar = id; @@ -499,11 +497,11 @@ static int validate_esw_config(struct qlcnic_adapter *adapter, for (i = 0; i < count; i++) { pci_func = esw_cfg[i].pci_func; if (pci_func >= ahw->max_vnic_func) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; if (adapter->ahw->op_mode == QLCNIC_MGMT_FUNC) if (qlcnic_is_valid_nic_func(adapter, pci_func) < 0) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; switch (esw_cfg[i].op_mode) { case QLCNIC_PORT_DEFAULTS: @@ -517,25 +515,25 @@ static int validate_esw_config(struct qlcnic_adapter *adapter, if (ret != QLCNIC_NON_PRIV_FUNC) { if (esw_cfg[i].mac_anti_spoof != 0) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; if (esw_cfg[i].mac_override != 1) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; if (esw_cfg[i].promisc_mode != 1) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; } break; case QLCNIC_ADD_VLAN: if (!IS_VALID_VLAN(esw_cfg[i].vlan_id)) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; if (!esw_cfg[i].op_type) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; break; case QLCNIC_DEL_VLAN: if (!esw_cfg[i].op_type) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; break; default: - return QL_STATUS_INVALID_PARAM; + return -EINVAL; } } @@ -559,7 +557,7 @@ static ssize_t qlcnic_sysfs_write_esw_config(struct file *file, count = size / sizeof(struct qlcnic_esw_func_cfg); rem = size % sizeof(struct qlcnic_esw_func_cfg); if (rem) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; qlcnic_swap32_buffer((u32 *)buf, size / sizeof(u32)); esw_cfg = (struct qlcnic_esw_func_cfg *)buf; @@ -570,7 +568,7 @@ static ssize_t qlcnic_sysfs_write_esw_config(struct file *file, for (i = 0; i < count; i++) { if (adapter->ahw->op_mode == QLCNIC_MGMT_FUNC) if (qlcnic_config_switch_port(adapter, &esw_cfg[i])) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; if (adapter->ahw->pci_func != esw_cfg[i].pci_func) continue; @@ -604,7 +602,7 @@ static ssize_t qlcnic_sysfs_write_esw_config(struct file *file, pci_func = esw_cfg[i].pci_func; index = qlcnic_is_valid_nic_func(adapter, pci_func); if (index < 0) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; npar = &adapter->npars[index]; switch (esw_cfg[i].op_mode) { case QLCNIC_PORT_DEFAULTS: @@ -654,7 +652,7 @@ static ssize_t qlcnic_sysfs_read_esw_config(struct file *file, esw_cfg[pci_func].pci_func = pci_func; if (qlcnic_get_eswitch_port_config(adapter, &esw_cfg[pci_func])) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; } qlcnic_swap32_buffer((u32 *)buf, size / sizeof(u32)); return size; @@ -669,11 +667,11 @@ static int validate_npar_config(struct qlcnic_adapter *adapter, for (i = 0; i < count; i++) { pci_func = np_cfg[i].pci_func; if (qlcnic_is_valid_nic_func(adapter, pci_func) < 0) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; if (!IS_VALID_BW(np_cfg[i].min_bw) || !IS_VALID_BW(np_cfg[i].max_bw)) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; } return 0; } @@ -694,7 +692,7 @@ static ssize_t qlcnic_sysfs_write_npar_config(struct file *file, count = size / sizeof(struct qlcnic_npar_func_cfg); rem = size % sizeof(struct qlcnic_npar_func_cfg); if (rem) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; qlcnic_swap32_buffer((u32 *)buf, size / sizeof(u32)); np_cfg = (struct qlcnic_npar_func_cfg *)buf; @@ -717,7 +715,7 @@ static ssize_t qlcnic_sysfs_write_npar_config(struct file *file, return ret; index = qlcnic_is_valid_nic_func(adapter, pci_func); if (index < 0) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; adapter->npars[index].min_bw = nic_info.min_tx_bw; adapter->npars[index].max_bw = nic_info.max_tx_bw; } @@ -784,13 +782,13 @@ static ssize_t qlcnic_sysfs_get_port_stats(struct file *file, int ret; if (qlcnic_83xx_check(adapter)) - return QLC_STATUS_UNSUPPORTED_CMD; + return -EOPNOTSUPP; if (size != sizeof(struct qlcnic_esw_statistics)) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; if (offset >= adapter->ahw->max_vnic_func) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; memset(&port_stats, 0, size); ret = qlcnic_get_port_stats(adapter, offset, QLCNIC_QUERY_RX_COUNTER, @@ -819,13 +817,13 @@ static ssize_t qlcnic_sysfs_get_esw_stats(struct file *file, int ret; if (qlcnic_83xx_check(adapter)) - return QLC_STATUS_UNSUPPORTED_CMD; + return -EOPNOTSUPP; if (size != sizeof(struct qlcnic_esw_statistics)) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; if (offset >= QLCNIC_NIU_MAX_XG_PORTS) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; memset(&esw_stats, 0, size); ret = qlcnic_get_eswitch_stats(adapter, offset, QLCNIC_QUERY_RX_COUNTER, @@ -853,10 +851,10 @@ static ssize_t qlcnic_sysfs_clear_esw_stats(struct file *file, int ret; if (qlcnic_83xx_check(adapter)) - return QLC_STATUS_UNSUPPORTED_CMD; + return -EOPNOTSUPP; if (offset >= QLCNIC_NIU_MAX_XG_PORTS) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; ret = qlcnic_clear_esw_stats(adapter, QLCNIC_STATS_ESWITCH, offset, QLCNIC_QUERY_RX_COUNTER); @@ -883,10 +881,10 @@ static ssize_t qlcnic_sysfs_clear_port_stats(struct file *file, int ret; if (qlcnic_83xx_check(adapter)) - return QLC_STATUS_UNSUPPORTED_CMD; + return -EOPNOTSUPP; if (offset >= adapter->ahw->max_vnic_func) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; ret = qlcnic_clear_esw_stats(adapter, QLCNIC_STATS_PORT, offset, QLCNIC_QUERY_RX_COUNTER); @@ -953,9 +951,7 @@ static ssize_t qlcnic_83xx_sysfs_flash_read_handler(struct file *filp, struct qlcnic_adapter *adapter = dev_get_drvdata(dev); if (!size) - return QL_STATUS_INVALID_PARAM; - if (!buf) - return QL_STATUS_INVALID_PARAM; + return -EINVAL; count = size / sizeof(u32); @@ -1132,9 +1128,6 @@ static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp, struct device *dev = container_of(kobj, struct device, kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); - if (!buf) - return QL_STATUS_INVALID_PARAM; - ret = kstrtoul(buf, 16, &data); switch (data) { diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 701ffc2..819289e 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -295,7 +295,7 @@ static bool rocker_vlan_id_is_internal(__be16 vlan_id) return (_vlan_id >= start && _vlan_id <= end); } -static __be16 rocker_port_vid_to_vlan(struct rocker_port *rocker_port, +static __be16 rocker_port_vid_to_vlan(const struct rocker_port *rocker_port, u16 vid, bool *pop_vlan) { __be16 vlan_id; @@ -312,7 +312,7 @@ static __be16 rocker_port_vid_to_vlan(struct rocker_port *rocker_port, return vlan_id; } -static u16 rocker_port_vlan_to_vid(struct rocker_port *rocker_port, +static u16 rocker_port_vlan_to_vid(const struct rocker_port *rocker_port, __be16 vlan_id) { if (rocker_vlan_id_is_internal(vlan_id)) @@ -321,7 +321,7 @@ static u16 rocker_port_vlan_to_vid(struct rocker_port *rocker_port, return ntohs(vlan_id); } -static bool rocker_port_is_bridged(struct rocker_port *rocker_port) +static bool rocker_port_is_bridged(const struct rocker_port *rocker_port) { return !!rocker_port->bridge_dev; } @@ -377,8 +377,7 @@ static void *rocker_port_kcalloc(struct rocker_port *rocker_port, return __rocker_port_mem_alloc(rocker_port, trans, n * size); } -static void rocker_port_kfree(struct rocker_port *rocker_port, - enum switchdev_trans trans, const void *mem) +static void rocker_port_kfree(enum switchdev_trans trans, const void *mem) { struct list_head *elem; @@ -423,11 +422,10 @@ static struct rocker_wait *rocker_wait_create(struct rocker_port *rocker_port, return wait; } -static void rocker_wait_destroy(struct rocker_port *rocker_port, - enum switchdev_trans trans, +static void rocker_wait_destroy(enum switchdev_trans trans, struct rocker_wait *wait) { - rocker_port_kfree(rocker_port, trans, wait); + rocker_port_kfree(trans, wait); } static bool rocker_wait_event_timeout(struct rocker_wait *wait, @@ -445,18 +443,18 @@ static void rocker_wait_wake_up(struct rocker_wait *wait) wake_up(&wait->wait); } -static u32 rocker_msix_vector(struct rocker *rocker, unsigned int vector) +static u32 rocker_msix_vector(const struct rocker *rocker, unsigned int vector) { return rocker->msix_entries[vector].vector; } -static u32 rocker_msix_tx_vector(struct rocker_port *rocker_port) +static u32 rocker_msix_tx_vector(const struct rocker_port *rocker_port) { return rocker_msix_vector(rocker_port->rocker, ROCKER_MSIX_VEC_TX(rocker_port->port_number)); } -static u32 rocker_msix_rx_vector(struct rocker_port *rocker_port) +static u32 rocker_msix_rx_vector(const struct rocker_port *rocker_port) { return rocker_msix_vector(rocker_port->rocker, ROCKER_MSIX_VEC_RX(rocker_port->port_number)); @@ -475,9 +473,9 @@ static u32 rocker_msix_rx_vector(struct rocker_port *rocker_port) * HW basic testing functions *****************************/ -static int rocker_reg_test(struct rocker *rocker) +static int rocker_reg_test(const struct rocker *rocker) { - struct pci_dev *pdev = rocker->pdev; + const struct pci_dev *pdev = rocker->pdev; u64 test_reg; u64 rnd; @@ -505,12 +503,12 @@ static int rocker_reg_test(struct rocker *rocker) return 0; } -static int rocker_dma_test_one(struct rocker *rocker, struct rocker_wait *wait, - u32 test_type, dma_addr_t dma_handle, - unsigned char *buf, unsigned char *expect, - size_t size) +static int rocker_dma_test_one(const struct rocker *rocker, + struct rocker_wait *wait, u32 test_type, + dma_addr_t dma_handle, const unsigned char *buf, + const unsigned char *expect, size_t size) { - struct pci_dev *pdev = rocker->pdev; + const struct pci_dev *pdev = rocker->pdev; int i; rocker_wait_reset(wait); @@ -534,7 +532,7 @@ static int rocker_dma_test_one(struct rocker *rocker, struct rocker_wait *wait, #define ROCKER_TEST_DMA_BUF_SIZE (PAGE_SIZE * 4) #define ROCKER_TEST_DMA_FILL_PATTERN 0x96 -static int rocker_dma_test_offset(struct rocker *rocker, +static int rocker_dma_test_offset(const struct rocker *rocker, struct rocker_wait *wait, int offset) { struct pci_dev *pdev = rocker->pdev; @@ -594,7 +592,8 @@ free_alloc: return err; } -static int rocker_dma_test(struct rocker *rocker, struct rocker_wait *wait) +static int rocker_dma_test(const struct rocker *rocker, + struct rocker_wait *wait) { int i; int err; @@ -616,9 +615,9 @@ static irqreturn_t rocker_test_irq_handler(int irq, void *dev_id) return IRQ_HANDLED; } -static int rocker_basic_hw_test(struct rocker *rocker) +static int rocker_basic_hw_test(const struct rocker *rocker) { - struct pci_dev *pdev = rocker->pdev; + const struct pci_dev *pdev = rocker->pdev; struct rocker_wait wait; int err; @@ -751,7 +750,7 @@ static u64 rocker_tlv_get_u64(const struct rocker_tlv *tlv) return *(u64 *) rocker_tlv_data(tlv); } -static void rocker_tlv_parse(struct rocker_tlv **tb, int maxtype, +static void rocker_tlv_parse(const struct rocker_tlv **tb, int maxtype, const char *buf, int buf_len) { const struct rocker_tlv *tlv; @@ -764,19 +763,19 @@ static void rocker_tlv_parse(struct rocker_tlv **tb, int maxtype, u32 type = rocker_tlv_type(tlv); if (type > 0 && type <= maxtype) - tb[type] = (struct rocker_tlv *) tlv; + tb[type] = tlv; } } -static void rocker_tlv_parse_nested(struct rocker_tlv **tb, int maxtype, +static void rocker_tlv_parse_nested(const struct rocker_tlv **tb, int maxtype, const struct rocker_tlv *tlv) { rocker_tlv_parse(tb, maxtype, rocker_tlv_data(tlv), rocker_tlv_len(tlv)); } -static void rocker_tlv_parse_desc(struct rocker_tlv **tb, int maxtype, - struct rocker_desc_info *desc_info) +static void rocker_tlv_parse_desc(const struct rocker_tlv **tb, int maxtype, + const struct rocker_desc_info *desc_info) { rocker_tlv_parse(tb, maxtype, desc_info->data, desc_info->desc->tlv_size); @@ -861,9 +860,9 @@ static void rocker_tlv_nest_end(struct rocker_desc_info *desc_info, } static void rocker_tlv_nest_cancel(struct rocker_desc_info *desc_info, - struct rocker_tlv *start) + const struct rocker_tlv *start) { - desc_info->tlv_size = (char *) start - desc_info->data; + desc_info->tlv_size = (const char *) start - desc_info->data; } /****************************************** @@ -875,7 +874,7 @@ static u32 __pos_inc(u32 pos, size_t limit) return ++pos == limit ? 0 : pos; } -static int rocker_desc_err(struct rocker_desc_info *desc_info) +static int rocker_desc_err(const struct rocker_desc_info *desc_info) { int err = desc_info->desc->comp_err & ~ROCKER_DMA_DESC_COMP_ERR_GEN; @@ -903,31 +902,31 @@ static int rocker_desc_err(struct rocker_desc_info *desc_info) return -EINVAL; } -static void rocker_desc_gen_clear(struct rocker_desc_info *desc_info) +static void rocker_desc_gen_clear(const struct rocker_desc_info *desc_info) { desc_info->desc->comp_err &= ~ROCKER_DMA_DESC_COMP_ERR_GEN; } -static bool rocker_desc_gen(struct rocker_desc_info *desc_info) +static bool rocker_desc_gen(const struct rocker_desc_info *desc_info) { u32 comp_err = desc_info->desc->comp_err; return comp_err & ROCKER_DMA_DESC_COMP_ERR_GEN ? true : false; } -static void *rocker_desc_cookie_ptr_get(struct rocker_desc_info *desc_info) +static void *rocker_desc_cookie_ptr_get(const struct rocker_desc_info *desc_info) { return (void *)(uintptr_t)desc_info->desc->cookie; } -static void rocker_desc_cookie_ptr_set(struct rocker_desc_info *desc_info, +static void rocker_desc_cookie_ptr_set(const struct rocker_desc_info *desc_info, void *ptr) { desc_info->desc->cookie = (uintptr_t) ptr; } static struct rocker_desc_info * -rocker_desc_head_get(struct rocker_dma_ring_info *info) +rocker_desc_head_get(const struct rocker_dma_ring_info *info) { static struct rocker_desc_info *desc_info; u32 head = __pos_inc(info->head, info->size); @@ -939,15 +938,15 @@ rocker_desc_head_get(struct rocker_dma_ring_info *info) return desc_info; } -static void rocker_desc_commit(struct rocker_desc_info *desc_info) +static void rocker_desc_commit(const struct rocker_desc_info *desc_info) { desc_info->desc->buf_size = desc_info->data_size; desc_info->desc->tlv_size = desc_info->tlv_size; } -static void rocker_desc_head_set(struct rocker *rocker, +static void rocker_desc_head_set(const struct rocker *rocker, struct rocker_dma_ring_info *info, - struct rocker_desc_info *desc_info) + const struct rocker_desc_info *desc_info) { u32 head = __pos_inc(info->head, info->size); @@ -972,8 +971,8 @@ rocker_desc_tail_get(struct rocker_dma_ring_info *info) return desc_info; } -static void rocker_dma_ring_credits_set(struct rocker *rocker, - struct rocker_dma_ring_info *info, +static void rocker_dma_ring_credits_set(const struct rocker *rocker, + const struct rocker_dma_ring_info *info, u32 credits) { if (credits) @@ -986,7 +985,7 @@ static unsigned long rocker_dma_ring_size_fix(size_t size) min(roundup_pow_of_two(size), ROCKER_DMA_SIZE_MAX)); } -static int rocker_dma_ring_create(struct rocker *rocker, +static int rocker_dma_ring_create(const struct rocker *rocker, unsigned int type, size_t size, struct rocker_dma_ring_info *info) @@ -1022,8 +1021,8 @@ static int rocker_dma_ring_create(struct rocker *rocker, return 0; } -static void rocker_dma_ring_destroy(struct rocker *rocker, - struct rocker_dma_ring_info *info) +static void rocker_dma_ring_destroy(const struct rocker *rocker, + const struct rocker_dma_ring_info *info) { rocker_write64(rocker, DMA_DESC_ADDR(info->type), 0); @@ -1033,7 +1032,7 @@ static void rocker_dma_ring_destroy(struct rocker *rocker, kfree(info->desc_info); } -static void rocker_dma_ring_pass_to_producer(struct rocker *rocker, +static void rocker_dma_ring_pass_to_producer(const struct rocker *rocker, struct rocker_dma_ring_info *info) { int i; @@ -1048,8 +1047,8 @@ static void rocker_dma_ring_pass_to_producer(struct rocker *rocker, rocker_desc_commit(&info->desc_info[i]); } -static int rocker_dma_ring_bufs_alloc(struct rocker *rocker, - struct rocker_dma_ring_info *info, +static int rocker_dma_ring_bufs_alloc(const struct rocker *rocker, + const struct rocker_dma_ring_info *info, int direction, size_t buf_size) { struct pci_dev *pdev = rocker->pdev; @@ -1086,7 +1085,7 @@ static int rocker_dma_ring_bufs_alloc(struct rocker *rocker, rollback: for (i--; i >= 0; i--) { - struct rocker_desc_info *desc_info = &info->desc_info[i]; + const struct rocker_desc_info *desc_info = &info->desc_info[i]; pci_unmap_single(pdev, dma_unmap_addr(desc_info, mapaddr), desc_info->data_size, direction); @@ -1095,15 +1094,15 @@ rollback: return err; } -static void rocker_dma_ring_bufs_free(struct rocker *rocker, - struct rocker_dma_ring_info *info, +static void rocker_dma_ring_bufs_free(const struct rocker *rocker, + const struct rocker_dma_ring_info *info, int direction) { struct pci_dev *pdev = rocker->pdev; int i; for (i = 0; i < info->size; i++) { - struct rocker_desc_info *desc_info = &info->desc_info[i]; + const struct rocker_desc_info *desc_info = &info->desc_info[i]; struct rocker_desc *desc = &info->desc[i]; desc->buf_addr = 0; @@ -1116,7 +1115,7 @@ static void rocker_dma_ring_bufs_free(struct rocker *rocker, static int rocker_dma_rings_init(struct rocker *rocker) { - struct pci_dev *pdev = rocker->pdev; + const struct pci_dev *pdev = rocker->pdev; int err; err = rocker_dma_ring_create(rocker, ROCKER_DMA_CMD, @@ -1173,11 +1172,11 @@ static void rocker_dma_rings_fini(struct rocker *rocker) rocker_dma_ring_destroy(rocker, &rocker->cmd_ring); } -static int rocker_dma_rx_ring_skb_map(struct rocker *rocker, - struct rocker_port *rocker_port, +static int rocker_dma_rx_ring_skb_map(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, struct sk_buff *skb, size_t buf_len) { + const struct rocker *rocker = rocker_port->rocker; struct pci_dev *pdev = rocker->pdev; dma_addr_t dma_handle; @@ -1197,13 +1196,12 @@ tlv_put_failure: return -EMSGSIZE; } -static size_t rocker_port_rx_buf_len(struct rocker_port *rocker_port) +static size_t rocker_port_rx_buf_len(const struct rocker_port *rocker_port) { return rocker_port->dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; } -static int rocker_dma_rx_ring_skb_alloc(struct rocker *rocker, - struct rocker_port *rocker_port, +static int rocker_dma_rx_ring_skb_alloc(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info) { struct net_device *dev = rocker_port->dev; @@ -1220,8 +1218,7 @@ static int rocker_dma_rx_ring_skb_alloc(struct rocker *rocker, skb = netdev_alloc_skb_ip_align(dev, buf_len); if (!skb) return -ENOMEM; - err = rocker_dma_rx_ring_skb_map(rocker, rocker_port, desc_info, - skb, buf_len); + err = rocker_dma_rx_ring_skb_map(rocker_port, desc_info, skb, buf_len); if (err) { dev_kfree_skb_any(skb); return err; @@ -1230,8 +1227,8 @@ static int rocker_dma_rx_ring_skb_alloc(struct rocker *rocker, return 0; } -static void rocker_dma_rx_ring_skb_unmap(struct rocker *rocker, - struct rocker_tlv **attrs) +static void rocker_dma_rx_ring_skb_unmap(const struct rocker *rocker, + const struct rocker_tlv **attrs) { struct pci_dev *pdev = rocker->pdev; dma_addr_t dma_handle; @@ -1245,10 +1242,10 @@ static void rocker_dma_rx_ring_skb_unmap(struct rocker *rocker, pci_unmap_single(pdev, dma_handle, len, PCI_DMA_FROMDEVICE); } -static void rocker_dma_rx_ring_skb_free(struct rocker *rocker, - struct rocker_desc_info *desc_info) +static void rocker_dma_rx_ring_skb_free(const struct rocker *rocker, + const struct rocker_desc_info *desc_info) { - struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1]; + const struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1]; struct sk_buff *skb = rocker_desc_cookie_ptr_get(desc_info); if (!skb) @@ -1258,15 +1255,15 @@ static void rocker_dma_rx_ring_skb_free(struct rocker *rocker, dev_kfree_skb_any(skb); } -static int rocker_dma_rx_ring_skbs_alloc(struct rocker *rocker, - struct rocker_port *rocker_port) +static int rocker_dma_rx_ring_skbs_alloc(const struct rocker_port *rocker_port) { - struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring; + const struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring; + const struct rocker *rocker = rocker_port->rocker; int i; int err; for (i = 0; i < rx_ring->size; i++) { - err = rocker_dma_rx_ring_skb_alloc(rocker, rocker_port, + err = rocker_dma_rx_ring_skb_alloc(rocker_port, &rx_ring->desc_info[i]); if (err) goto rollback; @@ -1279,10 +1276,10 @@ rollback: return err; } -static void rocker_dma_rx_ring_skbs_free(struct rocker *rocker, - struct rocker_port *rocker_port) +static void rocker_dma_rx_ring_skbs_free(const struct rocker_port *rocker_port) { - struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring; + const struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring; + const struct rocker *rocker = rocker_port->rocker; int i; for (i = 0; i < rx_ring->size; i++) @@ -1328,7 +1325,7 @@ static int rocker_port_dma_rings_init(struct rocker_port *rocker_port) goto err_dma_rx_ring_bufs_alloc; } - err = rocker_dma_rx_ring_skbs_alloc(rocker, rocker_port); + err = rocker_dma_rx_ring_skbs_alloc(rocker_port); if (err) { netdev_err(rocker_port->dev, "failed to alloc rx dma ring skbs\n"); goto err_dma_rx_ring_skbs_alloc; @@ -1354,7 +1351,7 @@ static void rocker_port_dma_rings_fini(struct rocker_port *rocker_port) { struct rocker *rocker = rocker_port->rocker; - rocker_dma_rx_ring_skbs_free(rocker, rocker_port); + rocker_dma_rx_ring_skbs_free(rocker_port); rocker_dma_ring_bufs_free(rocker, &rocker_port->rx_ring, PCI_DMA_BIDIRECTIONAL); rocker_dma_ring_destroy(rocker, &rocker_port->rx_ring); @@ -1363,7 +1360,8 @@ static void rocker_port_dma_rings_fini(struct rocker_port *rocker_port) rocker_dma_ring_destroy(rocker, &rocker_port->tx_ring); } -static void rocker_port_set_enable(struct rocker_port *rocker_port, bool enable) +static void rocker_port_set_enable(const struct rocker_port *rocker_port, + bool enable) { u64 val = rocker_read64(rocker_port->rocker, PORT_PHYS_ENABLE); @@ -1381,7 +1379,7 @@ static void rocker_port_set_enable(struct rocker_port *rocker_port, bool enable) static irqreturn_t rocker_cmd_irq_handler(int irq, void *dev_id) { struct rocker *rocker = dev_id; - struct rocker_desc_info *desc_info; + const struct rocker_desc_info *desc_info; struct rocker_wait *wait; u32 credits = 0; @@ -1397,22 +1395,22 @@ static irqreturn_t rocker_cmd_irq_handler(int irq, void *dev_id) return IRQ_HANDLED; } -static void rocker_port_link_up(struct rocker_port *rocker_port) +static void rocker_port_link_up(const struct rocker_port *rocker_port) { netif_carrier_on(rocker_port->dev); netdev_info(rocker_port->dev, "Link is up\n"); } -static void rocker_port_link_down(struct rocker_port *rocker_port) +static void rocker_port_link_down(const struct rocker_port *rocker_port) { netif_carrier_off(rocker_port->dev); netdev_info(rocker_port->dev, "Link is down\n"); } -static int rocker_event_link_change(struct rocker *rocker, +static int rocker_event_link_change(const struct rocker *rocker, const struct rocker_tlv *info) { - struct rocker_tlv *attrs[ROCKER_TLV_EVENT_LINK_CHANGED_MAX + 1]; + const struct rocker_tlv *attrs[ROCKER_TLV_EVENT_LINK_CHANGED_MAX + 1]; unsigned int port_number; bool link_up; struct rocker_port *rocker_port; @@ -1458,7 +1456,7 @@ struct rocker_mac_vlan_seen_work { static void rocker_event_mac_vlan_seen_work(struct work_struct *work) { - struct rocker_mac_vlan_seen_work *sw = + const struct rocker_mac_vlan_seen_work *sw = container_of(work, struct rocker_mac_vlan_seen_work, work); rtnl_lock(); @@ -1469,14 +1467,14 @@ static void rocker_event_mac_vlan_seen_work(struct work_struct *work) kfree(work); } -static int rocker_event_mac_vlan_seen(struct rocker *rocker, +static int rocker_event_mac_vlan_seen(const struct rocker *rocker, const struct rocker_tlv *info) { struct rocker_mac_vlan_seen_work *sw; - struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAC_VLAN_MAX + 1]; + const struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAC_VLAN_MAX + 1]; unsigned int port_number; struct rocker_port *rocker_port; - unsigned char *addr; + const unsigned char *addr; int flags = ROCKER_OP_FLAG_LEARNED; __be16 vlan_id; @@ -1515,11 +1513,11 @@ static int rocker_event_mac_vlan_seen(struct rocker *rocker, return 0; } -static int rocker_event_process(struct rocker *rocker, - struct rocker_desc_info *desc_info) +static int rocker_event_process(const struct rocker *rocker, + const struct rocker_desc_info *desc_info) { - struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAX + 1]; - struct rocker_tlv *info; + const struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAX + 1]; + const struct rocker_tlv *info; u16 type; rocker_tlv_parse_desc(attrs, ROCKER_TLV_EVENT_MAX, desc_info); @@ -1543,8 +1541,8 @@ static int rocker_event_process(struct rocker *rocker, static irqreturn_t rocker_event_irq_handler(int irq, void *dev_id) { struct rocker *rocker = dev_id; - struct pci_dev *pdev = rocker->pdev; - struct rocker_desc_info *desc_info; + const struct pci_dev *pdev = rocker->pdev; + const struct rocker_desc_info *desc_info; u32 credits = 0; int err; @@ -1588,17 +1586,20 @@ static irqreturn_t rocker_rx_irq_handler(int irq, void *dev_id) * Command interface ********************/ -typedef int (*rocker_cmd_cb_t)(struct rocker *rocker, - struct rocker_port *rocker_port, - struct rocker_desc_info *desc_info, - void *priv); +typedef int (*rocker_cmd_prep_cb_t)(const struct rocker_port *rocker_port, + struct rocker_desc_info *desc_info, + void *priv); -static int rocker_cmd_exec(struct rocker *rocker, - struct rocker_port *rocker_port, +typedef int (*rocker_cmd_proc_cb_t)(const struct rocker_port *rocker_port, + const struct rocker_desc_info *desc_info, + void *priv); + +static int rocker_cmd_exec(struct rocker_port *rocker_port, enum switchdev_trans trans, - rocker_cmd_cb_t prepare, void *prepare_priv, - rocker_cmd_cb_t process, void *process_priv) + rocker_cmd_prep_cb_t prepare, void *prepare_priv, + rocker_cmd_proc_cb_t process, void *process_priv) { + struct rocker *rocker = rocker_port->rocker; struct rocker_desc_info *desc_info; struct rocker_wait *wait; unsigned long flags; @@ -1617,7 +1618,7 @@ static int rocker_cmd_exec(struct rocker *rocker, goto out; } - err = prepare(rocker, rocker_port, desc_info, prepare_priv); + err = prepare(rocker_port, desc_info, prepare_priv); if (err) { spin_unlock_irqrestore(&rocker->cmd_ring_lock, flags); goto out; @@ -1639,17 +1640,16 @@ static int rocker_cmd_exec(struct rocker *rocker, return err; if (process) - err = process(rocker, rocker_port, desc_info, process_priv); + err = process(rocker_port, desc_info, process_priv); rocker_desc_gen_clear(desc_info); out: - rocker_wait_destroy(rocker_port, trans, wait); + rocker_wait_destroy(trans, wait); return err; } static int -rocker_cmd_get_port_settings_prep(struct rocker *rocker, - struct rocker_port *rocker_port, +rocker_cmd_get_port_settings_prep(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { @@ -1669,14 +1669,13 @@ rocker_cmd_get_port_settings_prep(struct rocker *rocker, } static int -rocker_cmd_get_port_settings_ethtool_proc(struct rocker *rocker, - struct rocker_port *rocker_port, - struct rocker_desc_info *desc_info, +rocker_cmd_get_port_settings_ethtool_proc(const struct rocker_port *rocker_port, + const struct rocker_desc_info *desc_info, void *priv) { struct ethtool_cmd *ecmd = priv; - struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; - struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1]; + const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; + const struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1]; u32 speed; u8 duplex; u8 autoneg; @@ -1708,15 +1707,14 @@ rocker_cmd_get_port_settings_ethtool_proc(struct rocker *rocker, } static int -rocker_cmd_get_port_settings_macaddr_proc(struct rocker *rocker, - struct rocker_port *rocker_port, - struct rocker_desc_info *desc_info, +rocker_cmd_get_port_settings_macaddr_proc(const struct rocker_port *rocker_port, + const struct rocker_desc_info *desc_info, void *priv) { unsigned char *macaddr = priv; - struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; - struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1]; - struct rocker_tlv *attr; + const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; + const struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1]; + const struct rocker_tlv *attr; rocker_tlv_parse_desc(attrs, ROCKER_TLV_CMD_MAX, desc_info); if (!attrs[ROCKER_TLV_CMD_INFO]) @@ -1741,17 +1739,16 @@ struct port_name { }; static int -rocker_cmd_get_port_settings_phys_name_proc(struct rocker *rocker, - struct rocker_port *rocker_port, - struct rocker_desc_info *desc_info, +rocker_cmd_get_port_settings_phys_name_proc(const struct rocker_port *rocker_port, + const struct rocker_desc_info *desc_info, void *priv) { - struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1]; - struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; + const struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1]; + const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; struct port_name *name = priv; - struct rocker_tlv *attr; + const struct rocker_tlv *attr; size_t i, j, len; - char *str; + const char *str; rocker_tlv_parse_desc(attrs, ROCKER_TLV_CMD_MAX, desc_info); if (!attrs[ROCKER_TLV_CMD_INFO]) @@ -1783,8 +1780,7 @@ rocker_cmd_get_port_settings_phys_name_proc(struct rocker *rocker, } static int -rocker_cmd_set_port_settings_ethtool_prep(struct rocker *rocker, - struct rocker_port *rocker_port, +rocker_cmd_set_port_settings_ethtool_prep(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { @@ -1814,12 +1810,11 @@ rocker_cmd_set_port_settings_ethtool_prep(struct rocker *rocker, } static int -rocker_cmd_set_port_settings_macaddr_prep(struct rocker *rocker, - struct rocker_port *rocker_port, +rocker_cmd_set_port_settings_macaddr_prep(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { - unsigned char *macaddr = priv; + const unsigned char *macaddr = priv; struct rocker_tlv *cmd_info; if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE, @@ -1839,8 +1834,7 @@ rocker_cmd_set_port_settings_macaddr_prep(struct rocker *rocker, } static int -rocker_cmd_set_port_learning_prep(struct rocker *rocker, - struct rocker_port *rocker_port, +rocker_cmd_set_port_learning_prep(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { @@ -1865,8 +1859,7 @@ rocker_cmd_set_port_learning_prep(struct rocker *rocker, static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port, struct ethtool_cmd *ecmd) { - return rocker_cmd_exec(rocker_port->rocker, rocker_port, - SWITCHDEV_TRANS_NONE, + return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, rocker_cmd_get_port_settings_prep, NULL, rocker_cmd_get_port_settings_ethtool_proc, ecmd); @@ -1875,8 +1868,7 @@ static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port, static int rocker_cmd_get_port_settings_macaddr(struct rocker_port *rocker_port, unsigned char *macaddr) { - return rocker_cmd_exec(rocker_port->rocker, rocker_port, - SWITCHDEV_TRANS_NONE, + return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, rocker_cmd_get_port_settings_prep, NULL, rocker_cmd_get_port_settings_macaddr_proc, macaddr); @@ -1885,8 +1877,7 @@ static int rocker_cmd_get_port_settings_macaddr(struct rocker_port *rocker_port, static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port, struct ethtool_cmd *ecmd) { - return rocker_cmd_exec(rocker_port->rocker, rocker_port, - SWITCHDEV_TRANS_NONE, + return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, rocker_cmd_set_port_settings_ethtool_prep, ecmd, NULL, NULL); } @@ -1894,8 +1885,7 @@ static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port, static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port, unsigned char *macaddr) { - return rocker_cmd_exec(rocker_port->rocker, rocker_port, - SWITCHDEV_TRANS_NONE, + return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, rocker_cmd_set_port_settings_macaddr_prep, macaddr, NULL, NULL); } @@ -1903,13 +1893,14 @@ static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port, static int rocker_port_set_learning(struct rocker_port *rocker_port, enum switchdev_trans trans) { - return rocker_cmd_exec(rocker_port->rocker, rocker_port, trans, + return rocker_cmd_exec(rocker_port, trans, rocker_cmd_set_port_learning_prep, NULL, NULL, NULL); } -static int rocker_cmd_flow_tbl_add_ig_port(struct rocker_desc_info *desc_info, - struct rocker_flow_tbl_entry *entry) +static int +rocker_cmd_flow_tbl_add_ig_port(struct rocker_desc_info *desc_info, + const struct rocker_flow_tbl_entry *entry) { if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_PPORT, entry->key.ig_port.in_pport)) @@ -1924,8 +1915,9 @@ static int rocker_cmd_flow_tbl_add_ig_port(struct rocker_desc_info *desc_info, return 0; } -static int rocker_cmd_flow_tbl_add_vlan(struct rocker_desc_info *desc_info, - struct rocker_flow_tbl_entry *entry) +static int +rocker_cmd_flow_tbl_add_vlan(struct rocker_desc_info *desc_info, + const struct rocker_flow_tbl_entry *entry) { if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_PPORT, entry->key.vlan.in_pport)) @@ -1947,8 +1939,9 @@ static int rocker_cmd_flow_tbl_add_vlan(struct rocker_desc_info *desc_info, return 0; } -static int rocker_cmd_flow_tbl_add_term_mac(struct rocker_desc_info *desc_info, - struct rocker_flow_tbl_entry *entry) +static int +rocker_cmd_flow_tbl_add_term_mac(struct rocker_desc_info *desc_info, + const struct rocker_flow_tbl_entry *entry) { if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_PPORT, entry->key.term_mac.in_pport)) @@ -1984,7 +1977,7 @@ static int rocker_cmd_flow_tbl_add_term_mac(struct rocker_desc_info *desc_info, static int rocker_cmd_flow_tbl_add_ucast_routing(struct rocker_desc_info *desc_info, - struct rocker_flow_tbl_entry *entry) + const struct rocker_flow_tbl_entry *entry) { if (rocker_tlv_put_be16(desc_info, ROCKER_TLV_OF_DPA_ETHERTYPE, entry->key.ucast_routing.eth_type)) @@ -2005,8 +1998,9 @@ rocker_cmd_flow_tbl_add_ucast_routing(struct rocker_desc_info *desc_info, return 0; } -static int rocker_cmd_flow_tbl_add_bridge(struct rocker_desc_info *desc_info, - struct rocker_flow_tbl_entry *entry) +static int +rocker_cmd_flow_tbl_add_bridge(struct rocker_desc_info *desc_info, + const struct rocker_flow_tbl_entry *entry) { if (entry->key.bridge.has_eth_dst && rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_DST_MAC, @@ -2038,8 +2032,9 @@ static int rocker_cmd_flow_tbl_add_bridge(struct rocker_desc_info *desc_info, return 0; } -static int rocker_cmd_flow_tbl_add_acl(struct rocker_desc_info *desc_info, - struct rocker_flow_tbl_entry *entry) +static int +rocker_cmd_flow_tbl_add_acl(struct rocker_desc_info *desc_info, + const struct rocker_flow_tbl_entry *entry) { if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_PPORT, entry->key.acl.in_pport)) @@ -2104,12 +2099,11 @@ static int rocker_cmd_flow_tbl_add_acl(struct rocker_desc_info *desc_info, return 0; } -static int rocker_cmd_flow_tbl_add(struct rocker *rocker, - struct rocker_port *rocker_port, +static int rocker_cmd_flow_tbl_add(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { - struct rocker_flow_tbl_entry *entry = priv; + const struct rocker_flow_tbl_entry *entry = priv; struct rocker_tlv *cmd_info; int err = 0; @@ -2162,8 +2156,7 @@ static int rocker_cmd_flow_tbl_add(struct rocker *rocker, return 0; } -static int rocker_cmd_flow_tbl_del(struct rocker *rocker, - struct rocker_port *rocker_port, +static int rocker_cmd_flow_tbl_del(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { @@ -2199,7 +2192,7 @@ rocker_cmd_group_tbl_add_l2_interface(struct rocker_desc_info *desc_info, static int rocker_cmd_group_tbl_add_l2_rewrite(struct rocker_desc_info *desc_info, - struct rocker_group_tbl_entry *entry) + const struct rocker_group_tbl_entry *entry) { if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_GROUP_ID_LOWER, entry->l2_rewrite.group_id)) @@ -2222,7 +2215,7 @@ rocker_cmd_group_tbl_add_l2_rewrite(struct rocker_desc_info *desc_info, static int rocker_cmd_group_tbl_add_group_ids(struct rocker_desc_info *desc_info, - struct rocker_group_tbl_entry *entry) + const struct rocker_group_tbl_entry *entry) { int i; struct rocker_tlv *group_ids; @@ -2248,7 +2241,7 @@ rocker_cmd_group_tbl_add_group_ids(struct rocker_desc_info *desc_info, static int rocker_cmd_group_tbl_add_l3_unicast(struct rocker_desc_info *desc_info, - struct rocker_group_tbl_entry *entry) + const struct rocker_group_tbl_entry *entry) { if (!is_zero_ether_addr(entry->l3_unicast.eth_src) && rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_SRC_MAC, @@ -2272,8 +2265,7 @@ rocker_cmd_group_tbl_add_l3_unicast(struct rocker_desc_info *desc_info, return 0; } -static int rocker_cmd_group_tbl_add(struct rocker *rocker, - struct rocker_port *rocker_port, +static int rocker_cmd_group_tbl_add(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { @@ -2318,8 +2310,7 @@ static int rocker_cmd_group_tbl_add(struct rocker *rocker, return 0; } -static int rocker_cmd_group_tbl_del(struct rocker *rocker, - struct rocker_port *rocker_port, +static int rocker_cmd_group_tbl_del(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { @@ -2402,7 +2393,8 @@ static void rocker_free_tbls(struct rocker *rocker) } static struct rocker_flow_tbl_entry * -rocker_flow_tbl_find(struct rocker *rocker, struct rocker_flow_tbl_entry *match) +rocker_flow_tbl_find(const struct rocker *rocker, + const struct rocker_flow_tbl_entry *match) { struct rocker_flow_tbl_entry *found; size_t key_len = match->key_len ? match->key_len : sizeof(found->key); @@ -2435,7 +2427,7 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port, match->cookie = found->cookie; if (trans != SWITCHDEV_TRANS_PREPARE) hash_del(&found->entry); - rocker_port_kfree(rocker_port, trans, found); + rocker_port_kfree(trans, found); found = match; found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_MOD; } else { @@ -2449,8 +2441,7 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port, spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags); - return rocker_cmd_exec(rocker, rocker_port, trans, - rocker_cmd_flow_tbl_add, + return rocker_cmd_exec(rocker_port, trans, rocker_cmd_flow_tbl_add, found, NULL, NULL); } @@ -2478,13 +2469,13 @@ static int rocker_flow_tbl_del(struct rocker_port *rocker_port, spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags); - rocker_port_kfree(rocker_port, trans, match); + rocker_port_kfree(trans, match); if (found) { - err = rocker_cmd_exec(rocker, rocker_port, trans, + err = rocker_cmd_exec(rocker_port, trans, rocker_cmd_flow_tbl_del, found, NULL, NULL); - rocker_port_kfree(rocker_port, trans, found); + rocker_port_kfree(trans, found); } return err; @@ -2715,8 +2706,8 @@ static int rocker_flow_tbl_acl(struct rocker_port *rocker_port, } static struct rocker_group_tbl_entry * -rocker_group_tbl_find(struct rocker *rocker, - struct rocker_group_tbl_entry *match) +rocker_group_tbl_find(const struct rocker *rocker, + const struct rocker_group_tbl_entry *match) { struct rocker_group_tbl_entry *found; @@ -2729,19 +2720,18 @@ rocker_group_tbl_find(struct rocker *rocker, return NULL; } -static void rocker_group_tbl_entry_free(struct rocker_port *rocker_port, - enum switchdev_trans trans, +static void rocker_group_tbl_entry_free(enum switchdev_trans trans, struct rocker_group_tbl_entry *entry) { switch (ROCKER_GROUP_TYPE_GET(entry->group_id)) { case ROCKER_OF_DPA_GROUP_TYPE_L2_FLOOD: case ROCKER_OF_DPA_GROUP_TYPE_L2_MCAST: - rocker_port_kfree(rocker_port, trans, entry->group_ids); + rocker_port_kfree(trans, entry->group_ids); break; default: break; } - rocker_port_kfree(rocker_port, trans, entry); + rocker_port_kfree(trans, entry); } static int rocker_group_tbl_add(struct rocker_port *rocker_port, @@ -2759,7 +2749,7 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port, if (found) { if (trans != SWITCHDEV_TRANS_PREPARE) hash_del(&found->entry); - rocker_group_tbl_entry_free(rocker_port, trans, found); + rocker_group_tbl_entry_free(trans, found); found = match; found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_MOD; } else { @@ -2772,8 +2762,7 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port, spin_unlock_irqrestore(&rocker->group_tbl_lock, flags); - return rocker_cmd_exec(rocker, rocker_port, trans, - rocker_cmd_group_tbl_add, + return rocker_cmd_exec(rocker_port, trans, rocker_cmd_group_tbl_add, found, NULL, NULL); } @@ -2798,13 +2787,13 @@ static int rocker_group_tbl_del(struct rocker_port *rocker_port, spin_unlock_irqrestore(&rocker->group_tbl_lock, flags); - rocker_group_tbl_entry_free(rocker_port, trans, match); + rocker_group_tbl_entry_free(trans, match); if (found) { - err = rocker_cmd_exec(rocker, rocker_port, trans, + err = rocker_cmd_exec(rocker_port, trans, rocker_cmd_group_tbl_del, found, NULL, NULL); - rocker_group_tbl_entry_free(rocker_port, trans, found); + rocker_group_tbl_entry_free(trans, found); } return err; @@ -2840,7 +2829,7 @@ static int rocker_group_l2_interface(struct rocker_port *rocker_port, static int rocker_group_l2_fan_out(struct rocker_port *rocker_port, enum switchdev_trans trans, int flags, u8 group_count, - u32 *group_ids, u32 group_id) + const u32 *group_ids, u32 group_id) { struct rocker_group_tbl_entry *entry; @@ -2854,7 +2843,7 @@ static int rocker_group_l2_fan_out(struct rocker_port *rocker_port, entry->group_ids = rocker_port_kcalloc(rocker_port, trans, group_count, sizeof(u32)); if (!entry->group_ids) { - rocker_port_kfree(rocker_port, trans, entry); + rocker_port_kfree(trans, entry); return -ENOMEM; } memcpy(entry->group_ids, group_ids, group_count * sizeof(u32)); @@ -2865,7 +2854,7 @@ static int rocker_group_l2_fan_out(struct rocker_port *rocker_port, static int rocker_group_l2_flood(struct rocker_port *rocker_port, enum switchdev_trans trans, int flags, __be16 vlan_id, u8 group_count, - u32 *group_ids, u32 group_id) + const u32 *group_ids, u32 group_id) { return rocker_group_l2_fan_out(rocker_port, trans, flags, group_count, group_ids, @@ -2874,7 +2863,7 @@ static int rocker_group_l2_flood(struct rocker_port *rocker_port, static int rocker_group_l3_unicast(struct rocker_port *rocker_port, enum switchdev_trans trans, int flags, - u32 index, u8 *src_mac, u8 *dst_mac, + u32 index, const u8 *src_mac, const u8 *dst_mac, __be16 vlan_id, bool ttl_check, u32 pport) { struct rocker_group_tbl_entry *entry; @@ -2896,7 +2885,7 @@ static int rocker_group_l3_unicast(struct rocker_port *rocker_port, } static struct rocker_neigh_tbl_entry * - rocker_neigh_tbl_find(struct rocker *rocker, __be32 ip_addr) +rocker_neigh_tbl_find(const struct rocker *rocker, __be32 ip_addr) { struct rocker_neigh_tbl_entry *found; @@ -2921,21 +2910,20 @@ static void _rocker_neigh_add(struct rocker *rocker, be32_to_cpu(entry->ip_addr)); } -static void _rocker_neigh_del(struct rocker_port *rocker_port, - enum switchdev_trans trans, +static void _rocker_neigh_del(enum switchdev_trans trans, struct rocker_neigh_tbl_entry *entry) { if (trans == SWITCHDEV_TRANS_PREPARE) return; if (--entry->ref_count == 0) { hash_del(&entry->entry); - rocker_port_kfree(rocker_port, trans, entry); + rocker_port_kfree(trans, entry); } } static void _rocker_neigh_update(struct rocker_neigh_tbl_entry *entry, enum switchdev_trans trans, - u8 *eth_dst, bool ttl_check) + const u8 *eth_dst, bool ttl_check) { if (eth_dst) { ether_addr_copy(entry->eth_dst, eth_dst); @@ -2947,7 +2935,7 @@ static void _rocker_neigh_update(struct rocker_neigh_tbl_entry *entry, static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, enum switchdev_trans trans, - int flags, __be32 ip_addr, u8 *eth_dst) + int flags, __be32 ip_addr, const u8 *eth_dst) { struct rocker *rocker = rocker_port->rocker; struct rocker_neigh_tbl_entry *entry; @@ -2983,7 +2971,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, _rocker_neigh_add(rocker, trans, entry); } else if (removing) { memcpy(entry, found, sizeof(*entry)); - _rocker_neigh_del(rocker_port, trans, found); + _rocker_neigh_del(trans, found); } else if (updating) { _rocker_neigh_update(found, trans, eth_dst, true); memcpy(entry, found, sizeof(*entry)); @@ -3032,7 +3020,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, err_out: if (!adding) - rocker_port_kfree(rocker_port, trans, entry); + rocker_port_kfree(trans, entry); return err; } @@ -3100,7 +3088,7 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, *index = entry->index; resolved = false; } else if (removing) { - _rocker_neigh_del(rocker_port, trans, found); + _rocker_neigh_del(trans, found); } else if (updating) { _rocker_neigh_update(found, trans, NULL, false); resolved = !is_zero_ether_addr(found->eth_dst); @@ -3111,7 +3099,7 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, spin_unlock_irqrestore(&rocker->neigh_tbl_lock, lock_flags); if (!adding) - rocker_port_kfree(rocker_port, trans, entry); + rocker_port_kfree(trans, entry); if (err) return err; @@ -3129,7 +3117,7 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, int flags, __be16 vlan_id) { struct rocker_port *p; - struct rocker *rocker = rocker_port->rocker; + const struct rocker *rocker = rocker_port->rocker; u32 group_id = ROCKER_GROUP_L2_FLOOD(vlan_id, 0); u32 *group_ids; u8 group_count = 0; @@ -3148,6 +3136,8 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, for (i = 0; i < rocker->port_count; i++) { p = rocker->ports[i]; + if (!p) + continue; if (!rocker_port_is_bridged(p)) continue; if (test_bit(ntohs(vlan_id), p->vlan_bitmap)) { @@ -3167,7 +3157,7 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, "Error (%d) port VLAN l2 flood group\n", err); no_ports_in_vlan: - rocker_port_kfree(rocker_port, trans, group_ids); + rocker_port_kfree(trans, group_ids); return err; } @@ -3175,7 +3165,7 @@ static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port, enum switchdev_trans trans, int flags, __be16 vlan_id, bool pop_vlan) { - struct rocker *rocker = rocker_port->rocker; + const struct rocker *rocker = rocker_port->rocker; struct rocker_port *p; bool adding = !(flags & ROCKER_OP_FLAG_REMOVE); u32 out_pport; @@ -3207,7 +3197,7 @@ static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port, for (i = 0; i < rocker->port_count; i++) { p = rocker->ports[i]; - if (test_bit(ntohs(vlan_id), p->vlan_bitmap)) + if (p && test_bit(ntohs(vlan_id), p->vlan_bitmap)) ref++; } @@ -3273,13 +3263,13 @@ static struct rocker_ctrl { static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, enum switchdev_trans trans, int flags, - struct rocker_ctrl *ctrl, __be16 vlan_id) + const struct rocker_ctrl *ctrl, __be16 vlan_id) { u32 in_pport = rocker_port->pport; u32 in_pport_mask = 0xffffffff; u32 out_pport = 0; - u8 *eth_src = NULL; - u8 *eth_src_mask = NULL; + const u8 *eth_src = NULL; + const u8 *eth_src_mask = NULL; __be16 vlan_id_mask = htons(0xffff); u8 ip_proto = 0; u8 ip_proto_mask = 0; @@ -3306,7 +3296,7 @@ static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port, enum switchdev_trans trans, int flags, - struct rocker_ctrl *ctrl, + const struct rocker_ctrl *ctrl, __be16 vlan_id) { enum rocker_of_dpa_table_id goto_tbl = @@ -3331,7 +3321,7 @@ static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port, static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port, enum switchdev_trans trans, int flags, - struct rocker_ctrl *ctrl, __be16 vlan_id) + const struct rocker_ctrl *ctrl, __be16 vlan_id) { u32 in_pport_mask = 0xffffffff; __be16 vlan_id_mask = htons(0xffff); @@ -3355,7 +3345,7 @@ static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port, static int rocker_port_ctrl_vlan(struct rocker_port *rocker_port, enum switchdev_trans trans, int flags, - struct rocker_ctrl *ctrl, __be16 vlan_id) + const struct rocker_ctrl *ctrl, __be16 vlan_id) { if (ctrl->acl) return rocker_port_ctrl_vlan_acl(rocker_port, trans, flags, @@ -3392,7 +3382,7 @@ static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port, static int rocker_port_ctrl(struct rocker_port *rocker_port, enum switchdev_trans trans, int flags, - struct rocker_ctrl *ctrl) + const struct rocker_ctrl *ctrl) { u16 vid; int err = 0; @@ -3510,7 +3500,7 @@ struct rocker_fdb_learn_work { static void rocker_port_fdb_learn_work(struct work_struct *work) { - struct rocker_fdb_learn_work *lw = + const struct rocker_fdb_learn_work *lw = container_of(work, struct rocker_fdb_learn_work, work); bool removing = (lw->flags & ROCKER_OP_FLAG_REMOVE); bool learned = (lw->flags & ROCKER_OP_FLAG_LEARNED); @@ -3526,7 +3516,7 @@ static void rocker_port_fdb_learn_work(struct work_struct *work) call_switchdev_notifiers(SWITCHDEV_FDB_ADD, lw->rocker_port->dev, &info.info); - rocker_port_kfree(lw->rocker_port, lw->trans, work); + rocker_port_kfree(lw->trans, work); } static int rocker_port_fdb_learn(struct rocker_port *rocker_port, @@ -3573,7 +3563,7 @@ static int rocker_port_fdb_learn(struct rocker_port *rocker_port, lw->vid = rocker_port_vlan_to_vid(rocker_port, vlan_id); if (trans == SWITCHDEV_TRANS_PREPARE) - rocker_port_kfree(rocker_port, trans, lw); + rocker_port_kfree(trans, lw); else schedule_work(&lw->work); @@ -3581,7 +3571,8 @@ static int rocker_port_fdb_learn(struct rocker_port *rocker_port, } static struct rocker_fdb_tbl_entry * -rocker_fdb_tbl_find(struct rocker *rocker, struct rocker_fdb_tbl_entry *match) +rocker_fdb_tbl_find(const struct rocker *rocker, + const struct rocker_fdb_tbl_entry *match) { struct rocker_fdb_tbl_entry *found; @@ -3618,7 +3609,7 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, found = rocker_fdb_tbl_find(rocker, fdb); if (removing && found) { - rocker_port_kfree(rocker_port, trans, fdb); + rocker_port_kfree(trans, fdb); if (trans != SWITCHDEV_TRANS_PREPARE) hash_del(&found->entry); } else if (!removing && !found) { @@ -3630,7 +3621,7 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, /* Check if adding and already exists, or removing and can't find */ if (!found != !removing) { - rocker_port_kfree(rocker_port, trans, fdb); + rocker_port_kfree(trans, fdb); if (!found && removing) return 0; /* Refreshing existing to update aging timers */ @@ -3839,7 +3830,7 @@ static int rocker_port_fwd_disable(struct rocker_port *rocker_port, } static struct rocker_internal_vlan_tbl_entry * -rocker_internal_vlan_tbl_find(struct rocker *rocker, int ifindex) +rocker_internal_vlan_tbl_find(const struct rocker *rocker, int ifindex) { struct rocker_internal_vlan_tbl_entry *found; @@ -3894,8 +3885,9 @@ found: return found->vlan_id; } -static void rocker_port_internal_vlan_id_put(struct rocker_port *rocker_port, - int ifindex) +static void +rocker_port_internal_vlan_id_put(const struct rocker_port *rocker_port, + int ifindex) { struct rocker *rocker = rocker_port->rocker; struct rocker_internal_vlan_tbl_entry *found; @@ -3925,10 +3917,10 @@ not_found: static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, enum switchdev_trans trans, __be32 dst, - int dst_len, struct fib_info *fi, u32 tb_id, - int flags) + int dst_len, const struct fib_info *fi, + u32 tb_id, int flags) { - struct fib_nh *nh; + const struct fib_nh *nh; __be16 eth_type = htons(ETH_P_IP); __be32 dst_mask = inet_make_mask(dst_len); __be16 internal_vlan_id = rocker_port->internal_vlan_id; @@ -4033,12 +4025,12 @@ static int rocker_port_stop(struct net_device *dev) return 0; } -static void rocker_tx_desc_frags_unmap(struct rocker_port *rocker_port, - struct rocker_desc_info *desc_info) +static void rocker_tx_desc_frags_unmap(const struct rocker_port *rocker_port, + const struct rocker_desc_info *desc_info) { - struct rocker *rocker = rocker_port->rocker; + const struct rocker *rocker = rocker_port->rocker; struct pci_dev *pdev = rocker->pdev; - struct rocker_tlv *attrs[ROCKER_TLV_TX_MAX + 1]; + const struct rocker_tlv *attrs[ROCKER_TLV_TX_MAX + 1]; struct rocker_tlv *attr; int rem; @@ -4046,7 +4038,7 @@ static void rocker_tx_desc_frags_unmap(struct rocker_port *rocker_port, if (!attrs[ROCKER_TLV_TX_FRAGS]) return; rocker_tlv_for_each_nested(attr, attrs[ROCKER_TLV_TX_FRAGS], rem) { - struct rocker_tlv *frag_attrs[ROCKER_TLV_TX_FRAG_ATTR_MAX + 1]; + const struct rocker_tlv *frag_attrs[ROCKER_TLV_TX_FRAG_ATTR_MAX + 1]; dma_addr_t dma_handle; size_t len; @@ -4063,11 +4055,11 @@ static void rocker_tx_desc_frags_unmap(struct rocker_port *rocker_port, } } -static int rocker_tx_desc_frag_map_put(struct rocker_port *rocker_port, +static int rocker_tx_desc_frag_map_put(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, char *buf, size_t buf_len) { - struct rocker *rocker = rocker_port->rocker; + const struct rocker *rocker = rocker_port->rocker; struct pci_dev *pdev = rocker->pdev; dma_addr_t dma_handle; struct rocker_tlv *frag; @@ -4172,35 +4164,6 @@ static int rocker_port_set_mac_address(struct net_device *dev, void *p) return 0; } -static int rocker_port_vlan_rx_add_vid(struct net_device *dev, - __be16 proto, u16 vid) -{ - struct rocker_port *rocker_port = netdev_priv(dev); - int err; - - err = rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, 0, vid); - if (err) - return err; - - return rocker_port_router_mac(rocker_port, SWITCHDEV_TRANS_NONE, - 0, htons(vid)); -} - -static int rocker_port_vlan_rx_kill_vid(struct net_device *dev, - __be16 proto, u16 vid) -{ - struct rocker_port *rocker_port = netdev_priv(dev); - int err; - - err = rocker_port_router_mac(rocker_port, SWITCHDEV_TRANS_NONE, - ROCKER_OP_FLAG_REMOVE, htons(vid)); - if (err) - return err; - - return rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, - ROCKER_OP_FLAG_REMOVE, vid); -} - static int rocker_port_get_phys_port_name(struct net_device *dev, char *buf, size_t len) { @@ -4208,8 +4171,7 @@ static int rocker_port_get_phys_port_name(struct net_device *dev, struct port_name name = { .buf = buf, .len = len }; int err; - err = rocker_cmd_exec(rocker_port->rocker, rocker_port, - SWITCHDEV_TRANS_NONE, + err = rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, rocker_cmd_get_port_settings_prep, NULL, rocker_cmd_get_port_settings_phys_name_proc, &name); @@ -4222,8 +4184,6 @@ static const struct net_device_ops rocker_port_netdev_ops = { .ndo_stop = rocker_port_stop, .ndo_start_xmit = rocker_port_xmit, .ndo_set_mac_address = rocker_port_set_mac_address, - .ndo_vlan_rx_add_vid = rocker_port_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = rocker_port_vlan_rx_kill_vid, .ndo_bridge_getlink = switchdev_port_bridge_getlink, .ndo_bridge_setlink = switchdev_port_bridge_setlink, .ndo_bridge_dellink = switchdev_port_bridge_dellink, @@ -4240,8 +4200,8 @@ static const struct net_device_ops rocker_port_netdev_ops = { static int rocker_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { - struct rocker_port *rocker_port = netdev_priv(dev); - struct rocker *rocker = rocker_port->rocker; + const struct rocker_port *rocker_port = netdev_priv(dev); + const struct rocker *rocker = rocker_port->rocker; switch (attr->id) { case SWITCHDEV_ATTR_PORT_PARENT_ID: @@ -4258,7 +4218,7 @@ static int rocker_port_attr_get(struct net_device *dev, return 0; } -static void rocker_port_trans_abort(struct rocker_port *rocker_port) +static void rocker_port_trans_abort(const struct rocker_port *rocker_port) { struct list_head *mem, *tmp; @@ -4331,12 +4291,17 @@ static int rocker_port_vlan_add(struct rocker_port *rocker_port, if (err) return err; - return rocker_port_router_mac(rocker_port, trans, 0, htons(vid)); + err = rocker_port_router_mac(rocker_port, trans, 0, htons(vid)); + if (err) + rocker_port_vlan(rocker_port, trans, + ROCKER_OP_FLAG_REMOVE, vid); + + return err; } static int rocker_port_vlans_add(struct rocker_port *rocker_port, enum switchdev_trans trans, - struct switchdev_obj_vlan *vlan) + const struct switchdev_obj_vlan *vlan) { u16 vid; int err; @@ -4353,7 +4318,7 @@ static int rocker_port_vlans_add(struct rocker_port *rocker_port, static int rocker_port_fdb_add(struct rocker_port *rocker_port, enum switchdev_trans trans, - struct switchdev_obj_fdb *fdb) + const struct switchdev_obj_fdb *fdb) { __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL); int flags = 0; @@ -4368,7 +4333,7 @@ static int rocker_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) { struct rocker_port *rocker_port = netdev_priv(dev); - struct switchdev_obj_ipv4_fib *fib4; + const struct switchdev_obj_ipv4_fib *fib4; int err = 0; switch (obj->trans) { @@ -4419,7 +4384,7 @@ static int rocker_port_vlan_del(struct rocker_port *rocker_port, } static int rocker_port_vlans_del(struct rocker_port *rocker_port, - struct switchdev_obj_vlan *vlan) + const struct switchdev_obj_vlan *vlan) { u16 vid; int err; @@ -4435,7 +4400,7 @@ static int rocker_port_vlans_del(struct rocker_port *rocker_port, static int rocker_port_fdb_del(struct rocker_port *rocker_port, enum switchdev_trans trans, - struct switchdev_obj_fdb *fdb) + const struct switchdev_obj_fdb *fdb) { __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL); int flags = ROCKER_OP_FLAG_REMOVE; @@ -4450,7 +4415,7 @@ static int rocker_port_obj_del(struct net_device *dev, struct switchdev_obj *obj) { struct rocker_port *rocker_port = netdev_priv(dev); - struct switchdev_obj_ipv4_fib *fib4; + const struct switchdev_obj_ipv4_fib *fib4; int err = 0; switch (obj->id) { @@ -4475,7 +4440,7 @@ static int rocker_port_obj_del(struct net_device *dev, return err; } -static int rocker_port_fdb_dump(struct rocker_port *rocker_port, +static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, struct switchdev_obj *obj) { struct rocker *rocker = rocker_port->rocker; @@ -4505,7 +4470,7 @@ static int rocker_port_fdb_dump(struct rocker_port *rocker_port, static int rocker_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj) { - struct rocker_port *rocker_port = netdev_priv(dev); + const struct rocker_port *rocker_port = netdev_priv(dev); int err = 0; switch (obj->id) { @@ -4589,8 +4554,7 @@ static void rocker_port_get_strings(struct net_device *netdev, u32 stringset, } static int -rocker_cmd_get_port_stats_prep(struct rocker *rocker, - struct rocker_port *rocker_port, +rocker_cmd_get_port_stats_prep(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { @@ -4614,14 +4578,13 @@ rocker_cmd_get_port_stats_prep(struct rocker *rocker, } static int -rocker_cmd_get_port_stats_ethtool_proc(struct rocker *rocker, - struct rocker_port *rocker_port, - struct rocker_desc_info *desc_info, +rocker_cmd_get_port_stats_ethtool_proc(const struct rocker_port *rocker_port, + const struct rocker_desc_info *desc_info, void *priv) { - struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; - struct rocker_tlv *stats_attrs[ROCKER_TLV_CMD_PORT_STATS_MAX + 1]; - struct rocker_tlv *pattr; + const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; + const struct rocker_tlv *stats_attrs[ROCKER_TLV_CMD_PORT_STATS_MAX + 1]; + const struct rocker_tlv *pattr; u32 pport; u64 *data = priv; int i; @@ -4655,8 +4618,7 @@ rocker_cmd_get_port_stats_ethtool_proc(struct rocker *rocker, static int rocker_cmd_get_port_stats_ethtool(struct rocker_port *rocker_port, void *priv) { - return rocker_cmd_exec(rocker_port->rocker, rocker_port, - SWITCHDEV_TRANS_NONE, + return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, rocker_cmd_get_port_stats_prep, NULL, rocker_cmd_get_port_stats_ethtool_proc, priv); @@ -4707,8 +4669,8 @@ static struct rocker_port *rocker_port_napi_tx_get(struct napi_struct *napi) static int rocker_port_poll_tx(struct napi_struct *napi, int budget) { struct rocker_port *rocker_port = rocker_port_napi_tx_get(napi); - struct rocker *rocker = rocker_port->rocker; - struct rocker_desc_info *desc_info; + const struct rocker *rocker = rocker_port->rocker; + const struct rocker_desc_info *desc_info; u32 credits = 0; int err; @@ -4743,11 +4705,11 @@ static int rocker_port_poll_tx(struct napi_struct *napi, int budget) return 0; } -static int rocker_port_rx_proc(struct rocker *rocker, - struct rocker_port *rocker_port, +static int rocker_port_rx_proc(const struct rocker *rocker, + const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info) { - struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1]; + const struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1]; struct sk_buff *skb = rocker_desc_cookie_ptr_get(desc_info); size_t rx_len; @@ -4769,7 +4731,7 @@ static int rocker_port_rx_proc(struct rocker *rocker, netif_receive_skb(skb); - return rocker_dma_rx_ring_skb_alloc(rocker, rocker_port, desc_info); + return rocker_dma_rx_ring_skb_alloc(rocker_port, desc_info); } static struct rocker_port *rocker_port_napi_rx_get(struct napi_struct *napi) @@ -4780,7 +4742,7 @@ static struct rocker_port *rocker_port_napi_rx_get(struct napi_struct *napi) static int rocker_port_poll_rx(struct napi_struct *napi, int budget) { struct rocker_port *rocker_port = rocker_port_napi_rx_get(napi); - struct rocker *rocker = rocker_port->rocker; + const struct rocker *rocker = rocker_port->rocker; struct rocker_desc_info *desc_info; u32 credits = 0; int err; @@ -4820,9 +4782,9 @@ static int rocker_port_poll_rx(struct napi_struct *napi, int budget) * PCI driver ops *****************/ -static void rocker_carrier_init(struct rocker_port *rocker_port) +static void rocker_carrier_init(const struct rocker_port *rocker_port) { - struct rocker *rocker = rocker_port->rocker; + const struct rocker *rocker = rocker_port->rocker; u64 link_status = rocker_read64(rocker, PORT_PHYS_LINK_STATUS); bool link_up; @@ -4833,7 +4795,7 @@ static void rocker_carrier_init(struct rocker_port *rocker_port) netif_carrier_off(rocker_port->dev); } -static void rocker_remove_ports(struct rocker *rocker) +static void rocker_remove_ports(const struct rocker *rocker) { struct rocker_port *rocker_port; int i; @@ -4847,10 +4809,10 @@ static void rocker_remove_ports(struct rocker *rocker) kfree(rocker->ports); } -static void rocker_port_dev_addr_init(struct rocker *rocker, - struct rocker_port *rocker_port) +static void rocker_port_dev_addr_init(struct rocker_port *rocker_port) { - struct pci_dev *pdev = rocker->pdev; + const struct rocker *rocker = rocker_port->rocker; + const struct pci_dev *pdev = rocker->pdev; int err; err = rocker_cmd_get_port_settings_macaddr(rocker_port, @@ -4863,9 +4825,10 @@ static void rocker_port_dev_addr_init(struct rocker *rocker, static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) { - struct pci_dev *pdev = rocker->pdev; + const struct pci_dev *pdev = rocker->pdev; struct rocker_port *rocker_port; struct net_device *dev; + u16 untagged_vid = 0; int err; dev = alloc_etherdev(sizeof(struct rocker_port)); @@ -4879,7 +4842,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) rocker_port->brport_flags = BR_LEARNING | BR_LEARNING_SYNC; INIT_LIST_HEAD(&rocker_port->trans_mem); - rocker_port_dev_addr_init(rocker, rocker_port); + rocker_port_dev_addr_init(rocker_port); dev->netdev_ops = &rocker_port_netdev_ops; dev->ethtool_ops = &rocker_port_ethtool_ops; dev->switchdev_ops = &rocker_port_switchdev_ops; @@ -4889,8 +4852,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) NAPI_POLL_WEIGHT); rocker_carrier_init(rocker_port); - dev->features |= NETIF_F_NETNS_LOCAL | - NETIF_F_HW_VLAN_CTAG_FILTER; + dev->features |= NETIF_F_NETNS_LOCAL; err = register_netdev(dev); if (err) { @@ -4901,16 +4863,27 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) rocker_port_set_learning(rocker_port, SWITCHDEV_TRANS_NONE); - rocker_port->internal_vlan_id = - rocker_port_internal_vlan_id_get(rocker_port, dev->ifindex); err = rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE, 0); if (err) { dev_err(&pdev->dev, "install ig port table failed\n"); goto err_port_ig_tbl; } + rocker_port->internal_vlan_id = + rocker_port_internal_vlan_id_get(rocker_port, dev->ifindex); + + err = rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE, + untagged_vid, 0); + if (err) { + netdev_err(rocker_port->dev, "install untagged VLAN failed\n"); + goto err_untagged_vlan; + } + return 0; +err_untagged_vlan: + rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE, + ROCKER_OP_FLAG_REMOVE); err_port_ig_tbl: unregister_netdev(dev); err_register_netdev: @@ -4925,7 +4898,7 @@ static int rocker_probe_ports(struct rocker *rocker) int err; alloc_size = sizeof(struct rocker_port *) * rocker->port_count; - rocker->ports = kmalloc(alloc_size, GFP_KERNEL); + rocker->ports = kzalloc(alloc_size, GFP_KERNEL); if (!rocker->ports) return -ENOMEM; for (i = 0; i < rocker->port_count; i++) { @@ -4974,7 +4947,7 @@ err_enable_msix: return err; } -static void rocker_msix_fini(struct rocker *rocker) +static void rocker_msix_fini(const struct rocker *rocker) { pci_disable_msix(rocker->pdev); kfree(rocker->msix_entries); @@ -5140,7 +5113,7 @@ static struct pci_driver rocker_pci_driver = { * Net device notifier event handler ************************************/ -static bool rocker_port_dev_check(struct net_device *dev) +static bool rocker_port_dev_check(const struct net_device *dev) { return dev->netdev_ops == &rocker_port_netdev_ops; } @@ -5148,41 +5121,49 @@ static bool rocker_port_dev_check(struct net_device *dev) static int rocker_port_bridge_join(struct rocker_port *rocker_port, struct net_device *bridge) { + u16 untagged_vid = 0; int err; - rocker_port_internal_vlan_id_put(rocker_port, - rocker_port->dev->ifindex); - - rocker_port->bridge_dev = bridge; + /* Port is joining bridge, so the internal VLAN for the + * port is going to change to the bridge internal VLAN. + * Let's remove untagged VLAN (vid=0) from port and + * re-add once internal VLAN has changed. + */ - /* Use bridge internal VLAN ID for untagged pkts */ - err = rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, - ROCKER_OP_FLAG_REMOVE, 0); + err = rocker_port_vlan_del(rocker_port, untagged_vid, 0); if (err) return err; + + rocker_port_internal_vlan_id_put(rocker_port, + rocker_port->dev->ifindex); rocker_port->internal_vlan_id = rocker_port_internal_vlan_id_get(rocker_port, bridge->ifindex); - return rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, 0, 0); + + rocker_port->bridge_dev = bridge; + + return rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE, + untagged_vid, 0); } static int rocker_port_bridge_leave(struct rocker_port *rocker_port) { + u16 untagged_vid = 0; int err; - rocker_port_internal_vlan_id_put(rocker_port, - rocker_port->bridge_dev->ifindex); - - rocker_port->bridge_dev = NULL; - - /* Use port internal VLAN ID for untagged pkts */ - err = rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, - ROCKER_OP_FLAG_REMOVE, 0); + err = rocker_port_vlan_del(rocker_port, untagged_vid, 0); if (err) return err; + + rocker_port_internal_vlan_id_put(rocker_port, + rocker_port->bridge_dev->ifindex); rocker_port->internal_vlan_id = rocker_port_internal_vlan_id_get(rocker_port, rocker_port->dev->ifindex); - err = rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, 0, 0); + + rocker_port->bridge_dev = NULL; + + err = rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE, + untagged_vid, 0); if (err) return err; diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig index 0889212..4dd92b7 100644 --- a/drivers/net/ethernet/sfc/Kconfig +++ b/drivers/net/ethernet/sfc/Kconfig @@ -36,3 +36,12 @@ config SFC_SRIOV This enables support for the SFC9000 I/O Virtualization features, allowing accelerated network performance in virtualized environments. +config SFC_MCDI_LOGGING + bool "Solarflare SFC9000/SFC9100-family MCDI logging support" + depends on SFC + default y + ---help--- + This enables support for tracing of MCDI (Management-Controller-to- + Driver-Interface) commands and responses, allowing debugging of + driver/firmware interaction. The tracing is actually enabled by + a sysfs file 'mcdi_logging' under the PCI device. diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index a547ceb..8476434 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -246,9 +246,38 @@ static int efx_ef10_get_mac_address_vf(struct efx_nic *efx, u8 *mac_address) return 0; } +static ssize_t efx_ef10_show_link_control_flag(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + + return sprintf(buf, "%d\n", + ((efx->mcdi->fn_flags) & + (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL)) + ? 1 : 0); +} + +static ssize_t efx_ef10_show_primary_flag(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + + return sprintf(buf, "%d\n", + ((efx->mcdi->fn_flags) & + (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY)) + ? 1 : 0); +} + +static DEVICE_ATTR(link_control_flag, 0444, efx_ef10_show_link_control_flag, + NULL); +static DEVICE_ATTR(primary_flag, 0444, efx_ef10_show_primary_flag, NULL); + static int efx_ef10_probe(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data; + struct net_device *net_dev = efx->net_dev; int i, rc; /* We can have one VI for each 8K region. However, until we @@ -267,6 +296,9 @@ static int efx_ef10_probe(struct efx_nic *efx) return -ENOMEM; efx->nic_data = nic_data; + /* we assume later that we can copy from this buffer in dwords */ + BUILD_BUG_ON(MCDI_CTL_SDU_LEN_MAX_V2 % 4); + rc = efx_nic_alloc_buffer(efx, &nic_data->mcdi_buf, 8 + MCDI_CTL_SDU_LEN_MAX_V2, GFP_KERNEL); if (rc) @@ -311,29 +343,39 @@ static int efx_ef10_probe(struct efx_nic *efx) if (rc) goto fail3; - rc = efx_ef10_get_pf_index(efx); + rc = device_create_file(&efx->pci_dev->dev, + &dev_attr_link_control_flag); if (rc) goto fail3; + rc = device_create_file(&efx->pci_dev->dev, &dev_attr_primary_flag); + if (rc) + goto fail4; + + rc = efx_ef10_get_pf_index(efx); + if (rc) + goto fail5; + rc = efx_ef10_init_datapath_caps(efx); if (rc < 0) - goto fail3; + goto fail5; efx->rx_packet_len_offset = ES_DZ_RX_PREFIX_PKTLEN_OFST - ES_DZ_RX_PREFIX_SIZE; rc = efx_mcdi_port_get_number(efx); if (rc < 0) - goto fail3; + goto fail5; efx->port_num = rc; + net_dev->dev_port = rc; rc = efx->type->get_mac_address(efx, efx->net_dev->perm_addr); if (rc) - goto fail3; + goto fail5; rc = efx_ef10_get_sysclk_freq(efx); if (rc < 0) - goto fail3; + goto fail5; efx->timer_quantum_ns = 1536000 / rc; /* 1536 cycles */ /* Check whether firmware supports bug 35388 workaround. @@ -341,9 +383,9 @@ static int efx_ef10_probe(struct efx_nic *efx) * ask if it's already enabled */ rc = efx_mcdi_set_workaround(efx, MC_CMD_WORKAROUND_BUG35388, true); - if (rc == 0) + if (rc == 0) { nic_data->workaround_35388 = true; - else if (rc == -EPERM) { + } else if (rc == -EPERM) { unsigned int enabled; rc = efx_mcdi_get_workarounds(efx, NULL, &enabled); @@ -351,21 +393,35 @@ static int efx_ef10_probe(struct efx_nic *efx) goto fail3; nic_data->workaround_35388 = enabled & MC_CMD_GET_WORKAROUNDS_OUT_BUG35388; + } else if (rc != -ENOSYS && rc != -ENOENT) { + goto fail5; } - else if (rc != -ENOSYS && rc != -ENOENT) - goto fail3; netif_dbg(efx, probe, efx->net_dev, "workaround for bug 35388 is %sabled\n", nic_data->workaround_35388 ? "en" : "dis"); rc = efx_mcdi_mon_probe(efx); if (rc && rc != -EPERM) - goto fail3; + goto fail5; efx_ptp_probe(efx, NULL); +#ifdef CONFIG_SFC_SRIOV + if ((efx->pci_dev->physfn) && (!efx->pci_dev->is_physfn)) { + struct pci_dev *pci_dev_pf = efx->pci_dev->physfn; + struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf); + + efx_pf->type->get_mac_address(efx_pf, nic_data->port_id); + } else +#endif + ether_addr_copy(nic_data->port_id, efx->net_dev->perm_addr); + return 0; +fail5: + device_remove_file(&efx->pci_dev->dev, &dev_attr_primary_flag); +fail4: + device_remove_file(&efx->pci_dev->dev, &dev_attr_link_control_flag); fail3: efx_mcdi_fini(efx); fail2: @@ -608,6 +664,9 @@ static void efx_ef10_remove(struct efx_nic *efx) if (!nic_data->must_restore_piobufs) efx_ef10_free_piobufs(efx); + device_remove_file(&efx->pci_dev->dev, &dev_attr_primary_flag); + device_remove_file(&efx->pci_dev->dev, &dev_attr_link_control_flag); + efx_mcdi_fini(efx); efx_nic_free_buffer(efx, &nic_data->mcdi_buf); kfree(nic_data); @@ -622,6 +681,24 @@ static int efx_ef10_probe_pf(struct efx_nic *efx) static int efx_ef10_probe_vf(struct efx_nic *efx) { int rc; + struct pci_dev *pci_dev_pf; + + /* If the parent PF has no VF data structure, it doesn't know about this + * VF so fail probe. The VF needs to be re-created. This can happen + * if the PF driver is unloaded while the VF is assigned to a guest. + */ + pci_dev_pf = efx->pci_dev->physfn; + if (pci_dev_pf) { + struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf); + struct efx_ef10_nic_data *nic_data_pf = efx_pf->nic_data; + + if (!nic_data_pf->vf) { + netif_info(efx, drv, efx->net_dev, + "The VF cannot link to its parent PF; " + "please destroy and re-create the VF\n"); + return -EBUSY; + } + } rc = efx_ef10_probe(efx); if (rc) @@ -639,6 +716,8 @@ static int efx_ef10_probe_vf(struct efx_nic *efx) struct efx_ef10_nic_data *nic_data = efx->nic_data; nic_data_p->vf[nic_data->vf_index].efx = efx; + nic_data_p->vf[nic_data->vf_index].pci_dev = + efx->pci_dev; } else netif_info(efx, drv, efx->net_dev, "Could not get the PF id from VF\n"); @@ -932,93 +1011,112 @@ static int efx_ef10_reset(struct efx_nic *efx, enum reset_type reset_type) [GENERIC_STAT_ ## ext_name] = { #ext_name, 0, 0 } static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = { - EF10_DMA_STAT(tx_bytes, TX_BYTES), - EF10_DMA_STAT(tx_packets, TX_PKTS), - EF10_DMA_STAT(tx_pause, TX_PAUSE_PKTS), - EF10_DMA_STAT(tx_control, TX_CONTROL_PKTS), - EF10_DMA_STAT(tx_unicast, TX_UNICAST_PKTS), - EF10_DMA_STAT(tx_multicast, TX_MULTICAST_PKTS), - EF10_DMA_STAT(tx_broadcast, TX_BROADCAST_PKTS), - EF10_DMA_STAT(tx_lt64, TX_LT64_PKTS), - EF10_DMA_STAT(tx_64, TX_64_PKTS), - EF10_DMA_STAT(tx_65_to_127, TX_65_TO_127_PKTS), - EF10_DMA_STAT(tx_128_to_255, TX_128_TO_255_PKTS), - EF10_DMA_STAT(tx_256_to_511, TX_256_TO_511_PKTS), - EF10_DMA_STAT(tx_512_to_1023, TX_512_TO_1023_PKTS), - EF10_DMA_STAT(tx_1024_to_15xx, TX_1024_TO_15XX_PKTS), - EF10_DMA_STAT(tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS), - EF10_DMA_STAT(rx_bytes, RX_BYTES), - EF10_DMA_INVIS_STAT(rx_bytes_minus_good_bytes, RX_BAD_BYTES), - EF10_OTHER_STAT(rx_good_bytes), - EF10_OTHER_STAT(rx_bad_bytes), - EF10_DMA_STAT(rx_packets, RX_PKTS), - EF10_DMA_STAT(rx_good, RX_GOOD_PKTS), - EF10_DMA_STAT(rx_bad, RX_BAD_FCS_PKTS), - EF10_DMA_STAT(rx_pause, RX_PAUSE_PKTS), - EF10_DMA_STAT(rx_control, RX_CONTROL_PKTS), - EF10_DMA_STAT(rx_unicast, RX_UNICAST_PKTS), - EF10_DMA_STAT(rx_multicast, RX_MULTICAST_PKTS), - EF10_DMA_STAT(rx_broadcast, RX_BROADCAST_PKTS), - EF10_DMA_STAT(rx_lt64, RX_UNDERSIZE_PKTS), - EF10_DMA_STAT(rx_64, RX_64_PKTS), - EF10_DMA_STAT(rx_65_to_127, RX_65_TO_127_PKTS), - EF10_DMA_STAT(rx_128_to_255, RX_128_TO_255_PKTS), - EF10_DMA_STAT(rx_256_to_511, RX_256_TO_511_PKTS), - EF10_DMA_STAT(rx_512_to_1023, RX_512_TO_1023_PKTS), - EF10_DMA_STAT(rx_1024_to_15xx, RX_1024_TO_15XX_PKTS), - EF10_DMA_STAT(rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS), - EF10_DMA_STAT(rx_gtjumbo, RX_GTJUMBO_PKTS), - EF10_DMA_STAT(rx_bad_gtjumbo, RX_JABBER_PKTS), - EF10_DMA_STAT(rx_overflow, RX_OVERFLOW_PKTS), - EF10_DMA_STAT(rx_align_error, RX_ALIGN_ERROR_PKTS), - EF10_DMA_STAT(rx_length_error, RX_LENGTH_ERROR_PKTS), - EF10_DMA_STAT(rx_nodesc_drops, RX_NODESC_DROPS), + EF10_DMA_STAT(port_tx_bytes, TX_BYTES), + EF10_DMA_STAT(port_tx_packets, TX_PKTS), + EF10_DMA_STAT(port_tx_pause, TX_PAUSE_PKTS), + EF10_DMA_STAT(port_tx_control, TX_CONTROL_PKTS), + EF10_DMA_STAT(port_tx_unicast, TX_UNICAST_PKTS), + EF10_DMA_STAT(port_tx_multicast, TX_MULTICAST_PKTS), + EF10_DMA_STAT(port_tx_broadcast, TX_BROADCAST_PKTS), + EF10_DMA_STAT(port_tx_lt64, TX_LT64_PKTS), + EF10_DMA_STAT(port_tx_64, TX_64_PKTS), + EF10_DMA_STAT(port_tx_65_to_127, TX_65_TO_127_PKTS), + EF10_DMA_STAT(port_tx_128_to_255, TX_128_TO_255_PKTS), + EF10_DMA_STAT(port_tx_256_to_511, TX_256_TO_511_PKTS), + EF10_DMA_STAT(port_tx_512_to_1023, TX_512_TO_1023_PKTS), + EF10_DMA_STAT(port_tx_1024_to_15xx, TX_1024_TO_15XX_PKTS), + EF10_DMA_STAT(port_tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS), + EF10_DMA_STAT(port_rx_bytes, RX_BYTES), + EF10_DMA_INVIS_STAT(port_rx_bytes_minus_good_bytes, RX_BAD_BYTES), + EF10_OTHER_STAT(port_rx_good_bytes), + EF10_OTHER_STAT(port_rx_bad_bytes), + EF10_DMA_STAT(port_rx_packets, RX_PKTS), + EF10_DMA_STAT(port_rx_good, RX_GOOD_PKTS), + EF10_DMA_STAT(port_rx_bad, RX_BAD_FCS_PKTS), + EF10_DMA_STAT(port_rx_pause, RX_PAUSE_PKTS), + EF10_DMA_STAT(port_rx_control, RX_CONTROL_PKTS), + EF10_DMA_STAT(port_rx_unicast, RX_UNICAST_PKTS), + EF10_DMA_STAT(port_rx_multicast, RX_MULTICAST_PKTS), + EF10_DMA_STAT(port_rx_broadcast, RX_BROADCAST_PKTS), + EF10_DMA_STAT(port_rx_lt64, RX_UNDERSIZE_PKTS), + EF10_DMA_STAT(port_rx_64, RX_64_PKTS), + EF10_DMA_STAT(port_rx_65_to_127, RX_65_TO_127_PKTS), + EF10_DMA_STAT(port_rx_128_to_255, RX_128_TO_255_PKTS), + EF10_DMA_STAT(port_rx_256_to_511, RX_256_TO_511_PKTS), + EF10_DMA_STAT(port_rx_512_to_1023, RX_512_TO_1023_PKTS), + EF10_DMA_STAT(port_rx_1024_to_15xx, RX_1024_TO_15XX_PKTS), + EF10_DMA_STAT(port_rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS), + EF10_DMA_STAT(port_rx_gtjumbo, RX_GTJUMBO_PKTS), + EF10_DMA_STAT(port_rx_bad_gtjumbo, RX_JABBER_PKTS), + EF10_DMA_STAT(port_rx_overflow, RX_OVERFLOW_PKTS), + EF10_DMA_STAT(port_rx_align_error, RX_ALIGN_ERROR_PKTS), + EF10_DMA_STAT(port_rx_length_error, RX_LENGTH_ERROR_PKTS), + EF10_DMA_STAT(port_rx_nodesc_drops, RX_NODESC_DROPS), GENERIC_SW_STAT(rx_nodesc_trunc), GENERIC_SW_STAT(rx_noskb_drops), - EF10_DMA_STAT(rx_pm_trunc_bb_overflow, PM_TRUNC_BB_OVERFLOW), - EF10_DMA_STAT(rx_pm_discard_bb_overflow, PM_DISCARD_BB_OVERFLOW), - EF10_DMA_STAT(rx_pm_trunc_vfifo_full, PM_TRUNC_VFIFO_FULL), - EF10_DMA_STAT(rx_pm_discard_vfifo_full, PM_DISCARD_VFIFO_FULL), - EF10_DMA_STAT(rx_pm_trunc_qbb, PM_TRUNC_QBB), - EF10_DMA_STAT(rx_pm_discard_qbb, PM_DISCARD_QBB), - EF10_DMA_STAT(rx_pm_discard_mapping, PM_DISCARD_MAPPING), - EF10_DMA_STAT(rx_dp_q_disabled_packets, RXDP_Q_DISABLED_PKTS), - EF10_DMA_STAT(rx_dp_di_dropped_packets, RXDP_DI_DROPPED_PKTS), - EF10_DMA_STAT(rx_dp_streaming_packets, RXDP_STREAMING_PKTS), - EF10_DMA_STAT(rx_dp_hlb_fetch, RXDP_EMERGENCY_FETCH_CONDITIONS), - EF10_DMA_STAT(rx_dp_hlb_wait, RXDP_EMERGENCY_WAIT_CONDITIONS), + EF10_DMA_STAT(port_rx_pm_trunc_bb_overflow, PM_TRUNC_BB_OVERFLOW), + EF10_DMA_STAT(port_rx_pm_discard_bb_overflow, PM_DISCARD_BB_OVERFLOW), + EF10_DMA_STAT(port_rx_pm_trunc_vfifo_full, PM_TRUNC_VFIFO_FULL), + EF10_DMA_STAT(port_rx_pm_discard_vfifo_full, PM_DISCARD_VFIFO_FULL), + EF10_DMA_STAT(port_rx_pm_trunc_qbb, PM_TRUNC_QBB), + EF10_DMA_STAT(port_rx_pm_discard_qbb, PM_DISCARD_QBB), + EF10_DMA_STAT(port_rx_pm_discard_mapping, PM_DISCARD_MAPPING), + EF10_DMA_STAT(port_rx_dp_q_disabled_packets, RXDP_Q_DISABLED_PKTS), + EF10_DMA_STAT(port_rx_dp_di_dropped_packets, RXDP_DI_DROPPED_PKTS), + EF10_DMA_STAT(port_rx_dp_streaming_packets, RXDP_STREAMING_PKTS), + EF10_DMA_STAT(port_rx_dp_hlb_fetch, RXDP_HLB_FETCH_CONDITIONS), + EF10_DMA_STAT(port_rx_dp_hlb_wait, RXDP_HLB_WAIT_CONDITIONS), + EF10_DMA_STAT(rx_unicast, VADAPTER_RX_UNICAST_PACKETS), + EF10_DMA_STAT(rx_unicast_bytes, VADAPTER_RX_UNICAST_BYTES), + EF10_DMA_STAT(rx_multicast, VADAPTER_RX_MULTICAST_PACKETS), + EF10_DMA_STAT(rx_multicast_bytes, VADAPTER_RX_MULTICAST_BYTES), + EF10_DMA_STAT(rx_broadcast, VADAPTER_RX_BROADCAST_PACKETS), + EF10_DMA_STAT(rx_broadcast_bytes, VADAPTER_RX_BROADCAST_BYTES), + EF10_DMA_STAT(rx_bad, VADAPTER_RX_BAD_PACKETS), + EF10_DMA_STAT(rx_bad_bytes, VADAPTER_RX_BAD_BYTES), + EF10_DMA_STAT(rx_overflow, VADAPTER_RX_OVERFLOW), + EF10_DMA_STAT(tx_unicast, VADAPTER_TX_UNICAST_PACKETS), + EF10_DMA_STAT(tx_unicast_bytes, VADAPTER_TX_UNICAST_BYTES), + EF10_DMA_STAT(tx_multicast, VADAPTER_TX_MULTICAST_PACKETS), + EF10_DMA_STAT(tx_multicast_bytes, VADAPTER_TX_MULTICAST_BYTES), + EF10_DMA_STAT(tx_broadcast, VADAPTER_TX_BROADCAST_PACKETS), + EF10_DMA_STAT(tx_broadcast_bytes, VADAPTER_TX_BROADCAST_BYTES), + EF10_DMA_STAT(tx_bad, VADAPTER_TX_BAD_PACKETS), + EF10_DMA_STAT(tx_bad_bytes, VADAPTER_TX_BAD_BYTES), + EF10_DMA_STAT(tx_overflow, VADAPTER_TX_OVERFLOW), }; -#define HUNT_COMMON_STAT_MASK ((1ULL << EF10_STAT_tx_bytes) | \ - (1ULL << EF10_STAT_tx_packets) | \ - (1ULL << EF10_STAT_tx_pause) | \ - (1ULL << EF10_STAT_tx_unicast) | \ - (1ULL << EF10_STAT_tx_multicast) | \ - (1ULL << EF10_STAT_tx_broadcast) | \ - (1ULL << EF10_STAT_rx_bytes) | \ - (1ULL << EF10_STAT_rx_bytes_minus_good_bytes) | \ - (1ULL << EF10_STAT_rx_good_bytes) | \ - (1ULL << EF10_STAT_rx_bad_bytes) | \ - (1ULL << EF10_STAT_rx_packets) | \ - (1ULL << EF10_STAT_rx_good) | \ - (1ULL << EF10_STAT_rx_bad) | \ - (1ULL << EF10_STAT_rx_pause) | \ - (1ULL << EF10_STAT_rx_control) | \ - (1ULL << EF10_STAT_rx_unicast) | \ - (1ULL << EF10_STAT_rx_multicast) | \ - (1ULL << EF10_STAT_rx_broadcast) | \ - (1ULL << EF10_STAT_rx_lt64) | \ - (1ULL << EF10_STAT_rx_64) | \ - (1ULL << EF10_STAT_rx_65_to_127) | \ - (1ULL << EF10_STAT_rx_128_to_255) | \ - (1ULL << EF10_STAT_rx_256_to_511) | \ - (1ULL << EF10_STAT_rx_512_to_1023) | \ - (1ULL << EF10_STAT_rx_1024_to_15xx) | \ - (1ULL << EF10_STAT_rx_15xx_to_jumbo) | \ - (1ULL << EF10_STAT_rx_gtjumbo) | \ - (1ULL << EF10_STAT_rx_bad_gtjumbo) | \ - (1ULL << EF10_STAT_rx_overflow) | \ - (1ULL << EF10_STAT_rx_nodesc_drops) | \ +#define HUNT_COMMON_STAT_MASK ((1ULL << EF10_STAT_port_tx_bytes) | \ + (1ULL << EF10_STAT_port_tx_packets) | \ + (1ULL << EF10_STAT_port_tx_pause) | \ + (1ULL << EF10_STAT_port_tx_unicast) | \ + (1ULL << EF10_STAT_port_tx_multicast) | \ + (1ULL << EF10_STAT_port_tx_broadcast) | \ + (1ULL << EF10_STAT_port_rx_bytes) | \ + (1ULL << \ + EF10_STAT_port_rx_bytes_minus_good_bytes) | \ + (1ULL << EF10_STAT_port_rx_good_bytes) | \ + (1ULL << EF10_STAT_port_rx_bad_bytes) | \ + (1ULL << EF10_STAT_port_rx_packets) | \ + (1ULL << EF10_STAT_port_rx_good) | \ + (1ULL << EF10_STAT_port_rx_bad) | \ + (1ULL << EF10_STAT_port_rx_pause) | \ + (1ULL << EF10_STAT_port_rx_control) | \ + (1ULL << EF10_STAT_port_rx_unicast) | \ + (1ULL << EF10_STAT_port_rx_multicast) | \ + (1ULL << EF10_STAT_port_rx_broadcast) | \ + (1ULL << EF10_STAT_port_rx_lt64) | \ + (1ULL << EF10_STAT_port_rx_64) | \ + (1ULL << EF10_STAT_port_rx_65_to_127) | \ + (1ULL << EF10_STAT_port_rx_128_to_255) | \ + (1ULL << EF10_STAT_port_rx_256_to_511) | \ + (1ULL << EF10_STAT_port_rx_512_to_1023) |\ + (1ULL << EF10_STAT_port_rx_1024_to_15xx) |\ + (1ULL << EF10_STAT_port_rx_15xx_to_jumbo) |\ + (1ULL << EF10_STAT_port_rx_gtjumbo) | \ + (1ULL << EF10_STAT_port_rx_bad_gtjumbo) |\ + (1ULL << EF10_STAT_port_rx_overflow) | \ + (1ULL << EF10_STAT_port_rx_nodesc_drops) |\ (1ULL << GENERIC_STAT_rx_nodesc_trunc) | \ (1ULL << GENERIC_STAT_rx_noskb_drops)) @@ -1026,39 +1124,39 @@ static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = { * switchable port we do not expose these because they might not * include all the packets they should. */ -#define HUNT_10G_ONLY_STAT_MASK ((1ULL << EF10_STAT_tx_control) | \ - (1ULL << EF10_STAT_tx_lt64) | \ - (1ULL << EF10_STAT_tx_64) | \ - (1ULL << EF10_STAT_tx_65_to_127) | \ - (1ULL << EF10_STAT_tx_128_to_255) | \ - (1ULL << EF10_STAT_tx_256_to_511) | \ - (1ULL << EF10_STAT_tx_512_to_1023) | \ - (1ULL << EF10_STAT_tx_1024_to_15xx) | \ - (1ULL << EF10_STAT_tx_15xx_to_jumbo)) +#define HUNT_10G_ONLY_STAT_MASK ((1ULL << EF10_STAT_port_tx_control) | \ + (1ULL << EF10_STAT_port_tx_lt64) | \ + (1ULL << EF10_STAT_port_tx_64) | \ + (1ULL << EF10_STAT_port_tx_65_to_127) |\ + (1ULL << EF10_STAT_port_tx_128_to_255) |\ + (1ULL << EF10_STAT_port_tx_256_to_511) |\ + (1ULL << EF10_STAT_port_tx_512_to_1023) |\ + (1ULL << EF10_STAT_port_tx_1024_to_15xx) |\ + (1ULL << EF10_STAT_port_tx_15xx_to_jumbo)) /* These statistics are only provided by the 40G MAC. For a 10G/40G * switchable port we do expose these because the errors will otherwise * be silent. */ -#define HUNT_40G_EXTRA_STAT_MASK ((1ULL << EF10_STAT_rx_align_error) | \ - (1ULL << EF10_STAT_rx_length_error)) +#define HUNT_40G_EXTRA_STAT_MASK ((1ULL << EF10_STAT_port_rx_align_error) |\ + (1ULL << EF10_STAT_port_rx_length_error)) /* These statistics are only provided if the firmware supports the * capability PM_AND_RXDP_COUNTERS. */ #define HUNT_PM_AND_RXDP_STAT_MASK ( \ - (1ULL << EF10_STAT_rx_pm_trunc_bb_overflow) | \ - (1ULL << EF10_STAT_rx_pm_discard_bb_overflow) | \ - (1ULL << EF10_STAT_rx_pm_trunc_vfifo_full) | \ - (1ULL << EF10_STAT_rx_pm_discard_vfifo_full) | \ - (1ULL << EF10_STAT_rx_pm_trunc_qbb) | \ - (1ULL << EF10_STAT_rx_pm_discard_qbb) | \ - (1ULL << EF10_STAT_rx_pm_discard_mapping) | \ - (1ULL << EF10_STAT_rx_dp_q_disabled_packets) | \ - (1ULL << EF10_STAT_rx_dp_di_dropped_packets) | \ - (1ULL << EF10_STAT_rx_dp_streaming_packets) | \ - (1ULL << EF10_STAT_rx_dp_hlb_fetch) | \ - (1ULL << EF10_STAT_rx_dp_hlb_wait)) + (1ULL << EF10_STAT_port_rx_pm_trunc_bb_overflow) | \ + (1ULL << EF10_STAT_port_rx_pm_discard_bb_overflow) | \ + (1ULL << EF10_STAT_port_rx_pm_trunc_vfifo_full) | \ + (1ULL << EF10_STAT_port_rx_pm_discard_vfifo_full) | \ + (1ULL << EF10_STAT_port_rx_pm_trunc_qbb) | \ + (1ULL << EF10_STAT_port_rx_pm_discard_qbb) | \ + (1ULL << EF10_STAT_port_rx_pm_discard_mapping) | \ + (1ULL << EF10_STAT_port_rx_dp_q_disabled_packets) | \ + (1ULL << EF10_STAT_port_rx_dp_di_dropped_packets) | \ + (1ULL << EF10_STAT_port_rx_dp_streaming_packets) | \ + (1ULL << EF10_STAT_port_rx_dp_hlb_fetch) | \ + (1ULL << EF10_STAT_port_rx_dp_hlb_wait)) static u64 efx_ef10_raw_stat_mask(struct efx_nic *efx) { @@ -1066,6 +1164,10 @@ static u64 efx_ef10_raw_stat_mask(struct efx_nic *efx) u32 port_caps = efx_mcdi_phy_get_caps(efx); struct efx_ef10_nic_data *nic_data = efx->nic_data; + if (!