diff options
462 files changed, 13367 insertions, 4921 deletions
diff --git a/Documentation/gdb-kernel-debugging.txt b/Documentation/gdb-kernel-debugging.txt index 4ab7d43..7050ce8 100644 --- a/Documentation/gdb-kernel-debugging.txt +++ b/Documentation/gdb-kernel-debugging.txt @@ -139,27 +139,6 @@ Examples of using the Linux-provided gdb helpers start_comm = "swapper/2\000\000\000\000\000\000" } - o Dig into a radix tree data structure, such as the IRQ descriptors: - (gdb) print (struct irq_desc)$lx_radix_tree_lookup(irq_desc_tree, 18) - $6 = { - irq_common_data = { - state_use_accessors = 67584, - handler_data = 0x0 <__vectors_start>, - msi_desc = 0x0 <__vectors_start>, - affinity = {{ - bits = {65535} - }} - }, - irq_data = { - mask = 0, - irq = 18, - hwirq = 27, - common = 0xee803d80, - chip = 0xc0eb0854 <gic_data>, - domain = 0xee808000, - parent_data = 0x0 <__vectors_start>, - chip_data = 0xc0eb0854 <gic_data> - } <... trimmed ...> List of commands and functions ------------------------------ diff --git a/Documentation/x86/intel_mpx.txt b/Documentation/x86/intel_mpx.txt index 1a5a121..85d0549 100644 --- a/Documentation/x86/intel_mpx.txt +++ b/Documentation/x86/intel_mpx.txt @@ -45,7 +45,7 @@ is how we expect the compiler, application and kernel to work together. MPX-instrumented. 3) The kernel detects that the CPU has MPX, allows the new prctl() to succeed, and notes the location of the bounds directory. Userspace is - expected to keep the bounds directory at that locationWe note it + expected to keep the bounds directory at that location. We note it instead of reading it each time because the 'xsave' operation needed to access the bounds directory register is an expensive operation. 4) If the application needs to spill bounds out of the 4 registers, it @@ -167,7 +167,7 @@ If a #BR is generated due to a bounds violation caused by MPX. We need to decode MPX instructions to get violation address and set this address into extended struct siginfo. -The _sigfault feild of struct siginfo is extended as follow: +The _sigfault field of struct siginfo is extended as follow: 87 /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ 88 struct { @@ -240,5 +240,5 @@ them at the same bounds table. This is allowed architecturally. See more information "Intel(R) Architecture Instruction Set Extensions Programming Reference" (9.3.4). -However, if users did this, the kernel might be fooled in to unmaping an +However, if users did this, the kernel might be fooled in to unmapping an in-use bounds table since it does not recognize sharing. diff --git a/Documentation/x86/tlb.txt b/Documentation/x86/tlb.txt index 39d1723..6a0607b 100644 --- a/Documentation/x86/tlb.txt +++ b/Documentation/x86/tlb.txt @@ -5,7 +5,7 @@ memory, it has two choices: from areas other than the one we are trying to flush will be destroyed and must be refilled later, at some cost. 2. Use the invlpg instruction to invalidate a single page at a - time. This could potentialy cost many more instructions, but + time. This could potentially cost many more instructions, but it is a much more precise operation, causing no collateral damage to other TLB entries. @@ -19,7 +19,7 @@ Which method to do depends on a few things: work. 3. The size of the TLB. The larger the TLB, the more collateral damage we do with a full flush. So, the larger the TLB, the - more attrative an individual flush looks. Data and + more attractive an individual flush looks. Data and instructions have separate TLBs, as do different page sizes. 4. The microarchitecture. The TLB has become a multi-level cache on modern CPUs, and the global flushes have become more diff --git a/Documentation/x86/x86_64/machinecheck b/Documentation/x86/x86_64/machinecheck index b1fb302..d0648a7 100644 --- a/Documentation/x86/x86_64/machinecheck +++ b/Documentation/x86/x86_64/machinecheck @@ -36,7 +36,7 @@ between all CPUs. check_interval How often to poll for corrected machine check errors, in seconds - (Note output is hexademical). Default 5 minutes. When the poller + (Note output is hexadecimal). Default 5 minutes. When the poller finds MCEs it triggers an exponential speedup (poll more often) on the polling interval. When the poller stops finding MCEs, it triggers an exponential backoff (poll less often) on the polling diff --git a/MAINTAINERS b/MAINTAINERS index 06e8411..dc3481d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1694,8 +1694,6 @@ S: Maintained F: drivers/edac/altera_edac. ARM/STI ARCHITECTURE -M: Srinivas Kandagatla <srinivas.kandagatla@gmail.com> -M: Maxime Coquelin <maxime.coquelin@st.com> M: Patrice Chotard <patrice.chotard@st.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kernel@stlinux.com @@ -1728,6 +1726,7 @@ F: drivers/ata/ahci_st.c ARM/STM32 ARCHITECTURE M: Maxime Coquelin <mcoquelin.stm32@gmail.com> +M: Alexandre Torgue <alexandre.torgue@st.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/mcoquelin/stm32.git @@ -4486,7 +4485,7 @@ S: Orphan F: fs/efs/ EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER -M: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com> +M: Douglas Miller <dougmill@linux.vnet.ibm.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/ibm/ehea/ @@ -7502,6 +7501,7 @@ Q: http://patchwork.ozlabs.org/project/linux-mtd/list/ T: git git://git.infradead.org/linux-mtd.git T: git git://git.infradead.org/l2-mtd.git S: Maintained +F: Documentation/devicetree/bindings/mtd/ F: drivers/mtd/ F: include/linux/mtd/ F: include/uapi/mtd/ @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Psychotic Stoned Sheep # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi index 8450944..22f7a13 100644 --- a/arch/arm/boot/dts/armada-385-linksys.dtsi +++ b/arch/arm/boot/dts/armada-385-linksys.dtsi @@ -58,8 +58,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0xf1100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0xf1110000 0x10000>; + MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>; internal-regs { diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index a03e56f..ca58eb2 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -65,8 +65,9 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>, <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>, + <&dram_gates 26>; status = "disabled"; }; @@ -74,8 +75,9 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_fe0-de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>, <&ahb_gates 46>, + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>, + <&ahb_gates 46>, <&dram_gates 25>, <&dram_gates 26>; status = "disabled"; }; @@ -84,9 +86,9 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_fe0-de_be0-lcd0"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>, - <&ahb_gates 46>, <&dram_gates 25>, - <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 44>, <&ahb_gates 46>, + <&dram_gates 25>, <&dram_gates 26>; status = "disabled"; }; @@ -94,8 +96,9 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_fe0-de_be0-lcd0-tve0"; - clocks = <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>, - <&ahb_gates 44>, <&ahb_gates 46>, + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>, + <&ahb_gates 36>, <&ahb_gates 44>, + <&ahb_gates 46>, <&dram_gates 5>, <&dram_gates 25>, <&dram_gates 26>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi index bddd0de..367f330 100644 --- a/arch/arm/boot/dts/sun5i-a10s.dtsi +++ b/arch/arm/boot/dts/sun5i-a10s.dtsi @@ -65,8 +65,8 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>; status = "disabled"; }; @@ -74,7 +74,8 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 44>; status = "disabled"; }; @@ -82,8 +83,8 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-tve0"; - clocks = <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>, - <&ahb_gates 44>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>, + <&ahb_gates 36>, <&ahb_gates 44>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/sun5i-r8-chip.dts b/arch/arm/boot/dts/sun5i-r8-chip.dts index a8d8b45..f694482 100644 --- a/arch/arm/boot/dts/sun5i-r8-chip.dts +++ b/arch/arm/boot/dts/sun5i-r8-chip.dts @@ -52,7 +52,7 @@ / { model = "NextThing C.H.I.P."; - compatible = "nextthing,chip", "allwinner,sun5i-r8"; + compatible = "nextthing,chip", "allwinner,sun5i-r8", "allwinner,sun5i-a13"; aliases { i2c0 = &i2c0; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index febdf4c..2c34bbb 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -67,8 +67,9 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>, <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>, + <&dram_gates 26>; status = "disabled"; }; @@ -76,8 +77,8 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>, - <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 44>, <&dram_gates 26>; status = "disabled"; }; @@ -85,7 +86,7 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-tve0"; - clocks = <&pll5 1>, + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>, <&ahb_gates 44>, <&dram_gates 5>, <&dram_gates 26>; status = "disabled"; @@ -231,6 +232,7 @@ pll3x2: pll3x2_clk { #clock-cells = <0>; compatible = "fixed-factor-clock"; + clocks = <&pll3>; clock-div = <1>; clock-mult = <2>; clock-output-names = "pll3-2x"; @@ -272,6 +274,7 @@ pll7x2: pll7x2_clk { #clock-cells = <0>; compatible = "fixed-factor-clock"; + clocks = <&pll7>; clock-div = <1>; clock-mult = <2>; clock-output-names = "pll7-2x"; diff --git a/arch/arm/boot/dts/tegra30-beaver.dts b/arch/arm/boot/dts/tegra30-beaver.dts index 1eca3b2..b6da15d 100644 --- a/arch/arm/boot/dts/tegra30-beaver.dts +++ b/arch/arm/boot/dts/tegra30-beaver.dts @@ -1843,7 +1843,7 @@ ldo5_reg: ldo5 { regulator-name = "vddio_sdmmc,avdd_vdac"; - regulator-min-microvolt = <3300000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-always-on; }; @@ -1914,6 +1914,7 @@ sdhci@78000000 { status = "okay"; + vqmmc-supply = <&ldo5_reg>; cd-gpios = <&gpio TEGRA_GPIO(I, 5) GPIO_ACTIVE_LOW>; wp-gpios = <&gpio TEGRA_GPIO(T, 3) GPIO_ACTIVE_HIGH>; power-gpios = <&gpio TEGRA_GPIO(D, 7) GPIO_ACTIVE_HIGH>; diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile index ecf9e0c..e53c6cf 100644 --- a/arch/arm/mach-mvebu/Makefile +++ b/arch/arm/mach-mvebu/Makefile @@ -7,9 +7,15 @@ CFLAGS_pmsu.o := -march=armv7-a obj-$(CONFIG_MACH_MVEBU_ANY) += system-controller.o mvebu-soc-id.o ifeq ($(CONFIG_MACH_MVEBU_V7),y) -obj-y += cpu-reset.o board-v7.o coherency.o coherency_ll.o pmsu.o pmsu_ll.o pm.o pm-board.o +obj-y += cpu-reset.o board-v7.o coherency.o coherency_ll.o pmsu.o pmsu_ll.o + +obj-$(CONFIG_PM) += pm.o pm-board.o obj-$(CONFIG_SMP) += platsmp.o headsmp.o platsmp-a9.o headsmp-a9.o endif obj-$(CONFIG_MACH_DOVE) += dove.o -obj-$(CONFIG_MACH_KIRKWOOD) += kirkwood.o kirkwood-pm.o + +ifeq ($(CONFIG_MACH_KIRKWOOD),y) +obj-y += kirkwood.o +obj-$(CONFIG_PM) += kirkwood-pm.o +endif diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index 7e989d6..e80f0dd 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -162,22 +162,16 @@ exit: } /* - * This ioremap hook is used on Armada 375/38x to ensure that PCIe - * memory areas are mapped as MT_UNCACHED instead of MT_DEVICE. This - * is needed as a workaround for a deadlock issue between the PCIe - * interface and the cache controller. + * This ioremap hook is used on Armada 375/38x to ensure that all MMIO + * areas are mapped as MT_UNCACHED instead of MT_DEVICE. This is + * needed for the HW I/O coherency mechanism to work properly without + * deadlock. */ static void __iomem * -armada_pcie_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, - unsigned int mtype, void *caller) +armada_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, + unsigned int mtype, void *caller) { - struct resource pcie_mem; - - mvebu_mbus_get_pcie_mem_aperture(&pcie_mem); - - if (pcie_mem.start <= phys_addr && (phys_addr + size) <= pcie_mem.end) - mtype = MT_UNCACHED; - + mtype = MT_UNCACHED; return __arm_ioremap_caller(phys_addr, size, mtype, caller); } @@ -186,7 +180,8 @@ static void __init armada_375_380_coherency_init(struct device_node *np) struct device_node *cache_dn; coherency_cpu_base = of_iomap(np, 0); - arch_ioremap_caller = armada_pcie_wa_ioremap_caller; + arch_ioremap_caller = armada_wa_ioremap_caller; + pci_ioremap_set_mem_type(MT_UNCACHED); /* * We should switch the PL310 to I/O coherency mode only if diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 87e1985..9d9fd4b 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -80,12 +80,14 @@ #define APM_CPU_PART_POTENZA 0x000 #define CAVIUM_CPU_PART_THUNDERX 0x0A1 +#define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2 #define BRCM_CPU_PART_VULCAN 0x516 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) +#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index a307eb6..7f94755 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -117,6 +117,8 @@ struct pt_regs { }; u64 orig_x0; u64 syscallno; + u64 orig_addr_limit; + u64 unused; // maintain 16 byte alignment }; #define arch_has_single_step() (1) diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index f8e5d47..2f4ba77 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -60,6 +60,7 @@ int main(void) DEFINE(S_PC, offsetof(struct pt_regs, pc)); DEFINE(S_ORIG_X0, offsetof(struct pt_regs, orig_x0)); DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); + DEFINE(S_ORIG_ADDR_LIMIT, offsetof(struct pt_regs, orig_addr_limit)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index d427894..af716b6 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -98,6 +98,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = { MIDR_RANGE(MIDR_THUNDERX, 0x00, (1 << MIDR_VARIANT_SHIFT) | 1), }, + { + /* Cavium ThunderX, T81 pass 1.0 */ + .desc = "Cavium erratum 27456", + .capability = ARM64_WORKAROUND_CAVIUM_27456, + MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00), + }, #endif { } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 12e8d2b..6c3b734 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -28,6 +28,7 @@ #include <asm/errno.h> #include <asm/esr.h> #include <asm/irq.h> +#include <asm/memory.h> #include <asm/thread_info.h> #include <asm/unistd.h> @@ -97,7 +98,14 @@ mov x29, xzr // fp pointed to user-space .else add x21, sp, #S_FRAME_SIZE - .endif + get_thread_info tsk + /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */ + ldr x20, [tsk, #TI_ADDR_LIMIT] + str x20, [sp, #S_ORIG_ADDR_LIMIT] + mov x20, #TASK_SIZE_64 + str x20, [tsk, #TI_ADDR_LIMIT] + ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO) + .endif /* \el == 0 */ mrs x22, elr_el1 mrs x23, spsr_el1 stp lr, x21, [sp, #S_LR] @@ -128,6 +136,14 @@ .endm .macro kernel_exit, el + .if \el != 0 + /* Restore the task's original addr_limit. */ + ldr x20, [sp, #S_ORIG_ADDR_LIMIT] + str x20, [tsk, #TI_ADDR_LIMIT] + + /* No need to restore UAO, it will be restored from SPSR_EL1 */ + .endif + ldp x21, x22, [sp, #S_PC] // load ELR, SPSR .if \el == 0 ct_user_enter @@ -406,7 +422,6 @@ el1_irq: bl trace_hardirqs_off #endif - get_thread_info tsk irq_handler #ifdef CONFIG_PREEMPT diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 013e2cb..b1166d1 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -280,7 +280,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, } if (permission_fault(esr) && (addr < USER_DS)) { - if (get_fs() == KERNEL_DS) + /* regs->orig_addr_limit may be 0 if we entered from EL0 */ + if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); if (!search_exception_tables(regs->pc)) diff --git a/arch/m32r/boot/compressed/m32r_sio.c b/arch/m32r/boot/compressed/m32r_sio.c index 01d877c..cf3023d 100644 --- a/arch/m32r/boot/compressed/m32r_sio.c +++ b/arch/m32r/boot/compressed/m32r_sio.c @@ -8,12 +8,13 @@ #include <asm/processor.h> -static void putc(char c); +static void m32r_putc(char c); static int puts(const char *s) { char c; - while ((c = *s++)) putc(c); + while ((c = *s++)) + m32r_putc(c); return 0; } @@ -41,7 +42,7 @@ static int puts(const char *s) #define BOOT_SIO0TXB PLD_ESIO0TXB #endif -static void putc(char c) +static void m32r_putc(char c) { while ((*BOOT_SIO0STS & 0x3) != 0x3) cpu_relax(); @@ -61,7 +62,7 @@ static void putc(char c) #define SIO0TXB (volatile unsigned short *)(0x00efd000 + 30) #endif -static void putc(char c) +static void m32r_putc(char c) { while ((*SIO0STS & 0x1) == 0) cpu_relax(); diff --git a/arch/m68k/coldfire/head.S b/arch/m68k/coldfire/head.S index fa31be2..73d92ea 100644 --- a/arch/m68k/coldfire/head.S +++ b/arch/m68k/coldfire/head.S @@ -288,7 +288,7 @@ _clear_bss: #endif /* - * Assember start up done, start code proper. + * Assembler start up done, start code proper. */ jsr start_kernel /* start Linux kernel */ diff --git a/arch/m68k/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c index c525e4c..9abb1a4 100644 --- a/arch/m68k/coldfire/m5272.c +++ b/arch/m68k/coldfire/m5272.c @@ -111,7 +111,7 @@ void __init config_BSP(char *commandp, int size) /***************************************************************************/ /* - * Some 5272 based boards have the FEC ethernet diectly connected to + * Some 5272 based boards have the FEC ethernet directly connected to * an ethernet switch. In this case we need to use the fixed phy type, * and we need to declare it early in boot. */ diff --git a/arch/m68k/coldfire/pci.c b/arch/m68k/coldfire/pci.c index 821de92..6a640be 100644 --- a/arch/m68k/coldfire/pci.c +++ b/arch/m68k/coldfire/pci.c @@ -42,7 +42,7 @@ static unsigned long iospace; /* * We need to be carefull probing on bus 0 (directly connected to host - * bridge). We should only acccess the well defined possible devices in + * bridge). We should only access the well defined possible devices in * use, ignore aliases and the like. */ static unsigned char mcf_host_slot2sid[32] = { diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 3ee6976..8f5b6f7 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -359,6 +360,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -553,7 +555,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index e96787f..31bded9 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -341,6 +342,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -512,7 +514,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 083fe6b..0d7739e 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -350,6 +351,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -533,7 +535,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 475130c..2cbb5c4 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -340,6 +341,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -504,7 +506,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index 4339658..96102a4 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -341,6 +342,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -514,7 +516,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 831cc8c..97d88f7 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -357,6 +358,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -536,7 +538,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 6377afe..be25ef2 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -390,6 +391,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -616,7 +618,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 4304b3d..a008344 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -339,6 +340,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -504,7 +506,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 074bda4..6735a25 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -340,6 +341,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -504,7 +506,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 07b9fa8..780c6e9 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -346,6 +347,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -527,7 +529,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 36e6fae..44693cf 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -337,6 +338,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -506,7 +508,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 903acf9..ef0071d 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -337,6 +338,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -506,7 +508,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/ifpsp060/src/fpsp.S b/arch/m68k/ifpsp060/src/fpsp.S index 78cb60f..9bbffeb 100644 --- a/arch/m68k/ifpsp060/src/fpsp.S +++ b/arch/m68k/ifpsp060/src/fpsp.S @@ -10191,7 +10191,7 @@ xdnrm_con: xdnrm_sd: mov.l %a1,-(%sp) tst.b LOCAL_EX(%a0) # is denorm pos or neg? - smi.b %d1 # set d0 accodingly + smi.b %d1 # set d0 accordingly bsr.l unf_sub mov.l (%sp)+,%a1 xdnrm_exit: @@ -10990,7 +10990,7 @@ src_qnan_m: # routines where an instruction is selected by an index into # a large jump table corresponding to a given instruction which # has been decoded. Flow continues here where we now decode -# further accoding to the source operand type. +# further according to the source operand type. # global fsinh @@ -23196,14 +23196,14 @@ m_sign: # # 1. Branch on the sign of the adjusted exponent. # 2p.(positive exp) -# 2. Check M16 and the digits in lwords 2 and 3 in decending order. +# 2. Check M16 and the digits in lwords 2 and 3 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Subtract the count from the exp. # 5. Check if the exp has crossed zero in #3 above; make the exp abs # and set SE. # 6. Multiply the mantissa by 10**count. # 2n.(negative exp) -# 2. Check the digits in lwords 3 and 2 in decending order. +# 2. Check the digits in lwords 3 and 2 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Add the count to the exp. # 5. Check if the exp has crossed zero in #3 above; clear SE. diff --git a/arch/m68k/ifpsp060/src/pfpsp.S b/arch/m68k/ifpsp060/src/pfpsp.S index 4aedef9..3535e6c 100644 --- a/arch/m68k/ifpsp060/src/pfpsp.S +++ b/arch/m68k/ifpsp060/src/pfpsp.S @@ -13156,14 +13156,14 @@ m_sign: # # 1. Branch on the sign of the adjusted exponent. # 2p.(positive exp) -# 2. Check M16 and the digits in lwords 2 and 3 in decending order. +# 2. Check M16 and the digits in lwords 2 and 3 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Subtract the count from the exp. # 5. Check if the exp has crossed zero in #3 above; make the exp abs # and set SE. # 6. Multiply the mantissa by 10**count. # 2n.(negative exp) -# 2. Check the digits in lwords 3 and 2 in decending order. +# 2. Check the digits in lwords 3 and 2 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Add the count to the exp. # 5. Check if the exp has crossed zero in #3 above; clear SE. diff --git a/arch/m68k/include/asm/dma.h b/arch/m68k/include/asm/dma.h index 429fe26..208b4da 100644 --- a/arch/m68k/include/asm/dma.h +++ b/arch/m68k/include/asm/dma.h @@ -18,7 +18,7 @@ * AUG/22/2000 : added support for 32-bit Dual-Address-Mode (K) 2000 * Oliver Kamphenkel (O.Kamphenkel@tu-bs.de) * - * AUG/25/2000 : addad support for 8, 16 and 32-bit Single-Address-Mode (K)2000 + * AUG/25/2000 : added support for 8, 16 and 32-bit Single-Address-Mode (K)2000 * Oliver Kamphenkel (O.Kamphenkel@tu-bs.de) * * APR/18/2002 : added proper support for MCF5272 DMA controller. diff --git a/arch/m68k/include/asm/m525xsim.h b/arch/m68k/include/asm/m525xsim.h index f186459..699f20c 100644 --- a/arch/m68k/include/asm/m525xsim.h +++ b/arch/m68k/include/asm/m525xsim.h @@ -123,10 +123,10 @@ /* * I2C module. */ -#define MCFI2C_BASE0 (MCF_MBAR + 0x280) /* Base addreess I2C0 */ +#define MCFI2C_BASE0 (MCF_MBAR + 0x280) /* Base address I2C0 */ #define MCFI2C_SIZE0 0x20 /* Register set size */ -#define MCFI2C_BASE1 (MCF_MBAR2 + 0x440) /* Base addreess I2C1 */ +#define MCFI2C_BASE1 (MCF_MBAR2 + 0x440) /* Base address I2C1 */ #define MCFI2C_SIZE1 0x20 /* Register set size */ /* diff --git a/arch/m68k/include/asm/mcfmmu.h b/arch/m68k/include/asm/mcfmmu.h index 26cc3d5..8824236 100644 --- a/arch/m68k/include/asm/mcfmmu.h +++ b/arch/m68k/include/asm/mcfmmu.h @@ -38,7 +38,7 @@ /* * MMU Operation register. */ -#define MMUOR_UAA 0x00000001 /* Update allocatiom address */ +#define MMUOR_UAA 0x00000001 /* Update allocation address */ #define MMUOR_ACC 0x00000002 /* TLB access */ #define MMUOR_RD 0x00000004 /* TLB access read */ #define MMUOR_WR 0x00000000 /* TLB access write */ diff --git a/arch/m68k/include/asm/q40_master.h b/arch/m68k/include/asm/q40_master.h index fc5b362..c48d21b 100644 --- a/arch/m68k/include/asm/q40_master.h +++ b/arch/m68k/include/asm/q40_master.h @@ -1,6 +1,6 @@ /* * Q40 master Chip Control - * RTC stuff merged for compactnes.. + * RTC stuff merged for compactness. */ #ifndef _Q40_MASTER_H diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c index 4d2adfb..7990b6f 100644 --- a/arch/m68k/mac/iop.c +++ b/arch/m68k/mac/iop.c @@ -60,7 +60,7 @@ * * The host talks to the IOPs using a rather simple message-passing scheme via * a shared memory area in the IOP RAM. Each IOP has seven "channels"; each - * channel is conneced to a specific software driver on the IOP. For example + * channel is connected to a specific software driver on the IOP. For example * on the SCC IOP there is one channel for each serial port. Each channel has * an incoming and and outgoing message queue with a depth of one. * diff --git a/arch/m68k/math-emu/fp_decode.h b/arch/m68k/math-emu/fp_decode.h index 759679d..6d1e760 100644 --- a/arch/m68k/math-emu/fp_decode.h +++ b/arch/m68k/math-emu/fp_decode.h @@ -130,7 +130,7 @@ do_fscc=0 bfextu %d2{#13,#3},%d0 .endm -| decode the 8bit diplacement from the brief extension word +| decode the 8bit displacement from the brief extension word .macro fp_decode_disp8 move.b %d2,%d0 ext.w %d0 diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index f538167..7d44e88 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -633,7 +633,7 @@ static inline struct page *pmd_page(pmd_t pmd) static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmd_val(pmd) = (pmd_val(pmd) & _PAGE_CHG_MASK) | + pmd_val(pmd) = (pmd_val(pmd) & (_PAGE_CHG_MASK | _PAGE_HUGE)) | (pgprot_val(newprot) & ~_PAGE_CHG_MASK); return pmd; } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 33787ee..91eac39 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -263,7 +263,7 @@ static bool check_hw_exists(void) msr_fail: pr_cont("Broken PMU hardware detected, using software events only.\n"); - pr_info("%sFailed to access perfctr msr (MSR %x is %Lx)\n", + printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n", boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR, reg, val_new); @@ -2319,7 +2319,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct stack_frame frame; - const void __user *fp; + const unsigned long __user *fp; if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ @@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) return; - fp = (void __user *)regs->bp; + fp = (unsigned long __user *)regs->bp; perf_callchain_store(entry, regs->ip); @@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs pagefault_disable(); while (entry->nr < entry->max_stack) { unsigned long bytes; + frame.next_frame = NULL; frame.return_address = 0; - if (!access_ok(VERIFY_READ, fp, 16)) + if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2)) break; - bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp)); if (bytes != 0) break; - bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); + bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp)); if (bytes != 0) break; diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile index 3660b2c..06c2baa 100644 --- a/arch/x86/events/intel/Makefile +++ b/arch/x86/events/intel/Makefile @@ -1,8 +1,8 @@ obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o -obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl.o -intel-rapl-objs := rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl-perf.o +intel-rapl-perf-objs := rapl.o obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel-uncore.o intel-uncore-objs := uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE) += intel-cstate.o diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7c66695..9b4f9d3 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -115,6 +115,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -139,6 +143,10 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -182,6 +190,16 @@ struct event_constraint intel_skl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ + + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc6, 0xf), /* FRONTEND_RETIRED.* */ + EVENT_CONSTRAINT_END }; @@ -250,6 +268,10 @@ static struct event_constraint intel_hsw_event_constraints[] = { /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -264,6 +286,13 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4a41348..c64b1e9 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -301,10 +301,6 @@ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ -#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ - - #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional @@ -312,5 +308,7 @@ */ #define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index a147e67..e991d5c 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -71,8 +71,8 @@ int amd_cache_northbridges(void) while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL) i++; - if (i == 0) - return 0; + if (!i) + return -ENODEV; nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index bca14c8..57b7137 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -11,7 +11,11 @@ #include <linux/pci.h> #include <linux/acpi.h> +#include <linux/delay.h> +#include <linux/dmi.h> #include <linux/pci_ids.h> +#include <linux/bcma/bcma.h> +#include <linux/bcma/bcma_regs.h> #include <drm/i915_drm.h> #include <asm/pci-direct.h> #include <asm/dma.h> @@ -21,6 +25,9 @@ #include <asm/iommu.h> #include <asm/gart.h> #include <asm/irq_remapping.h> +#include <asm/early_ioremap.h> + +#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg) static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -76,6 +83,13 @@ static void __init nvidia_bugs(int num, int slot, int func) #ifdef CONFIG_ACPI #ifdef CONFIG_X86_IO_APIC /* + * Only applies to Nvidia root ports (bus 0) and not to + * Nvidia graphics cards with PCI ports on secondary buses. + */ + if (num) + return; + + /* * All timer overrides on Nvidia are * wrong unless HPET is enabled. * Unfortunately that's not true on many Asus boards. @@ -590,6 +604,61 @@ static void __init force_disable_hpet(int num, int slot, int func) #endif } +#define BCM4331_MMIO_SIZE 16384 +#define BCM4331_PM_CAP 0x40 +#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg) +#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg) + +static void __init apple_airport_reset(int bus, int slot, int func) +{ + void __iomem *mmio; + u16 pmcsr; + u64 addr; + int i; + + if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc.")) + return; + + /* Card may have been put into PCI_D3hot by grub quirk */ + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + pmcsr &= ~PCI_PM_CTRL_STATE_MASK; + write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr); + mdelay(10); + + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + dev_err("Cannot power up Apple AirPort card\n"); + return; + } + } + + addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0); + addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32; + addr &= PCI_BASE_ADDRESS_MEM_MASK; + + mmio = early_ioremap(addr, BCM4331_MMIO_SIZE); + if (!mmio) { + dev_err("Cannot iomap Apple AirPort card\n"); + return; + } + + pr_info("Resetting Apple AirPort card (left enabled by EFI)\n"); + + for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++) + udelay(10); + + bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET); + bcma_aread32(BCMA_RESET_CTL); + udelay(1); + + bcma_awrite32(BCMA_RESET_CTL, 0); + bcma_aread32(BCMA_RESET_CTL); + udelay(10); + + early_iounmap(mmio, BCM4331_MMIO_SIZE); +} #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 @@ -603,12 +672,6 @@ struct chipset { void (*f)(int num, int slot, int func); }; -/* - * Only works for devices on the root bus. If you add any devices - * not on bus 0 readd another loop level in early_quirks(). But - * be careful because at least the Nvidia quirk here relies on - * only matching on bus 0. - */ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs }, @@ -638,9 +701,13 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_BROADCOM, 0x4331, + PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} }; +static void __init early_pci_scan_bus(int bus); + /** * check_dev_quirk - apply early quirks to a given PCI device * @num: bus number @@ -649,7 +716,7 @@ static struct chipset early_qrk[] __initdata = { * * Check the vendor & device ID against the early quirks table. * - * If the device is single function, let early_quirks() know so we don't + * If the device is single function, let early_pci_scan_bus() know so we don't * poke at this device again. */ static int __init check_dev_quirk(int num, int slot, int func) @@ -658,6 +725,7 @@ static int __init check_dev_quirk(int num, int slot, int func) u16 vendor; u16 device; u8 type; + u8 sec; int i; class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE); @@ -685,25 +753,36 @@ static int __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); + + if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) { + sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); + if (sec > num) + early_pci_scan_bus(sec); + } + if (!(type & 0x80)) return -1; return 0; } -void __init early_quirks(void) +static void __init early_pci_scan_bus(int bus) { int slot, func; - if (!early_pci_allowed()) - return; - /* Poor man's PCI discovery */ - /* Only scan the root bus */ for (slot = 0; slot < 32; slot++) for (func = 0; func < 8; func++) { /* Only probe function 0 on single fn devices */ - if (check_dev_quirk(0, slot, func)) + if (check_dev_quirk(bus, slot, func)) break; } } + +void __init early_quirks(void) +{ + if (!early_pci_allowed()) + return; + + early_pci_scan_bus(0); +} diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1b1110f..0493c17 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -54,8 +54,8 @@ static int kasan_die_handler(struct notifier_block *self, void *data) { if (val == DIE_GPF) { - pr_emerg("CONFIG_KASAN_INLINE enabled"); - pr_emerg("GPF could be caused by NULL-ptr deref or user memory access"); + pr_emerg("CONFIG_KASAN_INLINE enabled\n"); + pr_emerg("GPF could be caused by NULL-ptr deref or user memory access\n"); } return NOTIFY_OK; } diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b2a4e2a..3cd6983 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -396,6 +396,7 @@ int __init pci_acpi_init(void) return -ENODEV; printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n"); + acpi_irq_penalty_init(); pcibios_enable_irq = acpi_pci_irq_enable; pcibios_disable_irq = acpi_pci_irq_disable; x86_init.pci.init_irq = x86_init_noop; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 009947d..f2b5e6a 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -19,6 +19,7 @@ #include <asm/mtrr.h> #include <asm/sections.h> #include <asm/suspend.h> +#include <asm/tlbflush.h> /* Defined in hibernate_asm_64.S */ extern asmlinkage __visible int restore_image(void); @@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void); * kernel's text (this value is passed in the image header). */ unsigned long restore_jump_address __visible; +unsigned long jump_address_phys; /* * Value of the cr3 register from before the hibernation (this value is passed @@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible; pgd_t *temp_level4_pgt __visible; -void *relocated_restore_code __visible; +unsigned long relocated_restore_code __visible; + +static int set_up_temporary_text_mapping(void) +{ + pmd_t *pmd; + pud_t *pud; + + /* + * The new mapping only has to cover the page containing the image + * kernel's entry point (jump_address_phys), because the switch over to + * it is carried out by relocated code running from a page allocated + * specifically for this purpose and covered by the identity mapping, so + * the temporary kernel text mapping is only needed for the final jump. + * Moreover, in that mapping the virtual address of the image kernel's + * entry point must be the same as its virtual address in the image + * kernel (restore_jump_address), so the image kernel's + * restore_registers() code doesn't find itself in a different area of + * the virtual address space after switching over to the original page + * tables used by the image kernel. + */ + pud = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!pud) + return -ENOMEM; + + pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!pmd) + return -ENOMEM; + + set_pmd(pmd + pmd_index(restore_jump_address), + __pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC)); + set_pud(pud + pud_index(restore_jump_address), + __pud(__pa(pmd) | _KERNPG_TABLE)); + set_pgd(temp_level4_pgt + pgd_index(restore_jump_address), + __pgd(__pa(pud) | _KERNPG_TABLE)); + + return 0; +} static void *alloc_pgt_page(void *context) { @@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void) if (!temp_level4_pgt) return -ENOMEM; - /* It is safe to reuse the original kernel mapping */ - set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map), - init_level4_pgt[pgd_index(__START_KERNEL_map)]); + /* Prepare a temporary mapping for the kernel text */ + result = set_up_temporary_text_mapping(); + if (result) + return result; /* Set up the direct mapping from scratch */ for (i = 0; i < nr_pfn_mapped; i++) { @@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void) return 0; } +static int relocate_restore_code(void) +{ + pgd_t *pgd; + pud_t *pud; + + relocated_restore_code = get_safe_page(GFP_ATOMIC); + if (!relocated_restore_code) + return -ENOMEM; + + memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE); + + /* Make the page containing the relocated code executable */ + pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); + pud = pud_offset(pgd, relocated_restore_code); + if (pud_large(*pud)) { + set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); + } else { + pmd_t *pmd = pmd_offset(pud, relocated_restore_code); + + if (pmd_large(*pmd)) { + set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); + } else { + pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code); + + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); + } + } + __flush_tlb_all(); + + return 0; +} + int swsusp_arch_resume(void) { int error; /* We have got enough memory and from now on we cannot recover */ - if ((error = set_up_temporary_mappings())) + error = set_up_temporary_mappings(); + if (error) return error; - relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC); - if (!relocated_restore_code) - return -ENOMEM; - memcpy(relocated_restore_code, &core_restore_code, - &restore_registers - &core_restore_code); + error = relocate_restore_code(); + if (error) + return error; restore_image(); return 0; @@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn) struct restore_data_record { unsigned long jump_address; + unsigned long jump_address_phys; unsigned long cr3; unsigned long magic; }; -#define RESTORE_MAGIC 0x0123456789ABCDEFUL +#define RESTORE_MAGIC 0x123456789ABCDEF0UL /** * arch_hibernation_header_save - populate the architecture specific part @@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) if (max_size < sizeof(struct restore_data_record)) return -EOVERFLOW; - rdr->jump_address = restore_jump_address; + rdr->jump_address = (unsigned long)&restore_registers; + rdr->jump_address_phys = __pa_symbol(&restore_registers); rdr->cr3 = restore_cr3; rdr->magic = RESTORE_MAGIC; return 0; @@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr) struct restore_data_record *rdr = addr; restore_jump_address = rdr->jump_address; + jump_address_phys = rdr->jump_address_phys; restore_cr3 = rdr->cr3; return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 4400a43..3177c2b 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -44,9 +44,6 @@ ENTRY(swsusp_arch_suspend) pushfq popq pt_regs_flags(%rax) - /* save the address of restore_registers */ - movq $restore_registers, %rax - movq %rax, restore_jump_address(%rip) /* save cr3 */ movq %cr3, %rax movq %rax, restore_cr3(%rip) @@ -57,31 +54,34 @@ ENTRY(swsusp_arch_suspend) ENDPROC(swsusp_arch_suspend) ENTRY(restore_image) - /* switch to temporary page tables */ - movq $__PAGE_OFFSET, %rdx - movq temp_level4_pgt(%rip), %rax - subq %rdx, %rax - movq %rax, %cr3 - /* Flush TLB */ - movq mmu_cr4_features(%rip), %rax - movq %rax, %rdx - andq $~(X86_CR4_PGE), %rdx - movq %rdx, %cr4; # turn off PGE - movq %cr3, %rcx; # flush TLB - movq %rcx, %cr3; - movq %rax, %cr4; # turn PGE back on - /* prepare to jump to the image kernel */ - movq restore_jump_address(%rip), %rax - movq restore_cr3(%rip), %rbx + movq restore_jump_address(%rip), %r8 + movq restore_cr3(%rip), %r9 + + /* prepare to switch to temporary page tables */ + movq temp_level4_pgt(%rip), %rax + movq mmu_cr4_features(%rip), %rbx /* prepare to copy image data to their original locations */ movq restore_pblist(%rip), %rdx + + /* jump to relocated restore code */ movq relocated_restore_code(%rip), %rcx jmpq *%rcx /* code below has been relocated to a safe page */ ENTRY(core_restore_code) + /* switch to temporary page tables */ + movq $__PAGE_OFFSET, %rcx + subq %rcx, %rax + movq %rax, %cr3 + /* flush TLB */ + movq %rbx, %rcx + andq $~(X86_CR4_PGE), %rcx + movq %rcx, %cr4; # turn off PGE + movq %cr3, %rcx; # flush TLB + movq %rcx, %cr3; + movq %rbx, %cr4; # turn PGE back on .Lloop: testq %rdx, %rdx jz .Ldone @@ -96,24 +96,17 @@ ENTRY(core_restore_code) /* progress to the next pbe */ movq pbe_next(%rdx), %rdx jmp .Lloop + .Ldone: /* jump to the restore_registers address from the image header */ - jmpq *%rax - /* - * NOTE: This assumes that the boot kernel's text mapping covers the - * image kernel's page containing restore_registers and the address of - * this page is the same as in the image kernel's text mapping (it - * should always be true, because the text mapping is linear, starting - * from 0, and is supposed to cover the entire kernel text for every - * kernel). - * - * code below belongs to the image kernel - */ + jmpq *%r8 + /* code below belongs to the image kernel */ + .align PAGE_SIZE ENTRY(restore_registers) FRAME_BEGIN /* go back to the original page tables */ - movq %rbx, %cr3 + movq %r9, %cr3 /* Flush TLB, including "global" things (vmalloc) */ movq mmu_cr4_features(%rip), %rax diff --git a/block/ioprio.c b/block/ioprio.c index cc7800e..01b8116 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -150,8 +150,10 @@ static int get_task_ioprio(struct task_struct *p) if (ret) goto out; ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM); + task_lock(p); if (p->io_context) ret = p->io_context->ioprio; + task_unlock(p); out: return ret; } diff --git a/crypto/asymmetric_keys/mscode_parser.c b/crypto/asymmetric_keys/mscode_parser.c index 6a76d5c..9492e1c 100644 --- a/crypto/asymmetric_keys/mscode_parser.c +++ b/crypto/asymmetric_keys/mscode_parser.c @@ -124,5 +124,10 @@ int mscode_note_digest(void *context, size_t hdrlen, struct pefile_context *ctx = context; ctx->digest = kmemdup(value, vlen, GFP_KERNEL); - return ctx->digest ? 0 : -ENOMEM; + if (!ctx->digest) + return -ENOMEM; + + ctx->digest_len = vlen; + + return 0; } diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c index 44b746e..2ffd697 100644 --- a/crypto/asymmetric_keys/pkcs7_verify.c +++ b/crypto/asymmetric_keys/pkcs7_verify.c @@ -227,7 +227,7 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7, if (asymmetric_key_id_same(p->id, auth)) goto found_issuer_check_skid; } - } else { + } else if (sig->auth_ids[1]) { auth = sig->auth_ids[1]; pr_debug("- want %*phN\n", auth->len, auth->data); for (p = pkcs7->certs; p; p = p->next) { diff --git a/crypto/asymmetric_keys/restrict.c b/crypto/asymmetric_keys/restrict.c index ac4bddf..19d1afb9 100644 --- a/crypto/asymmetric_keys/restrict.c +++ b/crypto/asymmetric_keys/restrict.c @@ -87,7 +87,7 @@ int restrict_link_by_signature(struct key *trust_keyring, sig = payload->data[asym_auth]; if (!sig->auth_ids[0] && !sig->auth_ids[1]) - return 0; + return -ENOKEY; if (ca_keyid && !asymmetric_key_id_partial(sig->auth_ids[1], ca_keyid)) return -EPERM; diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c index ead8dc0..8ba4266 100644 --- a/crypto/rsa-pkcs1pad.c +++ b/crypto/rsa-pkcs1pad.c @@ -102,10 +102,10 @@ struct pkcs1pad_inst_ctx { }; struct pkcs1pad_request { - struct akcipher_request child_req; - struct scatterlist in_sg[3], out_sg[2]; uint8_t *in_buf, *out_buf; + + struct akcipher_request child_req; }; static int pkcs1pad_set_pub_key(struct crypto_akcipher *tfm, const void *key, diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c index 1f41284..dee8692 100644 --- a/drivers/acpi/acpi_dbg.c +++ b/drivers/acpi/acpi_dbg.c @@ -602,7 +602,7 @@ static int acpi_aml_read_user(char __user *buf, int len) crc->tail = (crc->tail + n) & (ACPI_AML_BUF_SIZE - 1); ret = n; out: - acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, !ret); + acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, ret >= 0); return ret; } @@ -672,7 +672,7 @@ static int acpi_aml_write_user(const char __user *buf, int len) crc->head = (crc->head + n) & (ACPI_AML_BUF_SIZE - 1); ret = n; out: - acpi_aml_unlock_fifo(ACPI_AML_IN_USER, !ret); + acpi_aml_unlock_fifo(ACPI_AML_IN_USER, ret >= 0); return n; } diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c index 21932d6..a1d177d 100644 --- a/drivers/acpi/acpica/exconfig.c +++ b/drivers/acpi/acpica/exconfig.c @@ -108,9 +108,7 @@ acpi_ex_add_table(u32 table_index, /* Add the table to the namespace */ - acpi_ex_exit_interpreter(); status = acpi_ns_load_table(table_index, parent_node); - acpi_ex_enter_interpreter(); if (ACPI_FAILURE(status)) { acpi_ut_remove_reference(obj_desc); *ddb_handle = NULL; diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c index 1783cd7..f631a47 100644 --- a/drivers/acpi/acpica/nsparse.c +++ b/drivers/acpi/acpica/nsparse.c @@ -47,7 +47,6 @@ #include "acparser.h" #include "acdispat.h" #include "actables.h" -#include "acinterp.h" #define _COMPONENT ACPI_NAMESPACE ACPI_MODULE_NAME("nsparse") @@ -171,8 +170,6 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node) ACPI_FUNCTION_TRACE(ns_parse_table); - acpi_ex_enter_interpreter(); - /* * AML Parse, pass 1 * @@ -188,7 +185,7 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node) status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS1, table_index, start_node); if (ACPI_FAILURE(status)) { - goto error_exit; + return_ACPI_STATUS(status); } /* @@ -204,10 +201,8 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node) status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS2, table_index, start_node); if (ACPI_FAILURE(status)) { - goto error_exit; + return_ACPI_STATUS(status); } -error_exit: - acpi_ex_exit_interpreter(); return_ACPI_STATUS(status); } diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 73c76d6..290d6f5 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1331,8 +1331,6 @@ static int ec_install_handlers(struct acpi_ec *ec) static void ec_remove_handlers(struct acpi_ec *ec) { - acpi_ec_stop(ec, false); - if (test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { if (ACPI_FAILURE(acpi_remove_address_space_handler(ec->handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler))) @@ -1340,6 +1338,19 @@ static void ec_remove_handlers(struct acpi_ec *ec) clear_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); } + /* + * Stops handling the EC transactions after removing the operation + * region handler. This is required because _REG(DISCONNECT) + * invoked during the removal can result in new EC transactions. + * + * Flushes the EC requests and thus disables the GPE before + * removing the GPE handler. This is required by the current ACPICA + * GPE core. ACPICA GPE core will automatically disable a GPE when + * it is indicated but there is no way to handle it. So the drivers + * must disable the GPEs prior to removing the GPE handlers. + */ + acpi_ec_stop(ec, false); + if (test_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags)) { if (ACPI_FAILURE(acpi_remove_gpe_handler(NULL, ec->gpe, &acpi_ec_gpe_handler))) diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index ac6ddcc0..1f0e060 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -1131,11 +1131,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, /* * Until standardization materializes we need to consider up to 3 - * different command sets. Note, that checking for zero functions - * tells us if any commands might be reachable through this uuid. + * different command sets. Note, that checking for function0 (bit0) + * tells us if any commands are reachable through this uuid. */ for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_HPE2; i++) - if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 0)) + if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1)) break; /* limit the supported commands to those that are publicly documented */ @@ -1151,9 +1151,10 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, if (disable_vendor_specific) dsm_mask &= ~(1 << 8); } else { - dev_err(dev, "unknown dimm command family\n"); + dev_dbg(dev, "unknown dimm command family\n"); nfit_mem->family = -1; - return force_enable_dimms ? 0 : -ENODEV; + /* DSMs are optional, continue loading the driver... */ + return 0; } uuid = to_nfit_uuid(nfit_mem->family); diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 4ed4061..c983bf7 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -470,6 +470,7 @@ static int acpi_irq_pci_sharing_penalty(int irq) { struct acpi_pci_link *link; int penalty = 0; + int i; list_for_each_entry(link, &acpi_link_list, list) { /* @@ -478,18 +479,14 @@ static int acpi_irq_pci_sharing_penalty(int irq) */ if (link->irq.active && link->irq.active == irq) penalty += PIRQ_PENALTY_PCI_USING; - else { - int i; - - /* - * If a link is inactive, penalize the IRQs it - * might use, but not as severely. - */ - for (i = 0; i < link->irq.possible_count; i++) - if (link->irq.possible[i] == irq) - penalty += PIRQ_PENALTY_PCI_POSSIBLE / - link->irq.possible_count; - } + + /* + * penalize the IRQs PCI might use, but not as severely. + */ + for (i = 0; i < link->irq.possible_count; i++) + if (link->irq.possible[i] == irq) + penalty += PIRQ_PENALTY_PCI_POSSIBLE / + link->irq.possible_count; } return penalty; @@ -499,9 +496,6 @@ static int acpi_irq_get_penalty(int irq) { int penalty = 0; - if (irq < ACPI_MAX_ISA_IRQS) - penalty += acpi_isa_irq_penalty[irq]; - /* * Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict * with PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be @@ -516,10 +510,49 @@ static int acpi_irq_get_penalty(int irq) penalty += PIRQ_PENALTY_PCI_USING; } + if (irq < ACPI_MAX_ISA_IRQS) + return penalty + acpi_isa_irq_penalty[irq]; + penalty += acpi_irq_pci_sharing_penalty(irq); return penalty; } +int __init acpi_irq_penalty_init(void) +{ + struct acpi_pci_link *link; + int i; + + /* + * Update penalties to facilitate IRQ balancing. + */ + list_for_each_entry(link, &acpi_link_list, list) { + + /* + * reflect the possible and active irqs in the penalty table -- + * useful for breaking ties. + */ + if (link->irq.possible_count) { + int penalty = + PIRQ_PENALTY_PCI_POSSIBLE / + link->irq.possible_count; + + for (i = 0; i < link->irq.possible_count; i++) { + if (link->irq.possible[i] < ACPI_MAX_ISA_IRQS) + acpi_isa_irq_penalty[link->irq. + possible[i]] += + penalty; + } + + } else if (link->irq.active && + (link->irq.active < ACPI_MAX_ISA_IRQS)) { + acpi_isa_irq_penalty[link->irq.active] += + PIRQ_PENALTY_PCI_POSSIBLE; + } + } + + return 0; +} + static int acpi_irq_balance = -1; /* 0: static, 1: balance */ static int acpi_pci_link_allocate(struct acpi_pci_link *link) diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index b4de130..22c0995 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -680,6 +680,9 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs) u64 mask = 0; union acpi_object *obj; + if (funcs == 0) + return false; + obj = acpi_evaluate_dsm(handle, uuid, rev, 0, NULL); if (!obj) return false; @@ -692,9 +695,6 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs) mask |= (((u64)obj->buffer.pointer[i]) << (i * 8)); ACPI_FREE(obj); - if (funcs == 0) - return true; - /* * Bit 0 indicates whether there's support for any functions other than * function 0 for the specified UUID and revision. diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 6be7770..31c183a 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4314,6 +4314,12 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { */ { "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 }, + /* + * Device times out with higher max sects. + * https://bugzilla.kernel.org/show_bug.cgi?id=121671 + */ + { "LITEON CX1-JB256-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, + /* Devices we expect to fail diagnostics */ /* Devices where NCQ should be avoided */ diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index ddc4ceb..700ed15 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -874,7 +874,8 @@ static scq_info *get_scq(ns_dev *card, int size, u32 scd) scq->skb = kmalloc(sizeof(struct sk_buff *) * (size / NS_SCQE_SIZE), GFP_KERNEL); if (!scq->skb) { - kfree(scq->org); + dma_free_coherent(&card->pcidev->dev, + 2 * size, scq->org, scq->dma); kfree(scq); return NULL; } diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index eda0909..f642c42 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -8,8 +8,6 @@ #include <linux/bcma/bcma.h> #include <linux/delay.h> -#define BCMA_CORE_SIZE 0x1000 - #define bcma_err(bus, fmt, ...) \ pr_err("bus%d: " fmt, (bus)->num, ##__VA_ARGS__) #define bcma_warn(bus, fmt, ...) \ diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 2e6d1e9..fcc5b4e 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -207,6 +207,9 @@ struct blkfront_info struct blk_mq_tag_set tag_set; struct blkfront_ring_info *rinfo; unsigned int nr_rings; + /* Save uncomplete reqs and bios for migration. */ + struct list_head requests; + struct bio_list bio_list; }; static unsigned int nr_minors; @@ -2002,69 +2005,22 @@ static int blkif_recover(struct blkfront_info *info) { unsigned int i, r_index; struct request *req, *n; - struct blk_shadow *copy; int rc; struct bio *bio, *cloned_bio; - struct bio_list bio_list, merge_bio; unsigned int segs, offset; int pending, size; struct split_bio *split_bio; - struct list_head requests; blkfront_gather_backend_features(info); segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; blk_queue_max_segments(info->rq, segs); - bio_list_init(&bio_list); - INIT_LIST_HEAD(&requests); for (r_index = 0; r_index < info->nr_rings; r_index++) { - struct blkfront_ring_info *rinfo; - - rinfo = &info->rinfo[r_index]; - /* Stage 1: Make a safe copy of the shadow state. */ - copy = kmemdup(rinfo->shadow, sizeof(rinfo->shadow), - GFP_NOIO | __GFP_REPEAT | __GFP_HIGH); - if (!copy) - return -ENOMEM; - - /* Stage 2: Set up free list. */ - memset(&rinfo->shadow, 0, sizeof(rinfo->shadow)); - for (i = 0; i < BLK_RING_SIZE(info); i++) - rinfo->shadow[i].req.u.rw.id = i+1; - rinfo->shadow_free = rinfo->ring.req_prod_pvt; - rinfo->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff; + struct blkfront_ring_info *rinfo = &info->rinfo[r_index]; rc = blkfront_setup_indirect(rinfo); - if (rc) { - kfree(copy); + if (rc) return rc; - } - - for (i = 0; i < BLK_RING_SIZE(info); i++) { - /* Not in use? */ - if (!copy[i].request) - continue; - - /* - * Get the bios in the request so we can re-queue them. - */ - if (copy[i].request->cmd_flags & - (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) { - /* - * Flush operations don't contain bios, so - * we need to requeue the whole request - */ - list_add(©[i].request->queuelist, &requests); - continue; - } - merge_bio.head = copy[i].request->bio; - merge_bio.tail = copy[i].request->biotail; - bio_list_merge(&bio_list, &merge_bio); - copy[i].request->bio = NULL; - blk_end_request_all(copy[i].request, 0); - } - - kfree(copy); } xenbus_switch_state(info->xbdev, XenbusStateConnected); @@ -2079,7 +2035,7 @@ static int blkif_recover(struct blkfront_info *info) kick_pending_request_queues(rinfo); } - list_for_each_entry_safe(req, n, &requests, queuelist) { + list_for_each_entry_safe(req, n, &info->requests, queuelist) { /* Requeue pending requests (flush or discard) */ list_del_init(&req->queuelist); BUG_ON(req->nr_phys_segments > segs); @@ -2087,7 +2043,7 @@ static int blkif_recover(struct blkfront_info *info) } blk_mq_kick_requeue_list(info->rq); - while ((bio = bio_list_pop(&bio_list)) != NULL) { + while ((bio = bio_list_pop(&info->bio_list)) != NULL) { /* Traverse the list of pending bios and re-queue them */ if (bio_segments(bio) > segs) { /* @@ -2133,9 +2089,42 @@ static int blkfront_resume(struct xenbus_device *dev) { struct blkfront_info *info = dev_get_drvdata(&dev->dev); int err = 0; + unsigned int i, j; dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename); + bio_list_init(&info->bio_list); + INIT_LIST_HEAD(&info->requests); + for (i = 0; i < info->nr_rings; i++) { + struct blkfront_ring_info *rinfo = &info->rinfo[i]; + struct bio_list merge_bio; + struct blk_shadow *shadow = rinfo->shadow; + + for (j = 0; j < BLK_RING_SIZE(info); j++) { + /* Not in use? */ + if (!shadow[j].request) + continue; + + /* + * Get the bios in the request so we can re-queue them. + */ + if (shadow[j].request->cmd_flags & + (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) { + /* + * Flush operations don't contain bios, so + * we need to requeue the whole request + */ + list_add(&shadow[j].request->queuelist, &info->requests); + continue; + } + merge_bio.head = shadow[j].request->bio; + merge_bio.tail = shadow[j].request->biotail; + bio_list_merge(&info->bio_list, &merge_bio); + shadow[j].request->bio = NULL; + blk_mq_end_request(shadow[j].request, 0); + } + } + blkif_free(info, info->connected == BLKIF_STATE_CONNECTED); err = negotiate_mq(info); diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c index fd6b53e..a9932fe 100644 --- a/drivers/bluetooth/bpa10x.c +++ b/drivers/bluetooth/bpa10x.c @@ -274,6 +274,8 @@ static int bpa10x_setup(struct hci_dev *hdev) BT_INFO("%s: %s", hdev->name, (char *)(skb->data + 1)); + hci_set_fw_info(hdev, "%s", skb->data + 1); + kfree_skb(skb); return 0; } diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index b7c3928..d02f2c1 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -1625,6 +1625,7 @@ static int btmrvl_sdio_suspend(struct device *dev) if (priv->adapter->hs_state != HS_ACTIVATED) { if (btmrvl_enable_hs(priv)) { BT_ERR("HS not actived, suspend failed!"); + priv->adapter->is_suspending = false; return -EBUSY; } } diff --git a/drivers/bluetooth/btwilink.c b/drivers/bluetooth/btwilink.c index 24a652f..485281b 100644 --- a/drivers/bluetooth/btwilink.c +++ b/drivers/bluetooth/btwilink.c @@ -51,7 +51,7 @@ */ struct ti_st { struct hci_dev *hdev; - char reg_status; + int reg_status; long (*st_write) (struct sk_buff *); struct completion wait_reg_completion; }; @@ -83,7 +83,7 @@ static inline void ti_st_tx_complete(struct ti_st *hst, int pkt_type) * status.ti_st_open() function will wait for signal from this * API when st_register() function returns ST_PENDING. */ -static void st_reg_completion_cb(void *priv_data, char data) +static void st_reg_completion_cb(void *priv_data, int data) { struct ti_st *lhst = priv_data; diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c index 10f846c..25d5906 100644 --- a/drivers/clk/at91/clk-programmable.c +++ b/drivers/clk/at91/clk-programmable.c @@ -99,7 +99,7 @@ static int clk_programmable_set_parent(struct clk_hw *hw, u8 index) struct clk_programmable *prog = to_clk_programmable(hw); const struct clk_programmable_layout *layout = prog->layout; unsigned int mask = layout->css_mask; - unsigned int pckr = 0; + unsigned int pckr = index; if (layout->have_slck_mck) mask |= AT91_PMC_CSSMCK_MCK; diff --git a/drivers/clk/sunxi/clk-sun4i-display.c b/drivers/clk/sunxi/clk-sun4i-display.c index 445a749..9780fac 100644 --- a/drivers/clk/sunxi/clk-sun4i-display.c +++ b/drivers/clk/sunxi/clk-sun4i-display.c @@ -33,6 +33,8 @@ struct sun4i_a10_display_clk_data { u8 width_div; u8 width_mux; + + u32 flags; }; struct reset_data { @@ -166,7 +168,7 @@ static void __init sun4i_a10_display_init(struct device_node *node, data->has_div ? &div->hw : NULL, data->has_div ? &clk_divider_ops : NULL, &gate->hw, &clk_gate_ops, - 0); + data->flags); if (IS_ERR(clk)) { pr_err("%s: Couldn't register the clock\n", clk_name); goto free_div; @@ -232,6 +234,7 @@ static const struct sun4i_a10_display_clk_data sun4i_a10_tcon_ch0_data __initcon .offset_rst = 29, .offset_mux = 24, .width_mux = 2, + .flags = CLK_SET_RATE_PARENT, }; static void __init sun4i_a10_tcon_ch0_setup(struct device_node *node) diff --git a/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c b/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c index 98a4582..b6d29d1 100644 --- a/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c +++ b/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c @@ -79,15 +79,11 @@ static int tcon_ch1_is_enabled(struct clk_hw *hw) static u8 tcon_ch1_get_parent(struct clk_hw *hw) { struct tcon_ch1_clk *tclk = hw_to_tclk(hw); - int num_parents = clk_hw_get_num_parents(hw); u32 reg; reg = readl(tclk->reg) >> TCON_CH1_SCLK2_MUX_SHIFT; reg &= reg >> TCON_CH1_SCLK2_MUX_MASK; - if (reg >= num_parents) - return -EINVAL; - return reg; } diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index a4d0059..c73207a 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -173,7 +173,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, struct cpuidle_state *target_state = &drv->states[index]; bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP); - u64 time_start, time_end; + ktime_t time_start, time_end; s64 diff; /* @@ -195,13 +195,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, sched_idle_set_state(target_state); trace_cpu_idle_rcuidle(index, dev->cpu); - time_start = local_clock(); + time_start = ns_to_ktime(local_clock()); stop_critical_timings(); entered_state = target_state->enter(dev, drv, index); start_critical_timings(); - time_end = local_clock(); + time_end = ns_to_ktime(local_clock()); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); /* The cpu is no longer idle or about to enter idle. */ @@ -217,11 +217,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, if (!cpuidle_state_is_coupled(drv, index)) local_irq_enable(); - /* - * local_clock() returns the time in nanosecond, let's shift - * by 10 (divide by 1024) to have microsecond based time. - */ - diff = (time_end - time_start) >> 10; + diff = ktime_us_delta(time_end, time_start); if (diff > INT_MAX) diff = INT_MAX; diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile index 6d74b91..5fc3dbb 100644 --- a/drivers/crypto/qat/qat_common/Makefile +++ b/drivers/crypto/qat/qat_common/Makefile @@ -2,6 +2,7 @@ $(obj)/qat_rsapubkey-asn1.o: $(obj)/qat_rsapubkey-asn1.c \ $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.o: $(obj)/qat_rsaprivkey-asn1.c \ $(obj)/qat_rsaprivkey-asn1.h +$(obj)/qat_asym_algs.o: $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.h clean-files += qat_rsapubkey-asn1.c qat_rsapubkey-asn1.h clean-files += qat_rsaprivkey-asn1.c qat_rsaprivkey-asn1.h diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 6744d88..4fb2eb7 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -2378,22 +2378,19 @@ static int sbridge_get_onedevice(struct pci_dev **prev, * @num_mc: pointer to the memory controllers count, to be incremented in case * of success. * @table: model specific table - * @allow_dups: allow for multiple devices to exist with the same device id - * (as implemented, this isn't expected to work correctly in the - * multi-socket case). - * @multi_bus: don't assume devices on different buses belong to different - * memory controllers. * * returns 0 in case of success or error code */ -static int sbridge_get_all_devices_full(u8 *num_mc, - const struct pci_id_table *table, - int allow_dups, - int multi_bus) +static int sbridge_get_all_devices(u8 *num_mc, + const struct pci_id_table *table) { int i, rc; struct pci_dev *pdev = NULL; + int allow_dups = 0; + int multi_bus = 0; + if (table->type == KNIGHTS_LANDING) + allow_dups = multi_bus = 1; while (table && table->descr) { for (i = 0; i < table->n_devs; i++) { if (!allow_dups || i == 0 || @@ -2420,11 +2417,6 @@ static int sbridge_get_all_devices_full(u8 *num_mc, return 0; } -#define sbridge_get_all_devices(num_mc, table) \ - sbridge_get_all_devices_full(num_mc, table, 0, 0) -#define sbridge_get_all_devices_knl(num_mc, table) \ - sbridge_get_all_devices_full(num_mc, table, 1, 1) - static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, struct sbridge_dev *sbridge_dev) { diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index cebcb40..d786061 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -49,7 +49,7 @@ config GPIO_DEVRES config OF_GPIO def_bool y - depends on OF || COMPILE_TEST + depends on OF config GPIO_ACPI def_bool y @@ -402,9 +402,12 @@ config GPIO_TB10X select OF_GPIO config GPIO_TEGRA - bool - default y + bool "NVIDIA Tegra GPIO support" + default ARCH_TEGRA depends on ARCH_TEGRA || COMPILE_TEST + depends on OF + help + Say yes here to support GPIO pins on NVIDIA Tegra SoCs. config GPIO_TS4800 tristate "TS-4800 DIO blocks and compatibles" diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c index e85e753..eb43ae4 100644 --- a/drivers/gpio/gpio-sch.c +++ b/drivers/gpio/gpio-sch.c @@ -61,9 +61,8 @@ static unsigned sch_gpio_bit(struct sch_gpio *sch, unsigned gpio) return gpio % 8; } -static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg) +static int sch_gpio_reg_get(struct sch_gpio *sch, unsigned gpio, unsigned reg) { - struct sch_gpio *sch = gpiochip_get_data(gc); unsigned short offset, bit; u8 reg_val; @@ -75,10 +74,9 @@ static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg) return reg_val; } -static void sch_gpio_reg_set(struct gpio_chip *gc, unsigned gpio, unsigned reg, +static void sch_gpio_reg_set(struct sch_gpio *sch, unsigned gpio, unsigned reg, int val) { - struct sch_gpio *sch = gpiochip_get_data(gc); unsigned short offset, bit; u8 reg_val; @@ -98,14 +96,15 @@ static int sch_gpio_direction_in(struct gpio_chip *gc, unsigned gpio_num) struct sch_gpio *sch = gpiochip_get_data(gc); spin_lock(&sch->lock); - sch_gpio_reg_set(gc, gpio_num, GIO, 1); + sch_gpio_reg_set(sch, gpio_num, GIO, 1); spin_unlock(&sch->lock); return 0; } static int sch_gpio_get(struct gpio_chip *gc, unsigned gpio_num) { - return sch_gpio_reg_get(gc, gpio_num, GLV); + struct sch_gpio *sch = gpiochip_get_data(gc); + return sch_gpio_reg_get(sch, gpio_num, GLV); } static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val) @@ -113,7 +112,7 @@ static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val) struct sch_gpio *sch = gpiochip_get_data(gc); spin_lock(&sch->lock); - sch_gpio_reg_set(gc, gpio_num, GLV, val); + sch_gpio_reg_set(sch, gpio_num, GLV, val); spin_unlock(&sch->lock); } @@ -123,7 +122,7 @@ static int sch_gpio_direction_out(struct gpio_chip *gc, unsigned gpio_num, struct sch_gpio *sch = gpiochip_get_data(gc); spin_lock(&sch->lock); - sch_gpio_reg_set(gc, gpio_num, GIO, 0); + sch_gpio_reg_set(sch, gpio_num, GIO, 0); spin_unlock(&sch->lock); /* @@ -182,13 +181,13 @@ static int sch_gpio_probe(struct platform_device *pdev) * GPIO7 is configured by the CMC as SLPIOVR * Enable GPIO[9:8] core powered gpios explicitly */ - sch_gpio_reg_set(&sch->chip, 8, GEN, 1); - sch_gpio_reg_set(&sch->chip, 9, GEN, 1); + sch_gpio_reg_set(sch, 8, GEN, 1); + sch_gpio_reg_set(sch, 9, GEN, 1); /* * SUS_GPIO[2:0] enabled by default * Enable SUS_GPIO3 resume powered gpio explicitly */ - sch_gpio_reg_set(&sch->chip, 13, GEN, 1); + sch_gpio_reg_set(sch, 13, GEN, 