diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-08-06 09:13:11 -0400 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-08-06 09:13:11 -0400 |
| commit | 4305f42401b29e2e024bd064618faf25aef5cb69 (patch) | |
| tree | 1bc924cfa60c9efbb21e07c1d834f495301cffc8 /arch | |
| parent | db8262787e82b5c0fa57bd9d676add187519a751 (diff) | |
| parent | 4a89cf810130fde41e3fc729e770cb1a5a87d245 (diff) | |
| download | op-kernel-dev-4305f42401b29e2e024bd064618faf25aef5cb69.zip op-kernel-dev-4305f42401b29e2e024bd064618faf25aef5cb69.tar.gz | |
Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus
Pull MIPS updates from Ralf Baechle:
"This is the main pull request for MIPS for 4.8. Also includes is a
minor SSB cleanup as SSB code traditionally is merged through the MIPS
tree:
ATH25:
- MIPS: Add default configuration for ath25
Boot:
- For zboot, copy appended dtb to the end of the kernel
- store the appended dtb address in a variable
BPF:
- Fix off by one error in offset allocation
Cobalt code:
- Fix typos
Core code:
- debugfs_create_file returns NULL on error, so don't use IS_ERR for
testing for errors.
- Fix double locking issue in RM7000 S-cache code. This would only
affect RM7000 ARC systems on reboot.
- Fix page table corruption on THP permission changes.
- Use compat_sys_keyctl for 32 bit userspace on 64 bit kernels.
David says, there are no compatibility issues raised by this fix.
- Move some signal code around.
- Rewrite r4k count/compare clockevent device registration such that
min_delta_ticks/max_delta_ticks files are guaranteed to be
initialized.
- Only register r4k count/compare as clockevent device if we can
assume the clock to be constant.
- Fix MSA asm warnings in control reg accessors
- uasm and tlbex fixes and tweaking.
- Print segment physical address when EU=1.
- Define AT_VECTOR_SIZE_ARCH for ARCH_DLINFO.
- CP: Allow booting by VP other than VP 0
- Cache handling fixes and optimizations for r4k class caches
- Add hotplug support for R6 processors
- Cleanup hotplug bits in kconfig
- traps: return correct si code for accessing nonmapped addresses
- Remove cpu_has_safe_index_cacheops
Lantiq:
- Register IRQ handler for virtual IRQ number
- Fix EIU interrupt loading code
- Use the real EXIN count
- Fix build error.
Loongson 3:
- Increase HPET_MIN_PROG_DELTA and decrease HPET_MIN_CYCLES
Octeon:
- Delete built-in DTB pruning code for D-Link DSR-1000N.
- Clean up GPIO definitions in dlink_dsr-1000n.dts.
- Add more LEDs to the DSR-100n DTS
- Fix off by one in octeon_irq_gpio_map()
- Typo fixes
- Enable SATA by default in cavium_octeon_defconfig
- Support readq/writeq()
- Remove forced mappings of USB interrupts.
- Ensure DMA descriptors are always in the low 4GB
- Improve USB reset code for OCTEON II.
Pistachio:
- Add maintainers entry for pistachio SoC Support
- Remove plat_setup_iocoherency
Ralink:
- Fix pwm UART in spis group pinmux.
SSB:
- Change bare unsigned to unsigned int to suit coding style
Tools:
- Fix reloc tool compiler warnings.
Other:
- Delete use of ARCH_WANT_OPTIONAL_GPIOLIB"
* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (61 commits)
MIPS: mm: Fix definition of R6 cache instruction
MIPS: tools: Fix relocs tool compiler warnings
MIPS: Cobalt: Fix typo
MIPS: Octeon: Fix typo
MIPS: Lantiq: Fix build failure
MIPS: Use CPHYSADDR to implement mips32 __pa
MIPS: Octeon: Dlink_dsr-1000n.dts: add more leds.
MIPS: Octeon: Clean up GPIO definitions in dlink_dsr-1000n.dts.
MIPS: Octeon: Delete built-in DTB pruning code for D-Link DSR-1000N.
MIPS: store the appended dtb address in a variable
MIPS: ZBOOT: copy appended dtb to the end of the kernel
MIPS: ralink: fix spis group pinmux
MIPS: Factor o32 specific code into signal_o32.c
MIPS: non-exec stack & heap when non-exec PT_GNU_STACK is present
MIPS: Use per-mm page to execute branch delay slot instructions
MIPS: Modify error handling
MIPS: c-r4k: Use SMP calls for CM indexed cache ops
MIPS: c-r4k: Avoid small flush_icache_range SMP calls
MIPS: c-r4k: Local flush_icache_range cache op override
MIPS: c-r4k: Split r4k_flush_kernel_vmap_range()
...
Diffstat (limited to 'arch')
67 files changed, 1397 insertions, 795 deletions
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 2986713..2638856 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -64,6 +64,7 @@ config MIPS select GENERIC_TIME_VSYSCALL select ARCH_CLOCKSOURCE_DATA select HANDLE_DOMAIN_IRQ + select HAVE_EXIT_THREAD menu "Machine selection" @@ -384,7 +385,7 @@ config MACH_PISTACHIO select CLKSRC_MIPS_GIC select COMMON_CLK select CSRC_R4K - select DMA_MAYBE_COHERENT + select DMA_NONCOHERENT select GPIOLIB select IRQ_MIPS_CPU select LIBFDT @@ -880,7 +881,6 @@ config CAVIUM_OCTEON_SOC select SYS_SUPPORTS_HOTPLUG_CPU if CPU_BIG_ENDIAN select SYS_HAS_EARLY_PRINTK select SYS_HAS_CPU_CAVIUM_OCTEON - select SWAP_IO_SPACE select HW_HAS_PCI select ZONE_DMA32 select HOLES_IN_ZONE @@ -1111,16 +1111,6 @@ config NEED_DMA_MAP_STATE config SYS_HAS_EARLY_PRINTK bool -config HOTPLUG_CPU - bool "Support for hot-pluggable CPUs" - depends on SMP && SYS_SUPPORTS_HOTPLUG_CPU - help - Say Y here to allow turning CPUs off and on. CPUs can be - controlled through /sys/devices/system/cpu. - (Note: power management support will enable this option - automatically on SMP systems. ) - Say N if you want to disable CPU hotplug. - config SYS_SUPPORTS_HOTPLUG_CPU bool @@ -1406,7 +1396,6 @@ config CPU_LOONGSON1B bool "Loongson 1B" depends on SYS_HAS_CPU_LOONGSON1B select CPU_LOONGSON1 - select ARCH_WANT_OPTIONAL_GPIOLIB select LEDS_GPIO_REGISTER help The Loongson 1B is a 32-bit SoC, which implements the MIPS32 @@ -2636,6 +2625,16 @@ config SMP If you don't know what to do here, say N. +config HOTPLUG_CPU + bool "Support for hot-pluggable CPUs" + depends on SMP && SYS_SUPPORTS_HOTPLUG_CPU + help + Say Y here to allow turning CPUs off and on. CPUs can be + controlled through /sys/devices/system/cpu. + (Note: power management support will enable this option + automatically on SMP systems. ) + Say N if you want to disable CPU hotplug. + config SMP_UP bool @@ -2887,10 +2886,10 @@ choice the documented boot protocol using a device tree. config MIPS_RAW_APPENDED_DTB - bool "vmlinux.bin" + bool "vmlinux.bin or vmlinuz.bin" help With this option, the boot code will look for a device tree binary - DTB) appended to raw vmlinux.bin (without decompressor). + DTB) appended to raw vmlinux.bin or vmlinuz.bin. (e.g. cat vmlinux.bin <filename>.dtb > vmlinux_w_dtb). This is meant as a backward compatibility convenience for those @@ -2902,24 +2901,6 @@ choice look like a DTB header after a reboot if no actual DTB is appended to vmlinux.bin. Do not leave this option active in a production kernel if you don't intend to always append a DTB. - - config MIPS_ZBOOT_APPENDED_DTB - bool "vmlinuz.bin" - depends on SYS_SUPPORTS_ZBOOT - help - With this option, the boot code will look for a device tree binary - DTB) appended to raw vmlinuz.bin (with decompressor). - (e.g. cat vmlinuz.bin <filename>.dtb > vmlinuz_w_dtb). - - This is meant as a backward compatibility convenience for those - systems with a bootloader that can't be upgraded to accommodate - the documented boot protocol using a device tree. - - Beware that there is very little in terms of protection against - this option being confused by leftover garbage in memory that might - look like a DTB header after a reboot if no actual DTB is appended - to vmlinuz.bin. Do not leave this option active in a production kernel - if you don't intend to always append a DTB. endchoice choice diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 3a0019d..f206daf 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -203,8 +203,8 @@ void __init plat_mem_setup(void) fdt_start = fw_getenvl("fdt_start"); if (fdt_start) __dt_setup_arch((void *)KSEG0ADDR(fdt_start)); - else if (fw_arg0 == -2) - __dt_setup_arch((void *)KSEG0ADDR(fw_arg1)); + else if (fw_passed_dtb) + __dt_setup_arch((void *)KSEG0ADDR(fw_passed_dtb)); if (mips_machtype != ATH79_MACH_GENERIC_OF) { ath79_reset_base = ioremap_nocache(AR71XX_RESET_BASE, diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index f146d12..6776042 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -162,8 +162,8 @@ void __init plat_mem_setup(void) /* intended to somewhat resemble ARM; see Documentation/arm/Booting */ if (fw_arg0 == 0 && fw_arg1 == 0xffffffff) dtb = phys_to_virt(fw_arg2); - else if (fw_arg0 == -2) /* UHI interface */ - dtb = (void *)fw_arg1; + else if (fw_passed_dtb) /* UHI interface */ + dtb = (void *)fw_passed_dtb; else if (__dtb_start != __dtb_end) dtb = (void *)__dtb_start; else diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index 080cd53..fdf99e9 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> +#include <linux/libfdt.h> #include <asm/addrspace.h> @@ -36,6 +37,8 @@ extern void puthex(unsigned long long val); #define puthex(val) do {} while (0) #endif +extern char __appended_dtb[]; + void error(char *x) { puts("\n\n"); @@ -114,6 +117,20 @@ void decompress_kernel(unsigned long boot_heap_start) __decompress((char *)zimage_start, zimage_size, 0, 0, (void *)VMLINUX_LOAD_ADDRESS_ULL, 0, 0, error); + if (IS_ENABLED(CONFIG_MIPS_RAW_APPENDED_DTB) && + fdt_magic((void *)&__appended_dtb) == FDT_MAGIC) { + unsigned int image_size, dtb_size; + + dtb_size = fdt_totalsize((void *)&__appended_dtb); + + /* last four bytes is always image size in little endian */ + image_size = le32_to_cpup((void *)&__image_end - 4); + + /* copy dtb to where the booted kernel will expect it */ + memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size, + __appended_dtb, dtb_size); + } + /* FIXME: should we flush cache here? */ puts("Now, booting the kernel...\n"); } diff --git a/arch/mips/boot/compressed/head.S b/arch/mips/boot/compressed/head.S index c580e85..409cb48 100644 --- a/arch/mips/boot/compressed/head.S +++ b/arch/mips/boot/compressed/head.S @@ -25,22 +25,6 @@ start: move s2, a2 move s3, a3 -#ifdef CONFIG_MIPS_ZBOOT_APPENDED_DTB - PTR_LA t0, __appended_dtb -#ifdef CONFIG_CPU_BIG_ENDIAN - li t1, 0xd00dfeed -#else - li t1, 0xedfe0dd0 -#endif - lw t2, (t0) - bne t1, t2, not_found - nop - - move s1, t0 - PTR_LI s0, -2 -not_found: -#endif - /* Clear BSS */ PTR_LA a0, _edata PTR_LA a2, _end diff --git a/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts b/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts index d6bc994..b134798 100644 --- a/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts +++ b/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts @@ -9,6 +9,7 @@ */ /include/ "octeon_3xxx.dtsi" +#include <dt-bindings/gpio/gpio.h> / { model = "dlink,dsr-1000n"; @@ -63,12 +64,27 @@ usb1 { label = "usb1"; - gpios = <&gpio 9 1>; /* Active low */ + gpios = <&gpio 9 GPIO_ACTIVE_LOW>; }; usb2 { label = "usb2"; - gpios = <&gpio 10 1>; /* Active low */ + gpios = <&gpio 10 GPIO_ACTIVE_LOW>; + }; + + wps { + label = "wps"; + gpios = <&gpio 11 GPIO_ACTIVE_LOW>; + }; + + wireless1 { + label = "5g"; + gpios = <&gpio 17 GPIO_ACTIVE_LOW>; + }; + + wireless2 { + label = "2.4g"; + gpios = <&gpio 18 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/mips/boot/dts/cavium-octeon/octeon_3xxx.dts b/arch/mips/boot/dts/cavium-octeon/octeon_3xxx.dts index de61f02..ca6b446 100644 --- a/arch/mips/boot/dts/cavium-octeon/octeon_3xxx.dts +++ b/arch/mips/boot/dts/cavium-octeon/octeon_3xxx.dts @@ -388,16 +388,4 @@ usbn = &usbn; led0 = &led0; }; - - dsr1000n-leds { - compatible = "gpio-leds"; - usb1 { - label = "usb1"; - gpios = <&gpio 9 1>; /* Active low */ - }; - usb2 { - label = "usb2"; - gpios = <&gpio 10 1>; /* Active low */ - }; - }; }; diff --git a/arch/mips/boot/tools/relocs_64.c b/arch/mips/boot/tools/relocs_64.c index b671b5e..06066e6a 100644 --- a/arch/mips/boot/tools/relocs_64.c +++ b/arch/mips/boot/tools/relocs_64.c @@ -9,17 +9,20 @@ typedef uint8_t Elf64_Byte; -typedef struct { - Elf64_Word r_sym; /* Symbol index. */ - Elf64_Byte r_ssym; /* Special symbol. */ - Elf64_Byte r_type3; /* Third relocation. */ - Elf64_Byte r_type2; /* Second relocation. */ - Elf64_Byte r_type; /* First relocation. */ +typedef union { + struct { + Elf64_Word r_sym; /* Symbol index. */ + Elf64_Byte r_ssym; /* Special symbol. */ + Elf64_Byte r_type3; /* Third relocation. */ + Elf64_Byte r_type2; /* Second relocation. */ + Elf64_Byte r_type; /* First relocation. */ + } fields; + Elf64_Xword unused; } Elf64_Mips_Rela; #define ELF_CLASS ELFCLASS64 -#define ELF_R_SYM(val) (((Elf64_Mips_Rela *)(&val))->r_sym) -#define ELF_R_TYPE(val) (((Elf64_Mips_Rela *)(&val))->r_type) +#define ELF_R_SYM(val) (((Elf64_Mips_Rela *)(&val))->fields.r_sym) +#define ELF_R_TYPE(val) (((Elf64_Mips_Rela *)(&val))->fields.r_type) #define ELF_ST_TYPE(o) ELF64_ST_TYPE(o) #define ELF_ST_BIND(o) ELF64_ST_BIND(o) #define ELF_ST_VISIBILITY(o) ELF64_ST_VISIBILITY(o) diff --git a/arch/mips/cavium-octeon/executive/cvmx-bootmem.c b/arch/mips/cavium-octeon/executive/cvmx-bootmem.c index 504ed61..b65a6c1 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-bootmem.c +++ b/arch/mips/cavium-octeon/executive/cvmx-bootmem.c @@ -668,7 +668,7 @@ int64_t cvmx_bootmem_phy_named_block_alloc(uint64_t size, uint64_t min_addr, /* * Round size up to mult of minimum alignment bytes We need * the actual size allocated to allow for blocks to be - * coallesced when they are freed. The alloc routine does the + * coalesced when they are freed. The alloc routine does the * same rounding up on all allocations. */ size = ALIGN(size, CVMX_BOOTMEM_ALIGNMENT_SIZE); diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c index 36e30d6..ff49fc0 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c @@ -186,15 +186,6 @@ int cvmx_helper_board_get_mii_address(int ipd_port) return 7 - ipd_port; else return -1; - case CVMX_BOARD_TYPE_CUST_DSR1000N: - /* - * Port 2 connects to Broadcom PHY (B5081). Other ports (0-1) - * connect to a switch (BCM53115). - */ - if (ipd_port == 2) - return 8; - else - return -1; case CVMX_BOARD_TYPE_KONTRON_S1901: if (ipd_port == CVMX_HELPER_BOARD_MGMT_IPD_PORT) return 1; @@ -289,18 +280,6 @@ cvmx_helper_link_info_t __cvmx_helper_board_link_get(int ipd_port) return result; } break; - case CVMX_BOARD_TYPE_CUST_DSR1000N: - if (ipd_port == 0 || ipd_port == 1) { - /* Ports 0 and 1 connect to a switch (BCM53115). */ - result.s.link_up = 1; - result.s.full_duplex = 1; - result.s.speed = 1000; - return result; - } else { - /* Port 2 uses a Broadcom PHY (B5081). */ - is_broadcom_phy = 1; - } - break; } phy_addr = cvmx_helper_board_get_mii_address(ipd_port); @@ -765,7 +744,6 @@ enum cvmx_helper_board_usb_clock_types __cvmx_helper_board_usb_get_clock_type(vo case CVMX_BOARD_TYPE_LANAI2_G: case CVMX_BOARD_TYPE_NIC10E_66: case CVMX_BOARD_TYPE_UBNT_E100: - case CVMX_BOARD_TYPE_CUST_DSR1000N: return USB_CLOCK_TYPE_CRYSTAL_12; case CVMX_BOARD_TYPE_NIC10E: return USB_CLOCK_TYPE_REF_12; diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 368eb49..5a9b87b 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -1260,7 +1260,7 @@ static int octeon_irq_gpio_map(struct irq_domain *d, line = (hw + gpiod->base_hwirq) >> 6; bit = (hw + gpiod->base_hwirq) & 63; - if (line > ARRAY_SIZE(octeon_irq_ciu_to_irq) || + if (line >= ARRAY_SIZE(octeon_irq_ciu_to_irq) || octeon_irq_ciu_to_irq[line][bit] != 0) return -EINVAL; @@ -1542,10 +1542,6 @@ static int __init octeon_irq_init_ciu( goto err; } - r = octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB0, 0, 56); - if (r) - goto err; - r = octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_TWSI2, 0, 59); if (r) goto err; @@ -1559,10 +1555,6 @@ static int __init octeon_irq_init_ciu( goto err; } - r = octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB1, 1, 17); - if (r) - goto err; - /* Enable the CIU lines */ set_c0_status(STATUSF_IP3 | STATUSF_IP2); if (octeon_irq_use_ip4) @@ -2077,10 +2069,6 @@ static int __init octeon_irq_init_ciu2( goto err; } - r = octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB0, 3, 44); - if (r) - goto err; - for (i = 0; i < 4; i++) { r = octeon_irq_force_ciu_mapping( ciu_domain, i + OCTEON_IRQ_PCI_INT0, 4, i); diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c index 7aeafed..b31fbc9 100644 --- a/arch/mips/cavium-octeon/octeon-platform.c +++ b/arch/mips/cavium-octeon/octeon-platform.c @@ -3,33 +3,27 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (C) 2004-2011 Cavium Networks + * Copyright (C) 2004-2016 Cavium Networks * Copyright (C) 2008 Wind River Systems */ -#include <linux/delay.h> #include <linux/init.h> -#include <linux/irq.h> -#include <linux/i2c.h> -#include <linux/usb.h> -#include <linux/dma-mapping.h> +#include <linux/delay.h> #include <linux/etherdevice.h> -#include <linux/module.h> -#include <linux/mutex.h> -#include <linux/slab.h> -#include <linux/platform_device.h> #include <linux/of_platform.h> #include <linux/of_fdt.h> #include <linux/libfdt.h> +#include <linux/usb/ehci_def.h> #include <linux/usb/ehci_pdriver.h> #include <linux/usb/ohci_pdriver.h> #include <asm/octeon/octeon.h> -#include <asm/octeon/cvmx-rnm-defs.h> -#include <asm/octeon/cvmx-helper.h> #include <asm/octeon/cvmx-helper-board.h> #include <asm/octeon/cvmx-uctlx-defs.h> +#define CVMX_UAHCX_EHCI_USBCMD (CVMX_ADD_IO_SEG(0x00016F0000000010ull)) +#define CVMX_UAHCX_OHCI_USBCMD (CVMX_ADD_IO_SEG(0x00016F0000000408ull)) + /* Octeon Random Number Generator. */ static int __init octeon_rng_device_init(void) { @@ -78,12 +72,36 @@ static DEFINE_MUTEX(octeon2_usb_clocks_mutex); static int octeon2_usb_clock_start_cnt; +static int __init octeon2_usb_reset(void) +{ + union cvmx_uctlx_clk_rst_ctl clk_rst_ctl; + u32 ucmd; + + if (!OCTEON_IS_OCTEON2()) + return 0; + + clk_rst_ctl.u64 = cvmx_read_csr(CVMX_UCTLX_CLK_RST_CTL(0)); + if (clk_rst_ctl.s.hrst) { + ucmd = cvmx_read64_uint32(CVMX_UAHCX_EHCI_USBCMD); + ucmd &= ~CMD_RUN; + cvmx_write64_uint32(CVMX_UAHCX_EHCI_USBCMD, ucmd); + mdelay(2); + ucmd |= CMD_RESET; + cvmx_write64_uint32(CVMX_UAHCX_EHCI_USBCMD, ucmd); + ucmd = cvmx_read64_uint32(CVMX_UAHCX_OHCI_USBCMD); + ucmd |= CMD_RUN; + cvmx_write64_uint32(CVMX_UAHCX_OHCI_USBCMD, ucmd); + } + + return 0; +} +arch_initcall(octeon2_usb_reset); + static void octeon2_usb_clocks_start(struct device *dev) { u64 div; union cvmx_uctlx_if_ena if_ena; union cvmx_uctlx_clk_rst_ctl clk_rst_ctl; - union cvmx_uctlx_uphy_ctl_status uphy_ctl_status; union cvmx_uctlx_uphy_portx_ctl_status port_ctl_status; int i; unsigned long io_clk_64_to_ns; @@ -131,6 +149,17 @@ static void octeon2_usb_clocks_start(struct device *dev) if_ena.s.en = 1; cvmx_write_csr(CVMX_UCTLX_IF_ENA(0), if_ena.u64); + for (i = 0; i <= 1; i++) { + port_ctl_status.u64 = + cvmx_read_csr(CVMX_UCTLX_UPHY_PORTX_CTL_STATUS(i, 0)); + /* Set txvreftune to 15 to obtain compliant 'eye' diagram. */ + port_ctl_status.s.txvreftune = 15; + port_ctl_status.s.txrisetune = 1; + port_ctl_status.s.txpreemphasistune = 1; + cvmx_write_csr(CVMX_UCTLX_UPHY_PORTX_CTL_STATUS(i, 0), + port_ctl_status.u64); + } + /* Step 3: Configure the reference clock, PHY, and HCLK */ clk_rst_ctl.u64 = cvmx_read_csr(CVMX_UCTLX_CLK_RST_CTL(0)); @@ -218,29 +247,10 @@ static void octeon2_usb_clocks_start(struct device *dev) clk_rst_ctl.s.p_por = 0; cvmx_write_csr(CVMX_UCTLX_CLK_RST_CTL(0), clk_rst_ctl.u64); - /* Step 5: Wait 1 ms for the PHY clock to start. */ - mdelay(1); + /* Step 5: Wait 3 ms for the PHY clock to start. */ + mdelay(3); - /* - * Step 6: Program the reset input from automatic test - * equipment field in the UPHY CSR - */ - uphy_ctl_status.u64 = cvmx_read_csr(CVMX_UCTLX_UPHY_CTL_STATUS(0)); - uphy_ctl_status.s.ate_reset = 1; - cvmx_write_csr(CVMX_UCTLX_UPHY_CTL_STATUS(0), uphy_ctl_status.u64); - - /* Step 7: Wait for at least 10ns. */ - ndelay(10); - - /* Step 8: Clear the ATE_RESET field in the UPHY CSR. */ - uphy_ctl_status.s.ate_reset = 0; - cvmx_write_csr(CVMX_UCTLX_UPHY_CTL_STATUS(0), uphy_ctl_status.u64); - - /* - * Step 9: Wait for at least 20ns for UPHY to output PHY clock - * signals and OHCI_CLK48 - */ - ndelay(20); + /* Steps 6..9 for ATE only, are skipped. */ /* Step 10: Configure the OHCI_CLK48 and OHCI_CLK12 clocks. */ /* 10a */ @@ -261,6 +271,20 @@ static void octeon2_usb_clocks_start(struct device *dev) clk_rst_ctl.s.p_prst = 1; cvmx_write_csr(CVMX_UCTLX_CLK_RST_CTL(0), clk_rst_ctl.u64); + /* Step 11b */ + udelay(1); + + /* Step 11c */ + clk_rst_ctl.s.p_prst = 0; + cvmx_write_csr(CVMX_UCTLX_CLK_RST_CTL(0), clk_rst_ctl.u64); + + /* Step 11d */ + mdelay(1); + + /* Step 11e */ + clk_rst_ctl.s.p_prst = 1; + cvmx_write_csr(CVMX_UCTLX_CLK_RST_CTL(0), clk_rst_ctl.u64); + /* Step 12: Wait 1 uS. */ udelay(1); @@ -269,21 +293,9 @@ static void octeon2_usb_clocks_start(struct device *dev) cvmx_write_csr(CVMX_UCTLX_CLK_RST_CTL(0), clk_rst_ctl.u64); end_clock: - /* Now we can set some other registers. */ - - for (i = 0; i <= 1; i++) { - port_ctl_status.u64 = - cvmx_read_csr(CVMX_UCTLX_UPHY_PORTX_CTL_STATUS(i, 0)); - /* Set txvreftune to 15 to obtain compliant 'eye' diagram. */ - port_ctl_status.s.txvreftune = 15; - port_ctl_status.s.txrisetune = 1; - port_ctl_status.s.txpreemphasistune = 1; - cvmx_write_csr(CVMX_UCTLX_UPHY_PORTX_CTL_STATUS(i, 0), - port_ctl_status.u64); - } - /* Set uSOF cycle period to 60,000 bits. */ cvmx_write_csr(CVMX_UCTLX_EHCI_FLA(0), 0x20ull); + exit: mutex_unlock(&octeon2_usb_clocks_mutex); } @@ -311,7 +323,11 @@ static struct usb_ehci_pdata octeon_ehci_pdata = { #ifdef __BIG_ENDIAN .big_endian_mmio = 1, #endif - .dma_mask_64 = 1, + /* + * We can DMA from anywhere. But the descriptors must be in + * the lower 4GB. + */ + .dma_mask_64 = 0, .power_on = octeon_ehci_power_on, .power_off = octeon_ehci_power_off, }; @@ -689,6 +705,10 @@ int __init octeon_prune_device_tree(void) if (fdt_check_header(initial_boot_params)) panic("Corrupt Device Tree."); + WARN(octeon_bootinfo->board_type == CVMX_BOARD_TYPE_CUST_DSR1000N, + "Built-in DTB booting is deprecated on %s. Please switch to use appended DTB.", + cvmx_board_type_to_string(octeon_bootinfo->board_type)); + aliases = fdt_path_offset(initial_boot_params, "/aliases"); if (aliases < 0) { pr_err("Error: No /aliases node in device tree."); @@ -1032,13 +1052,6 @@ end_led: } } - if (octeon_bootinfo->board_type != CVMX_BOARD_TYPE_CUST_DSR1000N) { - int dsr1000n_leds = fdt_path_offset(initial_boot_params, - "/dsr1000n-leds"); - if (dsr1000n_leds >= 0) - fdt_nop_node(initial_boot_params, dsr1000n_leds); - } - return 0; } diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index 64f852b..cb16fcc 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -40,9 +40,27 @@ #include <asm/octeon/octeon.h> #include <asm/octeon/pci-octeon.h> -#include <asm/octeon/cvmx-mio-defs.h> #include <asm/octeon/cvmx-rst-defs.h> +/* + * TRUE for devices having registers with little-endian byte + * order, FALSE for registers with native-endian byte order. + * PCI mandates little-endian, USB and SATA are configuraable, + * but we chose little-endian for these. + */ +const bool octeon_should_swizzle_table[256] = { + [0x00] = true, /* bootbus/CF */ + [0x1b] = true, /* PCI mmio window */ + [0x1c] = true, /* PCI mmio window */ + [0x1d] = true, /* PCI mmio window */ + [0x1e] = true, /* PCI mmio window */ + [0x68] = true, /* OCTEON III USB */ + [0x69] = true, /* OCTEON III USB */ + [0x6c] = true, /* OCTEON III SATA */ + [0x6f] = true, /* OCTEON II USB */ +}; +EXPORT_SYMBOL(octeon_should_swizzle_table); + #ifdef CONFIG_PCI extern void pci_console_init(const char *arg); #endif diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 33aab89..4d457d60 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -271,6 +271,7 @@ static int octeon_cpu_disable(void) return -ENOTSUPP; set_cpu_online(cpu, false); + calculate_cpu_foreign_map(); cpumask_clear_cpu(cpu, &cpu_callin_map); octeon_fixup_irqs(); diff --git a/arch/mips/cobalt/setup.c b/arch/mips/cobalt/setup.c index 9a8c2fe..c136a18 100644 --- a/arch/mips/cobalt/setup.c +++ b/arch/mips/cobalt/setup.c @@ -42,8 +42,8 @@ const char *get_system_type(void) /* * Cobalt doesn't have PS/2 keyboard/mouse interfaces, - * keyboard conntroller is never used. - * Also PCI-ISA bridge DMA contoroller is never used. + * keyboard controller is never used. + * Also PCI-ISA bridge DMA controller is never used. */ static struct resource cobalt_reserved_resources[] = { { /* dma1 */ diff --git a/arch/mips/configs/ath25_defconfig b/arch/mips/configs/ath25_defconfig new file mode 100644 index 0000000..2c82995 --- /dev/null +++ b/arch/mips/configs/ath25_defconfig @@ -0,0 +1,119 @@ +CONFIG_ATH25=y +# CONFIG_COMPACTION is not set +CONFIG_HZ_100=y +# CONFIG_SECCOMP is not set +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_SYSVIPC=y +# CONFIG_CROSS_MEMORY_ATTACH is not set +# CONFIG_FHANDLE is not set +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BLK_DEV_INITRD=y +# CONFIG_RD_GZIP is not set +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +# CONFIG_AIO is not set +CONFIG_EMBEDDED=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_CFQ is not set +# CONFIG_SUSPEND is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_IPV6 is not set +CONFIG_CFG80211=m +CONFIG_MAC80211=m +CONFIG_MAC80211_DEBUGFS=y +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +# CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_MTD=y +CONFIG_MTD_REDBOOT_PARTS=y +CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-2 +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_ADV_OPTIONS=y +CONFIG_MTD_CFI_GEOMETRY=y +# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_4 is not set +# CONFIG_MTD_CFI_I2 is not set +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_COMPLEX_MAPPINGS=y +CONFIG_MTD_PHYSMAP=y +CONFIG_NETDEVICES=y +# CONFIG_ETHERNET is not set +# CONFIG_WLAN_VENDOR_ADMTEK is not set +CONFIG_ATH5K=m +# CONFIG_WLAN_VENDOR_ATMEL is not set +# CONFIG_WLAN_VENDOR_BROADCOM is not set +# CONFIG_WLAN_VENDOR_CISCO is not set +# CONFIG_WLAN_VENDOR_INTEL is not set +# CONFIG_WLAN_VENDOR_INTERSIL is not set +# CONFIG_WLAN_VENDOR_MARVELL is not set +# CONFIG_WLAN_VENDOR_MEDIATEK is not set +# CONFIG_WLAN_VENDOR_RALINK is not set +# CONFIG_WLAN_VENDOR_REALTEK is not set +# CONFIG_WLAN_VENDOR_RSI is not set +# CONFIG_WLAN_VENDOR_ST is not set +# CONFIG_WLAN_VENDOR_TI is not set +# CONFIG_WLAN_VENDOR_ZYDAS is not set +CONFIG_INPUT=m +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +# CONFIG_SERIAL_8250_PCI is not set +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +# CONFIG_VGA_ARB is not set +CONFIG_USB=m +CONFIG_USB_EHCI_HCD=m +CONFIG_LEDS_CLASS=y +# CONFIG_IOMMU_SUPPORT is not set +# CONFIG_DNOTIFY is not set +# CONFIG_PROC_PAGE_MONITOR is not set +CONFIG_TMPFS=y +CONFIG_TMPFS_XATTR=y +CONFIG_JFFS2_FS=y +CONFIG_JFFS2_SUMMARY=y +CONFIG_JFFS2_FS_XATTR=y +# CONFIG_JFFS2_FS_POSIX_ACL is not set +# CONFIG_JFFS2_FS_SECURITY is not set +CONFIG_JFFS2_COMPRESSION_OPTIONS=y +# CONFIG_JFFS2_ZLIB is not set +CONFIG_SQUASHFS=y +CONFIG_SQUASHFS_FILE_DIRECT=y +CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU=y +# CONFIG_SQUASHFS_ZLIB is not set +CONFIG_SQUASHFS_XZ=y +CONFIG_PRINTK_TIME=y +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_STRIP_ASM_SYMS=y +CONFIG_DEBUG_FS=y +# CONFIG_SCHED_DEBUG is not set +# CONFIG_FTRACE is not set +# CONFIG_XZ_DEC_X86 is not set +# CONFIG_XZ_DEC_POWERPC is not set +# CONFIG_XZ_DEC_IA64 is not set +# CONFIG_XZ_DEC_ARM is not set +# CONFIG_XZ_DEC_ARMTHUMB is not set +# CONFIG_XZ_DEC_SPARC is not set diff --git a/arch/mips/configs/cavium_octeon_defconfig b/arch/mips/configs/cavium_octeon_defconfig index dcac308..d470d08 100644 --- a/arch/mips/configs/cavium_octeon_defconfig +++ b/arch/mips/configs/cavium_octeon_defconfig @@ -59,6 +59,8 @@ CONFIG_EEPROM_AT25=y CONFIG_BLK_DEV_SD=y CONFIG_ATA=y CONFIG_SATA_AHCI=y +CONFIG_SATA_AHCI_PLATFORM=y +CONFIG_AHCI_OCTEON=y CONFIG_PATA_OCTEON_CF=y CONFIG_SATA_SIL=y CONFIG_NETDEVICES=y diff --git a/arch/mips/include/asm/bootinfo.h b/arch/mips/include/asm/bootinfo.h index 9f67033..ee9f5f2 100644 --- a/arch/mips/include/asm/bootinfo.h +++ b/arch/mips/include/asm/bootinfo.h @@ -127,6 +127,10 @@ extern char arcs_cmdline[COMMAND_LINE_SIZE]; */ extern unsigned long fw_arg0, fw_arg1, fw_arg2, fw_arg3; +#ifdef CONFIG_USE_OF +extern unsigned long fw_passed_dtb; +#endif + /* * Platform memory detection hook called by setup_arch */ diff --git a/arch/mips/include/asm/dsemul.h b/arch/mips/include/asm/dsemul.h new file mode 100644 index 0000000..a6e0678 --- /dev/null +++ b/arch/mips/include/asm/dsemul.h @@ -0,0 +1,92 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * 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. + */ + +#ifndef __MIPS_ASM_DSEMUL_H__ +#define __MIPS_ASM_DSEMUL_H__ + +#include <asm/break.h> +#include <asm/inst.h> + +/* Break instruction with special math emu break code set */ +#define BREAK_MATH(micromips) (((micromips) ? 