(efx->mcdi->fn_flags & + 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL)) + return 0; + if (port_caps & (1 << MC_CMD_PHY_CAP_40000FDX_LBN)) raw_mask |= HUNT_40G_EXTRA_STAT_MASK; else @@ -1080,13 +1182,28 @@ static u64 efx_ef10_raw_stat_mask(struct efx_nic *efx) static void efx_ef10_get_stat_mask(struct efx_nic *efx, unsigned long *mask) { - u64 raw_mask = efx_ef10_raw_stat_mask(efx); + struct efx_ef10_nic_data *nic_data = efx->nic_data; + u64 raw_mask[2]; + + raw_mask[0] = efx_ef10_raw_stat_mask(efx); + + /* Only show vadaptor stats when EVB capability is present */ + if (nic_data->datapath_caps & + (1 << MC_CMD_GET_CAPABILITIES_OUT_EVB_LBN)) { + raw_mask[0] |= ~((1ULL << EF10_STAT_rx_unicast) - 1); + raw_mask[1] = (1ULL << (EF10_STAT_COUNT - 63)) - 1; + } else { + raw_mask[1] = 0; + } #if BITS_PER_LONG == 64 - mask[0] = raw_mask; + mask[0] = raw_mask[0]; + mask[1] = raw_mask[1]; #else - mask[0] = raw_mask & 0xffffffff; - mask[1] = raw_mask >> 32; + mask[0] = raw_mask[0] & 0xffffffff; + mask[1] = raw_mask[0] >> 32; + mask[2] = raw_mask[1] & 0xffffffff; + mask[3] = raw_mask[1] >> 32; #endif } @@ -1099,7 +1216,51 @@ static size_t efx_ef10_describe_stats(struct efx_nic *efx, u8 *names) mask, names); } -static int efx_ef10_try_update_nic_stats(struct efx_nic *efx) +static size_t efx_ef10_update_stats_common(struct efx_nic *efx, u64 *full_stats, + struct rtnl_link_stats64 *core_stats) +{ + DECLARE_BITMAP(mask, EF10_STAT_COUNT); + struct efx_ef10_nic_data *nic_data = efx->nic_data; + u64 *stats = nic_data->stats; + size_t stats_count = 0, index; + + efx_ef10_get_stat_mask(efx, mask); + + if (full_stats) { + for_each_set_bit(index, mask, EF10_STAT_COUNT) { + if (efx_ef10_stat_desc[index].name) { + *full_stats++ = stats[index]; + ++stats_count; + } + } + } + + if (core_stats) { + core_stats->rx_packets = stats[EF10_STAT_rx_unicast] + + stats[EF10_STAT_rx_multicast] + + stats[EF10_STAT_rx_broadcast]; + core_stats->tx_packets = stats[EF10_STAT_tx_unicast] + + stats[EF10_STAT_tx_multicast] + + stats[EF10_STAT_tx_broadcast]; + core_stats->rx_bytes = stats[EF10_STAT_rx_unicast_bytes] + + stats[EF10_STAT_rx_multicast_bytes] + + stats[EF10_STAT_rx_broadcast_bytes]; + core_stats->tx_bytes = stats[EF10_STAT_tx_unicast_bytes] + + stats[EF10_STAT_tx_multicast_bytes] + + stats[EF10_STAT_tx_broadcast_bytes]; + core_stats->rx_dropped = stats[GENERIC_STAT_rx_nodesc_trunc] + + stats[GENERIC_STAT_rx_noskb_drops]; + core_stats->multicast = stats[EF10_STAT_rx_multicast]; + core_stats->rx_crc_errors = stats[EF10_STAT_rx_bad]; + core_stats->rx_fifo_errors = stats[EF10_STAT_rx_overflow]; + core_stats->rx_errors = core_stats->rx_crc_errors; + core_stats->tx_errors = stats[EF10_STAT_tx_bad]; + } + + return stats_count; +} + +static int efx_ef10_try_update_nic_stats_pf(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; DECLARE_BITMAP(mask, EF10_STAT_COUNT); @@ -1124,67 +1285,114 @@ static int efx_ef10_try_update_nic_stats(struct efx_nic *efx) return -EAGAIN; /* Update derived statistics */ - efx_nic_fix_nodesc_drop_stat(efx, &stats[EF10_STAT_rx_nodesc_drops]); - stats[EF10_STAT_rx_good_bytes] = - stats[EF10_STAT_rx_bytes] - - stats[EF10_STAT_rx_bytes_minus_good_bytes]; - efx_update_diff_stat(&stats[EF10_STAT_rx_bad_bytes], - stats[EF10_STAT_rx_bytes_minus_good_bytes]); + efx_nic_fix_nodesc_drop_stat(efx, + &stats[EF10_STAT_port_rx_nodesc_drops]); + stats[EF10_STAT_port_rx_good_bytes] = + stats[EF10_STAT_port_rx_bytes] - + stats[EF10_STAT_port_rx_bytes_minus_good_bytes]; + efx_update_diff_stat(&stats[EF10_STAT_port_rx_bad_bytes], + stats[EF10_STAT_port_rx_bytes_minus_good_bytes]); efx_update_sw_stats(efx, stats); return 0; } -static size_t efx_ef10_update_stats(struct efx_nic *efx, u64 *full_stats, - struct rtnl_link_stats64 *core_stats) +static size_t efx_ef10_update_stats_pf(struct efx_nic *efx, u64 *full_stats, + struct rtnl_link_stats64 *core_stats) { - DECLARE_BITMAP(mask, EF10_STAT_COUNT); - struct efx_ef10_nic_data *nic_data = efx->nic_data; - u64 *stats = nic_data->stats; - size_t stats_count = 0, index; int retry; - efx_ef10_get_stat_mask(efx, mask); - /* If we're unlucky enough to read statistics during the DMA, wait * up to 10ms for it to finish (typically takes <500us) */ for (retry = 0; retry < 100; ++retry) { - if (efx_ef10_try_update_nic_stats(efx) == 0) + if (efx_ef10_try_update_nic_stats_pf(efx) == 0) break; udelay(100); } - if (full_stats) { - for_each_set_bit(index, mask, EF10_STAT_COUNT) { - if (efx_ef10_stat_desc[index].name) { - *full_stats++ = stats[index]; - ++stats_count; - } - } + return efx_ef10_update_stats_common(efx, full_stats, core_stats); +} + +static int efx_ef10_try_update_nic_stats_vf(struct efx_nic *efx) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_MAC_STATS_IN_LEN); + struct efx_ef10_nic_data *nic_data = efx->nic_data; + DECLARE_BITMAP(mask, EF10_STAT_COUNT); + __le64 generation_start, generation_end; + u64 *stats = nic_data->stats; + u32 dma_len = MC_CMD_MAC_NSTATS * sizeof(u64); + struct efx_buffer stats_buf; + __le64 *dma_stats; + int rc; + + spin_unlock_bh(&efx->stats_lock); + + if (in_interrupt()) { + /* If in atomic context, cannot update stats. Just update the + * software stats and return so the caller can continue. + */ + spin_lock_bh(&efx->stats_lock); + efx_update_sw_stats(efx, stats); + return 0; } - if (core_stats) { - core_stats->rx_packets = stats[EF10_STAT_rx_packets]; - core_stats->tx_packets = stats[EF10_STAT_tx_packets]; - core_stats->rx_bytes = stats[EF10_STAT_rx_bytes]; - core_stats->tx_bytes = stats[EF10_STAT_tx_bytes]; - core_stats->rx_dropped = stats[EF10_STAT_rx_nodesc_drops] + - stats[GENERIC_STAT_rx_nodesc_trunc] + - stats[GENERIC_STAT_rx_noskb_drops]; - core_stats->multicast = stats[EF10_STAT_rx_multicast]; - core_stats->rx_length_errors = - stats[EF10_STAT_rx_gtjumbo] + - stats[EF10_STAT_rx_length_error]; - core_stats->rx_crc_errors = stats[EF10_STAT_rx_bad]; - core_stats->rx_frame_errors = stats[EF10_STAT_rx_align_error]; - core_stats->rx_fifo_errors = stats[EF10_STAT_rx_overflow]; - core_stats->rx_errors = (core_stats->rx_length_errors + - core_stats->rx_crc_errors + - core_stats->rx_frame_errors); + efx_ef10_get_stat_mask(efx, mask); + + rc = efx_nic_alloc_buffer(efx, &stats_buf, dma_len, GFP_ATOMIC); + if (rc) { + spin_lock_bh(&efx->stats_lock); + return rc; } - return stats_count; + dma_stats = stats_buf.addr; + dma_stats[MC_CMD_MAC_GENERATION_END] = EFX_MC_STATS_GENERATION_INVALID; + + MCDI_SET_QWORD(inbuf, MAC_STATS_IN_DMA_ADDR, stats_buf.dma_addr); + MCDI_POPULATE_DWORD_1(inbuf, MAC_STATS_IN_CMD, + MAC_STATS_IN_DMA, 1); + MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len); + MCDI_SET_DWORD(inbuf, MAC_STATS_IN_PORT_ID, EVB_PORT_ID_ASSIGNED); + + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf), + NULL, 0, NULL); + spin_lock_bh(&efx->stats_lock); + if (rc) { + /* Expect ENOENT if DMA queues have not been set up */ + if (rc != -ENOENT || atomic_read(&efx->active_queues)) + efx_mcdi_display_error(efx, MC_CMD_MAC_STATS, + sizeof(inbuf), NULL, 0, rc); + goto out; + } + + generation_end = dma_stats[MC_CMD_MAC_GENERATION_END]; + if (generation_end == EFX_MC_STATS_GENERATION_INVALID) { + WARN_ON_ONCE(1); + goto out; + } + rmb(); + efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, mask, + stats, stats_buf.addr, false); + rmb(); + generation_start = dma_stats[MC_CMD_MAC_GENERATION_START]; + if (generation_end != generation_start) { + rc = -EAGAIN; + goto out; + } + + efx_update_sw_stats(efx, stats); +out: + efx_nic_free_buffer(efx, &stats_buf); + return rc; +} + +static size_t efx_ef10_update_stats_vf(struct efx_nic *efx, u64 *full_stats, + struct rtnl_link_stats64 *core_stats) +{ + if (efx_ef10_try_update_nic_stats_vf(efx)) + return 0; + + return efx_ef10_update_stats_common(efx, full_stats, core_stats); } static void efx_ef10_push_irq_moderation(struct efx_channel *channel) @@ -1313,7 +1521,7 @@ static int efx_ef10_mcdi_poll_reboot(struct efx_nic *efx) /* MAC statistics have been cleared on the NIC; clear the local * statistic that we update with efx_update_diff_stat(). */ - nic_data->stats[EF10_STAT_rx_bad_bytes] = 0; + nic_data->stats[EF10_STAT_port_rx_bad_bytes] = 0; return -EIO; } @@ -4029,7 +4237,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = { .prepare_flr = efx_ef10_prepare_flr, .finish_flr = efx_port_dummy_op_void, .describe_stats = efx_ef10_describe_stats, - .update_stats = efx_ef10_update_stats, + .update_stats = efx_ef10_update_stats_vf, .start_stats = efx_port_dummy_op_void, .pull_stats = efx_port_dummy_op_void, .stop_stats = efx_port_dummy_op_void, @@ -4091,6 +4299,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = { .vswitching_probe = efx_ef10_vswitching_probe_vf, .vswitching_restore = efx_ef10_vswitching_restore_vf, .vswitching_remove = efx_ef10_vswitching_remove_vf, + .sriov_get_phys_port_id = efx_ef10_sriov_get_phys_port_id, #endif .get_mac_address = efx_ef10_get_mac_address_vf, .set_mac_address = efx_ef10_set_mac_address, @@ -4130,7 +4339,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .prepare_flr = efx_ef10_prepare_flr, .finish_flr = efx_port_dummy_op_void, .describe_stats = efx_ef10_describe_stats, - .update_stats = efx_ef10_update_stats, + .update_stats = efx_ef10_update_stats_pf, .start_stats = efx_mcdi_mac_start_stats, .pull_stats = efx_mcdi_mac_pull_stats, .stop_stats = efx_mcdi_mac_stop_stats, diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c index 3969b1b..6c9b6e4 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.c +++ b/drivers/net/ethernet/sfc/ef10_sriov.c @@ -165,6 +165,11 @@ static void efx_ef10_sriov_free_vf_vports(struct efx_nic *efx) for (i = 0; i < efx->vf_count; i++) { struct ef10_vf *vf = nic_data->vf + i; + /* If VF is assigned, do not free the vport */ + if (vf->pci_dev && + vf->pci_dev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) + continue; + if (vf->vport_assigned) { efx_ef10_evb_port_assign(efx, EVB_PORT_ID_NULL, i); vf->vport_assigned = 0; @@ -380,7 +385,9 @@ void efx_ef10_vswitching_remove_pf(struct efx_nic *efx) efx_ef10_vport_free(efx, nic_data->vport_id); nic_data->vport_id = EVB_PORT_ID_ASSIGNED; - efx_ef10_vswitch_free(efx, nic_data->vport_id); + /* Only free the vswitch if no VFs are assigned */ + if (!pci_vfs_assigned(efx->pci_dev)) + efx_ef10_vswitch_free(efx, nic_data->vport_id); } void efx_ef10_vswitching_remove_vf(struct efx_nic *efx) @@ -413,11 +420,22 @@ fail1: return rc; } -static int efx_ef10_pci_sriov_disable(struct efx_nic *efx) +static int efx_ef10_pci_sriov_disable(struct efx_nic *efx, bool force) { struct pci_dev *dev = efx->pci_dev; + unsigned int vfs_assigned = 0; + + vfs_assigned = pci_vfs_assigned(dev); + + if (vfs_assigned && !force) { + netif_info(efx, drv, efx->net_dev, "VFs are assigned to guests; " + "please detach them before disabling SR-IOV\n"); + return -EBUSY; + } + + if (!vfs_assigned) + pci_disable_sriov(dev); - pci_disable_sriov(dev); efx_ef10_sriov_free_vf_vswitching(efx); efx->vf_count = 0; return 0; @@ -426,7 +444,7 @@ static int efx_ef10_pci_sriov_disable(struct efx_nic *efx) int efx_ef10_sriov_configure(struct efx_nic *efx, int num_vfs) { if (num_vfs == 0) - return efx_ef10_pci_sriov_disable(efx); + return efx_ef10_pci_sriov_disable(efx, false); else return efx_ef10_pci_sriov_enable(efx, num_vfs); } @@ -439,12 +457,25 @@ int efx_ef10_sriov_init(struct efx_nic *efx) void efx_ef10_sriov_fini(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; + unsigned int i; int rc; - if (!nic_data->vf) + if (!nic_data->vf) { + /* Remove any un-assigned orphaned VFs */ + if (pci_num_vf(efx->pci_dev) && !pci_vfs_assigned(efx->pci_dev)) + pci_disable_sriov(efx->pci_dev); return; + } + + /* Remove any VFs in the host */ + for (i = 0; i < efx->vf_count; ++i) { + struct efx_nic *vf_efx = nic_data->vf[i].efx; + + if (vf_efx) + vf_efx->pci_dev->driver->remove(vf_efx->pci_dev); + } - rc = efx_ef10_pci_sriov_disable(efx); + rc = efx_ef10_pci_sriov_disable(efx, true); if (rc) netif_dbg(efx, drv, efx->net_dev, "Disabling SRIOV was not successful rc=%d\n", rc); @@ -736,3 +767,17 @@ int efx_ef10_sriov_get_vf_config(struct efx_nic *efx, int vf_i, return 0; } + +int efx_ef10_sriov_get_phys_port_id(struct efx_nic *efx, + struct netdev_phys_item_id *ppid) +{ + struct efx_ef10_nic_data *nic_data = efx->nic_data; + + if (!is_valid_ether_addr(nic_data->port_id)) + return -EOPNOTSUPP; + + ppid->id_len = ETH_ALEN; + memcpy(ppid->id, nic_data->port_id, ppid->id_len); + + return 0; +} diff --git a/drivers/net/ethernet/sfc/ef10_sriov.h b/drivers/net/ethernet/sfc/ef10_sriov.h index b985576..db4ef53 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.h +++ b/drivers/net/ethernet/sfc/ef10_sriov.h @@ -15,6 +15,7 @@ /** * struct ef10_vf - PF's store of VF data * @efx: efx_nic struct for the current VF + * @pci_dev: the pci_dev struct for the VF, retained while the VF is assigned * @vport_id: vport ID for the VF * @vport_assigned: record whether the vport is currently assigned to the VF * @mac: MAC address for the VF, zero when address is removed from the vport @@ -22,6 +23,7 @@ */ struct ef10_vf { struct efx_nic *efx; + struct pci_dev *pci_dev; unsigned int vport_id; unsigned int vport_assigned; u8 mac[ETH_ALEN]; @@ -54,6 +56,9 @@ int efx_ef10_sriov_get_vf_config(struct efx_nic *efx, int vf_i, int efx_ef10_sriov_set_vf_link_state(struct efx_nic *efx, int vf_i, int link_state); +int efx_ef10_sriov_get_phys_port_id(struct efx_nic *efx, + struct netdev_phys_item_id *ppid); + int efx_ef10_vswitching_probe_pf(struct efx_nic *efx); int efx_ef10_vswitching_probe_vf(struct efx_nic *efx); int efx_ef10_vswitching_restore_pf(struct efx_nic *efx); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 9eafa39..0c42ed9 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1298,7 +1298,9 @@ static void efx_fini_io(struct efx_nic *efx) efx->membase_phys = 0; } - pci_disable_device(efx->pci_dev); + /* Don't disable bus-mastering if VFs are assigned */ + if (!pci_vfs_assigned(efx->pci_dev)) + pci_disable_device(efx->pci_dev); } void efx_set_default_rx_indir_table(struct efx_nic *efx) @@ -2282,6 +2284,7 @@ static const struct net_device_ops efx_netdev_ops = { .ndo_set_vf_spoofchk = efx_sriov_set_vf_spoofchk, .ndo_get_vf_config = efx_sriov_get_vf_config, .ndo_set_vf_link_state = efx_sriov_set_vf_link_state, + .ndo_get_phys_port_id = efx_sriov_get_phys_port_id, #endif #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = efx_netpoll, @@ -2326,6 +2329,28 @@ show_phy_type(struct device *dev, struct device_attribute *attr, char *buf) } static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL); +#ifdef CONFIG_SFC_MCDI_LOGGING +static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + + return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled); +} +static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + bool enable = count > 0 && *buf != '0'; + + mcdi->logging_enabled = enable; + return count; +} +static DEVICE_ATTR(mcdi_logging, 0644, show_mcdi_log, set_mcdi_log); +#endif + static int efx_register_netdev(struct efx_nic *efx) { struct net_device *net_dev = efx->net_dev; @@ -2383,9 +2408,21 @@ static int efx_register_netdev(struct efx_nic *efx) "failed to init net dev attributes\n"); goto fail_registered; } +#ifdef CONFIG_SFC_MCDI_LOGGING + rc = device_create_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging); + if (rc) { + netif_err(efx, drv, efx->net_dev, + "failed to init net dev attributes\n"); + goto fail_attr_mcdi_logging; + } +#endif return 0; +#ifdef CONFIG_SFC_MCDI_LOGGING +fail_attr_mcdi_logging: + device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type); +#endif fail_registered: rtnl_lock(); efx_dissociate(efx); @@ -2404,13 +2441,14 @@ static void efx_unregister_netdev(struct efx_nic *efx) BUG_ON(netdev_priv(efx->net_dev) != efx); - strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name)); - device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type); - - rtnl_lock(); - unregister_netdevice(efx->net_dev); - efx->state = STATE_UNINIT; - rtnl_unlock(); + if (efx_dev_registered(efx)) { + strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name)); +#ifdef CONFIG_SFC_MCDI_LOGGING + device_remove_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging); +#endif + device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type); + unregister_netdev(efx->net_dev); + } } /************************************************************************** @@ -2866,7 +2904,8 @@ static void efx_pci_remove_main(struct efx_nic *efx) } /* Final NIC shutdown - * This is called only at module unload (or hotplug removal). + * This is called only at module unload (or hotplug removal). A PF can call + * this on its VFs to ensure they are unbound first. */ static void efx_pci_remove(struct pci_dev *pci_dev) { diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 8267a1c..81640f8 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -8,6 +8,7 @@ */ #include <linux/delay.h> +#include <linux/moduleparam.h> #include <asm/cmpxchg.h> #include "net_driver.h" #include "nic.h" @@ -54,18 +55,32 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating, static bool efx_mcdi_poll_once(struct efx_nic *efx); static void efx_mcdi_abandon(struct efx_nic *efx); +#ifdef CONFIG_SFC_MCDI_LOGGING +static bool mcdi_logging_default; +module_param(mcdi_logging_default, bool, 0644); +MODULE_PARM_DESC(mcdi_logging_default, + "Enable MCDI logging on newly-probed functions"); +#endif + int efx_mcdi_init(struct efx_nic *efx) { struct efx_mcdi_iface *mcdi; bool already_attached; - int rc; + int rc = -ENOMEM; efx->mcdi = kzalloc(sizeof(*efx->mcdi), GFP_KERNEL); if (!efx->mcdi) - return -ENOMEM; + goto fail; mcdi = efx_mcdi(efx); mcdi->efx = efx; +#ifdef CONFIG_SFC_MCDI_LOGGING + /* consuming code assumes buffer is page-sized */ + mcdi->logging_buffer = (char *)__get_free_page(GFP_KERNEL); + if (!mcdi->logging_buffer) + goto fail1; + mcdi->logging_enabled = mcdi_logging_default; +#endif init_waitqueue_head(&mcdi->wq); spin_lock_init(&mcdi->iface_lock); mcdi->state = MCDI_STATE_QUIESCENT; @@ -81,7 +96,7 @@ int efx_mcdi_init(struct efx_nic *efx) /* Recover from a failed assertion before probing */ rc = efx_mcdi_handle_assertion(efx); if (rc) - return rc; + goto fail2; /* Let the MC (and BMC, if this is a LOM) know that the driver * is loaded. We should do this before we reset the NIC. @@ -90,7 +105,7 @@ int efx_mcdi_init(struct efx_nic *efx) if (rc) { netif_err(efx, probe, efx->net_dev, "Unable to register driver with MCPU\n"); - return rc; + goto fail2; } if (already_attached) /* Not a fatal error */ @@ -102,6 +117,15 @@ int efx_mcdi_init(struct efx_nic *efx) efx->primary = efx; return 0; +fail2: +#ifdef CONFIG_SFC_MCDI_LOGGING + free_page((unsigned long)mcdi->logging_buffer); +fail1: +#endif + kfree(efx->mcdi); + efx->mcdi = NULL; +fail: + return rc; } void efx_mcdi_fini(struct efx_nic *efx) @@ -114,6 +138,10 @@ void efx_mcdi_fini(struct efx_nic *efx) /* Relinquish the device (back to the BMC, if this is a LOM) */ efx_mcdi_drv_attach(efx, false, NULL); +#ifdef CONFIG_SFC_MCDI_LOGGING + free_page((unsigned long)efx->mcdi->iface.logging_buffer); +#endif + kfree(efx->mcdi); } @@ -121,6 +149,9 @@ static void efx_mcdi_send_request(struct efx_nic *efx, unsigned cmd, const efx_dword_t *inbuf, size_t inlen) { struct efx_mcdi_iface *mcdi = efx_mcdi(efx); +#ifdef CONFIG_SFC_MCDI_LOGGING + char *buf = mcdi->logging_buffer; /* page-sized */ +#endif efx_dword_t hdr[2]; size_t hdr_len; u32 xflags, seqno; @@ -165,6 +196,31 @@ static void efx_mcdi_send_request(struct efx_nic *efx, unsigned cmd, hdr_len = 8; } +#ifdef CONFIG_SFC_MCDI_LOGGING + if (mcdi->logging_enabled && !WARN_ON_ONCE(!buf)) { + int bytes = 0; + int i; + /* Lengths should always be a whole number of dwords, so scream + * if they're not. + */ + WARN_ON_ONCE(hdr_len % 4); + WARN_ON_ONCE(inlen % 4); + + /* We own the logging buffer, as only one MCDI can be in + * progress on a NIC at any one time. So no need for locking. + */ + for (i = 0; i < hdr_len / 4 && bytes < PAGE_SIZE; i++) + bytes += snprintf(buf + bytes, PAGE_SIZE - bytes, + " %08x", le32_to_cpu(hdr[i].u32[0])); + + for (i = 0; i < inlen / 4 && bytes < PAGE_SIZE; i++) + bytes += snprintf(buf + bytes, PAGE_SIZE - bytes, + " %08x", le32_to_cpu(inbuf[i].u32[0])); + + netif_info(efx, hw, efx->net_dev, "MCDI RPC REQ:%s\n", buf); + } +#endif + efx->type->mcdi_request(efx, hdr, hdr_len, inbuf, inlen); mcdi->new_epoch = false; @@ -206,6 +262,9 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx) { struct efx_mcdi_iface *mcdi = efx_mcdi(efx); unsigned int respseq, respcmd, error; +#ifdef CONFIG_SFC_MCDI_LOGGING + char *buf = mcdi->logging_buffer; /* page-sized */ +#endif efx_dword_t hdr; efx->type->mcdi_read_response(efx, &hdr, 0, 4); @@ -223,6 +282,39 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx) EFX_DWORD_FIELD(hdr, MC_CMD_V2_EXTN_IN_ACTUAL_LEN); } +#ifdef CONFIG_SFC_MCDI_LOGGING + if (mcdi->logging_enabled && !WARN_ON_ONCE(!buf)) { + size_t hdr_len, data_len; + int bytes = 0; + int i; + + WARN_ON_ONCE(mcdi->resp_hdr_len % 4); + hdr_len = mcdi->resp_hdr_len / 4; + /* MCDI_DECLARE_BUF ensures that underlying buffer is padded + * to dword size, and the MCDI buffer is always dword size + */ + data_len = DIV_ROUND_UP(mcdi->resp_data_len, 4); + + /* We own the logging buffer, as only one MCDI can be in + * progress on a NIC at any one time. So no need for locking. + */ + for (i = 0; i < hdr_len && bytes < PAGE_SIZE; i++) { + efx->type->mcdi_read_response(efx, &hdr, (i * 4), 4); + bytes += snprintf(buf + bytes, PAGE_SIZE - bytes, + " %08x", le32_to_cpu(hdr.u32[0])); + } + + for (i = 0; i < data_len && bytes < PAGE_SIZE; i++) { + efx->type->mcdi_read_response(efx, &hdr, + mcdi->resp_hdr_len + (i * 4), 4); + bytes += snprintf(buf + bytes, PAGE_SIZE - bytes, + " %08x", le32_to_cpu(hdr.u32[0])); + } + + netif_info(efx, hw, efx->net_dev, "MCDI RPC RESP:%s\n", buf); + } +#endif + if (error && mcdi->resp_data_len == 0) { netif_err(efx, hw, efx->net_dev, "MC rebooted\n"); mcdi->resprc = -EIO; diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index 7afab2f..1838afe 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -58,6 +58,8 @@ enum efx_mcdi_mode { * enabled * @async_list: Queue of asynchronous requests * @async_timer: Timer for asynchronous request timeout + * @logging_buffer: buffer that may be used to build MCDI tracing messages + * @logging_enabled: whether to trace MCDI */ struct efx_mcdi_iface { struct efx_nic *efx; @@ -74,6 +76,10 @@ struct efx_mcdi_iface { spinlock_t async_lock; struct list_head async_list; struct timer_list async_timer; +#ifdef CONFIG_SFC_MCDI_LOGGING + char *logging_buffer; + bool logging_enabled; +#endif }; struct efx_mcdi_mon { diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h index 9efdf0a..45fca9f 100644 --- a/drivers/net/ethernet/sfc/mcdi_pcol.h +++ b/drivers/net/ethernet/sfc/mcdi_pcol.h @@ -2755,7 +2755,7 @@ #define MC_CMD_0x2e_PRIVILEGE_CTG SRIOV_CTG_GENERAL /* MC_CMD_MAC_STATS_IN msgrequest */ -#define MC_CMD_MAC_STATS_IN_LEN 16 +#define MC_CMD_MAC_STATS_IN_LEN 20 /* ??? */ #define MC_CMD_MAC_STATS_IN_DMA_ADDR_OFST 0 #define MC_CMD_MAC_STATS_IN_DMA_ADDR_LEN 8 @@ -2777,6 +2777,8 @@ #define MC_CMD_MAC_STATS_IN_PERIOD_MS_LBN 16 #define MC_CMD_MAC_STATS_IN_PERIOD_MS_WIDTH 16 #define MC_CMD_MAC_STATS_IN_DMA_LEN_OFST 12 +/* port id so vadapter stats can be provided */ +#define MC_CMD_MAC_STATS_IN_PORT_ID_OFST 16 /* MC_CMD_MAC_STATS_OUT_DMA msgresponse */ #define MC_CMD_MAC_STATS_OUT_DMA_LEN 0 @@ -2891,11 +2893,31 @@ /* enum: RXDP counter: Number of times an emergency descriptor fetch was * performed. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only. */ -#define MC_CMD_MAC_RXDP_EMERGENCY_FETCH_CONDITIONS 0x47 +#define MC_CMD_MAC_RXDP_HLB_FETCH_CONDITIONS 0x47 /* enum: RXDP counter: Number of times the DPCPU waited for an existing * descriptor fetch. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only. */ -#define MC_CMD_MAC_RXDP_EMERGENCY_WAIT_CONDITIONS 0x48 +#define MC_CMD_MAC_RXDP_HLB_WAIT_CONDITIONS 0x48 +#define MC_CMD_MAC_VADAPTER_RX_DMABUF_START 0x4c /* enum */ +#define MC_CMD_MAC_VADAPTER_RX_UNICAST_PACKETS 0x4c /* enum */ +#define MC_CMD_MAC_VADAPTER_RX_UNICAST_BYTES 0x4d /* enum */ +#define MC_CMD_MAC_VADAPTER_RX_MULTICAST_PACKETS 0x4e /* enum */ +#define MC_CMD_MAC_VADAPTER_RX_MULTICAST_BYTES 0x4f /* enum */ +#define MC_CMD_MAC_VADAPTER_RX_BROADCAST_PACKETS 0x50 /* enum */ +#define MC_CMD_MAC_VADAPTER_RX_BROADCAST_BYTES 0x51 /* enum */ +#define MC_CMD_MAC_VADAPTER_RX_BAD_PACKETS 0x52 /* enum */ +#define MC_CMD_MAC_VADAPTER_RX_BAD_BYTES 0x53 /* enum */ +#define MC_CMD_MAC_VADAPTER_RX_OVERFLOW 0x54 /* enum */ +#define MC_CMD_MAC_VADAPTER_TX_DMABUF_START 0x57 /* enum */ +#define MC_CMD_MAC_VADAPTER_TX_UNICAST_PACKETS 0x57 /* enum */ +#define MC_CMD_MAC_VADAPTER_TX_UNICAST_BYTES 0x58 /* enum */ +#define MC_CMD_MAC_VADAPTER_TX_MULTICAST_PACKETS 0x59 /* enum */ +#define MC_CMD_MAC_VADAPTER_TX_MULTICAST_BYTES 0x5a /* enum */ +#define MC_CMD_MAC_VADAPTER_TX_BROADCAST_PACKETS 0x5b /* enum */ +#define MC_CMD_MAC_VADAPTER_TX_BROADCAST_BYTES 0x5c /* enum */ +#define MC_CMD_MAC_VADAPTER_TX_BAD_PACKETS 0x5d /* enum */ +#define MC_CMD_MAC_VADAPTER_TX_BAD_BYTES 0x5e /* enum */ +#define MC_CMD_MAC_VADAPTER_TX_OVERFLOW 0x5f /* enum */ /* enum: Start of GMAC stats buffer space, for Siena only. */ #define MC_CMD_GMAC_DMABUF_START 0x40 /* enum: End of GMAC stats buffer space, for Siena only. */ @@ -5578,6 +5600,8 @@ #define MC_CMD_GET_CAPABILITIES_OUT_MCAST_FILTER_CHAINING_WIDTH 1 #define MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_LBN 27 #define MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_EVB_LBN 30 +#define MC_CMD_GET_CAPABILITIES_OUT_EVB_WIDTH 1 /* RxDPCPU firmware id. */ #define MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_OFST 4 #define MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_LEN 2 diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c index 9bf04cb..7f295c4 100644 --- a/drivers/net/ethernet/sfc/mcdi_port.c +++ b/drivers/net/ethernet/sfc/mcdi_port.c @@ -924,6 +924,7 @@ enum efx_stats_action { static int efx_mcdi_mac_stats(struct efx_nic *efx, enum efx_stats_action action, int clear) { + struct efx_ef10_nic_data *nic_data = efx->nic_data; MCDI_DECLARE_BUF(inbuf, MC_CMD_MAC_STATS_IN_LEN); int rc; int change = action == EFX_STATS_PULL ? 0 : 1; @@ -945,9 +946,14 @@ static int efx_mcdi_mac_stats(struct efx_nic *efx, MAC_STATS_IN_PERIODIC_NOEVENT, 1, MAC_STATS_IN_PERIOD_MS, period); MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len); - - rc = efx_mcdi_rpc(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf), - NULL, 0, NULL); + MCDI_SET_DWORD(inbuf, MAC_STATS_IN_PORT_ID, nic_data->vport_id); + + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf), + NULL, 0, NULL); + /* Expect ENOENT if DMA queues have not been set up */ + if (rc && (rc != -ENOENT || atomic_read(&efx->active_queues))) + efx_mcdi_display_error(efx, MC_CMD_MAC_STATS, sizeof(inbuf), + NULL, 0, rc); return rc; } diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index a468a22..d72f522 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1350,6 +1350,8 @@ struct efx_nic_type { struct ifla_vf_info *ivi); int (*sriov_set_vf_link_state)(struct efx_nic *efx, int vf_i, int link_state); + int (*sriov_get_phys_port_id)(struct efx_nic *efx, + struct netdev_phys_item_id *ppid); int (*vswitching_probe)(struct efx_nic *efx); int (*vswitching_restore)(struct efx_nic *efx); void (*vswitching_remove)(struct efx_nic *efx); diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index db8562e..31ff908 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -407,59 +407,77 @@ struct siena_nic_data { }; enum { - EF10_STAT_tx_bytes = GENERIC_STAT_COUNT, - EF10_STAT_tx_packets, - EF10_STAT_tx_pause, - EF10_STAT_tx_control, - EF10_STAT_tx_unicast, - EF10_STAT_tx_multicast, - EF10_STAT_tx_broadcast, - EF10_STAT_tx_lt64, - EF10_STAT_tx_64, - EF10_STAT_tx_65_to_127, - EF10_STAT_tx_128_to_255, - EF10_STAT_tx_256_to_511, - EF10_STAT_tx_512_to_1023, - EF10_STAT_tx_1024_to_15xx, - EF10_STAT_tx_15xx_to_jumbo, - EF10_STAT_rx_bytes, - EF10_STAT_rx_bytes_minus_good_bytes, - EF10_STAT_rx_good_bytes, - EF10_STAT_rx_bad_bytes, - EF10_STAT_rx_packets, - EF10_STAT_rx_good, - EF10_STAT_rx_bad, - EF10_STAT_rx_pause, - EF10_STAT_rx_control, + EF10_STAT_port_tx_bytes = GENERIC_STAT_COUNT, + EF10_STAT_port_tx_packets, + EF10_STAT_port_tx_pause, + EF10_STAT_port_tx_control, + EF10_STAT_port_tx_unicast, + EF10_STAT_port_tx_multicast, + EF10_STAT_port_tx_broadcast, + EF10_STAT_port_tx_lt64, + EF10_STAT_port_tx_64, + EF10_STAT_port_tx_65_to_127, + EF10_STAT_port_tx_128_to_255, + EF10_STAT_port_tx_256_to_511, + EF10_STAT_port_tx_512_to_1023, + EF10_STAT_port_tx_1024_to_15xx, + EF10_STAT_port_tx_15xx_to_jumbo, + EF10_STAT_port_rx_bytes, + EF10_STAT_port_rx_bytes_minus_good_bytes, + EF10_STAT_port_rx_good_bytes, + EF10_STAT_port_rx_bad_bytes, + EF10_STAT_port_rx_packets, + EF10_STAT_port_rx_good, + EF10_STAT_port_rx_bad, + EF10_STAT_port_rx_pause, + EF10_STAT_port_rx_control, + EF10_STAT_port_rx_unicast, + EF10_STAT_port_rx_multicast, + EF10_STAT_port_rx_broadcast, + EF10_STAT_port_rx_lt64, + EF10_STAT_port_rx_64, + EF10_STAT_port_rx_65_to_127, + EF10_STAT_port_rx_128_to_255, + EF10_STAT_port_rx_256_to_511, + EF10_STAT_port_rx_512_to_1023, + EF10_STAT_port_rx_1024_to_15xx, + EF10_STAT_port_rx_15xx_to_jumbo, + EF10_STAT_port_rx_gtjumbo, + EF10_STAT_port_rx_bad_gtjumbo, + EF10_STAT_port_rx_overflow, + EF10_STAT_port_rx_align_error, + EF10_STAT_port_rx_length_error, + EF10_STAT_port_rx_nodesc_drops, + EF10_STAT_port_rx_pm_trunc_bb_overflow, + EF10_STAT_port_rx_pm_discard_bb_overflow, + EF10_STAT_port_rx_pm_trunc_vfifo_full, + EF10_STAT_port_rx_pm_discard_vfifo_full, + EF10_STAT_port_rx_pm_trunc_qbb, + EF10_STAT_port_rx_pm_discard_qbb, + EF10_STAT_port_rx_pm_discard_mapping, + EF10_STAT_port_rx_dp_q_disabled_packets, + EF10_STAT_port_rx_dp_di_dropped_packets, + EF10_STAT_port_rx_dp_streaming_packets, + EF10_STAT_port_rx_dp_hlb_fetch, + EF10_STAT_port_rx_dp_hlb_wait, EF10_STAT_rx_unicast, + EF10_STAT_rx_unicast_bytes, EF10_STAT_rx_multicast, + EF10_STAT_rx_multicast_bytes, EF10_STAT_rx_broadcast, - EF10_STAT_rx_lt64, - EF10_STAT_rx_64, - EF10_STAT_rx_65_to_127, - EF10_STAT_rx_128_to_255, - EF10_STAT_rx_256_to_511, - EF10_STAT_rx_512_to_1023, - EF10_STAT_rx_1024_to_15xx, - EF10_STAT_rx_15xx_to_jumbo, - EF10_STAT_rx_gtjumbo, - EF10_STAT_rx_bad_gtjumbo, + EF10_STAT_rx_broadcast_bytes, + EF10_STAT_rx_bad, + EF10_STAT_rx_bad_bytes, EF10_STAT_rx_overflow, - EF10_STAT_rx_align_error, - EF10_STAT_rx_length_error, - EF10_STAT_rx_nodesc_drops, - EF10_STAT_rx_pm_trunc_bb_overflow, - EF10_STAT_rx_pm_discard_bb_overflow, - EF10_STAT_rx_pm_trunc_vfifo_full, - EF10_STAT_rx_pm_discard_vfifo_full, - EF10_STAT_rx_pm_trunc_qbb, - EF10_STAT_rx_pm_discard_qbb, - EF10_STAT_rx_pm_discard_mapping, - EF10_STAT_rx_dp_q_disabled_packets, - EF10_STAT_rx_dp_di_dropped_packets, - EF10_STAT_rx_dp_streaming_packets, - EF10_STAT_rx_dp_hlb_fetch, - EF10_STAT_rx_dp_hlb_wait, + EF10_STAT_tx_unicast, + EF10_STAT_tx_unicast_bytes, + EF10_STAT_tx_multicast, + EF10_STAT_tx_multicast_bytes, + EF10_STAT_tx_broadcast, + EF10_STAT_tx_broadcast_bytes, + EF10_STAT_tx_bad, + EF10_STAT_tx_bad_bytes, + EF10_STAT_tx_overflow, EF10_STAT_COUNT }; @@ -524,6 +542,7 @@ struct efx_ef10_nic_data { unsigned int vport_id; bool must_probe_vswitching; unsigned int pf_index; + u8 port_id[ETH_ALEN]; #ifdef CONFIG_SFC_SRIOV unsigned int vf_index; struct ef10_vf *vf; diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index c0ad95d..809ea461 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -224,12 +224,17 @@ static void efx_unmap_rx_buffer(struct efx_nic *efx, } } -static void efx_free_rx_buffer(struct efx_rx_buffer *rx_buf) +static void efx_free_rx_buffers(struct efx_rx_queue *rx_queue, + struct efx_rx_buffer *rx_buf, + unsigned int num_bufs) { - if (rx_buf->page) { - put_page(rx_buf->page); - rx_buf->page = NULL; - } + do { + if (rx_buf->page) { + put_page(rx_buf->page); + rx_buf->page = NULL; + } + rx_buf = efx_rx_buf_next(rx_queue, rx_buf); + } while (--num_bufs); } /* Attempt to recycle the page if there is an RX recycle ring; the page can @@ -278,7 +283,7 @@ static void efx_fini_rx_buffer(struct efx_rx_queue *rx_queue, /* If this is the last buffer in a page, unmap and free it. */ if (rx_buf->flags & EFX_RX_BUF_LAST_IN_PAGE) { efx_unmap_rx_buffer(rx_queue->efx, rx_buf); - efx_free_rx_buffer(rx_buf); + efx_free_rx_buffers(rx_queue, rx_buf, 1); } rx_buf->page = NULL; } @@ -304,10 +309,7 @@ static void efx_discard_rx_packet(struct efx_channel *channel, efx_recycle_rx_pages(channel, rx_buf, n_frags); - do { - efx_free_rx_buffer(rx_buf); - rx_buf = efx_rx_buf_next(rx_queue, rx_buf); - } while (--n_frags); + efx_free_rx_buffers(rx_queue, rx_buf, n_frags); } /** @@ -431,11 +433,10 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, skb = napi_get_frags(napi); if (unlikely(!skb)) { - while (n_frags--) { - put_page(rx_buf->page); - rx_buf->page = NULL; - rx_buf = efx_rx_buf_next(&channel->rx_queue, rx_buf); - } + struct efx_rx_queue *rx_queue; + + rx_queue = efx_channel_get_rx_queue(channel); + efx_free_rx_buffers(rx_queue, rx_buf, n_frags); return; } @@ -622,7 +623,10 @@ static void efx_rx_deliver(struct efx_channel *channel, u8 *eh, skb = efx_rx_mk_skb(channel, rx_buf, n_frags, eh, hdr_len); if (unlikely(skb == NULL)) { - efx_free_rx_buffer(rx_buf); + struct efx_rx_queue *rx_queue; + + rx_queue = efx_channel_get_rx_queue(channel); + efx_free_rx_buffers(rx_queue, rx_buf, n_frags); return; } skb_record_rx_queue(skb, channel->rx_queue.core_index); @@ -661,8 +665,12 @@ void __efx_rx_packet(struct efx_channel *channel) * loopback layer, and free the rx_buf here */ if (unlikely(efx->loopback_selftest)) { + struct efx_rx_queue *rx_queue; + efx_loopback_rx_packet(efx, eh, rx_buf->len); - efx_free_rx_buffer(rx_buf); + rx_queue = efx_channel_get_rx_queue(channel); + efx_free_rx_buffers(rx_queue, rx_buf, + channel->rx_pkt_n_frags); goto out; } diff --git a/drivers/net/ethernet/sfc/sriov.c b/drivers/net/ethernet/sfc/sriov.c index 6c5edbd..816c446 100644 --- a/drivers/net/ethernet/sfc/sriov.c +++ b/drivers/net/ethernet/sfc/sriov.c @@ -70,3 +70,14 @@ int efx_sriov_set_vf_link_state(struct net_device *net_dev, int vf_i, else return -EOPNOTSUPP; } + +int efx_sriov_get_phys_port_id(struct net_device *net_dev, + struct netdev_phys_item_id *ppid) +{ + struct efx_nic *efx = netdev_priv(net_dev); + + if (efx->type->sriov_get_phys_port_id) + return efx->type->sriov_get_phys_port_id(efx, ppid); + else + return -EOPNOTSUPP; +} diff --git a/drivers/net/ethernet/sfc/sriov.h b/drivers/net/ethernet/sfc/sriov.h index 3be15a5..400df52 100644 --- a/drivers/net/ethernet/sfc/sriov.h +++ b/drivers/net/ethernet/sfc/sriov.h @@ -23,6 +23,8 @@ int efx_sriov_get_vf_config(struct net_device *net_dev, int vf_i, struct ifla_vf_info *ivi); int efx_sriov_set_vf_link_state(struct net_device *net_dev, int vf_i, int link_state); +int efx_sriov_get_phys_port_id(struct net_device *net_dev, + struct netdev_phys_item_id *ppid); #endif /* CONFIG_SFC_SRIOV */ diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 731e045..cec147d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -16,6 +16,7 @@ if STMMAC_ETH config STMMAC_PLATFORM tristate "STMMAC Platform bus support" depends on STMMAC_ETH + select MFD_SYSCON default y ---help--- This selects the platform specific bus support for the stmmac driver. @@ -36,6 +37,19 @@ config DWMAC_GENERIC platform specific code to function or is using platform data for setup. +config DWMAC_IPQ806X + tristate "QCA IPQ806x DWMAC support" + default ARCH_QCOM + depends on OF + select MFD_SYSCON + help + Support for QCA IPQ806X DWMAC Ethernet. + + This selects the IPQ806x SoC glue layer support for the stmmac + device driver. This driver does not use any of the hardware + acceleration features available on this SoC. Network devices + will behave like standard non-accelerated ethernet interfaces. + config DWMAC_LPC18XX tristate "NXP LPC18xx/43xx DWMAC support" default ARCH_LPC18XX diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index 92e714a..b390161 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -6,6 +6,7 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \ # Ordering matters. Generic driver must be last. obj-$(CONFIG_STMMAC_PLATFORM) += stmmac-platform.o +obj-$(CONFIG_DWMAC_IPQ806X) += dwmac-ipq806x.o obj-$(CONFIG_DWMAC_LPC18XX) += dwmac-lpc18xx.o obj-$(CONFIG_DWMAC_MESON) += dwmac-meson.o obj-$(CONFIG_DWMAC_ROCKCHIP) += dwmac-rk.o diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c new file mode 100644 index 0000000..7e3129e --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -0,0 +1,365 @@ +/* + * Qualcomm Atheros IPQ806x GMAC glue layer + * + * Copyright (C) 2015 The Linux Foundation + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#include <linux/device.h> +#include <linux/platform_device.h> +#include <linux/phy.h> +#include <linux/regmap.h> +#include <linux/clk.h> +#include <linux/reset.h> +#include <linux/of_net.h> +#include <linux/mfd/syscon.h> +#include <linux/stmmac.h> +#include <linux/of_mdio.h> +#include <linux/module.h> + +#include "stmmac_platform.h" + +#define NSS_COMMON_CLK_GATE 0x8 +#define NSS_COMMON_CLK_GATE_PTP_EN(x) BIT(0x10 + x) +#define NSS_COMMON_CLK_GATE_RGMII_RX_EN(x) BIT(0x9 + (x * 2)) +#define NSS_COMMON_CLK_GATE_RGMII_TX_EN(x) BIT(0x8 + (x * 2)) +#define NSS_COMMON_CLK_GATE_GMII_RX_EN(x) BIT(0x4 + x) +#define NSS_COMMON_CLK_GATE_GMII_TX_EN(x) BIT(0x0 + x) + +#define NSS_COMMON_CLK_DIV0 0xC +#define NSS_COMMON_CLK_DIV_OFFSET(x) (x * 8) +#define NSS_COMMON_CLK_DIV_MASK 0x7f + +#define NSS_COMMON_CLK_SRC_CTRL 0x14 +#define NSS_COMMON_CLK_SRC_CTRL_OFFSET(x) (1 << x) +/* Mode is coded on 1 bit but is different depending on the MAC ID: + * MAC0: QSGMII=0 RGMII=1 + * MAC1: QSGMII=0 SGMII=0 RGMII=1 + * MAC2 & MAC3: QSGMII=0 SGMII=1 + */ +#define NSS_COMMON_CLK_SRC_CTRL_RGMII(x) 1 +#define NSS_COMMON_CLK_SRC_CTRL_SGMII(x) ((x >= 2) ? 1 : 0) + +#define NSS_COMMON_MACSEC_CTL 0x28 +#define NSS_COMMON_MACSEC_CTL_EXT_BYPASS_EN(x) (1 << x) + +#define NSS_COMMON_GMAC_CTL(x) (0x30 + (x * 4)) +#define NSS_COMMON_GMAC_CTL_CSYS_REQ BIT(19) +#define NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL BIT(16) +#define NSS_COMMON_GMAC_CTL_IFG_LIMIT_OFFSET 8 +#define NSS_COMMON_GMAC_CTL_IFG_OFFSET 0 +#define NSS_COMMON_GMAC_CTL_IFG_MASK 0x3f + +#define NSS_COMMON_CLK_DIV_RGMII_1000 1 +#define NSS_COMMON_CLK_DIV_RGMII_100 9 +#define NSS_COMMON_CLK_DIV_RGMII_10 99 +#define NSS_COMMON_CLK_DIV_SGMII_1000 0 +#define NSS_COMMON_CLK_DIV_SGMII_100 4 +#define NSS_COMMON_CLK_DIV_SGMII_10 49 + +#define QSGMII_PCS_MODE_CTL 0x68 +#define QSGMII_PCS_MODE_CTL_AUTONEG_EN(x) BIT((x * 8) + 7) + +#define QSGMII_PCS_CAL_LCKDT_CTL 0x120 +#define QSGMII_PCS_CAL_LCKDT_CTL_RST BIT(19) + +/* Only GMAC1/2/3 support SGMII and their CTL register are not contiguous */ +#define QSGMII_PHY_SGMII_CTL(x) ((x == 1) ? 0x134 : \ + (0x13c + (4 * (x - 2)))) +#define QSGMII_PHY_CDR_EN BIT(0) +#define QSGMII_PHY_RX_FRONT_EN BIT(1) +#define QSGMII_PHY_RX_SIGNAL_DETECT_EN BIT(2) +#define QSGMII_PHY_TX_DRIVER_EN BIT(3) +#define QSGMII_PHY_QSGMII_EN BIT(7) +#define QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET 12 +#define QSGMII_PHY_PHASE_LOOP_GAIN_MASK 0x7 +#define QSGMII_PHY_RX_DC_BIAS_OFFSET 18 +#define QSGMII_PHY_RX_DC_BIAS_MASK 0x3 +#define QSGMII_PHY_RX_INPUT_EQU_OFFSET 20 +#define QSGMII_PHY_RX_INPUT_EQU_MASK 0x3 +#define QSGMII_PHY_CDR_PI_SLEW_OFFSET 22 +#define QSGMII_PHY_CDR_PI_SLEW_MASK 0x3 +#define QSGMII_PHY_TX_DRV_AMP_OFFSET 28 +#define QSGMII_PHY_TX_DRV_AMP_MASK 0xf + +struct ipq806x_gmac { + struct platform_device *pdev; + struct regmap *nss_common; + struct regmap *qsgmii_csr; + uint32_t id; + struct clk *core_clk; + phy_interface_t phy_mode; +}; + +static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, unsigned int speed) +{ + struct device *dev = &gmac->pdev->dev; + int div; + + switch (speed) { + case SPEED_1000: + div = NSS_COMMON_CLK_DIV_SGMII_1000; + break; + + case SPEED_100: + div = NSS_COMMON_CLK_DIV_SGMII_100; + break; + + case SPEED_10: + div = NSS_COMMON_CLK_DIV_SGMII_10; + break; + + default: + dev_err(dev, "Speed %dMbps not supported in SGMII\n", speed); + return -EINVAL; + } + + return div; +} + +static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, unsigned int speed) +{ + struct device *dev = &gmac->pdev->dev; + int div; + + switch (speed) { + case SPEED_1000: + div = NSS_COMMON_CLK_DIV_RGMII_1000; + break; + + case SPEED_100: + div = NSS_COMMON_CLK_DIV_RGMII_100; + break; + + case SPEED_10: + div = NSS_COMMON_CLK_DIV_RGMII_10; + break; + + default: + dev_err(dev, "Speed %dMbps not supported in RGMII\n", speed); + return -EINVAL; + } + + return div; +} + +static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, unsigned int speed) +{ + uint32_t clk_bits, val; + int div; + + switch (gmac->phy_mode) { + case PHY_INTERFACE_MODE_RGMII: + div = get_clk_div_rgmii(gmac, speed); + clk_bits = NSS_COMMON_CLK_GATE_RGMII_RX_EN(gmac->id) | + NSS_COMMON_CLK_GATE_RGMII_TX_EN(gmac->id); + break; + + case PHY_INTERFACE_MODE_SGMII: + div = get_clk_div_sgmii(gmac, speed); + clk_bits = NSS_COMMON_CLK_GATE_GMII_RX_EN(gmac->id) | + NSS_COMMON_CLK_GATE_GMII_TX_EN(gmac->id); + break; + + default: + dev_err(&gmac->pdev->dev, "Unsupported PHY mode: \"%s\"\n", + phy_modes(gmac->phy_mode)); + return -EINVAL; + } + + /* Disable the clocks */ + regmap_read(gmac->nss_common, NSS_COMMON_CLK_GATE, &val); + val &= ~clk_bits; + regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val); + + /* Set the divider */ + regmap_read(gmac->nss_common, NSS_COMMON_CLK_DIV0, &val); + val &= ~(NSS_COMMON_CLK_DIV_MASK + << NSS_COMMON_CLK_DIV_OFFSET(gmac->id)); + val |= div << NSS_COMMON_CLK_DIV_OFFSET(gmac->id); + regmap_write(gmac->nss_common, NSS_COMMON_CLK_DIV0, val); + + /* Enable the clock back */ + regmap_read(gmac->nss_common, NSS_COMMON_CLK_GATE, &val); + val |= clk_bits; + regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val); + + return 0; +} + +static void *ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac) +{ + struct device *dev = &gmac->pdev->dev; + + gmac->phy_mode = of_get_phy_mode(dev->of_node); + if (gmac->phy_mode < 0) { + dev_err(dev, "missing phy mode property\n"); + return ERR_PTR(-EINVAL); + } + + if (of_property_read_u32(dev->of_node, "qcom,id", &gmac->id) < 0) { + dev_err(dev, "missing qcom id property\n"); + return ERR_PTR(-EINVAL); + } + + /* The GMACs are called 1 to 4 in the documentation, but to simplify the + * code and keep it consistent with the Linux convention, we'll number + * them from 0 to 3 here. + */ + if (gmac->id < 0 || gmac->id > 3) { + dev_err(dev, "invalid gmac id\n"); + return ERR_PTR(-EINVAL); + } + + gmac->core_clk = devm_clk_get(dev, "stmmaceth"); + if (IS_ERR(gmac->core_clk)) { + dev_err(dev, "missing stmmaceth clk property\n"); + return gmac->core_clk; + } + clk_set_rate(gmac->core_clk, 266000000); + + /* Setup the register map for the nss common registers */ + gmac->nss_common = syscon_regmap_lookup_by_phandle(dev->of_node, + "qcom,nss-common"); + if (IS_ERR(gmac->nss_common)) { + dev_err(dev, "missing nss-common node\n"); + return gmac->nss_common; + } + + /* Setup the register map for the qsgmii csr registers */ + gmac->qsgmii_csr = syscon_regmap_lookup_by_phandle(dev->of_node, + "qcom,qsgmii-csr"); + if (IS_ERR(gmac->qsgmii_csr)) { + dev_err(dev, "missing qsgmii-csr node\n"); + return gmac->qsgmii_csr; + } + + return NULL; +} + +static void *ipq806x_gmac_setup(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct ipq806x_gmac *gmac; + int val; + void *err; + + gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL); + if (!gmac) + return ERR_PTR(-ENOMEM); + + gmac->pdev = pdev; + + err = ipq806x_gmac_of_parse(gmac); + if (err) { + dev_err(dev, "device tree parsing error\n"); + return err; + } + + regmap_write(gmac->qsgmii_csr, QSGMII_PCS_CAL_LCKDT_CTL, + QSGMII_PCS_CAL_LCKDT_CTL_RST); + + /* Inter frame gap is set to 12 */ + val = 12 << NSS_COMMON_GMAC_CTL_IFG_OFFSET | + 12 << NSS_COMMON_GMAC_CTL_IFG_LIMIT_OFFSET; + /* We also initiate an AXI low power exit request */ + val |= NSS_COMMON_GMAC_CTL_CSYS_REQ; + switch (gmac->phy_mode) { + case PHY_INTERFACE_MODE_RGMII: + val |= NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL; + break; + case PHY_INTERFACE_MODE_SGMII: + val &= ~NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL; + break; + default: + dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n", + phy_modes(gmac->phy_mode)); + return NULL; + } + regmap_write(gmac->nss_common, NSS_COMMON_GMAC_CTL(gmac->id), val); + + /* Configure the clock src according to the mode */ + regmap_read(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, &val); + val &= ~NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id); + switch (gmac->phy_mode) { + case PHY_INTERFACE_MODE_RGMII: + val |= NSS_COMMON_CLK_SRC_CTRL_RGMII(gmac->id) << + NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id); + break; + case PHY_INTERFACE_MODE_SGMII: + val |= NSS_COMMON_CLK_SRC_CTRL_SGMII(gmac->id) << + NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id); + break; + default: + dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n", + phy_modes(gmac->phy_mode)); + return NULL; + } + regmap_write(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, val); + + /* Enable PTP clock */ + regmap_read(gmac->nss_common, NSS_COMMON_CLK_GATE, &val); + val |= NSS_COMMON_CLK_GATE_PTP_EN(gmac->id); + regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val); + + if (gmac->phy_mode == PHY_INTERFACE_MODE_SGMII) { + regmap_write(gmac->qsgmii_csr, QSGMII_PHY_SGMII_CTL(gmac->id), + QSGMII_PHY_CDR_EN | + QSGMII_PHY_RX_FRONT_EN | + QSGMII_PHY_RX_SIGNAL_DETECT_EN | + QSGMII_PHY_TX_DRIVER_EN | + QSGMII_PHY_QSGMII_EN | + 0x4 << QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET | + 0x3 << QSGMII_PHY_RX_DC_BIAS_OFFSET | + 0x1 << QSGMII_PHY_RX_INPUT_EQU_OFFSET | + 0x2 << QSGMII_PHY_CDR_PI_SLEW_OFFSET | + 0xC << QSGMII_PHY_TX_DRV_AMP_OFFSET); + } + + return gmac; +} + +static void ipq806x_gmac_fix_mac_speed(void *priv, unsigned int speed) +{ + struct ipq806x_gmac *gmac = priv; + + ipq806x_gmac_set_speed(gmac, speed); +} + +static const struct stmmac_of_data ipq806x_gmac_data = { + .has_gmac = 1, + .setup = ipq806x_gmac_setup, + .fix_mac_speed = ipq806x_gmac_fix_mac_speed, +}; + +static const struct of_device_id ipq806x_gmac_dwmac_match[] = { + { .compatible = "qcom,ipq806x-gmac", .data = &ipq806x_gmac_data }, + { } +}; +MODULE_DEVICE_TABLE(of, ipq806x_gmac_dwmac_match); + +static struct platform_driver ipq806x_gmac_dwmac_driver = { + .probe = stmmac_pltfr_probe, + .remove = stmmac_pltfr_remove, + .driver = { + .name = "ipq806x-gmac-dwmac", + .pm = &stmmac_pltfr_pm_ops, + .of_match_table = ipq806x_gmac_dwmac_match, + }, +}; +module_platform_driver(ipq806x_gmac_dwmac_driver); + +MODULE_AUTHOR("Mathieu Olivari <mathieu@codeaurora.org>"); +MODULE_DESCRIPTION("Qualcomm Atheros IPQ806x DWMAC specific glue layer"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 9cbcae2..1f3b33a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -125,6 +125,12 @@ struct stmmac_priv { int use_riwt; int irq_wake; spinlock_t ptp_lock; + +#ifdef CONFIG_DEBUG_FS + struct dentry *dbgfs_dir; + struct dentry *dbgfs_rings_status; + struct dentry *dbgfs_dma_cap; +#endif }; int stmmac_mdio_unregister(struct net_device *ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e4f2739..a515673 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -52,6 +52,7 @@ #include "stmmac_ptp.h" #include "stmmac.h" #include <linux/reset.h> +#include <linux/of_mdio.h> #define STMMAC_ALIGN(x) L1_CACHE_ALIGN(x) @@ -118,7 +119,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id); #ifdef CONFIG_DEBUG_FS static int stmmac_init_fs(struct net_device *dev); -static void stmmac_exit_fs(void); +static void stmmac_exit_fs(struct net_device *dev); #endif #define STMMAC_COAL_TIMER(x) (jiffies + usecs_to_jiffies(x)) @@ -816,18 +817,25 @@ static int stmmac_init_phy(struct net_device *dev) priv->speed = 0; priv->oldduplex = -1; - if (priv->plat->phy_bus_name) - snprintf(bus_id, MII_BUS_ID_SIZE, "%s-%x", - priv->plat->phy_bus_name, priv->plat->bus_id); - else - snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x", - priv->plat->bus_id); + if (priv->plat->phy_node) { + phydev = of_phy_connect(dev, priv->plat->phy_node, + &stmmac_adjust_link, 0, interface); + } else { + if (priv->plat->phy_bus_name) + snprintf(bus_id, MII_BUS_ID_SIZE, "%s-%x", + priv->plat->phy_bus_name, priv->plat->bus_id); + else + snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x", + priv->plat->bus_id); - snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id, - priv->plat->phy_addr); - pr_debug("stmmac_init_phy: trying to attach to %s\n", phy_id_fmt); + snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id, + priv->plat->phy_addr); + pr_debug("stmmac_init_phy: trying to attach to %s\n", + phy_id_fmt); - phydev = phy_connect(dev, phy_id_fmt, &stmmac_adjust_link, interface); + phydev = phy_connect(dev, phy_id_fmt, &stmmac_adjust_link, + interface); + } if (IS_ERR(phydev)) { pr_err("%s: Could not attach to PHY\n", dev->name); @@ -848,7 +856,7 @@ static int stmmac_init_phy(struct net_device *dev) * device as well. * Note: phydev->phy_id is the result of reading the UID PHY registers. */ - if (phydev->phy_id == 0) { + if (!priv->plat->phy_node && phydev->phy_id == 0) { phy_disconnect(phydev); return -ENODEV; } @@ -1914,7 +1922,7 @@ static int stmmac_release(struct net_device *dev) netif_carrier_off(dev); #ifdef CONFIG_DEBUG_FS - stmmac_exit_fs(); + stmmac_exit_fs(dev); #endif stmmac_release_ptp(priv); @@ -2506,8 +2514,6 @@ static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) #ifdef CONFIG_DEBUG_FS static struct dentry *stmmac_fs_dir; -static struct dentry *stmmac_rings_status; -static struct dentry *stmmac_dma_cap; static void sysfs_display_ring(void *head, int size, int extend_desc, struct seq_file *seq) @@ -2646,36 +2652,39 @@ static const struct file_operations stmmac_dma_cap_fops = { static int stmmac_init_fs(struct net_device *dev) { - /* Create debugfs entries */ - stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL); + struct stmmac_priv *priv = netdev_priv(dev); + + /* Create per netdev entries */ + priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir); - if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) { - pr_err("ERROR %s, debugfs create directory failed\n", - STMMAC_RESOURCE_NAME); + if (!priv->dbgfs_dir || IS_ERR(priv->dbgfs_dir)) { + pr_err("ERROR %s/%s, debugfs create directory failed\n", + STMMAC_RESOURCE_NAME, dev->name); return -ENOMEM; } /* Entry to report DMA RX/TX rings */ - stmmac_rings_status = debugfs_create_file("descriptors_status", - S_IRUGO, stmmac_fs_dir, dev, - &stmmac_rings_status_fops); + priv->dbgfs_rings_status = + debugfs_create_file("descriptors_status", S_IRUGO, + priv->dbgfs_dir, dev, + &stmmac_rings_status_fops); - if (!stmmac_rings_status || IS_ERR(stmmac_rings_status)) { + if (!priv->dbgfs_rings_status || IS_ERR(priv->dbgfs_rings_status)) { pr_info("ERROR creating stmmac ring debugfs file\n"); - debugfs_remove(stmmac_fs_dir); + debugfs_remove_recursive(priv->dbgfs_dir); return -ENOMEM; } /* Entry to report the DMA HW features */ - stmmac_dma_cap = debugfs_create_file("dma_cap", S_IRUGO, stmmac_fs_dir, - dev, &stmmac_dma_cap_fops); + priv->dbgfs_dma_cap = debugfs_create_file("dma_cap", S_IRUGO, + priv->dbgfs_dir, + dev, &stmmac_dma_cap_fops); - if (!stmmac_dma_cap || IS_ERR(stmmac_dma_cap)) { + if (!priv->dbgfs_dma_cap || IS_ERR(priv->dbgfs_dma_cap)) { pr_info("ERROR creating stmmac MMC debugfs file\n"); - debugfs_remove(stmmac_rings_status); - debugfs_remove(stmmac_fs_dir); + debugfs_remove_recursive(priv->dbgfs_dir); return -ENOMEM; } @@ -2683,11 +2692,11 @@ static int stmmac_init_fs(struct net_device *dev) return 0; } -static void stmmac_exit_fs(void) +static void stmmac_exit_fs(struct net_device *dev) { - debugfs_remove(stmmac_rings_status); - debugfs_remove(stmmac_dma_cap); - debugfs_remove(stmmac_fs_dir); + struct stmmac_priv *priv = netdev_priv(dev); + + debugfs_remove_recursive(priv->dbgfs_dir); } #endif /* CONFIG_DEBUG_FS */ @@ -3155,6 +3164,35 @@ err: __setup("stmmaceth=", stmmac_cmdline_opt); #endif /* MODULE */ +static int __init stmmac_init(void) +{ +#ifdef CONFIG_DEBUG_FS + /* Create debugfs main directory if it doesn't exist yet */ + if (!stmmac_fs_dir) { + stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL); + + if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) { + pr_err("ERROR %s, debugfs create directory failed\n", + STMMAC_RESOURCE_NAME); + + return -ENOMEM; + } + } +#endif + + return 0; +} + +static void __exit stmmac_exit(void) +{ +#ifdef CONFIG_DEBUG_FS + debugfs_remove_recursive(stmmac_fs_dir); +#endif +} + +module_init(stmmac_init) +module_exit(stmmac_exit) + MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet device driver"); MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 1664c01..f3918c7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -28,6 +28,7 @@ #include <linux/of.h> #include <linux/of_net.h> #include <linux/of_device.h> +#include <linux/of_mdio.h> #include "stmmac.h" #include "stmmac_platform.h" @@ -144,13 +145,24 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, /* Default to phy auto-detection */ plat->phy_addr = -1; + /* If we find a phy-handle property, use it as the PHY */ + plat->phy_node = of_parse_phandle(np, "phy-handle", 0); + + /* If phy-handle is not specified, check if we have a fixed-phy */ + if (!plat->phy_node && of_phy_is_fixed_link(np)) { + if ((of_phy_register_fixed_link(np) < 0)) + return -ENODEV; + + plat->phy_node = of_node_get(np); + } + /* "snps,phy-addr" is not a standard property. Mark it as deprecated * and warn of its use. Remove this when phy node support is added. */ if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); - if (plat->phy_bus_name) + if (plat->phy_node || plat->phy_bus_name) plat->mdio_bus_data = NULL; else plat->mdio_bus_data = @@ -208,8 +220,10 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, if (of_find_property(np, "snps,pbl", NULL)) { dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL); - if (!dma_cfg) + if (!dma_cfg) { + of_node_put(np); return -ENOMEM; + } plat->dma_cfg = dma_cfg; of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl); dma_cfg->fixed_burst = diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index b536b4c..4628205 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1361,7 +1361,6 @@ static int cpsw_ndo_stop(struct net_device *ndev) if (cpsw_common_res_usage_state(priv) <= 1) { cpts_unregister(priv->cpts); cpsw_intr_disable(priv); - cpdma_ctlr_int_ctrl(priv->dma, false); cpdma_ctlr_stop(priv->dma); cpsw_ale_stop(priv->ale); } @@ -1456,7 +1455,7 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv) if (priv->cpts->rx_enable) ctrl |= CTRL_V2_RX_TS_BITS; - break; + break; case CPSW_VERSION_3: default: ctrl &= ~CTRL_V3_ALL_TS_MASK; @@ -1466,7 +1465,7 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv) if (priv->cpts->rx_enable) ctrl |= CTRL_V3_RX_TS_BITS; - break; + break; } mtype = (30 << TS_SEQ_ID_OFFSET_SHIFT) | EVENT_MSG_BITS; @@ -1589,10 +1588,8 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev) cpsw_err(priv, tx_err, "transmit timeout, restarting dma\n"); ndev->stats.tx_errors++; cpsw_intr_disable(priv); - cpdma_ctlr_int_ctrl(priv->dma, false); cpdma_chan_stop(priv->txch); cpdma_chan_start(priv->txch); - cpdma_ctlr_int_ctrl(priv->dma, true); cpsw_intr_enable(priv); } @@ -1629,10 +1626,8 @@ static void cpsw_ndo_poll_controller(struct net_device *ndev) struct cpsw_priv *priv = netdev_priv(ndev); cpsw_intr_disable(priv); - cpdma_ctlr_int_ctrl(priv->dma, false); cpsw_rx_interrupt(priv->irqs_table[0], priv); cpsw_tx_interrupt(priv->irqs_table[1], priv); - cpdma_ctlr_int_ctrl(priv->dma, true); cpsw_intr_enable(priv); } #endif diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 6e927b4..43b061b 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -268,39 +268,6 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid) } EXPORT_SYMBOL_GPL(cpsw_ale_flush_multicast); -static void cpsw_ale_flush_ucast(struct cpsw_ale *ale, u32 *ale_entry, - int port_mask) -{ - int port; - - port = cpsw_ale_get_port_num(ale_entry); - if ((BIT(port) & port_mask) == 0) - return; /* ports dont intersect, not interested */ - cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); -} - -int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask) -{ - u32 ale_entry[ALE_ENTRY_WORDS]; - int ret, idx; - - for (idx = 0; idx < ale->params.ale_entries; idx++) { - cpsw_ale_read(ale, idx, ale_entry); - ret = cpsw_ale_get_entry_type(ale_entry); - if (ret != ALE_TYPE_ADDR && ret != ALE_TYPE_VLAN_ADDR) - continue; - - if (cpsw_ale_get_mcast(ale_entry)) - cpsw_ale_flush_mcast(ale, ale_entry, port_mask); - else - cpsw_ale_flush_ucast(ale, ale_entry, port_mask); - - cpsw_ale_write(ale, idx, ale_entry); - } - return 0; -} -EXPORT_SYMBOL_GPL(cpsw_ale_flush); - static inline void cpsw_ale_set_vlan_entry_type(u32 *ale_entry, int flags, u16 vid) { @@ -752,18 +719,6 @@ static void cpsw_ale_timer(unsigned long arg) } } -int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout) -{ - del_timer_sync(&ale->timer); - ale->ageout = ageout * HZ; - if (ale->ageout) { - ale->timer.expires = jiffies + ale->ageout; - add_timer(&ale->timer); - } - return 0; -} -EXPORT_SYMBOL_GPL(cpsw_ale_set_ageout); - void cpsw_ale_start(struct cpsw_ale *ale) { u32 rev; diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h index af1e7ec..a700189 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.h +++ b/drivers/net/ethernet/ti/cpsw_ale.h @@ -90,8 +90,6 @@ int cpsw_ale_destroy(struct cpsw_ale *ale); void cpsw_ale_start(struct cpsw_ale *ale); void cpsw_ale_stop(struct cpsw_ale *ale); -int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout); -int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask); int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid); int cpsw_ale_add_ucast(struct cpsw_ale *ale, u8 *addr, int port, int flags, u16 vid); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index b7eafa4..78d49d1 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -44,7 +44,9 @@ struct geneve_dev { struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for geneve tunnel */ struct geneve_sock *sock; /* socket used for geneve tunnel */ - u8 vni[3]; /* virtual network ID for tunnel */ + u8 vni[3]; /* virtual network ID for tunnel */ + u8 ttl; /* TTL override */ + u8 tos; /* TOS override */ struct sockaddr_in remote; /* IPv4 address for link partner */ struct list_head next; /* geneve's per namespace list */ }; @@ -184,7 +186,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) struct flowi4 fl4; int err; __be16 sport; - __u8 tos, ttl = 0; + __u8 tos, ttl; iip = ip_hdr(skb); @@ -193,7 +195,12 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) /* TODO: port min/max limits should be configurable */ sport = udp_flow_src_port(dev_net(dev), skb, 0, 0, true); + tos = geneve->tos; + if (tos == 1) + tos = ip_tunnel_get_dsfield(iip, skb); + memset(&fl4, 0, sizeof(fl4)); + fl4.flowi4_tos = RT_TOS(tos); fl4.daddr = geneve->remote.sin_addr.s_addr; rt = ip_route_output_key(geneve->net, &fl4); if (IS_ERR(rt)) { @@ -207,11 +214,10 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) goto rt_tx_error; } - /* TODO: tos and ttl should be configurable */ - - tos = ip_tunnel_ecn_encap(0, iip, skb); + tos = ip_tunnel_ecn_encap(tos, iip, skb); - if (IN_MULTICAST(ntohl(fl4.daddr))) + ttl = geneve->ttl; + if (!ttl && IN_MULTICAST(ntohl(fl4.daddr))) ttl = 1; ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); @@ -297,6 +303,8 @@ static void geneve_setup(struct net_device *dev) static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_ID] = { .type = NLA_U32 }, [IFLA_GENEVE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, + [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, }; static int geneve_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -364,6 +372,12 @@ static int geneve_newlink(struct net *net, struct net_device *dev, if (err) return err; + if (data[IFLA_GENEVE_TTL]) + geneve->ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); + + if (data[IFLA_GENEVE_TOS]) + geneve->tos = nla_get_u8(data[IFLA_GENEVE_TOS]); + list_add(&geneve->next, &gn->geneve_list); hlist_add_head_rcu(&geneve->hlist, &gn->vni_list[hash]); @@ -386,6 +400,8 @@ static size_t geneve_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GENEVE_ID */ nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */ + nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ + nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ 0; } @@ -402,6 +418,10 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) geneve->remote.sin_addr.s_addr)) goto nla_put_failure; + if (nla_put_u8(skb, IFLA_GENEVE_TTL, geneve->ttl) || + nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos)) + goto nla_put_failure; + return 0; nla_put_failure: diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index ddcc7f8..dd45440 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -161,6 +161,7 @@ struct netvsc_device_info { unsigned char mac_adr[ETH_ALEN]; bool link_state; /* 0 - link up, 1 - link down */ int ring_size; + u32 max_num_vrss_chns; }; enum rndis_device_state { diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index b024968..06de98a 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -227,13 +227,18 @@ static int netvsc_init_buf(struct hv_device *device) struct netvsc_device *net_device; struct nvsp_message *init_packet; struct net_device *ndev; + int node; net_device = get_outbound_net_device(device); if (!net_device) return -ENODEV; ndev = net_device->ndev; - net_device->recv_buf = vzalloc(net_device->recv_buf_size); + node = cpu_to_node(device->channel->target_cpu); + net_device->recv_buf = vzalloc_node(net_device->recv_buf_size, node); + if (!net_device->recv_buf) + net_device->recv_buf = vzalloc(net_device->recv_buf_size); + if (!net_device->recv_buf) { netdev_err(ndev, "unable to allocate receive " "buffer of size %d\n", net_device->recv_buf_size); @@ -321,7 +326,9 @@ static int netvsc_init_buf(struct hv_device *device) /* Now setup the send buffer. */ - net_device->send_buf = vzalloc(net_device->send_buf_size); + net_device->send_buf = vzalloc_node(net_device->send_buf_size, node); + if (!net_device->send_buf) + net_device->send_buf = vzalloc(net_device->send_buf_size); if (!net_device->send_buf) { netdev_err(ndev, "unable to allocate send " "buffer of size %d\n", net_device->send_buf_size); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index d9c88bc..358475e 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -46,6 +46,8 @@ static int ring_size = 128; module_param(ring_size, int, S_IRUGO); MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)"); +static int max_num_vrss_chns = 8; + static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN | NETIF_MSG_RX_ERR | @@ -755,6 +757,7 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu) ndevctx->device_ctx = hdev; hv_set_drvdata(hdev, ndev); device_info.ring_size = ring_size; + device_info.max_num_vrss_chns = max_num_vrss_chns; rndis_filter_device_add(hdev, &device_info); netif_tx_wake_all_queues(ndev); @@ -975,6 +978,7 @@ static int netvsc_probe(struct hv_device *dev, /* Notify the netvsc driver of the new device */ device_info.ring_size = ring_size; + device_info.max_num_vrss_chns = max_num_vrss_chns; ret = rndis_filter_device_add(dev, &device_info); if (ret != 0) { netdev_err(net, "unable to add netvsc device (ret %d)\n", ret); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 9118cea..006c1b8 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1013,6 +1013,9 @@ int rndis_filter_device_add(struct hv_device *dev, struct ndis_recv_scale_cap rsscap; u32 rsscap_size = sizeof(struct ndis_recv_scale_cap); u32 mtu, size; + u32 num_rss_qs; + const struct cpumask *node_cpu_mask; + u32 num_possible_rss_qs; rndis_device = get_rndis_device(); if (!rndis_device) @@ -1100,9 +1103,18 @@ int rndis_filter_device_add(struct hv_device *dev, if (ret || rsscap.num_recv_que < 2) goto out; + num_rss_qs = min(device_info->max_num_vrss_chns, rsscap.num_recv_que); + net_device->max_chn = rsscap.num_recv_que; - net_device->num_chn = (num_online_cpus() < rsscap.num_recv_que) ? - num_online_cpus() : rsscap.num_recv_que; + + /* + * We will limit the VRSS channels to the number CPUs in the NUMA node + * the primary channel is currently bound to. + */ + node_cpu_mask = cpumask_of_node(cpu_to_node(dev->channel->target_cpu)); + num_possible_rss_qs = cpumask_weight(node_cpu_mask); + net_device->num_chn = min(num_possible_rss_qs, num_rss_qs); + if (net_device->num_chn == 1) goto out; diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig index 1a3c3e5..1dd5ab8 100644 --- a/drivers/net/ieee802154/Kconfig +++ b/drivers/net/ieee802154/Kconfig @@ -53,3 +53,13 @@ config IEEE802154_CC2520 This driver can also be built as a module. To do so, say M here. the module will be called 'cc2520'. + +config IEEE802154_ATUSB + tristate "ATUSB transceiver driver" + depends on IEEE802154_DRIVERS && MAC802154 && USB + ---help--- + Say Y here to enable the ATUSB IEEE 802.15.4 wireless + controller. + + This driver can also be built as a module. To do so say M here. + The module will be called 'atusb'. diff --git a/drivers/net/ieee802154/Makefile b/drivers/net/ieee802154/Makefile index d77fa4d..cf1d2a6 100644 --- a/drivers/net/ieee802154/Makefile +++ b/drivers/net/ieee802154/Makefile @@ -2,3 +2,4 @@ obj-$(CONFIG_IEEE802154_FAKELB) += fakelb.o obj-$(CONFIG_IEEE802154_AT86RF230) += at86rf230.o obj-$(CONFIG_IEEE802154_MRF24J40) += mrf24j40.o obj-$(CONFIG_IEEE802154_CC2520) += cc2520.o +obj-$(CONFIG_IEEE802154_ATUSB) += atusb.o diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 67d00fb..2f25a5e 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -35,6 +35,8 @@ #include <net/mac802154.h> #include <net/cfg802154.h> +#include "at86rf230.h" + struct at86rf230_local; /* at86rf2xx chip depend data. * All timings are in us. @@ -50,7 +52,7 @@ struct at86rf2xx_chip_data { int rssi_base_val; int (*set_channel)(struct at86rf230_local *, u8, u8); - int (*get_desense_steps)(struct at86rf230_local *, s32); + int (*set_txpower)(struct at86rf230_local *, s32); }; #define AT86RF2XX_MAX_BUF (127 + 3) @@ -102,200 +104,6 @@ struct at86rf230_local { struct at86rf230_state_change tx; }; -#define RG_TRX_STATUS (0x01) -#define SR_TRX_STATUS 0x01, 0x1f, 0 -#define SR_RESERVED_01_3 0x01, 0x20, 5 -#define SR_CCA_STATUS 0x01, 0x40, 6 -#define SR_CCA_DONE 0x01, 0x80, 7 -#define RG_TRX_STATE (0x02) -#define SR_TRX_CMD 0x02, 0x1f, 0 -#define SR_TRAC_STATUS 0x02, 0xe0, 5 -#define RG_TRX_CTRL_0 (0x03) -#define SR_CLKM_CTRL 0x03, 0x07, 0 -#define SR_CLKM_SHA_SEL 0x03, 0x08, 3 -#define SR_PAD_IO_CLKM 0x03, 0x30, 4 -#define SR_PAD_IO 0x03, 0xc0, 6 -#define RG_TRX_CTRL_1 (0x04) -#define SR_IRQ_POLARITY 0x04, 0x01, 0 -#define SR_IRQ_MASK_MODE 0x04, 0x02, 1 -#define SR_SPI_CMD_MODE 0x04, 0x0c, 2 -#define SR_RX_BL_CTRL 0x04, 0x10, 4 -#define SR_TX_AUTO_CRC_ON 0x04, 0x20, 5 -#define SR_IRQ_2_EXT_EN 0x04, 0x40, 6 -#define SR_PA_EXT_EN 0x04, 0x80, 7 -#define RG_PHY_TX_PWR (0x05) -#define SR_TX_PWR 0x05, 0x0f, 0 -#define SR_PA_LT 0x05, 0x30, 4 -#define SR_PA_BUF_LT 0x05, 0xc0, 6 -#define RG_PHY_RSSI (0x06) -#define SR_RSSI 0x06, 0x1f, 0 -#define SR_RND_VALUE 0x06, 0x60, 5 -#define SR_RX_CRC_VALID 0x06, 0x80, 7 -#define RG_PHY_ED_LEVEL (0x07) -#define SR_ED_LEVEL 0x07, 0xff, 0 -#define RG_PHY_CC_CCA (0x08) -#define SR_CHANNEL 0x08, 0x1f, 0 -#define SR_CCA_MODE 0x08, 0x60, 5 -#define SR_CCA_REQUEST 0x08, 0x80, 7 -#define RG_CCA_THRES (0x09) -#define SR_CCA_ED_THRES 0x09, 0x0f, 0 -#define SR_RESERVED_09_1 0x09, 0xf0, 4 -#define RG_RX_CTRL (0x0a) -#define SR_PDT_THRES 0x0a, 0x0f, 0 -#define SR_RESERVED_0a_1 0x0a, 0xf0, 4 -#define RG_SFD_VALUE (0x0b) -#define SR_SFD_VALUE 0x0b, 0xff, 0 -#define RG_TRX_CTRL_2 (0x0c) -#define SR_OQPSK_DATA_RATE 0x0c, 0x03, 0 -#define SR_SUB_MODE 0x0c, 0x04, 2 -#define SR_BPSK_QPSK 0x0c, 0x08, 3 -#define SR_OQPSK_SUB1_RC_EN 0x0c, 0x10, 4 -#define SR_RESERVED_0c_5 0x0c, 0x60, 5 -#define SR_RX_SAFE_MODE 0x0c, 0x80, 7 -#define RG_ANT_DIV (0x0d) -#define SR_ANT_CTRL 0x0d, 0x03, 0 -#define SR_ANT_EXT_SW_EN 0x0d, 0x04, 2 -#define SR_ANT_DIV_EN 0x0d, 0x08, 3 -#define SR_RESERVED_0d_2 0x0d, 0x70, 4 -#define SR_ANT_SEL 0x0d, 0x80, 7 -#define RG_IRQ_MASK (0x0e) -#define SR_IRQ_MASK 0x0e, 0xff, 0 -#define RG_IRQ_STATUS (0x0f) -#define SR_IRQ_0_PLL_LOCK 0x0f, 0x01, 0 -#define SR_IRQ_1_PLL_UNLOCK 0x0f, 0x02, 1 -#define SR_IRQ_2_RX_START 0x0f, 0x04, 2 -#define SR_IRQ_3_TRX_END 0x0f, 0x08, 3 -#define SR_IRQ_4_CCA_ED_DONE 0x0f, 0x10, 4 -#define SR_IRQ_5_AMI 0x0f, 0x20, 5 -#define SR_IRQ_6_TRX_UR 0x0f, 0x40, 6 -#define SR_IRQ_7_BAT_LOW 0x0f, 0x80, 7 -#define RG_VREG_CTRL (0x10) -#define SR_RESERVED_10_6 0x10, 0x03, 0 -#define SR_DVDD_OK 0x10, 0x04, 2 -#define SR_DVREG_EXT 0x10, 0x08, 3 -#define SR_RESERVED_10_3 0x10, 0x30, 4 -#define SR_AVDD_OK 0x10, 0x40, 6 -#define SR_AVREG_EXT 0x10, 0x80, 7 -#define RG_BATMON (0x11) -#define SR_BATMON_VTH 0x11, 0x0f, 0 -#define SR_BATMON_HR 0x11, 0x10, 4 -#define SR_BATMON_OK 0x11, 0x20, 5 -#define SR_RESERVED_11_1 0x11, 0xc0, 6 -#define RG_XOSC_CTRL (0x12) -#define SR_XTAL_TRIM 0x12, 0x0f, 0 -#define SR_XTAL_MODE 0x12, 0xf0, 4 -#define RG_RX_SYN (0x15) -#define SR_RX_PDT_LEVEL 0x15, 0x0f, 0 -#define SR_RESERVED_15_2 0x15, 0x70, 4 -#define SR_RX_PDT_DIS 0x15, 0x80, 7 -#define RG_XAH_CTRL_1 (0x17) -#define SR_RESERVED_17_8 0x17, 0x01, 0 -#define SR_AACK_PROM_MODE 0x17, 0x02, 1 -#define SR_AACK_ACK_TIME 0x17, 0x04, 2 -#define SR_RESERVED_17_5 0x17, 0x08, 3 -#define SR_AACK_UPLD_RES_FT 0x17, 0x10, 4 -#define SR_AACK_FLTR_RES_FT 0x17, 0x20, 5 -#define SR_CSMA_LBT_MODE 0x17, 0x40, 6 -#define SR_RESERVED_17_1 0x17, 0x80, 7 -#define RG_FTN_CTRL (0x18) -#define SR_RESERVED_18_2 0x18, 0x7f, 0 -#define SR_FTN_START 0x18, 0x80, 7 -#define RG_PLL_CF (0x1a) -#define SR_RESERVED_1a_2 0x1a, 0x7f, 0 -#define SR_PLL_CF_START 0x1a, 0x80, 7 -#define RG_PLL_DCU (0x1b) -#define SR_RESERVED_1b_3 0x1b, 0x3f, 0 -#define SR_RESERVED_1b_2 0x1b, 0x40, 6 -#define SR_PLL_DCU_START 0x1b, 0x80, 7 -#define RG_PART_NUM (0x1c) -#define SR_PART_NUM 0x1c, 0xff, 0 -#define RG_VERSION_NUM (0x1d) -#define SR_VERSION_NUM 0x1d, 0xff, 0 -#define RG_MAN_ID_0 (0x1e) -#define SR_MAN_ID_0 0x1e, 0xff, 0 -#define RG_MAN_ID_1 (0x1f) -#define SR_MAN_ID_1 0x1f, 0xff, 0 -#define RG_SHORT_ADDR_0 (0x20) -#define SR_SHORT_ADDR_0 0x20, 0xff, 0 -#define RG_SHORT_ADDR_1 (0x21) -#define SR_SHORT_ADDR_1 0x21, 0xff, 0 -#define RG_PAN_ID_0 (0x22) -#define SR_PAN_ID_0 0x22, 0xff, 0 -#define RG_PAN_ID_1 (0x23) -#define SR_PAN_ID_1 0x23, 0xff, 0 -#define RG_IEEE_ADDR_0 (0x24) -#define SR_IEEE_ADDR_0 0x24, 0xff, 0 -#define RG_IEEE_ADDR_1 (0x25) -#define SR_IEEE_ADDR_1 0x25, 0xff, 0 -#define RG_IEEE_ADDR_2 (0x26) -#define SR_IEEE_ADDR_2 0x26, 0xff, 0 -#define RG_IEEE_ADDR_3 (0x27) -#define SR_IEEE_ADDR_3 0x27, 0xff, 0 -#define RG_IEEE_ADDR_4 (0x28) -#define SR_IEEE_ADDR_4 0x28, 0xff, 0 -#define RG_IEEE_ADDR_5 (0x29) -#define SR_IEEE_ADDR_5 0x29, 0xff, 0 -#define RG_IEEE_ADDR_6 (0x2a) -#define SR_IEEE_ADDR_6 0x2a, 0xff, 0 -#define RG_IEEE_ADDR_7 (0x2b) -#define SR_IEEE_ADDR_7 0x2b, 0xff, 0 -#define RG_XAH_CTRL_0 (0x2c) -#define SR_SLOTTED_OPERATION 0x2c, 0x01, 0 -#define SR_MAX_CSMA_RETRIES 0x2c, 0x0e, 1 -#define SR_MAX_FRAME_RETRIES 0x2c, 0xf0, 4 -#define RG_CSMA_SEED_0 (0x2d) -#define SR_CSMA_SEED_0 0x2d, 0xff, 0 -#define RG_CSMA_SEED_1 (0x2e) -#define SR_CSMA_SEED_1 0x2e, 0x07, 0 -#define SR_AACK_I_AM_COORD 0x2e, 0x08, 3 -#define SR_AACK_DIS_ACK 0x2e, 0x10, 4 -#define SR_AACK_SET_PD 0x2e, 0x20, 5 -#define SR_AACK_FVN_MODE 0x2e, 0xc0, 6 -#define RG_CSMA_BE (0x2f) -#define SR_MIN_BE 0x2f, 0x0f, 0 -#define SR_MAX_BE 0x2f, 0xf0, 4 - -#define CMD_REG 0x80 -#define CMD_REG_MASK 0x3f -#define CMD_WRITE 0x40 -#define CMD_FB 0x20 - -#define IRQ_BAT_LOW (1 << 7) -#define IRQ_TRX_UR (1 << 6) -#define IRQ_AMI (1 << 5) -#define IRQ_CCA_ED (1 << 4) -#define IRQ_TRX_END (1 << 3) -#define IRQ_RX_START (1 << 2) -#define IRQ_PLL_UNL (1 << 1) -#define IRQ_PLL_LOCK (1 << 0) - -#define IRQ_ACTIVE_HIGH 0 -#define IRQ_ACTIVE_LOW 1 - -#define STATE_P_ON 0x00 /* BUSY */ -#define STATE_BUSY_RX 0x01 -#define STATE_BUSY_TX 0x02 -#define STATE_FORCE_TRX_OFF 0x03 -#define STATE_FORCE_TX_ON 0x04 /* IDLE */ -/* 0x05 */ /* INVALID_PARAMETER */ -#define STATE_RX_ON 0x06 -/* 0x07 */ /* SUCCESS */ -#define STATE_TRX_OFF 0x08 -#define STATE_TX_ON 0x09 -/* 0x0a - 0x0e */ /* 0x0a - UNSUPPORTED_ATTRIBUTE */ -#define STATE_SLEEP 0x0F -#define STATE_PREP_DEEP_SLEEP 0x10 -#define STATE_BUSY_RX_AACK 0x11 -#define STATE_BUSY_TX_ARET 0x12 -#define STATE_RX_AACK_ON 0x16 -#define STATE_TX_ARET_ON 0x19 -#define STATE_RX_ON_NOCLK 0x1C -#define STATE_RX_AACK_ON_NOCLK 0x1D -#define STATE_BUSY_RX_AACK_NOCLK 0x1E -#define STATE_TRANSITION_IN_PROGRESS 0x1F - -#define TRX_STATE_MASK (0x1F) - #define AT86RF2XX_NUMREGS 0x3F static void @@ -1010,7 +818,7 @@ at86rf230_xmit_start(void *context) if (lp->is_tx_from_off) { lp->is_tx_from_off = false; at86rf230_async_state_change(lp, ctx, STATE_TX_ARET_ON, - at86rf230_xmit_tx_on, + at86rf230_write_frame, false); } else { at86rf230_async_state_change(lp, ctx, STATE_TX_ON, @@ -1076,6 +884,50 @@ at86rf23x_set_channel(struct at86rf230_local *lp, u8 page, u8 channel) return at86rf230_write_subreg(lp, SR_CHANNEL, channel); } +#define AT86RF2XX_MAX_ED_LEVELS 0xF +static const s32 at86rf23x_ed_levels[AT86RF2XX_MAX_ED_LEVELS + 1] = { + -9100, -8900, -8700, -8500, -8300, -8100, -7900, -7700, -7500, -7300, + -7100, -6900, -6700, -6500, -6300, -6100, +}; + +static const s32 at86rf212_ed_levels_100[AT86RF2XX_MAX_ED_LEVELS + 1] = { + -10000, -9800, -9600, -9400, -9200, -9000, -8800, -8600, -8400, -8200, + -8000, -7800, -7600, -7400, -7200, -7000, +}; + +static const s32 at86rf212_ed_levels_98[AT86RF2XX_MAX_ED_LEVELS + 1] = { + -9800, -9600, -9400, -9200, -9000, -8800, -8600, -8400, -8200, -8000, + -7800, -7600, -7400, -7200, -7000, -6800, +}; + +static inline int +at86rf212_update_cca_ed_level(struct at86rf230_local *lp, int rssi_base_val) +{ + unsigned int cca_ed_thres; + int rc; + + rc = at86rf230_read_subreg(lp, SR_CCA_ED_THRES, &cca_ed_thres); + if (rc < 0) + return rc; + + switch (rssi_base_val) { + case -98: + lp->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_98; + lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_98); + lp->hw->phy->cca_ed_level = at86rf212_ed_levels_98[cca_ed_thres]; + break; + case -100: + lp->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_100; + lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_100); + lp->hw->phy->cca_ed_level = at86rf212_ed_levels_100[cca_ed_thres]; + break; + default: + WARN_ON(1); + } + + return 0; +} + static int at86rf212_set_channel(struct at86rf230_local *lp, u8 page, u8 channel) { @@ -1098,6 +950,10 @@ at86rf212_set_channel(struct at86rf230_local *lp, u8 page, u8 channel) if (rc < 0) return rc; + rc = at86rf212_update_cca_ed_level(lp, lp->data->rssi_base_val); + if (rc < 0) + return rc; + /* This sets the symbol_duration according frequency on the 212. * TODO move this handling while set channel and page in cfg802154. * We can do that, this timings are according 802.15.4 standard. @@ -1193,23 +1049,56 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw, return 0; } +#define AT86RF23X_MAX_TX_POWERS 0xF +static const s32 at86rf233_powers[AT86RF23X_MAX_TX_POWERS + 1] = { + 400, 370, 340, 300, 250, 200, 100, 0, -100, -200, -300, -400, -600, + -800, -1200, -1700, +}; + +static const s32 at86rf231_powers[AT86RF23X_MAX_TX_POWERS + 1] = { + 300, 280, 230, 180, 130, 70, 0, -100, -200, -300, -400, -500, -700, + -900, -1200, -1700, +}; + +#define AT86RF212_MAX_TX_POWERS 0x1F +static const s32 at86rf212_powers[AT86RF212_MAX_TX_POWERS + 1] = { + 500, 400, 300, 200, 100, 0, -100, -200, -300, -400, -500, -600, -700, + -800, -900, -1000, -1100, -1200, -1300, -1400, -1500, -1600, -1700, + -1800, -1900, -2000, -2100, -2200, -2300, -2400, -2500, -2600, +}; + +static int +at86rf23x_set_txpower(struct at86rf230_local *lp, s32 mbm) +{ + u32 i; + + for (i = 0; i < lp->hw->phy->supported.tx_powers_size; i++) { + if (lp->hw->phy->supported.tx_powers[i] == mbm) + return at86rf230_write_subreg(lp, SR_TX_PWR_23X, i); + } + + return -EINVAL; +} + static int -at86rf230_set_txpower(struct ieee802154_hw *hw, s8 db) +at86rf212_set_txpower(struct at86rf230_local *lp, s32 mbm) { - struct at86rf230_local *lp = hw->priv; + u32 i; - /* typical maximum output is 5dBm with RG_PHY_TX_PWR 0x60, lower five - * bits decrease power in 1dB steps. 0x60 represents extra PA gain of - * 0dB. - * thus, supported values for db range from -26 to 5, for 31dB of - * reduction to 0dB of reduction. - */ - if (db > 5 || db < -26) - return -EINVAL; + for (i = 0; i < lp->hw->phy->supported.tx_powers_size; i++) { + if (lp->hw->phy->supported.tx_powers[i] == mbm) + return at86rf230_write_subreg(lp, SR_TX_PWR_212, i); + } - db = -(db - 5); + return -EINVAL; +} + +static int +at86rf230_set_txpower(struct ieee802154_hw *hw, s32 mbm) +{ + struct at86rf230_local *lp = hw->priv; - return __at86rf230_write(lp, RG_PHY_TX_PWR, 0x60 | db); + return lp->data->set_txpower(lp, mbm); } static int @@ -1254,28 +1143,19 @@ at86rf230_set_cca_mode(struct ieee802154_hw *hw, return at86rf230_write_subreg(lp, SR_CCA_MODE, val); } -static int -at86rf212_get_desens_steps(struct at86rf230_local *lp, s32 level) -{ - return (level - lp->data->rssi_base_val) * 100 / 207; -} - -static int -at86rf23x_get_desens_steps(struct at86rf230_local *lp, s32 level) -{ - return (level - lp->data->rssi_base_val) / 2; -} static int -at86rf230_set_cca_ed_level(struct ieee802154_hw *hw, s32 level) +at86rf230_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm) { struct at86rf230_local *lp = hw->priv; + u32 i; - if (level < lp->data->rssi_base_val || level > 30) - return -EINVAL; + for (i = 0; i < hw->phy->supported.cca_ed_levels_size; i++) { + if (hw->phy->supported.cca_ed_levels[i] == mbm) + return at86rf230_write_subreg(lp, SR_CCA_ED_THRES, i); + } - return at86rf230_write_subreg(lp, SR_CCA_ED_THRES, - lp->data->get_desense_steps(lp, level)); + return -EINVAL; } static int @@ -1365,7 +1245,7 @@ static struct at86rf2xx_chip_data at86rf233_data = { .t_p_ack = 545, .rssi_base_val = -91, .set_channel = at86rf23x_set_channel, - .get_desense_steps = at86rf23x_get_desens_steps + .set_txpower = at86rf23x_set_txpower, }; static struct at86rf2xx_chip_data at86rf231_data = { @@ -1378,7 +1258,7 @@ static struct at86rf2xx_chip_data at86rf231_data = { .t_p_ack = 545, .rssi_base_val = -91, .set_channel = at86rf23x_set_channel, - .get_desense_steps = at86rf23x_get_desens_steps + .set_txpower = at86rf23x_set_txpower, }; static struct at86rf2xx_chip_data at86rf212_data = { @@ -1391,7 +1271,7 @@ static struct at86rf2xx_chip_data at86rf212_data = { .t_p_ack = 545, .rssi_base_val = -100, .set_channel = at86rf212_set_channel, - .get_desense_steps = at86rf212_get_desens_steps + .set_txpower = at86rf212_set_txpower, }; static int at86rf230_hw_init(struct at86rf230_local *lp, u8 xtal_trim) @@ -1564,8 +1444,21 @@ at86rf230_detect_device(struct at86rf230_local *lp) } lp->hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AACK | - IEEE802154_HW_TXPOWER | IEEE802154_HW_ARET | - IEEE802154_HW_AFILT | IEEE802154_HW_PROMISCUOUS; + IEEE802154_HW_CSMA_PARAMS | + IEEE802154_HW_FRAME_RETRIES | IEEE802154_HW_AFILT | + IEEE802154_HW_PROMISCUOUS; + + lp->hw->phy->flags = WPAN_PHY_FLAG_TXPOWER | + WPAN_PHY_FLAG_CCA_ED_LEVEL | + WPAN_PHY_FLAG_CCA_MODE; + + lp->hw->phy->supported.cca_modes = BIT(NL802154_CCA_ENERGY) | + BIT(NL802154_CCA_CARRIER) | BIT(NL802154_CCA_ENERGY_CARRIER); + lp->hw->phy->supported.cca_opts = BIT(NL802154_CCA_OPT_ENERGY_CARRIER_AND) | + BIT(NL802154_CCA_OPT_ENERGY_CARRIER_OR); + + lp->hw->phy->supported.cca_ed_levels = at86rf23x_ed_levels; + lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf23x_ed_levels); lp->hw->phy->cca.mode = NL802154_CCA_ENERGY; @@ -1573,36 +1466,49 @@ at86rf230_detect_device(struct at86rf230_local *lp) case 2: chip = "at86rf230"; rc = -ENOTSUPP; - break; + goto not_supp; case 3: chip = "at86rf231"; lp->data = &at86rf231_data; - lp->hw->phy->channels_supported[0] = 0x7FFF800; + lp->hw->phy->supported.channels[0] = 0x7FFF800; lp->hw->phy->current_channel = 11; lp->hw->phy->symbol_duration = 16; + lp->hw->phy->supported.tx_powers = at86rf231_powers; + lp->hw->phy->supported.tx_powers_size = ARRAY_SIZE(at86rf231_powers); break; case 7: chip = "at86rf212"; lp->data = &at86rf212_data; lp->hw->flags |= IEEE802154_HW_LBT; - lp->hw->phy->channels_supported[0] = 0x00007FF; - lp->hw->phy->channels_supported[2] = 0x00007FF; + lp->hw->phy->supported.channels[0] = 0x00007FF; + lp->hw->phy->supported.channels[2] = 0x00007FF; lp->hw->phy->current_channel = 5; lp->hw->phy->symbol_duration = 25; + lp->hw->phy->supported.lbt = NL802154_SUPPORTED_BOOL_BOTH; + lp->hw->phy->supported.tx_powers = at86rf212_powers; + lp->hw->phy->supported.tx_powers_size = ARRAY_SIZE(at86rf212_powers); + lp->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_100; + lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_100); break; case 11: chip = "at86rf233"; lp->data = &at86rf233_data; - lp->hw->phy->channels_supported[0] = 0x7FFF800; + lp->hw->phy->supported.channels[0] = 0x7FFF800; lp->hw->phy->current_channel = 13; lp->hw->phy->symbol_duration = 16; + lp->hw->phy->supported.tx_powers = at86rf233_powers; + lp->hw->phy->supported.tx_powers_size = ARRAY_SIZE(at86rf233_powers); break; default: chip = "unknown"; rc = -ENOTSUPP; - break; + goto not_supp; } + lp->hw->phy->cca_ed_level = lp->hw->phy->supported.cca_ed_levels[7]; + lp->hw->phy->transmit_power = lp->hw->phy->supported.tx_powers[0]; + +not_supp: dev_info(&lp->spi->dev, "Detected %s chip version %d\n", chip, version); return rc; diff --git a/drivers/net/ieee802154/at86rf230.h b/drivers/net/ieee802154/at86rf230.h new file mode 100644 index 0000000..1e6d1cc --- /dev/null +++ b/drivers/net/ieee802154/at86rf230.h @@ -0,0 +1,220 @@ +/* + * AT86RF230/RF231 driver + * + * Copyright (C) 2009-2012 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Written by: + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ + +#ifndef _AT86RF230_H +#define _AT86RF230_H + +#define RG_TRX_STATUS (0x01) +#define SR_TRX_STATUS 0x01, 0x1f, 0 +#define SR_RESERVED_01_3 0x01, 0x20, 5 +#define SR_CCA_STATUS 0x01, 0x40, 6 +#define SR_CCA_DONE 0x01, 0x80, 7 +#define RG_TRX_STATE (0x02) +#define SR_TRX_CMD 0x02, 0x1f, 0 +#define SR_TRAC_STATUS 0x02, 0xe0, 5 +#define RG_TRX_CTRL_0 (0x03) +#define SR_CLKM_CTRL 0x03, 0x07, 0 +#define SR_CLKM_SHA_SEL 0x03, 0x08, 3 +#define SR_PAD_IO_CLKM 0x03, 0x30, 4 +#define SR_PAD_IO 0x03, 0xc0, 6 +#define RG_TRX_CTRL_1 (0x04) +#define SR_IRQ_POLARITY 0x04, 0x01, 0 +#define SR_IRQ_MASK_MODE 0x04, 0x02, 1 +#define SR_SPI_CMD_MODE 0x04, 0x0c, 2 +#define SR_RX_BL_CTRL 0x04, 0x10, 4 +#define SR_TX_AUTO_CRC_ON 0x04, 0x20, 5 +#define SR_IRQ_2_EXT_EN 0x04, 0x40, 6 +#define SR_PA_EXT_EN 0x04, 0x80, 7 +#define RG_PHY_TX_PWR (0x05) +#define SR_TX_PWR_23X 0x05, 0x0f, 0 +#define SR_PA_LT_230 0x05, 0x30, 4 +#define SR_PA_BUF_LT_230 0x05, 0xc0, 6 +#define SR_TX_PWR_212 0x05, 0x1f, 0 +#define SR_GC_PA_212 0x05, 0x60, 5 +#define SR_PA_BOOST_LT_212 0x05, 0x80, 7 +#define RG_PHY_RSSI (0x06) +#define SR_RSSI 0x06, 0x1f, 0 +#define SR_RND_VALUE 0x06, 0x60, 5 +#define SR_RX_CRC_VALID 0x06, 0x80, 7 +#define RG_PHY_ED_LEVEL (0x07) +#define SR_ED_LEVEL 0x07, 0xff, 0 +#define RG_PHY_CC_CCA (0x08) +#define SR_CHANNEL 0x08, 0x1f, 0 +#define SR_CCA_MODE 0x08, 0x60, 5 +#define SR_CCA_REQUEST 0x08, 0x80, 7 +#define RG_CCA_THRES (0x09) +#define SR_CCA_ED_THRES 0x09, 0x0f, 0 +#define SR_RESERVED_09_1 0x09, 0xf0, 4 +#define RG_RX_CTRL (0x0a) +#define SR_PDT_THRES 0x0a, 0x0f, 0 +#define SR_RESERVED_0a_1 0x0a, 0xf0, 4 +#define RG_SFD_VALUE (0x0b) +#define SR_SFD_VALUE 0x0b, 0xff, 0 +#define RG_TRX_CTRL_2 (0x0c) +#define SR_OQPSK_DATA_RATE 0x0c, 0x03, 0 +#define SR_SUB_MODE 0x0c, 0x04, 2 +#define SR_BPSK_QPSK 0x0c, 0x08, 3 +#define SR_OQPSK_SUB1_RC_EN 0x0c, 0x10, 4 +#define SR_RESERVED_0c_5 0x0c, 0x60, 5 +#define SR_RX_SAFE_MODE 0x0c, 0x80, 7 +#define RG_ANT_DIV (0x0d) +#define SR_ANT_CTRL 0x0d, 0x03, 0 +#define SR_ANT_EXT_SW_EN 0x0d, 0x04, 2 +#define SR_ANT_DIV_EN 0x0d, 0x08, 3 +#define SR_RESERVED_0d_2 0x0d, 0x70, 4 +#define SR_ANT_SEL 0x0d, 0x80, 7 +#define RG_IRQ_MASK (0x0e) +#define SR_IRQ_MASK 0x0e, 0xff, 0 +#define RG_IRQ_STATUS (0x0f) +#define SR_IRQ_0_PLL_LOCK 0x0f, 0x01, 0 +#define SR_IRQ_1_PLL_UNLOCK 0x0f, 0x02, 1 +#define SR_IRQ_2_RX_START 0x0f, 0x04, 2 +#define SR_IRQ_3_TRX_END 0x0f, 0x08, 3 +#define SR_IRQ_4_CCA_ED_DONE 0x0f, 0x10, 4 +#define SR_IRQ_5_AMI 0x0f, 0x20, 5 +#define SR_IRQ_6_TRX_UR 0x0f, 0x40, 6 +#define SR_IRQ_7_BAT_LOW 0x0f, 0x80, 7 +#define RG_VREG_CTRL (0x10) +#define SR_RESERVED_10_6 0x10, 0x03, 0 +#define SR_DVDD_OK 0x10, 0x04, 2 +#define SR_DVREG_EXT 0x10, 0x08, 3 +#define SR_RESERVED_10_3 0x10, 0x30, 4 +#define SR_AVDD_OK 0x10, 0x40, 6 +#define SR_AVREG_EXT 0x10, 0x80, 7 +#define RG_BATMON (0x11) +#define SR_BATMON_VTH 0x11, 0x0f, 0 +#define SR_BATMON_HR 0x11, 0x10, 4 +#define SR_BATMON_OK 0x11, 0x20, 5 +#define SR_RESERVED_11_1 0x11, 0xc0, 6 +#define RG_XOSC_CTRL (0x12) +#define SR_XTAL_TRIM 0x12, 0x0f, 0 +#define SR_XTAL_MODE 0x12, 0xf0, 4 +#define RG_RX_SYN (0x15) +#define SR_RX_PDT_LEVEL 0x15, 0x0f, 0 +#define SR_RESERVED_15_2 0x15, 0x70, 4 +#define SR_RX_PDT_DIS 0x15, 0x80, 7 +#define RG_XAH_CTRL_1 (0x17) +#define SR_RESERVED_17_8 0x17, 0x01, 0 +#define SR_AACK_PROM_MODE 0x17, 0x02, 1 +#define SR_AACK_ACK_TIME 0x17, 0x04, 2 +#define SR_RESERVED_17_5 0x17, 0x08, 3 +#define SR_AACK_UPLD_RES_FT 0x17, 0x10, 4 +#define SR_AACK_FLTR_RES_FT 0x17, 0x20, 5 +#define SR_CSMA_LBT_MODE 0x17, 0x40, 6 +#define SR_RESERVED_17_1 0x17, 0x80, 7 +#define RG_FTN_CTRL (0x18) +#define SR_RESERVED_18_2 0x18, 0x7f, 0 +#define SR_FTN_START 0x18, 0x80, 7 +#define RG_PLL_CF (0x1a) +#define SR_RESERVED_1a_2 0x1a, 0x7f, 0 +#define SR_PLL_CF_START 0x1a, 0x80, 7 +#define RG_PLL_DCU (0x1b) +#define SR_RESERVED_1b_3 0x1b, 0x3f, 0 +#define SR_RESERVED_1b_2 0x1b, 0x40, 6 +#define SR_PLL_DCU_START 0x1b, 0x80, 7 +#define RG_PART_NUM (0x1c) +#define SR_PART_NUM 0x1c, 0xff, 0 +#define RG_VERSION_NUM (0x1d) +#define SR_VERSION_NUM 0x1d, 0xff, 0 +#define RG_MAN_ID_0 (0x1e) +#define SR_MAN_ID_0 0x1e, 0xff, 0 +#define RG_MAN_ID_1 (0x1f) +#define SR_MAN_ID_1 0x1f, 0xff, 0 +#define RG_SHORT_ADDR_0 (0x20) +#define SR_SHORT_ADDR_0 0x20, 0xff, 0 +#define RG_SHORT_ADDR_1 (0x21) +#define SR_SHORT_ADDR_1 0x21, 0xff, 0 +#define RG_PAN_ID_0 (0x22) +#define SR_PAN_ID_0 0x22, 0xff, 0 +#define RG_PAN_ID_1 (0x23) +#define SR_PAN_ID_1 0x23, 0xff, 0 +#define RG_IEEE_ADDR_0 (0x24) +#define SR_IEEE_ADDR_0 0x24, 0xff, 0 +#define RG_IEEE_ADDR_1 (0x25) +#define SR_IEEE_ADDR_1 0x25, 0xff, 0 +#define RG_IEEE_ADDR_2 (0x26) +#define SR_IEEE_ADDR_2 0x26, 0xff, 0 +#define RG_IEEE_ADDR_3 (0x27) +#define SR_IEEE_ADDR_3 0x27, 0xff, 0 +#define RG_IEEE_ADDR_4 (0x28) +#define SR_IEEE_ADDR_4 0x28, 0xff, 0 +#define RG_IEEE_ADDR_5 (0x29) +#define SR_IEEE_ADDR_5 0x29, 0xff, 0 +#define RG_IEEE_ADDR_6 (0x2a) +#define SR_IEEE_ADDR_6 0x2a, 0xff, 0 +#define RG_IEEE_ADDR_7 (0x2b) +#define SR_IEEE_ADDR_7 0x2b, 0xff, 0 +#define RG_XAH_CTRL_0 (0x2c) +#define SR_SLOTTED_OPERATION 0x2c, 0x01, 0 +#define SR_MAX_CSMA_RETRIES 0x2c, 0x0e, 1 +#define SR_MAX_FRAME_RETRIES 0x2c, 0xf0, 4 +#define RG_CSMA_SEED_0 (0x2d) +#define SR_CSMA_SEED_0 0x2d, 0xff, 0 +#define RG_CSMA_SEED_1 (0x2e) +#define SR_CSMA_SEED_1 0x2e, 0x07, 0 +#define SR_AACK_I_AM_COORD 0x2e, 0x08, 3 +#define SR_AACK_DIS_ACK 0x2e, 0x10, 4 +#define SR_AACK_SET_PD 0x2e, 0x20, 5 +#define SR_AACK_FVN_MODE 0x2e, 0xc0, 6 +#define RG_CSMA_BE (0x2f) +#define SR_MIN_BE 0x2f, 0x0f, 0 +#define SR_MAX_BE 0x2f, 0xf0, 4 + +#define CMD_REG 0x80 +#define CMD_REG_MASK 0x3f +#define CMD_WRITE 0x40 +#define CMD_FB 0x20 + +#define IRQ_BAT_LOW BIT(7) +#define IRQ_TRX_UR BIT(6) +#define IRQ_AMI BIT(5) +#define IRQ_CCA_ED BIT(4) +#define IRQ_TRX_END BIT(3) +#define IRQ_RX_START BIT(2) +#define IRQ_PLL_UNL BIT(1) +#define IRQ_PLL_LOCK BIT(0) + +#define IRQ_ACTIVE_HIGH 0 +#define IRQ_ACTIVE_LOW 1 + +#define STATE_P_ON 0x00 /* BUSY */ +#define STATE_BUSY_RX 0x01 +#define STATE_BUSY_TX 0x02 +#define STATE_FORCE_TRX_OFF 0x03 +#define STATE_FORCE_TX_ON 0x04 /* IDLE */ +/* 0x05 */ /* INVALID_PARAMETER */ +#define STATE_RX_ON 0x06 +/* 0x07 */ /* SUCCESS */ +#define STATE_TRX_OFF 0x08 +#define STATE_TX_ON 0x09 +/* 0x0a - 0x0e */ /* 0x0a - UNSUPPORTED_ATTRIBUTE */ +#define STATE_SLEEP 0x0F +#define STATE_PREP_DEEP_SLEEP 0x10 +#define STATE_BUSY_RX_AACK 0x11 +#define STATE_BUSY_TX_ARET 0x12 +#define STATE_RX_AACK_ON 0x16 +#define STATE_TX_ARET_ON 0x19 +#define STATE_RX_ON_NOCLK 0x1C +#define STATE_RX_AACK_ON_NOCLK 0x1D +#define STATE_BUSY_RX_AACK_NOCLK 0x1E +#define STATE_TRANSITION_IN_PROGRESS 0x1F + +#define TRX_STATE_MASK (0x1F) + +#endif /* !