1); break; case PCI_DEVICE_ID_INTEL_ITC_LPC: diff --git a/drivers/gpio/gpiolib-legacy.c b/drivers/gpio/gpiolib-legacy.c index 3a5c701..8b83099 100644 --- a/drivers/gpio/gpiolib-legacy.c +++ b/drivers/gpio/gpiolib-legacy.c @@ -28,6 +28,10 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) if (!desc && gpio_is_valid(gpio)) return -EPROBE_DEFER; + err = gpiod_request(desc, label); + if (err) + return err; + if (flags & GPIOF_OPEN_DRAIN) set_bit(FLAG_OPEN_DRAIN, &desc->flags); @@ -37,10 +41,6 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) if (flags & GPIOF_ACTIVE_LOW) set_bit(FLAG_ACTIVE_LOW, &desc->flags); - err = gpiod_request(desc, label); - if (err) - return err; - if (flags & GPIOF_DIR_IN) err = gpiod_direction_input(desc); else diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 570771e..be74bd3 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1352,14 +1352,6 @@ static int __gpiod_request(struct gpio_desc *desc, const char *label) spin_lock_irqsave(&gpio_lock, flags); } done: - if (status < 0) { - /* Clear flags that might have been set by the caller before - * requesting the GPIO. - */ - clear_bit(FLAG_ACTIVE_LOW, &desc->flags); - clear_bit(FLAG_OPEN_DRAIN, &desc->flags); - clear_bit(FLAG_OPEN_SOURCE, &desc->flags); - } spin_unlock_irqrestore(&gpio_lock, flags); return status; } @@ -2587,28 +2579,13 @@ struct gpio_desc *__must_check gpiod_get_optional(struct device *dev, } EXPORT_SYMBOL_GPL(gpiod_get_optional); -/** - * gpiod_parse_flags - helper function to parse GPIO lookup flags - * @desc: gpio to be setup - * @lflags: gpio_lookup_flags - returned from of_find_gpio() or - * of_get_gpio_hog() - * - * Set the GPIO descriptor flags based on the given GPIO lookup flags. - */ -static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags) -{ - if (lflags & GPIO_ACTIVE_LOW) - set_bit(FLAG_ACTIVE_LOW, &desc->flags); - if (lflags & GPIO_OPEN_DRAIN) - set_bit(FLAG_OPEN_DRAIN, &desc->flags); - if (lflags & GPIO_OPEN_SOURCE) - set_bit(FLAG_OPEN_SOURCE, &desc->flags); -} /** * gpiod_configure_flags - helper function to configure a given GPIO * @desc: gpio whose value will be assigned * @con_id: function within the GPIO consumer + * @lflags: gpio_lookup_flags - returned from of_find_gpio() or + * of_get_gpio_hog() * @dflags: gpiod_flags - optional GPIO initialization flags * * Return 0 on success, -ENOENT if no GPIO has been assigned to the @@ -2616,10 +2593,17 @@ static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags) * occurred while trying to acquire the GPIO. */ static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, - enum gpiod_flags dflags) + unsigned long lflags, enum gpiod_flags dflags) { int status; + if (lflags & GPIO_ACTIVE_LOW) + set_bit(FLAG_ACTIVE_LOW, &desc->flags); + if (lflags & GPIO_OPEN_DRAIN) + set_bit(FLAG_OPEN_DRAIN, &desc->flags); + if (lflags & GPIO_OPEN_SOURCE) + set_bit(FLAG_OPEN_SOURCE, &desc->flags); + /* No particular flag request, return here... */ if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) { pr_debug("no flags found for %s\n", con_id); @@ -2686,13 +2670,11 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev, return desc; } - gpiod_parse_flags(desc, lookupflags); - status = gpiod_request(desc, con_id); if (status < 0) return ERR_PTR(status); - status = gpiod_configure_flags(desc, con_id, flags); + status = gpiod_configure_flags(desc, con_id, lookupflags, flags); if (status < 0) { dev_dbg(dev, "setup of GPIO %s failed\n", con_id); gpiod_put(desc); @@ -2748,6 +2730,10 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, if (IS_ERR(desc)) return desc; + ret = gpiod_request(desc, NULL); + if (ret) + return ERR_PTR(ret); + if (active_low) set_bit(FLAG_ACTIVE_LOW, &desc->flags); @@ -2758,10 +2744,6 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, set_bit(FLAG_OPEN_SOURCE, &desc->flags); } - ret = gpiod_request(desc, NULL); - if (ret) - return ERR_PTR(ret); - return desc; } EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod); @@ -2814,8 +2796,6 @@ int gpiod_hog(struct gpio_desc *desc, const char *name, chip = gpiod_to_chip(desc); hwnum = gpio_chip_hwgpio(desc); - gpiod_parse_flags(desc, lflags); - local_desc = gpiochip_request_own_desc(chip, hwnum, name); if (IS_ERR(local_desc)) { status = PTR_ERR(local_desc); @@ -2824,7 +2804,7 @@ int gpiod_hog(struct gpio_desc *desc, const char *name, return status; } - status = gpiod_configure_flags(desc, name, dflags); + status = gpiod_configure_flags(desc, name, lflags, dflags); if (status < 0) { pr_err("setup of hog GPIO %s (chip %s, offset %d) failed, %d\n", name, chip->label, hwnum, status); diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c index 13cdb01..bc56c8a 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c @@ -156,3 +156,18 @@ u32 amdgpu_atombios_i2c_func(struct i2c_adapter *adap) return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; } +void amdgpu_atombios_i2c_channel_trans(struct amdgpu_device* adev, u8 slave_addr, u8 line_number, u8 offset, u8 data) +{ + PROCESS_I2C_CHANNEL_TRANSACTION_PS_ALLOCATION args; + int index = GetIndexIntoMasterTable(COMMAND, ProcessI2cChannelTransaction); + + args.ucRegIndex = offset; + args.lpI2CDataOut = data; + args.ucFlag = 1; + args.ucI2CSpeed = TARGET_HW_I2C_CLOCK; + args.ucTransBytes = 1; + args.ucSlaveAddr = slave_addr; + args.ucLineNumber = line_number; + + amdgpu_atom_execute_table(adev->mode_info.atom_context, index, (uint32_t *)&args); +} diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h index d6128d9d..251aaf4 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h +++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h @@ -27,5 +27,7 @@ int amdgpu_atombios_i2c_xfer(struct i2c_adapter *i2c_adap, struct i2c_msg *msgs, int num); u32 amdgpu_atombios_i2c_func(struct i2c_adapter *adap); +void amdgpu_atombios_i2c_channel_trans(struct amdgpu_device* adev, + u8 slave_addr, u8 line_number, u8 offset, u8 data); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index b2ebd4f..c2ef945 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -28,6 +28,7 @@ #include "vid.h" #include "amdgpu_ucode.h" #include "amdgpu_atombios.h" +#include "atombios_i2c.h" #include "clearstate_vi.h" #include "gmc/gmc_8_2_d.h" @@ -284,6 +285,7 @@ static const u32 golden_settings_polaris11_a11[] = mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f3, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000, mmTCP_CHAN_STEER_LO, 0xffffffff, 0x00003210, + mmVGT_RESET_DEBUG, 0x00000004, 0x00000004, }; static const u32 polaris11_golden_common_all[] = @@ -314,6 +316,7 @@ static const u32 golden_settings_polaris10_a11[] = mmTCC_CTRL, 0x00100000, 0xf31fff7f, mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f7, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000, + mmVGT_RESET_DEBUG, 0x00000004, 0x00000004, }; static const u32 polaris10_golden_common_all[] = @@ -696,6 +699,10 @@ static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev) polaris10_golden_common_all, (const u32)ARRAY_SIZE(polaris10_golden_common_all)); WREG32_SMC(ixCG_ACLK_CNTL, 0x0000001C); + if (adev->pdev->revision == 0xc7) { + amdgpu_atombios_i2c_channel_trans(adev, 0x10, 0x96, 0x1E, 0xDD); + amdgpu_atombios_i2c_channel_trans(adev, 0x10, 0x96, 0x1F, 0xD0); + } break; case CHIP_CARRIZO: amdgpu_program_register_sequence(adev, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c index ec2a7ad..91e25f9 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c @@ -98,7 +98,6 @@ #define PCIE_BUS_CLK 10000 #define TCLK (PCIE_BUS_CLK / 10) -#define CEILING_UCHAR(double) ((double-(uint8_t)(double)) > 0 ? (uint8_t)(double+1) : (uint8_t)(double)) static const uint16_t polaris10_clock_stretcher_lookup_table[2][4] = { {600, 1050, 3, 0}, {600, 1050, 6, 1} }; @@ -733,7 +732,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr, table->Smio[level] |= data->mvdd_voltage_table.entries[level].smio_low; } - table->SmioMask2 = data->vddci_voltage_table.mask_low; + table->SmioMask2 = data->mvdd_voltage_table.mask_low; table->MvddLevelCount = (uint32_t) PP_HOST_TO_SMC_UL(count); } @@ -1807,27 +1806,25 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr) ro = efuse * (max -min)/255 + min; - /* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset - * there is a little difference in calculating - * volt_with_cks with windows */ + /* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset */ for (i = 0; i < sclk_table->count; i++) { data->smc_state_table.Sclk_CKS_masterEn0_7 |= sclk_table->entries[i].cks_enable << i; if (hwmgr->chip_id == CHIP_POLARIS10) { - volt_without_cks = (uint32_t)((2753594000 + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \ + volt_without_cks = (uint32_t)((2753594000U + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \ (2424180 - (sclk_table->entries[i].clk/100) * 1132925/1000)); - volt_with_cks = (uint32_t)((279720200 + sclk_table->entries[i].clk * 3232 - (ro - 65) * 100000000) / \ - (252248000 - sclk_table->entries[i].clk/100 * 115764)); + volt_with_cks = (uint32_t)((2797202000U + sclk_table->entries[i].clk/100 * 3232 - (ro - 65) * 1000000) / \ + (2522480 - sclk_table->entries[i].clk/100 * 115764/100)); } else { - volt_without_cks = (uint32_t)((2416794800 + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \ - (2625416 - (sclk_table->entries[i].clk/100) * 12586807/10000)); - volt_with_cks = (uint32_t)((2999656000 + sclk_table->entries[i].clk * 392803/100 - (ro - 44) * 1000000) / \ - (3422454 - sclk_table->entries[i].clk/100 * 18886376/10000)); + volt_without_cks = (uint32_t)((2416794800U + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \ + (2625416 - (sclk_table->entries[i].clk/100) * (12586807/10000))); + volt_with_cks = (uint32_t)((2999656000U - sclk_table->entries[i].clk/100 * 392803 - (ro - 44) * 1000000) / \ + (3422454 - sclk_table->entries[i].clk/100 * (18886376/10000))); } if (volt_without_cks >= volt_with_cks) - volt_offset = (uint8_t)CEILING_UCHAR((volt_without_cks - volt_with_cks + - sclk_table->entries[i].cks_voffset) * 100 / 625); + volt_offset = (uint8_t)(((volt_without_cks - volt_with_cks + + sclk_table->entries[i].cks_voffset) * 100 + 624) / 625); data->smc_state_table.Sclk_voltageOffset[i] = volt_offset; } @@ -2685,7 +2682,7 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); uint16_t vv_id; - uint16_t vddc = 0; + uint32_t vddc = 0; uint16_t i, j; uint32_t sclk = 0; struct phm_ppt_v1_information *table_info = @@ -2716,8 +2713,9 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr) continue); - /* need to make sure vddc is less than 2v or else, it could burn the ASIC. */ - PP_ASSERT_WITH_CODE((vddc < 2000 && vddc != 0), + /* need to make sure vddc is less than 2v or else, it could burn the ASIC. + * real voltage level in unit of 0.01mv */ + PP_ASSERT_WITH_CODE((vddc < 200000 && vddc != 0), "Invalid VDDC value", result = -EINVAL;); /* the voltage should not be zero nor equal to leakage ID */ diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c index bf4e18f..90b35c5 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c @@ -1256,7 +1256,7 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock, } int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type, - uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage) + uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage) { int result; @@ -1274,7 +1274,7 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_ if (0 != result) return result; - *voltage = get_voltage_info_param_space.usVoltageLevel; + *voltage = ((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel; return result; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h index 248c5db..1e35a96 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h @@ -305,7 +305,7 @@ extern int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr, uint32_t extern int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock, uint8_t level); extern int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type, - uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage); + uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage); extern int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl_sclk_range_table *table); extern int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c index 233eb7f..5d0f655 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c @@ -1302,7 +1302,7 @@ static int tonga_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr, table->Smio[count] |= data->mvdd_voltage_table.entries[count].smio_low; } - table->SmioMask2 = data->vddci_voltage_table.mask_low; + table->SmioMask2 = data->mvdd_voltage_table.mask_low; CONVERT_FROM_HOST_TO_SMC_UL(table->MvddLevelCount); } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c index 671fdb4..dccc859 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c @@ -302,7 +302,7 @@ static int init_dpm_2_parameters( (((unsigned long)powerplay_table) + le16_to_cpu(powerplay_table->usPPMTableOffset)); if (0 != powerplay_table->usPPMTableOffset) { - if (1 == get_platform_power_management_table(hwmgr, atom_ppm_table)) { + if (get_platform_power_management_table(hwmgr, atom_ppm_table) == 0) { phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_EnablePlatformPowerManagement); } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f313b4d..85c4deb 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -512,6 +512,10 @@ void intel_detect_pch(struct drm_device *dev) DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n"); WARN_ON(!IS_SKYLAKE(dev) && !IS_KABYLAKE(dev)); + } else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) { + dev_priv->pch_type = PCH_KBP; + DRM_DEBUG_KMS("Found KabyPoint PCH\n"); + WARN_ON(!IS_KABYLAKE(dev)); } else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) || (id == INTEL_PCH_P3X_DEVICE_ID_TYPE) || ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) && diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 7c334e9..bc3f2e6 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -990,6 +990,7 @@ enum intel_pch { PCH_CPT, /* Cougarpoint PCH */ PCH_LPT, /* Lynxpoint PCH */ PCH_SPT, /* Sunrisepoint PCH */ + PCH_KBP, /* Kabypoint PCH */ PCH_NOP, }; @@ -2600,6 +2601,15 @@ struct drm_i915_cmd_table { #define IS_BXT_REVID(p, since, until) (IS_BROXTON(p) && IS_REVID(p, since, until)) +#define KBL_REVID_A0 0x0 +#define KBL_REVID_B0 0x1 +#define KBL_REVID_C0 0x2 +#define KBL_REVID_D0 0x3 +#define KBL_REVID_E0 0x4 + +#define IS_KBL_REVID(p, since, until) \ + (IS_KABYLAKE(p) && IS_REVID(p, since, until)) + /* * The genX designation typically refers to the render engine, so render * capability related checks should use IS_GEN, while display and other checks @@ -2708,11 +2718,13 @@ struct drm_i915_cmd_table { #define INTEL_PCH_LPT_LP_DEVICE_ID_TYPE 0x9c00 #define INTEL_PCH_SPT_DEVICE_ID_TYPE 0xA100 #define INTEL_PCH_SPT_LP_DEVICE_ID_TYPE 0x9D00 +#define INTEL_PCH_KBP_DEVICE_ID_TYPE 0xA200 #define INTEL_PCH_P2X_DEVICE_ID_TYPE 0x7100 #define INTEL_PCH_P3X_DEVICE_ID_TYPE 0x7000 #define INTEL_PCH_QEMU_DEVICE_ID_TYPE 0x2900 /* qemu q35 has 2918 */ #define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type) +#define HAS_PCH_KBP(dev) (INTEL_PCH_TYPE(dev) == PCH_KBP) #define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT) #define HAS_PCH_LPT(dev) (INTEL_PCH_TYPE(dev) == PCH_LPT) #define HAS_PCH_LPT_LP(dev) (__I915__(dev)->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 425e721..6657146 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -40,7 +40,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) if (!mutex_is_locked(mutex)) return false; -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES) +#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER) return mutex->owner == task; #else /* Since UP may be pre-empted, we cannot assume that we own the lock */ diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index b7ce963..44004e3 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -55,8 +55,10 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv, return -ENODEV; /* See the comment at the drm_mm_init() call for more about this check. - * WaSkipStolenMemoryFirstPage:bdw,chv (incomplete) */ - if (INTEL_INFO(dev_priv)->gen == 8 && start < 4096) + * WaSkipStolenMemoryFirstPage:bdw,chv,kbl (incomplete) + */ + if (start < 4096 && (IS_GEN8(dev_priv) || + IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0))) start = 4096; mutex_lock(&dev_priv->mm.stolen_lock); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 2f6fd33..aab47f7 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2471,7 +2471,7 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl) I915_WRITE(SDEIIR, iir); ret = IRQ_HANDLED; - if (HAS_PCH_SPT(dev_priv)) + if (HAS_PCH_SPT(dev_priv) || HAS_PCH_KBP(dev_priv)) spt_irq_handler(dev, iir); else cpt_irq_handler(dev, iir); @@ -4661,7 +4661,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv) dev->driver->disable_vblank = gen8_disable_vblank; if (IS_BROXTON(dev)) dev_priv->display.hpd_irq_setup = bxt_hpd_irq_setup; - else if (HAS_PCH_SPT(dev)) + else if (HAS_PCH_SPT(dev) || HAS_PCH_KBP(dev)) dev_priv->display.hpd_irq_setup = spt_hpd_irq_setup; else dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index b407411..3fcf7dd 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -220,6 +220,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ECOCHK_PPGTT_WT_HSW (0x2<<3) #define ECOCHK_PPGTT_WB_HSW (0x3<<3) +#define GEN8_CONFIG0 _MMIO(0xD00) +#define GEN9_DEFAULT_FIXES (1 << 3 | 1 << 2 | 1 << 1) + #define GAC_ECO_BITS _MMIO(0x14090) #define ECOBITS_SNB_BIT (1<<13) #define ECOBITS_PPGTT_CACHE64B (3<<8) @@ -1669,6 +1672,9 @@ enum skl_disp_power_wells { #define GEN7_TLB_RD_ADDR _MMIO(0x4700) +#define GAMT_CHKN_BIT_REG _MMIO(0x4ab8) +#define GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING (1<<28) + #if 0 #define PRB0_TAIL _MMIO(0x2030) #define PRB0_HEAD _MMIO(0x2034) @@ -1804,6 +1810,10 @@ enum skl_disp_power_wells { #define GEN9_IZ_HASHING_MASK(slice) (0x3 << ((slice) * 2)) #define GEN9_IZ_HASHING(slice, val) ((val) << ((slice) * 2)) +/* chicken reg for WaConextSwitchWithConcurrentTLBInvalidate */ +#define GEN9_CSFE_CHICKEN1_RCS _MMIO(0x20D4) +#define GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE (1 << 2) + /* WaClearTdlStateAckDirtyBits */ #define GEN8_STATE_ACK _MMIO(0x20F0) #define GEN9_STATE_ACK_SLICE1 _MMIO(0x20F8) @@ -2200,6 +2210,8 @@ enum skl_disp_power_wells { #define ILK_DPFC_STATUS _MMIO(0x43210) #define ILK_DPFC_FENCE_YOFF _MMIO(0x43218) #define ILK_DPFC_CHICKEN _MMIO(0x43224) +#define ILK_DPFC_DISABLE_DUMMY0 (1<<8) +#define ILK_DPFC_NUKE_ON_ANY_MODIFICATION (1<<23) #define ILK_FBC_RT_BASE _MMIO(0x2128) #define ILK_FBC_RT_VALID (1<<0) #define SNB_FBC_FRONT_BUFFER (1<<1) @@ -6031,6 +6043,7 @@ enum skl_disp_power_wells { #define CHICKEN_PAR1_1 _MMIO(0x42080) #define DPA_MASK_VBLANK_SRD (1 << 15) #define FORCE_ARB_IDLE_PLANES (1 << 14) +#define SKL_EDP_PSR_FIX_RDWRAP (1 << 3) #define _CHICKEN_PIPESL_1_A 0x420b0 #define _CHICKEN_PIPESL_1_B 0x420b4 @@ -6039,6 +6052,7 @@ enum skl_disp_power_wells { #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B) #define DISP_ARB_CTL _MMIO(0x45000) +#define DISP_FBC_MEMORY_WAKE (1<<31) #define DISP_TILE_SURFACE_SWIZZLING (1<<13) #define DISP_FBC_WM_DIS (1<<15) #define DISP_ARB_CTL2 _MMIO(0x45004) @@ -6052,6 +6066,9 @@ enum skl_disp_power_wells { #define HSW_NDE_RSTWRN_OPT _MMIO(0x46408) #define RESET_PCH_HANDSHAKE_ENABLE (1<<4) +#define GEN8_CHICKEN_DCPR_1 _MMIO(0x46430) +#define MASK_WAKEMEM (1<<13) + #define SKL_DFSM _MMIO(0x51000) #define SKL_DFSM_CDCLK_LIMIT_MASK (3 << 23) #define SKL_DFSM_CDCLK_LIMIT_675 (0 << 23) @@ -6069,6 +6086,7 @@ enum skl_disp_power_wells { #define GEN9_TSG_BARRIER_ACK_DISABLE (1<<8) #define GEN9_CS_DEBUG_MODE1 _MMIO(0x20ec) +#define GEN9_CTX_PREEMPT_REG _MMIO(0x2248) #define GEN8_CS_CHICKEN1 _MMIO(0x2580) /* GEN7 chicken */ @@ -6076,6 +6094,7 @@ enum skl_disp_power_wells { # define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC ((1<<10) | (1<<26)) # define GEN9_RHWO_OPTIMIZATION_DISABLE (1<<14) #define COMMON_SLICE_CHICKEN2 _MMIO(0x7014) +# define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION (1<<8) # define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE (1<<0) #define HIZ_CHICKEN _MMIO(0x7018) @@ -6921,6 +6940,7 @@ enum skl_disp_power_wells { #define EDRAM_SETS_IDX(cap) (((cap) >> 8) & 0x3) #define GEN6_UCGCTL1 _MMIO(0x9400) +# define GEN6_GAMUNIT_CLOCK_GATE_DISABLE (1 << 22) # define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE (1 << 16) # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE (1 << 5) # define GEN6_CSUNIT_CLOCK_GATE_DISABLE (1 << 7) @@ -6937,6 +6957,7 @@ enum skl_disp_power_wells { #define GEN7_UCGCTL4 _MMIO(0x940c) #define GEN7_L3BANK2X_CLOCK_GATE_DISABLE (1<<25) +#define GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE (1<<14) #define GEN6_RCGCTL1 _MMIO(0x9410) #define GEN6_RCGCTL2 _MMIO(0x9414) diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index a34c23e..2b3b428 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -41,16 +41,22 @@ * be moved to FW_FAILED. */ +#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin" +MODULE_FIRMWARE(I915_CSR_KBL); +#define KBL_CSR_VERSION_REQUIRED CSR_VERSION(1, 1) + #define I915_CSR_SKL "i915/skl_dmc_ver1.bin" +MODULE_FIRMWARE(I915_CSR_SKL); +#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23) + #define I915_CSR_BXT "i915/bxt_dmc_ver1.bin" +MODULE_FIRMWARE(I915_CSR_BXT); +#define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) #define FIRMWARE_URL "https://01.org/linuxgraphics/intel-linux-graphics-firmwares" -MODULE_FIRMWARE(I915_CSR_SKL); -MODULE_FIRMWARE(I915_CSR_BXT); -#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23) -#define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) + #define CSR_MAX_FW_SIZE 0x2FFF #define CSR_DEFAULT_FW_OFFSET 0xFFFFFFFF @@ -169,12 +175,10 @@ struct stepping_info { char substepping; }; -/* - * Kabylake derivated from Skylake H0, so SKL H0 - * is the right firmware for KBL A0 (revid 0). - */ static const struct stepping_info kbl_stepping_info[] = { - {'H', '0'}, {'I', '0'} + {'A', '0'}, {'B', '0'}, {'C', '0'}, + {'D', '0'}, {'E', '0'}, {'F', '0'}, + {'G', '0'}, {'H', '0'}, {'I', '0'}, }; static const struct stepping_info skl_stepping_info[] = { @@ -298,7 +302,9 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, csr->version = css_header->version; - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { + if (IS_KABYLAKE(dev_priv)) { + required_min_version = KBL_CSR_VERSION_REQUIRED; + } else if (IS_SKYLAKE(dev_priv)) { required_min_version = SKL_CSR_VERSION_REQUIRED; } else if (IS_BROXTON(dev_priv)) { required_min_version = BXT_CSR_VERSION_REQUIRED; @@ -446,7 +452,9 @@ void intel_csr_ucode_init(struct drm_i915_private *dev_priv) if (!HAS_CSR(dev_priv)) return; - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) + if (IS_KABYLAKE(dev_priv)) + csr->fw_path = I915_CSR_KBL; + else if (IS_SKYLAKE(dev_priv)) csr->fw_path = I915_CSR_SKL; else if (IS_BROXTON(dev_priv)) csr->fw_path = I915_CSR_BXT; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 04452cf..3074c56 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -11997,6 +11997,12 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc, ret = intel_color_check(crtc, crtc_state); if (ret) return ret; + + /* + * Changing color management on Intel hardware is + * handled as part of planes update. + */ + crtc_state->planes_changed = true; } ret = 0; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 40745e38d..891107f 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4645,7 +4645,7 @@ intel_dp_detect(struct drm_connector *connector, bool force) intel_dp->detect_done = false; - if (intel_connector->detect_edid) + if (is_edp(intel_dp) || intel_connector->detect_edid) return connector_status_connected; else return connector_status_disconnected; diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 42eac37..7f2d841 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1103,15 +1103,17 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, uint32_t *const batch, uint32_t index) { + struct drm_i915_private *dev_priv = engine->dev->dev_private; uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES); /* - * WaDisableLSQCROPERFforOCL:skl + * WaDisableLSQCROPERFforOCL:skl,kbl * This WA is implemented in skl_init_clock_gating() but since * this batch updates GEN8_L3SQCREG4 with default value we need to * set this bit here to retain the WA during flush. */ - if (IS_SKL_REVID(engine->dev, 0, SKL_REVID_E0)) + if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0) || + IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS; wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 | @@ -1273,6 +1275,7 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine, { int ret; struct drm_device *dev = engine->dev; + struct drm_i915_private *dev_priv = dev->dev_private; uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS); /* WaDisableCtxRestoreArbitration:skl,bxt */ @@ -1286,6 +1289,22 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine, return ret; index = ret; + /* WaClearSlmSpaceAtContextSwitch:kbl */ + /* Actual scratch location is at 128 bytes offset */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) { + uint32_t scratch_addr + = engine->scratch.gtt_offset + 2*CACHELINE_BYTES; + + wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6)); + wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 | + PIPE_CONTROL_GLOBAL_GTT_IVB | + PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_QW_WRITE)); + wa_ctx_emit(batch, index, scratch_addr); + wa_ctx_emit(batch, index, 0); + wa_ctx_emit(batch, index, 0); + wa_ctx_emit(batch, index, 0); + } /* Pad to end of cacheline */ while (index % CACHELINE_DWORDS) wa_ctx_emit(batch, index, MI_NOOP); @@ -1687,9 +1706,10 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, struct intel_ringbuffer *ringbuf = request->ringbuf; struct intel_engine_cs *engine = ringbuf->engine; u32 scratch_addr = engine->scratch.gtt_offset + 2 * CACHELINE_BYTES; - bool vf_flush_wa = false; + bool vf_flush_wa = false, dc_flush_wa = false; u32 flags = 0; int ret; + int len; flags |= PIPE_CONTROL_CS_STALL; @@ -1716,9 +1736,21 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, */ if (IS_GEN9(engine->dev)) vf_flush_wa = true; + + /* WaForGAMHang:kbl */ + if (IS_KBL_REVID(request->i915, 0, KBL_REVID_B0)) + dc_flush_wa = true; } - ret = intel_ring_begin(request, vf_flush_wa ? 12 : 6); + len = 6; + + if (vf_flush_wa) + len += 6; + + if (dc_flush_wa) + len += 12; + + ret = intel_ring_begin(request, len); if (ret) return ret; @@ -1731,12 +1763,31 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, intel_logical_ring_emit(ringbuf, 0); } + if (dc_flush_wa) { + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); + intel_logical_ring_emit(ringbuf, PIPE_CONTROL_DC_FLUSH_ENABLE); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + } + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); intel_logical_ring_emit(ringbuf, flags); intel_logical_ring_emit(ringbuf, scratch_addr); intel_logical_ring_emit(ringbuf, 0); intel_logical_ring_emit(ringbuf, 0); intel_logical_ring_emit(ringbuf, 0); + + if (dc_flush_wa) { + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); + intel_logical_ring_emit(ringbuf, PIPE_CONTROL_CS_STALL); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + } + intel_logical_ring_advance(ringbuf); return 0; diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index 99e2603..16e209d 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -1038,5 +1038,16 @@ intel_opregion_get_panel_type(struct drm_device *dev) return -ENODEV; } + /* + * FIXME On Dell XPS 13 9350 the OpRegion panel type (0) gives us + * low vswing for eDP, whereas the VBT panel type (2) gives us normal + * vswing instead. Low vswing results in some display flickers, so + * let's simply ignore the OpRegion panel type on SKL for now. + */ + if (IS_SKYLAKE(dev)) { + DRM_DEBUG_KMS("Ignoring OpRegion panel type (%d)\n", ret - 1); + return -ENODEV; + } + return ret - 1; } diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 8357d57..aba9409 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -1731,7 +1731,8 @@ intel_panel_init_backlight_funcs(struct intel_panel *panel) panel->backlight.set = bxt_set_backlight; panel->backlight.get = bxt_get_backlight; panel->backlight.hz_to_pwm = bxt_hz_to_pwm; - } else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_SPT(dev_priv)) { + } else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_SPT(dev_priv) || + HAS_PCH_KBP(dev_priv)) { panel->backlight.setup = lpt_setup_backlight; panel->backlight.enable = lpt_enable_backlight; panel->backlight.disable = lpt_disable_backlight; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index a7ef45d..2863b92 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -54,10 +54,38 @@ #define INTEL_RC6p_ENABLE (1<<1) #define INTEL_RC6pp_ENABLE (1<<2) +static void gen9_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + /* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl */ + I915_WRITE(CHICKEN_PAR1_1, + I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP); + + I915_WRITE(GEN8_CONFIG0, + I915_READ(GEN8_CONFIG0) | GEN9_DEFAULT_FIXES); + + /* WaEnableChickenDCPR:skl,bxt,kbl */ + I915_WRITE(GEN8_CHICKEN_DCPR_1, + I915_READ(GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM); + + /* WaFbcTurnOffFbcWatermark:skl,bxt,kbl */ + /* WaFbcWakeMemOn:skl,bxt,kbl */ + I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) | + DISP_FBC_WM_DIS | + DISP_FBC_MEMORY_WAKE); + + /* WaFbcHighMemBwCorruptionAvoidance:skl,bxt,kbl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_DISABLE_DUMMY0); +} + static void bxt_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + gen9_init_clock_gating(dev); + /* WaDisableSDEUnitClockGating:bxt */ I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | GEN8_SDEUNIT_CLOCK_GATE_DISABLE); @@ -6698,6 +6726,38 @@ static void lpt_suspend_hw(struct drm_device *dev) } } +static void kabylake_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + gen9_init_clock_gating(dev); + + /* WaDisableSDEUnitClockGating:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | + GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableGamClockGating:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) | + GEN6_GAMUNIT_CLOCK_GATE_DISABLE); + + /* WaFbcNukeOnHostModify:kbl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_NUKE_ON_ANY_MODIFICATION); +} + +static void skylake_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + gen9_init_clock_gating(dev); + + /* WaFbcNukeOnHostModify:skl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_NUKE_ON_ANY_MODIFICATION); +} + static void broadwell_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -7163,9 +7223,9 @@ static void nop_init_clock_gating(struct drm_device *dev) void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) { if (IS_SKYLAKE(dev_priv)) - dev_priv->display.init_clock_gating = nop_init_clock_gating; + dev_priv->display.init_clock_gating = skylake_init_clock_gating; else if (IS_KABYLAKE(dev_priv)) - dev_priv->display.init_clock_gating = nop_init_clock_gating; + dev_priv->display.init_clock_gating = kabylake_init_clock_gating; else if (IS_BROXTON(dev_priv)) dev_priv->display.init_clock_gating = bxt_init_clock_gating; else if (IS_BROADWELL(dev_priv)) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 04402bb..68c5af0 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -913,24 +913,26 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) { struct drm_device *dev = engine->dev; struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t tmp; int ret; - /* WaEnableLbsSlaRetryTimerDecrement:skl */ + /* WaConextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl */ + I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE)); + + /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl */ I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) | GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); - /* WaDisableKillLogic:bxt,skl */ + /* WaDisableKillLogic:bxt,skl,kbl */ I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | ECOCHK_DIS_TLB); - /* WaClearFlowControlGpgpuContextSave:skl,bxt */ - /* WaDisablePartialInstShootdown:skl,bxt */ + /* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl */ + /* WaDisablePartialInstShootdown:skl,bxt,kbl */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, FLOW_CONTROL_ENABLE | PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); - /* Syncing dependencies between camera and graphics:skl,bxt */ + /* Syncing dependencies between camera and graphics:skl,bxt,kbl */ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC); @@ -952,18 +954,18 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) */ } - /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt */ - /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt */ + /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl */ + /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl */ WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7, GEN9_ENABLE_YV12_BUGFIX | GEN9_ENABLE_GPGPU_PREEMPTION); - /* Wa4x4STCOptimizationDisable:skl,bxt */ - /* WaDisablePartialResolveInVc:skl,bxt */ + /* Wa4x4STCOptimizationDisable:skl,bxt,kbl */ + /* WaDisablePartialResolveInVc:skl,bxt,kbl */ WA_SET_BIT_MASKED(CACHE_MODE_1, (GEN8_4x4_STC_OPTIMIZATION_DISABLE | GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE)); - /* WaCcsTlbPrefetchDisable:skl,bxt */ + /* WaCcsTlbPrefetchDisable:skl,bxt,kbl */ WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5, GEN9_CCS_TLB_PREFETCH_ENABLE); @@ -973,31 +975,57 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(SLICE_ECO_CHICKEN0, PIXEL_MASK_CAMMING_DISABLE); - /* WaForceContextSaveRestoreNonCoherent:skl,bxt */ - tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT; - if (IS_SKL_REVID(dev, SKL_REVID_F0, REVID_FOREVER) || - IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER)) - tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE; - WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp); + /* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl */ + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT | + HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE); + + /* WaForceEnableNonCoherent and WaDisableHDCInvalidation are + * both tied to WaForceContextSaveRestoreNonCoherent + * in some hsds for skl. We keep the tie for all gen9. The + * documentation is a bit hazy and so we want to get common behaviour, + * even though there is no clear evidence we would need both on kbl/bxt. + * This area has been source of system hangs so we play it safe + * and mimic the skl regardless of what bspec says. + * + * Use Force Non-Coherent whenever executing a 3D context. This + * is a workaround for a possible hang in the unlikely event + * a TLB invalidation occurs during a PSD flush. + */ - /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt */ - if (IS_SKYLAKE(dev) || IS_BXT_REVID(dev, 0, BXT_REVID_B0)) + /* WaForceEnableNonCoherent:skl,bxt,kbl */ + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FORCE_NON_COHERENT); + + /* WaDisableHDCInvalidation:skl,bxt,kbl */ + I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | + BDW_DISABLE_HDC_INVALIDATION); + + /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl */ + if (IS_SKYLAKE(dev_priv) || + IS_KABYLAKE(dev_priv) || + IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN8_SAMPLER_POWER_BYPASS_DIS); - /* WaDisableSTUnitPowerOptimization:skl,bxt */ + /* WaDisableSTUnitPowerOptimization:skl,bxt,kbl */ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE); - /* WaOCLCoherentLineFlush:skl,bxt */ + /* WaOCLCoherentLineFlush:skl,bxt,kbl */ I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_FLUSH_COHERENT_LINES)); - /* WaEnablePreemptionGranularityControlByUMD:skl,bxt */ + /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt */ + ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG); + if (ret) + return ret; + + /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl */ ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); if (ret) return ret; - /* WaAllowUMDToModifyHDCChicken1:skl,bxt */ + /* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl */ ret = wa_ring_whitelist_reg(engine, GEN8_HDC_CHICKEN1); if (ret) return ret; @@ -1092,22 +1120,6 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(HIZ_CHICKEN, BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE); - /* This is tied to WaForceContextSaveRestoreNonCoherent */ - if (IS_SKL_REVID(dev, 0, REVID_FOREVER)) { - /* - *Use Force Non-Coherent whenever executing a 3D context. This - * is a workaround for a possible hang in the unlikely event - * a TLB invalidation occurs during a PSD flush. - */ - /* WaForceEnableNonCoherent:skl */ - WA_SET_BIT_MASKED(HDC_CHICKEN0, - HDC_FORCE_NON_COHERENT); - - /* WaDisableHDCInvalidation:skl */ - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - BDW_DISABLE_HDC_INVALIDATION); - } - /* WaBarrierPerformanceFixDisable:skl */ if (IS_SKL_REVID(dev, SKL_REVID_C0, SKL_REVID_D0)) WA_SET_BIT_MASKED(HDC_CHICKEN0, @@ -1120,6 +1132,9 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) GEN7_HALF_SLICE_CHICKEN1, GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + /* WaDisableGafsUnitClkGating:skl */ + WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + /* WaDisableLSQCROPERFforOCL:skl */ ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); if (ret) @@ -1174,6 +1189,63 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine) return ret; } + /* WaInsertDummyPushConstPs:bxt */ + if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); + + return 0; +} + +static int kbl_init_workarounds(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->dev->dev_private; + int ret; + + ret = gen9_init_workarounds(engine); + if (ret) + return ret; + + /* WaEnableGapsTsvCreditFix:kbl */ + I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) | + GEN9_GAPS_TSV_CREDIT_DISABLE)); + + /* WaDisableDynamicCreditSharing:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + WA_SET_BIT(GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); + + /* WaDisableFenceDestinationToSLM:kbl (pre-prod) */ + if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0)) + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FENCE_DEST_SLM_DISABLE); + + /* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes + * involving this register should also be added to WA batch as required. + */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) + /* WaDisableLSQCROPERFforOCL:kbl */ + I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | + GEN8_LQSC_RO_PERF_DIS); + + /* WaInsertDummyPushConstPs:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); + + /* WaDisableGafsUnitClkGating:kbl */ + WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableSbeCacheDispatchPortSharing:kbl */ + WA_SET_BIT_MASKED( + GEN7_HALF_SLICE_CHICKEN1, + GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + + /* WaDisableLSQCROPERFforOCL:kbl */ + ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); + if (ret) + return ret; + return 0; } @@ -1199,6 +1271,9 @@ int init_workarounds_ring(struct intel_engine_cs *engine) if (IS_BROXTON(dev)) return bxt_init_workarounds(engine); + if (IS_KABYLAKE(dev_priv)) + return kbl_init_workarounds(engine); + return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c index 22706c0..49bd5da 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c @@ -40,7 +40,8 @@ static int gf119_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern) { struct nvkm_device *device = outp->base.disp->engine.subdev.device; - nvkm_mask(device, 0x61c110, 0x0f0f0f0f, 0x01010101 * pattern); + const u32 soff = gf119_sor_soff(outp); + nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, 0x01010101 * pattern); return 0; } diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c index 4182a21..41cacec 100644 --- a/drivers/gpu/drm/sun4i/sun4i_crtc.c +++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c @@ -65,6 +65,14 @@ static void sun4i_crtc_disable(struct drm_crtc *crtc) DRM_DEBUG_DRIVER("Disabling the CRTC\n"); sun4i_tcon_disable(drv->tcon); + + if (crtc->state->event && !crtc->state->active) { + spin_lock_irq(&crtc->dev->event_lock); + drm_crtc_send_vblank_event(crtc, crtc->state->event); + spin_unlock_irq(&crtc->dev->event_lock); + + crtc->state->event = NULL; + } } static void sun4i_crtc_enable(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 257d2b4..937394c 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -92,7 +92,7 @@ static struct drm_driver sun4i_drv_driver = { /* Frame Buffer Operations */ /* VBlank Operations */ - .get_vblank_counter = drm_vblank_count, + .get_vblank_counter = drm_vblank_no_hw_counter, .enable_vblank = sun4i_drv_enable_vblank, .disable_vblank = sun4i_drv_disable_vblank, }; @@ -310,6 +310,7 @@ static int sun4i_drv_probe(struct platform_device *pdev) count += sun4i_drv_add_endpoints(&pdev->dev, &match, pipeline); + of_node_put(pipeline); DRM_DEBUG_DRIVER("Queued %d outputs on pipeline %d\n", count, i); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 39386f5..a71cf98 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1034,9 +1034,9 @@ out_unlock: return ret; } -static bool ttm_bo_mem_compat(struct ttm_placement *placement, - struct ttm_mem_reg *mem, - uint32_t *new_flags) +bool ttm_bo_mem_compat(struct ttm_placement *placement, + struct ttm_mem_reg *mem, + uint32_t *new_flags) { int i; @@ -1068,6 +1068,7 @@ static bool ttm_bo_mem_compat(struct ttm_placement *placement, return false; } +EXPORT_SYMBOL(ttm_bo_mem_compat); int ttm_bo_validate(struct ttm_buffer_object *bo, struct ttm_placement *placement, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c index 9b078a4..0cd8890 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c @@ -49,6 +49,7 @@ int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv, { struct ttm_buffer_object *bo = &buf->base; int ret; + uint32_t new_flags; ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); if (unlikely(ret != 0)) @@ -60,7 +61,12 @@ int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv, if (unlikely(ret != 0)) goto err; - ret = ttm_bo_validate(bo, placement, interruptible, false); + if (buf->pin_count > 0) + ret = ttm_bo_mem_compat(placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + else + ret = ttm_bo_validate(bo, placement, interruptible, false); + if (!ret) vmw_bo_pin_reserved(buf, true); @@ -91,6 +97,7 @@ int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv, { struct ttm_buffer_object *bo = &buf->base; int ret; + uint32_t new_flags; ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); if (unlikely(ret != 0)) @@ -102,6 +109,12 @@ int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv, if (unlikely(ret != 0)) goto err; + if (buf->pin_count > 0) { + ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + goto out_unreserve; + } + ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, interruptible, false); if (likely(ret == 0) || ret == -ERESTARTSYS) @@ -161,6 +174,7 @@ int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv, struct ttm_placement placement; struct ttm_place place; int ret = 0; + uint32_t new_flags; place = vmw_vram_placement.placement[0]; place.lpfn = bo->num_pages; @@ -185,10 +199,15 @@ int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv, */ if (bo->mem.mem_type == TTM_PL_VRAM && bo->mem.start < bo->num_pages && - bo->mem.start > 0) + bo->mem.start > 0 && + buf->pin_count == 0) (void) ttm_bo_validate(bo, &vmw_sys_placement, false, false); - ret = ttm_bo_validate(bo, &placement, interruptible, false); + if (buf->pin_count > 0) + ret = ttm_bo_mem_compat(&placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + else + ret = ttm_bo_validate(bo, &placement, interruptible, false); /* For some reason we didn't end up at the start of vram */ WARN_ON(ret == 0 && bo->offset != 0); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 9fcd820..8d528fc 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -233,6 +233,7 @@ static int vmw_force_iommu; static int vmw_restrict_iommu; static int vmw_force_coherent; static int vmw_restrict_dma_mask; +static int vmw_assume_16bpp; static int vmw_probe(struct pci_dev *, const struct pci_device_id *); static void vmw_master_init(struct vmw_master *); @@ -249,6 +250,8 @@ MODULE_PARM_DESC(force_coherent, "Force coherent TTM pages"); module_param_named(force_coherent, vmw_force_coherent, int, 0600); MODULE_PARM_DESC(restrict_dma_mask, "Restrict DMA mask to 44 bits with IOMMU"); module_param_named(restrict_dma_mask, vmw_restrict_dma_mask, int, 0600); +MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes"); +module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600); static void vmw_print_capabilities(uint32_t capabilities) @@ -660,6 +663,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) dev_priv->vram_start = pci_resource_start(dev->pdev, 1); dev_priv->mmio_start = pci_resource_start(dev->pdev, 2); + dev_priv->assume_16bpp = !!vmw_assume_16bpp; + dev_priv->enable_fb = enable_fbdev; vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2); @@ -706,6 +711,13 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) vmw_read(dev_priv, SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB); + /* + * Workaround for low memory 2D VMs to compensate for the + * allocation taken by fbdev + */ + if (!(dev_priv->capabilities & SVGA_CAP_3D)) + mem_size *= 2; + dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE; dev_priv->prim_bb_mem = vmw_read(dev_priv, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 1980e2a..89fb194 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -386,6 +386,7 @@ struct vmw_private { spinlock_t hw_lock; spinlock_t cap_lock; bool has_dx; + bool assume_16bpp; /* * VGA registers. diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 679a4cb..d2d9395 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -517,28 +517,6 @@ static int vmw_fb_kms_framebuffer(struct fb_info *info) par->set_fb = &vfb->base; - if (!par->bo_ptr) { - /* - * Pin before mapping. Since we don't know in what placement - * to pin, call into KMS to do it for us. - */ - ret = vfb->pin(vfb); - if (ret) { - DRM_ERROR("Could not pin the fbdev framebuffer.\n"); - return ret; - } - - ret = ttm_bo_kmap(&par->vmw_bo->base, 0, - par->vmw_bo->base.num_pages, &par->map); - if (ret) { - vfb->unpin(vfb); - DRM_ERROR("Could not map the fbdev framebuffer.\n"); - return ret; - } - - par->bo_ptr = ttm_kmap_obj_virtual(&par->map, &par->bo_iowrite); - } - return 0; } @@ -601,6 +579,31 @@ static int vmw_fb_set_par(struct fb_info *info) if (ret) goto out_unlock; + if (!par->bo_ptr) { + struct vmw_framebuffer *vfb = vmw_framebuffer_to_vfb(set.fb); + + /* + * Pin before mapping. Since we don't know in what placement + * to pin, call into KMS to do it for us. + */ + ret = vfb->pin(vfb); + if (ret) { + DRM_ERROR("Could not pin the fbdev framebuffer.\n"); + goto out_unlock; + } + + ret = ttm_bo_kmap(&par->vmw_bo->base, 0, + par->vmw_bo->base.num_pages, &par->map); + if (ret) { + vfb->unpin(vfb); + DRM_ERROR("Could not map the fbdev framebuffer.\n"); + goto out_unlock; + } + + par->bo_ptr = ttm_kmap_obj_virtual(&par->map, &par->bo_iowrite); + } + + vmw_fb_dirty_mark(par, par->fb_x, par->fb_y, par->set_fb->width, par->set_fb->height); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 55231cc..e29da45 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1553,14 +1553,10 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }; int i; - u32 assumed_bpp = 2; + u32 assumed_bpp = 4; - /* - * If using screen objects, then assume 32-bpp because that's what the - * SVGA device is assuming - */ - if (dev_priv->active_display_unit == vmw_du_screen_object) - assumed_bpp = 4; + if (dev_priv->assume_16bpp) + assumed_bpp = 2; if (dev_priv->active_display_unit == vmw_du_screen_target) { max_width = min(max_width, dev_priv->stdu_max_width); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index f0374f9..e57a0ba 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -300,6 +300,9 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg, break; } + if (retries == RETRIES) + return -EINVAL; + *msg_len = reply_len; *msg = reply; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 9ca818f..41932a7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -399,8 +399,10 @@ static int vmw_stdu_bind_fb(struct vmw_private *dev_priv, WARN_ON_ONCE(!stdu->defined); - if (!vfb->dmabuf && new_fb->width == mode->hdisplay && - new_fb->height == mode->vdisplay) + new_vfbs = (vfb->dmabuf) ? NULL : vmw_framebuffer_to_vfbs(new_fb); + + if (new_vfbs && new_vfbs->surface->base_size.width == mode->hdisplay && + new_vfbs->surface->base_size.height == mode->vdisplay) new_content_type = SAME_AS_DISPLAY; else if (vfb->dmabuf) new_content_type = SEPARATE_DMA; @@ -444,7 +446,6 @@ static int vmw_stdu_bind_fb(struct vmw_private *dev_priv, content_srf.mip_levels[0] = 1; content_srf.multisample_count = 0; } else { - new_vfbs = vmw_framebuffer_to_vfbs(new_fb); content_srf = *new_vfbs->surface; } @@ -464,7 +465,6 @@ static int vmw_stdu_bind_fb(struct vmw_private *dev_priv, return ret; } } else if (new_content_type == SAME_AS_DISPLAY) { - new_vfbs = vmw_framebuffer_to_vfbs(new_fb); new_display_srf = vmw_surface_reference(new_vfbs->surface); } diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c index cc6439a..041050e 100644 --- a/drivers/i2c/busses/i2c-qup.c +++ b/drivers/i2c/busses/i2c-qup.c @@ -1268,6 +1268,8 @@ static int qup_i2c_xfer_v2(struct i2c_adapter *adap, } } + idx = 0; + do { if (msgs[idx].len == 0) { ret = -EINVAL; diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 445398c3..b126dba 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -912,7 +912,7 @@ static int tegra_i2c_probe(struct platform_device *pdev) ret = tegra_i2c_init(i2c_dev); if (ret) { dev_err(&pdev->dev, "Failed to initialize i2c controller"); - goto unprepare_div_clk; + goto disable_div_clk; } ret = devm_request_irq(&pdev->dev, i2c_dev->irq, diff --git a/drivers/i2c/i2c-boardinfo.c b/drivers/i2c/i2c-boardinfo.c index e33022e..6e5fac6 100644 --- a/drivers/i2c/i2c-boardinfo.c +++ b/drivers/i2c/i2c-boardinfo.c @@ -56,9 +56,7 @@ EXPORT_SYMBOL_GPL(__i2c_first_dynamic_bus_num); * The board info passed can safely be __initdata, but be careful of embedded * pointers (for platform_data, functions, etc) since that won't be copied. */ -int __init -i2c_register_board_info(int busnum, - struct i2c_board_info const *info, unsigned len) +int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned len) { int status; diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c index 26e7c51..c6a90b4 100644 --- a/drivers/i2c/muxes/i2c-mux-reg.c +++ b/drivers/i2c/muxes/i2c-mux-reg.c @@ -145,7 +145,7 @@ static int i2c_mux_reg_probe_dt(struct regmux *mux, mux->data.idle_in_use = true; /* map address from "reg" if exists */ - if (of_address_to_resource(np, 0, &res)) { + if (of_address_to_resource(np, 0, &res) == 0) { mux->data.reg_size = resource_size(&res); mux->data.reg = devm_ioremap_resource(&pdev->dev, &res); if (IS_ERR(mux->data.reg)) diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index a5793c8..60df4f8 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -530,6 +530,7 @@ static PORT_PMA_ATTR(port_xmit_data , 12, 32, 192); static PORT_PMA_ATTR(port_rcv_data , 13, 32, 224); static PORT_PMA_ATTR(port_xmit_packets , 14, 32, 256); static PORT_PMA_ATTR(port_rcv_packets , 15, 32, 288); +static PORT_PMA_ATTR(port_xmit_wait , 0, 32, 320); /* * Counters added by extended set @@ -560,6 +561,7 @@ static struct attribute *pma_attrs[] = { &port_pma_attr_port_rcv_data.attr.attr, &port_pma_attr_port_xmit_packets.attr.attr, &port_pma_attr_port_rcv_packets.attr.attr, + &port_pma_attr_port_xmit_wait.attr.attr, NULL }; @@ -579,6 +581,7 @@ static struct attribute *pma_attrs_ext[] = { &port_pma_attr_ext_port_xmit_data.attr.attr, &port_pma_attr_ext_port_rcv_data.attr.attr, &port_pma_attr_ext_port_xmit_packets.attr.attr, + &port_pma_attr_port_xmit_wait.attr.attr, &port_pma_attr_ext_port_rcv_packets.attr.attr, &port_pma_attr_ext_unicast_rcv_packets.attr.attr, &port_pma_attr_ext_unicast_xmit_packets.attr.attr, @@ -604,6 +607,7 @@ static struct attribute *pma_attrs_noietf[] = { &port_pma_attr_ext_port_rcv_data.attr.attr, &port_pma_attr_ext_port_xmit_packets.attr.attr, &port_pma_attr_ext_port_rcv_packets.attr.attr, + &port_pma_attr_port_xmit_wait.attr.attr, NULL }; diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index f5de851..dad4d0e 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -14113,8 +14113,14 @@ static int init_asic_data(struct hfi1_devdata *dd) { unsigned long flags; struct hfi1_devdata *tmp, *peer = NULL; + struct hfi1_asic_data *asic_data; int ret = 0; + /* pre-allocate the asic structure in case we are the first device */ + asic_data = kzalloc(sizeof(*dd->asic_data), GFP_KERNEL); + if (!asic_data) + return -ENOMEM; + spin_lock_irqsave(&hfi1_devs_lock, flags); /* Find our peer device */ list_for_each_entry(tmp, &hfi1_dev_list, list) { @@ -14126,18 +14132,14 @@ static int init_asic_data(struct hfi1_devdata *dd) } if (peer) { + /* use already allocated structure */ dd->asic_data = peer->asic_data; + kfree(asic_data); } else { - dd->asic_data = kzalloc(sizeof(*dd->asic_data), GFP_KERNEL); - if (!dd->asic_data) { - ret = -ENOMEM; - goto done; - } + dd->asic_data = asic_data; mutex_init(&dd->asic_data->asic_resource_mutex); } dd->asic_data->dds[dd->hfi1_id] = dd; /* self back-pointer */ - -done: spin_unlock_irqrestore(&hfi1_devs_lock, flags); return ret; } diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 1e503ad..be91f6f 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -678,8 +678,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) u32 tlen = packet->tlen; struct rvt_qp *qp = packet->qp; bool has_grh = rcv_flags & HFI1_HAS_GRH; - bool sc4_bit = has_sc4_bit(packet); - u8 sc; + u8 sc5 = hdr2sc((struct hfi1_message_header *)hdr, packet->rhf); u32 bth1; int is_mcast; struct ib_grh *grh = NULL; @@ -697,10 +696,8 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) */ struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); u32 lqpn = be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK; - u8 sl, sc5; + u8 sl; - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; sl = ibp->sc_to_sl[sc5]; process_becn(ppd, sl, 0, lqpn, 0, IB_CC_SVCTYPE_UD); @@ -717,10 +714,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) if (!is_mcast && (opcode != IB_OPCODE_CNP) && bth1 & HFI1_FECN_SMASK) { u16 slid = be16_to_cpu(hdr->lrh[3]); - u8 sc5; - - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; return_cnp(ibp, qp, src_qp, pkey, dlid, slid, sc5, grh); } @@ -745,10 +738,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) if (qp->ibqp.qp_num > 1) { struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); u16 slid; - u8 sc5; - - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; slid = be16_to_cpu(hdr->lrh[3]); if (unlikely(rcv_pkey_check(ppd, pkey, sc5, slid))) { @@ -790,10 +779,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) /* Received on QP0, and so by definition, this is an SMP */ struct opa_smp *smp = (struct opa_smp *)data; u16 slid = be16_to_cpu(hdr->lrh[3]); - u8 sc5; - - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; if (opa_smp_check(ibp, pkey, sc5, qp, slid, smp)) goto drop; @@ -890,9 +875,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) } wc.slid = be16_to_cpu(hdr->lrh[3]); - sc = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc |= sc4_bit; - wc.sl = ibp->sc_to_sl[sc]; + wc.sl = ibp->sc_to_sl[sc5]; /* * Save the LMC lower bits if the destination LID is a unicast LID. diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index c963cad..6e90813 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -600,8 +600,7 @@ static enum i40iw_status_code i40iw_create_cqp(struct i40iw_device *iwdev) cqp_init_info.scratch_array = cqp->scratch_array; status = dev->cqp_ops->cqp_init(dev->cqp, &cqp_init_info); if (status) { - i40iw_pr_err("cqp init status %d maj_err %d min_err %d\n", - status, maj_err, min_err); + i40iw_pr_err("cqp init status %d\n", status); goto exit; } status = dev->cqp_ops->cqp_create(dev->cqp, true, &maj_err, &min_err); diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 33959ed..283b64c 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -1474,6 +1474,7 @@ static int i40iw_hw_alloc_stag(struct i40iw_device *iwdev, struct i40iw_mr *iwmr info->stag_idx = iwmr->stag >> I40IW_CQPSQ_STAG_IDX_SHIFT; info->pd_id = iwpd->sc_pd.pd_id; info->total_len = iwmr->length; + info->remote_access = true; cqp_info->cqp_cmd = OP_ALLOC_STAG; cqp_info->post_sq = 1; cqp_info->in.u.alloc_stag.dev = &iwdev->sc_dev; diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 8db8405..768085f 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -232,7 +232,7 @@ static void stamp_send_wqe(struct mlx4_ib_qp *qp, int n, int size) } } else { ctrl = buf = get_send_wqe(qp, n & (qp->sq.wqe_cnt - 1)); - s = (ctrl->fence_size & 0x3f) << 4; + s = (ctrl->qpn_vlan.fence_size & 0x3f) << 4; for (i = 64; i < s; i += 64) { wqe = buf + i; *wqe = cpu_to_be32(0xffffffff); @@ -264,7 +264,7 @@ static void post_nop_wqe(struct mlx4_ib_qp *qp, int n, int size) inl->byte_count = cpu_to_be32(1 << 31 | (size - s - sizeof *inl)); } ctrl->srcrb_flags = 0; - ctrl->fence_size = size / 16; + ctrl->qpn_vlan.fence_size = size / 16; /* * Make sure descriptor is fully written before setting ownership bit * (because HW can start executing as soon as we do). @@ -1992,7 +1992,8 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, ctrl = get_send_wqe(qp, i); ctrl->owner_opcode = cpu_to_be32(1 << 31); if (qp->sq_max_wqes_per_wr == 1) - ctrl->fence_size = 1 << (qp->sq.wqe_shift - 4); + ctrl->qpn_vlan.fence_size = + 1 << (qp->sq.wqe_shift - 4); stamp_send_wqe(qp, i, 1 << qp->sq.wqe_shift); } @@ -3169,8 +3170,8 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, wmb(); *lso_wqe = lso_hdr_sz; - ctrl->fence_size = (wr->send_flags & IB_SEND_FENCE ? - MLX4_WQE_CTRL_FENCE : 0) | size; + ctrl->qpn_vlan.fence_size = (wr->send_flags & IB_SEND_FENCE ? + MLX4_WQE_CTRL_FENCE : 0) | size; /* * Make sure descriptor is fully written before diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 3438e98..a529a45 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -1431,6 +1431,9 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id int ep_irq_in_idx; int i, error; + if (intf->cur_altsetting->desc.bNumEndpoints != 2) + return -ENODEV; + for (i = 0; xpad_device[i].idVendor; i++) { if ((le16_to_cpu(udev->descriptor.idVendor) == xpad_device[i].idVendor) && (le16_to_cpu(udev->descriptor.idProduct) == xpad_device[i].idProduct)) diff --git a/drivers/input/rmi4/rmi_bus.c b/drivers/input/rmi4/rmi_bus.c index b368b05..253df96 100644 --- a/drivers/input/rmi4/rmi_bus.c +++ b/drivers/input/rmi4/rmi_bus.c @@ -157,11 +157,11 @@ static int rmi_function_match(struct device *dev, struct device_driver *drv) static void rmi_function_of_probe(struct rmi_function *fn) { char of_name[9]; + struct device_node *node = fn->rmi_dev->xport->dev->of_node; snprintf(of_name, sizeof(of_name), "rmi4-f%02x", fn->fd.function_number); - fn->dev.of_node = of_find_node_by_name( - fn->rmi_dev->xport->dev->of_node, of_name); + fn->dev.of_node = of_get_child_by_name(node, of_name); } #else static inline void rmi_function_of_probe(struct rmi_function *fn) diff --git a/drivers/input/rmi4/rmi_f12.c b/drivers/input/rmi4/rmi_f12.c index 8dd3fb5..88e9155 100644 --- a/drivers/input/rmi4/rmi_f12.c +++ b/drivers/input/rmi4/rmi_f12.c @@ -66,7 +66,7 @@ static int rmi_f12_read_sensor_tuning(struct f12_data *f12) struct rmi_device *rmi_dev = fn->rmi_dev; int ret; int offset; - u8 buf[14]; + u8 buf[15]; int pitch_x = 0; int pitch_y = 0; int clip_x_low = 0; @@ -86,9 +86,10 @@ static int rmi_f12_read_sensor_tuning(struct f12_data *f12) offset = rmi_register_desc_calc_reg_offset(&f12->control_reg_desc, 8); - if (item->reg_size > 14) { - dev_err(&fn->dev, "F12 control8 should be 14 bytes, not: %ld\n", - item->reg_size); + if (item->reg_size > sizeof(buf)) { + dev_err(&fn->dev, + "F12 control8 should be no bigger than %zd bytes, not: %ld\n", + sizeof(buf), item->reg_size); return -ENODEV; } diff --git a/drivers/input/touchscreen/ts4800-ts.c b/drivers/input/touchscreen/ts4800-ts.c index 3c3dd78..fed73ee 100644 --- a/drivers/input/touchscreen/ts4800-ts.c +++ b/drivers/input/touchscreen/ts4800-ts.c @@ -118,6 +118,13 @@ static int ts4800_parse_dt(struct platform_device *pdev, return -ENODEV; } + ts->regmap = syscon_node_to_regmap(syscon_np); + of_node_put(syscon_np); + if (IS_ERR(ts->regmap)) { + dev_err(dev, "cannot get parent's regmap\n"); + return PTR_ERR(ts->regmap); + } + error = of_property_read_u32_index(np, "syscon", 1, ®); if (error < 0) { dev_err(dev, "no offset in syscon\n"); @@ -134,12 +141,6 @@ static int ts4800_parse_dt(struct platform_device *pdev, ts->bit = BIT(bit); - ts->regmap = syscon_node_to_regmap(syscon_np); - if (IS_ERR(ts->regmap)) { - dev_err(dev, "cannot get parent's regmap\n"); - return PTR_ERR(ts->regmap); - } - return 0; } diff --git a/drivers/input/touchscreen/tsc2004.c b/drivers/input/touchscreen/tsc2004.c index 7295c19..6fe55d5 100644 --- a/drivers/input/touchscreen/tsc2004.c +++ b/drivers/input/touchscreen/tsc2004.c @@ -22,6 +22,11 @@ #include <linux/regmap.h> #include "tsc200x-core.h" +static const struct input_id tsc2004_input_id = { + .bustype = BUS_I2C, + .product = 2004, +}; + static int tsc2004_cmd(struct device *dev, u8 cmd) { u8 tx = TSC200X_CMD | TSC200X_CMD_12BIT | cmd; @@ -42,7 +47,7 @@ static int tsc2004_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { - return tsc200x_probe(&i2c->dev, i2c->irq, BUS_I2C, + return tsc200x_probe(&i2c->dev, i2c->irq, &tsc2004_input_id, devm_regmap_init_i2c(i2c, &tsc200x_regmap_config), tsc2004_cmd); } diff --git a/drivers/input/touchscreen/tsc2005.c b/drivers/input/touchscreen/tsc2005.c index b9f593d..f2c5f0e47 100644 --- a/drivers/input/touchscreen/tsc2005.c +++ b/drivers/input/touchscreen/tsc2005.c @@ -24,6 +24,11 @@ #include <linux/regmap.h> #include "tsc200x-core.h" +static const struct input_id tsc2005_input_id = { + .bustype = BUS_SPI, + .product = 2005, +}; + static int tsc2005_cmd(struct device *dev, u8 cmd) { u8 tx = TSC200X_CMD | TSC200X_CMD_12BIT | cmd; @@ -62,7 +67,7 @@ static int tsc2005_probe(struct spi_device *spi) if (error) return error; - return tsc200x_probe(&spi->dev, spi->irq, BUS_SPI, + return tsc200x_probe(&spi->dev, spi->irq, &tsc2005_input_id, devm_regmap_init_spi(spi, &tsc200x_regmap_config), tsc2005_cmd); } diff --git a/drivers/input/touchscreen/tsc200x-core.c b/drivers/input/touchscreen/tsc200x-core.c index 15240c1..dfa7f1c 100644 --- a/drivers/input/touchscreen/tsc200x-core.c +++ b/drivers/input/touchscreen/tsc200x-core.c @@ -450,7 +450,7 @@ static void tsc200x_close(struct input_dev *input) mutex_unlock(&ts->mutex); } -int tsc200x_probe(struct device *dev, int irq, __u16 bustype, +int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id, struct regmap *regmap, int (*tsc200x_cmd)(struct device *dev, u8 cmd)) { @@ -547,9 +547,18 @@ int tsc200x_probe(struct device *dev, int irq, __u16 bustype, snprintf(ts->phys, sizeof(ts->phys), "%s/input-ts", dev_name(dev)); - input_dev->name = "TSC200X touchscreen"; + if (tsc_id->product == 2004) { + input_dev->name = "TSC200X touchscreen"; + } else { + input_dev->name = devm_kasprintf(dev, GFP_KERNEL, + "TSC%04d touchscreen", + tsc_id->product); + if (!input_dev->name) + return -ENOMEM; + } + input_dev->phys = ts->phys; - input_dev->id.bustype = bustype; + input_dev->id = *tsc_id; input_dev->dev.parent = dev; input_dev->evbit[0] = BIT(EV_ABS) | BIT(EV_KEY); input_dev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH); diff --git a/drivers/input/touchscreen/tsc200x-core.h b/drivers/input/touchscreen/tsc200x-core.h index 7a482d1..49a63a3 100644 --- a/drivers/input/touchscreen/tsc200x-core.h +++ b/drivers/input/touchscreen/tsc200x-core.h @@ -70,7 +70,7 @@ extern const struct regmap_config tsc200x_regmap_config; extern const struct dev_pm_ops tsc200x_pm_ops; -int tsc200x_probe(struct device *dev, int irq, __u16 bustype, +int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id, struct regmap *regmap, int (*tsc200x_cmd)(struct device *dev, u8 cmd)); int tsc200x_remove(struct device *dev); diff --git a/drivers/input/touchscreen/wacom_w8001.c b/drivers/input/touchscreen/wacom_w8001.c index 0c9191c..b6fc4bd 100644 --- a/drivers/input/touchscreen/wacom_w8001.c +++ b/drivers/input/touchscreen/wacom_w8001.c @@ -155,6 +155,7 @@ static void parse_multi_touch(struct w8001 *w8001) bool touch = data[0] & (1 << i); input_mt_slot(dev, i); + input_mt_report_slot_state(dev, MT_TOOL_FINGER, touch); if (touch) { x = (data[6 * i + 1] << 7) | data[6 * i + 2]; y = (data[6 * i + 3] << 7) | data[6 * i + 4]; @@ -522,6 +523,8 @@ static int w8001_setup_touch(struct w8001 *w8001, char *basename, 0, touch.x, 0, 0); input_set_abs_params(dev, ABS_MT_POSITION_Y, 0, touch.y, 0, 0); + input_set_abs_params(dev, ABS_MT_TOOL_TYPE, + 0, MT_TOOL_MAX, 0, 0); strlcat(basename, " 2FG", basename_sz); if (w8001->max_pen_x && w8001->max_pen_y) diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index d091def..59741ea 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1568,13 +1568,23 @@ static int __init amd_iommu_init_pci(void) break; } + /* + * Order is important here to make sure any unity map requirements are + * fulfilled. The unity mappings are created and written to the device + * table during the amd_iommu_init_api() call. + * + * After that we call init_device_table_dma() to make sure any + * uninitialized DTE will block DMA, and in the end we flush the caches + * of all IOMMUs to make sure the changes to the device table are + * active. + */ + ret = amd_iommu_init_api(); + init_device_table_dma(); for_each_iommu(iommu) iommu_flush_all_caches(iommu); - ret = amd_iommu_init_api(); - if (!ret) print_iommu_info(); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index cfe410e..323dac9 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4602,13 +4602,13 @@ static void free_all_cpu_cached_iovas(unsigned int cpu) for (i = 0; i < g_num_of_iommus; i++) { struct intel_iommu *iommu = g_iommus[i]; struct dmar_domain *domain; - u16 did; + int did; if (!iommu) continue; for (did = 0; did < cap_ndoms(iommu->cap); did++) { - domain = get_iommu_domain(iommu, did); + domain = get_iommu_domain(iommu, (u16)did); if (!domain) continue; diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 8a4adbeb..70ed1d0 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -718,7 +718,7 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, spin_lock_irqsave(&gic_lock, flags); gic_map_to_pin(intr, gic_cpu_pin); - gic_map_to_vpe(intr, vpe); + gic_map_to_vpe(intr, mips_cm_vp_id(vpe)); for (i = 0; i < min(gic_vpes, NR_CPUS); i++) clear_bit(intr, pcpu_masks[i].pcpu_mask); set_bit(intr, pcpu_masks[vpe].pcpu_mask); @@ -959,7 +959,7 @@ int gic_ipi_domain_match(struct irq_domain *d, struct device_node *node, switch (bus_token) { case DOMAIN_BUS_IPI: is_ipi = d->bus_token == bus_token; - return to_of_node(d->fwnode) == node && is_ipi; + return (!node || to_of_node(d->fwnode) == node) && is_ipi; break; default: return 0; diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index beb2841..3f1ab49 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -779,11 +779,31 @@ static const struct v4l2_dv_timings_cap adv76xx_timings_cap_digital = { V4L2_DV_BT_CAP_CUSTOM) }; -static inline const struct v4l2_dv_timings_cap * -adv76xx_get_dv_timings_cap(struct v4l2_subdev *sd) +/* + * Return the DV timings capabilities for the requested sink pad. As a special + * case, pad value -1 returns the capabilities for the currently selected input. + */ +static const struct v4l2_dv_timings_cap * +adv76xx_get_dv_timings_cap(struct v4l2_subdev *sd, int pad) { - return is_digital_input(sd) ? &adv76xx_timings_cap_digital : - &adv7604_timings_cap_analog; + if (pad == -1) { + struct adv76xx_state *state = to_state(sd); + + pad = state->selected_input; + } + + switch (pad) { + case ADV76XX_PAD_HDMI_PORT_A: + case ADV7604_PAD_HDMI_PORT_B: + case ADV7604_PAD_HDMI_PORT_C: + case ADV7604_PAD_HDMI_PORT_D: + return &adv76xx_timings_cap_digital; + + case ADV7604_PAD_VGA_RGB: + case ADV7604_PAD_VGA_COMP: + default: + return &adv7604_timings_cap_analog; + } } @@ -1329,7 +1349,7 @@ static int stdi2dv_timings(struct v4l2_subdev *sd, const struct v4l2_bt_timings *bt = &v4l2_dv_timings_presets[i].bt; if (!v4l2_valid_dv_timings(&v4l2_dv_timings_presets[i], - adv76xx_get_dv_timings_cap(sd), + adv76xx_get_dv_timings_cap(sd, -1), adv76xx_check_dv_timings, NULL)) continue; if (vtotal(bt) != stdi->lcf + 1) @@ -1430,18 +1450,22 @@ static int adv76xx_enum_dv_timings(struct v4l2_subdev *sd, return -EINVAL; return v4l2_enum_dv_timings_cap(timings, - adv76xx_get_dv_timings_cap(sd), adv76xx_check_dv_timings, NULL); + adv76xx_get_dv_timings_cap(sd, timings->pad), + adv76xx_check_dv_timings, NULL); } static int adv76xx_dv_timings_cap(struct v4l2_subdev *sd, struct v4l2_dv_timings_cap *cap) { struct adv76xx_state *state = to_state(sd); + unsigned int pad = cap->pad; if (cap->pad >= state->source_pad) return -EINVAL; - *cap = *adv76xx_get_dv_timings_cap(sd); + *cap = *adv76xx_get_dv_timings_cap(sd, pad); + cap->pad = pad; + return 0; } @@ -1450,9 +1474,9 @@ static int adv76xx_dv_timings_cap(struct v4l2_subdev *sd, static void adv76xx_fill_optional_dv_timings_fields(struct v4l2_subdev *sd, struct v4l2_dv_timings *timings) { - v4l2_find_dv_timings_cap(timings, adv76xx_get_dv_timings_cap(sd), - is_digital_input(sd) ? 