0x7 : 0xd) | (BRK_MEMU << 16)) + +/* When used as a frame index, indicates the lack of a frame */ +#define BD_EMUFRAME_NONE ((int)BIT(31)) + +struct mm_struct; +struct pt_regs; +struct task_struct; + +/** + * mips_dsemul() - 'Emulate' an instruction from a branch delay slot + * @regs: User thread register context. + * @ir: The instruction to be 'emulated'. + * @branch_pc: The PC of the branch instruction. + * @cont_pc: The PC to continue at following 'emulation'. + * + * Emulate or execute an arbitrary MIPS instruction within the context of + * the current user thread. This is used primarily to handle instructions + * in the delay slots of emulated branch instructions, for example FP + * branch instructions on systems without an FPU. + * + * Return: Zero on success, negative if ir is a NOP, signal number on failure. + */ +extern int mips_dsemul(struct pt_regs *regs, mips_instruction ir, + unsigned long branch_pc, unsigned long cont_pc); + +/** + * do_dsemulret() - Return from a delay slot 'emulation' frame + * @xcp: User thread register context. + * + * Call in response to the BRK_MEMU break instruction used to return to + * the kernel from branch delay slot 'emulation' frames following a call + * to mips_dsemul(). Restores the user thread PC to the value that was + * passed as the cpc parameter to mips_dsemul(). + * + * Return: True if an emulation frame was returned from, else false. + */ +extern bool do_dsemulret(struct pt_regs *xcp); + +/** + * dsemul_thread_cleanup() - Cleanup thread 'emulation' frame + * @tsk: The task structure associated with the thread + * + * If the thread @tsk has a branch delay slot 'emulation' frame + * allocated to it then free that frame. + * + * Return: True if a frame was freed, else false. + */ +extern bool dsemul_thread_cleanup(struct task_struct *tsk); + +/** + * dsemul_thread_rollback() - Rollback from an 'emulation' frame + * @regs: User thread register context. + * + * If the current thread, whose register context is represented by @regs, + * is executing within a delay slot 'emulation' frame then exit that + * frame. The PC will be rolled back to the branch if the instruction + * that was being 'emulated' has not yet executed, or advanced to the + * continuation PC if it has. + * + * Return: True if a frame was exited, else false. + */ +extern bool dsemul_thread_rollback(struct pt_regs *regs); + +/** + * dsemul_mm_cleanup() - Cleanup per-mm delay slot 'emulation' state + * @mm: The struct mm_struct to cleanup state for. + * + * Cleanup state for the given @mm, ensuring that any memory allocated + * for delay slot 'emulation' book-keeping is freed. This is to be called + * before @mm is freed in order to avoid memory leaks. + */ +extern void dsemul_mm_cleanup(struct mm_struct *mm); + +#endif /* __MIPS_ASM_DSEMUL_H__ */ diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h index f5f4571..2b3dc29 100644 --- a/arch/mips/include/asm/elf.h +++ b/arch/mips/include/asm/elf.h @@ -458,6 +458,7 @@ extern const char *__elf_platform; #define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) #endif +/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ #define ARCH_DLINFO \ do { \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ @@ -498,4 +499,7 @@ extern int arch_check_elf(void *ehdr, bool has_interpreter, void *interp_ehdr, extern void mips_set_personality_nan(struct arch_elf_state *state); extern void mips_set_personality_fp(struct arch_elf_state *state); +#define elf_read_implies_exec(ex, stk) mips_elf_read_implies_exec(&(ex), stk) +extern int mips_elf_read_implies_exec(void *elf_ex, int exstack); + #endif /* _ASM_ELF_H */ diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h index 3225c3c..355dc25 100644 --- a/arch/mips/include/asm/fpu_emulator.h +++ b/arch/mips/include/asm/fpu_emulator.h @@ -24,7 +24,7 @@ #define _ASM_FPU_EMULATOR_H #include <linux/sched.h> -#include <asm/break.h> +#include <asm/dsemul.h> #include <asm/thread_info.h> #include <asm/inst.h> #include <asm/local.h> @@ -60,27 +60,16 @@ do { \ #define MIPS_FPU_EMU_INC_STATS(M) do { } while (0) #endif /* CONFIG_DEBUG_FS */ -extern int mips_dsemul(struct pt_regs *regs, mips_instruction ir, - unsigned long cpc); -extern int do_dsemulret(struct pt_regs *xcp); extern int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, int has_fpu, void *__user *fault_addr); int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31); +int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, + unsigned long *contpc); int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, unsigned long *contpc); -/* - * Instruction inserted following the badinst to further tag the sequence - */ -#define BD_COOKIE 0x0000bd36 /* tne $0, $0 with baggage */ - -/* - * Break instruction with special math emu break code set - */ -#define BREAK_MATH(micromips) (((micromips) ? 0x7 : 0xd) | (BRK_MEMU << 16)) - #define SIGNALLING_NAN 0x7ff800007ff80000LL static inline void fpu_emulator_init_fpu(void) diff --git a/arch/mips/include/asm/mach-cavium-octeon/irq.h b/arch/mips/include/asm/mach-cavium-octeon/irq.h index cceae32..64b86b9 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/irq.h +++ b/arch/mips/include/asm/mach-cavium-octeon/irq.h @@ -42,8 +42,6 @@ enum octeon_irq { OCTEON_IRQ_TIMER1, OCTEON_IRQ_TIMER2, OCTEON_IRQ_TIMER3, - OCTEON_IRQ_USB0, - OCTEON_IRQ_USB1, #ifndef CONFIG_PCI_MSI OCTEON_IRQ_LAST = 127 #endif diff --git a/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h b/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h index 374eefa..0cf5ac1 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h +++ b/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h @@ -12,6 +12,14 @@ #ifdef __BIG_ENDIAN +static inline bool __should_swizzle_bits(volatile void *a) +{ + extern const bool octeon_should_swizzle_table[]; + + unsigned long did = ((unsigned long)a >> 40) & 0xff; + return octeon_should_swizzle_table[did]; +} + # define __swizzle_addr_b(port) (port) # define __swizzle_addr_w(port) (port) # define __swizzle_addr_l(port) (port) @@ -19,6 +27,8 @@ #else /* __LITTLE_ENDIAN */ +#define __should_swizzle_bits(a) false + static inline bool __should_swizzle_addr(unsigned long p) { /* boot bus? */ @@ -35,40 +45,14 @@ static inline bool __should_swizzle_addr(unsigned long p) #endif /* __BIG_ENDIAN */ -/* - * Sane hardware offers swapping of PCI/ISA I/O space accesses in hardware; - * less sane hardware forces software to fiddle with this... - * - * Regardless, if the host bus endianness mismatches that of PCI/ISA, then - * you can't have the numerical value of data and byte addresses within - * multibyte quantities both preserved at the same time. Hence two - * variations of functions: non-prefixed ones that preserve the value - * and prefixed ones that preserve byte addresses. The latters are - * typically used for moving raw data between a peripheral and memory (cf. - * string I/O functions), hence the "__mem_" prefix. - */ -#if defined(CONFIG_SWAP_IO_SPACE) # define ioswabb(a, x) (x) # define __mem_ioswabb(a, x) (x) -# define ioswabw(a, x) le16_to_cpu(x) +# define ioswabw(a, x) (__should_swizzle_bits(a) ? le16_to_cpu(x) : x) # define __mem_ioswabw(a, x) (x) -# define ioswabl(a, x) le32_to_cpu(x) +# define ioswabl(a, x) (__should_swizzle_bits(a) ? le32_to_cpu(x) : x) # define __mem_ioswabl(a, x) (x) -# define ioswabq(a, x) le64_to_cpu(x) +# define ioswabq(a, x) (__should_swizzle_bits(a) ? le64_to_cpu(x) : x) # define __mem_ioswabq(a, x) (x) -#else - -# define ioswabb(a, x) (x) -# define __mem_ioswabb(a, x) (x) -# define ioswabw(a, x) (x) -# define __mem_ioswabw(a, x) cpu_to_le16(x) -# define ioswabl(a, x) (x) -# define __mem_ioswabl(a, x) cpu_to_le32(x) -# define ioswabq(a, x) (x) -# define __mem_ioswabq(a, x) cpu_to_le32(x) - -#endif - #endif /* __ASM_MACH_GENERIC_MANGLE_PORT_H */ diff --git a/arch/mips/include/asm/mmu.h b/arch/mips/include/asm/mmu.h index 1afa1f9..f6ba08d 100644 --- a/arch/mips/include/asm/mmu.h +++ b/arch/mips/include/asm/mmu.h @@ -2,11 +2,20 @@ #define __ASM_MMU_H #include <linux/atomic.h> +#include <linux/spinlock.h> +#include <linux/wait.h> typedef struct { unsigned long asid[NR_CPUS]; void *vdso; atomic_t fp_mode_switching; + + /* lock to be held whilst modifying fp_bd_emupage_allocmap */ + spinlock_t bd_emupage_lock; + /* bitmap tracking allocation of fp_bd_emupage */ + unsigned long *bd_emupage_allocmap; + /* wait queue for threads requiring an emuframe */ + wait_queue_head_t bd_emupage_queue; } mm_context_t; #endif /* __ASM_MMU_H */ diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h index fc57e13..ddd57ad 100644 --- a/arch/mips/include/asm/mmu_context.h +++ b/arch/mips/include/asm/mmu_context.h @@ -16,6 +16,7 @@ #include <linux/smp.h> #include <linux/slab.h> #include <asm/cacheflush.h> +#include <asm/dsemul.h> #include <asm/hazards.h> #include <asm/tlbflush.h> #include <asm-generic/mm_hooks.h> @@ -128,6 +129,10 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm) atomic_set(&mm->context.fp_mode_switching, 0); + mm->context.bd_emupage_allocmap = NULL; + spin_lock_init(&mm->context.bd_emupage_lock); + init_waitqueue_head(&mm->context.bd_emupage_queue); + return 0; } @@ -162,6 +167,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ static inline void destroy_context(struct mm_struct *mm) { + dsemul_mm_cleanup(mm); } #define deactivate_mm(tsk, mm) do { } while (0) diff --git a/arch/mips/include/asm/msa.h b/arch/mips/include/asm/msa.h index ddf496c..8967b47 100644 --- a/arch/mips/include/asm/msa.h +++ b/arch/mips/include/asm/msa.h @@ -168,6 +168,7 @@ static inline unsigned int read_msa_##name(void) \ unsigned int reg; \ __asm__ __volatile__( \ " .set push\n" \ + " .set fp=64\n" \ " .set msa\n" \ " cfcmsa %0, $" #cs "\n" \ " .set pop\n" \ @@ -179,6 +180,7 @@ static inline void write_msa_##name(unsigned int val) \ { \ __asm__ __volatile__( \ " .set push\n" \ + " .set fp=64\n" \ " .set msa\n" \ " ctcmsa $" #cs ", %0\n" \ " .set pop\n" \ diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 21ed715..ea0cd97 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -162,16 +162,34 @@ typedef struct { unsigned long pgprot; } pgprot_t; /* * __pa()/__va() should be used only during mem init. */ -#ifdef CONFIG_64BIT -#define __pa(x) \ -({ \ - unsigned long __x = (unsigned long)(x); \ - __x < CKSEG0 ? XPHYSADDR(__x) : CPHYSADDR(__x); \ -}) -#else -#define __pa(x) \ - ((unsigned long)(x) - PAGE_OFFSET + PHYS_OFFSET) -#endif +static inline unsigned long ___pa(unsigned long x) +{ + if (config_enabled(CONFIG_64BIT)) { + /* + * For MIPS64 the virtual address may either be in one of + * the compatibility segements ckseg0 or ckseg1, or it may + * be in xkphys. + */ + return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x); + } + + if (!config_enabled(CONFIG_EVA)) { + /* + * We're using the standard MIPS32 legacy memory map, ie. + * the address x is going to be in kseg0 or kseg1. We can + * handle either case by masking out the desired bits using + * CPHYSADDR. + */ + return CPHYSADDR(x); + } + + /* + * EVA is in use so the memory map could be anything, making it not + * safe to just mask out bits. + */ + return x - PAGE_OFFSET + PHYS_OFFSET; +} +#define __pa(x) ___pa((unsigned long)(x)) #define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET - PHYS_OFFSET)) #include <asm/io.h> @@ -229,8 +247,10 @@ extern int __virt_addr_valid(const volatile void *kaddr); #define virt_addr_valid(kaddr) \ __virt_addr_valid((const volatile void *) (kaddr)) -#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_DATA_DEFAULT_FLAGS \ + (VM_READ | VM_WRITE | \ + ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define UNCAC_ADDR(addr) ((addr) - PAGE_OFFSET + UNCAC_BASE) #define CAC_ADDR(addr) ((addr) - UNCAC_BASE + PAGE_OFFSET) diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 7e78b62..0d36c87 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -11,12 +11,14 @@ #ifndef _ASM_PROCESSOR_H #define _ASM_PROCESSOR_H +#include <linux/atomic.h> #include <linux/cpumask.h> #include <linux/threads.h> #include <asm/cachectl.h> #include <asm/cpu.h> #include <asm/cpu-info.h> +#include <asm/dsemul.h> #include <asm/mipsregs.h> #include <asm/prefetch.h> @@ -78,7 +80,11 @@ extern unsigned int vced_count, vcei_count; #endif -#define STACK_TOP (TASK_SIZE & PAGE_MASK) +/* + * One page above the stack is used for branch delay slot "emulation". + * See dsemul.c for details. + */ +#define STACK_TOP ((TASK_SIZE & PAGE_MASK) - PAGE_SIZE) /* * This decides where the kernel will search for a free chunk of vm @@ -256,6 +262,12 @@ struct thread_struct { /* Saved fpu/fpu emulator stuff. */ struct mips_fpu_struct fpu FPU_ALIGN; + /* Assigned branch delay slot 'emulation' frame */ + atomic_t bd_emu_frame; + /* PC of the branch from a branch delay slot 'emulation' */ + unsigned long bd_emu_branch_pc; + /* PC to continue from following a branch delay slot 'emulation' */ + unsigned long bd_emu_cont_pc; #ifdef CONFIG_MIPS_MT_FPAFF /* Emulated instruction count */ unsigned long emulated_fp; @@ -323,6 +335,10 @@ struct thread_struct { * FPU affinity state (null if not FPAFF) \ */ \ FPAFF_INIT \ + /* Delay slot emulation */ \ + .bd_emu_frame = ATOMIC_INIT(BD_EMUFRAME_NONE), \ + .bd_emu_branch_pc = 0, \ + .bd_emu_cont_pc = 0, \ /* \ * Saved DSP stuff \ */ \ diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h index 38902bf..667ca3c 100644 --- a/arch/mips/include/asm/r4kcache.h +++ b/arch/mips/include/asm/r4kcache.h @@ -210,7 +210,11 @@ static inline void protected_writeback_dcache_line(unsigned long addr) static inline void protected_writeback_scache_line(unsigned long addr) { +#ifdef CONFIG_EVA + protected_cachee_op(Hit_Writeback_Inv_SD, addr); +#else protected_cache_op(Hit_Writeback_Inv_SD, addr); +#endif } /* diff --git a/arch/mips/include/asm/signal.h b/arch/mips/include/asm/signal.h index 82eae15..23d6b80 100644 --- a/arch/mips/include/asm/signal.h +++ b/arch/mips/include/asm/signal.h @@ -11,7 +11,7 @@ #include <uapi/asm/signal.h> -#ifdef CONFIG_MIPS32_COMPAT +#ifdef CONFIG_MIPS32_O32 extern struct mips_abi mips_abi_32; #define sig_uses_siginfo(ka, abi) \ diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 03722d4..8bc6c70 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -23,7 +23,7 @@ extern int smp_num_siblings; extern cpumask_t cpu_sibling_map[]; extern cpumask_t cpu_core_map[]; -extern cpumask_t cpu_foreign_map; +extern cpumask_t cpu_foreign_map[]; #define raw_smp_processor_id() (current_thread_info()->cpu) @@ -53,6 +53,8 @@ extern cpumask_t cpu_coherent_mask; extern void asmlinkage smp_bootstrap(void); +extern void calculate_cpu_foreign_map(void); + /* * this function sends a 'reschedule' IPI to another CPU. * it goes straight through and wastes no time serializing diff --git a/arch/mips/include/uapi/asm/auxvec.h b/arch/mips/include/uapi/asm/auxvec.h index c9c7195..45ba259 100644 --- a/arch/mips/include/uapi/asm/auxvec.h +++ b/arch/mips/include/uapi/asm/auxvec.h @@ -14,4 +14,6 @@ /* Location of VDSO image. */ #define AT_SYSINFO_EHDR 33 +#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */ + #endif /* __ASM_AUXVEC_H */ diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index e6053d0..4a603a3 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -71,7 +71,7 @@ obj-$(CONFIG_32BIT) += scall32-o32.o obj-$(CONFIG_64BIT) += scall64-64.o obj-$(CONFIG_MIPS32_COMPAT) += linux32.o ptrace32.o signal32.o obj-$(CONFIG_MIPS32_N32) += binfmt_elfn32.o scall64-n32.o signal_n32.o -obj-$(CONFIG_MIPS32_O32) += binfmt_elfo32.o scall64-o32.o +obj-$(CONFIG_MIPS32_O32) += binfmt_elfo32.o scall64-o32.o signal_o32.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_PROC_FS) += proc.o diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index e4c21bb..804d2a2 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -276,12 +276,7 @@ int r4k_clockevent_init(void) CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_PERCPU; - clockevent_set_clock(cd, mips_hpt_frequency); - - /* Calculate the min / max delta */ - cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd); min_delta = calculate_min_delta(); - cd->min_delta_ns = clockevent_delta2ns(min_delta, cd); cd->rating = 300; cd->irq = irq; @@ -289,7 +284,7 @@ int r4k_clockevent_init(void) cd->set_next_event = mips_next_event; cd->event_handler = mips_event_handler; - clockevents_register_device(cd); + clockevents_config_and_register(cd, mips_hpt_frequency, min_delta, 0x7fffffff); if (cp0_timer_irq_installed) return 0; diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c index 1f91056..d76275d 100644 --- a/arch/mips/kernel/csrc-r4k.c +++ b/arch/mips/kernel/csrc-r4k.c @@ -23,7 +23,7 @@ static struct clocksource clocksource_mips = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static u64 notrace r4k_read_sched_clock(void) +static u64 __maybe_unused notrace r4k_read_sched_clock(void) { return read_c0_count(); } @@ -82,7 +82,9 @@ int __init init_r4k_clocksource(void) clocksource_register_hz(&clocksource_mips, mips_hpt_frequency); +#ifndef CONFIG_CPU_FREQ sched_clock_register(r4k_read_sched_clock, 32, mips_hpt_frequency); +#endif return 0; } diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index e6eb7f1..6430bff 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -8,9 +8,12 @@ * option) any later version. */ +#include <linux/binfmts.h> #include <linux/elf.h> +#include <linux/export.h> #include <linux/sched.h> +#include <asm/cpu-features.h> #include <asm/cpu-info.h> /* Whether to accept legacy-NaN and 2008-NaN user binaries. */ @@ -326,3 +329,19 @@ void mips_set_personality_nan(struct arch_elf_state *state) BUG(); } } + +int mips_elf_read_implies_exec(void *elf_ex, int exstack) +{ + if (exstack != EXSTACK_DISABLE_X) { + /* The binary doesn't request a non-executable stack */ + return 1; + } + + if (!cpu_has_rixi) { + /* The CPU doesn't support non-executable memory */ + return 1; + } + + return 0; +} +EXPORT_SYMBOL(mips_elf_read_implies_exec); diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S index 56e8fed..cf05220 100644 --- a/arch/mips/kernel/head.S +++ b/arch/mips/kernel/head.S @@ -93,21 +93,24 @@ NESTED(kernel_entry, 16, sp) # kernel entry point jr t0 0: +#ifdef CONFIG_USE_OF #ifdef CONFIG_MIPS_RAW_APPENDED_DTB - PTR_LA t0, __appended_dtb + PTR_LA t2, __appended_dtb #ifdef CONFIG_CPU_BIG_ENDIAN li t1, 0xd00dfeed #else li t1, 0xedfe0dd0 #endif - lw t2, (t0) - bne t1, t2, not_found - nop + lw t0, (t2) + beq t0, t1, dtb_found +#endif + li t1, -2 + beq a0, t1, dtb_found + move t2, a1 - move a1, t0 - PTR_LI a0, -2 -not_found: + li t2, 0 +dtb_found: #endif PTR_LA t0, __bss_start # clear .bss LONG_S zero, (t0) @@ -122,6 +125,10 @@ not_found: LONG_S a2, fw_arg2 LONG_S a3, fw_arg3 +#ifdef CONFIG_USE_OF + LONG_S t2, fw_passed_dtb +#endif + MTC0 zero, CP0_CONTEXT # clear context register PTR_LA $28, init_thread_union /* Set the SP after an empty pt_regs. */ diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c index 43fbadc..c3372ca 100644 --- a/arch/mips/kernel/mips-r2-to-r6-emul.c +++ b/arch/mips/kernel/mips-r2-to-r6-emul.c @@ -283,7 +283,7 @@ static int jr_func(struct pt_regs *regs, u32 ir) err = mipsr6_emul(regs, nir); if (err > 0) { regs->cp0_epc = nepc; - err = mips_dsemul(regs, nir, cepc); + err = mips_dsemul(regs, nir, epc, cepc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -1033,7 +1033,7 @@ repeat: if (nir) { err = mipsr6_emul(regs, nir); if (err > 0) { - err = mips_dsemul(regs, nir, cpc); + err = mips_dsemul(regs, nir, epc, cpc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -1082,7 +1082,7 @@ repeat: if (nir) { err = mipsr6_emul(regs, nir); if (err > 0) { - err = mips_dsemul(regs, nir, cpc); + err = mips_dsemul(regs, nir, epc, cpc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -1149,7 +1149,7 @@ repeat: if (nir) { err = mipsr6_emul(regs, nir); if (err > 0) { - err = mips_dsemul(regs, nir, cpc); + err = mips_dsemul(regs, nir, epc, cpc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 813ed78..7429ad0 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -30,6 +30,7 @@ #include <asm/asm.h> #include <asm/bootinfo.h> #include <asm/cpu.h> +#include <asm/dsemul.h> #include <asm/dsp.h> #include <asm/fpu.h> #include <asm/msa.h> @@ -68,11 +69,22 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) lose_fpu(0); clear_thread_flag(TIF_MSA_CTX_LIVE); clear_used_math(); + atomic_set(¤t->thread.bd_emu_frame, BD_EMUFRAME_NONE); init_dsp(); regs->cp0_epc = pc; regs->regs[29] = sp; } +void exit_thread(struct task_struct *tsk) +{ + /* + * User threads may have allocated a delay slot emulation frame. + * If so, clean up that allocation. + */ + if (!(current->flags & PF_KTHREAD)) + dsemul_thread_cleanup(tsk); +} + int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { /* @@ -159,6 +171,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, clear_tsk_thread_flag(p, TIF_FPUBOUND); #endif /* CONFIG_MIPS_MT_FPAFF */ + atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE); + if (clone_flags & CLONE_SETTLS) ti->tp_value = regs->regs[7]; diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 9c0b387..51d3988 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -348,7 +348,7 @@ EXPORT(sysn32_call_table) PTR sys_ni_syscall /* available, was setaltroot */ PTR sys_add_key PTR sys_request_key - PTR sys_keyctl /* 6245 */ + PTR compat_sys_keyctl /* 6245 */ PTR sys_set_thread_area PTR sys_inotify_init PTR sys_inotify_add_watch diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index f4f28b1..6efa713 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -504,7 +504,7 @@ EXPORT(sys32_call_table) PTR sys_ni_syscall /* available, was setaltroot */ PTR sys_add_key /* 4280 */ PTR sys_request_key - PTR sys_keyctl + PTR compat_sys_keyctl PTR sys_set_thread_area PTR sys_inotify_init PTR sys_inotify_add_watch /* 4285 */ diff --git a/arch/mips/kernel/segment.c b/arch/mips/kernel/segment.c index 87bc74a..2703f21 100644 --- a/arch/mips/kernel/segment.c +++ b/arch/mips/kernel/segment.c @@ -26,17 +26,20 @@ static void build_segment_config(char *str, unsigned int cfg) /* * Access modes MK, MSK and MUSK are mapped segments. Therefore - * there is no direct physical address mapping. + * there is no direct physical address mapping unless it becomes + * unmapped uncached at error level due to EU. */ - if ((am == 0) || (am > 3)) { + if ((am == 0) || (am > 3) || (cfg & MIPS_SEGCFG_EU)) str += sprintf(str, " %03lx", ((cfg & MIPS_SEGCFG_PA) >> MIPS_SEGCFG_PA_SHIFT)); + else + str += sprintf(str, " UND"); + + if ((am == 0) || (am > 3)) str += sprintf(str, " %01ld", ((cfg & MIPS_SEGCFG_C) >> MIPS_SEGCFG_C_SHIFT)); - } else { - str += sprintf(str, " UND"); + else str += sprintf(str, " U"); - } /* Exception configuration. */ str += sprintf(str, " %01ld\n", diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index ef408a0..36cf8d6 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -875,6 +875,10 @@ void __init setup_arch(char **cmdline_p) unsigned long kernelsp[NR_CPUS]; unsigned long fw_arg0, fw_arg1, fw_arg2, fw_arg3; +#ifdef CONFIG_USE_OF +unsigned long fw_passed_dtb; +#endif + #ifdef CONFIG_DEBUG_FS struct dentry *mips_debugfs_dir; static int __init debugfs_mips(void) diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index 1975cd2..9e22446 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -772,6 +772,14 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) struct mips_abi *abi = current->thread.abi; void *vdso = current->mm->context.vdso; + /* + * If we were emulating a delay slot instruction, exit that frame such + * that addresses in the sigframe are as expected for userland and we + * don't have a problem if we reuse the thread's frame for an + * instruction within the signal handler. + */ + dsemul_thread_rollback(regs); + if (regs->regs[0]) { switch(regs->regs[2]) { case ERESTART_RESTARTBLOCK: diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c index 78c8349..97b7c51 100644 --- a/arch/mips/kernel/signal32.c +++ b/arch/mips/kernel/signal32.c @@ -6,129 +6,26 @@ * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1994 - 2000, 2006 Ralf Baechle * Copyright (C) 1999, 2000 Silicon Graphics, Inc. + * Copyright (C) 2016, Imagination Technologies Ltd. */ -#include <linux/cache.h> -#include <linux/compat.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/smp.h> +#include <linux/compiler.h> +#include <linux/errno.h> #include <linux/kernel.h> #include <linux/signal.h> #include <linux/syscalls.h> -#include <linux/errno.h> -#include <linux/wait.h> -#include <linux/ptrace.h> -#include <linux/suspend.h> -#include <linux/compiler.h> -#include <linux/uaccess.h> -#include <asm/abi.h> -#include <asm/asm.h> +#include <asm/compat.h> #include <asm/compat-signal.h> -#include <linux/bitops.h> -#include <asm/cacheflush.h> -#include <asm/sim.h> -#include <asm/ucontext.h> -#include <asm/fpu.h> -#include <asm/war.h> -#include <asm/dsp.h> +#include <asm/uaccess.h> +#include <asm/unistd.h> #include "signal-common.h" -/* - * Including <asm/unistd.h> would give use the 64-bit syscall numbers ... - */ -#define __NR_O32_restart_syscall 4253 - /* 32-bit compatibility types */ typedef unsigned int __sighandler32_t; typedef void (*vfptr_t)(void); -struct ucontext32 { - u32 uc_flags; - s32 uc_link; - compat_stack_t uc_stack; - struct sigcontext32 uc_mcontext; - compat_sigset_t uc_sigmask; /* mask last for extensibility */ -}; - -struct sigframe32 { - u32 sf_ass[4]; /* argument save space for o32 */ - u32 sf_pad[2]; /* Was: signal trampoline */ - struct sigcontext32 sf_sc; - compat_sigset_t sf_mask; -}; - -struct rt_sigframe32 { - u32 rs_ass[4]; /* argument save space for o32 */ - u32 rs_pad[2]; /* Was: signal trampoline */ - compat_siginfo_t rs_info; - struct ucontext32 rs_uc; -}; - -static int setup_sigcontext32(struct pt_regs *regs, - struct sigcontext32 __user *sc) -{ - int err = 0; - int i; - - err |= __put_user(regs->cp0_epc, &sc->sc_pc); - - err |= __put_user(0, &sc->sc_regs[0]); - for (i = 1; i < 32; i++) - err |= __put_user(regs->regs[i], &sc->sc_regs[i]); - - err |= __put_user(regs->hi, &sc->sc_mdhi); - err |= __put_user(regs->lo, &sc->sc_mdlo); - if (cpu_has_dsp) { - err |= __put_user(rddsp(DSP_MASK), &sc->sc_dsp); - err |= __put_user(mfhi1(), &sc->sc_hi1); - err |= __put_user(mflo1(), &sc->sc_lo1); - err |= __put_user(mfhi2(), &sc->sc_hi2); - err |= __put_user(mflo2(), &sc->sc_lo2); - err |= __put_user(mfhi3(), &sc->sc_hi3); - err |= __put_user(mflo3(), &sc->sc_lo3); - } - - /* - * Save FPU state to signal context. Signal handler - * will "inherit" current FPU state. - */ - err |= protected_save_fp_context(sc); - - return err; -} - -static int restore_sigcontext32(struct pt_regs *regs, - struct sigcontext32 __user *sc) -{ - int err = 0; - s32 treg; - int i; - - /* Always make any pending restarted system calls return -EINTR */ - current->restart_block.fn = do_no_restart_syscall; - - err |= __get_user(regs->cp0_epc, &sc->sc_pc); - err |= __get_user(regs->hi, &sc->sc_mdhi); - err |= __get_user(regs->lo, &sc->sc_mdlo); - if (cpu_has_dsp) { - err |= __get_user(treg, &sc->sc_hi1); mthi1(treg); - err |= __get_user(treg, &sc->sc_lo1); mtlo1(treg); - err |= __get_user(treg, &sc->sc_hi2); mthi2(treg); - err |= __get_user(treg, &sc->sc_lo2); mtlo2(treg); - err |= __get_user(treg, &sc->sc_hi3); mthi3(treg); - err |= __get_user(treg, &sc->sc_lo3); mtlo3(treg); - err |= __get_user(treg, &sc->sc_dsp); wrdsp(treg, DSP_MASK); - } - - for (i = 1; i < 32; i++) - err |= __get_user(regs->regs[i], &sc->sc_regs[i]); - - return err ?: protected_restore_fp_context(sc); -} - /* * Atomically swap in