_AT86RF230_H */ diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c new file mode 100644 index 0000000..5b6bb9a --- /dev/null +++ b/drivers/net/ieee802154/atusb.c @@ -0,0 +1,699 @@ +/* + * atusb.c - Driver for the ATUSB IEEE 802.15.4 dongle + * + * Written 2013 by Werner Almesberger <werner@almesberger.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 + * + * Based on at86rf230.c and spi_atusb.c. + * at86rf230.c is + * Copyright (C) 2009 Siemens AG + * Written by: Dmitry Eremin-Solenikov <dmitry.baryshkov@siemens.com> + * + * spi_atusb.c is + * Copyright (c) 2011 Richard Sharpe <realrichardsharpe@gmail.com> + * Copyright (c) 2011 Stefan Schmidt <stefan@datenfreihafen.org> + * Copyright (c) 2011 Werner Almesberger <werner@almesberger.net> + * + * USB initialization is + * Copyright (c) 2013 Alexander Aring <alex.aring@gmail.com> + */ + +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/jiffies.h> +#include <linux/usb.h> +#include <linux/skbuff.h> + +#include <net/cfg802154.h> +#include <net/mac802154.h> + +#include "at86rf230.h" +#include "atusb.h" + +#define ATUSB_JEDEC_ATMEL 0x1f /* JEDEC manufacturer ID */ + +#define ATUSB_NUM_RX_URBS 4 /* allow for a bit of local latency */ +#define ATUSB_ALLOC_DELAY_MS 100 /* delay after failed allocation */ +#define ATUSB_TX_TIMEOUT_MS 200 /* on the air timeout */ + +struct atusb { + struct ieee802154_hw *hw; + struct usb_device *usb_dev; + int shutdown; /* non-zero if shutting down */ + int err; /* set by first error */ + + /* RX variables */ + struct delayed_work work; /* memory allocations */ + struct usb_anchor idle_urbs; /* URBs waiting to be submitted */ + struct usb_anchor rx_urbs; /* URBs waiting for reception */ + + /* TX variables */ + struct usb_ctrlrequest tx_dr; + struct urb *tx_urb; + struct sk_buff *tx_skb; + uint8_t tx_ack_seq; /* current TX ACK sequence number */ +}; + +/* at86rf230.h defines values as <reg, mask, shift> tuples. We use the more + * traditional style of having registers and or-able values. SR_REG extracts + * the register number. SR_VALUE uses the shift to prepare a value accordingly. + */ + +#define __SR_REG(reg, mask, shift) (reg) +#define SR_REG(sr) __SR_REG(sr) + +#define __SR_VALUE(reg, mask, shift, val) ((val) << (shift)) +#define SR_VALUE(sr, val) __SR_VALUE(sr, (val)) + +/* ----- USB commands without data ----------------------------------------- */ + +/* To reduce the number of error checks in the code, we record the first error + * in atusb->err and reject all subsequent requests until the error is cleared. + */ + +static int atusb_control_msg(struct atusb *atusb, unsigned int pipe, + __u8 request, __u8 requesttype, + __u16 value, __u16 index, + void *data, __u16 size, int timeout) +{ + struct usb_device *usb_dev = atusb->usb_dev; + int ret; + + if (atusb->err) + return atusb->err; + + ret = usb_control_msg(usb_dev, pipe, request, requesttype, + value, index, data, size, timeout); + if (ret < 0) { + atusb->err = ret; + dev_err(&usb_dev->dev, + "atusb_control_msg: req 0x%02x val 0x%x idx 0x%x, error %d\n", + request, value, index, ret); + } + return ret; +} + +static int atusb_command(struct atusb *atusb, uint8_t cmd, uint8_t arg) +{ + struct usb_device *usb_dev = atusb->usb_dev; + + dev_dbg(&usb_dev->dev, "atusb_command: cmd = 0x%x\n", cmd); + return atusb_control_msg(atusb, usb_sndctrlpipe(usb_dev, 0), + cmd, ATUSB_REQ_TO_DEV, arg, 0, NULL, 0, 1000); +} + +static int atusb_write_reg(struct atusb *atusb, uint8_t reg, uint8_t value) +{ + struct usb_device *usb_dev = atusb->usb_dev; + + dev_dbg(&usb_dev->dev, "atusb_write_reg: 0x%02x <- 0x%02x\n", + reg, value); + return atusb_control_msg(atusb, usb_sndctrlpipe(usb_dev, 0), + ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV, + value, reg, NULL, 0, 1000); +} + +static int atusb_read_reg(struct atusb *atusb, uint8_t reg) +{ + struct usb_device *usb_dev = atusb->usb_dev; + int ret; + uint8_t value; + + dev_dbg(&usb_dev->dev, "atusb: reg = 0x%x\n", reg); + ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), + ATUSB_REG_READ, ATUSB_REQ_FROM_DEV, + 0, reg, &value, 1, 1000); + return ret >= 0 ? value : ret; +} + +static int atusb_get_and_clear_error(struct atusb *atusb) +{ + int err = atusb->err; + + atusb->err = 0; + return err; +} + +/* ----- skb allocation ---------------------------------------------------- */ + +#define MAX_PSDU 127 +#define MAX_RX_XFER (1 + MAX_PSDU + 2 + 1) /* PHR+PSDU+CRC+LQI */ + +#define SKB_ATUSB(skb) (*(struct atusb **)(skb)->cb) + +static void atusb_in(struct urb *urb); + +static int atusb_submit_rx_urb(struct atusb *atusb, struct urb *urb) +{ + struct usb_device *usb_dev = atusb->usb_dev; + struct sk_buff *skb = urb->context; + int ret; + + if (!skb) { + skb = alloc_skb(MAX_RX_XFER, GFP_KERNEL); + if (!skb) { + dev_warn_ratelimited(&usb_dev->dev, + "atusb_in: can't allocate skb\n"); + return -ENOMEM; + } + skb_put(skb, MAX_RX_XFER); + SKB_ATUSB(skb) = atusb; + } + + usb_fill_bulk_urb(urb, usb_dev, usb_rcvbulkpipe(usb_dev, 1), + skb->data, MAX_RX_XFER, atusb_in, skb); + usb_anchor_urb(urb, &atusb->rx_urbs); + + ret = usb_submit_urb(urb, GFP_KERNEL); + if (ret) { + usb_unanchor_urb(urb); + kfree_skb(skb); + urb->context = NULL; + } + return ret; +} + +static void atusb_work_urbs(struct work_struct *work) +{ + struct atusb *atusb = + container_of(to_delayed_work(work), struct atusb, work); + struct usb_device *usb_dev = atusb->usb_dev; + struct urb *urb; + int ret; + + if (atusb->shutdown) + return; + + do { + urb = usb_get_from_anchor(&atusb->idle_urbs); + if (!urb) + return; + ret = atusb_submit_rx_urb(atusb, urb); + } while (!ret); + + usb_anchor_urb(urb, &atusb->idle_urbs); + dev_warn_ratelimited(&usb_dev->dev, + "atusb_in: can't allocate/submit URB (%d)\n", ret); + schedule_delayed_work(&atusb->work, + msecs_to_jiffies(ATUSB_ALLOC_DELAY_MS) + 1); +} + +/* ----- Asynchronous USB -------------------------------------------------- */ + +static void atusb_tx_done(struct atusb *atusb, uint8_t seq) +{ + struct usb_device *usb_dev = atusb->usb_dev; + uint8_t expect = atusb->tx_ack_seq; + + dev_dbg(&usb_dev->dev, "atusb_tx_done (0x%02x/0x%02x)\n", seq, expect); + if (seq == expect) { + /* TODO check for ifs handling in firmware */ + ieee802154_xmit_complete(atusb->hw, atusb->tx_skb, false); + } else { + /* TODO I experience this case when atusb has a tx complete + * irq before probing, we should fix the firmware it's an + * unlikely case now that seq == expect is then true, but can + * happen and fail with a tx_skb = NULL; + */ + ieee802154_wake_queue(atusb->hw); + if (atusb->tx_skb) + dev_kfree_skb_irq(atusb->tx_skb); + } +} + +static void atusb_in_good(struct urb *urb) +{ + struct usb_device *usb_dev = urb->dev; + struct sk_buff *skb = urb->context; + struct atusb *atusb = SKB_ATUSB(skb); + uint8_t len, lqi; + + if (!urb->actual_length) { + dev_dbg(&usb_dev->dev, "atusb_in: zero-sized URB ?\n"); + return; + } + + len = *skb->data; + + if (urb->actual_length == 1) { + atusb_tx_done(atusb, len); + return; + } + + if (len + 1 > urb->actual_length - 1) { + dev_dbg(&usb_dev->dev, "atusb_in: frame len %d+1 > URB %u-1\n", + len, urb->actual_length); + return; + } + + if (!ieee802154_is_valid_psdu_len(len)) { + dev_dbg(&usb_dev->dev, "atusb_in: frame corrupted\n"); + return; + } + + lqi = skb->data[len + 1]; + dev_dbg(&usb_dev->dev, "atusb_in: rx len %d lqi 0x%02x\n", len, lqi); + skb_pull(skb, 1); /* remove PHR */ + skb_trim(skb, len); /* get payload only */ + ieee802154_rx_irqsafe(atusb->hw, skb, lqi); + urb->context = NULL; /* skb is gone */ +} + +static void atusb_in(struct urb *urb) +{ + struct usb_device *usb_dev = urb->dev; + struct sk_buff *skb = urb->context; + struct atusb *atusb = SKB_ATUSB(skb); + + dev_dbg(&usb_dev->dev, "atusb_in: status %d len %d\n", + urb->status, urb->actual_length); + if (urb->status) { + if (urb->status == -ENOENT) { /* being killed */ + kfree_skb(skb); + urb->context = NULL; + return; + } + dev_dbg(&usb_dev->dev, "atusb_in: URB error %d\n", urb->status); + } else { + atusb_in_good(urb); + } + + usb_anchor_urb(urb, &atusb->idle_urbs); + if (!atusb->shutdown) + schedule_delayed_work(&atusb->work, 0); +} + +/* ----- URB allocation/deallocation --------------------------------------- */ + +static void atusb_free_urbs(struct atusb *atusb) +{ + struct urb *urb; + + while (1) { + urb = usb_get_from_anchor(&atusb->idle_urbs); + if (!urb) + break; + if (urb->context) + kfree_skb(urb->context); + usb_free_urb(urb); + } +} + +static int atusb_alloc_urbs(struct atusb *atusb, int n) +{ + struct urb *urb; + + while (n) { + urb = usb_alloc_urb(0, GFP_KERNEL); + if (!urb) { + atusb_free_urbs(atusb); + return -ENOMEM; + } + usb_anchor_urb(urb, &atusb->idle_urbs); + n--; + } + return 0; +} + +/* ----- IEEE 802.15.4 interface operations -------------------------------- */ + +static void atusb_xmit_complete(struct urb *urb) +{ + dev_dbg(&urb->dev->dev, "atusb_xmit urb completed"); +} + +static int atusb_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) +{ + struct atusb *atusb = hw->priv; + struct usb_device *usb_dev = atusb->usb_dev; + int ret; + + dev_dbg(&usb_dev->dev, "atusb_xmit (%d)\n", skb->len); + atusb->tx_skb = skb; + atusb->tx_ack_seq++; + atusb->tx_dr.wIndex = cpu_to_le16(atusb->tx_ack_seq); + atusb->tx_dr.wLength = cpu_to_le16(skb->len); + + usb_fill_control_urb(atusb->tx_urb, usb_dev, + usb_sndctrlpipe(usb_dev, 0), + (unsigned char *)&atusb->tx_dr, skb->data, + skb->len, atusb_xmit_complete, NULL); + ret = usb_submit_urb(atusb->tx_urb, GFP_ATOMIC); + dev_dbg(&usb_dev->dev, "atusb_xmit done (%d)\n", ret); + return ret; +} + +static int atusb_channel(struct ieee802154_hw *hw, u8 page, u8 channel) +{ + struct atusb *atusb = hw->priv; + int ret; + + /* This implicitly sets the CCA (Clear Channel Assessment) mode to 0, + * "Mode 3a, Carrier sense OR energy above threshold". + * We should probably make this configurable. @@@ + */ + ret = atusb_write_reg(atusb, RG_PHY_CC_CCA, channel); + if (ret < 0) + return ret; + msleep(1); /* @@@ ugly synchronization */ + return 0; +} + +static int atusb_ed(struct ieee802154_hw *hw, u8 *level) +{ + BUG_ON(!level); + *level = 0xbe; + return 0; +} + +static int atusb_set_hw_addr_filt(struct ieee802154_hw *hw, + struct ieee802154_hw_addr_filt *filt, + unsigned long changed) +{ + struct atusb *atusb = hw->priv; + struct device *dev = &atusb->usb_dev->dev; + uint8_t reg; + + if (changed & IEEE802154_AFILT_SADDR_CHANGED) { + u16 addr = le16_to_cpu(filt->short_addr); + + dev_vdbg(dev, "atusb_set_hw_addr_filt called for saddr\n"); + atusb_write_reg(atusb, RG_SHORT_ADDR_0, addr); + atusb_write_reg(atusb, RG_SHORT_ADDR_1, addr >> 8); + } + + if (changed & IEEE802154_AFILT_PANID_CHANGED) { + u16 pan = le16_to_cpu(filt->pan_id); + + dev_vdbg(dev, "atusb_set_hw_addr_filt called for pan id\n"); + atusb_write_reg(atusb, RG_PAN_ID_0, pan); + atusb_write_reg(atusb, RG_PAN_ID_1, pan >> 8); + } + + if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) { + u8 i, addr[IEEE802154_EXTENDED_ADDR_LEN]; + + memcpy(addr, &filt->ieee_addr, IEEE802154_EXTENDED_ADDR_LEN); + dev_vdbg(dev, "atusb_set_hw_addr_filt called for IEEE addr\n"); + for (i = 0; i < 8; i++) + atusb_write_reg(atusb, RG_IEEE_ADDR_0 + i, addr[i]); + } + + if (changed & IEEE802154_AFILT_PANC_CHANGED) { + dev_vdbg(dev, + "atusb_set_hw_addr_filt called for panc change\n"); + reg = atusb_read_reg(atusb, SR_REG(SR_AACK_I_AM_COORD)); + if (filt->pan_coord) + reg |= SR_VALUE(SR_AACK_I_AM_COORD, 1); + else + reg &= ~SR_VALUE(SR_AACK_I_AM_COORD, 1); + atusb_write_reg(atusb, SR_REG(SR_AACK_I_AM_COORD), reg); + } + + return atusb_get_and_clear_error(atusb); +} + +static int atusb_start(struct ieee802154_hw *hw) +{ + struct atusb *atusb = hw->priv; + struct usb_device *usb_dev = atusb->usb_dev; + int ret; + + dev_dbg(&usb_dev->dev, "atusb_start\n"); + schedule_delayed_work(&atusb->work, 0); + atusb_command(atusb, ATUSB_RX_MODE, 1); + ret = atusb_get_and_clear_error(atusb); + if (ret < 0) + usb_kill_anchored_urbs(&atusb->idle_urbs); + return ret; +} + +static void atusb_stop(struct ieee802154_hw *hw) +{ + struct atusb *atusb = hw->priv; + struct usb_device *usb_dev = atusb->usb_dev; + + dev_dbg(&usb_dev->dev, "atusb_stop\n"); + usb_kill_anchored_urbs(&atusb->idle_urbs); + atusb_command(atusb, ATUSB_RX_MODE, 0); + atusb_get_and_clear_error(atusb); +} + +static struct ieee802154_ops atusb_ops = { + .owner = THIS_MODULE, + .xmit_async = atusb_xmit, + .ed = atusb_ed, + .set_channel = atusb_channel, + .start = atusb_start, + .stop = atusb_stop, + .set_hw_addr_filt = atusb_set_hw_addr_filt, +}; + +/* ----- Firmware and chip version information ----------------------------- */ + +static int atusb_get_and_show_revision(struct atusb *atusb) +{ + struct usb_device *usb_dev = atusb->usb_dev; + unsigned char buffer[3]; + int ret; + + /* Get a couple of the ATMega Firmware values */ + ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), + ATUSB_ID, ATUSB_REQ_FROM_DEV, 0, 0, + buffer, 3, 1000); + if (ret >= 0) + dev_info(&usb_dev->dev, + "Firmware: major: %u, minor: %u, hardware type: %u\n", + buffer[0], buffer[1], buffer[2]); + if (buffer[0] == 0 && buffer[1] < 2) { + dev_info(&usb_dev->dev, + "Firmware version (%u.%u) is predates our first public release.", + buffer[0], buffer[1]); + dev_info(&usb_dev->dev, "Please update to version 0.2 or newer"); + } + + return ret; +} + +static int atusb_get_and_show_build(struct atusb *atusb) +{ + struct usb_device *usb_dev = atusb->usb_dev; + char build[ATUSB_BUILD_SIZE + 1]; + int ret; + + ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), + ATUSB_BUILD, ATUSB_REQ_FROM_DEV, 0, 0, + build, ATUSB_BUILD_SIZE, 1000); + if (ret >= 0) { + build[ret] = 0; + dev_info(&usb_dev->dev, "Firmware: build %s\n", build); + } + + return ret; +} + +static int atusb_get_and_show_chip(struct atusb *atusb) +{ + struct usb_device *usb_dev = atusb->usb_dev; + uint8_t man_id_0, man_id_1, part_num, version_num; + + man_id_0 = atusb_read_reg(atusb, RG_MAN_ID_0); + man_id_1 = atusb_read_reg(atusb, RG_MAN_ID_1); + part_num = atusb_read_reg(atusb, RG_PART_NUM); + version_num = atusb_read_reg(atusb, RG_VERSION_NUM); + + if (atusb->err) + return atusb->err; + + if ((man_id_1 << 8 | man_id_0) != ATUSB_JEDEC_ATMEL) { + dev_err(&usb_dev->dev, + "non-Atmel transceiver xxxx%02x%02x\n", + man_id_1, man_id_0); + goto fail; + } + if (part_num != 3 && part_num != 2) { + dev_err(&usb_dev->dev, + "unexpected transceiver, part 0x%02x version 0x%02x\n", + part_num, version_num); + goto fail; + } + + dev_info(&usb_dev->dev, "ATUSB: AT86RF231 version %d\n", version_num); + + return 0; + +fail: + atusb->err = -ENODEV; + return -ENODEV; +} + +/* ----- Setup ------------------------------------------------------------- */ + +static int atusb_probe(struct usb_interface *interface, + const struct usb_device_id *id) +{ + struct usb_device *usb_dev = interface_to_usbdev(interface); + struct ieee802154_hw *hw; + struct atusb *atusb = NULL; + int ret = -ENOMEM; + + hw = ieee802154_alloc_hw(sizeof(struct atusb), &atusb_ops); + if (!hw) + return -ENOMEM; + + atusb = hw->priv; + atusb->hw = hw; + atusb->usb_dev = usb_get_dev(usb_dev); + usb_set_intfdata(interface, atusb); + + atusb->shutdown = 0; + atusb->err = 0; + INIT_DELAYED_WORK(&atusb->work, atusb_work_urbs); + init_usb_anchor(&atusb->idle_urbs); + init_usb_anchor(&atusb->rx_urbs); + + if (atusb_alloc_urbs(atusb, ATUSB_NUM_RX_URBS)) + goto fail; + + atusb->tx_dr.bRequestType = ATUSB_REQ_TO_DEV; + atusb->tx_dr.bRequest = ATUSB_TX; + atusb->tx_dr.wValue = cpu_to_le16(0); + + atusb->tx_urb = usb_alloc_urb(0, GFP_ATOMIC); + if (!atusb->tx_urb) + goto fail; + + hw->parent = &usb_dev->dev; + hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT | + IEEE802154_HW_AACK; + + hw->phy->current_page = 0; + hw->phy->current_channel = 11; /* reset default */ + hw->phy->supported.channels[0] = 0x7FFF800; + ieee802154_random_extended_addr(&hw->phy->perm_extended_addr); + + atusb_command(atusb, ATUSB_RF_RESET, 0); + atusb_get_and_show_chip(atusb); + atusb_get_and_show_revision(atusb); + atusb_get_and_show_build(atusb); + ret = atusb_get_and_clear_error(atusb); + if (ret) { + dev_err(&atusb->usb_dev->dev, + "%s: initialization failed, error = %d\n", + __func__, ret); + goto fail; + } + + ret = ieee802154_register_hw(hw); + if (ret) + goto fail; + + /* If we just powered on, we're now in P_ON and need to enter TRX_OFF + * explicitly. Any resets after that will send us straight to TRX_OFF, + * making the command below redundant. + */ + atusb_write_reg(atusb, RG_TRX_STATE, STATE_FORCE_TRX_OFF); + msleep(1); /* reset => TRX_OFF, tTR13 = 37 us */ + +#if 0 + /* Calculating the maximum time available to empty the frame buffer + * on reception: + * + * According to [1], the inter-frame gap is + * R * 20 * 16 us + 128 us + * where R is a random number from 0 to 7. Furthermore, we have 20 bit + * times (80 us at 250 kbps) of SHR of the next frame before the + * transceiver begins storing data in the frame buffer. + * + * This yields a minimum time of 208 us between the last data of a + * frame and the first data of the next frame. This time is further + * reduced by interrupt latency in the atusb firmware. + * + * atusb currently needs about 500 us to retrieve a maximum-sized + * frame. We therefore have to allow reception of a new frame to begin + * while we retrieve the previous frame. + * + * [1] "JN-AN-1035 Calculating data rates in an IEEE 802.15.4-based + * network", Jennic 2006. + * http://www.jennic.com/download_file.php?supportFile=JN-AN-1035%20Calculating%20802-15-4%20Data%20Rates-1v0.pdf + */ + + atusb_write_reg(atusb, + SR_REG(SR_RX_SAFE_MODE), SR_VALUE(SR_RX_SAFE_MODE, 1)); +#endif + atusb_write_reg(atusb, RG_IRQ_MASK, 0xff); + + ret = atusb_get_and_clear_error(atusb); + if (!ret) + return 0; + + dev_err(&atusb->usb_dev->dev, + "%s: setup failed, error = %d\n", + __func__, ret); + + ieee802154_unregister_hw(hw); +fail: + atusb_free_urbs(atusb); + usb_kill_urb(atusb->tx_urb); + usb_free_urb(atusb->tx_urb); + usb_put_dev(usb_dev); + ieee802154_free_hw(hw); + return ret; +} + +static void atusb_disconnect(struct usb_interface *interface) +{ + struct atusb *atusb = usb_get_intfdata(interface); + + dev_dbg(&atusb->usb_dev->dev, "atusb_disconnect\n"); + + atusb->shutdown = 1; + cancel_delayed_work_sync(&atusb->work); + + usb_kill_anchored_urbs(&atusb->rx_urbs); + atusb_free_urbs(atusb); + usb_kill_urb(atusb->tx_urb); + usb_free_urb(atusb->tx_urb); + + ieee802154_unregister_hw(atusb->hw); + + ieee802154_free_hw(atusb->hw); + + usb_set_intfdata(interface, NULL); + usb_put_dev(atusb->usb_dev); + + pr_debug("atusb_disconnect done\n"); +} + +/* The devices we work with */ +static const struct usb_device_id atusb_device_table[] = { + { + .match_flags = USB_DEVICE_ID_MATCH_DEVICE | + USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = ATUSB_VENDOR_ID, + .idProduct = ATUSB_PRODUCT_ID, + .bInterfaceClass = USB_CLASS_VENDOR_SPEC + }, + /* end with null element */ + {} +}; +MODULE_DEVICE_TABLE(usb, atusb_device_table); + +static struct usb_driver atusb_driver = { + .name = "atusb", + .probe = atusb_probe, + .disconnect = atusb_disconnect, + .id_table = atusb_device_table, +}; +module_usb_driver(atusb_driver); + +MODULE_AUTHOR("Alexander Aring <alex.aring@gmail.com>"); +MODULE_AUTHOR("Richard Sharpe <realrichardsharpe@gmail.com>"); +MODULE_AUTHOR("Stefan Schmidt <stefan@datenfreihafen.org>"); +MODULE_AUTHOR("Werner Almesberger <werner@almesberger.net>"); +MODULE_DESCRIPTION("ATUSB IEEE 802.15.4 Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ieee802154/atusb.h b/drivers/net/ieee802154/atusb.h new file mode 100644 index 0000000..0690edc --- /dev/null +++ b/drivers/net/ieee802154/atusb.h @@ -0,0 +1,84 @@ +/* + * atusb.h - Definitions shared between kernel and ATUSB firmware + * + * Written 2013 by Werner Almesberger <werner@almesberger.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2, or + * (at your option) any later version. + * + * This file should be identical for kernel and firmware. + * Kernel: drivers/net/ieee802154/atusb.h + * Firmware: ben-wpan/atusb/fw/include/atusb/atusb.h + */ + +#ifndef _ATUSB_H +#define _ATUSB_H + +#define ATUSB_VENDOR_ID 0x20b7 /* Qi Hardware*/ +#define ATUSB_PRODUCT_ID 0x1540 /* 802.15.4, device 0 */ + /* -- - - */ + +#define ATUSB_BUILD_SIZE 256 /* maximum build version/date message length */ + +/* Commands to our device. Make sure this is synced with the firmware */ +enum atusb_requests { + ATUSB_ID = 0x00, /* system status/control grp */ + ATUSB_BUILD, + ATUSB_RESET, + ATUSB_RF_RESET = 0x10, /* debug/test group */ + ATUSB_POLL_INT, + ATUSB_TEST, /* atusb-sil only */ + ATUSB_TIMER, + ATUSB_GPIO, + ATUSB_SLP_TR, + ATUSB_GPIO_CLEANUP, + ATUSB_REG_WRITE = 0x20, /* transceiver group */ + ATUSB_REG_READ, + ATUSB_BUF_WRITE, + ATUSB_BUF_READ, + ATUSB_SRAM_WRITE, + ATUSB_SRAM_READ, + ATUSB_SPI_WRITE = 0x30, /* SPI group */ + ATUSB_SPI_READ1, + ATUSB_SPI_READ2, + ATUSB_SPI_WRITE2_SYNC, + ATUSB_RX_MODE = 0x40, /* HardMAC group */ + ATUSB_TX, +}; + +/* Direction bRequest wValue wIndex wLength + * + * ->host ATUSB_ID - - 3 + * ->host ATUSB_BUILD - - #bytes + * host-> ATUSB_RESET - - 0 + * + * host-> ATUSB_RF_RESET - - 0 + * ->host ATUSB_POLL_INT - - 1 + * host-> ATUSB_TEST - - 0 + * ->host ATUSB_TIMER - - #bytes (6) + * ->host ATUSB_GPIO dir+data mask+p# 3 + * host-> ATUSB_SLP_TR - - 0 + * host-> ATUSB_GPIO_CLEANUP - - 0 + * + * host-> ATUSB_REG_WRITE value addr 0 + * ->host ATUSB_REG_READ - addr 1 + * host-> ATUSB_BUF_WRITE - - #bytes + * ->host ATUSB_BUF_READ - - #bytes + * host-> ATUSB_SRAM_WRITE - addr #bytes + * ->host ATUSB_SRAM_READ - addr #bytes + * + * host-> ATUSB_SPI_WRITE byte0 byte1 #bytes + * ->host ATUSB_SPI_READ1 byte0 - #bytes + * ->host ATUSB_SPI_READ2 byte0 byte1 #bytes + * ->host ATUSB_SPI_WRITE2_SYNC byte0 byte1 0/1 + * + * host-> ATUSB_RX_MODE on - 0 + * host-> ATUSB_TX flags ack_seq #bytes + */ + +#define ATUSB_REQ_FROM_DEV (USB_TYPE_VENDOR | USB_DIR_IN) +#define ATUSB_REQ_TO_DEV (USB_TYPE_VENDOR | USB_DIR_OUT) + +#endif /* !_ATUSB_H */ diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c index f833b8b..84b28a0 100644 --- a/drivers/net/ieee802154/cc2520.c +++ b/drivers/net/ieee802154/cc2520.c @@ -653,7 +653,7 @@ static int cc2520_register(struct cc2520_private *priv) ieee802154_random_extended_addr(&priv->hw->phy->perm_extended_addr); /* We do support only 2.4 Ghz */ - priv->hw->phy->channels_supported[0] = 0x7FFF800; + priv->hw->phy->supported.channels[0] = 0x7FFF800; priv->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK | IEEE802154_HW_AFILT; diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c index dc2bfb6..9d0da4e 100644 --- a/drivers/net/ieee802154/fakelb.c +++ b/drivers/net/ieee802154/fakelb.c @@ -27,25 +27,25 @@ #include <net/mac802154.h> #include <net/cfg802154.h> -static int numlbs = 1; +static int numlbs = 2; -struct fakelb_dev_priv { - struct ieee802154_hw *hw; +static LIST_HEAD(fakelb_phys); +static DEFINE_SPINLOCK(fakelb_phys_lock); - struct list_head list; - struct fakelb_priv *fake; +static LIST_HEAD(fakelb_ifup_phys); +static DEFINE_RWLOCK(fakelb_ifup_phys_lock); - spinlock_t lock; - bool working; -}; +struct fakelb_phy { + struct ieee802154_hw *hw; + + u8 page; + u8 channel; -struct fakelb_priv { struct list_head list; - rwlock_t lock; + struct list_head list_ifup; }; -static int -fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level) +static int fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level) { BUG_ON(!level); *level = 0xbe; @@ -53,78 +53,63 @@ fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level) return 0; } -static int -fakelb_hw_channel(struct ieee802154_hw *hw, u8 page, u8 channel) +static int fakelb_hw_channel(struct ieee802154_hw *hw, u8 page, u8 channel) { - pr_debug("set channel to %d\n", channel); + struct fakelb_phy *phy = hw->priv; + write_lock_bh(&fakelb_ifup_phys_lock); + phy->page = page; + phy->channel = channel; + write_unlock_bh(&fakelb_ifup_phys_lock); return 0; } -static void -fakelb_hw_deliver(struct fakelb_dev_priv *priv, struct sk_buff *skb) +static int fakelb_hw_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) { - struct sk_buff *newskb; + struct fakelb_phy *current_phy = hw->priv, *phy; - spin_lock(&priv->lock); - if (priv->working) { - newskb = pskb_copy(skb, GFP_ATOMIC); - ieee802154_rx_irqsafe(priv->hw, newskb, 0xcc); - } - spin_unlock(&priv->lock); -} + read_lock_bh(&fakelb_ifup_phys_lock); + list_for_each_entry(phy, &fakelb_ifup_phys, list_ifup) { + if (current_phy == phy) + continue; -static int -fakelb_hw_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) -{ - struct fakelb_dev_priv *priv = hw->priv; - struct fakelb_priv *fake = priv->fake; - - read_lock_bh(&fake->lock); - if (priv->list.next == priv->list.prev) { - /* we are the only one device */ - fakelb_hw_deliver(priv, skb); - } else { - struct fakelb_dev_priv *dp; - list_for_each_entry(dp, &priv->fake->list, list) { - if (dp != priv && - (dp->hw->phy->current_channel == - priv->hw->phy->current_channel)) - fakelb_hw_deliver(dp, skb); + if (current_phy->page == phy->page && + current_phy->channel == phy->channel) { + struct sk_buff *newskb = pskb_copy(skb, GFP_ATOMIC); + + if (newskb) + ieee802154_rx_irqsafe(phy->hw, newskb, 0xcc); } } - read_unlock_bh(&fake->lock); + read_unlock_bh(&fakelb_ifup_phys_lock); + ieee802154_xmit_complete(hw, skb, false); return 0; } -static int -fakelb_hw_start(struct ieee802154_hw *hw) { - struct fakelb_dev_priv *priv = hw->priv; - int ret = 0; +static int fakelb_hw_start(struct ieee802154_hw *hw) +{ + struct fakelb_phy *phy = hw->priv; - spin_lock(&priv->lock); - if (priv->working) - ret = -EBUSY; - else - priv->working = 1; - spin_unlock(&priv->lock); + write_lock_bh(&fakelb_ifup_phys_lock); + list_add(&phy->list_ifup, &fakelb_ifup_phys); + write_unlock_bh(&fakelb_ifup_phys_lock); - return ret; + return 0; } -static void -fakelb_hw_stop(struct ieee802154_hw *hw) { - struct fakelb_dev_priv *priv = hw->priv; +static void fakelb_hw_stop(struct ieee802154_hw *hw) +{ + struct fakelb_phy *phy = hw->priv; - spin_lock(&priv->lock); - priv->working = 0; - spin_unlock(&priv->lock); + write_lock_bh(&fakelb_ifup_phys_lock); + list_del(&phy->list_ifup); + write_unlock_bh(&fakelb_ifup_phys_lock); } static const struct ieee802154_ops fakelb_ops = { .owner = THIS_MODULE, - .xmit_sync = fakelb_hw_xmit, + .xmit_async = fakelb_hw_xmit, .ed = fakelb_hw_ed, .set_channel = fakelb_hw_channel, .start = fakelb_hw_start, @@ -135,54 +120,54 @@ static const struct ieee802154_ops fakelb_ops = { module_param(numlbs, int, 0); MODULE_PARM_DESC(numlbs, " number of pseudo devices"); -static int fakelb_add_one(struct device *dev, struct fakelb_priv *fake) +static int fakelb_add_one(struct device *dev) { - struct fakelb_dev_priv *priv; - int err; struct ieee802154_hw *hw; + struct fakelb_phy *phy; + int err; - hw = ieee802154_alloc_hw(sizeof(*priv), &fakelb_ops); + hw = ieee802154_alloc_hw(sizeof(*phy), &fakelb_ops); if (!hw) return -ENOMEM; - priv = hw->priv; - priv->hw = hw; + phy = hw->priv; + phy->hw = hw; /* 868 MHz BPSK 802.15.4-2003 */ - hw->phy->channels_supported[0] |= 1; + hw->phy->supported.channels[0] |= 1; /* 915 MHz BPSK 802.15.4-2003 */ - hw->phy->channels_supported[0] |= 0x7fe; + hw->phy->supported.channels[0] |= 0x7fe; /* 2.4 GHz O-QPSK 802.15.4-2003 */ - hw->phy->channels_supported[0] |= 0x7FFF800; + hw->phy->supported.channels[0] |= 0x7FFF800; /* 868 MHz ASK 802.15.4-2006 */ - hw->phy->channels_supported[1] |= 1; + hw->phy->supported.channels[1] |= 1; /* 915 MHz ASK 802.15.4-2006 */ - hw->phy->channels_supported[1] |= 0x7fe; + hw->phy->supported.channels[1] |= 0x7fe; /* 868 MHz O-QPSK 802.15.4-2006 */ - hw->phy->channels_supported[2] |= 1; + hw->phy->supported.channels[2] |= 1; /* 915 MHz O-QPSK 802.15.4-2006 */ - hw->phy->channels_supported[2] |= 0x7fe; + hw->phy->supported.channels[2] |= 0x7fe; /* 2.4 GHz CSS 802.15.4a-2007 */ - hw->phy->channels_supported[3] |= 0x3fff; + hw->phy->supported.channels[3] |= 0x3fff; /* UWB Sub-gigahertz 802.15.4a-2007 */ - hw->phy->channels_supported[4] |= 1; + hw->phy->supported.channels[4] |= 1; /* UWB Low band 802.15.4a-2007 */ - hw->phy->channels_supported[4] |= 0x1e; + hw->phy->supported.channels[4] |= 0x1e; /* UWB High band 802.15.4a-2007 */ - hw->phy->channels_supported[4] |= 0xffe0; + hw->phy->supported.channels[4] |= 0xffe0; /* 750 MHz O-QPSK 802.15.4c-2009 */ - hw->phy->channels_supported[5] |= 0xf; + hw->phy->supported.channels[5] |= 0xf; /* 750 MHz MPSK 802.15.4c-2009 */ - hw->phy->channels_supported[5] |= 0xf0; + hw->phy->supported.channels[5] |= 0xf0; /* 950 MHz BPSK 802.15.4d-2009 */ - hw->phy->channels_supported[6] |= 0x3ff; + hw->phy->supported.channels[6] |= 0x3ff; /* 950 MHz GFSK 802.15.4d-2009 */ - hw->phy->channels_supported[6] |= 0x3ffc00; + hw->phy->supported.channels[6] |= 0x3ffc00; - INIT_LIST_HEAD(&priv->list); - priv->fake = fake; - - spin_lock_init(&priv->lock); + ieee802154_random_extended_addr(&hw->phy->perm_extended_addr); + /* fake phy channel 13 as default */ + hw->phy->current_channel = 13; + phy->channel = hw->phy->current_channel; hw->parent = dev; @@ -190,67 +175,55 @@ static int fakelb_add_one(struct device *dev, struct fakelb_priv *fake) if (err) goto err_reg; - write_lock_bh(&fake->lock); - list_add_tail(&priv->list, &fake->list); - write_unlock_bh(&fake->lock); + spin_lock(&fakelb_phys_lock); + list_add_tail(&phy->list, &fakelb_phys); + spin_unlock(&fakelb_phys_lock); return 0; err_reg: - ieee802154_free_hw(priv->hw); + ieee802154_free_hw(phy->hw); return err; } -static void fakelb_del(struct fakelb_dev_priv *priv) +static void fakelb_del(struct fakelb_phy *phy) { - write_lock_bh(&priv->fake->lock); - list_del(&priv->list); - write_unlock_bh(&priv->fake->lock); + list_del(&phy->list); - ieee802154_unregister_hw(priv->hw); - ieee802154_free_hw(priv->hw); + ieee802154_unregister_hw(phy->hw); + ieee802154_free_hw(phy->hw); } static int fakelb_probe(struct platform_device *pdev) { - struct fakelb_priv *priv; - struct fakelb_dev_priv *dp; - int err = -ENOMEM; - int i; - - priv = devm_kzalloc(&pdev->dev, sizeof(struct fakelb_priv), - GFP_KERNEL); - if (!priv) - goto err_alloc; - - INIT_LIST_HEAD(&priv->list); - rwlock_init(&priv->lock); + struct fakelb_phy *phy, *tmp; + int err, i; for (i = 0; i < numlbs; i++) { - err = fakelb_add_one(&pdev->dev, priv); + err = fakelb_add_one(&pdev->dev); if (err < 0) goto err_slave; } - platform_set_drvdata(pdev, priv); dev_info(&pdev->dev, "added ieee802154 hardware\n"); return 0; err_slave: - list_for_each_entry(dp, &priv->list, list) - fakelb_del(dp); -err_alloc: + spin_lock(&fakelb_phys_lock); + list_for_each_entry_safe(phy, tmp, &fakelb_phys, list) + fakelb_del(phy); + spin_unlock(&fakelb_phys_lock); return err; } static int fakelb_remove(struct platform_device *pdev) { - struct fakelb_priv *priv = platform_get_drvdata(pdev); - struct fakelb_dev_priv *dp, *temp; - - list_for_each_entry_safe(dp, temp, &priv->list, list) - fakelb_del(dp); + struct fakelb_phy *phy, *tmp; + spin_lock(&fakelb_phys_lock); + list_for_each_entry_safe(phy, tmp, &fakelb_phys, list) + fakelb_del(phy); + spin_unlock(&fakelb_phys_lock); return 0; } diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c index fba2dfd..f2a1bd1 100644 --- a/drivers/net/ieee802154/mrf24j40.c +++ b/drivers/net/ieee802154/mrf24j40.c @@ -750,7 +750,7 @@ static int mrf24j40_probe(struct spi_device *spi) devrec->hw->priv = devrec; devrec->hw->parent = &devrec->spi->dev; - devrec->hw->phy->channels_supported[0] = CHANNEL_MASK; + devrec->hw->phy->supported.channels[0] = CHANNEL_MASK; devrec->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK | IEEE802154_HW_AFILT; diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c index f6c9163..25f2196 100644 --- a/drivers/net/irda/irda-usb.c +++ b/drivers/net/irda/irda-usb.c @@ -848,7 +848,9 @@ static void irda_usb_receive(struct urb *urb) * Jean II */ self->rx_defer_timer.function = irda_usb_rx_defer_expired; self->rx_defer_timer.data = (unsigned long) urb; - mod_timer(&self->rx_defer_timer, jiffies + (10 * HZ / 1000)); + mod_timer(&self->rx_defer_timer, + jiffies + msecs_to_jiffies(10)); + return; } diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 7c0cb87..cf18940 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -112,6 +112,11 @@ config MICREL_PHY ---help--- Supports the KSZ9021, VSC8201, KS8001 PHYs. +config DP83867_PHY + tristate "Drivers for Texas Instruments DP83867 Gigabit PHY" + ---help--- + Currently supports the DP83867 PHY. + config FIXED_PHY tristate "Driver for MDIO Bus/PHY emulation with fixed speed/link PHYs" depends on PHYLIB @@ -205,7 +210,6 @@ config MDIO_BCM_UNIMAC This hardware can be found in the Broadcom GENET Ethernet MAC controllers as well as some Broadcom Ethernet switches such as the Starfighter 2 switches. - endif # PHYLIB config MICREL_KS8995MA diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index e97e7f9..fcc25a0 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_MDIO_BITBANG) += mdio-bitbang.o obj-$(CONFIG_MDIO_GPIO) += mdio-gpio.o obj-$(CONFIG_NATIONAL_PHY) += national.o obj-$(CONFIG_DP83640_PHY) += dp83640.o +obj-$(CONFIG_DP83867_PHY) += dp83867.o obj-$(CONFIG_STE10XP) += ste10Xp.o obj-$(CONFIG_MICREL_PHY) += micrel.o obj-$(CONFIG_MDIO_OCTEON) += mdio-octeon.o diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 64c74c6..b5dc59d 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -404,7 +404,7 @@ static struct phy_driver bcm7xxx_driver[] = { .name = "Broadcom BCM7425", .features = PHY_GBIT_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause, - .flags = 0, + .flags = PHY_IS_INTERNAL, .config_init = bcm7xxx_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 496e02f..00cb41e 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -47,7 +47,7 @@ #define PSF_TX 0x1000 #define EXT_EVENT 1 #define CAL_EVENT 7 -#define CAL_TRIGGER 7 +#define CAL_TRIGGER 1 #define DP83640_N_PINS 12 #define MII_DP83640_MICR 0x11 @@ -496,7 +496,9 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp, else evnt |= EVNT_RISE; } + mutex_lock(&clock->extreg_lock); ext_write(0, phydev, PAGE5, PTP_EVNT, evnt); + mutex_unlock(&clock->extreg_lock); return 0; case PTP_CLK_REQ_PEROUT: @@ -532,6 +534,8 @@ static u8 status_frame_src[6] = { 0x08, 0x00, 0x17, 0x0B, 0x6B, 0x0F }; static void enable_status_frames(struct phy_device *phydev, bool on) { + struct dp83640_private *dp83640 = phydev->priv; + struct dp83640_clock *clock = dp83640->clock; u16 cfg0 = 0, ver; if (on) @@ -539,9 +543,13 @@ static void enable_status_frames(struct phy_device *phydev, bool on) ver = (PSF_PTPVER & VERSIONPTP_MASK) << VERSIONPTP_SHIFT; + mutex_lock(&clock->extreg_lock); + ext_write(0, phydev, PAGE5, PSF_CFG0, cfg0); ext_write(0, phydev, PAGE6, PSF_CFG1, ver); + mutex_unlock(&clock->extreg_lock); + if (!phydev->attached_dev) { pr_warn("expected to find an attached netdevice\n"); return; @@ -838,7 +846,7 @@ static void decode_rxts(struct dp83640_private *dp83640, list_del_init(&rxts->list); phy2rxts(phy_rxts, rxts); - spin_lock_irqsave(&dp83640->rx_queue.lock, flags); + spin_lock(&dp83640->rx_queue.lock); skb_queue_walk(&dp83640->rx_queue, skb) { struct dp83640_skb_info *skb_info; @@ -853,7 +861,7 @@ static void decode_rxts(struct dp83640_private *dp83640, break; } } - spin_unlock_irqrestore(&dp83640->rx_queue.lock, flags); + spin_unlock(&dp83640->rx_queue.lock); if (!shhwtstamps) list_add_tail(&rxts->list, &dp83640->rxts); @@ -1173,11 +1181,18 @@ static int dp83640_config_init(struct phy_device *phydev) if (clock->chosen && !list_empty(&clock->phylist)) recalibrate(clock); - else + else { + mutex_lock(&clock->extreg_lock); enable_broadcast(phydev, clock->page, 1); + mutex_unlock(&clock->extreg_lock); + } enable_status_frames(phydev, true); + + mutex_lock(&clock->extreg_lock); ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE); + mutex_unlock(&clock->extreg_lock); + return 0; } diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c new file mode 100644 index 0000000..ef0b4eb --- /dev/null +++ b/drivers/net/phy/dp83867.c @@ -0,0 +1,239 @@ +/* + * Driver for the Texas Instruments DP83867 PHY + * + * Copyright (C) 2015 Texas Instruments Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/ethtool.h> +#include <linux/kernel.h> +#include <linux/mii.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/phy.h> + +#include <dt-bindings/net/ti-dp83867.h> + +#define DP83867_PHY_ID 0x2000a231 +#define DP83867_DEVADDR 0x1f + +#define MII_DP83867_PHYCTRL 0x10 +#define MII_DP83867_MICR 0x12 +#define MII_DP83867_ISR 0x13 +#define DP83867_CTRL 0x1f + +/* Extended Registers */ +#define DP83867_RGMIICTL 0x0032 +#define DP83867_RGMIIDCTL 0x0086 + +#define DP83867_SW_RESET BIT(15) +#define DP83867_SW_RESTART BIT(14) + +/* MICR Interrupt bits */ +#define MII_DP83867_MICR_AN_ERR_INT_EN BIT(15) +#define MII_DP83867_MICR_SPEED_CHNG_INT_EN BIT(14) +#define MII_DP83867_MICR_DUP_MODE_CHNG_INT_EN BIT(13) +#define MII_DP83867_MICR_PAGE_RXD_INT_EN BIT(12) +#define MII_DP83867_MICR_AUTONEG_COMP_INT_EN BIT(11) +#define MII_DP83867_MICR_LINK_STS_CHNG_INT_EN BIT(10) +#define MII_DP83867_MICR_FALSE_CARRIER_INT_EN BIT(8) +#define MII_DP83867_MICR_SLEEP_MODE_CHNG_INT_EN BIT(4) +#define MII_DP83867_MICR_WOL_INT_EN BIT(3) +#define MII_DP83867_MICR_XGMII_ERR_INT_EN BIT(2) +#define MII_DP83867_MICR_POL_CHNG_INT_EN BIT(1) +#define MII_DP83867_MICR_JABBER_INT_EN BIT(0) + +/* RGMIICTL bits */ +#define DP83867_RGMII_TX_CLK_DELAY_EN BIT(1) +#define DP83867_RGMII_RX_CLK_DELAY_EN BIT(0) + +/* PHY CTRL bits */ +#define DP83867_PHYCR_FIFO_DEPTH_SHIFT 14 + +/* RGMIIDCTL bits */ +#define DP83867_RGMII_TX_CLK_DELAY_SHIFT 4 + +struct dp83867_private { + int rx_id_delay; + int tx_id_delay; + int fifo_depth; +}; + +static int dp83867_ack_interrupt(struct phy_device *phydev) +{ + int err = phy_read(phydev, MII_DP83867_ISR); + + if (err < 0) + return err; + + return 0; +} + +static int dp83867_config_intr(struct phy_device *phydev) +{ + int micr_status; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + micr_status = phy_read(phydev, MII_DP83867_MICR); + if (micr_status < 0) + return micr_status; + + micr_status |= + (MII_DP83867_MICR_AN_ERR_INT_EN | + MII_DP83867_MICR_SPEED_CHNG_INT_EN | + MII_DP83867_MICR_DUP_MODE_CHNG_INT_EN | + MII_DP83867_MICR_SLEEP_MODE_CHNG_INT_EN); + + return phy_write(phydev, MII_DP83867_MICR, micr_status); + } + + micr_status = 0x0; + return phy_write(phydev, MII_DP83867_MICR, micr_status); +} + +#ifdef CONFIG_OF_MDIO +static int dp83867_of_init(struct phy_device *phydev) +{ + struct dp83867_private *dp83867 = phydev->priv; + struct device *dev = &phydev->dev; + struct device_node *of_node = dev->of_node; + int ret; + + if (!of_node && dev->parent->of_node) + of_node = dev->parent->of_node; + + if (!phydev->dev.of_node) + return -ENODEV; + + ret = of_property_read_u32(of_node, "ti,rx_int_delay", + &dp83867->rx_id_delay); + if (ret) + return ret; + + ret = of_property_read_u32(of_node, "ti,tx_int_delay", + &dp83867->tx_id_delay); + if (ret) + return ret; + + ret = of_property_read_u32(of_node, "ti,fifo_depth", + &dp83867->fifo_depth); + if (ret) + return ret; + + return 0; +} +#else +static int dp83867_of_init(struct phy_device *phydev) +{ + return 0; +} +#endif /* CONFIG_OF_MDIO */ + +static int dp83867_config_init(struct phy_device *phydev) +{ + struct dp83867_private *dp83867; + int ret; + u16 val, delay; + + if (!phydev->priv) { + dp83867 = devm_kzalloc(&phydev->dev, sizeof(*dp83867), + GFP_KERNEL); + if (!dp83867) + return -ENOMEM; + + phydev->priv = dp83867; + ret = dp83867_of_init(phydev); + if (ret) + return ret; + } else { + dp83867 = (struct dp83867_private *)phydev->priv; + } + + if (phy_interface_is_rgmii(phydev)) { + ret = phy_write(phydev, MII_DP83867_PHYCTRL, + (dp83867->fifo_depth << DP83867_PHYCR_FIFO_DEPTH_SHIFT)); + if (ret) + return ret; + } + + if ((phydev->interface >= PHY_INTERFACE_MODE_RGMII_ID) || + (phydev->interface <= PHY_INTERFACE_MODE_RGMII_RXID)) { + val = phy_read_mmd_indirect(phydev, DP83867_RGMIICTL, + DP83867_DEVADDR, phydev->addr); + + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) + val |= (DP83867_RGMII_TX_CLK_DELAY_EN | DP83867_RGMII_RX_CLK_DELAY_EN); + + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) + val |= DP83867_RGMII_TX_CLK_DELAY_EN; + + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) + val |= DP83867_RGMII_RX_CLK_DELAY_EN; + + phy_write_mmd_indirect(phydev, DP83867_RGMIICTL, + DP83867_DEVADDR, phydev->addr, val); + + delay = (dp83867->rx_id_delay | + (dp83867->tx_id_delay << DP83867_RGMII_TX_CLK_DELAY_SHIFT)); + + phy_write_mmd_indirect(phydev, DP83867_RGMIIDCTL, + DP83867_DEVADDR, phydev->addr, delay); + } + + return 0; +} + +static int dp83867_phy_reset(struct phy_device *phydev) +{ + int err; + + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESET); + if (err < 0) + return err; + + return dp83867_config_init(phydev); +} + +static struct phy_driver dp83867_driver[] = { + { + .phy_id = DP83867_PHY_ID, + .phy_id_mask = 0xfffffff0, + .name = "TI DP83867", + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + + .config_init = dp83867_config_init, + .soft_reset = dp83867_phy_reset, + + /* IRQ related */ + .ack_interrupt = dp83867_ack_interrupt, + .config_intr = dp83867_config_intr, + + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .suspend = genphy_suspend, + .resume = genphy_resume, + + .driver = {.owner = THIS_MODULE,} + }, +}; +module_phy_driver(dp83867_driver); + +static struct mdio_device_id __maybe_unused dp83867_tbl[] = { + { DP83867_PHY_ID, 0xfffffff0 }, + { } +}; + +MODULE_DEVICE_TABLE(mdio, dp83867_tbl); + +MODULE_DESCRIPTION("Texas Instruments DP83867 PHY driver"); +MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c index 8644f03..0dbc445 100644 --- a/drivers/net/phy/icplus.c +++ b/drivers/net/phy/icplus.c @@ -139,10 +139,7 @@ static int ip1001_config_init(struct phy_device *phydev) if (c < 0) return c; - if ((phydev->interface == PHY_INTERFACE_MODE_RGMII) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)) { + if (phy_interface_is_rgmii(phydev)) { c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS); if (c < 0) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 1b1698f..f721444 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -317,10 +317,7 @@ static int m88e1121_config_aneg(struct phy_device *phydev) if (err < 0) return err; - if ((phydev->interface == PHY_INTERFACE_MODE_RGMII) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)) { + if (phy_interface_is_rgmii(phydev)) { mscr = phy_read(phydev, MII_88E1121_PHY_MSCR_REG) & MII_88E1121_PHY_MSCR_DELAY_MASK; @@ -469,10 +466,7 @@ static int m88e1111_config_init(struct phy_device *phydev) int err; int temp; - if ((phydev->interface == PHY_INTERFACE_MODE_RGMII) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)) { + if (phy_interface_is_rgmii(phydev)) { temp = phy_read(phydev, MII_M1111_PHY_EXT_CR); if (temp < 0) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 377d2db..b2197b5 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1093,8 +1093,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) if ((phydev->duplex == DUPLEX_FULL) && ((phydev->interface == PHY_INTERFACE_MODE_MII) || (phydev->interface == PHY_INTERFACE_MODE_GMII) || - (phydev->interface >= PHY_INTERFACE_MODE_RGMII && - phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID) || + phy_interface_is_rgmii(phydev) || phy_is_internal(phydev))) { int eee_lp, eee_cap, eee_adv; u32 lp, cap, adv; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 5eddbc0..34c519e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2131,9 +2131,10 @@ static void vxlan_cleanup(unsigned long arg) if (!netif_running(vxlan->dev)) return; - spin_lock_bh(&vxlan->hash_lock); for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; + + spin_lock_bh(&vxlan->hash_lock); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); @@ -2152,8 +2153,8 @@ static void vxlan_cleanup(unsigned long arg) } else if (time_before(timeout, next_timer)) next_timer = timeout; } + spin_unlock_bh(&vxlan->hash_lock); } - spin_unlock_bh(&vxlan->hash_lock); mod_timer(&vxlan->age_timer, next_timer); } diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index cce4625..a511ef3 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -889,7 +889,7 @@ void ath6kl_cfg80211_disconnect_event(struct ath6kl_vif *vif, u8 reason, GFP_KERNEL); } else if (vif->sme_state == SME_CONNECTED) { cfg80211_disconnected(vif->ndev, proto_reason, - NULL, 0, GFP_KERNEL); + NULL, 0, false, GFP_KERNEL); } vif->sme_state = SME_DISCONNECTED; @@ -3467,7 +3467,7 @@ void ath6kl_cfg80211_stop(struct ath6kl_vif *vif) GFP_KERNEL); break; case SME_CONNECTED: - cfg80211_disconnected(vif->ndev, 0, NULL, 0, GFP_KERNEL); + cfg80211_disconnected(vif->ndev, 0, NULL, 0, true, GFP_KERNEL); break; } diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c index ef3b6bc..6d704ae 100644 --- a/drivers/net/wireless/ath/wil6210/main.c +++ b/drivers/net/wireless/ath/wil6210/main.c @@ -227,7 +227,7 @@ static void _wil6210_disconnect(struct wil6210_priv *wil, const u8 *bssid, if (test_bit(wil_status_fwconnected, wil->status)) { clear_bit(wil_status_fwconnected, wil->status); cfg80211_disconnected(ndev, reason_code, - NULL, 0, GFP_KERNEL); + NULL, 0, false, GFP_KERNEL); } else if (test_bit(wil_status_fwconnecting, wil->status)) { cfg80211_connect_result(ndev, bssid, NULL, 0, NULL, 0, WLAN_STATUS_UNSPECIFIED_FAILURE, diff --git a/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c index 6fe2b75..e10fa67 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c @@ -1296,7 +1296,7 @@ static void brcmf_link_down(struct brcmf_cfg80211_vif *vif, u16 reason) } clear_bit(BRCMF_VIF_STATUS_CONNECTED, &vif->sme_state); cfg80211_disconnected(vif->wdev.netdev, reason, NULL, 0, - GFP_KERNEL); + true, GFP_KERNEL); } clear_bit(BRCMF_VIF_STATUS_CONNECTING, &vif->sme_state); @@ -1962,7 +1962,7 @@ brcmf_cfg80211_disconnect(struct wiphy *wiphy, struct net_device *ndev, clear_bit(BRCMF_VIF_STATUS_CONNECTED, &ifp->vif->sme_state); clear_bit(BRCMF_VIF_STATUS_CONNECTING, &ifp->vif->sme_state); - cfg80211_disconnected(ndev, reason_code, NULL, 0, GFP_KERNEL); + cfg80211_disconnected(ndev, reason_code, NULL, 0, true, GFP_KERNEL); memcpy(&scbval.ea, &profile->bssid, ETH_ALEN); scbval.val = cpu_to_le32(reason_code); diff --git a/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c index a932e45..1b47de0 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c @@ -500,11 +500,9 @@ static int brcmf_msgbuf_query_dcmd(struct brcmf_pub *drvr, int ifidx, msgbuf->rx_pktids, msgbuf->ioctl_resp_pktid); if (msgbuf->ioctl_resp_ret_len != 0) { - if (!skb) { - brcmf_err("Invalid packet id idx recv'd %d\n", - msgbuf->ioctl_resp_pktid); + if (!skb) return -EBADF; - } + memcpy(buf, skb->data, (len < msgbuf->ioctl_resp_ret_len) ? len : msgbuf->ioctl_resp_ret_len); } @@ -866,10 +864,8 @@ brcmf_msgbuf_process_txstatus(struct brcmf_msgbuf *msgbuf, void *buf) flowid -= BRCMF_NROF_H2D_COMMON_MSGRINGS; skb = brcmf_msgbuf_get_pktid(msgbuf->drvr->bus_if->dev, msgbuf->tx_pktids, idx); - if (!skb) { - brcmf_err("Invalid packet id idx recv'd %d\n", idx); + if (!skb) return; - } set_bit(flowid, msgbuf->txstatus_done_map); commonring = msgbuf->flowrings[flowid]; @@ -1148,6 +1144,8 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf) skb = brcmf_msgbuf_get_pktid(msgbuf->drvr->bus_if->dev, msgbuf->rx_pktids, idx); + if (!skb) + return; if (data_offset) skb_pull(skb, data_offset); diff --git a/drivers/net/wireless/iwlwifi/Kconfig b/drivers/net/wireless/iwlwifi/Kconfig index efe3cf3..aba0957 100644 --- a/drivers/net/wireless/iwlwifi/Kconfig +++ b/drivers/net/wireless/iwlwifi/Kconfig @@ -21,8 +21,8 @@ config IWLWIFI Intel 7260 Wi-Fi Adapter Intel 3160 Wi-Fi Adapter Intel 7265 Wi-Fi Adapter - Intel 3165 Wi-Fi Adapter Intel 8260 Wi-Fi Adapter + Intel 3165 Wi-Fi Adapter This driver uses the kernel's mac80211 subsystem. diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c index 830dfec..80fefe7 100644 --- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c @@ -471,7 +471,7 @@ static int iwl_get_radio_cfg(const struct iwl_cfg *cfg, const __le16 *nvm_sw, if (cfg->device_family != IWL_DEVICE_FAMILY_8000) return le16_to_cpup(nvm_sw + RADIO_CFG); - return le32_to_cpup((__le32 *)(nvm_sw + RADIO_CFG_FAMILY_8000)); + return le32_to_cpup((__le32 *)(phy_sku + RADIO_CFG_FAMILY_8000)); } diff --git a/drivers/net/wireless/iwlwifi/pcie/internal.h b/drivers/net/wireless/iwlwifi/pcie/internal.h index 9a3dae6..31f72a6 100644 --- a/drivers/net/wireless/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/iwlwifi/pcie/internal.h @@ -1,7 +1,7 @@ /****************************************************************************** * - * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. - * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright(c) 2003 - 2015 Intel Corporation. All rights reserved. + * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * * Portions of this file are derived from the ipw3945 project, as well * as portions of the ieee80211 subsystem header files. @@ -355,7 +355,7 @@ struct iwl_trans_pcie { /*protect hw register */ spinlock_t reg_lock; - bool cmd_in_flight; + bool cmd_hold_nic_awake; bool ref_cmd_in_flight; /* protect ref counter */ diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c index dd1b90b..43ae658 100644 --- a/drivers/net/wireless/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/iwlwifi/pcie/trans.c @@ -1387,7 +1387,7 @@ static bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans, bool silent, spin_lock_irqsave(&trans_pcie->reg_lock, *flags); - if (trans_pcie->cmd_in_flight) + if (trans_pcie->cmd_hold_nic_awake) goto out; /* this bit wakes up the NIC */ @@ -1453,7 +1453,7 @@ static void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans, */ __acquire(&trans_pcie->reg_lock); - if (trans_pcie->cmd_in_flight) + if (trans_pcie->cmd_hold_nic_awake) goto out; __iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL, diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c index 2b06f99..2b86c21 100644 --- a/drivers/net/wireless/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/iwlwifi/pcie/tx.c @@ -1039,18 +1039,14 @@ static int iwl_pcie_set_cmd_in_flight(struct iwl_trans *trans, iwl_trans_pcie_ref(trans); } - if (trans_pcie->cmd_in_flight) - return 0; - - trans_pcie->cmd_in_flight = true; - /* * wake up the NIC to make sure that the firmware will see the host * command - we will let the NIC sleep once all the host commands * returned. This needs to be done only on NICs that have * apmg_wake_up_wa set. */ - if (trans->cfg->base_params->apmg_wake_up_wa) { + if (trans->cfg->base_params->apmg_wake_up_wa && + !trans_pcie->cmd_hold_nic_awake) { __iwl_trans_pcie_set_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ); @@ -1062,10 +1058,10 @@ static int iwl_pcie_set_cmd_in_flight(struct iwl_trans *trans, if (ret < 0) { __iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ); - trans_pcie->cmd_in_flight = false; IWL_ERR(trans, "Failed to wake NIC for hcmd\n"); return -EIO; } + trans_pcie->cmd_hold_nic_awake = true; } return 0; @@ -1083,15 +1079,14 @@ static int iwl_pcie_clear_cmd_in_flight(struct iwl_trans *trans) iwl_trans_pcie_unref(trans); } - if (WARN_ON(!trans_pcie->cmd_in_flight)) - return 0; - - trans_pcie->cmd_in_flight = false; + if (trans->cfg->base_params->apmg_wake_up_wa) { + if (WARN_ON(!trans_pcie->cmd_hold_nic_awake)) + return 0; - if (trans->cfg->base_params->apmg_wake_up_wa) + trans_pcie->cmd_hold_nic_awake = false; __iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL, - CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ); - + CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ); + } return 0; } diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c index 1a4d558..8317afd 100644 --- a/drivers/net/wireless/libertas/cfg.c +++ b/drivers/net/wireless/libertas/cfg.c @@ -835,14 +835,13 @@ static int lbs_cfg_scan(struct wiphy *wiphy, * Events */ -void lbs_send_disconnect_notification(struct lbs_private *priv) +void lbs_send_disconnect_notification(struct lbs_private *priv, + bool locally_generated) { lbs_deb_enter(LBS_DEB_CFG80211); - cfg80211_disconnected(priv->dev, - 0, - NULL, 0, - GFP_KERNEL); + cfg80211_disconnected(priv->dev, 0, NULL, 0, locally_generated, + GFP_KERNEL); lbs_deb_leave(LBS_DEB_CFG80211); } @@ -1458,7 +1457,7 @@ int lbs_disconnect(struct lbs_private *priv, u16 reason) cfg80211_disconnected(priv->dev, reason, - NULL, 0, + NULL, 0, true, GFP_KERNEL); priv->connect_status = LBS_DISCONNECTED; @@ -2031,7 +2030,7 @@ static int lbs_leave_ibss(struct wiphy *wiphy, struct net_device *dev) ret = lbs_cmd_with_response(priv, CMD_802_11_AD_HOC_STOP, &cmd); /* TODO: consider doing this at MACREG_INT_CODE_ADHOC_BCN_LOST time */ - lbs_mac_event_disconnected(priv); + lbs_mac_event_disconnected(priv, true); lbs_deb_leave_args(LBS_DEB_CFG80211, "ret %d", ret); return ret; diff --git a/drivers/net/wireless/libertas/cfg.h b/drivers/net/wireless/libertas/cfg.h index 10995f5..acccc29 100644 --- a/drivers/net/wireless/libertas/cfg.h +++ b/drivers/net/wireless/libertas/cfg.h @@ -10,7 +10,8 @@ struct wireless_dev *lbs_cfg_alloc(struct device *dev); int lbs_cfg_register(struct lbs_private *priv); void lbs_cfg_free(struct lbs_private *priv); -void lbs_send_disconnect_notification(struct lbs_private *priv); +void lbs_send_disconnect_notification(struct lbs_private *priv, + bool locally_generated); void lbs_send_mic_failureevent(struct lbs_private *priv, u32 event); void lbs_scan_done(struct lbs_private *priv); diff --git a/drivers/net/wireless/libertas/cmd.h b/drivers/net/wireless/libertas/cmd.h index 4279e8a..0c5444b 100644 --- a/drivers/net/wireless/libertas/cmd.h +++ b/drivers/net/wireless/libertas/cmd.h @@ -68,7 +68,8 @@ int lbs_process_command_response(struct lbs_private *priv, u8 *data, u32 len); /* From cmdresp.c */ -void lbs_mac_event_disconnected(struct lbs_private *priv); +void lbs_mac_event_disconnected(struct lbs_private *priv, + bool locally_generated); diff --git a/drivers/net/wireless/libertas/cmdresp.c b/drivers/net/wireless/libertas/cmdresp.c index 65f18f1..e5442e8 100644 --- a/drivers/net/wireless/libertas/cmdresp.c +++ b/drivers/net/wireless/libertas/cmdresp.c @@ -19,10 +19,13 @@ * reset link state etc. * * @priv: A pointer to struct lbs_private structure + * @locally_generated: indicates disconnect was requested locally + * (usually by userspace) * * returns: n/a */ -void lbs_mac_event_disconnected(struct lbs_private *priv) +void lbs_mac_event_disconnected(struct lbs_private *priv, + bool locally_generated) { if (priv->connect_status != LBS_CONNECTED) return; @@ -36,7 +39,7 @@ void lbs_mac_event_disconnected(struct lbs_private *priv) msleep_interruptible(1000); if (priv->wdev->iftype == NL80211_IFTYPE_STATION) - lbs_send_disconnect_notification(priv); + lbs_send_disconnect_notification(priv, locally_generated); /* report disconnect to upper layer */ netif_stop_queue(priv->dev); @@ -229,17 +232,17 @@ int lbs_process_event(struct lbs_private *priv, u32 event) case MACREG_INT_CODE_DEAUTHENTICATED: lbs_deb_cmd("EVENT: deauthenticated\n"); - lbs_mac_event_disconnected(priv); + lbs_mac_event_disconnected(priv, false); break; case MACREG_INT_CODE_DISASSOCIATED: lbs_deb_cmd("EVENT: disassociated\n"); - lbs_mac_event_disconnected(priv); + lbs_mac_event_disconnected(priv, false); break; case MACREG_INT_CODE_LINK_LOST_NO_SCAN: lbs_deb_cmd("EVENT: link lost\n"); - lbs_mac_event_disconnected(priv); + lbs_mac_event_disconnected(priv, true); break; case MACREG_INT_CODE_PS_SLEEP: diff --git a/drivers/net/wireless/mwifiex/join.c b/drivers/net/wireless/mwifiex/join.c index 6208ef1..cce8e39 100644 --- a/drivers/net/wireless/mwifiex/join.c +++ b/drivers/net/wireless/mwifiex/join.c @@ -1449,7 +1449,7 @@ int mwifiex_deauthenticate(struct mwifiex_private *priv, u8 *mac) ret = mwifiex_deauthenticate_infra(priv, mac); if (ret) cfg80211_disconnected(priv->netdev, 0, NULL, 0, - GFP_KERNEL); + true, GFP_KERNEL); break; case NL80211_IFTYPE_ADHOC: return mwifiex_send_cmd(priv, HostCmd_CMD_802_11_AD_HOC_STOP, diff --git a/drivers/net/wireless/mwifiex/sta_event.c b/drivers/net/wireless/mwifiex/sta_event.c index bed67d4..9520378 100644 --- a/drivers/net/wireless/mwifiex/sta_event.c +++ b/drivers/net/wireless/mwifiex/sta_event.c @@ -136,7 +136,7 @@ mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason_code) if (priv->bss_mode == NL80211_IFTYPE_STATION || priv->bss_mode == NL80211_IFTYPE_P2P_CLIENT) { cfg80211_disconnected(priv->netdev, reason_code, NULL, 0, - GFP_KERNEL); + false, GFP_KERNEL); } eth_zero_addr(priv->cfg_bssid); diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index 96175a7..71a825c 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -2861,7 +2861,7 @@ static void rndis_wlan_do_link_down_work(struct usbnet *usbdev) deauthenticate(usbdev); - cfg80211_disconnected(usbdev->net, 0, NULL, 0, GFP_KERNEL); + cfg80211_disconnected(usbdev->net, 0, NULL, 0, true, GFP_KERNEL); } netif_carrier_off(usbdev->net); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 4de46aa..f1b2c17 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -52,7 +52,7 @@ * event channels are limited resource. Split event channels are * enabled by default. */ -bool separate_tx_rx_irq = 1; +bool separate_tx_rx_irq = true; module_param(separate_tx_rx_irq, bool, 0644); /* The time that packets can stay on the guest Rx internal queue @@ -1250,7 +1250,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, netdev_err(queue->vif->dev, "txreq.offset: %x, size: %u, end: %lu\n", txreq.offset, txreq.size, - (txreq.offset&~PAGE_MASK) + txreq.size); + (unsigned long)(txreq.offset&~PAGE_MASK) + txreq.size); xenvif_fatal_tx_err(queue->vif); break; } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 3d8dbf5..968787a 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -34,6 +34,8 @@ struct backend_info { enum xenbus_state frontend_state; struct xenbus_watch hotplug_status_watch; u8 have_hotplug_status_watch:1; + + const char *hotplug_script; }; static int connect_rings(struct backend_info *be, struct xenvif_queue *queue); @@ -238,6 +240,7 @@ static int netback_remove(struct xenbus_device *dev) xenvif_free(be->vif); be->vif = NULL; } + kfree(be->hotplug_script); kfree(be); dev_set_drvdata(&dev->dev, NULL); return 0; @@ -255,6 +258,7 @@ static int netback_probe(struct xenbus_device *dev, struct xenbus_transaction xbt; int err; int sg; + const char *script; struct backend_info *be = kzalloc(sizeof(struct backend_info), GFP_KERNEL); if (!be) { @@ -347,6 +351,15 @@ static int netback_probe(struct xenbus_device *dev, if (err) pr_debug("Error writing multi-queue-max-queues\n"); + script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL); + if (IS_ERR(script)) { + err = PTR_ERR(script); + xenbus_dev_fatal(dev, err, "reading script"); + goto fail; + } + + be->hotplug_script = script; + err = xenbus_switch_state(dev, XenbusStateInitWait); if (err) goto fail; @@ -379,22 +392,14 @@ static int netback_uevent(struct xenbus_device *xdev, struct kobj_uevent_env *env) { struct backend_info *be = dev_get_drvdata(&xdev->dev); - char *val; - val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL); - if (IS_ERR(val)) { - int err = PTR_ERR(val); - xenbus_dev_fatal(xdev, err, "reading script"); - return err; - } else { - if (add_uevent_var(env, "script=%s", val)) { - kfree(val); - return -ENOMEM; - } - kfree(val); - } + if (!be) + return 0; - if (!be || !be->vif) + if (add_uevent_var(env, "script=%s", be->hotplug_script)) + return -ENOMEM; + + if (!be->vif) return 0; return add_uevent_var(env, "vif=%s", be->vif->dev->name); @@ -793,6 +798,7 @@ static void connect(struct backend_info *be) goto err; } + queue->credit_bytes = credit_bytes; queue->remaining_credit = credit_bytes; queue->credit_usec = credit_usec; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 3f45afd4..c89ca26 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1560,9 +1560,8 @@ static int xennet_init_queue(struct netfront_queue *queue) spin_lock_init(&queue->tx_lock); spin_lock_init(&queue->rx_lock); - init_timer(&queue->rx_refill_timer); - queue->rx_refill_timer.data = (unsigned long)queue; - queue->rx_refill_timer.function = rx_refill_timeout; + setup_timer(&queue->rx_refill_timer, rx_refill_timeout, + (unsigned long)queue); snprintf(queue->name, sizeof(queue->name), "%s-q%u", queue->info->netdev->name, queue->id); @@ -1698,6 +1697,7 @@ static void xennet_destroy_queues(struct netfront_info *info) if (netif_running(info->netdev)) napi_disable(&queue->napi); + del_timer_sync(&queue->rx_refill_timer); netif_napi_del(&queue->napi); } @@ -2102,9 +2102,6 @@ static const struct attribute_group xennet_dev_group = { static int xennet_remove(struct xenbus_device *dev) { struct netfront_info *info = dev_get_drvdata(&dev->dev); - unsigned int num_queues = info->netdev->real_num_tx_queues; - struct netfront_queue *queue = NULL; - unsigned int i = 0; dev_dbg(&dev->dev, "%s\n", dev->nodename); @@ -2112,16 +2109,7 @@ static int xennet_remove(struct xenbus_device *dev) unregister_netdev(info->netdev); - for (i = 0; i < num_queues; ++i) { - queue = &info->queues[i]; - del_timer_sync(&queue->rx_refill_timer); - } - - if (num_queues) { - kfree(info->queues); - info->queues = NULL; - } - + xennet_destroy_queues(info); xennet_free_netdev(info->netdev); return 0; diff --git a/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c b/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c index 4ad5c1a..e406e3d 100644 --- a/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c @@ -643,7 +643,9 @@ static const struct cygnus_gpio_pin_range cygnus_gpio_pintable[] = { CYGNUS_PINRANGE(87, 104, 12), CYGNUS_PINRANGE(99, 102, 2), CYGNUS_PINRANGE(101, 90, 4), - CYGNUS_PINRANGE(105, 116, 10), + CYGNUS_PINRANGE(105, 116, 6), + CYGNUS_PINRANGE(111, 100, 2), + CYGNUS_PINRANGE(113, 122, 4), CYGNUS_PINRANGE(123, 11, 1), CYGNUS_PINRANGE(124, 38, 4), CYGNUS_PINRANGE(128, 43, 1), diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 82f691e..732ff75 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1292,6 +1292,49 @@ static void chv_gpio_irq_unmask(struct irq_data *d) chv_gpio_irq_mask_unmask(d, false); } +static unsigned chv_gpio_irq_startup(struct irq_data *d) +{ + /* + * Check if the interrupt has been requested with 0 as triggering + * type. In that case it is assumed that the current values + * programmed to the hardware are used (e.g BIOS configured + * defaults). + * + * In that case ->irq_set_type() will never be called so we need to + * read back the values from hardware now, set correct flow handler + * and update mappings before the interrupt is being used. + */ + if (irqd_get_trigger_type(d) == IRQ_TYPE_NONE) { + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct chv_pinctrl *pctrl = gpiochip_to_pinctrl(gc); + unsigned offset = irqd_to_hwirq(d); + int pin = chv_gpio_offset_to_pin(pctrl, offset); + irq_flow_handler_t handler; + unsigned long flags; + u32 intsel, value; + + intsel = readl(chv_padreg(pctrl, pin, CHV_PADCTRL0)); + intsel &= CHV_PADCTRL0_INTSEL_MASK; + intsel >>= CHV_PADCTRL0_INTSEL_SHIFT; + + value = readl(chv_padreg(pctrl, pin, CHV_PADCTRL1)); + if (value & CHV_PADCTRL1_INTWAKECFG_LEVEL) + handler = handle_level_irq; + else + handler = handle_edge_irq; + + spin_lock_irqsave(&pctrl->lock, flags); + if (!pctrl->intr_lines[intsel]) { + __irq_set_handler_locked(d->irq, handler); + pctrl->intr_lines[intsel] = offset; + } + spin_unlock_irqrestore(&pctrl->lock, flags); + } + + chv_gpio_irq_unmask(d); + return 0; +} + static int chv_gpio_irq_type(struct irq_data *d, unsigned type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); @@ -1357,6 +1400,7 @@ static int chv_gpio_irq_type(struct irq_data *d, unsigned type) static struct irq_chip chv_gpio_irqchip = { .name = "chv-gpio", + .irq_startup = chv_gpio_irq_startup, .irq_ack = chv_gpio_irq_ack, .irq_mask = chv_gpio_irq_mask, .irq_unmask = chv_gpio_irq_unmask, diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index edcd140..a70a5fe 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -569,7 +569,7 @@ static int meson_gpiolib_register(struct meson_pinctrl *pc) domain->chip.direction_output = meson_gpio_direction_output; domain->chip.get = meson_gpio_get; domain->chip.set = meson_gpio_set; - domain->chip.base = -1; + domain->chip.base = domain->data->pin_base; domain->chip.ngpio = domain->data->num_pins; domain->chip.can_sleep = false; domain->chip.of_node = domain->of_node; diff --git a/drivers/pinctrl/meson/pinctrl-meson8b.c b/drivers/pinctrl/meson/pinctrl-meson8b.c index 2f7ea62..9677807 100644 --- a/drivers/pinctrl/meson/pinctrl-meson8b.c +++ b/drivers/pinctrl/meson/pinctrl-meson8b.c @@ -876,13 +876,13 @@ static struct meson_domain_data meson8b_domain_data[] = { .banks = meson8b_banks, .num_banks = ARRAY_SIZE(meson8b_banks), .pin_base = 0, - .num_pins = 83, + .num_pins = 130, }, { .name = "ao-bank", .banks = meson8b_ao_banks, .num_banks = ARRAY_SIZE(meson8b_ao_banks), - .pin_base = 83, + .pin_base = 130, .num_pins = 16, }, }; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 9bb9ad6..28f3281 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -2897,7 +2897,7 @@ static ssize_t hotkey_wakeup_reason_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%d\n", hotkey_wakeup_reason); } -static DEVICE_ATTR_RO(hotkey_wakeup_reason); +static DEVICE_ATTR(wakeup_reason, S_IRUGO, hotkey_wakeup_reason_show, NULL); static void hotkey_wakeup_reason_notify_change(void) { @@ -2913,7 +2913,8 @@ static ssize_t hotkey_wakeup_hotunplug_complete_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%d\n", hotkey_autosleep_ack); } -static DEVICE_ATTR_RO(hotkey_wakeup_hotunplug_complete); +static DEVICE_ATTR(wakeup_hotunplug_complete, S_IRUGO, + hotkey_wakeup_hotunplug_complete_show, NULL); static void hotkey_wakeup_hotunplug_complete_notify_change(void) { @@ -2978,8 +2979,8 @@ static struct attribute *hotkey_attributes[] __initdata = { &dev_attr_hotkey_enable.attr, &dev_attr_hotkey_bios_enabled.attr, &dev_attr_hotkey_bios_mask.attr, - &dev_attr_hotkey_wakeup_reason.attr, - &dev_attr_hotkey_wakeup_hotunplug_complete.attr, + &dev_attr_wakeup_reason.attr, + &dev_attr_wakeup_hotunplug_complete.attr, &dev_attr_hotkey_mask.attr, &dev_attr_hotkey_all_mask.attr, &dev_attr_hotkey_recommended_mask.attr, @@ -4393,12 +4394,13 @@ static ssize_t wan_enable_store(struct device *dev, attr, buf, count); } -static DEVICE_ATTR_RW(wan_enable); +static DEVICE_ATTR(wwan_enable, S_IWUSR | S_IRUGO, + wan_enable_show, wan_enable_store); /* --------------------------------------------------------------------- */ static struct attribute *wan_attributes[] = { - &dev_attr_wan_enable.attr, + &dev_attr_wwan_enable.attr, NULL }; @@ -8138,7 +8140,8 @@ static ssize_t fan_pwm1_enable_store(struct device *dev, return count; } -static DEVICE_ATTR_RW(fan_pwm1_enable); +static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO, + fan_pwm1_enable_show, fan_pwm1_enable_store); /* sysfs fan pwm1 ------------------------------------------------------ */ static ssize_t fan_pwm1_show(struct device *dev, @@ -8198,7 +8201,7 @@ static ssize_t fan_pwm1_store(struct device *dev, return (rc) ? rc : count; } -static DEVICE_ATTR_RW(fan_pwm1); +static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, fan_pwm1_show, fan_pwm1_store); /* sysfs fan fan1_input ------------------------------------------------ */ static ssize_t fan_fan1_input_show(struct device *dev, @@ -8215,7 +8218,7 @@ static ssize_t fan_fan1_input_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%u\n", speed); } -static DEVICE_ATTR_RO(fan_fan1_input); +static DEVICE_ATTR(fan1_input, S_IRUGO, fan_fan1_input_show, NULL); /* sysfs fan fan2_input ------------------------------------------------ */ static ssize_t fan_fan2_input_show(struct device *dev, @@ -8232,7 +8235,7 @@ static ssize_t fan_fan2_input_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%u\n", speed); } -static DEVICE_ATTR_RO(fan_fan2_input); +static DEVICE_ATTR(fan2_input, S_IRUGO, fan_fan2_input_show, NULL); /* sysfs fan fan_watchdog (hwmon driver) ------------------------------- */ static ssize_t fan_fan_watchdog_show(struct device_driver *drv, @@ -8265,8 +8268,8 @@ static DRIVER_ATTR(fan_watchdog, S_IWUSR | S_IRUGO, /* --------------------------------------------------------------------- */ static struct attribute *fan_attributes[] = { - &dev_attr_fan_pwm1_enable.attr, &dev_attr_fan_pwm1.attr, - &dev_attr_fan_fan1_input.attr, + &dev_attr_pwm1_enable.attr, &dev_attr_pwm1.attr, + &dev_attr_fan1_input.attr, NULL, /* for fan2_input */ NULL }; @@ -8400,7 +8403,7 @@ static int __init fan_init(struct ibm_init_struct *iibm) if (tp_features.second_fan) { /* attach second fan tachometer */ fan_attributes[ARRAY_SIZE(fan_attributes)-2] = - &dev_attr_fan_fan2_input.attr; + &dev_attr_fan2_input.attr; } rc = sysfs_create_group(&tpacpi_sensors_pdev->dev.kobj, &fan_attr_group); @@ -8848,7 +8851,7 @@ static ssize_t thinkpad_acpi_pdev_name_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%s\n", TPACPI_NAME); } -static DEVICE_ATTR_RO(thinkpad_acpi_pdev_name); +static DEVICE_ATTR(name, S_IRUGO, thinkpad_acpi_pdev_name_show, NULL); /* --------------------------------------------------------------------- */ @@ -9390,8 +9393,7 @@ static void thinkpad_acpi_module_exit(void) hwmon_device_unregister(tpacpi_hwmon); if (tp_features.sensors_pdev_attrs_registered) - device_remove_file(&tpacpi_sensors_pdev->dev, - &dev_attr_thinkpad_acpi_pdev_name); + device_remove_file(&tpacpi_sensors_pdev->dev, &dev_attr_name); if (tpacpi_sensors_pdev) platform_device_unregister(tpacpi_sensors_pdev); if (tpacpi_pdev) @@ -9512,8 +9514,7 @@ static int __init thinkpad_acpi_module_init(void) thinkpad_acpi_module_exit(); return ret; } - ret = device_create_file(&tpacpi_sensors_pdev->dev, - &dev_attr_thinkpad_acpi_pdev_name); + ret = device_create_file(&tpacpi_sensors_pdev->dev, &dev_attr_name); if (ret) { pr_err("unable to create sysfs hwmon device attributes\n"); thinkpad_acpi_module_exit(); diff --git a/drivers/regulator/da9052-regulator.c b/drivers/regulator/da9052-regulator.c index 8a4df7a..e628d4c 100644 --- a/drivers/regulator/da9052-regulator.c +++ b/drivers/regulator/da9052-regulator.c @@ -394,6 +394,7 @@ static inline struct da9052_regulator_info *find_regulator_info(u8 chip_id, static int da9052_regulator_probe(struct platform_device *pdev) { + const struct mfd_cell *cell = mfd_get_cell(pdev); struct regulator_config config = { }; struct da9052_regulator *regulator; struct da9052 *da9052; @@ -409,7 +410,7 @@ static int da9052_regulator_probe(struct platform_device *pdev) regulator->da9052 = da9052; regulator->info = find_regulator_info(regulator->da9052->chip_id, - pdev->id); + cell->id); if (regulator->info == NULL) { dev_err(&pdev->dev, "invalid regulator ID specified\n"); return -EINVAL; @@ -419,7 +420,7 @@ static int da9052_regulator_probe(struct platform_device *pdev) config.driver_data = regulator; config.regmap = da9052->regmap; if (pdata && pdata->regulators) { - config.init_data = pdata->regulators[pdev->id]; + config.init_data = pdata->regulators[cell->id]; } else { #ifdef CONFIG_OF struct device_node *nproot = da9052->dev->of_node; diff --git a/drivers/scsi/be2iscsi/be.h b/drivers/scsi/be2iscsi/be.h index 81e83a6..3207009 100644 --- a/drivers/scsi/be2iscsi/be.h +++ b/drivers/scsi/be2iscsi/be.h @@ -1,5 +1,5 @@ /** - * Copyright (C) 2005 - 2014 Emulex + * Copyright (C) 2005 - 2015 Avago Technologies * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -8,9 +8,9 @@ * Public License is included in this distribution in the file called COPYING. * * Contact Information: - * linux-drivers@emulex.com + * linux-drivers@avagotech.com * - * Emulex + * Avago Technologies * 3333 Susan Street * Costa Mesa, CA 92626 */ diff --git a/drivers/scsi/be2iscsi/be_cmds.c b/drivers/scsi/be2iscsi/be_cmds.c index 1028760..447cf7c 100644 --- a/drivers/scsi/be2iscsi/be_cmds.c +++ b/drivers/scsi/be2iscsi/be_cmds.c @@ -1,5 +1,5 @@ /** - * Copyright (C) 2005 - 2014 Emulex + * Copyright (C) 2005 - 2015 Avago Technologies * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -8,9 +8,9 @@ * Public License is included in this distribution in the file called COPYING. * * Contact Information: - * linux-drivers@emulex.com + * linux-drivers@avagotech.com * - * Emulex + * Avago Technologies * 3333 Susan Street * Costa Mesa, CA 92626 */ diff --git a/drivers/scsi/be2iscsi/be_cmds.h b/drivers/scsi/be2iscsi/be_cmds.h index 98897434..f11d325 100644 --- a/drivers/scsi/be2iscsi/be_cmds.h +++ b/drivers/scsi/be2iscsi/be_cmds.h @@ -1,5 +1,5 @@ /** - * Copyright (C) 2005 - 2014 Emulex + * Copyright (C) 2005 - 2015 Avago Technologies * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -8,9 +8,9 @@ * Public License is included in this distribution in the file called COPYING. * * Contact Information: - * linux-drivers@emulex.com + * linux-drivers@avagotech.com * - * Emulex + * Avago Technologies * 3333 Susan Street * Costa Mesa, CA 92626 */ diff --git a/drivers/scsi/be2iscsi/be_iscsi.c b/drivers/scsi/be2iscsi/be_iscsi.c index b7391a3..2f07007 100644 --- a/drivers/scsi/be2iscsi/be_iscsi.c +++ b/drivers/scsi/be2iscsi/be_iscsi.c @@ -1,5 +1,5 @@ /** - * Copyright (C) 2005 - 2014 Emulex + * Copyright (C) 2005 - 2015 Avago Technologies * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -7,12 +7,12 @@ * as published by the Free Software Foundation. The full GNU General * Public License is included in this distribution in the file called COPYING. * - * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com) + * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com) * * Contact Information: - * linux-drivers@emulex.com + * linux-drivers@avagotech.com * - * Emulex + * Avago Technologies * 3333 Susan Street * Costa Mesa, CA 92626 */ diff --git a/drivers/scsi/be2iscsi/be_iscsi.h b/drivers/scsi/be2iscsi/be_iscsi.h index e0b3b2d..0c84e1c 100644 --- a/drivers/scsi/be2iscsi/be_iscsi.h +++ b/drivers/scsi/be2iscsi/be_iscsi.h @@ -1,5 +1,5 @@ /** - * Copyright (C) 2005 - 2014 Emulex + * Copyright (C) 2005 - 2015 Avago Technologies * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -7,12 +7,12 @@ * as published by the Free Software Foundation. The full GNU General * Public License is included in this distribution in the file called COPYING. * - * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com) + * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com) * * Contact Information: - * linux-drivers@emulex.com + * linux-drivers@avagotech.com * - * Emulex + * Avago Technologies * 3333 Susan Street * Costa Mesa, CA 92626 */ diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index 923a2b5..1f74760 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -1,5 +1,5 @@ /** - * Copyright (C) 2005 - 2014 Emulex + * Copyright (C) 2005 - 2015 Avago Technologies * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -7,12 +7,12 @@ * as published by the Free Software Foundation. The full GNU General * Public License is included in this distribution in the file called COPYING. * - * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com) + * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com) * * Contact Information: - * linux-drivers@emulex.com + * linux-drivers@avagotech.com * - * Emulex + * Avago Technologies * 3333 Susan Street * Costa Mesa, CA 92626 */ @@ -50,7 +50,7 @@ static unsigned int enable_msix = 1; MODULE_DESCRIPTION(DRV_DESC " " BUILD_STR); MODULE_VERSION(BUILD_STR); -MODULE_AUTHOR("Emulex Corporation"); +MODULE_AUTHOR("Avago Technologies"); MODULE_LICENSE("GPL"); module_param(be_iopoll_budget, int, 0); module_param(enable_msix, int, 0); @@ -552,7 +552,7 @@ MODULE_DEVICE_TABLE(pci, beiscsi_pci_id_table); static struct scsi_host_template beiscsi_sht = { .module = THIS_MODULE, - .name = "Emulex 10Gbe open-iscsi Initiator Driver", + .name = "Avago Technologies 10Gbe open-iscsi Initiator Driver", .proc_name = DRV_NAME, .queuecommand = iscsi_queuecommand, .change_queue_depth = scsi_change_queue_depth, diff --git a/drivers/scsi/be2iscsi/be_main.h b/drivers/scsi/be2iscsi/be_main.h index 7ee0ffc..e70ea26b 100644 --- a/drivers/scsi/be2iscsi/be_main.h +++ b/drivers/scsi/be2iscsi/be_main.h @@ -1,5 +1,5 @@ /** - * Copyright (C) 2005 - 2014 Emulex + * Copyright (C) 2005 - 2015 Avago Technologies * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -7,12 +7,12 @@ * as published by the Free Software Foundation. The full GNU General * Public License is included in this distribution in the file called COPYING. * - * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com) + * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com) * * Contact Information: - * linux-drivers@emulex.com + * linux-drivers@avagotech.com * - * Emulex + * Avago Technologies * 3333 Susan Street * Costa Mesa, CA 92626 */ @@ -37,7 +37,7 @@ #define DRV_NAME "be2iscsi" #define BUILD_STR "10.4.114.0" -#define BE_NAME "Emulex OneConnect" \ +#define BE_NAME "Avago Technologies OneConnect" \ "Open-iSCSI Driver version" BUILD_STR #define DRV_DESC BE_NAME " " "Driver" diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c index 681d4e8..c2c4d69 100644 --- a/drivers/scsi/be2iscsi/be_mgmt.c +++ b/drivers/scsi/be2iscsi/be_mgmt.c @@ -1,5 +1,5 @@ /** - * Copyright (C) 2005 - 2014 Emulex + * Copyright (C) 2005 - 2015 Avago Technologies * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -7,12 +7,12 @@ * as published by the Free Software Foundation. The full GNU General * Public License is included in this distribution in the file called COPYING. * - * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com) + * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com) * * Contact Information: - * linux-drivers@emulex.com + * linux-drivers@avagotech.com * - * Emulex + * Avago Technologies * 3333 Susan Street * Costa Mesa, CA 92626 */ diff --git a/drivers/scsi/be2iscsi/be_mgmt.h b/drivers/scsi/be2iscsi/be_mgmt.h index bd81446..9356b9a 100644 --- a/drivers/scsi/be2iscsi/be_mgmt.h +++ b/drivers/scsi/be2iscsi/be_mgmt.h @@ -1,5 +1,5 @@ /** - * Copyright (C) 2005 - 2014 Emulex + * Copyright (C) 2005 - 2015 Avago Technologies * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -7,12 +7,12 @@ * as published by the Free Software Foundation. The full GNU General * Public License is included in this distribution in the file called COPYING. * - * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com) + * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com) * * Contact Information: - * linux-drivers@emulex.com + * linux-drivers@avagotech.com * - * Emulex + * Avago Technologies * 3333 Susan Street * Costa Mesa, CA 92626 */ diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index eb58afc..45d3039 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -728,7 +728,7 @@ static struct cxgbi_sock *cxgbi_check_route6(struct sockaddr *dst_addr) } ndev = n->dev; - if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) { + if (ipv6_addr_is_multicast(&daddr6->sin6_addr)) { pr_info("multi-cast route %pI6 port %u, dev %s.\n", daddr6->sin6_addr.s6_addr, ntohs(daddr6->sin6_port), ndev->name); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index cb73cf9..c140f99 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -1130,25 +1130,6 @@ lpfc_release_scsi_buf(struct lpfc_hba *phba, struct lpfc_scsi_buf *psb) } /** - * lpfc_fcpcmd_to_iocb - copy the fcp_cmd data into the IOCB - * @data: A pointer to the immediate command data portion of the IOCB. - * @fcp_cmnd: The FCP Command that is provided by the SCSI layer. - * - * The routine copies the entire FCP command from @fcp_cmnd to @data while - * byte swapping the data to big endian format for transmission on the wire. - **/ -static void -lpfc_fcpcmd_to_iocb(uint8_t *data, struct fcp_cmnd *fcp_cmnd) -{ - int i, j; - - for (i = 0, j = 0; i < sizeof(struct fcp_cmnd); - i += sizeof(uint32_t), j++) { - ((uint32_t *)data)[j] = cpu_to_be32(((uint32_t *)fcp_cmnd)[j]); - } -} - -/** * lpfc_scsi_prep_dma_buf_s3 - DMA mapping for scsi buffer to SLI3 IF spec * @phba: The Hba for which this call is being executed. * @lpfc_cmd: The scsi buffer which is going to be mapped. @@ -1283,7 +1264,6 @@ lpfc_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd) * we need to set word 4 of IOCB here */ iocb_cmd->un.fcpi.fcpi_parm = scsi_bufflen(scsi_cmnd); - lpfc_fcpcmd_to_iocb(iocb_cmd->unsli3.fcp_ext.icd, fcp_cmnd); return 0; } @@ -4147,6 +4127,24 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, } /** + * lpfc_fcpcmd_to_iocb - copy the fcp_cmd data into the IOCB + * @data: A pointer to the immediate command data portion of the IOCB. + * @fcp_cmnd: The FCP Command that is provided by the SCSI layer. + * + * The routine copies the entire FCP command from @fcp_cmnd to @data while + * byte swapping the data to big endian format for transmission on the wire. + **/ +static void +lpfc_fcpcmd_to_iocb(uint8_t *data, struct fcp_cmnd *fcp_cmnd) +{ + int i, j; + for (i = 0, j = 0; i < sizeof(struct fcp_cmnd); + i += sizeof(uint32_t), j++) { + ((uint32_t *)data)[j] = cpu_to_be32(((uint32_t *)fcp_cmnd)[j]); + } +} + +/** * lpfc_scsi_prep_cmnd - Wrapper func for convert scsi cmnd to FCP info unit * @vport: The virtual port for which this call is being executed. * @lpfc_cmd: The scsi command which needs to send. @@ -4225,6 +4223,9 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd, fcp_cmnd->fcpCntl3 = 0; phba->fc4ControlRequests++; } + if (phba->sli_rev == 3 && + !(phba->sli3_options & LPFC_SLI3_BG_ENABLED)) + lpfc_fcpcmd_to_iocb(iocb_cmd->unsli3.fcp_ext.icd, fcp_cmnd); /* * Finish initializing those IOCB fields that are independent * of the scsi_cmnd request_buffer diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 68c2002..e32d24e 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -27,6 +27,7 @@ #include <linux/moduleparam.h> #include <generated/utsrelease.h> #include <linux/utsname.h> +#include <linux/vmalloc.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> @@ -1020,8 +1021,7 @@ static void tcm_qla2xxx_depend_tpg(struct work_struct *work) struct se_portal_group *se_tpg = &base_tpg->se_tpg; struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha; - if (!configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys, - &se_tpg->tpg_group.cg_item)) { + if (!target_depend_item(&se_tpg->tpg_group.cg_item)) { atomic_set(&base_tpg->lport_tpg_enabled, 1); qlt_enable_vha(base_vha); } @@ -1037,8 +1037,7 @@ static void tcm_qla2xxx_undepend_tpg(struct work_struct *work) if (!qlt_stop_phase1(base_vha->vha_tgt.qla_tgt)) { atomic_set(&base_tpg->lport_tpg_enabled, 0); - configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys, - &se_tpg->tpg_group.cg_item); + target_undepend_item(&se_tpg->tpg_group.cg_item); } complete(&base_tpg->tpg_base_comp); } diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index 8f6d0fb..a7cfc27 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -26,6 +26,7 @@ #include <linux/mutex.h> #include <linux/aer.h> #include <linux/bsg-lib.h> +#include <linux/vmalloc.h> #include <net/tcp.h> #include <scsi/scsi.h> diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 79beebf..7f9d65f 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1600,6 +1600,7 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) { u64 start_lba = blk_rq_pos(scmd->request); u64 end_lba = blk_rq_pos(scmd->request) + (scsi_bufflen(scmd) / 512); + u64 factor = scmd->device->sector_size / 512; u64 bad_lba; int info_valid; /* @@ -1621,16 +1622,9 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) if (scsi_bufflen(scmd) <= scmd->device->sector_size) return 0; - if (scmd->device->sector_size < 512) { - /* only legitimate sector_size here is 256 */ - start_lba <<= 1; - end_lba <<= 1; - } else { - /* be careful ... don't want any overflows */ - unsigned int factor = scmd->device->sector_size / 512; - do_div(start_lba, factor); - do_div(end_lba, factor); - } + /* be careful ... don't want any overflows */ + do_div(start_lba, factor); + do_div(end_lba, factor); /* The bad lba was reported incorrectly, we have no idea where * the error is. @@ -2188,8 +2182,7 @@ got_data: if (sector_size != 512 && sector_size != 1024 && sector_size != 2048 && - sector_size != 4096 && - sector_size != 256) { + sector_size != 4096) { sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n", sector_size); /* @@ -2244,8 +2237,6 @@ got_data: sdkp->capacity <<= 2; else if (sector_size == 1024) sdkp->capacity <<= 1; - else if (sector_size == 256) - sdkp->capacity >>= 1; blk_queue_physical_block_size(sdp->request_queue, sdkp->physical_block_size); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index d9dad90..3c6584f 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1600,8 +1600,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) break; default: vm_srb->data_in = UNKNOWN_TYPE; - vm_srb->win8_extension.srb_flags |= (SRB_FLAGS_DATA_IN | - SRB_FLAGS_DATA_OUT); + vm_srb->win8_extension.srb_flags |= SRB_FLAGS_NO_DATA_TRANSFER; break; } diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c index 15a7ee3..5fe1c22 100644 --- a/drivers/ssb/driver_pcicore.c +++ b/drivers/ssb/driver_pcicore.c @@ -359,12 +359,13 @@ static void ssb_pcicore_init_hostmode(struct ssb_pcicore *pc) /* * Accessing PCI config without a proper delay after devices reset (not - * GPIO reset) was causing reboots on WRT300N v1.0. + * GPIO reset) was causing reboots on WRT300N v1.0 (BCM4704). * Tested delay 850 us lowered reboot chance to 50-80%, 1000 us fixed it * completely. Flushing all writes was also tested but with no luck. + * The same problem was reported for WRT350N v1 (BCM4705), so we just + * sleep here unconditionally. */ - if (pc->dev->bus->chip_id == 0x4704) - usleep_range(1000, 2000); + usleep_range(1000, 2000); /* Enable PCI bridge BAR0 prefetch and burst */ val = PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY; diff --git a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c index bc95ce8..5ab2f69 100644 --- a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c @@ -379,7 +379,7 @@ void rtw_cfg80211_indicate_disconnect(struct rtw_adapter *padapter) GFP_ATOMIC); } else { cfg80211_disconnected(padapter->pnetdev, 0, NULL, - 0, GFP_ATOMIC); + 0, false, GFP_ATOMIC); } } } diff --git a/drivers/staging/wlan-ng/cfg80211.c b/drivers/staging/wlan-ng/cfg80211.c index 7c87aec..342e2b3 100644 --- a/drivers/staging/wlan-ng/cfg80211.c +++ b/drivers/staging/wlan-ng/cfg80211.c @@ -722,7 +722,7 @@ void prism2_connect_result(wlandevice_t *wlandev, u8 failed) void prism2_disconnected(wlandevice_t *wlandev) { cfg80211_disconnected(wlandev->netdev, 0, NULL, - 0, GFP_KERNEL); + 0, false, GFP_KERNEL); } void prism2_roamed(wlandevice_t *wlandev) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 34871a6..eb66d36 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -21,6 +21,7 @@ #include <linux/crypto.h> #include <linux/completion.h> #include <linux/module.h> +#include <linux/vmalloc.h> #include <linux/idr.h> #include <asm/unaligned.h> #include <scsi/scsi_device.h> @@ -230,7 +231,7 @@ int iscsit_access_np(struct iscsi_np *np, struct iscsi_portal_group *tpg) * Here we serialize access across the TIQN+TPG Tuple. */ ret = down_interruptible(&tpg->np_login_sem); - if ((ret != 0) || signal_pending(current)) + if (ret != 0) return -1; spin_lock_bh(&tpg->tpg_state_lock); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 8ce94ff..70d799d 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -346,6 +346,7 @@ static int iscsi_login_zero_tsih_s1( if (IS_ERR(sess->se_sess)) { iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_NO_RESOURCES); + kfree(sess->sess_ops); kfree(sess); return -ENOMEM; } diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index e8a2408..5e3295f 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -161,10 +161,7 @@ struct iscsi_portal_group *iscsit_get_tpg_from_np( int iscsit_get_tpg( struct iscsi_portal_group *tpg) { - int ret; - - ret = mutex_lock_interruptible(&tpg->tpg_access_lock); - return ((ret != 0) || signal_pending(current)) ? -1 : 0; + return mutex_lock_interruptible(&tpg->tpg_access_lock); } void iscsit_put_tpg(struct iscsi_portal_group *tpg) diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c index 75cbde1..4f8d4d4 100644 --- a/drivers/target/target_core_alua.c +++ b/drivers/target/target_core_alua.c @@ -704,7 +704,7 @@ target_alua_state_check(struct se_cmd *cmd) if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE) return 0; - if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) + if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) return 0; if (!port) @@ -2377,7 +2377,7 @@ ssize_t core_alua_store_secondary_write_metadata( int core_setup_alua(struct se_device *dev) { - if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV && + if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) && !