250000 : 1000000, - adv76xx_check_dv_timings, NULL); + v4l2_find_dv_timings_cap(timings, adv76xx_get_dv_timings_cap(sd, -1), + is_digital_input(sd) ? 250000 : 1000000, + adv76xx_check_dv_timings, NULL); } static unsigned int adv7604_read_hdmi_pixelclock(struct v4l2_subdev *sd) @@ -1620,7 +1644,7 @@ static int adv76xx_s_dv_timings(struct v4l2_subdev *sd, bt = &timings->bt; - if (!v4l2_valid_dv_timings(timings, adv76xx_get_dv_timings_cap(sd), + if (!v4l2_valid_dv_timings(timings, adv76xx_get_dv_timings_cap(sd, -1), adv76xx_check_dv_timings, NULL)) return -ERANGE; diff --git a/drivers/media/radio/wl128x/fmdrv_common.c b/drivers/media/radio/wl128x/fmdrv_common.c index 3f9e6df..642b89c 100644 --- a/drivers/media/radio/wl128x/fmdrv_common.c +++ b/drivers/media/radio/wl128x/fmdrv_common.c @@ -1472,7 +1472,7 @@ static long fm_st_receive(void *arg, struct sk_buff *skb) * Called by ST layer to indicate protocol registration completion * status. */ -static void fm_st_reg_comp_cb(void *arg, char data) +static void fm_st_reg_comp_cb(void *arg, int data) { struct fmdev *fmdev; diff --git a/drivers/media/usb/airspy/airspy.c b/drivers/media/usb/airspy/airspy.c index 87c1293..92d9d42 100644 --- a/drivers/media/usb/airspy/airspy.c +++ b/drivers/media/usb/airspy/airspy.c @@ -1072,7 +1072,7 @@ static int airspy_probe(struct usb_interface *intf, if (ret) { dev_err(s->dev, "Failed to register as video device (%d)\n", ret); - goto err_unregister_v4l2_dev; + goto err_free_controls; } dev_info(s->dev, "Registered as %s\n", video_device_node_name(&s->vdev)); @@ -1081,7 +1081,6 @@ static int airspy_probe(struct usb_interface *intf, err_free_controls: v4l2_ctrl_handler_free(&s->hdl); -err_unregister_v4l2_dev: v4l2_device_unregister(&s->v4l2_dev); err_free_mem: kfree(s); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 28e5be2..528390f 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2171,7 +2171,7 @@ static int v4l_cropcap(const struct v4l2_ioctl_ops *ops, * The determine_valid_ioctls() call already should ensure * that this can never happen, but just in case... */ - if (WARN_ON(!ops->vidioc_cropcap && !ops->vidioc_cropcap)) + if (WARN_ON(!ops->vidioc_cropcap && !ops->vidioc_g_selection)) return -ENOTTY; if (ops->vidioc_cropcap) diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c index dcdbd58..0005159 100644 --- a/drivers/misc/ti-st/st_core.c +++ b/drivers/misc/ti-st/st_core.c @@ -141,7 +141,7 @@ static void st_send_frame(unsigned char chnl_id, struct st_data_s *st_gdata) * This function is being called with spin lock held, protocol drivers are * only expected to complete their waits and do nothing more than that. */ -static void st_reg_complete(struct st_data_s *st_gdata, char err) +static void st_reg_complete(struct st_data_s *st_gdata, int err) { unsigned char i = 0; pr_info(" %s ", __func__); diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index e62fde3..c5472e3 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -355,8 +355,10 @@ static struct mmc_blk_ioc_data *mmc_blk_ioctl_copy_from_user( goto idata_err; } - if (!idata->buf_bytes) + if (!idata->buf_bytes) { + idata->buf = NULL; return idata; + } idata->buf = kmalloc(idata->buf_bytes, GFP_KERNEL); if (!idata->buf) { @@ -1786,8 +1788,8 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq, packed_cmd_hdr = packed->cmd_hdr; memset(packed_cmd_hdr, 0, sizeof(packed->cmd_hdr)); - packed_cmd_hdr[0] = (packed->nr_entries << 16) | - (PACKED_CMD_WR << 8) | PACKED_CMD_VER; + packed_cmd_hdr[0] = cpu_to_le32((packed->nr_entries << 16) | + (PACKED_CMD_WR << 8) | PACKED_CMD_VER); hdr_blocks = mmc_large_sector(card) ? 8 : 1; /* @@ -1801,14 +1803,14 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq, ((brq->data.blocks * brq->data.blksz) >= card->ext_csd.data_tag_unit_size); /* Argument of CMD23 */ - packed_cmd_hdr[(i * 2)] = + packed_cmd_hdr[(i * 2)] = cpu_to_le32( (do_rel_wr ? MMC_CMD23_ARG_REL_WR : 0) | (do_data_tag ? MMC_CMD23_ARG_TAG_REQ : 0) | - blk_rq_sectors(prq); + blk_rq_sectors(prq)); /* Argument of CMD18 or CMD25 */ - packed_cmd_hdr[((i * 2)) + 1] = + packed_cmd_hdr[((i * 2)) + 1] = cpu_to_le32( mmc_card_blockaddr(card) ? - blk_rq_pos(prq) : blk_rq_pos(prq) << 9; + blk_rq_pos(prq) : blk_rq_pos(prq) << 9); packed->blocks += blk_rq_sectors(prq); i++; } diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index 86fac3e..c763b40 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -789,14 +789,16 @@ static int pxamci_probe(struct platform_device *pdev) gpio_direction_output(gpio_power, host->pdata->gpio_power_invert); } - if (gpio_is_valid(gpio_ro)) + if (gpio_is_valid(gpio_ro)) { ret = mmc_gpio_request_ro(mmc, gpio_ro); - if (ret) { - dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro); - goto out; - } else { - mmc->caps2 |= host->pdata->gpio_card_ro_invert ? - 0 : MMC_CAP2_RO_ACTIVE_HIGH; + if (ret) { + dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", + gpio_ro); + goto out; + } else { + mmc->caps2 |= host->pdata->gpio_card_ro_invert ? + 0 : MMC_CAP2_RO_ACTIVE_HIGH; + } } if (gpio_is_valid(gpio_cd)) diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c index 08e1588..a136da8 100644 --- a/drivers/mtd/nand/omap2.c +++ b/drivers/mtd/nand/omap2.c @@ -1657,8 +1657,11 @@ static int omap_get_dt_info(struct device *dev, struct omap_nand_info *info) /* detect availability of ELM module. Won't be present pre-OMAP4 */ info->elm_of_node = of_parse_phandle(child, "ti,elm-id", 0); - if (!info->elm_of_node) - dev_dbg(dev, "ti,elm-id not in DT\n"); + if (!info->elm_of_node) { + info->elm_of_node = of_parse_phandle(child, "elm_id", 0); + if (!info->elm_of_node) + dev_dbg(dev, "ti,elm-id not in DT\n"); + } /* select ecc-scheme for NAND */ if (of_property_read_string(child, "ti,nand-ecc-opt", &s)) { diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b571ed9..1f276fa 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1422,7 +1422,16 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) return -EINVAL; } - if (slave_ops->ndo_set_mac_address == NULL) { + if (slave_dev->type == ARPHRD_INFINIBAND && + BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { + netdev_warn(bond_dev, "Type (%d) supports only active-backup mode\n", + slave_dev->type); + res = -EOPNOTSUPP; + goto err_undo_flags; + } + + if (!slave_ops->ndo_set_mac_address || + slave_dev->type == ARPHRD_INFINIBAND) { netdev_warn(bond_dev, "The slave device specified does not support setting the MAC address\n"); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && bond->params.fail_over_mac != BOND_FOM_ACTIVE) { diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index db760e8..b8df0f5 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -446,7 +446,11 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev, if (err < 0) return err; - return register_netdevice(bond_dev); + err = register_netdevice(bond_dev); + + netif_carrier_off(bond_dev); + + return err; } static size_t bond_get_size(const struct net_device *bond_dev) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 5cb06f7..d36aedd 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -216,107 +216,48 @@ static int mv88e6xxx_write(struct mv88e6xxx_chip *chip, return 0; } -static int _mv88e6xxx_reg_read(struct mv88e6xxx_chip *chip, int addr, int reg) +/* Indirect write to single pointer-data register with an Update bit */ +static int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, + u16 update) { u16 val; - int err; - - err = mv88e6xxx_read(chip, addr, reg, &val); - if (err) - return err; + int i, err; - return val; -} + /* Wait until the previous operation is completed */ + for (i = 0; i < 16; ++i) { + err = mv88e6xxx_read(chip, addr, reg, &val); + if (err) + return err; -static int mv88e6xxx_reg_read(struct mv88e6xxx_chip *chip, int addr, int reg) -{ - int ret; + if (!(val & BIT(15))) + break; + } - mutex_lock(&chip->reg_lock); - ret = _mv88e6xxx_reg_read(chip, addr, reg); - mutex_unlock(&chip->reg_lock); + if (i == 16) + return -ETIMEDOUT; - return ret; -} + /* Set the Update bit to trigger a write operation */ + val = BIT(15) | update; -static int _mv88e6xxx_reg_write(struct mv88e6xxx_chip *chip, int addr, - int reg, u16 val) -{ return mv88e6xxx_write(chip, addr, reg, val); } -static int mv88e6xxx_reg_write(struct mv88e6xxx_chip *chip, int addr, - int reg, u16 val) -{ - int ret; - - mutex_lock(&chip->reg_lock); - ret = _mv88e6xxx_reg_write(chip, addr, reg, val); - mutex_unlock(&chip->reg_lock); - - return ret; -} - -static int mv88e6xxx_set_addr_direct(struct dsa_switch *ds, u8 *addr) +static int _mv88e6xxx_reg_read(struct mv88e6xxx_chip *chip, int addr, int reg) { - struct mv88e6xxx_chip *chip = ds_to_priv(ds); + u16 val; int err; - err = mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_MAC_01, - (addr[0] << 8) | addr[1]); - if (err) - return err; - - err = mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_MAC_23, - (addr[2] << 8) | addr[3]); + err = mv88e6xxx_read(chip, addr, reg, &val); if (err) return err; - return mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_MAC_45, - (addr[4] << 8) | addr[5]); -} - -static int mv88e6xxx_set_addr_indirect(struct dsa_switch *ds, u8 *addr) -{ - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - int ret; - int i; - - for (i = 0; i < 6; i++) { - int j; - - /* Write the MAC address byte. */ - ret = mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_SWITCH_MAC, - GLOBAL2_SWITCH_MAC_BUSY | - (i << 8) | addr[i]); - if (ret) - return ret; - - /* Wait for the write to complete. */ - for (j = 0; j < 16; j++) { - ret = mv88e6xxx_reg_read(chip, REG_GLOBAL2, - GLOBAL2_SWITCH_MAC); - if (ret < 0) - return ret; - - if ((ret & GLOBAL2_SWITCH_MAC_BUSY) == 0) - break; - } - if (j == 16) - return -ETIMEDOUT; - } - - return 0; + return val; } -static int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr) +static int _mv88e6xxx_reg_write(struct mv88e6xxx_chip *chip, int addr, + int reg, u16 val) { - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - - if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_SWITCH_MAC)) - return mv88e6xxx_set_addr_indirect(ds, addr); - else - return mv88e6xxx_set_addr_direct(ds, addr); + return mv88e6xxx_write(chip, addr, reg, val); } static int mv88e6xxx_mdio_read_direct(struct mv88e6xxx_chip *chip, @@ -897,259 +838,12 @@ static int _mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int reg, int offset, return -ETIMEDOUT; } -static int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int reg, - int offset, u16 mask) -{ - int ret; - - mutex_lock(&chip->reg_lock); - ret = _mv88e6xxx_wait(chip, reg, offset, mask); - mutex_unlock(&chip->reg_lock); - - return ret; -} - static int mv88e6xxx_mdio_wait(struct mv88e6xxx_chip *chip) { return _mv88e6xxx_wait(chip, REG_GLOBAL2, GLOBAL2_SMI_OP, GLOBAL2_SMI_OP_BUSY); } -static int mv88e6xxx_eeprom_load_wait(struct dsa_switch *ds) -{ - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - - return mv88e6xxx_wait(chip, REG_GLOBAL2, GLOBAL2_EEPROM_OP, - GLOBAL2_EEPROM_OP_LOAD); -} - -static int mv88e6xxx_eeprom_busy_wait(struct dsa_switch *ds) -{ - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - - return mv88e6xxx_wait(chip, REG_GLOBAL2, GLOBAL2_EEPROM_OP, - GLOBAL2_EEPROM_OP_BUSY); -} - -static int mv88e6xxx_read_eeprom_word(struct dsa_switch *ds, int addr) -{ - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - int ret; - - mutex_lock(&chip->eeprom_mutex); - - ret = mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_EEPROM_OP, - GLOBAL2_EEPROM_OP_READ | - (addr & GLOBAL2_EEPROM_OP_ADDR_MASK)); - if (ret < 0) - goto error; - - ret = mv88e6xxx_eeprom_busy_wait(ds); - if (ret < 0) - goto error; - - ret = mv88e6xxx_reg_read(chip, REG_GLOBAL2, GLOBAL2_EEPROM_DATA); -error: - mutex_unlock(&chip->eeprom_mutex); - return ret; -} - -static int mv88e6xxx_get_eeprom_len(struct dsa_switch *ds) -{ - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - - if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEPROM)) - return chip->eeprom_len; - - return 0; -} - -static int mv88e6xxx_get_eeprom(struct dsa_switch *ds, - struct ethtool_eeprom *eeprom, u8 *data) -{ - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - int offset; - int len; - int ret; - - if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEPROM)) - return -EOPNOTSUPP; - - offset = eeprom->offset; - len = eeprom->len; - eeprom->len = 0; - - eeprom->magic = 0xc3ec4951; - - ret = mv88e6xxx_eeprom_load_wait(ds); - if (ret < 0) - return ret; - - if (offset & 1) { - int word; - - word = mv88e6xxx_read_eeprom_word(ds, offset >> 1); - if (word < 0) - return word; - - *data++ = (word >> 8) & 0xff; - - offset++; - len--; - eeprom->len++; - } - - while (len >= 2) { - int word; - - word = mv88e6xxx_read_eeprom_word(ds, offset >> 1); - if (word < 0) - return word; - - *data++ = word & 0xff; - *data++ = (word >> 8) & 0xff; - - offset += 2; - len -= 2; - eeprom->len += 2; - } - - if (len) { - int word; - - word = mv88e6xxx_read_eeprom_word(ds, offset >> 1); - if (word < 0) - return word; - - *data++ = word & 0xff; - - offset++; - len--; - eeprom->len++; - } - - return 0; -} - -static int mv88e6xxx_eeprom_is_readonly(struct dsa_switch *ds) -{ - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - int ret; - - ret = mv88e6xxx_reg_read(chip, REG_GLOBAL2, GLOBAL2_EEPROM_OP); - if (ret < 0) - return ret; - - if (!(ret & GLOBAL2_EEPROM_OP_WRITE_EN)) - return -EROFS; - - return 0; -} - -static int mv88e6xxx_write_eeprom_word(struct dsa_switch *ds, int addr, - u16 data) -{ - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - int ret; - - mutex_lock(&chip->eeprom_mutex); - - ret = mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_EEPROM_DATA, data); - if (ret < 0) - goto error; - - ret = mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_EEPROM_OP, - GLOBAL2_EEPROM_OP_WRITE | - (addr & GLOBAL2_EEPROM_OP_ADDR_MASK)); - if (ret < 0) - goto error; - - ret = mv88e6xxx_eeprom_busy_wait(ds); -error: - mutex_unlock(&chip->eeprom_mutex); - return ret; -} - -static int mv88e6xxx_set_eeprom(struct dsa_switch *ds, - struct ethtool_eeprom *eeprom, u8 *data) -{ - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - int offset; - int ret; - int len; - - if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEPROM)) - return -EOPNOTSUPP; - - if (eeprom->magic != 0xc3ec4951) - return -EINVAL; - - ret = mv88e6xxx_eeprom_is_readonly(ds); - if (ret) - return ret; - - offset = eeprom->offset; - len = eeprom->len; - eeprom->len = 0; - - ret = mv88e6xxx_eeprom_load_wait(ds); - if (ret < 0) - return ret; - - if (offset & 1) { - int word; - - word = mv88e6xxx_read_eeprom_word(ds, offset >> 1); - if (word < 0) - return word; - - word = (*data++ << 8) | (word & 0xff); - - ret = mv88e6xxx_write_eeprom_word(ds, offset >> 1, word); - if (ret < 0) - return ret; - - offset++; - len--; - eeprom->len++; - } - - while (len >= 2) { - int word; - - word = *data++; - word |= *data++ << 8; - - ret = mv88e6xxx_write_eeprom_word(ds, offset >> 1, word); - if (ret < 0) - return ret; - - offset += 2; - len -= 2; - eeprom->len += 2; - } - - if (len) { - int word; - - word = mv88e6xxx_read_eeprom_word(ds, offset >> 1); - if (word < 0) - return word; - - word = (word & 0xff00) | *data++; - - ret = mv88e6xxx_write_eeprom_word(ds, offset >> 1, word); - if (ret < 0) - return ret; - - offset++; - len--; - eeprom->len++; - } - - return 0; -} - static int _mv88e6xxx_atu_wait(struct mv88e6xxx_chip *chip) { return _mv88e6xxx_wait(chip, REG_GLOBAL, GLOBAL_ATU_OP, @@ -1460,9 +1154,6 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port, int stp_state; int err; - if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_PORTSTATE)) - return; - switch (state) { case BR_STATE_DISABLED: stp_state = PORT_CONTROL_STATE_DISABLED; @@ -2398,11 +2089,6 @@ static int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans) { - struct mv88e6xxx_chip *chip = ds_to_priv(ds); - - if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_ATU)) - return -EOPNOTSUPP; - /* We don't need any dynamic resource from the kernel (yet), * so skip the prepare phase. */ @@ -2418,9 +2104,6 @@ static void mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port, GLOBAL_ATU_DATA_STATE_UC_STATIC; struct mv88e6xxx_chip *chip = ds_to_priv(ds); - if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_ATU)) - return; - mutex_lock(&chip->reg_lock); if (_mv88e6xxx_port_fdb_load(chip, port, fdb->addr, fdb->vid, state)) netdev_err(ds->ports[port].netdev, @@ -2434,9 +2117,6 @@ static int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, struct mv88e6xxx_chip *chip = ds_to_priv(ds); int ret; - if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_ATU)) - return -EOPNOTSUPP; - mutex_lock(&chip->reg_lock); ret = _mv88e6xxx_port_fdb_load(chip, port, fdb->addr, fdb->vid, GLOBAL_ATU_DATA_STATE_UNUSED); @@ -2542,9 +2222,6 @@ static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port, u16 fid; int err; - if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_ATU)) - return -EOPNOTSUPP; - mutex_lock(&chip->reg_lock); /* Dump port's default Filtering Information Database (VLAN ID 0) */ @@ -2587,9 +2264,6 @@ static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, struct mv88e6xxx_chip *chip = ds_to_priv(ds); int i, err = 0; - if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VLANTABLE)) - return -EOPNOTSUPP; - mutex_lock(&chip->reg_lock); /* Assign the bridge and remap each port's VLANTable */ @@ -2614,9 +2288,6 @@ static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port) struct net_device *bridge = chip->ports[port].bridge_dev; int i; - if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VLANTABLE)) - return; - mutex_lock(&chip->reg_lock); /* Unassign the bridge and remap each port's VLANTable */ @@ -2744,6 +2415,17 @@ static int mv88e6xxx_power_on_serdes(struct mv88e6xxx_chip *chip) return ret; } +static int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, + int reg, u16 *val) +{ + int addr = chip->info->port_base_addr + port; + + if (port >= chip->info->num_ports) + return -EINVAL; + + return mv88e6xxx_read(chip, addr, reg, val); +} + static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) { struct dsa_switch *ds = chip->ds; @@ -3016,13 +2698,70 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return 0; } -static int mv88e6xxx_setup_global(struct mv88e6xxx_chip *chip) +static int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr) +{ + int err; + + err = mv88e6xxx_write(chip, REG_GLOBAL, GLOBAL_MAC_01, + (addr[0] << 8) | addr[1]); + if (err) + return err; + + err = mv88e6xxx_write(chip, REG_GLOBAL, GLOBAL_MAC_23, + (addr[2] << 8) | addr[3]); + if (err) + return err; + + return mv88e6xxx_write(chip, REG_GLOBAL, GLOBAL_MAC_45, + (addr[4] << 8) | addr[5]); +} + +static int mv88e6xxx_g1_set_age_time(struct mv88e6xxx_chip *chip, + unsigned int msecs) +{ + const unsigned int coeff = chip->info->age_time_coeff; + const unsigned int min = 0x01 * coeff; + const unsigned int max = 0xff * coeff; + u8 age_time; + u16 val; + int err; + + if (msecs < min || msecs > max) + return -ERANGE; + + /* Round to nearest multiple of coeff */ + age_time = (msecs + coeff / 2) / coeff; + + err = mv88e6xxx_read(chip, REG_GLOBAL, GLOBAL_ATU_CONTROL, &val); + if (err) + return err; + + /* AgeTime is 11:4 bits */ + val &= ~0xff0; + val |= age_time << 4; + + return mv88e6xxx_write(chip, REG_GLOBAL, GLOBAL_ATU_CONTROL, val); +} + +static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds, + unsigned int ageing_time) +{ + struct mv88e6xxx_chip *chip = ds_to_priv(ds); + int err; + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_g1_set_age_time(chip, ageing_time); + mutex_unlock(&chip->reg_lock); + + return err; +} + +static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip) { struct dsa_switch *ds = chip->ds; u32 upstream_port = dsa_upstream_port(ds); u16 reg; int err; - int i; /* Enable the PHY Polling Unit if present, don't discard any packets, * and mask all interrupt sources. @@ -3054,12 +2793,26 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_chip *chip) if (err) return err; + /* Clear all the VTU and STU entries */ + err = _mv88e6xxx_vtu_stu_flush(chip); + if (err < 0) + return err; + /* Set the default address aging time to 5 minutes, and * enable address learn messages to be sent to all message * ports. */ - err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_ATU_CONTROL, - 0x0140 | GLOBAL_ATU_CONTROL_LEARN2ALL); + err = mv88e6xxx_write(chip, REG_GLOBAL, GLOBAL_ATU_CONTROL, + GLOBAL_ATU_CONTROL_LEARN2ALL); + if (err) + return err; + + err = mv88e6xxx_g1_set_age_time(chip, 300000); + if (err) + return err; + + /* Clear all ATU entries */ + err = _mv88e6xxx_atu_flush(chip, 0, true); if (err) return err; @@ -3094,131 +2847,286 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_chip *chip) if (err) return err; - /* Send all frames with destination addresses matching - * 01:80:c2:00:00:0x to the CPU port. - */ - err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_MGMT_EN_0X, - 0xffff); + /* Clear the statistics counters for all ports */ + err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_STATS_OP, + GLOBAL_STATS_OP_FLUSH_ALL); if (err) return err; - /* Ignore removed tag data on doubly tagged packets, disable - * flow control messages, force flow control priority to the - * highest, and send all special multicast frames to the CPU - * port at the highest priority. - */ - err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_SWITCH_MGMT, - 0x7 | GLOBAL2_SWITCH_MGMT_RSVD2CPU | 0x70 | - GLOBAL2_SWITCH_MGMT_FORCE_FLOW_CTRL_PRI); + /* Wait for the flush to complete. */ + err = _mv88e6xxx_stats_wait(chip); if (err) return err; - /* Program the DSA routing table. */ - for (i = 0; i < 32; i++) { - int nexthop = 0x1f; + return 0; +} + +static int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, + int target, int port) +{ + u16 val = (target << 8) | (port & 0xf); + + return mv88e6xxx_update(chip, REG_GLOBAL2, GLOBAL2_DEVICE_MAPPING, val); +} - if (i != ds->index && i < DSA_MAX_SWITCHES) - nexthop = ds->rtable[i] & 0x1f; +static int mv88e6xxx_g2_set_device_mapping(struct mv88e6xxx_chip *chip) +{ + int target, port; + int err; + + /* Initialize the routing port to the 32 possible target devices */ + for (target = 0; target < 32; ++target) { + port = 0xf; + + if (target < DSA_MAX_SWITCHES) { + port = chip->ds->rtable[target]; + if (port == DSA_RTABLE_NONE) + port = 0xf; + } - err = _mv88e6xxx_reg_write( - chip, REG_GLOBAL2, - GLOBAL2_DEVICE_MAPPING, - GLOBAL2_DEVICE_MAPPING_UPDATE | - (i << GLOBAL2_DEVICE_MAPPING_TARGET_SHIFT) | nexthop); + err = mv88e6xxx_g2_device_mapping_write(chip, target, port); if (err) - return err; + break; } - /* Clear all trunk masks. */ - for (i = 0; i < 8; i++) { - err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, - GLOBAL2_TRUNK_MASK, - 0x8000 | - (i << GLOBAL2_TRUNK_MASK_NUM_SHIFT) | - ((1 << chip->info->num_ports) - 1)); + return err; +} + +static int mv88e6xxx_g2_trunk_mask_write(struct mv88e6xxx_chip *chip, int num, + bool hask, u16 mask) +{ + const u16 port_mask = BIT(chip->info->num_ports) - 1; + u16 val = (num << 12) | (mask & port_mask); + + if (hask) + val |= GLOBAL2_TRUNK_MASK_HASK; + + return mv88e6xxx_update(chip, REG_GLOBAL2, GLOBAL2_TRUNK_MASK, val); +} + +static int mv88e6xxx_g2_trunk_mapping_write(struct mv88e6xxx_chip *chip, int id, + u16 map) +{ + const u16 port_mask = BIT(chip->info->num_ports) - 1; + u16 val = (id << 11) | (map & port_mask); + + return mv88e6xxx_update(chip, REG_GLOBAL2, GLOBAL2_TRUNK_MAPPING, val); +} + +static int mv88e6xxx_g2_clear_trunk(struct mv88e6xxx_chip *chip) +{ + const u16 port_mask = BIT(chip->info->num_ports) - 1; + int i, err; + + /* Clear all eight possible Trunk Mask vectors */ + for (i = 0; i < 8; ++i) { + err = mv88e6xxx_g2_trunk_mask_write(chip, i, false, port_mask); if (err) return err; } - /* Clear all trunk mappings. */ - for (i = 0; i < 16; i++) { - err = _mv88e6xxx_reg_write( - chip, REG_GLOBAL2, - GLOBAL2_TRUNK_MAPPING, - GLOBAL2_TRUNK_MAPPING_UPDATE | - (i << GLOBAL2_TRUNK_MAPPING_ID_SHIFT)); + /* Clear all sixteen possible Trunk ID routing vectors */ + for (i = 0; i < 16; ++i) { + err = mv88e6xxx_g2_trunk_mapping_write(chip, i, 0); if (err) return err; } - if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) || - mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) || - mv88e6xxx_6320_family(chip)) { - /* Send all frames with destination addresses matching - * 01:80:c2:00:00:2x to the CPU port. - */ - err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, - GLOBAL2_MGMT_EN_2X, 0xffff); + return 0; +} + +static int mv88e6xxx_g2_clear_irl(struct mv88e6xxx_chip *chip) +{ + int port, err; + + /* Init all Ingress Rate Limit resources of all ports */ + for (port = 0; port < chip->info->num_ports; ++port) { + /* XXX newer chips (like 88E6390) have different 2-bit ops */ + err = mv88e6xxx_write(chip, REG_GLOBAL2, GLOBAL2_IRL_CMD, + GLOBAL2_IRL_CMD_OP_INIT_ALL | + (port << 8)); if (err) - return err; + break; + + /* Wait for the operation to complete */ + err = _mv88e6xxx_wait(chip, REG_GLOBAL2, GLOBAL2_IRL_CMD, + GLOBAL2_IRL_CMD_BUSY); + if (err) + break; + } + + return err; +} + +/* Indirect write to the Switch MAC/WoL/WoF register */ +static int mv88e6xxx_g2_switch_mac_write(struct mv88e6xxx_chip *chip, + unsigned int pointer, u8 data) +{ + u16 val = (pointer << 8) | data; + + return mv88e6xxx_update(chip, REG_GLOBAL2, GLOBAL2_SWITCH_MAC, val); +} + +static int mv88e6xxx_g2_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr) +{ + int i, err; + + for (i = 0; i < 6; i++) { + err = mv88e6xxx_g2_switch_mac_write(chip, i, addr[i]); + if (err) + break; + } + + return err; +} + +static int mv88e6xxx_g2_pot_write(struct mv88e6xxx_chip *chip, int pointer, + u8 data) +{ + u16 val = (pointer << 8) | (data & 0x7); + + return mv88e6xxx_update(chip, REG_GLOBAL2, GLOBAL2_PRIO_OVERRIDE, val); +} + +static int mv88e6xxx_g2_clear_pot(struct mv88e6xxx_chip *chip) +{ + int i, err; + + /* Clear all sixteen possible Priority Override entries */ + for (i = 0; i < 16; i++) { + err = mv88e6xxx_g2_pot_write(chip, i, 0); + if (err) + break; + } + + return err; +} + +static int mv88e6xxx_g2_eeprom_wait(struct mv88e6xxx_chip *chip) +{ + return _mv88e6xxx_wait(chip, REG_GLOBAL2, GLOBAL2_EEPROM_CMD, + GLOBAL2_EEPROM_CMD_BUSY | + GLOBAL2_EEPROM_CMD_RUNNING); +} + +static int mv88e6xxx_g2_eeprom_cmd(struct mv88e6xxx_chip *chip, u16 cmd) +{ + int err; + + err = mv88e6xxx_write(chip, REG_GLOBAL2, GLOBAL2_EEPROM_CMD, cmd); + if (err) + return err; + + return mv88e6xxx_g2_eeprom_wait(chip); +} + +static int mv88e6xxx_g2_eeprom_read16(struct mv88e6xxx_chip *chip, + u8 addr, u16 *data) +{ + u16 cmd = GLOBAL2_EEPROM_CMD_OP_READ | addr; + int err; + + err = mv88e6xxx_g2_eeprom_wait(chip); + if (err) + return err; + + err = mv88e6xxx_g2_eeprom_cmd(chip, cmd); + if (err) + return err; + + return mv88e6xxx_read(chip, REG_GLOBAL2, GLOBAL2_EEPROM_DATA, data); +} + +static int mv88e6xxx_g2_eeprom_write16(struct mv88e6xxx_chip *chip, + u8 addr, u16 data) +{ + u16 cmd = GLOBAL2_EEPROM_CMD_OP_WRITE | addr; + int err; + + err = mv88e6xxx_g2_eeprom_wait(chip); + if (err) + return err; + + err = mv88e6xxx_write(chip, REG_GLOBAL2, GLOBAL2_EEPROM_DATA, data); + if (err) + return err; + + return mv88e6xxx_g2_eeprom_cmd(chip, cmd); +} + +static int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip) +{ + u16 reg; + int err; - /* Initialise cross-chip port VLAN table to reset - * defaults. + if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G2_MGMT_EN_2X)) { + /* Consider the frames with reserved multicast destination + * addresses matching 01:80:c2:00:00:2x as MGMT. */ - err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, - GLOBAL2_PVT_ADDR, 0x9000); + err = mv88e6xxx_write(chip, REG_GLOBAL2, GLOBAL2_MGMT_EN_2X, + 0xffff); if (err) return err; - - /* Clear the priority override table. */ - for (i = 0; i < 16; i++) { - err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, - GLOBAL2_PRIO_OVERRIDE, - 0x8000 | (i << 8)); - if (err) - return err; - } } - if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) || - mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) || - mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip) || - mv88e6xxx_6320_family(chip)) { - /* Disable ingress rate limiting by resetting all - * ingress rate limit registers to their initial - * state. + if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G2_MGMT_EN_0X)) { + /* Consider the frames with reserved multicast destination + * addresses matching 01:80:c2:00:00:0x as MGMT. */ - for (i = 0; i < chip->info->num_ports; i++) { - err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, - GLOBAL2_INGRESS_OP, - 0x9000 | (i << 8)); - if (err) - return err; - } + err = mv88e6xxx_write(chip, REG_GLOBAL2, GLOBAL2_MGMT_EN_0X, + 0xffff); + if (err) + return err; } - /* Clear the statistics counters for all ports */ - err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_STATS_OP, - GLOBAL_STATS_OP_FLUSH_ALL); + /* Ignore removed tag data on doubly tagged packets, disable + * flow control messages, force flow control priority to the + * highest, and send all special multicast frames to the CPU + * port at the highest priority. + */ + reg = GLOBAL2_SWITCH_MGMT_FORCE_FLOW_CTRL_PRI | (0x7 << 4); + if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G2_MGMT_EN_0X) || + mv88e6xxx_has(chip, MV88E6XXX_FLAG_G2_MGMT_EN_2X)) + reg |= GLOBAL2_SWITCH_MGMT_RSVD2CPU | 0x7; + err = mv88e6xxx_write(chip, REG_GLOBAL2, GLOBAL2_SWITCH_MGMT, reg); if (err) return err; - /* Wait for the flush to complete. */ - err = _mv88e6xxx_stats_wait(chip); + /* Program the DSA routing table. */ + err = mv88e6xxx_g2_set_device_mapping(chip); if (err) return err; - /* Clear all ATU entries */ - err = _mv88e6xxx_atu_flush(chip, 0, true); + /* Clear all trunk masks and mapping. */ + err = mv88e6xxx_g2_clear_trunk(chip); if (err) return err; - /* Clear all the VTU and STU entries */ - err = _mv88e6xxx_vtu_stu_flush(chip); - if (err < 0) - return err; + if (mv88e6xxx_has(chip, MV88E6XXX_FLAGS_IRL)) { + /* Disable ingress rate limiting by resetting all per port + * ingress rate limit resources to their initial state. + */ + err = mv88e6xxx_g2_clear_irl(chip); + if (err) + return err; + } - return err; + if (mv88e6xxx_has(chip, MV88E6XXX_FLAGS_PVT)) { + /* Initialize Cross-chip Port VLAN Table to reset defaults */ + err = mv88e6xxx_write(chip, REG_GLOBAL2, GLOBAL2_PVT_ADDR, + GLOBAL2_PVT_ADDR_OP_INIT_ONES); + if (err) + return err; + } + + if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G2_POT)) { + /* Clear the priority override table. */ + err = mv88e6xxx_g2_clear_pot(chip); + if (err) + return err; + } + + return 0; } static int mv88e6xxx_setup(struct dsa_switch *ds) @@ -3230,21 +3138,27 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) chip->ds = ds; ds->slave_mii_bus = chip->mdio_bus; - if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEPROM)) - mutex_init(&chip->eeprom_mutex); - mutex_lock(&chip->reg_lock); err = mv88e6xxx_switch_reset(chip); if (err) goto unlock; - err = mv88e6xxx_setup_global(chip); + /* Setup Switch Port Registers */ + for (i = 0; i < chip->info->num_ports; i++) { + err = mv88e6xxx_setup_port(chip, i); + if (err) + goto unlock; + } + + /* Setup Switch Global 1 Registers */ + err = mv88e6xxx_g1_setup(chip); if (err) goto unlock; - for (i = 0; i < chip->info->num_ports; i++) { - err = mv88e6xxx_setup_port(chip, i); + /* Setup Switch Global 2 Registers */ + if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_GLOBAL2)) { + err = mv88e6xxx_g2_setup(chip); if (err) goto unlock; } @@ -3255,6 +3169,24 @@ unlock: return err; } +static int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr) +{ + struct mv88e6xxx_chip *chip = ds_to_priv(ds); + int err; + + mutex_lock(&chip->reg_lock); + + /* Has an indirect Switch MAC/WoL/WoF register in Global 2? */ + if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G2_SWITCH_MAC)) + err = mv88e6xxx_g2_set_switch_mac(chip, addr); + else + err = mv88e6xxx_g1_set_switch_mac(chip, addr); + + mutex_unlock(&chip->reg_lock); + + return err; +} + static int mv88e6xxx_mdio_page_read(struct dsa_switch *ds, int port, int page, int reg) { @@ -3528,6 +3460,173 @@ static int mv88e6xxx_get_temp_alarm(struct dsa_switch *ds, bool *alarm) } #endif /* CONFIG_NET_DSA_HWMON */ +static int mv88e6xxx_get_eeprom_len(struct dsa_switch *ds) +{ + struct mv88e6xxx_chip *chip = ds_to_priv(ds); + + return chip->eeprom_len; +} + +static int mv88e6xxx_get_eeprom16(struct mv88e6xxx_chip *chip, + struct ethtool_eeprom *eeprom, u8 *data) +{ + unsigned int offset = eeprom->offset; + unsigned int len = eeprom->len; + u16 val; + int err; + + eeprom->len = 0; + + if (offset & 1) { + err = mv88e6xxx_g2_eeprom_read16(chip, offset >> 1, &val); + if (err) + return err; + + *data++ = (val >> 8) & 0xff; + + offset++; + len--; + eeprom->len++; + } + + while (len >= 2) { + err = mv88e6xxx_g2_eeprom_read16(chip, offset >> 1, &val); + if (err) + return err; + + *data++ = val & 0xff; + *data++ = (val >> 8) & 0xff; + + offset += 2; + len -= 2; + eeprom->len += 2; + } + + if (len) { + err = mv88e6xxx_g2_eeprom_read16(chip, offset >> 1, &val); + if (err) + return err; + + *data++ = val & 0xff; + + offset++; + len--; + eeprom->len++; + } + + return 0; +} + +static int mv88e6xxx_get_eeprom(struct dsa_switch *ds, + struct ethtool_eeprom *eeprom, u8 *data) +{ + struct mv88e6xxx_chip *chip = ds_to_priv(ds); + int err; + + mutex_lock(&chip->reg_lock); + + if (mv88e6xxx_has(chip, MV88E6XXX_FLAGS_EEPROM16)) + err = mv88e6xxx_get_eeprom16(chip, eeprom, data); + else + err = -EOPNOTSUPP; + + mutex_unlock(&chip->reg_lock); + + if (err) + return err; + + eeprom->magic = 0xc3ec4951; + + return 0; +} + +static int mv88e6xxx_set_eeprom16(struct mv88e6xxx_chip *chip, + struct ethtool_eeprom *eeprom, u8 *data) +{ + unsigned int offset = eeprom->offset; + unsigned int len = eeprom->len; + u16 val; + int err; + + /* Ensure the RO WriteEn bit is set */ + err = mv88e6xxx_read(chip, REG_GLOBAL2, GLOBAL2_EEPROM_CMD, &val); + if (err) + return err; + + if (!(val & GLOBAL2_EEPROM_CMD_WRITE_EN)) + return -EROFS; + + eeprom->len = 0; + + if (offset & 1) { + err = mv88e6xxx_g2_eeprom_read16(chip, offset >> 1, &val); + if (err) + return err; + + val = (*data++ << 8) | (val & 0xff); + + err = mv88e6xxx_g2_eeprom_write16(chip, offset >> 1, val); + if (err) + return err; + + offset++; + len--; + eeprom->len++; + } + + while (len >= 2) { + val = *data++; + val |= *data++ << 8; + + err = mv88e6xxx_g2_eeprom_write16(chip, offset >> 1, val); + if (err) + return err; + + offset += 2; + len -= 2; + eeprom->len += 2; + } + + if (len) { + err = mv88e6xxx_g2_eeprom_read16(chip, offset >> 1, &val); + if (err) + return err; + + val = (val & 0xff00) | *data++; + + err = mv88e6xxx_g2_eeprom_write16(chip, offset >> 1, val); + if (err) + return err; + + offset++; + len--; + eeprom->len++; + } + + return 0; +} + +static int mv88e6xxx_set_eeprom(struct dsa_switch *ds, + struct ethtool_eeprom *eeprom, u8 *data) +{ + struct mv88e6xxx_chip *chip = ds_to_priv(ds); + int err; + + if (eeprom->magic != 0xc3ec4951) + return -EINVAL; + + mutex_lock(&chip->reg_lock); + + if (mv88e6xxx_has(chip, MV88E6XXX_FLAGS_EEPROM16)) + err = mv88e6xxx_set_eeprom16(chip, eeprom, data); + else + err = -EOPNOTSUPP; + + mutex_unlock(&chip->reg_lock); + + return err; +} + static const struct mv88e6xxx_info mv88e6xxx_table[] = { [MV88E6085] = { .prod_num = PORT_SWITCH_ID_PROD_NUM_6085, @@ -3536,6 +3635,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 10, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6097, }, @@ -3546,6 +3646,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 256, .num_ports = 11, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6095, }, @@ -3556,6 +3657,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 3, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6165, }, @@ -3566,6 +3668,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 256, .num_ports = 8, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6185, }, @@ -3576,6 +3679,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 6, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6165, }, @@ -3586,6 +3690,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 6, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6165, }, @@ -3596,6 +3701,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 7, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6351, }, @@ -3606,6 +3712,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 7, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6352, }, @@ -3616,6 +3723,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 7, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6351, }, @@ -3626,6 +3734,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 7, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6352, }, @@ -3636,6 +3745,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 256, .num_ports = 10, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6185, }, @@ -3646,6 +3756,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 7, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6352, }, @@ -3656,6 +3767,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 7, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6320, }, @@ -3666,6 +3778,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 7, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6320, }, @@ -3676,6 +3789,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 7, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6351, }, @@ -3686,6 +3800,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 7, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6351, }, @@ -3696,6 +3811,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_databases = 4096, .num_ports = 7, .port_base_addr = 0x10, + .age_time_coeff = 15000, .flags = MV88E6XXX_FLAGS_FAMILY_6352, }, }; @@ -3714,12 +3830,15 @@ static const struct mv88e6xxx_info *mv88e6xxx_lookup_info(unsigned int prod_num) static int mv88e6xxx_detect(struct mv88e6xxx_chip *chip) { const struct mv88e6xxx_info *info; - int id, prod_num, rev; + unsigned int prod_num, rev; + u16 id; + int err; - id = mv88e6xxx_reg_read(chip, chip->info->port_base_addr, - PORT_SWITCH_ID); - if (id < 0) - return id; + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_read(chip, 0, PORT_SWITCH_ID, &id); + mutex_unlock(&chip->reg_lock); + if (err) + return err; prod_num = (id & 0xfff0) >> 4; rev = id & 0x000f; @@ -3834,6 +3953,7 @@ static struct dsa_switch_driver mv88e6xxx_switch_driver = { .set_eeprom = mv88e6xxx_set_eeprom, .get_regs_len = mv88e6xxx_get_regs_len, .get_regs = mv88e6xxx_get_regs, + .set_ageing_time = mv88e6xxx_set_ageing_time, .port_bridge_join = mv88e6xxx_port_bridge_join, .port_bridge_leave = mv88e6xxx_port_bridge_leave, .port_stp_state_set = mv88e6xxx_port_stp_state_set, @@ -3903,7 +4023,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) if (IS_ERR(chip->reset)) return PTR_ERR(chip->reset); - if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEPROM) && + if (mv88e6xxx_has(chip, MV88E6XXX_FLAGS_EEPROM16) && !of_property_read_u32(np, "eeprom-length", &eeprom_len)) chip->eeprom_len = eeprom_len; diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index 83f0662..48d6ea7 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -294,28 +294,38 @@ #define GLOBAL2_TRUNK_MASK 0x07 #define GLOBAL2_TRUNK_MASK_UPDATE BIT(15) #define GLOBAL2_TRUNK_MASK_NUM_SHIFT 12 +#define GLOBAL2_TRUNK_MASK_HASK BIT(11) #define GLOBAL2_TRUNK_MAPPING 0x08 #define GLOBAL2_TRUNK_MAPPING_UPDATE BIT(15) #define GLOBAL2_TRUNK_MAPPING_ID_SHIFT 11 -#define GLOBAL2_INGRESS_OP 0x09 -#define GLOBAL2_INGRESS_DATA 0x0a +#define GLOBAL2_IRL_CMD 0x09 +#define GLOBAL2_IRL_CMD_BUSY BIT(15) +#define GLOBAL2_IRL_CMD_OP_INIT_ALL ((0x001 << 12) | GLOBAL2_IRL_CMD_BUSY) +#define GLOBAL2_IRL_CMD_OP_INIT_SEL ((0x010 << 12) | GLOBAL2_IRL_CMD_BUSY) +#define GLOBAL2_IRL_CMD_OP_WRITE_SEL ((0x011 << 12) | GLOBAL2_IRL_CMD_BUSY) +#define GLOBAL2_IRL_CMD_OP_READ_SEL ((0x100 << 12) | GLOBAL2_IRL_CMD_BUSY) +#define GLOBAL2_IRL_DATA 0x0a #define GLOBAL2_PVT_ADDR 0x0b +#define GLOBAL2_PVT_ADDR_BUSY BIT(15) +#define GLOBAL2_PVT_ADDR_OP_INIT_ONES ((0x01 << 12) | GLOBAL2_PVT_ADDR_BUSY) +#define GLOBAL2_PVT_ADDR_OP_WRITE_PVLAN ((0x03 << 12) | GLOBAL2_PVT_ADDR_BUSY) +#define GLOBAL2_PVT_ADDR_OP_READ ((0x04 << 12) | GLOBAL2_PVT_ADDR_BUSY) #define GLOBAL2_PVT_DATA 0x0c #define GLOBAL2_SWITCH_MAC 0x0d -#define GLOBAL2_SWITCH_MAC_BUSY BIT(15) #define GLOBAL2_ATU_STATS 0x0e #define GLOBAL2_PRIO_OVERRIDE 0x0f #define GLOBAL2_PRIO_OVERRIDE_FORCE_SNOOP BIT(7) #define GLOBAL2_PRIO_OVERRIDE_SNOOP_SHIFT 4 #define GLOBAL2_PRIO_OVERRIDE_FORCE_ARP BIT(3) #define GLOBAL2_PRIO_OVERRIDE_ARP_SHIFT 0 -#define GLOBAL2_EEPROM_OP 0x14 -#define GLOBAL2_EEPROM_OP_BUSY BIT(15) -#define GLOBAL2_EEPROM_OP_WRITE ((3 << 12) | GLOBAL2_EEPROM_OP_BUSY) -#define GLOBAL2_EEPROM_OP_READ ((4 << 12) | GLOBAL2_EEPROM_OP_BUSY) -#define GLOBAL2_EEPROM_OP_LOAD BIT(11) -#define GLOBAL2_EEPROM_OP_WRITE_EN BIT(10) -#define GLOBAL2_EEPROM_OP_ADDR_MASK 0xff +#define GLOBAL2_EEPROM_CMD 0x14 +#define GLOBAL2_EEPROM_CMD_BUSY BIT(15) +#define GLOBAL2_EEPROM_CMD_OP_WRITE ((0x3 << 12) | GLOBAL2_EEPROM_CMD_BUSY) +#define GLOBAL2_EEPROM_CMD_OP_READ ((0x4 << 12) | GLOBAL2_EEPROM_CMD_BUSY) +#define GLOBAL2_EEPROM_CMD_OP_LOAD ((0x6 << 12) | GLOBAL2_EEPROM_CMD_BUSY) +#define GLOBAL2_EEPROM_CMD_RUNNING BIT(11) +#define GLOBAL2_EEPROM_CMD_WRITE_EN BIT(10) +#define GLOBAL2_EEPROM_CMD_ADDR_MASK 0xff #define GLOBAL2_EEPROM_DATA 0x15 #define GLOBAL2_PTP_AVB_OP 0x16 #define GLOBAL2_PTP_AVB_DATA 0x17 @@ -374,19 +384,24 @@ enum mv88e6xxx_family { }; enum mv88e6xxx_cap { - /* Address Translation Unit. - * The ATU is used to lookup and learn MAC addresses. See GLOBAL_ATU_OP. - */ - MV88E6XXX_CAP_ATU, - /* Energy Efficient Ethernet. */ MV88E6XXX_CAP_EEE, - /* EEPROM Command and Data registers. - * See GLOBAL2_EEPROM_OP and GLOBAL2_EEPROM_DATA. + /* Switch Global 2 Registers. + * The device contains a second set of global 16-bit registers. */ - MV88E6XXX_CAP_EEPROM, + MV88E6XXX_CAP_GLOBAL2, + MV88E6XXX_CAP_G2_MGMT_EN_2X, /* (0x02) MGMT Enable Register 2x */ + MV88E6XXX_CAP_G2_MGMT_EN_0X, /* (0x03) MGMT Enable Register 0x */ + MV88E6XXX_CAP_G2_IRL_CMD, /* (0x09) Ingress Rate Command */ + MV88E6XXX_CAP_G2_IRL_DATA, /* (0x0a) Ingress Rate Data */ + MV88E6XXX_CAP_G2_PVT_ADDR, /* (0x0b) Cross Chip Port VLAN Addr */ + MV88E6XXX_CAP_G2_PVT_DATA, /* (0x0c) Cross Chip Port VLAN Data */ + MV88E6XXX_CAP_G2_SWITCH_MAC, /* (0x0d) Switch MAC/WoL/WoF */ + MV88E6XXX_CAP_G2_POT, /* (0x0f) Priority Override Table */ + MV88E6XXX_CAP_G2_EEPROM_CMD, /* (0x14) EEPROM Command */ + MV88E6XXX_CAP_G2_EEPROM_DATA, /* (0x15) EEPROM Data */ /* Multi-chip Addressing Mode. * Some chips require an indirect SMI access when their SMI device @@ -394,11 +409,6 @@ enum mv88e6xxx_cap { */ MV88E6XXX_CAP_MULTI_CHIP, - /* Port State Filtering for 802.1D Spanning Tree. - * See PORT_CONTROL_STATE_* values in the PORT_CONTROL register. - */ - MV88E6XXX_CAP_PORTSTATE, - /* PHY Polling Unit. * See GLOBAL_CONTROL_PPU_ENABLE and GLOBAL_STATUS_PPU_POLLING. */ @@ -417,25 +427,12 @@ enum mv88e6xxx_cap { */ MV88E6XXX_CAP_STU, - /* Switch MAC/WoL/WoF register. - * This requires an indirect access to set the switch MAC address - * through GLOBAL2_SWITCH_MAC, otherwise GLOBAL_MAC_01, GLOBAL_MAC_23, - * and GLOBAL_MAC_45 are used with a direct access. - */ - MV88E6XXX_CAP_SWITCH_MAC_WOL_WOF, - /* Internal temperature sensor. * Available from any enabled port's PHY register 26, page 6. */ MV88E6XXX_CAP_TEMP, MV88E6XXX_CAP_TEMP_LIMIT, - /* In-chip Port Based VLANs. - * Each port VLANTable register (see PORT_BASE_VLAN) is used to restrict - * the output (or egress) ports to which it is allowed to send frames. - */ - MV88E6XXX_CAP_VLANTABLE, - /* VLAN Table Unit. * The VTU is used to program 802.1Q VLANs. See GLOBAL_VTU_OP. */ @@ -443,90 +440,130 @@ enum mv88e6xxx_cap { }; /* Bitmask of capabilities */ -#define MV88E6XXX_FLAG_ATU BIT(MV88E6XXX_CAP_ATU) #define MV88E6XXX_FLAG_EEE BIT(MV88E6XXX_CAP_EEE) -#define MV88E6XXX_FLAG_EEPROM BIT(MV88E6XXX_CAP_EEPROM) +#define MV88E6XXX_FLAG_GLOBAL2 BIT(MV88E6XXX_CAP_GLOBAL2) +#define MV88E6XXX_FLAG_G2_MGMT_EN_2X BIT(MV88E6XXX_CAP_G2_MGMT_EN_2X) +#define MV88E6XXX_FLAG_G2_MGMT_EN_0X BIT(MV88E6XXX_CAP_G2_MGMT_EN_0X) +#define MV88E6XXX_FLAG_G2_IRL_CMD BIT(MV88E6XXX_CAP_G2_IRL_CMD) +#define MV88E6XXX_FLAG_G2_IRL_DATA BIT(MV88E6XXX_CAP_G2_IRL_DATA) +#define MV88E6XXX_FLAG_G2_PVT_ADDR BIT(MV88E6XXX_CAP_G2_PVT_ADDR) +#define MV88E6XXX_FLAG_G2_PVT_DATA BIT(MV88E6XXX_CAP_G2_PVT_DATA) +#define MV88E6XXX_FLAG_G2_SWITCH_MAC BIT(MV88E6XXX_CAP_G2_SWITCH_MAC) +#define MV88E6XXX_FLAG_G2_POT BIT(MV88E6XXX_CAP_G2_POT) +#define MV88E6XXX_FLAG_G2_EEPROM_CMD BIT(MV88E6XXX_CAP_G2_EEPROM_CMD) +#define MV88E6XXX_FLAG_G2_EEPROM_DATA BIT(MV88E6XXX_CAP_G2_EEPROM_DATA) #define MV88E6XXX_FLAG_MULTI_CHIP BIT(MV88E6XXX_CAP_MULTI_CHIP) -#define MV88E6XXX_FLAG_PORTSTATE BIT(MV88E6XXX_CAP_PORTSTATE) #define MV88E6XXX_FLAG_PPU BIT(MV88E6XXX_CAP_PPU) #define MV88E6XXX_FLAG_PPU_ACTIVE BIT(MV88E6XXX_CAP_PPU_ACTIVE) #define MV88E6XXX_FLAG_SMI_PHY BIT(MV88E6XXX_CAP_SMI_PHY) #define MV88E6XXX_FLAG_STU BIT(MV88E6XXX_CAP_STU) -#define MV88E6XXX_FLAG_SWITCH_MAC BIT(MV88E6XXX_CAP_SWITCH_MAC_WOL_WOF) #define MV88E6XXX_FLAG_TEMP BIT(MV88E6XXX_CAP_TEMP) #define MV88E6XXX_FLAG_TEMP_LIMIT BIT(MV88E6XXX_CAP_TEMP_LIMIT) -#define MV88E6XXX_FLAG_VLANTABLE BIT(MV88E6XXX_CAP_VLANTABLE) #define MV88E6XXX_FLAG_VTU BIT(MV88E6XXX_CAP_VTU) +/* EEPROM Programming via Global2 with 16-bit data */ +#define MV88E6XXX_FLAGS_EEPROM16 \ + (MV88E6XXX_FLAG_G2_EEPROM_CMD | \ + MV88E6XXX_FLAG_G2_EEPROM_DATA) + +/* Ingress Rate Limit unit */ +#define MV88E6XXX_FLAGS_IRL \ + (MV88E6XXX_FLAG_G2_IRL_CMD | \ + MV88E6XXX_FLAG_G2_IRL_DATA) + +/* Cross-chip Port VLAN Table */ +#define MV88E6XXX_FLAGS_PVT \ + (MV88E6XXX_FLAG_G2_PVT_ADDR | \ + MV88E6XXX_FLAG_G2_PVT_DATA) + #define MV88E6XXX_FLAGS_FAMILY_6095 \ - (MV88E6XXX_FLAG_ATU | \ + (MV88E6XXX_FLAG_GLOBAL2 | \ + MV88E6XXX_FLAG_G2_MGMT_EN_0X | \ MV88E6XXX_FLAG_MULTI_CHIP | \ MV88E6XXX_FLAG_PPU | \ - MV88E6XXX_FLAG_VLANTABLE | \ MV88E6XXX_FLAG_VTU) #define MV88E6XXX_FLAGS_FAMILY_6097 \ - (MV88E6XXX_FLAG_ATU | \ + (MV88E6XXX_FLAG_GLOBAL2 | \ + MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ + MV88E6XXX_FLAG_G2_MGMT_EN_0X | \ + MV88E6XXX_FLAG_G2_POT | \ MV88E6XXX_FLAG_MULTI_CHIP | \ MV88E6XXX_FLAG_PPU | \ MV88E6XXX_FLAG_STU | \ - MV88E6XXX_FLAG_VLANTABLE | \ - MV88E6XXX_FLAG_VTU) + MV88E6XXX_FLAG_VTU | \ + MV88E6XXX_FLAGS_IRL | \ + MV88E6XXX_FLAGS_PVT) #define MV88E6XXX_FLAGS_FAMILY_6165 \ - (MV88E6XXX_FLAG_MULTI_CHIP | \ + (MV88E6XXX_FLAG_GLOBAL2 | \ + MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ + MV88E6XXX_FLAG_G2_MGMT_EN_0X | \ + MV88E6XXX_FLAG_G2_SWITCH_MAC | \ + MV88E6XXX_FLAG_G2_POT | \ + MV88E6XXX_FLAG_MULTI_CHIP | \ MV88E6XXX_FLAG_STU | \ - MV88E6XXX_FLAG_SWITCH_MAC | \ MV88E6XXX_FLAG_TEMP | \ - MV88E6XXX_FLAG_VTU) + MV88E6XXX_FLAG_VTU | \ + MV88E6XXX_FLAGS_IRL | \ + MV88E6XXX_FLAGS_PVT) #define MV88E6XXX_FLAGS_FAMILY_6185 \ - (MV88E6XXX_FLAG_ATU | \ + (MV88E6XXX_FLAG_GLOBAL2 | \ + MV88E6XXX_FLAG_G2_MGMT_EN_0X | \ MV88E6XXX_FLAG_MULTI_CHIP | \ MV88E6XXX_FLAG_PPU | \ - MV88E6XXX_FLAG_VLANTABLE | \ MV88E6XXX_FLAG_VTU) #define MV88E6XXX_FLAGS_FAMILY_6320 \ - (MV88E6XXX_FLAG_ATU | \ - MV88E6XXX_FLAG_EEE | \ - MV88E6XXX_FLAG_EEPROM | \ + (MV88E6XXX_FLAG_EEE | \ + MV88E6XXX_FLAG_GLOBAL2 | \ + MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ + MV88E6XXX_FLAG_G2_MGMT_EN_0X | \ + MV88E6XXX_FLAG_G2_SWITCH_MAC | \ + MV88E6XXX_FLAG_G2_POT | \ MV88E6XXX_FLAG_MULTI_CHIP | \ - MV88E6XXX_FLAG_PORTSTATE | \ MV88E6XXX_FLAG_PPU_ACTIVE | \ MV88E6XXX_FLAG_SMI_PHY | \ - MV88E6XXX_FLAG_SWITCH_MAC | \ MV88E6XXX_FLAG_TEMP | \ MV88E6XXX_FLAG_TEMP_LIMIT | \ - MV88E6XXX_FLAG_VLANTABLE | \ - MV88E6XXX_FLAG_VTU) + MV88E6XXX_FLAG_VTU | \ + MV88E6XXX_FLAGS_EEPROM16 | \ + MV88E6XXX_FLAGS_IRL | \ + MV88E6XXX_FLAGS_PVT) #define MV88E6XXX_FLAGS_FAMILY_6351 \ - (MV88E6XXX_FLAG_ATU | \ + (MV88E6XXX_FLAG_GLOBAL2 | \ + MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ + MV88E6XXX_FLAG_G2_MGMT_EN_0X | \ + MV88E6XXX_FLAG_G2_SWITCH_MAC | \ + MV88E6XXX_FLAG_G2_POT | \ MV88E6XXX_FLAG_MULTI_CHIP | \ - MV88E6XXX_FLAG_PORTSTATE | \ MV88E6XXX_FLAG_PPU_ACTIVE | \ MV88E6XXX_FLAG_SMI_PHY | \ MV88E6XXX_FLAG_STU | \ - MV88E6XXX_FLAG_SWITCH_MAC | \ MV88E6XXX_FLAG_TEMP | \ - MV88E6XXX_FLAG_VLANTABLE | \ - MV88E6XXX_FLAG_VTU) + MV88E6XXX_FLAG_VTU | \ + MV88E6XXX_FLAGS_IRL | \ + MV88E6XXX_FLAGS_PVT) #define MV88E6XXX_FLAGS_FAMILY_6352 \ - (MV88E6XXX_FLAG_ATU | \ - MV88E6XXX_FLAG_EEE | \ - MV88E6XXX_FLAG_EEPROM | \ + (MV88E6XXX_FLAG_EEE | \ + MV88E6XXX_FLAG_GLOBAL2 | \ + MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ + MV88E6XXX_FLAG_G2_MGMT_EN_0X | \ + MV88E6XXX_FLAG_G2_SWITCH_MAC | \ + MV88E6XXX_FLAG_G2_POT | \ MV88E6XXX_FLAG_MULTI_CHIP | \ - MV88E6XXX_FLAG_PORTSTATE | \ MV88E6XXX_FLAG_PPU_ACTIVE | \ MV88E6XXX_FLAG_SMI_PHY | \ MV88E6XXX_FLAG_STU | \ - MV88E6XXX_FLAG_SWITCH_MAC | \ MV88E6XXX_FLAG_TEMP | \ MV88E6XXX_FLAG_TEMP_LIMIT | \ - MV88E6XXX_FLAG_VLANTABLE | \ - MV88E6XXX_FLAG_VTU) + MV88E6XXX_FLAG_VTU | \ + MV88E6XXX_FLAGS_EEPROM16 | \ + MV88E6XXX_FLAGS_IRL | \ + MV88E6XXX_FLAGS_PVT) struct mv88e6xxx_info { enum mv88e6xxx_family family; @@ -535,6 +572,7 @@ struct mv88e6xxx_info { unsigned int num_databases; unsigned int num_ports; unsigned int port_base_addr; + unsigned int age_time_coeff; unsigned long flags; }; @@ -595,17 +633,6 @@ struct mv88e6xxx_chip { */ struct mutex stats_mutex; - /* This mutex serializes phy access for chips with - * indirect phy addressing. It is unused for chips - * with direct phy access. - */ - struct mutex phy_mutex; - - /* This mutex serializes eeprom access for chips with - * eeprom support. - */ - struct mutex eeprom_mutex; - struct mv88e6xxx_priv_port ports[DSA_MAX_PORTS]; /* A switch may have a GPIO line tied to its reset pin. Parse diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index cd7e2e5..c83ebae 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -3827,7 +3827,7 @@ static void et131x_tx_timeout(struct net_device *netdev) unsigned long flags; /* If the device is closed, ignore the timeout */ - if (~(adapter->flags & FMP_ADAPTER_INTERRUPT_IN_USE)) + if (!(adapter->flags & FMP_ADAPTER_INTERRUPT_IN_USE)) return; /* Any nonrecoverable hardware error? diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index dc2c35d..0d4ea92 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -259,6 +259,7 @@ static void nb8800_receive(struct net_device *dev, unsigned int i, if (err) { netdev_err(dev, "rx buffer allocation failed\n"); dev->stats.rx_dropped++; + dev_kfree_skb(skb); return; } @@ -1418,7 +1419,7 @@ static int nb8800_probe(struct platform_device *pdev) if (ops && ops->reset) { ret = ops->reset(dev); if (ret) - goto err_free_dev; + goto err_disable_clk; } bus = devm_mdiobus_alloc(&pdev->dev); diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 13b0725..c4751ec 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -207,7 +207,7 @@ err_dma: dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb), DMA_TO_DEVICE); - while (i > 0) { + while (i-- > 0) { int index = (ring->end + i) % BGMAC_TX_RING_SLOTS; struct bgmac_slot_info *slot = &ring->slots[index]; u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 659faa6..8a0165b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -73,6 +73,7 @@ enum board_idx { BCM57301, BCM57302, BCM57304, + BCM58700, BCM57311, BCM57312, BCM57402, @@ -98,6 +99,7 @@ static const struct { { "Broadcom BCM57301 NetXtreme-C Single-port 10Gb Ethernet" }, { "Broadcom BCM57302 NetXtreme-C Dual-port 10Gb/25Gb Ethernet" }, { "Broadcom BCM57304 NetXtreme-C Dual-port 10Gb/25Gb/40Gb/50Gb Ethernet" }, + { "Broadcom BCM58700 Nitro 4-port 1Gb/2.5Gb/10Gb Ethernet" }, { "Broadcom BCM57311 NetXtreme-C Single-port 10Gb Ethernet" }, { "Broadcom BCM57312 NetXtreme-C Dual-port 10Gb/25Gb Ethernet" }, { "Broadcom BCM57402 NetXtreme-E Dual-port 10Gb Ethernet" }, @@ -120,6 +122,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = { { PCI_VDEVICE(BROADCOM, 0x16c8), .driver_data = BCM57301 }, { PCI_VDEVICE(BROADCOM, 0x16c9), .driver_data = BCM57302 }, { PCI_VDEVICE(BROADCOM, 0x16ca), .driver_data = BCM57304 }, + { PCI_VDEVICE(BROADCOM, 0x16cd), .driver_data = BCM58700 }, { PCI_VDEVICE(BROADCOM, 0x16ce), .driver_data = BCM57311 }, { PCI_VDEVICE(BROADCOM, 0x16cf), .driver_data = BCM57312 }, { PCI_VDEVICE(BROADCOM, 0x16d0), .driver_data = BCM57402 }, @@ -1668,6 +1671,76 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) return rx_pkts; } +static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget) +{ + struct bnxt_napi *bnapi = container_of(napi, struct bnxt_napi, napi); + struct bnxt *bp = bnapi->bp; + struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; + struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; + struct tx_cmp *txcmp; + struct rx_cmp_ext *rxcmp1; + u32 cp_cons, tmp_raw_cons; + u32 raw_cons = cpr->cp_raw_cons; + u32 rx_pkts = 0; + bool agg_event = false; + + while (1) { + int rc; + + cp_cons = RING_CMP(raw_cons); + txcmp = &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + + if (!TX_CMP_VALID(txcmp, raw_cons)) + break; + + if ((TX_CMP_TYPE(txcmp) & 0x30) == 0x10) { + tmp_raw_cons = NEXT_RAW_CMP(raw_cons); + cp_cons = RING_CMP(tmp_raw_cons); + rxcmp1 = (struct rx_cmp_ext *) + &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + + if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons)) + break; + + /* force an error to recycle the buffer */ + rxcmp1->rx_cmp_cfa_code_errors_v2 |= + cpu_to_le32(RX_CMPL_ERRORS_CRC_ERROR); + + rc = bnxt_rx_pkt(bp, bnapi, &raw_cons, &agg_event); + if (likely(rc == -EIO)) + rx_pkts++; + else if (rc == -EBUSY) /* partial completion */ + break; + } else if (unlikely(TX_CMP_TYPE(txcmp) == + CMPL_BASE_TYPE_HWRM_DONE)) { + bnxt_hwrm_handler(bp, txcmp); + } else { + netdev_err(bp->dev, + "Invalid completion received on special ring\n"); + } + raw_cons = NEXT_RAW_CMP(raw_cons); + + if (rx_pkts == budget) + break; + } + + cpr->cp_raw_cons = raw_cons; + BNXT_CP_DB(cpr->cp_doorbell, cpr->cp_raw_cons); + writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell); + writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell); + + if (agg_event) { + writel(DB_KEY_RX | rxr->rx_agg_prod, rxr->rx_agg_doorbell); + writel(DB_KEY_RX | rxr->rx_agg_prod, rxr->rx_agg_doorbell); + } + + if (!bnxt_has_work(bp, cpr) && rx_pkts < budget) { + napi_complete(napi); + BNXT_CP_DB_REARM(cpr->cp_doorbell, cpr->cp_raw_cons); + } + return rx_pkts; +} + static int bnxt_poll(struct napi_struct *napi, int budget) { struct bnxt_napi *bnapi = container_of(napi, struct bnxt_napi, napi); @@ -2340,6 +2413,9 @@ static int bnxt_alloc_vnics(struct bnxt *bp) num_vnics += bp->rx_nr_rings; #endif + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) + num_vnics++; + bp->vnic_info = kcalloc(num_vnics, sizeof(struct bnxt_vnic_info), GFP_KERNEL); if (!bp->vnic_info) @@ -2357,7 +2433,8 @@ static void bnxt_init_vnics(struct bnxt *bp) struct bnxt_vnic_info *vnic = &bp->vnic_info[i]; vnic->fw_vnic_id = INVALID_HW_RING_ID; - vnic->fw_rss_cos_lb_ctx = INVALID_HW_RING_ID; + vnic->fw_rss_cos_lb_ctx[0] = INVALID_HW_RING_ID; + vnic->fw_rss_cos_lb_ctx[1] = INVALID_HW_RING_ID; vnic->fw_l2_ctx_id = INVALID_HW_RING_ID; if (bp->vnic_info[i].rss_hash_key) { @@ -2661,7 +2738,7 @@ static int bnxt_alloc_stats(struct bnxt *bp) cpr->hw_stats_ctx_id = INVALID_STATS_CTX_ID; } - if (BNXT_PF(bp)) { + if (BNXT_PF(bp) && bp->chip_num != CHIP_NUM_58700) { bp->hw_port_stats_size = sizeof(struct rx_port_stats) + sizeof(struct tx_port_stats) + 1024; @@ -3200,8 +3277,10 @@ static int bnxt_hwrm_set_vnic_filter(struct bnxt *bp, u16 vnic_id, u16 idx, struct hwrm_cfa_l2_filter_alloc_output *resp = bp->hwrm_cmd_resp_addr; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_L2_FILTER_ALLOC, -1, -1); - req.flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX | - CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST); + req.flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX); + if (!BNXT_CHIP_TYPE_NITRO_A0(bp)) + req.flags |= + cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST); req.dst_id = cpu_to_le16(bp->vnic_info[vnic_id].fw_vnic_id); req.enables = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR | @@ -3308,7 +3387,7 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; struct hwrm_vnic_rss_cfg_input req = {0}; - if (vnic->fw_rss_cos_lb_ctx == INVALID_HW_RING_ID) + if (vnic->fw_rss_cos_lb_ctx[0] == INVALID_HW_RING_ID) return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_CFG, -1, -1); @@ -3320,10 +3399,14 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) req.hash_type = cpu_to_le32(vnic->hash_type); - if (vnic->flags & BNXT_VNIC_RSS_FLAG) - max_rings = bp->rx_nr_rings; - else + if (vnic->flags & BNXT_VNIC_RSS_FLAG) { + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) + max_rings = bp->rx_nr_rings - 1; + else + max_rings = bp->rx_nr_rings; + } else { max_rings = 1; + } /* Fill the RSS indirection table with ring group ids */ for (i = 0, j = 0; i < HW_HASH_INDEX_SIZE; i++, j++) { @@ -3336,7 +3419,7 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) req.hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr); } - req.rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx); + req.rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]); return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); } @@ -3359,32 +3442,35 @@ static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id) return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); } -static void bnxt_hwrm_vnic_ctx_free_one(struct bnxt *bp, u16 vnic_id) +static void bnxt_hwrm_vnic_ctx_free_one(struct bnxt *bp, u16 vnic_id, + u16 ctx_idx) { struct hwrm_vnic_rss_cos_lb_ctx_free_input req = {0}; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_COS_LB_CTX_FREE, -1, -1); req.rss_cos_lb_ctx_id = - cpu_to_le16(bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx); + cpu_to_le16(bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx]); hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx = INVALID_HW_RING_ID; + bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx] = INVALID_HW_RING_ID; } static void bnxt_hwrm_vnic_ctx_free(struct bnxt *bp) { - int i; + int i, j; for (i = 0; i < bp->nr_vnics; i++) { struct bnxt_vnic_info *vnic = &bp->vnic_info[i]; - if (vnic->fw_rss_cos_lb_ctx != INVALID_HW_RING_ID) - bnxt_hwrm_vnic_ctx_free_one(bp, i); + for (j = 0; j < BNXT_MAX_CTX_PER_VNIC; j++) { + if (vnic->fw_rss_cos_lb_ctx[j] != INVALID_HW_RING_ID) + bnxt_hwrm_vnic_ctx_free_one(bp, i, j); + } } bp->rsscos_nr_ctxs = 0; } -static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id) +static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id, u16 ctx_idx) { int rc; struct hwrm_vnic_rss_cos_lb_ctx_alloc_input req = {0}; @@ -3397,7 +3483,7 @@ static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id) mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) - bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx = + bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx] = le16_to_cpu(resp->rss_cos_lb_ctx_id); mutex_unlock(&bp->hwrm_cmd_lock); @@ -3412,16 +3498,31 @@ static int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id) u16 def_vlan = 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_CFG, -1, -1); + + req.enables = cpu_to_le32(VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP); /* Only RSS support for now TBD: COS & LB */ - req.enables = cpu_to_le32(VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP | - VNIC_CFG_REQ_ENABLES_RSS_RULE | - VNIC_CFG_REQ_ENABLES_MRU); - req.rss_rule = cpu_to_le16(vnic->fw_rss_cos_lb_ctx); - req.cos_rule = cpu_to_le16(0xffff); + if (vnic->fw_rss_cos_lb_ctx[0] != INVALID_HW_RING_ID) { + req.rss_rule = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]); + req.enables |= cpu_to_le32(VNIC_CFG_REQ_ENABLES_RSS_RULE | + VNIC_CFG_REQ_ENABLES_MRU); + } else { + req.rss_rule = cpu_to_le16(0xffff); + } + + if (BNXT_CHIP_TYPE_NITRO_A0(bp) && + (vnic->fw_rss_cos_lb_ctx[0] != INVALID_HW_RING_ID)) { + req.cos_rule = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[1]); + req.enables |= cpu_to_le32(VNIC_CFG_REQ_ENABLES_COS_RULE); + } else { + req.cos_rule = cpu_to_le16(0xffff); + } + if (vnic->flags & BNXT_VNIC_RSS_FLAG) ring = 0; else if (vnic->flags & BNXT_VNIC_RFS_FLAG) ring = vnic_id - 1; + else if ((vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp)) + ring = bp->rx_nr_rings - 1; grp_idx = bp->rx_ring[ring].bnapi->index; req.vnic_id = cpu_to_le16(vnic->fw_vnic_id); @@ -3489,7 +3590,8 @@ static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id, bp->grp_info[grp_idx].fw_grp_id; } - bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx = INVALID_HW_RING_ID; + bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[0] = INVALID_HW_RING_ID; + bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[1] = INVALID_HW_RING_ID; if (vnic_id == 0) req.flags = cpu_to_le32(VNIC_ALLOC_REQ_FLAGS_DEFAULT); @@ -3922,6 +4024,9 @@ static int bnxt_hwrm_stat_ctx_free(struct bnxt *bp) if (!bp->bnapi) return 0; + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) + return 0; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_FREE, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); @@ -3950,6 +4055,9 @@ static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp) struct hwrm_stat_ctx_alloc_input req = {0}; struct hwrm_stat_ctx_alloc_output *resp = bp->hwrm_cmd_resp_addr; + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) + return 0; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_ALLOC, -1, -1); req.update_period_ms = cpu_to_le32(bp->stats_coal_ticks / 1000); @@ -4163,6 +4271,9 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp) bp->hwrm_max_req_len = le16_to_cpu(resp->max_req_win_len); bp->chip_num = le16_to_cpu(resp->chip_num); + if (bp->chip_num == CHIP_NUM_58700 && !resp->chip_rev && + !resp->chip_metal) + bp->flags |= BNXT_FLAG_CHIP_NITRO_A0; hwrm_ver_get_exit: mutex_unlock(&bp->hwrm_cmd_lock); @@ -4252,7 +4363,7 @@ static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id) int rc; /* allocate context for vnic */ - rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id); + rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id, 0); if (rc) { netdev_err(bp->dev, "hwrm vnic %d alloc failure rc: %x\n", vnic_id, rc); @@ -4260,6 +4371,16 @@ static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id) } bp->rsscos_nr_ctxs++; + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) { + rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id, 1); + if (rc) { + netdev_err(bp->dev, "hwrm vnic %d cos ctx alloc failure rc: %x\n", + vnic_id, rc); + goto vnic_setup_err; + } + bp->rsscos_nr_ctxs++; + } + /* configure default vnic, ring grp */ rc = bnxt_hwrm_vnic_cfg(bp, vnic_id); if (rc) { @@ -4327,6 +4448,26 @@ static bool bnxt_promisc_ok(struct bnxt *bp) return true; } +static int bnxt_setup_nitroa0_vnic(struct bnxt *bp) +{ + unsigned int rc = 0; + + rc = bnxt_hwrm_vnic_alloc(bp, 1, bp->rx_nr_rings - 1, 1); + if (rc) { + netdev_err(bp->dev, "Cannot allocate special vnic for NS2 A0: %x\n", + rc); + return rc; + } + + rc = bnxt_hwrm_vnic_cfg(bp, 1); + if (rc) { + netdev_err(bp->dev, "Cannot allocate special vnic for NS2 A0: %x\n", + rc); + return rc; + } + return rc; +} + static int bnxt_cfg_rx_mode(struct bnxt *); static bool bnxt_mc_list_updated(struct bnxt *, u32 *); @@ -4334,6 +4475,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) { struct bnxt_vnic_info *vnic = &bp->vnic_info[0]; int rc = 0; + unsigned int rx_nr_rings = bp->rx_nr_rings; if (irq_re_init) { rc = bnxt_hwrm_stat_ctx_alloc(bp); @@ -4356,8 +4498,11 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) goto err_out; } + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) + rx_nr_rings--; + /* default vnic 0 */ - rc = bnxt_hwrm_vnic_alloc(bp, 0, 0, bp->rx_nr_rings); + rc = bnxt_hwrm_vnic_alloc(bp, 0, 0, rx_nr_rings); if (rc) { netdev_err(bp->dev, "hwrm vnic alloc failure rc: %x\n", rc); goto err_out; @@ -4412,7 +4557,14 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) rc = bnxt_hwrm_set_coal(bp); if (rc) netdev_warn(bp->dev, "HWRM set coalescing failure rc: %x\n", - rc); + rc); + + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) { + rc = bnxt_setup_nitroa0_vnic(bp); + if (rc) + netdev_err(bp->dev, "Special vnic setup failure for NS2 A0 rc: %x\n", + rc); + } if (BNXT_VF(bp)) { bnxt_hwrm_func_qcfg(bp); @@ -4721,14 +4873,23 @@ static void bnxt_del_napi(struct bnxt *bp) static void bnxt_init_napi(struct bnxt *bp) { int i; + unsigned int cp_nr_rings = bp->cp_nr_rings; struct bnxt_napi *bnapi; if (bp->flags & BNXT_FLAG_USING_MSIX) { - for (i = 0; i < bp->cp_nr_rings; i++) { + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) + cp_nr_rings--; + for (i = 0; i < cp_nr_rings; i++) { bnapi = bp->bnapi[i]; netif_napi_add(bp->dev, &bnapi->napi, bnxt_poll, 64); } + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) { + bnapi = bp->bnapi[cp_nr_rings]; + netif_napi_add(bp->dev, &bnapi->napi, + bnxt_poll_nitroa0, 64); + napi_hash_add(&bnapi->napi); + } } else { bnapi = bp->bnapi[0]; netif_napi_add(bp->dev, &bnapi->napi, bnxt_poll, 64); @@ -4769,9 +4930,7 @@ static void bnxt_tx_disable(struct bnxt *bp) for (i = 0; i < bp->tx_nr_rings; i++) { txr = &bp->tx_ring[i]; txq = netdev_get_tx_queue(bp->dev, i); - __netif_tx_lock(txq, smp_processor_id()); txr->dev_state = BNXT_DEV_STATE_CLOSING; - __netif_tx_unlock(txq); } } /* Stop all TX queues */ @@ -5681,7 +5840,7 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) bool update_tpa = false; flags &= ~BNXT_FLAG_ALL_CONFIG_FEATS; - if ((features & NETIF_F_GRO) && (bp->pdev->revision > 0)) + if ((features & NETIF_F_GRO) && !BNXT_CHIP_TYPE_NITRO_A0(bp)) flags |= BNXT_FLAG_GRO; if (features & NETIF_F_LRO) flags |= BNXT_FLAG_LRO; @@ -6488,7 +6647,10 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, *max_cp = min_t(int, *max_cp, bp->pf.max_stat_ctxs); max_ring_grps = bp->pf.max_hw_ring_grps; } - + if (BNXT_CHIP_TYPE_NITRO_A0(bp) && BNXT_PF(bp)) { + *max_cp -= 1; + *max_rx -= 2; + } if (bp->flags & BNXT_FLAG_AGG_RINGS) *max_rx >>= 1; *max_rx = min_t(int, *max_rx, max_ring_grps); @@ -6524,6 +6686,10 @@ static int bnxt_set_dflt_rings(struct bnxt *bp) bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) : bp->tx_nr_rings + bp->rx_nr_rings; bp->num_stat_ctxs = bp->cp_nr_rings; + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) { + bp->rx_nr_rings++; + bp->cp_nr_rings++; + } return rc; } @@ -6550,6 +6716,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) struct bnxt *bp; int rc, max_irqs; + if (pdev->device == 0x16cd && pci_is_bridge(pdev)) + return -ENODEV; + if (version_printed++ == 0) pr_info("%s", version); @@ -6576,13 +6745,25 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, dev); + rc = bnxt_alloc_hwrm_resources(bp); + if (rc) + goto init_err; + + mutex_init(&bp->hwrm_cmd_lock); + rc = bnxt_hwrm_ver_get(bp); + if (rc) + goto init_err; + dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_PARTIAL | NETIF_F_RXHASH | - NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO; + NETIF_F_RXCSUM | NETIF_F_GRO; + + if (!BNXT_CHIP_TYPE_NITRO_A0(bp)) + dev->hw_features |= NETIF_F_LRO; dev->hw_enc_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | @@ -6601,15 +6782,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) #ifdef CONFIG_BNXT_SRIOV init_waitqueue_head(&bp->sriov_cfg_wait); #endif - rc = bnxt_alloc_hwrm_resources(bp); - if (rc) - goto init_err; - - mutex_init(&bp->hwrm_cmd_lock); - rc = bnxt_hwrm_ver_get(bp); - if (rc) - goto init_err; - bp->gro_func = bnxt_gro_func_5730x; if (BNXT_CHIP_NUM_57X1X(bp->chip_num)) bp->gro_func = bnxt_gro_func_5731x; @@ -6647,7 +6819,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) #endif bnxt_set_dflt_rings(bp); - if (BNXT_PF(bp)) { + if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp)) { dev->hw_features |= NETIF_F_NTUPLE; if (bnxt_rfs_capable(bp)) { bp->flags |= BNXT_FLAG_RFS; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 2313e37..5307a2e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -695,7 +695,8 @@ struct bnxt_ring_grp_info { struct bnxt_vnic_info { u16 fw_vnic_id; /* returned by Chimp during alloc */ - u16 fw_rss_cos_lb_ctx; +#define BNXT_MAX_CTX_PER_VNIC 2 + u16 fw_rss_cos_lb_ctx[BNXT_MAX_CTX_PER_VNIC]; u16 fw_l2_ctx_id; #define BNXT_MAX_UC_ADDRS 4 __le64 fw_l2_filter_id[BNXT_MAX_UC_ADDRS]; @@ -893,6 +894,7 @@ struct bnxt { #define CHIP_NUM_57301 0x16c8 #define CHIP_NUM_57302 0x16c9 #define CHIP_NUM_57304 0x16ca +#define CHIP_NUM_58700 0x16cd #define CHIP_NUM_57402 0x16d0 #define CHIP_NUM_57404 0x16d1 #define CHIP_NUM_57406 0x16d2 @@ -954,6 +956,7 @@ struct bnxt { #define BNXT_FLAG_SHARED_RINGS 0x200 #define BNXT_FLAG_PORT_STATS 0x400 #define BNXT_FLAG_EEE_CAP 0x1000 + #define BNXT_FLAG_CHIP_NITRO_A0 0x1000000 #define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA | \ BNXT_FLAG_RFS | \ @@ -963,6 +966,7 @@ struct bnxt { #define BNXT_VF(bp) ((bp)->flags & BNXT_FLAG_VF) #define BNXT_NPAR(bp) ((bp)->port_partition_type) #define BNXT_SINGLE_PF(bp) (BNXT_PF(bp) && !BNXT_NPAR(bp)) +#define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0) struct bnxt_napi **bnapi; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 0f7dd86..b83e174 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -362,9 +362,13 @@ static void bnxt_get_channels(struct net_device *dev, channel->max_other = 0; if (bp->flags & BNXT_FLAG_SHARED_RINGS) { channel->combined_count = bp->rx_nr_rings; + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) + channel->combined_count--; } else { - channel->rx_count = bp->rx_nr_rings; - channel->tx_count = bp->tx_nr_rings_per_tc; + if (!BNXT_CHIP_TYPE_NITRO_A0(bp)) { + channel->rx_count = bp->rx_nr_rings; + channel->tx_count = bp->tx_nr_rings_per_tc; + } } } @@ -387,6 +391,10 @@ static int bnxt_set_channels(struct net_device *dev, (channel->rx_count || channel->tx_count)) return -EINVAL; + if (BNXT_CHIP_TYPE_NITRO_A0(bp) && (channel->rx_count || + channel->tx_count)) + return -EINVAL; + if (channel->combined_count) sh = true; @@ -1684,7 +1692,7 @@ static int bnxt_get_module_eeprom(struct net_device *dev, { struct bnxt *bp = netdev_priv(dev); u16 start = eeprom->offset, length = eeprom->len; - int rc; + int rc = 0; memset(data, 0, eeprom->len); diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig index 4686a85..5713e83 100644 --- a/drivers/net/ethernet/chelsio/Kconfig +++ b/drivers/net/ethernet/chelsio/Kconfig @@ -96,17 +96,6 @@ config CHELSIO_T4_DCB If unsure, say N. -config CHELSIO_T4_UWIRE - bool "Unified Wire Support for Chelsio T5 cards" - default n - depends on CHELSIO_T4 - ---help--- - Enable unified-wire offload features. - Say Y here if you want to enable unified-wire over Ethernet - in the driver. - - If unsure, say N. - config CHELSIO_T4_FCOE bool "Fibre Channel over Ethernet (FCoE) Support for Chelsio T5 cards" default n @@ -137,4 +126,9 @@ config CHELSIO_T4VF To compile this driver as a module choose M here; the module will be called cxgb4vf. +config CHELSIO_LIB + tristate + ---help--- + Common library for Chelsio drivers. + endif # NET_VENDOR_CHELSIO diff --git a/drivers/net/ethernet/chelsio/Makefile b/drivers/net/ethernet/chelsio/Makefile index 390510b..b6a5eec 100644 --- a/drivers/net/ethernet/chelsio/Makefile +++ b/drivers/net/ethernet/chelsio/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_CHELSIO_T1) += cxgb/ obj-$(CONFIG_CHELSIO_T3) += cxgb3/ obj-$(CONFIG_CHELSIO_T4) += cxgb4/ obj-$(CONFIG_CHELSIO_T4VF) += cxgb4vf/ +obj-$(CONFIG_CHELSIO_LIB) += libcxgb/ diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile index 85c9282..ace0ab9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/Makefile +++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile @@ -7,5 +7,4 @@ obj-$(CONFIG_CHELSIO_T4) += cxgb4.o cxgb4-objs := cxgb4_main.o l2t.