the new signal mask, and wait for a signal. */ @@ -247,176 +144,3 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) return 0; } - -asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs) -{ - struct sigframe32 __user *frame; - sigset_t blocked; - int sig; - - frame = (struct sigframe32 __user *) regs.regs[29]; - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) - goto badframe; - if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask)) - goto badframe; - - set_current_blocked(&blocked); - - sig = restore_sigcontext32(®s, &frame->sf_sc); - if (sig < 0) - goto badframe; - else if (sig) - force_sig(sig, current); - - /* - * Don't let your children do this ... - */ - __asm__ __volatile__( - "move\t$29, %0\n\t" - "j\tsyscall_exit" - :/* no outputs */ - :"r" (®s)); - /* Unreached */ - -badframe: - force_sig(SIGSEGV, current); -} - -asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) -{ - struct rt_sigframe32 __user *frame; - sigset_t set; - int sig; - - frame = (struct rt_sigframe32 __user *) regs.regs[29]; - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) - goto badframe; - if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask)) - goto badframe; - - set_current_blocked(&set); - - sig = restore_sigcontext32(®s, &frame->rs_uc.uc_mcontext); - if (sig < 0) - goto badframe; - else if (sig) - force_sig(sig, current); - - if (compat_restore_altstack(&frame->rs_uc.uc_stack)) - goto badframe; - - /* - * Don't let your children do this ... - */ - __asm__ __volatile__( - "move\t$29, %0\n\t" - "j\tsyscall_exit" - :/* no outputs */ - :"r" (®s)); - /* Unreached */ - -badframe: - force_sig(SIGSEGV, current); -} - -static int setup_frame_32(void *sig_return, struct ksignal *ksig, - struct pt_regs *regs, sigset_t *set) -{ - struct sigframe32 __user *frame; - int err = 0; - - frame = get_sigframe(ksig, regs, sizeof(*frame)); - if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame))) - return -EFAULT; - - err |= setup_sigcontext32(regs, &frame->sf_sc); - err |= __copy_conv_sigset_to_user(&frame->sf_mask, set); - - if (err) - return -EFAULT; - - /* - * Arguments to signal handler: - * - * a0 = signal number - * a1 = 0 (should be cause) - * a2 = pointer to struct sigcontext - * - * $25 and c0_epc point to the signal handler, $29 points to the - * struct sigframe. - */ - regs->regs[ 4] = ksig->sig; - regs->regs[ 5] = 0; - regs->regs[ 6] = (unsigned long) &frame->sf_sc; - regs->regs[29] = (unsigned long) frame; - regs->regs[31] = (unsigned long) sig_return; - regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler; - - DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n", - current->comm, current->pid, - frame, regs->cp0_epc, regs->regs[31]); - - return 0; -} - -static int setup_rt_frame_32(void *sig_return, struct ksignal *ksig, - struct pt_regs *regs, sigset_t *set) -{ - struct rt_sigframe32 __user *frame; - int err = 0; - - frame = get_sigframe(ksig, regs, sizeof(*frame)); - if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame))) - return -EFAULT; - - /* Convert (siginfo_t -> compat_siginfo_t) and copy to user. */ - err |= copy_siginfo_to_user32(&frame->rs_info, &ksig->info); - - /* Create the ucontext. */ - err |= __put_user(0, &frame->rs_uc.uc_flags); - err |= __put_user(0, &frame->rs_uc.uc_link); - err |= __compat_save_altstack(&frame->rs_uc.uc_stack, regs->regs[29]); - err |= setup_sigcontext32(regs, &frame->rs_uc.uc_mcontext); - err |= __copy_conv_sigset_to_user(&frame->rs_uc.uc_sigmask, set); - - if (err) - return -EFAULT; - - /* - * Arguments to signal handler: - * - * a0 = signal number - * a1 = 0 (should be cause) - * a2 = pointer to ucontext - * - * $25 and c0_epc point to the signal handler, $29 points to - * the struct rt_sigframe32. - */ - regs->regs[ 4] = ksig->sig; - regs->regs[ 5] = (unsigned long) &frame->rs_info; - regs->regs[ 6] = (unsigned long) &frame->rs_uc; - regs->regs[29] = (unsigned long) frame; - regs->regs[31] = (unsigned long) sig_return; - regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler; - - DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n", - current->comm, current->pid, - frame, regs->cp0_epc, regs->regs[31]); - - return 0; -} - -/* - * o32 compatibility on 64-bit kernels, without DSP ASE - */ -struct mips_abi mips_abi_32 = { - .setup_frame = setup_frame_32, - .setup_rt_frame = setup_rt_frame_32, - .restart = __NR_O32_restart_syscall, - - .off_sc_fpregs = offsetof(struct sigcontext32, sc_fpregs), - .off_sc_fpc_csr = offsetof(struct sigcontext32, sc_fpc_csr), - .off_sc_used_math = offsetof(struct sigcontext32, sc_used_math), - - .vdso = &vdso_image_o32, -}; diff --git a/arch/mips/kernel/signal_o32.c b/arch/mips/kernel/signal_o32.c new file mode 100644 index 0000000..5e169fc --- /dev/null +++ b/arch/mips/kernel/signal_o32.c @@ -0,0 +1,285 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 1994 - 2000, 2006 Ralf Baechle + * Copyright (C) 1999, 2000 Silicon Graphics, Inc. + * Copyright (C) 2016, Imagination Technologies Ltd. + */ +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/signal.h> +#include <linux/uaccess.h> + +#include <asm/abi.h> +#include <asm/compat-signal.h> +#include <asm/dsp.h> +#include <asm/sim.h> +#include <asm/unistd.h> + +#include "signal-common.h" + +/* + * Including <asm/unistd.h> would give use the 64-bit syscall numbers ... + */ +#define __NR_O32_restart_syscall 4253 + +struct sigframe32 { + u32 sf_ass[4]; /* argument save space for o32 */ + u32 sf_pad[2]; /* Was: signal trampoline */ + struct sigcontext32 sf_sc; + compat_sigset_t sf_mask; +}; + +struct ucontext32 { + u32 uc_flags; + s32 uc_link; + compat_stack_t uc_stack; + struct sigcontext32 uc_mcontext; + compat_sigset_t uc_sigmask; /* mask last for extensibility */ +}; + +struct rt_sigframe32 { + u32 rs_ass[4]; /* argument save space for o32 */ + u32 rs_pad[2]; /* Was: signal trampoline */ + compat_siginfo_t rs_info; + struct ucontext32 rs_uc; +}; + +static int setup_sigcontext32(struct pt_regs *regs, + struct sigcontext32 __user *sc) +{ + int err = 0; + int i; + + err |= __put_user(regs->cp0_epc, &sc->sc_pc); + + err |= __put_user(0, &sc->sc_regs[0]); + for (i = 1; i < 32; i++) + err |= __put_user(regs->regs[i], &sc->sc_regs[i]); + + err |= __put_user(regs->hi, &sc->sc_mdhi); + err |= __put_user(regs->lo, &sc->sc_mdlo); + if (cpu_has_dsp) { + err |= __put_user(rddsp(DSP_MASK), &sc->sc_dsp); + err |= __put_user(mfhi1(), &sc->sc_hi1); + err |= __put_user(mflo1(), &sc->sc_lo1); + err |= __put_user(mfhi2(), &sc->sc_hi2); + err |= __put_user(mflo2(), &sc->sc_lo2); + err |= __put_user(mfhi3(), &sc->sc_hi3); + err |= __put_user(mflo3(), &sc->sc_lo3); + } + + /* + * Save FPU state to signal context. Signal handler + * will "inherit" current FPU state. + */ + err |= protected_save_fp_context(sc); + + return err; +} + +static int restore_sigcontext32(struct pt_regs *regs, + struct sigcontext32 __user *sc) +{ + int err = 0; + s32 treg; + int i; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + err |= __get_user(regs->cp0_epc, &sc->sc_pc); + err |= __get_user(regs->hi, &sc->sc_mdhi); + err |= __get_user(regs->lo, &sc->sc_mdlo); + if (cpu_has_dsp) { + err |= __get_user(treg, &sc->sc_hi1); mthi1(treg); + err |= __get_user(treg, &sc->sc_lo1); mtlo1(treg); + err |= __get_user(treg, &sc->sc_hi2); mthi2(treg); + err |= __get_user(treg, &sc->sc_lo2); mtlo2(treg); + err |= __get_user(treg, &sc->sc_hi3); mthi3(treg); + err |= __get_user(treg, &sc->sc_lo3); mtlo3(treg); + err |= __get_user(treg, &sc->sc_dsp); wrdsp(treg, DSP_MASK); + } + + for (i = 1; i < 32; i++) + err |= __get_user(regs->regs[i], &sc->sc_regs[i]); + + return err ?: protected_restore_fp_context(sc); +} + +static int setup_frame_32(void *sig_return, struct ksignal *ksig, + struct pt_regs *regs, sigset_t *set) +{ + struct sigframe32 __user *frame; + int err = 0; + + frame = get_sigframe(ksig, regs, sizeof(*frame)); + if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame))) + return -EFAULT; + + err |= setup_sigcontext32(regs, &frame->sf_sc); + err |= __copy_conv_sigset_to_user(&frame->sf_mask, set); + + if (err) + return -EFAULT; + + /* + * Arguments to signal handler: + * + * a0 = signal number + * a1 = 0 (should be cause) + * a2 = pointer to struct sigcontext + * + * $25 and c0_epc point to the signal handler, $29 points to the + * struct sigframe. + */ + regs->regs[ 4] = ksig->sig; + regs->regs[ 5] = 0; + regs->regs[ 6] = (unsigned long) &frame->sf_sc; + regs->regs[29] = (unsigned long) frame; + regs->regs[31] = (unsigned long) sig_return; + regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler; + + DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n", + current->comm, current->pid, + frame, regs->cp0_epc, regs->regs[31]); + + return 0; +} + +asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) +{ + struct rt_sigframe32 __user *frame; + sigset_t set; + int sig; + + frame = (struct rt_sigframe32 __user *) regs.regs[29]; + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask)) + goto badframe; + + set_current_blocked(&set); + + sig = restore_sigcontext32(®s, &frame->rs_uc.uc_mcontext); + if (sig < 0) + goto badframe; + else if (sig) + force_sig(sig, current); + + if (compat_restore_altstack(&frame->rs_uc.uc_stack)) + goto badframe; + + /* + * Don't let your children do this ... + */ + __asm__ __volatile__( + "move\t$29, %0\n\t" + "j\tsyscall_exit" + :/* no outputs */ + :"r" (®s)); + /* Unreached */ + +badframe: + force_sig(SIGSEGV, current); +} + +static int setup_rt_frame_32(void *sig_return, struct ksignal *ksig, + struct pt_regs *regs, sigset_t *set) +{ + struct rt_sigframe32 __user *frame; + int err = 0; + + frame = get_sigframe(ksig, regs, sizeof(*frame)); + if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame))) + return -EFAULT; + + /* Convert (siginfo_t -> compat_siginfo_t) and copy to user. */ + err |= copy_siginfo_to_user32(&frame->rs_info, &ksig->info); + + /* Create the ucontext. */ + err |= __put_user(0, &frame->rs_uc.uc_flags); + err |= __put_user(0, &frame->rs_uc.uc_link); + err |= __compat_save_altstack(&frame->rs_uc.uc_stack, regs->regs[29]); + err |= setup_sigcontext32(regs, &frame->rs_uc.uc_mcontext); + err |= __copy_conv_sigset_to_user(&frame->rs_uc.uc_sigmask, set); + + if (err) + return -EFAULT; + + /* + * Arguments to signal handler: + * + * a0 = signal number + * a1 = 0 (should be cause) + * a2 = pointer to ucontext + * + * $25 and c0_epc point to the signal handler, $29 points to + * the struct rt_sigframe32. + */ + regs->regs[ 4] = ksig->sig; + regs->regs[ 5] = (unsigned long) &frame->rs_info; + regs->regs[ 6] = (unsigned long) &frame->rs_uc; + regs->regs[29] = (unsigned long) frame; + regs->regs[31] = (unsigned long) sig_return; + regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler; + + DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n", + current->comm, current->pid, + frame, regs->cp0_epc, regs->regs[31]); + + return 0; +} + +/* + * o32 compatibility on 64-bit kernels, without DSP ASE + */ +struct mips_abi mips_abi_32 = { + .setup_frame = setup_frame_32, + .setup_rt_frame = setup_rt_frame_32, + .restart = __NR_O32_restart_syscall, + + .off_sc_fpregs = offsetof(struct sigcontext32, sc_fpregs), + .off_sc_fpc_csr = offsetof(struct sigcontext32, sc_fpc_csr), + .off_sc_used_math = offsetof(struct sigcontext32, sc_used_math), + + .vdso = &vdso_image_o32, +}; + + +asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs) +{ + struct sigframe32 __user *frame; + sigset_t blocked; + int sig; + + frame = (struct sigframe32 __user *) regs.regs[29]; + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask)) + goto badframe; + + set_current_blocked(&blocked); + + sig = restore_sigcontext32(®s, &frame->sf_sc); + if (sig < 0) + goto badframe; + else if (sig) + force_sig(sig, current); + + /* + * Don't let your children do this ... + */ + __asm__ __volatile__( + "move\t$29, %0\n\t" + "j\tsyscall_exit" + :/* no outputs */ + :"r" (®s)); + /* Unreached */ + +badframe: + force_sig(SIGSEGV, current); +} diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index e02addc..6d0f132 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -363,6 +363,7 @@ static int bmips_cpu_disable(void) pr_info("SMP: CPU%d is offline\n", cpu); set_cpu_online(cpu, false); + calculate_cpu_foreign_map(); cpumask_clear_cpu(cpu, &cpu_callin_map); clear_c0_status(IE_IRQ5); diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 05b3201..e9d9fc6 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -206,7 +206,7 @@ err_out: } } -static void boot_core(unsigned core) +static void boot_core(unsigned int core, unsigned int vpe_id) { u32 access, stat, seq_state; unsigned timeout; @@ -233,8 +233,9 @@ static void boot_core(unsigned core) mips_cpc_lock_other(core); if (mips_cm_revision() >= CM_REV_CM3) { - /* Run VP0 following the reset */ - write_cpc_co_vp_run(0x1); + /* Run only the requested VP following the reset */ + write_cpc_co_vp_stop(0xf); + write_cpc_co_vp_run(1 << vpe_id); /* * Ensure that the VP_RUN register is written before the @@ -306,7 +307,7 @@ static void cps_boot_secondary(int cpu, struct task_struct *idle) if (!test_bit(core, core_power)) { /* Boot a VPE on a powered down core */ - boot_core(core); + boot_core(core, vpe_id); goto out; } @@ -397,6 +398,7 @@ static int cps_cpu_disable(void) atomic_sub(1 << cpu_vpe_id(¤t_cpu_data), &core_cfg->vpe_mask); smp_mb__after_atomic(); set_cpu_online(cpu, false); + calculate_cpu_foreign_map(); cpumask_clear_cpu(cpu, &cpu_callin_map); return 0; @@ -411,14 +413,16 @@ static enum { void play_dead(void) { - unsigned cpu, core; + unsigned int cpu, core, vpe_id; local_irq_disable(); idle_task_exit(); cpu = smp_processor_id(); cpu_death = CPU_DEATH_POWER; - if (cpu_has_mipsmt) { + pr_debug("CPU%d going offline\n", cpu); + + if (cpu_has_mipsmt || cpu_has_vp) { core = cpu_data[cpu].core; /* Look for another online VPE within the core */ @@ -439,10 +443,21 @@ void play_dead(void) complete(&cpu_death_chosen); if (cpu_death == CPU_DEATH_HALT) { - /* Halt this TC */ - write_c0_tchalt(TCHALT_H); - instruction_hazard(); + vpe_id = cpu_vpe_id(&cpu_data[cpu]); + + pr_debug("Halting core %d VP%d\n", core, vpe_id); + if (cpu_has_mipsmt) { + /* Halt this TC */ + write_c0_tchalt(TCHALT_H); + instruction_hazard(); + } else if (cpu_has_vp) { + write_cpc_cl_vp_stop(1 << vpe_id); + + /* Ensure that the VP_STOP register is written */ + wmb(); + } } else { + pr_debug("Gating power to core %d\n", core); /* Power down the core */ cps_pm_enter_state(CPS_PM_POWER_GATED); } @@ -469,6 +484,7 @@ static void wait_for_sibling_halt(void *ptr_cpu) static void cps_cpu_die(unsigned int cpu) { unsigned core = cpu_data[cpu].core; + unsigned int vpe_id = cpu_vpe_id(&cpu_data[cpu]); unsigned stat; int err; @@ -497,10 +513,12 @@ static void cps_cpu_die(unsigned int cpu) * in which case the CPC will refuse to power down the core. */ do { + mips_cm_lock_other(core, vpe_id); mips_cpc_lock_other(core); stat = read_cpc_co_stat_conf(); stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK; mips_cpc_unlock_other(); + mips_cm_unlock_other(); } while (stat != CPC_Cx_STAT_CONF_SEQSTATE_D0 && stat != CPC_Cx_STAT_CONF_SEQSTATE_D2 && stat != CPC_Cx_STAT_CONF_SEQSTATE_U2); @@ -517,6 +535,12 @@ static void cps_cpu_die(unsigned int cpu) (void *)(unsigned long)cpu, 1); if (err) panic("Failed to call remote sibling CPU\n"); + } else if (cpu_has_vp) { + do { + mips_cm_lock_other(core, vpe_id); + stat = read_cpc_co_vp_running(); + mips_cm_unlock_other(); + } while (stat & (1 << vpe_id)); } } diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index f9d01e9..f95f094 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -72,7 +72,7 @@ EXPORT_SYMBOL(cpu_core_map); * A logcal cpu mask containing only one VPE per core to * reduce the number of IPIs on large MT systems. */ -cpumask_t cpu_foreign_map __read_mostly; +cpumask_t cpu_foreign_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_foreign_map); /* representing cpus for which sibling maps can be computed */ @@ -124,7 +124,7 @@ static inline void set_cpu_core_map(int cpu) * Calculate a new cpu_foreign_map mask whenever a * new cpu appears or disappears. */ -static inline void calculate_cpu_foreign_map(void) +void calculate_cpu_foreign_map(void) { int i, k, core_present; cpumask_t temp_foreign_map; @@ -141,7 +141,9 @@ static inline void calculate_cpu_foreign_map(void) cpumask_set_cpu(i, &temp_foreign_map); } - cpumask_copy(&cpu_foreign_map, &temp_foreign_map); + for_each_online_cpu(i) + cpumask_andnot(&cpu_foreign_map[i], + &temp_foreign_map, &cpu_sibling_map[i]); } struct plat_smp_ops *mp_ops; @@ -344,16 +346,9 @@ asmlinkage void start_secondary(void) static void stop_this_cpu(void *dummy) { /* - * Remove this CPU. Be a bit slow here and - * set the bits for every online CPU so we don't miss - * any IPI whilst taking this VPE down. + * Remove this CPU: */ - cpumask_copy(&cpu_foreign_map, cpu_online_mask); - - /* Make it visible to every other CPU */ - smp_mb(); - set_cpu_online(smp_processor_id(), false); calculate_cpu_foreign_map(); local_irq_disable(); @@ -512,10 +507,17 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned l smp_on_other_tlbs(flush_tlb_range_ipi, &fd); } else { unsigned int cpu; + int exec = vma->vm_flags & VM_EXEC; for_each_online_cpu(cpu) { + /* + * flush_cache_range() will only fully flush icache if + * the VMA is executable, otherwise we must invalidate + * ASID without it appearing to has_valid_asid() as if + * mm has been completely unused by that CPU. + */ if (cpu != smp_processor_id() && cpu_context(cpu, mm)) - cpu_context(cpu, mm) = 0; + cpu_context(cpu, mm) = !exec; } } local_flush_tlb_range(vma, start, end); @@ -560,8 +562,14 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long page) unsigned int cpu; for_each_online_cpu(cpu) { + /* + * flush_cache_page() only does partial flushes, so + * invalidate ASID without it appearing to + * has_valid_asid() as if mm has been completely unused + * by that CPU. + */ if (cpu != smp_processor_id() && cpu_context(cpu, vma->vm_mm)) - cpu_context(cpu, vma->vm_mm) = 0; + cpu_context(cpu, vma->vm_mm) = 1; } } local_flush_tlb_page(vma, page); diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 6fb4704..3de85be 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -704,6 +704,7 @@ asmlinkage void do_ov(struct pt_regs *regs) int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31) { struct siginfo si = { 0 }; + struct vm_area_struct *vma; switch (sig) { case 0: @@ -744,7 +745,8 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31) si.si_addr = fault_addr; si.si_signo = sig; down_read(¤t->mm->mmap_sem); - if (find_vma(current->mm, (unsigned long)fault_addr)) + vma = find_vma(current->mm, (unsigned long)fault_addr); + if (vma && (vma->vm_start <= (unsigned long)fault_addr)) si.si_code = SEGV_ACCERR; else si.si_code = SEGV_MAPERR; diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 54e1663..9abe447 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -107,6 +107,16 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (down_write_killable(&mm->mmap_sem)) return -EINTR; + /* Map delay slot emulation page */ + base = mmap_region(NULL, STACK_TOP, PAGE_SIZE, + VM_READ|VM_WRITE|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + 0); + if (IS_ERR_VALUE(base)) { + ret = base; + goto out; + } + /* * Determine total area size. This includes the VDSO data itself, the * data page, and the GIC user page if present. Always create a mapping diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index ff17669e..8ac0e59 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -66,7 +66,7 @@ int gic_present; #endif static int exin_avail; -static struct resource ltq_eiu_irq[MAX_EIU]; +static u32 ltq_eiu_irq[MAX_EIU]; static void __iomem *ltq_icu_membase[MAX_IM]; static void __iomem *ltq_eiu_membase; static struct irq_domain *ltq_domain; @@ -75,7 +75,7 @@ static int ltq_perfcount_irq; int ltq_eiu_get_irq(int exin) { if (exin < exin_avail) - return ltq_eiu_irq[exin].start; + return ltq_eiu_irq[exin]; return -1; } @@ -125,8 +125,8 @@ static int ltq_eiu_settype(struct irq_data *d, unsigned int type) { int i; - for (i = 0; i < MAX_EIU; i++) { - if (d->hwirq == ltq_eiu_irq[i].start) { + for (i = 0; i < exin_avail; i++) { + if (d->hwirq == ltq_eiu_irq[i]) { int val = 0; int edge = 0; @@ -173,8 +173,8 @@ static unsigned int ltq_startup_eiu_irq(struct irq_data *d) int i; ltq_enable_irq(d); - for (i = 0; i < MAX_EIU; i++) { - if (d->hwirq == ltq_eiu_irq[i].start) { + for (i = 0; i < exin_avail; i++) { + if (d->hwirq == ltq_eiu_irq[i]) { /* by default we are low level triggered */ ltq_eiu_settype(d, IRQF_TRIGGER_LOW); /* clear all pending */ @@ -195,8 +195,8 @@ static void ltq_shutdown_eiu_irq(struct irq_data *d) int i; ltq_disable_irq(d); - for (i = 0; i < MAX_EIU; i++) { - if (d->hwirq == ltq_eiu_irq[i].start) { + for (i = 0; i < exin_avail; i++) { + if (d->hwirq == ltq_eiu_irq[i]) { /* disable */ ltq_eiu_w32(ltq_eiu_r32(LTQ_EIU_EXIN_INEN) & ~BIT(i), LTQ_EIU_EXIN_INEN); @@ -206,7 +206,7 @@ static void ltq_shutdown_eiu_irq(struct irq_data *d) } static struct irq_chip ltq_irq_type = { - "icu", + .name = "icu", .irq_enable = ltq_enable_irq, .irq_disable = ltq_disable_irq, .irq_unmask = ltq_enable_irq, @@ -216,7 +216,7 @@ static struct irq_chip ltq_irq_type = { }; static struct irq_chip ltq_eiu_type = { - "eiu", + .name = "eiu", .irq_startup = ltq_startup_eiu_irq, .irq_shutdown = ltq_shutdown_eiu_irq, .irq_enable = ltq_enable_irq, @@ -341,10 +341,10 @@ static int icu_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) return 0; for (i = 0; i < exin_avail; i++) - if (hw == ltq_eiu_irq[i].start) + if (hw == ltq_eiu_irq[i]) chip = <q_eiu_type; - irq_set_chip_and_handler(hw, chip, handle_level_irq); + irq_set_chip_and_handler(irq, chip, handle_level_irq); return 0; } @@ -439,14 +439,15 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent) eiu_node = of_find_compatible_node(NULL, NULL, "lantiq,eiu-xway"); if (eiu_node && !of_address_to_resource(eiu_node, 0, &res)) { /* find out how many external irq sources we have */ - exin_avail = of_irq_count(eiu_node); + exin_avail = of_property_count_u32_elems(eiu_node, + "lantiq,eiu-irqs"); if (exin_avail > MAX_EIU) exin_avail = MAX_EIU; - ret = of_irq_to_resource_table(eiu_node, + ret = of_property_read_u32_array(eiu_node, "lantiq,eiu-irqs", ltq_eiu_irq, exin_avail); - if (ret != exin_avail) + if (ret) panic("failed to load external irq resources"); if (!request_mem_region(res.start, resource_size(&res), diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c index 5f693ac7..4cbb000 100644 --- a/arch/mips/lantiq/prom.c +++ b/arch/mips/lantiq/prom.c @@ -74,8 +74,8 @@ void __init plat_mem_setup(void) set_io_port_base((unsigned long) KSEG1); - if (fw_arg0 == -2) /* UHI interface */ - dtb = (void *)fw_arg1; + if (fw_passed_dtb) /* UHI interface */ + dtb = (void *)fw_passed_dtb; else if (__dtb_start != __dtb_end) dtb = (void *)__dtb_start; else diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c index 249039a..4788bea 100644 --- a/arch/mips/loongson64/loongson-3/hpet.c +++ b/arch/mips/loongson64/loongson-3/hpet.c @@ -13,8 +13,8 @@ #define SMBUS_PCI_REG64 0x64 #define SMBUS_PCI_REGB4 0xb4 -#define HPET_MIN_CYCLES 64 -#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1)) +#define HPET_MIN_CYCLES 16 +#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES * 12) static DEFINE_SPINLOCK(hpet_lock); DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device); @@ -157,14 +157,14 @@ static int hpet_tick_resume(struct clock_event_device *evt) static int hpet_next_event(unsigned long delta, struct clock_event_device *evt) { - unsigned int cnt; - int res; + u32 cnt; + s32 res; cnt = hpet_read(HPET_COUNTER); - cnt += delta; + cnt += (u32) delta; hpet_write(HPET_T0_CMP, cnt); - res = (int)(cnt - hpet_read(HPET_COUNTER)); + res = (s32)(cnt - hpet_read(HPET_COUNTER)); return res < HPET_MIN_CYCLES ? -ETIME : 0; } @@ -230,7 +230,7 @@ void __init setup_hpet_timer(void) cd = &per_cpu(hpet_clockevent_device, cpu); cd->name = "hpet"; - cd->rating = 320; + cd->rating = 100; cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; cd->set_state_shutdown = hpet_set_state_shutdown; cd->set_state_periodic = hpet_set_state_periodic; diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index e59759a..2fec6f7 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -417,6 +417,7 @@ static int loongson3_cpu_disable(void) return -EBUSY; set_cpu_online(cpu, false); + calculate_cpu_foreign_map(); cpumask_clear_cpu(cpu, &cpu_callin_map); local_irq_save(flags); fixup_irqs(); diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 92d15e6..36775d2 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -434,8 +434,8 @@ static int microMIPS32_to_MIPS32(union mips_instruction *insn_ptr) * a single subroutine should be used across both * modules. */ -static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, - unsigned long *contpc) +int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, + unsigned long *contpc) { union mips_instruction insn = (union mips_instruction)dec_insn.insn; unsigned int fcr31; @@ -1268,7 +1268,7 @@ branch_common: * instruction in the dslot. */ sig = mips_dsemul(xcp, ir, - contpc); + bcpc, contpc); if (sig < 0) break; if (sig) @@ -1323,7 +1323,7 @@ branch_common: * Single step the non-cp1 * instruction in the dslot */ - sig = mips_dsemul(xcp, ir, contpc); + sig = mips_dsemul(xcp, ir, bcpc, contpc); if (sig < 0) break; if (sig) diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c index 4707488..72a4642 100644 --- a/arch/mips/math-emu/dsemul.c +++ b/arch/mips/math-emu/dsemul.c @@ -1,3 +1,6 @@ +#include <linux/err.h> +#include <linux/slab.h> + #include <asm/branch.h> #include <asm/cacheflush.h> #include <asm/fpu_emulator.h> @@ -5,43 +8,211 @@ #include <asm/mipsregs.h> #include <asm/uaccess.h> -#include "ieee754.h" - -/* - * Emulate the arbitrary instruction ir at xcp->cp0_epc. Required when - * we have to emulate the instruction in a COP1 branch delay slot. Do - * not change cp0_epc due to the instruction +/** + * struct emuframe - The 'emulation' frame structure + * @emul: The instruction to 'emulate'. + * @badinst: A break instruction to cause a return to the kernel. * - * According to the spec: - * 1) it shouldn't be a branch :-) - * 2) it can be a COP instruction :-( - * 3) if we are tring to run a protected memory space we must take - * special care on memory access instructions :-( - */ - -/* - * "Trampoline" return routine to catch exception following - * execution of delay-slot instruction execution. + * This structure defines the frames placed within the delay slot emulation + * page in response to a call to mips_dsemul(). Each thread may be allocated + * only one frame at any given time. The kernel stores within it the + * instruction to be 'emulated' followed by a break instruction, then + * executes the frame in user mode. The break causes a trap to the kernel + * which leads to do_dsemulret() being called unless the instruction in + * @emul causes a trap itself, is a branch, or a signal is delivered to + * the thread. In these cases the allocated frame will either be reused by + * a subsequent delay slot 'emulation', or be freed during signal delivery or + * upon thread exit. + * + * This approach is used because: + * + * - Actually emulating all instructions isn't feasible. We would need to + * be able to handle instructions from all revisions of the MIPS ISA, + * all ASEs & all vendor instruction set extensions. This would be a + * whole lot of work & continual maintenance burden as new instructions + * are introduced, and in the case of some vendor extensions may not + * even be possible. Thus we need to take the approach of actually + * executing the instruction. + * + * - We must execute the instruction within user context. If we were to + * execute the instruction in kernel mode then it would have access to + * kernel resources without very careful checks, leaving us with a + * high potential for security or stability issues to arise. + * + * - We used to place the frame on the users stack, but this requires + * that the