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) { struct t10_alua_lu_gp_member *lu_gp_mem; diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index ddaf76a..e7b0430 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -212,10 +212,6 @@ static struct config_group *target_core_register_fabric( pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric:" " %s\n", tf->tf_group.cg_item.ci_name); - /* - * Setup tf_ops.tf_subsys pointer for usage with configfs_depend_item() - */ - tf->tf_ops.tf_subsys = tf->tf_subsys; tf->tf_fabric = &tf->tf_group.cg_item; pr_debug("Target_Core_ConfigFS: REGISTER -> Set tf->tf_fabric" " for %s\n", name); @@ -291,10 +287,17 @@ static struct configfs_subsystem target_core_fabrics = { }, }; -struct configfs_subsystem *target_core_subsystem[] = { - &target_core_fabrics, - NULL, -}; +int target_depend_item(struct config_item *item) +{ + return configfs_depend_item(&target_core_fabrics, item); +} +EXPORT_SYMBOL(target_depend_item); + +void target_undepend_item(struct config_item *item) +{ + return configfs_undepend_item(&target_core_fabrics, item); +} +EXPORT_SYMBOL(target_undepend_item); /*############################################################################## // Start functions called by external Target Fabrics Modules @@ -467,7 +470,6 @@ int target_register_template(const struct target_core_fabric_ops *fo) * struct target_fabric_configfs->tf_cit_tmpl */ tf->tf_module = fo->module; - tf->tf_subsys = target_core_subsystem[0]; snprintf(tf->tf_name, TARGET_FABRIC_NAME_SIZE, "%s", fo->name); tf->tf_ops = *fo; @@ -809,7 +811,7 @@ static ssize_t target_core_dev_pr_show_attr_res_holder(struct se_device *dev, { int ret; - if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) + if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) return sprintf(page, "Passthrough\n"); spin_lock(&dev->dev_reservation_lock); @@ -960,7 +962,7 @@ SE_DEV_PR_ATTR_RO(res_pr_type); static ssize_t target_core_dev_pr_show_attr_res_type( struct se_device *dev, char *page) { - if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) + if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) return sprintf(page, "SPC_PASSTHROUGH\n"); else if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS) return sprintf(page, "SPC2_RESERVATIONS\n"); @@ -973,7 +975,7 @@ SE_DEV_PR_ATTR_RO(res_type); static ssize_t target_core_dev_pr_show_attr_res_aptpl_active( struct se_device *dev, char *page) { - if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) + if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) return 0; return sprintf(page, "APTPL Bit Status: %s\n", @@ -988,7 +990,7 @@ SE_DEV_PR_ATTR_RO(res_aptpl_active); static ssize_t target_core_dev_pr_show_attr_res_aptpl_metadata( struct se_device *dev, char *page) { - if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) + if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) return 0; return sprintf(page, "Ready to process PR APTPL metadata..\n"); @@ -1035,7 +1037,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata( u16 port_rpti = 0, tpgt = 0; u8 type = 0, scope; - if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) + if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) return 0; if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS) return 0; @@ -2870,7 +2872,7 @@ static int __init target_core_init_configfs(void) { struct config_group *target_cg, *hba_cg = NULL, *alua_cg = NULL; struct config_group *lu_gp_cg = NULL; - struct configfs_subsystem *subsys; + struct configfs_subsystem *subsys = &target_core_fabrics; struct t10_alua_lu_gp *lu_gp; int ret; @@ -2878,7 +2880,6 @@ static int __init target_core_init_configfs(void) " Engine: %s on %s/%s on "UTS_RELEASE"\n", TARGET_CORE_VERSION, utsname()->sysname, utsname()->machine); - subsys = target_core_subsystem[0]; config_group_init(&subsys->su_group); mutex_init(&subsys->su_mutex); @@ -3008,13 +3009,10 @@ out_global: static void __exit target_core_exit_configfs(void) { - struct configfs_subsystem *subsys; struct config_group *hba_cg, *alua_cg, *lu_gp_cg; struct config_item *item; int i; - subsys = target_core_subsystem[0]; - lu_gp_cg = &alua_lu_gps_group; for (i = 0; lu_gp_cg->default_groups[i]; i++) { item = &lu_gp_cg->default_groups[i]->cg_item; @@ -3045,8 +3043,8 @@ static void __exit target_core_exit_configfs(void) * We expect subsys->su_group.default_groups to be released * by configfs subsystem provider logic.. */ - configfs_unregister_subsystem(subsys); - kfree(subsys->su_group.default_groups); + configfs_unregister_subsystem(&target_core_fabrics); + kfree(target_core_fabrics.su_group.default_groups); core_alua_free_lu_gp(default_lu_gp); default_lu_gp = NULL; diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 7faa6ae..ce5f768 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -33,6 +33,7 @@ #include <linux/kthread.h> #include <linux/in.h> #include <linux/export.h> +#include <asm/unaligned.h> #include <net/sock.h> #include <net/tcp.h> #include <scsi/scsi.h> @@ -527,7 +528,7 @@ static void core_export_port( list_add_tail(&port->sep_list, &dev->dev_sep_list); spin_unlock(&dev->se_port_lock); - if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV && + if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) && !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) { tg_pt_gp_mem = core_alua_allocate_tg_pt_gp_mem(port); if (IS_ERR(tg_pt_gp_mem) || !tg_pt_gp_mem) { @@ -1603,7 +1604,7 @@ int target_configure_device(struct se_device *dev) * anything virtual (IBLOCK, FILEIO, RAMDISK), but not for TCM/pSCSI * passthrough because this is being provided by the backend LLD. */ - if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV) { + if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)) { strncpy(&dev->t10_wwn.vendor[0], "LIO-ORG", 8); strncpy(&dev->t10_wwn.model[0], dev->transport->inquiry_prod, 16); @@ -1707,3 +1708,76 @@ void core_dev_release_virtual_lun0(void) target_free_device(g_lun0_dev); core_delete_hba(hba); } + +/* + * Common CDB parsing for kernel and user passthrough. + */ +sense_reason_t +passthrough_parse_cdb(struct se_cmd *cmd, + sense_reason_t (*exec_cmd)(struct se_cmd *cmd)) +{ + unsigned char *cdb = cmd->t_task_cdb; + + /* + * Clear a lun set in the cdb if the initiator talking to use spoke + * and old standards version, as we can't assume the underlying device + * won't choke up on it. + */ + switch (cdb[0]) { + case READ_10: /* SBC - RDProtect */ + case READ_12: /* SBC - RDProtect */ + case READ_16: /* SBC - RDProtect */ + case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */ + case VERIFY: /* SBC - VRProtect */ + case VERIFY_16: /* SBC - VRProtect */ + case WRITE_VERIFY: /* SBC - VRProtect */ + case WRITE_VERIFY_12: /* SBC - VRProtect */ + case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */ + break; + default: + cdb[1] &= 0x1f; /* clear logical unit number */ + break; + } + + /* + * For REPORT LUNS we always need to emulate the response, for everything + * else, pass it up. + */ + if (cdb[0] == REPORT_LUNS) { + cmd->execute_cmd = spc_emulate_report_luns; + return TCM_NO_SENSE; + } + + /* Set DATA_CDB flag for ops that should have it */ + switch (cdb[0]) { + case READ_6: + case READ_10: + case READ_12: + case READ_16: + case WRITE_6: + case WRITE_10: + case WRITE_12: + case WRITE_16: + case WRITE_VERIFY: + case WRITE_VERIFY_12: + case 0x8e: /* WRITE_VERIFY_16 */ + case COMPARE_AND_WRITE: + case XDWRITEREAD_10: + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + break; + case VARIABLE_LENGTH_CMD: + switch (get_unaligned_be16(&cdb[8])) { + case READ_32: + case WRITE_32: + case 0x0c: /* WRITE_VERIFY_32 */ + case XDWRITEREAD_32: + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + break; + } + } + + cmd->execute_cmd = exec_cmd; + + return TCM_NO_SENSE; +} +EXPORT_SYMBOL(passthrough_parse_cdb); diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index f7e6e51..a3a3d85 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -30,6 +30,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/module.h> +#include <linux/vmalloc.h> #include <linux/falloc.h> #include <scsi/scsi.h> #include <scsi/scsi_host.h> @@ -958,7 +959,6 @@ static struct se_subsystem_api fileio_template = { .inquiry_prod = "FILEIO", .inquiry_rev = FD_VERSION, .owner = THIS_MODULE, - .transport_type = TRANSPORT_PLUGIN_VHBA_PDEV, .attach_hba = fd_attach_hba, .detach_hba = fd_detach_hba, .alloc_device = fd_alloc_device, diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 1b7947c..8c96568 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -904,7 +904,6 @@ static struct se_subsystem_api iblock_template = { .inquiry_prod = "IBLOCK", .inquiry_rev = IBLOCK_VERSION, .owner = THIS_MODULE, - .transport_type = TRANSPORT_PLUGIN_VHBA_PDEV, .attach_hba = iblock_attach_hba, .detach_hba = iblock_detach_hba, .alloc_device = iblock_alloc_device, diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h index 874a9bc..68bd7f5 100644 --- a/drivers/target/target_core_internal.h +++ b/drivers/target/target_core_internal.h @@ -4,9 +4,6 @@ /* target_core_alua.c */ extern struct t10_alua_lu_gp *default_lu_gp; -/* target_core_configfs.c */ -extern struct configfs_subsystem *target_core_subsystem[]; - /* target_core_device.c */ extern struct mutex g_device_mutex; extern struct list_head g_device_list; diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index c1aa965..61dac49 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -27,6 +27,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/list.h> +#include <linux/vmalloc.h> #include <linux/file.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> @@ -1367,41 +1368,26 @@ void core_scsi3_free_all_registrations( static int core_scsi3_tpg_depend_item(struct se_portal_group *tpg) { - return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys, - &tpg->tpg_group.cg_item); + return target_depend_item(&tpg->tpg_group.cg_item); } static void core_scsi3_tpg_undepend_item(struct se_portal_group *tpg) { - configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys, - &tpg->tpg_group.cg_item); - + target_undepend_item(&tpg->tpg_group.cg_item); atomic_dec_mb(&tpg->tpg_pr_ref_count); } static int core_scsi3_nodeacl_depend_item(struct se_node_acl *nacl) { - struct se_portal_group *tpg = nacl->se_tpg; - if (nacl->dynamic_node_acl) return 0; - - return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys, - &nacl->acl_group.cg_item); + return target_depend_item(&nacl->acl_group.cg_item); } static void core_scsi3_nodeacl_undepend_item(struct se_node_acl *nacl) { - struct se_portal_group *tpg = nacl->se_tpg; - - if (nacl->dynamic_node_acl) { - atomic_dec_mb(&nacl->acl_pr_ref_count); - return; - } - - configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys, - &nacl->acl_group.cg_item); - + if (!nacl->dynamic_node_acl) + target_undepend_item(&nacl->acl_group.cg_item); atomic_dec_mb(&nacl->acl_pr_ref_count); } @@ -1419,8 +1405,7 @@ static int core_scsi3_lunacl_depend_item(struct se_dev_entry *se_deve) nacl = lun_acl->se_lun_nacl; tpg = nacl->se_tpg; - return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys, - &lun_acl->se_lun_group.cg_item); + return target_depend_item(&lun_acl->se_lun_group.cg_item); } static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve) @@ -1438,9 +1423,7 @@ static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve) nacl = lun_acl->se_lun_nacl; tpg = nacl->se_tpg; - configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys, - &lun_acl->se_lun_group.cg_item); - + target_undepend_item(&lun_acl->se_lun_group.cg_item); atomic_dec_mb(&se_deve->pr_ref_count); } @@ -4111,7 +4094,7 @@ target_check_reservation(struct se_cmd *cmd) return 0; if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE) return 0; - if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) + if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) return 0; spin_lock(&dev->dev_reservation_lock); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index f6c954c..ecc5eae 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -521,6 +521,7 @@ static int pscsi_configure_device(struct se_device *dev) " pdv_host_id: %d\n", pdv->pdv_host_id); return -EINVAL; } + pdv->pdv_lld_host = sh; } } else { if (phv->phv_mode == PHV_VIRTUAL_HOST_ID) { @@ -603,6 +604,8 @@ static void pscsi_free_device(struct se_device *dev) if ((phv->phv_mode == PHV_LLD_SCSI_HOST_NO) && (phv->phv_lld_host != NULL)) scsi_host_put(phv->phv_lld_host); + else if (pdv->pdv_lld_host) + scsi_host_put(pdv->pdv_lld_host); if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM)) scsi_device_put(sd); @@ -970,64 +973,13 @@ fail: return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } -/* - * Clear a lun set in the cdb if the initiator talking to use spoke - * and old standards version, as we can't assume the underlying device - * won't choke up on it. - */ -static inline void pscsi_clear_cdb_lun(unsigned char *cdb) -{ - switch (cdb[0]) { - case READ_10: /* SBC - RDProtect */ - case READ_12: /* SBC - RDProtect */ - case READ_16: /* SBC - RDProtect */ - case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */ - case VERIFY: /* SBC - VRProtect */ - case VERIFY_16: /* SBC - VRProtect */ - case WRITE_VERIFY: /* SBC - VRProtect */ - case WRITE_VERIFY_12: /* SBC - VRProtect */ - case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */ - break; - default: - cdb[1] &= 0x1f; /* clear logical unit number */ - break; - } -} - static sense_reason_t pscsi_parse_cdb(struct se_cmd *cmd) { - unsigned char *cdb = cmd->t_task_cdb; - if (cmd->se_cmd_flags & SCF_BIDI) return TCM_UNSUPPORTED_SCSI_OPCODE; - pscsi_clear_cdb_lun(cdb); - - /* - * For REPORT LUNS we always need to emulate the response, for everything - * else the default for pSCSI is to pass the command to the underlying - * LLD / physical hardware. - */ - switch (cdb[0]) { - case REPORT_LUNS: - cmd->execute_cmd = spc_emulate_report_luns; - return 0; - case READ_6: - case READ_10: - case READ_12: - case READ_16: - case WRITE_6: - case WRITE_10: - case WRITE_12: - case WRITE_16: - case WRITE_VERIFY: - cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; - /* FALLTHROUGH*/ - default: - cmd->execute_cmd = pscsi_execute_cmd; - return 0; - } + return passthrough_parse_cdb(cmd, pscsi_execute_cmd); } static sense_reason_t @@ -1189,7 +1141,7 @@ static struct configfs_attribute *pscsi_backend_dev_attrs[] = { static struct se_subsystem_api pscsi_template = { .name = "pscsi", .owner = THIS_MODULE, - .transport_type = TRANSPORT_PLUGIN_PHBA_PDEV, + .transport_flags = TRANSPORT_FLAG_PASSTHROUGH, .attach_hba = pscsi_attach_hba, .detach_hba = pscsi_detach_hba, .pmode_enable_hba = pscsi_pmode_enable_hba, diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h index 1bd757d..820d305 100644 --- a/drivers/target/target_core_pscsi.h +++ b/drivers/target/target_core_pscsi.h @@ -45,6 +45,7 @@ struct pscsi_dev_virt { int pdv_lun_id; struct block_device *pdv_bd; struct scsi_device *pdv_sd; + struct Scsi_Host *pdv_lld_host; } ____cacheline_aligned; typedef enum phv_modes { diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c index a263bf5..d16489b 100644 --- a/drivers/target/target_core_rd.c +++ b/drivers/target/target_core_rd.c @@ -733,7 +733,6 @@ static struct se_subsystem_api rd_mcp_template = { .name = "rd_mcp", .inquiry_prod = "RAMDISK-MCP", .inquiry_rev = RD_MCP_VERSION, - .transport_type = TRANSPORT_PLUGIN_VHBA_VDEV, .attach_hba = rd_attach_hba, .detach_hba = rd_detach_hba, .alloc_device = rd_alloc_device, diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 8855781..733824e 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -568,7 +568,7 @@ sbc_compare_and_write(struct se_cmd *cmd) * comparision using SGLs at cmd->t_bidi_data_sg.. */ rc = down_interruptible(&dev->caw_sem); - if ((rc != 0) || signal_pending(current)) { + if (rc != 0) { cmd->transport_complete_callback = NULL; return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 3fe5cb2..2b17bdd 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -34,6 +34,7 @@ #include <linux/cdrom.h> #include <linux/module.h> #include <linux/ratelimit.h> +#include <linux/vmalloc.h> #include <asm/unaligned.h> #include <net/sock.h> #include <net/tcp.h> @@ -1196,7 +1197,7 @@ transport_check_alloc_task_attr(struct se_cmd *cmd) * Check if SAM Task Attribute emulation is enabled for this * struct se_device storage object */ - if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) + if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) return 0; if (cmd->sam_task_attr == TCM_ACA_TAG) { @@ -1770,7 +1771,7 @@ static int target_write_prot_action(struct se_cmd *cmd) sectors, 0, NULL, 0); if (unlikely(cmd->pi_err)) { spin_lock_irq(&cmd->t_state_lock); - cmd->transport_state &= ~CMD_T_BUSY|CMD_T_SENT; + cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT); spin_unlock_irq(&cmd->t_state_lock); transport_generic_request_failure(cmd, cmd->pi_err); return -1; @@ -1787,7 +1788,7 @@ static bool target_handle_task_attr(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; - if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) + if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) return false; /* @@ -1868,7 +1869,7 @@ void target_execute_cmd(struct se_cmd *cmd) if (target_handle_task_attr(cmd)) { spin_lock_irq(&cmd->t_state_lock); - cmd->transport_state &= ~CMD_T_BUSY|CMD_T_SENT; + cmd->transport_state &= ~(CMD_T_BUSY | CMD_T_SENT); spin_unlock_irq(&cmd->t_state_lock); return; } @@ -1912,7 +1913,7 @@ static void transport_complete_task_attr(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; - if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) + if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) return; if (cmd->sam_task_attr == TCM_SIMPLE_TAG) { @@ -1957,8 +1958,7 @@ static void transport_complete_qf(struct se_cmd *cmd) case DMA_TO_DEVICE: if (cmd->se_cmd_flags & SCF_BIDI) { ret = cmd->se_tfo->queue_data_in(cmd); - if (ret < 0) - break; + break; } /* Fall through for DMA_TO_DEVICE */ case DMA_NONE: diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index dbc872a..edc9555 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -21,6 +21,7 @@ #include <linux/idr.h> #include <linux/timer.h> #include <linux/parser.h> +#include <linux/vmalloc.h> #include <scsi/scsi.h> #include <scsi/scsi_host.h> #include <linux/uio_driver.h> @@ -71,13 +72,6 @@ struct tcmu_hba { u32 host_id; }; -/* User wants all cmds or just some */ -enum passthru_level { - TCMU_PASS_ALL = 0, - TCMU_PASS_IO, - TCMU_PASS_INVALID, -}; - #define TCMU_CONFIG_LEN 256 struct tcmu_dev { @@ -89,7 +83,6 @@ struct tcmu_dev { #define TCMU_DEV_BIT_OPEN 0 #define TCMU_DEV_BIT_BROKEN 1 unsigned long flags; - enum passthru_level pass_level; struct uio_info uio_info; @@ -683,8 +676,6 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name) setup_timer(&udev->timeout, tcmu_device_timedout, (unsigned long)udev); - udev->pass_level = TCMU_PASS_ALL; - return &udev->se_dev; } @@ -948,13 +939,13 @@ static void tcmu_free_device(struct se_device *dev) } enum { - Opt_dev_config, Opt_dev_size, Opt_err, Opt_pass_level, + Opt_dev_config, Opt_dev_size, Opt_hw_block_size, Opt_err, }; static match_table_t tokens = { {Opt_dev_config, "dev_config=%s"}, {Opt_dev_size, "dev_size=%u"}, - {Opt_pass_level, "pass_level=%u"}, + {Opt_hw_block_size, "hw_block_size=%u"}, {Opt_err, NULL} }; @@ -965,7 +956,7 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev, char *orig, *ptr, *opts, *arg_p; substring_t args[MAX_OPT_ARGS]; int ret = 0, token; - int arg; + unsigned long tmp_ul; opts = kstrdup(page, GFP_KERNEL); if (!opts) @@ -998,15 +989,23 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev, if (ret < 0) pr_err("kstrtoul() failed for dev_size=\n"); break; - case Opt_pass_level: - match_int(args, &arg); - if (arg >= TCMU_PASS_INVALID) { - pr_warn("TCMU: Invalid pass_level: %d\n", arg); + case Opt_hw_block_size: + arg_p = match_strdup(&args[0]); + if (!arg_p) { + ret = -ENOMEM; break; } - - pr_debug("TCMU: Setting pass_level to %d\n", arg); - udev->pass_level = arg; + ret = kstrtoul(arg_p, 0, &tmp_ul); + kfree(arg_p); + if (ret < 0) { + pr_err("kstrtoul() failed for hw_block_size=\n"); + break; + } + if (!tmp_ul) { + pr_err("hw_block_size must be nonzero\n"); + break; + } + dev->dev_attrib.hw_block_size = tmp_ul; break; default: break; @@ -1024,8 +1023,7 @@ static ssize_t tcmu_show_configfs_dev_params(struct se_device *dev, char *b) bl = sprintf(b + bl, "Config: %s ", udev->dev_config[0] ? udev->dev_config : "NULL"); - bl += sprintf(b + bl, "Size: %zu PassLevel: %u\n", - udev->dev_size, udev->pass_level); + bl += sprintf(b + bl, "Size: %zu\n", udev->dev_size); return bl; } @@ -1039,20 +1037,6 @@ static sector_t tcmu_get_blocks(struct se_device *dev) } static sense_reason_t -tcmu_execute_rw(struct se_cmd *se_cmd, struct scatterlist *sgl, u32 sgl_nents, - enum dma_data_direction data_direction) -{ - int ret; - - ret = tcmu_queue_cmd(se_cmd); - - if (ret != 0) - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - else - return TCM_NO_SENSE; -} - -static sense_reason_t tcmu_pass_op(struct se_cmd *se_cmd) { int ret = tcmu_queue_cmd(se_cmd); @@ -1063,91 +1047,29 @@ tcmu_pass_op(struct se_cmd *se_cmd) return TCM_NO_SENSE; } -static struct sbc_ops tcmu_sbc_ops = { - .execute_rw = tcmu_execute_rw, - .execute_sync_cache = tcmu_pass_op, - .execute_write_same = tcmu_pass_op, - .execute_write_same_unmap = tcmu_pass_op, - .execute_unmap = tcmu_pass_op, -}; - static sense_reason_t tcmu_parse_cdb(struct se_cmd *cmd) { - unsigned char *cdb = cmd->t_task_cdb; - struct tcmu_dev *udev = TCMU_DEV(cmd->se_dev); - sense_reason_t ret; - - switch (udev->pass_level) { - case TCMU_PASS_ALL: - /* We're just like pscsi, then */ - /* - * For REPORT LUNS we always need to emulate the response, for everything - * else, pass it up. - */ - switch (cdb[0]) { - case REPORT_LUNS: - cmd->execute_cmd = spc_emulate_report_luns; - break; - case READ_6: - case READ_10: - case READ_12: - case READ_16: - case WRITE_6: - case WRITE_10: - case WRITE_12: - case WRITE_16: - case WRITE_VERIFY: - cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; - /* FALLTHROUGH */ - default: - cmd->execute_cmd = tcmu_pass_op; - } - ret = TCM_NO_SENSE; - break; - case TCMU_PASS_IO: - ret = sbc_parse_cdb(cmd, &tcmu_sbc_ops); - break; - default: - pr_err("Unknown tcm-user pass level %d\n", udev->pass_level); - ret = TCM_CHECK_CONDITION_ABORT_CMD; - } - - return ret; + return passthrough_parse_cdb(cmd, tcmu_pass_op); } -DEF_TB_DEFAULT_ATTRIBS(tcmu); +DEF_TB_DEV_ATTRIB_RO(tcmu, hw_pi_prot_type); +TB_DEV_ATTR_RO(tcmu, hw_pi_prot_type); + +DEF_TB_DEV_ATTRIB_RO(tcmu, hw_block_size); +TB_DEV_ATTR_RO(tcmu, hw_block_size); + +DEF_TB_DEV_ATTRIB_RO(tcmu, hw_max_sectors); +TB_DEV_ATTR_RO(tcmu, hw_max_sectors); + +DEF_TB_DEV_ATTRIB_RO(tcmu, hw_queue_depth); +TB_DEV_ATTR_RO(tcmu, hw_queue_depth); static struct configfs_attribute *tcmu_backend_dev_attrs[] = { - &tcmu_dev_attrib_emulate_model_alias.attr, - &tcmu_dev_attrib_emulate_dpo.attr, - &tcmu_dev_attrib_emulate_fua_write.attr, - &tcmu_dev_attrib_emulate_fua_read.attr, - &tcmu_dev_attrib_emulate_write_cache.attr, - &tcmu_dev_attrib_emulate_ua_intlck_ctrl.attr, - &tcmu_dev_attrib_emulate_tas.attr, - &tcmu_dev_attrib_emulate_tpu.attr, - &tcmu_dev_attrib_emulate_tpws.attr, - &tcmu_dev_attrib_emulate_caw.attr, - &tcmu_dev_attrib_emulate_3pc.attr, - &tcmu_dev_attrib_pi_prot_type.attr, &tcmu_dev_attrib_hw_pi_prot_type.attr, - &tcmu_dev_attrib_pi_prot_format.attr, - &tcmu_dev_attrib_enforce_pr_isids.attr, - &tcmu_dev_attrib_is_nonrot.attr, - &tcmu_dev_attrib_emulate_rest_reord.attr, - &tcmu_dev_attrib_force_pr_aptpl.attr, &tcmu_dev_attrib_hw_block_size.attr, - &tcmu_dev_attrib_block_size.attr, &tcmu_dev_attrib_hw_max_sectors.attr, - &tcmu_dev_attrib_optimal_sectors.attr, &tcmu_dev_attrib_hw_queue_depth.attr, - &tcmu_dev_attrib_queue_depth.attr, - &tcmu_dev_attrib_max_unmap_lba_count.attr, - &tcmu_dev_attrib_max_unmap_block_desc_count.attr, - &tcmu_dev_attrib_unmap_granularity.attr, - &tcmu_dev_attrib_unmap_granularity_alignment.attr, - &tcmu_dev_attrib_max_write_same_len.attr, NULL, }; @@ -1156,7 +1078,7 @@ static struct se_subsystem_api tcmu_template = { .inquiry_prod = "USER", .inquiry_rev = TCMU_VERSION, .owner = THIS_MODULE, - .transport_type = TRANSPORT_PLUGIN_VHBA_PDEV, + .transport_flags = TRANSPORT_FLAG_PASSTHROUGH, .attach_hba = tcmu_attach_hba, .detach_hba = tcmu_detach_hba, .alloc_device = tcmu_alloc_device, diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index a600ff1..8fd680a 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -58,7 +58,6 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op bool src) { struct se_device *se_dev; - struct configfs_subsystem *subsys = target_core_subsystem[0]; unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN], *dev_wwn; int rc; @@ -90,8 +89,7 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op " se_dev\n", xop->src_dev); } - rc = configfs_depend_item(subsys, - &se_dev->dev_group.cg_item); + rc = target_depend_item(&se_dev->dev_group.cg_item); if (rc != 0) { pr_err("configfs_depend_item attempt failed:" " %d for se_dev: %p\n", rc, se_dev); @@ -99,8 +97,8 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op return rc; } - pr_debug("Called configfs_depend_item for subsys: %p se_dev: %p" - " se_dev->se_dev_group: %p\n", subsys, se_dev, + pr_debug("Called configfs_depend_item for se_dev: %p" + " se_dev->se_dev_group: %p\n", se_dev, &se_dev->dev_group); mutex_unlock(&g_device_mutex); @@ -373,7 +371,6 @@ static int xcopy_pt_get_cmd_state(struct se_cmd *se_cmd) static void xcopy_pt_undepend_remotedev(struct xcopy_op *xop) { - struct configfs_subsystem *subsys = target_core_subsystem[0]; struct se_device *remote_dev; if (xop->op_origin == XCOL_SOURCE_RECV_OP) @@ -381,11 +378,11 @@ static void xcopy_pt_undepend_remotedev(struct xcopy_op *xop) else remote_dev = xop->src_dev; - pr_debug("Calling configfs_undepend_item for subsys: %p" + pr_debug("Calling configfs_undepend_item for" " remote_dev: %p remote_dev->dev_group: %p\n", - subsys, remote_dev, &remote_dev->dev_group.cg_item); + remote_dev, &remote_dev->dev_group.cg_item); - configfs_undepend_item(subsys, &remote_dev->dev_group.cg_item); + target_undepend_item(&remote_dev->dev_group.cg_item); } static void xcopy_pt_release_cmd(struct se_cmd *se_cmd) diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c index 04d9e23..358323c 100644 --- a/drivers/tty/mips_ejtag_fdc.c +++ b/drivers/tty/mips_ejtag_fdc.c @@ -174,13 +174,13 @@ struct mips_ejtag_fdc_tty { static inline void mips_ejtag_fdc_write(struct mips_ejtag_fdc_tty *priv, unsigned int offs, unsigned int data) { - iowrite32(data, priv->reg + offs); + __raw_writel(data, priv->reg + offs); } static inline unsigned int mips_ejtag_fdc_read(struct mips_ejtag_fdc_tty *priv, unsigned int offs) { - return ioread32(priv->reg + offs); + return __raw_readl(priv->reg + offs); } /* Encoding of byte stream in FDC words */ @@ -347,9 +347,9 @@ static void mips_ejtag_fdc_console_write(struct console *c, const char *s, s += inc[word.bytes - 1]; /* Busy wait until there's space in fifo */ - while (ioread32(regs + REG_FDSTAT) & REG_FDSTAT_TXF) + while (__raw_readl(regs + REG_FDSTAT) & REG_FDSTAT_TXF) ; - iowrite32(word.word, regs + REG_FDTX(c->index)); + __raw_writel(word.word, regs + REG_FDTX(c->index)); } out: local_irq_restore(flags); @@ -1227,7 +1227,7 @@ static int kgdbfdc_read_char(void) /* Read next word from KGDB channel */ do { - stat = ioread32(regs + REG_FDSTAT); + stat = __raw_readl(regs + REG_FDSTAT); /* No data waiting? */ if (stat & REG_FDSTAT_RXE) @@ -1236,7 +1236,7 @@ static int kgdbfdc_read_char(void) /* Read next word */ channel = (stat & REG_FDSTAT_RXCHAN) >> REG_FDSTAT_RXCHAN_SHIFT; - data = ioread32(regs + REG_FDRX); + data = __raw_readl(regs + REG_FDRX); } while (channel != CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN); /* Decode into rbuf */ @@ -1266,9 +1266,10 @@ static void kgdbfdc_push_one(void) return; /* Busy wait until there's space in fifo */ - while (ioread32(regs + REG_FDSTAT) & REG_FDSTAT_TXF) + while (__raw_readl(regs + REG_FDSTAT) & REG_FDSTAT_TXF) ; - iowrite32(word.word, regs + REG_FDTX(CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN)); + __raw_writel(word.word, + regs + REG_FDTX(CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN)); } /* flush the whole write buffer to the TX FIFO */ diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 5e19bb5..83bbb26 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -35,6 +35,7 @@ #include <linux/compat.h> #include <linux/eventfd.h> #include <linux/fs.h> +#include <linux/vmalloc.h> #include <linux/miscdevice.h> #include <asm/unaligned.h> #include <scsi/scsi.h> @@ -1409,8 +1410,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, * dependency now. */ se_tpg = &tpg->se_tpg; - ret = configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys, - &se_tpg->tpg_group.cg_item); + ret = target_depend_item(&se_tpg->tpg_group.cg_item); if (ret) { pr_warn("configfs_depend_item() failed: %d\n", ret); kfree(vs_tpg); @@ -1513,8 +1513,7 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, * to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur. */ se_tpg = &tpg->se_tpg; - configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys, - &se_tpg->tpg_group.cg_item); + target_undepend_item(&se_tpg->tpg_group.cg_item); } if (match) { for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index 3a145a6..6897f1c 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -274,6 +274,10 @@ static int pwm_backlight_probe(struct platform_device *pdev) pb->pwm = devm_pwm_get(&pdev->dev, NULL); if (IS_ERR(pb->pwm)) { + ret = PTR_ERR(pb->pwm); + if (ret == -EPROBE_DEFER) + goto err_alloc; + dev_err(&pdev->dev, "unable to request PWM, trying legacy API\n"); pb->legacy = true; pb->pwm = pwm_request(data->pwm_id, "pwm-backlight"); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 241ef68..cd46e41 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -918,7 +918,7 @@ static int load_elf_binary(struct linux_binprm *bprm) total_size = total_mapping_size(elf_phdata, loc->elf_ex.e_phnum); if (!total_size) { - error = -EINVAL; + retval = -EINVAL; goto out_free_dentry; } } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 9de772e..614aaa1 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -880,6 +880,8 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, * indirect refs to their parent bytenr. * When roots are found, they're added to the roots list * + * NOTE: This can return values > 0 + * * FIXME some caching might speed things up */ static int find_parent_nodes(struct btrfs_trans_handle *trans, @@ -1198,6 +1200,19 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, return ret; } +/** + * btrfs_check_shared - tell us whether an extent is shared + * + * @trans: optional trans handle + * + * btrfs_check_shared uses the backref walking code but will short + * circuit as soon as it finds a root or inode that doesn't match the + * one passed in. This provides a significant performance benefit for + * callers (such as fiemap) which want to know whether the extent is + * shared but do not need a ref count. + * + * Return: 0 if extent is not shared, 1 if it is shared, < 0 on error. + */ int btrfs_check_shared(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 root_objectid, u64 inum, u64 bytenr) @@ -1226,11 +1241,13 @@ int btrfs_check_shared(struct btrfs_trans_handle *trans, ret = find_parent_nodes(trans, fs_info, bytenr, elem.seq, tmp, roots, NULL, root_objectid, inum); if (ret == BACKREF_FOUND_SHARED) { + /* this is the only condition under which we return 1 */ ret = 1; break; } if (ret < 0 && ret != -ENOENT) break; + ret = 0; node = ulist_next(tmp, &uiter); if (!node) break; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 7effed6..0ec3acd 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -8829,6 +8829,24 @@ again: goto again; } + /* + * if we are changing raid levels, try to allocate a corresponding + * block group with the new raid level. + */ + alloc_flags = update_block_group_flags(root, cache->flags); + if (alloc_flags != cache->flags) { + ret = do_chunk_alloc(trans, root, alloc_flags, + CHUNK_ALLOC_FORCE); + /* + * ENOSPC is allowed here, we may have enough space + * already allocated at the new raid level to + * carry on + */ + if (ret == -ENOSPC) + ret = 0; + if (ret < 0) + goto out; + } ret = set_block_group_ro(cache, 0); if (!ret) @@ -8842,7 +8860,9 @@ again: out: if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) { alloc_flags = update_block_group_flags(root, cache->flags); + lock_chunks(root->fs_info->chunk_root); check_system_chunk(trans, root, alloc_flags); + unlock_chunks(root->fs_info->chunk_root); } mutex_unlock(&root->fs_info->ro_block_group_mutex); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 96aebf3..174f5e1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4625,6 +4625,7 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, { u64 chunk_offset; + ASSERT(mutex_is_locked(&extent_root->fs_info->chunk_mutex)); chunk_offset = find_next_chunk(extent_root->fs_info); return __btrfs_alloc_chunk(trans, extent_root, chunk_offset, type); } diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 430e034..7dc886c 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -24,6 +24,7 @@ #include "cifsfs.h" #include "dns_resolve.h" #include "cifs_debug.h" +#include "cifs_unicode.h" static LIST_HEAD(cifs_dfs_automount_list); @@ -312,7 +313,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) xid = get_xid(); rc = get_dfs_path(xid, ses, full_path + 1, cifs_sb->local_nls, &num_referrals, &referrals, - cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_remap(cifs_sb)); free_xid(xid); cifs_put_tlink(tlink); diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 0303c67..5a53ac6 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -27,41 +27,6 @@ #include "cifsglob.h" #include "cifs_debug.h" -/* - * cifs_utf16_bytes - how long will a string be after conversion? - * @utf16 - pointer to input string - * @maxbytes - don't go past this many bytes of input string - * @codepage - destination codepage - * - * Walk a utf16le string and return the number of bytes that the string will - * be after being converted to the given charset, not including any null - * termination required. Don't walk past maxbytes in the source buffer. - */ -int -cifs_utf16_bytes(const __le16 *from, int maxbytes, - const struct nls_table *codepage) -{ - int i; - int charlen, outlen = 0; - int maxwords = maxbytes / 2; - char tmp[NLS_MAX_CHARSET_SIZE]; - __u16 ftmp; - - for (i = 0; i < maxwords; i++) { - ftmp = get_unaligned_le16(&from[i]); - if (ftmp == 0) - break; - - charlen = codepage->uni2char(ftmp, tmp, NLS_MAX_CHARSET_SIZE); - if (charlen > 0) - outlen += charlen; - else - outlen++; - } - - return outlen; -} - int cifs_remap(struct cifs_sb_info *cifs_sb) { int map_type; @@ -155,10 +120,13 @@ convert_sfm_char(const __u16 src_char, char *target) * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE). */ static int -cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp, +cifs_mapchar(char *target, const __u16 *from, const struct nls_table *cp, int maptype) { int len = 1; + __u16 src_char; + + src_char = *from; if ((maptype == SFM_MAP_UNI_RSVD) && convert_sfm_char(src_char, target)) return len; @@ -168,10 +136,23 @@ cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp, /* if character not one of seven in special remap set */ len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE); - if (len <= 0) { - *target = '?'; - len = 1; - } + if (len <= 0) + goto surrogate_pair; + + return len; + +surrogate_pair: + /* convert SURROGATE_PAIR and IVS */ + if (strcmp(cp->charset, "utf8")) + goto unknown; + len = utf16s_to_utf8s(from, 3, UTF16_LITTLE_ENDIAN, target, 6); + if (len <= 0) + goto unknown; + return len; + +unknown: + *target = '?'; + len = 1; return len; } @@ -206,7 +187,7 @@ cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen, int nullsize = nls_nullsize(codepage); int fromwords = fromlen / 2; char tmp[NLS_MAX_CHARSET_SIZE]; - __u16 ftmp; + __u16 ftmp[3]; /* ftmp[3] = 3array x 2bytes = 6bytes UTF-16 */ /* * because the chars can be of varying widths, we need to take care @@ -217,9 +198,17 @@ cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen, safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize); for (i = 0; i < fromwords; i++) { - ftmp = get_unaligned_le16(&from[i]); - if (ftmp == 0) + ftmp[0] = get_unaligned_le16(&from[i]); + if (ftmp[0] == 0) break; + if (i + 1 < fromwords) + ftmp[1] = get_unaligned_le16(&from[i + 1]); + else + ftmp[1] = 0; + if (i + 2 < fromwords) + ftmp[2] = get_unaligned_le16(&from[i + 2]); + else + ftmp[2] = 0; /* * check to see if converting this character might make the @@ -234,6 +223,17 @@ cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen, /* put converted char into 'to' buffer */ charlen = cifs_mapchar(&to[outlen], ftmp, codepage, map_type); outlen += charlen; + + /* charlen (=bytes of UTF-8 for 1 character) + * 4bytes UTF-8(surrogate pair) is charlen=4 + * (4bytes UTF-16 code) + * 7-8bytes UTF-8(IVS) is charlen=3+4 or 4+4 + * (2 UTF-8 pairs divided to 2 UTF-16 pairs) */ + if (charlen == 4) + i++; + else if (charlen >= 5) + /* 5-6bytes UTF-8 */ + i += 2; } /* properly null-terminate string */ @@ -296,6 +296,46 @@ success: } /* + * cifs_utf16_bytes - how long will a string be after conversion? + * @utf16 - pointer to input string + * @maxbytes - don't go past this many bytes of input string + * @codepage - destination codepage + * + * Walk a utf16le string and return the number of bytes that the string will + * be after being converted to the given charset, not including any null + * termination required. Don't walk past maxbytes in the source buffer. + */ +int +cifs_utf16_bytes(const __le16 *from, int maxbytes, + const struct nls_table *codepage) +{ + int i; + int charlen, outlen = 0; + int maxwords = maxbytes / 2; + char tmp[NLS_MAX_CHARSET_SIZE]; + __u16 ftmp[3]; + + for (i = 0; i < maxwords; i++) { + ftmp[0] = get_unaligned_le16(&from[i]); + if (ftmp[0] == 0) + break; + if (i + 1 < maxwords) + ftmp[1] = get_unaligned_le16(&from[i + 1]); + else + ftmp[1] = 0; + if (i + 2 < maxwords) + ftmp[2] = get_unaligned_le16(&from[i + 2]); + else + ftmp[2] = 0; + + charlen = cifs_mapchar(tmp, ftmp, codepage, NO_MAP_UNI_RSVD); + outlen += charlen; + } + + return outlen; +} + +/* * cifs_strndup_from_utf16 - copy a string from wire format to the local * codepage * @src - source string @@ -409,10 +449,15 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, char src_char; __le16 dst_char; wchar_t tmp; + wchar_t *wchar_to; /* UTF-16 */ + int ret; + unicode_t u; if (map_chars == NO_MAP_UNI_RSVD) return cifs_strtoUTF16(target, source, PATH_MAX, cp); + wchar_to = kzalloc(6, GFP_KERNEL); + for (i = 0; i < srclen; j++) { src_char = source[i]; charlen = 1; @@ -441,11 +486,55 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, * if no match, use question mark, which at least in * some cases serves as wild card */ - if (charlen < 1) { - dst_char = cpu_to_le16(0x003f); - charlen = 1; + if (charlen > 0) + goto ctoUTF16; + + /* convert SURROGATE_PAIR */ + if (strcmp(cp->charset, "utf8") || !wchar_to) + goto unknown; + if (*(source + i) & 0x80) { + charlen = utf8_to_utf32(source + i, 6, &u); + if (charlen < 0) + goto unknown; + } else + goto unknown; + ret = utf8s_to_utf16s(source + i, charlen, + UTF16_LITTLE_ENDIAN, + wchar_to, 6); + if (ret < 0) + goto unknown; + + i += charlen; + dst_char = cpu_to_le16(*wchar_to); + if (charlen <= 3) + /* 1-3bytes UTF-8 to 2bytes UTF-16 */ + put_unaligned(dst_char, &target[j]); + else if (charlen == 4) { + /* 4bytes UTF-8(surrogate pair) to 4bytes UTF-16 + * 7-8bytes UTF-8(IVS) divided to 2 UTF-16 + * (charlen=3+4 or 4+4) */ + put_unaligned(dst_char, &target[j]); + dst_char = cpu_to_le16(*(wchar_to + 1)); + j++; + put_unaligned(dst_char, &target[j]); + } else if (charlen >= 5) { + /* 5-6bytes UTF-8 to 6bytes UTF-16 */ + put_unaligned(dst_char, &target[j]); + dst_char = cpu_to_le16(*(wchar_to + 1)); + j++; + put_unaligned(dst_char, &target[j]); + dst_char = cpu_to_le16(*(wchar_to + 2)); + j++; + put_unaligned(dst_char, &target[j]); } + continue; + +unknown: + dst_char = cpu_to_le16(0x003f); + charlen = 1; } + +ctoUTF16: /* * character may take more than one byte in the source string, * but will take exactly two bytes in the target string @@ -456,6 +545,7 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, ctoUTF16_out: put_unaligned(0, &target[j]); /* Null terminate target unicode string */ + kfree(wchar_to); return j; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index f5089bd..0a9fb6b 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -469,6 +469,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_puts(s, ",nouser_xattr"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR) seq_puts(s, ",mapchars"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR) + seq_puts(s, ",mapposix"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) seq_puts(s, ",sfu"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index c31ce98..c63fd1d 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -361,11 +361,11 @@ extern int CIFSUnixCreateHardLink(const unsigned int xid, extern int CIFSUnixCreateSymLink(const unsigned int xid, struct cifs_tcon *tcon, const char *fromName, const char *toName, - const struct nls_table *nls_codepage); + const struct nls_table *nls_codepage, int remap); extern int CIFSSMBUnixQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, const unsigned char *searchName, char **syminfo, - const struct nls_table *nls_codepage); + const struct nls_table *nls_codepage, int remap); extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid, char **symlinkinfo, const struct nls_table *nls_codepage); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 84650a5..f26ffbf 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -2784,7 +2784,7 @@ copyRetry: int CIFSUnixCreateSymLink(const unsigned int xid, struct cifs_tcon *tcon, const char *fromName, const char *toName, - const struct nls_table *nls_codepage) + const struct nls_table *nls_codepage, int remap) { TRANSACTION2_SPI_REQ *pSMB = NULL; TRANSACTION2_SPI_RSP *pSMBr = NULL; @@ -2804,9 +2804,9 @@ createSymLinkRetry: if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) { name_len = - cifs_strtoUTF16((__le16 *) pSMB->FileName, fromName, - /* find define for this maxpathcomponent */ - PATH_MAX, nls_codepage); + cifsConvertToUTF16((__le16 *) pSMB->FileName, fromName, + /* find define for this maxpathcomponent */ + PATH_MAX, nls_codepage, remap); name_len++; /* trailing null */ name_len *= 2; @@ -2828,9 +2828,9 @@ createSymLinkRetry: data_offset = (char *) (&pSMB->hdr.Protocol) + offset; if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) { name_len_target = - cifs_strtoUTF16((__le16 *) data_offset, toName, PATH_MAX - /* find define for this maxpathcomponent */ - , nls_codepage); + cifsConvertToUTF16((__le16 *) data_offset, toName, + /* find define for this maxpathcomponent */ + PATH_MAX, nls_codepage, remap); name_len_target++; /* trailing null */ name_len_target *= 2; } else { /* BB improve the check for buffer overruns BB */ @@ -3034,7 +3034,7 @@ winCreateHardLinkRetry: int CIFSSMBUnixQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, const unsigned char *searchName, char **symlinkinfo, - const struct nls_table *nls_codepage) + const struct nls_table *nls_codepage, int remap) { /* SMB_QUERY_FILE_UNIX_LINK */ TRANSACTION2_QPI_REQ *pSMB = NULL; @@ -3055,8 +3055,9 @@ querySymLinkRetry: if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) { name_len = - cifs_strtoUTF16((__le16 *) pSMB->FileName, searchName, - PATH_MAX, nls_codepage); + cifsConvertToUTF16((__le16 *) pSMB->FileName, + searchName, PATH_MAX, nls_codepage, + remap); name_len++; /* trailing null */ name_len *= 2; } else { /* BB improve the check for buffer overruns BB */ @@ -4917,7 +4918,7 @@ getDFSRetry: strncpy(pSMB->RequestFileName, search_name, name_len); } - if (ses->server && ses->server->sign) + if (ses->server->sign) pSMB->hdr.Flags2 |= SMBFLG2_SECURITY_SIGNATURE; pSMB->hdr.Uid = ses->Suid; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index f3bfe08..8383d5e 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -386,6 +386,7 @@ cifs_reconnect(struct TCP_Server_Info *server) rc = generic_ip_connect(server); if (rc) { cifs_dbg(FYI, "reconnect error %d\n", rc); + mutex_unlock(&server->srv_mutex); msleep(3000); } else { atomic_inc(&tcpSesReconnectCount); @@ -393,8 +394,8 @@ cifs_reconnect(struct TCP_Server_Info *server) if (server->tcpStatus != CifsExiting) server->tcpStatus = CifsNeedNegotiate; spin_unlock(&GlobalMid_Lock); + mutex_unlock(&server->srv_mutex); } - mutex_unlock(&server->srv_mutex); } while (server->tcpStatus == CifsNeedReconnect); return rc; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 338d569..c3eb998 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -620,8 +620,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode, } rc = CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args, cifs_sb->local_nls, - cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_remap(cifs_sb)); if (rc) goto mknod_out; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index cafbf10..3f50cee 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -140,8 +140,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode, posix_flags = cifs_posix_convert_flags(f_flags); rc = CIFSPOSIXCreate(xid, tcon, posix_flags, mode, pnetfid, presp_data, poplock, full_path, cifs_sb->local_nls, - cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_remap(cifs_sb)); cifs_put_tlink(tlink); if (rc) @@ -1553,8 +1552,8 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, rc = server->ops->mand_unlock_range(cfile, flock, xid); out: - if (flock->fl_flags & FL_POSIX) - posix_lock_file_wait(file, flock); + if (flock->fl_flags & FL_POSIX && !rc) + rc = posix_lock_file_wait(file, flock); return rc; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 55b5811..f621b44 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -373,8 +373,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, /* could have done a find first instead but this returns more info */ rc = CIFSSMBUnixQPathInfo(xid, tcon, full_path, &find_data, - cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_sb->local_nls, cifs_remap(cifs_sb)); cifs_put_tlink(tlink); if (!rc) { @@ -402,9 +401,25 @@ int cifs_get_inode_info_unix(struct inode **pinode, rc = -ENOMEM; } else { /* we already have inode, update it */ + + /* if uniqueid is different, return error */ + if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM && + CIFS_I(*pinode)->uniqueid != fattr.cf_uniqueid)) { + rc = -ESTALE; + goto cgiiu_exit; + } + + /* if filetype is different, return error */ + if (unlikely(((*pinode)->i_mode & S_IFMT) != + (fattr.cf_mode & S_IFMT))) { + rc = -ESTALE; + goto cgiiu_exit; + } + cifs_fattr_to_inode(*pinode, &fattr); } +cgiiu_exit: return rc; } @@ -839,6 +854,15 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, if (!*inode) rc = -ENOMEM; } else { + /* we already have inode, update it */ + + /* if filetype is different, return error */ + if (unlikely(((*inode)->i_mode & S_IFMT) != + (fattr.cf_mode & S_IFMT))) { + rc = -ESTALE; + goto cgii_exit; + } + cifs_fattr_to_inode(*inode, &fattr); } @@ -2215,8 +2239,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) pTcon = tlink_tcon(tlink); rc = CIFSSMBUnixSetPathInfo(xid, pTcon, full_path, args, cifs_sb->local_nls, - cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_remap(cifs_sb)); cifs_put_tlink(tlink); } diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 252e672..e6c707c 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -717,7 +717,8 @@ cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname) rc = create_mf_symlink(xid, pTcon, cifs_sb, full_path, symname); else if (pTcon->unix_ext) rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, symname, - cifs_sb->local_nls); + cifs_sb->local_nls, + cifs_remap(cifs_sb)); /* else rc = CIFSCreateReparseSymLink(xid, pTcon, fromName, toName, cifs_sb_target->local_nls); */ diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index b4a4723..b1eede3 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -90,6 +90,8 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, if (dentry) { inode = d_inode(dentry); if (inode) { + if (d_mountpoint(dentry)) + goto out; /* * If we're generating inode numbers, then we don't * want to clobber the existing one with the one that diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 7bfdd60..fc537c2 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -960,7 +960,8 @@ cifs_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, /* Check for unix extensions */ if (cap_unix(tcon->ses)) { rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path, - cifs_sb->local_nls); + cifs_sb->local_nls, + cifs_remap(cifs_sb)); if (rc == -EREMOTE) rc = cifs_unix_dfs_readlink(xid, tcon, full_path, target_path, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 65cd7a8..54cbe19 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -110,7 +110,7 @@ smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ , /* GLOBAL_CAP_LARGE_MTU will only be set if dialect > SMB2.02 */ /* See sections 2.2.4 and 3.2.4.1.5 of MS-SMB2 */ - if ((tcon->ses) && + if ((tcon->ses) && (tcon->ses->server) && (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU)) hdr->CreditCharge = cpu_to_le16(1); /* else CreditCharge MBZ */ diff --git a/fs/dcache.c b/fs/dcache.c index 656ce52..37b5afd 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1239,13 +1239,13 @@ ascend: /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; - next = child->d_child.next; - while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) { + /* go into the first sibling still alive */ + do { + next = child->d_child.next; if (next == &this_parent->d_subdirs) goto ascend; child = list_entry(next, struct dentry, d_child); - next = next->next; - } + } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); rcu_read_unlock(); goto resume; } diff --git a/fs/omfs/bitmap.c b/fs/omfs/bitmap.c index 0822345..83f4e76 100644 --- a/fs/omfs/bitmap.c +++ b/fs/omfs/bitmap.c @@ -159,7 +159,7 @@ int omfs_allocate_range(struct super_block *sb, goto out; found: - *return_block = i * bits_per_entry + bit; + *return_block = (u64) i * bits_per_entry + bit; *return_size = run; ret = set_run(sb, i, bits_per_entry, bit, run, 1); diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 138321b..3d935c8 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -306,7 +306,8 @@ static const struct super_operations omfs_sops = { */ static int omfs_get_imap(struct super_block *sb) { - unsigned int bitmap_size, count, array_size; + unsigned int bitmap_size, array_size; + int count; struct omfs_sb_info *sbi = OMFS_SB(sb); struct buffer_head *bh; unsigned long **ptr; @@ -359,7 +360,7 @@ nomem: } enum { - Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask + Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_err }; static const match_table_t tokens = { @@ -368,6 +369,7 @@ static const match_table_t tokens = { {Opt_umask, "umask=%o"}, {Opt_dmask, "dmask=%o"}, {Opt_fmask, "fmask=%o"}, + {Opt_err, NULL}, }; static int parse_options(char *options, struct omfs_sb_info *sbi) @@ -548,8 +550,10 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent) } sb->s_root = d_make_root(root); - if (!sb->s_root) + if (!sb->s_root) { + ret = -ENOMEM; goto out_brelse_bh2; + } printk(KERN_DEBUG "omfs: Mounted volume %s\n", omfs_rb->r_name); ret = 0; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 24f6404..84d693d 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -299,6 +299,9 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, struct cred *override_cred; char *link = NULL; + if (WARN_ON(!workdir)) + return -EROFS; + ovl_path_upper(parent, &parentpath); upperdir = parentpath.dentry; diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index d139405..692ceda 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -222,6 +222,9 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry, struct kstat stat; int err; + if (WARN_ON(!workdir)) + return ERR_PTR(-EROFS); + err = ovl_lock_rename_workdir(workdir, upperdir); if (err) goto out; @@ -322,6 +325,9 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, struct dentry *newdentry; int err; + if (WARN_ON(!workdir)) + return -EROFS; + err = ovl_lock_rename_workdir(workdir, upperdir); if (err) goto out; @@ -506,11 +512,28 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) struct dentry *opaquedir = NULL; int err; - if (is_dir && OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) { - opaquedir = ovl_check_empty_and_clear(dentry); - err = PTR_ERR(opaquedir); - if (IS_ERR(opaquedir)) - goto out; + if (WARN_ON(!workdir)) + return -EROFS; + + if (is_dir) { + if (OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) { + opaquedir = ovl_check_empty_and_clear(dentry); + err = PTR_ERR(opaquedir); + if (IS_ERR(opaquedir)) + goto out; + } else { + LIST_HEAD(list); + + /* + * When removing an empty opaque directory, then it + * makes no sense to replace it with an exact replica of + * itself. But emptiness still needs to be checked. + */ + err = ovl_check_empty_dir(dentry, &list); + ovl_cache_free(&list); + if (err) + goto out; + } } err = ovl_lock_rename_workdir(workdir, upperdir); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 5f0d199..bf8537c 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -529,7 +529,7 @@ static int ovl_remount(struct super_block *sb, int *flags, char *data) { struct ovl_fs *ufs = sb->s_fs_info; - if (!(*flags & MS_RDONLY) && !ufs->upper_mnt) + if (!(*flags & MS_RDONLY) && (!ufs->upper_mnt || !ufs->workdir)) return -EROFS; return 0; @@ -925,9 +925,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry); err = PTR_ERR(ufs->workdir); if (IS_ERR(ufs->workdir)) { - pr_err("overlayfs: failed to create directory %s/%s\n", - ufs->config.workdir, OVL_WORKDIR_NAME); - goto out_put_upper_mnt; + pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n", + ufs->config.workdir, OVL_WORKDIR_NAME, -err); + sb->s_flags |= MS_RDONLY; + ufs->workdir = NULL; } } @@ -997,7 +998,6 @@ out_put_lower_mnt: kfree(ufs->lower_mnt); out_put_workdir: dput(ufs->workdir); -out_put_upper_mnt: mntput(ufs->upper_mnt); out_put_lowerpath: for (i = 0; i < numlower; i++) diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 04e79d5..e9d401c 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -574,8 +574,8 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff) * After the last attribute is removed revert to original inode format, * making all literal area available to the data fork once more. */ -STATIC void -xfs_attr_fork_reset( +void +xfs_attr_fork_remove( struct xfs_inode *ip, struct xfs_trans *tp) { @@ -641,7 +641,7 @@ xfs_attr_shortform_remove(xfs_da_args_t *args) (mp->m_flags & XFS_MOUNT_ATTR2) && (dp->i_d.di_format != XFS_DINODE_FMT_BTREE) && !(args->op_flags & XFS_DA_OP_ADDNAME)) { - xfs_attr_fork_reset(dp, args->trans); + xfs_attr_fork_remove(dp, args->trans); } else { xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize); @@ -905,7 +905,7 @@ xfs_attr3_leaf_to_shortform( if (forkoff == -1) { ASSERT(dp->i_mount->m_flags & XFS_MOUNT_ATTR2); ASSERT(dp->i_d.di_format != XFS_DINODE_FMT_BTREE); - xfs_attr_fork_reset(dp, args->trans); + xfs_attr_fork_remove(dp, args->trans); goto out; } diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index 025c4b8..882c8d3 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -53,7 +53,7 @@ int xfs_attr_shortform_remove(struct xfs_da_args *args); int xfs_attr_shortform_list(struct xfs_attr_list_context *context); int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp); int xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes); - +void xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp); /* * Internal routines when attribute fork size == XFS_LBSIZE(mp). diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index aeffeaa..f1026e8 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3224,12 +3224,24 @@ xfs_bmap_extsize_align( align_alen += temp; align_off -= temp; } + + /* Same adjustment for the end of the requested area. */ + temp = (align_alen % extsz); + if (temp) + align_alen += extsz - temp; + /* - * Same adjustment for the end of the requested area. + * For large extent hint sizes, the aligned extent might be larger than + * MAXEXTLEN. In that case, reduce the size by an extsz so that it pulls + * the length back under MAXEXTLEN. The outer allocation loops handle + * short allocation just fine, so it is safe to do this. We only want to + * do it when we are forced to, though, because it means more allocation + * operations are required. */ - if ((temp = (align_alen % extsz))) { - align_alen += extsz - temp; - } + while (align_alen > MAXEXTLEN) + align_alen -= extsz; + ASSERT(align_alen <= MAXEXTLEN); + /* * If the previous block overlaps with this proposed allocation * then move the start forward without adjusting the length. @@ -3318,7 +3330,9 @@ xfs_bmap_extsize_align( return -EINVAL; } else { ASSERT(orig_off >= align_off); - ASSERT(orig_end <= align_off + align_alen); + /* see MAXEXTLEN handling above */ + ASSERT(orig_end <= align_off + align_alen || + align_alen + extsz > MAXEXTLEN); } #ifdef DEBUG @@ -4099,13 +4113,6 @@ xfs_bmapi_reserve_delalloc( /* Figure out the extent size, adjust alen */ extsz = xfs_get_extsz_hint(ip); if (extsz) { - /* - * Make sure we don't exceed a single extent length when we - * align the extent by reducing length we are going to - * allocate by the maximum amount extent size aligment may - * require. - */ - alen = XFS_FILBLKS_MIN(len, MAXEXTLEN - (2 * extsz - 1)); error = xfs_bmap_extsize_align(mp, got, prev, extsz, rt, eof, 1, 0, &aoff, &alen); ASSERT(!error); diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 07349a1..1c9e755 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -376,7 +376,7 @@ xfs_ialloc_ag_alloc( */ newlen = args.mp->m_ialloc_inos; if (args.mp->m_maxicount && - percpu_counter_read(&args.mp->m_icount) + newlen > + percpu_counter_read_positive(&args.mp->m_icount) + newlen > args.mp->m_maxicount) return -ENOSPC; args.minlen = args.maxlen = args.mp->m_ialloc_blks; @@ -1339,10 +1339,13 @@ xfs_dialloc( * If we have already hit the ceiling of inode blocks then clear * okalloc so we scan all available agi structures for a free * inode. + * + * Read rough value of mp->m_icount by percpu_counter_read_positive, + * which will sacrifice the preciseness but improve the performance. */ if (mp->m_maxicount && - percpu_counter_read(&mp->m_icount) + mp->m_ialloc_inos > - mp->m_maxicount) { + percpu_counter_read_positive(&mp->m_icount) + mp->m_ialloc_inos + > mp->m_maxicount) { noroom = 1; okalloc = 0; } diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index f9c1c64..3fbf167 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -380,23 +380,31 @@ xfs_attr3_root_inactive( return error; } +/* + * xfs_attr_inactive kills all traces of an attribute fork on an inode. It + * removes both the on-disk and in-memory inode fork. Note that this also has to + * handle the condition of inodes without attributes but with an attribute fork + * configured, so we can't use xfs_inode_hasattr() here. + * + * The in-memory attribute fork is removed even on error. + */ int -xfs_attr_inactive(xfs_inode_t *dp) +xfs_attr_inactive( + struct xfs_inode *dp) { - xfs_trans_t *trans; - xfs_mount_t *mp; - int error; + struct xfs_trans *trans; + struct xfs_mount *mp; + int cancel_flags = 0; + int lock_mode = XFS_ILOCK_SHARED; + int error = 0; mp = dp->i_mount; ASSERT(! XFS_NOT_DQATTACHED(mp, dp)); - xfs_ilock(dp, XFS_ILOCK_SHARED); - if (!xfs_inode_hasattr(dp) || - dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { - xfs_iunlock(dp, XFS_ILOCK_SHARED); - return 0; - } - xfs_iunlock(dp, XFS_ILOCK_SHARED); + xfs_ilock(dp, lock_mode); + if (!XFS_IFORK_Q(dp)) + goto out_destroy_fork; + xfs_iunlock(dp, lock_mode); /* * Start our first transaction of the day. @@ -408,13 +416,18 @@ xfs_attr_inactive(xfs_inode_t *dp) * the inode in every transaction to let it float upward through * the log. */ + lock_mode = 0; trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL); error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0); - if (error) { - xfs_trans_cancel(trans, 0); - return error; - } - xfs_ilock(dp, XFS_ILOCK_EXCL); + if (error) + goto out_cancel; + + lock_mode = XFS_ILOCK_EXCL; + cancel_flags = XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT; + xfs_ilock(dp, lock_mode); + + if (!XFS_IFORK_Q(dp)) + goto out_cancel; /* * No need to make quota reservations here. We expect to release some @@ -422,29 +435,31 @@ xfs_attr_inactive(xfs_inode_t *dp) */ xfs_trans_ijoin(trans, dp, 0); - /* - * Decide on what work routines to call based on the inode size. - */ - if (!xfs_inode_hasattr(dp) || - dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { - error = 0; - goto out; + /* invalidate and truncate the attribute fork extents */ + if (dp->i_d.di_aformat != XFS_DINODE_FMT_LOCAL) { + error = xfs_attr3_root_inactive(&trans, dp); + if (error) + goto out_cancel; + + error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0); + if (error) + goto out_cancel; } - error = xfs_attr3_root_inactive(&trans, dp); - if (error) - goto out; - error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0); - if (error) - goto out; + /* Reset the attribute fork - this also destroys the in-core fork */ + xfs_attr_fork_remove(dp, trans); error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES); - xfs_iunlock(dp, XFS_ILOCK_EXCL); - + xfs_iunlock(dp, lock_mode); return error; -out: - xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT); - xfs_iunlock(dp, XFS_ILOCK_EXCL); +out_cancel: + xfs_trans_cancel(trans, cancel_flags); +out_destroy_fork: + /* kill the in-core attr fork before we drop the inode lock */ + if (dp->i_afp) + xfs_idestroy_fork(dp, XFS_ATTR_FORK); + if (lock_mode) + xfs_iunlock(dp, lock_mode); return error; } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 8121e75..3b75912 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -124,7 +124,7 @@ xfs_iozero( status = 0; } while (count); - return (-status); + return status; } int diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index d6ebc85..539a85f 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1946,21 +1946,17 @@ xfs_inactive( /* * If there are attributes associated with the file then blow them away * now. The code calls a routine that recursively deconstructs the - * attribute fork. We need to just commit the current transaction - * because we can't use it for xfs_attr_inactive(). + * attribute fork. If also blows away the in-core attribute fork. */ - if (ip->i_d.di_anextents > 0) { - ASSERT(ip->i_d.di_forkoff != 0); - + if (XFS_IFORK_Q(ip)) { error = xfs_attr_inactive(ip); if (error) return; } - if (ip->i_afp) - xfs_idestroy_fork(ip, XFS_ATTR_FORK); - + ASSERT(!ip->i_afp); ASSERT(ip->i_d.di_anextents == 0); + ASSERT(ip->i_d.di_forkoff == 0); /* * Free the inode. @@ -2883,7 +2879,13 @@ xfs_rename_alloc_whiteout( if (error) return error; - /* Satisfy xfs_bumplink that this is a real tmpfile */ + /* + * Prepare the tmpfile inode as if it were created through the VFS. + * Otherwise, the link increment paths will complain about nlink 0->1. + * Drop the link count as done by d_tmpfile(), complete the inode setup + * and flag it as linkable. + */ + drop_nlink(VFS_I(tmpfile)); xfs_finish_inode_setup(tmpfile); VFS_I(tmpfile)->i_state |= I_LINKABLE; @@ -3151,7 +3153,7 @@ xfs_rename( * intermediate state on disk. */ if (wip) { - ASSERT(wip->i_d.di_nlink == 0); + ASSERT(VFS_I(wip)->i_nlink == 0 && wip->i_d.di_nlink == 0); error = xfs_bumplink(tp, wip); if (error) goto out_trans_abort; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 2ce7ee3..6f23fbd 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1084,14 +1084,18 @@ xfs_log_sbcount(xfs_mount_t *mp) return xfs_sync_sb(mp, true); } +/* + * Deltas for the inode count are +/-64, hence we use a large batch size + * of 128 so we don't need to take the counter lock on every update. + */ +#define XFS_ICOUNT_BATCH 128 int xfs_mod_icount( struct xfs_mount *mp, int64_t delta) { - /* deltas are +/-64, hence the large batch size of 128. */ - __percpu_counter_add(&mp->m_icount, delta, 128); - if (percpu_counter_compare(&mp->m_icount, 0) < 0) { + __percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH); + if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) { ASSERT(0); percpu_counter_add(&mp->m_icount, -delta); return -EINVAL; @@ -1113,6 +1117,14 @@ xfs_mod_ifree( return 0; } +/* + * Deltas for the block count can vary from 1 to very large, but lock contention + * only occurs on frequent small block count updates such as in the delayed + * allocation path for buffered writes (page a time updates). Hence we set + * a large batch count (1024) to minimise global counter updates except when + * we get near to ENOSPC and we have to be very accurate with our updates. + */ +#define XFS_FDBLOCKS_BATCH 1024 int xfs_mod_fdblocks( struct xfs_mount *mp, @@ -1151,25 +1163,19 @@ xfs_mod_fdblocks( * Taking blocks away, need to be more accurate the closer we * are to zero. * - * batch size is set to a maximum of 1024 blocks - if we are - * allocating of freeing extents larger than this then we aren't - * going to be hammering the counter lock so a lock per update - * is not a problem. - * * If the counter has a value of less than 2 * max batch size, * then make everything serialise as we are real close to * ENOSPC. */ -#define __BATCH 1024 - if (percpu_counter_compare(&mp->m_fdblocks, 2 * __BATCH) < 0) + if (__percpu_counter_compare(&mp->m_fdblocks, 2 * XFS_FDBLOCKS_BATCH, + XFS_FDBLOCKS_BATCH) < 0) batch = 1; else - batch = __BATCH; -#undef __BATCH + batch = XFS_FDBLOCKS_BATCH; __percpu_counter_add(&mp->m_fdblocks, delta, batch); - if (percpu_counter_compare(&mp->m_fdblocks, - XFS_ALLOC_SET_ASIDE(mp)) >= 0) { + if (__percpu_counter_compare(&mp->m_fdblocks, XFS_ALLOC_SET_ASIDE(mp), + XFS_FDBLOCKS_BATCH) >= 0) { /* we had space! */ return 0; } diff --git a/include/dt-bindings/clock/qcom,gcc-ipq806x.h b/include/dt-bindings/clock/qcom,gcc-ipq806x.h index ebd63fd..dc4254b 100644 --- a/include/dt-bindings/clock/qcom,gcc-ipq806x.h +++ b/include/dt-bindings/clock/qcom,gcc-ipq806x.h @@ -289,5 +289,7 @@ #define UBI32_CORE1_CLK 279 #define UBI32_CORE2_CLK 280 #define EBI2_AON_CLK 281 +#define NSSTCM_CLK_SRC 282 +#define NSSTCM_CLK 283 #endif diff --git a/include/dt-bindings/net/ti-dp83867.h b/include/dt-bindings/net/ti-dp83867.h new file mode 100644 index 0000000..172744a --- /dev/null +++ b/include/dt-bindings/net/ti-dp83867.h @@ -0,0 +1,45 @@ +/* + * Device Tree constants for the Texas Instruments DP83867 PHY + * + * Author: Dan Murphy <dmurphy@ti.com> + * + * Copyright: (C) 2015 Texas Instruments, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _DT_BINDINGS_TI_DP83867_H +#define _DT_BINDINGS_TI_DP83867_H + +/* PHY CTRL bits */ +#define DP83867_PHYCR_FIFO_DEPTH_3_B_NIB 0x00 +#define DP83867_PHYCR_FIFO_DEPTH_4_B_NIB 0x01 +#define DP83867_PHYCR_FIFO_DEPTH_6_B_NIB 0x02 +#define DP83867_PHYCR_FIFO_DEPTH_8_B_NIB 0x03 + +/* RGMIIDCTL internal delay for rx and tx */ +#define DP83867_RGMIIDCTL_250_PS 0x0 +#define DP83867_RGMIIDCTL_500_PS 0x1 +#define DP83867_RGMIIDCTL_750_PS 0x2 +#define DP83867_RGMIIDCTL_1_NS 0x3 +#define DP83867_RGMIIDCTL_1_25_NS 0x4 +#define DP83867_RGMIIDCTL_1_50_NS 0x5 +#define DP83867_RGMIIDCTL_1_75_NS 0x6 +#define DP83867_RGMIIDCTL_2_00_NS 0x7 +#define DP83867_RGMIIDCTL_2_25_NS 0x8 +#define DP83867_RGMIIDCTL_2_50_NS 0x9 +#define DP83867_RGMIIDCTL_2_75_NS 0xa +#define DP83867_RGMIIDCTL_3_00_NS 0xb +#define DP83867_RGMIIDCTL_3_25_NS 0xc +#define DP83867_RGMIIDCTL_3_50_NS 0xd +#define DP83867_RGMIIDCTL_3_75_NS 0xe +#define DP83867_RGMIIDCTL_4_00_NS 0xf + +#endif diff --git a/include/dt-bindings/reset/qcom,gcc-ipq806x.h b/include/dt-bindings/reset/qcom,gcc-ipq806x.h index 0ad5ef9..de9c814 100644 --- a/include/dt-bindings/reset/qcom,gcc-ipq806x.h +++ b/include/dt-bindings/reset/qcom,gcc-ipq806x.h @@ -129,4 +129,47 @@ #define USB30_1_PHY_RESET 112 #define NSSFB0_RESET 113 #define NSSFB1_RESET 114 +#define UBI32_CORE1_CLKRST_CLAMP_RESET 115 +#define UBI32_CORE1_CLAMP_RESET 116 +#define UBI32_CORE1_AHB_RESET 117 +#define UBI32_CORE1_AXI_RESET 118 +#define UBI32_CORE2_CLKRST_CLAMP_RESET 119 +#define UBI32_CORE2_CLAMP_RESET 120 +#define UBI32_CORE2_AHB_RESET 121 +#define UBI32_CORE2_AXI_RESET 122 +#define GMAC_CORE1_RESET 123 +#define GMAC_CORE2_RESET 124 +#define GMAC_CORE3_RESET 125 +#define GMAC_CORE4_RESET 126 +#define GMAC_AHB_RESET 127 +#define NSS_CH0_RST_RX_CLK_N_RESET 128 +#define NSS_CH0_RST_TX_CLK_N_RESET 129 +#define NSS_CH0_RST_RX_125M_N_RESET 130 +#define NSS_CH0_HW_RST_RX_125M_N_RESET 131 +#define NSS_CH0_RST_TX_125M_N_RESET 132 +#define NSS_CH1_RST_RX_CLK_N_RESET 133 +#define NSS_CH1_RST_TX_CLK_N_RESET 134 +#define NSS_CH1_RST_RX_125M_N_RESET 135 +#define NSS_CH1_HW_RST_RX_125M_N_RESET 136 +#define NSS_CH1_RST_TX_125M_N_RESET 137 +#define NSS_CH2_RST_RX_CLK_N_RESET 138 +#define NSS_CH2_RST_TX_CLK_N_RESET 139 +#define NSS_CH2_RST_RX_125M_N_RESET 140 +#define NSS_CH2_HW_RST_RX_125M_N_RESET 141 +#define NSS_CH2_RST_TX_125M_N_RESET 142 +#define NSS_CH3_RST_RX_CLK_N_RESET 143 +#define NSS_CH3_RST_TX_CLK_N_RESET 144 +#define NSS_CH3_RST_RX_125M_N_RESET 145 +#define NSS_CH3_HW_RST_RX_125M_N_RESET 146 +#define NSS_CH3_RST_TX_125M_N_RESET 147 +#define NSS_RST_RX_250M_125M_N_RESET 148 +#define NSS_RST_TX_250M_125M_N_RESET 149 +#define NSS_QSGMII_TXPI_RST_N_RESET 150 +#define NSS_QSGMII_CDR_RST_N_RESET 151 +#define NSS_SGMII2_CDR_RST_N_RESET 152 +#define NSS_SGMII3_CDR_RST_N_RESET 153 +#define NSS_CAL_PRBS_RST_N_RESET 154 +#define NSS_LCKDT_RST_N_RESET 155 +#define NSS_SRDS_N_RESET 156 + #endif diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8821b9a..ca854e5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -123,7 +123,10 @@ struct bpf_prog_aux { const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; - struct work_struct work; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; struct bpf_array { @@ -153,6 +156,7 @@ void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); void bpf_prog_put(struct bpf_prog *prog); +void bpf_prog_put_rcu(struct bpf_prog *prog); struct bpf_map *bpf_map_get(struct fd f); void bpf_map_put(struct bpf_map *map); @@ -182,5 +186,6 @@ extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; +extern const struct bpf_func_proto bpf_ktime_get_ns_proto; #endif /* _LINUX_BPF_H */ diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index ae2982c..656da2a 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -17,7 +17,7 @@ #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7364 0xae025260 #define PHY_ID_BCM7366 0x600d8490 -#define PHY_ID_BCM7425 0x03625e60 +#define PHY_ID_BCM7425 0x600d86b0 #define PHY_ID_BCM7429 0x600d8730 #define PHY_ID_BCM7439 0x600d8480 #define PHY_ID_BCM7439_2 0xae025080 diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 27e285b..59915ea 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -151,10 +151,8 @@ static inline unsigned int cpumask_any_but(const struct cpumask *mask, return 1; } -static inline int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp) +static inline unsigned int cpumask_local_spread(unsigned int i, int node) { - set_bit(0, cpumask_bits(dstp)); - return 0; } @@ -208,7 +206,7 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); int cpumask_any_but(const struct cpumask *mask, unsigned int cpu); -int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp); +unsigned int cpumask_local_spread(unsigned int i, int node); /** * for_each_cpu - iterate over every cpu in a mask diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index b9ab677..67ce5bd 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -416,7 +416,7 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, /** * __vlan_get_tag - get the VLAN ID that is part of the payload * @skb: skbuff to query - * @vlan_tci: buffer to store vlaue + * @vlan_tci: buffer to store value * * Returns error if the skb is not of VLAN type */ @@ -435,7 +435,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) /** * __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[] * @skb: skbuff to query - * @vlan_tci: buffer to store vlaue + * @vlan_tci: buffer to store value * * Returns error if @skb->vlan_tci is not set correctly */ @@ -456,7 +456,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, /** * vlan_get_tag - get the VLAN ID from the skb * @skb: skbuff to query - * @vlan_tci: buffer to store vlaue + * @vlan_tci: buffer to store value * * Returns error if the skb is not VLAN tagged */ @@ -628,4 +628,24 @@ static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, return features; } +/** + * compare_vlan_header - Compare two vlan headers + * @h1: Pointer to vlan header + * @h2: Pointer to vlan header + * + * Compare two vlan headers, returns 0 if equal. + * + * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits. + */ +static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1, + const struct vlan_hdr *h2) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + return *(u32 *)h1 ^ *(u32 *)h2; +#else + return ((__force u32)h1->h_vlan_TCI ^ (__force u32)h2->h_vlan_TCI) | + ((__force u32)h1->h_vlan_encapsulated_proto ^ + (__force u32)h2->h_vlan_encapsulated_proto); +#endif +} #endif /* !(_LINUX_IF_VLAN_H_) */ diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 5fc3d10..2b6a204 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -166,19 +166,34 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) } #if BITS_PER_LONG < 64 -extern u64 __ktime_divns(const ktime_t kt, s64 div); -static inline u64 ktime_divns(const ktime_t kt, s64 div) +extern s64 __ktime_divns(const ktime_t kt, s64 div); +static inline s64 ktime_divns(const ktime_t kt, s64 div) { + /* + * Negative divisors could cause an inf loop, + * so bug out here. + */ + BUG_ON(div < 0); if (__builtin_constant_p(div) && !(div >> 32)) { - u64 ns = kt.tv64; - do_div(ns, div); - return ns; + s64 ns = kt.tv64; + u64 tmp = ns < 0 ? -ns : ns; + + do_div(tmp, div); + return ns < 0 ? -tmp : tmp; } else { return __ktime_divns(kt, div); } } #else /* BITS_PER_LONG < 64 */ -# define ktime_divns(kt, div) (u64)((kt).tv64 / (div)) +static inline s64 ktime_divns(const ktime_t kt, s64 div) +{ + /* + * 32-bit implementation cannot handle negative divisors, + * so catch them on 64bit as well. + */ + WARN_ON(div < 0); + return kt.tv64 / div; +} #endif static inline s64 ktime_to_us(const ktime_t kt) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 83e80ab..ad31e47 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -46,8 +46,9 @@ #define MAX_MSIX_P_PORT 17 #define MAX_MSIX 64 -#define MSIX_LEGACY_SZ 4 #define MIN_MSIX_P_PORT 5 +#define MLX4_IS_LEGACY_EQ_MODE(dev_cap) ((dev_cap).num_comp_vectors < \ + (dev_cap).num_ports * MIN_MSIX_P_PORT) #define MLX4_MAX_100M_UNITS_VAL 255 /* * work around: can't set values @@ -528,7 +529,6 @@ struct mlx4_caps { int num_eqs; int reserved_eqs; int num_comp_vectors; - int comp_pool; int num_mpts; int max_fmr_maps; int num_mtts; @@ -1332,10 +1332,13 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupts(struct mlx4_dev *dev); -int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, - int *vector); +u32 mlx4_get_eqs_per_port(struct mlx4_dev *dev, u8 port); +bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector); +struct cpu_rmap *mlx4_get_cpu_rmap(struct mlx4_dev *dev, int port); +int mlx4_assign_eq(struct mlx4_dev *dev, u8 port, int *vector); void mlx4_release_eq(struct mlx4_dev *dev, int vec); +int mlx4_is_eq_shared(struct mlx4_dev *dev, int vector); int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec); int mlx4_get_phys_port_id(struct mlx4_dev *dev); diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 2695ced..abc4767 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -169,6 +169,9 @@ int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, struct mlx5_query_cq_mbox_out *out); int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, struct mlx5_modify_cq_mbox_in *in, int in_sz); +int mlx5_core_modify_cq_moderation(struct mlx5_core_dev *dev, + struct mlx5_core_cq *cq, u16 cq_period, + u16 cq_max_count); int mlx5_debug_cq_add(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index abf65c7..b288c538 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -35,6 +35,7 @@ #include <linux/types.h> #include <rdma/ib_verbs.h> +#include <linux/mlx5/mlx5_ifc.h> #if defined(__LITTLE_ENDIAN) #define MLX5_SET_HOST_ENDIANNESS 0 @@ -58,6 +59,8 @@ #define MLX5_FLD_SZ_BYTES(typ, fld) (__mlx5_bit_sz(typ, fld) / 8) #define MLX5_ST_SZ_BYTES(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 8) #define MLX5_ST_SZ_DW(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 32) +#define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8) +#define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32) #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8) #define MLX5_ADDR_OF(typ, p, fld) ((char *)(p) + MLX5_BYTE_OFF(typ, fld)) @@ -70,6 +73,14 @@ << __mlx5_dw_bit_off(typ, fld))); \ } while (0) +#define MLX5_SET_TO_ONES(typ, p, fld) do { \ + BUILD_BUG_ON(__mlx5_st_sz_bits(typ) % 32); \ + *((__be32 *)(p) + __mlx5_dw_off(typ, fld)) = \ + cpu_to_be32((be32_to_cpu(*((__be32 *)(p) + __mlx5_dw_off(typ, fld))) & \ + (~__mlx5_dw_mask(typ, fld))) | ((__mlx5_mask(typ, fld)) \ + << __mlx5_dw_bit_off(typ, fld))); \ +} while (0) + #define MLX5_GET(typ, p, fld) ((be32_to_cpu(*((__be32 *)(p) +\ __mlx5_dw_off(typ, fld))) >> __mlx5_dw_bit_off(typ, fld)) & \ __mlx5_mask(typ, fld)) @@ -264,6 +275,7 @@ enum { MLX5_OPCODE_RDMA_WRITE_IMM = 0x09, MLX5_OPCODE_SEND = 0x0a, MLX5_OPCODE_SEND_IMM = 0x0b, + MLX5_OPCODE_LSO = 0x0e, MLX5_OPCODE_RDMA_READ = 0x10, MLX5_OPCODE_ATOMIC_CS = 0x11, MLX5_OPCODE_ATOMIC_FA = 0x12, @@ -312,13 +324,6 @@ enum { MLX5_CAP_OFF_CMDIF_CSUM = 46, }; -enum { - HCA_CAP_OPMOD_GET_MAX = 0, - HCA_CAP_OPMOD_GET_CUR = 1, - HCA_CAP_OPMOD_GET_ODP_MAX = 4, - HCA_CAP_OPMOD_GET_ODP_CUR = 5 -}; - struct mlx5_inbox_hdr { __be16 opcode; u8 rsvd[4]; @@ -541,6 +546,10 @@ struct mlx5_cmd_prot_block { u8 sig; }; +enum { + MLX5_CQE_SYND_FLUSHED_IN_ERROR = 5, +}; + struct mlx5_err_cqe { u8 rsvd0[32]; __be32 srqn; @@ -554,13 +563,22 @@ struct mlx5_err_cqe { }; struct mlx5_cqe64 { - u8 rsvd0[17]; + u8 rsvd0[4]; + u8 lro_tcppsh_abort_dupack; + u8 lro_min_ttl; + __be16 lro_tcp_win; + __be32 lro_ack_seq_num; + __be32 rss_hash_result; + u8 rss_hash_type; u8 ml_path; - u8 rsvd20[4]; + u8 rsvd20[2]; + __be16 check_sum; __be16 slid; __be32 flags_rqpn; - u8 rsvd28[4]; - __be32 srqn; + u8 hds_ip_ext; + u8 l4_hdr_type_etc; + __be16 vlan_info; + __be32 srqn; /* [31:24]: lro_num_seg, [23:0]: srqn */ __be32 imm_inval_pkey; u8 rsvd40[4]; __be32 byte_cnt; @@ -571,6 +589,40 @@ struct mlx5_cqe64 { u8 op_own; }; +static inline int get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) +{ + return (cqe->lro_tcppsh_abort_dupack >> 6) & 1; +} + +static inline u8 get_cqe_l4_hdr_type(struct mlx5_cqe64 *cqe) +{ + return (cqe->l4_hdr_type_etc >> 4) & 0x7; +} + +static inline int cqe_has_vlan(struct mlx5_cqe64 *cqe) +{ + return !!