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o cxgb4-$(CONFIG_CHELSIO_T4_DCB) += cxgb4_dcb.o cxgb4-$(CONFIG_CHELSIO_T4_FCOE) += cxgb4_fcoe.o -cxgb4-$(CONFIG_CHELSIO_T4_UWIRE) += cxgb4_ppm.o cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index b4fceb9..2e2aa9f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -418,6 +418,7 @@ struct trace_params { struct link_config { unsigned short supported; /* link capabilities */ unsigned short advertising; /* advertised capabilities */ + unsigned short lp_advertising; /* peer advertised capabilities */ unsigned short requested_speed; /* speed user has requested */ unsigned short speed; /* actual link speed */ unsigned char requested_fc; /* flow control user has requested */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 7a0b92b..02f80fe 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -480,178 +480,293 @@ static int identify_port(struct net_device *dev, return t4_identify_port(adap, adap->pf, netdev2pinfo(dev)->viid, val); } -static unsigned int from_fw_linkcaps(enum fw_port_type type, unsigned int caps) +/** + * from_fw_port_mod_type - translate Firmware Port/Module type to Ethtool + * @port_type: Firmware Port Type + * @mod_type: Firmware Module Type + * + * Translate Firmware Port/Module type to Ethtool Port Type. + */ +static int from_fw_port_mod_type(enum fw_port_type port_type, + enum fw_port_module_type mod_type) { - unsigned int v = 0; - - if (type == FW_PORT_TYPE_BT_SGMII || type == FW_PORT_TYPE_BT_XFI || - type == FW_PORT_TYPE_BT_XAUI) { - v |= SUPPORTED_TP; - if (caps & FW_PORT_CAP_SPEED_100M) - v |= SUPPORTED_100baseT_Full; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseT_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseT_Full; - } else if (type == FW_PORT_TYPE_KX4 || type == FW_PORT_TYPE_KX) { - v |= SUPPORTED_Backplane; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseKX_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseKX4_Full; - } else if (type == FW_PORT_TYPE_KR) { - v |= SUPPORTED_Backplane | SUPPORTED_10000baseKR_Full; - } else if (type == FW_PORT_TYPE_BP_AP) { - v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC | - SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full; - } else if (type == FW_PORT_TYPE_BP4_AP) { - v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC | - SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full | - SUPPORTED_10000baseKX4_Full; - } else if (type == FW_PORT_TYPE_FIBER_XFI || - type == FW_PORT_TYPE_FIBER_XAUI || - type == FW_PORT_TYPE_SFP || - type == FW_PORT_TYPE_QSFP_10G || - type == FW_PORT_TYPE_QSA) { - v |= SUPPORTED_FIBRE; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseT_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseT_Full; - } else if (type == FW_PORT_TYPE_BP40_BA || - type == FW_PORT_TYPE_QSFP) { - v |= SUPPORTED_40000baseSR4_Full; - v |= SUPPORTED_FIBRE; + if (port_type == FW_PORT_TYPE_BT_SGMII || + port_type == FW_PORT_TYPE_BT_XFI || + port_type == FW_PORT_TYPE_BT_XAUI) { + return PORT_TP; + } else if (port_type == FW_PORT_TYPE_FIBER_XFI || + port_type == FW_PORT_TYPE_FIBER_XAUI) { + return PORT_FIBRE; + } else if (port_type == FW_PORT_TYPE_SFP || + port_type == FW_PORT_TYPE_QSFP_10G || + port_type == FW_PORT_TYPE_QSA || + port_type == FW_PORT_TYPE_QSFP) { + if (mod_type == FW_PORT_MOD_TYPE_LR || + mod_type == FW_PORT_MOD_TYPE_SR || + mod_type == FW_PORT_MOD_TYPE_ER || + mod_type == FW_PORT_MOD_TYPE_LRM) + return PORT_FIBRE; + else if (mod_type == FW_PORT_MOD_TYPE_TWINAX_PASSIVE || + mod_type == FW_PORT_MOD_TYPE_TWINAX_ACTIVE) + return PORT_DA; + else + return PORT_OTHER; } - if (caps & FW_PORT_CAP_ANEG) - v |= SUPPORTED_Autoneg; - return v; + return PORT_OTHER; } -static unsigned int to_fw_linkcaps(unsigned int caps) +/** + * speed_to_fw_caps - translate Port Speed to Firmware Port Capabilities + * @speed: speed in Kb/s + * + * Translates a specific Port Speed into a Firmware Port Capabilities + * value. + */ +static unsigned int speed_to_fw_caps(int speed) { - unsigned int v = 0; - - if (caps & ADVERTISED_100baseT_Full) - v |= FW_PORT_CAP_SPEED_100M; - if (caps & ADVERTISED_1000baseT_Full) - v |= FW_PORT_CAP_SPEED_1G; - if (caps & ADVERTISED_10000baseT_Full) - v |= FW_PORT_CAP_SPEED_10G; - if (caps & ADVERTISED_40000baseSR4_Full) - v |= FW_PORT_CAP_SPEED_40G; - return v; + if (speed == 100) + return FW_PORT_CAP_SPEED_100M; + if (speed == 1000) + return FW_PORT_CAP_SPEED_1G; + if (speed == 10000) + return FW_PORT_CAP_SPEED_10G; + if (speed == 25000) + return FW_PORT_CAP_SPEED_25G; + if (speed == 40000) + return FW_PORT_CAP_SPEED_40G; + if (speed == 100000) + return FW_PORT_CAP_SPEED_100G; + return 0; } -static int get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +/** + * fw_caps_to_lmm - translate Firmware to ethtool Link Mode Mask + * @port_type: Firmware Port Type + * @fw_caps: Firmware Port Capabilities + * @link_mode_mask: ethtool Link Mode Mask + * + * Translate a Firmware Port Capabilities specification to an ethtool + * Link Mode Mask. + */ +static void fw_caps_to_lmm(enum fw_port_type port_type, + unsigned int fw_caps, + unsigned long *link_mode_mask) { - const struct port_info *p = netdev_priv(dev); - - if (p->port_type == FW_PORT_TYPE_BT_SGMII || - p->port_type == FW_PORT_TYPE_BT_XFI || - p->port_type == FW_PORT_TYPE_BT_XAUI) { - cmd->port = PORT_TP; - } else if (p->port_type == FW_PORT_TYPE_FIBER_XFI || - p->port_type == FW_PORT_TYPE_FIBER_XAUI) { - cmd->port = PORT_FIBRE; - } else if (p->port_type == FW_PORT_TYPE_SFP || - p->port_type == FW_PORT_TYPE_QSFP_10G || - p->port_type == FW_PORT_TYPE_QSA || - p->port_type == FW_PORT_TYPE_QSFP) { - if (p->mod_type == FW_PORT_MOD_TYPE_LR || - p->mod_type == FW_PORT_MOD_TYPE_SR || - p->mod_type == FW_PORT_MOD_TYPE_ER || - p->mod_type == FW_PORT_MOD_TYPE_LRM) - cmd->port = PORT_FIBRE; - else if (p->mod_type == FW_PORT_MOD_TYPE_TWINAX_PASSIVE || - p->mod_type == FW_PORT_MOD_TYPE_TWINAX_ACTIVE) - cmd->port = PORT_DA; - else - cmd->port = PORT_OTHER; + #define SET_LMM(__lmm_name) __set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name \ + ## _BIT, link_mode_mask) + + #define FW_CAPS_TO_LMM(__fw_name, __lmm_name) \ + do { \ + if (fw_caps & FW_PORT_CAP_ ## __fw_name) \ + SET_LMM(__lmm_name); \ + } while (0) + + switch (port_type) { + case FW_PORT_TYPE_BT_SGMII: + case FW_PORT_TYPE_BT_XFI: + case FW_PORT_TYPE_BT_XAUI: + SET_LMM(TP); + FW_CAPS_TO_LMM(SPEED_100M, 100baseT_Full); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseT_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseT_Full); + break; + + case FW_PORT_TYPE_KX4: + case FW_PORT_TYPE_KX: + SET_LMM(Backplane); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseKX_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseKX4_Full); + break; + + case FW_PORT_TYPE_KR: + SET_LMM(Backplane); + SET_LMM(10000baseKR_Full); + break; + + case FW_PORT_TYPE_BP_AP: + SET_LMM(Backplane); + SET_LMM(10000baseR_FEC); + SET_LMM(10000baseKR_Full); + SET_LMM(1000baseKX_Full); + break; + + case FW_PORT_TYPE_BP4_AP: + SET_LMM(Backplane); + SET_LMM(10000baseR_FEC); + SET_LMM(10000baseKR_Full); + SET_LMM(1000baseKX_Full); + SET_LMM(10000baseKX4_Full); + break; + + case FW_PORT_TYPE_FIBER_XFI: + case FW_PORT_TYPE_FIBER_XAUI: + case FW_PORT_TYPE_SFP: + case FW_PORT_TYPE_QSFP_10G: + case FW_PORT_TYPE_QSA: + SET_LMM(FIBRE); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseT_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseT_Full); + break; + + case FW_PORT_TYPE_BP40_BA: + case FW_PORT_TYPE_QSFP: + SET_LMM(FIBRE); + SET_LMM(40000baseSR4_Full); + break; + + case FW_PORT_TYPE_CR_QSFP: + case FW_PORT_TYPE_SFP28: + SET_LMM(FIBRE); + SET_LMM(25000baseCR_Full); + break; + + case FW_PORT_TYPE_KR4_100G: + case FW_PORT_TYPE_CR4_QSFP: + SET_LMM(FIBRE); + SET_LMM(100000baseCR4_Full); + break; + + default: + break; + } + + FW_CAPS_TO_LMM(ANEG, Autoneg); + FW_CAPS_TO_LMM(802_3_PAUSE, Pause); + FW_CAPS_TO_LMM(802_3_ASM_DIR, Asym_Pause); + + #undef FW_CAPS_TO_LMM + #undef SET_LMM +} + +/** + * lmm_to_fw_caps - translate ethtool Link Mode Mask to Firmware + * capabilities + * + * @link_mode_mask: ethtool Link Mode Mask + * + * Translate ethtool Link Mode Mask into a Firmware Port capabilities + * value. + */ +static unsigned int lmm_to_fw_caps(const unsigned long *link_mode_mask) +{ + unsigned int fw_caps = 0; + + #define LMM_TO_FW_CAPS(__lmm_name, __fw_name) \ + do { \ + if (test_bit(ETHTOOL_LINK_MODE_ ## __lmm_name ## _BIT, \ + link_mode_mask)) \ + fw_caps |= FW_PORT_CAP_ ## __fw_name; \ + } while (0) + + LMM_TO_FW_CAPS(100baseT_Full, SPEED_100M); + LMM_TO_FW_CAPS(1000baseT_Full, SPEED_1G); + LMM_TO_FW_CAPS(10000baseT_Full, SPEED_10G); + LMM_TO_FW_CAPS(40000baseSR4_Full, SPEED_40G); + LMM_TO_FW_CAPS(25000baseCR_Full, SPEED_25G); + LMM_TO_FW_CAPS(100000baseCR4_Full, SPEED_100G); + + #undef LMM_TO_FW_CAPS + + return fw_caps; +} + +static int get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings) +{ + const struct port_info *pi = netdev_priv(dev); + struct ethtool_link_settings *base = &link_ksettings->base; + + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); + ethtool_link_ksettings_zero_link_mode(link_ksettings, lp_advertising); + + base->port = from_fw_port_mod_type(pi->port_type, pi->mod_type); + + if (pi->mdio_addr >= 0) { + base->phy_address = pi->mdio_addr; + base->mdio_support = (pi->port_type == FW_PORT_TYPE_BT_SGMII + ? ETH_MDIO_SUPPORTS_C22 + : ETH_MDIO_SUPPORTS_C45); } else { - cmd->port = PORT_OTHER; + base->phy_address = 255; + base->mdio_support = 0; } - if (p->mdio_addr >= 0) { - cmd->phy_address = p->mdio_addr; - cmd->transceiver = XCVR_EXTERNAL; - cmd->mdio_support = p->port_type == FW_PORT_TYPE_BT_SGMII ? - MDIO_SUPPORTS_C22 : MDIO_SUPPORTS_C45; + fw_caps_to_lmm(pi->port_type, pi->link_cfg.supported, + link_ksettings->link_modes.supported); + fw_caps_to_lmm(pi->port_type, pi->link_cfg.advertising, + link_ksettings->link_modes.advertising); + fw_caps_to_lmm(pi->port_type, pi->link_cfg.lp_advertising, + link_ksettings->link_modes.lp_advertising); + + if (netif_carrier_ok(dev)) { + base->speed = pi->link_cfg.speed; + base->duplex = DUPLEX_FULL; } else { - cmd->phy_address = 0; /* not really, but no better option */ - cmd->transceiver = XCVR_INTERNAL; - cmd->mdio_support = 0; + base->speed = SPEED_UNKNOWN; + base->duplex = DUPLEX_UNKNOWN; } - cmd->supported = from_fw_linkcaps(p->port_type, p->link_cfg.supported); - cmd->advertising = from_fw_linkcaps(p->port_type, - p->link_cfg.advertising); - ethtool_cmd_speed_set(cmd, - netif_carrier_ok(dev) ? p->link_cfg.speed : 0); - cmd->duplex = DUPLEX_FULL; - cmd->autoneg = p->link_cfg.autoneg; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; - return 0; -} + base->autoneg = pi->link_cfg.autoneg; + if (pi->link_cfg.supported & FW_PORT_CAP_ANEG) + ethtool_link_ksettings_add_link_mode(link_ksettings, + supported, Autoneg); + if (pi->link_cfg.autoneg) + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Autoneg); -static unsigned int speed_to_caps(int speed) -{ - if (speed == 100) - return FW_PORT_CAP_SPEED_100M; - if (speed == 1000) - return FW_PORT_CAP_SPEED_1G; - if (speed == 10000) - return FW_PORT_CAP_SPEED_10G; - if (speed == 40000) - return FW_PORT_CAP_SPEED_40G; return 0; } -static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings + *link_ksettings) { - unsigned int cap; - struct port_info *p = netdev_priv(dev); - struct link_config *lc = &p->link_cfg; - u32 speed = ethtool_cmd_speed(cmd); + struct port_info *pi = netdev_priv(dev); + struct link_config *lc = &pi->link_cfg; + const struct ethtool_link_settings *base = &link_ksettings->base; struct link_config old_lc; - int ret; + unsigned int fw_caps; + int ret = 0; - if (cmd->duplex != DUPLEX_FULL) /* only full-duplex supported */ + /* only full-duplex supported */ + if (base->duplex != DUPLEX_FULL) return -EINVAL; if (!(lc->supported & FW_PORT_CAP_ANEG)) { /* PHY offers a single speed. See if that's what's * being requested. */ - if (cmd->autoneg == AUTONEG_DISABLE && - (lc->supported & speed_to_caps(speed))) + if (base->autoneg == AUTONEG_DISABLE && + (lc->supported & speed_to_fw_caps(base->speed))) return 0; return -EINVAL; } old_lc = *lc; - if (cmd->autoneg == AUTONEG_DISABLE) { - cap = speed_to_caps(speed); + if (base->autoneg == AUTONEG_DISABLE) { + fw_caps = speed_to_fw_caps(base->speed); - if (!(lc->supported & cap)) + if (!(lc->supported & fw_caps)) return -EINVAL; - lc->requested_speed = cap; + lc->requested_speed = fw_caps; lc->advertising = 0; } else { - cap = to_fw_linkcaps(cmd->advertising); - if (!(lc->supported & cap)) + fw_caps = + lmm_to_fw_caps(link_ksettings->link_modes.advertising); + + if (!(lc->supported & fw_caps)) return -EINVAL; lc->requested_speed = 0; - lc->advertising = cap | FW_PORT_CAP_ANEG; + lc->advertising = fw_caps | FW_PORT_CAP_ANEG; } - lc->autoneg = cmd->autoneg; + lc->autoneg = base->autoneg; /* If the firmware rejects the Link Configuration request, back out * the changes and report the error. */ - ret = t4_link_l1cfg(p->adapter, p->adapter->mbox, p->tx_chan, lc); + ret = t4_link_l1cfg(pi->adapter, pi->adapter->mbox, pi->tx_chan, lc); if (ret) *lc = old_lc; @@ -1093,8 +1208,8 @@ static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, } static const struct ethtool_ops cxgb_ethtool_ops = { - .get_settings = get_settings, - .set_settings = set_settings, + .get_link_ksettings = get_link_ksettings, + .set_link_ksettings = set_link_ksettings, .get_drvinfo = get_drvinfo, .get_msglevel = get_msglevel, .set_msglevel = set_msglevel, diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index a63addb..dc92c80 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -7219,6 +7219,7 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) lc->speed = speed; lc->fc = fc; lc->supported = be16_to_cpu(p->u.info.pcap); + lc->lp_advertising = be16_to_cpu(p->u.info.lpacap); t4_os_link_changed(adap, pi->port_id, link_ok); } } @@ -7284,6 +7285,7 @@ static void get_pci_mode(struct adapter *adapter, struct pci_params *p) static void init_link_config(struct link_config *lc, unsigned int caps) { lc->supported = caps; + lc->lp_advertising = 0; lc->requested_speed = 0; lc->speed = 0; lc->requested_fc = lc->fc = PAUSE_RX | PAUSE_TX; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 392d664..a89b307 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -2249,20 +2249,20 @@ struct fw_acl_vlan_cmd { enum fw_port_cap { FW_PORT_CAP_SPEED_100M = 0x0001, FW_PORT_CAP_SPEED_1G = 0x0002, - FW_PORT_CAP_SPEED_2_5G = 0x0004, + FW_PORT_CAP_SPEED_25G = 0x0004, FW_PORT_CAP_SPEED_10G = 0x0008, FW_PORT_CAP_SPEED_40G = 0x0010, FW_PORT_CAP_SPEED_100G = 0x0020, FW_PORT_CAP_FC_RX = 0x0040, FW_PORT_CAP_FC_TX = 0x0080, FW_PORT_CAP_ANEG = 0x0100, - FW_PORT_CAP_MDI_0 = 0x0200, - FW_PORT_CAP_MDI_1 = 0x0400, - FW_PORT_CAP_BEAN = 0x0800, - FW_PORT_CAP_PMA_LPBK = 0x1000, - FW_PORT_CAP_PCS_LPBK = 0x2000, - FW_PORT_CAP_PHYXS_LPBK = 0x4000, - FW_PORT_CAP_FAR_END_LPBK = 0x8000, + FW_PORT_CAP_MDIX = 0x0200, + FW_PORT_CAP_MDIAUTO = 0x0400, + FW_PORT_CAP_FEC = 0x0800, + FW_PORT_CAP_TECHKR = 0x1000, + FW_PORT_CAP_TECHKX4 = 0x2000, + FW_PORT_CAP_802_3_PAUSE = 0x4000, + FW_PORT_CAP_802_3_ASM_DIR = 0x8000, }; enum fw_port_mdi { @@ -2376,7 +2376,8 @@ struct fw_port_cmd { __u8 cbllen; __u8 auxlinfo; __u8 dcbxdis_pkd; - __u8 r8_lo[3]; + __u8 r8_lo; + __be16 lpacap; __be64 r9; } info; struct fw_port_diags { @@ -2555,6 +2556,11 @@ enum fw_port_type { FW_PORT_TYPE_QSA, FW_PORT_TYPE_QSFP, FW_PORT_TYPE_BP40_BA, + FW_PORT_TYPE_KR4_100G, + FW_PORT_TYPE_CR4_QSFP, + FW_PORT_TYPE_CR_QSFP, + FW_PORT_TYPE_CR2_QSFP, + FW_PORT_TYPE_SFP28, FW_PORT_TYPE_NONE = FW_PORT_CMD_PTYPE_M }; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 9f55264..e116bb8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -1201,105 +1201,187 @@ static void cxgb4vf_poll_controller(struct net_device *dev) * state of the port to which we're linked. */ -static unsigned int t4vf_from_fw_linkcaps(enum fw_port_type type, - unsigned int caps) -{ - unsigned int v = 0; - - if (type == FW_PORT_TYPE_BT_SGMII || type == FW_PORT_TYPE_BT_XFI || - type == FW_PORT_TYPE_BT_XAUI) { - v |= SUPPORTED_TP; - if (caps & FW_PORT_CAP_SPEED_100M) - v |= SUPPORTED_100baseT_Full; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseT_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseT_Full; - } else if (type == FW_PORT_TYPE_KX4 || type == FW_PORT_TYPE_KX) { - v |= SUPPORTED_Backplane; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseKX_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseKX4_Full; - } else if (type == FW_PORT_TYPE_KR) - v |= SUPPORTED_Backplane | SUPPORTED_10000baseKR_Full; - else if (type == FW_PORT_TYPE_BP_AP) - v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC | - SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full; - else if (type == FW_PORT_TYPE_BP4_AP) - v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC | - SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full | - SUPPORTED_10000baseKX4_Full; - else if (type == FW_PORT_TYPE_FIBER_XFI || - type == FW_PORT_TYPE_FIBER_XAUI || - type == FW_PORT_TYPE_SFP || - type == FW_PORT_TYPE_QSFP_10G || - type == FW_PORT_TYPE_QSA) { - v |= SUPPORTED_FIBRE; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseT_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseT_Full; - } else if (type == FW_PORT_TYPE_BP40_BA || - type == FW_PORT_TYPE_QSFP) { - v |= SUPPORTED_40000baseSR4_Full; - v |= SUPPORTED_FIBRE; - } - - if (caps & FW_PORT_CAP_ANEG) - v |= SUPPORTED_Autoneg; - return v; -} - -static int cxgb4vf_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - const struct port_info *p = netdev_priv(dev); - - if (p->port_type == FW_PORT_TYPE_BT_SGMII || - p->port_type == FW_PORT_TYPE_BT_XFI || - p->port_type == FW_PORT_TYPE_BT_XAUI) - cmd->port = PORT_TP; - else if (p->port_type == FW_PORT_TYPE_FIBER_XFI || - p->port_type == FW_PORT_TYPE_FIBER_XAUI) - cmd->port = PORT_FIBRE; - else if (p->port_type == FW_PORT_TYPE_SFP || - p->port_type == FW_PORT_TYPE_QSFP_10G || - p->port_type == FW_PORT_TYPE_QSA || - p->port_type == FW_PORT_TYPE_QSFP) { - if (p->mod_type == FW_PORT_MOD_TYPE_LR || - p->mod_type == FW_PORT_MOD_TYPE_SR || - p->mod_type == FW_PORT_MOD_TYPE_ER || - p->mod_type == FW_PORT_MOD_TYPE_LRM) - cmd->port = PORT_FIBRE; - else if (p->mod_type == FW_PORT_MOD_TYPE_TWINAX_PASSIVE || - p->mod_type == FW_PORT_MOD_TYPE_TWINAX_ACTIVE) - cmd->port = PORT_DA; +/** + * from_fw_port_mod_type - translate Firmware Port/Module type to Ethtool + * @port_type: Firmware Port Type + * @mod_type: Firmware Module Type + * + * Translate Firmware Port/Module type to Ethtool Port Type. + */ +static int from_fw_port_mod_type(enum fw_port_type port_type, + enum fw_port_module_type mod_type) +{ + if (port_type == FW_PORT_TYPE_BT_SGMII || + port_type == FW_PORT_TYPE_BT_XFI || + port_type == FW_PORT_TYPE_BT_XAUI) { + return PORT_TP; + } else if (port_type == FW_PORT_TYPE_FIBER_XFI || + port_type == FW_PORT_TYPE_FIBER_XAUI) { + return PORT_FIBRE; + } else if (port_type == FW_PORT_TYPE_SFP || + port_type == FW_PORT_TYPE_QSFP_10G || + port_type == FW_PORT_TYPE_QSA || + port_type == FW_PORT_TYPE_QSFP) { + if (mod_type == FW_PORT_MOD_TYPE_LR || + mod_type == FW_PORT_MOD_TYPE_SR || + mod_type == FW_PORT_MOD_TYPE_ER || + mod_type == FW_PORT_MOD_TYPE_LRM) + return PORT_FIBRE; + else if (mod_type == FW_PORT_MOD_TYPE_TWINAX_PASSIVE || + mod_type == FW_PORT_MOD_TYPE_TWINAX_ACTIVE) + return PORT_DA; else - cmd->port = PORT_OTHER; - } else - cmd->port = PORT_OTHER; + return PORT_OTHER; + } + + return PORT_OTHER; +} + +/** + * fw_caps_to_lmm - translate Firmware to ethtool Link Mode Mask + * @port_type: Firmware Port Type + * @fw_caps: Firmware Port Capabilities + * @link_mode_mask: ethtool Link Mode Mask + * + * Translate a Firmware Port Capabilities specification to an ethtool + * Link Mode Mask. + */ +static void fw_caps_to_lmm(enum fw_port_type port_type, + unsigned int fw_caps, + unsigned long *link_mode_mask) +{ + #define SET_LMM(__lmm_name) __set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name\ + ## _BIT, link_mode_mask) + + #define FW_CAPS_TO_LMM(__fw_name, __lmm_name) \ + do { \ + if (fw_caps & FW_PORT_CAP_ ## __fw_name) \ + SET_LMM(__lmm_name); \ + } while (0) + + switch (port_type) { + case FW_PORT_TYPE_BT_SGMII: + case FW_PORT_TYPE_BT_XFI: + case FW_PORT_TYPE_BT_XAUI: + SET_LMM(TP); + FW_CAPS_TO_LMM(SPEED_100M, 100baseT_Full); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseT_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseT_Full); + break; + + case FW_PORT_TYPE_KX4: + case FW_PORT_TYPE_KX: + SET_LMM(Backplane); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseKX_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseKX4_Full); + break; + + case FW_PORT_TYPE_KR: + SET_LMM(Backplane); + SET_LMM(10000baseKR_Full); + break; + + case FW_PORT_TYPE_BP_AP: + SET_LMM(Backplane); + SET_LMM(10000baseR_FEC); + SET_LMM(10000baseKR_Full); + SET_LMM(1000baseKX_Full); + break; + + case FW_PORT_TYPE_BP4_AP: + SET_LMM(Backplane); + SET_LMM(10000baseR_FEC); + SET_LMM(10000baseKR_Full); + SET_LMM(1000baseKX_Full); + SET_LMM(10000baseKX4_Full); + break; + + case FW_PORT_TYPE_FIBER_XFI: + case FW_PORT_TYPE_FIBER_XAUI: + case FW_PORT_TYPE_SFP: + case FW_PORT_TYPE_QSFP_10G: + case FW_PORT_TYPE_QSA: + SET_LMM(FIBRE); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseT_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseT_Full); + break; - if (p->mdio_addr >= 0) { - cmd->phy_address = p->mdio_addr; - cmd->transceiver = XCVR_EXTERNAL; - cmd->mdio_support = p->port_type == FW_PORT_TYPE_BT_SGMII ? - MDIO_SUPPORTS_C22 : MDIO_SUPPORTS_C45; + case FW_PORT_TYPE_BP40_BA: + case FW_PORT_TYPE_QSFP: + SET_LMM(FIBRE); + SET_LMM(40000baseSR4_Full); + break; + + case FW_PORT_TYPE_CR_QSFP: + case FW_PORT_TYPE_SFP28: + SET_LMM(FIBRE); + SET_LMM(25000baseCR_Full); + break; + + case FW_PORT_TYPE_KR4_100G: + case FW_PORT_TYPE_CR4_QSFP: + SET_LMM(FIBRE); + SET_LMM(100000baseCR4_Full); + break; + + default: + break; + } + + FW_CAPS_TO_LMM(ANEG, Autoneg); + FW_CAPS_TO_LMM(802_3_PAUSE, Pause); + FW_CAPS_TO_LMM(802_3_ASM_DIR, Asym_Pause); + + #undef FW_CAPS_TO_LMM + #undef SET_LMM +} + +static int cxgb4vf_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings + *link_ksettings) +{ + const struct port_info *pi = netdev_priv(dev); + struct ethtool_link_settings *base = &link_ksettings->base; + + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); + ethtool_link_ksettings_zero_link_mode(link_ksettings, lp_advertising); + + base->port = from_fw_port_mod_type(pi->port_type, pi->mod_type); + + if (pi->mdio_addr >= 0) { + base->phy_address = pi->mdio_addr; + base->mdio_support = (pi->port_type == FW_PORT_TYPE_BT_SGMII + ? ETH_MDIO_SUPPORTS_C22 + : ETH_MDIO_SUPPORTS_C45); + } else { + base->phy_address = 255; + base->mdio_support = 0; + } + + fw_caps_to_lmm(pi->port_type, pi->link_cfg.supported, + link_ksettings->link_modes.supported); + fw_caps_to_lmm(pi->port_type, pi->link_cfg.advertising, + link_ksettings->link_modes.advertising); + fw_caps_to_lmm(pi->port_type, pi->link_cfg.lp_advertising, + link_ksettings->link_modes.lp_advertising); + + if (netif_carrier_ok(dev)) { + base->speed = pi->link_cfg.speed; + base->duplex = DUPLEX_FULL; } else { - cmd->phy_address = 0; /* not really, but no better option */ - cmd->transceiver = XCVR_INTERNAL; - cmd->mdio_support = 0; - } - - cmd->supported = t4vf_from_fw_linkcaps(p->port_type, - p->link_cfg.supported); - cmd->advertising = t4vf_from_fw_linkcaps(p->port_type, - p->link_cfg.advertising); - ethtool_cmd_speed_set(cmd, - netif_carrier_ok(dev) ? p->link_cfg.speed : 0); - cmd->duplex = DUPLEX_FULL; - cmd->autoneg = p->link_cfg.autoneg; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; + base->speed = SPEED_UNKNOWN; + base->duplex = DUPLEX_UNKNOWN; + } + + base->autoneg = pi->link_cfg.autoneg; + if (pi->link_cfg.supported & FW_PORT_CAP_ANEG) + ethtool_link_ksettings_add_link_mode(link_ksettings, + supported, Autoneg); + if (pi->link_cfg.autoneg) + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Autoneg); + return 0; } @@ -1675,7 +1757,7 @@ static void cxgb4vf_get_wol(struct net_device *dev, #define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN) static const struct ethtool_ops cxgb4vf_ethtool_ops = { - .get_settings = cxgb4vf_get_settings, + .get_link_ksettings = cxgb4vf_get_link_ksettings, .get_drvinfo = cxgb4vf_get_drvinfo, .get_msglevel = cxgb4vf_get_msglevel, .set_msglevel = cxgb4vf_set_msglevel, diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h index 438374a..8ee5414 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h @@ -107,6 +107,7 @@ struct t4vf_port_stats { struct link_config { unsigned int supported; /* link capabilities */ unsigned int advertising; /* advertised capabilities */ + unsigned short lp_advertising; /* peer advertised capabilities */ unsigned short requested_speed; /* speed user has requested */ unsigned short speed; /* actual link speed */ unsigned char requested_fc; /* flow control user has requested */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index 61bfe86..427bfa7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -328,6 +328,7 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, static void init_link_config(struct link_config *lc, unsigned int caps) { lc->supported = caps; + lc->lp_advertising = 0; lc->requested_speed = 0; lc->speed = 0; lc->requested_fc = lc->fc = PAUSE_RX | PAUSE_TX; @@ -1743,6 +1744,8 @@ int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl) lc->fc = fc; lc->supported = be16_to_cpu(port_cmd->u.info.pcap); + lc->lp_advertising = + be16_to_cpu(port_cmd->u.info.lpacap); t4vf_os_link_changed(adapter, pidx, link_ok); } } diff --git a/drivers/net/ethernet/chelsio/libcxgb/Makefile b/drivers/net/ethernet/chelsio/libcxgb/Makefile new file mode 100644 index 0000000..2362230 --- /dev/null +++ b/drivers/net/ethernet/chelsio/libcxgb/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_CHELSIO_LIB) += libcxgb.o + +libcxgb-y := libcxgb_ppm.o diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c index d88a7a7..0ed1616 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ppm.c +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c @@ -1,17 +1,44 @@ /* - * cxgb4_ppm.c: Chelsio common library for T4/T5 iSCSI PagePod Manager + * libcxgb_ppm.c: Chelsio common library for T3/T4/T5 iSCSI PagePod Manager * * Copyright (c) 2016 Chelsio Communications, Inc. All rights reserved. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. * * Written by: Karen Xie (kxie@chelsio.com) */ +#define DRV_NAME "libcxgb" +#define DRV_VERSION "1.0.0-ko" +#define pr_fmt(fmt) DRV_NAME ": " fmt + #include <linux/kernel.h> -#include <linux/version.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> @@ -22,7 +49,7 @@ #include <linux/pci.h> #include <linux/scatterlist.h> -#include "cxgb4_ppm.h" +#include "libcxgb_ppm.h" /* Direct Data Placement - * Directly place the iSCSI Data-In or Data-Out PDU's payload into @@ -309,6 +336,7 @@ int cxgbi_ppm_release(struct cxgbi_ppm *ppm) } return 1; } +EXPORT_SYMBOL(cxgbi_ppm_release); static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total, unsigned int *pcpu_ppmax) @@ -462,3 +490,9 @@ unsigned int cxgbi_tagmask_set(unsigned int ppmax) return 1 << (bits + PPOD_IDX_SHIFT); } +EXPORT_SYMBOL(cxgbi_tagmask_set); + +MODULE_AUTHOR("Chelsio Communications"); +MODULE_DESCRIPTION("Chelsio common library"); +MODULE_VERSION(DRV_VERSION); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ppm.h b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h index d487326..e995a1a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ppm.h +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h @@ -1,17 +1,41 @@ /* - * cxgb4_ppm.h: Chelsio common library for T4/T5 iSCSI ddp operation + * libcxgb_ppm.h: Chelsio common library for T3/T4/T5 iSCSI ddp operation * * Copyright (c) 2016 Chelsio Communications, Inc. All rights reserved. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. * * Written by: Karen Xie (kxie@chelsio.com) */ -#ifndef __CXGB4PPM_H__ -#define __CXGB4PPM_H__ +#ifndef __LIBCXGB_PPM_H__ +#define __LIBCXGB_PPM_H__ #include <linux/kernel.h> #include <linux/errno.h> @@ -307,4 +331,4 @@ int cxgbi_ppm_release(struct cxgbi_ppm *ppm); void cxgbi_tagmask_check(unsigned int tagmask, struct cxgbi_tag_format *); unsigned int cxgbi_tagmask_set(unsigned int ppmax); -#endif /*__CXGB4PPM_H__*/ +#endif /*__LIBCXGB_PPM_H__*/ diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index 37a39b4..c044667 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -857,6 +857,11 @@ static netdev_tx_t ethoc_start_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int entry; void *dest; + if (skb_put_padto(skb, ETHOC_ZLEN)) { + dev->stats.tx_errors++; + goto out_no_free; + } + if (unlikely(skb->len > ETHOC_BUFSIZ)) { dev->stats.tx_errors++; goto out; @@ -891,6 +896,7 @@ static netdev_tx_t ethoc_start_xmit(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); out: dev_kfree_skb(skb); +out_no_free: return NETDEV_TX_OK; } @@ -1061,7 +1067,7 @@ static int ethoc_probe(struct platform_device *pdev) if (!priv->iobase) { dev_err(&pdev->dev, "cannot remap I/O memory space\n"); ret = -ENXIO; - goto error; + goto free; } if (netdev->mem_end) { @@ -1070,7 +1076,7 @@ static int ethoc_probe(struct platform_device *pdev) if (!priv->membase) { dev_err(&pdev->dev, "cannot remap memory space\n"); ret = -ENXIO; - goto error; + goto free; } } else { /* Allocate buffer memory */ @@ -1081,7 +1087,7 @@ static int ethoc_probe(struct platform_device *pdev) dev_err(&pdev->dev, "cannot allocate %dB buffer\n", buffer_size); ret = -ENOMEM; - goto error; + goto free; } netdev->mem_end = netdev->mem_start + buffer_size; priv->dma_alloc = buffer_size; @@ -1095,7 +1101,7 @@ static int ethoc_probe(struct platform_device *pdev) 128, (netdev->mem_end - netdev->mem_start + 1) / ETHOC_BUFSIZ); if (num_bd < 4) { ret = -ENODEV; - goto error; + goto free; } priv->num_bd = num_bd; /* num_tx must be a power of two */ @@ -1108,7 +1114,7 @@ static int ethoc_probe(struct platform_device *pdev) priv->vma = devm_kzalloc(&pdev->dev, num_bd*sizeof(void *), GFP_KERNEL); if (!priv->vma) { ret = -ENOMEM; - goto error; + goto free; } /* Allow the platform setup code to pass in a MAC address. */ diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index 25faa3d..f928e6f 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -287,6 +287,7 @@ static void nps_enet_hw_reset(struct net_device *ndev) ge_rst_value |= NPS_ENET_ENABLE << RST_GMAC_0_SHIFT; nps_enet_reg_set(priv, NPS_ENET_REG_GE_RST, ge_rst_value); usleep_range(10, 20); + ge_rst_value = 0; nps_enet_reg_set(priv, NPS_ENET_REG_GE_RST, ge_rst_value); /* Tx fifo reset sequence */ diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index e7cf313..36361f8 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -31,6 +31,7 @@ #include <linux/phy.h> #include <linux/platform_device.h> #include <net/ip.h> +#include <net/ncsi.h> #include "ftgmac100.h" @@ -68,10 +69,14 @@ struct ftgmac100 { struct net_device *netdev; struct device *dev; + struct ncsi_dev *ndev; struct napi_struct napi; struct mii_bus *mii_bus; int old_speed; + int int_mask_all; + bool use_ncsi; + bool enabled; }; static int ftgmac100_alloc_rx_page(struct ftgmac100 *priv, @@ -80,14 +85,6 @@ static int ftgmac100_alloc_rx_page(struct ftgmac100 *priv, /****************************************************************************** * internal functions (hardware register access) *****************************************************************************/ -#define INT_MASK_ALL_ENABLED (FTGMAC100_INT_RPKT_LOST | \ - FTGMAC100_INT_XPKT_ETH | \ - FTGMAC100_INT_XPKT_LOST | \ - FTGMAC100_INT_AHB_ERR | \ - FTGMAC100_INT_PHYSTS_CHG | \ - FTGMAC100_INT_RPKT_BUF | \ - FTGMAC100_INT_NO_RXBUF) - static void ftgmac100_set_rx_ring_base(struct ftgmac100 *priv, dma_addr_t addr) { iowrite32(addr, priv->base + FTGMAC100_OFFSET_RXR_BADR); @@ -141,6 +138,55 @@ static void ftgmac100_set_mac(struct ftgmac100 *priv, const unsigned char *mac) iowrite32(laddr, priv->base + FTGMAC100_OFFSET_MAC_LADR); } +static void ftgmac100_setup_mac(struct ftgmac100 *priv) +{ + u8 mac[ETH_ALEN]; + unsigned int m; + unsigned int l; + void *addr; + + addr = device_get_mac_address(priv->dev, mac, ETH_ALEN); + if (addr) { + ether_addr_copy(priv->netdev->dev_addr, mac); + dev_info(priv->dev, "Read MAC address %pM from device tree\n", + mac); + return; + } + + m = ioread32(priv->base + FTGMAC100_OFFSET_MAC_MADR); + l = ioread32(priv->base + FTGMAC100_OFFSET_MAC_LADR); + + mac[0] = (m >> 8) & 0xff; + mac[1] = m & 0xff; + mac[2] = (l >> 24) & 0xff; + mac[3] = (l >> 16) & 0xff; + mac[4] = (l >> 8) & 0xff; + mac[5] = l & 0xff; + + if (is_valid_ether_addr(mac)) { + ether_addr_copy(priv->netdev->dev_addr, mac); + dev_info(priv->dev, "Read MAC address %pM from chip\n", mac); + } else { + eth_hw_addr_random(priv->netdev); + dev_info(priv->dev, "Generated random MAC address %pM\n", + priv->netdev->dev_addr); + } +} + +static int ftgmac100_set_mac_addr(struct net_device *dev, void *p) +{ + int ret; + + ret = eth_prepare_mac_addr_change(dev, p); + if (ret < 0) + return ret; + + eth_commit_mac_addr_change(dev, p); + ftgmac100_set_mac(netdev_priv(dev), dev->dev_addr); + + return 0; +} + static void ftgmac100_init_hw(struct ftgmac100 *priv) { /* setup ring buffer base registers */ @@ -952,7 +998,10 @@ static irqreturn_t ftgmac100_interrupt(int irq, void *dev_id) struct net_device *netdev = dev_id; struct ftgmac100 *priv = netdev_priv(netdev); - if (likely(netif_running(netdev))) { + /* When running in NCSI mode, the interface should be ready for + * receiving or transmitting NCSI packets before it's opened. + */ + if (likely(priv->use_ncsi || netif_running(netdev))) { /* Disable interrupts for polling */ iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); napi_schedule(&priv->napi); @@ -1005,8 +1054,9 @@ static int ftgmac100_poll(struct napi_struct *napi, int budget) ftgmac100_tx_complete(priv); } - if (status & (FTGMAC100_INT_NO_RXBUF | FTGMAC100_INT_RPKT_LOST | - FTGMAC100_INT_AHB_ERR | FTGMAC100_INT_PHYSTS_CHG)) { + if (status & priv->int_mask_all & (FTGMAC100_INT_NO_RXBUF | + FTGMAC100_INT_RPKT_LOST | FTGMAC100_INT_AHB_ERR | + FTGMAC100_INT_PHYSTS_CHG)) { if (net_ratelimit()) netdev_info(netdev, "[ISR] = 0x%x: %s%s%s%s\n", status, status & FTGMAC100_INT_NO_RXBUF ? "NO_RXBUF " : "", @@ -1029,7 +1079,8 @@ static int ftgmac100_poll(struct napi_struct *napi, int budget) napi_complete(napi); /* enable all interrupts */ - iowrite32(INT_MASK_ALL_ENABLED, priv->base + FTGMAC100_OFFSET_IER); + iowrite32(priv->int_mask_all, + priv->base + FTGMAC100_OFFSET_IER); } return rx; @@ -1065,17 +1116,33 @@ static int ftgmac100_open(struct net_device *netdev) goto err_hw; ftgmac100_init_hw(priv); - ftgmac100_start_hw(priv, 10); - - phy_start(netdev->phydev); + ftgmac100_start_hw(priv, priv->use_ncsi ? 100 : 10); + if (netdev->phydev) + phy_start(netdev->phydev); + else if (priv->use_ncsi) + netif_carrier_on(netdev); napi_enable(&priv->napi); netif_start_queue(netdev); /* enable all interrupts */ - iowrite32(INT_MASK_ALL_ENABLED, priv->base + FTGMAC100_OFFSET_IER); + iowrite32(priv->int_mask_all, priv->base + FTGMAC100_OFFSET_IER); + + /* Start the NCSI device */ + if (priv->use_ncsi) { + err = ncsi_start_dev(priv->ndev); + if (err) + goto err_ncsi; + } + + priv->enabled = true; + return 0; +err_ncsi: + napi_disable(&priv->napi); + netif_stop_queue(netdev); + iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); err_hw: free_irq(priv->irq, netdev); err_irq: @@ -1088,12 +1155,17 @@ static int ftgmac100_stop(struct net_device *netdev) { struct ftgmac100 *priv = netdev_priv(netdev); + if (!priv->enabled) + return 0; + /* disable all interrupts */ + priv->enabled = false; iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); netif_stop_queue(netdev); napi_disable(&priv->napi); - phy_stop(netdev->phydev); + if (netdev->phydev) + phy_stop(netdev->phydev); ftgmac100_stop_hw(priv); free_irq(priv->irq, netdev); @@ -1134,6 +1206,9 @@ static int ftgmac100_hard_start_xmit(struct sk_buff *skb, /* optional */ static int ftgmac100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) { + if (!netdev->phydev) + return -ENXIO; + return phy_mii_ioctl(netdev->phydev, ifr, cmd); } @@ -1141,11 +1216,74 @@ static const struct net_device_ops ftgmac100_netdev_ops = { .ndo_open = ftgmac100_open, .ndo_stop = ftgmac100_stop, .ndo_start_xmit = ftgmac100_hard_start_xmit, - .ndo_set_mac_address = eth_mac_addr, + .ndo_set_mac_address = ftgmac100_set_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_do_ioctl = ftgmac100_do_ioctl, }; +static int ftgmac100_setup_mdio(struct net_device *netdev) +{ + struct ftgmac100 *priv = netdev_priv(netdev); + struct platform_device *pdev = to_platform_device(priv->dev); + int i, err = 0; + + /* initialize mdio bus */ + priv->mii_bus = mdiobus_alloc(); + if (!priv->mii_bus) + return -EIO; + + priv->mii_bus->name = "ftgmac100_mdio"; + snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%d", + pdev->name, pdev->id); + priv->mii_bus->priv = priv->netdev; + priv->mii_bus->read = ftgmac100_mdiobus_read; + priv->mii_bus->write = ftgmac100_mdiobus_write; + + for (i = 0; i < PHY_MAX_ADDR; i++) + priv->mii_bus->irq[i] = PHY_POLL; + + err = mdiobus_register(priv->mii_bus); + if (err) { + dev_err(priv->dev, "Cannot register MDIO bus!\n"); + goto err_register_mdiobus; + } + + err = ftgmac100_mii_probe(priv); + if (err) { + dev_err(priv->dev, "MII Probe failed!\n"); + goto err_mii_probe; + } + + return 0; + +err_mii_probe: + mdiobus_unregister(priv->mii_bus); +err_register_mdiobus: + mdiobus_free(priv->mii_bus); + return err; +} + +static void ftgmac100_destroy_mdio(struct net_device *netdev) +{ + struct ftgmac100 *priv = netdev_priv(netdev); + + if (!netdev->phydev) + return; + + phy_disconnect(netdev->phydev); + mdiobus_unregister(priv->mii_bus); + mdiobus_free(priv->mii_bus); +} + +static void ftgmac100_ncsi_handler(struct ncsi_dev *nd) +{ + if (unlikely(nd->state != ncsi_dev_state_functional)) + return; + + netdev_info(nd->dev, "NCSI interface %s\n", + nd->link_up ? "up" : "down"); +} + /****************************************************************************** * struct platform_driver functions *****************************************************************************/ @@ -1155,7 +1293,7 @@ static int ftgmac100_probe(struct platform_device *pdev) int irq; struct net_device *netdev; struct ftgmac100 *priv; - int err; + int err = 0; if (!pdev) return -ENODEV; @@ -1179,7 +1317,6 @@ static int ftgmac100_probe(struct platform_device *pdev) netdev->ethtool_ops = &ftgmac100_ethtool_ops; netdev->netdev_ops = &ftgmac100_netdev_ops; - netdev->features = NETIF_F_IP_CSUM | NETIF_F_GRO; platform_set_drvdata(pdev, netdev); @@ -1211,31 +1348,45 @@ static int ftgmac100_probe(struct platform_device *pdev) priv->irq = irq; - /* initialize mdio bus */ - priv->mii_bus = mdiobus_alloc(); - if (!priv->mii_bus) { - err = -EIO; - goto err_alloc_mdiobus; - } - - priv->mii_bus->name = "ftgmac100_mdio"; - snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "ftgmac100_mii"); - - priv->mii_bus->priv = netdev; - priv->mii_bus->read = ftgmac100_mdiobus_read; - priv->mii_bus->write = ftgmac100_mdiobus_write; + /* MAC address from chip or random one */ + ftgmac100_setup_mac(priv); + + priv->int_mask_all = (FTGMAC100_INT_RPKT_LOST | + FTGMAC100_INT_XPKT_ETH | + FTGMAC100_INT_XPKT_LOST | + FTGMAC100_INT_AHB_ERR | + FTGMAC100_INT_PHYSTS_CHG | + FTGMAC100_INT_RPKT_BUF | + FTGMAC100_INT_NO_RXBUF); + if (pdev->dev.of_node && + of_get_property(pdev->dev.of_node, "use-ncsi", NULL)) { + if (!IS_ENABLED(CONFIG_NET_NCSI)) { + dev_err(&pdev->dev, "NCSI stack not enabled\n"); + goto err_ncsi_dev; + } - err = mdiobus_register(priv->mii_bus); - if (err) { - dev_err(&pdev->dev, "Cannot register MDIO bus!\n"); - goto err_register_mdiobus; + dev_info(&pdev->dev, "Using NCSI interface\n"); + priv->use_ncsi = true; + priv->int_mask_all &= ~FTGMAC100_INT_PHYSTS_CHG; + priv->ndev = ncsi_register_dev(netdev, ftgmac100_ncsi_handler); + if (!priv->ndev) + goto err_ncsi_dev; + } else { + priv->use_ncsi = false; + err = ftgmac100_setup_mdio(netdev); + if (err) + goto err_setup_mdio; } - err = ftgmac100_mii_probe(priv); - if (err) { - dev_err(&pdev->dev, "MII Probe failed!\n"); - goto err_mii_probe; - } + /* We have to disable on-chip IP checksum functionality + * when NCSI is enabled on the interface. It doesn't work + * in that case. + */ + netdev->features = NETIF_F_IP_CSUM | NETIF_F_GRO; + if (priv->use_ncsi && + of_get_property(pdev->dev.of_node, "no-hw-checksum", NULL)) + netdev->features &= ~NETIF_F_IP_CSUM; + /* register network device */ err = register_netdev(netdev); @@ -1246,21 +1397,12 @@ static int ftgmac100_probe(struct platform_device *pdev) netdev_info(netdev, "irq %d, mapped at %p\n", priv->irq, priv->base); - if (!is_valid_ether_addr(netdev->dev_addr)) { - eth_hw_addr_random(netdev); - netdev_info(netdev, "generated random MAC address %pM\n", - netdev->dev_addr); - } - return 0; +err_ncsi_dev: err_register_netdev: - phy_disconnect(netdev->phydev); -err_mii_probe: - mdiobus_unregister(priv->mii_bus); -err_register_mdiobus: - mdiobus_free(priv->mii_bus); -err_alloc_mdiobus: + ftgmac100_destroy_mdio(netdev); +err_setup_mdio: iounmap(priv->base); err_ioremap: release_resource(priv->res); @@ -1280,10 +1422,7 @@ static int __exit ftgmac100_remove(struct platform_device *pdev) priv = netdev_priv(netdev); unregister_netdev(netdev); - - phy_disconnect(netdev->phydev); - mdiobus_unregister(priv->mii_bus); - mdiobus_free(priv->mii_bus); + ftgmac100_destroy_mdio(netdev); iounmap(priv->base); release_resource(priv->res); @@ -1293,14 +1432,20 @@ static int __exit ftgmac100_remove(struct platform_device *pdev) return 0; } +static const struct of_device_id ftgmac100_of_match[] = { + { .compatible = "faraday,ftgmac100" }, + { } +}; +MODULE_DEVICE_TABLE(of, ftgmac100_of_match); + static struct platform_driver ftgmac100_driver = { - .probe = ftgmac100_probe, - .remove = __exit_p(ftgmac100_remove), - .driver = { - .name = DRV_NAME, + .probe = ftgmac100_probe, + .remove = __exit_p(ftgmac100_remove), + .driver = { + .name = DRV_NAME, + .of_match_table = ftgmac100_of_match, }, }; - module_platform_driver(ftgmac100_driver); MODULE_AUTHOR("Po-Yu Chuang <ratbert@faraday-tech.com>"); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index ecdb685..88f3c85 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -75,6 +75,7 @@ #include <linux/uaccess.h> #include <asm/firmware.h> #include <linux/seq_file.h> +#include <linux/workqueue.h> #include "ibmvnic.h" @@ -89,6 +90,7 @@ MODULE_VERSION(IBMVNIC_DRIVER_VERSION); static int ibmvnic_version = IBMVNIC_INITIAL_VERSION; static int ibmvnic_remove(struct vio_dev *); static void release_sub_crqs(struct ibmvnic_adapter *); +static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *); static int ibmvnic_reset_crq(struct ibmvnic_adapter *); static int ibmvnic_send_crq_init(struct ibmvnic_adapter *); static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *); @@ -469,7 +471,8 @@ static int ibmvnic_open(struct net_device *netdev) crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_UP; ibmvnic_send_crq(adapter, &crq); - netif_start_queue(netdev); + netif_tx_start_all_queues(netdev); + return 0; bounce_map_failed: @@ -519,7 +522,7 @@ static int ibmvnic_close(struct net_device *netdev) for (i = 0; i < adapter->req_rx_queues; i++) napi_disable(&adapter->napi[i]); - netif_stop_queue(netdev); + netif_tx_stop_all_queues(netdev); if (adapter->bounce_buffer) { if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) { @@ -1212,12 +1215,6 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter goto reg_failed; } - scrq->irq = irq_create_mapping(NULL, scrq->hw_irq); - if (scrq->irq == NO_IRQ) { - dev_err(dev, "Error mapping irq\n"); - goto map_irq_failed; - } - scrq->adapter = adapter; scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs); scrq->cur = 0; @@ -1230,12 +1227,6 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter return scrq; -map_irq_failed: - do { - rc = plpar_hcall_norets(H_FREE_SUB_CRQ, - adapter->vdev->unit_address, - scrq->crq_num); - } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); reg_failed: dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE, DMA_BIDIRECTIONAL); @@ -1256,6 +1247,7 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) if (adapter->tx_scrq[i]) { free_irq(adapter->tx_scrq[i]->irq, adapter->tx_scrq[i]); + irq_dispose_mapping(adapter->tx_scrq[i]->irq); release_sub_crq_queue(adapter, adapter->tx_scrq[i]); } @@ -1267,6 +1259,7 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) if (adapter->rx_scrq[i]) { free_irq(adapter->rx_scrq[i]->irq, adapter->rx_scrq[i]); + irq_dispose_mapping(adapter->rx_scrq[i]->irq); release_sub_crq_queue(adapter, adapter->rx_scrq[i]); } @@ -1276,6 +1269,29 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) adapter->requested_caps = 0; } +static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *adapter) +{ + int i; + + if (adapter->tx_scrq) { + for (i = 0; i < adapter->req_tx_queues; i++) + if (adapter->tx_scrq[i]) + release_sub_crq_queue(adapter, + adapter->tx_scrq[i]); + adapter->tx_scrq = NULL; + } + + if (adapter->rx_scrq) { + for (i = 0; i < adapter->req_rx_queues; i++) + if (adapter->rx_scrq[i]) + release_sub_crq_queue(adapter, + adapter->rx_scrq[i]); + adapter->rx_scrq = NULL; + } + + adapter->requested_caps = 0; +} + static int disable_scrq_irq(struct ibmvnic_adapter *adapter, struct ibmvnic_sub_crq_queue *scrq) { @@ -1395,6 +1411,66 @@ static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance) return IRQ_HANDLED; } +static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter) +{ + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_sub_crq_queue *scrq; + int i = 0, j = 0; + int rc = 0; + + for (i = 0; i < adapter->req_tx_queues; i++) { + scrq = adapter->tx_scrq[i]; + scrq->irq = irq_create_mapping(NULL, scrq->hw_irq); + + if (scrq->irq == NO_IRQ) { + rc = -EINVAL; + dev_err(dev, "Error mapping irq\n"); + goto req_tx_irq_failed; + } + + rc = request_irq(scrq->irq, ibmvnic_interrupt_tx, + 0, "ibmvnic_tx", scrq); + + if (rc) { + dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n", + scrq->irq, rc); + irq_dispose_mapping(scrq->irq); + goto req_rx_irq_failed; + } + } + + for (i = 0; i < adapter->req_rx_queues; i++) { + scrq = adapter->rx_scrq[i]; + scrq->irq = irq_create_mapping(NULL, scrq->hw_irq); + if (scrq->irq == NO_IRQ) { + rc = -EINVAL; + dev_err(dev, "Error mapping irq\n"); + goto req_rx_irq_failed; + } + rc = request_irq(scrq->irq, ibmvnic_interrupt_rx, + 0, "ibmvnic_rx", scrq); + if (rc) { + dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n", + scrq->irq, rc); + irq_dispose_mapping(scrq->irq); + goto req_rx_irq_failed; + } + } + return rc; + +req_rx_irq_failed: + for (j = 0; j < i; j++) + free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]); + irq_dispose_mapping(adapter->rx_scrq[j]->irq); + i = adapter->req_tx_queues; +req_tx_irq_failed: + for (j = 0; j < i; j++) + free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); + irq_dispose_mapping(adapter->rx_scrq[j]->irq); + release_sub_crqs_no_irqs(adapter); + return rc; +} + static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) { struct device *dev = &adapter->vdev->dev; @@ -1403,8 +1479,7 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) union ibmvnic_crq crq; int total_queues; int more = 0; - int i, j; - int rc; + int i; if (!retry) { /* Sub-CRQ entries are 32 byte long */ @@ -1483,13 +1558,6 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) for (i = 0; i < adapter->req_tx_queues; i++) { adapter->tx_scrq[i] = allqueues[i]; adapter->tx_scrq[i]->pool_index = i; - rc = request_irq(adapter->tx_scrq[i]->irq, ibmvnic_interrupt_tx, - 0, "ibmvnic_tx", adapter->tx_scrq[i]); - if (rc) { - dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n", - adapter->tx_scrq[i]->irq, rc); - goto req_tx_irq_failed; - } } adapter->rx_scrq = kcalloc(adapter->req_rx_queues, @@ -1500,13 +1568,6 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) for (i = 0; i < adapter->req_rx_queues; i++) { adapter->rx_scrq[i] = allqueues[i + adapter->req_tx_queues]; adapter->rx_scrq[i]->scrq_num = i; - rc = request_irq(adapter->rx_scrq[i]->irq, ibmvnic_interrupt_rx, - 0, "ibmvnic_rx", adapter->rx_scrq[i]); - if (rc) { - dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n", - adapter->rx_scrq[i]->irq, rc); - goto req_rx_irq_failed; - } } memset(&crq, 0, sizeof(crq)); @@ -1559,15 +1620,6 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) return; -req_rx_irq_failed: - for (j = 0; j < i; j++) - free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]); - i = adapter->req_tx_queues; -req_tx_irq_failed: - for (j = 0; j < i; j++) - free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); - kfree(adapter->rx_scrq); - adapter->rx_scrq = NULL; rx_failed: kfree(adapter->tx_scrq); adapter->tx_scrq = NULL; @@ -2348,9 +2400,9 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq, *req_value, (long int)be32_to_cpu(crq->request_capability_rsp. number), name); - release_sub_crqs(adapter); + release_sub_crqs_no_irqs(adapter); *req_value = be32_to_cpu(crq->request_capability_rsp.number); - complete(&adapter->init_done); + init_sub_crqs(adapter, 1); return; default: dev_err(dev, "Error %d in request cap rsp\n", @@ -2659,7 +2711,7 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, out: if (atomic_read(&adapter->running_cap_queries) == 0) - complete(&adapter->init_done); + init_sub_crqs(adapter, 0); /* We're done querying the capabilities, initialize sub-crqs */ } @@ -3202,8 +3254,8 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, dev_info(dev, "Partner initialized\n"); /* Send back a response */ rc = ibmvnic_send_crq_init_complete(adapter); - if (rc == 0) - send_version_xchg(adapter); + if (!rc) + schedule_work(&adapter->vnic_crq_init); else dev_err(dev, "Can't send initrsp rc=%ld\n", rc); break; @@ -3555,8 +3607,63 @@ static const struct file_operations ibmvnic_dump_ops = { .release = single_release, }; +static void handle_crq_init_rsp(struct work_struct *work) +{ + struct ibmvnic_adapter *adapter = container_of(work, + struct ibmvnic_adapter, + vnic_crq_init); + struct device *dev = &adapter->vdev->dev; + struct net_device *netdev = adapter->netdev; + unsigned long timeout = msecs_to_jiffies(30000); + int rc; + + send_version_xchg(adapter); + reinit_completion(&adapter->init_done); + if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { + dev_err(dev, "Passive init timeout\n"); + goto task_failed; + } + + do { + if (adapter->renegotiate) { + adapter->renegotiate = false; + release_sub_crqs_no_irqs(adapter); + send_cap_queries(adapter); + + reinit_completion(&adapter->init_done); + if (!wait_for_completion_timeout(&adapter->init_done, + timeout)) { + dev_err(dev, "Passive init timeout\n"); + goto task_failed; + } + } + } while (adapter->renegotiate); + rc = init_sub_crq_irqs(adapter); + + if (rc) + goto task_failed; + + netdev->real_num_tx_queues = adapter->req_tx_queues; + + rc = register_netdev(netdev); + if (rc) { + dev_err(dev, + "failed to register netdev rc=%d\n", rc); + goto register_failed; + } + dev_info(dev, "ibmvnic registered\n"); + + return; + +register_failed: + release_sub_crqs(adapter); +task_failed: + dev_err(dev, "Passive initialization was not successful\n"); +} + static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) { + unsigned long timeout = msecs_to_jiffies(30000); struct ibmvnic_adapter *adapter; struct net_device *netdev; unsigned char *mac_addr_p; @@ -3593,6 +3700,8 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) netdev->ethtool_ops = &ibmvnic_ethtool_ops; SET_NETDEV_DEV(netdev, &dev->dev); + INIT_WORK(&adapter->vnic_crq_init, handle_crq_init_rsp); + spin_lock_init(&adapter->stats_lock); rc = ibmvnic_init_crq_queue(adapter); @@ -3635,30 +3744,26 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) ibmvnic_send_crq_init(adapter); init_completion(&adapter->init_done); - wait_for_completion(&adapter->init_done); + if (!wait_for_completion_timeout(&adapter->init_done, timeout)) + return 0; do { - adapter->renegotiate = false; - - init_sub_crqs(adapter, 0); - reinit_completion(&adapter->init_done); - wait_for_completion(&adapter->init_done); - if (adapter->renegotiate) { - release_sub_crqs(adapter); + adapter->renegotiate = false; + release_sub_crqs_no_irqs(adapter); send_cap_queries(adapter); reinit_completion(&adapter->init_done); - wait_for_completion(&adapter->init_done); + if (!wait_for_completion_timeout(&adapter->init_done, + timeout)) + return 0; } } while (adapter->renegotiate); - /* if init_sub_crqs is partially successful, retry */ - while (!adapter->tx_scrq || !adapter->rx_scrq) { - init_sub_crqs(adapter, 1); - - reinit_completion(&adapter->init_done); - wait_for_completion(&adapter->init_done); + rc = init_sub_crq_irqs(adapter); + if (rc) { + dev_err(&dev->dev, "failed to initialize sub crq irqs\n"); + goto free_debugfs; } netdev->real_num_tx_queues = adapter->req_tx_queues; @@ -3666,12 +3771,14 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) rc = register_netdev(netdev); if (rc) { dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); - goto free_debugfs; + goto free_sub_crqs; } dev_info(&dev->dev, "ibmvnic registered\n"); return 0; +free_sub_crqs: + release_sub_crqs(adapter); free_debugfs: if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir)) debugfs_remove_recursive(adapter->debugfs_dir); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 0b66a50..e82898f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -1045,4 +1045,6 @@ struct ibmvnic_adapter { u64 opt_rxba_entries_per_subcrq; __be64 tx_rx_desc_req; u8 map_id; + + struct work_struct vnic_crq_init; }; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index e98b86b..c4cf08d 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -362,6 +362,7 @@ enum fm10k_state_t { __FM10K_SERVICE_DISABLE, __FM10K_MBX_LOCK, __FM10K_LINK_DOWN, + __FM10K_UPDATING_STATS, }; static inline void fm10k_mbx_lock(struct fm10k_intfc *interface) @@ -457,6 +458,7 @@ __be16 fm10k_tx_encap_offload(struct sk_buff *skb); netdev_tx_t fm10k_xmit_frame_ring(struct sk_buff *skb, struct fm10k_ring *tx_ring); void fm10k_tx_timeout_reset(struct fm10k_intfc *interface); +u64 fm10k_get_tx_pending(struct fm10k_ring *ring); bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring); void fm10k_alloc_rx_buffers(struct fm10k_ring *rx_ring, u16 cleaned_count); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.c b/drivers/net/ethernet/intel/fm10k/fm10k_common.c index 5bbf19c..d6baaea 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_common.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.c @@ -519,8 +519,12 @@ s32 fm10k_get_host_state_generic(struct fm10k_hw *hw, bool *host_ready) goto out; /* interface cannot receive traffic without logical ports */ - if (mac->dglort_map == FM10K_DGLORTMAP_NONE) + if (mac->dglort_map == FM10K_DGLORTMAP_NONE) { + if (hw->mac.ops.request_lport_map) + ret_val = hw->mac.ops.request_lport_map(hw); + goto out; + } /* if we passed all the tests above then the switch is ready and we no * longer need to check for link diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 9b51954..c04cbe9 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -76,6 +76,8 @@ static const struct fm10k_stats fm10k_gstrings_global_stats[] = { FM10K_STAT("mac_rules_used", hw.swapi.mac.used), FM10K_STAT("mac_rules_avail", hw.swapi.mac.avail), + FM10K_STAT("reset_while_pending", hw.mac.reset_while_pending), + FM10K_STAT("tx_hang_count", tx_timeout_count), }; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index a9ccc1e..e9767b6 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -28,7 +28,7 @@ #include "fm10k.h" -#define DRV_VERSION "0.19.3-k" +#define DRV_VERSION "0.21.2-k" #define DRV_SUMMARY "Intel(R) Ethernet Switch Host Interface Driver" const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; @@ -1128,11 +1128,13 @@ static u64 fm10k_get_tx_completed(struct fm10k_ring *ring) return ring->stats.packets; } -static u64 fm10k_get_tx_pending(struct fm10k_ring *ring) +u64 fm10k_get_tx_pending(struct fm10k_ring *ring) { - /* use SW head and tail until we have real hardware */ - u32 head = ring->next_to_clean; - u32 tail = ring->next_to_use; + struct fm10k_intfc *interface = ring->q_vector->interface; + struct fm10k_hw *hw = &interface->hw; + + u32 head = fm10k_read_reg(hw, FM10K_TDH(ring->reg_idx)); + u32 tail = fm10k_read_reg(hw, FM10K_TDT(ring->reg_idx)); return ((head <= tail) ? tail : tail + ring->count) - head; } @@ -1856,7 +1858,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) if (v_budget < 0) { kfree(interface->msix_entries); interface->msix_entries = NULL; - return -ENOMEM; + return v_budget; } /* record the number of queues available for q_vectors */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h index b7dbc8a..35c1dba 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h @@ -41,6 +41,8 @@ struct fm10k_mbx_info; #define FM10K_MBX_ACK_INTERRUPT 0x00000010 #define FM10K_MBX_INTERRUPT_ENABLE 0x00000020 #define FM10K_MBX_INTERRUPT_DISABLE 0x00000040 +#define FM10K_MBX_GLOBAL_REQ_INTERRUPT 0x00000200 +#define FM10K_MBX_GLOBAL_ACK_INTERRUPT 0x00000400 #define FM10K_MBICR(_n) ((_n) + 0x18840) #define FM10K_GMBX 0x18842 diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index e05aca9..b8245c7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -123,11 +123,24 @@ static void fm10k_service_timer(unsigned long data) static void fm10k_detach_subtask(struct fm10k_intfc *interface) { struct net_device *netdev = interface->netdev; + u32 __iomem *hw_addr; + u32 value; /* do nothing if device is still present or hw_addr is set */ if (netif_device_present(netdev) || interface->hw.hw_addr) return; + /* check the real address space to see if we've recovered */ + hw_addr = READ_ONCE(interface->uc_addr); + value = readl(hw_addr); + if ((~value)) { + interface->hw.hw_addr = interface->uc_addr; + netif_device_attach(netdev); + interface->flags |= FM10K_FLAG_RESET_REQUESTED; + netdev_warn(netdev, "PCIe link restored, device now attached\n"); + return; + } + rtnl_lock(); if (netif_running(netdev)) @@ -136,11 +149,9 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) rtnl_unlock(); } -static void fm10k_reinit(struct fm10k_intfc *interface) +static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) { struct net_device *netdev = interface->netdev; - struct fm10k_hw *hw = &interface->hw; - int err; WARN_ON(in_interrupt()); @@ -165,6 +176,19 @@ static void fm10k_reinit(struct fm10k_intfc *interface) /* delay any future reset requests */ interface->last_reset = jiffies + (10 * HZ); + rtnl_unlock(); +} + +static int fm10k_handle_reset(struct fm10k_intfc *interface) +{ + struct net_device *netdev = interface->netdev; + struct fm10k_hw *hw = &interface->hw; + int err; + + rtnl_lock(); + + pci_set_master(interface->pdev); + /* reset and initialize the hardware so it is in a known state */ err = hw->mac.ops.reset_hw(hw); if (err) { @@ -185,7 +209,7 @@ static void fm10k_reinit(struct fm10k_intfc *interface) goto reinit_err; } - /* reassociate interrupts */ + /* re-associate interrupts */ err = fm10k_mbx_request_irq(interface); if (err) goto err_mbx_irq; @@ -219,7 +243,7 @@ static void fm10k_reinit(struct fm10k_intfc *interface) clear_bit(__FM10K_RESETTING, &interface->state); - return; + return err; err_open: fm10k_mbx_free_irq(interface); err_mbx_irq: @@ -230,6 +254,20 @@ reinit_err: rtnl_unlock(); clear_bit(__FM10K_RESETTING, &interface->state); + + return err; +} + +static void fm10k_reinit(struct fm10k_intfc *interface) +{ + int err; + + fm10k_prepare_for_reset(interface); + + err = fm10k_handle_reset(interface); + if (err) + dev_err(&interface->pdev->dev, + "fm10k_handle_reset failed: %d\n", err); } static void fm10k_reset_subtask(struct fm10k_intfc *interface) @@ -372,12 +410,19 @@ void fm10k_update_stats(struct fm10k_intfc *interface) u64 bytes, pkts; int i; + /* ensure only one thread updates stats at a time */ + if (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state)) + return; + /* do not allow stats update via service task for next second */ interface->next_stats_update = jiffies + HZ; /* gather some stats to the interface struct that are per queue */ for (bytes = 0, pkts = 0, i = 0; i < interface->num_tx_queues; i++) { - struct fm10k_ring *tx_ring = interface->tx_ring[i]; + struct fm10k_ring *tx_ring = READ_ONCE(interface->tx_ring[i]); + + if (!tx_ring) + continue; restart_queue += tx_ring->tx_stats.restart_queue; tx_busy += tx_ring->tx_stats.tx_busy; @@ -396,7 +441,10 @@ void fm10k_update_stats(struct fm10k_intfc *interface) /* gather some stats to the interface struct that are per queue */ for (bytes = 0, pkts = 0, i = 0; i < interface->num_rx_queues; i++) { - struct fm10k_ring *rx_ring = interface->rx_ring[i]; + struct fm10k_ring *rx_ring = READ_ONCE(interface->rx_ring[i]); + + if (!rx_ring) + continue; bytes += rx_ring->stats.bytes; pkts += rx_ring->stats.packets; @@ -443,6 +491,8 @@ void fm10k_update_stats(struct fm10k_intfc *interface) /* Fill out the OS statistics structure */ net_stats->rx_errors = rx_errors; net_stats->rx_dropped = interface->stats.nodesc_drop.count; + + clear_bit(__FM10K_UPDATING_STATS, &interface->state); } /** @@ -1566,6 +1616,9 @@ void fm10k_up(struct fm10k_intfc *interface) /* configure interrupts */ hw->mac.ops.update_int_moderator(hw); + /* enable statistics capture again */ + clear_bit(__FM10K_UPDATING_STATS, &interface->state); + /* clear down bit to indicate we are ready to go */ clear_bit(__FM10K_DOWN, &interface->state); @@ -1598,10 +1651,11 @@ void fm10k_down(struct fm10k_intfc *interface) { struct net_device *netdev = interface->netdev; struct fm10k_hw *hw = &interface->hw; - int err; + int err, i = 0, count = 0; /* signal that we are down to the interrupt handler and service task */ - set_bit(__FM10K_DOWN, &interface->state); + if (test_and_set_bit(__FM10K_DOWN, &interface->state)) + return; /* call carrier off first to avoid false dev_watchdog timeouts */ netif_carrier_off(netdev); @@ -1613,18 +1667,57 @@ void fm10k_down(struct fm10k_intfc *interface) /* reset Rx filters */ fm10k_reset_rx_state(interface); - /* allow 10ms for device to quiesce */ - usleep_range(10000, 20000); - /* disable polling routines */ fm10k_napi_disable_all(interface); /* capture stats one last time before stopping interface */ fm10k_update_stats(interface); + /* prevent updating statistics while we're down */ + while (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state)) + usleep_range(1000, 2000); + + /* skip waiting for TX DMA if we lost PCIe link */ + if (FM10K_REMOVED(hw->hw_addr)) + goto skip_tx_dma_drain; + + /* In some rare circumstances it can take a while for Tx queues to + * quiesce and be fully disabled. Attempt to .stop_hw() first, and + * then if we get ERR_REQUESTS_PENDING, go ahead and wait in a loop + * until the Tx queues have emptied, or until a number of retries. If + * we fail to clear within the retry loop, we will issue a warning + * indicating that Tx DMA is probably hung. Note this means we call + * .stop_hw() twice but this shouldn't cause any problems. + */ + err = hw->mac.ops.stop_hw(hw); + if (err != FM10K_ERR_REQUESTS_PENDING) + goto skip_tx_dma_drain; + +#define TX_DMA_DRAIN_RETRIES 25 + for (count = 0; count < TX_DMA_DRAIN_RETRIES; count++) { + usleep_range(10000, 20000); + + /* start checking at the last ring to have pending Tx */ + for (; i < interface->num_tx_queues; i++) + if (fm10k_get_tx_pending(interface->tx_ring[i])) + break; + + /* if all the queues are drained, we can break now */ + if (i == interface->num_tx_queues) + break; + } + + if (count >= TX_DMA_DRAIN_RETRIES) + dev_err(&interface->pdev->dev, + "Tx queues failed to drain after %d tries. Tx DMA is probably hung.