stack be executable. This is bad for security so the + * per-process page is now used instead. + * + * - The instruction in @emul may be something entirely invalid for a + * delay slot. The user may (intentionally or otherwise) place a branch + * in a delay slot, or a kernel mode instruction, or something else + * which generates an exception. Thus we can't rely upon the break in + * @badinst always being hit. For this reason we track the index of the + * frame allocated to each thread, allowing us to clean it up at later + * points such as signal delivery or thread exit. + * + * - The user may generate a fake struct emuframe if they wish, invoking + * the BRK_MEMU break instruction themselves. We must therefore not + * trust that BRK_MEMU means there's actually a valid frame allocated + * to the thread, and must not allow the user to do anything they + * couldn't already. */ - struct emuframe { mips_instruction emul; mips_instruction badinst; - mips_instruction cookie; - unsigned long epc; }; -/* - * Set up an emulation frame for instruction IR, from a delay slot of - * a branch jumping to CPC. Return 0 if successful, -1 if no emulation - * required, otherwise a signal number causing a frame setup failure. - */ -int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc) +static const int emupage_frame_count = PAGE_SIZE / sizeof(struct emuframe); + +static inline __user struct emuframe *dsemul_page(void) +{ + return (__user struct emuframe *)STACK_TOP; +} + +static int alloc_emuframe(void) +{ + mm_context_t *mm_ctx = ¤t->mm->context; + int idx; + +retry: + spin_lock(&mm_ctx->bd_emupage_lock); + + /* Ensure we have an allocation bitmap */ + if (!mm_ctx->bd_emupage_allocmap) { + mm_ctx->bd_emupage_allocmap = + kcalloc(BITS_TO_LONGS(emupage_frame_count), + sizeof(unsigned long), + GFP_ATOMIC); + + if (!mm_ctx->bd_emupage_allocmap) { + idx = BD_EMUFRAME_NONE; + goto out_unlock; + } + } + + /* Attempt to allocate a single bit/frame */ + idx = bitmap_find_free_region(mm_ctx->bd_emupage_allocmap, + emupage_frame_count, 0); + if (idx < 0) { + /* + * Failed to allocate a frame. We'll wait until one becomes + * available. We unlock the page so that other threads actually + * get the opportunity to free their frames, which means + * technically the result of bitmap_full may be incorrect. + * However the worst case is that we repeat all this and end up + * back here again. + */ + spin_unlock(&mm_ctx->bd_emupage_lock); + if (!wait_event_killable(mm_ctx->bd_emupage_queue, + !bitmap_full(mm_ctx->bd_emupage_allocmap, + emupage_frame_count))) + goto retry; + + /* Received a fatal signal - just give in */ + return BD_EMUFRAME_NONE; + } + + /* Success! */ + pr_debug("allocate emuframe %d to %d\n", idx, current->pid); +out_unlock: + spin_unlock(&mm_ctx->bd_emupage_lock); + return idx; +} + +static void free_emuframe(int idx, struct mm_struct *mm) +{ + mm_context_t *mm_ctx = &mm->context; + + spin_lock(&mm_ctx->bd_emupage_lock); + + pr_debug("free emuframe %d from %d\n", idx, current->pid); + bitmap_clear(mm_ctx->bd_emupage_allocmap, idx, 1); + + /* If some thread is waiting for a frame, now's its chance */ + wake_up(&mm_ctx->bd_emupage_queue); + + spin_unlock(&mm_ctx->bd_emupage_lock); +} + +static bool within_emuframe(struct pt_regs *regs) +{ + unsigned long base = (unsigned long)dsemul_page(); + + if (regs->cp0_epc < base) + return false; + if (regs->cp0_epc >= (base + PAGE_SIZE)) + return false; + + return true; +} + +bool dsemul_thread_cleanup(struct task_struct *tsk) +{ + int fr_idx; + + /* Clear any allocated frame, retrieving its index */ + fr_idx = atomic_xchg(&tsk->thread.bd_emu_frame, BD_EMUFRAME_NONE); + + /* If no frame was allocated, we're done */ + if (fr_idx == BD_EMUFRAME_NONE) + return false; + + task_lock(tsk); + + /* Free the frame that this thread had allocated */ + if (tsk->mm) + free_emuframe(fr_idx, tsk->mm); + + task_unlock(tsk); + return true; +} + +bool dsemul_thread_rollback(struct pt_regs *regs) +{ + struct emuframe __user *fr; + int fr_idx; + + /* Do nothing if we're not executing from a frame */ + if (!within_emuframe(regs)) + return false; + + /* Find the frame being executed */ + fr_idx = atomic_read(¤t->thread.bd_emu_frame); + if (fr_idx == BD_EMUFRAME_NONE) + return false; + fr = &dsemul_page()[fr_idx]; + + /* + * If the PC is at the emul instruction, roll back to the branch. If + * PC is at the badinst (break) instruction, we've already emulated the + * instruction so progress to the continue PC. If it's anything else + * then something is amiss & the user has branched into some other area + * of the emupage - we'll free the allocated frame anyway. + */ + if (msk_isa16_mode(regs->cp0_epc) == (unsigned long)&fr->emul) + regs->cp0_epc = current->thread.bd_emu_branch_pc; + else if (msk_isa16_mode(regs->cp0_epc) == (unsigned long)&fr->badinst) + regs->cp0_epc = current->thread.bd_emu_cont_pc; + + atomic_set(¤t->thread.bd_emu_frame, BD_EMUFRAME_NONE); + free_emuframe(fr_idx, current->mm); + return true; +} + +void dsemul_mm_cleanup(struct mm_struct *mm) +{ + mm_context_t *mm_ctx = &mm->context; + + kfree(mm_ctx->bd_emupage_allocmap); +} + +int mips_dsemul(struct pt_regs *regs, mips_instruction ir, + unsigned long branch_pc, unsigned long cont_pc) { int isa16 = get_isa16_mode(regs->cp0_epc); mips_instruction break_math; struct emuframe __user *fr; - int err; + int err, fr_idx; /* NOP is easy */ if (ir == 0) @@ -68,30 +239,20 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc) } } - pr_debug("dsemul %lx %lx\n", regs->cp0_epc, cpc); + pr_debug("dsemul 0x%08lx cont at 0x%08lx\n", regs->cp0_epc, cont_pc); - /* - * The strategy is to push the instruction onto the user stack - * and put a trap after it which we can catch and jump to - * the required address any alternative apart from full - * instruction emulation!!. - * - * Algorithmics used a system call instruction, and - * borrowed that vector. MIPS/Linux version is a bit - * more heavyweight in the interests of portability and - * multiprocessor support. For Linux we use a BREAK 514 - * instruction causing a breakpoint exception. - */ - break_math = BREAK_MATH(isa16); - - /* Ensure that the two instructions are in the same cache line */ - fr = (struct emuframe __user *) - ((regs->regs[29] - sizeof(struct emuframe)) & ~0x7); - - /* Verify that the stack pointer is not completely insane */ - if (unlikely(!access_ok(VERIFY_WRITE, fr, sizeof(struct emuframe)))) + /* Allocate a frame if we don't already have one */ + fr_idx = atomic_read(¤t->thread.bd_emu_frame); + if (fr_idx == BD_EMUFRAME_NONE) + fr_idx = alloc_emuframe(); + if (fr_idx == BD_EMUFRAME_NONE) return SIGBUS; + fr = &dsemul_page()[fr_idx]; + + /* Retrieve the appropriately encoded break instruction */ + break_math = BREAK_MATH(isa16); + /* Write the instructions to the frame */ if (isa16) { err = __put_user(ir >> 16, (u16 __user *)(&fr->emul)); @@ -106,84 +267,36 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc) err |= __put_user(break_math, &fr->badinst); } - err |= __put_user((mips_instruction)BD_COOKIE, &fr->cookie); - err |= __put_user(cpc, &fr->epc); - if (unlikely(err)) { MIPS_FPU_EMU_INC_STATS(errors); + free_emuframe(fr_idx, current->mm); return SIGBUS; } + /* Record the PC of the branch, PC to continue from & frame index */ + current->thread.bd_emu_branch_pc = branch_pc; + current->thread.bd_emu_cont_pc = cont_pc; + atomic_set(¤t->thread.bd_emu_frame, fr_idx); + + /* Change user register context to execute the frame */ regs->cp0_epc = (unsigned long)&fr->emul | isa16; + /* Ensure the icache observes our newly written frame */ flush_cache_sigtramp((unsigned long)&fr->emul); return 0; } -int do_dsemulret(struct pt_regs *xcp) +bool do_dsemulret(struct pt_regs *xcp) { - int isa16 = get_isa16_mode(xcp->cp0_epc); - struct emuframe __user *fr; - unsigned long epc; - u32 insn, cookie; - int err = 0; - u16 instr[2]; - - fr = (struct emuframe __user *) - (msk_isa16_mode(xcp->cp0_epc) - sizeof(mips_instruction)); - - /* - * If we can't even access the area, something is very wrong, but we'll - * leave that to the default handling - */ - if (!access_ok(VERIFY_READ, fr, sizeof(struct emuframe))) - return 0; - - /* - * Do some sanity checking on the stackframe: - * - * - Is the instruction pointed to by the EPC an BREAK_MATH? - * - Is the following memory word the BD_COOKIE? - */ - if (isa16) { - err = __get_user(instr[0], - (u16 __user *)(&fr->badinst)); - err |= __get_user(instr[1], - (u16 __user *)((long)(&fr->badinst) + 2)); - insn = (instr[0] << 16) | instr[1]; - } else { - err = __get_user(insn, &fr->badinst); - } - err |= __get_user(cookie, &fr->cookie); - - if (unlikely(err || - insn != BREAK_MATH(isa16) || cookie != BD_COOKIE)) { + /* Cleanup the allocated frame, returning if there wasn't one */ + if (!dsemul_thread_cleanup(current)) { MIPS_FPU_EMU_INC_STATS(errors); - return 0; - } - - /* - * At this point, we are satisfied that it's a BD emulation trap. Yes, - * a user might have deliberately put two malformed and useless - * instructions in a row in his program, in which case he's in for a - * nasty surprise - the next instruction will be treated as a - * continuation address! Alas, this seems to be the only way that we - * can handle signals, recursion, and longjmps() in the context of - * emulating the branch delay instruction. - */ - - pr_debug("dsemulret\n"); - - if (__get_user(epc, &fr->epc)) { /* Saved EPC */ - /* This is not a good situation to be in */ - force_sig(SIGBUS, current); - - return 0; + return false; } /* Set EPC to return to post-branch instruction */ - xcp->cp0_epc = epc; - MIPS_FPU_EMU_INC_STATS(ds_emul); - return 1; + xcp->cp0_epc = current->thread.bd_emu_cont_pc; + pr_debug("dsemulret to 0x%08lx\n", xcp->cp0_epc); + return true; } diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 7a9c345..cd72805 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -40,6 +40,51 @@ #include <asm/mips-cm.h> /* + * Bits describing what cache ops an SMP callback function may perform. + * + * R4K_HIT - Virtual user or kernel address based cache operations. The + * active_mm must be checked before using user addresses, falling + * back to kmap. + * R4K_INDEX - Index based cache operations. + */ + +#define R4K_HIT BIT(0) +#define R4K_INDEX BIT(1) + +/** + * r4k_op_needs_ipi() - Decide if a cache op needs to be done on every core. + * @type: Type of cache operations (R4K_HIT or R4K_INDEX). + * + * Decides whether a cache op needs to be performed on every core in the system. + * This may change depending on the @type of cache operation, as well as the set + * of online CPUs, so preemption should be disabled by the caller to prevent CPU + * hotplug from changing the result. + * + * Returns: 1 if the cache operation @type should be done on every core in + * the system. + * 0 if the cache operation @type is globalized and only needs to + * be performed on a simple CPU. + */ +static inline bool r4k_op_needs_ipi(unsigned int type) +{ + /* The MIPS Coherence Manager (CM) globalizes address-based cache ops */ + if (type == R4K_HIT && mips_cm_present()) + return false; + + /* + * Hardware doesn't globalize the required cache ops, so SMP calls may + * be needed, but only if there are foreign CPUs (non-siblings with + * separate caches). + */ + /* cpu_foreign_map[] undeclared when !CONFIG_SMP */ +#ifdef CONFIG_SMP + return !cpumask_empty(&cpu_foreign_map[0]); +#else + return false; +#endif +} + +/* * Special Variant of smp_call_function for use by cache functions: * * o No return value @@ -48,30 +93,17 @@ * primary cache. * o doesn't disable interrupts on the local CPU */ -static inline void r4k_on_each_cpu(void (*func) (void *info), void *info) +static inline void r4k_on_each_cpu(unsigned int type, + void (*func)(void *info), void *info) { preempt_disable(); - - /* - * The Coherent Manager propagates address-based cache ops to other - * cores but not index-based ops. However, r4k_on_each_cpu is used - * in both cases so there is no easy way to tell what kind of op is - * executed to the other cores. The best we can probably do is - * to restrict that call when a CM is not present because both - * CM-based SMP protocols (CMP & CPS) restrict index-based cache ops. - */ - if (!mips_cm_present()) - smp_call_function_many(&cpu_foreign_map, func, info, 1); + if (r4k_op_needs_ipi(type)) + smp_call_function_many(&cpu_foreign_map[smp_processor_id()], + func, info, 1); func(info); preempt_enable(); } -#if defined(CONFIG_MIPS_CMP) || defined(CONFIG_MIPS_CPS) -#define cpu_has_safe_index_cacheops 0 -#else -#define cpu_has_safe_index_cacheops 1 -#endif - /* * Must die. */ @@ -462,22 +494,44 @@ static inline void local_r4k___flush_cache_all(void * args) static void r4k___flush_cache_all(void) { - r4k_on_each_cpu(local_r4k___flush_cache_all, NULL); + r4k_on_each_cpu(R4K_INDEX, local_r4k___flush_cache_all, NULL); } -static inline int has_valid_asid(const struct mm_struct *mm) +/** + * has_valid_asid() - Determine if an mm already has an ASID. + * @mm: Memory map. + * @type: R4K_HIT or R4K_INDEX, type of cache op. + * + * Determines whether @mm already has an ASID on any of the CPUs which cache ops + * of type @type within an r4k_on_each_cpu() call will affect. If + * r4k_on_each_cpu() does an SMP call to a single VPE in each core, then the + * scope of the operation is confined to sibling CPUs, otherwise all online CPUs + * will need to be checked. + * + * Must be called in non-preemptive context. + * + * Returns: 1 if the CPUs affected by @type cache ops have an ASID for @mm. + * 0 otherwise. + */ +static inline int has_valid_asid(const struct mm_struct *mm, unsigned int type) { -#ifdef CONFIG_MIPS_MT_SMP - int i; + unsigned int i; + const cpumask_t *mask = cpu_present_mask; - for_each_online_cpu(i) + /* cpu_sibling_map[] undeclared when !CONFIG_SMP */ +#ifdef CONFIG_SMP + /* + * If r4k_on_each_cpu does SMP calls, it does them to a single VPE in + * each foreign core, so we only need to worry about siblings. + * Otherwise we need to worry about all present CPUs. + */ + if (r4k_op_needs_ipi(type)) + mask = &cpu_sibling_map[smp_processor_id()]; +#endif + for_each_cpu(i, mask) if (cpu_context(i, mm)) return 1; - return 0; -#else - return cpu_context(smp_processor_id(), mm); -#endif } static void r4k__flush_cache_vmap(void) @@ -490,12 +544,16 @@ static void r4k__flush_cache_vunmap(void) r4k_blast_dcache(); } +/* + * Note: flush_tlb_range() assumes flush_cache_range() sufficiently flushes + * whole caches when vma is executable. + */ static inline void local_r4k_flush_cache_range(void * args) { struct vm_area_struct *vma = args; int exec = vma->vm_flags & VM_EXEC; - if (!