(cqe->l4_hdr_type_etc & 0x1); +} + +enum { + CQE_L4_HDR_TYPE_NONE = 0x0, + CQE_L4_HDR_TYPE_TCP_NO_ACK = 0x1, + CQE_L4_HDR_TYPE_UDP = 0x2, + CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA = 0x3, + CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA = 0x4, +}; + +enum { + CQE_RSS_HTYPE_IP = 0x3 << 6, + CQE_RSS_HTYPE_L4 = 0x3 << 2, +}; + +enum { + CQE_L2_OK = 1 << 0, + CQE_L3_OK = 1 << 1, + CQE_L4_OK = 1 << 2, +}; + struct mlx5_sig_err_cqe { u8 rsvd0[16]; __be32 expected_trans_sig; @@ -996,4 +1048,128 @@ struct mlx5_destroy_psv_out { u8 rsvd[8]; }; +#define MLX5_CMD_OP_MAX 0x920 + +enum { + VPORT_STATE_DOWN = 0x0, + VPORT_STATE_UP = 0x1, +}; + +enum { + MLX5_L3_PROT_TYPE_IPV4 = 0, + MLX5_L3_PROT_TYPE_IPV6 = 1, +}; + +enum { + MLX5_L4_PROT_TYPE_TCP = 0, + MLX5_L4_PROT_TYPE_UDP = 1, +}; + +enum { + MLX5_HASH_FIELD_SEL_SRC_IP = 1 << 0, + MLX5_HASH_FIELD_SEL_DST_IP = 1 << 1, + MLX5_HASH_FIELD_SEL_L4_SPORT = 1 << 2, + MLX5_HASH_FIELD_SEL_L4_DPORT = 1 << 3, + MLX5_HASH_FIELD_SEL_IPSEC_SPI = 1 << 4, +}; + +enum { + MLX5_MATCH_OUTER_HEADERS = 1 << 0, + MLX5_MATCH_MISC_PARAMETERS = 1 << 1, + MLX5_MATCH_INNER_HEADERS = 1 << 2, + +}; + +enum { + MLX5_FLOW_TABLE_TYPE_NIC_RCV = 0, + MLX5_FLOW_TABLE_TYPE_ESWITCH = 4, +}; + +enum { + MLX5_FLOW_CONTEXT_DEST_TYPE_VPORT = 0, + MLX5_FLOW_CONTEXT_DEST_TYPE_FLOW_TABLE = 1, + MLX5_FLOW_CONTEXT_DEST_TYPE_TIR = 2, +}; + +enum { + MLX5_RQC_RQ_TYPE_MEMORY_RQ_INLINE = 0x0, + MLX5_RQC_RQ_TYPE_MEMORY_RQ_RPM = 0x1, +}; + +/* MLX5 DEV CAPs */ + +/* TODO: EAT.ME */ +enum mlx5_cap_mode { + HCA_CAP_OPMOD_GET_MAX = 0, + HCA_CAP_OPMOD_GET_CUR = 1, +}; + +enum mlx5_cap_type { + MLX5_CAP_GENERAL = 0, + MLX5_CAP_ETHERNET_OFFLOADS, + MLX5_CAP_ODP, + MLX5_CAP_ATOMIC, + MLX5_CAP_ROCE, + MLX5_CAP_IPOIB_OFFLOADS, + MLX5_CAP_EOIB_OFFLOADS, + MLX5_CAP_FLOW_TABLE, + /* NUM OF CAP Types */ + MLX5_CAP_NUM +}; + +/* GET Dev Caps macros */ +#define MLX5_CAP_GEN(mdev, cap) \ + MLX5_GET(cmd_hca_cap, mdev->hca_caps_cur[MLX5_CAP_GENERAL], cap) + +#define MLX5_CAP_GEN_MAX(mdev, cap) \ + MLX5_GET(cmd_hca_cap, mdev->hca_caps_max[MLX5_CAP_GENERAL], cap) + +#define MLX5_CAP_ETH(mdev, cap) \ + MLX5_GET(per_protocol_networking_offload_caps,\ + mdev->hca_caps_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) + +#define MLX5_CAP_ETH_MAX(mdev, cap) \ + MLX5_GET(per_protocol_networking_offload_caps,\ + mdev->hca_caps_max[MLX5_CAP_ETHERNET_OFFLOADS], cap) + +#define MLX5_CAP_ROCE(mdev, cap) \ + MLX5_GET(roce_cap, mdev->hca_caps_cur[MLX5_CAP_ROCE], cap) + +#define MLX5_CAP_ROCE_MAX(mdev, cap) \ + MLX5_GET(roce_cap, mdev->hca_caps_max[MLX5_CAP_ROCE], cap) + +#define MLX5_CAP_ATOMIC(mdev, cap) \ + MLX5_GET(atomic_caps, mdev->hca_caps_cur[MLX5_CAP_ATOMIC], cap) + +#define MLX5_CAP_ATOMIC_MAX(mdev, cap) \ + MLX5_GET(atomic_caps, mdev->hca_caps_max[MLX5_CAP_ATOMIC], cap) + +#define MLX5_CAP_FLOWTABLE(mdev, cap) \ + MLX5_GET(flow_table_nic_cap, mdev->hca_caps_cur[MLX5_CAP_FLOW_TABLE], cap) + +#define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ + MLX5_GET(flow_table_nic_cap, mdev->hca_caps_max[MLX5_CAP_FLOW_TABLE], cap) + +#define MLX5_CAP_ODP(mdev, cap)\ + MLX5_GET(odp_cap, mdev->hca_caps_cur[MLX5_CAP_ODP], cap) + +enum { + MLX5_CMD_STAT_OK = 0x0, + MLX5_CMD_STAT_INT_ERR = 0x1, + MLX5_CMD_STAT_BAD_OP_ERR = 0x2, + MLX5_CMD_STAT_BAD_PARAM_ERR = 0x3, + MLX5_CMD_STAT_BAD_SYS_STATE_ERR = 0x4, + MLX5_CMD_STAT_BAD_RES_ERR = 0x5, + MLX5_CMD_STAT_RES_BUSY = 0x6, + MLX5_CMD_STAT_LIM_ERR = 0x8, + MLX5_CMD_STAT_BAD_RES_STATE_ERR = 0x9, + MLX5_CMD_STAT_IX_ERR = 0xa, + MLX5_CMD_STAT_NO_RES_ERR = 0xf, + MLX5_CMD_STAT_BAD_INP_LEN_ERR = 0x50, + MLX5_CMD_STAT_BAD_OUTP_LEN_ERR = 0x51, + MLX5_CMD_STAT_BAD_QP_STATE_ERR = 0x10, + MLX5_CMD_STAT_BAD_PKT_ERR = 0x30, + MLX5_CMD_STAT_BAD_SIZE_OUTS_CQES_ERR = 0x40, +}; + #endif /* MLX5_DEVICE_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 9a90e75..7fa26f0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -44,7 +44,6 @@ #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> -#include <linux/mlx5/mlx5_ifc.h> enum { MLX5_BOARD_ID_LEN = 64, @@ -85,7 +84,7 @@ enum { }; enum { - MLX5_MAX_EQ_NAME = 32 + MLX5_MAX_IRQ_NAME = 32 }; enum { @@ -150,6 +149,11 @@ enum mlx5_dev_event { MLX5_DEV_EVENT_CLIENT_REREG, }; +enum mlx5_port_status { + MLX5_PORT_UP = 1 << 1, + MLX5_PORT_DOWN = 1 << 2, +}; + struct mlx5_uuar_info { struct mlx5_uar *uars; int num_uars; @@ -269,56 +273,7 @@ struct mlx5_cmd { struct mlx5_port_caps { int gid_table_len; int pkey_table_len; -}; - -struct mlx5_general_caps { - u8 log_max_eq; - u8 log_max_cq; - u8 log_max_qp; - u8 log_max_mkey; - u8 log_max_pd; - u8 log_max_srq; - u8 log_max_strq; - u8 log_max_mrw_sz; - u8 log_max_bsf_list_size; - u8 log_max_klm_list_size; - u32 max_cqes; - int max_wqes; - u32 max_eqes; - u32 max_indirection; - int max_sq_desc_sz; - int max_rq_desc_sz; - int max_dc_sq_desc_sz; - u64 flags; - u16 stat_rate_support; - int log_max_msg; - int num_ports; - u8 log_max_ra_res_qp; - u8 log_max_ra_req_qp; - int max_srq_wqes; - int bf_reg_size; - int bf_regs_per_page; - struct mlx5_port_caps port[MLX5_MAX_PORTS]; - u8 ext_port_cap[MLX5_MAX_PORTS]; - int max_vf; - u32 reserved_lkey; - u8 local_ca_ack_delay; - u8 log_max_mcg; - u32 max_qp_mcg; - int min_page_sz; - int pd_cap; - u32 max_qp_counters; - u32 pkey_table_size; - u8 log_max_ra_req_dc; - u8 log_max_ra_res_dc; - u32 uar_sz; - u8 min_log_pg_sz; - u8 log_max_xrcd; - u16 log_uar_page_sz; -}; - -struct mlx5_caps { - struct mlx5_general_caps gen; + u8 ext_port_cap; }; struct mlx5_cmd_mailbox { @@ -334,8 +289,6 @@ struct mlx5_buf_list { struct mlx5_buf { struct mlx5_buf_list direct; - struct mlx5_buf_list *page_list; - int nbufs; int npages; int size; u8 page_shift; @@ -351,7 +304,6 @@ struct mlx5_eq { u8 eqn; int nent; u64 mask; - char name[MLX5_MAX_EQ_NAME]; struct list_head list; int index; struct mlx5_rsc_debug *dbg; @@ -414,7 +366,6 @@ struct mlx5_eq_table { struct mlx5_eq pages_eq; struct mlx5_eq async_eq; struct mlx5_eq cmd_eq; - struct msix_entry *msix_arr; int num_comp_vectors; /* protect EQs list */ @@ -467,9 +418,16 @@ struct mlx5_mr_table { struct radix_tree_root tree; }; +struct mlx5_irq_info { + cpumask_var_t mask; + char name[MLX5_MAX_IRQ_NAME]; +}; + struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table eq_table; + struct msix_entry *msix_arr; + struct mlx5_irq_info *irq_info; struct mlx5_uuar_info uuari; MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock); @@ -520,7 +478,9 @@ struct mlx5_core_dev { u8 rev_id; char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; - struct mlx5_caps caps; + struct mlx5_port_caps port_caps[MLX5_MAX_PORTS]; + u32 hca_caps_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; + u32 hca_caps_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; void (*event) (struct mlx5_core_dev *dev, @@ -529,6 +489,7 @@ struct mlx5_core_dev { struct mlx5_priv priv; struct mlx5_profile *profile; atomic_t num_qps; + u32 issi; }; struct mlx5_db { @@ -549,6 +510,11 @@ enum { MLX5_COMP_EQ_SIZE = 1024, }; +enum { + MLX5_PTYS_IB = 1 << 0, + MLX5_PTYS_EN = 1 << 2, +}; + struct mlx5_db_pgdir { struct list_head list; DECLARE_BITMAP(bitmap, MLX5_DB_PER_PAGE); @@ -586,11 +552,7 @@ struct mlx5_pas { static inline void *mlx5_buf_offset(struct mlx5_buf *buf, int offset) { - if (likely(BITS_PER_LONG == 64 || buf->nbufs == 1)) return buf->direct.buf + offset; - else - return buf->page_list[offset >> PAGE_SHIFT].buf + - (offset & (PAGE_SIZE - 1)); } extern struct workqueue_struct *mlx5_core_wq; @@ -654,8 +616,8 @@ void mlx5_cmd_use_events(struct mlx5_core_dev *dev); void mlx5_cmd_use_polling(struct mlx5_core_dev *dev); int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr); int mlx5_cmd_status_to_err_v2(void *ptr); -int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps, - u16 opmod); +int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, + enum mlx5_cap_mode cap_mode); int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, @@ -665,12 +627,13 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); +int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); +void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); void mlx5_health_cleanup(void); void __init mlx5_health_init(void); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev); -int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, int max_direct, - struct mlx5_buf *buf); +int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf); void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf); struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, gfp_t flags, int npages); @@ -734,7 +697,23 @@ void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); + int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); +int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, + int ptys_size, int proto_mask); +int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, + u32 *proto_cap, int proto_mask); +int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, + u32 *proto_admin, int proto_mask); +int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, + int proto_mask); +int mlx5_set_port_status(struct mlx5_core_dev *dev, + enum mlx5_port_status status); +int mlx5_query_port_status(struct mlx5_core_dev *dev, u8 *status); + +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu); +int mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu); +int mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu); int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); diff --git a/include/linux/mlx5/flow_table.h b/include/linux/mlx5/flow_table.h new file mode 100644 index 0000000..5f922c6 --- /dev/null +++ b/include/linux/mlx5/flow_table.h @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef MLX5_FLOW_TABLE_H +#define MLX5_FLOW_TABLE_H + +#include <linux/mlx5/driver.h> + +struct mlx5_flow_table_group { + u8 log_sz; + u8 match_criteria_enable; + u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; +}; + +void *mlx5_create_flow_table(struct mlx5_core_dev *dev, u8 level, u8 table_type, + u16 num_groups, + struct mlx5_flow_table_group *group); +void mlx5_destroy_flow_table(void *flow_table); +int mlx5_add_flow_table_entry(void *flow_table, u8 match_criteria_enable, + void *match_criteria, void *flow_context, + u32 *flow_index); +void mlx5_del_flow_table_entry(void *flow_table, u32 flow_index); +u32 mlx5_get_flow_table_id(void *flow_table); + +#endif /* MLX5_FLOW_TABLE_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cb3ad17..b27e9f6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -28,12 +28,45 @@ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. - */ - +*/ #ifndef MLX5_IFC_H #define MLX5_IFC_H enum { + MLX5_EVENT_TYPE_CODING_COMPLETION_EVENTS = 0x0, + MLX5_EVENT_TYPE_CODING_PATH_MIGRATED_SUCCEEDED = 0x1, + MLX5_EVENT_TYPE_CODING_COMMUNICATION_ESTABLISHED = 0x2, + MLX5_EVENT_TYPE_CODING_SEND_QUEUE_DRAINED = 0x3, + MLX5_EVENT_TYPE_CODING_LAST_WQE_REACHED = 0x13, + MLX5_EVENT_TYPE_CODING_SRQ_LIMIT = 0x14, + MLX5_EVENT_TYPE_CODING_DCT_ALL_CONNECTIONS_CLOSED = 0x1c, + MLX5_EVENT_TYPE_CODING_DCT_ACCESS_KEY_VIOLATION = 0x1d, + MLX5_EVENT_TYPE_CODING_CQ_ERROR = 0x4, + MLX5_EVENT_TYPE_CODING_LOCAL_WQ_CATASTROPHIC_ERROR = 0x5, + MLX5_EVENT_TYPE_CODING_PATH_MIGRATION_FAILED = 0x7, + MLX5_EVENT_TYPE_CODING_PAGE_FAULT_EVENT = 0xc, + MLX5_EVENT_TYPE_CODING_INVALID_REQUEST_LOCAL_WQ_ERROR = 0x10, + MLX5_EVENT_TYPE_CODING_LOCAL_ACCESS_VIOLATION_WQ_ERROR = 0x11, + MLX5_EVENT_TYPE_CODING_LOCAL_SRQ_CATASTROPHIC_ERROR = 0x12, + MLX5_EVENT_TYPE_CODING_INTERNAL_ERROR = 0x8, + MLX5_EVENT_TYPE_CODING_PORT_STATE_CHANGE = 0x9, + MLX5_EVENT_TYPE_CODING_GPIO_EVENT = 0x15, + MLX5_EVENT_TYPE_CODING_REMOTE_CONFIGURATION_PROTOCOL_EVENT = 0x19, + MLX5_EVENT_TYPE_CODING_DOORBELL_BLUEFLAME_CONGESTION_EVENT = 0x1a, + MLX5_EVENT_TYPE_CODING_STALL_VL_EVENT = 0x1b, + MLX5_EVENT_TYPE_CODING_DROPPED_PACKET_LOGGED_EVENT = 0x1f, + MLX5_EVENT_TYPE_CODING_COMMAND_INTERFACE_COMPLETION = 0xa, + MLX5_EVENT_TYPE_CODING_PAGE_REQUEST = 0xb +}; + +enum { + MLX5_MODIFY_TIR_BITMASK_LRO = 0x0, + MLX5_MODIFY_TIR_BITMASK_INDIRECT_TABLE = 0x1, + MLX5_MODIFY_TIR_BITMASK_HASH = 0x2, + MLX5_MODIFY_TIR_BITMASK_TUNNELED_OFFLOAD_EN = 0x3 +}; + +enum { MLX5_CMD_OP_QUERY_HCA_CAP = 0x100, MLX5_CMD_OP_QUERY_ADAPTER = 0x101, MLX5_CMD_OP_INIT_HCA = 0x102, @@ -43,6 +76,8 @@ enum { MLX5_CMD_OP_QUERY_PAGES = 0x107, MLX5_CMD_OP_MANAGE_PAGES = 0x108, MLX5_CMD_OP_SET_HCA_CAP = 0x109, + MLX5_CMD_OP_QUERY_ISSI = 0x10a, + MLX5_CMD_OP_SET_ISSI = 0x10b, MLX5_CMD_OP_CREATE_MKEY = 0x200, MLX5_CMD_OP_QUERY_MKEY = 0x201, MLX5_CMD_OP_DESTROY_MKEY = 0x202, @@ -66,6 +101,7 @@ enum { MLX5_CMD_OP_2ERR_QP = 0x507, MLX5_CMD_OP_2RST_QP = 0x50a, MLX5_CMD_OP_QUERY_QP = 0x50b, + MLX5_CMD_OP_SQD_RTS_QP = 0x50c, MLX5_CMD_OP_INIT2INIT_QP = 0x50e, MLX5_CMD_OP_CREATE_PSV = 0x600, MLX5_CMD_OP_DESTROY_PSV = 0x601, @@ -73,7 +109,10 @@ enum { MLX5_CMD_OP_DESTROY_SRQ = 0x701, MLX5_CMD_OP_QUERY_SRQ = 0x702, MLX5_CMD_OP_ARM_RQ = 0x703, - MLX5_CMD_OP_RESIZE_SRQ = 0x704, + MLX5_CMD_OP_CREATE_XRC_SRQ = 0x705, + MLX5_CMD_OP_DESTROY_XRC_SRQ = 0x706, + MLX5_CMD_OP_QUERY_XRC_SRQ = 0x707, + MLX5_CMD_OP_ARM_XRC_SRQ = 0x708, MLX5_CMD_OP_CREATE_DCT = 0x710, MLX5_CMD_OP_DESTROY_DCT = 0x711, MLX5_CMD_OP_DRAIN_DCT = 0x712, @@ -85,8 +124,12 @@ enum { MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT = 0x753, MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT = 0x754, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT = 0x755, - MLX5_CMD_OP_QUERY_RCOE_ADDRESS = 0x760, + MLX5_CMD_OP_QUERY_ROCE_ADDRESS = 0x760, MLX5_CMD_OP_SET_ROCE_ADDRESS = 0x761, + MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT = 0x762, + MLX5_CMD_OP_MODIFY_HCA_VPORT_CONTEXT = 0x763, + MLX5_CMD_OP_QUERY_HCA_VPORT_GID = 0x764, + MLX5_CMD_OP_QUERY_HCA_VPORT_PKEY = 0x765, MLX5_CMD_OP_QUERY_VPORT_COUNTER = 0x770, MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771, MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772, @@ -98,7 +141,7 @@ enum { MLX5_CMD_OP_CONFIG_INT_MODERATION = 0x804, MLX5_CMD_OP_ACCESS_REG = 0x805, MLX5_CMD_OP_ATTACH_TO_MCG = 0x806, - MLX5_CMD_OP_DETACH_FROM_MCG = 0x807, + MLX5_CMD_OP_DETTACH_FROM_MCG = 0x807, MLX5_CMD_OP_GET_DROPPED_PACKET_LOG = 0x80a, MLX5_CMD_OP_MAD_IFC = 0x50d, MLX5_CMD_OP_QUERY_MAD_DEMUX = 0x80b, @@ -106,23 +149,22 @@ enum { MLX5_CMD_OP_NOP = 0x80d, MLX5_CMD_OP_ALLOC_XRCD = 0x80e, MLX5_CMD_OP_DEALLOC_XRCD = 0x80f, - MLX5_CMD_OP_SET_BURST_SIZE = 0x812, - MLX5_CMD_OP_QUERY_BURST_SZIE = 0x813, - MLX5_CMD_OP_ACTIVATE_TRACER = 0x814, - MLX5_CMD_OP_DEACTIVATE_TRACER = 0x815, - MLX5_CMD_OP_CREATE_SNIFFER_RULE = 0x820, - MLX5_CMD_OP_DESTROY_SNIFFER_RULE = 0x821, - MLX5_CMD_OP_QUERY_CONG_PARAMS = 0x822, - MLX5_CMD_OP_MODIFY_CONG_PARAMS = 0x823, - MLX5_CMD_OP_QUERY_CONG_STATISTICS = 0x824, + MLX5_CMD_OP_ALLOC_TRANSPORT_DOMAIN = 0x816, + MLX5_CMD_OP_DEALLOC_TRANSPORT_DOMAIN = 0x817, + MLX5_CMD_OP_QUERY_CONG_STATUS = 0x822, + MLX5_CMD_OP_MODIFY_CONG_STATUS = 0x823, + MLX5_CMD_OP_QUERY_CONG_PARAMS = 0x824, + MLX5_CMD_OP_MODIFY_CONG_PARAMS = 0x825, + MLX5_CMD_OP_QUERY_CONG_STATISTICS = 0x826, + MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT = 0x827, + MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT = 0x828, + MLX5_CMD_OP_SET_L2_TABLE_ENTRY = 0x829, + MLX5_CMD_OP_QUERY_L2_TABLE_ENTRY = 0x82a, + MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY = 0x82b, MLX5_CMD_OP_CREATE_TIR = 0x900, MLX5_CMD_OP_MODIFY_TIR = 0x901, MLX5_CMD_OP_DESTROY_TIR = 0x902, MLX5_CMD_OP_QUERY_TIR = 0x903, - MLX5_CMD_OP_CREATE_TIS = 0x912, - MLX5_CMD_OP_MODIFY_TIS = 0x913, - MLX5_CMD_OP_DESTROY_TIS = 0x914, - MLX5_CMD_OP_QUERY_TIS = 0x915, MLX5_CMD_OP_CREATE_SQ = 0x904, MLX5_CMD_OP_MODIFY_SQ = 0x905, MLX5_CMD_OP_DESTROY_SQ = 0x906, @@ -135,9 +177,430 @@ enum { MLX5_CMD_OP_MODIFY_RMP = 0x90d, MLX5_CMD_OP_DESTROY_RMP = 0x90e, MLX5_CMD_OP_QUERY_RMP = 0x90f, - MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY = 0x910, - MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY = 0x911, - MLX5_CMD_OP_MAX = 0x911 + MLX5_CMD_OP_CREATE_TIS = 0x912, + MLX5_CMD_OP_MODIFY_TIS = 0x913, + MLX5_CMD_OP_DESTROY_TIS = 0x914, + MLX5_CMD_OP_QUERY_TIS = 0x915, + MLX5_CMD_OP_CREATE_RQT = 0x916, + MLX5_CMD_OP_MODIFY_RQT = 0x917, + MLX5_CMD_OP_DESTROY_RQT = 0x918, + MLX5_CMD_OP_QUERY_RQT = 0x919, + MLX5_CMD_OP_CREATE_FLOW_TABLE = 0x930, + MLX5_CMD_OP_DESTROY_FLOW_TABLE = 0x931, + MLX5_CMD_OP_QUERY_FLOW_TABLE = 0x932, + MLX5_CMD_OP_CREATE_FLOW_GROUP = 0x933, + MLX5_CMD_OP_DESTROY_FLOW_GROUP = 0x934, + MLX5_CMD_OP_QUERY_FLOW_GROUP = 0x935, + MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY = 0x936, + MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY = 0x937, + MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY = 0x938 +}; + +struct mlx5_ifc_flow_table_fields_supported_bits { + u8 outer_dmac[0x1]; + u8 outer_smac[0x1]; + u8 outer_ether_type[0x1]; + u8 reserved_0[0x1]; + u8 outer_first_prio[0x1]; + u8 outer_first_cfi[0x1]; + u8 outer_first_vid[0x1]; + u8 reserved_1[0x1]; + u8 outer_second_prio[0x1]; + u8 outer_second_cfi[0x1]; + u8 outer_second_vid[0x1]; + u8 reserved_2[0x1]; + u8 outer_sip[0x1]; + u8 outer_dip[0x1]; + u8 outer_frag[0x1]; + u8 outer_ip_protocol[0x1]; + u8 outer_ip_ecn[0x1]; + u8 outer_ip_dscp[0x1]; + u8 outer_udp_sport[0x1]; + u8 outer_udp_dport[0x1]; + u8 outer_tcp_sport[0x1]; + u8 outer_tcp_dport[0x1]; + u8 outer_tcp_flags[0x1]; + u8 outer_gre_protocol[0x1]; + u8 outer_gre_key[0x1]; + u8 outer_vxlan_vni[0x1]; + u8 reserved_3[0x5]; + u8 source_eswitch_port[0x1]; + + u8 inner_dmac[0x1]; + u8 inner_smac[0x1]; + u8 inner_ether_type[0x1]; + u8 reserved_4[0x1]; + u8 inner_first_prio[0x1]; + u8 inner_first_cfi[0x1]; + u8 inner_first_vid[0x1]; + u8 reserved_5[0x1]; + u8 inner_second_prio[0x1]; + u8 inner_second_cfi[0x1]; + u8 inner_second_vid[0x1]; + u8 reserved_6[0x1]; + u8 inner_sip[0x1]; + u8 inner_dip[0x1]; + u8 inner_frag[0x1]; + u8 inner_ip_protocol[0x1]; + u8 inner_ip_ecn[0x1]; + u8 inner_ip_dscp[0x1]; + u8 inner_udp_sport[0x1]; + u8 inner_udp_dport[0x1]; + u8 inner_tcp_sport[0x1]; + u8 inner_tcp_dport[0x1]; + u8 inner_tcp_flags[0x1]; + u8 reserved_7[0x9]; + + u8 reserved_8[0x40]; +}; + +struct mlx5_ifc_flow_table_prop_layout_bits { + u8 ft_support[0x1]; + u8 reserved_0[0x1f]; + + u8 reserved_1[0x2]; + u8 log_max_ft_size[0x6]; + u8 reserved_2[0x10]; + u8 max_ft_level[0x8]; + + u8 reserved_3[0x20]; + + u8 reserved_4[0x18]; + u8 log_max_ft_num[0x8]; + + u8 reserved_5[0x18]; + u8 log_max_destination[0x8]; + + u8 reserved_6[0x18]; + u8 log_max_flow[0x8]; + + u8 reserved_7[0x40]; + + struct mlx5_ifc_flow_table_fields_supported_bits ft_field_support; + + struct mlx5_ifc_flow_table_fields_supported_bits ft_field_bitmask_support; +}; + +struct mlx5_ifc_odp_per_transport_service_cap_bits { + u8 send[0x1]; + u8 receive[0x1]; + u8 write[0x1]; + u8 read[0x1]; + u8 reserved_0[0x1]; + u8 srq_receive[0x1]; + u8 reserved_1[0x1a]; +}; + +struct mlx5_ifc_fte_match_set_lyr_2_4_bits { + u8 smac_47_16[0x20]; + + u8 smac_15_0[0x10]; + u8 ethertype[0x10]; + + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 first_prio[0x3]; + u8 first_cfi[0x1]; + u8 first_vid[0xc]; + + u8 ip_protocol[0x8]; + u8 ip_dscp[0x6]; + u8 ip_ecn[0x2]; + u8 vlan_tag[0x1]; + u8 reserved_0[0x1]; + u8 frag[0x1]; + u8 reserved_1[0x4]; + u8 tcp_flags[0x9]; + + u8 tcp_sport[0x10]; + u8 tcp_dport[0x10]; + + u8 reserved_2[0x20]; + + u8 udp_sport[0x10]; + u8 udp_dport[0x10]; + + u8 src_ip[4][0x20]; + + u8 dst_ip[4][0x20]; +}; + +struct mlx5_ifc_fte_match_set_misc_bits { + u8 reserved_0[0x20]; + + u8 reserved_1[0x10]; + u8 source_port[0x10]; + + u8 outer_second_prio[0x3]; + u8 outer_second_cfi[0x1]; + u8 outer_second_vid[0xc]; + u8 inner_second_prio[0x3]; + u8 inner_second_cfi[0x1]; + u8 inner_second_vid[0xc]; + + u8 outer_second_vlan_tag[0x1]; + u8 inner_second_vlan_tag[0x1]; + u8 reserved_2[0xe]; + u8 gre_protocol[0x10]; + + u8 gre_key_h[0x18]; + u8 gre_key_l[0x8]; + + u8 vxlan_vni[0x18]; + u8 reserved_3[0x8]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0xc]; + u8 outer_ipv6_flow_label[0x14]; + + u8 reserved_6[0xc]; + u8 inner_ipv6_flow_label[0x14]; + + u8 reserved_7[0xe0]; +}; + +struct mlx5_ifc_cmd_pas_bits { + u8 pa_h[0x20]; + + u8 pa_l[0x14]; + u8 reserved_0[0xc]; +}; + +struct mlx5_ifc_uint64_bits { + u8 hi[0x20]; + + u8 lo[0x20]; +}; + +enum { + MLX5_ADS_STAT_RATE_NO_LIMIT = 0x0, + MLX5_ADS_STAT_RATE_2_5GBPS = 0x7, + MLX5_ADS_STAT_RATE_10GBPS = 0x8, + MLX5_ADS_STAT_RATE_30GBPS = 0x9, + MLX5_ADS_STAT_RATE_5GBPS = 0xa, + MLX5_ADS_STAT_RATE_20GBPS = 0xb, + MLX5_ADS_STAT_RATE_40GBPS = 0xc, + MLX5_ADS_STAT_RATE_60GBPS = 0xd, + MLX5_ADS_STAT_RATE_80GBPS = 0xe, + MLX5_ADS_STAT_RATE_120GBPS = 0xf, +}; + +struct mlx5_ifc_ads_bits { + u8 fl[0x1]; + u8 free_ar[0x1]; + u8 reserved_0[0xe]; + u8 pkey_index[0x10]; + + u8 reserved_1[0x8]; + u8 grh[0x1]; + u8 mlid[0x7]; + u8 rlid[0x10]; + + u8 ack_timeout[0x5]; + u8 reserved_2[0x3]; + u8 src_addr_index[0x8]; + u8 reserved_3[0x4]; + u8 stat_rate[0x4]; + u8 hop_limit[0x8]; + + u8 reserved_4[0x4]; + u8 tclass[0x8]; + u8 flow_label[0x14]; + + u8 rgid_rip[16][0x8]; + + u8 reserved_5[0x4]; + u8 f_dscp[0x1]; + u8 f_ecn[0x1]; + u8 reserved_6[0x1]; + u8 f_eth_prio[0x1]; + u8 ecn[0x2]; + u8 dscp[0x6]; + u8 udp_sport[0x10]; + + u8 dei_cfi[0x1]; + u8 eth_prio[0x3]; + u8 sl[0x4]; + u8 port[0x8]; + u8 rmac_47_32[0x10]; + + u8 rmac_31_0[0x20]; +}; + +struct mlx5_ifc_flow_table_nic_cap_bits { + u8 reserved_0[0x200]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; + + u8 reserved_1[0x200]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_sniffer; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit; + + u8 reserved_2[0x200]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; + + u8 reserved_3[0x7200]; +}; + +struct mlx5_ifc_per_protocol_networking_offload_caps_bits { + u8 csum_cap[0x1]; + u8 vlan_cap[0x1]; + u8 lro_cap[0x1]; + u8 lro_psh_flag[0x1]; + u8 lro_time_stamp[0x1]; + u8 reserved_0[0x6]; + u8 max_lso_cap[0x5]; + u8 reserved_1[0x4]; + u8 rss_ind_tbl_cap[0x4]; + u8 reserved_2[0x3]; + u8 tunnel_lso_const_out_ip_id[0x1]; + u8 reserved_3[0x2]; + u8 tunnel_statless_gre[0x1]; + u8 tunnel_stateless_vxlan[0x1]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x10]; + u8 lro_min_mss_size[0x10]; + + u8 reserved_6[0x120]; + + u8 lro_timer_supported_periods[4][0x20]; + + u8 reserved_7[0x600]; +}; + +struct mlx5_ifc_roce_cap_bits { + u8 roce_apm[0x1]; + u8 reserved_0[0x1f]; + + u8 reserved_1[0x60]; + + u8 reserved_2[0xc]; + u8 l3_type[0x4]; + u8 reserved_3[0x8]; + u8 roce_version[0x8]; + + u8 reserved_4[0x10]; + u8 r_roce_dest_udp_port[0x10]; + + u8 r_roce_max_src_udp_port[0x10]; + u8 r_roce_min_src_udp_port[0x10]; + + u8 reserved_5[0x10]; + u8 roce_address_table_size[0x10]; + + u8 reserved_6[0x700]; +}; + +enum { + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_1_BYTE = 0x0, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_2_BYTES = 0x2, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_4_BYTES = 0x4, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_8_BYTES = 0x8, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_16_BYTES = 0x10, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_32_BYTES = 0x20, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_64_BYTES = 0x40, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_128_BYTES = 0x80, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_256_BYTES = 0x100, +}; + +enum { + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_1_BYTE = 0x1, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_2_BYTES = 0x2, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_4_BYTES = 0x4, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_8_BYTES = 0x8, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_16_BYTES = 0x10, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_32_BYTES = 0x20, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_64_BYTES = 0x40, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_128_BYTES = 0x80, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_256_BYTES = 0x100, +}; + +struct mlx5_ifc_atomic_caps_bits { + u8 reserved_0[0x40]; + + u8 atomic_req_endianness[0x1]; + u8 reserved_1[0x1f]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x10]; + u8 atomic_operations[0x10]; + + u8 reserved_4[0x10]; + u8 atomic_size_qp[0x10]; + + u8 reserved_5[0x10]; + u8 atomic_size_dc[0x10]; + + u8 reserved_6[0x720]; +}; + +struct mlx5_ifc_odp_cap_bits { + u8 reserved_0[0x40]; + + u8 sig[0x1]; + u8 reserved_1[0x1f]; + + u8 reserved_2[0x20]; + + struct mlx5_ifc_odp_per_transport_service_cap_bits rc_odp_caps; + + struct mlx5_ifc_odp_per_transport_service_cap_bits uc_odp_caps; + + struct mlx5_ifc_odp_per_transport_service_cap_bits ud_odp_caps; + + u8 reserved_3[0x720]; +}; + +enum { + MLX5_WQ_TYPE_LINKED_LIST = 0x0, + MLX5_WQ_TYPE_CYCLIC = 0x1, + MLX5_WQ_TYPE_STRQ = 0x2, +}; + +enum { + MLX5_WQ_END_PAD_MODE_NONE = 0x0, + MLX5_WQ_END_PAD_MODE_ALIGN = 0x1, +}; + +enum { + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_8_GID_ENTRIES = 0x0, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_16_GID_ENTRIES = 0x1, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_32_GID_ENTRIES = 0x2, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_64_GID_ENTRIES = 0x3, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_128_GID_ENTRIES = 0x4, +}; + +enum { + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_128_ENTRIES = 0x0, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_256_ENTRIES = 0x1, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_512_ENTRIES = 0x2, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_1K_ENTRIES = 0x3, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_2K_ENTRIES = 0x4, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_4K_ENTRIES = 0x5, +}; + +enum { + MLX5_CMD_HCA_CAP_PORT_TYPE_IB = 0x0, + MLX5_CMD_HCA_CAP_PORT_TYPE_ETHERNET = 0x1, +}; + +enum { + MLX5_CMD_HCA_CAP_CMDIF_CHECKSUM_DISABLED = 0x0, + MLX5_CMD_HCA_CAP_CMDIF_CHECKSUM_INITIAL_STATE = 0x1, + MLX5_CMD_HCA_CAP_CMDIF_CHECKSUM_ENABLED = 0x3, +}; + +enum { + MLX5_CAP_PORT_TYPE_IB = 0x0, + MLX5_CAP_PORT_TYPE_ETH = 0x1, }; struct mlx5_ifc_cmd_hca_cap_bits { @@ -148,9 +611,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_1[0xb]; u8 log_max_qp[0x5]; - u8 log_max_strq_sz[0x8]; - u8 reserved_2[0x3]; - u8 log_max_srqs[0x5]; + u8 reserved_2[0xb]; + u8 log_max_srq[0x5]; u8 reserved_3[0x10]; u8 reserved_4[0x8]; @@ -185,123 +647,2109 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 pad_cap[0x1]; u8 cc_query_allowed[0x1]; u8 cc_modify_allowed[0x1]; - u8 reserved_15[0x1d]; + u8 reserved_15[0xd]; + u8 gid_table_size[0x10]; - u8 reserved_16[0x6]; + u8 out_of_seq_cnt[0x1]; + u8 vport_counters[0x1]; + u8 reserved_16[0x4]; u8 max_qp_cnt[0xa]; u8 pkey_table_size[0x10]; - u8 eswitch_owner[0x1]; - u8 reserved_17[0xa]; + u8 vport_group_manager[0x1]; + u8 vhca_group_manager[0x1]; + u8 ib_virt[0x1]; + u8 eth_virt[0x1]; + u8 reserved_17[0x1]; + u8 ets[0x1]; + u8 nic_flow_table[0x1]; + u8 reserved_18[0x4]; u8 local_ca_ack_delay[0x5]; - u8 reserved_18[0x8]; + u8 reserved_19[0x6]; + u8 port_type[0x2]; u8 num_ports[0x8]; - u8 reserved_19[0x3]; + u8 reserved_20[0x3]; u8 log_max_msg[0x5]; - u8 reserved_20[0x18]; + u8 reserved_21[0x18]; u8 stat_rate_support[0x10]; - u8 reserved_21[0x10]; + u8 reserved_22[0xc]; + u8 cqe_version[0x4]; - u8 reserved_22[0x10]; + u8 compact_address_vector[0x1]; + u8 reserved_23[0xe]; + u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; - u8 reserved_23[0x1]; + u8 reserved_24[0x1]; u8 wq_signature[0x1]; u8 sctr_data_cqe[0x1]; - u8 reserved_24[0x1]; + u8 reserved_25[0x1]; u8 sho[0x1]; u8 tph[0x1]; u8 rf[0x1]; - u8 dc[0x1]; - u8 reserved_25[0x2]; + u8 dct[0x1]; + u8 reserved_26[0x1]; + u8 eth_net_offloads[0x1]; u8 roce[0x1]; u8 atomic[0x1]; - u8 rsz_srq[0x1]; + u8 reserved_27[0x1]; u8 cq_oi[0x1]; u8 cq_resize[0x1]; u8 cq_moderation[0x1]; - u8 sniffer_rule_flow[0x1]; - u8 sniffer_rule_vport[0x1]; - u8 sniffer_rule_phy[0x1]; - u8 reserved_26[0x1]; + u8 reserved_28[0x3]; + u8 cq_eq_remap[0x1]; u8 pg[0x1]; u8 block_lb_mc[0x1]; - u8 reserved_27[0x3]; + u8 reserved_29[0x1]; + u8 scqe_break_moderation[0x1]; + u8 reserved_30[0x1]; u8 cd[0x1]; - u8 reserved_28[0x1]; + u8 reserved_31[0x1]; u8 apm[0x1]; - u8 reserved_29[0x7]; + u8 reserved_32[0x7]; u8 qkv[0x1]; u8 pkv[0x1]; - u8 reserved_30[0x4]; + u8 reserved_33[0x4]; u8 xrc[0x1]; u8 ud[0x1]; u8 uc[0x1]; u8 rc[0x1]; - u8 reserved_31[0xa]; + u8 reserved_34[0xa]; u8 uar_sz[0x6]; - u8 reserved_32[0x8]; + u8 reserved_35[0x8]; u8 log_pg_sz[0x8]; u8 bf[0x1]; - u8 reserved_33[0xa]; + u8 reserved_36[0x1]; + u8 pad_tx_eth_packet[0x1]; + u8 reserved_37[0x8]; u8 log_bf_reg_size[0x5]; - u8 reserved_34[0x10]; + u8 reserved_38[0x10]; - u8 reserved_35[0x10]; + u8 reserved_39[0x10]; u8 max_wqe_sz_sq[0x10]; - u8 reserved_36[0x10]; + u8 reserved_40[0x10]; u8 max_wqe_sz_rq[0x10]; - u8 reserved_37[0x10]; + u8 reserved_41[0x10]; u8 max_wqe_sz_sq_dc[0x10]; - u8 reserved_38[0x7]; + u8 reserved_42[0x7]; u8 max_qp_mcg[0x19]; - u8 reserved_39[0x18]; + u8 reserved_43[0x18]; u8 log_max_mcg[0x8]; - u8 reserved_40[0xb]; + u8 reserved_44[0x3]; + u8 log_max_transport_domain[0x5]; + u8 reserved_45[0x3]; u8 log_max_pd[0x5]; - u8 reserved_41[0xb]; + u8 reserved_46[0xb]; u8 log_max_xrcd[0x5]; - u8 reserved_42[0x20]; + u8 reserved_47[0x20]; - u8 reserved_43[0x3]; + u8 reserved_48[0x3]; u8 log_max_rq[0x5]; - u8 reserved_44[0x3]; + u8 reserved_49[0x3]; u8 log_max_sq[0x5]; - u8 reserved_45[0x3]; + u8 reserved_50[0x3]; u8 log_max_tir[0x5]; - u8 reserved_46[0x3]; + u8 reserved_51[0x3]; u8 log_max_tis[0x5]; - u8 reserved_47[0x13]; - u8 log_max_rq_per_tir[0x5]; - u8 reserved_48[0x3]; + u8 basic_cyclic_rcv_wqe[0x1]; + u8 reserved_52[0x2]; + u8 log_max_rmp[0x5]; + u8 reserved_53[0x3]; + u8 log_max_rqt[0x5]; + u8 reserved_54[0x3]; + u8 log_max_rqt_size[0x5]; + u8 reserved_55[0x3]; u8 log_max_tis_per_sq[0x5]; - u8 reserved_49[0xe0]; + u8 reserved_56[0x3]; + u8 log_max_stride_sz_rq[0x5]; + u8 reserved_57[0x3]; + u8 log_min_stride_sz_rq[0x5]; + u8 reserved_58[0x3]; + u8 log_max_stride_sz_sq[0x5]; + u8 reserved_59[0x3]; + u8 log_min_stride_sz_sq[0x5]; - u8 reserved_50[0x10]; + u8 reserved_60[0x1b]; + u8 log_max_wq_sz[0x5]; + + u8 reserved_61[0xa0]; + + u8 reserved_62[0x3]; + u8 log_max_l2_table[0x5]; + u8 reserved_63[0x8]; u8 log_uar_page_sz[0x10]; - u8 reserved_51[0x100]; + u8 reserved_64[0x100]; - u8 reserved_52[0x1f]; + u8 reserved_65[0x1f]; u8 cqe_zip[0x1]; u8 cqe_zip_timeout[0x10]; u8 cqe_zip_max_num[0x10]; - u8 reserved_53[0x220]; + u8 reserved_66[0x220]; +}; + +enum { + MLX5_DEST_FORMAT_STRUCT_DESTINATION_TYPE_FLOW_TABLE_ = 0x1, + MLX5_DEST_FORMAT_STRUCT_DESTINATION_TYPE_TIR = 0x2, +}; + +struct mlx5_ifc_dest_format_struct_bits { + u8 destination_type[0x8]; + u8 destination_id[0x18]; + + u8 reserved_0[0x20]; +}; + +struct mlx5_ifc_fte_match_param_bits { + struct mlx5_ifc_fte_match_set_lyr_2_4_bits outer_headers; + + struct mlx5_ifc_fte_match_set_misc_bits misc_parameters; + + struct mlx5_ifc_fte_match_set_lyr_2_4_bits inner_headers; + + u8 reserved_0[0xa00]; +}; + +enum { + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_SRC_IP = 0x0, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_DST_IP = 0x1, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_L4_SPORT = 0x2, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_L4_DPORT = 0x3, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_IPSEC_SPI = 0x4, +}; + +struct mlx5_ifc_rx_hash_field_select_bits { + u8 l3_prot_type[0x1]; + u8 l4_prot_type[0x1]; + u8 selected_fields[0x1e]; +}; + +enum { + MLX5_WQ_WQ_TYPE_WQ_LINKED_LIST = 0x0, + MLX5_WQ_WQ_TYPE_WQ_CYCLIC = 0x1, +}; + +enum { + MLX5_WQ_END_PADDING_MODE_END_PAD_NONE = 0x0, + MLX5_WQ_END_PADDING_MODE_END_PAD_ALIGN = 0x1, +}; + +struct mlx5_ifc_wq_bits { + u8 wq_type[0x4]; + u8 wq_signature[0x1]; + u8 end_padding_mode[0x2]; + u8 cd_slave[0x1]; + u8 reserved_0[0x18]; + + u8 hds_skip_first_sge[0x1]; + u8 log2_hds_buf_size[0x3]; + u8 reserved_1[0x7]; + u8 page_offset[0x5]; + u8 lwm[0x10]; + + u8 reserved_2[0x8]; + u8 pd[0x18]; + + u8 reserved_3[0x8]; + u8 uar_page[0x18]; + + u8 dbr_addr[0x40]; + + u8 hw_counter[0x20]; + + u8 sw_counter[0x20]; + + u8 reserved_4[0xc]; + u8 log_wq_stride[0x4]; + u8 reserved_5[0x3]; + u8 log_wq_pg_sz[0x5]; + u8 reserved_6[0x3]; + u8 log_wq_sz[0x5]; + + u8 reserved_7[0x4e0]; + + struct mlx5_ifc_cmd_pas_bits pas[0]; +}; + +struct mlx5_ifc_rq_num_bits { + u8 reserved_0[0x8]; + u8 rq_num[0x18]; +}; + +struct mlx5_ifc_mac_address_layout_bits { + u8 reserved_0[0x10]; + u8 mac_addr_47_32[0x10]; + + u8 mac_addr_31_0[0x20]; +}; + +struct mlx5_ifc_cong_control_r_roce_ecn_np_bits { + u8 reserved_0[0xa0]; + + u8 min_time_between_cnps[0x20]; + + u8 reserved_1[0x12]; + u8 cnp_dscp[0x6]; + u8 reserved_2[0x5]; + u8 cnp_802p_prio[0x3]; + + u8 reserved_3[0x720]; +}; + +struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits { + u8 reserved_0[0x60]; + + u8 reserved_1[0x4]; + u8 clamp_tgt_rate[0x1]; + u8 reserved_2[0x3]; + u8 clamp_tgt_rate_after_time_inc[0x1]; + u8 reserved_3[0x17]; + + u8 reserved_4[0x20]; + + u8 rpg_time_reset[0x20]; + + u8 rpg_byte_reset[0x20]; + + u8 rpg_threshold[0x20]; + + u8 rpg_max_rate[0x20]; + + u8 rpg_ai_rate[0x20]; + + u8 rpg_hai_rate[0x20]; + + u8 rpg_gd[0x20]; + + u8 rpg_min_dec_fac[0x20]; + + u8 rpg_min_rate[0x20]; + + u8 reserved_5[0xe0]; + + u8 rate_to_set_on_first_cnp[0x20]; + + u8 dce_tcp_g[0x20]; + + u8 dce_tcp_rtt[0x20]; + + u8 rate_reduce_monitor_period[0x20]; + + u8 reserved_6[0x20]; + + u8 initial_alpha_value[0x20]; + + u8 reserved_7[0x4a0]; +}; + +struct mlx5_ifc_cong_control_802_1qau_rp_bits { + u8 reserved_0[0x80]; + + u8 rppp_max_rps[0x20]; + + u8 rpg_time_reset[0x20]; + + u8 rpg_byte_reset[0x20]; + + u8 rpg_threshold[0x20]; + + u8 rpg_max_rate[0x20]; + + u8 rpg_ai_rate[0x20]; + + u8 rpg_hai_rate[0x20]; + + u8 rpg_gd[0x20]; + + u8 rpg_min_dec_fac[0x20]; + + u8 rpg_min_rate[0x20]; + + u8 reserved_1[0x640]; +}; + +enum { + MLX5_RESIZE_FIELD_SELECT_RESIZE_FIELD_SELECT_LOG_CQ_SIZE = 0x1, + MLX5_RESIZE_FIELD_SELECT_RESIZE_FIELD_SELECT_PAGE_OFFSET = 0x2, + MLX5_RESIZE_FIELD_SELECT_RESIZE_FIELD_SELECT_LOG_PAGE_SIZE = 0x4, +}; + +struct mlx5_ifc_resize_field_select_bits { + u8 resize_field_select[0x20]; +}; + +enum { + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_CQ_PERIOD = 0x1, + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_CQ_MAX_COUNT = 0x2, + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_OI = 0x4, + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_C_EQN = 0x8, +}; + +struct mlx5_ifc_modify_field_select_bits { + u8 modify_field_select[0x20]; +}; + +struct mlx5_ifc_field_select_r_roce_np_bits { + u8 field_select_r_roce_np[0x20]; +}; + +struct mlx5_ifc_field_select_r_roce_rp_bits { + u8 field_select_r_roce_rp[0x20]; +}; + +enum { + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPPP_MAX_RPS = 0x4, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_TIME_RESET = 0x8, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_BYTE_RESET = 0x10, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_THRESHOLD = 0x20, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_MAX_RATE = 0x40, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_AI_RATE = 0x80, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_HAI_RATE = 0x100, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_GD = 0x200, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_MIN_DEC_FAC = 0x400, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_MIN_RATE = 0x800, +}; + +struct mlx5_ifc_field_select_802_1qau_rp_bits { + u8 field_select_8021qaurp[0x20]; +}; + +struct mlx5_ifc_phys_layer_cntrs_bits { + u8 time_since_last_clear_high[0x20]; + + u8 time_since_last_clear_low[0x20]; + + u8 symbol_errors_high[0x20]; + + u8 symbol_errors_low[0x20]; + + u8 sync_headers_errors_high[0x20]; + + u8 sync_headers_errors_low[0x20]; + + u8 edpl_bip_errors_lane0_high[0x20]; + + u8 edpl_bip_errors_lane0_low[0x20]; + + u8 edpl_bip_errors_lane1_high[0x20]; + + u8 edpl_bip_errors_lane1_low[0x20]; + + u8 edpl_bip_errors_lane2_high[0x20]; + + u8 edpl_bip_errors_lane2_low[0x20]; + + u8 edpl_bip_errors_lane3_high[0x20]; + + u8 edpl_bip_errors_lane3_low[0x20]; + + u8 fc_fec_corrected_blocks_lane0_high[0x20]; + + u8 fc_fec_corrected_blocks_lane0_low[0x20]; + + u8 fc_fec_corrected_blocks_lane1_high[0x20]; + + u8 fc_fec_corrected_blocks_lane1_low[0x20]; + + u8 fc_fec_corrected_blocks_lane2_high[0x20]; + + u8 fc_fec_corrected_blocks_lane2_low[0x20]; + + u8 fc_fec_corrected_blocks_lane3_high[0x20]; + + u8 fc_fec_corrected_blocks_lane3_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane0_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane0_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane1_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane1_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane2_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane2_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane3_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane3_low[0x20]; + + u8 rs_fec_corrected_blocks_high[0x20]; + + u8 rs_fec_corrected_blocks_low[0x20]; + + u8 rs_fec_uncorrectable_blocks_high[0x20]; + + u8 rs_fec_uncorrectable_blocks_low[0x20]; + + u8 rs_fec_no_errors_blocks_high[0x20]; + + u8 rs_fec_no_errors_blocks_low[0x20]; + + u8 rs_fec_single_error_blocks_high[0x20]; + + u8 rs_fec_single_error_blocks_low[0x20]; + + u8 rs_fec_corrected_symbols_total_high[0x20]; + + u8 rs_fec_corrected_symbols_total_low[0x20]; + + u8 rs_fec_corrected_symbols_lane0_high[0x20]; + + u8 rs_fec_corrected_symbols_lane0_low[0x20]; + + u8 rs_fec_corrected_symbols_lane1_high[0x20]; + + u8 rs_fec_corrected_symbols_lane1_low[0x20]; + + u8 rs_fec_corrected_symbols_lane2_high[0x20]; + + u8 rs_fec_corrected_symbols_lane2_low[0x20]; + + u8 rs_fec_corrected_symbols_lane3_high[0x20]; + + u8 rs_fec_corrected_symbols_lane3_low[0x20]; + + u8 link_down_events[0x20]; + + u8 successful_recovery_events[0x20]; + + u8 reserved_0[0x180]; +}; + +struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { + u8 transmit_queue_high[0x20]; + + u8 transmit_queue_low[0x20]; + + u8 reserved_0[0x780]; +}; + +struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { + u8 rx_octets_high[0x20]; + + u8 rx_octets_low[0x20]; + + u8 reserved_0[0xc0]; + + u8 rx_frames_high[0x20]; + + u8 rx_frames_low[0x20]; + + u8 tx_octets_high[0x20]; + + u8 tx_octets_low[0x20]; + + u8 reserved_1[0xc0]; + + u8 tx_frames_high[0x20]; + + u8 tx_frames_low[0x20]; + + u8 rx_pause_high[0x20]; + + u8 rx_pause_low[0x20]; + + u8 rx_pause_duration_high[0x20]; + + u8 rx_pause_duration_low[0x20]; + + u8 tx_pause_high[0x20]; + + u8 tx_pause_low[0x20]; + + u8 tx_pause_duration_high[0x20]; + + u8 tx_pause_duration_low[0x20]; + + u8 rx_pause_transition_high[0x20]; + + u8 rx_pause_transition_low[0x20]; + + u8 reserved_2[0x400]; +}; + +struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { + u8 port_transmit_wait_high[0x20]; + + u8 port_transmit_wait_low[0x20]; + + u8 reserved_0[0x780]; +}; + +struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { + u8 dot3stats_alignment_errors_high[0x20]; + + u8 dot3stats_alignment_errors_low[0x20]; + + u8 dot3stats_fcs_errors_high[0x20]; + + u8 dot3stats_fcs_errors_low[0x20]; + + u8 dot3stats_single_collision_frames_high[0x20]; + + u8 dot3stats_single_collision_frames_low[0x20]; + + u8 dot3stats_multiple_collision_frames_high[0x20]; + + u8 dot3stats_multiple_collision_frames_low[0x20]; + + u8 dot3stats_sqe_test_errors_high[0x20]; + + u8 dot3stats_sqe_test_errors_low[0x20]; + + u8 dot3stats_deferred_transmissions_high[0x20]; + + u8 dot3stats_deferred_transmissions_low[0x20]; + + u8 dot3stats_late_collisions_high[0x20]; + + u8 dot3stats_late_collisions_low[0x20]; + + u8 dot3stats_excessive_collisions_high[0x20]; + + u8 dot3stats_excessive_collisions_low[0x20]; + + u8 dot3stats_internal_mac_transmit_errors_high[0x20]; + + u8 dot3stats_internal_mac_transmit_errors_low[0x20]; + + u8 dot3stats_carrier_sense_errors_high[0x20]; + + u8 dot3stats_carrier_sense_errors_low[0x20]; + + u8 dot3stats_frame_too_longs_high[0x20]; + + u8 dot3stats_frame_too_longs_low[0x20]; + + u8 dot3stats_internal_mac_receive_errors_high[0x20]; + + u8 dot3stats_internal_mac_receive_errors_low[0x20]; + + u8 dot3stats_symbol_errors_high[0x20]; + + u8 dot3stats_symbol_errors_low[0x20]; + + u8 dot3control_in_unknown_opcodes_high[0x20]; + + u8 dot3control_in_unknown_opcodes_low[0x20]; + + u8 dot3in_pause_frames_high[0x20]; + + u8 dot3in_pause_frames_low[0x20]; + + u8 dot3out_pause_frames_high[0x20]; + + u8 dot3out_pause_frames_low[0x20]; + + u8 reserved_0[0x3c0]; +}; + +struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits { + u8 ether_stats_drop_events_high[0x20]; + + u8 ether_stats_drop_events_low[0x20]; + + u8 ether_stats_octets_high[0x20]; + + u8 ether_stats_octets_low[0x20]; + + u8 ether_stats_pkts_high[0x20]; + + u8 ether_stats_pkts_low[0x20]; + + u8 ether_stats_broadcast_pkts_high[0x20]; + + u8 ether_stats_broadcast_pkts_low[0x20]; + + u8 ether_stats_multicast_pkts_high[0x20]; + + u8 ether_stats_multicast_pkts_low[0x20]; + + u8 ether_stats_crc_align_errors_high[0x20]; + + u8 ether_stats_crc_align_errors_low[0x20]; + + u8 ether_stats_undersize_pkts_high[0x20]; + + u8 ether_stats_undersize_pkts_low[0x20]; + + u8 ether_stats_oversize_pkts_high[0x20]; + + u8 ether_stats_oversize_pkts_low[0x20]; + + u8 ether_stats_fragments_high[0x20]; + + u8 ether_stats_fragments_low[0x20]; + + u8 ether_stats_jabbers_high[0x20]; + + u8 ether_stats_jabbers_low[0x20]; + + u8 ether_stats_collisions_high[0x20]; + + u8 ether_stats_collisions_low[0x20]; + + u8 ether_stats_pkts64octets_high[0x20]; + + u8 ether_stats_pkts64octets_low[0x20]; + + u8 ether_stats_pkts65to127octets_high[0x20]; + + u8 ether_stats_pkts65to127octets_low[0x20]; + + u8 ether_stats_pkts128to255octets_high[0x20]; + + u8 ether_stats_pkts128to255octets_low[0x20]; + + u8 ether_stats_pkts256to511octets_high[0x20]; + + u8 ether_stats_pkts256to511octets_low[0x20]; + + u8 ether_stats_pkts512to1023octets_high[0x20]; + + u8 ether_stats_pkts512to1023octets_low[0x20]; + + u8 ether_stats_pkts1024to1518octets_high[0x20]; + + u8 ether_stats_pkts1024to1518octets_low[0x20]; + + u8 ether_stats_pkts1519to2047octets_high[0x20]; + + u8 ether_stats_pkts1519to2047octets_low[0x20]; + + u8 ether_stats_pkts2048to4095octets_high[0x20]; + + u8 ether_stats_pkts2048to4095octets_low[0x20]; + + u8 ether_stats_pkts4096to8191octets_high[0x20]; + + u8 ether_stats_pkts4096to8191octets_low[0x20]; + + u8 ether_stats_pkts8192to10239octets_high[0x20]; + + u8 ether_stats_pkts8192to10239octets_low[0x20]; + + u8 reserved_0[0x280]; +}; + +struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits { + u8 if_in_octets_high[0x20]; + + u8 if_in_octets_low[0x20]; + + u8 if_in_ucast_pkts_high[0x20]; + + u8 if_in_ucast_pkts_low[0x20]; + + u8 if_in_discards_high[0x20]; + + u8 if_in_discards_low[0x20]; + + u8 if_in_errors_high[0x20]; + + u8 if_in_errors_low[0x20]; + + u8 if_in_unknown_protos_high[0x20]; + + u8 if_in_unknown_protos_low[0x20]; + + u8 if_out_octets_high[0x20]; + + u8 if_out_octets_low[0x20]; + + u8 if_out_ucast_pkts_high[0x20]; + + u8 if_out_ucast_pkts_low[0x20]; + + u8 if_out_discards_high[0x20]; + + u8 if_out_discards_low[0x20]; + + u8 if_out_errors_high[0x20]; + + u8 if_out_errors_low[0x20]; + + u8 if_in_multicast_pkts_high[0x20]; + + u8 if_in_multicast_pkts_low[0x20]; + + u8 if_in_broadcast_pkts_high[0x20]; + + u8 if_in_broadcast_pkts_low[0x20]; + + u8 if_out_multicast_pkts_high[0x20]; + + u8 if_out_multicast_pkts_low[0x20]; + + u8 if_out_broadcast_pkts_high[0x20]; + + u8 if_out_broadcast_pkts_low[0x20]; + + u8 reserved_0[0x480]; +}; + +struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits { + u8 a_frames_transmitted_ok_high[0x20]; + + u8 a_frames_transmitted_ok_low[0x20]; + + u8 a_frames_received_ok_high[0x20]; + + u8 a_frames_received_ok_low[0x20]; + + u8 a_frame_check_sequence_errors_high[0x20]; + + u8 a_frame_check_sequence_errors_low[0x20]; + + u8 a_alignment_errors_high[0x20]; + + u8 a_alignment_errors_low[0x20]; + + u8 a_octets_transmitted_ok_high[0x20]; + + u8 a_octets_transmitted_ok_low[0x20]; + + u8 a_octets_received_ok_high[0x20]; + + u8 a_octets_received_ok_low[0x20]; + + u8 a_multicast_frames_xmitted_ok_high[0x20]; + + u8 a_multicast_frames_xmitted_ok_low[0x20]; + + u8 a_broadcast_frames_xmitted_ok_high[0x20]; + + u8 a_broadcast_frames_xmitted_ok_low[0x20]; + + u8 a_multicast_frames_received_ok_high[0x20]; + + u8 a_multicast_frames_received_ok_low[0x20]; + + u8 a_broadcast_frames_received_ok_high[0x20]; + + u8 a_broadcast_frames_received_ok_low[0x20]; + + u8 a_in_range_length_errors_high[0x20]; + + u8 a_in_range_length_errors_low[0x20]; + + u8 a_out_of_range_length_field_high[0x20]; + + u8 a_out_of_range_length_field_low[0x20]; + + u8 a_frame_too_long_errors_high[0x20]; + + u8 a_frame_too_long_errors_low[0x20]; + + u8 a_symbol_error_during_carrier_high[0x20]; + + u8 a_symbol_error_during_carrier_low[0x20]; + + u8 a_mac_control_frames_transmitted_high[0x20]; + + u8 a_mac_control_frames_transmitted_low[0x20]; + + u8 a_mac_control_frames_received_high[0x20]; + + u8 a_mac_control_frames_received_low[0x20]; + + u8 a_unsupported_opcodes_received_high[0x20]; + + u8 a_unsupported_opcodes_received_low[0x20]; + + u8 a_pause_mac_ctrl_frames_received_high[0x20]; + + u8 a_pause_mac_ctrl_frames_received_low[0x20]; + + u8 a_pause_mac_ctrl_frames_transmitted_high[0x20]; + + u8 a_pause_mac_ctrl_frames_transmitted_low[0x20]; + + u8 reserved_0[0x300]; +}; + +struct mlx5_ifc_cmd_inter_comp_event_bits { + u8 command_completion_vector[0x20]; + + u8 reserved_0[0xc0]; +}; + +struct mlx5_ifc_stall_vl_event_bits { + u8 reserved_0[0x18]; + u8 port_num[0x1]; + u8 reserved_1[0x3]; + u8 vl[0x4]; + + u8 reserved_2[0xa0]; +}; + +struct mlx5_ifc_db_bf_congestion_event_bits { + u8 event_subtype[0x8]; + u8 reserved_0[0x8]; + u8 congestion_level[0x8]; + u8 reserved_1[0x8]; + + u8 reserved_2[0xa0]; +}; + +struct mlx5_ifc_gpio_event_bits { + u8 reserved_0[0x60]; + + u8 gpio_event_hi[0x20]; + + u8 gpio_event_lo[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_port_state_change_event_bits { + u8 reserved_0[0x40]; + + u8 port_num[0x4]; + u8 reserved_1[0x1c]; + + u8 reserved_2[0x80]; +}; + +struct mlx5_ifc_dropped_packet_logged_bits { + u8 reserved_0[0xe0]; +}; + +enum { + MLX5_CQ_ERROR_SYNDROME_CQ_OVERRUN = 0x1, + MLX5_CQ_ERROR_SYNDROME_CQ_ACCESS_VIOLATION_ERROR = 0x2, +}; + +struct mlx5_ifc_cq_error_bits { + u8 reserved_0[0x8]; + u8 cqn[0x18]; + + u8 reserved_1[0x20]; + + u8 reserved_2[0x18]; + u8 syndrome[0x8]; + + u8 reserved_3[0x80]; +}; + +struct mlx5_ifc_rdma_page_fault_event_bits { + u8 bytes_committed[0x20]; + + u8 r_key[0x20]; + + u8 reserved_0[0x10]; + u8 packet_len[0x10]; + + u8 rdma_op_len[0x20]; + + u8 rdma_va[0x40]; + + u8 reserved_1[0x5]; + u8 rdma[0x1]; + u8 write[0x1]; + u8 requestor[0x1]; + u8 qp_number[0x18]; +}; + +struct mlx5_ifc_wqe_associated_page_fault_event_bits { + u8 bytes_committed[0x20]; + + u8 reserved_0[0x10]; + u8 wqe_index[0x10]; + + u8 reserved_1[0x10]; + u8 len[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x5]; + u8 rdma[0x1]; + u8 write_read[0x1]; + u8 requestor[0x1]; + u8 qpn[0x18]; +}; + +struct mlx5_ifc_qp_events_bits { + u8 reserved_0[0xa0]; + + u8 type[0x8]; + u8 reserved_1[0x18]; + + u8 reserved_2[0x8]; + u8 qpn_rqn_sqn[0x18]; +}; + +struct mlx5_ifc_dct_events_bits { + u8 reserved_0[0xc0]; + + u8 reserved_1[0x8]; + u8 dct_number[0x18]; +}; + +struct mlx5_ifc_comp_event_bits { + u8 reserved_0[0xc0]; + + u8 reserved_1[0x8]; + u8 cq_number[0x18]; +}; + +enum { + MLX5_QPC_STATE_RST = 0x0, + MLX5_QPC_STATE_INIT = 0x1, + MLX5_QPC_STATE_RTR = 0x2, + MLX5_QPC_STATE_RTS = 0x3, + MLX5_QPC_STATE_SQER = 0x4, + MLX5_QPC_STATE_ERR = 0x6, + MLX5_QPC_STATE_SQD = 0x7, + MLX5_QPC_STATE_SUSPENDED = 0x9, +}; + +enum { + MLX5_QPC_ST_RC = 0x0, + MLX5_QPC_ST_UC = 0x1, + MLX5_QPC_ST_UD = 0x2, + MLX5_QPC_ST_XRC = 0x3, + MLX5_QPC_ST_DCI = 0x5, + MLX5_QPC_ST_QP0 = 0x7, + MLX5_QPC_ST_QP1 = 0x8, + MLX5_QPC_ST_RAW_DATAGRAM = 0x9, + MLX5_QPC_ST_REG_UMR = 0xc, +}; + +enum { + MLX5_QPC_PM_STATE_ARMED = 0x0, + MLX5_QPC_PM_STATE_REARM = 0x1, + MLX5_QPC_PM_STATE_RESERVED = 0x2, + MLX5_QPC_PM_STATE_MIGRATED = 0x3, +}; + +enum { + MLX5_QPC_END_PADDING_MODE_SCATTER_AS_IS = 0x0, + MLX5_QPC_END_PADDING_MODE_PAD_TO_CACHE_LINE_ALIGNMENT = 0x1, +}; + +enum { + MLX5_QPC_MTU_256_BYTES = 0x1, + MLX5_QPC_MTU_512_BYTES = 0x2, + MLX5_QPC_MTU_1K_BYTES = 0x3, + MLX5_QPC_MTU_2K_BYTES = 0x4, + MLX5_QPC_MTU_4K_BYTES = 0x5, + MLX5_QPC_MTU_RAW_ETHERNET_QP = 0x7, +}; + +enum { + MLX5_QPC_ATOMIC_MODE_IB_SPEC = 0x1, + MLX5_QPC_ATOMIC_MODE_ONLY_8B = 0x2, + MLX5_QPC_ATOMIC_MODE_UP_TO_8B = 0x3, + MLX5_QPC_ATOMIC_MODE_UP_TO_16B = 0x4, + MLX5_QPC_ATOMIC_MODE_UP_TO_32B = 0x5, + MLX5_QPC_ATOMIC_MODE_UP_TO_64B = 0x6, + MLX5_QPC_ATOMIC_MODE_UP_TO_128B = 0x7, + MLX5_QPC_ATOMIC_MODE_UP_TO_256B = 0x8, +}; + +enum { + MLX5_QPC_CS_REQ_DISABLE = 0x0, + MLX5_QPC_CS_REQ_UP_TO_32B = 0x11, + MLX5_QPC_CS_REQ_UP_TO_64B = 0x22, +}; + +enum { + MLX5_QPC_CS_RES_DISABLE = 0x0, + MLX5_QPC_CS_RES_UP_TO_32B = 0x1, + MLX5_QPC_CS_RES_UP_TO_64B = 0x2, +}; + +struct mlx5_ifc_qpc_bits { + u8 state[0x4]; + u8 reserved_0[0x4]; + u8 st[0x8]; + u8 reserved_1[0x3]; + u8 pm_state[0x2]; + u8 reserved_2[0x7]; + u8 end_padding_mode[0x2]; + u8 reserved_3[0x2]; + + u8 wq_signature[0x1]; + u8 block_lb_mc[0x1]; + u8 atomic_like_write_en[0x1]; + u8 latency_sensitive[0x1]; + u8 reserved_4[0x1]; + u8 drain_sigerr[0x1]; + u8 reserved_5[0x2]; + u8 pd[0x18]; + + u8 mtu[0x3]; + u8 log_msg_max[0x5]; + u8 reserved_6[0x1]; + u8 log_rq_size[0x4]; + u8 log_rq_stride[0x3]; + u8 no_sq[0x1]; + u8 log_sq_size[0x4]; + u8 reserved_7[0x6]; + u8 rlky[0x1]; + u8 reserved_8[0x4]; + + u8 counter_set_id[0x8]; + u8 uar_page[0x18]; + + u8 reserved_9[0x8]; + u8 user_index[0x18]; + + u8 reserved_10[0x3]; + u8 log_page_size[0x5]; + u8 remote_qpn[0x18]; + + struct mlx5_ifc_ads_bits primary_address_path; + + struct mlx5_ifc_ads_bits secondary_address_path; + + u8 log_ack_req_freq[0x4]; + u8 reserved_11[0x4]; + u8 log_sra_max[0x3]; + u8 reserved_12[0x2]; + u8 retry_count[0x3]; + u8 rnr_retry[0x3]; + u8 reserved_13[0x1]; + u8 fre[0x1]; + u8 cur_rnr_retry[0x3]; + u8 cur_retry_count[0x3]; + u8 reserved_14[0x5]; + + u8 reserved_15[0x20]; + + u8 reserved_16[0x8]; + u8 next_send_psn[0x18]; + + u8 reserved_17[0x8]; + u8 cqn_snd[0x18]; + + u8 reserved_18[0x40]; + + u8 reserved_19[0x8]; + u8 last_acked_psn[0x18]; + + u8 reserved_20[0x8]; + u8 ssn[0x18]; + + u8 reserved_21[0x8]; + u8 log_rra_max[0x3]; + u8 reserved_22[0x1]; + u8 atomic_mode[0x4]; + u8 rre[0x1]; + u8 rwe[0x1]; + u8 rae[0x1]; + u8 reserved_23[0x1]; + u8 page_offset[0x6]; + u8 reserved_24[0x3]; + u8 cd_slave_receive[0x1]; + u8 cd_slave_send[0x1]; + u8 cd_master[0x1]; + + u8 reserved_25[0x3]; + u8 min_rnr_nak[0x5]; + u8 next_rcv_psn[0x18]; + + u8 reserved_26[0x8]; + u8 xrcd[0x18]; + + u8 reserved_27[0x8]; + u8 cqn_rcv[0x18]; + + u8 dbr_addr[0x40]; + + u8 q_key[0x20]; + + u8 reserved_28[0x5]; + u8 rq_type[0x3]; + u8 srqn_rmpn[0x18]; + + u8 reserved_29[0x8]; + u8 rmsn[0x18]; + + u8 hw_sq_wqebb_counter[0x10]; + u8 sw_sq_wqebb_counter[0x10]; + + u8 hw_rq_counter[0x20]; + + u8 sw_rq_counter[0x20]; + + u8 reserved_30[0x20]; + + u8 reserved_31[0xf]; + u8 cgs[0x1]; + u8 cs_req[0x8]; + u8 cs_res[0x8]; + + u8 dc_access_key[0x40]; + + u8 reserved_32[0xc0]; +}; + +struct mlx5_ifc_roce_addr_layout_bits { + u8 source_l3_address[16][0x8]; + + u8 reserved_0[0x3]; + u8 vlan_valid[0x1]; + u8 vlan_id[0xc]; + u8 source_mac_47_32[0x10]; + + u8 source_mac_31_0[0x20]; + + u8 reserved_1[0x14]; + u8 roce_l3_type[0x4]; + u8 roce_version[0x8]; + + u8 reserved_2[0x20]; +}; + +union mlx5_ifc_hca_cap_union_bits { + struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; + struct mlx5_ifc_odp_cap_bits odp_cap; + struct mlx5_ifc_atomic_caps_bits atomic_caps; + struct mlx5_ifc_roce_cap_bits roce_cap; + struct mlx5_ifc_per_protocol_networking_offload_caps_bits per_protocol_networking_offload_caps; + struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; + u8 reserved_0[0x8000]; +}; + +enum { + MLX5_FLOW_CONTEXT_ACTION_ALLOW = 0x1, + MLX5_FLOW_CONTEXT_ACTION_DROP = 0x2, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST = 0x4, +}; + +struct mlx5_ifc_flow_context_bits { + u8 reserved_0[0x20]; + + u8 group_id[0x20]; + + u8 reserved_1[0x8]; + u8 flow_tag[0x18]; + + u8 reserved_2[0x10]; + u8 action[0x10]; + + u8 reserved_3[0x8]; + u8 destination_list_size[0x18]; + + u8 reserved_4[0x160]; + + struct mlx5_ifc_fte_match_param_bits match_value; + + u8 reserved_5[0x600]; + + struct mlx5_ifc_dest_format_struct_bits destination[0]; +}; + +enum { + MLX5_XRC_SRQC_STATE_GOOD = 0x0, + MLX5_XRC_SRQC_STATE_ERROR = 0x1, +}; + +struct mlx5_ifc_xrc_srqc_bits { + u8 state[0x4]; + u8 log_xrc_srq_size[0x4]; + u8 reserved_0[0x18]; + + u8 wq_signature[0x1]; + u8 cont_srq[0x1]; + u8 reserved_1[0x1]; + u8 rlky[0x1]; + u8 basic_cyclic_rcv_wqe[0x1]; + u8 log_rq_stride[0x3]; + u8 xrcd[0x18]; + + u8 page_offset[0x6]; + u8 reserved_2[0x2]; + u8 cqn[0x18]; + + u8 reserved_3[0x20]; + + u8 user_index_equal_xrc_srqn[0x1]; + u8 reserved_4[0x1]; + u8 log_page_size[0x6]; + u8 user_index[0x18]; + + u8 reserved_5[0x20]; + + u8 reserved_6[0x8]; + u8 pd[0x18]; + + u8 lwm[0x10]; + u8 wqe_cnt[0x10]; + + u8 reserved_7[0x40]; + + u8 db_record_addr_h[0x20]; + + u8 db_record_addr_l[0x1e]; + u8 reserved_8[0x2]; + + u8 reserved_9[0x80]; +}; + +struct mlx5_ifc_traffic_counter_bits { + u8 packets[0x40]; + + u8 octets[0x40]; +}; + +struct mlx5_ifc_tisc_bits { + u8 reserved_0[0xc]; + u8 prio[0x4]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x100]; + + u8 reserved_3[0x8]; + u8 transport_domain[0x18]; + + u8 reserved_4[0x3c0]; +}; + +enum { + MLX5_TIRC_DISP_TYPE_DIRECT = 0x0, + MLX5_TIRC_DISP_TYPE_INDIRECT = 0x1, +}; + +enum { + MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO = 0x1, + MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO = 0x2, +}; + +enum { + MLX5_TIRC_RX_HASH_FN_HASH_NONE = 0x0, + MLX5_TIRC_RX_HASH_FN_HASH_INVERTED_XOR8 = 0x1, + MLX5_TIRC_RX_HASH_FN_HASH_TOEPLITZ = 0x2, +}; + +enum { + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_ = 0x1, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST_ = 0x2, +}; + +struct mlx5_ifc_tirc_bits { + u8 reserved_0[0x20]; + + u8 disp_type[0x4]; + u8 reserved_1[0x1c]; + + u8 reserved_2[0x40]; + + u8 reserved_3[0x4]; + u8 lro_timeout_period_usecs[0x10]; + u8 lro_enable_mask[0x4]; + u8 lro_max_ip_payload_size[0x8]; + + u8 reserved_4[0x40]; + + u8 reserved_5[0x8]; + u8 inline_rqn[0x18]; + + u8 rx_hash_symmetric[0x1]; + u8 reserved_6[0x1]; + u8 tunneled_offload_en[0x1]; + u8 reserved_7[0x5]; + u8 indirect_table[0x18]; + + u8 rx_hash_fn[0x4]; + u8 reserved_8[0x2]; + u8 self_lb_block[0x2]; + u8 transport_domain[0x18]; + + u8 rx_hash_toeplitz_key[10][0x20]; + + struct mlx5_ifc_rx_hash_field_select_bits rx_hash_field_selector_outer; + + struct mlx5_ifc_rx_hash_field_select_bits rx_hash_field_selector_inner; + + u8 reserved_9[0x4c0]; +}; + +enum { + MLX5_SRQC_STATE_GOOD = 0x0, + MLX5_SRQC_STATE_ERROR = 0x1, +}; + +struct mlx5_ifc_srqc_bits { + u8 state[0x4]; + u8 log_srq_size[0x4]; + u8 reserved_0[0x18]; + + u8 wq_signature[0x1]; + u8 cont_srq[0x1]; + u8 reserved_1[0x1]; + u8 rlky[0x1]; + u8 reserved_2[0x1]; + u8 log_rq_stride[0x3]; + u8 xrcd[0x18]; + + u8 page_offset[0x6]; + u8 reserved_3[0x2]; + u8 cqn[0x18]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x2]; + u8 log_page_size[0x6]; + u8 reserved_6[0x18]; + + u8 reserved_7[0x20]; + + u8 reserved_8[0x8]; + u8 pd[0x18]; + + u8 lwm[0x10]; + u8 wqe_cnt[0x10]; + + u8 reserved_9[0x40]; + + u8 db_record_addr_h[0x20]; + + u8 db_record_addr_l[0x1e]; + u8 reserved_10[0x2]; + + u8 reserved_11[0x80]; +}; + +enum { + MLX5_SQC_STATE_RST = 0x0, + MLX5_SQC_STATE_RDY = 0x1, + MLX5_SQC_STATE_ERR = 0x3, +}; + +struct mlx5_ifc_sqc_bits { + u8 rlky[0x1]; + u8 cd_master[0x1]; + u8 fre[0x1]; + u8 flush_in_error_en[0x1]; + u8 reserved_0[0x4]; + u8 state[0x4]; + u8 reserved_1[0x14]; + + u8 reserved_2[0x8]; + u8 user_index[0x18]; + + u8 reserved_3[0x8]; + u8 cqn[0x18]; + + u8 reserved_4[0xa0]; + + u8 tis_lst_sz[0x10]; + u8 reserved_5[0x10]; + + u8 reserved_6[0x40]; + + u8 reserved_7[0x8]; + u8 tis_num_0[0x18]; + + struct mlx5_ifc_wq_bits wq; +}; + +struct mlx5_ifc_rqtc_bits { + u8 reserved_0[0xa0]; + + u8 reserved_1[0x10]; + u8 rqt_max_size[0x10]; + + u8 reserved_2[0x10]; + u8 rqt_actual_size[0x10]; + + u8 reserved_3[0x6a0]; + + struct mlx5_ifc_rq_num_bits rq_num[0]; +}; + +enum { + MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_INLINE = 0x0, + MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_RMP = 0x1, +}; + +enum { + MLX5_RQC_STATE_RST = 0x0, + MLX5_RQC_STATE_RDY = 0x1, + MLX5_RQC_STATE_ERR = 0x3, +}; + +struct mlx5_ifc_rqc_bits { + u8 rlky[0x1]; + u8 reserved_0[0x2]; + u8 vsd[0x1]; + u8 mem_rq_type[0x4]; + u8 state[0x4]; + u8 reserved_1[0x1]; + u8 flush_in_error_en[0x1]; + u8 reserved_2[0x12]; + + u8 reserved_3[0x8]; + u8 user_index[0x18]; + + u8 reserved_4[0x8]; + u8 cqn[0x18]; + + u8 counter_set_id[0x8]; + u8 reserved_5[0x18]; + + u8 reserved_6[0x8]; + u8 rmpn[0x18]; + + u8 reserved_7[0xe0]; + + struct mlx5_ifc_wq_bits wq; +}; + +enum { + MLX5_RMPC_STATE_RDY = 0x1, + MLX5_RMPC_STATE_ERR = 0x3, +}; + +struct mlx5_ifc_rmpc_bits { + u8 reserved_0[0x8]; + u8 state[0x4]; + u8 reserved_1[0x14]; + + u8 basic_cyclic_rcv_wqe[0x1]; + u8 reserved_2[0x1f]; + + u8 reserved_3[0x140]; + + struct mlx5_ifc_wq_bits wq; +}; + +enum { + MLX5_NIC_VPORT_CONTEXT_ALLOWED_LIST_TYPE_CURRENT_UC_MAC_ADDRESS = 0x0, +}; + +struct mlx5_ifc_nic_vport_context_bits { + u8 reserved_0[0x1f]; + u8 roce_en[0x1]; + + u8 reserved_1[0x760]; + + u8 reserved_2[0x5]; + u8 allowed_list_type[0x3]; + u8 reserved_3[0xc]; + u8 allowed_list_size[0xc]; + + struct mlx5_ifc_mac_address_layout_bits permanent_address; + + u8 reserved_4[0x20]; + + u8 current_uc_mac_address[0][0x40]; +}; + +enum { + MLX5_MKC_ACCESS_MODE_PA = 0x0, + MLX5_MKC_ACCESS_MODE_MTT = 0x1, + MLX5_MKC_ACCESS_MODE_KLMS = 0x2, +}; + +struct mlx5_ifc_mkc_bits { + u8 reserved_0[0x1]; + u8 free[0x1]; + u8 reserved_1[0xd]; + u8 small_fence_on_rdma_read_response[0x1]; + u8 umr_en[0x1]; + u8 a[0x1]; + u8 rw[0x1]; + u8 rr[0x1]; + u8 lw[0x1]; + u8 lr[0x1]; + u8 access_mode[0x2]; + u8 reserved_2[0x8]; + + u8 qpn[0x18]; + u8 mkey_7_0[0x8]; + + u8 reserved_3[0x20]; + + u8 length64[0x1]; + u8 bsf_en[0x1]; + u8 sync_umr[0x1]; + u8 reserved_4[0x2]; + u8 expected_sigerr_count[0x1]; + u8 reserved_5[0x1]; + u8 en_rinval[0x1]; + u8 pd[0x18]; + + u8 start_addr[0x40]; + + u8 len[0x40]; + + u8 bsf_octword_size[0x20]; + + u8 reserved_6[0x80]; + + u8 translations_octword_size[0x20]; + + u8 reserved_7[0x1b]; + u8 log_page_size[0x5]; + + u8 reserved_8[0x20]; +}; + +struct mlx5_ifc_pkey_bits { + u8 reserved_0[0x10]; + u8 pkey[0x10]; +}; + +struct mlx5_ifc_array128_auto_bits { + u8 array128_auto[16][0x8]; +}; + +struct mlx5_ifc_hca_vport_context_bits { + u8 field_select[0x20]; + + u8 reserved_0[0xe0]; + + u8 sm_virt_aware[0x1]; + u8 has_smi[0x1]; + u8 has_raw[0x1]; + u8 grh_required[0x1]; + u8 reserved_1[0x10]; + u8 port_state_policy[0x4]; + u8 phy_port_state[0x4]; + u8 vport_state[0x4]; + + u8 reserved_2[0x60]; + + u8 port_guid[0x40]; + + u8 node_guid[0x40]; + + u8 cap_mask1[0x20]; + + u8 cap_mask1_field_select[0x20]; + + u8 cap_mask2[0x20]; + + u8 cap_mask2_field_select[0x20]; + + u8 reserved_3[0x80]; + + u8 lid[0x10]; + u8 reserved_4[0x4]; + u8 init_type_reply[0x4]; + u8 lmc[0x3]; + u8 subnet_timeout[0x5]; + + u8 sm_lid[0x10]; + u8 sm_sl[0x4]; + u8 reserved_5[0xc]; + + u8 qkey_violation_counter[0x10]; + u8 pkey_violation_counter[0x10]; + + u8 reserved_6[0xca0]; +}; + +enum { + MLX5_EQC_STATUS_OK = 0x0, + MLX5_EQC_STATUS_EQ_WRITE_FAILURE = 0xa, +}; + +enum { + MLX5_EQC_ST_ARMED = 0x9, + MLX5_EQC_ST_FIRED = 0xa, +}; + +struct mlx5_ifc_eqc_bits { + u8 status[0x4]; + u8 reserved_0[0x9]; + u8 ec[0x1]; + u8 oi[0x1]; + u8 reserved_1[0x5]; + u8 st[0x4]; + u8 reserved_2[0x8]; + + u8 reserved_3[0x20]; + + u8 reserved_4[0x14]; + u8 page_offset[0x6]; + u8 reserved_5[0x6]; + + u8 reserved_6[0x3]; + u8 log_eq_size[0x5]; + u8 uar_page[0x18]; + + u8 reserved_7[0x20]; + + u8 reserved_8[0x18]; + u8 intr[0x8]; + + u8 reserved_9[0x3]; + u8 log_page_size[0x5]; + u8 reserved_10[0x18]; + + u8 reserved_11[0x60]; + + u8 reserved_12[0x8]; + u8 consumer_counter[0x18]; + + u8 reserved_13[0x8]; + u8 producer_counter[0x18]; + + u8 reserved_14[0x80]; +}; + +enum { + MLX5_DCTC_STATE_ACTIVE = 0x0, + MLX5_DCTC_STATE_DRAINING = 0x1, + MLX5_DCTC_STATE_DRAINED = 0x2, +}; + +enum { + MLX5_DCTC_CS_RES_DISABLE = 0x0, + MLX5_DCTC_CS_RES_NA = 0x1, + MLX5_DCTC_CS_RES_UP_TO_64B = 0x2, +}; + +enum { + MLX5_DCTC_MTU_256_BYTES = 0x1, + MLX5_DCTC_MTU_512_BYTES = 0x2, + MLX5_DCTC_MTU_1K_BYTES = 0x3, + MLX5_DCTC_MTU_2K_BYTES = 0x4, + MLX5_DCTC_MTU_4K_BYTES = 0x5, +}; + +struct mlx5_ifc_dctc_bits { + u8 reserved_0[0x4]; + u8 state[0x4]; + u8 reserved_1[0x18]; + + u8 reserved_2[0x8]; + u8 user_index[0x18]; + + u8 reserved_3[0x8]; + u8 cqn[0x18]; + + u8 counter_set_id[0x8]; + u8 atomic_mode[0x4]; + u8 rre[0x1]; + u8 rwe[0x1]; + u8 rae[0x1]; + u8 atomic_like_write_en[0x1]; + u8 latency_sensitive[0x1]; + u8 rlky[0x1]; + u8 free_ar[0x1]; + u8 reserved_4[0xd]; + + u8 reserved_5[0x8]; + u8 cs_res[0x8]; + u8 reserved_6[0x3]; + u8 min_rnr_nak[0x5]; + u8 reserved_7[0x8]; + + u8 reserved_8[0x8]; + u8 srqn[0x18]; + + u8 reserved_9[0x8]; + u8 pd[0x18]; + + u8 tclass[0x8]; + u8 reserved_10[0x4]; + u8 flow_label[0x14]; + + u8 dc_access_key[0x40]; + + u8 reserved_11[0x5]; + u8 mtu[0x3]; + u8 port[0x8]; + u8 pkey_index[0x10]; + + u8 reserved_12[0x8]; + u8 my_addr_index[0x8]; + u8 reserved_13[0x8]; + u8 hop_limit[0x8]; + + u8 dc_access_key_violation_count[0x20]; + + u8 reserved_14[0x14]; + u8 dei_cfi[0x1]; + u8 eth_prio[0x3]; + u8 ecn[0x2]; + u8 dscp[0x6]; + + u8 reserved_15[0x40]; +}; + +enum { + MLX5_CQC_STATUS_OK = 0x0, + MLX5_CQC_STATUS_CQ_OVERFLOW = 0x9, + MLX5_CQC_STATUS_CQ_WRITE_FAIL = 0xa, +}; + +enum { + MLX5_CQC_CQE_SZ_64_BYTES = 0x0, + MLX5_CQC_CQE_SZ_128_BYTES = 0x1, +}; + +enum { + MLX5_CQC_ST_SOLICITED_NOTIFICATION_REQUEST_ARMED = 0x6, + MLX5_CQC_ST_NOTIFICATION_REQUEST_ARMED = 0x9, + MLX5_CQC_ST_FIRED = 0xa, +}; + +struct mlx5_ifc_cqc_bits { + u8 status[0x4]; + u8 reserved_0[0x4]; + u8 cqe_sz[0x3]; + u8 cc[0x1]; + u8 reserved_1[0x1]; + u8 scqe_break_moderation_en[0x1]; + u8 oi[0x1]; + u8 reserved_2[0x2]; + u8 cqe_zip_en[0x1]; + u8 mini_cqe_res_format[0x2]; + u8 st[0x4]; + u8 reserved_3[0x8]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x14]; + u8 page_offset[0x6]; + u8 reserved_6[0x6]; + + u8 reserved_7[0x3]; + u8 log_cq_size[0x5]; + u8 uar_page[0x18]; + + u8 reserved_8[0x4]; + u8 cq_period[0xc]; + u8 cq_max_count[0x10]; + + u8 reserved_9[0x18]; + u8 c_eqn[0x8]; + + u8 reserved_10[0x3]; + u8 log_page_size[0x5]; + u8 reserved_11[0x18]; + + u8 reserved_12[0x20]; + + u8 reserved_13[0x8]; + u8 last_notified_index[0x18]; + + u8 reserved_14[0x8]; + u8 last_solicit_index[0x18]; + + u8 reserved_15[0x8]; + u8 consumer_counter[0x18]; + + u8 reserved_16[0x8]; + u8 producer_counter[0x18]; + + u8 reserved_17[0x40]; + + u8 dbr_addr[0x40]; +}; + +union mlx5_ifc_cong_control_roce_ecn_auto_bits { + struct mlx5_ifc_cong_control_802_1qau_rp_bits cong_control_802_1qau_rp; + struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits cong_control_r_roce_ecn_rp; + struct mlx5_ifc_cong_control_r_roce_ecn_np_bits cong_control_r_roce_ecn_np; + u8 reserved_0[0x800]; +}; + +struct mlx5_ifc_query_adapter_param_block_bits { + u8 reserved_0[0xe0]; + + u8 reserved_1[0x10]; + u8 vsd_vendor_id[0x10]; + + u8 vsd[208][0x8]; + + u8 vsd_contd_psid[16][0x8]; +}; + +union mlx5_ifc_modify_field_select_resize_field_select_auto_bits { + struct mlx5_ifc_modify_field_select_bits modify_field_select; + struct mlx5_ifc_resize_field_select_bits resize_field_select; + u8 reserved_0[0x20]; +}; + +union mlx5_ifc_field_select_802_1_r_roce_auto_bits { + struct mlx5_ifc_field_select_802_1qau_rp_bits field_select_802_1qau_rp; + struct mlx5_ifc_field_select_r_roce_rp_bits field_select_r_roce_rp; + struct mlx5_ifc_field_select_r_roce_np_bits field_select_r_roce_np; + u8 reserved_0[0x20]; +}; + +union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { + struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits eth_802_3_cntrs_grp_data_layout; + struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits eth_2863_cntrs_grp_data_layout; + struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; + struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits eth_3635_cntrs_grp_data_layout; + struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits eth_extended_cntrs_grp_data_layout; + struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; + struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; + struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; + u8 reserved_0[0x7c0]; +}; + +union mlx5_ifc_event_auto_bits { + struct mlx5_ifc_comp_event_bits comp_event; + struct mlx5_ifc_dct_events_bits dct_events; + struct mlx5_ifc_qp_events_bits qp_events; + struct mlx5_ifc_wqe_associated_page_fault_event_bits wqe_associated_page_fault_event; + struct mlx5_ifc_rdma_page_fault_event_bits rdma_page_fault_event; + struct mlx5_ifc_cq_error_bits cq_error; + struct mlx5_ifc_dropped_packet_logged_bits dropped_packet_logged; + struct mlx5_ifc_port_state_change_event_bits port_state_change_event; + struct mlx5_ifc_gpio_event_bits gpio_event; + struct mlx5_ifc_db_bf_congestion_event_bits db_bf_congestion_event; + struct mlx5_ifc_stall_vl_event_bits stall_vl_event; + struct mlx5_ifc_cmd_inter_comp_event_bits cmd_inter_comp_event; + u8 reserved_0[0xe0]; +}; + +struct mlx5_ifc_health_buffer_bits { + u8 reserved_0[0x100]; + + u8 assert_existptr[0x20]; + + u8 assert_callra[0x20]; + + u8 reserved_1[0x40]; + + u8 fw_version[0x20]; + + u8 hw_id[0x20]; + + u8 reserved_2[0x20]; + + u8 irisc_index[0x8]; + u8 synd[0x8]; + u8 ext_synd[0x10]; +}; + +struct mlx5_ifc_register_loopback_control_bits { + u8 no_lb[0x1]; + u8 reserved_0[0x7]; + u8 port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_teardown_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_TEARDOWN_HCA_IN_PROFILE_GRACEFUL_CLOSE = 0x0, + MLX5_TEARDOWN_HCA_IN_PROFILE_PANIC_CLOSE = 0x1, +}; + +struct mlx5_ifc_teardown_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 profile[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_sqerr2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_sqerr2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_sqd2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_sqd2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_set_roce_address_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_roce_address_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 roce_address_index[0x10]; + u8 reserved_2[0x10]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_roce_addr_layout_bits roce_address; +}; + +struct mlx5_ifc_set_mad_demux_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_SET_MAD_DEMUX_IN_DEMUX_MODE_PASS_ALL = 0x0, + MLX5_SET_MAD_DEMUX_IN_DEMUX_MODE_SELECTIVE = 0x2, +}; + +struct mlx5_ifc_set_mad_demux_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x6]; + u8 demux_mode[0x2]; + u8 reserved_4[0x18]; +}; + +struct mlx5_ifc_set_l2_table_entry_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_l2_table_entry_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x8]; + u8 table_index[0x18]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x13]; + u8 vlan_valid[0x1]; + u8 vlan[0xc]; + + struct mlx5_ifc_mac_address_layout_bits mac_address; + + u8 reserved_6[0xc0]; +}; + +struct mlx5_ifc_set_issi_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_issi_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 current_issi[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_set_hca_cap_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; }; struct mlx5_ifc_set_hca_cap_in_bits { @@ -313,10 +2761,653 @@ struct mlx5_ifc_set_hca_cap_in_bits { u8 reserved_2[0x40]; - struct mlx5_ifc_cmd_hca_cap_bits hca_capability_struct; + union mlx5_ifc_hca_cap_union_bits capability; }; -struct mlx5_ifc_query_hca_cap_in_bits { +struct mlx5_ifc_set_fte_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_fte_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x40]; + + u8 flow_index[0x20]; + + u8 reserved_6[0xe0]; + + struct mlx5_ifc_flow_context_bits flow_context; +}; + +struct mlx5_ifc_rts2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rts2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_rtr2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rtr2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_rst2init_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rst2init_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_query_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; + + u8 reserved_2[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +enum { + MLX5_QUERY_VPORT_STATE_OUT_STATE_DOWN = 0x0, + MLX5_QUERY_VPORT_STATE_OUT_STATE_UP = 0x1, +}; + +struct mlx5_ifc_query_vport_state_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 reserved_2[0x18]; + u8 admin_state[0x4]; + u8 state[0x4]; +}; + +enum { + MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT = 0x0, +}; + +struct mlx5_ifc_query_vport_state_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_vport_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_traffic_counter_bits received_errors; + + struct mlx5_ifc_traffic_counter_bits transmit_errors; + + struct mlx5_ifc_traffic_counter_bits received_ib_unicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_ib_unicast; + + struct mlx5_ifc_traffic_counter_bits received_ib_multicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_ib_multicast; + + struct mlx5_ifc_traffic_counter_bits received_eth_broadcast; + + struct mlx5_ifc_traffic_counter_bits transmitted_eth_broadcast; + + struct mlx5_ifc_traffic_counter_bits received_eth_unicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_eth_unicast; + + struct mlx5_ifc_traffic_counter_bits received_eth_multicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_eth_multicast; + + u8 reserved_2[0xa00]; +}; + +enum { + MLX5_QUERY_VPORT_COUNTER_IN_OP_MOD_VPORT_COUNTERS = 0x0, +}; + +struct mlx5_ifc_query_vport_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x60]; + + u8 clear[0x1]; + u8 reserved_4[0x1f]; + + u8 reserved_5[0x20]; +}; + +struct mlx5_ifc_query_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_tisc_bits tis_context; +}; + +struct mlx5_ifc_query_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tisn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_tirc_bits tir_context; +}; + +struct mlx5_ifc_query_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tirn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_srqc_bits srq_context_entry; + + u8 reserved_2[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_sqc_bits sq_context; +}; + +struct mlx5_ifc_query_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 sqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_special_contexts_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 resd_lkey[0x20]; +}; + +struct mlx5_ifc_query_special_contexts_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_query_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_rqtc_bits rqt_context; +}; + +struct mlx5_ifc_query_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqtn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_rqc_bits rq_context; +}; + +struct mlx5_ifc_query_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_roce_address_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_roce_addr_layout_bits roce_address; +}; + +struct mlx5_ifc_query_roce_address_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 roce_address_index[0x10]; + u8 reserved_2[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_rmpc_bits rmp_context; +}; + +struct mlx5_ifc_query_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rmpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 opt_param_mask[0x20]; + + u8 reserved_2[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_3[0x80]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_q_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 rx_write_requests[0x20]; + + u8 reserved_2[0x20]; + + u8 rx_read_requests[0x20]; + + u8 reserved_3[0x20]; + + u8 rx_atomic_requests[0x20]; + + u8 reserved_4[0x20]; + + u8 rx_dct_connect[0x20]; + + u8 reserved_5[0x20]; + + u8 out_of_buffer[0x20]; + + u8 reserved_6[0x20]; + + u8 out_of_sequence[0x20]; + + u8 reserved_7[0x620]; +}; + +struct mlx5_ifc_query_q_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x80]; + + u8 clear[0x1]; + u8 reserved_3[0x1f]; + + u8 reserved_4[0x18]; + u8 counter_set_id[0x8]; +}; + +struct mlx5_ifc_query_pages_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x10]; + u8 function_id[0x10]; + + u8 num_pages[0x20]; +}; + +enum { + MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES = 0x1, + MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES = 0x2, + MLX5_QUERY_PAGES_IN_OP_MOD_REGULAR_PAGES = 0x3, +}; + +struct mlx5_ifc_query_pages_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_nic_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_nic_vport_context_bits nic_vport_context; +}; + +struct mlx5_ifc_query_nic_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x5]; + u8 allowed_list_type[0x3]; + u8 reserved_4[0x18]; +}; + +struct mlx5_ifc_query_mkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_mkc_bits memory_key_mkey_entry; + + u8 reserved_2[0x600]; + + u8 bsf0_klm0_pas_mtt0_1[16][0x8]; + + u8 bsf1_klm1_pas_mtt2_3[16][0x8]; +}; + +struct mlx5_ifc_query_mkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 mkey_index[0x18]; + + u8 pg_access[0x1]; + u8 reserved_3[0x1f]; +}; + +struct mlx5_ifc_query_mad_demux_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 mad_dumux_parameters_block[0x20]; +}; + +struct mlx5_ifc_query_mad_demux_in_bits { u8 opcode[0x10]; u8 reserved_0[0x10]; @@ -326,6 +3417,143 @@ struct mlx5_ifc_query_hca_cap_in_bits { u8 reserved_2[0x40]; }; +struct mlx5_ifc_query_l2_table_entry_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xa0]; + + u8 reserved_2[0x13]; + u8 vlan_valid[0x1]; + u8 vlan[0xc]; + + struct mlx5_ifc_mac_address_layout_bits mac_address; + + u8 reserved_3[0xc0]; +}; + +struct mlx5_ifc_query_l2_table_entry_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x8]; + u8 table_index[0x18]; + + u8 reserved_4[0x140]; +}; + +struct mlx5_ifc_query_issi_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x10]; + u8 current_issi[0x10]; + + u8 reserved_2[0xa0]; + + u8 supported_issi_reserved[76][0x8]; + u8 supported_issi_dw0[0x20]; +}; + +struct mlx5_ifc_query_issi_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_query_hca_vport_pkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_pkey_bits pkey[0]; +}; + +struct mlx5_ifc_query_hca_vport_pkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x10]; + u8 pkey_index[0x10]; +}; + +struct mlx5_ifc_query_hca_vport_gid_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 gids_num[0x10]; + u8 reserved_2[0x10]; + + struct mlx5_ifc_array128_auto_bits gid[0]; +}; + +struct mlx5_ifc_query_hca_vport_gid_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x10]; + u8 gid_index[0x10]; +}; + +struct mlx5_ifc_query_hca_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_hca_vport_context_bits hca_vport_context; +}; + +struct mlx5_ifc_query_hca_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x20]; +}; + struct mlx5_ifc_query_hca_cap_out_bits { u8 status[0x8]; u8 reserved_0[0x18]; @@ -334,16 +3562,3208 @@ struct mlx5_ifc_query_hca_cap_out_bits { u8 reserved_1[0x40]; - u8 capability_struct[256][0x8]; + union mlx5_ifc_hca_cap_union_bits capability; }; -struct mlx5_ifc_set_hca_cap_out_bits { +struct mlx5_ifc_query_hca_cap_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_query_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x80]; + + u8 reserved_2[0x8]; + u8 level[0x8]; + u8 reserved_3[0x8]; + u8 log_size[0x8]; + + u8 reserved_4[0x120]; +}; + +struct mlx5_ifc_query_flow_table_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x140]; +}; + +struct mlx5_ifc_query_fte_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x1c0]; + + struct mlx5_ifc_flow_context_bits flow_context; +}; + +struct mlx5_ifc_query_fte_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x40]; + + u8 flow_index[0x20]; + + u8 reserved_6[0xe0]; +}; + +enum { + MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, + MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, + MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2, +}; + +struct mlx5_ifc_query_flow_group_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xa0]; + + u8 start_flow_index[0x20]; + + u8 reserved_2[0x20]; + + u8 end_flow_index[0x20]; + + u8 reserved_3[0xa0]; + + u8 reserved_4[0x18]; + u8 match_criteria_enable[0x8]; + + struct mlx5_ifc_fte_match_param_bits match_criteria; + + u8 reserved_5[0xe00]; +}; + +struct mlx5_ifc_query_flow_group_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 group_id[0x20]; + + u8 reserved_5[0x120]; +}; + +struct mlx5_ifc_query_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_eqc_bits eq_context_entry; + + u8 reserved_2[0x40]; + + u8 event_bitmask[0x40]; + + u8 reserved_3[0x580]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_eq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 eq_number[0x8]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_dctc_bits dct_context_entry; + + u8 reserved_2[0x180]; +}; + +struct mlx5_ifc_query_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dctn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_cqc_bits cq_context; + + u8 reserved_2[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 cqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cong_status_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 enable[0x1]; + u8 tag_enable[0x1]; + u8 reserved_2[0x1e]; +}; + +struct mlx5_ifc_query_cong_status_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 priority[0x4]; + u8 cong_protocol[0x4]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cong_statistics_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 cur_flows[0x20]; + + u8 sum_flows[0x20]; + + u8 cnp_ignored_high[0x20]; + + u8 cnp_ignored_low[0x20]; + + u8 cnp_handled_high[0x20]; + + u8 cnp_handled_low[0x20]; + + u8 reserved_2[0x100]; + + u8 time_stamp_high[0x20]; + + u8 time_stamp_low[0x20]; + + u8 accumulators_period[0x20]; + + u8 ecn_marked_roce_packets_high[0x20]; + + u8 ecn_marked_roce_packets_low[0x20]; + + u8 cnps_sent_high[0x20]; + + u8 cnps_sent_low[0x20]; + + u8 reserved_3[0x560]; +}; + +struct mlx5_ifc_query_cong_statistics_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 clear[0x1]; + u8 reserved_2[0x1f]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cong_params_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters; +}; + +struct mlx5_ifc_query_cong_params_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x1c]; + u8 cong_protocol[0x4]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_adapter_out_bits { u8 status[0x8]; u8 reserved_0[0x18]; u8 syndrome[0x20]; u8 reserved_1[0x40]; + + struct mlx5_ifc_query_adapter_param_block_bits query_adapter_struct; +}; + +struct mlx5_ifc_query_adapter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_qp_2rst_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_qp_2rst_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_qp_2err_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_qp_2err_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_page_fault_resume_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_page_fault_resume_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 error[0x1]; + u8 reserved_2[0x4]; + u8 rdma[0x1]; + u8 read_write[0x1]; + u8 req_res[0x1]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_nop_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_nop_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_modify_vport_state_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_vport_state_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x18]; + u8 admin_state[0x4]; + u8 reserved_4[0x4]; +}; + +struct mlx5_ifc_modify_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tisn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_tisc_bits ctx; +}; + +struct mlx5_ifc_modify_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tirn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_tirc_bits ctx; +}; + +struct mlx5_ifc_modify_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 sq_state[0x4]; + u8 reserved_2[0x4]; + u8 sqn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_sqc_bits ctx; +}; + +struct mlx5_ifc_modify_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqtn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_rqtc_bits ctx; +}; + +struct mlx5_ifc_modify_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 rq_state[0x4]; + u8 reserved_2[0x4]; + u8 rqn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_rqc_bits ctx; +}; + +struct mlx5_ifc_modify_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 rmp_state[0x4]; + u8 reserved_2[0x4]; + u8 rmpn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_rmpc_bits ctx; +}; + +struct mlx5_ifc_modify_nic_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_nic_vport_field_select_bits { + u8 reserved_0[0x1c]; + u8 permanent_address[0x1]; + u8 addresses_list[0x1]; + u8 roce_en[0x1]; + u8 reserved_1[0x1]; +}; + +struct mlx5_ifc_modify_nic_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + struct mlx5_ifc_modify_nic_vport_field_select_bits field_select; + + u8 reserved_3[0x780]; + + struct mlx5_ifc_nic_vport_context_bits nic_vport_context; +}; + +struct mlx5_ifc_modify_hca_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_hca_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_hca_vport_context_bits hca_vport_context; +}; + +struct mlx5_ifc_modify_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_MODIFY_CQ_IN_OP_MOD_MODIFY_CQ = 0x0, + MLX5_MODIFY_CQ_IN_OP_MOD_RESIZE_CQ = 0x1, +}; + +struct mlx5_ifc_modify_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 cqn[0x18]; + + union mlx5_ifc_modify_field_select_resize_field_select_auto_bits modify_field_select_resize_field_select; + + struct mlx5_ifc_cqc_bits cq_context; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_modify_cong_status_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_cong_status_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 priority[0x4]; + u8 cong_protocol[0x4]; + + u8 enable[0x1]; + u8 tag_enable[0x1]; + u8 reserved_3[0x1e]; +}; + +struct mlx5_ifc_modify_cong_params_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_cong_params_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x1c]; + u8 cong_protocol[0x4]; + + union mlx5_ifc_field_select_802_1_r_roce_auto_bits field_select; + + u8 reserved_3[0x80]; + + union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters; +}; + +struct mlx5_ifc_manage_pages_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 output_num_entries[0x20]; + + u8 reserved_1[0x20]; + + u8 pas[0][0x40]; +}; + +enum { + MLX5_MANAGE_PAGES_IN_OP_MOD_ALLOCATION_FAIL = 0x0, + MLX5_MANAGE_PAGES_IN_OP_MOD_ALLOCATION_SUCCESS = 0x1, + MLX5_MANAGE_PAGES_IN_OP_MOD_HCA_RETURN_PAGES = 0x2, +}; + +struct mlx5_ifc_manage_pages_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 input_num_entries[0x20]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_mad_ifc_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 response_mad_packet[256][0x8]; +}; + +struct mlx5_ifc_mad_ifc_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 remote_lid[0x10]; + u8 reserved_2[0x8]; + u8 port[0x8]; + + u8 reserved_3[0x20]; + + u8 mad[256][0x8]; +}; + +struct mlx5_ifc_init_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_init_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_init2rtr_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_init2rtr_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_init2init_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_init2init_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_get_dropped_packet_log_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 packet_headers_log[128][0x8]; + + u8 packet_syndrome[64][0x8]; +}; + +struct mlx5_ifc_get_dropped_packet_log_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_gen_eqe_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 eq_number[0x8]; + + u8 reserved_3[0x20]; + + u8 eqe[64][0x8]; +}; + +struct mlx5_ifc_gen_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_enable_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; +}; + +struct mlx5_ifc_enable_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_drain_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_drain_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dctn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_disable_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; +}; + +struct mlx5_ifc_disable_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_detach_from_mcg_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_detach_from_mcg_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 multicast_gid[16][0x8]; +}; + +struct mlx5_ifc_destroy_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tisn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tirn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 sqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqtn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rmpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_psv_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_psv_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 psvn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_mkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_mkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 mkey_index[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_flow_table_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x140]; +}; + +struct mlx5_ifc_destroy_flow_group_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_flow_group_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 group_id[0x20]; + + u8 reserved_5[0x120]; +}; + +struct mlx5_ifc_destroy_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_eq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 eq_number[0x8]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dctn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 cqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_delete_vxlan_udp_dport_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_delete_vxlan_udp_dport_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x10]; + u8 vxlan_udp_port[0x10]; +}; + +struct mlx5_ifc_delete_l2_table_entry_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_delete_l2_table_entry_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x8]; + u8 table_index[0x18]; + + u8 reserved_4[0x140]; +}; + +struct mlx5_ifc_delete_fte_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_delete_fte_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x40]; + + u8 flow_index[0x20]; + + u8 reserved_6[0xe0]; +}; + +struct mlx5_ifc_dealloc_xrcd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_xrcd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrcd[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_uar_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_uar_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 uar[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_transport_domain_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_transport_domain_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 transport_domain[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_q_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_q_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 counter_set_id[0x8]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_pd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_pd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 pd[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_create_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 tisn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_tisc_bits ctx; +}; + +struct mlx5_ifc_create_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 tirn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_tirc_bits ctx; +}; + +struct mlx5_ifc_create_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 srqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_srqc_bits srq_context_entry; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 sqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_sqc_bits ctx; +}; + +struct mlx5_ifc_create_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 rqtn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_rqtc_bits rqt_context; +}; + +struct mlx5_ifc_create_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 rqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_rqc_bits ctx; +}; + +struct mlx5_ifc_create_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 rmpn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_rmpc_bits ctx; +}; + +struct mlx5_ifc_create_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 qpn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 opt_param_mask[0x20]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_4[0x80]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_psv_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 reserved_2[0x8]; + u8 psv0_index[0x18]; + + u8 reserved_3[0x8]; + u8 psv1_index[0x18]; + + u8 reserved_4[0x8]; + u8 psv2_index[0x18]; + + u8 reserved_5[0x8]; + u8 psv3_index[0x18]; +}; + +struct mlx5_ifc_create_psv_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 num_psv[0x4]; + u8 reserved_2[0x4]; + u8 pd[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_create_mkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 mkey_index[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_mkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 pg_access[0x1]; + u8 reserved_3[0x1f]; + + struct mlx5_ifc_mkc_bits memory_key_mkey_entry; + + u8 reserved_4[0x80]; + + u8 translations_octword_actual_size[0x20]; + + u8 reserved_5[0x560]; + + u8 klm_pas_mtt[0][0x20]; +}; + +struct mlx5_ifc_create_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 table_id[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_flow_table_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x8]; + u8 level[0x8]; + u8 reserved_6[0x8]; + u8 log_size[0x8]; + + u8 reserved_7[0x120]; +}; + +struct mlx5_ifc_create_flow_group_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 group_id[0x18]; + + u8 reserved_2[0x20]; +}; + +enum { + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2, +}; + +struct mlx5_ifc_create_flow_group_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x20]; + + u8 start_flow_index[0x20]; + + u8 reserved_6[0x20]; + + u8 end_flow_index[0x20]; + + u8 reserved_7[0xa0]; + + u8 reserved_8[0x18]; + u8 match_criteria_enable[0x8]; + + struct mlx5_ifc_fte_match_param_bits match_criteria; + + u8 reserved_9[0xe00]; +}; + +struct mlx5_ifc_create_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x18]; + u8 eq_number[0x8]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_eq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_eqc_bits eq_context_entry; + + u8 reserved_3[0x40]; + + u8 event_bitmask[0x40]; + + u8 reserved_4[0x580]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 dctn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_dctc_bits dct_context_entry; + + u8 reserved_3[0x180]; +}; + +struct mlx5_ifc_create_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 cqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_cqc_bits cq_context; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_config_int_moderation_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x4]; + u8 min_delay[0xc]; + u8 int_vector[0x10]; + + u8 reserved_2[0x20]; +}; + +enum { + MLX5_CONFIG_INT_MODERATION_IN_OP_MOD_WRITE = 0x0, + MLX5_CONFIG_INT_MODERATION_IN_OP_MOD_READ = 0x1, +}; + +struct mlx5_ifc_config_int_moderation_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x4]; + u8 min_delay[0xc]; + u8 int_vector[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_attach_to_mcg_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_attach_to_mcg_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 multicast_gid[16][0x8]; +}; + +struct mlx5_ifc_arm_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ = 0x1, +}; + +struct mlx5_ifc_arm_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_3[0x10]; + u8 lwm[0x10]; +}; + +struct mlx5_ifc_arm_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_ARM_RQ_IN_OP_MOD_SRQ_ = 0x1, +}; + +struct mlx5_ifc_arm_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 srq_number[0x18]; + + u8 reserved_3[0x10]; + u8 lwm[0x10]; +}; + +struct