\n", + count); +skip_tx_dma_drain: /* Disable DMA engine for Tx/Rx */ err = hw->mac.ops.stop_hw(hw); - if (err) + if (err == FM10K_ERR_REQUESTS_PENDING) + dev_err(&interface->pdev->dev, + "due to pending requests hw was not shut down gracefully\n"); + else if (err) dev_err(&interface->pdev->dev, "stop_hw failed: %d\n", err); /* free any buffers still on the rings */ @@ -1750,6 +1843,7 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, /* Start off interface as being down */ set_bit(__FM10K_DOWN, &interface->state); + set_bit(__FM10K_UPDATING_STATS, &interface->state); return 0; } @@ -2033,6 +2127,48 @@ static void fm10k_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static void fm10k_prepare_suspend(struct fm10k_intfc *interface) +{ + /* the watchdog task reads from registers, which might appear like + * a surprise remove if the PCIe device is disabled while we're + * stopped. We stop the watchdog task until after we resume software + * activity. + */ + set_bit(__FM10K_SERVICE_DISABLE, &interface->state); + cancel_work_sync(&interface->service_task); + + fm10k_prepare_for_reset(interface); +} + +static int fm10k_handle_resume(struct fm10k_intfc *interface) +{ + struct fm10k_hw *hw = &interface->hw; + int err; + + /* reset statistics starting values */ + hw->mac.ops.rebind_hw_stats(hw, &interface->stats); + + err = fm10k_handle_reset(interface); + if (err) + return err; + + /* assume host is not ready, to prevent race with watchdog in case we + * actually don't have connection to the switch + */ + interface->host_ready = false; + fm10k_watchdog_host_not_ready(interface); + + /* force link to stay down for a second to prevent link flutter */ + interface->link_down_event = jiffies + (HZ); + set_bit(__FM10K_LINK_DOWN, &interface->state); + + /* clear the service task disable bit to allow service task to start */ + clear_bit(__FM10K_SERVICE_DISABLE, &interface->state); + fm10k_service_event_schedule(interface); + + return err; +} + #ifdef CONFIG_PM /** * fm10k_resume - Restore device to pre-sleep state @@ -2069,60 +2205,13 @@ static int fm10k_resume(struct pci_dev *pdev) /* refresh hw_addr in case it was dropped */ hw->hw_addr = interface->uc_addr; - /* reset hardware to known state */ - err = hw->mac.ops.init_hw(&interface->hw); - if (err) { - dev_err(&pdev->dev, "init_hw failed: %d\n", err); - return err; - } - - /* reset statistics starting values */ - hw->mac.ops.rebind_hw_stats(hw, &interface->stats); - - rtnl_lock(); - - err = fm10k_init_queueing_scheme(interface); - if (err) - goto err_queueing_scheme; - - err = fm10k_mbx_request_irq(interface); - if (err) - goto err_mbx_irq; - - err = fm10k_hw_ready(interface); + err = fm10k_handle_resume(interface); if (err) - goto err_open; - - err = netif_running(netdev) ? fm10k_open(netdev) : 0; - if (err) - goto err_open; - - rtnl_unlock(); - - /* assume host is not ready, to prevent race with watchdog in case we - * actually don't have connection to the switch - */ - interface->host_ready = false; - fm10k_watchdog_host_not_ready(interface); - - /* clear the service task disable bit to allow service task to start */ - clear_bit(__FM10K_SERVICE_DISABLE, &interface->state); - fm10k_service_event_schedule(interface); - - /* restore SR-IOV interface */ - fm10k_iov_resume(pdev); + return err; netif_device_attach(netdev); return 0; -err_open: - fm10k_mbx_free_irq(interface); -err_mbx_irq: - fm10k_clear_queueing_scheme(interface); -err_queueing_scheme: - rtnl_unlock(); - - return err; } /** @@ -2142,27 +2231,7 @@ static int fm10k_suspend(struct pci_dev *pdev, netif_device_detach(netdev); - fm10k_iov_suspend(pdev); - - /* the watchdog tasks may read registers, which will appear like a - * surprise-remove event once the PCI device is disabled. This will - * cause us to close the netdevice, so we don't retain the open/closed - * state post-resume. Prevent this by disabling the service task while - * suspended, until we actually resume. - */ - set_bit(__FM10K_SERVICE_DISABLE, &interface->state); - cancel_work_sync(&interface->service_task); - - rtnl_lock(); - - if (netif_running(netdev)) - fm10k_close(netdev); - - fm10k_mbx_free_irq(interface); - - fm10k_clear_queueing_scheme(interface); - - rtnl_unlock(); + fm10k_prepare_suspend(interface); err = pci_save_state(pdev); if (err) @@ -2195,17 +2264,7 @@ static pci_ers_result_t fm10k_io_error_detected(struct pci_dev *pdev, if (state == pci_channel_io_perm_failure) return PCI_ERS_RESULT_DISCONNECT; - rtnl_lock(); - - if (netif_running(netdev)) - fm10k_close(netdev); - - fm10k_mbx_free_irq(interface); - - /* free interrupts */ - fm10k_clear_queueing_scheme(interface); - - rtnl_unlock(); + fm10k_prepare_suspend(interface); /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; @@ -2219,7 +2278,6 @@ static pci_ers_result_t fm10k_io_error_detected(struct pci_dev *pdev, */ static pci_ers_result_t fm10k_io_slot_reset(struct pci_dev *pdev) { - struct fm10k_intfc *interface = pci_get_drvdata(pdev); pci_ers_result_t result; if (pci_enable_device_mem(pdev)) { @@ -2237,12 +2295,6 @@ static pci_ers_result_t fm10k_io_slot_reset(struct pci_dev *pdev) pci_wake_from_d3(pdev, false); - /* refresh hw_addr in case it was dropped */ - interface->hw.hw_addr = interface->uc_addr; - - interface->flags |= FM10K_FLAG_RESET_REQUESTED; - fm10k_service_event_schedule(interface); - result = PCI_ERS_RESULT_RECOVERED; } @@ -2262,50 +2314,54 @@ static void fm10k_io_resume(struct pci_dev *pdev) { struct fm10k_intfc *interface = pci_get_drvdata(pdev); struct net_device *netdev = interface->netdev; - struct fm10k_hw *hw = &interface->hw; - int err = 0; - - /* reset hardware to known state */ - err = hw->mac.ops.init_hw(&interface->hw); - if (err) { - dev_err(&pdev->dev, "init_hw failed: %d\n", err); - return; - } - - /* reset statistics starting values */ - hw->mac.ops.rebind_hw_stats(hw, &interface->stats); - - rtnl_lock(); + int err; - err = fm10k_init_queueing_scheme(interface); - if (err) { - dev_err(&interface->pdev->dev, - "init_queueing_scheme failed: %d\n", err); - goto unlock; - } + err = fm10k_handle_resume(interface); - /* reassociate interrupts */ - fm10k_mbx_request_irq(interface); + if (err) + dev_warn(&pdev->dev, + "fm10k_io_resume failed: %d\n", err); + else + netif_device_attach(netdev); +} - rtnl_lock(); - if (netif_running(netdev)) - err = fm10k_open(netdev); - rtnl_unlock(); +/** + * fm10k_io_reset_notify - called when PCI function is reset + * @pdev: Pointer to PCI device + * + * This callback is called when the PCI function is reset such as from + * /sys/class/net/<enpX>/device/reset or similar. When prepare is true, it + * means we should prepare for a function reset. If prepare is false, it means + * the function reset just occurred. + */ +static void fm10k_io_reset_notify(struct pci_dev *pdev, bool prepare) +{ + struct fm10k_intfc *interface = pci_get_drvdata(pdev); + int err = 0; - /* final check of hardware state before registering the interface */ - err = err ? : fm10k_hw_ready(interface); + if (prepare) { + /* warn incase we have any active VF devices */ + if (pci_num_vf(pdev)) + dev_warn(&pdev->dev, + "PCIe FLR may cause issues for any active VF devices\n"); - if (!err) - netif_device_attach(netdev); + fm10k_prepare_suspend(interface); + } else { + err = fm10k_handle_resume(interface); + } -unlock: - rtnl_unlock(); + if (err) { + dev_warn(&pdev->dev, + "fm10k_io_reset_notify failed: %d\n", err); + netif_device_detach(interface->netdev); + } } static const struct pci_error_handlers fm10k_err_handler = { .error_detected = fm10k_io_error_detected, .slot_reset = fm10k_io_slot_reset, .resume = fm10k_io_resume, + .reset_notify = fm10k_io_reset_notify, }; static struct pci_driver fm10k_driver = { diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index dc75507..682299d 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -51,34 +51,37 @@ static s32 fm10k_reset_hw_pf(struct fm10k_hw *hw) /* shut down all rings */ err = fm10k_disable_queues_generic(hw, FM10K_MAX_QUEUES); - if (err) + if (err == FM10K_ERR_REQUESTS_PENDING) { + hw->mac.reset_while_pending++; + goto force_reset; + } else if (err) { return err; + } /* Verify that DMA is no longer active */ reg = fm10k_read_reg(hw, FM10K_DMA_CTRL); if (reg & (FM10K_DMA_CTRL_TX_ACTIVE | FM10K_DMA_CTRL_RX_ACTIVE)) return FM10K_ERR_DMA_PENDING; - /* verify the switch is ready for reset */ - reg = fm10k_read_reg(hw, FM10K_DMA_CTRL2); - if (!(reg & FM10K_DMA_CTRL2_SWITCH_READY)) - goto out; - +force_reset: /* Inititate data path reset */ - reg |= FM10K_DMA_CTRL_DATAPATH_RESET; + reg = FM10K_DMA_CTRL_DATAPATH_RESET; fm10k_write_reg(hw, FM10K_DMA_CTRL, reg); /* Flush write and allow 100us for reset to complete */ fm10k_write_flush(hw); udelay(FM10K_RESET_TIMEOUT); + /* Reset mailbox global interrupts */ + reg = FM10K_MBX_GLOBAL_REQ_INTERRUPT | FM10K_MBX_GLOBAL_ACK_INTERRUPT; + fm10k_write_reg(hw, FM10K_GMBX, reg); + /* Verify we made it out of reset */ reg = fm10k_read_reg(hw, FM10K_IP); if (!(reg & FM10K_IP_NOTINRESET)) - err = FM10K_ERR_RESET_FAILED; + return FM10K_ERR_RESET_FAILED; -out: - return err; + return 0; } /** @@ -1619,25 +1622,15 @@ static s32 fm10k_request_lport_map_pf(struct fm10k_hw *hw) **/ static s32 fm10k_get_host_state_pf(struct fm10k_hw *hw, bool *switch_ready) { - s32 ret_val = 0; u32 dma_ctrl2; /* verify the switch is ready for interaction */ dma_ctrl2 = fm10k_read_reg(hw, FM10K_DMA_CTRL2); if (!(dma_ctrl2 & FM10K_DMA_CTRL2_SWITCH_READY)) - goto out; + return 0; /* retrieve generic host state info */ - ret_val = fm10k_get_host_state_generic(hw, switch_ready); - if (ret_val) - goto out; - - /* interface cannot receive traffic without logical ports */ - if (hw->mac.dglort_map == FM10K_DGLORTMAP_NONE) - ret_val = fm10k_request_lport_map_pf(hw); - -out: - return ret_val; + return fm10k_get_host_state_generic(hw, switch_ready); } /* This structure defines the attibutes to be parsed below */ @@ -1813,6 +1806,7 @@ static const struct fm10k_mac_ops mac_ops_pf = { .set_dma_mask = fm10k_set_dma_mask_pf, .get_fault = fm10k_get_fault_pf, .get_host_state = fm10k_get_host_state_pf, + .request_lport_map = fm10k_request_lport_map_pf, }; static const struct fm10k_iov_ops iov_ops_pf = { diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h index b8bc061..f4e75c4 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h @@ -526,6 +526,7 @@ struct fm10k_mac_ops { s32 (*stop_hw)(struct fm10k_hw *); s32 (*get_bus_info)(struct fm10k_hw *); s32 (*get_host_state)(struct fm10k_hw *, bool *); + s32 (*request_lport_map)(struct fm10k_hw *); s32 (*update_vlan)(struct fm10k_hw *, u32, u8, bool); s32 (*read_mac_addr)(struct fm10k_hw *); s32 (*update_uc_addr)(struct fm10k_hw *, u16, const u8 *, @@ -562,6 +563,7 @@ struct fm10k_mac_info { bool tx_ready; u32 dglort_map; u8 itr_scale; + u64 reset_while_pending; }; struct fm10k_swapi_table_info { diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c index 3b06685e..337ba65 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c @@ -34,7 +34,7 @@ static s32 fm10k_stop_hw_vf(struct fm10k_hw *hw) /* we need to disable the queues before taking further steps */ err = fm10k_stop_hw_generic(hw); - if (err) + if (err && err != FM10K_ERR_REQUESTS_PENDING) return err; /* If permanent address is set then we need to restore it */ @@ -67,7 +67,7 @@ static s32 fm10k_stop_hw_vf(struct fm10k_hw *hw) fm10k_write_reg(hw, FM10K_TDLEN(i), tdlen); } - return 0; + return err; } /** @@ -83,7 +83,9 @@ static s32 fm10k_reset_hw_vf(struct fm10k_hw *hw) /* shut down queues we own and reset DMA configuration */ err = fm10k_stop_hw_vf(hw); - if (err) + if (err == FM10K_ERR_REQUESTS_PENDING) + hw->mac.reset_while_pending++; + else if (err) return err; /* Inititate VF reset */ @@ -96,9 +98,9 @@ static s32 fm10k_reset_hw_vf(struct fm10k_hw *hw) /* Clear reset bit and verify it was cleared */ fm10k_write_reg(hw, FM10K_VFCTRL, 0); if (fm10k_read_reg(hw, FM10K_VFCTRL) & FM10K_VFCTRL_RST) - err = FM10K_ERR_RESET_FAILED; + return FM10K_ERR_RESET_FAILED; - return err; + return 0; } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index e83fc8a..2a88291 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -448,6 +448,14 @@ struct i40e_pf { u16 phy_led_val; }; +enum i40e_filter_state { + I40E_FILTER_INVALID = 0, /* Invalid state */ + I40E_FILTER_NEW, /* New, not sent to FW yet */ + I40E_FILTER_ACTIVE, /* Added to switch by FW */ + I40E_FILTER_FAILED, /* Rejected by FW */ + I40E_FILTER_REMOVE, /* To be removed */ +/* There is no 'removed' state; the filter struct is freed */ +}; struct i40e_mac_filter { struct list_head list; u8 macaddr[ETH_ALEN]; @@ -456,8 +464,7 @@ struct i40e_mac_filter { u8 counter; /* number of instances of this filter */ bool is_vf; /* filter belongs to a VF */ bool is_netdev; /* filter belongs to a netdev */ - bool changed; /* filter needs to be sync'd to the HW */ - bool is_laa; /* filter is a Locally Administered Address */ + enum i40e_filter_state state; }; struct i40e_veb { @@ -523,6 +530,9 @@ struct i40e_vsi { struct i40e_ring **rx_rings; struct i40e_ring **tx_rings; + u32 active_filters; + u32 promisc_threshold; + u16 work_limit; u16 int_rate_limit; /* value in usecs */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 0e6ac84..e1370c5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -980,13 +980,13 @@ int i40e_unregister_client(struct i40e_client *client) * a close for each of the client instances that were opened. * client_release function is called to handle this. */ + mutex_lock(&i40e_client_mutex); if (!client || i40e_client_release(client)) { ret = -EIO; goto out; } /* TODO: check if device is in reset, or if that matters? */ - mutex_lock(&i40e_client_mutex); if (!i40e_client_is_registered(client)) { pr_info("i40e: Client %s has not been registered\n", client->name); @@ -1005,8 +1005,8 @@ int i40e_unregister_client(struct i40e_client *client) client->name); } - mutex_unlock(&i40e_client_mutex); out: + mutex_unlock(&i40e_client_mutex); return ret; } EXPORT_SYMBOL(i40e_unregister_client); diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index e447dc4..2154a34 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -61,7 +61,6 @@ static i40e_status i40e_set_mac_type(struct i40e_hw *hw) case I40E_DEV_ID_1G_BASE_T_X722: case I40E_DEV_ID_10G_BASE_T_X722: case I40E_DEV_ID_SFP_I_X722: - case I40E_DEV_ID_QSFP_I_X722: hw->mac.type = I40E_MAC_X722; break; default: @@ -297,13 +296,15 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc, void *buffer, u16 buf_len) { struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc; - u16 len = le16_to_cpu(aq_desc->datalen); + u16 len; u8 *buf = (u8 *)buffer; u16 i = 0; if ((!(mask & hw->debug_mask)) || (desc == NULL)) return; + len = le16_to_cpu(aq_desc->datalen); + i40e_debug(hw, mask, "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n", le16_to_cpu(aq_desc->opcode), diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index e6af8c8..05cf9a7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -116,6 +116,14 @@ static ssize_t i40e_dbg_command_read(struct file *filp, char __user *buffer, return len; } +static char *i40e_filter_state_string[] = { + "INVALID", + "NEW", + "ACTIVE", + "FAILED", + "REMOVE", +}; + /** * i40e_dbg_dump_vsi_seid - handles dump vsi seid write into command datum * @pf: the i40e_pf created in command write @@ -160,10 +168,14 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) pf->hw.mac.port_addr); list_for_each_entry(f, &vsi->mac_filter_list, list) { dev_info(&pf->pdev->dev, - " mac_filter_list: %pM vid=%d, is_netdev=%d is_vf=%d counter=%d\n", + " mac_filter_list: %pM vid=%d, is_netdev=%d is_vf=%d counter=%d, state %s\n", f->macaddr, f->vlan, f->is_netdev, f->is_vf, - f->counter); + f->counter, i40e_filter_state_string[f->state]); } + dev_info(&pf->pdev->dev, " active_filters %d, promisc_threshold %d, overflow promisc %s\n", + vsi->active_filters, vsi->promisc_threshold, + (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state) ? + "ON" : "OFF")); nstat = i40e_get_vsi_stats_struct(vsi); dev_info(&pf->pdev->dev, " net_stats: rx_packets = %lu, rx_bytes = %lu, rx_errors = %lu, rx_dropped = %lu\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_devids.h b/drivers/net/ethernet/intel/i40e/i40e_devids.h index d701861..dd4457d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_devids.h +++ b/drivers/net/ethernet/intel/i40e/i40e_devids.h @@ -45,7 +45,6 @@ #define I40E_DEV_ID_1G_BASE_T_X722 0x37D1 #define I40E_DEV_ID_10G_BASE_T_X722 0x37D2 #define I40E_DEV_ID_SFP_I_X722 0x37D3 -#define I40E_DEV_ID_QSFP_I_X722 0x37D4 #define i40e_is_40G_device(d) ((d) == I40E_DEV_ID_QSFP_A || \ (d) == I40E_DEV_ID_QSFP_B || \ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 4962e85..c912e04 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -272,15 +272,16 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, u32 *advertising) { enum i40e_aq_capabilities_phy_type phy_types = pf->hw.phy.phy_types; - + struct i40e_link_status *hw_link_info = &pf->hw.phy.link_info; *supported = 0x0; *advertising = 0x0; if (phy_types & I40E_CAP_PHY_TYPE_SGMII) { *supported |= SUPPORTED_Autoneg | SUPPORTED_1000baseT_Full; - *advertising |= ADVERTISED_Autoneg | - ADVERTISED_1000baseT_Full; + *advertising |= ADVERTISED_Autoneg; + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) + *advertising |= ADVERTISED_1000baseT_Full; if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) { *supported |= SUPPORTED_100baseT_Full; *advertising |= ADVERTISED_100baseT_Full; @@ -299,8 +300,9 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) { *supported |= SUPPORTED_Autoneg | SUPPORTED_10000baseT_Full; - *advertising |= ADVERTISED_Autoneg | - ADVERTISED_10000baseT_Full; + *advertising |= ADVERTISED_Autoneg; + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + *advertising |= ADVERTISED_10000baseT_Full; } if (phy_types & I40E_CAP_PHY_TYPE_XLAUI || phy_types & I40E_CAP_PHY_TYPE_XLPPI || @@ -310,14 +312,16 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4) { *supported |= SUPPORTED_Autoneg | SUPPORTED_40000baseCR4_Full; - *advertising |= ADVERTISED_Autoneg | - ADVERTISED_40000baseCR4_Full; + *advertising |= ADVERTISED_Autoneg; + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_40GB) + *advertising |= ADVERTISED_40000baseCR4_Full; } if (phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) { *supported |= SUPPORTED_Autoneg | SUPPORTED_100baseT_Full; - *advertising |= ADVERTISED_Autoneg | - ADVERTISED_100baseT_Full; + *advertising |= ADVERTISED_Autoneg; + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) + *advertising |= ADVERTISED_100baseT_Full; } if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_T || phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX || @@ -325,8 +329,9 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) { *supported |= SUPPORTED_Autoneg | SUPPORTED_1000baseT_Full; - *advertising |= ADVERTISED_Autoneg | - ADVERTISED_1000baseT_Full; + *advertising |= ADVERTISED_Autoneg; + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) + *advertising |= ADVERTISED_1000baseT_Full; } if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4) *supported |= SUPPORTED_40000baseSR4_Full; @@ -341,26 +346,30 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, if (phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2) { *supported |= SUPPORTED_20000baseKR2_Full | SUPPORTED_Autoneg; - *advertising |= ADVERTISED_20000baseKR2_Full | - ADVERTISED_Autoneg; + *advertising |= ADVERTISED_Autoneg; + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_20GB) + *advertising |= ADVERTISED_20000baseKR2_Full; } if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR) { *supported |= SUPPORTED_10000baseKR_Full | SUPPORTED_Autoneg; - *advertising |= ADVERTISED_10000baseKR_Full | - ADVERTISED_Autoneg; + *advertising |= ADVERTISED_Autoneg; + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + *advertising |= ADVERTISED_10000baseKR_Full; } if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) { *supported |= SUPPORTED_10000baseKX4_Full | SUPPORTED_Autoneg; - *advertising |= ADVERTISED_10000baseKX4_Full | - ADVERTISED_Autoneg; + *advertising |= ADVERTISED_Autoneg; + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + *advertising |= ADVERTISED_10000baseKX4_Full; } if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX) { *supported |= SUPPORTED_1000baseKX_Full | SUPPORTED_Autoneg; - *advertising |= ADVERTISED_1000baseKX_Full | - ADVERTISED_Autoneg; + *advertising |= ADVERTISED_Autoneg; + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) + *advertising |= ADVERTISED_1000baseKX_Full; } } @@ -452,6 +461,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, case I40E_PHY_TYPE_10GBASE_SFPP_CU: case I40E_PHY_TYPE_10GBASE_AOC: ecmd->supported = SUPPORTED_10000baseT_Full; + ecmd->advertising = SUPPORTED_10000baseT_Full; break; case I40E_PHY_TYPE_SGMII: ecmd->supported = SUPPORTED_Autoneg | diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2b11405..339d99b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -41,7 +41,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 6 -#define DRV_VERSION_BUILD 4 +#define DRV_VERSION_BUILD 11 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -86,7 +86,6 @@ static const struct pci_device_id i40e_pci_tbl[] = { {PCI_VDEVICE(INTEL, I40E_DEV_ID_1G_BASE_T_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_I_X722), 0}, - {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_I_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2_A), 0}, /* required last entry */ @@ -1275,8 +1274,9 @@ int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr, (is_vf == f->is_vf) && (is_netdev == f->is_netdev)) { f->counter--; - f->changed = true; changed = 1; + if (f->counter == 0) + f->state = I40E_FILTER_REMOVE; } } if (changed) { @@ -1292,29 +1292,32 @@ int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr, * @vsi: the PF Main VSI - inappropriate for any other VSI * @macaddr: the MAC address * - * Some older firmware configurations set up a default promiscuous VLAN - * filter that needs to be removed. + * Remove whatever filter the firmware set up so the driver can manage + * its own filtering intelligently. **/ -static int i40e_rm_default_mac_filter(struct i40e_vsi *vsi, u8 *macaddr) +static void i40e_rm_default_mac_filter(struct i40e_vsi *vsi, u8 *macaddr) { struct i40e_aqc_remove_macvlan_element_data element; struct i40e_pf *pf = vsi->back; - i40e_status ret; /* Only appropriate for the PF main VSI */ if (vsi->type != I40E_VSI_MAIN) - return -EINVAL; + return; memset(&element, 0, sizeof(element)); ether_addr_copy(element.mac_addr, macaddr); element.vlan_tag = 0; - element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH | - I40E_AQC_MACVLAN_DEL_IGNORE_VLAN; - ret = i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL); - if (ret) - return -ENOENT; + /* Ignore error returns, some firmware does it this way... */ + element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH; + i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL); - return 0; + memset(&element, 0, sizeof(element)); + ether_addr_copy(element.mac_addr, macaddr); + element.vlan_tag = 0; + /* ...and some firmware does it this way. */ + element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH | + I40E_AQC_MACVLAN_ADD_IGNORE_VLAN; + i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL); } /** @@ -1335,10 +1338,18 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, bool is_vf, bool is_netdev) { struct i40e_mac_filter *f; + int changed = false; if (!vsi || !macaddr) return NULL; + /* Do not allow broadcast filter to be added since broadcast filter + * is added as part of add VSI for any newly created VSI except + * FDIR VSI + */ + if (is_broadcast_ether_addr(macaddr)) + return NULL; + f = i40e_find_filter(vsi, macaddr, vlan, is_vf, is_netdev); if (!f) { f = kzalloc(sizeof(*f), GFP_ATOMIC); @@ -1347,8 +1358,15 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, ether_addr_copy(f->macaddr, macaddr); f->vlan = vlan; - f->changed = true; - + /* If we're in overflow promisc mode, set the state directly + * to failed, so we don't bother to try sending the filter + * to the hardware. + */ + if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state)) + f->state = I40E_FILTER_FAILED; + else + f->state = I40E_FILTER_NEW; + changed = true; INIT_LIST_HEAD(&f->list); list_add_tail(&f->list, &vsi->mac_filter_list); } @@ -1368,10 +1386,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, f->counter++; } - /* changed tells sync_filters_subtask to - * push the filter down to the firmware - */ - if (f->changed) { + if (changed) { vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; vsi->back->flags |= I40E_FLAG_FILTER_SYNC; } @@ -1390,6 +1405,9 @@ add_filter_out: * * NOTE: This function is expected to be called with mac_filter_list_lock * being held. + * ANOTHER NOTE: This function MUST be called from within the context of + * the "safe" variants of any list iterators, e.g. list_for_each_entry_safe() + * instead of list_for_each_entry(). **/ void i40e_del_filter(struct i40e_vsi *vsi, u8 *macaddr, s16 vlan, @@ -1429,9 +1447,18 @@ void i40e_del_filter(struct i40e_vsi *vsi, * remove the filter from the firmware's list */ if (f->counter == 0) { - f->changed = true; - vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; - vsi->back->flags |= I40E_FLAG_FILTER_SYNC; + if ((f->state == I40E_FILTER_FAILED) || + (f->state == I40E_FILTER_NEW)) { + /* this one never got added by the FW. Just remove it, + * no need to sync anything. + */ + list_del(&f->list); + kfree(f); + } else { + f->state = I40E_FILTER_REMOVE; + vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; + vsi->back->flags |= I40E_FLAG_FILTER_SYNC; + } } } @@ -1453,7 +1480,6 @@ static int i40e_set_mac(struct net_device *netdev, void *p) struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; struct sockaddr *addr = p; - struct i40e_mac_filter *f; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; @@ -1474,52 +1500,23 @@ static int i40e_set_mac(struct net_device *netdev, void *p) else netdev_info(netdev, "set new mac address %pM\n", addr->sa_data); + spin_lock_bh(&vsi->mac_filter_list_lock); + i40e_del_mac_all_vlan(vsi, netdev->dev_addr, false, true); + i40e_put_mac_in_vlan(vsi, addr->sa_data, false, true); + spin_unlock_bh(&vsi->mac_filter_list_lock); + ether_addr_copy(netdev->dev_addr, addr->sa_data); if (vsi->type == I40E_VSI_MAIN) { i40e_status ret; ret = i40e_aq_mac_address_write(&vsi->back->hw, I40E_AQC_WRITE_TYPE_LAA_WOL, addr->sa_data, NULL); - if (ret) { - netdev_info(netdev, - "Addr change for Main VSI failed: %d\n", - ret); - return -EADDRNOTAVAIL; - } - } - - if (ether_addr_equal(netdev->dev_addr, hw->mac.addr)) { - struct i40e_aqc_remove_macvlan_element_data element; - - memset(&element, 0, sizeof(element)); - ether_addr_copy(element.mac_addr, netdev->dev_addr); - element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH; - i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL); - } else { - spin_lock_bh(&vsi->mac_filter_list_lock); - i40e_del_filter(vsi, netdev->dev_addr, I40E_VLAN_ANY, - false, false); - spin_unlock_bh(&vsi->mac_filter_list_lock); - } - - if (ether_addr_equal(addr->sa_data, hw->mac.addr)) { - struct i40e_aqc_add_macvlan_element_data element; - - memset(&element, 0, sizeof(element)); - ether_addr_copy(element.mac_addr, hw->mac.addr); - element.flags = cpu_to_le16(I40E_AQC_MACVLAN_ADD_PERFECT_MATCH); - i40e_aq_add_macvlan(&pf->hw, vsi->seid, &element, 1, NULL); - } else { - spin_lock_bh(&vsi->mac_filter_list_lock); - f = i40e_add_filter(vsi, addr->sa_data, I40E_VLAN_ANY, - false, false); - if (f) - f->is_laa = true; - spin_unlock_bh(&vsi->mac_filter_list_lock); + if (ret) + netdev_info(netdev, "Ignoring error from firmware on LAA update, status %s, AQ ret %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); } - ether_addr_copy(netdev->dev_addr, addr->sa_data); - /* schedule our worker thread which will take care of * applying the new filter changes */ @@ -1750,28 +1747,6 @@ bottom_of_search_loop: } /** - * i40e_mac_filter_entry_clone - Clones a MAC filter entry - * @src: source MAC filter entry to be clones - * - * Returns the pointer to newly cloned MAC filter entry or NULL - * in case of error - **/ -static struct i40e_mac_filter *i40e_mac_filter_entry_clone( - struct i40e_mac_filter *src) -{ - struct i40e_mac_filter *f; - - f = kzalloc(sizeof(*f), GFP_ATOMIC); - if (!f) - return NULL; - *f = *src; - - INIT_LIST_HEAD(&f->list); - - return f; -} - -/** * i40e_undo_del_filter_entries - Undo the changes made to MAC filter entries * @vsi: pointer to vsi struct * @from: Pointer to list which contains MAC filter entries - changes to @@ -1785,41 +1760,61 @@ static void i40e_undo_del_filter_entries(struct i40e_vsi *vsi, struct i40e_mac_filter *f, *ftmp; list_for_each_entry_safe(f, ftmp, from, list) { - f->changed = true; /* Move the element back into MAC filter list*/ list_move_tail(&f->list, &vsi->mac_filter_list); } } /** - * i40e_undo_add_filter_entries - Undo the changes made to MAC filter entries - * @vsi: pointer to vsi struct + * i40e_update_filter_state - Update filter state based on return data + * from firmware + * @count: Number of filters added + * @add_list: return data from fw + * @head: pointer to first filter in current batch + * @aq_err: status from fw * - * MAC filter entries from list were slated to be added from device. + * MAC filter entries from list were slated to be added to device. Returns + * number of successful filters. Note that 0 does NOT mean success! **/ -static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi) +static int +i40e_update_filter_state(int count, + struct i40e_aqc_add_macvlan_element_data *add_list, + struct i40e_mac_filter *add_head, int aq_err) { - struct i40e_mac_filter *f, *ftmp; + int retval = 0; + int i; - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { - if (!f->changed && f->counter) - f->changed = true; - } -} -/** - * i40e_cleanup_add_list - Deletes the element from add list and release - * memory - * @add_list: Pointer to list which contains MAC filter entries - **/ -static void i40e_cleanup_add_list(struct list_head *add_list) -{ - struct i40e_mac_filter *f, *ftmp; - - list_for_each_entry_safe(f, ftmp, add_list, list) { - list_del(&f->list); - kfree(f); + if (!aq_err) { + retval = count; + /* Everything's good, mark all filters active. */ + for (i = 0; i < count ; i++) { + add_head->state = I40E_FILTER_ACTIVE; + add_head = list_next_entry(add_head, list); + } + } else if (aq_err == I40E_AQ_RC_ENOSPC) { + /* Device ran out of filter space. Check the return value + * for each filter to see which ones are active. + */ + for (i = 0; i < count ; i++) { + if (add_list[i].match_method == + I40E_AQC_MM_ERR_NO_RES) { + add_head->state = I40E_FILTER_FAILED; + } else { + add_head->state = I40E_FILTER_ACTIVE; + retval++; + } + add_head = list_next_entry(add_head, list); + } + } else { + /* Some other horrible thing happened, fail all filters */ + retval = 0; + for (i = 0; i < count ; i++) { + add_head->state = I40E_FILTER_FAILED; + add_head = list_next_entry(add_head, list); + } } + return retval; } /** @@ -1832,22 +1827,22 @@ static void i40e_cleanup_add_list(struct list_head *add_list) **/ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) { - struct list_head tmp_del_list, tmp_add_list; - struct i40e_mac_filter *f, *ftmp, *fclone; + struct i40e_mac_filter *f, *ftmp, *add_head = NULL; + struct list_head tmp_add_list, tmp_del_list; struct i40e_hw *hw = &vsi->back->hw; - bool promisc_forced_on = false; - bool add_happened = false; + bool promisc_changed = false; char vsi_name[16] = "PF"; int filter_list_len = 0; u32 changed_flags = 0; i40e_status aq_ret = 0; - bool err_cond = false; int retval = 0; struct i40e_pf *pf; int num_add = 0; int num_del = 0; int aq_err = 0; u16 cmd_flags; + int list_size; + int fcnt; /* empty array typed pointers, kcalloc later */ struct i40e_aqc_add_macvlan_element_data *add_list; @@ -1862,8 +1857,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) vsi->current_netdev_flags = vsi->netdev->flags; } - INIT_LIST_HEAD(&tmp_del_list); INIT_LIST_HEAD(&tmp_add_list); + INIT_LIST_HEAD(&tmp_del_list); if (vsi->type == I40E_VSI_SRIOV) snprintf(vsi_name, sizeof(vsi_name) - 1, "VF %d", vsi->vf_id); @@ -1874,65 +1869,34 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) vsi->flags &= ~I40E_VSI_FLAG_FILTER_CHANGED; spin_lock_bh(&vsi->mac_filter_list_lock); + /* Create a list of filters to delete. */ list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { - if (!f->changed) - continue; - - if (f->counter != 0) - continue; - f->changed = false; - - /* Move the element into temporary del_list */ - list_move_tail(&f->list, &tmp_del_list); - } - - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { - if (!f->changed) - continue; - - if (f->counter == 0) - continue; - f->changed = false; - - /* Clone MAC filter entry and add into temporary list */ - fclone = i40e_mac_filter_entry_clone(f); - if (!fclone) { - err_cond = true; - break; + if (f->state == I40E_FILTER_REMOVE) { + WARN_ON(f->counter != 0); + /* Move the element into temporary del_list */ + list_move_tail(&f->list, &tmp_del_list); + vsi->active_filters--; + } + if (f->state == I40E_FILTER_NEW) { + WARN_ON(f->counter == 0); + /* Move the element into temporary add_list */ + list_move_tail(&f->list, &tmp_add_list); } - list_add_tail(&fclone->list, &tmp_add_list); - } - - /* if failed to clone MAC filter entry - undo */ - if (err_cond) { - i40e_undo_del_filter_entries(vsi, &tmp_del_list); - i40e_undo_add_filter_entries(vsi); } spin_unlock_bh(&vsi->mac_filter_list_lock); - - if (err_cond) { - i40e_cleanup_add_list(&tmp_add_list); - retval = -ENOMEM; - goto out; - } } /* Now process 'del_list' outside the lock */ if (!list_empty(&tmp_del_list)) { - int del_list_size; - filter_list_len = hw->aq.asq_buf_size / sizeof(struct i40e_aqc_remove_macvlan_element_data); - del_list_size = filter_list_len * + list_size = filter_list_len * sizeof(struct i40e_aqc_remove_macvlan_element_data); - del_list = kzalloc(del_list_size, GFP_ATOMIC); + del_list = kzalloc(list_size, GFP_ATOMIC); if (!del_list) { - i40e_cleanup_add_list(&tmp_add_list); - /* Undo VSI's MAC filter entry element updates */ spin_lock_bh(&vsi->mac_filter_list_lock); i40e_undo_del_filter_entries(vsi, &tmp_del_list); - i40e_undo_add_filter_entries(vsi); spin_unlock_bh(&vsi->mac_filter_list_lock); retval = -ENOMEM; goto out; @@ -1943,9 +1907,13 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) /* add to delete list */ ether_addr_copy(del_list[num_del].mac_addr, f->macaddr); - del_list[num_del].vlan_tag = - cpu_to_le16((u16)(f->vlan == - I40E_VLAN_ANY ? 0 : f->vlan)); + if (f->vlan == I40E_VLAN_ANY) { + del_list[num_del].vlan_tag = 0; + cmd_flags |= I40E_AQC_MACVLAN_ADD_IGNORE_VLAN; + } else { + del_list[num_del].vlan_tag = + cpu_to_le16((u16)(f->vlan)); + } cmd_flags |= I40E_AQC_MACVLAN_DEL_PERFECT_MATCH; del_list[num_del].flags = cmd_flags; @@ -1953,18 +1921,20 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) /* flush a full buffer */ if (num_del == filter_list_len) { - aq_ret = - i40e_aq_remove_macvlan(hw, vsi->seid, - del_list, - num_del, NULL); + aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid, + del_list, + num_del, NULL); aq_err = hw->aq.asq_last_status; num_del = 0; - memset(del_list, 0, del_list_size); + memset(del_list, 0, list_size); - if (aq_ret && aq_err != I40E_AQ_RC_ENOENT) { + /* Explicitly ignore and do not report when + * firmware returns ENOENT. + */ + if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) { retval = -EIO; - dev_err(&pf->pdev->dev, - "ignoring delete macvlan error on %s, err %s, aq_err %s while flushing a full buffer\n", + dev_info(&pf->pdev->dev, + "ignoring delete macvlan error on %s, err %s, aq_err %s\n", vsi_name, i40e_stat_str(hw, aq_ret), i40e_aq_str(hw, aq_err)); @@ -1983,12 +1953,17 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) aq_err = hw->aq.asq_last_status; num_del = 0; - if (aq_ret && aq_err != I40E_AQ_RC_ENOENT) + /* Explicitly ignore and do not report when firmware + * returns ENOENT. + */ + if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) { + retval = -EIO; dev_info(&pf->pdev->dev, "ignoring delete macvlan error on %s, err %s aq_err %s\n", vsi_name, i40e_stat_str(hw, aq_ret), i40e_aq_str(hw, aq_err)); + } } kfree(del_list); @@ -1996,38 +1971,36 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } if (!list_empty(&tmp_add_list)) { - int add_list_size; - - /* do all the adds now */ + /* Do all the adds now. */ filter_list_len = hw->aq.asq_buf_size / - sizeof(struct i40e_aqc_add_macvlan_element_data), - add_list_size = filter_list_len * sizeof(struct i40e_aqc_add_macvlan_element_data); - add_list = kzalloc(add_list_size, GFP_ATOMIC); + list_size = filter_list_len * + sizeof(struct i40e_aqc_add_macvlan_element_data); + add_list = kzalloc(list_size, GFP_ATOMIC); if (!add_list) { - /* Purge element from temporary lists */ - i40e_cleanup_add_list(&tmp_add_list); - - /* Undo add filter entries from VSI MAC filter list */ - spin_lock_bh(&vsi->mac_filter_list_lock); - i40e_undo_add_filter_entries(vsi); - spin_unlock_bh(&vsi->mac_filter_list_lock); retval = -ENOMEM; goto out; } - - list_for_each_entry_safe(f, ftmp, &tmp_add_list, list) { - - add_happened = true; - cmd_flags = 0; - + num_add = 0; + list_for_each_entry(f, &tmp_add_list, list) { + if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, + &vsi->state)) { + f->state = I40E_FILTER_FAILED; + continue; + } /* add to add array */ + if (num_add == 0) + add_head = f; + cmd_flags = 0; ether_addr_copy(add_list[num_add].mac_addr, f->macaddr); - add_list[num_add].vlan_tag = - cpu_to_le16( - (u16)(f->vlan == I40E_VLAN_ANY ? 0 : f->vlan)); + if (f->vlan == I40E_VLAN_ANY) { + add_list[num_add].vlan_tag = 0; + cmd_flags |= I40E_AQC_MACVLAN_ADD_IGNORE_VLAN; + } else { + add_list[num_add].vlan_tag = + cpu_to_le16((u16)(f->vlan)); + } add_list[num_add].queue_number = 0; - cmd_flags |= I40E_AQC_MACVLAN_ADD_PERFECT_MATCH; add_list[num_add].flags = cpu_to_le16(cmd_flags); num_add++; @@ -2038,44 +2011,77 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) add_list, num_add, NULL); aq_err = hw->aq.asq_last_status; + fcnt = i40e_update_filter_state(num_add, + add_list, + add_head, + aq_ret); + vsi->active_filters += fcnt; + + if (fcnt != num_add) { + promisc_changed = true; + set_bit(__I40E_FILTER_OVERFLOW_PROMISC, + &vsi->state); + vsi->promisc_threshold = + (vsi->active_filters * 3) / 4; + dev_warn(&pf->pdev->dev, + "Error %s adding RX filters on %s, promiscuous mode forced on\n", + i40e_aq_str(hw, aq_err), + vsi_name); + } + memset(add_list, 0, list_size); num_add = 0; - - if (aq_ret) - break; - memset(add_list, 0, add_list_size); } - /* Entries from tmp_add_list were cloned from MAC - * filter list, hence clean those cloned entries - */ - list_del(&f->list); - kfree(f); } - if (num_add) { aq_ret = i40e_aq_add_macvlan(hw, vsi->seid, add_list, num_add, NULL); aq_err = hw->aq.asq_last_status; - num_add = 0; + fcnt = i40e_update_filter_state(num_add, add_list, + add_head, aq_ret); + vsi->active_filters += fcnt; + if (fcnt != num_add) { + promisc_changed = true; + set_bit(__I40E_FILTER_OVERFLOW_PROMISC, + &vsi->state); + vsi->promisc_threshold = + (vsi->active_filters * 3) / 4; + dev_warn(&pf->pdev->dev, + "Error %s adding RX filters on %s, promiscuous mode forced on\n", + i40e_aq_str(hw, aq_err), vsi_name); + } + } + /* Now move all of the filters from the temp add list back to + * the VSI's list. + */ + spin_lock_bh(&vsi->mac_filter_list_lock); + list_for_each_entry_safe(f, ftmp, &tmp_add_list, list) { + list_move_tail(&f->list, &vsi->mac_filter_list); } + spin_unlock_bh(&vsi->mac_filter_list_lock); kfree(add_list); add_list = NULL; + } - if (add_happened && aq_ret && aq_err != I40E_AQ_RC_EINVAL) { - retval = i40e_aq_rc_to_posix(aq_ret, aq_err); + /* Check to see if we can drop out of overflow promiscuous mode. */ + if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state) && + (vsi->active_filters < vsi->promisc_threshold)) { + int failed_count = 0; + /* See if we have any failed filters. We can't drop out of + * promiscuous until these have all been deleted. + */ + spin_lock_bh(&vsi->mac_filter_list_lock); + list_for_each_entry(f, &vsi->mac_filter_list, list) { + if (f->state == I40E_FILTER_FAILED) + failed_count++; + } + spin_unlock_bh(&vsi->mac_filter_list_lock); + if (!failed_count) { dev_info(&pf->pdev->dev, - "add filter failed on %s, err %s aq_err %s\n", - vsi_name, - i40e_stat_str(hw, aq_ret), - i40e_aq_str(hw, aq_err)); - if ((hw->aq.asq_last_status == I40E_AQ_RC_ENOSPC) && - !test_bit(__I40E_FILTER_OVERFLOW_PROMISC, - &vsi->state)) { - promisc_forced_on = true; - set_bit(__I40E_FILTER_OVERFLOW_PROMISC, - &vsi->state); - dev_info(&pf->pdev->dev, "promiscuous mode forced on %s\n", - vsi_name); - } + "filter logjam cleared on %s, leaving overflow promiscuous mode\n", + vsi_name); + clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state); + promisc_changed = true; + vsi->promisc_threshold = 0; } } @@ -2104,7 +2110,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) i40e_aq_str(hw, hw->aq.asq_last_status)); } } - if ((changed_flags & IFF_PROMISC) || promisc_forced_on) { + if ((changed_flags & IFF_PROMISC) || + (promisc_changed && + test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state))) { bool cur_promisc; cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) || @@ -2353,7 +2361,7 @@ static void i40e_vlan_rx_register(struct net_device *netdev, u32 features) **/ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) { - struct i40e_mac_filter *f, *add_f; + struct i40e_mac_filter *f, *ftmp, *add_f; bool is_netdev, is_vf; is_vf = (vsi->type == I40E_VSI_SRIOV); @@ -2374,7 +2382,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) } } - list_for_each_entry(f, &vsi->mac_filter_list, list) { + list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { add_f = i40e_add_filter(vsi, f->macaddr, vid, is_vf, is_netdev); if (!add_f) { dev_info(&vsi->back->pdev->dev, @@ -2388,7 +2396,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) /* Now if we add a vlan tag, make sure to check if it is the first * tag (i.e. a "tag" -1 does exist) and if so replace the -1 "tag" * with 0, so we now accept untagged and specified tagged traffic - * (and not any taged and untagged) + * (and not all tags along with untagged) */ if (vid > 0) { if (is_netdev && i40e_find_filter(vsi, vsi->netdev->dev_addr, @@ -2410,7 +2418,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) /* Do not assume that I40E_VLAN_ANY should be reset to VLAN 0 */ if (vid > 0 && !vsi->info.pvid) { - list_for_each_entry(f, &vsi->mac_filter_list, list) { + list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { if (!i40e_find_filter(vsi, f->macaddr, I40E_VLAN_ANY, is_vf, is_netdev)) continue; @@ -2447,7 +2455,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid) { struct net_device *netdev = vsi->netdev; - struct i40e_mac_filter *f, *add_f; + struct i40e_mac_filter *f, *ftmp, *add_f; bool is_vf, is_netdev; int filter_count = 0; @@ -2460,7 +2468,7 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid) if (is_netdev) i40e_del_filter(vsi, netdev->dev_addr, vid, is_vf, is_netdev); - list_for_each_entry(f, &vsi->mac_filter_list, list) + list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) i40e_del_filter(vsi, f->macaddr, vid, is_vf, is_netdev); /* go through all the filters for this VSI and if there is only @@ -2493,7 +2501,7 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid) } if (!filter_count) { - list_for_each_entry(f, &vsi->mac_filter_list, list) { + list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { i40e_del_filter(vsi, f->macaddr, 0, is_vf, is_netdev); add_f = i40e_add_filter(vsi, f->macaddr, I40E_VLAN_ANY, is_vf, is_netdev); @@ -2538,8 +2546,6 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev, if (vid > 4095) return -EINVAL; - netdev_info(netdev, "adding %pM vid=%d\n", netdev->dev_addr, vid); - /* If the network stack called us with vid = 0 then * it is asking to receive priority tagged packets with * vlan id 0. Our HW receives them by default when configured @@ -2573,8 +2579,6 @@ static int i40e_vlan_rx_kill_vid(struct net_device *netdev, struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; - netdev_info(netdev, "removing %pM vid=%d\n", netdev->dev_addr, vid); - /* return code is ignored as there is nothing a user * can do about failure to remove and a log message was * already printed from the other function @@ -2587,6 +2591,44 @@ static int i40e_vlan_rx_kill_vid(struct net_device *netdev, } /** + * i40e_macaddr_init - explicitly write the mac address filters + * + * @vsi: pointer to the vsi + * @macaddr: the MAC address + * + * This is needed when the macaddr has been obtained by other + * means than the default, e.g., from Open Firmware or IDPROM. + * Returns 0 on success, negative on failure + **/ +static int i40e_macaddr_init(struct i40e_vsi *vsi, u8 *macaddr) +{ + int ret; + struct i40e_aqc_add_macvlan_element_data element; + + ret = i40e_aq_mac_address_write(&vsi->back->hw, + I40E_AQC_WRITE_TYPE_LAA_WOL, + macaddr, NULL); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Addr change for VSI failed: %d\n", ret); + return -EADDRNOTAVAIL; + } + + memset(&element, 0, sizeof(element)); + ether_addr_copy(element.mac_addr, macaddr); + element.flags = cpu_to_le16(I40E_AQC_MACVLAN_ADD_PERFECT_MATCH); + ret = i40e_aq_add_macvlan(&vsi->back->hw, vsi->seid, &element, 1, NULL); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "add filter failed err %s aq_err %s\n", + i40e_stat_str(&vsi->back->hw, ret), + i40e_aq_str(&vsi->back->hw, + vsi->back->hw.aq.asq_last_status)); + } + return ret; +} + +/** * i40e_restore_vlan - Reinstate vlans when vsi/netdev comes back up * @vsi: the vsi being brought back up **/ @@ -3032,8 +3074,19 @@ static void i40e_vsi_config_dcb_rings(struct i40e_vsi *vsi) **/ static void i40e_set_vsi_rx_mode(struct i40e_vsi *vsi) { + struct i40e_pf *pf = vsi->back; + int err; + if (vsi->netdev) i40e_set_rx_mode(vsi->netdev); + + if (!!(pf->flags & I40E_FLAG_PF_MAC)) { + err = i40e_macaddr_init(vsi, pf->hw.mac.addr); + if (err) { + dev_warn(&pf->pdev->dev, + "could not set up macaddr; err %d\n", err); + } + } } /** @@ -7740,10 +7793,11 @@ static int i40e_init_msix(struct i40e_pf *pf) * i40e_vsi_alloc_q_vector - Allocate memory for a single interrupt vector * @vsi: the VSI being configured * @v_idx: index of the vector in the vsi struct + * @cpu: cpu to be used on affinity_mask * * We allocate one q_vector. If allocation fails we return -ENOMEM. **/ -static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx) +static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu) { struct i40e_q_vector *q_vector; @@ -7754,7 +7808,8 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx) q_vector->vsi = vsi; q_vector->v_idx = v_idx; - cpumask_set_cpu(v_idx, &q_vector->affinity_mask); + cpumask_set_cpu(cpu, &q_vector->affinity_mask); + if (vsi->netdev) netif_napi_add(vsi->netdev, &q_vector->napi, i40e_napi_poll, NAPI_POLL_WEIGHT); @@ -7778,8 +7833,7 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx) static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; - int v_idx, num_q_vectors; - int err; + int err, v_idx, num_q_vectors, current_cpu; /* if not MSIX, give the one vector only to the LAN VSI */ if (pf->flags & I40E_FLAG_MSIX_ENABLED) @@ -7789,10 +7843,15 @@ static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi) else return -EINVAL; + current_cpu = cpumask_first(cpu_online_mask); + for (v_idx = 0; v_idx < num_q_vectors; v_idx++) { - err = i40e_vsi_alloc_q_vector(vsi, v_idx); + err = i40e_vsi_alloc_q_vector(vsi, v_idx, current_cpu); if (err) goto err_out; + current_cpu = cpumask_next(current_cpu, cpu_online_mask); + if (unlikely(current_cpu >= nr_cpu_ids)) + current_cpu = cpumask_first(cpu_online_mask); } return 0; @@ -7919,7 +7978,6 @@ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, u8 *rss_lut; int ret, i; - memset(&rss_key, 0, sizeof(rss_key)); memcpy(&rss_key, seed, sizeof(rss_key)); rss_lut = kzalloc(pf->rss_table_size, GFP_KERNEL); @@ -9006,7 +9064,6 @@ static const struct net_device_ops i40e_netdev_ops = { **/ static int i40e_config_netdev(struct i40e_vsi *vsi) { - u8 brdcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_netdev_priv *np; @@ -9070,18 +9127,10 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) * default a MAC-VLAN filter that accepts any tagged packet * which must be replaced by a normal filter. */ - if (!i40e_rm_default_mac_filter(vsi, mac_addr)) { - spin_lock_bh(&vsi->mac_filter_list_lock); - i40e_add_filter(vsi, mac_addr, - I40E_VLAN_ANY, false, true); - spin_unlock_bh(&vsi->mac_filter_list_lock); - } - } else if ((pf->hw.aq.api_maj_ver > 1) || - ((pf->hw.aq.api_maj_ver == 1) && - (pf->hw.aq.api_min_ver > 4))) { - /* Supported in FW API version higher than 1.4 */ - pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE; - pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; + i40e_rm_default_mac_filter(vsi, mac_addr); + spin_lock_bh(&vsi->mac_filter_list_lock); + i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, true); + spin_unlock_bh(&vsi->mac_filter_list_lock); } else { /* relate the VSI_VMDQ name to the VSI_MAIN name */ snprintf(netdev->name, IFNAMSIZ, "%sv%%d", @@ -9093,10 +9142,6 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) spin_unlock_bh(&vsi->mac_filter_list_lock); } - spin_lock_bh(&vsi->mac_filter_list_lock); - i40e_add_filter(vsi, brdcast, I40E_VLAN_ANY, false, false); - spin_unlock_bh(&vsi->mac_filter_list_lock); - ether_addr_copy(netdev->dev_addr, mac_addr); ether_addr_copy(netdev->perm_addr, mac_addr); @@ -9174,8 +9219,7 @@ int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi) static int i40e_add_vsi(struct i40e_vsi *vsi) { int ret = -ENODEV; - u8 laa_macaddr[ETH_ALEN]; - bool found_laa_mac_filter = false; + i40e_status aq_ret = 0; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_vsi_context ctxt; @@ -9363,42 +9407,29 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) vsi->seid = ctxt.seid; vsi->id = ctxt.vsi_number; } + /* Except FDIR VSI, for all othet VSI set the broadcast filter */ + if (vsi->type != I40E_VSI_FDIR) { + aq_ret = i40e_aq_set_vsi_broadcast(hw, vsi->seid, true, NULL); + if (aq_ret) { + ret = i40e_aq_rc_to_posix(aq_ret, + hw->aq.asq_last_status); + dev_info(&pf->pdev->dev, + "set brdcast promisc failed, err %s, aq_err %s\n", + i40e_stat_str(hw, aq_ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + } + } + vsi->active_filters = 0; + clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state); spin_lock_bh(&vsi->mac_filter_list_lock); /* If macvlan filters already exist, force them to get loaded */ list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { - f->changed = true; + f->state = I40E_FILTER_NEW; f_count++; - - /* Expected to have only one MAC filter entry for LAA in list */ - if (f->is_laa && vsi->type == I40E_VSI_MAIN) { - ether_addr_copy(laa_macaddr, f->macaddr); - found_laa_mac_filter = true; - } } spin_unlock_bh(&vsi->mac_filter_list_lock); - if (found_laa_mac_filter) { - struct i40e_aqc_remove_macvlan_element_data element; - - memset(&element, 0, sizeof(element)); - ether_addr_copy(element.mac_addr, laa_macaddr); - element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH; - ret = i40e_aq_remove_macvlan(hw, vsi->seid, - &element, 1, NULL); - if (ret) { - /* some older FW has a different default */ - element.flags |= - I40E_AQC_MACVLAN_DEL_IGNORE_VLAN; - i40e_aq_remove_macvlan(hw, vsi->seid, - &element, 1, NULL); - } - - i40e_aq_mac_address_write(hw, - I40E_AQC_WRITE_TYPE_LAA_WOL, - laa_macaddr, NULL); - } - if (f_count) { vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; pf->flags |= I40E_FLAG_FILTER_SYNC; @@ -9609,6 +9640,8 @@ static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi) pf->vsi[pf->lan_vsi]->tc_config.enabled_tc = 0; pf->vsi[pf->lan_vsi]->seid = pf->main_vsi_seid; i40e_vsi_config_tc(pf->vsi[pf->lan_vsi], enabled_tc); + if (vsi->type == I40E_VSI_MAIN) + i40e_rm_default_mac_filter(vsi, pf->hw.mac.perm_addr); /* assign it some queues */ ret = i40e_alloc_rings(vsi); @@ -9634,44 +9667,6 @@ err_vsi: } /** - * i40e_macaddr_init - explicitly write the mac address filters. - * - * @vsi: pointer to the vsi. - * @macaddr: the MAC address - * - * This is needed when the macaddr has been obtained by other - * means than the default, e.g., from Open Firmware or IDPROM. - * Returns 0 on success, negative on failure - **/ -static int i40e_macaddr_init(struct i40e_vsi *vsi, u8 *macaddr) -{ - int ret; - struct i40e_aqc_add_macvlan_element_data element; - - ret = i40e_aq_mac_address_write(&vsi->back->hw, - I40E_AQC_WRITE_TYPE_LAA_WOL, - macaddr, NULL); - if (ret) { - dev_info(&vsi->back->pdev->dev, - "Addr change for VSI failed: %d\n", ret); - return -EADDRNOTAVAIL; - } - - memset(&element, 0, sizeof(element)); - ether_addr_copy(element.mac_addr, macaddr); - element.flags = cpu_to_le16(I40E_AQC_MACVLAN_ADD_PERFECT_MATCH); - ret = i40e_aq_add_macvlan(&vsi->back->hw, vsi->seid, &element, 1, NULL); - if (ret) { - dev_info(&vsi->back->pdev->dev, - "add filter failed err %s aq_err %s\n", - i40e_stat_str(&vsi->back->hw, ret), - i40e_aq_str(&vsi->back->hw, - vsi->back->hw.aq.asq_last_status)); - } - return ret; -} - -/** * i40e_vsi_setup - Set up a VSI by a given type * @pf: board private structure * @type: VSI type diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 55f151f..df7ecc9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -740,14 +740,12 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, tx_ring->q_vector->tx.total_packets += total_packets; if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { - unsigned int j = 0; - /* check to see if there are < 4 descriptors * waiting to be written back, then kick the hardware to force * them to be written back in case we stay in NAPI. * In this mode on X722 we do not enable Interrupt. */ - j = i40e_get_tx_pending(tx_ring, false); + unsigned int j = i40e_get_tx_pending(tx_ring, false); if (budget && ((j / (WB_STRIDE + 1)) == 0) && (j != 0) && @@ -1280,8 +1278,8 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, union i40e_rx_desc *rx_desc) { struct i40e_rx_ptype_decoded decoded; - bool ipv4, ipv6, tunnel = false; u32 rx_error, rx_status; + bool ipv4, ipv6; u8 ptype; u64 qword; @@ -1336,19 +1334,23 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT)) return; - /* The hardware supported by this driver does not validate outer - * checksums for tunneled VXLAN or GENEVE frames. I don't agree - * with it but the specification states that you "MAY validate", it - * doesn't make it a hard requirement so if we have validated the - * inner checksum report CHECKSUM_UNNECESSARY. + /* If there is an outer header present that might contain a checksum + * we need to bump the checksum level by 1 to reflect the fact that + * we are indicating we validated the inner checksum. */ - if (decoded.inner_prot & (I40E_RX_PTYPE_INNER_PROT_TCP | - I40E_RX_PTYPE_INNER_PROT_UDP | - I40E_RX_PTYPE_INNER_PROT_SCTP)) - tunnel = true; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = tunnel ? 1 : 0; + if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT) + skb->csum_level = 1; + + /* Only report checksum unnecessary for TCP, UDP, or SCTP */ + switch (decoded.inner_prot) { + case I40E_RX_PTYPE_INNER_PROT_TCP: + case I40E_RX_PTYPE_INNER_PROT_UDP: + case I40E_RX_PTYPE_INNER_PROT_SCTP: + skb->ip_summed = CHECKSUM_UNNECESSARY; + /* fall though */ + default: + break; + } return; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 8f64204..4db0c03 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -59,7 +59,6 @@ i40e_status i40e_set_mac_type(struct i40e_hw *hw) case I40E_DEV_ID_1G_BASE_T_X722: case I40E_DEV_ID_10G_BASE_T_X722: case I40E_DEV_ID_SFP_I_X722: - case I40E_DEV_ID_QSFP_I_X722: hw->mac.type = I40E_MAC_X722; break; case I40E_DEV_ID_X722_VF: diff --git a/drivers/net/ethernet/intel/i40evf/i40e_devids.h b/drivers/net/ethernet/intel/i40evf/i40e_devids.h index d34972b..7023570 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_devids.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_devids.h @@ -45,7 +45,6 @@ #define I40E_DEV_ID_1G_BASE_T_X722 0x37D1 #define I40E_DEV_ID_10G_BASE_T_X722 0x37D2 #define I40E_DEV_ID_SFP_I_X722 0x37D3 -#define I40E_DEV_ID_QSFP_I_X722 0x37D4 #define I40E_DEV_ID_X722_VF 0x37CD #define I40E_DEV_ID_X722_VF_HV 0x37D9 diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index be99189..a579193 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -259,13 +259,12 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, tx_ring->q_vector->tx.total_packets += total_packets; if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { - unsigned int j = 0; /* check to see if there are < 4 descriptors * waiting to be written back, then kick the hardware to force * them to be written back in case we stay in NAPI. * In this mode on X722 we do not enable Interrupt. */ - j = i40evf_get_tx_pending(tx_ring, false); + unsigned int j = i40evf_get_tx_pending(tx_ring, false); if (budget && ((j / (WB_STRIDE + 1)) == 0) && (j > 0) && @@ -752,8 +751,8 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, union i40e_rx_desc *rx_desc) { struct i40e_rx_ptype_decoded decoded; - bool ipv4, ipv6, tunnel = false; u32 rx_error, rx_status; + bool ipv4, ipv6; u8 ptype; u64 qword; @@ -808,19 +807,23 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT)) return; - /* The hardware supported by this driver does not validate outer - * checksums for tunneled VXLAN or GENEVE frames. I don't agree - * with it but the specification states that you "MAY validate", it - * doesn't make it a hard requirement so if we have validated the - * inner checksum report CHECKSUM_UNNECESSARY. + /* If there is an outer header present that might contain a checksum + * we need to bump the checksum level by 1 to reflect the fact that + * we are indicating we validated the inner checksum. */ - if (decoded.inner_prot & (I40E_RX_PTYPE_INNER_PROT_TCP | - I40E_RX_PTYPE_INNER_PROT_UDP | - I40E_RX_PTYPE_INNER_PROT_SCTP)) - tunnel = true; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = tunnel ? 1 : 0; + if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT) + skb->csum_level = 1; + + /* Only report checksum unnecessary for TCP, UDP, or SCTP */ + switch (decoded.inner_prot) { + case I40E_RX_PTYPE_INNER_PROT_TCP: + case I40E_RX_PTYPE_INNER_PROT_UDP: + case I40E_RX_PTYPE_INNER_PROT_SCTP: + skb->ip_summed = CHECKSUM_UNNECESSARY; + /* fall though */ + default: + break; + } return; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index eac057b..600fb9c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -38,7 +38,7 @@ static const char i40evf_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 6 -#define DRV_VERSION_BUILD 4 +#define DRV_VERSION_BUILD 11 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) \ @@ -57,7 +57,9 @@ static const char i40evf_copyright[] = */ static const struct pci_device_id i40evf_pci_tbl[] = { {PCI_VDEVICE(INTEL, I40E_DEV_ID_VF), 0}, + {PCI_VDEVICE(INTEL, I40E_DEV_ID_VF_HV), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_X722_VF), 0}, + {PCI_VDEVICE(INTEL, I40E_DEV_ID_X722_VF_HV), 0}, /* required last entry */ {0, } }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 918b94b..fdbea54 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2887,7 +2887,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) if (!test_bit(__IXGBE_DOWN, &adapter->state)) ixgbe_irq_enable_queues(adapter, BIT_ULL(q_vector->v_idx)); - return 0; + return min(work_done, budget - 1); } /** diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index d5d263b..f92018b 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -244,7 +244,7 @@ /* Various constants */ /* Coalescing */ -#define MVNETA_TXDONE_COAL_PKTS 1 +#define MVNETA_TXDONE_COAL_PKTS 0 /* interrupt per packet */ #define MVNETA_RX_COAL_PKTS 32 #define MVNETA_RX_COAL_USEC 100 diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 51a2e82..bdda17d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1042,6 +1042,8 @@ static int mlx4_en_set_ringparam(struct net_device *dev, { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_port_profile new_prof; + struct mlx4_en_priv *tmp; u32 rx_size, tx_size; int port_up = 0; int err = 0; @@ -1061,22 +1063,25 @@ static int mlx4_en_set_ringparam(struct net_device *dev, tx_size == priv->tx_ring[0]->size) return 0; + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + mutex_lock(&mdev->state_lock); + memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); + new_prof.tx_ring_size = tx_size; + new_prof.rx_ring_size = rx_size; + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + if (err) + goto out; + if (priv->port_up) { port_up = 1; mlx4_en_stop_port(dev, 1); } - mlx4_en_free_resources(priv); - - priv->prof->tx_ring_size = tx_size; - priv->prof->rx_ring_size = rx_size; + mlx4_en_safe_replace_resources(priv, tmp); - err = mlx4_en_alloc_resources(priv); - if (err) { - en_err(priv, "Failed reallocating port resources\n"); - goto out; - } if (port_up) { err = mlx4_en_start_port(dev); if (err) @@ -1084,8 +1089,8 @@ static int mlx4_en_set_ringparam(struct net_device *dev, } err = mlx4_en_moderation_update(priv); - out: + kfree(tmp); mutex_unlock(&mdev->state_lock); return err; } @@ -1713,6 +1718,8 @@ static int mlx4_en_set_channels(struct net_device *dev, { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_port_profile new_prof; + struct mlx4_en_priv *tmp; int port_up = 0; int err = 0; @@ -1722,25 +1729,35 @@ static int mlx4_en_set_channels(struct net_device *dev, !channel->tx_count || !channel->rx_count) return -EINVAL; - mutex_lock(&mdev->state_lock); - if (priv->port_up) { - port_up = 1; - mlx4_en_stop_port(dev, 1); + if (channel->tx_count * MLX4_EN_NUM_UP <= priv->xdp_ring_num) { + en_err(priv, "Minimum %d tx channels required with XDP on\n", + priv->xdp_ring_num / MLX4_EN_NUM_UP + 1); + return -EINVAL; } - mlx4_en_free_resources(priv); + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; - priv->num_tx_rings_p_up = channel->tx_count; - priv->tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP; - priv->rx_ring_num = channel->rx_count; + mutex_lock(&mdev->state_lock); + memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); + new_prof.num_tx_rings_p_up = channel->tx_count; + new_prof.tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP; + new_prof.rx_ring_num = channel->rx_count; - err = mlx4_en_alloc_resources(priv); - if (err) { - en_err(priv, "Failed reallocating port resources\n"); + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + if (err) goto out; + + if (priv->port_up) { + port_up = 1; + mlx4_en_stop_port(dev, 1); } - netif_set_real_num_tx_queues(dev, priv->tx_ring_num); + mlx4_en_safe_replace_resources(priv, tmp); + + netif_set_real_num_tx_queues(dev, priv->tx_ring_num - + priv->xdp_ring_num); netif_set_real_num_rx_queues(dev, priv->rx_ring_num); if (dev->num_tc) @@ -1756,8 +1773,8 @@ static int mlx4_en_set_channels(struct net_device *dev, } err = mlx4_en_moderation_update(priv); - out: + kfree(tmp); mutex_unlock(&mdev->state_lock); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 6083775..4198e9b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -31,6 +31,7 @@ * */ +#include <linux/bpf.h> #include <linux/etherdevice.h> #include <linux/tcp.h> #include <linux/if_vlan.h> @@ -1521,6 +1522,24 @@ static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx) free_cpumask_var(priv->rx_ring[ring_idx]->affinity_mask); } +static void mlx4_en_init_recycle_ring(struct mlx4_en_priv *priv, + int tx_ring_idx) +{ + struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[tx_ring_idx]; + int rr_index; + + rr_index = (priv->xdp_ring_num - priv->tx_ring_num) + tx_ring_idx; + if (rr_index >= 0) { + tx_ring->free_tx_desc = mlx4_en_recycle_tx_desc; + tx_ring->recycle_ring = priv->rx_ring[rr_index]; + en_dbg(DRV, priv, + "Set tx_ring[%d]->recycle_ring = rx_ring[%d]\n", + tx_ring_idx, rr_index); + } else { + tx_ring->recycle_ring = NULL; + } +} + int mlx4_en_start_port(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -1643,6 +1662,8 @@ int mlx4_en_start_port(struct net_device *dev) } tx_ring->tx_queue = netdev_get_tx_queue(dev, i); + mlx4_en_init_recycle_ring(priv, i); + /* Arm CQ for TX completions */ mlx4_en_arm_cq(priv, cq); @@ -1964,7 +1985,7 @@ static int mlx4_en_close(struct net_device *dev) return 0; } -void mlx4_en_free_resources(struct mlx4_en_priv *priv) +static void mlx4_en_free_resources(struct mlx4_en_priv *priv) { int i; @@ -1989,7 +2010,7 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv) } -int mlx4_en_alloc_resources(struct mlx4_en_priv *priv) +static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv) { struct mlx4_en_port_profile *prof = priv->prof; int i; @@ -2054,6 +2075,77 @@ static void mlx4_en_shutdown(struct net_device *dev) rtnl_unlock(); } +static int mlx4_en_copy_priv(struct mlx4_en_priv *dst, + struct mlx4_en_priv *src, + struct mlx4_en_port_profile *prof) +{ + memcpy(&dst->hwtstamp_config, &prof->hwtstamp_config, + sizeof(dst->hwtstamp_config)); + dst->num_tx_rings_p_up = src->mdev->profile.num_tx_rings_p_up; + dst->tx_ring_num = prof->tx_ring_num; + dst->rx_ring_num = prof->rx_ring_num; + dst->flags = prof->flags; + dst->mdev = src->mdev; + dst->port = src->port; + dst->dev = src->dev; + dst->prof = prof; + dst->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) + + DS_SIZE * MLX4_EN_MAX_RX_FRAGS); + + dst->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS, + GFP_KERNEL); + if (!dst->tx_ring) + return -ENOMEM; + + dst->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS, + GFP_KERNEL); + if (!dst->tx_cq) { + kfree(dst->tx_ring); + return -ENOMEM; + } + return 0; +} + +static void mlx4_en_update_priv(struct mlx4_en_priv *dst, + struct mlx4_en_priv *src) +{ + memcpy(dst->rx_ring, src->rx_ring, + sizeof(struct mlx4_en_rx_ring *) * src->rx_ring_num); + memcpy(dst->rx_cq, src->rx_cq, + sizeof(struct mlx4_en_cq *) * src->rx_ring_num); + memcpy(&dst->hwtstamp_config, &src->hwtstamp_config, + sizeof(dst->hwtstamp_config)); + dst->tx_ring_num = src->tx_ring_num; + dst->rx_ring_num = src->rx_ring_num; + dst->tx_ring = src->tx_ring; + dst->tx_cq = src->tx_cq; + memcpy(dst->prof, src->prof, sizeof(struct mlx4_en_port_profile)); +} + +int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, + struct mlx4_en_priv *tmp, + struct mlx4_en_port_profile *prof) +{ + mlx4_en_copy_priv(tmp, priv, prof); + + if (mlx4_en_alloc_resources(tmp)) { + en_warn(priv, + "%s: Resource allocation failed, using previous configuration\n", + __func__); + kfree(tmp->tx_ring); + kfree(tmp->tx_cq); + return -ENOMEM; + } + return 0; +} + +void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv, + struct mlx4_en_priv *tmp) +{ + mlx4_en_free_resources(priv); + mlx4_en_update_priv(priv, tmp); +} + void mlx4_en_destroy_netdev(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -2090,6 +2182,10 @@ void mlx4_en_destroy_netdev(struct net_device *dev) mdev->upper[priv->port] = NULL; mutex_unlock(&mdev->state_lock); +#ifdef CONFIG_RFS_ACCEL + mlx4_en_cleanup_filters(priv); +#endif + mlx4_en_free_resources(priv); kfree(priv->tx_ring); @@ -2112,6 +2208,11 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) en_err(priv, "Bad MTU size:%d.