(has_valid_asid(vma->vm_mm))) + if (!has_valid_asid(vma->vm_mm, R4K_INDEX)) return; /* @@ -516,14 +574,14 @@ static void r4k_flush_cache_range(struct vm_area_struct *vma, int exec = vma->vm_flags & VM_EXEC; if (cpu_has_dc_aliases || exec) - r4k_on_each_cpu(local_r4k_flush_cache_range, vma); + r4k_on_each_cpu(R4K_INDEX, local_r4k_flush_cache_range, vma); } static inline void local_r4k_flush_cache_mm(void * args) { struct mm_struct *mm = args; - if (!has_valid_asid(mm)) + if (!has_valid_asid(mm, R4K_INDEX)) return; /* @@ -548,7 +606,7 @@ static void r4k_flush_cache_mm(struct mm_struct *mm) if (!cpu_has_dc_aliases) return; - r4k_on_each_cpu(local_r4k_flush_cache_mm, mm); + r4k_on_each_cpu(R4K_INDEX, local_r4k_flush_cache_mm, mm); } struct flush_cache_page_args { @@ -573,10 +631,10 @@ static inline void local_r4k_flush_cache_page(void *args) void *vaddr; /* - * If ownes no valid ASID yet, cannot possibly have gotten + * If owns no valid ASID yet, cannot possibly have gotten * this page into the cache. */ - if (!has_valid_asid(mm)) + if (!has_valid_asid(mm, R4K_HIT)) return; addr &= PAGE_MASK; @@ -643,7 +701,7 @@ static void r4k_flush_cache_page(struct vm_area_struct *vma, args.addr = addr; args.pfn = pfn; - r4k_on_each_cpu(local_r4k_flush_cache_page, &args); + r4k_on_each_cpu(R4K_HIT, local_r4k_flush_cache_page, &args); } static inline void local_r4k_flush_data_cache_page(void * addr) @@ -656,18 +714,23 @@ static void r4k_flush_data_cache_page(unsigned long addr) if (in_atomic()) local_r4k_flush_data_cache_page((void *)addr); else - r4k_on_each_cpu(local_r4k_flush_data_cache_page, (void *) addr); + r4k_on_each_cpu(R4K_HIT, local_r4k_flush_data_cache_page, + (void *) addr); } struct flush_icache_range_args { unsigned long start; unsigned long end; + unsigned int type; }; -static inline void local_r4k_flush_icache_range(unsigned long start, unsigned long end) +static inline void __local_r4k_flush_icache_range(unsigned long start, + unsigned long end, + unsigned int type) { if (!cpu_has_ic_fills_f_dc) { - if (end - start >= dcache_size) { + if (type == R4K_INDEX || + (type & R4K_INDEX && end - start >= dcache_size)) { r4k_blast_dcache(); } else { R4600_HIT_CACHEOP_WAR_IMPL; @@ -675,7 +738,8 @@ static inline void local_r4k_flush_icache_range(unsigned long start, unsigned lo } } - if (end - start > icache_size) + if (type == R4K_INDEX || + (type & R4K_INDEX && end - start > icache_size)) r4k_blast_icache(); else { switch (boot_cpu_type()) { @@ -701,23 +765,52 @@ static inline void local_r4k_flush_icache_range(unsigned long start, unsigned lo #endif } +static inline void local_r4k_flush_icache_range(unsigned long start, + unsigned long end) +{ + __local_r4k_flush_icache_range(start, end, R4K_HIT | R4K_INDEX); +} + static inline void local_r4k_flush_icache_range_ipi(void *args) { struct flush_icache_range_args *fir_args = args; unsigned long start = fir_args->start; unsigned long end = fir_args->end; + unsigned int type = fir_args->type; - local_r4k_flush_icache_range(start, end); + __local_r4k_flush_icache_range(start, end, type); } static void r4k_flush_icache_range(unsigned long start, unsigned long end) { struct flush_icache_range_args args; + unsigned long size, cache_size; args.start = start; args.end = end; + args.type = R4K_HIT | R4K_INDEX; - r4k_on_each_cpu(local_r4k_flush_icache_range_ipi, &args); + /* + * Indexed cache ops require an SMP call. + * Consider if that can or should be avoided. + */ + preempt_disable(); + if (r4k_op_needs_ipi(R4K_INDEX) && !r4k_op_needs_ipi(R4K_HIT)) { + /* + * If address-based cache ops don't require an SMP call, then + * use them exclusively for small flushes. + */ + size = start - end; + cache_size = icache_size; + if (!cpu_has_ic_fills_f_dc) { + size *= 2; + cache_size += dcache_size; + } + if (size <= cache_size) + args.type &= ~R4K_INDEX; + } + r4k_on_each_cpu(args.type, local_r4k_flush_icache_range_ipi, &args); + preempt_enable(); instruction_hazard(); } @@ -744,7 +837,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) * subset property so we have to flush the primary caches * explicitly */ - if (cpu_has_safe_index_cacheops && size >= dcache_size) { + if (size >= dcache_size) { r4k_blast_dcache(); } else { R4600_HIT_CACHEOP_WAR_IMPL; @@ -781,7 +874,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) return; } - if (cpu_has_safe_index_cacheops && size >= dcache_size) { + if (size >= dcache_size) { r4k_blast_dcache(); } else { R4600_HIT_CACHEOP_WAR_IMPL; @@ -794,25 +887,76 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) } #endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */ +struct flush_cache_sigtramp_args { + struct mm_struct *mm; + struct page *page; + unsigned long addr; +}; + /* * While we're protected against bad userland addresses we don't care * very much about what happens in that case. Usually a segmentation * fault will dump the process later on anyway ... */ -static void local_r4k_flush_cache_sigtramp(void * arg) +static void local_r4k_flush_cache_sigtramp(void *args) { + struct flush_cache_sigtramp_args *fcs_args = args; + unsigned long addr = fcs_args->addr; + struct page *page = fcs_args->page; + struct mm_struct *mm = fcs_args->mm; + int map_coherent = 0; + void *vaddr; + unsigned long ic_lsize = cpu_icache_line_size(); unsigned long dc_lsize = cpu_dcache_line_size(); unsigned long sc_lsize = cpu_scache_line_size(); - unsigned long addr = (unsigned long) arg; + + /* + * If owns no valid ASID yet, cannot possibly have gotten + * this page into the cache. + */ + if (!has_valid_asid(mm, R4K_HIT)) + return; + + if (mm == current->active_mm) { + vaddr = NULL; + } else { + /* + * Use kmap_coherent or kmap_atomic to do flushes for + * another ASID than the current one. + */ + map_coherent = (cpu_has_dc_aliases && + page_mapcount(page) && + !Page_dcache_dirty(page)); + if (map_coherent) + vaddr = kmap_coherent(page, addr); + else + vaddr = kmap_atomic(page); + addr = (unsigned long)vaddr + (addr & ~PAGE_MASK); + } R4600_HIT_CACHEOP_WAR_IMPL; - if (dc_lsize) - protected_writeback_dcache_line(addr & ~(dc_lsize - 1)); - if (!cpu_icache_snoops_remote_store && scache_size) - protected_writeback_scache_line(addr & ~(sc_lsize - 1)); + if (!cpu_has_ic_fills_f_dc) { + if (dc_lsize) + vaddr ? flush_dcache_line(addr & ~(dc_lsize - 1)) + : protected_writeback_dcache_line( + addr & ~(dc_lsize - 1)); + if (!cpu_icache_snoops_remote_store && scache_size) + vaddr ? flush_scache_line(addr & ~(sc_lsize - 1)) + : protected_writeback_scache_line( + addr & ~(sc_lsize - 1)); + } if (ic_lsize) - protected_flush_icache_line(addr & ~(ic_lsize - 1)); + vaddr ? flush_icache_line(addr & ~(ic_lsize - 1)) + : protected_flush_icache_line(addr & ~(ic_lsize - 1)); + + if (vaddr) { + if (map_coherent) + kunmap_coherent(); + else + kunmap_atomic(vaddr); + } + if (MIPS4K_ICACHE_REFILL_WAR) { __asm__ __volatile__ ( ".set push\n\t" @@ -837,7 +981,23 @@ static void local_r4k_flush_cache_sigtramp(void * arg) static void r4k_flush_cache_sigtramp(unsigned long addr) { - r4k_on_each_cpu(local_r4k_flush_cache_sigtramp, (void *) addr); + struct flush_cache_sigtramp_args args; + int npages; + + down_read(¤t->mm->mmap_sem); + + npages = get_user_pages_fast(addr, 1, 0, &args.page); + if (npages < 1) + goto out; + + args.mm = current->mm; + args.addr = addr; + + r4k_on_each_cpu(R4K_HIT, local_r4k_flush_cache_sigtramp, &args); + + put_page(args.page); +out: + up_read(¤t->mm->mmap_sem); } static void r4k_flush_icache_all(void) @@ -851,6 +1011,15 @@ struct flush_kernel_vmap_range_args { int size; }; +static inline void local_r4k_flush_kernel_vmap_range_index(void *args) +{ + /* + * Aliases only affect the primary caches so don't bother with + * S-caches or T-caches. + */ + r4k_blast_dcache(); +} + static inline void local_r4k_flush_kernel_vmap_range(void *args) { struct flush_kernel_vmap_range_args *vmra = args; @@ -861,12 +1030,8 @@ static inline void local_r4k_flush_kernel_vmap_range(void *args) * Aliases only affect the primary caches so don't bother with * S-caches or T-caches. */ - if (cpu_has_safe_index_cacheops && size >= dcache_size) - r4k_blast_dcache(); - else { - R4600_HIT_CACHEOP_WAR_IMPL; - blast_dcache_range(vaddr, vaddr + size); - } + R4600_HIT_CACHEOP_WAR_IMPL; + blast_dcache_range(vaddr, vaddr + size); } static void r4k_flush_kernel_vmap_range(unsigned long vaddr, int size) @@ -876,7 +1041,12 @@ static void r4k_flush_kernel_vmap_range(unsigned long vaddr, int size) args.vaddr = (unsigned long) vaddr; args.size = size; - r4k_on_each_cpu(local_r4k_flush_kernel_vmap_range, &args); + if (size >= dcache_size) + r4k_on_each_cpu(R4K_INDEX, + local_r4k_flush_kernel_vmap_range_index, NULL); + else + r4k_on_each_cpu(R4K_HIT, local_r4k_flush_kernel_vmap_range, + &args); } static inline void rm7k_erratum31(void) diff --git a/arch/mips/mm/sc-debugfs.c b/arch/mips/mm/sc-debugfs.c index 5eefe32..01f1154 100644 --- a/arch/mips/mm/sc-debugfs.c +++ b/arch/mips/mm/sc-debugfs.c @@ -73,8 +73,8 @@ static int __init sc_debugfs_init(void) file = debugfs_create_file("prefetch", S_IRUGO | S_IWUSR, dir, NULL, &sc_prefetch_fops); - if (IS_ERR(file)) - return PTR_ERR(file); + if (!file) + return -ENOMEM; return 0; } diff --git a/arch/mips/mm/sc-rm7k.c b/arch/mips/mm/sc-rm7k.c index 9ac1efc..78f900c 100644 --- a/arch/mips/mm/sc-rm7k.c +++ b/arch/mips/mm/sc-rm7k.c @@ -161,7 +161,7 @@ static void rm7k_tc_disable(void) local_irq_save(flags); blast_rm7k_tcache(); clear_c0_config(RM7K_CONF_TE); - local_irq_save(flags); + local_irq_restore(flags); } static void rm7k_sc_disable(void) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index ff49b29..55ce396 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -888,7 +888,7 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, } } if (!did_vmalloc_branch) { - if (uasm_in_compat_space_p(swpd) && !uasm_rel_lo(swpd)) { + if (single_insn_swpd) { uasm_il_b(p, r, label_vmalloc_done); uasm_i_lui(p, ptr, uasm_rel_hi(swpd)); } else { diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c index cec5241..763d3f1 100644 --- a/arch/mips/mm/uasm-mips.c +++ b/arch/mips/mm/uasm-mips.c @@ -65,7 +65,7 @@ static struct insn insn_table[] = { #ifndef CONFIG_CPU_MIPSR6 { insn_cache, M(cache_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, #else - { insn_cache, M6(cache_op, 0, 0, 0, cache6_op), RS | RT | SIMM9 }, + { insn_cache, M6(spec3_op, 0, 0, 0, cache6_op), RS | RT | SIMM9 }, #endif { insn_cfc1, M(cop1_op, cfc_op, 0, 0, 0, 0), RT | RD }, { insn_cfcmsa, M(msa_op, 0, msa_cfc_op, 0, 0, msa_elm_op), RD | RE }, diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c index 3e0282d..a829704 100644 --- a/arch/mips/mm/uasm.c +++ b/arch/mips/mm/uasm.c @@ -378,11 +378,7 @@ UASM_EXPORT_SYMBOL(ISAFUNC(uasm_build_label)); int ISAFUNC(uasm_in_compat_space_p)(long addr) { /* Is this address in 32bit compat space? */ -#ifdef CONFIG_64BIT - return (((addr) & 0xffffffff00000000L) == 0xffffffff00000000L); -#else - return 1; -#endif + return addr == (int)addr; } UASM_EXPORT_SYMBOL(ISAFUNC(uasm_in_compat_space_p)); diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index d1b7bd0..39e7b47 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -1199,7 +1199,7 @@ void bpf_jit_compile(struct bpf_prog *fp) memset(&ctx, 0, sizeof(ctx)); - ctx.offsets = kcalloc(fp->len, sizeof(*ctx.offsets), GFP_KERNEL); + ctx.offsets = kcalloc(fp->len + 1, sizeof(*ctx.offsets), GFP_KERNEL); if (ctx.offsets == NULL) return; diff --git a/arch/mips/pic32/pic32mzda/init.c b/arch/mips/pic32/pic32mzda/init.c index 77ecf32..5159971 100644 --- a/arch/mips/pic32/pic32mzda/init.c +++ b/arch/mips/pic32/pic32mzda/init.c @@ -33,8 +33,8 @@ static ulong get_fdtaddr(void) { ulong ftaddr = 0; - if ((fw_arg0 == -2) && fw_arg1 && !fw_arg2 && !fw_arg3) - return (ulong)fw_arg1; + if (fw_passed_dtb && !fw_arg2 && !fw_arg3) + return (ulong)fw_passed_dtb; if (__dtb_start < __dtb_end) ftaddr = (ulong)__dtb_start; diff --git a/arch/mips/pistachio/init.c b/arch/mips/pistachio/init.c index c50a670..1c91cad7 100644 --- a/arch/mips/pistachio/init.c +++ b/arch/mips/pistachio/init.c @@ -59,29 +59,6 @@ const char *get_system_type(void) return sys_type; } -static void __init plat_setup_iocoherency(void) -{ - /* - * Kernel has been configured with software coherency - * but we might choose to turn it off and use hardware - * coherency instead. - */ - if (mips_cm_numiocu() != 0) { - /* Nothing special needs to be done to enable coherency */ - pr_info("CMP IOCU detected\n"); - hw_coherentio = 1; - if (coherentio == 0) - pr_info("Hardware DMA cache coherency disabled\n"); - else - pr_info("Hardware DMA cache coherency enabled\n"); - } else { - if (coherentio == 1) - pr_info("Hardware DMA cache coherency unsupported, but enabled from command line!\n"); - else - pr_info("Software DMA cache coherency enabled\n"); - } -} - void __init *plat_get_fdt(void) { if (fw_arg0 != -2) @@ -92,8 +69,6 @@ void __init *plat_get_fdt(void) void __init plat_mem_setup(void) { __dt_setup_arch(plat_get_fdt()); - - plat_setup_iocoherency(); } #define DEFAULT_CPC_BASE_ADDR 0x1bde0000 diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c index d40edda..3c7c9bf 100644 --- a/arch/mips/ralink/mt7620.c +++ b/arch/mips/ralink/mt7620.c @@ -175,7 +175,7 @@ static struct rt2880_pmx_func spi_cs1_grp_mt7628[] = { }; static struct rt2880_pmx_func spis_grp_mt7628[] = { - FUNC("pwm", 3, 14, 4), + FUNC("pwm_uart2", 3, 14, 4), FUNC("util", 2, 14, 4), FUNC("gpio", 1, 14, 4), FUNC("spis", 0, 14, 4), |