mlx5_ifc_arm_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_arm_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dct_number[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_alloc_xrcd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 xrcd[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_xrcd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_uar_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 uar[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_uar_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_transport_domain_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 transport_domain[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_transport_domain_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_q_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x18]; + u8 counter_set_id[0x8]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_q_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_pd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 pd[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_pd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_add_vxlan_udp_dport_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_add_vxlan_udp_dport_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x10]; + u8 vxlan_udp_port[0x10]; +}; + +struct mlx5_ifc_access_register_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 register_data[0][0x20]; +}; + +enum { + MLX5_ACCESS_REGISTER_IN_OP_MOD_WRITE = 0x0, + MLX5_ACCESS_REGISTER_IN_OP_MOD_READ = 0x1, +}; + +struct mlx5_ifc_access_register_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 register_id[0x10]; + + u8 argument[0x20]; + + u8 register_data[0][0x20]; +}; + +struct mlx5_ifc_sltp_reg_bits { + u8 status[0x4]; + u8 version[0x4]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 reserved_0[0x2]; + u8 lane[0x4]; + u8 reserved_1[0x8]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x7]; + u8 polarity[0x1]; + u8 ob_tap0[0x8]; + u8 ob_tap1[0x8]; + u8 ob_tap2[0x8]; + + u8 reserved_4[0xc]; + u8 ob_preemp_mode[0x4]; + u8 ob_reg[0x8]; + u8 ob_bias[0x8]; + + u8 reserved_5[0x20]; +}; + +struct mlx5_ifc_slrg_reg_bits { + u8 status[0x4]; + u8 version[0x4]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 reserved_0[0x2]; + u8 lane[0x4]; + u8 reserved_1[0x8]; + + u8 time_to_link_up[0x10]; + u8 reserved_2[0xc]; + u8 grade_lane_speed[0x4]; + + u8 grade_version[0x8]; + u8 grade[0x18]; + + u8 reserved_3[0x4]; + u8 height_grade_type[0x4]; + u8 height_grade[0x18]; + + u8 height_dz[0x10]; + u8 height_dv[0x10]; + + u8 reserved_4[0x10]; + u8 height_sigma[0x10]; + + u8 reserved_5[0x20]; + + u8 reserved_6[0x4]; + u8 phase_grade_type[0x4]; + u8 phase_grade[0x18]; + + u8 reserved_7[0x8]; + u8 phase_eo_pos[0x8]; + u8 reserved_8[0x8]; + u8 phase_eo_neg[0x8]; + + u8 ffe_set_tested[0x10]; + u8 test_errors_per_lane[0x10]; +}; + +struct mlx5_ifc_pvlc_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x1c]; + u8 vl_hw_cap[0x4]; + + u8 reserved_3[0x1c]; + u8 vl_admin[0x4]; + + u8 reserved_4[0x1c]; + u8 vl_operational[0x4]; +}; + +struct mlx5_ifc_pude_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 reserved_0[0x4]; + u8 admin_status[0x4]; + u8 reserved_1[0x4]; + u8 oper_status[0x4]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_ptys_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0xd]; + u8 proto_mask[0x3]; + + u8 reserved_2[0x40]; + + u8 eth_proto_capability[0x20]; + + u8 ib_link_width_capability[0x10]; + u8 ib_proto_capability[0x10]; + + u8 reserved_3[0x20]; + + u8 eth_proto_admin[0x20]; + + u8 ib_link_width_admin[0x10]; + u8 ib_proto_admin[0x10]; + + u8 reserved_4[0x20]; + + u8 eth_proto_oper[0x20]; + + u8 ib_link_width_oper[0x10]; + u8 ib_proto_oper[0x10]; + + u8 reserved_5[0x20]; + + u8 eth_proto_lp_advertise[0x20]; + + u8 reserved_6[0x60]; +}; + +struct mlx5_ifc_ptas_reg_bits { + u8 reserved_0[0x20]; + + u8 algorithm_options[0x10]; + u8 reserved_1[0x4]; + u8 repetitions_mode[0x4]; + u8 num_of_repetitions[0x8]; + + u8 grade_version[0x8]; + u8 height_grade_type[0x4]; + u8 phase_grade_type[0x4]; + u8 height_grade_weight[0x8]; + u8 phase_grade_weight[0x8]; + + u8 gisim_measure_bits[0x10]; + u8 adaptive_tap_measure_bits[0x10]; + + u8 ber_bath_high_error_threshold[0x10]; + u8 ber_bath_mid_error_threshold[0x10]; + + u8 ber_bath_low_error_threshold[0x10]; + u8 one_ratio_high_threshold[0x10]; + + u8 one_ratio_high_mid_threshold[0x10]; + u8 one_ratio_low_mid_threshold[0x10]; + + u8 one_ratio_low_threshold[0x10]; + u8 ndeo_error_threshold[0x10]; + + u8 mixer_offset_step_size[0x10]; + u8 reserved_2[0x8]; + u8 mix90_phase_for_voltage_bath[0x8]; + + u8 mixer_offset_start[0x10]; + u8 mixer_offset_end[0x10]; + + u8 reserved_3[0x15]; + u8 ber_test_time[0xb]; +}; + +struct mlx5_ifc_pspa_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 sub_port[0x8]; + u8 reserved_0[0x8]; + + u8 reserved_1[0x20]; +}; + +struct mlx5_ifc_pqdr_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x5]; + u8 prio[0x3]; + u8 reserved_2[0x6]; + u8 mode[0x2]; + + u8 reserved_3[0x20]; + + u8 reserved_4[0x10]; + u8 min_threshold[0x10]; + + u8 reserved_5[0x10]; + u8 max_threshold[0x10]; + + u8 reserved_6[0x10]; + u8 mark_probability_denominator[0x10]; + + u8 reserved_7[0x60]; +}; + +struct mlx5_ifc_ppsc_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x1c]; + u8 wrps_admin[0x4]; + + u8 reserved_4[0x1c]; + u8 wrps_status[0x4]; + + u8 reserved_5[0x8]; + u8 up_threshold[0x8]; + u8 reserved_6[0x8]; + u8 down_threshold[0x8]; + + u8 reserved_7[0x20]; + + u8 reserved_8[0x1c]; + u8 srps_admin[0x4]; + + u8 reserved_9[0x1c]; + u8 srps_status[0x4]; + + u8 reserved_10[0x40]; +}; + +struct mlx5_ifc_pplr_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x8]; + u8 lb_cap[0x8]; + u8 reserved_3[0x8]; + u8 lb_en[0x8]; +}; + +struct mlx5_ifc_pplm_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x20]; + + u8 port_profile_mode[0x8]; + u8 static_port_profile[0x8]; + u8 active_port_profile[0x8]; + u8 reserved_3[0x8]; + + u8 retransmission_active[0x8]; + u8 fec_mode_active[0x18]; + + u8 reserved_4[0x20]; +}; + +struct mlx5_ifc_ppcnt_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 reserved_0[0x8]; + u8 grp[0x6]; + + u8 clr[0x1]; + u8 reserved_1[0x1c]; + u8 prio_tc[0x3]; + + union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; +}; + +struct mlx5_ifc_ppad_reg_bits { + u8 reserved_0[0x3]; + u8 single_mac[0x1]; + u8 reserved_1[0x4]; + u8 local_port[0x8]; + u8 mac_47_32[0x10]; + + u8 mac_31_0[0x20]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_pmtu_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 max_mtu[0x10]; + u8 reserved_2[0x10]; + + u8 admin_mtu[0x10]; + u8 reserved_3[0x10]; + + u8 oper_mtu[0x10]; + u8 reserved_4[0x10]; +}; + +struct mlx5_ifc_pmpr_reg_bits { + u8 reserved_0[0x8]; + u8 module[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x18]; + u8 attenuation_5g[0x8]; + + u8 reserved_3[0x18]; + u8 attenuation_7g[0x8]; + + u8 reserved_4[0x18]; + u8 attenuation_12g[0x8]; +}; + +struct mlx5_ifc_pmpe_reg_bits { + u8 reserved_0[0x8]; + u8 module[0x8]; + u8 reserved_1[0xc]; + u8 module_status[0x4]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_pmpc_reg_bits { + u8 module_state_updated[32][0x8]; +}; + +struct mlx5_ifc_pmlpn_reg_bits { + u8 reserved_0[0x4]; + u8 mlpn_status[0x4]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 e[0x1]; + u8 reserved_2[0x1f]; +}; + +struct mlx5_ifc_pmlp_reg_bits { + u8 rxtx[0x1]; + u8 reserved_0[0x7]; + u8 local_port[0x8]; + u8 reserved_1[0x8]; + u8 width[0x8]; + + u8 lane0_module_mapping[0x20]; + + u8 lane1_module_mapping[0x20]; + + u8 lane2_module_mapping[0x20]; + + u8 lane3_module_mapping[0x20]; + + u8 reserved_2[0x160]; +}; + +struct mlx5_ifc_pmaos_reg_bits { + u8 reserved_0[0x8]; + u8 module[0x8]; + u8 reserved_1[0x4]; + u8 admin_status[0x4]; + u8 reserved_2[0x4]; + u8 oper_status[0x4]; + + u8 ase[0x1]; + u8 ee[0x1]; + u8 reserved_3[0x1c]; + u8 e[0x2]; + + u8 reserved_4[0x40]; +}; + +struct mlx5_ifc_plpc_reg_bits { + u8 reserved_0[0x4]; + u8 profile_id[0xc]; + u8 reserved_1[0x4]; + u8 proto_mask[0x4]; + u8 reserved_2[0x8]; + + u8 reserved_3[0x10]; + u8 lane_speed[0x10]; + + u8 reserved_4[0x17]; + u8 lpbf[0x1]; + u8 fec_mode_policy[0x8]; + + u8 retransmission_capability[0x8]; + u8 fec_mode_capability[0x18]; + + u8 retransmission_support_admin[0x8]; + u8 fec_mode_support_admin[0x18]; + + u8 retransmission_request_admin[0x8]; + u8 fec_mode_request_admin[0x18]; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_plib_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x8]; + u8 ib_port[0x8]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_plbf_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0xd]; + u8 lbf_mode[0x3]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_pipg_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 dic[0x1]; + u8 reserved_2[0x19]; + u8 ipg[0x4]; + u8 reserved_3[0x2]; +}; + +struct mlx5_ifc_pifr_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0xe0]; + + u8 port_filter[8][0x20]; + + u8 port_filter_update_en[8][0x20]; +}; + +struct mlx5_ifc_pfcc_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 ppan[0x4]; + u8 reserved_2[0x4]; + u8 prio_mask_tx[0x8]; + u8 reserved_3[0x8]; + u8 prio_mask_rx[0x8]; + + u8 pptx[0x1]; + u8 aptx[0x1]; + u8 reserved_4[0x6]; + u8 pfctx[0x8]; + u8 reserved_5[0x10]; + + u8 pprx[0x1]; + u8 aprx[0x1]; + u8 reserved_6[0x6]; + u8 pfcrx[0x8]; + u8 reserved_7[0x10]; + + u8 reserved_8[0x80]; +}; + +struct mlx5_ifc_pelc_reg_bits { + u8 op[0x4]; + u8 reserved_0[0x4]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 op_admin[0x8]; + u8 op_capability[0x8]; + u8 op_request[0x8]; + u8 op_active[0x8]; + + u8 admin[0x40]; + + u8 capability[0x40]; + + u8 request[0x40]; + + u8 active[0x40]; + + u8 reserved_2[0x80]; +}; + +struct mlx5_ifc_peir_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0xc]; + u8 error_count[0x4]; + u8 reserved_3[0x10]; + + u8 reserved_4[0xc]; + u8 lane[0x4]; + u8 reserved_5[0x8]; + u8 error_type[0x8]; +}; + +struct mlx5_ifc_pcap_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 port_capability_mask[4][0x20]; +}; + +struct mlx5_ifc_paos_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 reserved_0[0x4]; + u8 admin_status[0x4]; + u8 reserved_1[0x4]; + u8 oper_status[0x4]; + + u8 ase[0x1]; + u8 ee[0x1]; + u8 reserved_2[0x1c]; + u8 e[0x2]; + + u8 reserved_3[0x40]; +}; + +struct mlx5_ifc_pamp_reg_bits { + u8 reserved_0[0x8]; + u8 opamp_group[0x8]; + u8 reserved_1[0xc]; + u8 opamp_group_type[0x4]; + + u8 start_index[0x10]; + u8 reserved_2[0x4]; + u8 num_of_indices[0xc]; + + u8 index_data[18][0x10]; +}; + +struct mlx5_ifc_lane_2_module_mapping_bits { + u8 reserved_0[0x6]; + u8 rx_lane[0x2]; + u8 reserved_1[0x6]; + u8 tx_lane[0x2]; + u8 reserved_2[0x8]; + u8 module[0x8]; +}; + +struct mlx5_ifc_bufferx_reg_bits { + u8 reserved_0[0x6]; + u8 lossy[0x1]; + u8 epsb[0x1]; + u8 reserved_1[0xc]; + u8 size[0xc]; + + u8 xoff_threshold[0x10]; + u8 xon_threshold[0x10]; +}; + +struct mlx5_ifc_set_node_in_bits { + u8 node_description[64][0x8]; +}; + +struct mlx5_ifc_register_power_settings_bits { + u8 reserved_0[0x18]; + u8 power_settings_level[0x8]; + + u8 reserved_1[0x60]; +}; + +struct mlx5_ifc_register_host_endianness_bits { + u8 he[0x1]; + u8 reserved_0[0x1f]; + + u8 reserved_1[0x60]; +}; + +struct mlx5_ifc_umr_pointer_desc_argument_bits { + u8 reserved_0[0x20]; + + u8 mkey[0x20]; + + u8 addressh_63_32[0x20]; + + u8 addressl_31_0[0x20]; +}; + +struct mlx5_ifc_ud_adrs_vector_bits { + u8 dc_key[0x40]; + + u8 ext[0x1]; + u8 reserved_0[0x7]; + u8 destination_qp_dct[0x18]; + + u8 static_rate[0x4]; + u8 sl_eth_prio[0x4]; + u8 fl[0x1]; + u8 mlid[0x7]; + u8 rlid_udp_sport[0x10]; + + u8 reserved_1[0x20]; + + u8 rmac_47_16[0x20]; + + u8 rmac_15_0[0x10]; + u8 tclass[0x8]; + u8 hop_limit[0x8]; + + u8 reserved_2[0x1]; + u8 grh[0x1]; + u8 reserved_3[0x2]; + u8 src_addr_index[0x8]; + u8 flow_label[0x14]; + + u8 rgid_rip[16][0x8]; +}; + +struct mlx5_ifc_pages_req_event_bits { + u8 reserved_0[0x10]; + u8 function_id[0x10]; + + u8 num_pages[0x20]; + + u8 reserved_1[0xa0]; +}; + +struct mlx5_ifc_eqe_bits { + u8 reserved_0[0x8]; + u8 event_type[0x8]; + u8 reserved_1[0x8]; + u8 event_sub_type[0x8]; + + u8 reserved_2[0xe0]; + + union mlx5_ifc_event_auto_bits event_data; + + u8 reserved_3[0x10]; + u8 signature[0x8]; + u8 reserved_4[0x7]; + u8 owner[0x1]; +}; + +enum { + MLX5_CMD_QUEUE_ENTRY_TYPE_PCIE_CMD_IF_TRANSPORT = 0x7, +}; + +struct mlx5_ifc_cmd_queue_entry_bits { + u8 type[0x8]; + u8 reserved_0[0x18]; + + u8 input_length[0x20]; + + u8 input_mailbox_pointer_63_32[0x20]; + + u8 input_mailbox_pointer_31_9[0x17]; + u8 reserved_1[0x9]; + + u8 command_input_inline_data[16][0x8]; + + u8 command_output_inline_data[16][0x8]; + + u8 output_mailbox_pointer_63_32[0x20]; + + u8 output_mailbox_pointer_31_9[0x17]; + u8 reserved_2[0x9]; + + u8 output_length[0x20]; + + u8 token[0x8]; + u8 signature[0x8]; + u8 reserved_3[0x8]; + u8 status[0x7]; + u8 ownership[0x1]; +}; + +struct mlx5_ifc_cmd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 command_output[0x20]; +}; + +struct mlx5_ifc_cmd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 command[0][0x20]; +}; + +struct mlx5_ifc_cmd_if_box_bits { + u8 mailbox_data[512][0x8]; + + u8 reserved_0[0x180]; + + u8 next_pointer_63_32[0x20]; + + u8 next_pointer_31_10[0x16]; + u8 reserved_1[0xa]; + + u8 block_number[0x20]; + + u8 reserved_2[0x8]; + u8 token[0x8]; + u8 ctrl_signature[0x8]; + u8 signature[0x8]; +}; + +struct mlx5_ifc_mtt_bits { + u8 ptag_63_32[0x20]; + + u8 ptag_31_8[0x18]; + u8 reserved_0[0x6]; + u8 wr_en[0x1]; + u8 rd_en[0x1]; +}; + +enum { + MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER = 0x0, + MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED = 0x1, + MLX5_INITIAL_SEG_NIC_INTERFACE_NO_DRAM_NIC = 0x2, +}; + +enum { + MLX5_INITIAL_SEG_NIC_INTERFACE_SUPPORTED_FULL_DRIVER = 0x0, + MLX5_INITIAL_SEG_NIC_INTERFACE_SUPPORTED_DISABLED = 0x1, + MLX5_INITIAL_SEG_NIC_INTERFACE_SUPPORTED_NO_DRAM_NIC = 0x2, +}; + +enum { + MLX5_INITIAL_SEG_HEALTH_SYNDROME_FW_INTERNAL_ERR = 0x1, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_DEAD_IRISC = 0x7, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_HW_FATAL_ERR = 0x8, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_FW_CRC_ERR = 0x9, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_FETCH_PCI_ERR = 0xa, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PAGE_ERR = 0xb, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ASYNCHRONOUS_EQ_BUF_OVERRUN = 0xc, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_IN_ERR = 0xd, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_INV = 0xe, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_FFSER_ERR = 0xf, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_HIGH_TEMP_ERR = 0x10, +}; + +struct mlx5_ifc_initial_seg_bits { + u8 fw_rev_minor[0x10]; + u8 fw_rev_major[0x10]; + + u8 cmd_interface_rev[0x10]; + u8 fw_rev_subminor[0x10]; + + u8 reserved_0[0x40]; + + u8 cmdq_phy_addr_63_32[0x20]; + + u8 cmdq_phy_addr_31_12[0x14]; + u8 reserved_1[0x2]; + u8 nic_interface[0x2]; + u8 log_cmdq_size[0x4]; + u8 log_cmdq_stride[0x4]; + + u8 command_doorbell_vector[0x20]; + + u8 reserved_2[0xf00]; + + u8 initializing[0x1]; + u8 reserved_3[0x4]; + u8 nic_interface_supported[0x3]; + u8 reserved_4[0x18]; + + struct mlx5_ifc_health_buffer_bits health_buffer; + + u8 no_dram_nic_offset[0x20]; + + u8 reserved_5[0x6e40]; + + u8 reserved_6[0x1f]; + u8 clear_int[0x1]; + + u8 health_syndrome[0x8]; + u8 health_counter[0x18]; + + u8 reserved_7[0x17fc0]; +}; + +union mlx5_ifc_ports_control_registers_document_bits { + struct mlx5_ifc_bufferx_reg_bits bufferx_reg; + struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; + struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits eth_2863_cntrs_grp_data_layout; + struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits eth_3635_cntrs_grp_data_layout; + struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits eth_802_3_cntrs_grp_data_layout; + struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits eth_extended_cntrs_grp_data_layout; + struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; + struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; + struct mlx5_ifc_lane_2_module_mapping_bits lane_2_module_mapping; + struct mlx5_ifc_pamp_reg_bits pamp_reg; + struct mlx5_ifc_paos_reg_bits paos_reg; + struct mlx5_ifc_pcap_reg_bits pcap_reg; + struct mlx5_ifc_peir_reg_bits peir_reg; + struct mlx5_ifc_pelc_reg_bits pelc_reg; + struct mlx5_ifc_pfcc_reg_bits pfcc_reg; + struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; + struct mlx5_ifc_pifr_reg_bits pifr_reg; + struct mlx5_ifc_pipg_reg_bits pipg_reg; + struct mlx5_ifc_plbf_reg_bits plbf_reg; + struct mlx5_ifc_plib_reg_bits plib_reg; + struct mlx5_ifc_plpc_reg_bits plpc_reg; + struct mlx5_ifc_pmaos_reg_bits pmaos_reg; + struct mlx5_ifc_pmlp_reg_bits pmlp_reg; + struct mlx5_ifc_pmlpn_reg_bits pmlpn_reg; + struct mlx5_ifc_pmpc_reg_bits pmpc_reg; + struct mlx5_ifc_pmpe_reg_bits pmpe_reg; + struct mlx5_ifc_pmpr_reg_bits pmpr_reg; + struct mlx5_ifc_pmtu_reg_bits pmtu_reg; + struct mlx5_ifc_ppad_reg_bits ppad_reg; + struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg; + struct mlx5_ifc_pplm_reg_bits pplm_reg; + struct mlx5_ifc_pplr_reg_bits pplr_reg; + struct mlx5_ifc_ppsc_reg_bits ppsc_reg; + struct mlx5_ifc_pqdr_reg_bits pqdr_reg; + struct mlx5_ifc_pspa_reg_bits pspa_reg; + struct mlx5_ifc_ptas_reg_bits ptas_reg; + struct mlx5_ifc_ptys_reg_bits ptys_reg; + struct mlx5_ifc_pude_reg_bits pude_reg; + struct mlx5_ifc_pvlc_reg_bits pvlc_reg; + struct mlx5_ifc_slrg_reg_bits slrg_reg; + struct mlx5_ifc_sltp_reg_bits sltp_reg; + u8 reserved_0[0x60e0]; +}; + +union mlx5_ifc_debug_enhancements_document_bits { + struct mlx5_ifc_health_buffer_bits health_buffer; + u8 reserved_0[0x200]; +}; + +union mlx5_ifc_uplink_pci_interface_document_bits { + struct mlx5_ifc_initial_seg_bits initial_seg; + u8 reserved_0[0x20060]; }; #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 310b5f7..f079fb1 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -134,13 +134,21 @@ enum { enum { MLX5_WQE_CTRL_CQ_UPDATE = 2 << 2, + MLX5_WQE_CTRL_CQ_UPDATE_AND_EQE = 3 << 2, MLX5_WQE_CTRL_SOLICITED = 1 << 1, }; enum { + MLX5_SEND_WQE_DS = 16, MLX5_SEND_WQE_BB = 64, }; +#define MLX5_SEND_WQEBB_NUM_DS (MLX5_SEND_WQE_BB / MLX5_SEND_WQE_DS) + +enum { + MLX5_SEND_WQE_MAX_WQEBBS = 16, +}; + enum { MLX5_WQE_FMR_PERM_LOCAL_READ = 1 << 27, MLX5_WQE_FMR_PERM_LOCAL_WRITE = 1 << 28, @@ -200,6 +208,23 @@ struct mlx5_wqe_ctrl_seg { #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8 +enum { + MLX5_ETH_WQE_L3_INNER_CSUM = 1 << 4, + MLX5_ETH_WQE_L4_INNER_CSUM = 1 << 5, + MLX5_ETH_WQE_L3_CSUM = 1 << 6, + MLX5_ETH_WQE_L4_CSUM = 1 << 7, +}; + +struct mlx5_wqe_eth_seg { + u8 rsvd0[4]; + u8 cs_flags; + u8 rsvd1; + __be16 mss; + __be32 rsvd2; + __be16 inline_hdr_sz; + u8 inline_hdr_start[2]; +}; + struct mlx5_wqe_xrc_seg { __be32 xrc_srqn; u8 rsvd[12]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 51f8d2f..6f5f71f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1997,6 +1997,7 @@ struct offload_callbacks { struct packet_offload { __be16 type; /* This is really htons(ether_type). */ + u16 priority; struct offload_callbacks callbacks; struct list_head list; }; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 2f7b9a4..2972c7f 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2329,6 +2329,8 @@ #define PCI_DEVICE_ID_ALTIMA_AC9100 0x03ea #define PCI_DEVICE_ID_ALTIMA_AC1003 0x03eb +#define PCI_VENDOR_ID_CAVIUM 0x177d + #define PCI_VENDOR_ID_BELKIN 0x1799 #define PCI_DEVICE_ID_BELKIN_F5D7010V7 0x701f diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 50e5009..84a1094 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -41,7 +41,12 @@ void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); -int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs); +int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); + +static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) +{ + return __percpu_counter_compare(fbc, rhs, percpu_counter_batch); +} static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -116,6 +121,12 @@ static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) return 0; } +static inline int +__percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) +{ + return percpu_counter_compare(fbc, rhs); +} + static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { diff --git a/include/linux/phy.h b/include/linux/phy.h index 701c7a3..a26c3f8 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -678,6 +678,17 @@ static inline bool phy_is_internal(struct phy_device *phydev) } /** + * phy_interface_is_rgmii - Convenience function for testing if a PHY interface + * is RGMII (all variants) + * @phydev: the phy_device struct + */ +static inline bool phy_interface_is_rgmii(struct phy_device *phydev) +{ + return phydev->interface >= PHY_INTERFACE_MODE_RGMII && + phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID; +} + +/** * phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. * @phydev: The phy_device struct diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7f484a2..c735f5c 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -99,6 +99,7 @@ struct plat_stmmacenet_data { int phy_addr; int interface; struct stmmac_mdio_bus_data *mdio_bus_data; + struct device_node *phy_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d63ecec..a741678 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4575,13 +4575,15 @@ void cfg80211_roamed_bss(struct net_device *dev, struct cfg80211_bss *bss, * @ie: information elements of the deauth/disassoc frame (may be %NULL) * @ie_len: length of IEs * @reason: reason code for the disconnection, set it to 0 if unknown + * @locally_generated: disconnection was requested locally * @gfp: allocation flags * * After it calls this function, the driver should enter an idle state * and not try to connect to any AP any more. */ void cfg80211_disconnected(struct net_device *dev, u16 reason, - const u8 *ie, size_t ie_len, gfp_t gfp); + const u8 *ie, size_t ie_len, + bool locally_generated, gfp_t gfp); /** * cfg80211_ready_on_channel - notification of remain_on_channel start diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 6ea16c8..290a9a6 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -44,6 +44,8 @@ struct cfg802154_ops { int (*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel); int (*set_cca_mode)(struct wpan_phy *wpan_phy, const struct wpan_phy_cca *cca); + int (*set_cca_ed_level)(struct wpan_phy *wpan_phy, s32 ed_level); + int (*set_tx_power)(struct wpan_phy *wpan_phy, s32 power); int (*set_pan_id)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 pan_id); int (*set_short_addr)(struct wpan_phy *wpan_phy, @@ -61,14 +63,66 @@ struct cfg802154_ops { struct wpan_dev *wpan_dev, bool mode); }; +static inline bool +wpan_phy_supported_bool(bool b, enum nl802154_supported_bool_states st) +{ + switch (st) { + case NL802154_SUPPORTED_BOOL_TRUE: + return b; + case NL802154_SUPPORTED_BOOL_FALSE: + return !b; + case NL802154_SUPPORTED_BOOL_BOTH: + return true; + default: + WARN_ON(1); + } + + return false; +} + +struct wpan_phy_supported { + u32 channels[IEEE802154_MAX_PAGE + 1], + cca_modes, cca_opts, iftypes; + enum nl802154_supported_bool_states lbt; + u8 min_minbe, max_minbe, min_maxbe, max_maxbe, + min_csma_backoffs, max_csma_backoffs; + s8 min_frame_retries, max_frame_retries; + size_t tx_powers_size, cca_ed_levels_size; + const s32 *tx_powers, *cca_ed_levels; +}; + struct wpan_phy_cca { enum nl802154_cca_modes mode; enum nl802154_cca_opts opt; }; -struct wpan_phy { - struct mutex pib_lock; +static inline bool +wpan_phy_cca_cmp(const struct wpan_phy_cca *a, const struct wpan_phy_cca *b) +{ + if (a->mode != b->mode) + return false; + + if (a->mode == NL802154_CCA_ENERGY_CARRIER) + return a->opt == b->opt; + return true; +} + +/** + * @WPAN_PHY_FLAG_TRANSMIT_POWER: Indicates that transceiver will support + * transmit power setting. + * @WPAN_PHY_FLAG_CCA_ED_LEVEL: Indicates that transceiver will support cca ed + * level setting. + * @WPAN_PHY_FLAG_CCA_MODE: Indicates that transceiver will support cca mode + * setting. + */ +enum wpan_phy_flags { + WPAN_PHY_FLAG_TXPOWER = BIT(1), + WPAN_PHY_FLAG_CCA_ED_LEVEL = BIT(2), + WPAN_PHY_FLAG_CCA_MODE = BIT(3), +}; + +struct wpan_phy { /* If multiple wpan_phys are registered and you're handed e.g. * a regular netdev with assigned ieee802154_ptr, you won't * know whether it points to a wpan_phy your driver has registered @@ -77,6 +131,8 @@ struct wpan_phy { */ const void *privid; + u32 flags; + /* * This is a PIB according to 802.15.4-2011. * We do not provide timing-related variables, as they @@ -84,12 +140,14 @@ struct wpan_phy { */ u8 current_channel; u8 current_page; - u32 channels_supported[IEEE802154_MAX_PAGE + 1]; - s8 transmit_power; + struct wpan_phy_supported supported; + /* current transmit_power in mBm */ + s32 transmit_power; struct wpan_phy_cca cca; __le64 perm_extended_addr; + /* current cca ed threshold in mBm */ s32 cca_ed_level; /* PHY depended MAC PIB values */ @@ -121,9 +179,9 @@ struct wpan_dev { __le64 extended_addr; /* MAC BSN field */ - u8 bsn; + atomic_t bsn; /* MAC DSN field */ - u8 dsn; + atomic_t dsn; u8 min_be; u8 max_be; diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index 94a2970..0a87975 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -422,16 +422,6 @@ struct ieee802154_mlme_ops { struct ieee802154_mac_params *params); struct ieee802154_llsec_ops *llsec; - - /* The fields below are required. */ - - /* - * FIXME: these should become the part of PIB/MIB interface. - * However we still don't have IB interface of any kind - */ - __le16 (*get_pan_id)(const struct net_device *dev); - __le16 (*get_short_addr)(const struct net_device *dev); - u8 (*get_dsn)(const struct net_device *dev); }; static inline struct ieee802154_mlme_ops * @@ -440,10 +430,4 @@ ieee802154_mlme_ops(const struct net_device *dev) return dev->ml_priv; } -static inline struct ieee802154_reduced_mlme_ops * -ieee802154_reduced_mlme_ops(const struct net_device *dev) -{ - return dev->ml_priv; -} - #endif diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 497bc14..0320bbb 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -98,7 +98,8 @@ struct inet_connection_sock { const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); - __u8 icsk_ca_state:7, + __u8 icsk_ca_state:6, + icsk_ca_setsockopt:1, icsk_ca_dst_locked:1; __u8 icsk_retransmits; __u8 icsk_pending; diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 8d17655..e1300b3 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -43,7 +43,7 @@ enum { * @len: total length of the original datagram * @meat: length of received fragments so far * @flags: fragment queue flags - * @max_size: (ipv4 only) maximum received fragment size with IP_DF set + * @max_size: maximum received fragment size * @net: namespace that this frag belongs to */ struct inet_frag_queue { diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 774d241..b73c88a 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -24,7 +24,6 @@ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/wait.h> -#include <linux/vmalloc.h> #include <net/inet_connection_sock.h> #include <net/inet_sock.h> @@ -164,52 +163,12 @@ static inline spinlock_t *inet_ehash_lockp( return &hashinfo->ehash_locks[hash & hashinfo->ehash_locks_mask]; } -static inline int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) -{ - unsigned int i, size = 256; -#if defined(CONFIG_PROVE_LOCKING) - unsigned int nr_pcpus = 2; -#else - unsigned int nr_pcpus = num_possible_cpus(); -#endif - if (nr_pcpus >= 4) - size = 512; - if (nr_pcpus >= 8) - size = 1024; - if (nr_pcpus >= 16) - size = 2048; - if (nr_pcpus >= 32) - size = 4096; - if (sizeof(spinlock_t) != 0) { -#ifdef CONFIG_NUMA - if (size * sizeof(spinlock_t) > PAGE_SIZE) - hashinfo->ehash_locks = vmalloc(size * sizeof(spinlock_t)); - else -#endif - hashinfo->ehash_locks = kmalloc(size * sizeof(spinlock_t), - GFP_KERNEL); - if (!hashinfo->ehash_locks) - return ENOMEM; - for (i = 0; i < size; i++) - spin_lock_init(&hashinfo->ehash_locks[i]); - } - hashinfo->ehash_locks_mask = size - 1; - return 0; -} +int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo); static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo) { - if (hashinfo->ehash_locks) { -#ifdef CONFIG_NUMA - unsigned int size = (hashinfo->ehash_locks_mask + 1) * - sizeof(spinlock_t); - if (size > PAGE_SIZE) - vfree(hashinfo->ehash_locks); - else -#endif - kfree(hashinfo->ehash_locks); - hashinfo->ehash_locks = NULL; - } + kvfree(hashinfo->ehash_locks); + hashinfo->ehash_locks = NULL; } struct inet_bind_bucket * diff --git a/include/net/ip.h b/include/net/ip.h index 7921a36..9b976cf 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -45,6 +45,7 @@ struct inet_skb_parm { #define IPSKB_FRAG_COMPLETE BIT(3) #define IPSKB_REROUTED BIT(4) #define IPSKB_DOREDIRECT BIT(5) +#define IPSKB_FRAG_PMTU BIT(6) u16 frag_max_size; }; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index e000180..3b76849 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -120,7 +120,11 @@ struct rt6_info { struct rt6key rt6i_src; struct rt6key rt6i_prefsrc; + struct list_head rt6i_uncached; + struct uncached_list *rt6i_uncached_list; + struct inet6_dev *rt6i_idev; + struct rt6_info * __percpu *rt6i_pcpu; u32 rt6i_metric; u32 rt6i_pmtu; @@ -159,6 +163,14 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) rt0->rt6i_flags |= RTF_EXPIRES; } +static inline u32 rt6_get_cookie(const struct rt6_info *rt) +{ + if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE)) + rt = (struct rt6_info *)(rt->dst.from); + + return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; +} + static inline void ip6_rt_put(struct rt6_info *rt) { /* dst_release() accepts a NULL parameter. diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 5e19206..297629a 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -145,7 +145,7 @@ static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_IPV6_SUBTREES np->saddr_cache = saddr; #endif - np->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; + np->dst_cookie = rt6_get_cookie(rt); } static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, @@ -163,11 +163,14 @@ static inline bool ipv6_unicast_destination(const struct sk_buff *skb) return rt->rt6i_flags & RTF_LOCAL; } -static inline bool ipv6_anycast_destination(const struct sk_buff *skb) +static inline bool ipv6_anycast_destination(const struct dst_entry *dst, + const struct in6_addr *daddr) { - struct rt6_info *rt = (struct rt6_info *) skb_dst(skb); + struct rt6_info *rt = (struct rt6_info *)dst; - return rt->rt6i_flags & RTF_ANYCAST; + return rt->rt6i_flags & RTF_ANYCAST || + (rt->rt6i_dst.plen != 128 && + ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)); } int ip6_fragment(struct sock *sk, struct sk_buff *skb, @@ -194,9 +197,15 @@ static inline bool ip6_sk_ignore_df(const struct sock *sk) inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT; } -static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt) +static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, + struct in6_addr *daddr) { - return &rt->rt6i_gateway; + if (rt->rt6i_flags & RTF_GATEWAY) + return &rt->rt6i_gateway; + else if (unlikely(rt->rt6i_flags & RTF_CACHE)) + return &rt->rt6i_dst.addr; + else + return daddr; } #endif diff --git a/include/net/ipv6.h b/include/net/ipv6.h index aab8190..35d485c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -671,8 +671,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } -void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr, - struct rt6_info *rt); +__be32 ipv6_select_ident(struct net *net, + const struct in6_addr *daddr, + const struct in6_addr *saddr); void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 2f8b7de..887fe95 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1728,8 +1728,7 @@ struct ieee80211_tx_control { * @sta: station table entry, %NULL for per-vif queue * @tid: the TID for this queue (unused for per-vif queue) * @ac: the AC for this queue - * @drv_priv: data area for driver use, will always be aligned to - * sizeof(void *). + * @drv_priv: driver private area, sized by hw->txq_data_size * * The driver can obtain packets from this queue by calling * ieee80211_tx_dequeue(). diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 7df28a4..9605c7f 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -89,41 +89,26 @@ struct ieee802154_hw { #define IEEE802154_HW_TX_OMIT_CKSUM 0x00000001 /* Indicates that receiver will autorespond with ACK frames. */ #define IEEE802154_HW_AACK 0x00000002 -/* Indicates that transceiver will support transmit power setting. */ -#define IEEE802154_HW_TXPOWER 0x00000004 /* Indicates that transceiver will support listen before transmit. */ -#define IEEE802154_HW_LBT 0x00000008 -/* Indicates that transceiver will support cca mode setting. */ -#define IEEE802154_HW_CCA_MODE 0x00000010 -/* Indicates that transceiver will support cca ed level setting. */ -#define IEEE802154_HW_CCA_ED_LEVEL 0x00000020 +#define IEEE802154_HW_LBT 0x00000004 /* Indicates that transceiver will support csma (max_be, min_be, csma retries) * settings. */ -#define IEEE802154_HW_CSMA_PARAMS 0x00000040 +#define IEEE802154_HW_CSMA_PARAMS 0x00000008 /* Indicates that transceiver will support ARET frame retries setting. */ -#define IEEE802154_HW_FRAME_RETRIES 0x00000080 +#define IEEE802154_HW_FRAME_RETRIES 0x00000010 /* Indicates that transceiver will support hardware address filter setting. */ -#define IEEE802154_HW_AFILT 0x00000100 +#define IEEE802154_HW_AFILT 0x00000020 /* Indicates that transceiver will support promiscuous mode setting. */ -#define IEEE802154_HW_PROMISCUOUS 0x00000200 +#define IEEE802154_HW_PROMISCUOUS 0x00000040 /* Indicates that receiver omits FCS. */ -#define IEEE802154_HW_RX_OMIT_CKSUM 0x00000400 +#define IEEE802154_HW_RX_OMIT_CKSUM 0x00000080 /* Indicates that receiver will not filter frames with bad checksum. */ -#define IEEE802154_HW_RX_DROP_BAD_CKSUM 0x00000800 +#define IEEE802154_HW_RX_DROP_BAD_CKSUM 0x00000100 /* Indicates that receiver omits FCS and xmitter will add FCS on it's own. */ #define IEEE802154_HW_OMIT_CKSUM (IEEE802154_HW_TX_OMIT_CKSUM | \ IEEE802154_HW_RX_OMIT_CKSUM) -/* This groups the most common CSMA support fields into one. */ -#define IEEE802154_HW_CSMA (IEEE802154_HW_CCA_MODE | \ - IEEE802154_HW_CCA_ED_LEVEL | \ - IEEE802154_HW_CSMA_PARAMS) - -/* This groups the most common ARET support fields into one. */ -#define IEEE802154_HW_ARET (IEEE802154_HW_CSMA | \ - IEEE802154_HW_FRAME_RETRIES) - /* struct ieee802154_ops - callbacks from mac802154 to the driver * * This structure contains various callbacks that the driver may @@ -171,7 +156,7 @@ struct ieee802154_hw { * Returns either zero, or negative errno. * * set_txpower: - * Set radio transmit power in dB. Called with pib_lock held. + * Set radio transmit power in mBm. Called with pib_lock held. * Returns either zero, or negative errno. * * set_lbt @@ -184,7 +169,7 @@ struct ieee802154_hw { * Returns either zero, or negative errno. * * set_cca_ed_level - * Sets the CCA energy detection threshold in dBm. Called with pib_lock + * Sets the CCA energy detection threshold in mBm. Called with pib_lock * held. * Returns either zero, or negative errno. * @@ -213,12 +198,11 @@ struct ieee802154_ops { int (*set_hw_addr_filt)(struct ieee802154_hw *hw, struct ieee802154_hw_addr_filt *filt, unsigned long changed); - int (*set_txpower)(struct ieee802154_hw *hw, s8 dbm); + int (*set_txpower)(struct ieee802154_hw *hw, s32 mbm); int (*set_lbt)(struct ieee802154_hw *hw, bool on); int (*set_cca_mode)(struct ieee802154_hw *hw, const struct wpan_phy_cca *cca); - int (*set_cca_ed_level)(struct ieee802154_hw *hw, - s32 level); + int (*set_cca_ed_level)(struct ieee802154_hw *hw, s32 mbm); int (*set_csma_params)(struct ieee802154_hw *hw, u8 min_be, u8 max_be, u8 retries); int (*set_frame_retries)(struct ieee802154_hw *hw, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index e6bcf55..3d6f48c 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -819,6 +819,7 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, * @use: number of chain references to this table * @flags: table flag (see enum nft_table_flags) * @name: name of the table + * @dev: this table is bound to this device (if any) */ struct nft_table { struct list_head list; @@ -828,6 +829,11 @@ struct nft_table { u32 use; u16 flags; char name[NFT_TABLE_MAXNAMELEN]; + struct net_device *dev; +}; + +enum nft_af_flags { + NFT_AF_NEEDS_DEV = (1 << 0), }; /** @@ -838,6 +844,7 @@ struct nft_table { * @nhooks: number of hooks in this family * @owner: module owner * @tables: used internally + * @flags: family flags * @nops: number of hook ops in this family * @hook_ops_init: initialization function for chain hook ops * @hooks: hookfn overrides for packet validation @@ -848,6 +855,7 @@ struct nft_af_info { unsigned int nhooks; struct module *owner; struct list_head tables; + u32 flags; unsigned int nops; void (*hook_ops_init)(struct nf_hook_ops *, unsigned int); diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 6848b8b..c68926b 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -19,6 +19,7 @@ struct sock; struct local_ports { seqlock_t lock; int range[2]; + bool warned; }; struct ping_group_range { diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index eee608b..c807811 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -13,6 +13,7 @@ struct netns_nftables { struct nft_af_info *inet; struct nft_af_info *arp; struct nft_af_info *bridge; + struct nft_af_info *netdev; unsigned int base_seq; u8 gencursor; }; diff --git a/include/net/nl802154.h b/include/net/nl802154.h index f8b5bc9..0badebd 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -100,6 +100,8 @@ enum nl802154_attrs { NL802154_ATTR_EXTENDED_ADDR, + NL802154_ATTR_WPAN_PHY_CAPS, + /* add attributes here, update the policy in nl802154.c */ __NL802154_ATTR_AFTER_LAST, @@ -120,6 +122,61 @@ enum nl802154_iftype { }; /** + * enum nl802154_wpan_phy_capability_attr - wpan phy capability attributes + * + * @__NL802154_CAP_ATTR_INVALID: attribute number 0 is reserved + * @NL802154_CAP_ATTR_CHANNELS: a nested attribute for nl802154_channel_attr + * @NL802154_CAP_ATTR_TX_POWERS: a nested attribute for + * nl802154_wpan_phy_tx_power + * @NL802154_CAP_ATTR_MIN_CCA_ED_LEVEL: minimum value for cca_ed_level + * @NL802154_CAP_ATTR_MAX_CCA_ED_LEVEL: maxmimum value for cca_ed_level + * @NL802154_CAP_ATTR_CCA_MODES: nl802154_cca_modes flags + * @NL802154_CAP_ATTR_CCA_OPTS: nl802154_cca_opts flags + * @NL802154_CAP_ATTR_MIN_MINBE: minimum of minbe value + * @NL802154_CAP_ATTR_MAX_MINBE: maximum of minbe value + * @NL802154_CAP_ATTR_MIN_MAXBE: minimum of maxbe value + * @NL802154_CAP_ATTR_MAX_MINBE: maximum of maxbe value + * @NL802154_CAP_ATTR_MIN_CSMA_BACKOFFS: minimum of csma backoff value + * @NL802154_CAP_ATTR_MAX_CSMA_BACKOFFS: maximum of csma backoffs value + * @NL802154_CAP_ATTR_MIN_FRAME_RETRIES: minimum of frame retries value + * @NL802154_CAP_ATTR_MAX_FRAME_RETRIES: maximum of frame retries value + * @NL802154_CAP_ATTR_IFTYPES: nl802154_iftype flags + * @NL802154_CAP_ATTR_LBT: nl802154_supported_bool_states flags + * @NL802154_CAP_ATTR_MAX: highest cap attribute currently defined + * @__NL802154_CAP_ATTR_AFTER_LAST: internal use + */ +enum nl802154_wpan_phy_capability_attr { + __NL802154_CAP_ATTR_INVALID, + + NL802154_CAP_ATTR_IFTYPES, + + NL802154_CAP_ATTR_CHANNELS, + NL802154_CAP_ATTR_TX_POWERS, + + NL802154_CAP_ATTR_CCA_ED_LEVELS, + NL802154_CAP_ATTR_CCA_MODES, + NL802154_CAP_ATTR_CCA_OPTS, + + NL802154_CAP_ATTR_MIN_MINBE, + NL802154_CAP_ATTR_MAX_MINBE, + + NL802154_CAP_ATTR_MIN_MAXBE, + NL802154_CAP_ATTR_MAX_MAXBE, + + NL802154_CAP_ATTR_MIN_CSMA_BACKOFFS, + NL802154_CAP_ATTR_MAX_CSMA_BACKOFFS, + + NL802154_CAP_ATTR_MIN_FRAME_RETRIES, + NL802154_CAP_ATTR_MAX_FRAME_RETRIES, + + NL802154_CAP_ATTR_LBT, + + /* keep last */ + __NL802154_CAP_ATTR_AFTER_LAST, + NL802154_CAP_ATTR_MAX = __NL802154_CAP_ATTR_AFTER_LAST - 1 +}; + +/** * enum nl802154_cca_modes - cca modes * * @__NL802154_CCA_INVALID: cca mode number 0 is reserved @@ -162,4 +219,26 @@ enum nl802154_cca_opts { NL802154_CCA_OPT_ATTR_MAX = __NL802154_CCA_OPT_ATTR_AFTER_LAST - 1 }; +/** + * enum nl802154_supported_bool_states - bool states for bool capability entry + * + * @NL802154_SUPPORTED_BOOL_FALSE: indicates to set false + * @NL802154_SUPPORTED_BOOL_TRUE: indicates to set true + * @__NL802154_SUPPORTED_BOOL_INVALD: reserved + * @NL802154_SUPPORTED_BOOL_BOTH: indicates to set true and false + * @__NL802154_SUPPORTED_BOOL_AFTER_LAST: Internal + * @NL802154_SUPPORTED_BOOL_MAX: highest value for bool states + */ +enum nl802154_supported_bool_states { + NL802154_SUPPORTED_BOOL_FALSE, + NL802154_SUPPORTED_BOOL_TRUE, + /* to handle them in a mask */ + __NL802154_SUPPORTED_BOOL_INVALD, + NL802154_SUPPORTED_BOOL_BOTH, + + /* keep last */ + __NL802154_SUPPORTED_BOOL_AFTER_LAST, + NL802154_SUPPORTED_BOOL_MAX = __NL802154_SUPPORTED_BOOL_AFTER_LAST - 1 +}; + #endif /* __NL802154_H */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index c56a438..ce13cf2 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -574,11 +574,14 @@ static inline void sctp_v6_map_v4(union sctp_addr *addr) /* Map v4 address to v4-mapped v6 address */ static inline void sctp_v4_map_v6(union sctp_addr *addr) { + __be16 port; + + port = addr->v4.sin_port; + addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr; + addr->v6.sin6_port = port; addr->v6.sin6_family = AF_INET6; addr->v6.sin6_flowinfo = 0; addr->v6.sin6_scope_id = 0; - addr->v6.sin6_port = addr->v4.sin_port; - addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr; addr->v6.sin6_addr.s6_addr32[0] = 0; addr->v6.sin6_addr.s6_addr32[1] = 0; addr->v6.sin6_addr.s6_addr32[2] = htonl(0x0000ffff); diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index d61be72..5f12257 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -1,9 +1,7 @@ #ifndef TARGET_CORE_BACKEND_H #define TARGET_CORE_BACKEND_H -#define TRANSPORT_PLUGIN_PHBA_PDEV 1 -#define TRANSPORT_PLUGIN_VHBA_PDEV 2 -#define TRANSPORT_PLUGIN_VHBA_VDEV 3 +#define TRANSPORT_FLAG_PASSTHROUGH 1 struct target_backend_cits { struct config_item_type tb_dev_cit; @@ -22,7 +20,7 @@ struct se_subsystem_api { char inquiry_rev[4]; struct module *owner; - u8 transport_type; + u8 transport_flags; int (*attach_hba)(struct se_hba *, u32); void (*detach_hba)(struct se_hba *); @@ -138,5 +136,7 @@ int se_dev_set_queue_depth(struct se_device *, u32); int se_dev_set_max_sectors(struct se_device *, u32); int se_dev_set_optimal_sectors(struct se_device *, u32); int se_dev_set_block_size(struct se_device *, u32); +sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, + sense_reason_t (*exec_cmd)(struct se_cmd *cmd)); #endif /* TARGET_CORE_BACKEND_H */ diff --git a/include/target/target_core_configfs.h b/include/target/target_core_configfs.h index 25bb04c..b99c011 100644 --- a/include/target/target_core_configfs.h +++ b/include/target/target_core_configfs.h @@ -40,8 +40,6 @@ struct target_fabric_configfs { struct config_item *tf_fabric; /* Passed from fabric modules */ struct config_item_type *tf_fabric_cit; - /* Pointer to target core subsystem */ - struct configfs_subsystem *tf_subsys; /* Pointer to fabric's struct module */ struct module *tf_module; struct target_core_fabric_ops tf_ops; diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 17c7f5ac..0f4dc37 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -4,7 +4,6 @@ struct target_core_fabric_ops { struct module *module; const char *name; - struct configfs_subsystem *tf_subsys; char *(*get_fabric_name)(void); u8 (*get_fabric_proto_ident)(struct se_portal_group *); char *(*tpg_get_wwn)(struct se_portal_group *); @@ -109,6 +108,9 @@ struct target_core_fabric_ops { int target_register_template(const struct target_core_fabric_ops *fo); void target_unregister_template(const struct target_core_fabric_ops *fo); +int target_depend_item(struct config_item *item); +void target_undepend_item(struct config_item *item); + struct se_session *transport_init_session(enum target_prot_op); int transport_alloc_session_tags(struct se_session *, unsigned int, unsigned int); diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 81ea598..f7554fd 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -140,19 +140,42 @@ DEFINE_EVENT(kmem_free, kfree, TP_ARGS(call_site, ptr) ); -DEFINE_EVENT(kmem_free, kmem_cache_free, +DEFINE_EVENT_CONDITION(kmem_free, kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr), - TP_ARGS(call_site, ptr) + TP_ARGS(call_site, ptr), + + /* + * This trace can be potentially called from an offlined cpu. + * Since trace points use RCU and RCU should not be used from + * offline cpus, filter such calls out. + * While this trace can be called from a preemptable section, + * it has no impact on the condition since tasks can migrate + * only from online cpus to other online cpus. Thus its safe + * to use raw_smp_processor_id. + */ + TP_CONDITION(cpu_online(raw_smp_processor_id())) ); -TRACE_EVENT(mm_page_free, +TRACE_EVENT_CONDITION(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), + + /* + * This trace can be potentially called from an offlined cpu. + * Since trace points use RCU and RCU should not be used from + * offline cpus, filter such calls out. + * While this trace can be called from a preemptable section, + * it has no impact on the condition since tasks can migrate + * only from online cpus to other online cpus. Thus its safe + * to use raw_smp_processor_id. + */ + TP_CONDITION(cpu_online(raw_smp_processor_id())), + TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) @@ -253,12 +276,35 @@ DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_ARGS(page, order, migratetype) ); -DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain, +TRACE_EVENT_CONDITION(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), + /* + * This trace can be potentially called from an offlined cpu. + * Since trace points use RCU and RCU should not be used from + * offline cpus, filter such calls out. + * While this trace can be called from a preemptable section, + * it has no impact on the condition since tasks can migrate + * only from online cpus to other online cpus. Thus its safe + * to use raw_smp_processor_id. + */ + TP_CONDITION(cpu_online(raw_smp_processor_id())), + + TP_STRUCT__entry( + __field( unsigned long, pfn ) + __field( unsigned int, order ) + __field( int, migratetype ) + ), + + TP_fast_assign( + __entry->pfn = page ? page_to_pfn(page) : -1UL; + __entry->order = order; + __entry->migratetype = migratetype; + ), + TP_printk("page=%p pfn=%lu order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f0a9af8b..42aa19a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -220,6 +220,16 @@ enum bpf_func_id { * Return: 0 on success */ BPF_FUNC_tail_call, + + /** + * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev + * @skb: pointer to skb + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_clone_redirect, __BPF_FUNC_MAX_ID, }; @@ -236,6 +246,8 @@ struct __sk_buff { __u32 vlan_tci; __u32 vlan_proto; __u32 priority; + __u32 ingress_ifindex; + __u32 ifindex; }; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index ae832b4..0594933 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -796,6 +796,31 @@ struct ethtool_rx_flow_spec { __u32 location; }; +/* How rings are layed out when accessing virtual functions or + * offloaded queues is device specific. To allow users to do flow + * steering and specify these queues the ring cookie is partitioned + * into a 32bit queue index with an 8 bit virtual function id. + * This also leaves the 3bytes for further specifiers. It is possible + * future devices may support more than 256 virtual functions if + * devices start supporting PCIe w/ARI. However at the moment I + * do not know of any devices that support this so I do not reserve + * space for this at this time. If a future patch consumes the next + * byte it should be aware of this possiblity. + */ +#define ETHTOOL_RX_FLOW_SPEC_RING 0x00000000FFFFFFFFLL +#define ETHTOOL_RX_FLOW_SPEC_RING_VF 0x000000FF00000000LL +#define ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF 32 +static inline __u64 ethtool_get_flow_spec_ring(__u64 ring_cookie) +{ + return ETHTOOL_RX_FLOW_SPEC_RING & ring_cookie; +}; + +static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie) +{ + return (ETHTOOL_RX_FLOW_SPEC_RING_VF & ring_cookie) >> + ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF; +}; + /** * struct ethtool_rxnfc - command to get or set RX flow classification rules * @cmd: Specific command number - %ETHTOOL_GRXFH, %ETHTOOL_SRXFH, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index afccc93..1737b7a 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -395,6 +395,8 @@ enum { IFLA_GENEVE_UNSPEC, IFLA_GENEVE_ID, IFLA_GENEVE_REMOTE, + IFLA_GENEVE_TTL, + IFLA_GENEVE_TOS, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h index 2be7bd1..f6598d1 100644 --- a/include/uapi/linux/ipv6_route.h +++ b/include/uapi/linux/ipv6_route.h @@ -34,6 +34,7 @@ #define RTF_PREF(pref) ((pref) << 27) #define RTF_PREF_MASK 0x18000000 +#define RTF_PCPU 0x40000000 #define RTF_LOCAL 0x80000000 diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 5fa1cd0..89a671e 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -146,12 +146,14 @@ enum nft_table_flags { * @NFTA_TABLE_NAME: name of the table (NLA_STRING) * @NFTA_TABLE_FLAGS: bitmask of enum nft_table_flags (NLA_U32) * @NFTA_TABLE_USE: number of chains in this table (NLA_U32) + * @NFTA_TABLE_DEV: net device name (NLA_STRING) */ enum nft_table_attributes { NFTA_TABLE_UNSPEC, NFTA_TABLE_NAME, NFTA_TABLE_FLAGS, NFTA_TABLE_USE, + NFTA_TABLE_DEV, __NFTA_TABLE_MAX }; #define NFTA_TABLE_MAX (__NFTA_TABLE_MAX - 1) diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index bbd49a0..1dab776 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -153,6 +153,8 @@ enum ovs_packet_cmd { * flow key against the kernel's. * @OVS_PACKET_ATTR_ACTIONS: Contains actions for the packet. Used * for %OVS_PACKET_CMD_EXECUTE. It has nested %OVS_ACTION_ATTR_* attributes. + * Also used in upcall when %OVS_ACTION_ATTR_USERSPACE has optional + * %OVS_USERSPACE_ATTR_ACTIONS attribute. * @OVS_PACKET_ATTR_USERDATA: Present for an %OVS_PACKET_CMD_ACTION * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an * %OVS_USERSPACE_ATTR_USERDATA attribute, with the same length and content @@ -528,6 +530,7 @@ enum ovs_sample_attr { * copied to the %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA. * @OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: If present, u32 output port to get * tunnel info. + * @OVS_USERSPACE_ATTR_ACTIONS: If present, send actions with upcall. */ enum ovs_userspace_attr { OVS_USERSPACE_ATTR_UNSPEC, @@ -535,6 +538,7 @@ enum ovs_userspace_attr { OVS_USERSPACE_ATTR_USERDATA, /* Optional user-specified cookie. */ OVS_USERSPACE_ATTR_EGRESS_TUN_PORT, /* Optional, u32 output port * to get tunnel info. */ + OVS_USERSPACE_ATTR_ACTIONS, /* Optional flag to get actions. */ __OVS_USERSPACE_ATTR_MAX }; diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index 9195095..0f9265c 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -38,6 +38,8 @@ #define RDS_IB_ABI_VERSION 0x301 +#define SOL_RDS 276 + /* * setsockopt/getsockopt for SOL_RDS */ @@ -48,6 +50,14 @@ #define RDS_RECVERR 5 #define RDS_CONG_MONITOR 6 #define RDS_GET_MR_FOR_DEST 7 +#define SO_RDS_TRANSPORT 8 + +/* supported values for SO_RDS_TRANSPORT */ +#define RDS_TRANS_IB 0 +#define RDS_TRANS_IWARP 1 +#define RDS_TRANS_TCP 2 +#define RDS_TRANS_COUNT 3 +#define RDS_TRANS_NONE (~0) /* * Control message types for SOL_RDS. diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h index 984169a..d7f1cbc 100644 --- a/include/uapi/linux/virtio_balloon.h +++ b/include/uapi/linux/virtio_balloon.h @@ -26,6 +26,7 @@ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #include <linux/types.h> +#include <linux/virtio_types.h> #include <linux/virtio_ids.h> #include <linux/virtio_config.h> diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 614bcd4..cb31229 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -202,7 +202,7 @@ static int prog_array_map_update_elem(struct bpf_map *map, void *key, old_prog = xchg(array->prog + index, prog); if (old_prog) - bpf_prog_put(old_prog); + bpf_prog_put_rcu(old_prog); return 0; } @@ -218,7 +218,7 @@ static int prog_array_map_delete_elem(struct bpf_map *map, void *key) old_prog = xchg(array->prog + index, NULL); if (old_prog) { - bpf_prog_put(old_prog); + bpf_prog_put_rcu(old_prog); return 0; } else { return -ENOENT; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index d44b25c..1e00aa3 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -26,9 +26,10 @@ #include <linux/vmalloc.h> #include <linux/random.h> #include <linux/moduleloader.h> -#include <asm/unaligned.h> #include <linux/bpf.h> +#include <asm/unaligned.h> + /* Registers */ #define BPF_R0 regs[BPF_REG_0] #define BPF_R1 regs[BPF_REG_1] @@ -62,6 +63,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns ptr = skb_network_header(skb) + k - SKF_NET_OFF; else if (k >= SKF_LL_OFF) ptr = skb_mac_header(skb) + k - SKF_LL_OFF; + if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; @@ -176,15 +178,6 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return 0; } -const struct bpf_func_proto bpf_tail_call_proto = { - .func = NULL, - .gpl_only = false, - .ret_type = RET_VOID, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_ANYTHING, -}; - /** * __bpf_prog_run - run eBPF program on a given context * @ctx: is the data we are operating on @@ -650,36 +643,35 @@ load_byte: return 0; } -void __weak bpf_int_jit_compile(struct bpf_prog *prog) -{ -} - -bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) +bool bpf_prog_array_compatible(struct bpf_array *array, + const struct bpf_prog *fp) { - if (array->owner_prog_type) { - if (array->owner_prog_type != fp->type) - return false; - if (array->owner_jited != fp->jited) - return false; - } else { + if (!array->owner_prog_type) { + /* There's no owner yet where we could check for + * compatibility. + */ array->owner_prog_type = fp->type; array->owner_jited = fp->jited; + + return true; } - return true; + + return array->owner_prog_type == fp->type && + array->owner_jited == fp->jited; } -static int check_tail_call(const struct bpf_prog *fp) +static int bpf_check_tail_call(const struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; int i; for (i = 0; i < aux->used_map_cnt; i++) { + struct bpf_map *map = aux->used_maps[i]; struct bpf_array *array; - struct bpf_map *map; - map = aux->used_maps[i]; if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) continue; + array = container_of(map, struct bpf_array, map); if (!bpf_prog_array_compatible(array, fp)) return -EINVAL; @@ -689,22 +681,25 @@ static int check_tail_call(const struct bpf_prog *fp) } /** - * bpf_prog_select_runtime - select execution runtime for BPF program + * bpf_prog_select_runtime - select exec runtime for BPF program * @fp: bpf_prog populated with internal BPF program * - * try to JIT internal BPF program, if JIT is not available select interpreter - * BPF program will be executed via BPF_PROG_RUN() macro + * Try to JIT eBPF program, if JIT is not available, use interpreter. + * The BPF program will be executed via BPF_PROG_RUN() macro. */ int bpf_prog_select_runtime(struct bpf_prog *fp) { fp->bpf_func = (void *) __bpf_prog_run; - /* Probe if internal BPF can be JITed */ bpf_int_jit_compile(fp); - /* Lock whole bpf_prog as read-only */ bpf_prog_lock_ro(fp); - return check_tail_call(fp); + /* The tail call compatibility check can only be done at + * this late stage as we need to determine, if we deal + * with JITed or non JITed program concatenations and not + * all eBPF JITs might immediately support all features. + */ + return bpf_check_tail_call(fp); } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); @@ -734,6 +729,22 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; +const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; + +/* Always built-in helper functions. */ +const struct bpf_func_proto bpf_tail_call_proto = { + .func = NULL, + .gpl_only = false, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, +}; + +/* For classic BPF JITs that don't implement bpf_int_jit_compile(). */ +void __weak bpf_int_jit_compile(struct bpf_prog *prog) +{ +} /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index bd7f598..7ad5d88 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -13,6 +13,7 @@ #include <linux/rcupdate.h> #include <linux/random.h> #include <linux/smp.h> +#include <linux/ktime.h> /* If kernel subsystem is allowing eBPF programs to call this function, * inside its own verifier_ops->get_func_proto() callback it should return @@ -44,11 +45,11 @@ static u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) } const struct bpf_func_proto bpf_map_lookup_elem_proto = { - .func = bpf_map_lookup_elem, - .gpl_only = false, - .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MAP_KEY, + .func = bpf_map_lookup_elem, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, }; static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) @@ -63,13 +64,13 @@ static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) } const struct bpf_func_proto bpf_map_update_elem_proto = { - .func = bpf_map_update_elem, - .gpl_only = false, - .ret_type = RET_INTEGER, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MAP_KEY, - .arg3_type = ARG_PTR_TO_MAP_VALUE, - .arg4_type = ARG_ANYTHING, + .func = bpf_map_update_elem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, + .arg3_type = ARG_PTR_TO_MAP_VALUE, + .arg4_type = ARG_ANYTHING, }; static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) @@ -83,11 +84,11 @@ static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) } const struct bpf_func_proto bpf_map_delete_elem_proto = { - .func = bpf_map_delete_elem, - .gpl_only = false, - .ret_type = RET_INTEGER, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MAP_KEY, + .func = bpf_map_delete_elem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, }; static u64 bpf_get_prandom_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) @@ -111,3 +112,15 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto = { .gpl_only = false, .ret_type = RET_INTEGER, }; + +static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + /* NMI safe access to clock monotonic */ + return ktime_get_mono_fast_ns(); +} + +const struct bpf_func_proto bpf_ktime_get_ns_proto = { + .func = bpf_ktime_get_ns, + .gpl_only = true, + .ret_type = RET_INTEGER, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 98a69bd..a1b14d1 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -432,6 +432,23 @@ static void free_used_maps(struct bpf_prog_aux *aux) kfree(aux->used_maps); } +static void __prog_put_rcu(struct rcu_head *rcu) +{ + struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); + + free_used_maps(aux); + bpf_prog_free(aux->prog); +} + +/* version of bpf_prog_put() that is called after a grace period */ +void bpf_prog_put_rcu(struct bpf_prog *prog) +{ + if (atomic_dec_and_test(&prog->aux->refcnt)) { + prog->aux->prog = prog; + call_rcu(&prog->aux->rcu, __prog_put_rcu); + } +} + void bpf_prog_put(struct bpf_prog *prog) { if (atomic_dec_and_test(&prog->aux->refcnt)) { @@ -445,7 +462,7 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) { struct bpf_prog *prog = filp->private_data; - bpf_prog_put(prog); + bpf_prog_put_rcu(prog); return 0; } diff --git a/kernel/module.c b/kernel/module.c index 42a1d2a..cfc9e84 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3370,6 +3370,9 @@ static int load_module(struct load_info *info, const char __user *uargs, module_bug_cleanup(mod); mutex_unlock(&module_mutex); + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_GOING, mod); + /* we can't deallocate the module until we clear memory protection */ unset_module_init_ro_nx(mod); unset_module_core_ro_nx(mod); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 76d4bd9..93ef7190 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -266,21 +266,23 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) /* * Divide a ktime value by a nanosecond value */ -u64 __ktime_divns(const ktime_t kt, s64 div) +s64 __ktime_divns(const ktime_t kt, s64 div) { - u64 dclc; int sft = 0; + s64 dclc; + u64 tmp; dclc = ktime_to_ns(kt); + tmp = dclc < 0 ? -dclc : dclc; + /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; div >>= 1; } - dclc >>= sft; - do_div(dclc, (unsigned long) div); - - return dclc; + tmp >>= sft; + do_div(tmp, (unsigned long) div); + return dclc < 0 ? -tmp : tmp; } EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 646445e..50c4015 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -79,18 +79,6 @@ static const struct bpf_func_proto bpf_probe_read_proto = { .arg3_type = ARG_ANYTHING, }; -static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) -{ - /* NMI safe access to clock monotonic */ - return ktime_get_mono_fast_ns(); -} - -static const struct bpf_func_proto bpf_ktime_get_ns_proto = { - .func = bpf_ktime_get_ns, - .gpl_only = true, - .ret_type = RET_INTEGER, -}; - /* * limited trace_printk() * only %d %u %x %ld %lu %lx %lld %llu %llx %p conversion specifiers allowed diff --git a/lib/cpumask.c b/lib/cpumask.c index 830dd5d..5f62708 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -139,64 +139,42 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask) #endif /** - * cpumask_set_cpu_local_first - set i'th cpu with local numa cpu's first - * + * cpumask_local_spread - select the i'th cpu with local numa cpu's first * @i: index number - * @numa_node: local numa_node - * @dstp: cpumask with the relevant cpu bit set according to the policy + * @node: local numa_node * - * This function sets the cpumask according to a numa aware policy. - * cpumask could be used as an affinity hint for the IRQ related to a - * queue. When the policy is to spread queues across cores - local cores - * first. + * This function selects an online CPU according to a numa aware policy; + * local cpus are returned first, followed by non-local ones, then it + * wraps around. * - * Returns 0 on success, -ENOMEM for no memory, and -EAGAIN when failed to set - * the cpu bit and need to re-call the function. + * It's not very efficient, but useful for setup. */ -int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp) +unsigned int cpumask_local_spread(unsigned int i, int node) { - cpumask_var_t mask; int cpu; - int ret = 0; - - if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; + /* Wrap: we always want a cpu. */ i %= num_online_cpus(); - if (numa_node == -1 || !cpumask_of_node(numa_node)) { - /* Use all online cpu's for non numa aware system */ - cpumask_copy(mask, cpu_online_mask); + if (node == -1) { + for_each_cpu(cpu, cpu_online_mask) + if (i-- == 0) + return cpu; } else { - int n; - - cpumask_and(mask, - cpumask_of_node(numa_node), cpu_online_mask); - - n = cpumask_weight(mask); - if (i >= n) { - i -= n; - - /* If index > number of local cpu's, mask out local - * cpu's - */ - cpumask_andnot(mask, cpu_online_mask, mask); + /* NUMA first. */ + for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask) + if (i-- == 0) + return cpu; + + for_each_cpu(cpu, cpu_online_mask) { + /* Skip NUMA nodes, done above. */ + if (cpumask_test_cpu(cpu, cpumask_of_node(node))) + continue; + + if (i-- == 0) + return cpu; } } - - for_each_cpu(cpu, mask) { - if (--i < 0) - goto out; - } - - ret = -EAGAIN; - -out: - free_cpumask_var(mask); - - if (!ret) - cpumask_set_cpu(cpu, dstp); - - return ret; + BUG(); } -EXPORT_SYMBOL(cpumask_set_cpu_local_first); +EXPORT_SYMBOL(cpumask_local_spread); diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 48144cd..f051d69 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -197,13 +197,13 @@ static int percpu_counter_hotcpu_callback(struct notifier_block *nb, * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ -int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) +int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ - if (abs(count - rhs) > (percpu_counter_batch*num_online_cpus())) { + if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else @@ -218,7 +218,7 @@ int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) else return 0; } -EXPORT_SYMBOL(percpu_counter_compare); +EXPORT_SYMBOL(__percpu_counter_compare); static int __init percpu_counter_startup(void) { diff --git a/lib/test_bpf.c b/lib/test_bpf.c index c07b8e7..7f58c73 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -314,6 +314,47 @@ static int bpf_fill_maxinsns10(struct bpf_test *self) return 0; } +static int __bpf_fill_ja(struct bpf_test *self, unsigned int len, + unsigned int plen) +{ + struct sock_filter *insn; + unsigned int rlen; + int i, j; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + rlen = (len % plen) - 1; + + for (i = 0; i + plen < len; i += plen) + for (j = 0; j < plen; j++) + insn[i + j] = __BPF_JUMP(BPF_JMP | BPF_JA, + plen - 1 - j, 0, 0); + for (j = 0; j < rlen; j++) + insn[i + j] = __BPF_JUMP(BPF_JMP | BPF_JA, rlen - 1 - j, + 0, 0); + + insn[len - 1] = __BPF_STMT(BPF_RET | BPF_K, 0xababcbac); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +static int bpf_fill_maxinsns11(struct bpf_test *self) +{ + /* Hits 70 passes on x86_64, so cannot get JITed there. */ + return __bpf_fill_ja(self, BPF_MAXINSNS, 68); +} + +static int bpf_fill_ja(struct bpf_test *self) +{ + /* Hits exactly 11 passes on x86_64 JIT. */ + return __bpf_fill_ja(self, 12, 9); +} + static struct bpf_test tests[] = { { "TAX", @@ -4252,6 +4293,14 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + { + "JMP_JA: Jump, gap, jump, ...", + { }, + CLASSIC | FLAG_NO_DATA, + { }, + { { 0, 0xababcbac } }, + .fill_helper = bpf_fill_ja, + }, { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Maximum possible literals", { }, @@ -4335,6 +4384,14 @@ static struct bpf_test tests[] = { { { 0, 0xabababac } }, .fill_helper = bpf_fill_maxinsns10, }, + { + "BPF_MAXINSNS: Jump, gap, jump, ...", + { }, + CLASSIC | FLAG_NO_DATA, + { }, + { { 0, 0xababcbac } }, + .fill_helper = bpf_fill_maxinsns11, + }, }; static struct net_device dev; diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 59555f0..d2cd9de 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -618,6 +618,92 @@ out: return err; } +static struct sk_buff **vlan_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + struct sk_buff *p, **pp = NULL; + struct vlan_hdr *vhdr; + unsigned int hlen, off_vlan; + const struct packet_offload *ptype; + __be16 type; + int flush = 1; + + off_vlan = skb_gro_offset(skb); + hlen = off_vlan + sizeof(*vhdr); + vhdr = skb_gro_header_fast(skb, off_vlan); + if (skb_gro_header_hard(skb, hlen)) { + vhdr = skb_gro_header_slow(skb, hlen, off_vlan); + if (unlikely(!vhdr)) + goto out; + } + + type = vhdr->h_vlan_encapsulated_proto; + + rcu_read_lock(); + ptype = gro_find_receive_by_type(type); + if (!ptype) + goto out_unlock; + + flush = 0; + + for (p = *head; p; p = p->next) { + struct vlan_hdr *vhdr2; + + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + vhdr2 = (struct vlan_hdr *)(p->data + off_vlan); + if (compare_vlan_header(vhdr, vhdr2)) + NAPI_GRO_CB(p)->same_flow = 0; + } + + skb_gro_pull(skb, sizeof(*vhdr)); + skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr)); + pp = ptype->callbacks.gro_receive(head, skb); + +out_unlock: + rcu_read_unlock(); +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int vlan_gro_complete(struct sk_buff *skb, int nhoff) +{ + struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + nhoff); + __be16 type = vhdr->h_vlan_encapsulated_proto; + struct packet_offload *ptype; + int err = -ENOENT; + + rcu_read_lock(); + ptype = gro_find_complete_by_type(type); + if (ptype) + err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(*vhdr)); + + rcu_read_unlock(); + return err; +} + +static struct packet_offload vlan_packet_offloads[] __read_mostly = { + { + .type = cpu_to_be16(ETH_P_8021Q), + .priority = 10, + .callbacks = { + .gro_receive = vlan_gro_receive, + .gro_complete = vlan_gro_complete, + }, + }, + { + .type = cpu_to_be16(ETH_P_8021AD), + .priority = 10, + .callbacks = { + .gro_receive = vlan_gro_receive, + .gro_complete = vlan_gro_complete, + }, + }, +}; + static int __net_init vlan_init_net(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); @@ -645,6 +731,7 @@ static struct pernet_operations vlan_net_ops = { static int __init vlan_proto_init(void) { int err; + unsigned int i; pr_info("%s v%s\n", vlan_fullname, vlan_version); @@ -668,6 +755,9 @@ static int __init vlan_proto_init(void) if (err < 0) goto err5; + for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++) + dev_add_offload(&vlan_packet_offloads[i]); + vlan_ioctl_set(vlan_ioctl_handler); return 0; @@ -685,7 +775,13 @@ err0: static void __exit vlan_cleanup_module(void) { + unsigned int i; + vlan_ioctl_set(NULL); + + for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++) + dev_remove_offload(&vlan_packet_offloads[i]); + vlan_netlink_fini(); unregister_netdevice_notifier(&vlan_notifier_block); diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index eb7d8c03..21434ab 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # -# Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # @@ -20,7 +20,7 @@ obj-$(CONFIG_BATMAN_ADV) += batman-adv.o batman-adv-y += bat_iv_ogm.o batman-adv-y += bitarray.o batman-adv-$(CONFIG_BATMAN_ADV_BLA) += bridge_loop_avoidance.o -batman-adv-y += debugfs.o +batman-adv-$(CONFIG_DEBUG_FS) += debugfs.o batman-adv-$(CONFIG_BATMAN_ADV_DAT) += distributed-arp-table.o batman-adv-y += fragmentation.o batman-adv-y += gateway_client.o @@ -29,6 +29,7 @@ batman-adv-y += hard-interface.o batman-adv-y += hash.o batman-adv-y += icmp_socket.o batman-adv-y += main.o +batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o batman-adv-y += originator.o batman-adv-y += routing.o @@ -36,4 +37,3 @@ batman-adv-y += send.o batman-adv-y += soft-interface.o batman-adv-y += sysfs.o batman-adv-y += translation-table.o -batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 4e49666..4e59cf3 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 00e00e0..4e93d2d 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -28,7 +28,7 @@ /** * enum batadv_dup_status - duplicate status - * @BATADV_NO_DUP: the packet is a duplicate + * @BATADV_NO_DUP: the packet is no duplicate * @BATADV_ORIG_DUP: OGM is a duplicate in the originator (but not for the * neighbor) * @BATADV_NEIGH_DUP: OGM is a duplicate for the neighbor @@ -55,7 +55,7 @@ static void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, } /** - * batadv_ring_buffer_set - compute the average of all non-zero values stored + * batadv_ring_buffer_avg - compute the average of all non-zero values stored * in the given ring buffer * @lq_recv: pointer to the ring buffer * @@ -64,7 +64,9 @@ static void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, static uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]) { const uint8_t *ptr; - uint16_t count = 0, i = 0, sum = 0; + uint16_t count = 0; + uint16_t i = 0; + uint16_t sum = 0; ptr = lq_recv; @@ -308,7 +310,6 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) struct batadv_ogm_packet *batadv_ogm_packet; unsigned char *ogm_buff; uint32_t random_seqno; - int res = -ENOMEM; /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); @@ -317,7 +318,7 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) hard_iface->bat_iv.ogm_buff_len = BATADV_OGM_HLEN; ogm_buff = kmalloc(hard_iface->bat_iv.ogm_buff_len, GFP_ATOMIC); if (!ogm_buff) - goto out; + return -ENOMEM; hard_iface->bat_iv.ogm_buff = ogm_buff; @@ -329,10 +330,7 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) batadv_ogm_packet->reserved = 0; batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE; - res = 0; - -out: - return res; + return 0; } static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface) @@ -396,8 +394,8 @@ static uint8_t batadv_hop_penalty(uint8_t tq, } /* is there another aggregated packet here? */ -static int batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, - __be16 tvlv_len) +static bool batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, + __be16 tvlv_len) { int next_buff_pos = 0; @@ -413,7 +411,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - char *fwd_str; + const char *fwd_str; uint8_t packet_num; int16_t buff_pos; struct batadv_ogm_packet *batadv_ogm_packet; @@ -548,58 +546,62 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, * - the send time is within our MAX_AGGREGATION_MS time * - the resulting packet wont be bigger than * MAX_AGGREGATION_BYTES + * otherwise aggregation is not possible */ - if (time_before(send_time, forw_packet->send_time) && - time_after_eq(aggregation_end_time, forw_packet->send_time) && - (aggregated_bytes <= BATADV_MAX_AGGREGATION_BYTES)) { - /* check aggregation compatibility - * -> direct link packets are broadcasted on - * their interface only - * -> aggregate packet if the current packet is - * a "global" packet as well as the base - * packet - */ - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) - goto out; - - /* packet is not leaving on the same interface. */ - if (forw_packet->if_outgoing != if_outgoing) - goto out; + if (!time_before(send_time, forw_packet->send_time) || + !time_after_eq(aggregation_end_time, forw_packet->send_time)) + return false; + + if (aggregated_bytes > BATADV_MAX_AGGREGATION_BYTES) + return false; + + /* packet is not leaving on the same interface. */ + if (forw_packet->if_outgoing != if_outgoing) + return false; + + /* check aggregation compatibility + * -> direct link packets are broadcasted on + * their interface only + * -> aggregate packet if the current packet is + * a "global" packet as well as the base + * packet + */ + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + return false; - /* packets without direct link flag and high TTL - * are flooded through the net - */ - if ((!directlink) && - (!(batadv_ogm_packet->flags & BATADV_DIRECTLINK)) && - (batadv_ogm_packet->ttl != 1) && - - /* own packets originating non-primary - * interfaces leave only that interface - */ - ((!forw_packet->own) || - (forw_packet->if_incoming == primary_if))) { - res = true; - goto out; - } + /* packets without direct link flag and high TTL + * are flooded through the net + */ + if (!directlink && + !(batadv_ogm_packet->flags & BATADV_DIRECTLINK) && + batadv_ogm_packet->ttl != 1 && + + /* own packets originating non-primary + * interfaces leave only that interface + */ + (!forw_packet->own || + forw_packet->if_incoming == primary_if)) { + res = true; + goto out; + } - /* if the incoming packet is sent via this one - * interface only - we still can aggregate - */ - if ((directlink) && - (new_bat_ogm_packet->ttl == 1) && - (forw_packet->if_incoming == if_incoming) && - - /* packets from direct neighbors or - * own secondary interface packets - * (= secondary interface packets in general) - */ - (batadv_ogm_packet->flags & BATADV_DIRECTLINK || - (forw_packet->own && - forw_packet->if_incoming != primary_if))) { - res = true; - goto out; - } + /* if the incoming packet is sent via this one + * interface only - we still can aggregate + */ + if (directlink && + new_bat_ogm_packet->ttl == 1 && + forw_packet->if_incoming == if_incoming && + + /* packets from direct neighbors or + * own secondary interface packets + * (= secondary interface packets in general) + */ + (batadv_ogm_packet->flags & BATADV_DIRECTLINK || + (forw_packet->own && + forw_packet->if_incoming != primary_if))) { + res = true; + goto out; } out: @@ -642,19 +644,16 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, if (!batadv_atomic_dec_not_zero(&bat_priv->batman_queue_left)) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "batman packet queue full\n"); - goto out; + goto out_free_outgoing; } } forw_packet_aggr = kmalloc(sizeof(*forw_packet_aggr), GFP_ATOMIC); - if (!forw_packet_aggr) { - if (!own_packet) - atomic_inc(&bat_priv->batman_queue_left); - goto out; - } + if (!forw_packet_aggr) + goto out_nomem; - if ((atomic_read(&bat_priv->aggregated_ogms)) && - (packet_len < BATADV_MAX_AGGREGATION_BYTES)) + if (atomic_read(&bat_priv->aggregated_ogms) && + packet_len < BATADV_MAX_AGGREGATION_BYTES) skb_size = BATADV_MAX_AGGREGATION_BYTES; else skb_size = packet_len; @@ -662,12 +661,8 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, skb_size += ETH_HLEN; forw_packet_aggr->skb = netdev_alloc_skb_ip_align(NULL, skb_size); - if (!forw_packet_aggr->skb) { - if (!own_packet) - atomic_inc(&bat_priv->batman_queue_left); - kfree(forw_packet_aggr); - goto out; - } + if (!forw_packet_aggr->skb) + goto out_free_forw_packet; forw_packet_aggr->skb->priority = TC_PRIO_CONTROL; skb_reserve(forw_packet_aggr->skb, ETH_HLEN); @@ -699,7 +694,12 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, send_time - jiffies); return; -out: +out_free_forw_packet: + kfree(forw_packet_aggr); +out_nomem: + if (!own_packet) + atomic_inc(&bat_priv->batman_queue_left); +out_free_outgoing: batadv_hardif_free_ref(if_outgoing); out_free_incoming: batadv_hardif_free_ref(if_incoming); @@ -752,13 +752,13 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, unsigned long max_aggregation_jiffies; batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff; - direct_link = batadv_ogm_packet->flags & BATADV_DIRECTLINK ? 1 : 0; + direct_link = !!