\n", new_mtu); return -EPERM; } + if (priv->xdp_ring_num && MLX4_EN_EFF_MTU(new_mtu) > FRAG_SZ0) { + en_err(priv, "MTU size:%d requires frags but XDP running\n", + new_mtu); + return -EOPNOTSUPP; + } dev->mtu = new_mtu; if (netif_running(dev)) { @@ -2520,6 +2621,103 @@ static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 m return err; } +static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = priv->mdev; + struct bpf_prog *old_prog; + int xdp_ring_num; + int port_up = 0; + int err; + int i; + + xdp_ring_num = prog ? ALIGN(priv->rx_ring_num, MLX4_EN_NUM_UP) : 0; + + /* No need to reconfigure buffers when simply swapping the + * program for a new one. + */ + if (priv->xdp_ring_num == xdp_ring_num) { + if (prog) { + prog = bpf_prog_add(prog, priv->rx_ring_num - 1); + if (IS_ERR(prog)) + return PTR_ERR(prog); + } + for (i = 0; i < priv->rx_ring_num; i++) { + /* This xchg is paired with READ_ONCE in the fastpath */ + old_prog = xchg(&priv->rx_ring[i]->xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + } + return 0; + } + + if (priv->num_frags > 1) { + en_err(priv, "Cannot set XDP if MTU requires multiple frags\n"); + return -EOPNOTSUPP; + } + + if (priv->tx_ring_num < xdp_ring_num + MLX4_EN_NUM_UP) { + en_err(priv, + "Minimum %d tx channels required to run XDP\n", + (xdp_ring_num + MLX4_EN_NUM_UP) / MLX4_EN_NUM_UP); + return -EINVAL; + } + + if (prog) { + prog = bpf_prog_add(prog, priv->rx_ring_num - 1); + if (IS_ERR(prog)) + return PTR_ERR(prog); + } + + mutex_lock(&mdev->state_lock); + if (priv->port_up) { + port_up = 1; + mlx4_en_stop_port(dev, 1); + } + + priv->xdp_ring_num = xdp_ring_num; + netif_set_real_num_tx_queues(dev, priv->tx_ring_num - + priv->xdp_ring_num); + + for (i = 0; i < priv->rx_ring_num; i++) { + old_prog = xchg(&priv->rx_ring[i]->xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + } + + if (port_up) { + err = mlx4_en_start_port(dev); + if (err) { + en_err(priv, "Failed starting port %d for XDP change\n", + priv->port); + queue_work(mdev->workqueue, &priv->watchdog_task); + } + } + + mutex_unlock(&mdev->state_lock); + return 0; +} + +static bool mlx4_xdp_attached(struct net_device *dev) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + + return !!priv->xdp_ring_num; +} + +static int mlx4_xdp(struct net_device *dev, struct netdev_xdp *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return mlx4_xdp_set(dev, xdp->prog); + case XDP_QUERY_PROG: + xdp->prog_attached = mlx4_xdp_attached(dev); + return 0; + default: + return -EINVAL; + } +} + static const struct net_device_ops mlx4_netdev_ops = { .ndo_open = mlx4_en_open, .ndo_stop = mlx4_en_close, @@ -2548,6 +2746,7 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_udp_tunnel_del = mlx4_en_del_vxlan_port, .ndo_features_check = mlx4_en_features_check, .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, + .ndo_xdp = mlx4_xdp, }; static const struct net_device_ops mlx4_netdev_ops_master = { @@ -2584,6 +2783,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = { .ndo_udp_tunnel_del = mlx4_en_del_vxlan_port, .ndo_features_check = mlx4_en_features_check, .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, + .ndo_xdp = mlx4_xdp, }; struct mlx4_en_bond { @@ -3148,6 +3348,8 @@ int mlx4_en_reset_config(struct net_device *dev, { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_port_profile new_prof; + struct mlx4_en_priv *tmp; int port_up = 0; int err = 0; @@ -3164,19 +3366,29 @@ int mlx4_en_reset_config(struct net_device *dev, return -EINVAL; } + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + mutex_lock(&mdev->state_lock); + + memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); + memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config)); + + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + if (err) + goto out; + if (priv->port_up) { port_up = 1; mlx4_en_stop_port(dev, 1); } - mlx4_en_free_resources(priv); - en_warn(priv, "Changing device configuration rx filter(%x) rx vlan(%x)\n", - ts_config.rx_filter, !!(features & NETIF_F_HW_VLAN_CTAG_RX)); + ts_config.rx_filter, + !!(features & NETIF_F_HW_VLAN_CTAG_RX)); - priv->hwtstamp_config.tx_type = ts_config.tx_type; - priv->hwtstamp_config.rx_filter = ts_config.rx_filter; + mlx4_en_safe_replace_resources(priv, tmp); if (DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX)) { if (features & NETIF_F_HW_VLAN_CTAG_RX) @@ -3210,11 +3422,6 @@ int mlx4_en_reset_config(struct net_device *dev, dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; } - err = mlx4_en_alloc_resources(priv); - if (err) { - en_err(priv, "Failed reallocating port resources\n"); - goto out; - } if (port_up) { err = mlx4_en_start_port(dev); if (err) @@ -3223,6 +3430,8 @@ int mlx4_en_reset_config(struct net_device *dev, out: mutex_unlock(&mdev->state_lock); - netdev_features_change(dev); + kfree(tmp); + if (!err) + netdev_features_change(dev); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index c1b3a9c..2040dad 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -32,6 +32,7 @@ */ #include <net/busy_poll.h> +#include <linux/bpf.h> #include <linux/mlx4/cq.h> #include <linux/slab.h> #include <linux/mlx4/qp.h> @@ -57,7 +58,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, struct page *page; dma_addr_t dma; - for (order = MLX4_EN_ALLOC_PREFER_ORDER; ;) { + for (order = frag_info->order; ;) { gfp_t gfp = _gfp; if (order) @@ -70,7 +71,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, return -ENOMEM; } dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE << order, - PCI_DMA_FROMDEVICE); + frag_info->dma_dir); if (dma_mapping_error(priv->ddev, dma)) { put_page(page); return -ENOMEM; @@ -124,7 +125,8 @@ out: while (i--) { if (page_alloc[i].page != ring_alloc[i].page) { dma_unmap_page(priv->ddev, page_alloc[i].dma, - page_alloc[i].page_size, PCI_DMA_FROMDEVICE); + page_alloc[i].page_size, + priv->frag_info[i].dma_dir); page = page_alloc[i].page; /* Revert changes done by mlx4_alloc_pages */ page_ref_sub(page, page_alloc[i].page_size / @@ -145,7 +147,7 @@ static void mlx4_en_free_frag(struct mlx4_en_priv *priv, if (next_frag_end > frags[i].page_size) dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size, - PCI_DMA_FROMDEVICE); + frag_info->dma_dir); if (frags[i].page) put_page(frags[i].page); @@ -176,7 +178,8 @@ out: page_alloc = &ring->page_alloc[i]; dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->page_size, PCI_DMA_FROMDEVICE); + page_alloc->page_size, + priv->frag_info[i].dma_dir); page = page_alloc->page; /* Revert changes done by mlx4_alloc_pages */ page_ref_sub(page, page_alloc->page_size / @@ -201,7 +204,7 @@ static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv, i, page_count(page_alloc->page)); dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->page_size, PCI_DMA_FROMDEVICE); + page_alloc->page_size, frag_info->dma_dir); while (page_alloc->page_offset + frag_info->frag_stride < page_alloc->page_size) { put_page(page_alloc->page); @@ -244,6 +247,12 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, struct mlx4_en_rx_alloc *frags = ring->rx_info + (index << priv->log_rx_info); + if (ring->page_cache.index > 0) { + frags[0] = ring->page_cache.buf[--ring->page_cache.index]; + rx_desc->data[0].addr = cpu_to_be64(frags[0].dma); + return 0; + } + return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp); } @@ -502,26 +511,55 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv) } } +/* When the rx ring is running in page-per-packet mode, a released frame can go + * directly into a small cache, to avoid unmapping or touching the page + * allocator. In bpf prog performance scenarios, buffers are either forwarded + * or dropped, never converted to skbs, so every page can come directly from + * this cache when it is sized to be a multiple of the napi budget. + */ +bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring, + struct mlx4_en_rx_alloc *frame) +{ + struct mlx4_en_page_cache *cache = &ring->page_cache; + + if (cache->index >= MLX4_EN_CACHE_SIZE) + return false; + + cache->buf[cache->index++] = *frame; + return true; +} + void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv, struct mlx4_en_rx_ring **pring, u32 size, u16 stride) { struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_rx_ring *ring = *pring; + struct bpf_prog *old_prog; + old_prog = READ_ONCE(ring->xdp_prog); + if (old_prog) + bpf_prog_put(old_prog); mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE); vfree(ring->rx_info); ring->rx_info = NULL; kfree(ring); *pring = NULL; -#ifdef CONFIG_RFS_ACCEL - mlx4_en_cleanup_filters(priv); -#endif } void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv, struct mlx4_en_rx_ring *ring) { + int i; + + for (i = 0; i < ring->page_cache.index; i++) { + struct mlx4_en_rx_alloc *frame = &ring->page_cache.buf[i]; + + dma_unmap_page(priv->ddev, frame->dma, frame->page_size, + priv->frag_info[0].dma_dir); + put_page(frame->page); + } + ring->page_cache.index = 0; mlx4_en_free_rx_buf(priv, ring); if (ring->stride <= TXBB_SIZE) ring->buf -= TXBB_SIZE; @@ -743,7 +781,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring]; struct mlx4_en_rx_alloc *frags; struct mlx4_en_rx_desc *rx_desc; + struct bpf_prog *xdp_prog; + int doorbell_pending; struct sk_buff *skb; + int tx_index; int index; int nr; unsigned int length; @@ -759,6 +800,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud if (budget <= 0) return polled; + xdp_prog = READ_ONCE(ring->xdp_prog); + doorbell_pending = 0; + tx_index = (priv->tx_ring_num - priv->xdp_ring_num) + cq->ring; + /* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx * descriptor offset can be deduced from the CQE index instead of * reading 'cqe->index' */ @@ -835,6 +880,43 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) && (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL)); + /* A bpf program gets first chance to drop the packet. It may + * read bytes but not past the end of the frag. + */ + if (xdp_prog) { + struct xdp_buff xdp; + dma_addr_t dma; + u32 act; + + dma = be64_to_cpu(rx_desc->data[0].addr); + dma_sync_single_for_cpu(priv->ddev, dma, + priv->frag_info[0].frag_size, + DMA_FROM_DEVICE); + + xdp.data = page_address(frags[0].page) + + frags[0].page_offset; + xdp.data_end = xdp.data + length; + + act = bpf_prog_run_xdp(xdp_prog, &xdp); + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + if (!mlx4_en_xmit_frame(frags, dev, + length, tx_index, + &doorbell_pending)) + goto consumed; + break; + default: + bpf_warn_invalid_xdp_action(act); + case XDP_ABORTED: + case XDP_DROP: + if (mlx4_en_rx_recycle(ring, frags)) + goto consumed; + goto next; + } + } + if (likely(dev->features & NETIF_F_RXCSUM)) { if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP | MLX4_CQE_STATUS_UDP)) { @@ -986,6 +1068,7 @@ next: for (nr = 0; nr < priv->num_frags; nr++) mlx4_en_free_frag(priv, frags, nr); +consumed: ++cq->mcq.cons_index; index = (cq->mcq.cons_index) & ring->size_mask; cqe = mlx4_en_get_cqe(cq->buf, index, priv->cqe_size) + factor; @@ -994,6 +1077,9 @@ next: } out: + if (doorbell_pending) + mlx4_en_xmit_doorbell(priv->tx_ring[tx_index]); + AVG_PERF_COUNTER(priv->pstats.rx_coal_avg, polled); mlx4_cq_set_ci(&cq->mcq); wmb(); /* ensure HW sees CQ consumer before we post new buffers */ @@ -1061,22 +1147,35 @@ static const int frag_sizes[] = { void mlx4_en_calc_rx_buf(struct net_device *dev) { + enum dma_data_direction dma_dir = PCI_DMA_FROMDEVICE; struct mlx4_en_priv *priv = netdev_priv(dev); - /* VLAN_HLEN is added twice,to support skb vlan tagged with multiple - * headers. (For example: ETH_P_8021Q and ETH_P_8021AD). - */ - int eff_mtu = dev->mtu + ETH_HLEN + (2 * VLAN_HLEN); + int eff_mtu = MLX4_EN_EFF_MTU(dev->mtu); + int order = MLX4_EN_ALLOC_PREFER_ORDER; + u32 align = SMP_CACHE_BYTES; int buf_size = 0; int i = 0; + /* bpf requires buffers to be set up as 1 packet per page. + * This only works when num_frags == 1. + */ + if (priv->xdp_ring_num) { + dma_dir = PCI_DMA_BIDIRECTIONAL; + /* This will gain efficient xdp frame recycling at the expense + * of more costly truesize accounting + */ + align = PAGE_SIZE; + order = 0; + } + while (buf_size < eff_mtu) { + priv->frag_info[i].order = order; priv->frag_info[i].frag_size = (eff_mtu > buf_size + frag_sizes[i]) ? frag_sizes[i] : eff_mtu - buf_size; priv->frag_info[i].frag_prefix_size = buf_size; priv->frag_info[i].frag_stride = - ALIGN(priv->frag_info[i].frag_size, - SMP_CACHE_BYTES); + ALIGN(priv->frag_info[i].frag_size, align); + priv->frag_info[i].dma_dir = dma_dir; buf_size += priv->frag_info[i].frag_size; i++; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 76aa4d2..9df87ca 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -196,6 +196,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, ring->last_nr_txbb = 1; memset(ring->tx_info, 0, ring->size * sizeof(struct mlx4_en_tx_info)); memset(ring->buf, 0, ring->buf_size); + ring->free_tx_desc = mlx4_en_free_tx_desc; ring->qp_state = MLX4_QP_STATE_RST; ring->doorbell_qpn = cpu_to_be32(ring->qp.qpn << 8); @@ -265,10 +266,10 @@ static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv, } -static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, - struct mlx4_en_tx_ring *ring, - int index, u8 owner, u64 timestamp, - int napi_mode) +u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring, + int index, u8 owner, u64 timestamp, + int napi_mode) { struct mlx4_en_tx_info *tx_info = &ring->tx_info[index]; struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE; @@ -344,6 +345,27 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, return tx_info->nr_txbb; } +u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring, + int index, u8 owner, u64 timestamp, + int napi_mode) +{ + struct mlx4_en_tx_info *tx_info = &ring->tx_info[index]; + struct mlx4_en_rx_alloc frame = { + .page = tx_info->page, + .dma = tx_info->map0_dma, + .page_offset = 0, + .page_size = PAGE_SIZE, + }; + + if (!mlx4_en_rx_recycle(ring->recycle_ring, &frame)) { + dma_unmap_page(priv->ddev, tx_info->map0_dma, + PAGE_SIZE, priv->frag_info[0].dma_dir); + put_page(tx_info->page); + } + + return tx_info->nr_txbb; +} int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) { @@ -362,7 +384,7 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) } while (ring->cons != ring->prod) { - ring->last_nr_txbb = mlx4_en_free_tx_desc(priv, ring, + ring->last_nr_txbb = ring->free_tx_desc(priv, ring, ring->cons & ring->size_mask, !!(ring->cons & ring->size), 0, 0 /* Non-NAPI caller */); @@ -444,7 +466,7 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev, timestamp = mlx4_en_get_cqe_ts(cqe); /* free next descriptor */ - last_nr_txbb = mlx4_en_free_tx_desc( + last_nr_txbb = ring->free_tx_desc( priv, ring, ring_index, !!((ring_cons + txbbs_skipped) & ring->size), timestamp, napi_budget); @@ -476,6 +498,9 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev, ACCESS_ONCE(ring->last_nr_txbb) = last_nr_txbb; ACCESS_ONCE(ring->cons) = ring_cons + txbbs_skipped; + if (ring->free_tx_desc == mlx4_en_recycle_tx_desc) + return done < budget; + netdev_tx_completed_queue(ring->tx_queue, packets, bytes); /* Wakeup Tx queue if this stopped, and ring is not full. @@ -631,8 +656,7 @@ static int get_real_size(const struct sk_buff *skb, static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, const struct sk_buff *skb, const struct skb_shared_info *shinfo, - int real_size, u16 *vlan_tag, - int tx_ind, void *fragptr) + void *fragptr) { struct mlx4_wqe_inline_seg *inl = &tx_desc->inl; int spc = MLX4_INLINE_ALIGN - CTRL_SIZE - sizeof *inl; @@ -700,10 +724,66 @@ static void mlx4_bf_copy(void __iomem *dst, const void *src, __iowrite64_copy(dst, src, bytecnt / 8); } +void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring) +{ + wmb(); + /* Since there is no iowrite*_native() that writes the + * value as is, without byteswapping - using the one + * the doesn't do byteswapping in the relevant arch + * endianness. + */ +#if defined(__LITTLE_ENDIAN) + iowrite32( +#else + iowrite32be( +#endif + ring->doorbell_qpn, + ring->bf.uar->map + MLX4_SEND_DOORBELL); +} + +static void mlx4_en_tx_write_desc(struct mlx4_en_tx_ring *ring, + struct mlx4_en_tx_desc *tx_desc, + union mlx4_wqe_qpn_vlan qpn_vlan, + int desc_size, int bf_index, + __be32 op_own, bool bf_ok, + bool send_doorbell) +{ + tx_desc->ctrl.qpn_vlan = qpn_vlan; + + if (bf_ok) { + op_own |= htonl((bf_index & 0xffff) << 8); + /* Ensure new descriptor hits memory + * before setting ownership of this descriptor to HW + */ + dma_wmb(); + tx_desc->ctrl.owner_opcode = op_own; + + wmb(); + + mlx4_bf_copy(ring->bf.reg + ring->bf.offset, &tx_desc->ctrl, + desc_size); + + wmb(); + + ring->bf.offset ^= ring->bf.buf_size; + } else { + /* Ensure new descriptor hits memory + * before setting ownership of this descriptor to HW + */ + dma_wmb(); + tx_desc->ctrl.owner_opcode = op_own; + if (send_doorbell) + mlx4_en_xmit_doorbell(ring); + else + ring->xmit_more++; + } +} + netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct mlx4_en_priv *priv = netdev_priv(dev); + union mlx4_wqe_qpn_vlan qpn_vlan = {}; struct device *ddev = priv->ddev; struct mlx4_en_tx_ring *ring; struct mlx4_en_tx_desc *tx_desc; @@ -715,7 +795,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) int real_size; u32 index, bf_index; __be32 op_own; - u16 vlan_tag = 0; u16 vlan_proto = 0; int i_frag; int lso_header_size; @@ -725,6 +804,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) bool stop_queue; bool inline_ok; u32 ring_cons; + bool bf_ok; tx_ind = skb_get_queue_mapping(skb); ring = priv->tx_ring[tx_ind]; @@ -749,9 +829,17 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_drop; } + bf_ok = ring->bf_enabled; if (skb_vlan_tag_present(skb)) { - vlan_tag = skb_vlan_tag_get(skb); + qpn_vlan.vlan_tag = cpu_to_be16(skb_vlan_tag_get(skb)); vlan_proto = be16_to_cpu(skb->vlan_proto); + if (vlan_proto == ETH_P_8021AD) + qpn_vlan.ins_vlan = MLX4_WQE_CTRL_INS_SVLAN; + else if (vlan_proto == ETH_P_8021Q) + qpn_vlan.ins_vlan = MLX4_WQE_CTRL_INS_CVLAN; + else + qpn_vlan.ins_vlan = 0; + bf_ok = false; } netdev_txq_bql_enqueue_prefetchw(ring->tx_queue); @@ -771,6 +859,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) else { tx_desc = (struct mlx4_en_tx_desc *) ring->bounce_buf; bounce = true; + bf_ok = false; } /* Save skb in tx_info ring */ @@ -907,8 +996,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len); if (tx_info->inl) - build_inline_wqe(tx_desc, skb, shinfo, real_size, &vlan_tag, - tx_ind, fragptr); + build_inline_wqe(tx_desc, skb, shinfo, fragptr); if (skb->encapsulation) { union { @@ -946,60 +1034,15 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) real_size = (real_size / 16) & 0x3f; - if (ring->bf_enabled && desc_size <= MAX_BF && !bounce && - !skb_vlan_tag_present(skb) && send_doorbell) { - tx_desc->ctrl.bf_qpn = ring->doorbell_qpn | - cpu_to_be32(real_size); - - op_own |= htonl((bf_index & 0xffff) << 8); - /* Ensure new descriptor hits memory - * before setting ownership of this descriptor to HW - */ - dma_wmb(); - tx_desc->ctrl.owner_opcode = op_own; - - wmb(); + bf_ok &= desc_size <= MAX_BF && send_doorbell; - mlx4_bf_copy(ring->bf.reg + ring->bf.offset, &tx_desc->ctrl, - desc_size); - - wmb(); - - ring->bf.offset ^= ring->bf.buf_size; - } else { - tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag); - if (vlan_proto == ETH_P_8021AD) - tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_SVLAN; - else if (vlan_proto == ETH_P_8021Q) - tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_CVLAN; - else - tx_desc->ctrl.ins_vlan = 0; - - tx_desc->ctrl.fence_size = real_size; + if (bf_ok) + qpn_vlan.bf_qpn = ring->doorbell_qpn | cpu_to_be32(real_size); + else + qpn_vlan.fence_size = real_size; - /* Ensure new descriptor hits memory - * before setting ownership of this descriptor to HW - */ - dma_wmb(); - tx_desc->ctrl.owner_opcode = op_own; - if (send_doorbell) { - wmb(); - /* Since there is no iowrite*_native() that writes the - * value as is, without byteswapping - using the one - * the doesn't do byteswapping in the relevant arch - * endianness. - */ -#if defined(__LITTLE_ENDIAN) - iowrite32( -#else - iowrite32be( -#endif - ring->doorbell_qpn, - ring->bf.uar->map + MLX4_SEND_DOORBELL); - } else { - ring->xmit_more++; - } - } + mlx4_en_tx_write_desc(ring, tx_desc, qpn_vlan, desc_size, bf_index, + op_own, bf_ok, send_doorbell); if (unlikely(stop_queue)) { /* If queue was emptied after the if (stop_queue) , and before @@ -1034,3 +1077,106 @@ tx_drop: return NETDEV_TX_OK; } +netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame, + struct net_device *dev, unsigned int length, + int tx_ind, int *doorbell_pending) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + union mlx4_wqe_qpn_vlan qpn_vlan = {}; + struct mlx4_en_tx_ring *ring; + struct mlx4_en_tx_desc *tx_desc; + struct mlx4_wqe_data_seg *data; + struct mlx4_en_tx_info *tx_info; + int index, bf_index; + bool send_doorbell; + int nr_txbb = 1; + bool stop_queue; + dma_addr_t dma; + int real_size; + __be32 op_own; + u32 ring_cons; + bool bf_ok; + + BUILD_BUG_ON_MSG(ALIGN(CTRL_SIZE + DS_SIZE, TXBB_SIZE) != TXBB_SIZE, + "mlx4_en_xmit_frame requires minimum size tx desc"); + + ring = priv->tx_ring[tx_ind]; + + if (!priv->port_up) + goto tx_drop; + + if (mlx4_en_is_tx_ring_full(ring)) + goto tx_drop; + + /* fetch ring->cons far ahead before needing it to avoid stall */ + ring_cons = READ_ONCE(ring->cons); + + index = ring->prod & ring->size_mask; + tx_info = &ring->tx_info[index]; + + bf_ok = ring->bf_enabled; + + /* Track current inflight packets for performance analysis */ + AVG_PERF_COUNTER(priv->pstats.inflight_avg, + (u32)(ring->prod - ring_cons - 1)); + + bf_index = ring->prod; + tx_desc = ring->buf + index * TXBB_SIZE; + data = &tx_desc->data; + + dma = frame->dma; + + tx_info->page = frame->page; + frame->page = NULL; + tx_info->map0_dma = dma; + tx_info->map0_byte_count = length; + tx_info->nr_txbb = nr_txbb; + tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN); + tx_info->data_offset = (void *)data - (void *)tx_desc; + tx_info->ts_requested = 0; + tx_info->nr_maps = 1; + tx_info->linear = 1; + tx_info->inl = 0; + + dma_sync_single_for_device(priv->ddev, dma, length, PCI_DMA_TODEVICE); + + data->addr = cpu_to_be64(dma); + data->lkey = ring->mr_key; + dma_wmb(); + data->byte_count = cpu_to_be32(length); + + /* tx completion can avoid cache line miss for common cases */ + tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; + + op_own = cpu_to_be32(MLX4_OPCODE_SEND) | + ((ring->prod & ring->size) ? + cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0); + + ring->packets++; + ring->bytes += tx_info->nr_bytes; + AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, length); + + ring->prod += nr_txbb; + + stop_queue = mlx4_en_is_tx_ring_full(ring); + send_doorbell = stop_queue || + *doorbell_pending > MLX4_EN_DOORBELL_BUDGET; + bf_ok &= send_doorbell; + + real_size = ((CTRL_SIZE + nr_txbb * DS_SIZE) / 16) & 0x3f; + + if (bf_ok) + qpn_vlan.bf_qpn = ring->doorbell_qpn | cpu_to_be32(real_size); + else + qpn_vlan.fence_size = real_size; + + mlx4_en_tx_write_desc(ring, tx_desc, qpn_vlan, TXBB_SIZE, bf_index, + op_own, bf_ok, send_doorbell); + *doorbell_pending = send_doorbell ? 0 : *doorbell_pending + 1; + + return NETDEV_TX_OK; + +tx_drop: + ring->tx_dropped++; + return NETDEV_TX_BUSY; +} diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index d39bf59..2c2913d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -132,6 +132,7 @@ enum { MLX4_EN_NUM_UP) #define MLX4_EN_DEFAULT_TX_WORK 256 +#define MLX4_EN_DOORBELL_BUDGET 8 /* Target number of packets to coalesce with interrupt moderation */ #define MLX4_EN_RX_COAL_TARGET 44 @@ -164,6 +165,10 @@ enum { #define MLX4_LOOPBACK_TEST_PAYLOAD (HEADER_COPY_SIZE - ETH_HLEN) #define MLX4_EN_MIN_MTU 46 +/* VLAN_HLEN is added twice,to support skb vlan tagged with multiple + * headers. (For example: ETH_P_8021Q and ETH_P_8021AD). + */ +#define MLX4_EN_EFF_MTU(mtu) ((mtu) + ETH_HLEN + (2 * VLAN_HLEN)) #define ETH_BCAST 0xffffffffffffULL #define MLX4_EN_LOOPBACK_RETRIES 5 @@ -215,7 +220,10 @@ enum cq_type { struct mlx4_en_tx_info { - struct sk_buff *skb; + union { + struct sk_buff *skb; + struct page *page; + }; dma_addr_t map0_dma; u32 map0_byte_count; u32 nr_txbb; @@ -255,6 +263,14 @@ struct mlx4_en_rx_alloc { u32 page_size; }; +#define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT) +struct mlx4_en_page_cache { + u32 index; + struct mlx4_en_rx_alloc buf[MLX4_EN_CACHE_SIZE]; +}; + +struct mlx4_en_priv; + struct mlx4_en_tx_ring { /* cache line used and dirtied in tx completion * (mlx4_en_free_tx_buf()) @@ -288,6 +304,11 @@ struct mlx4_en_tx_ring { __be32 mr_key; void *buf; struct mlx4_en_tx_info *tx_info; + struct mlx4_en_rx_ring *recycle_ring; + u32 (*free_tx_desc)(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring, + int index, u8 owner, + u64 timestamp, int napi_mode); u8 *bounce_buf; struct mlx4_qp_context context; int qpn; @@ -319,6 +340,8 @@ struct mlx4_en_rx_ring { u8 fcs_del; void *buf; void *rx_info; + struct bpf_prog *xdp_prog; + struct mlx4_en_page_cache page_cache; unsigned long bytes; unsigned long packets; unsigned long csum_ok; @@ -353,12 +376,14 @@ struct mlx4_en_port_profile { u32 rx_ring_num; u32 tx_ring_size; u32 rx_ring_size; + u8 num_tx_rings_p_up; u8 rx_pause; u8 rx_ppp; u8 tx_pause; u8 tx_ppp; int rss_rings; int inline_thold; + struct hwtstamp_config hwtstamp_config; }; struct mlx4_en_profile { @@ -438,7 +463,9 @@ struct mlx4_en_mc_list { struct mlx4_en_frag_info { u16 frag_size; u16 frag_prefix_size; - u16 frag_stride; + u32 frag_stride; + enum dma_data_direction dma_dir; + int order; }; #ifdef CONFIG_MLX4_EN_DCB @@ -558,6 +585,7 @@ struct mlx4_en_priv { struct mlx4_en_frag_info frag_info[MLX4_EN_MAX_RX_FRAGS]; u16 num_frags; u16 log_rx_info; + int xdp_ring_num; struct mlx4_en_tx_ring **tx_ring; struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS]; @@ -647,8 +675,11 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev, u8 rx_ppp, u8 rx_pause, u8 tx_ppp, u8 tx_pause); -void mlx4_en_free_resources(struct mlx4_en_priv *priv); -int mlx4_en_alloc_resources(struct mlx4_en_priv *priv); +int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, + struct mlx4_en_priv *tmp, + struct mlx4_en_port_profile *prof); +void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv, + struct mlx4_en_priv *tmp); int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq, int entries, int ring, enum cq_type mode, int node); @@ -663,6 +694,12 @@ void mlx4_en_tx_irq(struct mlx4_cq *mcq); u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, void *accel_priv, select_queue_fallback_t fallback); netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame, + struct net_device *dev, unsigned int length, + int tx_ind, int *doorbell_pending); +void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring); +bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring, + struct mlx4_en_rx_alloc *frame); int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring **pring, @@ -691,6 +728,14 @@ int mlx4_en_process_rx_cq(struct net_device *dev, int budget); int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget); int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget); +u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring, + int index, u8 owner, u64 timestamp, + int napi_mode); +u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring, + int index, u8 owner, u64 timestamp, + int napi_mode); void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, int is_tx, int rss, int qpn, int cqn, int user_prio, struct mlx4_qp_context *context); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 611ab55..bdcb699 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1464,6 +1464,11 @@ static int mlx5e_open_channels(struct mlx5e_priv *priv) goto err_close_channels; } + /* FIXME: This is a W/A for tx timeout watch dog false alarm when + * polling for inactive tx queues. + */ + netif_tx_start_all_queues(priv->netdev); + kfree(cparam); return 0; @@ -1483,6 +1488,12 @@ static void mlx5e_close_channels(struct mlx5e_priv *priv) { int i; + /* FIXME: This is a W/A only for tx timeout watch dog false alarm when + * polling for inactive tx queues. + */ + netif_tx_stop_all_queues(priv->netdev); + netif_tx_disable(priv->netdev); + for (i = 0; i < priv->params.num_channels; i++) mlx5e_close_channel(priv->channel[i]); @@ -2774,7 +2785,7 @@ static void mlx5e_tx_timeout(struct net_device *dev) for (i = 0; i < priv->params.num_channels * priv->params.num_tc; i++) { struct mlx5e_sq *sq = priv->txq_to_sq_map[i]; - if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i))) + if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i))) continue; sched_work = true; set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 1a377b4..75bb8c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1740,10 +1740,7 @@ static int init_ingress_acl_root_ns(struct mlx5_flow_steering *steering) /* create 1 prio*/ prio = fs_create_prio(&steering->esw_egress_root_ns->ns, 0, MLX5_TOTAL_VPORTS(steering->dev)); - if (IS_ERR(prio)) - return PTR_ERR(prio); - else - return 0; + return PTR_ERR_OR_ZERO(prio); } static int init_egress_acl_root_ns(struct mlx5_flow_steering *steering) @@ -1757,10 +1754,7 @@ static int init_egress_acl_root_ns(struct mlx5_flow_steering *steering) /* create 1 prio*/ prio = fs_create_prio(&steering->esw_ingress_root_ns->ns, 0, MLX5_TOTAL_VPORTS(steering->dev)); - if (IS_ERR(prio)) - return PTR_ERR(prio); - else - return 0; + return PTR_ERR_OR_ZERO(prio); } int mlx5_init_fs(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c index 05de772..e25a73ed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -72,8 +72,8 @@ static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port) u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]; u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)]; - memset(&in, 0, sizeof(in)); - memset(&out, 0, sizeof(out)); + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); MLX5_SET(delete_vxlan_udp_dport_in, in, opcode, MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT); diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h index f9cd6e3..28271be 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h +++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h @@ -105,6 +105,7 @@ enum mlxsw_cmd_opcode { MLXSW_CMD_OPCODE_SW2HW_EQ = 0x013, MLXSW_CMD_OPCODE_HW2SW_EQ = 0x014, MLXSW_CMD_OPCODE_QUERY_EQ = 0x015, + MLXSW_CMD_OPCODE_QUERY_RESOURCES = 0x101, }; static inline const char *mlxsw_cmd_opcode_str(u16 opcode) @@ -144,6 +145,8 @@ static inline const char *mlxsw_cmd_opcode_str(u16 opcode) return "HW2SW_EQ"; case MLXSW_CMD_OPCODE_QUERY_EQ: return "QUERY_EQ"; + case MLXSW_CMD_OPCODE_QUERY_RESOURCES: + return "QUERY_RESOURCES"; default: return "*UNKNOWN*"; } @@ -500,6 +503,35 @@ static inline int mlxsw_cmd_unmap_fa(struct mlxsw_core *mlxsw_core) return mlxsw_cmd_exec_none(mlxsw_core, MLXSW_CMD_OPCODE_UNMAP_FA, 0, 0); } +/* QUERY_RESOURCES - Query chip resources + * -------------------------------------- + * OpMod == 0 (N/A) , INMmod is index + * ---------------------------------- + * The QUERY_RESOURCES command retrieves information related to chip resources + * by resource ID. Every command returns 32 entries. INmod is being use as base. + * for example, index 1 will return entries 32-63. When the tables end and there + * are no more sources in the table, will return resource id 0xFFF to indicate + * it. + */ +static inline int mlxsw_cmd_query_resources(struct mlxsw_core *mlxsw_core, + char *out_mbox, int index) +{ + return mlxsw_cmd_exec_out(mlxsw_core, MLXSW_CMD_OPCODE_QUERY_RESOURCES, + 0, index, false, out_mbox, + MLXSW_CMD_MBOX_SIZE); +} + +/* cmd_mbox_query_resource_id + * The resource id. 0xFFFF indicates table's end. + */ +MLXSW_ITEM32_INDEXED(cmd_mbox, query_resource, id, 0x00, 16, 16, 0x8, 0, false); + +/* cmd_mbox_query_resource_data + * The resource + */ +MLXSW_ITEM64_INDEXED(cmd_mbox, query_resource, data, + 0x00, 0, 40, 0x8, 0, false); + /* CONFIG_PROFILE (Set) - Configure Switch Profile * ------------------------------ * OpMod == 1 (Set), INMmod == 0 (N/A) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 480a3ba..068ee65a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -111,6 +111,7 @@ struct mlxsw_core { struct { u8 *mapping; /* lag_id+port_index to local_port mapping */ } lag; + struct mlxsw_resources resources; struct mlxsw_hwmon *hwmon; unsigned long driver_priv[0]; /* driver_priv has to be always the last item */ @@ -1110,7 +1111,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, } } - err = mlxsw_bus->init(bus_priv, mlxsw_core, mlxsw_driver->profile); + err = mlxsw_bus->init(bus_priv, mlxsw_core, mlxsw_driver->profile, + &mlxsw_core->resources); if (err) goto err_bus_init; @@ -1652,6 +1654,12 @@ void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_lag_mapping_clear); +struct mlxsw_resources *mlxsw_core_resources_get(struct mlxsw_core *mlxsw_core) +{ + return &mlxsw_core->resources; +} +EXPORT_SYMBOL(mlxsw_core_resources_get); + int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, struct mlxsw_core_port *mlxsw_core_port, u8 local_port, struct net_device *dev, bool split, u32 split_group) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 2fe385c..d3476ea 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -215,6 +215,7 @@ struct mlxsw_config_profile { u32 kvd_linear_size; u32 kvd_hash_single_size; u32 kvd_hash_double_size; + u8 resource_query_enable; struct mlxsw_swid_config swid_config[MLXSW_CONFIG_PROFILE_SWID_COUNT]; }; @@ -266,10 +267,18 @@ struct mlxsw_driver { const struct mlxsw_config_profile *profile; }; +struct mlxsw_resources { + u8 max_span_valid:1; + u8 max_span; +}; + +struct mlxsw_resources *mlxsw_core_resources_get(struct mlxsw_core *mlxsw_core); + struct mlxsw_bus { const char *kind; int (*init)(void *bus_priv, struct mlxsw_core *mlxsw_core, - const struct mlxsw_config_profile *profile); + const struct mlxsw_config_profile *profile, + struct mlxsw_resources *resources); void (*fini)(void *bus_priv); bool (*skb_transmit_busy)(void *bus_priv, const struct mlxsw_tx_info *tx_info); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index ddbc9f2..1d1360c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1154,6 +1154,61 @@ mlxsw_pci_config_profile_swid_config(struct mlxsw_pci *mlxsw_pci, mlxsw_cmd_mbox_config_profile_swid_config_mask_set(mbox, index, mask); } +#define MLXSW_RESOURCES_TABLE_END_ID 0xffff +#define MLXSW_MAX_SPAN_ID 0x2420 +#define MLXSW_RESOURCES_QUERY_MAX_QUERIES 100 +#define MLXSW_RESOURCES_PER_QUERY 32 + +static void mlxsw_pci_resources_query_parse(int id, u64 val, + struct mlxsw_resources *resources) +{ + switch (id) { + case MLXSW_MAX_SPAN_ID: + resources->max_span = val; + resources->max_span_valid = 1; + break; + default: + break; + } +} + +static int mlxsw_pci_resources_query(struct mlxsw_pci *mlxsw_pci, char *mbox, + struct mlxsw_resources *resources, + u8 query_enabled) +{ + int index, i; + u64 data; + u16 id; + int err; + + /* Not all the versions support resources query */ + if (!query_enabled) + return 0; + + mlxsw_cmd_mbox_zero(mbox); + + for (index = 0; index < MLXSW_RESOURCES_QUERY_MAX_QUERIES; index++) { + err = mlxsw_cmd_query_resources(mlxsw_pci->core, mbox, index); + if (err) + return err; + + for (i = 0; i < MLXSW_RESOURCES_PER_QUERY; i++) { + id = mlxsw_cmd_mbox_query_resource_id_get(mbox, i); + data = mlxsw_cmd_mbox_query_resource_data_get(mbox, i); + + if (id == MLXSW_RESOURCES_TABLE_END_ID) + return 0; + + mlxsw_pci_resources_query_parse(id, data, resources); + } + } + + /* If after MLXSW_RESOURCES_QUERY_MAX_QUERIES we still didn't get + * MLXSW_RESOURCES_TABLE_END_ID, something went bad in the FW. + */ + return -EIO; +} + static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, const struct mlxsw_config_profile *profile) { @@ -1404,7 +1459,8 @@ static void mlxsw_pci_mbox_free(struct mlxsw_pci *mlxsw_pci, } static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, - const struct mlxsw_config_profile *profile) + const struct mlxsw_config_profile *profile, + struct mlxsw_resources *resources) { struct mlxsw_pci *mlxsw_pci = bus_priv; struct pci_dev *pdev = mlxsw_pci->pdev; @@ -1463,6 +1519,11 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, if (err) goto err_boardinfo; + err = mlxsw_pci_resources_query(mlxsw_pci, mbox, resources, + profile->resource_query_enable); + if (err) + goto err_query_resources; + err = mlxsw_pci_config_profile(mlxsw_pci, mbox, profile); if (err) goto err_config_profile; @@ -1485,6 +1546,7 @@ err_request_eq_irq: mlxsw_pci_aqs_fini(mlxsw_pci); err_aqs_init: err_config_profile: +err_query_resources: err_boardinfo: mlxsw_pci_fw_area_fini(mlxsw_pci); err_fw_area_init: diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0cc1485..7ca9201 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -2503,6 +2503,7 @@ MLXSW_ITEM32(reg, ppcnt, pnat, 0x00, 14, 2); enum mlxsw_reg_ppcnt_grp { MLXSW_REG_PPCNT_IEEE_8023_CNT = 0x0, MLXSW_REG_PPCNT_PRIO_CNT = 0x10, + MLXSW_REG_PPCNT_TC_CNT = 0x11, }; /* reg_ppcnt_grp @@ -2703,6 +2704,23 @@ MLXSW_ITEM64(reg, ppcnt, tx_pause_duration, 0x08 + 0x68, 0, 64); */ MLXSW_ITEM64(reg, ppcnt, tx_pause_transition, 0x08 + 0x70, 0, 64); +/* Ethernet Per Traffic Group Counters */ + +/* reg_ppcnt_tc_transmit_queue + * Contains the transmit queue depth in cells of traffic class + * selected by prio_tc and the port selected by local_port. + * The field cannot be cleared. + * Access: RO + */ +MLXSW_ITEM64(reg, ppcnt, tc_transmit_queue, 0x08 + 0x00, 0, 64); + +/* reg_ppcnt_tc_no_buffer_discard_uc + * The number of unicast packets dropped due to lack of shared + * buffer resources. + * Access: RO + */ +MLXSW_ITEM64(reg, ppcnt, tc_no_buffer_discard_uc, 0x08 + 0x08, 0, 64); + static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port, enum mlxsw_reg_ppcnt_grp grp, u8 prio_tc) @@ -2721,7 +2739,7 @@ static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port, * Configures the switch priority to buffer table. */ #define MLXSW_REG_PPTB_ID 0x500B -#define MLXSW_REG_PPTB_LEN 0x0C +#define MLXSW_REG_PPTB_LEN 0x10 static const struct mlxsw_reg_info mlxsw_reg_pptb = { .id = MLXSW_REG_PPTB_ID, @@ -2787,6 +2805,13 @@ MLXSW_ITEM32(reg, pptb, pm_msb, 0x08, 24, 8); */ MLXSW_ITEM32(reg, pptb, untagged_buff, 0x08, 0, 4); +/* reg_pptb_prio_to_buff_msb + * Mapping of switch priority <i+8> to one of the allocated receive port + * buffers. + * Access: RW + */ +MLXSW_ITEM_BIT_ARRAY(reg, pptb, prio_to_buff_msb, 0x0C, 0x04, 4); + #define MLXSW_REG_PPTB_ALL_PRIO 0xFF static inline void mlxsw_reg_pptb_pack(char *payload, u8 local_port) @@ -2795,6 +2820,14 @@ static inline void mlxsw_reg_pptb_pack(char *payload, u8 local_port) mlxsw_reg_pptb_mm_set(payload, MLXSW_REG_PPTB_MM_UM); mlxsw_reg_pptb_local_port_set(payload, local_port); mlxsw_reg_pptb_pm_set(payload, MLXSW_REG_PPTB_ALL_PRIO); + mlxsw_reg_pptb_pm_msb_set(payload, MLXSW_REG_PPTB_ALL_PRIO); +} + +static inline void mlxsw_reg_pptb_prio_to_buff_pack(char *payload, u8 prio, + u8 buff) +{ + mlxsw_reg_pptb_prio_to_buff_set(payload, prio, buff); + mlxsw_reg_pptb_prio_to_buff_msb_set(payload, prio, buff); } /* PBMC - Port Buffer Management Control Register @@ -4600,6 +4633,123 @@ static inline void mlxsw_reg_mtmp_unpack(char *payload, unsigned int *p_temp, mlxsw_reg_mtmp_sensor_name_memcpy_from(payload, sensor_name); } +/* MPAT - Monitoring Port Analyzer Table + * ------------------------------------- + * MPAT Register is used to query and configure the Switch PortAnalyzer Table. + * For an enabled analyzer, all fields except e (enable) cannot be modified. + */ +#define MLXSW_REG_MPAT_ID 0x901A +#define MLXSW_REG_MPAT_LEN 0x78 + +static const struct mlxsw_reg_info mlxsw_reg_mpat = { + .id = MLXSW_REG_MPAT_ID, + .len = MLXSW_REG_MPAT_LEN, +}; + +/* reg_mpat_pa_id + * Port Analyzer ID. + * Access: Index + */ +MLXSW_ITEM32(reg, mpat, pa_id, 0x00, 28, 4); + +/* reg_mpat_system_port + * A unique port identifier for the final destination of the packet. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, system_port, 0x00, 0, 16); + +/* reg_mpat_e + * Enable. Indicating the Port Analyzer is enabled. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, e, 0x04, 31, 1); + +/* reg_mpat_qos + * Quality Of Service Mode. + * 0: CONFIGURED - QoS parameters (Switch Priority, and encapsulation + * PCP, DEI, DSCP or VL) are configured. + * 1: MAINTAIN - QoS parameters (Switch Priority, Color) are the + * same as in the original packet that has triggered the mirroring. For + * SPAN also the pcp,dei are maintained. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, qos, 0x04, 26, 1); + +/* reg_mpat_be + * Best effort mode. Indicates mirroring traffic should not cause packet + * drop or back pressure, but will discard the mirrored packets. Mirrored + * packets will be forwarded on a best effort manner. + * 0: Do not discard mirrored packets + * 1: Discard mirrored packets if causing congestion + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, be, 0x04, 25, 1); + +static inline void mlxsw_reg_mpat_pack(char *payload, u8 pa_id, + u16 system_port, bool e) +{ + MLXSW_REG_ZERO(mpat, payload); + mlxsw_reg_mpat_pa_id_set(payload, pa_id); + mlxsw_reg_mpat_system_port_set(payload, system_port); + mlxsw_reg_mpat_e_set(payload, e); + mlxsw_reg_mpat_qos_set(payload, 1); + mlxsw_reg_mpat_be_set(payload, 1); +} + +/* MPAR - Monitoring Port Analyzer Register + * ---------------------------------------- + * MPAR register is used to query and configure the port analyzer port mirroring + * properties. + */ +#define MLXSW_REG_MPAR_ID 0x901B +#define MLXSW_REG_MPAR_LEN 0x08 + +static const struct mlxsw_reg_info mlxsw_reg_mpar = { + .id = MLXSW_REG_MPAR_ID, + .len = MLXSW_REG_MPAR_LEN, +}; + +/* reg_mpar_local_port + * The local port to mirror the packets from. + * Access: Index + */ +MLXSW_ITEM32(reg, mpar, local_port, 0x00, 16, 8); + +enum mlxsw_reg_mpar_i_e { + MLXSW_REG_MPAR_TYPE_EGRESS, + MLXSW_REG_MPAR_TYPE_INGRESS, +}; + +/* reg_mpar_i_e + * Ingress/Egress + * Access: Index + */ +MLXSW_ITEM32(reg, mpar, i_e, 0x00, 0, 4); + +/* reg_mpar_enable + * Enable mirroring + * By default, port mirroring is disabled for all ports. + * Access: RW + */ +MLXSW_ITEM32(reg, mpar, enable, 0x04, 31, 1); + +/* reg_mpar_pa_id + * Port Analyzer ID. + * Access: RW + */ +MLXSW_ITEM32(reg, mpar, pa_id, 0x04, 0, 4); + +static inline void mlxsw_reg_mpar_pack(char *payload, u8 local_port, + enum mlxsw_reg_mpar_i_e i_e, + bool enable, u8 pa_id) +{ + MLXSW_REG_ZERO(mpar, payload); + mlxsw_reg_mpar_local_port_set(payload, local_port); + mlxsw_reg_mpar_enable_set(payload, enable); + mlxsw_reg_mpar_i_e_set(payload, i_e); + mlxsw_reg_mpar_pa_id_set(payload, pa_id); +} + /* MLCR - Management LED Control Register * -------------------------------------- * Controls the system LEDs. @@ -5029,6 +5179,45 @@ static inline void mlxsw_reg_sbsr_rec_unpack(char *payload, int rec_index, mlxsw_reg_sbsr_rec_max_buff_occupancy_get(payload, rec_index); } +/* SBIB - Shared Buffer Internal Buffer Register + * --------------------------------------------- + * The SBIB register configures per port buffers for internal use. The internal + * buffers consume memory on the port buffers (note that the port buffers are + * used also by PBMC). + * + * For Spectrum this is used for egress mirroring. + */ +#define MLXSW_REG_SBIB_ID 0xB006 +#define MLXSW_REG_SBIB_LEN 0x10 + +static const struct mlxsw_reg_info mlxsw_reg_sbib = { + .id = MLXSW_REG_SBIB_ID, + .len = MLXSW_REG_SBIB_LEN, +}; + +/* reg_sbib_local_port + * Local port number + * Not supported for CPU port and router port + * Access: Index + */ +MLXSW_ITEM32(reg, sbib, local_port, 0x00, 16, 8); + +/* reg_sbib_buff_size + * Units represented in cells + * Allowed range is 0 to (cap_max_headroom_size - 1) + * Default is 0 + * Access: RW + */ +MLXSW_ITEM32(reg, sbib, buff_size, 0x08, 0, 24); + +static inline void mlxsw_reg_sbib_pack(char *payload, u8 local_port, + u32 buff_size) +{ + MLXSW_REG_ZERO(sbib, payload); + mlxsw_reg_sbib_local_port_set(payload, local_port); + mlxsw_reg_sbib_buff_size_set(payload, buff_size); +} + static inline const char *mlxsw_reg_id_str(u16 reg_id) { switch (reg_id) { @@ -5132,6 +5321,10 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id) return "MFSM"; case MLXSW_REG_MTCAP_ID: return "MTCAP"; + case MLXSW_REG_MPAT_ID: + return "MPAT"; + case MLXSW_REG_MPAR_ID: + return "MPAR"; case MLXSW_REG_MTMP_ID: return "MTMP"; case MLXSW_REG_MLCR_ID: @@ -5146,6 +5339,8 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id) return "SBMM"; case MLXSW_REG_SBSR_ID: return "SBSR"; + case MLXSW_REG_SBIB_ID: + return "SBIB"; default: return "*UNKNOWN*"; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index c812513..552636b7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -54,6 +54,8 @@ #include <linux/inetdevice.h> #include <net/switchdev.h> #include <generated/utsrelease.h> +#include <net/pkt_cls.h> +#include <net/tc_act/tc_mirred.h> #include "spectrum.h" #include "core.h" @@ -133,6 +135,8 @@ MLXSW_ITEM32(tx, hdr, fid, 0x08, 0, 16); */ MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); +static bool mlxsw_sp_port_dev_check(const struct net_device *dev); + static void mlxsw_sp_txhdr_construct(struct sk_buff *skb, const struct mlxsw_tx_info *tx_info) { @@ -161,6 +165,303 @@ static int mlxsw_sp_base_mac_get(struct mlxsw_sp *mlxsw_sp) return 0; } +static int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_resources *resources; + int i; + + resources = mlxsw_core_resources_get(mlxsw_sp->core); + if (!resources->max_span_valid) + return -EIO; + + mlxsw_sp->span.entries_count = resources->max_span; + mlxsw_sp->span.entries = kcalloc(mlxsw_sp->span.entries_count, + sizeof(struct mlxsw_sp_span_entry), + GFP_KERNEL); + if (!mlxsw_sp->span.entries) + return -ENOMEM; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) + INIT_LIST_HEAD(&mlxsw_sp->span.entries[i].bound_ports_list); + + return 0; +} + +static void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + WARN_ON_ONCE(!list_empty(&curr->bound_ports_list)); + } + kfree(mlxsw_sp->span.entries); +} + +static struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_create(struct mlxsw_sp_port *port) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + struct mlxsw_sp_span_entry *span_entry; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + u8 local_port = port->local_port; + int index; + int i; + int err; + + /* find a free entry to use */ + index = -1; + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + if (!mlxsw_sp->span.entries[i].used) { + index = i; + span_entry = &mlxsw_sp->span.entries[i]; + break; + } + } + if (index < 0) + return NULL; + + /* create a new port analayzer entry for local_port */ + mlxsw_reg_mpat_pack(mpat_pl, index, local_port, true); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); + if (err) + return NULL; + + span_entry->used = true; + span_entry->id = index; + span_entry->ref_count = 0; + span_entry->local_port = local_port; + return span_entry; +} + +static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry) +{ + u8 local_port = span_entry->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, false); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); + span_entry->used = false; +} + +struct mlxsw_sp_span_entry *mlxsw_sp_span_entry_find(struct mlxsw_sp_port *port) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + if (curr->used && curr->local_port == port->local_port) + return curr; + } + return NULL; +} + +struct mlxsw_sp_span_entry *mlxsw_sp_span_entry_get(struct mlxsw_sp_port *port) +{ + struct mlxsw_sp_span_entry *span_entry; + + span_entry = mlxsw_sp_span_entry_find(port); + if (span_entry) { + span_entry->ref_count++; + return span_entry; + } + + return mlxsw_sp_span_entry_create(port); +} + +static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry) +{ + if (--span_entry->ref_count == 0) + mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry); + return 0; +} + +static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + struct mlxsw_sp_span_inspected_port *p; + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + list_for_each_entry(p, &curr->bound_ports_list, list) + if (p->local_port == port->local_port && + p->type == MLXSW_SP_SPAN_EGRESS) + return true; + } + + return false; +} + +static int mlxsw_sp_span_mtu_to_buffsize(int mtu) +{ + return MLXSW_SP_BYTES_TO_CELLS(mtu * 5 / 2) + 1; +} + +static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + int err; + + /* If port is egress mirrored, the shared buffer size should be + * updated according to the mtu value + */ + if (mlxsw_sp_span_is_egress_mirror(port)) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, + mlxsw_sp_span_mtu_to_buffsize(mtu)); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + if (err) { + netdev_err(port->dev, "Could not update shared buffer for mirroring\n"); + return err; + } + } + + return 0; +} + +static struct mlxsw_sp_span_inspected_port * +mlxsw_sp_span_entry_bound_port_find(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry) +{ + struct mlxsw_sp_span_inspected_port *p; + + list_for_each_entry(p, &span_entry->bound_ports_list, list) + if (port->local_port == p->local_port) + return p; + return NULL; +} + +static int +mlxsw_sp_span_inspected_port_bind(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type) +{ + struct mlxsw_sp_span_inspected_port *inspected_port; + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char mpar_pl[MLXSW_REG_MPAR_LEN]; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + int pa_id = span_entry->id; + int err; + + /* if it is an egress SPAN, bind a shared buffer to it */ + if (type == MLXSW_SP_SPAN_EGRESS) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, + mlxsw_sp_span_mtu_to_buffsize(port->dev->mtu)); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + if (err) { + netdev_err(port->dev, "Could not create shared buffer for mirroring\n"); + return err; + } + } + + /* bind the port to the SPAN entry */ + mlxsw_reg_mpar_pack(mpar_pl, port->local_port, type, true, pa_id); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpar), mpar_pl); + if (err) + goto err_mpar_reg_write; + + inspected_port = kzalloc(sizeof(*inspected_port), GFP_KERNEL); + if (!inspected_port) { + err = -ENOMEM; + goto err_inspected_port_alloc; + } + inspected_port->local_port = port->local_port; + inspected_port->type = type; + list_add_tail(&inspected_port->list, &span_entry->bound_ports_list); + + return 0; + +err_mpar_reg_write: +err_inspected_port_alloc: + if (type == MLXSW_SP_SPAN_EGRESS) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + } + return err; +} + +static void +mlxsw_sp_span_inspected_port_unbind(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type) +{ + struct mlxsw_sp_span_inspected_port *inspected_port; + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char mpar_pl[MLXSW_REG_MPAR_LEN]; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + int pa_id = span_entry->id; + + inspected_port = mlxsw_sp_span_entry_bound_port_find(port, span_entry); + if (!inspected_port) + return; + + /* remove the inspected port */ + mlxsw_reg_mpar_pack(mpar_pl, port->local_port, type, false, pa_id); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpar), mpar_pl); + + /* remove the SBIB buffer if it was egress SPAN */ + if (type == MLXSW_SP_SPAN_EGRESS) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + } + + mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); + + list_del(&inspected_port->list); + kfree(inspected_port); +} + +static int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, + struct mlxsw_sp_port *to, + enum mlxsw_sp_span_type type) +{ + struct mlxsw_sp *mlxsw_sp = from->mlxsw_sp; + struct mlxsw_sp_span_entry *span_entry; + int err; + + span_entry = mlxsw_sp_span_entry_get(to); + if (!span_entry) + return -ENOENT; + + netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n", + span_entry->id); + + err = mlxsw_sp_span_inspected_port_bind(from, span_entry, type); + if (err) + goto err_port_bind; + + return 0; + +err_port_bind: + mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); + return err; +} + +static void mlxsw_sp_span_mirror_remove(struct mlxsw_sp_port *from, + struct mlxsw_sp_port *to, + enum mlxsw_sp_span_type type) +{ + struct mlxsw_sp_span_entry *span_entry; + + span_entry = mlxsw_sp_span_entry_find(to); + if (!span_entry) { + netdev_err(from->dev, "no span entry found\n"); + return; + } + + netdev_dbg(from->dev, "removing inspected port from SPAN entry %d\n", + span_entry->id); + mlxsw_sp_span_inspected_port_unbind(from, span_entry, type); +} + static int mlxsw_sp_port_admin_status_set(struct mlxsw_sp_port *mlxsw_sp_port, bool is_up) { @@ -173,23 +474,6 @@ static int mlxsw_sp_port_admin_status_set(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(paos), paos_pl); } -static int mlxsw_sp_port_oper_status_get(struct mlxsw_sp_port *mlxsw_sp_port, - bool *p_is_up) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - char paos_pl[MLXSW_REG_PAOS_LEN]; - u8 oper_status; - int err; - - mlxsw_reg_paos_pack(paos_pl, mlxsw_sp_port->local_port, 0); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(paos), paos_pl); - if (err) - return err; - oper_status = mlxsw_reg_paos_oper_status_get(paos_pl); - *p_is_up = oper_status == MLXSW_PORT_ADMIN_STATUS_UP ? true : false; - return 0; -} - static int mlxsw_sp_port_dev_addr_set(struct mlxsw_sp_port *mlxsw_sp_port, unsigned char *addr) { @@ -510,6 +794,9 @@ static int mlxsw_sp_port_change_mtu(struct net_device *dev, int mtu) err = mlxsw_sp_port_headroom_set(mlxsw_sp_port, mtu, pause_en); if (err) return err; + err = mlxsw_sp_span_port_mtu_update(mlxsw_sp_port, mtu); + if (err) + goto err_span_port_mtu_update; err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, mtu); if (err) goto err_port_mtu_set; @@ -517,6 +804,8 @@ static int mlxsw_sp_port_change_mtu(struct net_device *dev, int mtu) return 0; err_port_mtu_set: + mlxsw_sp_span_port_mtu_update(mlxsw_sp_port, dev->mtu); +err_span_port_mtu_update: mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu, pause_en); return err; } @@ -793,10 +1082,155 @@ static int mlxsw_sp_port_get_phys_port_name(struct net_device *dev, char *name, return 0; } +static struct mlxsw_sp_port_mall_tc_entry * +mlxsw_sp_port_mirror_entry_find(struct mlxsw_sp_port *port, + unsigned long cookie) { + struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry; + + list_for_each_entry(mall_tc_entry, &port->mall_tc_list, list) + if (mall_tc_entry->cookie == cookie) + return mall_tc_entry; + + return NULL; +} + +static int +mlxsw_sp_port_add_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port, + struct tc_cls_matchall_offload *cls, + const struct tc_action *a, + bool ingress) +{ + struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry; + struct net *net = dev_net(mlxsw_sp_port->dev); + enum mlxsw_sp_span_type span_type; + struct mlxsw_sp_port *to_port; + struct net_device *to_dev; + int ifindex; + int err; + + ifindex = tcf_mirred_ifindex(a); + to_dev = __dev_get_by_index(net, ifindex); + if (!to_dev) { + netdev_err(mlxsw_sp_port->dev, "Could not find requested device\n"); + return -EINVAL; + } + + if (!mlxsw_sp_port_dev_check(to_dev)) { + netdev_err(mlxsw_sp_port->dev, "Cannot mirror to a non-spectrum port"); + return -ENOTSUPP; + } + to_port = netdev_priv(to_dev); + + mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); + if (!mall_tc_entry) + return -ENOMEM; + + mall_tc_entry->cookie = cls->cookie; + mall_tc_entry->type = MLXSW_SP_PORT_MALL_MIRROR; + mall_tc_entry->mirror.to_local_port = to_port->local_port; + mall_tc_entry->mirror.ingress = ingress; + list_add_tail(&mall_tc_entry->list, &mlxsw_sp_port->mall_tc_list); + + span_type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; + err = mlxsw_sp_span_mirror_add(mlxsw_sp_port, to_port, span_type); + if (err) + goto err_mirror_add; + return 0; + +err_mirror_add: + list_del(&mall_tc_entry->list); + kfree(mall_tc_entry); + return err; +} + +static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, + __be16 protocol, + struct tc_cls_matchall_offload *cls, + bool ingress) +{ + struct tcf_exts *exts = cls->exts; + const struct tc_action *a; + int err; + + if (!list_is_singular(&exts->actions)) { + netdev_err(mlxsw_sp_port->dev, "only singular actions are supported\n"); + return -ENOTSUPP; + } + + a = list_first_entry(&exts->actions, struct tc_action, list); + if (is_tcf_mirred_mirror(a) && protocol == htons(ETH_P_ALL)) { + err = mlxsw_sp_port_add_cls_matchall_mirror(mlxsw_sp_port, cls, + a, ingress); + if (err) + return err; + } else { + return -ENOTSUPP; + } + + return 0; +} + +static void mlxsw_sp_port_del_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, + struct tc_cls_matchall_offload *cls) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry; + enum mlxsw_sp_span_type span_type; + struct mlxsw_sp_port *to_port; + + mall_tc_entry = mlxsw_sp_port_mirror_entry_find(mlxsw_sp_port, + cls->cookie); + if (!mall_tc_entry) { + netdev_dbg(mlxsw_sp_port->dev, "tc entry not found on port\n"); + return; + } + + switch (mall_tc_entry->type) { + case MLXSW_SP_PORT_MALL_MIRROR: + to_port = mlxsw_sp->ports[mall_tc_entry->mirror.to_local_port]; + span_type = mall_tc_entry->mirror.ingress ? + MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; + + mlxsw_sp_span_mirror_remove(mlxsw_sp_port, to_port, span_type); + break; + default: + WARN_ON(1); + } + + list_del(&mall_tc_entry->list); + kfree(mall_tc_entry); +} + +static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle, + __be16 proto, struct tc_to_netdev *tc) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + bool ingress = TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS); + + if (tc->type == TC_SETUP_MATCHALL) { + switch (tc->cls_mall->command) { + case TC_CLSMATCHALL_REPLACE: + return mlxsw_sp_port_add_cls_matchall(mlxsw_sp_port, + proto, + tc->cls_mall, + ingress); + case TC_CLSMATCHALL_DESTROY: + mlxsw_sp_port_del_cls_matchall(mlxsw_sp_port, + tc->cls_mall); + return 0; + default: + return -EINVAL; + } + } + + return -ENOTSUPP; +} + static const struct net_device_ops mlxsw_sp_port_netdev_ops = { .ndo_open = mlxsw_sp_port_open, .ndo_stop = mlxsw_sp_port_stop, .ndo_start_xmit = mlxsw_sp_port_xmit, + .ndo_setup_tc = mlxsw_sp_setup_tc, .ndo_set_rx_mode = mlxsw_sp_set_rx_mode, .ndo_set_mac_address = mlxsw_sp_port_set_mac_address, .ndo_change_mtu = mlxsw_sp_port_change_mtu, @@ -899,7 +1333,7 @@ struct mlxsw_sp_port_hw_stats { u64 (*getter)(char *payload); }; -static const struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = { +static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = { { .str = "a_frames_transmitted_ok", .getter = mlxsw_reg_ppcnt_a_frames_transmitted_ok_get, @@ -980,6 +1414,90 @@ static const struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = { #define MLXSW_SP_PORT_HW_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_stats) +static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_prio_stats[] = { + { + .str = "rx_octets_prio", + .getter = mlxsw_reg_ppcnt_rx_octets_get, + }, + { + .str = "rx_frames_prio", + .getter = mlxsw_reg_ppcnt_rx_frames_get, + }, + { + .str = "tx_octets_prio", + .getter = mlxsw_reg_ppcnt_tx_octets_get, + }, + { + .str = "tx_frames_prio", + .getter = mlxsw_reg_ppcnt_tx_frames_get, + }, + { + .str = "rx_pause_prio", + .getter = mlxsw_reg_ppcnt_rx_pause_get, + }, + { + .str = "rx_pause_duration_prio", + .getter = mlxsw_reg_ppcnt_rx_pause_duration_get, + }, + { + .str = "tx_pause_prio", + .getter = mlxsw_reg_ppcnt_tx_pause_get, + }, + { + .str = "tx_pause_duration_prio", + .getter = mlxsw_reg_ppcnt_tx_pause_duration_get, + }, +}; + +#define MLXSW_SP_PORT_HW_PRIO_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_prio_stats) + +static u64 mlxsw_reg_ppcnt_tc_transmit_queue_bytes_get(char *ppcnt_pl) +{ + u64 transmit_queue = mlxsw_reg_ppcnt_tc_transmit_queue_get(ppcnt_pl); + + return MLXSW_SP_CELLS_TO_BYTES(transmit_queue); +} + +static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = { + { + .str = "tc_transmit_queue_tc", + .getter = mlxsw_reg_ppcnt_tc_transmit_queue_bytes_get, + }, + { + .str = "tc_no_buffer_discard_uc_tc", + .getter = mlxsw_reg_ppcnt_tc_no_buffer_discard_uc_get, + }, +}; + +#define MLXSW_SP_PORT_HW_TC_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_tc_stats) + +#define MLXSW_SP_PORT_ETHTOOL_STATS_LEN (MLXSW_SP_PORT_HW_STATS_LEN + \ + (MLXSW_SP_PORT_HW_PRIO_STATS_LEN + \ + MLXSW_SP_PORT_HW_TC_STATS_LEN) * \ + IEEE_8021QAZ_MAX_TCS) + +static void mlxsw_sp_port_get_prio_strings(u8 **p, int prio) +{ + int i; + + for (i = 0; i < MLXSW_SP_PORT_HW_PRIO_STATS_LEN; i++) { + snprintf(*p, ETH_GSTRING_LEN, "%s_%d", + mlxsw_sp_port_hw_prio_stats[i].str, prio); + *p += ETH_GSTRING_LEN; + } +} + +static void mlxsw_sp_port_get_tc_strings(u8 **p, int tc) +{ + int i; + + for (i = 0; i < MLXSW_SP_PORT_HW_TC_STATS_LEN; i++) { + snprintf(*p, ETH_GSTRING_LEN, "%s_%d", + mlxsw_sp_port_hw_tc_stats[i].str, tc); + *p += ETH_GSTRING_LEN; + } +} + static void mlxsw_sp_port_get_strings(struct net_device *dev, u32 stringset, u8 *data) { @@ -993,6 +1511,13 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev, ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + mlxsw_sp_port_get_prio_strings(&p, i); + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + mlxsw_sp_port_get_tc_strings(&p, i); + break; } } @@ -1020,27 +1545,80 @@ static int mlxsw_sp_port_set_phys_id(struct net_device *dev, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mlcr), mlcr_pl); } -static void mlxsw_sp_port_get_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) +static int +mlxsw_sp_get_hw_stats_by_group(struct mlxsw_sp_port_hw_stats **p_hw_stats, + int *p_len, enum mlxsw_reg_ppcnt_grp grp) +{ + switch (grp) { + case MLXSW_REG_PPCNT_IEEE_8023_CNT: + *p_hw_stats = mlxsw_sp_port_hw_stats; + *p_len = MLXSW_SP_PORT_HW_STATS_LEN; + break; + case MLXSW_REG_PPCNT_PRIO_CNT: + *p_hw_stats = mlxsw_sp_port_hw_prio_stats; + *p_len = MLXSW_SP_PORT_HW_PRIO_STATS_LEN; + break; + case MLXSW_REG_PPCNT_TC_CNT: + *p_hw_stats = mlxsw_sp_port_hw_tc_stats; + *p_len = MLXSW_SP_PORT_HW_TC_STATS_LEN; + break; + default: + WARN_ON(1); + return -ENOTSUPP; + } + return 0; +} + +static void __mlxsw_sp_port_get_stats(struct net_device *dev, + enum mlxsw_reg_ppcnt_grp grp, int prio, + u64 *data, int data_index) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_port_hw_stats *hw_stats; char ppcnt_pl[MLXSW_REG_PPCNT_LEN]; - int i; + int i, len; int err; - mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sp_port->local_port, - MLXSW_REG_PPCNT_IEEE_8023_CNT, 0); + err = mlxsw_sp_get_hw_stats_by_group(&hw_stats, &len, grp); + if (err) + return; + mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sp_port->local_port, grp, prio); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ppcnt), ppcnt_pl); - for (i = 0; i < MLXSW_SP_PORT_HW_STATS_LEN; i++) - data[i] = !err ? mlxsw_sp_port_hw_stats[i].getter(ppcnt_pl) : 0; + for (i = 0; i < len; i++) + data[data_index + i] = !err ? hw_stats[i].getter(ppcnt_pl) : 0; +} + +static void mlxsw_sp_port_get_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + int i, data_index = 0; + + /* IEEE 802.3 Counters */ + __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_IEEE_8023_CNT, 0, + data, data_index); + data_index = MLXSW_SP_PORT_HW_STATS_LEN; + + /* Per-Priority Counters */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_PRIO_CNT, i, + data, data_index); + data_index += MLXSW_SP_PORT_HW_PRIO_STATS_LEN; + } + + /* Per-TC Counters */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_TC_CNT, i, + data, data_index); + data_index += MLXSW_SP_PORT_HW_TC_STATS_LEN; + } } static int mlxsw_sp_port_get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: - return MLXSW_SP_PORT_HW_STATS_LEN; + return MLXSW_SP_PORT_ETHTOOL_STATS_LEN; default: return -EOPNOTSUPP; } @@ -1261,7 +1839,8 @@ static int mlxsw_sp_port_get_settings(struct net_device *dev, cmd->supported = mlxsw_sp_from_ptys_supported_port(eth_proto_cap) | mlxsw_sp_from_ptys_supported_link(eth_proto_cap) | - SUPPORTED_Pause | SUPPORTED_Asym_Pause; + SUPPORTED_Pause | SUPPORTED_Asym_Pause | + SUPPORTED_Autoneg; cmd->advertising = mlxsw_sp_from_ptys_advert_link(eth_proto_admin); mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev), eth_proto_oper, cmd); @@ -1320,7 +1899,6 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev, u32 eth_proto_new; u32 eth_proto_cap; u32 eth_proto_admin; - bool is_up; int err; speed = ethtool_cmd_speed(cmd); @@ -1352,12 +1930,7 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev, return err; } - err = mlxsw_sp_port_oper_status_get(mlxsw_sp_port, &is_up); - if (err) { - netdev_err(dev, "Failed to get oper status"); - return err; - } - if (!is_up) + if (!netif_running(dev)) return 0; err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); @@ -1535,6 +2108,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, goto err_port_untagged_vlans_alloc; } INIT_LIST_HEAD(&mlxsw_sp_port->vports_list); + INIT_LIST_HEAD(&mlxsw_sp_port->mall_tc_list); mlxsw_sp_port->pcpu_stats = netdev_alloc_pcpu_stats(struct mlxsw_sp_port_pcpu_stats); @@ -1556,7 +2130,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, netif_carrier_off(dev); dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_LLTX | NETIF_F_SG | - NETIF_F_HW_VLAN_CTAG_FILTER; + NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC; + dev->hw_features |= NETIF_F_HW_TC; /* Each packet needs to have a Tx header (metadata) on top all other * headers. @@ -2288,6 +2863,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_router_init; } + err = mlxsw_sp_span_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); + goto