(batadv_ogm_packet->flags & BATADV_DIRECTLINK); max_aggregation_jiffies = msecs_to_jiffies(BATADV_MAX_AGGREGATION_MS); /* find position for the packet in the forward queue */ spin_lock_bh(&bat_priv->forw_bat_list_lock); /* own packets are not to be aggregated */ - if ((atomic_read(&bat_priv->aggregated_ogms)) && (!own_packet)) { + if (atomic_read(&bat_priv->aggregated_ogms) && !own_packet) { hlist_for_each_entry(forw_packet_pos, &bat_priv->forw_bat_list, list) { if (batadv_iv_ogm_can_aggregate(batadv_ogm_packet, @@ -1034,9 +1034,10 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, batadv_orig_node_free_ref(orig_tmp); if (!neigh_node) goto unlock; - } else + } else { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Updating existing last-hop neighbor of originator\n"); + } rcu_read_unlock(); neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); @@ -1081,7 +1082,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, * won't consider it either */ if (router_ifinfo && - (neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg)) { + neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg) { orig_node_tmp = router->orig_node; spin_lock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); if_num = router->if_incoming->if_num; @@ -1356,8 +1357,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, out: spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); batadv_orig_node_free_ref(orig_node); - if (orig_ifinfo) - batadv_orig_ifinfo_free_ref(orig_ifinfo); + batadv_orig_ifinfo_free_ref(orig_ifinfo); return ret; } diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index e3da07a..40e4a2a 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 2acaafe..be497be 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index ac4b96e..fa941cd 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 43c985d..1f506d3 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index a4972874..4611808 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -482,11 +482,7 @@ rem_attr: debugfs_remove_recursive(hard_iface->debug_dir); hard_iface->debug_dir = NULL; out: -#ifdef CONFIG_DEBUG_FS return -ENOMEM; -#else - return 0; -#endif /* CONFIG_DEBUG_FS */ } /** @@ -541,11 +537,7 @@ rem_attr: debugfs_remove_recursive(bat_priv->debug_dir); bat_priv->debug_dir = NULL; out: -#ifdef CONFIG_DEBUG_FS return -ENOMEM; -#else - return 0; -#endif /* CONFIG_DEBUG_FS */ } void batadv_debugfs_del_meshif(struct net_device *dev) diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 37c4d6d..ed25605 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -20,6 +20,8 @@ #define BATADV_DEBUGFS_SUBDIR "batman_adv" +#if IS_ENABLED(CONFIG_DEBUG_FS) + void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); int batadv_debugfs_add_meshif(struct net_device *dev); @@ -27,4 +29,36 @@ void batadv_debugfs_del_meshif(struct net_device *dev); int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface); void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface); +#else + +static inline void batadv_debugfs_init(void) +{ +} + +static inline void batadv_debugfs_destroy(void) +{ +} + +static inline int batadv_debugfs_add_meshif(struct net_device *dev) +{ + return 0; +} + +static inline void batadv_debugfs_del_meshif(struct net_device *dev) +{ +} + +static inline +int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface) +{ + return 0; +} + +static inline +void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface) +{ +} + +#endif + #endif /* _NET_BATMAN_ADV_DEBUGFS_H_ */ diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index aad022d..da1742d 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index 2fe0764..ed41b8e 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 3d1dcaa..6ce3c84 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2015 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * @@ -161,6 +161,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, hlist_add_head(&frag_entry_new->list, &chain->head); chain->size = skb->len - hdr_size; chain->timestamp = jiffies; + chain->total_size = ntohs(frag_packet->total_size); ret = true; goto out; } @@ -195,9 +196,11 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, out: if (chain->size > batadv_frag_size_limit() || - ntohs(frag_packet->total_size) > batadv_frag_size_limit()) { + chain->total_size != ntohs(frag_packet->total_size) || + chain->total_size > batadv_frag_size_limit()) { /* Clear chain if total size of either the list or the packet - * exceeds the maximum size of one merged packet. + * exceeds the maximum size of one merged packet. Don't allow + * packets to have different total_size. */ batadv_frag_clear_chain(&chain->head); chain->size = 0; @@ -228,19 +231,13 @@ err: * Returns the merged skb or NULL on error. */ static struct sk_buff * -batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb) +batadv_frag_merge_packets(struct hlist_head *chain) { struct batadv_frag_packet *packet; struct batadv_frag_list_entry *entry; struct sk_buff *skb_out = NULL; int size, hdr_size = sizeof(struct batadv_frag_packet); - /* Make sure incoming skb has non-bogus data. */ - packet = (struct batadv_frag_packet *)skb->data; - size = ntohs(packet->total_size); - if (size > batadv_frag_size_limit()) - goto free; - /* Remove first entry, as this is the destination for the rest of the * fragments. */ @@ -249,6 +246,9 @@ batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb) skb_out = entry->skb; kfree(entry); + packet = (struct batadv_frag_packet *)skb_out->data; + size = ntohs(packet->total_size); + /* Make room for the rest of the fragments. */ if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) { kfree_skb(skb_out); @@ -304,7 +304,7 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb, if (hlist_empty(&head)) goto out; - skb_out = batadv_frag_merge_packets(&head, *skb); + skb_out = batadv_frag_merge_packets(&head); if (!skb_out) goto out_err; diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index d848cf6..ec1e86f 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2015 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 090828c..a85eaca 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 7ee53bb..185fb08 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 88a1bc3..0792e2f 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index aa51165..df54342 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index baf1f98..bdb020e 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 1918cd5..e8b6ffe 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 7c1c630..3a0e1dc 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 539fc12..379e32a 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 161ef8f..6c3cfb5 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 0c33950..4815824 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 12fc77b..548e405 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -209,10 +209,13 @@ void batadv_mesh_free(struct net_device *soft_iface) * interfaces in the current mesh * @bat_priv: the bat priv with all the soft interface information * @addr: the address to check + * + * Returns 'true' if the mac address was found, false otherwise. */ -int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr) +bool batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr) { const struct batadv_hard_iface *hard_iface; + bool is_my_mac = false; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { @@ -223,12 +226,12 @@ int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr) continue; if (batadv_compare_eth(hard_iface->net_dev->dev_addr, addr)) { - rcu_read_unlock(); - return 1; + is_my_mac = true; + break; } } rcu_read_unlock(); - return 0; + return is_my_mac; } /** @@ -510,14 +513,12 @@ static struct batadv_algo_ops *batadv_algo_get(char *name) int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops) { struct batadv_algo_ops *bat_algo_ops_tmp; - int ret; bat_algo_ops_tmp = batadv_algo_get(bat_algo_ops->name); if (bat_algo_ops_tmp) { pr_info("Trying to register already registered routing algorithm: %s\n", bat_algo_ops->name); - ret = -EEXIST; - goto out; + return -EEXIST; } /* all algorithms must implement all ops (for now) */ @@ -531,32 +532,26 @@ int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops) !bat_algo_ops->bat_neigh_is_equiv_or_better) { pr_info("Routing algo '%s' does not implement required ops\n", bat_algo_ops->name); - ret = -EINVAL; - goto out; + return -EINVAL; } INIT_HLIST_NODE(&bat_algo_ops->list); hlist_add_head(&bat_algo_ops->list, &batadv_algo_list); - ret = 0; -out: - return ret; + return 0; } int batadv_algo_select(struct batadv_priv *bat_priv, char *name) { struct batadv_algo_ops *bat_algo_ops; - int ret = -EINVAL; bat_algo_ops = batadv_algo_get(name); if (!bat_algo_ops) - goto out; + return -EINVAL; bat_priv->bat_algo_ops = bat_algo_ops; - ret = 0; -out: - return ret; + return 0; } int batadv_algo_seq_print_text(struct seq_file *seq, void *offset) @@ -819,15 +814,15 @@ static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff, new_buff = kmalloc(min_packet_len + additional_packet_len, GFP_ATOMIC); /* keep old buffer if kmalloc should fail */ - if (new_buff) { - memcpy(new_buff, *packet_buff, min_packet_len); - kfree(*packet_buff); - *packet_buff = new_buff; - *packet_buff_len = min_packet_len + additional_packet_len; - return true; - } + if (!new_buff) + return false; + + memcpy(new_buff, *packet_buff, min_packet_len); + kfree(*packet_buff); + *packet_buff = new_buff; + *packet_buff_len = min_packet_len + additional_packet_len; - return false; + return true; } /** diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 4d23188..af0a336 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2015.0" +#define BATADV_SOURCE_VERSION "2015.1" #endif /* B.A.T.M.A.N. parameters */ @@ -44,7 +44,7 @@ #define BATADV_TT_CLIENT_TEMP_TIMEOUT 600000 /* in milliseconds */ #define BATADV_TT_WORK_PERIOD 5000 /* 5 seconds */ #define BATADV_ORIG_WORK_PERIOD 1000 /* 1 second */ -#define BATADV_DAT_ENTRY_TIMEOUT (5*60000) /* 5 mins in milliseconds */ +#define BATADV_DAT_ENTRY_TIMEOUT (5 * 60000) /* 5 mins in milliseconds */ /* sliding packet range of received originator messages in sequence numbers * (should be a multiple of our word size) */ @@ -195,7 +195,7 @@ extern struct workqueue_struct *batadv_event_workqueue; int batadv_mesh_init(struct net_device *soft_iface); void batadv_mesh_free(struct net_device *soft_iface); -int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr); +bool batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_hard_iface * batadv_seq_print_text_primary_if_get(struct seq_file *seq); int batadv_max_header_len(void); @@ -279,7 +279,7 @@ static inline void _batadv_dbg(int type __always_unused, * * note: can't use ether_addr_equal() as it requires aligned memory */ -static inline int batadv_compare_eth(const void *data1, const void *data2) +static inline bool batadv_compare_eth(const void *data1, const void *data2) { return ether_addr_equal_unaligned(data1, data2); } diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index b24e4bb..09f2838 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2015 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 3a44ebd..033d80e 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2015 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 127cc4d..b984bc4 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2015 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * @@ -155,7 +155,7 @@ err: */ void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv) { - atomic_set(&bat_priv->network_coding, 1); + atomic_set(&bat_priv->network_coding, 0); bat_priv->nc.min_tq = 200; bat_priv->nc.max_fwd_delay = 10; bat_priv->nc.max_buffer_time = 200; @@ -275,7 +275,7 @@ static bool batadv_nc_to_purge_nc_path_decoding(struct batadv_priv *bat_priv, * max_buffer time */ return batadv_has_timed_out(nc_path->last_valid, - bat_priv->nc.max_buffer_time*10); + bat_priv->nc.max_buffer_time * 10); } /** diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 358c0d6..b5ab8ff 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2015 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 90e805a..e3900e4 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index aa4a436..9133914 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index b81fbbf..9468bc0 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index da83982..c5d9009 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 557d3d1..6573f12 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 3d64ed2..23635bd 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -255,8 +255,8 @@ int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, unsigned short vid) { - struct ethhdr *ethhdr; struct batadv_unicast_packet *unicast_packet; + struct ethhdr *ethhdr; int ret = NET_XMIT_DROP; if (!orig_node) diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 38d0ec1..60c233e 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5ec31d7..50cf722 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -732,7 +732,7 @@ static int batadv_softif_init_late(struct net_device *dev) atomic_set(&bat_priv->aggregated_ogms, 1); atomic_set(&bat_priv->bonding, 0); #ifdef CONFIG_BATMAN_ADV_BLA - atomic_set(&bat_priv->bridge_loop_avoidance, 0); + atomic_set(&bat_priv->bridge_loop_avoidance, 1); #endif #ifdef CONFIG_BATMAN_ADV_DAT atomic_set(&bat_priv->distributed_arp_table, 1); @@ -818,7 +818,7 @@ static int batadv_softif_slave_add(struct net_device *dev, int ret = -EINVAL; hard_iface = batadv_hardif_get_by_netdev(slave_dev); - if (!hard_iface || hard_iface->soft_iface != NULL) + if (!hard_iface || hard_iface->soft_iface) goto out; ret = batadv_hardif_enable_interface(hard_iface, dev->name); diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index dbab22f..9ce0804 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index a75dc12..fa8c347 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index b715b60..b9e79ad 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 07b263a..b098e53 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index ad84d7b..5769037c 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 9398c3f..c1000c0 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -132,6 +132,7 @@ struct batadv_orig_ifinfo { * @timestamp: time (jiffie) of last received fragment * @seqno: sequence number of the fragments in the list * @size: accumulated size of packets in list + * @total_size: expected size of the assembled packet */ struct batadv_frag_table_entry { struct hlist_head head; @@ -139,6 +140,7 @@ struct batadv_frag_table_entry { unsigned long timestamp; uint16_t seqno; uint16_t size; + uint16_t total_size; }; /** @@ -181,9 +183,10 @@ struct batadv_orig_node_vlan { /** * struct batadv_orig_bat_iv - B.A.T.M.A.N. IV private orig_node members - * @bcast_own: bitfield containing the number of our OGMs this orig_node - * rebroadcasted "back" to us (relative to last_real_seqno) - * @bcast_own_sum: counted result of bcast_own + * @bcast_own: set of bitfields (one per hard interface) where each one counts + * the number of our OGMs this orig_node rebroadcasted "back" to us (relative + * to last_real_seqno). Every bitfield is BATADV_TQ_LOCAL_WINDOW_SIZE bits long. + * @bcast_own_sum: sum of bcast_own * @ogm_cnt_lock: lock protecting bcast_own, bcast_own_sum, * neigh_node->bat_iv.real_bits & neigh_node->bat_iv.real_packet_count */ diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 1742b84..f3d6046 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -192,7 +192,7 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_dev *dev, if (ipv6_addr_any(nexthop)) return NULL; } else { - nexthop = rt6_nexthop(rt); + nexthop = rt6_nexthop(rt, daddr); /* We need to remember the address because it is needed * by bt_xmit() when sending the packet. In bt_xmit(), the diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index c4802f3..f6c9909 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -94,7 +94,6 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf, char buf[32]; size_t buf_size = min(count, (sizeof(buf)-1)); bool enable; - int err; if (!test_bit(HCI_UP, &hdev->flags)) return -ENETDOWN; @@ -121,12 +120,8 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf, if (IS_ERR(skb)) return PTR_ERR(skb); - err = -bt_to_errno(skb->data[0]); kfree_skb(skb); - if (err < 0) - return err; - hci_dev_change_flag(hdev, HCI_DUT_MODE); return count; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 7fd87e7..a6f21f8 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7577,7 +7577,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) memset(&ev, 0, sizeof(ev)); /* Devices using resolvable or non-resolvable random addresses - * without providing an indentity resolving key don't require + * without providing an identity resolving key don't require * to store long term keys. Their addresses will change the * next time around. * @@ -7617,7 +7617,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk) /* For identity resolving keys from devices that are already * using a public address or static random address, do not * ask for storing this key. The identity resolving key really - * is only mandatory for devices using resovlable random + * is only mandatory for devices using resolvable random * addresses. * * Storing all identity resolving keys has the downside that @@ -7646,7 +7646,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, memset(&ev, 0, sizeof(ev)); /* Devices using resolvable or non-resolvable random addresses - * without providing an indentity resolving key don't require + * without providing an identity resolving key don't require * to store signature resolving keys. Their addresses will change * the next time around. * diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 1ab3dc9..659371a 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -371,6 +371,8 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) uint8_t tmp[16], data[16]; int err; + SMP_DBG("k %16phN r %16phN", k, r); + if (!tfm) { BT_ERR("tfm %p", tfm); return -EINVAL; @@ -400,6 +402,8 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) /* Most significant octet of encryptedData corresponds to data[0] */ swap_buf(data, r, 16); + SMP_DBG("r %16phN", r); + return err; } @@ -410,6 +414,10 @@ static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16], u8 p1[16], p2[16]; int err; + SMP_DBG("k %16phN r %16phN", k, r); + SMP_DBG("iat %u ia %6phN rat %u ra %6phN", _iat, ia, _rat, ra); + SMP_DBG("preq %7phN pres %7phN", preq, pres); + memset(p1, 0, 16); /* p1 = pres || preq || _rat || _iat */ @@ -418,10 +426,7 @@ static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16], memcpy(p1 + 2, preq, 7); memcpy(p1 + 9, pres, 7); - /* p2 = padding || ia || ra */ - memcpy(p2, ra, 6); - memcpy(p2 + 6, ia, 6); - memset(p2 + 12, 0, 4); + SMP_DBG("p1 %16phN", p1); /* res = r XOR p1 */ u128_xor((u128 *) res, (u128 *) r, (u128 *) p1); @@ -433,6 +438,13 @@ static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16], return err; } + /* p2 = padding || ia || ra */ + memcpy(p2, ra, 6); + memcpy(p2 + 6, ia, 6); + memset(p2 + 12, 0, 4); + + SMP_DBG("p2 %16phN", p2); + /* res = res XOR p2 */ u128_xor((u128 *) res, (u128 *) res, (u128 *) p2); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index e0670d7..7896cf1 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -736,6 +736,12 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, struct net_bridge_fdb_entry *fdb; bool modified = false; + /* If the port cannot learn allow only local and static entries */ + if (!(state & NUD_PERMANENT) && !(state & NUD_NOARP) && + !(source->state == BR_STATE_LEARNING || + source->state == BR_STATE_FORWARDING)) + return -EPERM; + fdb = fdb_find(head, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index d7e103e..0b38ee9 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1644,7 +1644,7 @@ static void br_multicast_query_expired(struct net_bridge *br, if (query->startup_sent < br->multicast_startup_query_count) query->startup_sent++; - RCU_INIT_POINTER(querier, NULL); + RCU_INIT_POINTER(querier->port, NULL); br_multicast_send_query(br, NULL, query); spin_unlock(&br->multicast_lock); } @@ -1772,11 +1772,9 @@ out: int br_multicast_set_router(struct net_bridge *br, unsigned long val) { - int err = -ENOENT; + int err = -EINVAL; spin_lock_bh(&br->multicast_lock); - if (!netif_running(br->dev)) - goto unlock; switch (val) { case 0: @@ -1787,13 +1785,8 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) br->multicast_router = val; err = 0; break; - - default: - err = -EINVAL; - break; } -unlock: spin_unlock_bh(&br->multicast_lock); return err; @@ -1802,11 +1795,9 @@ unlock: int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) { struct net_bridge *br = p->br; - int err = -ENOENT; + int err = -EINVAL; spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || p->state == BR_STATE_DISABLED) - goto unlock; switch (val) { case 0: @@ -1828,13 +1819,8 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) br_multicast_add_router(br, p); break; - - default: - err = -EINVAL; - break; } -unlock: spin_unlock(&br->multicast_lock); return err; @@ -1939,15 +1925,11 @@ unlock: int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val) { - int err = -ENOENT; + int err = -EINVAL; u32 old; struct net_bridge_mdb_htable *mdb; spin_lock_bh(&br->multicast_lock); - if (!netif_running(br->dev)) - goto unlock; - - err = -EINVAL; if (!is_power_of_2(val)) goto unlock; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index d5aba39..5149d9e 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1117,8 +1117,6 @@ static int do_replace(struct net *net, const void __user *user, return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) return -ENOMEM; - if (tmp.num_counters == 0) - return -EINVAL; tmp.name[sizeof(tmp.name) - 1] = 0; @@ -2161,8 +2159,6 @@ static int compat_copy_ebt_replace_from_user(struct ebt_replace *repl, return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) return -ENOMEM; - if (tmp.num_counters == 0) - return -EINVAL; memcpy(repl, &tmp, offsetof(struct ebt_replace, hook_entry)); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 78a04eb..3cc71b9 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -330,6 +330,10 @@ static long caif_stream_data_wait(struct sock *sk, long timeo) release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); + + if (sock_flag(sk, SOCK_DEAD)) + break; + clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); } @@ -373,6 +377,10 @@ static int caif_stream_recvmsg(struct socket *sock, struct msghdr *msg, struct sk_buff *skb; lock_sock(sk); + if (sock_flag(sk, SOCK_DEAD)) { + err = -ECONNRESET; + goto unlock; + } skb = skb_dequeue(&sk->sk_receive_queue); caif_check_flow_release(sk); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 41a4abc..c4ec923 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1306,8 +1306,6 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc, if (list_empty(&req->r_osd_item)) req->r_osd = NULL; } - - list_del_init(&req->r_req_lru_item); /* can be on notarget */ ceph_osdc_put_request(req); } @@ -2017,20 +2015,29 @@ static void kick_requests(struct ceph_osd_client *osdc, bool force_resend, err = __map_request(osdc, req, force_resend || force_resend_writes); dout("__map_request returned %d\n", err); - if (err == 0) - continue; /* no change and no osd was specified */ if (err < 0) continue; /* hrm! */ - if (req->r_osd == NULL) { - dout("tid %llu maps to no valid osd\n", req->r_tid); - needmap++; /* request a newer map */ - continue; - } + if (req->r_osd == NULL || err > 0) { + if (req->r_osd == NULL) { + dout("lingering %p tid %llu maps to no osd\n", + req, req->r_tid); + /* + * A homeless lingering request makes + * no sense, as it's job is to keep + * a particular OSD connection open. + * Request a newer map and kick the + * request, knowing that it won't be + * resent until we actually get a map + * that can tell us where to send it. + */ + needmap++; + } - dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid, - req->r_osd ? req->r_osd->o_osd : -1); - __register_request(osdc, req); - __unregister_linger_request(osdc, req); + dout("kicking lingering %p tid %llu osd%d\n", req, + req->r_tid, req->r_osd ? req->r_osd->o_osd : -1); + __register_request(osdc, req); + __unregister_linger_request(osdc, req); + } } reset_changed_osds(osdc); mutex_unlock(&osdc->request_mutex); diff --git a/net/core/dev.c b/net/core/dev.c index 594163d..0602e91 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -469,10 +469,14 @@ EXPORT_SYMBOL(dev_remove_pack); */ void dev_add_offload(struct packet_offload *po) { - struct list_head *head = &offload_base; + struct packet_offload *elem; spin_lock(&offload_lock); - list_add_rcu(&po->list, head); + list_for_each_entry(elem, &offload_base, list) { + if (po->priority < elem->priority) + break; + } + list_add_rcu(&po->list, elem->list.prev); spin_unlock(&offload_lock); } EXPORT_SYMBOL(dev_add_offload); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 4f6a17e..eb0c3ac 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -358,15 +358,7 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) int err; struct ethtool_cmd cmd; - if (!dev->ethtool_ops->get_settings) - return -EOPNOTSUPP; - - if (copy_from_user(&cmd, useraddr, sizeof(cmd))) - return -EFAULT; - - cmd.cmd = ETHTOOL_GSET; - - err = dev->ethtool_ops->get_settings(dev, &cmd); + err = __ethtool_get_settings(dev, &cmd); if (err < 0) return err; diff --git a/net/core/filter.c b/net/core/filter.c index 3adcca6..64c121c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -46,6 +46,7 @@ #include <linux/seccomp.h> #include <linux/if_vlan.h> #include <linux/bpf.h> +#include <net/sch_generic.h> /** * sk_filter - run a packet through a socket filter @@ -1407,6 +1408,43 @@ const struct bpf_func_proto bpf_l4_csum_replace_proto = { .arg5_type = ARG_ANYTHING, }; +#define BPF_IS_REDIRECT_INGRESS(flags) ((flags) & 1) + +static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2; + struct net_device *dev; + + dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); + if (unlikely(!dev)) + return -EINVAL; + + if (unlikely(!(dev->flags & IFF_UP))) + return -EINVAL; + + skb2 = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!skb2)) + return -ENOMEM; + + if (G_TC_AT(skb2->tc_verd) & AT_INGRESS) + skb_push(skb2, skb2->mac_len); + + if (BPF_IS_REDIRECT_INGRESS(flags)) + return dev_forward_skb(dev, skb2); + + skb2->dev = dev; + return dev_queue_xmit(skb2); +} + +const struct bpf_func_proto bpf_clone_redirect_proto = { + .func = bpf_clone_redirect, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id) { @@ -1423,6 +1461,8 @@ sk_filter_func_proto(enum bpf_func_id func_id) return &bpf_get_smp_processor_id_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; + case BPF_FUNC_ktime_get_ns: + return &bpf_ktime_get_ns_proto; default: return NULL; } @@ -1438,6 +1478,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; + case BPF_FUNC_clone_redirect: + return &bpf_clone_redirect_proto; default: return sk_filter_func_proto(func_id); } @@ -1499,6 +1541,24 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, offsetof(struct sk_buff, priority)); break; + case offsetof(struct __sk_buff, ingress_ifindex): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, skb_iif) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, skb_iif)); + break; + + case offsetof(struct __sk_buff, ifindex): + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); + + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + dst_reg, src_reg, + offsetof(struct sk_buff, dev)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, dst_reg, + offsetof(struct net_device, ifindex)); + break; + case offsetof(struct __sk_buff, mark): return convert_skb_access(SKF_AD_MARK, dst_reg, src_reg, insn); diff --git a/net/core/netevent.c b/net/core/netevent.c index f17ccd2..8b3bc4f 100644 --- a/net/core/netevent.c +++ b/net/core/netevent.c @@ -31,10 +31,7 @@ static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain); */ int register_netevent_notifier(struct notifier_block *nb) { - int err; - - err = atomic_notifier_chain_register(&netevent_notif_chain, nb); - return err; + return atomic_notifier_chain_register(&netevent_notif_chain, nb); } EXPORT_SYMBOL_GPL(register_netevent_notifier); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 676550f..d93cbc5 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2645,9 +2645,9 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; int nhead = 0; if (x) { - int ret; - __u8 *eth; + struct ethhdr *eth; struct iphdr *iph; + int ret; nhead = x->props.header_len - skb_headroom(skb); if (nhead > 0) { @@ -2667,9 +2667,9 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, goto err; } /* restore ll */ - eth = (__u8 *) skb_push(skb, ETH_HLEN); - memcpy(eth, pkt_dev->hh, 12); - *(u16 *) ð[12] = protocol; + eth = (struct ethhdr *)skb_push(skb, ETH_HLEN); + memcpy(eth, pkt_dev->hh, 2 * ETH_ALEN); + eth->h_proto = protocol; /* Update IPv4 header len as well as checksum value */ iph = ip_hdr(skb); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 51dd319..fd3ce46 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -154,7 +154,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) - secret[i] = net_secret[i] + daddr[i]; + secret[i] = net_secret[i] + (__force u32)daddr[i]; secret[4] = net_secret[4] + (((__force u16)sport << 16) + (__force u16)dport); for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) diff --git a/net/core/sock.c b/net/core/sock.c index 29124fc..e72633c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1581,6 +1581,8 @@ EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { + u32 max_segs = 1; + __sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features; if (sk->sk_route_caps & NETIF_F_GSO) @@ -1592,9 +1594,10 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = dst->dev->gso_max_size; - sk->sk_gso_max_segs = dst->dev->gso_max_segs; + max_segs = max_t(u32, dst->dev->gso_max_segs, 1); } } + sk->sk_gso_max_segs = max_segs; } EXPORT_SYMBOL_GPL(sk_setup_caps); diff --git a/net/core/utils.c b/net/core/utils.c index 7b80388..a7732a0 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -304,13 +304,15 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, int pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { - *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), from), - to)); + csum_replace4(sum, from, to); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) - skb->csum = ~csum_add(csum_sub(~(skb->csum), from), to); + skb->csum = ~csum_add(csum_sub(~(skb->csum), + (__force __wsum)from), + (__force __wsum)to); } else if (pseudohdr) - *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), from), - to)); + *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), + (__force __wsum)from), + (__force __wsum)to)); } EXPORT_SYMBOL(inet_proto_csum_replace4); diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index e6f6cc3..392e29a 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -359,7 +359,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, */ ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL); if (ds == NULL) - return NULL; + return ERR_PTR(-ENOMEM); ds->dst = dst; ds->index = index; @@ -370,7 +370,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, ret = dsa_switch_setup_one(ds, parent); if (ret) - return NULL; + return ERR_PTR(ret); return ds; } diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index c3325bd..7d0e239 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -470,6 +470,7 @@ EXPORT_SYMBOL(eth_gro_complete); static struct packet_offload eth_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_TEB), + .priority = 10, .callbacks = { .gro_receive = eth_gro_receive, .gro_complete = eth_gro_complete, diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 0ae5822..f20a387 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -55,27 +55,6 @@ LIST_HEAD(lowpan_devices); static int lowpan_open_count; -static __le16 lowpan_get_pan_id(const struct net_device *dev) -{ - struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; - - return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev); -} - -static __le16 lowpan_get_short_addr(const struct net_device *dev) -{ - struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; - - return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev); -} - -static u8 lowpan_get_dsn(const struct net_device *dev) -{ - struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; - - return ieee802154_mlme_ops(real_dev)->get_dsn(real_dev); -} - static struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; @@ -103,12 +82,6 @@ static const struct net_device_ops lowpan_netdev_ops = { .ndo_start_xmit = lowpan_xmit, }; -static struct ieee802154_mlme_ops lowpan_mlme = { - .get_pan_id = lowpan_get_pan_id, - .get_short_addr = lowpan_get_short_addr, - .get_dsn = lowpan_get_dsn, -}; - static void lowpan_setup(struct net_device *dev) { dev->addr_len = IEEE802154_ADDR_LEN; @@ -124,7 +97,6 @@ static void lowpan_setup(struct net_device *dev) dev->netdev_ops = &lowpan_netdev_ops; dev->header_ops = &lowpan_header_ops; - dev->ml_priv = &lowpan_mlme; dev->destructor = free_netdev; dev->features |= NETIF_F_NETNS_LOCAL; } diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c index 2349070..98acf73 100644 --- a/net/ieee802154/6lowpan/tx.c +++ b/net/ieee802154/6lowpan/tx.c @@ -207,7 +207,7 @@ static int lowpan_header(struct sk_buff *skb, struct net_device *dev) /* prepare wpan address data */ sa.mode = IEEE802154_ADDR_LONG; - sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + sa.pan_id = lowpan_dev_info(dev)->real_dev->ieee802154_ptr->pan_id; sa.extended_addr = ieee802154_devaddr_from_raw(saddr); /* intra-PAN communications */ diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index 2ee00e8..b0248e9 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -121,8 +121,6 @@ wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size) /* atomic_inc_return makes it start at 1, make it start at 0 */ rdev->wpan_phy_idx--; - mutex_init(&rdev->wpan_phy.pib_lock); - INIT_LIST_HEAD(&rdev->wpan_dev_list); device_initialize(&rdev->wpan_phy.dev); dev_set_name(&rdev->wpan_phy.dev, PHY_NAME "%d", rdev->wpan_phy_idx); diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 2b4955d..3503c38 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -97,8 +97,10 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, BUG_ON(!phy); get_device(&phy->dev); - short_addr = ops->get_short_addr(dev); - pan_id = ops->get_pan_id(dev); + rtnl_lock(); + short_addr = dev->ieee802154_ptr->short_addr; + pan_id = dev->ieee802154_ptr->pan_id; + rtnl_unlock(); if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || @@ -117,12 +119,12 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, rtnl_unlock(); if (nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, - params.transmit_power) || + params.transmit_power / 100) || nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, params.lbt) || nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, params.cca.mode) || nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL, - params.cca_ed_level) || + params.cca_ed_level / 100) || nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES, params.csma_retries) || nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE, @@ -166,10 +168,7 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) if (!dev) return NULL; - /* Check on mtu is currently a hacked solution because lowpan - * and wpan have the same ARPHRD type. - */ - if (dev->type != ARPHRD_IEEE802154 || dev->mtu != IEEE802154_MTU) { + if (dev->type != ARPHRD_IEEE802154) { dev_put(dev); return NULL; } @@ -244,7 +243,9 @@ int ieee802154_associate_resp(struct sk_buff *skb, struct genl_info *info) addr.mode = IEEE802154_ADDR_LONG; addr.extended_addr = nla_get_hwaddr( info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]); - addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + rtnl_lock(); + addr.pan_id = dev->ieee802154_ptr->pan_id; + rtnl_unlock(); ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr, nla_get_shortaddr(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]), @@ -281,7 +282,9 @@ int ieee802154_disassociate_req(struct sk_buff *skb, struct genl_info *info) addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]); } - addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + rtnl_lock(); + addr.pan_id = dev->ieee802154_ptr->pan_id; + rtnl_unlock(); ret = ieee802154_mlme_ops(dev)->disassoc_req(dev, &addr, nla_get_u8(info->attrs[IEEE802154_ATTR_REASON])); @@ -449,11 +452,7 @@ int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; for_each_netdev(net, dev) { - /* Check on mtu is currently a hacked solution because lowpan - * and wpan have the same ARPHRD type. - */ - if (idx < s_idx || dev->type != ARPHRD_IEEE802154 || - dev->mtu != IEEE802154_MTU) + if (idx < s_idx || dev->type != ARPHRD_IEEE802154) goto cont; if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).portid, @@ -510,7 +509,7 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info) ops->get_mac_params(dev, ¶ms); if (info->attrs[IEEE802154_ATTR_TXPOWER]) - params.transmit_power = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]); + params.transmit_power = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]) * 100; if (info->attrs[IEEE802154_ATTR_LBT_ENABLED]) params.lbt = nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]); @@ -519,7 +518,7 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info) params.cca.mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]); if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) - params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]); + params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) * 100; if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES]) params.csma_retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]); @@ -783,11 +782,7 @@ ieee802154_llsec_dump_table(struct sk_buff *skb, struct netlink_callback *cb, int rc; for_each_netdev(net, dev) { - /* Check on mtu is currently a hacked solution because lowpan - * and wpan have the same ARPHRD type. - */ - if (idx < first_dev || dev->type != ARPHRD_IEEE802154 || - dev->mtu != IEEE802154_MTU) + if (idx < first_dev || dev->type != ARPHRD_IEEE802154) goto skip; data.ops = ieee802154_mlme_ops(dev); diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 346c666..77d7301 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -50,26 +50,26 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid, if (!hdr) goto out; - mutex_lock(&phy->pib_lock); + rtnl_lock(); if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) || nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel)) goto nla_put_failure; for (i = 0; i < 32; i++) { - if (phy->channels_supported[i]) - buf[pages++] = phy->channels_supported[i] | (i << 27); + if (phy->supported.channels[i]) + buf[pages++] = phy->supported.channels[i] | (i << 27); } if (pages && nla_put(msg, IEEE802154_ATTR_CHANNEL_PAGE_LIST, pages * sizeof(uint32_t), buf)) goto nla_put_failure; - mutex_unlock(&phy->pib_lock); + rtnl_unlock(); kfree(buf); genlmsg_end(msg, hdr); return 0; nla_put_failure: - mutex_unlock(&phy->pib_lock); + rtnl_unlock(); genlmsg_cancel(msg, hdr); out: kfree(buf); diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index f3c12f6..7dbb1f4 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -207,10 +207,11 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = { [NL802154_ATTR_PAGE] = { .type = NLA_U8, }, [NL802154_ATTR_CHANNEL] = { .type = NLA_U8, }, - [NL802154_ATTR_TX_POWER] = { .type = NLA_S8, }, + [NL802154_ATTR_TX_POWER] = { .type = NLA_S32, }, [NL802154_ATTR_CCA_MODE] = { .type = NLA_U32, }, [NL802154_ATTR_CCA_OPT] = { .type = NLA_U32, }, + [NL802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, }, [NL802154_ATTR_SUPPORTED_CHANNEL] = { .type = NLA_U32, }, @@ -225,6 +226,8 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = { [NL802154_ATTR_MAX_FRAME_RETRIES] = { .type = NLA_S8, }, [NL802154_ATTR_LBT_MODE] = { .type = NLA_U8, }, + + [NL802154_ATTR_WPAN_PHY_CAPS] = { .type = NLA_NESTED }, }; /* message building helper */ @@ -236,6 +239,28 @@ static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq, } static int +nl802154_put_flags(struct sk_buff *msg, int attr, u32 mask) +{ + struct nlattr *nl_flags = nla_nest_start(msg, attr); + int i; + + if (!nl_flags) + return -ENOBUFS; + + i = 0; + while (mask) { + if ((mask & 1) && nla_put_flag(msg, i)) + return -ENOBUFS; + + mask >>= 1; + i++; + } + + nla_nest_end(msg, nl_flags); + return 0; +} + +static int nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev, struct sk_buff *msg) { @@ -248,7 +273,7 @@ nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev, for (page = 0; page <= IEEE802154_MAX_PAGE; page++) { if (nla_put_u32(msg, NL802154_ATTR_SUPPORTED_CHANNEL, - rdev->wpan_phy.channels_supported[page])) + rdev->wpan_phy.supported.channels[page])) return -ENOBUFS; } nla_nest_end(msg, nl_page); @@ -256,6 +281,92 @@ nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev, return 0; } +static int +nl802154_put_capabilities(struct sk_buff *msg, + struct cfg802154_registered_device *rdev) +{ + const struct wpan_phy_supported *caps = &rdev->wpan_phy.supported; + struct nlattr *nl_caps, *nl_channels; + int i; + + nl_caps = nla_nest_start(msg, NL802154_ATTR_WPAN_PHY_CAPS); + if (!nl_caps) + return -ENOBUFS; + + nl_channels = nla_nest_start(msg, NL802154_CAP_ATTR_CHANNELS); + if (!nl_channels) + return -ENOBUFS; + + for (i = 0; i <= IEEE802154_MAX_PAGE; i++) { + if (caps->channels[i]) { + if (nl802154_put_flags(msg, i, caps->channels[i])) + return -ENOBUFS; + } + } + + nla_nest_end(msg, nl_channels); + + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { + struct nlattr *nl_ed_lvls; + + nl_ed_lvls = nla_nest_start(msg, + NL802154_CAP_ATTR_CCA_ED_LEVELS); + if (!nl_ed_lvls) + return -ENOBUFS; + + for (i = 0; i < caps->cca_ed_levels_size; i++) { + if (nla_put_s32(msg, i, caps->cca_ed_levels[i])) + return -ENOBUFS; + } + + nla_nest_end(msg, nl_ed_lvls); + } + + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) { + struct nlattr *nl_tx_pwrs; + + nl_tx_pwrs = nla_nest_start(msg, NL802154_CAP_ATTR_TX_POWERS); + if (!nl_tx_pwrs) + return -ENOBUFS; + + for (i = 0; i < caps->tx_powers_size; i++) { + if (nla_put_s32(msg, i, caps->tx_powers[i])) + return -ENOBUFS; + } + + nla_nest_end(msg, nl_tx_pwrs); + } + + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) { + if (nl802154_put_flags(msg, NL802154_CAP_ATTR_CCA_MODES, + caps->cca_modes) || + nl802154_put_flags(msg, NL802154_CAP_ATTR_CCA_OPTS, + caps->cca_opts)) + return -ENOBUFS; + } + + if (nla_put_u8(msg, NL802154_CAP_ATTR_MIN_MINBE, caps->min_minbe) || + nla_put_u8(msg, NL802154_CAP_ATTR_MAX_MINBE, caps->max_minbe) || + nla_put_u8(msg, NL802154_CAP_ATTR_MIN_MAXBE, caps->min_maxbe) || + nla_put_u8(msg, NL802154_CAP_ATTR_MAX_MAXBE, caps->max_maxbe) || + nla_put_u8(msg, NL802154_CAP_ATTR_MIN_CSMA_BACKOFFS, + caps->min_csma_backoffs) || + nla_put_u8(msg, NL802154_CAP_ATTR_MAX_CSMA_BACKOFFS, + caps->max_csma_backoffs) || + nla_put_s8(msg, NL802154_CAP_ATTR_MIN_FRAME_RETRIES, + caps->min_frame_retries) || + nla_put_s8(msg, NL802154_CAP_ATTR_MAX_FRAME_RETRIES, + caps->max_frame_retries) || + nl802154_put_flags(msg, NL802154_CAP_ATTR_IFTYPES, + caps->iftypes) || + nla_put_u32(msg, NL802154_CAP_ATTR_LBT, caps->lbt)) + return -ENOBUFS; + + nla_nest_end(msg, nl_caps); + + return 0; +} + static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev, enum nl802154_commands cmd, struct sk_buff *msg, u32 portid, u32 seq, @@ -286,23 +397,38 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev, rdev->wpan_phy.current_channel)) goto nla_put_failure; - /* supported channels array */ + /* TODO remove this behaviour, we still keep support it for a while + * so users can change the behaviour to the new one. + */ if (nl802154_send_wpan_phy_channels(rdev, msg)) goto nla_put_failure; /* cca mode */ - if (nla_put_u32(msg, NL802154_ATTR_CCA_MODE, - rdev->wpan_phy.cca.mode)) - goto nla_put_failure; + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) { + if (nla_put_u32(msg, NL802154_ATTR_CCA_MODE, + rdev->wpan_phy.cca.mode)) + goto nla_put_failure; + + if (rdev->wpan_phy.cca.mode == NL802154_CCA_ENERGY_CARRIER) { + if (nla_put_u32(msg, NL802154_ATTR_CCA_OPT, + rdev->wpan_phy.cca.opt)) + goto nla_put_failure; + } + } - if (rdev->wpan_phy.cca.mode == NL802154_CCA_ENERGY_CARRIER) { - if (nla_put_u32(msg, NL802154_ATTR_CCA_OPT, - rdev->wpan_phy.cca.opt)) + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) { + if (nla_put_s32(msg, NL802154_ATTR_TX_POWER, + rdev->wpan_phy.transmit_power)) goto nla_put_failure; } - if (nla_put_s8(msg, NL802154_ATTR_TX_POWER, - rdev->wpan_phy.transmit_power)) + if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { + if (nla_put_s32(msg, NL802154_ATTR_CCA_ED_LEVEL, + rdev->wpan_phy.cca_ed_level)) + goto nla_put_failure; + } + + if (nl802154_put_capabilities(msg, rdev)) goto nla_put_failure; finish: @@ -575,7 +701,8 @@ static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL802154_ATTR_IFTYPE]) { type = nla_get_u32(info->attrs[NL802154_ATTR_IFTYPE]); - if (type > NL802154_IFTYPE_MAX) + if (type > NL802154_IFTYPE_MAX || + !(rdev->wpan_phy.supported.iftypes & BIT(type))) return -EINVAL; } @@ -625,7 +752,8 @@ static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info) channel = nla_get_u8(info->attrs[NL802154_ATTR_CHANNEL]); /* check 802.15.4 constraints */ - if (page > IEEE802154_MAX_PAGE || channel > IEEE802154_MAX_CHANNEL) + if (page > IEEE802154_MAX_PAGE || channel > IEEE802154_MAX_CHANNEL || + !(rdev->wpan_phy.supported.channels[page] & BIT(channel))) return -EINVAL; return rdev_set_channel(rdev, page, channel); @@ -636,12 +764,17 @@ static int nl802154_set_cca_mode(struct sk_buff *skb, struct genl_info *info) struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct wpan_phy_cca cca; + if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE)) + return -EOPNOTSUPP; + if (!info->attrs[NL802154_ATTR_CCA_MODE]) return -EINVAL; cca.mode = nla_get_u32(info->attrs[NL802154_ATTR_CCA_MODE]); /* checking 802.15.4 constraints */ - if (cca.mode < NL802154_CCA_ENERGY || cca.mode > NL802154_CCA_ATTR_MAX) + if (cca.mode < NL802154_CCA_ENERGY || + cca.mode > NL802154_CCA_ATTR_MAX || + !(rdev->wpan_phy.supported.cca_modes & BIT(cca.mode))) return -EINVAL; if (cca.mode == NL802154_CCA_ENERGY_CARRIER) { @@ -649,13 +782,58 @@ static int nl802154_set_cca_mode(struct sk_buff *skb, struct genl_info *info) return -EINVAL; cca.opt = nla_get_u32(info->attrs[NL802154_ATTR_CCA_OPT]); - if (cca.opt > NL802154_CCA_OPT_ATTR_MAX) + if (cca.opt > NL802154_CCA_OPT_ATTR_MAX || + !(rdev->wpan_phy.supported.cca_opts & BIT(cca.opt))) return -EINVAL; } return rdev_set_cca_mode(rdev, &cca); } +static int nl802154_set_cca_ed_level(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + s32 ed_level; + int i; + + if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL)) + return -EOPNOTSUPP; + + if (!info->attrs[NL802154_ATTR_CCA_ED_LEVEL]) + return -EINVAL; + + ed_level = nla_get_s32(info->attrs[NL802154_ATTR_CCA_ED_LEVEL]); + + for (i = 0; i < rdev->wpan_phy.supported.cca_ed_levels_size; i++) { + if (ed_level == rdev->wpan_phy.supported.cca_ed_levels[i]) + return rdev_set_cca_ed_level(rdev, ed_level); + } + + return -EINVAL; +} + +static int nl802154_set_tx_power(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + s32 power; + int i; + + if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER)) + return -EOPNOTSUPP; + + if (!info->attrs[NL802154_ATTR_TX_POWER]) + return -EINVAL; + + power = nla_get_s32(info->attrs[NL802154_ATTR_TX_POWER]); + + for (i = 0; i < rdev->wpan_phy.supported.tx_powers_size; i++) { + if (power == rdev->wpan_phy.supported.tx_powers[i]) + return rdev_set_tx_power(rdev, power); + } + + return -EINVAL; +} + static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; @@ -668,14 +846,22 @@ static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info) return -EBUSY; /* don't change address fields on monitor */ - if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) - return -EINVAL; - - if (!info->attrs[NL802154_ATTR_PAN_ID]) + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR || + !info->attrs[NL802154_ATTR_PAN_ID]) return -EINVAL; pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]); + /* TODO + * I am not sure about to check here on broadcast pan_id. + * Broadcast is a valid setting, comment from 802.15.4: + * If this value is 0xffff, the device is not associated. + * + * This could useful to simple deassociate an device. + */ + if (pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST)) + return -EINVAL; + return rdev_set_pan_id(rdev, wpan_dev, pan_id); } @@ -691,14 +877,27 @@ static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info) return -EBUSY; /* don't change address fields on monitor */ - if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) - return -EINVAL; - - if (!info->attrs[NL802154_ATTR_SHORT_ADDR]) + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR || + !info->attrs[NL802154_ATTR_SHORT_ADDR]) return -EINVAL; short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]); + /* TODO + * I am not sure about to check here on broadcast short_addr. + * Broadcast is a valid setting, comment from 802.15.4: + * A value of 0xfffe indicates that the device has + * associated but has not been allocated an address. A + * value of 0xffff indicates that the device does not + * have a short address. + * + * I think we should allow to set these settings but + * don't allow to allow socket communication with it. + */ + if (short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC) || + short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST)) + return -EINVAL; + return rdev_set_short_addr(rdev, wpan_dev, short_addr); } @@ -722,7 +921,11 @@ nl802154_set_backoff_exponent(struct sk_buff *skb, struct genl_info *info) max_be = nla_get_u8(info->attrs[NL802154_ATTR_MAX_BE]); /* check 802.15.4 constraints */ - if (max_be < 3 || max_be > 8 || min_be > max_be) + if (min_be < rdev->wpan_phy.supported.min_minbe || + min_be > rdev->wpan_phy.supported.max_minbe || + max_be < rdev->wpan_phy.supported.min_maxbe || + max_be > rdev->wpan_phy.supported.max_maxbe || + min_be > max_be) return -EINVAL; return rdev_set_backoff_exponent(rdev, wpan_dev, min_be, max_be); @@ -747,7 +950,8 @@ nl802154_set_max_csma_backoffs(struct sk_buff *skb, struct genl_info *info) info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS]); /* check 802.15.4 constraints */ - if (max_csma_backoffs > 5) + if (max_csma_backoffs < rdev->wpan_phy.supported.min_csma_backoffs || + max_csma_backoffs > rdev->wpan_phy.supported.max_csma_backoffs) return -EINVAL; return rdev_set_max_csma_backoffs(rdev, wpan_dev, max_csma_backoffs); @@ -771,7 +975,8 @@ nl802154_set_max_frame_retries(struct sk_buff *skb, struct genl_info *info) info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES]); /* check 802.15.4 constraints */ - if (max_frame_retries < -1 || max_frame_retries > 7) + if (max_frame_retries < rdev->wpan_phy.supported.min_frame_retries || + max_frame_retries > rdev->wpan_phy.supported.max_frame_retries) return -EINVAL; return rdev_set_max_frame_retries(rdev, wpan_dev, max_frame_retries); @@ -791,6 +996,9 @@ static int nl802154_set_lbt_mode(struct sk_buff *skb, struct genl_info *info) return -EINVAL; mode = !!nla_get_u8(info->attrs[NL802154_ATTR_LBT_MODE]); + if (!wpan_phy_supported_bool(mode, rdev->wpan_phy.supported.lbt)) + return -EINVAL; + return rdev_set_lbt_mode(rdev, wpan_dev, mode); } @@ -937,6 +1145,22 @@ static const struct genl_ops nl802154_ops[] = { NL802154_FLAG_NEED_RTNL, }, { + .cmd = NL802154_CMD_SET_CCA_ED_LEVEL, + .doit = nl802154_set_cca_ed_level, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | + NL802154_FLAG_NEED_RTNL, + }, + { + .cmd = NL802154_CMD_SET_TX_POWER, + .doit = nl802154_set_tx_power, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | + NL802154_FLAG_NEED_RTNL, + }, + { .cmd = NL802154_CMD_SET_PAN_ID, .doit = nl802154_set_pan_id, .policy = nl802154_policy, diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h index 7b5a9dd..b2155a1 100644 --- a/net/ieee802154/rdev-ops.h +++ b/net/ieee802154/rdev-ops.h @@ -75,6 +75,29 @@ rdev_set_cca_mode(struct cfg802154_registered_device *rdev, } static inline int +rdev_set_cca_ed_level(struct cfg802154_registered_device *rdev, s32 ed_level) +{ + int ret; + + trace_802154_rdev_set_cca_ed_level(&rdev->wpan_phy, ed_level); + ret = rdev->ops->set_cca_ed_level(&rdev->wpan_phy, ed_level); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; +} + +static inline int +rdev_set_tx_power(struct cfg802154_registered_device *rdev, + s32 power) +{ + int ret; + + trace_802154_rdev_set_tx_power(&rdev->wpan_phy, power); + ret = rdev->ops->set_tx_power(&rdev->wpan_phy, power); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; +} + +static inline int rdev_set_pan_id(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, __le16 pan_id) { diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 7aaaf96..02abef2 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -64,10 +64,8 @@ ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr) if (tmp->type != ARPHRD_IEEE802154) continue; - pan_id = ieee802154_mlme_ops(tmp)->get_pan_id(tmp); - short_addr = - ieee802154_mlme_ops(tmp)->get_short_addr(tmp); - + pan_id = tmp->ieee802154_ptr->pan_id; + short_addr = tmp->ieee802154_ptr->short_addr; if (pan_id == addr->pan_id && short_addr == addr->short_addr) { dev = tmp; @@ -228,15 +226,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len) goto out; } - if (dev->type != ARPHRD_IEEE802154) { - err = -ENODEV; - goto out_put; - } - sk->sk_bound_dev_if = dev->ifindex; sk_dst_reset(sk); -out_put: dev_put(dev); out: release_sock(sk); @@ -286,7 +278,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) if (size > mtu) { pr_debug("size = %Zu, mtu = %u\n", size, mtu); - err = -EINVAL; + err = -EMSGSIZE; goto out_dev; } @@ -797,9 +789,9 @@ static int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) /* Data frame processing */ BUG_ON(dev->type != ARPHRD_IEEE802154); - pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); - short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev); - hw_addr = ieee802154_devaddr_from_raw(dev->dev_addr); + pan_id = dev->ieee802154_ptr->pan_id; + short_addr = dev->ieee802154_ptr->short_addr; + hw_addr = dev->ieee802154_ptr->extended_addr; read_lock(&dgram_lock); sk_for_each(sk, &dgram_head) { diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h index 5ac25eb..73eb760 100644 --- a/net/ieee802154/trace.h +++ b/net/ieee802154/trace.h @@ -1,4 +1,4 @@ -/* Based on net/wireless/tracing.h */ +/* Based on net/wireless/trace.h */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cfg802154 @@ -93,6 +93,21 @@ TRACE_EVENT(802154_rdev_set_channel, __entry->page, __entry->channel) ); +TRACE_EVENT(802154_rdev_set_tx_power, + TP_PROTO(struct wpan_phy *wpan_phy, s32 power), + TP_ARGS(wpan_phy, power), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + __field(s32, power) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + __entry->power = power; + ), + TP_printk(WPAN_PHY_PR_FMT ", power: %d", WPAN_PHY_PR_ARG, + __entry->power) +); + TRACE_EVENT(802154_rdev_set_cca_mode, TP_PROTO(struct wpan_phy *wpan_phy, const struct wpan_phy_cca *cca), TP_ARGS(wpan_phy, cca), @@ -108,6 +123,21 @@ TRACE_EVENT(802154_rdev_set_cca_mode, WPAN_CCA_PR_ARG) ); +TRACE_EVENT(802154_rdev_set_cca_ed_level, + TP_PROTO(struct wpan_phy *wpan_phy, s32 ed_level), + TP_ARGS(wpan_phy, ed_level), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + __field(s32, ed_level) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + __entry->ed_level = ed_level; + ), + TP_printk(WPAN_PHY_PR_FMT ", ed_level: %d", WPAN_PHY_PR_ARG, + __entry->ed_level) +); + DECLARE_EVENT_CLASS(802154_le16_template, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 le16arg), diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 235d36a..6ad0f7a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1595,7 +1595,7 @@ static __net_init int inet_init_net(struct net *net) */ seqlock_init(&net->ipv4.ip_local_ports.lock); net->ipv4.ip_local_ports.range[0] = 32768; - net->ipv4.ip_local_ports.range[1] = 61000; + net->ipv4.ip_local_ports.range[1] = 60999; seqlock_init(&net->ipv4.ping_group_range.lock); /* diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 421a80b..30b544f 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -256,7 +256,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) aead_givcrypt_set_crypt(req, sg, sg, clen, iv); aead_givcrypt_set_assoc(req, asg, assoclen); aead_givcrypt_set_giv(req, esph->enc_data, - XFRM_SKB_CB(skb)->seq.output.low); + XFRM_SKB_CB(skb)->seq.output.low + + ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32)); ESP_SKB_CB(skb)->tmp = tmp; err = crypto_aead_givencrypt(req); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 5a5d9bd..01bce15 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -72,6 +72,7 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 3766bdd..5f9b063 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/wait.h> +#include <linux/vmalloc.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> @@ -393,9 +394,10 @@ not_unique: return -EADDRNOTAVAIL; } -static inline u32 inet_sk_port_offset(const struct sock *sk) +static u32 inet_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); + return secure_ipv4_port_ephemeral(inet->inet_rcv_saddr, inet->inet_daddr, inet->inet_dport); @@ -501,8 +503,14 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; + /* By starting with offset being an even number, + * we tend to leave about 50% of ports for other uses, + * like bind(0). + */ + offset &= ~1; + local_bh_disable(); - for (i = 1; i <= remaining; i++) { + for (i = 0; i < remaining; i++) { port = low + (i + offset) % remaining; if (inet_is_local_reserved_port(net, port)) continue; @@ -546,7 +554,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, return -EADDRNOTAVAIL; ok: - hint += i; + hint += (i + 2) & ~1; /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, port); @@ -593,7 +601,11 @@ out: int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - return __inet_hash_connect(death_row, sk, inet_sk_port_offset(sk), + u32 port_offset = 0; + + if (!inet_sk(sk)->inet_num) + port_offset = inet_sk_port_offset(sk); + return __inet_hash_connect(death_row, sk, port_offset, __inet_check_established); } EXPORT_SYMBOL_GPL(inet_hash_connect); @@ -609,3 +621,33 @@ void inet_hashinfo_init(struct inet_hashinfo *h) } } EXPORT_SYMBOL_GPL(inet_hashinfo_init); + +int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) +{ + unsigned int i, nblocks = 1; + + if (sizeof(spinlock_t) != 0) { + /* allocate 2 cache lines or at least one spinlock per cpu */ + nblocks = max_t(unsigned int, + 2 * L1_CACHE_BYTES / sizeof(spinlock_t), + 1); + nblocks = roundup_pow_of_two(nblocks * num_possible_cpus()); + + /* no more locks than number of hash buckets */ + nblocks = min(nblocks, hashinfo->ehash_mask + 1); + + hashinfo->ehash_locks = kmalloc_array(nblocks, sizeof(spinlock_t), + GFP_KERNEL | __GFP_NOWARN); + if (!hashinfo->ehash_locks) + hashinfo->ehash_locks = vmalloc(nblocks * sizeof(spinlock_t)); + + if (!hashinfo->ehash_locks) + return -ENOMEM; + + for (i = 0; i < nblocks; i++) + spin_lock_init(&hashinfo->ehash_locks[i]); + } + hashinfo->ehash_locks_mask = nblocks - 1; + return 0; +} +EXPORT_SYMBOL_GPL(inet_ehash_locks_alloc); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 47fa64e..a50dc6d 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -75,6 +75,7 @@ struct ipq { __be16 id; u8 protocol; u8 ecn; /* RFC3168 support */ + u16 max_df_size; /* largest frag with DF set seen */ int iif; unsigned int rid; struct inet_peer *peer; @@ -326,6 +327,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { struct sk_buff *prev, *next; struct net_device *dev; + unsigned int fragsize; int flags, offset; int ihl, end; int err = -ENOENT; @@ -481,9 +483,14 @@ found: if (offset == 0) qp->q.flags |= INET_FRAG_FIRST_IN; + fragsize = skb->len + ihl; + + if (fragsize > qp->q.max_size) + qp->q.max_size = fragsize; + if (ip_hdr(skb)->frag_off & htons(IP_DF) && - skb->len + ihl > qp->q.max_size) - qp->q.max_size = skb->len + ihl; + fragsize > qp->max_df_size) + qp->max_df_size = fragsize; if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && qp->q.meat == qp->q.len) { @@ -613,13 +620,27 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, head->next = NULL; head->dev = dev; head->tstamp = qp->q.stamp; - IPCB(head)->frag_max_size = qp->q.max_size; + IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); iph = ip_hdr(head); - /* max_size != 0 implies at least one fragment had IP_DF set */ - iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0; iph->tot_len = htons(len); iph->tos |= ecn; + + /* When we set IP_DF on a refragmented skb we must also force a + * call to ip_fragment to avoid forwarding a DF-skb of size s while + * original sender only sent fragments of size f (where f < s). + * + * We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest + * frag seen to avoid sending tiny DF-fragments in case skb was built + * from one very small df-fragment and one large non-df frag. + */ + if (qp->max_df_size == qp->q.max_size) { + IPCB(head)->flags |= IPSKB_FRAG_PMTU; + iph->frag_off = htons(IP_DF); + } else { + iph->frag_off = 0; + } + IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS); qp->q.fragments = NULL; qp->q.fragments_tail = NULL; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 451b009..f5f5ef1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -84,6 +84,7 @@ int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; EXPORT_SYMBOL(sysctl_ip_default_ttl); static int ip_fragment(struct sock *sk, struct sk_buff *skb, + unsigned int mtu, int (*output)(struct sock *, struct sk_buff *)); /* Generate a checksum for an outgoing IP datagram. */ @@ -219,7 +220,8 @@ static inline int ip_finish_output2(struct sock *sk, struct sk_buff *skb) return -EINVAL; } -static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb) +static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb, + unsigned int mtu) { netdev_features_t features; struct sk_buff *segs; @@ -227,7 +229,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb) /* common case: locally created skb or seglen is <= mtu */ if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) || - skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb)) + skb_gso_network_seglen(skb) <= mtu) return ip_finish_output2(sk, skb); /* Slowpath - GSO segment length is exceeding the dst MTU. @@ -251,7 +253,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb) int err; segs->next = NULL; - err = ip_fragment(sk, segs, ip_finish_output2); + err = ip_fragment(sk, segs, mtu, ip_finish_output2); if (err && ret == 0) ret = err; @@ -263,6 +265,8 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb) static int ip_finish_output(struct sock *sk, struct sk_buff *skb) { + unsigned int mtu; + #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { @@ -270,11 +274,12 @@ static int ip_finish_output(struct sock *sk, struct sk_buff *skb) return dst_output_sk(sk, skb); } #endif + mtu = ip_skb_dst_mtu(skb); if (skb_is_gso(skb)) - return ip_finish_output_gso(sk, skb); + return ip_finish_output_gso(sk, skb, mtu); - if (skb->len > ip_skb_dst_mtu(skb)) - return ip_fragment(sk, skb, ip_finish_output2); + if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU)) + return ip_fragment(sk, skb, mtu, ip_finish_output2); return ip_finish_output2(sk, skb); } @@ -482,12 +487,15 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) } static int ip_fragment(struct sock *sk, struct sk_buff *skb, + unsigned int mtu, int (*output)(struct sock *, struct sk_buff *)) { struct iphdr *iph = ip_hdr(skb); - unsigned int mtu = ip_skb_dst_mtu(skb); - if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || + if ((iph->frag_off & htons(IP_DF)) == 0) + return ip_do_fragment(sk, skb, output); + + if (unlikely(!skb->ignore_df || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { struct rtable *rt = skb_rtable(skb); @@ -532,6 +540,8 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb, iph = ip_hdr(skb); mtu = ip_skb_dst_mtu(skb); + if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) + mtu = IPCB(skb)->frag_max_size; /* * Setup starting values. @@ -727,6 +737,9 @@ slow_path: iph = ip_hdr(skb2); iph->frag_off = htons((offset >> 3)); + if (IPCB(skb)->flags & IPSKB_FRAG_PMTU) + iph->frag_off |= htons(IP_DF); + /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 9f7269f..0c15208 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -65,7 +65,6 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, goto drop; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; - skb->mark = be32_to_cpu(tunnel->parms.i_key); return xfrm_input(skb, nexthdr, spi, encap_type); } @@ -91,6 +90,8 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) struct pcpu_sw_netstats *tstats; struct xfrm_state *x; struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; + u32 orig_mark = skb->mark; + int ret; if (!tunnel) return 1; @@ -107,7 +108,11 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) x = xfrm_input_state(skb); family = x->inner_mode->afinfo->family; - if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + skb->mark = be32_to_cpu(tunnel->parms.i_key); + ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); + skb->mark = orig_mark; + + if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); @@ -216,8 +221,6 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&fl, 0, sizeof(fl)); - skb->mark = be32_to_cpu(tunnel->parms.o_key); - switch (skb->protocol) { case htons(ETH_P_IP): xfrm_decode_session(skb, &fl, AF_INET); @@ -233,6 +236,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } + /* override mark with tunnel output key */ + fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key); + return vti_xmit(skb, dev, &fl); } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2d0e265..e7abf51 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1444,7 +1444,6 @@ static int compat_find_calc_match(struct xt_entry_match *m, const char *name, const struct ipt_ip *ip, - unsigned int hookmask, int *size) { struct xt_match *match; @@ -1513,8 +1512,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { - ret = compat_find_calc_match(ematch, name, - &e->ip, e->comefrom, &off); + ret = compat_find_calc_match(ematch, name, &e->ip, &off); if (ret != 0) goto release_matches; ++j; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 841de32..433231c 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -41,11 +41,19 @@ static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; +static int min_sndbuf = SOCK_MIN_SNDBUF; +static int min_rcvbuf = SOCK_MIN_RCVBUF; /* Update system visible IP port range */ static void set_local_port_range(struct net *net, int range[2]) { + bool same_parity = !((range[0] ^ range[1]) & 1); + write_seqlock(&net->ipv4.ip_local_ports.lock); + if (same_parity && !net->ipv4.ip_local_ports.warned) { + net->ipv4.ip_local_ports.warned = true; + pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n"); + } net->ipv4.ip_local_ports.range[0] = range[0]; net->ipv4.ip_local_ports.range[1] = range[1]; write_sequnlock(&net->ipv4.ip_local_ports.lock); @@ -522,7 +530,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_tcp_wmem), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "tcp_notsent_lowat", @@ -537,7 +545,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_tcp_rmem), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "tcp_app_win", @@ -702,7 +710,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = &one, .extra2 = &gso_max_segs, }, { @@ -750,7 +758,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_rmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one + .extra1 = &min_rcvbuf, }, { .procname = "udp_wmem_min", @@ -758,7 +766,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_wmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one + .extra1 = &min_sndbuf, }, { } }; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 7a5ae50..84be008 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -187,6 +187,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, tcp_cleanup_congestion_control(sk); icsk->icsk_ca_ops = ca; + icsk->icsk_ca_setsockopt = 1; if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); @@ -335,8 +336,10 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) rcu_read_lock(); ca = __tcp_ca_find_autoload(name); /* No change asking for existing value */ - if (ca == icsk->icsk_ca_ops) + if (ca == icsk->icsk_ca_ops) { + icsk->icsk_ca_setsockopt = 1; goto out; + } if (!ca) err = -ENOENT; else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index df7fe3c..4bc00cb 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -420,7 +420,10 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) rcu_read_unlock(); } - if (!ca_got_dst && !try_module_get(icsk->icsk_ca_ops->owner)) + /* If no valid choice made yet, assign current system default ca. */ + if (!ca_got_dst && + (!icsk->icsk_ca_setsockopt || + !try_module_get(icsk->icsk_ca_ops->owner))) tcp_assign_congestion_control(sk); tcp_set_ca_state(sk, TCP_CA_Open); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 534e5fd..190538a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2088,7 +2088,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) break; - if (tso_segs == 1 || !max_segs) { + if (tso_segs == 1) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) @@ -2101,7 +2101,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } limit = mss_now; - if (tso_segs > 1 && max_segs && !tcp_urg_mode(tp)) + if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, min_t(unsigned int, cwnd_quota, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d10b7e0..1c92ea6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1345,10 +1345,8 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 31f1b5d..7c07ce3 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -248,7 +248,8 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) aead_givcrypt_set_crypt(req, sg, sg, clen, iv); aead_givcrypt_set_assoc(req, asg, assoclen); aead_givcrypt_set_giv(req, esph->enc_data, - XFRM_SKB_CB(skb)->seq.output.low); + XFRM_SKB_CB(skb)->seq.output.low + + ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32)); ESP_SKB_CB(skb)->tmp = tmp; err = crypto_aead_givencrypt(req); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 2c2b5d5..713d743 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -207,7 +207,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, struct inet_peer *peer; peer = inet_getpeer_v6(net->ipv6.peers, - &rt->rt6i_dst.addr, 1); + &fl6->daddr, 1); res = inet_peer_xrlim_allow(peer, tmo); if (peer) inet_putpeer(peer); @@ -337,7 +337,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, * We won't send icmp if the destination is known * anycast. */ - if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) { + if (ipv6_anycast_destination(dst, &fl6->daddr)) { net_dbg_ratelimited("icmp6_send: acast source\n"); dst_release(dst); return ERR_PTR(-EINVAL); @@ -564,7 +564,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (!ipv6_unicast_destination(skb) && !(net->ipv6.sysctl.anycast_src_echo_reply && - ipv6_anycast_destination(skb))) + ipv6_anycast_destination(skb_dst(skb), saddr))) saddr = NULL; memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr)); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 871641b..b4fd96d 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -257,7 +257,7 @@ not_unique: return -EADDRNOTAVAIL; } -static inline u32 inet6_sk_port_offset(const struct sock *sk) +static u32 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); @@ -269,7 +269,11 @@ static inline u32 inet6_sk_port_offset(const struct sock *sk) int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk), + u32 port_offset = 0; + + if (!inet_sk(sk)->inet_num) + port_offset = inet6_sk_port_offset(sk); + return __inet_hash_connect(death_row, sk, port_offset, __inet6_check_established); } EXPORT_SYMBOL_GPL(inet6_hash_connect); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index bde57b1..55d1986 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -154,10 +154,32 @@ static void node_free(struct fib6_node *fn) kmem_cache_free(fib6_node_kmem, fn); } +static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) +{ + int cpu; + + if (!non_pcpu_rt->rt6i_pcpu) + return; + + for_each_possible_cpu(cpu) { + struct rt6_info **ppcpu_rt; + struct rt6_info *pcpu_rt; + + ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu); + pcpu_rt = *ppcpu_rt; + if (pcpu_rt) { + dst_free(&pcpu_rt->dst); + *ppcpu_rt = NULL; + } + } +} + static void rt6_release(struct rt6_info *rt) { - if (atomic_dec_and_test(&rt->rt6i_ref)) + if (atomic_dec_and_test(&rt->rt6i_ref)) { + rt6_free_pcpu(rt); dst_free(&rt->dst); + } } static void fib6_link_table(struct net *net, struct fib6_table *tb) @@ -738,6 +760,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, rt6_clean_expires(iter); else rt6_set_expires(iter, rt->dst.expires); + iter->rt6i_pmtu = rt->rt6i_pmtu; return -EEXIST; } /* If we have the same destination and the same metric, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index bc09cb9..d5f7716 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -105,7 +105,7 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb) } rcu_read_lock_bh(); - nexthop = rt6_nexthop((struct rt6_info *)dst); + nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); @@ -459,7 +459,7 @@ int ip6_forward(struct sk_buff *skb) else target = &hdr->daddr; - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) @@ -551,7 +551,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, struct frag_hdr *fh; unsigned int mtu, hlen, left, len; int hroom, troom; - __be32 frag_id = 0; + __be32 frag_id; int ptr, offset = 0, err = 0; u8 *prevhdr, nexthdr = 0; struct net *net = dev_net(skb_dst(skb)->dev); @@ -564,18 +564,17 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ - if (unlikely(!skb->ignore_df && skb->len > mtu) || - (IP6CB(skb)->frag_max_size && - IP6CB(skb)->frag_max_size > mtu)) { - if (skb->sk && dst_allfrag(skb_dst(skb))) - sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK); + if (unlikely(!skb->ignore_df && skb->len > mtu)) + goto fail_toobig; - skb->dev = skb_dst(skb)->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_FRAGFAILS); - kfree_skb(skb); - return -EMSGSIZE; + if (IP6CB(skb)->frag_max_size) { + if (IP6CB(skb)->frag_max_size > mtu) + goto fail_toobig; + + /* don't send fragments larger than what we received */ + mtu = IP6CB(skb)->frag_max_size; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; } if (np && np->frag_size < mtu) { @@ -584,6 +583,9 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, } mtu -= hlen + sizeof(struct frag_hdr); + frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, + &ipv6_hdr(skb)->saddr); + if (skb_has_frag_list(skb)) { int first_len = skb_pagelen(skb); struct sk_buff *frag2; @@ -632,11 +634,10 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); - ipv6_select_ident(net, fh, rt); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); - frag_id = fh->identification; + fh->identification = frag_id; first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); @@ -778,11 +779,7 @@ slow_path: */ fh->nexthdr = nexthdr; fh->reserved = 0; - if (!frag_id) { - ipv6_select_ident(net, fh, rt); - frag_id = fh->identification; - } else - fh->identification = frag_id; + fh->identification = frag_id; /* * Copy a block of the IP datagram. @@ -815,6 +812,14 @@ slow_path: consume_skb(skb); return err; +fail_toobig: + if (skb->sk && dst_allfrag(skb_dst(skb))) + sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK); + + skb->dev = skb_dst(skb)->dev; + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + err = -EMSGSIZE; + fail: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); @@ -936,7 +941,8 @@ static int ip6_dst_lookup_tail(struct sock *sk, */ rt = (struct rt6_info *) *dst; rcu_read_lock_bh(); - n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt)); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, + rt6_nexthop(rt, &fl6->daddr)); err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock_bh(); @@ -1060,11 +1066,10 @@ static inline int ip6_ufo_append_data(struct sock *sk, int odd, struct sk_buff *skb), void *from, int length, int hh_len, int fragheaderlen, int transhdrlen, int mtu, unsigned int flags, - struct rt6_info *rt) + const struct flowi6 *fl6) { struct sk_buff *skb; - struct frag_hdr fhdr; int err; /* There is support for UDP large send offload by network @@ -1106,8 +1111,9 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - sizeof(struct frag_hdr)) & ~7; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(sock_net(sk), &fhdr, rt); - skb_shinfo(skb)->ip6_frag_id = fhdr.identification; + skb_shinfo(skb)->ip6_frag_id = ipv6_select_ident(sock_net(sk), + &fl6->daddr, + &fl6->saddr); append: return skb_append_datato_frags(sk, skb, getfrag, from, @@ -1332,7 +1338,7 @@ emsgsize: (sk->sk_type == SOCK_DGRAM)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, - transhdrlen, mtu, flags, rt); + transhdrlen, mtu, flags, fl6); if (err) goto error; return 0; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5cafd92..2e67b66 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -151,7 +151,7 @@ EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset); void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *) dst; - t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; + t->dst_cookie = rt6_get_cookie(rt); dst_release(t->dst_cache); t->dst_cache = dst; } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index ed9d681..0224c03 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -322,7 +322,6 @@ static int vti6_rcv(struct sk_buff *skb) } XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; - skb->mark = be32_to_cpu(t->parms.i_key); rcu_read_unlock(); @@ -342,6 +341,8 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) struct pcpu_sw_netstats *tstats; struct xfrm_state *x; struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; + u32 orig_mark = skb->mark; + int ret; if (!t) return 1; @@ -358,7 +359,11 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) x = xfrm_input_state(skb); family = x->inner_mode->afinfo->family; - if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + skb->mark = be32_to_cpu(t->parms.i_key); + ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); + skb->mark = orig_mark; + + if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev))); @@ -430,6 +435,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) struct net_device *tdev; struct xfrm_state *x; int err = -1; + int mtu; if (!dst) goto tx_err_link_failure; @@ -463,6 +469,19 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; + mtu = dst_mtu(dst); + if (!skb->ignore_df && skb->len > mtu) { + skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu); + + if (skb->protocol == htons(ETH_P_IPV6)) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + else + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + + return -EMSGSIZE; + } + err = dst_output(skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); @@ -495,7 +514,6 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) int ret; memset(&fl, 0, sizeof(fl)); - skb->mark = be32_to_cpu(t->parms.o_key); switch (skb->protocol) { case htons(ETH_P_IPV6): @@ -516,6 +534,9 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_err; } + /* override mark with tunnel output key */ + fl.flowi_mark = be32_to_cpu(t->parms.o_key); + ret = vti6_xmit(skb, dev, &fl); if (ret < 0) goto tx_err; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 96f153c..0a05b35 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1506,7 +1506,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) "Redirect: destination is not a neighbour\n"); goto release; } - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1); ret = inet_peer_xrlim_allow(peer, 1*HZ); if (peer) inet_putpeer(peer); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 62f5b0d..cdd085f 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1459,7 +1459,6 @@ static int compat_find_calc_match(struct xt_entry_match *m, const char *name, const struct ip6t_ip6 *ipv6, - unsigned int hookmask, int *size) { struct xt_match *match; @@ -1528,8 +1527,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { - ret = compat_find_calc_match(ematch, name, - &e->ipv6, e->comefrom, &off); + ret = compat_find_calc_match(ematch, name, &e->ipv6, &off); if (ret != 0) goto release_matches; ++j; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 85892af..21678ac 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -10,7 +10,8 @@ #include <net/secure_seq.h> static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, - struct in6_addr *dst, struct in6_addr *src) + const struct in6_addr *dst, + const struct in6_addr *src) { u32 hash, id; @@ -60,17 +61,17 @@ void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); -void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr, - struct rt6_info *rt) +__be32 ipv6_select_ident(struct net *net, + const struct in6_addr *daddr, + const struct in6_addr *saddr) { static u32 ip6_idents_hashrnd __read_mostly; u32 id; net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); - id = __ipv6_select_ident(net, ip6_idents_hashrnd, &rt->rt6i_dst.addr, - &rt->rt6i_src.addr); - fhdr->identification = htonl(id); + id = __ipv6_select_ident(net, ip6_idents_hashrnd, daddr, saddr); + return htonl(id); } EXPORT_SYMBOL(ipv6_select_ident); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8072bd4..ca4700c 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -865,6 +865,9 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + if (inet->hdrincl) + fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); @@ -1324,13 +1327,7 @@ static struct inet_protosw rawv6_protosw = { int __init rawv6_init(void) { - int ret; - - ret = inet6_register_protosw(&rawv6_protosw); - if (ret) - goto out; -out: - return ret; + return inet6_register_protosw(&rawv6_protosw); } void rawv6_exit(void) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0c889cb..1a1122a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -72,8 +72,7 @@ enum rt6_nud_state { RT6_NUD_SUCCEED = 1 }; -static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, - const struct in6_addr *dest); +static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); static unsigned int ip6_mtu(const struct dst_entry *dst); @@ -105,11 +104,79 @@ static struct rt6_info *rt6_get_route_info(struct net *net, const struct in6_addr *gwaddr, int ifindex); #endif +struct uncached_list { + spinlock_t lock; + struct list_head head; +}; + +static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); + +static void rt6_uncached_list_add(struct rt6_info *rt) +{ + struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); + + rt->dst.flags |= DST_NOCACHE; + rt->rt6i_uncached_list = ul; + + spin_lock_bh(&ul->lock); + list_add_tail(&rt->rt6i_uncached, &ul->head); + spin_unlock_bh(&ul->lock); +} + +static void rt6_uncached_list_del(struct rt6_info *rt) +{ + if (!list_empty(&rt->rt6i_uncached)) { + struct uncached_list *ul = rt->rt6i_uncached_list; + + spin_lock_bh(&ul->lock); + list_del(&rt->rt6i_uncached); + spin_unlock_bh(&ul->lock); + } +} + +static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) +{ + struct net_device *loopback_dev = net->loopback_dev; + int cpu; + + for_each_possible_cpu(cpu) { + struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); + struct rt6_info *rt; + + spin_lock_bh(&ul->lock); + list_for_each_entry(rt, &ul->head, rt6i_uncached) { + struct inet6_dev *rt_idev = rt->rt6i_idev; + struct net_device *rt_dev = rt->dst.dev; + + if (rt_idev && (rt_idev->dev == dev || !dev) && + rt_idev->dev != loopback_dev) { + rt->rt6i_idev = in6_dev_get(loopback_dev); + in6_dev_put(rt_idev); + } + + if (rt_dev && (rt_dev == dev || !dev) && + rt_dev != loopback_dev) { + rt->dst.dev = loopback_dev; + dev_hold(rt->dst.dev); + dev_put(rt_dev); + } + } + spin_unlock_bh(&ul->lock); + } +} + +static u32 *rt6_pcpu_cow_metrics(struct rt6_info *rt) +{ + return dst_metrics_write_ptr(rt->dst.from); +} + static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) { struct rt6_info *rt = (struct rt6_info *)dst; - if (rt->rt6i_flags & RTF_CACHE) + if (rt->rt6i_flags & RTF_PCPU) + return rt6_pcpu_cow_metrics(rt); + else if (rt->rt6i_flags & RTF_CACHE) return NULL; else return dst_cow_metrics_generic(dst, old); @@ -249,10 +316,10 @@ static const struct rt6_info ip6_blk_hole_entry_template = { #endif /* allocate dst with ip6_dst_ops */ -static inline struct rt6_info *ip6_dst_alloc(struct net *net, - struct net_device *dev, - int flags, - struct fib6_table *table) +static struct rt6_info *__ip6_dst_alloc(struct net *net, + struct net_device *dev, + int flags, + struct fib6_table *table) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0, DST_OBSOLETE_FORCE_CHK, flags); @@ -262,18 +329,53 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); INIT_LIST_HEAD(&rt->rt6i_siblings); + INIT_LIST_HEAD(&rt->rt6i_uncached); } return rt; } +static struct rt6_info *ip6_dst_alloc(struct net *net, + struct net_device *dev, + int flags, + struct fib6_table *table) +{ + struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags, table); + + if (rt) { + rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC); + if (rt->rt6i_pcpu) { + int cpu; + + for_each_possible_cpu(cpu) { + struct rt6_info **p; + + p = per_cpu_ptr(rt->rt6i_pcpu, cpu); + /* no one shares rt */ + *p = NULL; + } + } else { + dst_destroy((struct dst_entry *)rt); + return NULL; + } + } + + return rt; +} + static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; - struct inet6_dev *idev = rt->rt6i_idev; struct dst_entry *from = dst->from; + struct inet6_dev *idev; dst_destroy_metrics_generic(dst); + if (rt->rt6i_pcpu) + free_percpu(rt->rt6i_pcpu); + + rt6_uncached_list_del(rt); + + idev = rt->rt6i_idev; if (idev) { rt->rt6i_idev = NULL; in6_dev_put(idev); @@ -655,6 +757,11 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) return match ? match : net->ipv6.ip6_null_entry; } +static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt) +{ + return (rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)); +} + #ifdef CONFIG_IPV6_ROUTE_INFO int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr) @@ -833,9 +940,9 @@ int ip6_ins_rt(struct rt6_info *rt) return __ip6_ins_rt(rt, &info, &mxc); } -static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, - const struct in6_addr *daddr, - const struct in6_addr *saddr) +static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, + const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct rt6_info *rt; @@ -843,15 +950,26 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, * Clone the route. */ - rt = ip6_rt_copy(ort, daddr); + if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)) + ort = (struct rt6_info *)ort->dst.from; - if (rt) { + rt = __ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev, + 0, ort->rt6i_table); + + if (!rt) + return NULL; + + ip6_rt_copy_init(rt, ort); + rt->rt6i_flags |= RTF_CACHE; + rt->rt6i_metric = 0; + rt->dst.flags |= DST_HOST; + rt->rt6i_dst.addr = *daddr; + rt->rt6i_dst.plen = 128; + + if (!rt6_is_gw_or_nonexthop(ort)) { if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; - - rt->rt6i_flags |= RTF_CACHE; - #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { rt->rt6i_src.addr = *saddr; @@ -863,30 +981,65 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, return rt; } -static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, - const struct in6_addr *daddr) +static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt) { - struct rt6_info *rt = ip6_rt_copy(ort, daddr); + struct rt6_info *pcpu_rt; - if (rt) - rt->rt6i_flags |= RTF_CACHE; - return rt; + pcpu_rt = __ip6_dst_alloc(dev_net(rt->dst.dev), + rt->dst.dev, rt->dst.flags, + rt->rt6i_table); + + if (!pcpu_rt) + return NULL; + ip6_rt_copy_init(pcpu_rt, rt); + pcpu_rt->rt6i_protocol = rt->rt6i_protocol; + pcpu_rt->rt6i_flags |= RTF_PCPU; + return pcpu_rt; +} + +/* It should be called with read_lock_bh(&tb6_lock) acquired */ +static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) +{ + struct rt6_info *pcpu_rt, *prev, **p; + + p = this_cpu_ptr(rt->rt6i_pcpu); + pcpu_rt = *p; + + if (pcpu_rt) + goto done; + + pcpu_rt = ip6_rt_pcpu_alloc(rt); + if (!pcpu_rt) { + struct net *net = dev_net(rt->dst.dev); + + pcpu_rt = net->ipv6.ip6_null_entry; + goto done; + } + + prev = cmpxchg(p, NULL, pcpu_rt); + if (prev) { + /* If someone did it before us, return prev instead */ + dst_destroy(&pcpu_rt->dst); + pcpu_rt = prev; + } + +done: + dst_hold(&pcpu_rt->dst); + rt6_dst_from_metrics_check(pcpu_rt); + return pcpu_rt; } static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { struct fib6_node *fn, *saved_fn; - struct rt6_info *rt, *nrt; + struct rt6_info *rt; int strict = 0; - int attempts = 3; - int err; strict |= flags & RT6_LOOKUP_F_IFACE; if (net->ipv6.devconf_all->forwarding == 0) strict |= RT6_LOOKUP_F_REACHABLE; -redo_fib6_lookup_lock: read_lock_bh(&table->tb6_lock); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); @@ -905,52 +1058,52 @@ redo_rt6_select: strict &= ~RT6_LOOKUP_F_REACHABLE; fn = saved_fn; goto redo_rt6_select; - } else { - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - goto out2; } } - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - if (rt->rt6i_flags & RTF_CACHE) - goto out2; + if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) { + dst_use(&rt->dst, jiffies); + read_unlock_bh(&table->tb6_lock); - if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY))) - nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); - else if (!(rt->dst.flags & DST_HOST) || !(rt->rt6i_flags & RTF_LOCAL)) - nrt = rt6_alloc_clone(rt, &fl6->daddr); - else - goto out2; + rt6_dst_from_metrics_check(rt); + return rt; + } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && + !(rt->rt6i_flags & RTF_GATEWAY))) { + /* Create a RTF_CACHE clone which will not be + * owned by the fib6 tree. It is for the special case where + * the daddr in the skb during the neighbor look-up is different + * from the fl6->daddr used to look-up route here. + */ - ip6_rt_put(rt); - rt = nrt ? : net->ipv6.ip6_null_entry; + struct rt6_info *uncached_rt; - dst_hold(&rt->dst); - if (nrt) { - err = ip6_ins_rt(nrt); - if (!err) - goto out2; - } + dst_use(&rt->dst, jiffies); + read_unlock_bh(&table->tb6_lock); - if (--attempts <= 0) - goto out2; + uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); + dst_release(&rt->dst); - /* - * Race condition! In the gap, when table->tb6_lock was - * released someone could insert this route. Relookup. - */ - ip6_rt_put(rt); - goto redo_fib6_lookup_lock; + if (uncached_rt) + rt6_uncached_list_add(uncached_rt); + else + uncached_rt = net->ipv6.ip6_null_entry; -out2: - rt6_dst_from_metrics_check(rt); - rt->dst.lastuse = jiffies; - rt->dst.__use++; + dst_hold(&uncached_rt->dst); + return uncached_rt; - return rt; + } else { + /* Get a percpu copy */ + + struct rt6_info *pcpu_rt; + + rt->dst.lastuse = jiffies; + rt->dst.__use++; + pcpu_rt = rt6_get_pcpu_route(rt); + read_unlock_bh(&table->tb6_lock); + + return pcpu_rt; + } } static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, @@ -1061,6 +1214,26 @@ static void rt6_dst_from_metrics_check(struct rt6_info *rt) dst_init_metrics(&rt->dst, dst_metrics_ptr(rt->dst.from), true); } +static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie) +{ + if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + return NULL; + + if (rt6_check_expired(rt)) + return NULL; + + return &rt->dst; +} + +static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie) +{ + if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && + rt6_check((struct rt6_info *)(rt->dst.from), cookie)) + return &rt->dst; + else + return NULL; +} + static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) { struct rt6_info *rt; @@ -1071,15 +1244,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ - if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) - return NULL; - - if (rt6_check_expired(rt)) - return NULL; rt6_dst_from_metrics_check(rt); - return dst; + if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE)) + return rt6_dst_from_check(rt, cookie); + else + return rt6_check(rt, cookie); } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) @@ -1118,24 +1289,63 @@ static void ip6_link_failure(struct sk_buff *skb) } } -static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) +static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) +{ + struct net *net = dev_net(rt->dst.dev); + + rt->rt6i_flags |= RTF_MODIFIED; + rt->rt6i_pmtu = mtu; + rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); +} + +static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, + const struct ipv6hdr *iph, u32 mtu) { struct rt6_info *rt6 = (struct rt6_info *)dst; - dst_confirm(dst); - if (mtu < dst_mtu(dst) && (rt6->rt6i_flags & RTF_CACHE)) { - struct net *net = dev_net(dst->dev); + if (rt6->rt6i_flags & RTF_LOCAL) + return; - rt6->rt6i_flags |= RTF_MODIFIED; - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; + dst_confirm(dst); + mtu = max_t(u32, mtu, IPV6_MIN_MTU); + if (mtu >= dst_mtu(dst)) + return; - rt6->rt6i_pmtu = mtu; - rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); + if (rt6->rt6i_flags & RTF_CACHE) { + rt6_do_update_pmtu(rt6, mtu); + } else { + const struct in6_addr *daddr, *saddr; + struct rt6_info *nrt6; + + if (iph) { + daddr = &iph->daddr; + saddr = &iph->saddr; + } else if (sk) { + daddr = &sk->sk_v6_daddr; + saddr = &inet6_sk(sk)->saddr; + } else { + return; + } + nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr); + if (nrt6) { + rt6_do_update_pmtu(nrt6, mtu); + + /* ip6_ins_rt(nrt6) will bump the + * rt6->rt6i_node->fn_sernum + * which will fail the next rt6_check() and + * invalidate the sk->sk_dst_cache. + */ + ip6_ins_rt(nrt6); + } } } +static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ + __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu); +} + void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark) { @@ -1152,7 +1362,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) - ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu)); + __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu)); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); @@ -1879,7 +2089,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu NEIGH_UPDATE_F_ISROUTER)) ); - nrt = ip6_rt_copy(rt, &msg->dest); + nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL); if (!nrt) goto out; @@ -1921,46 +2131,25 @@ static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from) dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true); } -static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, - const struct in6_addr *dest) +static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort) { - struct net *net = dev_net(ort->dst.dev); - struct rt6_info *rt; - - if (ort->rt6i_flags & RTF_CACHE) - ort = (struct rt6_info *)ort->dst.from; - - rt = ip6_dst_alloc(net, ort->dst.dev, 0, - ort->rt6i_table); - - if (rt) { - rt->dst.input = ort->dst.input; - rt->dst.output = ort->dst.output; - rt->dst.flags |= DST_HOST; - - rt->rt6i_dst.addr = *dest; - rt->rt6i_dst.plen = 128; - rt->dst.error = ort->dst.error; - rt->rt6i_idev = ort->rt6i_idev; - if (rt->rt6i_idev) - in6_dev_hold(rt->rt6i_idev); - rt->dst.lastuse = jiffies; - - if (ort->rt6i_flags & RTF_GATEWAY) - rt->rt6i_gateway = ort->rt6i_gateway; - else - rt->rt6i_gateway = *dest; - rt->rt6i_flags = ort->rt6i_flags; - rt6_set_from(rt, ort); - rt->rt6i_metric = 0; - + rt->dst.input = ort->dst.input; + rt->dst.output = ort->dst.output; + rt->rt6i_dst = ort->rt6i_dst; + rt->dst.error = ort->dst.error; + rt->rt6i_idev = ort->rt6i_idev; + if (rt->rt6i_idev) + in6_dev_hold(rt->rt6i_idev); + rt->dst.lastuse = jiffies; + rt->rt6i_gateway = ort->rt6i_gateway; + rt->rt6i_flags = ort->rt6i_flags; + rt6_set_from(rt, ort); + rt->rt6i_metric = ort->rt6i_metric; #ifdef CONFIG_IPV6_SUBTREES - memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); + rt->rt6i_src = ort->rt6i_src; #endif - memcpy(&rt->rt6i_prefsrc, &ort->rt6i_prefsrc, sizeof(struct rt6key)); - rt->rt6i_table = ort->rt6i_table; - } - return rt; + rt->rt6i_prefsrc = ort->rt6i_prefsrc; + rt->rt6i_table = ort->rt6i_table; } #ifdef CONFIG_IPV6_ROUTE_INFO @@ -2335,6 +2524,7 @@ void rt6_ifdown(struct net *net, struct net_device *dev) fib6_clean_all(net, fib6_ifdown, &adn); icmp6_clean_all(fib6_ifdown, &adn); + rt6_uncached_list_flush_dev(net, dev); } struct rt6_mtu_change_arg { @@ -3231,6 +3421,7 @@ static struct notifier_block ip6_route_dev_notifier = { int __init ip6_route_init(void) { int ret; + int cpu; ret = -ENOMEM; ip6_dst_ops_template.kmem_cachep = @@ -3290,6 +3481,13 @@ int __init ip6_route_init(void) if (ret) goto out_register_late_subsys; + for_each_possible_cpu(cpu) { + struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); + + INIT_LIST_HEAD(&ul->head); + spin_lock_init(&ul->lock); + } + out: return ret; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index fefe445..7be3d85 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -99,8 +99,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) dst_hold(dst); sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; - if (rt->rt6i_node) - inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum; + inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); } } @@ -262,7 +261,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, rt = (struct rt6_info *) dst; if (tcp_death_row.sysctl_tw_recycle && !