err_span_init; + } + err = mlxsw_sp_ports_create(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n"); @@ -2297,6 +2878,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, return 0; err_ports_create: + mlxsw_sp_span_fini(mlxsw_sp); +err_span_init: mlxsw_sp_router_fini(mlxsw_sp); err_router_init: mlxsw_sp_switchdev_fini(mlxsw_sp); @@ -2317,6 +2900,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) int i; mlxsw_sp_ports_remove(mlxsw_sp); + mlxsw_sp_span_fini(mlxsw_sp); mlxsw_sp_router_fini(mlxsw_sp); mlxsw_sp_switchdev_fini(mlxsw_sp); mlxsw_sp_buffers_fini(mlxsw_sp); @@ -2366,6 +2950,7 @@ static struct mlxsw_config_profile mlxsw_sp_config_profile = { .type = MLXSW_PORT_SWID_TYPE_ETH, } }, + .resource_query_enable = 1, }; static struct mlxsw_driver mlxsw_sp_driver = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index ef4ac89..f69aa37 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -214,6 +214,43 @@ struct mlxsw_sp_vr { struct mlxsw_sp_fib *fib; }; +enum mlxsw_sp_span_type { + MLXSW_SP_SPAN_EGRESS, + MLXSW_SP_SPAN_INGRESS +}; + +struct mlxsw_sp_span_inspected_port { + struct list_head list; + enum mlxsw_sp_span_type type; + u8 local_port; +}; + +struct mlxsw_sp_span_entry { + u8 local_port; + bool used; + struct list_head bound_ports_list; + int ref_count; + int id; +}; + +enum mlxsw_sp_port_mall_action_type { + MLXSW_SP_PORT_MALL_MIRROR, +}; + +struct mlxsw_sp_port_mall_mirror_tc_entry { + u8 to_local_port; + bool ingress; +}; + +struct mlxsw_sp_port_mall_tc_entry { + struct list_head list; + unsigned long cookie; + enum mlxsw_sp_port_mall_action_type type; + union { + struct mlxsw_sp_port_mall_mirror_tc_entry mirror; + }; +}; + struct mlxsw_sp_router { struct mlxsw_sp_lpm_tree lpm_trees[MLXSW_SP_LPM_TREE_COUNT]; struct mlxsw_sp_vr vrs[MLXSW_SP_VIRTUAL_ROUTER_MAX]; @@ -260,6 +297,11 @@ struct mlxsw_sp { struct { DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE); } kvdl; + + struct { + struct mlxsw_sp_span_entry *entries; + int entries_count; + } span; }; static inline struct mlxsw_sp_upper * @@ -316,6 +358,8 @@ struct mlxsw_sp_port { unsigned long *untagged_vlans; /* VLAN interfaces */ struct list_head vports_list; + /* TC handles */ + struct list_head mall_tc_list; }; struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index a3720a0..074cdda 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -194,7 +194,7 @@ static int mlxsw_sp_port_pb_prio_init(struct mlxsw_sp_port *mlxsw_sp_port) mlxsw_reg_pptb_pack(pptb_pl, mlxsw_sp_port->local_port); for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - mlxsw_reg_pptb_prio_to_buff_set(pptb_pl, i, 0); + mlxsw_reg_pptb_prio_to_buff_pack(pptb_pl, i, 0); return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pptb), pptb_pl); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c index 0b32366..01cfb75 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c @@ -103,7 +103,8 @@ static int mlxsw_sp_port_pg_prio_map(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_reg_pptb_pack(pptb_pl, mlxsw_sp_port->local_port); for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - mlxsw_reg_pptb_prio_to_buff_set(pptb_pl, i, prio_tc[i]); + mlxsw_reg_pptb_prio_to_buff_pack(pptb_pl, i, prio_tc[i]); + return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pptb), pptb_pl); } @@ -249,6 +250,7 @@ static int mlxsw_sp_dcbnl_ieee_setets(struct net_device *dev, return err; memcpy(mlxsw_sp_port->dcb.ets, ets, sizeof(*ets)); + mlxsw_sp_port->dcb.ets->ets_cap = IEEE_8021QAZ_MAX_TCS; return 0; } @@ -351,7 +353,8 @@ static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); int err; - if (mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause) { + if ((mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause) && + pfc->pfc_en) { netdev_err(dev, "PAUSE frames already enabled on port\n"); return -EINVAL; } @@ -371,6 +374,7 @@ static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev, } memcpy(mlxsw_sp_port->dcb.pfc, pfc, sizeof(*pfc)); + mlxsw_sp_port->dcb.pfc->pfc_cap = IEEE_8021QAZ_MAX_TCS; return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 25f658b..377daa4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -1541,6 +1541,7 @@ static struct mlxsw_config_profile mlxsw_sx_config_profile = { .type = MLXSW_PORT_SWID_TYPE_ETH, } }, + .resource_query_enable = 0, }; static struct mlxsw_driver mlxsw_sx_driver = { diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 5349284..8377d02 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1908,7 +1908,6 @@ static int ravb_probe(struct platform_device *pdev) /* The Ether-specific entries in the device structure. */ ndev->base_addr = res->start; - ndev->dma = -1; chip_id = (enum ravb_chip_id)of_device_get_match_data(&pdev->dev); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 04cd39f..7bd910c 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2996,7 +2996,6 @@ static int sh_eth_drv_probe(struct platform_device *pdev) if (devno < 0) devno = 0; - ndev->dma = -1; ret = platform_get_irq(pdev, 0); if (ret < 0) goto out_release; diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index f86497c..d300d53 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -1006,8 +1006,10 @@ fail_desc: kfree_skb(priv->rx_head[i].skb); } } + dma_free_coherent(&dev->dev, sizeof(struct cpmac_desc) * size, + priv->desc_ring, priv->dma_ring); + fail_alloc: - kfree(priv->desc_ring); iounmap(priv->regs); fail_remap: @@ -1117,7 +1119,7 @@ static int cpmac_probe(struct platform_device *pdev) mem = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs"); if (!mem) { rc = -ENODEV; - goto out; + goto fail; } dev->irq = platform_get_irq_byname(pdev, "irq"); @@ -1145,7 +1147,7 @@ static int cpmac_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Could not attach to PHY\n"); rc = PTR_ERR(phydev); - goto out; + goto fail; } rc = register_netdev(dev); @@ -1164,7 +1166,6 @@ static int cpmac_probe(struct platform_device *pdev) fail: free_netdev(dev); -out: return rc; } diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 9c82993..36ee7ab 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1541,9 +1541,9 @@ static int axienet_probe(struct platform_device *pdev) /* Find the DMA node, map the DMA registers, and decode the DMA IRQs */ np = of_parse_phandle(pdev->dev.of_node, "axistream-connected", 0); - if (IS_ERR(np)) { + if (!np) { dev_err(&pdev->dev, "could not find DMA node\n"); - ret = PTR_ERR(np); + ret = -ENODEV; goto free_netdev; } ret = of_address_to_resource(np, 0, &dmares); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 8bcd78f..d8b2b49 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -18,6 +18,7 @@ #include <linux/rtnetlink.h> #include <net/genetlink.h> #include <net/sock.h> +#include <net/gro_cells.h> #include <uapi/linux/if_macsec.h> @@ -268,6 +269,7 @@ struct macsec_dev { struct net_device *real_dev; struct pcpu_secy_stats __percpu *stats; struct list_head secys; + struct gro_cells gro_cells; }; /** @@ -508,7 +510,7 @@ static bool macsec_validate_skb(struct sk_buff *skb, u16 icv_len) } #define MACSEC_NEEDED_HEADROOM (macsec_extra_len(true)) -#define MACSEC_NEEDED_TAILROOM MACSEC_MAX_ICV_LEN +#define MACSEC_NEEDED_TAILROOM MACSEC_STD_ICV_LEN static void macsec_fill_iv(unsigned char *iv, sci_t sci, u32 pn) { @@ -879,7 +881,7 @@ static void macsec_decrypt_done(struct crypto_async_request *base, int err) macsec_reset_skb(skb, macsec->secy.netdev); len = skb->len; - ret = netif_rx(skb); + ret = gro_cells_receive(&macsec->gro_cells, skb); if (ret == NET_RX_SUCCESS) count_rx(dev, len); else @@ -1052,6 +1054,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) struct pcpu_rx_sc_stats *rxsc_stats; struct pcpu_secy_stats *secy_stats; bool pulled_sci; + int ret; if (skb_headroom(skb) < ETH_HLEN) goto drop_direct; @@ -1193,12 +1196,17 @@ deliver: if (rx_sa) macsec_rxsa_put(rx_sa); - count_rx(dev, skb->len); + + ret = gro_cells_receive(&macsec->gro_cells, skb); + if (ret == NET_RX_SUCCESS) + count_rx(dev, skb->len); + else + macsec->secy.netdev->stats.rx_dropped++; rcu_read_unlock(); - *pskb = skb; - return RX_HANDLER_ANOTHER; + *pskb = NULL; + return RX_HANDLER_CONSUMED; drop: macsec_rxsa_put(rx_sa); @@ -1218,7 +1226,6 @@ nosci: list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct sk_buff *nskb; - int ret; secy_stats = this_cpu_ptr(macsec->stats); @@ -1263,22 +1270,22 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len) int ret; tfm = crypto_alloc_aead("gcm(aes)", 0, 0); - if (!tfm || IS_ERR(tfm)) - return NULL; + + if (IS_ERR(tfm)) + return tfm; ret = crypto_aead_setkey(tfm, key, key_len); - if (ret < 0) { - crypto_free_aead(tfm); - return NULL; - } + if (ret < 0) + goto fail; ret = crypto_aead_setauthsize(tfm, icv_len); - if (ret < 0) { - crypto_free_aead(tfm); - return NULL; - } + if (ret < 0) + goto fail; return tfm; +fail: + crypto_free_aead(tfm); + return ERR_PTR(ret); } static int init_rx_sa(struct macsec_rx_sa *rx_sa, char *sak, int key_len, @@ -1286,12 +1293,12 @@ static int init_rx_sa(struct macsec_rx_sa *rx_sa, char *sak, int key_len, { rx_sa->stats = alloc_percpu(struct macsec_rx_sa_stats); if (!rx_sa->stats) - return -1; + return -ENOMEM; rx_sa->key.tfm = macsec_alloc_tfm(sak, key_len, icv_len); - if (!rx_sa->key.tfm) { + if (IS_ERR(rx_sa->key.tfm)) { free_percpu(rx_sa->stats); - return -1; + return PTR_ERR(rx_sa->key.tfm); } rx_sa->active = false; @@ -1384,12 +1391,12 @@ static int init_tx_sa(struct macsec_tx_sa *tx_sa, char *sak, int key_len, { tx_sa->stats = alloc_percpu(struct macsec_tx_sa_stats); if (!tx_sa->stats) - return -1; + return -ENOMEM; tx_sa->key.tfm = macsec_alloc_tfm(sak, key_len, icv_len); - if (!tx_sa->key.tfm) { + if (IS_ERR(tx_sa->key.tfm)) { free_percpu(tx_sa->stats); - return -1; + return PTR_ERR(tx_sa->key.tfm); } tx_sa->active = false; @@ -1622,6 +1629,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) unsigned char assoc_num; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; + int err; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; @@ -1658,13 +1666,19 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) } rx_sa = kmalloc(sizeof(*rx_sa), GFP_KERNEL); - if (!rx_sa || init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), - secy->key_len, secy->icv_len)) { - kfree(rx_sa); + if (!rx_sa) { rtnl_unlock(); return -ENOMEM; } + err = init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), + secy->key_len, secy->icv_len); + if (err < 0) { + kfree(rx_sa); + rtnl_unlock(); + return err; + } + if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&rx_sa->lock); rx_sa->next_pn = nla_get_u32(tb_sa[MACSEC_SA_ATTR_PN]); @@ -1770,6 +1784,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) struct macsec_tx_sa *tx_sa; unsigned char assoc_num; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; + int err; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; @@ -1806,13 +1821,19 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) } tx_sa = kmalloc(sizeof(*tx_sa), GFP_KERNEL); - if (!tx_sa || init_tx_sa(tx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), - secy->key_len, secy->icv_len)) { - kfree(tx_sa); + if (!tx_sa) { rtnl_unlock(); return -ENOMEM; } + err = init_tx_sa(tx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), + secy->key_len, secy->icv_len); + if (err < 0) { + kfree(tx_sa); + rtnl_unlock(); + return err; + } + nla_memcpy(tx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN); spin_lock_bh(&tx_sa->lock); @@ -2675,11 +2696,18 @@ static int macsec_dev_init(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; + int err; dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; + err = gro_cells_init(&macsec->gro_cells, dev); + if (err) { + free_percpu(dev->tstats); + return err; + } + dev->features = real_dev->features & MACSEC_FEATURES; dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; @@ -2698,6 +2726,9 @@ static int macsec_dev_init(struct net_device *dev) static void macsec_dev_uninit(struct net_device *dev) { + struct macsec_dev *macsec = macsec_priv(dev); + + gro_cells_destroy(&macsec->gro_cells); free_percpu(dev->tstats); } @@ -2707,8 +2738,9 @@ static netdev_features_t macsec_fix_features(struct net_device *dev, struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; - features &= real_dev->features & MACSEC_FEATURES; - features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; + features &= (real_dev->features & MACSEC_FEATURES) | + NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES; + features |= NETIF_F_LLTX; return features; } @@ -3192,14 +3224,26 @@ static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) if (data[IFLA_MACSEC_CIPHER_SUITE]) csid = nla_get_u64(data[IFLA_MACSEC_CIPHER_SUITE]); - if (data[IFLA_MACSEC_ICV_LEN]) + if (data[IFLA_MACSEC_ICV_LEN]) { icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); + if (icv_len != DEFAULT_ICV_LEN) { + char dummy_key[DEFAULT_SAK_LEN] = { 0 }; + struct crypto_aead *dummy_tfm; + + dummy_tfm = macsec_alloc_tfm(dummy_key, + DEFAULT_SAK_LEN, + icv_len); + if (IS_ERR(dummy_tfm)) + return PTR_ERR(dummy_tfm); + crypto_free_aead(dummy_tfm); + } + } switch (csid) { case MACSEC_DEFAULT_CIPHER_ID: case MACSEC_DEFAULT_CIPHER_ALT: if (icv_len < MACSEC_MIN_ICV_LEN || - icv_len > MACSEC_MAX_ICV_LEN) + icv_len > MACSEC_STD_ICV_LEN) return -EINVAL; break; default: diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 9204d19..a38c0da 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -536,7 +536,7 @@ static void macvtap_sock_destruct(struct sock *sk) struct sk_buff *skb; while ((skb = skb_array_consume(&q->skb_array)) != NULL) - kfree(skb); + kfree_skb(skb); } static int macvtap_open(struct inode *inode, struct file *file) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index ec2c1ee..c2dcf02 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -138,6 +138,21 @@ #define MII_88E1510_GEN_CTRL_REG_1_MODE_SGMII 0x1 /* SGMII to copper */ #define MII_88E1510_GEN_CTRL_REG_1_RESET 0x8000 /* Soft reset */ +#define LPA_FIBER_1000HALF 0x40 +#define LPA_FIBER_1000FULL 0x20 + +#define LPA_PAUSE_FIBER 0x180 +#define LPA_PAUSE_ASYM_FIBER 0x100 + +#define ADVERTISE_FIBER_1000HALF 0x40 +#define ADVERTISE_FIBER_1000FULL 0x20 + +#define ADVERTISE_PAUSE_FIBER 0x180 +#define ADVERTISE_PAUSE_ASYM_FIBER 0x100 + +#define REGISTER_LINK_STATUS 0x400 +#define NB_FIBER_STATS 1 + MODULE_DESCRIPTION("Marvell PHY driver"); MODULE_AUTHOR("Andy Fleming"); MODULE_LICENSE("GPL"); @@ -150,8 +165,9 @@ struct marvell_hw_stat { }; static struct marvell_hw_stat marvell_hw_stats[] = { - { "phy_receive_errors", 0, 21, 16}, + { "phy_receive_errors_copper", 0, 21, 16}, { "phy_idle_errors", 0, 10, 8 }, + { "phy_receive_errors_fiber", 1, 21, 16}, }; struct marvell_priv { @@ -477,15 +493,122 @@ static int m88e1318_config_aneg(struct phy_device *phydev) return m88e1121_config_aneg(phydev); } +/** + * ethtool_adv_to_fiber_adv_t + * @ethadv: the ethtool advertisement settings + * + * A small helper function that translates ethtool advertisement + * settings to phy autonegotiation advertisements for the + * MII_ADV register for fiber link. + */ +static inline u32 ethtool_adv_to_fiber_adv_t(u32 ethadv) +{ + u32 result = 0; + + if (ethadv & ADVERTISED_1000baseT_Half) + result |= ADVERTISE_FIBER_1000HALF; + if (ethadv & ADVERTISED_1000baseT_Full) + result |= ADVERTISE_FIBER_1000FULL; + + if ((ethadv & ADVERTISE_PAUSE_ASYM) && (ethadv & ADVERTISE_PAUSE_CAP)) + result |= LPA_PAUSE_ASYM_FIBER; + else if (ethadv & ADVERTISE_PAUSE_CAP) + result |= (ADVERTISE_PAUSE_FIBER + & (~ADVERTISE_PAUSE_ASYM_FIBER)); + + return result; +} + +/** + * marvell_config_aneg_fiber - restart auto-negotiation or write BMCR + * @phydev: target phy_device struct + * + * Description: If auto-negotiation is enabled, we configure the + * advertising, and then restart auto-negotiation. If it is not + * enabled, then we write the BMCR. Adapted for fiber link in + * some Marvell's devices. + */ +static int marvell_config_aneg_fiber(struct phy_device *phydev) +{ + int changed = 0; + int err; + int adv, oldadv; + u32 advertise; + + if (phydev->autoneg != AUTONEG_ENABLE) + return genphy_setup_forced(phydev); + + /* Only allow advertising what this PHY supports */ + phydev->advertising &= phydev->supported; + advertise = phydev->advertising; + + /* Setup fiber advertisement */ + adv = phy_read(phydev, MII_ADVERTISE); + if (adv < 0) + return adv; + + oldadv = adv; + adv &= ~(ADVERTISE_FIBER_1000HALF | ADVERTISE_FIBER_1000FULL + | LPA_PAUSE_FIBER); + adv |= ethtool_adv_to_fiber_adv_t(advertise); + + if (adv != oldadv) { + err = phy_write(phydev, MII_ADVERTISE, adv); + if (err < 0) + return err; + + changed = 1; + } + + if (changed == 0) { + /* Advertisement hasn't changed, but maybe aneg was never on to + * begin with? Or maybe phy was isolated? + */ + int ctl = phy_read(phydev, MII_BMCR); + + if (ctl < 0) + return ctl; + + if (!(ctl & BMCR_ANENABLE) || (ctl & BMCR_ISOLATE)) + changed = 1; /* do restart aneg */ + } + + /* Only restart aneg if we are advertising something different + * than we were before. + */ + if (changed > 0) + changed = genphy_restart_aneg(phydev); + + return changed; +} + static int m88e1510_config_aneg(struct phy_device *phydev) { int err; + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_COPPER); + if (err < 0) + goto error; + + /* Configure the copper link first */ err = m88e1318_config_aneg(phydev); if (err < 0) - return err; + goto error; - return 0; + /* Then the fiber link */ + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_FIBER); + if (err < 0) + goto error; + + err = marvell_config_aneg_fiber(phydev); + if (err < 0) + goto error; + + return phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_COPPER); + +error: + phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_COPPER); + return err; } static int marvell_config_init(struct phy_device *phydev) @@ -890,26 +1013,79 @@ static int m88e1145_config_init(struct phy_device *phydev) return 0; } -/* marvell_read_status +/** + * fiber_lpa_to_ethtool_lpa_t + * @lpa: value of the MII_LPA register for fiber link + * + * A small helper function that translates MII_LPA + * bits to ethtool LP advertisement settings. + */ +static u32 fiber_lpa_to_ethtool_lpa_t(u32 lpa) +{ + u32 result = 0; + + if (lpa & LPA_FIBER_1000HALF) + result |= ADVERTISED_1000baseT_Half; + if (lpa & LPA_FIBER_1000FULL) + result |= ADVERTISED_1000baseT_Full; + + return result; +} + +/** + * marvell_update_link - update link status in real time in @phydev + * @phydev: target phy_device struct + * + * Description: Update the value in phydev->link to reflect the + * current link value. + */ +static int marvell_update_link(struct phy_device *phydev, int fiber) +{ + int status; + + /* Use the generic register for copper link, or specific + * register for fiber case */ + if (fiber) { + status = phy_read(phydev, MII_M1011_PHY_STATUS); + if (status < 0) + return status; + + if ((status & REGISTER_LINK_STATUS) == 0) + phydev->link = 0; + else + phydev->link = 1; + } else { + return genphy_update_link(phydev); + } + + return 0; +} + +/* marvell_read_status_page * - * Generic status code does not detect Fiber correctly! * Description: * Check the link, then figure out the current state * by comparing what we advertise with what the link partner * advertises. Start by checking the gigabit possibilities, * then move on to 10/100. */ -static int marvell_read_status(struct phy_device *phydev) +static int marvell_read_status_page(struct phy_device *phydev, int page) { int adv; int err; int lpa; int lpagb; int status = 0; + int fiber; - /* Update the link, but return if there + /* Detect and update the link, but return if there * was an error */ - err = genphy_update_link(phydev); + if (page == MII_M1111_FIBER) + fiber = 1; + else + fiber = 0; + + err = marvell_update_link(phydev, fiber); if (err) return err; @@ -930,9 +1106,6 @@ static int marvell_read_status(struct phy_device *phydev) if (adv < 0) return adv; - phydev->lp_advertising = mii_stat1000_to_ethtool_lpa_t(lpagb) | - mii_lpa_to_ethtool_lpa_t(lpa); - lpa &= adv; if (status & MII_M1011_PHY_STATUS_FULLDUPLEX) @@ -957,9 +1130,30 @@ static int marvell_read_status(struct phy_device *phydev) break; } - if (phydev->duplex == DUPLEX_FULL) { - phydev->pause = lpa & LPA_PAUSE_CAP ? 1 : 0; - phydev->asym_pause = lpa & LPA_PAUSE_ASYM ? 1 : 0; + if (!fiber) { + phydev->lp_advertising = mii_stat1000_to_ethtool_lpa_t(lpagb) | + mii_lpa_to_ethtool_lpa_t(lpa); + + if (phydev->duplex == DUPLEX_FULL) { + phydev->pause = lpa & LPA_PAUSE_CAP ? 1 : 0; + phydev->asym_pause = lpa & LPA_PAUSE_ASYM ? 1 : 0; + } + } else { + /* The fiber link is only 1000M capable */ + phydev->lp_advertising = fiber_lpa_to_ethtool_lpa_t(lpa); + + if (phydev->duplex == DUPLEX_FULL) { + if (!(lpa & LPA_PAUSE_FIBER)) { + phydev->pause = 0; + phydev->asym_pause = 0; + } else if ((lpa & LPA_PAUSE_ASYM_FIBER)) { + phydev->pause = 1; + phydev->asym_pause = 1; + } else { + phydev->pause = 1; + phydev->asym_pause = 0; + } + } } } else { int bmcr = phy_read(phydev, MII_BMCR); @@ -986,6 +1180,119 @@ static int marvell_read_status(struct phy_device *phydev) return 0; } +/* marvell_read_status + * + * Some Marvell's phys have two modes: fiber and copper. + * Both need status checked. + * Description: + * First, check the fiber link and status. + * If the fiber link is down, check the copper link and status which + * will be the default value if both link are down. + */ +static int marvell_read_status(struct phy_device *phydev) +{ + int err; + + /* Check the fiber mode first */ + if (phydev->supported & SUPPORTED_FIBRE) { + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_FIBER); + if (err < 0) + goto error; + + err = marvell_read_status_page(phydev, MII_M1111_FIBER); + if (err < 0) + goto error; + + /* If the fiber link is up, it is the selected and used link. + * In this case, we need to stay in the fiber page. + * Please to be careful about that, avoid to restore Copper page + * in other functions which could break the behaviour + * for some fiber phy like 88E1512. + * */ + if (phydev->link) + return 0; + + /* If fiber link is down, check and save copper mode state */ + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_COPPER); + if (err < 0) + goto error; + } + + return marvell_read_status_page(phydev, MII_M1111_COPPER); + +error: + phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_COPPER); + return err; +} + +/* marvell_suspend + * + * Some Marvell's phys have two modes: fiber and copper. + * Both need to be suspended + */ +static int marvell_suspend(struct phy_device *phydev) +{ + int err; + + /* Suspend the fiber mode first */ + if (!(phydev->supported & SUPPORTED_FIBRE)) { + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_FIBER); + if (err < 0) + goto error; + + /* With the page set, use the generic suspend */ + err = genphy_suspend(phydev); + if (err < 0) + goto error; + + /* Then, the copper link */ + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_COPPER); + if (err < 0) + goto error; + } + + /* With the page set, use the generic suspend */ + return genphy_suspend(phydev); + +error: + phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_COPPER); + return err; +} + +/* marvell_resume + * + * Some Marvell's phys have two modes: fiber and copper. + * Both need to be resumed + */ +static int marvell_resume(struct phy_device *phydev) +{ + int err; + + /* Resume the fiber mode first */ + if (!(phydev->supported & SUPPORTED_FIBRE)) { + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_FIBER); + if (err < 0) + goto error; + + /* With the page set, use the generic resume */ + err = genphy_resume(phydev); + if (err < 0) + goto error; + + /* Then, the copper link */ + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_COPPER); + if (err < 0) + goto error; + } + + /* With the page set, use the generic resume */ + return genphy_resume(phydev); + +error: + phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_COPPER); + return err; +} + static int marvell_aneg_done(struct phy_device *phydev) { int retval = phy_read(phydev, MII_M1011_PHY_STATUS); @@ -1107,7 +1414,10 @@ static int m88e1318_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *w static int marvell_get_sset_count(struct phy_device *phydev) { - return ARRAY_SIZE(marvell_hw_stats); + if (phydev->supported & SUPPORTED_FIBRE) + return ARRAY_SIZE(marvell_hw_stats); + else + return ARRAY_SIZE(marvell_hw_stats) - NB_FIBER_STATS; } static void marvell_get_strings(struct phy_device *phydev, u8 *data) @@ -1361,7 +1671,7 @@ static struct phy_driver marvell_drivers[] = { .phy_id = MARVELL_PHY_ID_88E1510, .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "Marvell 88E1510", - .features = PHY_GBIT_FEATURES, + .features = PHY_GBIT_FEATURES | SUPPORTED_FIBRE, .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, .config_init = &m88e1510_config_init, @@ -1370,8 +1680,8 @@ static struct phy_driver marvell_drivers[] = { .ack_interrupt = &marvell_ack_interrupt, .config_intr = &marvell_config_intr, .did_interrupt = &m88e1121_did_interrupt, - .resume = &genphy_resume, - .suspend = &genphy_suspend, + .resume = &marvell_resume, + .suspend = &marvell_suspend, .get_sset_count = marvell_get_sset_count, .get_strings = marvell_get_strings, .get_stats = marvell_get_stats, diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 17953ab..f226db4 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -2600,8 +2600,6 @@ ppp_unregister_channel(struct ppp_channel *chan) spin_lock_bh(&pn->all_channels_lock); list_del(&pch->list); spin_unlock_bh(&pn->all_channels_lock); - put_net(pch->chan_net); - pch->chan_net = NULL; pch->file.dead = 1; wake_up_interruptible(&pch->file.rwait); @@ -3135,6 +3133,9 @@ ppp_disconnect_channel(struct channel *pch) */ static void ppp_destroy_channel(struct channel *pch) { + put_net(pch->chan_net); + pch->chan_net = NULL; + atomic_dec(&channel_count); if (!pch->file.dead) { diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 7cba2c3..c47ec0a 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -388,6 +388,12 @@ void usbnet_cdc_status(struct usbnet *dev, struct urb *urb) case USB_CDC_NOTIFY_NETWORK_CONNECTION: netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n", event->wValue ? "on" : "off"); + + /* Work-around for devices with broken off-notifications */ + if (event->wValue && + !test_bit(__LINK_STATE_NOCARRIER, &dev->net->state)) + usbnet_link_change(dev, 0, 0); + usbnet_link_change(dev, !!event->wValue, 0); break; case USB_CDC_NOTIFY_SPEED_CHANGE: /* tx/rx rates */ @@ -432,6 +438,34 @@ int usbnet_cdc_bind(struct usbnet *dev, struct usb_interface *intf) } EXPORT_SYMBOL_GPL(usbnet_cdc_bind); +static int usbnet_cdc_zte_bind(struct usbnet *dev, struct usb_interface *intf) +{ + int status = usbnet_cdc_bind(dev, intf); + + if (!status && (dev->net->dev_addr[0] & 0x02)) + eth_hw_addr_random(dev->net); + + return status; +} + +/* Make sure packets have correct destination MAC address + * + * A firmware bug observed on some devices (ZTE MF823/831/910) is that the + * device sends packets with a static, bogus, random MAC address (event if + * device MAC address has been updated). Always set MAC address to that of the + * device. + */ +static int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb) +{ + if (skb->len < ETH_HLEN || !(skb->data[0] & 0x02)) + return 1; + + skb_reset_mac_header(skb); + ether_addr_copy(eth_hdr(skb)->h_dest, dev->net->dev_addr); + + return 1; +} + static const struct driver_info cdc_info = { .description = "CDC Ethernet Device", .flags = FLAG_ETHER | FLAG_POINTTOPOINT, @@ -442,6 +476,17 @@ static const struct driver_info cdc_info = { .manage_power = usbnet_manage_power, }; +static const struct driver_info zte_cdc_info = { + .description = "ZTE CDC Ethernet Device", + .flags = FLAG_ETHER | FLAG_POINTTOPOINT, + .bind = usbnet_cdc_zte_bind, + .unbind = usbnet_cdc_unbind, + .status = usbnet_cdc_status, + .set_rx_mode = usbnet_cdc_update_filter, + .manage_power = usbnet_manage_power, + .rx_fixup = usbnet_cdc_zte_rx_fixup, +}; + static const struct driver_info wwan_info = { .description = "Mobile Broadband Network Device", .flags = FLAG_WWAN, @@ -707,6 +752,12 @@ static const struct usb_device_id products[] = { USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (kernel_ulong_t)&wwan_info, }, { + /* ZTE modules */ + USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&zte_cdc_info, +}, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long) &cdc_info, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 168a8e2..f41a8ad 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -26,6 +26,7 @@ #include <linux/mdio.h> #include <linux/usb/cdc.h> #include <linux/suspend.h> +#include <linux/acpi.h> /* Information for net-next */ #define NETNEXT_VERSION "08" @@ -460,6 +461,11 @@ /* SRAM_IMPEDANCE */ #define RX_DRIVING_MASK 0x6000 +/* MAC PASSTHRU */ +#define AD_MASK 0xfee0 +#define EFUSE 0xcfdb +#define PASS_THRU_MASK 0x1 + enum rtl_register_content { _1000bps = 0x10, _100bps = 0x08, @@ -1040,6 +1046,65 @@ out1: return ret; } +/* Devices containing RTL8153-AD can support a persistent + * host system provided MAC address. + * Examples of this are Dell TB15 and Dell WD15 docks + */ +static int vendor_mac_passthru_addr_read(struct r8152 *tp, struct sockaddr *sa) +{ + acpi_status status; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object *obj; + int ret = -EINVAL; + u32 ocp_data; + unsigned char buf[6]; + + /* test for -AD variant of RTL8153 */ + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0); + if ((ocp_data & AD_MASK) != 0x1000) + return -ENODEV; + + /* test for MAC address pass-through bit */ + ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, EFUSE); + if ((ocp_data & PASS_THRU_MASK) != 1) + return -ENODEV; + + /* returns _AUXMAC_#AABBCCDDEEFF# */ + status = acpi_evaluate_object(NULL, "\\_SB.AMAC", NULL, &buffer); + obj = (union acpi_object *)buffer.pointer; + if (!ACPI_SUCCESS(status)) + return -ENODEV; + if (obj->type != ACPI_TYPE_BUFFER || obj->string.length != 0x17) { + netif_warn(tp, probe, tp->netdev, + "Invalid buffer when reading pass-thru MAC addr: " + "(%d, %d)\n", + obj->type, obj->string.length); + goto amacout; + } + if (strncmp(obj->string.pointer, "_AUXMAC_#", 9) != 0 || + strncmp(obj->string.pointer + 0x15, "#", 1) != 0) { + netif_warn(tp, probe, tp->netdev, + "Invalid header when reading pass-thru MAC addr\n"); + goto amacout; + } + ret = hex2bin(buf, obj->string.pointer + 9, 6); + if (!(ret == 0 && is_valid_ether_addr(buf))) { + netif_warn(tp, probe, tp->netdev, + "Invalid MAC when reading pass-thru MAC addr: " + "%d, %pM\n", ret, buf); + ret = -EINVAL; + goto amacout; + } + memcpy(sa->sa_data, buf, 6); + ether_addr_copy(tp->netdev->dev_addr, sa->sa_data); + netif_info(tp, probe, tp->netdev, + "Using pass-thru MAC addr %pM\n", sa->sa_data); + +amacout: + kfree(obj); + return ret; +} + static int set_ethernet_addr(struct r8152 *tp) { struct net_device *dev = tp->netdev; @@ -1048,8 +1113,15 @@ static int set_ethernet_addr(struct r8152 *tp) if (tp->version == RTL_VER_01) ret = pla_ocp_read(tp, PLA_IDR, 8, sa.sa_data); - else - ret = pla_ocp_read(tp, PLA_BACKUP, 8, sa.sa_data); + else { + /* if this is not an RTL8153-AD, no eFuse mac pass thru set, + * or system doesn't provide valid _SB.AMAC this will be + * be expected to non-zero + */ + ret = vendor_mac_passthru_addr_read(tp, &sa); + if (ret < 0) + ret = pla_ocp_read(tp, PLA_BACKUP, 8, sa.sa_data); + } if (ret < 0) { netif_err(tp, probe, dev, "Get ether addr fail\n"); @@ -2300,10 +2372,6 @@ static u32 __rtl_get_wol(struct r8152 *tp) u32 ocp_data; u32 wolopts = 0; - ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG5); - if (!(ocp_data & LAN_WAKE_EN)) - return 0; - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34); if (ocp_data & LINK_ON_WAKE_EN) wolopts |= WAKE_PHY; @@ -2336,15 +2404,13 @@ static void __rtl_set_wol(struct r8152 *tp, u32 wolopts) ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG34, ocp_data); ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG5); - ocp_data &= ~(UWF_EN | BWF_EN | MWF_EN | LAN_WAKE_EN); + ocp_data &= ~(UWF_EN | BWF_EN | MWF_EN); if (wolopts & WAKE_UCAST) ocp_data |= UWF_EN; if (wolopts & WAKE_BCAST) ocp_data |= BWF_EN; if (wolopts & WAKE_MCAST) ocp_data |= MWF_EN; - if (wolopts & WAKE_ANY) - ocp_data |= LAN_WAKE_EN; ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG5, ocp_data); ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML); @@ -4361,3 +4427,4 @@ module_usb_driver(rtl8152_driver); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); +MODULE_VERSION(DRIVER_VERSION); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 1dd08d4..1b5f531 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -144,8 +144,10 @@ struct virtnet_info { /* Control VQ buffers: protected by the rtnl lock */ struct virtio_net_ctrl_hdr ctrl_hdr; virtio_net_ctrl_ack ctrl_status; + struct virtio_net_ctrl_mq ctrl_mq; u8 ctrl_promisc; u8 ctrl_allmulti; + u16 ctrl_vid; /* Ethtool settings */ u8 duplex; @@ -1058,14 +1060,13 @@ static void virtnet_ack_link_announce(struct virtnet_info *vi) static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) { struct scatterlist sg; - struct virtio_net_ctrl_mq s; struct net_device *dev = vi->dev; if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ)) return 0; - s.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs); - sg_init_one(&sg, &s, sizeof(s)); + vi->ctrl_mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs); + sg_init_one(&sg, &vi->ctrl_mq, sizeof(vi->ctrl_mq)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ, VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) { @@ -1172,7 +1173,8 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev, struct virtnet_info *vi = netdev_priv(dev); struct scatterlist sg; - sg_init_one(&sg, &vid, sizeof(vid)); + vi->ctrl_vid = vid; + sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, VIRTIO_NET_CTRL_VLAN_ADD, &sg)) @@ -1186,7 +1188,8 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev, struct virtnet_info *vi = netdev_priv(dev); struct scatterlist sg; - sg_init_one(&sg, &vid, sizeof(vid)); + vi->ctrl_vid = vid; + sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, VIRTIO_NET_CTRL_VLAN_DEL, &sg)) diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index b3861bf..2fc50ec 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -1168,22 +1168,10 @@ static struct platform_driver ucc_hdlc_driver = { .probe = ucc_hdlc_probe, .remove = ucc_hdlc_remove, .driver = { - .owner = THIS_MODULE, .name = DRV_NAME, .pm = HDLC_PM_OPS, .of_match_table = fsl_ucc_hdlc_of_match, }, }; -static int __init ucc_hdlc_init(void) -{ - return platform_driver_register(&ucc_hdlc_driver); -} - -static void __exit ucc_hdlc_exit(void) -{ - platform_driver_unregister(&ucc_hdlc_driver); -} - -module_init(ucc_hdlc_init); -module_exit(ucc_hdlc_exit); +module_platform_driver(ucc_hdlc_driver); diff --git a/drivers/nfc/Kconfig b/drivers/nfc/Kconfig index ea8321a..9d23692 100644 --- a/drivers/nfc/Kconfig +++ b/drivers/nfc/Kconfig @@ -40,6 +40,7 @@ config NFC_MEI_PHY config NFC_SIM tristate "NFC hardware simulator driver" + depends on NFC_DIGITAL help This driver declares two virtual NFC devices supporting NFC-DEP protocol. An LLCP connection can be established between them and diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index e44a7a2..7c1eaea 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -345,7 +345,7 @@ static void fdp_nci_release_firmware(struct nci_dev *ndev) if (info->ram_patch) { release_firmware(info->ram_patch); - info->otp_patch = NULL; + info->ram_patch = NULL; } } @@ -353,7 +353,7 @@ static int fdp_nci_patch_otp(struct nci_dev *ndev) { struct fdp_nci_info *info = nci_get_drvdata(ndev); struct device *dev = &info->phy->i2c_dev->dev; - u8 conn_id; + int conn_id; int r = 0; if (info->otp_version >= info->otp_patch_version) @@ -424,7 +424,7 @@ static int fdp_nci_patch_ram(struct nci_dev *ndev) { struct fdp_nci_info *info = nci_get_drvdata(ndev); struct device *dev = &info->phy->i2c_dev->dev; - u8 conn_id; + int conn_id; int r = 0; if (info->ram_version >= info->ram_patch_version) diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c index 93aaca5..a466e79 100644 --- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -16,525 +16,492 @@ #include <linux/device.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/ctype.h> +#include <linux/debugfs.h> #include <linux/nfc.h> #include <net/nfc/nfc.h> +#include <net/nfc/digital.h> -#define DEV_ERR(_dev, fmt, args...) nfc_err(&_dev->nfc_dev->dev, \ - "%s: " fmt, __func__, ## args) +#define NFCSIM_ERR(d, fmt, args...) nfc_err(&d->nfc_digital_dev->nfc_dev->dev, \ + "%s: " fmt, __func__, ## args) -#define DEV_DBG(_dev, fmt, args...) dev_dbg(&_dev->nfc_dev->dev, \ - "%s: " fmt, __func__, ## args) +#define NFCSIM_DBG(d, fmt, args...) dev_dbg(&d->nfc_digital_dev->nfc_dev->dev, \ + "%s: " fmt, __func__, ## args) -#define NFCSIM_VERSION "0.1" +#define NFCSIM_VERSION "0.2" -#define NFCSIM_POLL_NONE 0 -#define NFCSIM_POLL_INITIATOR 1 -#define NFCSIM_POLL_TARGET 2 -#define NFCSIM_POLL_DUAL (NFCSIM_POLL_INITIATOR | NFCSIM_POLL_TARGET) +#define NFCSIM_MODE_NONE 0 +#define NFCSIM_MODE_INITIATOR 1 +#define NFCSIM_MODE_TARGET 2 -#define RX_DEFAULT_DELAY 5 +#define NFCSIM_CAPABILITIES (NFC_DIGITAL_DRV_CAPS_IN_CRC | \ + NFC_DIGITAL_DRV_CAPS_TG_CRC) struct nfcsim { - struct nfc_dev *nfc_dev; + struct nfc_digital_dev *nfc_digital_dev; - struct mutex lock; + struct work_struct recv_work; + struct delayed_work send_work; - struct delayed_work recv_work; + struct nfcsim_link *link_in; + struct nfcsim_link *link_out; - struct sk_buff *clone_skb; + bool up; + u8 mode; + u8 rf_tech; - struct delayed_work poll_work; - u8 polling_mode; - u8 curr_polling_mode; + u16 recv_timeout; - u8 shutting_down; + nfc_digital_cmd_complete_t cb; + void *arg; - u8 up; + u8 dropframe; +}; - u8 initiator; +struct nfcsim_link { + struct mutex lock; - u32 rx_delay; + u8 rf_tech; + u8 mode; - data_exchange_cb_t cb; - void *cb_context; + u8 shutdown; - struct nfcsim *peer_dev; + struct sk_buff *skb; + wait_queue_head_t recv_wait; + u8 cond; }; -static struct nfcsim *dev0; -static struct nfcsim *dev1; - -static struct workqueue_struct *wq; - -static void nfcsim_cleanup_dev(struct nfcsim *dev, u8 shutdown) +static struct nfcsim_link *nfcsim_link_new(void) { - DEV_DBG(dev, "shutdown=%d\n", shutdown); + struct nfcsim_link *link; - mutex_lock(&dev->lock); + link = kzalloc(sizeof(struct nfcsim_link), GFP_KERNEL); + if (!link) + return NULL; - dev->polling_mode = NFCSIM_POLL_NONE; - dev->shutting_down = shutdown; - dev->cb = NULL; - dev_kfree_skb(dev->clone_skb); - dev->clone_skb = NULL; + mutex_init(&link->lock); + init_waitqueue_head(&link->recv_wait); - mutex_unlock(&dev->lock); - - cancel_delayed_work_sync(&dev->poll_work); - cancel_delayed_work_sync(&dev->recv_work); + return link; } -static int nfcsim_target_found(struct nfcsim *dev) +static void nfcsim_link_free(struct nfcsim_link *link) { - struct nfc_target nfc_tgt; + dev_kfree_skb(link->skb); + kfree(link); +} - DEV_DBG(dev, "\n"); +static void nfcsim_link_recv_wake(struct nfcsim_link *link) +{ + link->cond = 1; + wake_up_interruptible(&link->recv_wait); +} - memset(&nfc_tgt, 0, sizeof(struct nfc_target)); +static void nfcsim_link_set_skb(struct nfcsim_link *link, struct sk_buff *skb, + u8 rf_tech, u8 mode) +{ + mutex_lock(&link->lock); - nfc_tgt.supported_protocols = NFC_PROTO_NFC_DEP_MASK; - nfc_targets_found(dev->nfc_dev, &nfc_tgt, 1); + dev_kfree_skb(link->skb); + link->skb = skb; + link->rf_tech = rf_tech; + link->mode = mode; - return 0; + mutex_unlock(&link->lock); } -static int nfcsim_dev_up(struct nfc_dev *nfc_dev) +static void nfcsim_link_recv_cancel(struct nfcsim_link *link) { - struct nfcsim *dev = nfc_get_drvdata(nfc_dev); + mutex_lock(&link->lock); - DEV_DBG(dev, "\n"); + link->mode = NFCSIM_MODE_NONE; - mutex_lock(&dev->lock); + mutex_unlock(&link->lock); - dev->up = 1; - - mutex_unlock(&dev->lock); - - return 0; + nfcsim_link_recv_wake(link); } -static int nfcsim_dev_down(struct nfc_dev *nfc_dev) +static void nfcsim_link_shutdown(struct nfcsim_link *link) { - struct nfcsim *dev = nfc_get_drvdata(nfc_dev); - - DEV_DBG(dev, "\n"); + mutex_lock(&link->lock); - mutex_lock(&dev->lock); + link->shutdown = 1; + link->mode = NFCSIM_MODE_NONE; - dev->up = 0; + mutex_unlock(&link->lock); - mutex_unlock(&dev->lock); - - return 0; + nfcsim_link_recv_wake(link); } -static int nfcsim_dep_link_up(struct nfc_dev *nfc_dev, - struct nfc_target *target, - u8 comm_mode, u8 *gb, size_t gb_len) +static struct sk_buff *nfcsim_link_recv_skb(struct nfcsim_link *link, + int timeout, u8 rf_tech, u8 mode) { int rc; - struct nfcsim *dev = nfc_get_drvdata(nfc_dev); - struct nfcsim *peer = dev->peer_dev; - u8 *remote_gb; - size_t remote_gb_len; + struct sk_buff *skb; - DEV_DBG(dev, "target_idx: %d, comm_mode: %d\n", target->idx, comm_mode); + rc = wait_event_interruptible_timeout(link->recv_wait, + link->cond, + msecs_to_jiffies(timeout)); - mutex_lock(&peer->lock); + mutex_lock(&link->lock); - nfc_tm_activated(peer->nfc_dev, NFC_PROTO_NFC_DEP_MASK, - NFC_COMM_ACTIVE, gb, gb_len); + skb = link->skb; + link->skb = NULL; - remote_gb = nfc_get_local_general_bytes(peer->nfc_dev, &remote_gb_len); - if (!remote_gb) { - DEV_ERR(peer, "Can't get remote general bytes\n"); + if (!rc) { + rc = -ETIMEDOUT; + goto done; + } - mutex_unlock(&peer->lock); - return -EINVAL; + if (!skb || link->rf_tech != rf_tech || link->mode == mode) { + rc = -EINVAL; + goto done; } - mutex_unlock(&peer->lock); + if (link->shutdown) { + rc = -ENODEV; + goto done; + } - mutex_lock(&dev->lock); +done: + mutex_unlock(&link->lock); - rc = nfc_set_remote_general_bytes(nfc_dev, remote_gb, remote_gb_len); - if (rc) { - DEV_ERR(dev, "Can't set remote general bytes\n"); - mutex_unlock(&dev->lock); - return rc; + if (rc < 0) { + dev_kfree_skb(skb); + skb = ERR_PTR(rc); } - rc = nfc_dep_link_is_up(nfc_dev, target->idx, NFC_COMM_ACTIVE, - NFC_RF_INITIATOR); - - mutex_unlock(&dev->lock); + link->cond = 0; - return rc; + return skb; } -static int nfcsim_dep_link_down(struct nfc_dev *nfc_dev) +static void nfcsim_send_wq(struct work_struct *work) { - struct nfcsim *dev = nfc_get_drvdata(nfc_dev); + struct nfcsim *dev = container_of(work, struct nfcsim, send_work.work); - DEV_DBG(dev, "\n"); - - nfcsim_cleanup_dev(dev, 0); - - return 0; + /* + * To effectively send data, the device just wake up its link_out which + * is the link_in of the peer device. The exchanged skb has already been + * stored in the dev->link_out through nfcsim_link_set_skb(). + */ + nfcsim_link_recv_wake(dev->link_out); } -static int nfcsim_start_poll(struct nfc_dev *nfc_dev, - u32 im_protocols, u32 tm_protocols) +static void nfcsim_recv_wq(struct work_struct *work) { - struct nfcsim *dev = nfc_get_drvdata(nfc_dev); - int rc; - - mutex_lock(&dev->lock); + struct nfcsim *dev = container_of(work, struct nfcsim, recv_work); + struct sk_buff *skb; - if (dev->polling_mode != NFCSIM_POLL_NONE) { - DEV_ERR(dev, "Already in polling mode\n"); - rc = -EBUSY; - goto exit; - } + skb = nfcsim_link_recv_skb(dev->link_in, dev->recv_timeout, + dev->rf_tech, dev->mode); - if (im_protocols & NFC_PROTO_NFC_DEP_MASK) - dev->polling_mode |= NFCSIM_POLL_INITIATOR; + if (!dev->up) { + NFCSIM_ERR(dev, "Device is down\n"); - if (tm_protocols & NFC_PROTO_NFC_DEP_MASK) - dev->polling_mode |= NFCSIM_POLL_TARGET; + if (!IS_ERR(skb)) + dev_kfree_skb(skb); - if (dev->polling_mode == NFCSIM_POLL_NONE) { - DEV_ERR(dev, "Unsupported polling mode\n"); - rc = -EINVAL; - goto exit; + skb = ERR_PTR(-ENODEV); } - dev->initiator = 0; - dev->curr_polling_mode = NFCSIM_POLL_NONE; + dev->cb(dev->nfc_digital_dev, dev->arg, skb); +} - queue_delayed_work(wq, &dev->poll_work, 0); +static int nfcsim_send(struct nfc_digital_dev *ddev, struct sk_buff *skb, + u16 timeout, nfc_digital_cmd_complete_t cb, void *arg) +{ + struct nfcsim *dev = nfc_digital_get_drvdata(ddev); + u8 delay; - DEV_DBG(dev, "Start polling: im: 0x%X, tm: 0x%X\n", im_protocols, - tm_protocols); + if (!dev->up) { + NFCSIM_ERR(dev, "Device is down\n"); + return -ENODEV; + } - rc = 0; -exit: - mutex_unlock(&dev->lock); + dev->recv_timeout = timeout; + dev->cb = cb; + dev->arg = arg; - return rc; -} + schedule_work(&dev->recv_work); -static void nfcsim_stop_poll(struct nfc_dev *nfc_dev) -{ - struct nfcsim *dev = nfc_get_drvdata(nfc_dev); + if (dev->dropframe) { + NFCSIM_DBG(dev, "dropping frame (out of %d)\n", dev->dropframe); + dev_kfree_skb(skb); + dev->dropframe--; - DEV_DBG(dev, "Stop poll\n"); + return 0; + } - mutex_lock(&dev->lock); + if (skb) { + nfcsim_link_set_skb(dev->link_out, skb, dev->rf_tech, + dev->mode); - dev->polling_mode = NFCSIM_POLL_NONE; + /* Add random delay (between 3 and 10 ms) before sending data */ + get_random_bytes(&delay, 1); + delay = 3 + (delay & 0x07); - mutex_unlock(&dev->lock); + schedule_delayed_work(&dev->send_work, msecs_to_jiffies(delay)); + } - cancel_delayed_work_sync(&dev->poll_work); + return 0; } -static int nfcsim_activate_target(struct nfc_dev *nfc_dev, - struct nfc_target *target, u32 protocol) +static void nfcsim_abort_cmd(struct nfc_digital_dev *ddev) { - struct nfcsim *dev = nfc_get_drvdata(nfc_dev); - - DEV_DBG(dev, "\n"); + struct nfcsim *dev = nfc_digital_get_drvdata(ddev); - return -ENOTSUPP; + nfcsim_link_recv_cancel(dev->link_in); } -static void nfcsim_deactivate_target(struct nfc_dev *nfc_dev, - struct nfc_target *target, u8 mode) +static int nfcsim_switch_rf(struct nfc_digital_dev *ddev, bool on) { - struct nfcsim *dev = nfc_get_drvdata(nfc_dev); + struct nfcsim *dev = nfc_digital_get_drvdata(ddev); + + dev->up = on; - DEV_DBG(dev, "\n"); + return 0; } -static void nfcsim_wq_recv(struct work_struct *work) +static int nfcsim_in_configure_hw(struct nfc_digital_dev *ddev, + int type, int param) { - struct nfcsim *dev = container_of(work, struct nfcsim, - recv_work.work); + struct nfcsim *dev = nfc_digital_get_drvdata(ddev); - mutex_lock(&dev->lock); + switch (type) { + case NFC_DIGITAL_CONFIG_RF_TECH: + dev->up = true; + dev->mode = NFCSIM_MODE_INITIATOR; + dev->rf_tech = param; + break; - if (dev->shutting_down || !dev->up || !dev->clone_skb) { - dev_kfree_skb(dev->clone_skb); - goto exit; - } + case NFC_DIGITAL_CONFIG_FRAMING: + break; - if (dev->initiator) { - if (!dev->cb) { - DEV_ERR(dev, "Null recv callback\n"); - dev_kfree_skb(dev->clone_skb); - goto exit; - } - - dev->cb(dev->cb_context, dev->clone_skb, 0); - dev->cb = NULL; - } else { - nfc_tm_data_received(dev->nfc_dev, dev->clone_skb); + default: + NFCSIM_ERR(dev, "Invalid configuration type: %d\n", type); + return -EINVAL; } -exit: - dev->clone_skb = NULL; + return 0; +} - mutex_unlock(&dev->lock); +static int nfcsim_in_send_cmd(struct nfc_digital_dev *ddev, + struct sk_buff *skb, u16 timeout, + nfc_digital_cmd_complete_t cb, void *arg) +{ + return nfcsim_send(ddev, skb, timeout, cb, arg); } -static int nfcsim_tx(struct nfc_dev *nfc_dev, struct nfc_target *target, - struct sk_buff *skb, data_exchange_cb_t cb, - void *cb_context) +static int nfcsim_tg_configure_hw(struct nfc_digital_dev *ddev, + int type, int param) { - struct nfcsim *dev = nfc_get_drvdata(nfc_dev); - struct nfcsim *peer = dev->peer_dev; - int err; + struct nfcsim *dev = nfc_digital_get_drvdata(ddev); - mutex_lock(&dev->lock); + switch (type) { + case NFC_DIGITAL_CONFIG_RF_TECH: + dev->up = true; + dev->mode = NFCSIM_MODE_TARGET; + dev->rf_tech = param; + break; - if (dev->shutting_down || !dev->up) { - mutex_unlock(&dev->lock); - err = -ENODEV; - goto exit; + case NFC_DIGITAL_CONFIG_FRAMING: + break; + + default: + NFCSIM_ERR(dev, "Invalid configuration type: %d\n", type); + return -EINVAL; } - dev->cb = cb; - dev->cb_context = cb_context; + return 0; +} - mutex_unlock(&dev->lock); +static int nfcsim_tg_send_cmd(struct nfc_digital_dev *ddev, + struct sk_buff *skb, u16 timeout, + nfc_digital_cmd_complete_t cb, void *arg) +{ + return nfcsim_send(ddev, skb, timeout, cb, arg); +} - mutex_lock(&peer->lock); +static int nfcsim_tg_listen(struct nfc_digital_dev *ddev, u16 timeout, + nfc_digital_cmd_complete_t cb, void *arg) +{ + return nfcsim_send(ddev, NULL, timeout, cb, arg); +} - peer->clone_skb = skb_clone(skb, GFP_KERNEL); +static struct nfc_digital_ops nfcsim_digital_ops = { + .in_configure_hw = nfcsim_in_configure_hw, + .in_send_cmd = nfcsim_in_send_cmd, - if (!peer->clone_skb) { - DEV_ERR(dev, "skb_clone failed\n"); - mutex_unlock(&peer->lock); - err = -ENOMEM; - goto exit; - } + .tg_listen = nfcsim_tg_listen, + .tg_configure_hw = nfcsim_tg_configure_hw, + .tg_send_cmd = nfcsim_tg_send_cmd, - /* This simulates an arbitrary transmission delay between the 2 devices. - * If packet transmission occurs immediately between them, we have a - * non-stop flow of several tens of thousands SYMM packets per second - * and a burning cpu. - */ - queue_delayed_work(wq, &peer->recv_work, - msecs_to_jiffies(dev->rx_delay)); + .abort_cmd = nfcsim_abort_cmd, + .switch_rf = nfcsim_switch_rf, +}; + +static struct dentry *nfcsim_debugfs_root; - mutex_unlock(&peer->lock); +static void nfcsim_debugfs_init(void) +{ + nfcsim_debugfs_root = debugfs_create_dir("nfcsim", NULL); - err = 0; -exit: - dev_kfree_skb(skb); + if (!nfcsim_debugfs_root) + pr_err("Could not create debugfs entry\n"); - return err; } -static int nfcsim_im_transceive(struct nfc_dev *nfc_dev, - struct nfc_target *target, struct sk_buff *skb, - data_exchange_cb_t cb, void *cb_context) +static void nfcsim_debugfs_remove(void) { - return nfcsim_tx(nfc_dev, target, skb, cb, cb_context); + debugfs_remove_recursive(nfcsim_debugfs_root); } -static int nfcsim_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb) +static void nfcsim_debugfs_init_dev(struct nfcsim *dev) { - return nfcsim_tx(nfc_dev, NULL, skb, NULL, NULL); -} - -static struct nfc_ops nfcsim_nfc_ops = { - .dev_up = nfcsim_dev_up, - .dev_down = nfcsim_dev_down, - .dep_link_up = nfcsim_dep_link_up, - .dep_link_down = nfcsim_dep_link_down, - .start_poll = nfcsim_start_poll, - .stop_poll = nfcsim_stop_poll, - .activate_target = nfcsim_activate_target, - .deactivate_target = nfcsim_deactivate_target, - .im_transceive = nfcsim_im_transceive, - .tm_send = nfcsim_tm_send, -}; + struct dentry *dev_dir; + char devname[5]; /* nfcX\0 */ + u32 idx; + int n; -static void nfcsim_set_polling_mode(struct nfcsim *dev) -{ - if (dev->polling_mode == NFCSIM_POLL_NONE) { - dev->curr_polling_mode = NFCSIM_POLL_NONE; + if (!nfcsim_debugfs_root) { + NFCSIM_ERR(dev, "nfcsim debugfs not initialized\n"); return; } - if (dev->curr_polling_mode == NFCSIM_POLL_NONE) { - if (dev->polling_mode & NFCSIM_POLL_INITIATOR) - dev->curr_polling_mode = NFCSIM_POLL_INITIATOR; - else - dev->curr_polling_mode = NFCSIM_POLL_TARGET; - + idx = dev->nfc_digital_dev->nfc_dev->idx; + n = snprintf(devname, sizeof(devname), "nfc%d", idx); + if (n >= sizeof(devname)) { + NFCSIM_ERR(dev, "Could not compute dev name for dev %d\n", idx); return; } - if (dev->polling_mode == NFCSIM_POLL_DUAL) { - if (dev->curr_polling_mode == NFCSIM_POLL_TARGET) - dev->curr_polling_mode = NFCSIM_POLL_INITIATOR; - else - dev->curr_polling_mode = NFCSIM_POLL_TARGET; + dev_dir = debugfs_create_dir(devname, nfcsim_debugfs_root); + if (!dev_dir) { + NFCSIM_ERR(dev, "Could not create debugfs entries for nfc%d\n", + idx); + return; } + + debugfs_create_u8("dropframe", 0664, dev_dir, &dev->dropframe); } -static void nfcsim_wq_poll(struct work_struct *work) +static struct nfcsim *nfcsim_device_new(struct nfcsim_link *link_in, + struct nfcsim_link *link_out) { - struct nfcsim *dev = container_of(work, struct nfcsim, poll_work.work); - struct nfcsim *peer = dev->peer_dev; + struct nfcsim *dev; + int rc; - /* These work items run on an ordered workqueue and are therefore - * serialized. So we can take both mutexes without being dead locked. - */ - mutex_lock(&dev->lock); - mutex_lock(&peer->lock); + dev = kzalloc(sizeof(struct nfcsim), GFP_KERNEL); + if (!dev) + return ERR_PTR(-ENOMEM); - nfcsim_set_polling_mode(dev); + INIT_DELAYED_WORK(&dev->send_work, nfcsim_send_wq); + INIT_WORK(&dev->recv_work, nfcsim_recv_wq); - if (dev->curr_polling_mode == NFCSIM_POLL_NONE) { - DEV_DBG(dev, "Not polling\n"); - goto unlock; + dev->nfc_digital_dev = + nfc_digital_allocate_device(&nfcsim_digital_ops, + NFC_PROTO_NFC_DEP_MASK, + NFCSIM_CAPABILITIES, + 0, 0); + if (!dev->nfc_digital_dev) { + kfree(dev); + return ERR_PTR(-ENOMEM); } - DEV_DBG(dev, "Polling as %s", - dev->curr_polling_mode == NFCSIM_POLL_INITIATOR ? - "initiator\n" : "target\n"); + nfc_digital_set_drvdata(dev->nfc_digital_dev, dev); - if (dev->curr_polling_mode == NFCSIM_POLL_TARGET) - goto sched_work; + dev->link_in = link_in; + dev->link_out = link_out; - if (peer->curr_polling_mode == NFCSIM_POLL_TARGET) { - peer->polling_mode = NFCSIM_POLL_NONE; - dev->polling_mode = NFCSIM_POLL_NONE; - - dev->initiator = 1; - - nfcsim_target_found(dev); + rc = nfc_digital_register_device(dev->nfc_digital_dev); + if (rc) { + pr_err("Could not register digital device (%d)\n", rc); + nfc_digital_free_device(dev->nfc_digital_dev); + kfree(dev); - goto unlock; + return ERR_PTR(rc); } -sched_work: - /* This defines the delay for an initiator to check if the other device - * is polling in target mode. - * If the device starts in dual mode polling, it switches between - * initiator and target at every round. - * Because the wq is ordered and only 1 work item is executed at a time, - * we'll always have one device polling as initiator and the other as - * target at some point, even if both are started in dual mode. - */ - queue_delayed_work(wq, &dev->poll_work, msecs_to_jiffies(200)); + nfcsim_debugfs_init_dev(dev); -unlock: - mutex_unlock(&peer->lock); - mutex_unlock(&dev->lock); + return dev; } -static struct nfcsim *nfcsim_init_dev(void) +static void nfcsim_device_free(struct nfcsim *dev) { - struct nfcsim *dev; - int rc = -ENOMEM; + nfc_digital_unregister_device(dev->nfc_digital_dev); - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (dev == NULL) - return ERR_PTR(-ENOMEM); + dev->up = false; - mutex_init(&dev->lock); + nfcsim_link_shutdown(dev->link_in); - INIT_DELAYED_WORK(&dev->recv_work, nfcsim_wq_recv); - INIT_DELAYED_WORK(&dev->poll_work, nfcsim_wq_poll); + cancel_delayed_work_sync(&dev->send_work); + cancel_work_sync(&dev->recv_work); - dev->nfc_dev = nfc_allocate_device(&nfcsim_nfc_ops, - NFC_PROTO_NFC_DEP_MASK, - 0, 0); - if (!dev->nfc_dev) - goto error; + nfc_digital_free_device(dev->nfc_digital_dev); - nfc_set_drvdata(dev->nfc_dev, dev); - - rc = nfc_register_device(dev->nfc_dev); - if (rc) - goto free_nfc_dev; - - dev->rx_delay = RX_DEFAULT_DELAY; - return dev; - -free_nfc_dev: - nfc_free_device(dev->nfc_dev); - -error: kfree(dev); - - return ERR_PTR(rc); } -static void nfcsim_free_device(struct nfcsim *dev) -{ - nfc_unregister_device(dev->nfc_dev); - - nfc_free_device(dev->nfc_dev); - - kfree(dev); -} +static struct nfcsim *dev0; +static struct nfcsim *dev1; static int __init nfcsim_init(void) { + struct nfcsim_link *link0, *link1; int rc; - /* We need an ordered wq to ensure that poll_work items are executed - * one at a time. - */ - wq = alloc_ordered_workqueue("nfcsim", 0); - if (!wq) { + link0 = nfcsim_link_new(); + link1 = nfcsim_link_new(); + if (!link0 || !link1) { rc = -ENOMEM; - goto exit; + goto exit_err; } - dev0 = nfcsim_init_dev(); + nfcsim_debugfs_init(); + + dev0 = nfcsim_device_new(link0, link1); if (IS_ERR(dev0)) { rc = PTR_ERR(dev0); - goto exit; + goto exit_err; } - dev1 = nfcsim_init_dev(); + dev1 = nfcsim_device_new(link1, link0); if (IS_ERR(dev1)) { - kfree(dev0); + nfcsim_device_free(dev0); rc = PTR_ERR(dev1); - goto exit; + goto exit_err; } - dev0->peer_dev = dev1; - dev1->peer_dev = dev0; + pr_info("nfcsim " NFCSIM_VERSION " initialized\n"); + + return 0; - pr_debug("NFCsim " NFCSIM_VERSION " initialized\n"); +exit_err: + pr_err("Failed to initialize nfcsim driver (%d)\n", rc); - rc = 0; -exit: - if (rc) - pr_err("Failed to initialize nfcsim driver (%d)\n", - rc); + nfcsim_link_free(link0); + nfcsim_link_free(link1); return rc; } static void __exit nfcsim_exit(void) { - nfcsim_cleanup_dev(dev0, 1); - nfcsim_cleanup_dev(dev1, 1); + struct nfcsim_link *link0, *link1; + + link0 = dev0->link_in; + link1 = dev0->link_out; + + nfcsim_device_free(dev0); + nfcsim_device_free(dev1); - nfcsim_free_device(dev0); - nfcsim_free_device(dev1); + nfcsim_link_free(link0); + nfcsim_link_free(link1); - destroy_workqueue(wq); + nfcsim_debugfs_remove(); } module_init(nfcsim_init); diff --git a/drivers/nfc/nfcwilink.c b/drivers/nfc/nfcwilink.c index f81e500..3fbd18b 100644 --- a/drivers/nfc/nfcwilink.c +++ b/drivers/nfc/nfcwilink.c @@ -94,7 +94,7 @@ struct nfcwilink { struct nci_dev *ndev; unsigned long flags; - char st_register_cb_status; + int st_register_cb_status; long (*st_write) (struct sk_buff *); struct completion completed; @@ -320,7 +320,7 @@ exit: } /* Called by ST when registration is complete */ -static void nfcwilink_register_complete(void *priv_data, char data) +static void nfcwilink_register_complete(void *priv_data, int data) { struct nfcwilink *drv = priv_data; diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index 8ca0603..33ed78b 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -464,10 +464,8 @@ static int pn533_usb_probe(struct usb_interface *interface, return -ENOMEM; in_buf = kzalloc(in_buf_len, GFP_KERNEL); - if (!in_buf) { - rc = -ENOMEM; - goto out_free_phy; - } + if (!in_buf) + return -ENOMEM; phy->udev = usb_get_dev(interface_to_usbdev(interface)); phy->interface = interface; @@ -554,8 +552,7 @@ error: usb_free_urb(phy->out_urb); usb_put_dev(phy->udev); kfree(in_buf); -out_free_phy: - kfree(phy); + return rc; } diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index 87d5099..2b2330b 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -343,7 +343,26 @@ in_protocols[][PORT100_IN_MAX_NUM_PROTOCOLS + 1] = { }, [NFC_DIGITAL_FRAMING_NFCF_NFC_DEP] = { /* nfc_digital_framing_nfcf */ - { PORT100_IN_PROT_END, 0 }, + { PORT100_IN_PROT_INITIAL_GUARD_TIME, 18 }, + { PORT100_IN_PROT_ADD_CRC, 1 }, + { PORT100_IN_PROT_CHECK_CRC, 1 }, + { PORT100_IN_PROT_MULTI_CARD, 0 }, + { PORT100_IN_PROT_ADD_PARITY, 0 }, + { PORT100_IN_PROT_CHECK_PARITY, 0 }, + { PORT100_IN_PROT_BITWISE_AC_RECV_MODE, 0 }, + { PORT100_IN_PROT_VALID_BIT_NUMBER, 8 }, + { PORT100_IN_PROT_CRYPTO1, 0 }, + { PORT100_IN_PROT_ADD_SOF, 0 }, + { PORT100_IN_PROT_CHECK_SOF, 0 }, + { PORT100_IN_PROT_ADD_EOF, 0 }, + { PORT100_IN_PROT_CHECK_EOF, 0 }, + { PORT100_IN_PROT_DEAF_TIME, 4 }, + { PORT100_IN_PROT_CRM, 0 }, + { PORT100_IN_PROT_CRM_MIN_LEN, 0 }, + { PORT100_IN_PROT_T1_TAG_FRAME, 0 }, + { PORT100_IN_PROT_RFCA, 0 }, + { PORT100_IN_PROT_GUARD_TIME_AT_INITIATOR, 6 }, + { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFC_DEP_ACTIVATED] = { { PORT100_IN_PROT_END, 0 }, @@ -437,6 +456,12 @@ struct port100 { struct urb *out_urb; struct urb *in_urb; + /* This mutex protects the out_urb and avoids to submit a new command + * through port100_send_frame_async() while the previous one is being + * canceled through port100_abort_cmd(). + */ + struct mutex out_urb_lock; + struct work_struct cmd_complete_work; u8 cmd_type; @@ -445,6 +470,9 @@ struct port100 { * for any queuing/locking mechanism at driver level. */ struct port100_cmd *cmd; + + bool cmd_cancel; + struct completion cmd_cancel_done; }; struct port100_cmd { @@ -699,10 +727,27 @@ static int port100_send_ack(struct port100 *dev) { int rc; + mutex_lock(&dev->out_urb_lock); + + init_completion(&dev->cmd_cancel_done); + + usb_kill_urb(dev->out_urb); + dev->out_urb->transfer_buffer = ack_frame; dev->out_urb->transfer_buffer_length = sizeof(ack_frame); rc = usb_submit_urb(dev->out_urb, GFP_KERNEL); + /* Set the cmd_cancel flag only if the URB has been successfully + * submitted. It will be reset by the out URB completion callback + * port100_send_complete(). + */ + dev->cmd_cancel = !rc; + + mutex_unlock(&dev->out_urb_lock); + + if (!rc) + wait_for_completion(&dev->cmd_cancel_done); + return rc; } @@ -711,6 +756,16 @@ static int port100_send_frame_async(struct port100 *dev, struct sk_buff *out, { int rc; + mutex_lock(&dev->out_urb_lock); + + /* A command cancel frame as been sent through dev->out_urb. Don't try + * to submit a new one. + */ + if (dev->cmd_cancel) { + rc = -EAGAIN; + goto exit; + } + dev->out_urb->transfer_buffer = out->data; dev->out_urb->transfer_buffer_length = out->len; @@ -722,16 +777,15 @@ static int port100_send_frame_async(struct port100 *dev, struct sk_buff *out, rc = usb_submit_urb(dev->out_urb, GFP_KERNEL); if (rc) - return rc; + goto exit; rc = port100_submit_urb_for_ack(dev, GFP_KERNEL); if (rc) - goto error; + usb_unlink_urb(dev->out_urb); - return 0; +exit: + mutex_unlock(&dev->out_urb_lock); -error: - usb_unlink_urb(dev->out_urb); return rc; } @@ -790,6 +844,12 @@ static int port100_send_cmd_async(struct port100 *dev, u8 cmd_code, PORT100_FRAME_MAX_PAYLOAD_LEN + PORT100_FRAME_TAIL_LEN; + if (dev->cmd) { + nfc_err(&dev->interface->dev, + "A command is still in process\n"); + return -EBUSY; + } + resp = alloc_skb(resp_len, GFP_KERNEL); if (!resp) return -ENOMEM; @@ -867,6 +927,11 @@ static void port100_send_complete(struct urb *urb) { struct port100 *dev = urb->context; + if (dev->cmd_cancel) { + dev->cmd_cancel = false; + complete(&dev->cmd_cancel_done); + } + switch (urb->status) { case 0: break; /* success */ @@ -985,6 +1050,10 @@ static int port100_switch_rf(struct nfc_digital_dev *ddev, bool on) *skb_put(skb, 1) = on ? 1 : 0; + /* Cancel the last command if the device is being switched off */ + if (!on) + port100_abort_cmd(ddev); + resp = port100_send_cmd_sync(dev, PORT100_CMD_SWITCH_RF, skb); if (IS_ERR(resp)) @@ -1430,6 +1499,7 @@ static int port100_probe(struct usb_interface *interface, if (!dev) return -ENOMEM; + mutex_init(&dev->out_urb_lock); dev->udev = usb_get_dev(interface_to_usbdev(interface)); dev->interface = interface; usb_set_intfdata(interface, dev); diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index 10842b7..26c9dbb 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -1048,6 +1048,10 @@ static int trf7970a_init(struct trf7970a *trf) if (ret) goto err_out; + ret = trf7970a_write(trf, TRF7970A_NFC_TARGET_LEVEL, 0); + if (ret) + goto err_out; + usleep_range(1000, 2000); trf->chip_status_ctrl &= ~TRF7970A_CHIP_STATUS_RF_ON; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 1a51584..d5fb55c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1394,19 +1394,22 @@ static int ns_cmp(void *priv, struct list_head *a, struct list_head *b) return nsa->ns_id - nsb->ns_id; } -static struct nvme_ns *nvme_find_ns(struct nvme_ctrl *ctrl, unsigned nsid) +static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid) { - struct nvme_ns *ns; - - lockdep_assert_held(&ctrl->namespaces_mutex); + struct nvme_ns *ns, *ret = NULL; + mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry(ns, &ctrl->namespaces, list) { - if (ns->ns_id == nsid) - return ns; + if (ns->ns_id == nsid) { + kref_get(&ns->kref); + ret = ns; + break; + } if (ns->ns_id > nsid) break; } - return NULL; + mutex_unlock(&ctrl->namespaces_mutex); + return ret; } static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) @@ -1415,8 +1418,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) struct gendisk *disk; int node = dev_to_node(ctrl->dev); - lockdep_assert_held(&ctrl->namespaces_mutex); - ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node); if (!ns) return; @@ -1457,7 +1458,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (nvme_revalidate_disk(ns->disk)) goto out_free_disk; - list_add_tail_rcu(&ns->list, &ctrl->namespaces); + mutex_lock(&ctrl->namespaces_mutex); + list_add_tail(&ns->list, &ctrl->namespaces); + mutex_unlock(&ctrl->namespaces_mutex); + kref_get(&ctrl->kref); if (ns->type == NVME_NS_LIGHTNVM) return; @@ -1480,8 +1484,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) static void nvme_ns_remove(struct nvme_ns *ns) { - lockdep_assert_held(&ns->ctrl->namespaces_mutex); - if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) return; @@ -1494,8 +1496,11 @@ static void nvme_ns_remove(struct nvme_ns *ns) blk_mq_abort_requeue_list(ns->queue); blk_cleanup_queue(ns->queue); } + + mutex_lock(&ns->ctrl->namespaces_mutex); list_del_init(&ns->list); - synchronize_rcu(); + mutex_unlock(&ns->ctrl->namespaces_mutex); + nvme_put_ns(ns); } @@ -1503,10 +1508,11 @@ static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns *ns; - ns = nvme_find_ns(ctrl, nsid); + ns = nvme_find_get_ns(ctrl, nsid); if (ns) { if (revalidate_disk(ns->disk)) nvme_ns_remove(ns); + nvme_put_ns(ns); } else nvme_alloc_ns(ctrl, nsid); } @@ -1535,9 +1541,11 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn) nvme_validate_ns(ctrl, nsid); while (++prev < nsid) { - ns = nvme_find_ns(ctrl, prev); - if (ns) + ns = nvme_find_get_ns(ctrl, prev); + if (ns) { nvme_ns_remove(ns); + nvme_put_ns(ns); + } } } nn -= j; @@ -1552,8 +1560,6 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn) struct nvme_ns *ns, *next; unsigned i; - lockdep_assert_held(&ctrl->namespaces_mutex); - for (i = 1; i <= nn; i++) nvme_validate_ns(ctrl, i); @@ -1576,7 +1582,6 @@ static void nvme_scan_work(struct work_struct *work) if (nvme_identify_ctrl(ctrl, &id)) return; - mutex_lock(&ctrl->namespaces_mutex); nn = le32_to_cpu(id->nn); if (ctrl->vs >= NVME_VS(1, 1) && !