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr)) + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr)) tcp_fetch_timewait_stamp(sk, dst); icsk->icsk_ext_hdr_len = 0; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index c2ec416..e51fc3e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -525,10 +525,8 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 6ae256b..ed0583c 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -76,8 +76,7 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst, { if (dst->ops->family == AF_INET6) { struct rt6_info *rt = (struct rt6_info *)dst; - if (rt->rt6i_node) - path->path_cookie = rt->rt6i_node->fn_sernum; + path->path_cookie = rt6_get_cookie(rt); } path->u.rt6.rt6i_nfheader_len = nfheader_len; @@ -105,8 +104,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, RTF_LOCAL); xdst->u.rt6.rt6i_metric = rt->rt6i_metric; xdst->u.rt6.rt6i_node = rt->rt6i_node; - if (rt->rt6i_node) - xdst->route_cookie = rt->rt6i_node->fn_sernum; + xdst->route_cookie = rt6_get_cookie(rt); xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; xdst->u.rt6.rt6i_src = rt->rt6i_src; diff --git a/net/irda/timer.c b/net/irda/timer.c index 0c4c115..f2280f7 100644 --- a/net/irda/timer.c +++ b/net/irda/timer.c @@ -60,8 +60,8 @@ void irlap_start_query_timer(struct irlap_cb *self, int S, int s) * to avoid messing with for incoming connections requests and * to accommodate devices that perform discovery slower than us. * Jean II */ - timeout = ((sysctl_slot_timeout * HZ / 1000) * (S - s) - + XIDEXTRA_TIMEOUT + SMALLBUSY_TIMEOUT); + timeout = msecs_to_jiffies(sysctl_slot_timeout) * (S - s) + + XIDEXTRA_TIMEOUT + SMALLBUSY_TIMEOUT; /* Set or re-set the timer. We reset the timer for each received * discovery query, which allow us to automatically adjust to diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 3469bbd..690b9f6 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1411,6 +1411,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, } sta->sdata = vlansdata; + ieee80211_check_fast_xmit(sta); if (sta->sta_state == IEEE80211_STA_AUTHORIZED && prev_4addr != new_4addr) { @@ -2538,51 +2539,22 @@ static bool ieee80211_coalesce_started_roc(struct ieee80211_local *local, struct ieee80211_roc_work *new_roc, struct ieee80211_roc_work *cur_roc) { - unsigned long j = jiffies; - unsigned long cur_roc_end = cur_roc->hw_start_time + - msecs_to_jiffies(cur_roc->duration); - struct ieee80211_roc_work *next_roc; - int new_dur; + unsigned long now = jiffies; + unsigned long remaining = cur_roc->hw_start_time + + msecs_to_jiffies(cur_roc->duration) - + now; if (WARN_ON(!cur_roc->started || !cur_roc->hw_begun)) return false; - if (time_after(j + IEEE80211_ROC_MIN_LEFT, cur_roc_end)) + /* if it doesn't fit entirely, schedule a new one */ + if (new_roc->duration > jiffies_to_msecs(remaining)) return false; ieee80211_handle_roc_started(new_roc); - new_dur = new_roc->duration - jiffies_to_msecs(cur_roc_end - j); - - /* cur_roc is long enough - add new_roc to the dependents list. */ - if (new_dur <= 0) { - list_add_tail(&new_roc->list, &cur_roc->dependents); - return true; - } - - new_roc->duration = new_dur; - - /* - * if cur_roc was already coalesced before, we might - * want to extend the next roc instead of adding - * a new one. - */ - next_roc = list_entry(cur_roc->list.next, - struct ieee80211_roc_work, list); - if (&next_roc->list != &local->roc_list && - next_roc->chan == new_roc->chan && - next_roc->sdata == new_roc->sdata && - !WARN_ON(next_roc->started)) { - list_add_tail(&new_roc->list, &next_roc->dependents); - next_roc->duration = max(next_roc->duration, - new_roc->duration); - next_roc->type = max(next_roc->type, new_roc->type); - return true; - } - - /* add right after cur_roc */ - list_add(&new_roc->list, &cur_roc->list); - + /* add to dependents so we send the expired event properly */ + list_add_tail(&new_roc->list, &cur_roc->dependents); return true; } @@ -2695,17 +2667,9 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, * In the offloaded ROC case, if it hasn't begun, add * this new one to the dependent list to be handled * when the master one begins. If it has begun, - * check that there's still a minimum time left and - * if so, start this one, transmitting the frame, but - * add it to the list directly after this one with - * a reduced time so we'll ask the driver to execute - * it right after finishing the previous one, in the - * hope that it'll also be executed right afterwards, - * effectively extending the old one. - * If there's no minimum time left, just add it to the - * normal list. - * TODO: the ROC type is ignored here, assuming that it - * is better to immediately use the current ROC. + * check if it fits entirely within the existing one, + * in which case it will just be dependent as well. + * Otherwise, schedule it by itself. */ if (!tmp->hw_begun) { list_add_tail(&roc->list, &tmp->dependents); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 2c4fe45..b12f615 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -202,6 +202,8 @@ enum ieee80211_packet_rx_flags { * @IEEE80211_RX_CMNTR: received on cooked monitor already * @IEEE80211_RX_BEACON_REPORTED: This frame was already reported * to cfg80211_report_obss_beacon(). + * @IEEE80211_RX_REORDER_TIMER: this frame is released by the + * reorder buffer timeout timer, not the normal RX path * * These flags are used across handling multiple interfaces * for a single frame. @@ -209,6 +211,7 @@ enum ieee80211_packet_rx_flags { enum ieee80211_rx_flags { IEEE80211_RX_CMNTR = BIT(0), IEEE80211_RX_BEACON_REPORTED = BIT(1), + IEEE80211_RX_REORDER_TIMER = BIT(2), }; struct ieee80211_rx_data { @@ -322,12 +325,6 @@ struct mesh_preq_queue { u8 flags; }; -#if HZ/100 == 0 -#define IEEE80211_ROC_MIN_LEFT 1 -#else -#define IEEE80211_ROC_MIN_LEFT (HZ/100) -#endif - struct ieee80211_roc_work { struct list_head list; struct list_head dependents; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 4ee8fea..b2e85ff 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -522,6 +522,12 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) memcpy(sdata->vif.hw_queue, master->vif.hw_queue, sizeof(sdata->vif.hw_queue)); sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef; + + mutex_lock(&local->key_mtx); + sdata->crypto_tx_tailroom_needed_cnt += + master->crypto_tx_tailroom_needed_cnt; + mutex_unlock(&local->key_mtx); + break; } case NL80211_IFTYPE_AP: diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 2e67737..577a11a 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -58,6 +58,22 @@ static void assert_key_lock(struct ieee80211_local *local) lockdep_assert_held(&local->key_mtx); } +static void +update_vlan_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta) +{ + struct ieee80211_sub_if_data *vlan; + + if (sdata->vif.type != NL80211_IFTYPE_AP) + return; + + mutex_lock(&sdata->local->mtx); + + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + vlan->crypto_tx_tailroom_needed_cnt += delta; + + mutex_unlock(&sdata->local->mtx); +} + static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) { /* @@ -79,6 +95,8 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) * http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net */ + update_vlan_tailroom_need_count(sdata, 1); + if (!sdata->crypto_tx_tailroom_needed_cnt++) { /* * Flush all XMIT packets currently using HW encryption or no @@ -88,6 +106,15 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) } } +static void decrease_tailroom_need_count(struct ieee80211_sub_if_data *sdata, + int delta) +{ + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt < delta); + + update_vlan_tailroom_need_count(sdata, -delta); + sdata->crypto_tx_tailroom_needed_cnt -= delta; +} + static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) { struct ieee80211_sub_if_data *sdata; @@ -144,7 +171,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) - sdata->crypto_tx_tailroom_needed_cnt--; + decrease_tailroom_need_count(sdata, 1); WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) && (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)); @@ -545,7 +572,7 @@ static void __ieee80211_key_destroy(struct ieee80211_key *key, schedule_delayed_work(&sdata->dec_tailroom_needed_wk, HZ/2); } else { - sdata->crypto_tx_tailroom_needed_cnt--; + decrease_tailroom_need_count(sdata, 1); } } @@ -635,6 +662,7 @@ void ieee80211_key_free(struct ieee80211_key *key, bool delay_tailroom) void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) { struct ieee80211_key *key; + struct ieee80211_sub_if_data *vlan; ASSERT_RTNL(); @@ -643,7 +671,14 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) mutex_lock(&sdata->local->key_mtx); - sdata->crypto_tx_tailroom_needed_cnt = 0; + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || + sdata->crypto_tx_tailroom_pending_dec); + + if (sdata->vif.type == NL80211_IFTYPE_AP) { + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt || + vlan->crypto_tx_tailroom_pending_dec); + } list_for_each_entry(key, &sdata->key_list, list) { increment_tailroom_need_count(sdata); @@ -653,6 +688,22 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) mutex_unlock(&sdata->local->key_mtx); } +void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_sub_if_data *vlan; + + mutex_lock(&sdata->local->key_mtx); + + sdata->crypto_tx_tailroom_needed_cnt = 0; + + if (sdata->vif.type == NL80211_IFTYPE_AP) { + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + vlan->crypto_tx_tailroom_needed_cnt = 0; + } + + mutex_unlock(&sdata->local->key_mtx); +} + void ieee80211_iter_keys(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void (*iter)(struct ieee80211_hw *hw, @@ -692,8 +743,8 @@ static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata, { struct ieee80211_key *key, *tmp; - sdata->crypto_tx_tailroom_needed_cnt -= - sdata->crypto_tx_tailroom_pending_dec; + decrease_tailroom_need_count(sdata, + sdata->crypto_tx_tailroom_pending_dec); sdata->crypto_tx_tailroom_pending_dec = 0; ieee80211_debugfs_key_remove_mgmt_default(sdata); @@ -713,6 +764,7 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *vlan; + struct ieee80211_sub_if_data *master; struct ieee80211_key *key, *tmp; LIST_HEAD(keys); @@ -732,8 +784,20 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, list_for_each_entry_safe(key, tmp, &keys, list) __ieee80211_key_destroy(key, false); - WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || - sdata->crypto_tx_tailroom_pending_dec); + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + if (sdata->bss) { + master = container_of(sdata->bss, + struct ieee80211_sub_if_data, + u.ap); + + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt != + master->crypto_tx_tailroom_needed_cnt); + } + } else { + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || + sdata->crypto_tx_tailroom_pending_dec); + } + if (sdata->vif.type == NL80211_IFTYPE_AP) { list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt || @@ -797,8 +861,8 @@ void ieee80211_delayed_tailroom_dec(struct work_struct *wk) */ mutex_lock(&sdata->local->key_mtx); - sdata->crypto_tx_tailroom_needed_cnt -= - sdata->crypto_tx_tailroom_pending_dec; + decrease_tailroom_need_count(sdata, + sdata->crypto_tx_tailroom_pending_dec); sdata->crypto_tx_tailroom_pending_dec = 0; mutex_unlock(&sdata->local->key_mtx); } diff --git a/net/mac80211/key.h b/net/mac80211/key.h index df430a6..2119526 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -160,6 +160,7 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, void ieee80211_free_sta_keys(struct ieee80211_local *local, struct sta_info *sta); void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata); +void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata); #define key_mtx_dereference(local, ref) \ rcu_dereference_protected(ref, lockdep_is_held(&((local)->key_mtx))) diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 3c956c5..674164f 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -246,6 +246,7 @@ static void ieee80211_restart_work(struct work_struct *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, restart_work); + struct ieee80211_sub_if_data *sdata; /* wait for scan work complete */ flush_workqueue(local->workqueue); @@ -254,6 +255,8 @@ static void ieee80211_restart_work(struct work_struct *work) "%s called with hardware scan in progress\n", __func__); rtnl_lock(); + list_for_each_entry(sdata, &local->interfaces, list) + flush_delayed_work(&sdata->dec_tailroom_needed_wk); ieee80211_scan_cancel(local); ieee80211_reconfig(local); rtnl_unlock(); @@ -770,8 +773,10 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local) for (r = 0; r < local->hw.n_cipher_schemes; r++) { suites[w++] = cs[r].cipher; - if (WARN_ON(cs[r].pn_len > IEEE80211_MAX_PN_LEN)) + if (WARN_ON(cs[r].pn_len > IEEE80211_MAX_PN_LEN)) { + kfree(suites); return -EINVAL; + } } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3294666..387fe70 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1098,6 +1098,24 @@ static void ieee80211_chswitch_timer(unsigned long data) ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.chswitch_work); } +static void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata) +{ + struct sta_info *sta; + u16 reason = WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { + if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || + !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + continue; + + ieee80211_tdls_oper_request(&sdata->vif, sta->sta.addr, + NL80211_TDLS_TEARDOWN, reason, + GFP_ATOMIC); + } + rcu_read_unlock(); +} + static void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, u64 timestamp, u32 device_timestamp, @@ -1161,6 +1179,14 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, return; } + /* + * Drop all TDLS peers - either we disconnect or move to a different + * channel from this point on. There's no telling what our peer will do. + * The TDLS WIDER_BW scenario is also problematic, as peers might now + * have an incompatible wider chandef. + */ + ieee80211_teardown_tdls_peers(sdata); + mutex_lock(&local->mtx); mutex_lock(&local->chanctx_mtx); conf = rcu_dereference_protected(sdata->vif.chanctx_conf, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index aa35977..7d85f75 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2108,7 +2108,8 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) /* deliver to local stack */ skb->protocol = eth_type_trans(skb, dev); memset(skb->cb, 0, sizeof(skb->cb)); - if (rx->local->napi) + if (!(rx->flags & IEEE80211_RX_REORDER_TIMER) && + rx->local->napi) napi_gro_receive(rx->local->napi, skb); else netif_receive_skb(skb); @@ -3215,7 +3216,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) /* This is OK -- must be QoS data frame */ .security_idx = tid, .seqno_idx = tid, - .flags = 0, + .flags = IEEE80211_RX_REORDER_TIMER, }; struct tid_ampdu_rx *tid_agg_rx; diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 8a92a92..75e8e3b 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -1183,6 +1183,12 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, switch (oper) { case NL80211_TDLS_ENABLE_LINK: + if (sdata->vif.csa_active) { + tdls_dbg(sdata, "TDLS: disallow link during CSA\n"); + ret = -EBUSY; + break; + } + rcu_read_lock(); sta = sta_info_get(sdata, peer); if (!sta) { diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 79412f1..b864ebc 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2023,6 +2023,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* add back keys */ list_for_each_entry(sdata, &local->interfaces, list) + ieee80211_reset_crypto_tx_tailroom(sdata); + + list_for_each_entry(sdata, &local->interfaces, list) if (ieee80211_sdata_running(sdata)) ieee80211_enable_keys(sdata); diff --git a/net/mac802154/Kconfig b/net/mac802154/Kconfig index aa462b4..fb45287 100644 --- a/net/mac802154/Kconfig +++ b/net/mac802154/Kconfig @@ -2,6 +2,7 @@ config MAC802154 tristate "Generic IEEE 802.15.4 Soft Networking Stack (mac802154)" depends on IEEE802154 select CRC_CCITT + select CRYPTO select CRYPTO_AUTHENC select CRYPTO_CCM select CRYPTO_CTR diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c index 70be9c7..317c466 100644 --- a/net/mac802154/cfg.c +++ b/net/mac802154/cfg.c @@ -73,9 +73,9 @@ ieee802154_set_channel(struct wpan_phy *wpan_phy, u8 page, u8 channel) ASSERT_RTNL(); - /* check if phy support this setting */ - if (!(wpan_phy->channels_supported[page] & BIT(channel))) - return -EINVAL; + if (wpan_phy->current_page == page && + wpan_phy->current_channel == channel) + return 0; ret = drv_set_channel(local, page, channel); if (!ret) { @@ -95,9 +95,8 @@ ieee802154_set_cca_mode(struct wpan_phy *wpan_phy, ASSERT_RTNL(); - /* check if phy support this setting */ - if (!(local->hw.flags & IEEE802154_HW_CCA_MODE)) - return -EOPNOTSUPP; + if (wpan_phy_cca_cmp(&wpan_phy->cca, cca)) + return 0; ret = drv_set_cca_mode(local, cca); if (!ret) @@ -107,20 +106,49 @@ ieee802154_set_cca_mode(struct wpan_phy *wpan_phy, } static int +ieee802154_set_cca_ed_level(struct wpan_phy *wpan_phy, s32 ed_level) +{ + struct ieee802154_local *local = wpan_phy_priv(wpan_phy); + int ret; + + ASSERT_RTNL(); + + if (wpan_phy->cca_ed_level == ed_level) + return 0; + + ret = drv_set_cca_ed_level(local, ed_level); + if (!ret) + wpan_phy->cca_ed_level = ed_level; + + return ret; +} + +static int +ieee802154_set_tx_power(struct wpan_phy *wpan_phy, s32 power) +{ + struct ieee802154_local *local = wpan_phy_priv(wpan_phy); + int ret; + + ASSERT_RTNL(); + + if (wpan_phy->transmit_power == power) + return 0; + + ret = drv_set_tx_power(local, power); + if (!ret) + wpan_phy->transmit_power = power; + + return ret; +} + +static int ieee802154_set_pan_id(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 pan_id) { ASSERT_RTNL(); - /* TODO - * I am not sure about to check here on broadcast pan_id. - * Broadcast is a valid setting, comment from 802.15.4: - * If this value is 0xffff, the device is not associated. - * - * This could useful to simple deassociate an device. - */ - if (pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST)) - return -EINVAL; + if (wpan_dev->pan_id == pan_id) + return 0; wpan_dev->pan_id = pan_id; return 0; @@ -131,12 +159,11 @@ ieee802154_set_backoff_exponent(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, u8 min_be, u8 max_be) { - struct ieee802154_local *local = wpan_phy_priv(wpan_phy); - ASSERT_RTNL(); - if (!(local->hw.flags & IEEE802154_HW_CSMA_PARAMS)) - return -EOPNOTSUPP; + if (wpan_dev->min_be == min_be && + wpan_dev->max_be == max_be) + return 0; wpan_dev->min_be = min_be; wpan_dev->max_be = max_be; @@ -149,20 +176,8 @@ ieee802154_set_short_addr(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, { ASSERT_RTNL(); - /* TODO - * I am not sure about to check here on broadcast short_addr. - * Broadcast is a valid setting, comment from 802.15.4: - * A value of 0xfffe indicates that the device has - * associated but has not been allocated an address. A - * value of 0xffff indicates that the device does not - * have a short address. - * - * I think we should allow to set these settings but - * don't allow to allow socket communication with it. - */ - if (short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC) || - short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST)) - return -EINVAL; + if (wpan_dev->short_addr == short_addr) + return 0; wpan_dev->short_addr = short_addr; return 0; @@ -173,12 +188,10 @@ ieee802154_set_max_csma_backoffs(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, u8 max_csma_backoffs) { - struct ieee802154_local *local = wpan_phy_priv(wpan_phy); - ASSERT_RTNL(); - if (!(local->hw.flags & IEEE802154_HW_CSMA_PARAMS)) - return -EOPNOTSUPP; + if (wpan_dev->csma_retries == max_csma_backoffs) + return 0; wpan_dev->csma_retries = max_csma_backoffs; return 0; @@ -189,12 +202,10 @@ ieee802154_set_max_frame_retries(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, s8 max_frame_retries) { - struct ieee802154_local *local = wpan_phy_priv(wpan_phy); - ASSERT_RTNL(); - if (!(local->hw.flags & IEEE802154_HW_FRAME_RETRIES)) - return -EOPNOTSUPP; + if (wpan_dev->frame_retries == max_frame_retries) + return 0; wpan_dev->frame_retries = max_frame_retries; return 0; @@ -204,12 +215,10 @@ static int ieee802154_set_lbt_mode(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, bool mode) { - struct ieee802154_local *local = wpan_phy_priv(wpan_phy); - ASSERT_RTNL(); - if (!(local->hw.flags & IEEE802154_HW_LBT)) - return -EOPNOTSUPP; + if (wpan_dev->lbt == mode) + return 0; wpan_dev->lbt = mode; return 0; @@ -222,6 +231,8 @@ const struct cfg802154_ops mac802154_config_ops = { .del_virtual_intf = ieee802154_del_iface, .set_channel = ieee802154_set_channel, .set_cca_mode = ieee802154_set_cca_mode, + .set_cca_ed_level = ieee802154_set_cca_ed_level, + .set_tx_power = ieee802154_set_tx_power, .set_pan_id = ieee802154_set_pan_id, .set_short_addr = ieee802154_set_short_addr, .set_backoff_exponent = ieee802154_set_backoff_exponent, diff --git a/net/mac802154/driver-ops.h b/net/mac802154/driver-ops.h index a053335..caecd5f 100644 --- a/net/mac802154/driver-ops.h +++ b/net/mac802154/driver-ops.h @@ -58,7 +58,7 @@ drv_set_channel(struct ieee802154_local *local, u8 page, u8 channel) return local->ops->set_channel(&local->hw, page, channel); } -static inline int drv_set_tx_power(struct ieee802154_local *local, s8 dbm) +static inline int drv_set_tx_power(struct ieee802154_local *local, s32 mbm) { might_sleep(); @@ -67,7 +67,7 @@ static inline int drv_set_tx_power(struct ieee802154_local *local, s8 dbm) return -EOPNOTSUPP; } - return local->ops->set_txpower(&local->hw, dbm); + return local->ops->set_txpower(&local->hw, mbm); } static inline int drv_set_cca_mode(struct ieee802154_local *local, @@ -96,7 +96,7 @@ static inline int drv_set_lbt_mode(struct ieee802154_local *local, bool mode) } static inline int -drv_set_cca_ed_level(struct ieee802154_local *local, s32 ed_level) +drv_set_cca_ed_level(struct ieee802154_local *local, s32 mbm) { might_sleep(); @@ -105,7 +105,7 @@ drv_set_cca_ed_level(struct ieee802154_local *local, s32 ed_level) return -EOPNOTSUPP; } - return local->ops->set_cca_ed_level(&local->hw, ed_level); + return local->ops->set_cca_ed_level(&local->hw, mbm); } static inline int drv_set_pan_id(struct ieee802154_local *local, __le16 pan_id) diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 127ba18..eec668f 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -86,8 +86,6 @@ struct ieee802154_sub_if_data { unsigned long state; char name[IFNAMSIZ]; - spinlock_t mib_lock; - /* protects sec from concurrent access by netlink. access by * encrypt/decrypt/header_create safe without additional protection. */ @@ -136,12 +134,7 @@ ieee802154_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); enum hrtimer_restart ieee802154_xmit_ifs_timer(struct hrtimer *timer); /* MIB callbacks */ -void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val); -__le16 mac802154_dev_get_short_addr(const struct net_device *dev); -__le16 mac802154_dev_get_pan_id(const struct net_device *dev); -void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val); void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan); -u8 mac802154_dev_get_dsn(const struct net_device *dev); int mac802154_get_params(struct net_device *dev, struct ieee802154_llsec_params *params); diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 91b75ab..b544b5d 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -62,9 +62,10 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) (struct sockaddr_ieee802154 *)&ifr->ifr_addr; int err = -ENOIOCTLCMD; - ASSERT_RTNL(); + if (cmd != SIOCGIFADDR && cmd != SIOCSIFADDR) + return err; - spin_lock_bh(&sdata->mib_lock); + rtnl_lock(); switch (cmd) { case SIOCGIFADDR: @@ -89,7 +90,7 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } case SIOCSIFADDR: if (netif_running(dev)) { - spin_unlock_bh(&sdata->mib_lock); + rtnl_unlock(); return -EBUSY; } @@ -111,7 +112,7 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; } - spin_unlock_bh(&sdata->mib_lock); + rtnl_unlock(); return err; } @@ -241,7 +242,6 @@ static int mac802154_wpan_open(struct net_device *dev) struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; struct wpan_dev *wpan_dev = &sdata->wpan_dev; - struct wpan_phy *phy = sdata->local->phy; rc = ieee802154_check_concurrent_iface(sdata, sdata->vif.type); if (rc < 0) @@ -251,8 +251,6 @@ static int mac802154_wpan_open(struct net_device *dev) if (rc < 0) return rc; - mutex_lock(&phy->pib_lock); - if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { rc = drv_set_promiscuous_mode(local, wpan_dev->promiscuous_mode); @@ -294,11 +292,7 @@ static int mac802154_wpan_open(struct net_device *dev) goto out; } - mutex_unlock(&phy->pib_lock); - return 0; - out: - mutex_unlock(&phy->pib_lock); return rc; } @@ -374,14 +368,12 @@ static int mac802154_header_create(struct sk_buff *skb, hdr.fc.type = cb->type; hdr.fc.security_enabled = cb->secen; hdr.fc.ack_request = cb->ackreq; - hdr.seq = ieee802154_mlme_ops(dev)->get_dsn(dev); + hdr.seq = atomic_inc_return(&dev->ieee802154_ptr->dsn) & 0xFF; if (mac802154_set_header_security(sdata, &hdr, cb) < 0) return -EINVAL; if (!saddr) { - spin_lock_bh(&sdata->mib_lock); - if (wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) || wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) || wpan_dev->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) { @@ -393,8 +385,6 @@ static int mac802154_header_create(struct sk_buff *skb, } hdr.source.pan_id = wpan_dev->pan_id; - - spin_unlock_bh(&sdata->mib_lock); } else { hdr.source = *(const struct ieee802154_addr *)saddr; } @@ -474,13 +464,16 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, enum nl802154_iftype type) { struct wpan_dev *wpan_dev = &sdata->wpan_dev; + u8 tmp; /* set some type-dependent values */ sdata->vif.type = type; sdata->wpan_dev.iftype = type; - get_random_bytes(&wpan_dev->bsn, 1); - get_random_bytes(&wpan_dev->dsn, 1); + get_random_bytes(&tmp, sizeof(tmp)); + atomic_set(&wpan_dev->bsn, tmp); + get_random_bytes(&tmp, sizeof(tmp)); + atomic_set(&wpan_dev->dsn, tmp); /* defaults per 802.15.4-2011 */ wpan_dev->min_be = 3; @@ -503,7 +496,6 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, sdata->dev->ml_priv = &mac802154_mlme_wpan; wpan_dev->promiscuous_mode = false; - spin_lock_init(&sdata->mib_lock); mutex_init(&sdata->sec_mtx); mac802154_llsec_init(&sdata->sec); diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c index bdccb4e..8606da4 100644 --- a/net/mac802154/mac_cmd.c +++ b/net/mac802154/mac_cmd.c @@ -36,37 +36,30 @@ static int mac802154_mlme_start_req(struct net_device *dev, u8 pan_coord, u8 blx, u8 coord_realign) { - struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); - int rc = 0; + struct ieee802154_llsec_params params; + int changed = 0; ASSERT_RTNL(); BUG_ON(addr->mode != IEEE802154_ADDR_SHORT); - mac802154_dev_set_pan_id(dev, addr->pan_id); - mac802154_dev_set_short_addr(dev, addr->short_addr); + dev->ieee802154_ptr->pan_id = addr->pan_id; + dev->ieee802154_ptr->short_addr = addr->short_addr; mac802154_dev_set_page_channel(dev, page, channel); - if (ops->llsec) { - struct ieee802154_llsec_params params; - int changed = 0; + params.pan_id = addr->pan_id; + changed |= IEEE802154_LLSEC_PARAM_PAN_ID; - params.coord_shortaddr = addr->short_addr; - changed |= IEEE802154_LLSEC_PARAM_COORD_SHORTADDR; + params.hwaddr = ieee802154_devaddr_from_raw(dev->dev_addr); + changed |= IEEE802154_LLSEC_PARAM_HWADDR; - params.pan_id = addr->pan_id; - changed |= IEEE802154_LLSEC_PARAM_PAN_ID; + params.coord_hwaddr = params.hwaddr; + changed |= IEEE802154_LLSEC_PARAM_COORD_HWADDR; - params.hwaddr = ieee802154_devaddr_from_raw(dev->dev_addr); - changed |= IEEE802154_LLSEC_PARAM_HWADDR; + params.coord_shortaddr = addr->short_addr; + changed |= IEEE802154_LLSEC_PARAM_COORD_SHORTADDR; - params.coord_hwaddr = params.hwaddr; - changed |= IEEE802154_LLSEC_PARAM_COORD_HWADDR; - - rc = ops->llsec->set_params(dev, ¶ms, changed); - } - - return rc; + return mac802154_set_params(dev, ¶ms, changed); } static int mac802154_set_mac_params(struct net_device *dev, @@ -91,19 +84,19 @@ static int mac802154_set_mac_params(struct net_device *dev, wpan_dev->frame_retries = params->frame_retries; wpan_dev->lbt = params->lbt; - if (local->hw.flags & IEEE802154_HW_TXPOWER) { + if (local->hw.phy->flags & WPAN_PHY_FLAG_TXPOWER) { ret = drv_set_tx_power(local, params->transmit_power); if (ret < 0) return ret; } - if (local->hw.flags & IEEE802154_HW_CCA_MODE) { + if (local->hw.phy->flags & WPAN_PHY_FLAG_CCA_MODE) { ret = drv_set_cca_mode(local, ¶ms->cca); if (ret < 0) return ret; } - if (local->hw.flags & IEEE802154_HW_CCA_ED_LEVEL) { + if (local->hw.phy->flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { ret = drv_set_cca_ed_level(local, params->cca_ed_level); if (ret < 0) return ret; @@ -151,9 +144,6 @@ static struct ieee802154_llsec_ops mac802154_llsec_ops = { struct ieee802154_mlme_ops mac802154_mlme_wpan = { .start_req = mac802154_mlme_start_req, - .get_pan_id = mac802154_dev_get_pan_id, - .get_short_addr = mac802154_dev_get_short_addr, - .get_dsn = mac802154_dev_get_dsn, .llsec = &mac802154_llsec_ops, diff --git a/net/mac802154/main.c b/net/mac802154/main.c index 08cb32d..356b346 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -107,6 +107,18 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) skb_queue_head_init(&local->skb_queue); + /* init supported flags with 802.15.4 default ranges */ + phy->supported.max_minbe = 8; + phy->supported.min_maxbe = 3; + phy->supported.max_maxbe = 8; + phy->supported.min_frame_retries = -1; + phy->supported.max_frame_retries = 7; + phy->supported.max_csma_backoffs = 5; + phy->supported.lbt = NL802154_SUPPORTED_BOOL_FALSE; + + /* always supported */ + phy->supported.iftypes = BIT(NL802154_IFTYPE_NODE); + return &local->hw; } EXPORT_SYMBOL(ieee802154_alloc_hw); @@ -155,6 +167,26 @@ int ieee802154_register_hw(struct ieee802154_hw *hw) ieee802154_setup_wpan_phy_pib(local->phy); + if (!(hw->flags & IEEE802154_HW_CSMA_PARAMS)) { + local->phy->supported.min_csma_backoffs = 4; + local->phy->supported.max_csma_backoffs = 4; + local->phy->supported.min_maxbe = 5; + local->phy->supported.max_maxbe = 5; + local->phy->supported.min_minbe = 3; + local->phy->supported.max_minbe = 3; + } + + if (!(hw->flags & IEEE802154_HW_FRAME_RETRIES)) { + /* TODO should be 3, but our default value is -1 which means + * no ARET handling. + */ + local->phy->supported.min_frame_retries = -1; + local->phy->supported.max_frame_retries = -1; + } + + if (hw->flags & IEEE802154_HW_PROMISCUOUS) + local->phy->supported.iftypes |= BIT(NL802154_IFTYPE_MONITOR); + rc = wpan_phy_register(local->phy); if (rc < 0) goto out_wq; diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c index 5cf019a..73f94fb 100644 --- a/net/mac802154/mib.c +++ b/net/mac802154/mib.c @@ -26,81 +26,22 @@ #include "ieee802154_i.h" #include "driver-ops.h" -void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val) -{ - struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); - - BUG_ON(dev->type != ARPHRD_IEEE802154); - - spin_lock_bh(&sdata->mib_lock); - sdata->wpan_dev.short_addr = val; - spin_unlock_bh(&sdata->mib_lock); -} - -__le16 mac802154_dev_get_short_addr(const struct net_device *dev) -{ - struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); - __le16 ret; - - BUG_ON(dev->type != ARPHRD_IEEE802154); - - spin_lock_bh(&sdata->mib_lock); - ret = sdata->wpan_dev.short_addr; - spin_unlock_bh(&sdata->mib_lock); - - return ret; -} - -__le16 mac802154_dev_get_pan_id(const struct net_device *dev) -{ - struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); - __le16 ret; - - BUG_ON(dev->type != ARPHRD_IEEE802154); - - spin_lock_bh(&sdata->mib_lock); - ret = sdata->wpan_dev.pan_id; - spin_unlock_bh(&sdata->mib_lock); - - return ret; -} - -void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val) -{ - struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); - - BUG_ON(dev->type != ARPHRD_IEEE802154); - - spin_lock_bh(&sdata->mib_lock); - sdata->wpan_dev.pan_id = val; - spin_unlock_bh(&sdata->mib_lock); -} - -u8 mac802154_dev_get_dsn(const struct net_device *dev) -{ - struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); - - BUG_ON(dev->type != ARPHRD_IEEE802154); - - return sdata->wpan_dev.dsn++; -} - void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; int res; + ASSERT_RTNL(); + BUG_ON(dev->type != ARPHRD_IEEE802154); res = drv_set_channel(local, page, chan); if (res) { pr_debug("set_channel failed\n"); } else { - mutex_lock(&local->phy->pib_lock); local->phy->current_channel = chan; local->phy->current_page = page; - mutex_unlock(&local->phy->pib_lock); } } diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index c0d67b2..e0f1006 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -47,8 +47,6 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, pr_debug("getting packet via slave interface %s\n", sdata->dev->name); - spin_lock_bh(&sdata->mib_lock); - span = wpan_dev->pan_id; sshort = wpan_dev->short_addr; @@ -83,13 +81,10 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, skb->pkt_type = PACKET_OTHERHOST; break; default: - spin_unlock_bh(&sdata->mib_lock); pr_debug("invalid dest mode\n"); goto fail; } - spin_unlock_bh(&sdata->mib_lock); - skb->dev = sdata->dev; rc = mac802154_llsec_decrypt(&sdata->sec, skb); diff --git a/net/mac802154/util.c b/net/mac802154/util.c index 150bf80..583435f 100644 --- a/net/mac802154/util.c +++ b/net/mac802154/util.c @@ -85,11 +85,10 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, hrtimer_start(&local->ifs_timer, ktime_set(0, hw->phy->sifs_period * NSEC_PER_USEC), HRTIMER_MODE_REL); - - consume_skb(skb); } else { ieee802154_wake_queue(hw); - consume_skb(skb); } + + dev_consume_skb_any(skb); } EXPORT_SYMBOL(ieee802154_xmit_complete); diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index 809df53..0183b32 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -62,6 +62,7 @@ out: static struct packet_offload mpls_mc_offload __read_mostly = { .type = cpu_to_be16(ETH_P_MPLS_MC), + .priority = 15, .callbacks = { .gso_segment = mpls_gso_segment, }, @@ -69,6 +70,7 @@ static struct packet_offload mpls_mc_offload __read_mostly = { static struct packet_offload mpls_uc_offload __read_mostly = { .type = cpu_to_be16(ETH_P_MPLS_UC), + .priority = 15, .callbacks = { .gso_segment = mpls_gso_segment, }, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 1c78d7f..fbc8d15 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -3,6 +3,7 @@ menu "Core Netfilter Configuration" config NETFILTER_INGRESS bool "Netfilter ingress support" + default y select NET_INGRESS help This allows you to classify packets from ingress using the Netfilter @@ -455,6 +456,11 @@ config NF_TABLES_INET help This option enables support for a mixed IPv4/IPv6 "inet" table. +config NF_TABLES_NETDEV + tristate "Netfilter nf_tables netdev tables support" + help + This option enables support for the "netdev" table. + config NFT_EXTHDR tristate "Netfilter nf_tables IPv6 exthdr module" help diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index a87d8b8..70d026d 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -75,6 +75,7 @@ nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NF_TABLES_INET) += nf_tables_inet.o +obj-$(CONFIG_NF_TABLES_NETDEV) += nf_tables_netdev.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o obj-$(CONFIG_NFT_META) += nft_meta.o diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 19986ec..bf66a86 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -364,13 +364,16 @@ err_unreach: #ifdef CONFIG_IP_VS_IPV6 static struct dst_entry * __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr, - struct in6_addr *ret_saddr, int do_xfrm) + struct in6_addr *ret_saddr, int do_xfrm, int rt_mode) { struct dst_entry *dst; struct flowi6 fl6 = { .daddr = *daddr, }; + if (rt_mode & IP_VS_RT_MODE_KNOWN_NH) + fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; + dst = ip6_route_output(net, NULL, &fl6); if (dst->error) goto out_err; @@ -427,7 +430,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, } dst = __ip_vs_route_output_v6(net, &dest->addr.in6, &dest_dst->dst_saddr.in6, - do_xfrm); + do_xfrm, rt_mode); if (!dst) { __ip_vs_dst_set(dest, NULL, NULL, 0); spin_unlock_bh(&dest->dst_lock); @@ -435,7 +438,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, goto err_unreach; } rt = (struct rt6_info *) dst; - cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; + cookie = rt6_get_cookie(rt); __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie); spin_unlock_bh(&dest->dst_lock); IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", @@ -446,7 +449,8 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, *ret_saddr = dest_dst->dst_saddr.in6; } else { noref = 0; - dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm); + dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm, + rt_mode); if (!dst) goto err_unreach; rt = (struct rt6_info *) dst; @@ -781,7 +785,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && - ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { + ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) { IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0, "ip_vs_nat_xmit_v6(): " "stopping DNAT to loopback address"); @@ -1164,7 +1168,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6, NULL, ipvsh, 0, IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL); + IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_KNOWN_NH); if (local < 0) goto tx_error; if (local) { @@ -1346,7 +1351,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && - ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { + ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) { IP_VS_DBG(1, "%s(): " "stopping DNAT to loopback %pI6\n", __func__, &cp->daddr.in6); diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 1d69f5b..9511af0 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -779,8 +779,8 @@ static int callforward_do_filter(struct net *net, flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(net, (struct dst_entry **)&rt2, flowi6_to_flowi(&fl2), false)) { - if (ipv6_addr_equal(rt6_nexthop(rt1), - rt6_nexthop(rt2)) && + if (ipv6_addr_equal(rt6_nexthop(rt1, &fl1.daddr), + rt6_nexthop(rt2, &fl2.daddr)) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 34ded09..4528f12 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -399,6 +399,8 @@ static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { [NFTA_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_TABLE_FLAGS] = { .type = NLA_U32 }, + [NFTA_TABLE_DEV] = { .type = NLA_STRING, + .len = IFNAMSIZ - 1 }, }; static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, @@ -423,6 +425,10 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use))) goto nla_put_failure; + if (table->dev && + nla_put_string(skb, NFTA_TABLE_DEV, table->dev->name)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -608,6 +614,11 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags == ctx->table->flags) return 0; + if ((ctx->afi->flags & NFT_AF_NEEDS_DEV) && + ctx->nla[NFTA_TABLE_DEV] && + nla_strcmp(ctx->nla[NFTA_TABLE_DEV], ctx->table->dev->name)) + return -EOPNOTSUPP; + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) @@ -645,6 +656,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, struct nft_table *table; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct net_device *dev = NULL; u32 flags = 0; struct nft_ctx ctx; int err; @@ -679,30 +691,50 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, return -EINVAL; } + if (afi->flags & NFT_AF_NEEDS_DEV) { + char ifname[IFNAMSIZ]; + + if (!nla[NFTA_TABLE_DEV]) + return -EOPNOTSUPP; + + nla_strlcpy(ifname, nla[NFTA_TABLE_DEV], IFNAMSIZ); + dev = dev_get_by_name(net, ifname); + if (!dev) + return -ENOENT; + } else if (nla[NFTA_TABLE_DEV]) { + return -EOPNOTSUPP; + } + + err = -EAFNOSUPPORT; if (!try_module_get(afi->owner)) - return -EAFNOSUPPORT; + goto err1; err = -ENOMEM; table = kzalloc(sizeof(*table), GFP_KERNEL); if (table == NULL) - goto err1; + goto err2; nla_strlcpy(table->name, name, NFT_TABLE_MAXNAMELEN); INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); table->flags = flags; + table->dev = dev; nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); if (err < 0) - goto err2; + goto err3; list_add_tail_rcu(&table->list, &afi->tables); return 0; -err2: +err3: kfree(table); -err1: +err2: module_put(afi->owner); +err1: + if (dev != NULL) + dev_put(dev); + return err; } @@ -806,6 +838,9 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx) { BUG_ON(ctx->table->use > 0); + if (ctx->table->dev) + dev_put(ctx->table->dev); + kfree(ctx->table); module_put(ctx->afi->owner); } @@ -1361,6 +1396,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, ops->priority = priority; ops->priv = chain; ops->hook = afi->hooks[ops->hooknum]; + ops->dev = table->dev; if (hookfn) ops->hook = hookfn; if (afi->hook_ops_init) diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c new file mode 100644 index 0000000..04cb170 --- /dev/null +++ b/net/netfilter/nf_tables_netdev.c @@ -0,0 +1,183 @@ +/* + * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <net/netfilter/nf_tables.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <net/netfilter/nf_tables_ipv4.h> +#include <net/netfilter/nf_tables_ipv6.h> + +static inline void +nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt, + const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct iphdr *iph, _iph; + u32 len, thoff; + + nft_set_pktinfo(pkt, ops, skb, state); + + iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), + &_iph); + if (!iph) + return; + + iph = ip_hdr(skb); + if (iph->ihl < 5 || iph->version != 4) + return; + + len = ntohs(iph->tot_len); + thoff = iph->ihl * 4; + if (skb->len < len) + return; + else if (len < thoff) + return; + + pkt->tprot = iph->protocol; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; +} + +static inline void +__nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, + const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ +#if IS_ENABLED(CONFIG_IPV6) + struct ipv6hdr *ip6h, _ip6h; + unsigned int thoff = 0; + unsigned short frag_off; + int protohdr; + u32 pkt_len; + + ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h), + &_ip6h); + if (!ip6h) + return; + + if (ip6h->version != 6) + return; + + pkt_len = ntohs(ip6h->payload_len); + if (pkt_len + sizeof(*ip6h) > skb->len) + return; + + protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); + if (protohdr < 0) + return; + + pkt->tprot = protohdr; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = frag_off; +#endif +} + +static inline void nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, + const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + nft_set_pktinfo(pkt, ops, skb, state); + __nft_netdev_set_pktinfo_ipv6(pkt, ops, skb, state); +} + +static unsigned int +nft_do_chain_netdev(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nft_pktinfo pkt; + + switch (eth_hdr(skb)->h_proto) { + case htons(ETH_P_IP): + nft_netdev_set_pktinfo_ipv4(&pkt, ops, skb, state); + break; + case htons(ETH_P_IPV6): + nft_netdev_set_pktinfo_ipv6(&pkt, ops, skb, state); + break; + default: + nft_set_pktinfo(&pkt, ops, skb, state); + break; + } + + return nft_do_chain(&pkt, ops); +} + +static struct nft_af_info nft_af_netdev __read_mostly = { + .family = NFPROTO_NETDEV, + .nhooks = NF_NETDEV_NUMHOOKS, + .owner = THIS_MODULE, + .flags = NFT_AF_NEEDS_DEV, + .nops = 1, + .hooks = { + [NF_NETDEV_INGRESS] = nft_do_chain_netdev, + }, +}; + +static int nf_tables_netdev_init_net(struct net *net) +{ + net->nft.netdev = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL); + if (net->nft.netdev == NULL) + return -ENOMEM; + + memcpy(net->nft.netdev, &nft_af_netdev, sizeof(nft_af_netdev)); + + if (nft_register_afinfo(net, net->nft.netdev) < 0) + goto err; + + return 0; +err: + kfree(net->nft.netdev); + return -ENOMEM; +} + +static void nf_tables_netdev_exit_net(struct net *net) +{ + nft_unregister_afinfo(net->nft.netdev); + kfree(net->nft.netdev); +} + +static struct pernet_operations nf_tables_netdev_net_ops = { + .init = nf_tables_netdev_init_net, + .exit = nf_tables_netdev_exit_net, +}; + +static const struct nf_chain_type nft_filter_chain_netdev = { + .name = "filter", + .type = NFT_CHAIN_T_DEFAULT, + .family = NFPROTO_NETDEV, + .owner = THIS_MODULE, + .hook_mask = (1 << NF_NETDEV_INGRESS), +}; + +static int __init nf_tables_netdev_init(void) +{ + int ret; + + nft_register_chain_type(&nft_filter_chain_netdev); + ret = register_pernet_subsys(&nf_tables_netdev_net_ops); + if (ret < 0) + nft_unregister_chain_type(&nft_filter_chain_netdev); + + return ret; +} + +static void __exit nf_tables_netdev_exit(void) +{ + unregister_pernet_subsys(&nf_tables_netdev_net_ops); + nft_unregister_chain_type(&nft_filter_chain_netdev); +} + +module_init(nf_tables_netdev_init); +module_exit(nf_tables_netdev_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_FAMILY(5); /* NFPROTO_NETDEV */ diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 292934d..a747eb4 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -152,6 +152,7 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info) fl6.daddr = info->gw.in6; fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) | (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]; + fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index fab6eea..5b4743c 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -73,7 +73,7 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, if (dev == NULL && rt->rt6i_flags & RTF_LOCAL) ret |= XT_ADDRTYPE_LOCAL; - if (rt->rt6i_flags & RTF_ANYCAST) + if (ipv6_anycast_destination((struct dst_entry *)rt, addr)) ret |= XT_ADDRTYPE_ANYCAST; dst_release(&rt->dst); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index b491c1c..8a8c0b8 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -608,17 +608,16 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port) } static int output_userspace(struct datapath *dp, struct sk_buff *skb, - struct sw_flow_key *key, const struct nlattr *attr) + struct sw_flow_key *key, const struct nlattr *attr, + const struct nlattr *actions, int actions_len) { struct ovs_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; + memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_ACTION; - upcall.userdata = NULL; - upcall.portid = 0; - upcall.egress_tun_info = NULL; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; a = nla_next(a, &rem)) { @@ -647,6 +646,13 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, break; } + case OVS_USERSPACE_ATTR_ACTIONS: { + /* Include actions. */ + upcall.actions = actions; + upcall.actions_len = actions_len; + break; + } + } /* End of switch. */ } @@ -654,7 +660,8 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, } static int sample(struct datapath *dp, struct sk_buff *skb, - struct sw_flow_key *key, const struct nlattr *attr) + struct sw_flow_key *key, const struct nlattr *attr, + const struct nlattr *actions, int actions_len) { const struct nlattr *acts_list = NULL; const struct nlattr *a; @@ -688,7 +695,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, */ if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE && nla_is_last(a, rem))) - return output_userspace(dp, skb, key, a); + return output_userspace(dp, skb, key, a, actions, actions_len); skb = skb_clone(skb, GFP_ATOMIC); if (!skb) @@ -872,7 +879,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; case OVS_ACTION_ATTR_USERSPACE: - output_userspace(dp, skb, key, a); + output_userspace(dp, skb, key, a, attr, len); break; case OVS_ACTION_ATTR_HASH: @@ -916,7 +923,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; case OVS_ACTION_ATTR_SAMPLE: - err = sample(dp, skb, key, a); + err = sample(dp, skb, key, a, attr, len); break; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 3b90461..ff8c4a4 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -272,10 +272,9 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) struct dp_upcall_info upcall; int error; + memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_MISS; - upcall.userdata = NULL; upcall.portid = ovs_vport_find_upcall_portid(p, skb); - upcall.egress_tun_info = NULL; error = ovs_dp_upcall(dp, skb, key, &upcall); if (unlikely(error)) kfree_skb(skb); @@ -397,6 +396,10 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info, if (upcall_info->egress_tun_info) size += nla_total_size(ovs_tun_key_attr_size()); + /* OVS_PACKET_ATTR_ACTIONS */ + if (upcall_info->actions_len) + size += nla_total_size(upcall_info->actions_len); + return size; } @@ -478,6 +481,17 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, nla_nest_end(user_skb, nla); } + if (upcall_info->actions_len) { + nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_ACTIONS); + err = ovs_nla_put_actions(upcall_info->actions, + upcall_info->actions_len, + user_skb); + if (!err) + nla_nest_end(user_skb, nla); + else + nla_nest_cancel(user_skb, nla); + } + /* Only reserve room for attribute header, packet data is added * in skb_zerocopy() */ if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) { diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 4ec4a48..cd691e9 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -116,6 +116,8 @@ struct ovs_skb_cb { struct dp_upcall_info { const struct ovs_tunnel_info *egress_tun_info; const struct nlattr *userdata; + const struct nlattr *actions; + int actions_len; u32 portid; u8 cmd; }; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 3d83641..2ad9032 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -270,6 +270,28 @@ static int rds_cong_monitor(struct rds_sock *rs, char __user *optval, return ret; } +static int rds_set_transport(struct rds_sock *rs, char __user *optval, + int optlen) +{ + int t_type; + + if (rs->rs_transport) + return -EOPNOTSUPP; /* previously attached to transport */ + + if (optlen != sizeof(int)) + return -EINVAL; + + if (copy_from_user(&t_type, (int __user *)optval, sizeof(t_type))) + return -EFAULT; + + if (t_type < 0 || t_type >= RDS_TRANS_COUNT) + return -EINVAL; + + rs->rs_transport = rds_trans_get(t_type); + + return rs->rs_transport ? 0 : -ENOPROTOOPT; +} + static int rds_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { @@ -300,6 +322,11 @@ static int rds_setsockopt(struct socket *sock, int level, int optname, case RDS_CONG_MONITOR: ret = rds_cong_monitor(rs, optval, optlen); break; + case SO_RDS_TRANSPORT: + lock_sock(sock->sk); + ret = rds_set_transport(rs, optval, optlen); + release_sock(sock->sk); + break; default: ret = -ENOPROTOOPT; } @@ -312,6 +339,7 @@ static int rds_getsockopt(struct socket *sock, int level, int optname, { struct rds_sock *rs = rds_sk_to_rs(sock->sk); int ret = -ENOPROTOOPT, len; + int trans; if (level != SOL_RDS) goto out; @@ -337,6 +365,19 @@ static int rds_getsockopt(struct socket *sock, int level, int optname, else ret = 0; break; + case SO_RDS_TRANSPORT: + if (len < sizeof(int)) { + ret = -EINVAL; + break; + } + trans = (rs->rs_transport ? rs->rs_transport->t_type : + RDS_TRANS_NONE); /* unbound */ + if (put_user(trans, (int __user *)optval) || + put_user(sizeof(int), optlen)) + ret = -EFAULT; + else + ret = 0; + break; default: break; } diff --git a/net/rds/bind.c b/net/rds/bind.c index a2e6562..4ebd29c 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -181,6 +181,10 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (ret) goto out; + if (rs->rs_transport) { /* previously bound */ + ret = 0; + goto out; + } trans = rds_trans_get_preferred(sin->sin_addr.s_addr); if (!trans) { ret = -EADDRNOTAVAIL; diff --git a/net/rds/rds.h b/net/rds/rds.h index 0d41155..a33fb4a 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -408,11 +408,6 @@ struct rds_notifier { * should try hard not to block. */ -#define RDS_TRANS_IB 0 -#define RDS_TRANS_IWARP 1 -#define RDS_TRANS_TCP 2 -#define RDS_TRANS_COUNT 3 - struct rds_transport { char t_name[TRANSNAMSIZ]; struct list_head t_item; @@ -803,6 +798,7 @@ struct rds_transport *rds_trans_get_preferred(__be32 addr); void rds_trans_put(struct rds_transport *trans); unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter, unsigned int avail); +struct rds_transport *rds_trans_get(int t_type); int rds_trans_init(void); void rds_trans_exit(void); diff --git a/net/rds/transport.c b/net/rds/transport.c index 7f2ac4f..8b4a6cd 100644 --- a/net/rds/transport.c +++ b/net/rds/transport.c @@ -101,6 +101,27 @@ struct rds_transport *rds_trans_get_preferred(__be32 addr) return ret; } +struct rds_transport *rds_trans_get(int t_type) +{ + struct rds_transport *ret = NULL; + struct rds_transport *trans; + unsigned int i; + + down_read(&rds_trans_sem); + for (i = 0; i < RDS_TRANS_COUNT; i++) { + trans = transports[i]; + + if (trans && trans->t_type == t_type && + (!trans->t_owner || try_module_get(trans->t_owner))) { + ret = trans; + break; + } + } + up_read(&rds_trans_sem); + + return ret; +} + /* * This returns the number of stats entries in the snapshot and only * copies them using the iter if there is enough space for them. The diff --git a/net/rfkill/core.c b/net/rfkill/core.c index fa7cd79..f12149a 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -794,7 +794,8 @@ void rfkill_resume_polling(struct rfkill *rfkill) } EXPORT_SYMBOL(rfkill_resume_polling); -static int rfkill_suspend(struct device *dev, pm_message_t state) +#ifdef CONFIG_PM_SLEEP +static int rfkill_suspend(struct device *dev) { struct rfkill *rfkill = to_rfkill(dev); @@ -818,13 +819,18 @@ static int rfkill_resume(struct device *dev) return 0; } +static SIMPLE_DEV_PM_OPS(rfkill_pm_ops, rfkill_suspend, rfkill_resume); +#define RFKILL_PM_OPS (&rfkill_pm_ops) +#else +#define RFKILL_PM_OPS NULL +#endif + static struct class rfkill_class = { .name = "rfkill", .dev_release = rfkill_release, .dev_groups = rfkill_dev_groups, .dev_uevent = rfkill_dev_uevent, - .suspend = rfkill_suspend, - .resume = rfkill_resume, + .pm = RFKILL_PM_OPS, }; bool rfkill_blocked(struct rfkill *rfkill) diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index d978f2f..d5d58d9 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -112,21 +112,17 @@ static int rfkill_gpio_probe(struct platform_device *pdev) rfkill->clk = devm_clk_get(&pdev->dev, NULL); - gpio = devm_gpiod_get(&pdev->dev, "reset"); - if (!IS_ERR(gpio)) { - ret = gpiod_direction_output(gpio, 0); - if (ret) - return ret; - rfkill->reset_gpio = gpio; - } + gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(gpio)) + return PTR_ERR(gpio); - gpio = devm_gpiod_get(&pdev->dev, "shutdown"); - if (!IS_ERR(gpio)) { - ret = gpiod_direction_output(gpio, 0); - if (ret) - return ret; - rfkill->shutdown_gpio = gpio; - } + rfkill->reset_gpio = gpio; + + gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_OUT_LOW); + if (IS_ERR(gpio)) + return PTR_ERR(gpio); + + rfkill->shutdown_gpio = gpio; /* Make sure at-least one of the GPIO is defined and that * a name is specified for this instance diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 0b74dc0..c5b9db8 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -815,10 +815,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (dev->flags & IFF_UP) dev_deactivate(dev); - if (new && new->ops->attach) { - new->ops->attach(new); - num_q = 0; - } + if (new && new->ops->attach) + goto skip; for (i = 0; i < num_q; i++) { struct netdev_queue *dev_queue = dev_ingress_queue(dev); @@ -834,12 +832,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, qdisc_destroy(old); } +skip: if (!ingress) { notify_and_destroy(net, skb, n, classid, dev->qdisc, new); if (new && !new->ops->attach) atomic_inc(&new->refcnt); dev->qdisc = new ? : &noop_qdisc; + + if (new && new->ops->attach) + new->ops->attach(new); } else { notify_and_destroy(net, skb, n, classid, old, new); } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e703ff7..e917d27 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -331,8 +331,9 @@ out: rt = (struct rt6_info *)dst; t->dst = dst; - t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; - pr_debug("rt6_dst:%pI6 rt6_src:%pI6\n", &rt->rt6i_dst.addr, + t->dst_cookie = rt6_get_cookie(rt); + pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n", + &rt->rt6i_dst.addr, rt->rt6i_dst.plen, &fl6->saddr); } else { t->dst = NULL; diff --git a/net/tipc/link.c b/net/tipc/link.c index fb2a003..ca8b8e0 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1320,8 +1320,6 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, if (!tipc_link_is_up(l_ptr)) return; - if (skb_queue_len(&l_ptr->backlogq)) - next_sent = buf_seqno(skb_peek(&l_ptr->backlogq)); msg_set_next_sent(msg, next_sent); if (!skb_queue_empty(&l_ptr->deferdq)) { last_rcv = buf_seqno(skb_peek(&l_ptr->deferdq)); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 9370f95..30ea82a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -410,7 +410,7 @@ static int tipc_release(struct socket *sock) struct net *net; struct tipc_sock *tsk; struct sk_buff *skb; - u32 dnode, probing_state; + u32 dnode; /* * Exit if socket isn't fully initialized (occurs when a failed accept() @@ -448,10 +448,7 @@ static int tipc_release(struct socket *sock) } tipc_sk_withdraw(tsk, 0, NULL); - probing_state = tsk->probing_state; - if (del_timer_sync(&sk->sk_timer) && - probing_state != TIPC_CONN_PROBING) - sock_put(sk); + sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); if (tsk->connected) { skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index b8c4407..f25e167 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1984,6 +1984,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, unix_state_unlock(sk); timeo = freezable_schedule_timeout(timeo); unix_state_lock(sk); + + if (sock_flag(sk, SOCK_DEAD)) + break; + clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); } @@ -2055,6 +2059,10 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) struct sk_buff *skb, *last; unix_state_lock(sk); + if (sock_flag(sk, SOCK_DEAD)) { + err = -ECONNRESET; + goto unlock; + } last = skb = skb_peek(&sk->sk_receive_queue); last_len = last ? last->len : 0; again: diff --git a/net/wireless/core.h b/net/wireless/core.h index 801cd49..311eef2 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -222,6 +222,7 @@ struct cfg80211_event { const u8 *ie; size_t ie_len; u16 reason; + bool locally_generated; } dc; struct { u8 bssid[ETH_ALEN]; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index d11454f..8020b5b 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -938,7 +938,8 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, } void cfg80211_disconnected(struct net_device *dev, u16 reason, - const u8 *ie, size_t ie_len, gfp_t gfp) + const u8 *ie, size_t ie_len, + bool locally_generated, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); @@ -954,6 +955,7 @@ void cfg80211_disconnected(struct net_device *dev, u16 reason, ev->dc.ie_len = ie_len; memcpy((void *)ev->dc.ie, ie, ie_len); ev->dc.reason = reason; + ev->dc.locally_generated = locally_generated; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 9ee6bc1..9cee022 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -86,7 +86,7 @@ static int wiphy_uevent(struct device *dev, struct kobj_uevent_env *env) return 0; } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static void cfg80211_leave_all(struct cfg80211_registered_device *rdev) { struct wireless_dev *wdev; @@ -95,7 +95,7 @@ static void cfg80211_leave_all(struct cfg80211_registered_device *rdev) cfg80211_leave(rdev, wdev); } -static int wiphy_suspend(struct device *dev, pm_message_t state) +static int wiphy_suspend(struct device *dev) { struct cfg80211_registered_device *rdev = dev_to_rdev(dev); int ret = 0; @@ -136,6 +136,11 @@ static int wiphy_resume(struct device *dev) return ret; } + +static SIMPLE_DEV_PM_OPS(wiphy_pm_ops, wiphy_suspend, wiphy_resume); +#define WIPHY_PM_OPS (&wiphy_pm_ops) +#else +#define WIPHY_PM_OPS NULL #endif static const void *wiphy_namespace(struct device *d) @@ -151,10 +156,7 @@ struct class ieee80211_class = { .dev_release = wiphy_dev_release, .dev_groups = ieee80211_groups, .dev_uevent = wiphy_uevent, -#ifdef CONFIG_PM - .suspend = wiphy_suspend, - .resume = wiphy_resume, -#endif + .pm = WIPHY_PM_OPS, .ns_type = &net_ns_type_operations, .namespace = wiphy_namespace, }; diff --git a/net/wireless/util.c b/net/wireless/util.c index 70051ab..baf7218 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -887,7 +887,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) case EVENT_DISCONNECTED: __cfg80211_disconnected(wdev->netdev, ev->dc.ie, ev->dc.ie_len, - ev->dc.reason, true); + ev->dc.reason, + !ev->dc.locally_generated); break; case EVENT_IBSS_JOINED: __cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid, @@ -944,7 +945,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, ntype == NL80211_IFTYPE_P2P_CLIENT)) return -EBUSY; - if (ntype != otype && netif_running(dev)) { + if (ntype != otype) { dev->ieee80211_ptr->use_4addr = false; dev->ieee80211_ptr->mesh_id_up_len = 0; wdev_lock(dev->ieee80211_ptr); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 526c4fe..60ce701 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -13,6 +13,8 @@ #include <net/dst.h> #include <net/ip.h> #include <net/xfrm.h> +#include <net/ip_tunnels.h> +#include <net/ip6_tunnel.h> static struct kmem_cache *secpath_cachep __read_mostly; @@ -29,7 +31,7 @@ int xfrm_input_register_afinfo(struct xfrm_input_afinfo *afinfo) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_input_afinfo_lock); if (unlikely(xfrm_input_afinfo[afinfo->family] != NULL)) - err = -ENOBUFS; + err = -EEXIST; else rcu_assign_pointer(xfrm_input_afinfo[afinfo->family], afinfo); spin_unlock_bh(&xfrm_input_afinfo_lock); @@ -186,6 +188,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) struct xfrm_state *x = NULL; xfrm_address_t *daddr; struct xfrm_mode *inner_mode; + u32 mark = skb->mark; unsigned int family; int decaps = 0; int async = 0; @@ -203,6 +206,18 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SPI_SKB_CB(skb)->daddroff); family = XFRM_SPI_SKB_CB(skb)->family; + /* if tunnel is present override skb->mark value with tunnel i_key */ + if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) { + switch (family) { + case AF_INET: + mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key); + break; + case AF_INET6: + mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key); + break; + } + } + /* Allocate new secpath or COW existing one. */ if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) { struct sec_path *sp; @@ -229,7 +244,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } - x = xfrm_state_lookup(net, skb->mark, daddr, spi, nexthdr, family); + x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family); if (x == NULL) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound(skb, family, spi, seq); @@ -239,13 +254,13 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp->xvec[skb->sp->len++] = x; spin_lock(&x->lock); - if (unlikely(x->km.state == XFRM_STATE_ACQ)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); - goto drop_unlock; - } if (unlikely(x->km.state != XFRM_STATE_VALID)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); + if (x->km.state == XFRM_STATE_ACQ) + XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); + else + XFRM_INC_STATS(net, + LINUX_MIB_XFRMINSTATEINVALID); goto drop_unlock; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 638af06..18cead7 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -315,14 +315,6 @@ void xfrm_policy_destroy(struct xfrm_policy *policy) } EXPORT_SYMBOL(xfrm_policy_destroy); -static void xfrm_queue_purge(struct sk_buff_head *list) -{ - struct sk_buff *skb; - - while ((skb = skb_dequeue(list)) != NULL) - kfree_skb(skb); -} - /* Rule must be locked. Release descentant resources, announce * entry dead. The rule must be unlinked from lists to the moment. */ @@ -335,7 +327,7 @@ static void xfrm_policy_kill(struct xfrm_policy *policy) if (del_timer(&policy->polq.hold_timer)) xfrm_pol_put(policy); - xfrm_queue_purge(&policy->polq.hold_queue); + skb_queue_purge(&policy->polq.hold_queue); if (del_timer(&policy->timer)) xfrm_pol_put(policy); @@ -708,6 +700,9 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, struct xfrm_policy_queue *pq = &old->polq; struct sk_buff_head list; + if (skb_queue_empty(&pq->hold_queue)) + return; + __skb_queue_head_init(&list); spin_lock_bh(&pq->hold_queue.lock); @@ -716,9 +711,6 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, xfrm_pol_put(old); spin_unlock_bh(&pq->hold_queue.lock); - if (skb_queue_empty(&list)) - return; - pq = &new->polq; spin_lock_bh(&pq->hold_queue.lock); @@ -1012,7 +1004,9 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, if (list_empty(&walk->walk.all)) x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all); else - x = list_entry(&walk->walk.all, struct xfrm_policy_walk_entry, all); + x = list_first_entry(&walk->walk.all, + struct xfrm_policy_walk_entry, all); + list_for_each_entry_from(x, &net->xfrm.policy_all, all) { if (x->dead) continue; @@ -1120,6 +1114,9 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } chain = &net->xfrm.policy_inexact[dir]; hlist_for_each_entry(pol, chain, bydst) { + if ((pol->priority >= priority) && ret) + break; + err = xfrm_policy_match(pol, fl, type, family, dir); if (err) { if (err == -ESRCH) @@ -1128,13 +1125,13 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, ret = ERR_PTR(err); goto fail; } - } else if (pol->priority < priority) { + } else { ret = pol; break; } } - if (ret) - xfrm_pol_hold(ret); + + xfrm_pol_hold(ret); fail: read_unlock_bh(&net->xfrm.xfrm_policy_lock); @@ -1955,7 +1952,7 @@ out: purge_queue: pq->timeout = 0; - xfrm_queue_purge(&pq->hold_queue); + skb_queue_purge(&pq->hold_queue); xfrm_pol_put(pol); } @@ -2814,7 +2811,7 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) return -EAFNOSUPPORT; spin_lock(&xfrm_policy_afinfo_lock); if (unlikely(xfrm_policy_afinfo[afinfo->family] != NULL)) - err = -ENOBUFS; + err = -EEXIST; else { struct dst_ops *dst_ops = afinfo->dst_ops; if (likely(dst_ops->kmem_cachep == NULL)) @@ -3209,16 +3206,17 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector * } chain = &net->xfrm.policy_inexact[dir]; hlist_for_each_entry(pol, chain, bydst) { + if ((pol->priority >= priority) && ret) + break; + if (xfrm_migrate_selector_match(sel, &pol->selector) && - pol->type == type && - pol->priority < priority) { + pol->type == type) { ret = pol; break; } } - if (ret) - xfrm_pol_hold(ret); + xfrm_pol_hold(ret); read_unlock_bh(&net->xfrm.xfrm_policy_lock); diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index dab57da..4fd725a 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -99,6 +99,7 @@ static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq; + XFRM_SKB_CB(skb)->seq.output.hi = 0; if (unlikely(x->replay.oseq == 0)) { x->replay.oseq--; xfrm_audit_state_replay_overflow(x, skb); @@ -177,6 +178,7 @@ static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb) if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq; + XFRM_SKB_CB(skb)->seq.output.hi = 0; if (unlikely(replay_esn->oseq == 0)) { replay_esn->oseq--; xfrm_audit_state_replay_overflow(x, skb); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f5e39e3..9895a8c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -927,8 +927,8 @@ struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, x->id.spi != spi) continue; - spin_unlock_bh(&net->xfrm.xfrm_state_lock); xfrm_state_hold(x); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } spin_unlock_bh(&net->xfrm.xfrm_state_lock); @@ -1626,7 +1626,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, if (list_empty(&walk->all)) x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all); else - x = list_entry(&walk->all, struct xfrm_state_walk, all); + x = list_first_entry(&walk->all, struct xfrm_state_walk, all); list_for_each_entry_from(x, &net->xfrm.state_all, all) { if (x->state == XFRM_STATE_DEAD) continue; @@ -1908,7 +1908,7 @@ int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_afinfo_lock); if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL)) - err = -ENOBUFS; + err = -EEXIST; else rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo); spin_unlock_bh(&xfrm_state_afinfo_lock); diff --git a/scripts/gdb/linux/modules.py b/scripts/gdb/linux/modules.py index a1504c4..25db8cf 100644 --- a/scripts/gdb/linux/modules.py +++ b/scripts/gdb/linux/modules.py @@ -73,18 +73,11 @@ class LxLsmod(gdb.Command): " " if utils.get_long_type().sizeof == 8 else "")) for module in module_list(): - ref = 0 - module_refptr = module['refptr'] - for cpu in cpus.cpu_list("cpu_possible_mask"): - refptr = cpus.per_cpu(module_refptr, cpu) - ref += refptr['incs'] - ref -= refptr['decs'] - gdb.write("{address} {name:<19} {size:>8} {ref}".format( address=str(module['module_core']).split()[0], name=module['name'].string(), size=str(module['core_size']), - ref=str(ref))) + ref=str(module['refcnt']['counter']))) source_list = module['source_list'] t = self._module_use_type.get_type().pointer() diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 1c86787..ac0db16 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -4926,9 +4926,12 @@ int snd_hda_gen_parse_auto_config(struct hda_codec *codec, dig_only: parse_digital(codec); - if (spec->power_down_unused || codec->power_save_node) + if (spec->power_down_unused || codec->power_save_node) { if (!codec->power_filter) codec->power_filter = snd_hda_gen_path_power_filter; + if (!codec->patch_ops.stream_pm) + codec->patch_ops.stream_pm = snd_hda_gen_stream_pm; + } if (!spec->no_analog && spec->beep_nid) { err = snd_hda_attach_beep_device(codec, spec->beep_nid); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 34040d2..fea198c 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2089,6 +2089,8 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, { PCI_DEVICE(0x1002, 0xaab0), .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, + { PCI_DEVICE(0x1002, 0xaac8), + .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, /* VIA VT8251/VT8237A */ { PCI_DEVICE(0x1106, 0x3288), .driver_data = AZX_DRIVER_VIA | AZX_DCAPS_POSFIX_VIA }, diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 31f8f13..4641684 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -884,6 +884,7 @@ static struct alc_codec_rename_pci_table rename_pci_tbl[] = { { 0x10ec0275, 0x1028, 0, "ALC3260" }, { 0x10ec0899, 0x1028, 0, "ALC3861" }, { 0x10ec0298, 0x1028, 0, "ALC3266" }, + { 0x10ec0256, 0x1028, 0, "ALC3246" }, { 0x10ec0670, 0x1025, 0, "ALC669X" }, { 0x10ec0676, 0x1025, 0, "ALC679X" }, { 0x10ec0282, 0x1043, 0, "ALC3229" }, @@ -4227,6 +4228,11 @@ static void alc_fixup_headset_mode_alc662(struct hda_codec *codec, if (action == HDA_FIXUP_ACT_PRE_PROBE) { spec->parse_flags |= HDA_PINCFG_HEADSET_MIC; spec->gen.hp_mic = 1; /* Mic-in is same pin as headphone */ + + /* Disable boost for mic-in permanently. (This code is only called + from quirks that guarantee that the headphone is at NID 0x1b.) */ + snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_AMP_GAIN_MUTE, 0x7000); + snd_hda_override_wcaps(codec, 0x1b, get_wcaps(codec, 0x1b) & ~AC_WCAP_IN_AMP); } else alc_fixup_headset_mode(codec, fix, action); } diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 43c99ce..6833c74 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -4403,7 +4403,6 @@ static const struct hda_codec_ops stac_patch_ops = { #ifdef CONFIG_PM .suspend = stac_suspend, #endif - .stream_pm = snd_hda_gen_stream_pm, .reboot_notify = stac_shutup, }; @@ -4697,7 +4696,8 @@ static int patch_stac92hd71bxx(struct hda_codec *codec) return err; spec = codec->spec; - codec->power_save_node = 1; + /* disabled power_save_node since it causes noises on a Dell machine */ + /* codec->power_save_node = 1; */ spec->linear_tone_beep = 0; spec->gen.own_eapd_ctl = 1; spec->gen.power_down_unused = 1; diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c index d51703e..0a4ad5f 100644 --- a/sound/pci/hda/thinkpad_helper.c +++ b/sound/pci/hda/thinkpad_helper.c @@ -72,7 +72,6 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec, if (led_set_func(TPACPI_LED_MUTE, false) >= 0) { old_vmaster_hook = spec->vmaster_mute.hook; spec->vmaster_mute.hook = update_tpacpi_mute_led; - spec->vmaster_mute_enum = 1; removefunc = false; } if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 46facfc..2917534 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1118,6 +1118,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */ case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */ case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */ + case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ return true; } diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c index c5baf9c..618c2bc 100644 --- a/tools/net/bpf_jit_disasm.c +++ b/tools/net/bpf_jit_disasm.c @@ -123,6 +123,8 @@ static int get_last_jit_image(char *haystack, size_t hlen, assert(ret == 0); ptr = haystack; + memset(pmatch, 0, sizeof(pmatch)); + while (1) { ret = regexec(®ex, ptr, 1, pmatch, 0); if (ret == 0) { diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index bac98ca..323b65e 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -52,6 +52,7 @@ unsigned int skip_c0; unsigned int skip_c1; unsigned int do_nhm_cstates; unsigned int do_snb_cstates; +unsigned int do_knl_cstates; unsigned int do_pc2; unsigned int do_pc3; unsigned int do_pc6; @@ -91,6 +92,7 @@ unsigned int do_gfx_perf_limit_reasons; unsigned int do_ring_perf_limit_reasons; unsigned int crystal_hz; unsigned long long tsc_hz; +int base_cpu; #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -316,7 +318,7 @@ void print_header(void) if (do_nhm_cstates) outp += sprintf(outp, " CPU%%c1"); - if (do_nhm_cstates && !do_slm_cstates) + if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) outp += sprintf(outp, " CPU%%c3"); if (do_nhm_cstates) outp += sprintf(outp, " CPU%%c6"); @@ -546,7 +548,7 @@ int format_counters(struct thread_data *t, struct core_data *c, if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (do_nhm_cstates && !do_slm_cstates) + if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) outp += sprintf(outp, "%8.2f", 100.0 * c->c3/t->tsc); if (do_nhm_cstates) outp += sprintf(outp, "%8.2f", 100.0 * c->c6/t->tsc); @@ -1018,14 +1020,17 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) return 0; - if (do_nhm_cstates && !do_slm_cstates) { + if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; } - if (do_nhm_cstates) { + if (do_nhm_cstates && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6)) return -7; + } else if (do_knl_cstates) { + if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6)) + return -7; } if (do_snb_cstates) @@ -1150,7 +1155,7 @@ dump_nhm_platform_info(void) unsigned long long msr; unsigned int ratio; - get_msr(0, MSR_NHM_PLATFORM_INFO, &msr); + get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr); fprintf(stderr, "cpu0: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", msr); @@ -1162,7 +1167,7 @@ dump_nhm_platform_info(void) fprintf(stderr, "%d * %.0f = %.0f MHz base frequency\n", ratio, bclk, ratio * bclk); - get_msr(0, MSR_IA32_POWER_CTL, &msr); + get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr); fprintf(stderr, "cpu0: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n", msr, msr & 0x2 ? "EN" : "DIS"); @@ -1175,7 +1180,7 @@ dump_hsw_turbo_ratio_limits(void) unsigned long long msr; unsigned int ratio; - get_msr(0, MSR_TURBO_RATIO_LIMIT2, &msr); + get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT2, &msr); fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT2: 0x%08llx\n", msr); @@ -1197,7 +1202,7 @@ dump_ivt_turbo_ratio_limits(void) unsigned long long msr; unsigned int ratio; - get_msr(0, MSR_TURBO_RATIO_LIMIT1, &msr); + get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &msr); fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", msr); @@ -1249,7 +1254,7 @@ dump_nhm_turbo_ratio_limits(void) unsigned long long msr; unsigned int ratio; - get_msr(0, MSR_TURBO_RATIO_LIMIT, &msr); + get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr); fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", msr); @@ -1296,11 +1301,72 @@ dump_nhm_turbo_ratio_limits(void) } static void +dump_knl_turbo_ratio_limits(void) +{ + int cores; + unsigned int ratio; + unsigned long long msr; + int delta_cores; + int delta_ratio; + int i; + + get_msr(base_cpu, MSR_NHM_TURBO_RATIO_LIMIT, &msr); + + fprintf(stderr, "cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n", + msr); + + /** + * Turbo encoding in KNL is as follows: + * [7:0] -- Base value of number of active cores of bucket 1. + * [15:8] -- Base value of freq ratio of bucket 1. + * [20:16] -- +ve delta of number of active cores of bucket 2. + * i.e. active cores of bucket 2 = + * active cores of bucket 1 + delta + * [23:21] -- Negative delta of freq ratio of bucket 2. + * i.e. freq ratio of bucket 2 = + * freq ratio of bucket 1 - delta + * [28:24]-- +ve delta of number of active cores of bucket 3. + * [31:29]-- -ve delta of freq ratio of bucket 3. + * [36:32]-- +ve delta of number of active cores of bucket 4. + * [39:37]-- -ve delta of freq ratio of bucket 4. + * [44:40]-- +ve delta of number of active cores of bucket 5. + * [47:45]-- -ve delta of freq ratio of bucket 5. + * [52:48]-- +ve delta of number of active cores of bucket 6. + * [55:53]-- -ve delta of freq ratio of bucket 6. + * [60:56]-- +ve delta of number of active cores of bucket 7. + * [63:61]-- -ve delta of freq ratio of bucket 7. + */ + cores = msr & 0xFF; + ratio = (msr >> 8) && 0xFF; + if (ratio > 0) + fprintf(stderr, + "%d * %.0f = %.0f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, cores); + + for (i = 16; i < 64; i = i + 8) { + delta_cores = (msr >> i) & 0x1F; + delta_ratio = (msr >> (i + 5)) && 0x7; + if (!delta_cores || !delta_ratio) + return; + cores = cores + delta_cores; + ratio = ratio - delta_ratio; + + /** -ve ratios will make successive ratio calculations + * negative. Hence return instead of carrying on. + */ + if (ratio > 0) + fprintf(stderr, + "%d * %.0f = %.0f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, cores); + } +} + +static void dump_nhm_cst_cfg(void) { unsigned long long msr; - get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); + get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); #define SNB_C1_AUTO_UNDEMOTE (1UL << 27) #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) @@ -1381,12 +1447,41 @@ int parse_int_file(const char *fmt, ...) } /* - * cpu_is_first_sibling_in_core(cpu) - * return 1 if given CPU is 1st HT sibling in the core + * get_cpu_position_in_core(cpu) + * return the position of the CPU among its HT siblings in the core + * return -1 if the sibling is not in list */ -int cpu_is_first_sibling_in_core(int cpu) +int get_cpu_position_in_core(int cpu) { - return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu); + char path[64]; + FILE *filep; + int this_cpu; + char character; + int i; + + sprintf(path, + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", + cpu); + filep = fopen(path, "r"); + if (filep == NULL) { + perror(path); + exit(1); + } + + for (i = 0; i < topo.num_threads_per_core; i++) { + fscanf(filep, "%d", &this_cpu); + if (this_cpu == cpu) { + fclose(filep); + return i; + } + + /* Account for no separator after last thread*/ + if (i != (topo.num_threads_per_core - 1)) + fscanf(filep, "%c", &character); + } + + fclose(filep); + return -1; } /* @@ -1412,25 +1507,31 @@ int get_num_ht_siblings(int cpu) { char path[80]; FILE *filep; - int sib1, sib2; - int matches; + int sib1; + int matches = 0; char character; + char str[100]; + char *ch; sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu); filep = fopen_or_die(path, "r"); + /* * file format: - * if a pair of number with a character between: 2 siblings (eg. 1-2, or 1,4) - * otherwinse 1 sibling (self). + * A ',' separated or '-' separated set of numbers + * (eg 1-2 or 1,3,4,5) */ - matches = fscanf(filep, "%d%c%d\n", &sib1, &character, &sib2); + fscanf(filep, "%d%c\n", &sib1, &character); + fseek(filep, 0, SEEK_SET); + fgets(str, 100, filep); + ch = strchr(str, character); + while (ch != NULL) { + matches++; + ch = strchr(ch+1, character); + } fclose(filep); - - if (matches == 3) - return 2; - else - return 1; + return matches+1; } /* @@ -1594,8 +1695,10 @@ restart: void check_dev_msr() { struct stat sb; + char pathname[32]; - if (stat("/dev/cpu/0/msr", &sb)) + sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); + if (stat(pathname, &sb)) if (system("/sbin/modprobe msr > /dev/null 2>&1")) err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" "); } @@ -1608,6 +1711,7 @@ void check_permissions() cap_user_data_t cap_data = &cap_data_data; extern int capget(cap_user_header_t hdrp, cap_user_data_t datap); int do_exit = 0; + char pathname[32]; /* check for CAP_SYS_RAWIO */ cap_header->pid = getpid(); @@ -1622,7 +1726,8 @@ void check_permissions() } /* test file permissions */ - if (euidaccess("/dev/cpu/0/msr", R_OK)) { + sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); + if (euidaccess(pathname, R_OK)) { do_exit++; warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr"); } @@ -1704,7 +1809,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) default: return 0; } - get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); + get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); pkg_cstate_limit = pkg_cstate_limits[msr & 0xF]; @@ -1753,6 +1858,21 @@ int has_hsw_turbo_ratio_limit(unsigned int family, unsigned int model) } } +int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + if (family != 6) + return 0; + + switch (model) { + case 0x57: /* Knights Landing */ + return 1; + default: + return 0; + } +} static void dump_cstate_pstate_config_info(family, model) { @@ -1770,6 +1890,9 @@ dump_cstate_pstate_config_info(family, model) if (has_nhm_turbo_ratio_limit(family, model)) dump_nhm_turbo_ratio_limits(); + if (has_knl_turbo_ratio_limit(family, model)) + dump_knl_turbo_ratio_limits(); + dump_nhm_cst_cfg(); } @@ -1801,7 +1924,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr)) return 0; - switch (msr & 0x7) { + switch (msr & 0xF) { case ENERGY_PERF_BIAS_PERFORMANCE: epb_string = "performance"; break; @@ -1925,7 +2048,7 @@ double get_tdp(model) unsigned long long msr; if (do_rapl & RAPL_PKG_POWER_INFO) - if (!get_msr(0, MSR_PKG_POWER_INFO, &msr)) + if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr)) return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units; switch (model) { @@ -1950,6 +2073,7 @@ rapl_dram_energy_units_probe(int model, double rapl_energy_units) case 0x3F: /* HSX */ case 0x4F: /* BDX */ case 0x56: /* BDX-DE */ + case 0x57: /* KNL */ return (rapl_dram_energy_units = 15.3 / 1000000); default: return (rapl_energy_units); @@ -1991,6 +2115,7 @@ void rapl_probe(unsigned int family, unsigned int model) case 0x3F: /* HSX */ case 0x4F: /* BDX */ case 0x56: /* BDX-DE */ + case 0x57: /* KNL */ do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; break; case 0x2D: @@ -2006,7 +2131,7 @@ void rapl_probe(unsigned int family, unsigned int model) } /* units on package 0, verify later other packages match */ - if (get_msr(0, MSR_RAPL_POWER_UNIT, &msr)) + if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr)) return; rapl_power_units = 1.0 / (1 << (msr & 0xF)); @@ -2331,6 +2456,17 @@ int is_slm(unsigned int family, unsigned int model) return 0; } +int is_knl(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + switch (model) { + case 0x57: /* KNL */ + return 1; + } + return 0; +} + #define SLM_BCLK_FREQS 5 double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0}; @@ -2340,7 +2476,7 @@ double slm_bclk(void) unsigned int i; double freq; - if (get_msr(0, MSR_FSB_FREQ, &msr)) + if (get_msr(base_cpu, MSR_FSB_FREQ, &msr)) fprintf(stderr, "SLM BCLK: unknown\n"); i = msr & 0xf; @@ -2408,7 +2544,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk if (!do_nhm_platform_info) goto guess; - if (get_msr(0, MSR_IA32_TEMPERATURE_TARGET, &msr)) + if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) goto guess; target_c_local = (msr >> 16) & 0xFF; @@ -2541,6 +2677,7 @@ void process_cpuid() do_c8_c9_c10 = has_hsw_msrs(family, model); do_skl_residency = has_skl_msrs(family, model); do_slm_cstates = is_slm(family, model); + do_knl_cstates = is_knl(family, model); bclk = discover_bclk(family, model); rapl_probe(family, model); @@ -2755,13 +2892,9 @@ int initialize_counters(int cpu_id) my_package_id = get_physical_package_id(cpu_id); my_core_id = get_core_id(cpu_id); - - if (cpu_is_first_sibling_in_core(cpu_id)) { - my_thread_id = 0; + my_thread_id = get_cpu_position_in_core(cpu_id); + if (!my_thread_id) topo.num_cores++; - } else { - my_thread_id = 1; - } init_counter(EVEN_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id); init_counter(ODD_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id); @@ -2785,13 +2918,24 @@ void setup_all_buffers(void) for_all_proc_cpus(initialize_counters); } +void set_base_cpu(void) +{ + base_cpu = sched_getcpu(); + if (base_cpu < 0) + err(-ENODEV, "No valid cpus found"); + + if (debug > 1) + fprintf(stderr, "base_cpu = %d\n", base_cpu); +} + void turbostat_init() { + setup_all_buffers(); + set_base_cpu(); check_dev_msr(); check_permissions(); process_cpuid(); - setup_all_buffers(); if (debug) for_all_cpus(print_epb, ODD_COUNTERS); @@ -2870,7 +3014,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(stderr, "turbostat version 4.5 2 Apr, 2015" + fprintf(stderr, "turbostat version 4.7 27-May, 2015" " - Len Brown <lenb@kernel.org>\n"); } |