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) { @@ -1585,6 +1590,7 @@ static void nvme_scan_work(struct work_struct *work) } nvme_scan_ns_sequential(ctrl, nn); done: + mutex_lock(&ctrl->namespaces_mutex); list_sort(NULL, &ctrl->namespaces, ns_cmp); mutex_unlock(&ctrl->namespaces_mutex); kfree(id); @@ -1604,6 +1610,11 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_queue_scan); +/* + * This function iterates the namespace list unlocked to allow recovery from + * controller failure. It is up to the caller to ensure the namespace list is + * not modified by scan work while this function is executing. + */ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) { struct nvme_ns *ns, *next; @@ -1617,10 +1628,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) if (ctrl->state == NVME_CTRL_DEAD) nvme_kill_queues(ctrl); - mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) nvme_ns_remove(ns); - mutex_unlock(&ctrl->namespaces_mutex); } EXPORT_SYMBOL_GPL(nvme_remove_namespaces); @@ -1791,11 +1800,8 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; - rcu_read_lock(); - list_for_each_entry_rcu(ns, &ctrl->namespaces, list) { - if (!kref_get_unless_zero(&ns->kref)) - continue; - + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { /* * Revalidating a dead namespace sets capacity to 0. This will * end buffered writers dirtying pages that can't be synced. @@ -1806,10 +1812,8 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) blk_set_queue_dying(ns->queue); blk_mq_abort_requeue_list(ns->queue); blk_mq_start_stopped_hw_queues(ns->queue, true); - - nvme_put_ns(ns); } - rcu_read_unlock(); + mutex_unlock(&ctrl->namespaces_mutex); } EXPORT_SYMBOL_GPL(nvme_kill_queues); @@ -1817,8 +1821,8 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; - rcu_read_lock(); - list_for_each_entry_rcu(ns, &ctrl->namespaces, list) { + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { spin_lock_irq(ns->queue->queue_lock); queue_flag_set(QUEUE_FLAG_STOPPED, ns->queue); spin_unlock_irq(ns->queue->queue_lock); @@ -1826,7 +1830,7 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl) blk_mq_cancel_requeue_work(ns->queue); blk_mq_stop_hw_queues(ns->queue); } - rcu_read_unlock(); + mutex_unlock(&ctrl->namespaces_mutex); } EXPORT_SYMBOL_GPL(nvme_stop_queues); @@ -1834,13 +1838,13 @@ void nvme_start_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; - rcu_read_lock(); - list_for_each_entry_rcu(ns, &ctrl->namespaces, list) { + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, ns->queue); blk_mq_start_stopped_hw_queues(ns->queue, true); blk_mq_kick_requeue_list(ns->queue); } - rcu_read_unlock(); + mutex_unlock(&ctrl->namespaces_mutex); } EXPORT_SYMBOL_GPL(nvme_start_queues); diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c index 38a8bbe..83797d8 100644 --- a/drivers/pps/clients/pps_parport.c +++ b/drivers/pps/clients/pps_parport.c @@ -195,7 +195,7 @@ static void parport_detach(struct parport *port) struct pps_client_pp *device; /* FIXME: oooh, this is ugly! */ - if (strcmp(pardev->name, KBUILD_MODNAME)) + if (!pardev || strcmp(pardev->name, KBUILD_MODNAME)) /* not our port */ return; diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c index 526bf23..6c7fe477 100644 --- a/drivers/regulator/qcom_smd-regulator.c +++ b/drivers/regulator/qcom_smd-regulator.c @@ -152,7 +152,6 @@ static const struct regulator_ops rpm_smps_ldo_ops_fixed = { .enable = rpm_reg_enable, .disable = rpm_reg_disable, .is_enabled = rpm_reg_is_enabled, - .list_voltage = regulator_list_voltage_linear_range, .get_voltage = rpm_reg_get_voltage, .set_voltage = rpm_reg_set_voltage, diff --git a/drivers/scsi/cxgbi/Makefile b/drivers/scsi/cxgbi/Makefile index 86007e3..a73781a 100644 --- a/drivers/scsi/cxgbi/Makefile +++ b/drivers/scsi/cxgbi/Makefile @@ -1,2 +1,4 @@ +ccflags-y += -Idrivers/net/ethernet/chelsio/libcxgb + obj-$(CONFIG_SCSI_CXGB3_ISCSI) += libcxgbi.o cxgb3i/ obj-$(CONFIG_SCSI_CXGB4_ISCSI) += libcxgbi.o cxgb4i/ diff --git a/drivers/scsi/cxgbi/cxgb3i/Kbuild b/drivers/scsi/cxgbi/cxgb3i/Kbuild index 961a12f..663c52e 100644 --- a/drivers/scsi/cxgbi/cxgb3i/Kbuild +++ b/drivers/scsi/cxgbi/cxgb3i/Kbuild @@ -1,3 +1,4 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/chelsio/cxgb3 +ccflags-y += -I$(srctree)/drivers/net/ethernet/chelsio/libcxgb obj-$(CONFIG_SCSI_CXGB3_ISCSI) += cxgb3i.o diff --git a/drivers/scsi/cxgbi/cxgb3i/Kconfig b/drivers/scsi/cxgbi/cxgb3i/Kconfig index e460398..f68c871 100644 --- a/drivers/scsi/cxgbi/cxgb3i/Kconfig +++ b/drivers/scsi/cxgbi/cxgb3i/Kconfig @@ -5,6 +5,7 @@ config SCSI_CXGB3_ISCSI select ETHERNET select NET_VENDOR_CHELSIO select CHELSIO_T3 + select CHELSIO_LIB select SCSI_ISCSI_ATTRS ---help--- This driver supports iSCSI offload for the Chelsio T3 devices. diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c index e22a268..33e8346 100644 --- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c +++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c @@ -1028,7 +1028,7 @@ cxgb3_cpl_handler_func cxgb3i_cpl_handlers[NUM_CPL_CMDS] = { * cxgb3i_ofld_init - allocate and initialize resources for each adapter found * @cdev: cxgbi adapter */ -int cxgb3i_ofld_init(struct cxgbi_device *cdev) +static int cxgb3i_ofld_init(struct cxgbi_device *cdev) { struct t3cdev *t3dev = (struct t3cdev *)cdev->lldev; struct adap_ports port; @@ -1076,64 +1076,69 @@ static inline void ulp_mem_io_set_hdr(struct sk_buff *skb, unsigned int addr) req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_BYPASS)); req->cmd_lock_addr = htonl(V_ULP_MEMIO_ADDR(addr >> 5) | V_ULPTX_CMD(ULP_MEM_WRITE)); - req->len = htonl(V_ULP_MEMIO_DATA_LEN(PPOD_SIZE >> 5) | - V_ULPTX_NFLITS((PPOD_SIZE >> 3) + 1)); + req->len = htonl(V_ULP_MEMIO_DATA_LEN(IPPOD_SIZE >> 5) | + V_ULPTX_NFLITS((IPPOD_SIZE >> 3) + 1)); } -static int ddp_set_map(struct cxgbi_sock *csk, struct cxgbi_pagepod_hdr *hdr, - unsigned int idx, unsigned int npods, - struct cxgbi_gather_list *gl) +static struct cxgbi_ppm *cdev2ppm(struct cxgbi_device *cdev) { - struct cxgbi_device *cdev = csk->cdev; - struct cxgbi_ddp_info *ddp = cdev->ddp; - unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ddp->llimit; - int i; + return ((struct t3cdev *)cdev->lldev)->ulp_iscsi; +} - log_debug(1 << CXGBI_DBG_DDP, - "csk 0x%p, idx %u, npods %u, gl 0x%p.\n", - csk, idx, npods, gl); +static int ddp_set_map(struct cxgbi_ppm *ppm, struct cxgbi_sock *csk, + struct cxgbi_task_tag_info *ttinfo) +{ + unsigned int idx = ttinfo->idx; + unsigned int npods = ttinfo->npods; + struct scatterlist *sg = ttinfo->sgl; + struct cxgbi_pagepod *ppod; + struct ulp_mem_io *req; + unsigned int sg_off; + unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ppm->llimit; + int i; - for (i = 0; i < npods; i++, idx++, pm_addr += PPOD_SIZE) { + for (i = 0; i < npods; i++, idx++, pm_addr += IPPOD_SIZE) { struct sk_buff *skb = alloc_wr(sizeof(struct ulp_mem_io) + - PPOD_SIZE, 0, GFP_ATOMIC); + IPPOD_SIZE, 0, GFP_ATOMIC); if (!skb) return -ENOMEM; - ulp_mem_io_set_hdr(skb, pm_addr); - cxgbi_ddp_ppod_set((struct cxgbi_pagepod *)(skb->head + - sizeof(struct ulp_mem_io)), - hdr, gl, i * PPOD_PAGES_MAX); + req = (struct ulp_mem_io *)skb->head; + ppod = (struct cxgbi_pagepod *)(req + 1); + sg_off = i * PPOD_PAGES_MAX; + cxgbi_ddp_set_one_ppod(ppod, ttinfo, &sg, + &sg_off); skb->priority = CPL_PRIORITY_CONTROL; - cxgb3_ofld_send(cdev->lldev, skb); + cxgb3_ofld_send(ppm->lldev, skb); } return 0; } -static void ddp_clear_map(struct cxgbi_hba *chba, unsigned int tag, - unsigned int idx, unsigned int npods) +static void ddp_clear_map(struct cxgbi_device *cdev, struct cxgbi_ppm *ppm, + struct cxgbi_task_tag_info *ttinfo) { - struct cxgbi_device *cdev = chba->cdev; - struct cxgbi_ddp_info *ddp = cdev->ddp; - unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ddp->llimit; + unsigned int idx = ttinfo->idx; + unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ppm->llimit; + unsigned int npods = ttinfo->npods; int i; log_debug(1 << CXGBI_DBG_DDP, - "cdev 0x%p, idx %u, npods %u, tag 0x%x.\n", - cdev, idx, npods, tag); + "cdev 0x%p, clear idx %u, npods %u.\n", + cdev, idx, npods); - for (i = 0; i < npods; i++, idx++, pm_addr += PPOD_SIZE) { + for (i = 0; i < npods; i++, idx++, pm_addr += IPPOD_SIZE) { struct sk_buff *skb = alloc_wr(sizeof(struct ulp_mem_io) + - PPOD_SIZE, 0, GFP_ATOMIC); + IPPOD_SIZE, 0, GFP_ATOMIC); if (!skb) { - pr_err("tag 0x%x, 0x%x, %d/%u, skb OOM.\n", - tag, idx, i, npods); + pr_err("cdev 0x%p, clear ddp, %u,%d/%u, skb OOM.\n", + cdev, idx, i, npods); continue; } ulp_mem_io_set_hdr(skb, pm_addr); skb->priority = CPL_PRIORITY_CONTROL; - cxgb3_ofld_send(cdev->lldev, skb); + cxgb3_ofld_send(ppm->lldev, skb); } } @@ -1203,82 +1208,68 @@ static int ddp_setup_conn_digest(struct cxgbi_sock *csk, unsigned int tid, } /** - * t3_ddp_cleanup - release the cxgb3 adapter's ddp resource - * @cdev: cxgb3i adapter - * release all the resource held by the ddp pagepod manager for a given - * adapter if needed - */ - -static void t3_ddp_cleanup(struct cxgbi_device *cdev) -{ - struct t3cdev *tdev = (struct t3cdev *)cdev->lldev; - - if (cxgbi_ddp_cleanup(cdev)) { - pr_info("t3dev 0x%p, ulp_iscsi no more user.\n", tdev); - tdev->ulp_iscsi = NULL; - } -} - -/** - * ddp_init - initialize the cxgb3 adapter's ddp resource + * cxgb3i_ddp_init - initialize the cxgb3 adapter's ddp resource * @cdev: cxgb3i adapter * initialize the ddp pagepod manager for a given adapter */ static int cxgb3i_ddp_init(struct cxgbi_device *cdev) { struct t3cdev *tdev = (struct t3cdev *)cdev->lldev; - struct cxgbi_ddp_info *ddp = tdev->ulp_iscsi; + struct net_device *ndev = cdev->ports[0]; + struct cxgbi_tag_format tformat; + unsigned int ppmax, tagmask = 0; struct ulp_iscsi_info uinfo; - unsigned int pgsz_factor[4]; int i, err; - if (ddp) { - kref_get(&ddp->refcnt); - pr_warn("t3dev 0x%p, ddp 0x%p already set up.\n", - tdev, tdev->ulp_iscsi); - cdev->ddp = ddp; - return -EALREADY; - } - err = tdev->ctl(tdev, ULP_ISCSI_GET_PARAMS, &uinfo); if (err < 0) { - pr_err("%s, failed to get iscsi param err=%d.\n", - tdev->name, err); + pr_err("%s, failed to get iscsi param %d.\n", + ndev->name, err); return err; } + if (uinfo.llimit >= uinfo.ulimit) { + pr_warn("T3 %s, iscsi NOT enabled %u ~ %u!\n", + ndev->name, uinfo.llimit, uinfo.ulimit); + return -EACCES; + } - err = cxgbi_ddp_init(cdev, uinfo.llimit, uinfo.ulimit, - uinfo.max_txsz, uinfo.max_rxsz); - if (err < 0) - return err; + ppmax = (uinfo.ulimit - uinfo.llimit + 1) >> PPOD_SIZE_SHIFT; + tagmask = cxgbi_tagmask_set(ppmax); - ddp = cdev->ddp; + pr_info("T3 %s: 0x%x~0x%x, 0x%x, tagmask 0x%x -> 0x%x.\n", + ndev->name, uinfo.llimit, uinfo.ulimit, ppmax, uinfo.tagmask, + tagmask); - uinfo.tagmask = ddp->idx_mask << PPOD_IDX_SHIFT; - cxgbi_ddp_page_size_factor(pgsz_factor); + memset(&tformat, 0, sizeof(struct cxgbi_tag_format)); for (i = 0; i < 4; i++) - uinfo.pgsz_factor[i] = pgsz_factor[i]; - uinfo.ulimit = uinfo.llimit + (ddp->nppods << PPOD_SIZE_SHIFT); + tformat.pgsz_order[i] = uinfo.pgsz_factor[i]; + cxgbi_tagmask_check(tagmask, &tformat); - err = tdev->ctl(tdev, ULP_ISCSI_SET_PARAMS, &uinfo); - if (err < 0) { - pr_warn("%s unable to set iscsi param err=%d, ddp disabled.\n", - tdev->name, err); - cxgbi_ddp_cleanup(cdev); - return err; + cxgbi_ddp_ppm_setup(&tdev->ulp_iscsi, cdev, &tformat, ppmax, + uinfo.llimit, uinfo.llimit, 0); + if (!(cdev->flags & CXGBI_FLAG_DDP_OFF)) { + uinfo.tagmask = tagmask; + uinfo.ulimit = uinfo.llimit + (ppmax << PPOD_SIZE_SHIFT); + + err = tdev->ctl(tdev, ULP_ISCSI_SET_PARAMS, &uinfo); + if (err < 0) { + pr_err("T3 %s fail to set iscsi param %d.\n", + ndev->name, err); + cdev->flags |= CXGBI_FLAG_DDP_OFF; + } + err = 0; } - tdev->ulp_iscsi = ddp; cdev->csk_ddp_setup_digest = ddp_setup_conn_digest; cdev->csk_ddp_setup_pgidx = ddp_setup_conn_pgidx; - cdev->csk_ddp_set = ddp_set_map; - cdev->csk_ddp_clear = ddp_clear_map; - - pr_info("tdev 0x%p, nppods %u, bits %u, mask 0x%x,0x%x pkt %u/%u, " - "%u/%u.\n", - tdev, ddp->nppods, ddp->idx_bits, ddp->idx_mask, - ddp->rsvd_tag_mask, ddp->max_txsz, uinfo.max_txsz, - ddp->max_rxsz, uinfo.max_rxsz); + cdev->csk_ddp_set_map = ddp_set_map; + cdev->csk_ddp_clear_map = ddp_clear_map; + cdev->cdev2ppm = cdev2ppm; + cdev->tx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD, + uinfo.max_txsz - ISCSI_PDU_NONPAYLOAD_LEN); + cdev->rx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD, + uinfo.max_rxsz - ISCSI_PDU_NONPAYLOAD_LEN); + return 0; } @@ -1325,7 +1316,6 @@ static void cxgb3i_dev_open(struct t3cdev *t3dev) cdev->rx_credit_thres = cxgb3i_rx_credit_thres; cdev->skb_tx_rsvd = CXGB3I_TX_HEADER_LEN; cdev->skb_rx_extra = sizeof(struct cpl_iscsi_hdr_norss); - cdev->dev_ddp_cleanup = t3_ddp_cleanup; cdev->itp = &cxgb3i_iscsi_transport; err = cxgb3i_ddp_init(cdev); diff --git a/drivers/scsi/cxgbi/cxgb4i/Kbuild b/drivers/scsi/cxgbi/cxgb4i/Kbuild index 3745864..38e03c2 100644 --- a/drivers/scsi/cxgbi/cxgb4i/Kbuild +++ b/drivers/scsi/cxgbi/cxgb4i/Kbuild @@ -1,3 +1,4 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/chelsio/cxgb4 +ccflags-y += -I$(srctree)/drivers/net/ethernet/chelsio/libcxgb obj-$(CONFIG_SCSI_CXGB4_ISCSI) += cxgb4i.o diff --git a/drivers/scsi/cxgbi/cxgb4i/Kconfig b/drivers/scsi/cxgbi/cxgb4i/Kconfig index 8c4e423..594f593 100644 --- a/drivers/scsi/cxgbi/cxgb4i/Kconfig +++ b/drivers/scsi/cxgbi/cxgb4i/Kconfig @@ -5,6 +5,7 @@ config SCSI_CXGB4_ISCSI select ETHERNET select NET_VENDOR_CHELSIO select CHELSIO_T4 + select CHELSIO_LIB select SCSI_ISCSI_ATTRS ---help--- This driver supports iSCSI offload for the Chelsio T4 devices. diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c index 339f6b7..e4ba2d2 100644 --- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c +++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c @@ -1503,7 +1503,7 @@ rel_resource_without_clip: return -EINVAL; } -cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = { +static cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = { [CPL_ACT_ESTABLISH] = do_act_establish, [CPL_ACT_OPEN_RPL] = do_act_open_rpl, [CPL_PEER_CLOSE] = do_peer_close, @@ -1519,7 +1519,7 @@ cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = { [CPL_RX_DATA] = do_rx_data, }; -int cxgb4i_ofld_init(struct cxgbi_device *cdev) +static int cxgb4i_ofld_init(struct cxgbi_device *cdev) { int rc; @@ -1543,24 +1543,22 @@ int cxgb4i_ofld_init(struct cxgbi_device *cdev) return 0; } -/* - * functions to program the pagepod in h/w - */ -#define ULPMEM_IDATA_MAX_NPPODS 4 /* 256/PPOD_SIZE */ -static inline void ulp_mem_io_set_hdr(struct cxgb4_lld_info *lldi, - struct ulp_mem_io *req, - unsigned int wr_len, unsigned int dlen, - unsigned int pm_addr) +static inline void +ulp_mem_io_set_hdr(struct cxgbi_device *cdev, + struct ulp_mem_io *req, + unsigned int wr_len, unsigned int dlen, + unsigned int pm_addr, + int tid) { + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); struct ulptx_idata *idata = (struct ulptx_idata *)(req + 1); - INIT_ULPTX_WR(req, wr_len, 0, 0); - if (is_t4(lldi->adapter_type)) - req->cmd = htonl(ULPTX_CMD_V(ULP_TX_MEM_WRITE) | - (ULP_MEMIO_ORDER_F)); - else - req->cmd = htonl(ULPTX_CMD_V(ULP_TX_MEM_WRITE) | - (T5_ULP_MEMIO_IMM_F)); + INIT_ULPTX_WR(req, wr_len, 0, tid); + req->wr.wr_hi = htonl(FW_WR_OP_V(FW_ULPTX_WR) | + FW_WR_ATOMIC_V(0)); + req->cmd = htonl(ULPTX_CMD_V(ULP_TX_MEM_WRITE) | + ULP_MEMIO_ORDER_V(is_t4(lldi->adapter_type)) | + T5_ULP_MEMIO_IMM_V(!is_t4(lldi->adapter_type))); req->dlen = htonl(ULP_MEMIO_DATA_LEN_V(dlen >> 5)); req->lock_addr = htonl(ULP_MEMIO_ADDR_V(pm_addr >> 5)); req->len16 = htonl(DIV_ROUND_UP(wr_len - sizeof(req->wr), 16)); @@ -1569,82 +1567,89 @@ static inline void ulp_mem_io_set_hdr(struct cxgb4_lld_info *lldi, idata->len = htonl(dlen); } -static int ddp_ppod_write_idata(struct cxgbi_device *cdev, unsigned int port_id, - struct cxgbi_pagepod_hdr *hdr, unsigned int idx, - unsigned int npods, - struct cxgbi_gather_list *gl, - unsigned int gl_pidx) +static struct sk_buff * +ddp_ppod_init_idata(struct cxgbi_device *cdev, + struct cxgbi_ppm *ppm, + unsigned int idx, unsigned int npods, + unsigned int tid) { - struct cxgbi_ddp_info *ddp = cdev->ddp; - struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); - struct sk_buff *skb; - struct ulp_mem_io *req; - struct ulptx_idata *idata; - struct cxgbi_pagepod *ppod; - unsigned int pm_addr = idx * PPOD_SIZE + ddp->llimit; - unsigned int dlen = PPOD_SIZE * npods; + unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ppm->llimit; + unsigned int dlen = npods << PPOD_SIZE_SHIFT; unsigned int wr_len = roundup(sizeof(struct ulp_mem_io) + sizeof(struct ulptx_idata) + dlen, 16); - unsigned int i; + struct sk_buff *skb = alloc_wr(wr_len, 0, GFP_ATOMIC); - skb = alloc_wr(wr_len, 0, GFP_ATOMIC); if (!skb) { - pr_err("cdev 0x%p, idx %u, npods %u, OOM.\n", - cdev, idx, npods); - return -ENOMEM; + pr_err("%s: %s idx %u, npods %u, OOM.\n", + __func__, ppm->ndev->name, idx, npods); + return NULL; } - req = (struct ulp_mem_io *)skb->head; - set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0); - ulp_mem_io_set_hdr(lldi, req, wr_len, dlen, pm_addr); + ulp_mem_io_set_hdr(cdev, (struct ulp_mem_io *)skb->head, wr_len, dlen, + pm_addr, tid); + + return skb; +} + +static int ddp_ppod_write_idata(struct cxgbi_ppm *ppm, struct cxgbi_sock *csk, + struct cxgbi_task_tag_info *ttinfo, + unsigned int idx, unsigned int npods, + struct scatterlist **sg_pp, + unsigned int *sg_off) +{ + struct cxgbi_device *cdev = csk->cdev; + struct sk_buff *skb = ddp_ppod_init_idata(cdev, ppm, idx, npods, + csk->tid); + struct ulp_mem_io *req; + struct ulptx_idata *idata; + struct cxgbi_pagepod *ppod; + int i; + + if (!skb) + return -ENOMEM; + + req = (struct ulp_mem_io *)skb->head; idata = (struct ulptx_idata *)(req + 1); ppod = (struct cxgbi_pagepod *)(idata + 1); - for (i = 0; i < npods; i++, ppod++, gl_pidx += PPOD_PAGES_MAX) { - if (!hdr && !gl) - cxgbi_ddp_ppod_clear(ppod); - else - cxgbi_ddp_ppod_set(ppod, hdr, gl, gl_pidx); - } + for (i = 0; i < npods; i++, ppod++) + cxgbi_ddp_set_one_ppod(ppod, ttinfo, sg_pp, sg_off); + + cxgbi_skcb_set_flag(skb, SKCBF_TX_MEM_WRITE); + cxgbi_skcb_set_flag(skb, SKCBF_TX_FLAG_COMPL); + set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id); + + spin_lock_bh(&csk->lock); + cxgbi_sock_skb_entail(csk, skb); + spin_unlock_bh(&csk->lock); - cxgb4_ofld_send(cdev->ports[port_id], skb); return 0; } -static int ddp_set_map(struct cxgbi_sock *csk, struct cxgbi_pagepod_hdr *hdr, - unsigned int idx, unsigned int npods, - struct cxgbi_gather_list *gl) +static int ddp_set_map(struct cxgbi_ppm *ppm, struct cxgbi_sock *csk, + struct cxgbi_task_tag_info *ttinfo) { + unsigned int pidx = ttinfo->idx; + unsigned int npods = ttinfo->npods; unsigned int i, cnt; int err = 0; + struct scatterlist *sg = ttinfo->sgl; + unsigned int offset = 0; - for (i = 0; i < npods; i += cnt, idx += cnt) { - cnt = npods - i; - if (cnt > ULPMEM_IDATA_MAX_NPPODS) - cnt = ULPMEM_IDATA_MAX_NPPODS; - err = ddp_ppod_write_idata(csk->cdev, csk->port_id, hdr, - idx, cnt, gl, 4 * i); - if (err < 0) - break; - } - return err; -} - -static void ddp_clear_map(struct cxgbi_hba *chba, unsigned int tag, - unsigned int idx, unsigned int npods) -{ - unsigned int i, cnt; - int err; + ttinfo->cid = csk->port_id; - for (i = 0; i < npods; i += cnt, idx += cnt) { + for (i = 0; i < npods; i += cnt, pidx += cnt) { cnt = npods - i; + if (cnt > ULPMEM_IDATA_MAX_NPPODS) cnt = ULPMEM_IDATA_MAX_NPPODS; - err = ddp_ppod_write_idata(chba->cdev, chba->port_id, NULL, - idx, cnt, NULL, 0); + err = ddp_ppod_write_idata(ppm, csk, ttinfo, pidx, cnt, + &sg, &offset); if (err < 0) break; } + + return err; } static int ddp_setup_conn_pgidx(struct cxgbi_sock *csk, unsigned int tid, @@ -1710,48 +1715,46 @@ static int ddp_setup_conn_digest(struct cxgbi_sock *csk, unsigned int tid, return 0; } +static struct cxgbi_ppm *cdev2ppm(struct cxgbi_device *cdev) +{ + return (struct cxgbi_ppm *)(*((struct cxgb4_lld_info *) + (cxgbi_cdev_priv(cdev)))->iscsi_ppm); +} + static int cxgb4i_ddp_init(struct cxgbi_device *cdev) { struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); - struct cxgbi_ddp_info *ddp = cdev->ddp; - unsigned int tagmask, pgsz_factor[4]; - int err; - - if (ddp) { - kref_get(&ddp->refcnt); - pr_warn("cdev 0x%p, ddp 0x%p already set up.\n", - cdev, cdev->ddp); - return -EALREADY; + struct net_device *ndev = cdev->ports[0]; + struct cxgbi_tag_format tformat; + unsigned int ppmax; + int i; + + if (!lldi->vr->iscsi.size) { + pr_warn("%s, iscsi NOT enabled, check config!\n", ndev->name); + return -EACCES; } - err = cxgbi_ddp_init(cdev, lldi->vr->iscsi.start, - lldi->vr->iscsi.start + lldi->vr->iscsi.size - 1, - lldi->iscsi_iolen, lldi->iscsi_iolen); - if (err < 0) - return err; + cdev->flags |= CXGBI_FLAG_USE_PPOD_OFLDQ; + ppmax = lldi->vr->iscsi.size >> PPOD_SIZE_SHIFT; - ddp = cdev->ddp; + memset(&tformat, 0, sizeof(struct cxgbi_tag_format)); + for (i = 0; i < 4; i++) + tformat.pgsz_order[i] = (lldi->iscsi_pgsz_order >> (i << 3)) + & 0xF; + cxgbi_tagmask_check(lldi->iscsi_tagmask, &tformat); - tagmask = ddp->idx_mask << PPOD_IDX_SHIFT; - cxgbi_ddp_page_size_factor(pgsz_factor); - cxgb4_iscsi_init(lldi->ports[0], tagmask, pgsz_factor); + cxgbi_ddp_ppm_setup(lldi->iscsi_ppm, cdev, &tformat, ppmax, + lldi->iscsi_llimit, lldi->vr->iscsi.start, 2); cdev->csk_ddp_setup_digest = ddp_setup_conn_digest; cdev->csk_ddp_setup_pgidx = ddp_setup_conn_pgidx; - cdev->csk_ddp_set = ddp_set_map; - cdev->csk_ddp_clear = ddp_clear_map; - - pr_info("cxgb4i 0x%p tag: sw %u, rsvd %u,%u, mask 0x%x.\n", - cdev, cdev->tag_format.sw_bits, cdev->tag_format.rsvd_bits, - cdev->tag_format.rsvd_shift, cdev->tag_format.rsvd_mask); - pr_info("cxgb4i 0x%p, nppods %u, bits %u, mask 0x%x,0x%x pkt %u/%u, " - " %u/%u.\n", - cdev, ddp->nppods, ddp->idx_bits, ddp->idx_mask, - ddp->rsvd_tag_mask, ddp->max_txsz, lldi->iscsi_iolen, - ddp->max_rxsz, lldi->iscsi_iolen); - pr_info("cxgb4i 0x%p max payload size: %u/%u, %u/%u.\n", - cdev, cdev->tx_max_size, ddp->max_txsz, cdev->rx_max_size, - ddp->max_rxsz); + cdev->csk_ddp_set_map = ddp_set_map; + cdev->tx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD, + lldi->iscsi_iolen - ISCSI_PDU_NONPAYLOAD_LEN); + cdev->rx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD, + lldi->iscsi_iolen - ISCSI_PDU_NONPAYLOAD_LEN); + cdev->cdev2ppm = cdev2ppm; + return 0; } diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index ead83a2..d142113 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -64,6 +64,14 @@ static DEFINE_MUTEX(cdev_mutex); static LIST_HEAD(cdev_rcu_list); static DEFINE_SPINLOCK(cdev_rcu_lock); +static inline void cxgbi_decode_sw_tag(u32 sw_tag, int *idx, int *age) +{ + if (age) + *age = sw_tag & 0x7FFF; + if (idx) + *idx = (sw_tag >> 16) & 0x7FFF; +} + int cxgbi_device_portmap_create(struct cxgbi_device *cdev, unsigned int base, unsigned int max_conn) { @@ -113,12 +121,7 @@ static inline void cxgbi_device_destroy(struct cxgbi_device *cdev) "cdev 0x%p, p# %u.\n", cdev, cdev->nports); cxgbi_hbas_remove(cdev); cxgbi_device_portmap_cleanup(cdev); - if (cdev->dev_ddp_cleanup) - cdev->dev_ddp_cleanup(cdev); - else - cxgbi_ddp_cleanup(cdev); - if (cdev->ddp) - cxgbi_ddp_cleanup(cdev); + cxgbi_ppm_release(cdev->cdev2ppm(cdev)); if (cdev->pmap.max_connect) cxgbi_free_big_mem(cdev->pmap.port_csk); kfree(cdev); @@ -1182,525 +1185,245 @@ out_err: goto done; } -/* - * Direct Data Placement - - * Directly place the iSCSI Data-In or Data-Out PDU's payload into pre-posted - * final destination host-memory buffers based on the Initiator Task Tag (ITT) - * in Data-In or Target Task Tag (TTT) in Data-Out PDUs. - * The host memory address is programmed into h/w in the format of pagepod - * entries. - * The location of the pagepod entry is encoded into ddp tag which is used as - * the base for ITT/TTT. - */ - -static unsigned char ddp_page_order[DDP_PGIDX_MAX] = {0, 1, 2, 4}; -static unsigned char ddp_page_shift[DDP_PGIDX_MAX] = {12, 13, 14, 16}; -static unsigned char page_idx = DDP_PGIDX_MAX; - -static unsigned char sw_tag_idx_bits; -static unsigned char sw_tag_age_bits; - -/* - * Direct-Data Placement page size adjustment - */ -static int ddp_adjust_page_table(void) +static inline void +scmd_get_params(struct scsi_cmnd *sc, struct scatterlist **sgl, + unsigned int *sgcnt, unsigned int *dlen, + unsigned int prot) { - int i; - unsigned int base_order, order; - - if (PAGE_SIZE < (1UL << ddp_page_shift[0])) { - pr_info("PAGE_SIZE 0x%lx too small, min 0x%lx\n", - PAGE_SIZE, 1UL << ddp_page_shift[0]); - return -EINVAL; - } - - base_order = get_order(1UL << ddp_page_shift[0]); - order = get_order(1UL << PAGE_SHIFT); + struct scsi_data_buffer *sdb = prot ? scsi_prot(sc) : scsi_out(sc); - for (i = 0; i < DDP_PGIDX_MAX; i++) { - /* first is the kernel page size, then just doubling */ - ddp_page_order[i] = order - base_order + i; - ddp_page_shift[i] = PAGE_SHIFT + i; - } - return 0; + *sgl = sdb->table.sgl; + *sgcnt = sdb->table.nents; + *dlen = sdb->length; + /* Caution: for protection sdb, sdb->length is invalid */ } -static int ddp_find_page_index(unsigned long pgsz) +void cxgbi_ddp_set_one_ppod(struct cxgbi_pagepod *ppod, + struct cxgbi_task_tag_info *ttinfo, + struct scatterlist **sg_pp, unsigned int *sg_off) { + struct scatterlist *sg = sg_pp ? *sg_pp : NULL; + unsigned int offset = sg_off ? *sg_off : 0; + dma_addr_t addr = 0UL; + unsigned int len = 0; int i; - for (i = 0; i < DDP_PGIDX_MAX; i++) { - if (pgsz == (1UL << ddp_page_shift[i])) - return i; - } - pr_info("ddp page size %lu not supported.\n", pgsz); - return DDP_PGIDX_MAX; -} + memcpy(ppod, &ttinfo->hdr, sizeof(struct cxgbi_pagepod_hdr)); -static void ddp_setup_host_page_size(void) -{ - if (page_idx == DDP_PGIDX_MAX) { - page_idx = ddp_find_page_index(PAGE_SIZE); + if (sg) { + addr = sg_dma_address(sg); + len = sg_dma_len(sg); + } - if (page_idx == DDP_PGIDX_MAX) { - pr_info("system PAGE %lu, update hw.\n", PAGE_SIZE); - if (ddp_adjust_page_table() < 0) { - pr_info("PAGE %lu, disable ddp.\n", PAGE_SIZE); - return; + for (i = 0; i < PPOD_PAGES_MAX; i++) { + if (sg) { + ppod->addr[i] = cpu_to_be64(addr + offset); + offset += PAGE_SIZE; + if (offset == (len + sg->offset)) { + offset = 0; + sg = sg_next(sg); + if (sg) { + addr = sg_dma_address(sg); + len = sg_dma_len(sg); + } } - page_idx = ddp_find_page_index(PAGE_SIZE); + } else { + ppod->addr[i] = 0ULL; } - pr_info("system PAGE %lu, ddp idx %u.\n", PAGE_SIZE, page_idx); } -} - -void cxgbi_ddp_page_size_factor(int *pgsz_factor) -{ - int i; - - for (i = 0; i < DDP_PGIDX_MAX; i++) - pgsz_factor[i] = ddp_page_order[i]; -} -EXPORT_SYMBOL_GPL(cxgbi_ddp_page_size_factor); - -/* - * DDP setup & teardown - */ - -void cxgbi_ddp_ppod_set(struct cxgbi_pagepod *ppod, - struct cxgbi_pagepod_hdr *hdr, - struct cxgbi_gather_list *gl, unsigned int gidx) -{ - int i; - - memcpy(ppod, hdr, sizeof(*hdr)); - for (i = 0; i < (PPOD_PAGES_MAX + 1); i++, gidx++) { - ppod->addr[i] = gidx < gl->nelem ? - cpu_to_be64(gl->phys_addr[gidx]) : 0ULL; - } -} -EXPORT_SYMBOL_GPL(cxgbi_ddp_ppod_set); - -void cxgbi_ddp_ppod_clear(struct cxgbi_pagepod *ppod) -{ - memset(ppod, 0, sizeof(*ppod)); -} -EXPORT_SYMBOL_GPL(cxgbi_ddp_ppod_clear); - -static inline int ddp_find_unused_entries(struct cxgbi_ddp_info *ddp, - unsigned int start, unsigned int max, - unsigned int count, - struct cxgbi_gather_list *gl) -{ - unsigned int i, j, k; - /* not enough entries */ - if ((max - start) < count) { - log_debug(1 << CXGBI_DBG_DDP, - "NOT enough entries %u+%u < %u.\n", start, count, max); - return -EBUSY; + /* + * the fifth address needs to be repeated in the next ppod, so do + * not move sg + */ + if (sg_pp) { + *sg_pp = sg; + *sg_off = offset; } - max -= count; - spin_lock(&ddp->map_lock); - for (i = start; i < max;) { - for (j = 0, k = i; j < count; j++, k++) { - if (ddp->gl_map[k]) - break; - } - if (j == count) { - for (j = 0, k = i; j < count; j++, k++) - ddp->gl_map[k] = gl; - spin_unlock(&ddp->map_lock); - return i; + if (offset == len) { + offset = 0; + sg = sg_next(sg); + if (sg) { + addr = sg_dma_address(sg); + len = sg_dma_len(sg); } - i += j + 1; } - spin_unlock(&ddp->map_lock); - log_debug(1 << CXGBI_DBG_DDP, - "NO suitable entries %u available.\n", count); - return -EBUSY; -} - -static inline void ddp_unmark_entries(struct cxgbi_ddp_info *ddp, - int start, int count) -{ - spin_lock(&ddp->map_lock); - memset(&ddp->gl_map[start], 0, - count * sizeof(struct cxgbi_gather_list *)); - spin_unlock(&ddp->map_lock); + ppod->addr[i] = sg ? cpu_to_be64(addr + offset) : 0ULL; } +EXPORT_SYMBOL_GPL(cxgbi_ddp_set_one_ppod); -static inline void ddp_gl_unmap(struct pci_dev *pdev, - struct cxgbi_gather_list *gl) -{ - int i; +/* + * APIs interacting with open-iscsi libraries + */ - for (i = 0; i < gl->nelem; i++) - dma_unmap_page(&pdev->dev, gl->phys_addr[i], PAGE_SIZE, - PCI_DMA_FROMDEVICE); -} +static unsigned char padding[4]; -static inline int ddp_gl_map(struct pci_dev *pdev, - struct cxgbi_gather_list *gl) +void cxgbi_ddp_ppm_setup(void **ppm_pp, struct cxgbi_device *cdev, + struct cxgbi_tag_format *tformat, unsigned int ppmax, + unsigned int llimit, unsigned int start, + unsigned int rsvd_factor) { - int i; + int err = cxgbi_ppm_init(ppm_pp, cdev->ports[0], cdev->pdev, + cdev->lldev, tformat, ppmax, llimit, start, + rsvd_factor); - for (i = 0; i < gl->nelem; i++) { - gl->phys_addr[i] = dma_map_page(&pdev->dev, gl->pages[i], 0, - PAGE_SIZE, - PCI_DMA_FROMDEVICE); - if (unlikely(dma_mapping_error(&pdev->dev, gl->phys_addr[i]))) { - log_debug(1 << CXGBI_DBG_DDP, - "page %d 0x%p, 0x%p dma mapping err.\n", - i, gl->pages[i], pdev); - goto unmap; - } - } - return i; -unmap: - if (i) { - unsigned int nelem = gl->nelem; + if (err >= 0) { + struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*ppm_pp); - gl->nelem = i; - ddp_gl_unmap(pdev, gl); - gl->nelem = nelem; + if (ppm->ppmax < 1024 || + ppm->tformat.pgsz_idx_dflt >= DDP_PGIDX_MAX) + cdev->flags |= CXGBI_FLAG_DDP_OFF; + err = 0; + } else { + cdev->flags |= CXGBI_FLAG_DDP_OFF; } - return -EINVAL; -} - -static void ddp_release_gl(struct cxgbi_gather_list *gl, - struct pci_dev *pdev) -{ - ddp_gl_unmap(pdev, gl); - kfree(gl); } +EXPORT_SYMBOL_GPL(cxgbi_ddp_ppm_setup); -static struct cxgbi_gather_list *ddp_make_gl(unsigned int xferlen, - struct scatterlist *sgl, - unsigned int sgcnt, - struct pci_dev *pdev, - gfp_t gfp) +static int cxgbi_ddp_sgl_check(struct scatterlist *sgl, int nents) { - struct cxgbi_gather_list *gl; + int i; + int last_sgidx = nents - 1; struct scatterlist *sg = sgl; - struct page *sgpage = sg_page(sg); - unsigned int sglen = sg->length; - unsigned int sgoffset = sg->offset; - unsigned int npages = (xferlen + sgoffset + PAGE_SIZE - 1) >> - PAGE_SHIFT; - int i = 1, j = 0; - - if (xferlen < DDP_THRESHOLD) { - log_debug(1 << CXGBI_DBG_DDP, - "xfer %u < threshold %u, no ddp.\n", - xferlen, DDP_THRESHOLD); - return NULL; - } - - gl = kzalloc(sizeof(struct cxgbi_gather_list) + - npages * (sizeof(dma_addr_t) + - sizeof(struct page *)), gfp); - if (!gl) { - log_debug(1 << CXGBI_DBG_DDP, - "xfer %u, %u pages, OOM.\n", xferlen, npages); - return NULL; - } - log_debug(1 << CXGBI_DBG_DDP, - "xfer %u, sgl %u, gl max %u.\n", xferlen, sgcnt, npages); - - gl->pages = (struct page **)&gl->phys_addr[npages]; - gl->nelem = npages; - gl->length = xferlen; - gl->offset = sgoffset; - gl->pages[0] = sgpage; - - for (i = 1, sg = sg_next(sgl), j = 0; i < sgcnt; - i++, sg = sg_next(sg)) { - struct page *page = sg_page(sg); - - if (sgpage == page && sg->offset == sgoffset + sglen) - sglen += sg->length; - else { - /* make sure the sgl is fit for ddp: - * each has the same page size, and - * all of the middle pages are used completely - */ - if ((j && sgoffset) || ((i != sgcnt - 1) && - ((sglen + sgoffset) & ~PAGE_MASK))) { - log_debug(1 << CXGBI_DBG_DDP, - "page %d/%u, %u + %u.\n", - i, sgcnt, sgoffset, sglen); - goto error_out; - } + for (i = 0; i < nents; i++, sg = sg_next(sg)) { + unsigned int len = sg->length + sg->offset; - j++; - if (j == gl->nelem || sg->offset) { - log_debug(1 << CXGBI_DBG_DDP, - "page %d/%u, offset %u.\n", - j, gl->nelem, sg->offset); - goto error_out; - } - gl->pages[j] = page; - sglen = sg->length; - sgoffset = sg->offset; - sgpage = page; - } - } - gl->nelem = ++j; - - if (ddp_gl_map(pdev, gl) < 0) - goto error_out; - - return gl; - -error_out: - kfree(gl); - return NULL; -} - -static void ddp_tag_release(struct cxgbi_hba *chba, u32 tag) -{ - struct cxgbi_device *cdev = chba->cdev; - struct cxgbi_ddp_info *ddp = cdev->ddp; - u32 idx; - - idx = (tag >> PPOD_IDX_SHIFT) & ddp->idx_mask; - if (idx < ddp->nppods) { - struct cxgbi_gather_list *gl = ddp->gl_map[idx]; - unsigned int npods; - - if (!gl || !gl->nelem) { - pr_warn("tag 0x%x, idx %u, gl 0x%p, %u.\n", - tag, idx, gl, gl ? gl->nelem : 0); - return; - } - npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT; - log_debug(1 << CXGBI_DBG_DDP, - "tag 0x%x, release idx %u, npods %u.\n", - tag, idx, npods); - cdev->csk_ddp_clear(chba, tag, idx, npods); - ddp_unmark_entries(ddp, idx, npods); - ddp_release_gl(gl, ddp->pdev); - } else - pr_warn("tag 0x%x, idx %u > max %u.\n", tag, idx, ddp->nppods); -} - -static int ddp_tag_reserve(struct cxgbi_sock *csk, unsigned int tid, - u32 sw_tag, u32 *tagp, struct cxgbi_gather_list *gl, - gfp_t gfp) -{ - struct cxgbi_device *cdev = csk->cdev; - struct cxgbi_ddp_info *ddp = cdev->ddp; - struct cxgbi_tag_format *tformat = &cdev->tag_format; - struct cxgbi_pagepod_hdr hdr; - unsigned int npods; - int idx = -1; - int err = -ENOMEM; - u32 tag; - - npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT; - if (ddp->idx_last == ddp->nppods) - idx = ddp_find_unused_entries(ddp, 0, ddp->nppods, - npods, gl); - else { - idx = ddp_find_unused_entries(ddp, ddp->idx_last + 1, - ddp->nppods, npods, - gl); - if (idx < 0 && ddp->idx_last >= npods) { - idx = ddp_find_unused_entries(ddp, 0, - min(ddp->idx_last + npods, ddp->nppods), - npods, gl); + if ((sg->offset & 0x3) || (i && sg->offset) || + ((i != last_sgidx) && len != PAGE_SIZE)) { + log_debug(1 << CXGBI_DBG_DDP, + "sg %u/%u, %u,%u, not aligned.\n", + i, nents, sg->offset, sg->length); + goto err_out; } } - if (idx < 0) { - log_debug(1 << CXGBI_DBG_DDP, - "xferlen %u, gl %u, npods %u NO DDP.\n", - gl->length, gl->nelem, npods); - return idx; - } - - tag = cxgbi_ddp_tag_base(tformat, sw_tag); - tag |= idx << PPOD_IDX_SHIFT; - - hdr.rsvd = 0; - hdr.vld_tid = htonl(PPOD_VALID_FLAG | PPOD_TID(tid)); - hdr.pgsz_tag_clr = htonl(tag & ddp->rsvd_tag_mask); - hdr.max_offset = htonl(gl->length); - hdr.page_offset = htonl(gl->offset); - - err = cdev->csk_ddp_set(csk, &hdr, idx, npods, gl); - if (err < 0) - goto unmark_entries; - - ddp->idx_last = idx; - log_debug(1 << CXGBI_DBG_DDP, - "xfer %u, gl %u,%u, tid 0x%x, tag 0x%x->0x%x(%u,%u).\n", - gl->length, gl->nelem, gl->offset, tid, sw_tag, tag, idx, - npods); - *tagp = tag; return 0; - -unmark_entries: - ddp_unmark_entries(ddp, idx, npods); - return err; +err_out: + return -EINVAL; } -int cxgbi_ddp_reserve(struct cxgbi_sock *csk, unsigned int *tagp, - unsigned int sw_tag, unsigned int xferlen, - struct scatterlist *sgl, unsigned int sgcnt, gfp_t gfp) +static int cxgbi_ddp_reserve(struct cxgbi_conn *cconn, + struct cxgbi_task_data *tdata, u32 sw_tag, + unsigned int xferlen) { + struct cxgbi_sock *csk = cconn->cep->csk; struct cxgbi_device *cdev = csk->cdev; - struct cxgbi_tag_format *tformat = &cdev->tag_format; - struct cxgbi_gather_list *gl; + struct cxgbi_ppm *ppm = cdev->cdev2ppm(cdev); + struct cxgbi_task_tag_info *ttinfo = &tdata->ttinfo; + struct scatterlist *sgl = ttinfo->sgl; + unsigned int sgcnt = ttinfo->nents; + unsigned int sg_offset = sgl->offset; int err; - if (page_idx >= DDP_PGIDX_MAX || !cdev->ddp || - xferlen < DDP_THRESHOLD) { + if (cdev->flags & CXGBI_FLAG_DDP_OFF) { log_debug(1 << CXGBI_DBG_DDP, - "pgidx %u, xfer %u, NO ddp.\n", page_idx, xferlen); + "cdev 0x%p DDP off.\n", cdev); return -EINVAL; } - if (!cxgbi_sw_tag_usable(tformat, sw_tag)) { + if (!ppm || xferlen < DDP_THRESHOLD || !sgcnt || + ppm->tformat.pgsz_idx_dflt >= DDP_PGIDX_MAX) { log_debug(1 << CXGBI_DBG_DDP, - "sw_tag 0x%x NOT usable.\n", sw_tag); + "ppm 0x%p, pgidx %u, xfer %u, sgcnt %u, NO ddp.\n", + ppm, ppm ? ppm->tformat.pgsz_idx_dflt : DDP_PGIDX_MAX, + xferlen, ttinfo->nents); return -EINVAL; } - gl = ddp_make_gl(xferlen, sgl, sgcnt, cdev->pdev, gfp); - if (!gl) - return -ENOMEM; + /* make sure the buffer is suitable for ddp */ + if (cxgbi_ddp_sgl_check(sgl, sgcnt) < 0) + return -EINVAL; - err = ddp_tag_reserve(csk, csk->tid, sw_tag, tagp, gl, gfp); - if (err < 0) - ddp_release_gl(gl, cdev->pdev); + ttinfo->nr_pages = (xferlen + sgl->offset + (1 << PAGE_SHIFT) - 1) >> + PAGE_SHIFT; - return err; -} + /* + * the ddp tag will be used for the itt in the outgoing pdu, + * the itt genrated by libiscsi is saved in the ppm and can be + * retrieved via the ddp tag + */ + err = cxgbi_ppm_ppods_reserve(ppm, ttinfo->nr_pages, 0, &ttinfo->idx, + &ttinfo->tag, (unsigned long)sw_tag); + if (err < 0) { + cconn->ddp_full++; + return err; + } + ttinfo->npods = err; -static void ddp_destroy(struct kref *kref) -{ - struct cxgbi_ddp_info *ddp = container_of(kref, - struct cxgbi_ddp_info, - refcnt); - struct cxgbi_device *cdev = ddp->cdev; - int i = 0; + /* setup dma from scsi command sgl */ + sgl->offset = 0; + err = dma_map_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE); + sgl->offset = sg_offset; + if (err == 0) { + pr_info("%s: 0x%x, xfer %u, sgl %u dma mapping err.\n", + __func__, sw_tag, xferlen, sgcnt); + goto rel_ppods; + } + if (err != ttinfo->nr_pages) { + log_debug(1 << CXGBI_DBG_DDP, + "%s: sw tag 0x%x, xfer %u, sgl %u, dma count %d.\n", + __func__, sw_tag, xferlen, sgcnt, err); + } - pr_info("kref 0, destroy ddp 0x%p, cdev 0x%p.\n", ddp, cdev); + ttinfo->flags |= CXGBI_PPOD_INFO_FLAG_MAPPED; + ttinfo->cid = csk->port_id; - while (i < ddp->nppods) { - struct cxgbi_gather_list *gl = ddp->gl_map[i]; + cxgbi_ppm_make_ppod_hdr(ppm, ttinfo->tag, csk->tid, sgl->offset, + xferlen, &ttinfo->hdr); - if (gl) { - int npods = (gl->nelem + PPOD_PAGES_MAX - 1) - >> PPOD_PAGES_SHIFT; - pr_info("cdev 0x%p, ddp %d + %d.\n", cdev, i, npods); - kfree(gl); - i += npods; - } else - i++; + if (cdev->flags & CXGBI_FLAG_USE_PPOD_OFLDQ) { + /* write ppod from xmit_pdu (of iscsi_scsi_command pdu) */ + ttinfo->flags |= CXGBI_PPOD_INFO_FLAG_VALID; + } else { + /* write ppod from control queue now */ + err = cdev->csk_ddp_set_map(ppm, csk, ttinfo); + if (err < 0) + goto rel_ppods; } - cxgbi_free_big_mem(ddp); -} - -int cxgbi_ddp_cleanup(struct cxgbi_device *cdev) -{ - struct cxgbi_ddp_info *ddp = cdev->ddp; - log_debug(1 << CXGBI_DBG_DDP, - "cdev 0x%p, release ddp 0x%p.\n", cdev, ddp); - cdev->ddp = NULL; - if (ddp) - return kref_put(&ddp->refcnt, ddp_destroy); return 0; -} -EXPORT_SYMBOL_GPL(cxgbi_ddp_cleanup); -int cxgbi_ddp_init(struct cxgbi_device *cdev, - unsigned int llimit, unsigned int ulimit, - unsigned int max_txsz, unsigned int max_rxsz) -{ - struct cxgbi_ddp_info *ddp; - unsigned int ppmax, bits; +rel_ppods: + cxgbi_ppm_ppod_release(ppm, ttinfo->idx); - ppmax = (ulimit - llimit + 1) >> PPOD_SIZE_SHIFT; - bits = __ilog2_u32(ppmax) + 1; - if (bits > PPOD_IDX_MAX_SIZE) - bits = PPOD_IDX_MAX_SIZE; - ppmax = (1 << (bits - 1)) - 1; - - ddp = cxgbi_alloc_big_mem(sizeof(struct cxgbi_ddp_info) + - ppmax * (sizeof(struct cxgbi_gather_list *) + - sizeof(struct sk_buff *)), - GFP_KERNEL); - if (!ddp) { - pr_warn("cdev 0x%p, ddp ppmax %u OOM.\n", cdev, ppmax); - return -ENOMEM; + if (ttinfo->flags & CXGBI_PPOD_INFO_FLAG_MAPPED) { + ttinfo->flags &= ~CXGBI_PPOD_INFO_FLAG_MAPPED; + dma_unmap_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE); } - ddp->gl_map = (struct cxgbi_gather_list **)(ddp + 1); - cdev->ddp = ddp; - - spin_lock_init(&ddp->map_lock); - kref_init(&ddp->refcnt); - - ddp->cdev = cdev; - ddp->pdev = cdev->pdev; - ddp->llimit = llimit; - ddp->ulimit = ulimit; - ddp->max_txsz = min_t(unsigned int, max_txsz, ULP2_MAX_PKT_SIZE); - ddp->max_rxsz = min_t(unsigned int, max_rxsz, ULP2_MAX_PKT_SIZE); - ddp->nppods = ppmax; - ddp->idx_last = ppmax; - ddp->idx_bits = bits; - ddp->idx_mask = (1 << bits) - 1; - ddp->rsvd_tag_mask = (1 << (bits + PPOD_IDX_SHIFT)) - 1; - - cdev->tag_format.sw_bits = sw_tag_idx_bits + sw_tag_age_bits; - cdev->tag_format.rsvd_bits = ddp->idx_bits; - cdev->tag_format.rsvd_shift = PPOD_IDX_SHIFT; - cdev->tag_format.rsvd_mask = (1 << cdev->tag_format.rsvd_bits) - 1; - - pr_info("%s tag format, sw %u, rsvd %u,%u, mask 0x%x.\n", - cdev->ports[0]->name, cdev->tag_format.sw_bits, - cdev->tag_format.rsvd_bits, cdev->tag_format.rsvd_shift, - cdev->tag_format.rsvd_mask); - - cdev->tx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD, - ddp->max_txsz - ISCSI_PDU_NONPAYLOAD_LEN); - cdev->rx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD, - ddp->max_rxsz - ISCSI_PDU_NONPAYLOAD_LEN); - - log_debug(1 << CXGBI_DBG_DDP, - "%s max payload size: %u/%u, %u/%u.\n", - cdev->ports[0]->name, cdev->tx_max_size, ddp->max_txsz, - cdev->rx_max_size, ddp->max_rxsz); - return 0; + return -EINVAL; } -EXPORT_SYMBOL_GPL(cxgbi_ddp_init); - -/* - * APIs interacting with open-iscsi libraries - */ - -static unsigned char padding[4]; static void task_release_itt(struct iscsi_task *task, itt_t hdr_itt) { struct scsi_cmnd *sc = task->sc; struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data; struct cxgbi_conn *cconn = tcp_conn->dd_data; - struct cxgbi_hba *chba = cconn->chba; - struct cxgbi_tag_format *tformat = &chba->cdev->tag_format; + struct cxgbi_device *cdev = cconn->chba->cdev; + struct cxgbi_ppm *ppm = cdev->cdev2ppm(cdev); u32 tag = ntohl((__force u32)hdr_itt); log_debug(1 << CXGBI_DBG_DDP, - "cdev 0x%p, release tag 0x%x.\n", chba->cdev, tag); + "cdev 0x%p, task 0x%p, release tag 0x%x.\n", + cdev, task, tag); if (sc && (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE) && - cxgbi_is_ddp_tag(tformat, tag)) - ddp_tag_release(chba, tag); + cxgbi_ppm_is_ddp_tag(ppm, tag)) { + struct cxgbi_task_data *tdata = iscsi_task_cxgbi_data(task); + struct cxgbi_task_tag_info *ttinfo = &tdata->ttinfo; + + if (!(cdev->flags & CXGBI_FLAG_USE_PPOD_OFLDQ)) + cdev->csk_ddp_clear_map(cdev, ppm, ttinfo); + cxgbi_ppm_ppod_release(ppm, ttinfo->idx); + dma_unmap_sg(&ppm->pdev->dev, ttinfo->sgl, ttinfo->nents, + DMA_FROM_DEVICE); + } +} + +static inline u32 cxgbi_build_sw_tag(u32 idx, u32 age) +{ + /* assume idx and age both are < 0x7FFF (32767) */ + return (idx << 16) | age; } static int task_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt) @@ -1710,34 +1433,41 @@ static int task_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt) struct iscsi_session *sess = conn->session; struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct cxgbi_conn *cconn = tcp_conn->dd_data; - struct cxgbi_hba *chba = cconn->chba; - struct cxgbi_tag_format *tformat = &chba->cdev->tag_format; - u32 sw_tag = (sess->age << cconn->task_idx_bits) | task->itt; + struct cxgbi_device *cdev = cconn->chba->cdev; + struct cxgbi_ppm *ppm = cdev->cdev2ppm(cdev); + u32 sw_tag = cxgbi_build_sw_tag(task->itt, sess->age); u32 tag = 0; int err = -EINVAL; if (sc && - (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE)) { - err = cxgbi_ddp_reserve(cconn->cep->csk, &tag, sw_tag, - scsi_in(sc)->length, - scsi_in(sc)->table.sgl, - scsi_in(sc)->table.nents, - GFP_ATOMIC); - if (err < 0) - log_debug(1 << CXGBI_DBG_DDP, - "csk 0x%p, R task 0x%p, %u,%u, no ddp.\n", - cconn->cep->csk, task, scsi_in(sc)->length, - scsi_in(sc)->table.nents); + (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE) + ) { + struct cxgbi_task_data *tdata = iscsi_task_cxgbi_data(task); + struct cxgbi_task_tag_info *ttinfo = &tdata->ttinfo; + + scmd_get_params(sc, &ttinfo->sgl, &ttinfo->nents, + &tdata->dlen, 0); + err = cxgbi_ddp_reserve(cconn, tdata, sw_tag, tdata->dlen); + if (!err) + tag = ttinfo->tag; + else + log_debug(1 << CXGBI_DBG_DDP, + "csk 0x%p, R task 0x%p, %u,%u, no ddp.\n", + cconn->cep->csk, task, tdata->dlen, + ttinfo->nents); } - if (err < 0) - tag = cxgbi_set_non_ddp_tag(tformat, sw_tag); + if (err < 0) { + err = cxgbi_ppm_make_non_ddp_tag(ppm, sw_tag, &tag); + if (err < 0) + return err; + } /* the itt need to sent in big-endian order */ *hdr_itt = (__force itt_t)htonl(tag); log_debug(1 << CXGBI_DBG_DDP, - "cdev 0x%p, task 0x%p, 0x%x(0x%x,0x%x)->0x%x/0x%x.\n", - chba->cdev, task, sw_tag, task->itt, sess->age, tag, *hdr_itt); + "cdev 0x%p, task 0x%p, 0x%x(0x%x,0x%x)->0x%x/0x%x.\n", + cdev, task, sw_tag, task->itt, sess->age, tag, *hdr_itt); return 0; } @@ -1746,19 +1476,24 @@ void cxgbi_parse_pdu_itt(struct iscsi_conn *conn, itt_t itt, int *idx, int *age) struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct cxgbi_conn *cconn = tcp_conn->dd_data; struct cxgbi_device *cdev = cconn->chba->cdev; - u32 tag = ntohl((__force u32) itt); + struct cxgbi_ppm *ppm = cdev->cdev2ppm(cdev); + u32 tag = ntohl((__force u32)itt); u32 sw_bits; - sw_bits = cxgbi_tag_nonrsvd_bits(&cdev->tag_format, tag); - if (idx) - *idx = sw_bits & ((1 << cconn->task_idx_bits) - 1); - if (age) - *age = (sw_bits >> cconn->task_idx_bits) & ISCSI_AGE_MASK; + if (ppm) { + if (cxgbi_ppm_is_ddp_tag(ppm, tag)) + sw_bits = cxgbi_ppm_get_tag_caller_data(ppm, tag); + else + sw_bits = cxgbi_ppm_decode_non_ddp_tag(ppm, tag); + } else { + sw_bits = tag; + } + cxgbi_decode_sw_tag(sw_bits, idx, age); log_debug(1 << CXGBI_DBG_DDP, - "cdev 0x%p, tag 0x%x/0x%x, -> 0x%x(0x%x,0x%x).\n", - cdev, tag, itt, sw_bits, idx ? *idx : 0xFFFFF, - age ? *age : 0xFF); + "cdev 0x%p, tag 0x%x/0x%x, -> 0x%x(0x%x,0x%x).\n", + cdev, tag, itt, sw_bits, idx ? *idx : 0xFFFFF, + age ? *age : 0xFF); } EXPORT_SYMBOL_GPL(cxgbi_parse_pdu_itt); @@ -2260,7 +1995,9 @@ int cxgbi_conn_xmit_pdu(struct iscsi_task *task) struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data; struct cxgbi_conn *cconn = tcp_conn->dd_data; struct cxgbi_task_data *tdata = iscsi_task_cxgbi_data(task); + struct cxgbi_task_tag_info *ttinfo = &tdata->ttinfo; struct sk_buff *skb = tdata->skb; + struct cxgbi_sock *csk = NULL; unsigned int datalen; int err; @@ -2270,8 +2007,28 @@ int cxgbi_conn_xmit_pdu(struct iscsi_task *task) return 0; } + if (cconn && cconn->cep) + csk = cconn->cep->csk; + if (!csk) { + log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX, + "task 0x%p, csk gone.\n", task); + return -EPIPE; + } + datalen = skb->data_len; tdata->skb = NULL; + + /* write ppod first if using ofldq to write ppod */ + if (ttinfo->flags & CXGBI_PPOD_INFO_FLAG_VALID) { + struct cxgbi_ppm *ppm = csk->cdev->cdev2ppm(csk->cdev); + + ttinfo->flags &= ~CXGBI_PPOD_INFO_FLAG_VALID; + if (csk->cdev->csk_ddp_set_map(ppm, csk, ttinfo) < 0) + pr_err("task 0x%p, ppod writing using ofldq failed.\n", + task); + /* continue. Let fl get the data */ + } + err = cxgbi_sock_send_pdus(cconn->cep->csk, skb); if (err > 0) { int pdulen = err; @@ -2313,12 +2070,14 @@ EXPORT_SYMBOL_GPL(cxgbi_conn_xmit_pdu); void cxgbi_cleanup_task(struct iscsi_task *task) { + struct iscsi_tcp_task *tcp_task = task->dd_data; struct cxgbi_task_data *tdata = iscsi_task_cxgbi_data(task); log_debug(1 << CXGBI_DBG_ISCSI, "task 0x%p, skb 0x%p, itt 0x%x.\n", task, tdata->skb, task->hdr_itt); + tcp_task->dd_data = NULL; /* never reached the xmit task callout */ if (tdata->skb) __kfree_skb(tdata->skb); @@ -2528,6 +2287,7 @@ int cxgbi_bind_conn(struct iscsi_cls_session *cls_session, struct iscsi_conn *conn = cls_conn->dd_data; struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct cxgbi_conn *cconn = tcp_conn->dd_data; + struct cxgbi_ppm *ppm; struct iscsi_endpoint *ep; struct cxgbi_endpoint *cep; struct cxgbi_sock *csk; @@ -2540,7 +2300,10 @@ int cxgbi_bind_conn(struct iscsi_cls_session *cls_session, /* setup ddp pagesize */ cep = ep->dd_data; csk = cep->csk; - err = csk->cdev->csk_ddp_setup_pgidx(csk, csk->tid, page_idx, 0); + + ppm = csk->cdev->cdev2ppm(csk->cdev); + err = csk->cdev->csk_ddp_setup_pgidx(csk, csk->tid, + ppm->tformat.pgsz_idx_dflt, 0); if (err < 0) return err; @@ -2915,16 +2678,7 @@ EXPORT_SYMBOL_GPL(cxgbi_attr_is_visible); static int __init libcxgbi_init_module(void) { - sw_tag_idx_bits = (__ilog2_u32(ISCSI_ITT_MASK)) + 1; - sw_tag_age_bits = (__ilog2_u32(ISCSI_AGE_MASK)) + 1; - pr_info("%s", version); - - pr_info("tag itt 0x%x, %u bits, age 0x%x, %u bits.\n", - ISCSI_ITT_MASK, sw_tag_idx_bits, - ISCSI_AGE_MASK, sw_tag_age_bits); - - ddp_setup_host_page_size(); return 0; } diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h index 9842301..e780273 100644 --- a/drivers/scsi/cxgbi/libcxgbi.h +++ b/drivers/scsi/cxgbi/libcxgbi.h @@ -24,9 +24,12 @@ #include <linux/scatterlist.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> +#include <linux/version.h> #include <scsi/scsi_device.h> #include <scsi/libiscsi_tcp.h> +#include <libcxgb_ppm.h> + enum cxgbi_dbg_flag { CXGBI_DBG_ISCSI, CXGBI_DBG_DDP, @@ -84,92 +87,11 @@ static inline unsigned int cxgbi_ulp_extra_len(int submode) return ulp2_extra_len[submode & 3]; } -/* - * struct pagepod_hdr, pagepod - pagepod format - */ - #define CPL_RX_DDP_STATUS_DDP_SHIFT 16 /* ddp'able */ #define CPL_RX_DDP_STATUS_PAD_SHIFT 19 /* pad error */ #define CPL_RX_DDP_STATUS_HCRC_SHIFT 20 /* hcrc error */ #define CPL_RX_DDP_STATUS_DCRC_SHIFT 21 /* dcrc error */ -struct cxgbi_pagepod_hdr { - u32 vld_tid; - u32 pgsz_tag_clr; - u32 max_offset; - u32 page_offset; - u64 rsvd; -}; - -#define PPOD_PAGES_MAX 4 -struct cxgbi_pagepod { - struct cxgbi_pagepod_hdr hdr; - u64 addr[PPOD_PAGES_MAX + 1]; -}; - -struct cxgbi_tag_format { - unsigned char sw_bits; - unsigned char rsvd_bits; - unsigned char rsvd_shift; - unsigned char filler[1]; - u32 rsvd_mask; -}; - -struct cxgbi_gather_list { - unsigned int tag; - unsigned int length; - unsigned int offset; - unsigned int nelem; - struct page **pages; - dma_addr_t phys_addr[0]; -}; - -struct cxgbi_ddp_info { - struct kref refcnt; - struct cxgbi_device *cdev; - struct pci_dev *pdev; - unsigned int max_txsz; - unsigned int max_rxsz; - unsigned int llimit; - unsigned int ulimit; - unsigned int nppods; - unsigned int idx_last; - unsigned char idx_bits; - unsigned char filler[3]; - unsigned int idx_mask; - unsigned int rsvd_tag_mask; - spinlock_t map_lock; - struct cxgbi_gather_list **gl_map; -}; - -#define DDP_PGIDX_MAX 4 -#define DDP_THRESHOLD 2048 - -#define PPOD_PAGES_SHIFT 2 /* 4 pages per pod */ - -#define PPOD_SIZE sizeof(struct cxgbi_pagepod) /* 64 */ -#define PPOD_SIZE_SHIFT 6 - -#define ULPMEM_DSGL_MAX_NPPODS 16 /* 1024/PPOD_SIZE */ -#define ULPMEM_IDATA_MAX_NPPODS 4 /* 256/PPOD_SIZE */ -#define PCIE_MEMWIN_MAX_NPPODS 16 /* 1024/PPOD_SIZE */ - -#define PPOD_COLOR_SHIFT 0 -#define PPOD_COLOR(x) ((x) << PPOD_COLOR_SHIFT) - -#define PPOD_IDX_SHIFT 6 -#define PPOD_IDX_MAX_SIZE 24 - -#define PPOD_TID_SHIFT 0 -#define PPOD_TID(x) ((x) << PPOD_TID_SHIFT) - -#define PPOD_TAG_SHIFT 6 -#define PPOD_TAG(x) ((x) << PPOD_TAG_SHIFT) - -#define PPOD_VALID_SHIFT 24 -#define PPOD_VALID(x) ((x) << PPOD_VALID_SHIFT) -#define PPOD_VALID_FLAG PPOD_VALID(1U) - /* * sge_opaque_hdr - * Opaque version of structure the SGE stores at skb->head of TX_DATA packets @@ -279,6 +201,8 @@ struct cxgbi_skb_tx_cb { enum cxgbi_skcb_flags { SKCBF_TX_NEED_HDR, /* packet needs a header */ + SKCBF_TX_MEM_WRITE, /* memory write */ + SKCBF_TX_FLAG_COMPL, /* wr completion flag */ SKCBF_RX_COALESCED, /* received whole pdu */ SKCBF_RX_HDR, /* received pdu header */ SKCBF_RX_DATA, /* received pdu payload */ @@ -527,6 +451,9 @@ struct cxgbi_ports_map { #define CXGBI_FLAG_DEV_T4 0x2 #define CXGBI_FLAG_ADAPTER_RESET 0x4 #define CXGBI_FLAG_IPV4_SET 0x10 +#define CXGBI_FLAG_USE_PPOD_OFLDQ 0x40 +#define CXGBI_FLAG_DDP_OFF 0x100 + struct cxgbi_device { struct list_head list_head; struct list_head rcu_node; @@ -548,15 +475,14 @@ struct cxgbi_device { unsigned int tx_max_size; unsigned int rx_max_size; struct cxgbi_ports_map pmap; - struct cxgbi_tag_format tag_format; - struct cxgbi_ddp_info *ddp; void (*dev_ddp_cleanup)(struct cxgbi_device *); - int (*csk_ddp_set)(struct cxgbi_sock *, struct cxgbi_pagepod_hdr *, - unsigned int, unsigned int, - struct cxgbi_gather_list *); - void (*csk_ddp_clear)(struct cxgbi_hba *, - unsigned int, unsigned int, unsigned int); + struct cxgbi_ppm* (*cdev2ppm)(struct cxgbi_device *); + int (*csk_ddp_set_map)(struct cxgbi_ppm *, struct cxgbi_sock *, + struct cxgbi_task_tag_info *); + void (*csk_ddp_clear_map)(struct cxgbi_device *cdev, + struct cxgbi_ppm *, + struct cxgbi_task_tag_info *); int (*csk_ddp_setup_digest)(struct cxgbi_sock *, unsigned int, int, int, int); int (*csk_ddp_setup_pgidx)(struct cxgbi_sock *, @@ -580,6 +506,8 @@ struct cxgbi_conn { struct iscsi_conn *iconn; struct cxgbi_hba *chba; u32 task_idx_bits; + unsigned int ddp_full; + unsigned int ddp_tag_full; }; struct cxgbi_endpoint { @@ -593,85 +521,15 @@ struct cxgbi_task_data { unsigned short nr_frags; struct page_frag frags[MAX_PDU_FRAGS]; struct sk_buff *skb; + unsigned int dlen; unsigned int offset; unsigned int count; unsigned int sgoffset; + struct cxgbi_task_tag_info ttinfo; }; #define iscsi_task_cxgbi_data(task) \ ((task)->dd_data + sizeof(struct iscsi_tcp_task)) -static inline int cxgbi_is_ddp_tag(struct cxgbi_tag_format *tformat, u32 tag) -{ - return !(tag & (1 << (tformat->rsvd_bits + tformat->rsvd_shift - 1))); -} - -static inline int cxgbi_sw_tag_usable(struct cxgbi_tag_format *tformat, - u32 sw_tag) -{ - sw_tag >>= (32 - tformat->rsvd_bits); - return !sw_tag; -} - -static inline u32 cxgbi_set_non_ddp_tag(struct cxgbi_tag_format *tformat, - u32 sw_tag) -{ - unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1; - u32 mask = (1 << shift) - 1; - - if (sw_tag && (sw_tag & ~mask)) { - u32 v1 = sw_tag & ((1 << shift) - 1); - u32 v2 = (sw_tag >> (shift - 1)) << shift; - - return v2 | v1 | 1 << shift; - } - - return sw_tag | 1 << shift; -} - -static inline u32 cxgbi_ddp_tag_base(struct cxgbi_tag_format *tformat, - u32 sw_tag) -{ - u32 mask = (1 << tformat->rsvd_shift) - 1; - - if (sw_tag && (sw_tag & ~mask)) { - u32 v1 = sw_tag & mask; - u32 v2 = sw_tag >> tformat->rsvd_shift; - - v2 <<= tformat->rsvd_bits + tformat->rsvd_shift; - - return v2 | v1; - } - - return sw_tag; -} - -static inline u32 cxgbi_tag_rsvd_bits(struct cxgbi_tag_format *tformat, - u32 tag) -{ - if (cxgbi_is_ddp_tag(tformat, tag)) - return (tag >> tformat->rsvd_shift) & tformat->rsvd_mask; - - return 0; -} - -static inline u32 cxgbi_tag_nonrsvd_bits(struct cxgbi_tag_format *tformat, - u32 tag) -{ - unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1; - u32 v1, v2; - - if (cxgbi_is_ddp_tag(tformat, tag)) { - v1 = tag & ((1 << tformat->rsvd_shift) - 1); - v2 = (tag >> (shift + 1)) << tformat->rsvd_shift; - } else { - u32 mask = (1 << shift) - 1; - tag &= ~(1 << shift); - v1 = tag & mask; - v2 = (tag >> 1) & ~mask; - } - return v1 | v2; -} - static inline void *cxgbi_alloc_big_mem(unsigned int size, gfp_t gfp) { @@ -749,7 +607,11 @@ int cxgbi_ddp_init(struct cxgbi_device *, unsigned int, unsigned int, unsigned int, unsigned int); int cxgbi_ddp_cleanup(struct cxgbi_device *); void cxgbi_ddp_page_size_factor(int *); -void cxgbi_ddp_ppod_clear(struct cxgbi_pagepod *); -void cxgbi_ddp_ppod_set(struct cxgbi_pagepod *, struct cxgbi_pagepod_hdr *, - struct cxgbi_gather_list *, unsigned int); +void cxgbi_ddp_set_one_ppod(struct cxgbi_pagepod *, + struct cxgbi_task_tag_info *, + struct scatterlist **sg_pp, unsigned int *sg_off); +void cxgbi_ddp_ppm_setup(void **ppm_pp, struct cxgbi_device *, + struct cxgbi_tag_format *, unsigned int ppmax, + unsigned int llimit, unsigned int start, + unsigned int rsvd_factor); #endif /*__LIBCXGBI_H__*/ diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index d6a691e..d6803a9 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -10093,6 +10093,7 @@ static int ipr_probe_ioa(struct pci_dev *pdev, ioa_cfg->intr_flag = IPR_USE_MSI; else { ioa_cfg->intr_flag = IPR_USE_LSI; + ioa_cfg->clear_isr = 1; ioa_cfg->nvectors = 1; dev_info(&pdev->dev, "Cannot enable MSI.\n"); } diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 5649c20..a92a62d 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2548,7 +2548,7 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha, if (!vha->flags.online) return; - if (rsp->msix->cpuid != smp_processor_id()) { + if (rsp->msix && rsp->msix->cpuid != smp_processor_id()) { /* if kernel does not notify qla of IRQ's CPU change, * then set it here. */ diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index ff41c31..eaccd65 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -429,7 +429,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, * here, and we don't know what device it is * trying to work with, leave it as-is. */ - vmax = 8; /* max length of vendor */ + vmax = sizeof(devinfo->vendor); vskip = vendor; while (vmax > 0 && *vskip == ' ') { vmax--; @@ -439,7 +439,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, while (vmax > 0 && vskip[vmax - 1] == ' ') --vmax; - mmax = 16; /* max length of model */ + mmax = sizeof(devinfo->model); mskip = model; while (mmax > 0 && *mskip == ' ') { mmax--; @@ -455,10 +455,12 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, * Behave like the older version of get_device_flags. */ if (memcmp(devinfo->vendor, vskip, vmax) || - devinfo->vendor[vmax]) + (vmax < sizeof(devinfo->vendor) && + devinfo->vendor[vmax])) continue; if (memcmp(devinfo->model, mskip, mmax) || - devinfo->model[mmax]) + (mmax < sizeof(devinfo->model) && + devinfo->model[mmax])) continue; return devinfo; } else { diff --git a/drivers/target/iscsi/cxgbit/Kconfig b/drivers/target/iscsi/cxgbit/Kconfig index c9b6a3c..bc6c1d5 100644 --- a/drivers/target/iscsi/cxgbit/Kconfig +++ b/drivers/target/iscsi/cxgbit/Kconfig @@ -1,7 +1,7 @@ config ISCSI_TARGET_CXGB4 tristate "Chelsio iSCSI target offload driver" depends on ISCSI_TARGET && CHELSIO_T4 && INET - select CHELSIO_T4_UWIRE + select CHELSIO_LIB ---help--- To compile this driver as module, choose M here: the module will be called cxgbit. diff --git a/drivers/target/iscsi/cxgbit/Makefile b/drivers/target/iscsi/cxgbit/Makefile index bd56c07..4893ec2 100644 --- a/drivers/target/iscsi/cxgbit/Makefile +++ b/drivers/target/iscsi/cxgbit/Makefile @@ -1,4 +1,5 @@ ccflags-y := -Idrivers/net/ethernet/chelsio/cxgb4 +ccflags-y += -Idrivers/net/ethernet/chelsio/libcxgb ccflags-y += -Idrivers/target/iscsi obj-$(CONFIG_ISCSI_TARGET_CXGB4) += cxgbit.o diff --git a/drivers/target/iscsi/cxgbit/cxgbit.h b/drivers/target/iscsi/cxgbit/cxgbit.h index 625c7f6..9038869 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit.h +++ b/drivers/target/iscsi/cxgbit/cxgbit.h @@ -37,7 +37,7 @@ #include "cxgb4.h" #include "cxgb4_uld.h" #include "l2t.h" -#include "cxgb4_ppm.h" +#include "libcxgb_ppm.h" #include "cxgbit_lro.h" extern struct mutex cdev_list_lock; diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c index 60dccd0..27dd11a 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_main.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c @@ -26,6 +26,8 @@ void _cxgbit_free_cdev(struct kref *kref) struct cxgbit_device *cdev; cdev = container_of(kref, struct cxgbit_device, kref); + + cxgbi_ppm_release(cdev2ppm(cdev)); kfree(cdev); } diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index f973bfc..1e93a37 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -366,34 +366,22 @@ static void to_utf8(struct vc_data *vc, uint c) static void do_compute_shiftstate(void) { - unsigned int i, j, k, sym, val; + unsigned int k, sym, val; shift_state = 0; memset(shift_down, 0, sizeof(shift_down)); - for (i = 0; i < ARRAY_SIZE(key_down); i++) { - - if (!key_down[i]) + for_each_set_bit(k, key_down, min(NR_KEYS, KEY_CNT)) { + sym = U(key_maps[0][k]); + if (KTYP(sym) != KT_SHIFT && KTYP(sym) != KT_SLOCK) continue; - k = i * BITS_PER_LONG; - - for (j = 0; j < BITS_PER_LONG; j++, k++) { - - if (!test_bit(k, key_down)) - continue; + val = KVAL(sym); + if (val == KVAL(K_CAPSSHIFT)) + val = KVAL(K_SHIFT); - sym = U(key_maps[0][k]); - if (KTYP(sym) != KT_SHIFT && KTYP(sym) != KT_SLOCK) - continue; - - val = KVAL(sym); - if (val == KVAL(K_CAPSSHIFT)) - val = KVAL(K_SHIFT); - - shift_down[val]++; - shift_state |= (1 << val); - } + shift_down[val]++; + shift_state |= BIT(val); } } diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c index 076970a..4ce10bc 100644 --- a/drivers/xen/xen-acpi-processor.c +++ b/drivers/xen/xen-acpi-processor.c @@ -423,36 +423,7 @@ upload: return 0; } -static int __init check_prereq(void) -{ - struct cpuinfo_x86 *c = &cpu_data(0); - - if (!xen_initial_domain()) - return -ENODEV; - - if (!acpi_gbl_FADT.smi_command) - return -ENODEV; - - if (c->x86_vendor == X86_VENDOR_INTEL) { - if (!cpu_has(c, X86_FEATURE_EST)) - return -ENODEV; - return 0; - } - if (c->x86_vendor == X86_VENDOR_AMD) { - /* Copied from powernow-k8.h, can't include ../cpufreq/powernow - * as we get compile warnings for the static functions. - */ -#define CPUID_FREQ_VOLT_CAPABILITIES 0x80000007 -#define USE_HW_PSTATE 0x00000080 - u32 eax, ebx, ecx, edx; - cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx); - if ((edx & USE_HW_PSTATE) != USE_HW_PSTATE) - return -ENODEV; - return 0; - } - return -ENODEV; -} /* acpi_perf_data is a pointer to percpu data. */ static struct acpi_processor_performance __percpu *acpi_perf_data; @@ -509,10 +480,10 @@ struct notifier_block xen_acpi_processor_resume_nb = { static int __init xen_acpi_processor_init(void) { unsigned int i; - int rc = check_prereq(); + int rc; - if (rc) - return rc; + if (!xen_initial_domain()) + return -ENODEV; nr_acpi_bits = get_max_acpi_id() + 1; acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index cacf30d..7487971 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -316,11 +316,18 @@ static int xenbus_write_transaction(unsigned msg_type, rc = -ENOMEM; goto out; } + } else { + list_for_each_entry(trans, &u->transactions, list) + if (trans->handle.id == u->u.msg.tx_id) + break; + if (&trans->list == &u->transactions) + return -ESRCH; } reply = xenbus_dev_request_and_reply(&u->u.msg); if (IS_ERR(reply)) { - kfree(trans); + if (msg_type == XS_TRANSACTION_START) + kfree(trans); rc = PTR_ERR(reply); goto out; } @@ -333,12 +340,7 @@ static int xenbus_write_transaction(unsigned msg_type, list_add(&trans->list, &u->transactions); } } else if (u->u.msg.type == XS_TRANSACTION_END) { - list_for_each_entry(trans, &u->transactions, list) - if (trans->handle.id == u->u.msg.tx_id) - break; - BUG_ON(&trans->list == &u->transactions); list_del(&trans->list); - kfree(trans); } diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 374b12a..22f7cd7 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -232,10 +232,10 @@ static void transaction_resume(void) void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg) { void *ret; - struct xsd_sockmsg req_msg = *msg; + enum xsd_sockmsg_type type = msg->type; int err; - if (req_msg.type == XS_TRANSACTION_START) + if (type == XS_TRANSACTION_START) transaction_start(); mutex_lock(&xs_state.request_mutex); @@ -249,12 +249,8 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg) mutex_unlock(&xs_state.request_mutex); - if (IS_ERR(ret)) - return ret; - if ((msg->type == XS_TRANSACTION_END) || - ((req_msg.type == XS_TRANSACTION_START) && - (msg->type == XS_ERROR))) + ((type == XS_TRANSACTION_START) && (msg->type == XS_ERROR))) transaction_end(); return ret; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index f4645c5..e2e7c74 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -853,7 +853,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, struct p9_fid *fid, *inode_fid; struct dentry *res = NULL; - if (d_unhashed(dentry)) { + if (d_in_lookup(dentry)) { res = v9fs_vfs_lookup(dir, dentry, 0); if (IS_ERR(res)) return PTR_ERR(res); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index a34702c..1b51eaa 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -254,7 +254,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, struct posix_acl *pacl = NULL, *dacl = NULL; struct dentry *res = NULL; - if (d_unhashed(dentry)) { + if (d_in_lookup(dentry)) { res = v9fs_vfs_lookup(dir, dentry, 0); if (IS_ERR(res)) return PTR_ERR(res); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index ce2f579..0daaf7c 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -394,7 +394,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, if ((flags & O_CREAT) && !req->r_reply_info.head->is_dentry) err = ceph_handle_notrace_create(dir, dentry); - if (d_unhashed(dentry)) { + if (d_in_lookup(dentry)) { dn = ceph_finish_lookup(req, dentry, err); if (IS_ERR(dn)) err = PTR_ERR(dn); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index c3eb998..fb0903f 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -445,7 +445,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, * Check for hashed negative dentry. We have already revalidated * the dentry and it is fine. No need to perform another lookup. */ - if (!d_unhashed(direntry)) + if (!d_in_lookup(direntry)) return -ENOENT; res = cifs_lookup(inode, direntry, 0); diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 33b7ee3..bbc1252 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -357,8 +357,6 @@ configfs_write_bin_file(struct file *file, const char __user *buf, len = simple_write_to_buffer(buffer->bin_buffer, buffer->bin_buffer_size, ppos, buf, count); - if (len > 0) - *ppos += len; out: mutex_unlock(&buffer->mutex); return len; diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 0d8eb34..e5e29f8 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -45,7 +45,7 @@ * ecryptfs_to_hex * @dst: Buffer to take hex character representation of contents of * src; must be at least of size (src_size * 2) - * @src: Buffer to be converted to a hex string respresentation + * @src: Buffer to be converted to a hex string representation * @src_size: number of bytes to convert */ void ecryptfs_to_hex(char *dst, char *src, size_t src_size) @@ -60,7 +60,7 @@ void ecryptfs_to_hex(char *dst, char *src, size_t src_size) * ecryptfs_from_hex * @dst: Buffer to take the bytes from src hex; must be at least of * size (src_size / 2) - * @src: Buffer to be converted from a hex string respresentation to raw value + * @src: Buffer to be converted from a hex string representation to raw value * @dst_size: size of dst buffer, or number of hex characters pairs to convert */ void ecryptfs_from_hex(char *dst, char *src, int dst_size) @@ -953,7 +953,7 @@ struct ecryptfs_cipher_code_str_map_elem { }; /* Add support for additional ciphers by adding elements here. The - * cipher_code is whatever OpenPGP applicatoins use to identify the + * cipher_code is whatever OpenPGP applications use to identify the * ciphers. List in order of probability. */ static struct ecryptfs_cipher_code_str_map_elem ecryptfs_cipher_code_str_map[] = { @@ -1410,7 +1410,7 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry, * * Common entry point for reading file metadata. From here, we could * retrieve the header information from the header region of the file, - * the xattr region of the file, or some other repostory that is + * the xattr region of the file, or some other repository that is * stored separately from the file itself. The current implementation * supports retrieving the metadata information from the file contents * and from the xattr region. diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 7000b96..ca4e837 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -169,9 +169,22 @@ out: return rc; } +static int ecryptfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct file *lower_file = ecryptfs_file_to_lower(file); + /* + * Don't allow mmap on top of file systems that don't support it + * natively. If FILESYSTEM_MAX_STACK_DEPTH > 2 or ecryptfs + * allows recursive mounting, this will need to be extended. + */ + if (!lower_file->f_op->mmap) + return -ENODEV; + return generic_file_mmap(file, vma); +} + /** * ecryptfs_open - * @inode: inode speciying file to open + * @inode: inode specifying file to open * @file: Structure to return filled in * * Opens the file specified by inode. @@ -240,7 +253,7 @@ out: /** * ecryptfs_dir_open - * @inode: inode speciying file to open + * @inode: inode specifying file to open * @file: Structure to return filled in * * Opens the file specified by inode. @@ -403,7 +416,7 @@ const struct file_operations ecryptfs_main_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = ecryptfs_compat_ioctl, #endif - .mmap = generic_file_mmap, + .mmap = ecryptfs_mmap, .open = ecryptfs_open, .flush = ecryptfs_flush, .release = ecryptfs_release, diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index e818f5a..866bb18 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -25,7 +25,6 @@ #include <linux/slab.h> #include <linux/wait.h> #include <linux/mount.h> -#include <linux/file.h> #include "ecryptfs_kernel.h" struct ecryptfs_open_req { @@ -148,7 +147,7 @@ int ecryptfs_privileged_open(struct file **lower_file, flags |= IS_RDONLY(d_inode(lower_dentry)) ? O_RDONLY : O_RDWR; (*lower_file) = dentry_open(&req.path, flags, cred); if (!IS_ERR(*lower_file)) - goto have_file; + goto out; if ((flags & O_ACCMODE) == O_RDONLY) { rc = PTR_ERR((*lower_file)); goto out; @@ -166,16 +165,8 @@ int ecryptfs_privileged_open(struct file **lower_file, mutex_unlock(&ecryptfs_kthread_ctl.mux); wake_up(&ecryptfs_kthread_ctl.wait); wait_for_completion(&req.done); - if (IS_ERR(*lower_file)) { + if (IS_ERR(*lower_file)) rc = PTR_ERR(*lower_file); - goto out; - } -have_file: - if ((*lower_file)->f_op->mmap == NULL) { - fput(*lower_file); - *lower_file = NULL; - rc = -EMEDIUMTYPE; - } out: return rc; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 1698132..6120044 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -738,8 +738,7 @@ static void ecryptfs_free_kmem_caches(void) struct ecryptfs_cache_info *info; info = &ecryptfs_cache_infos[i]; - if (*(info->cache)) - kmem_cache_destroy(*(info->cache)); + kmem_cache_destroy(*(info->cache)); } } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 989a2ce..fe7e83a 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -483,9 +483,9 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) goto out_free; } inode->i_state |= I_WB_SWITCH; + __iget(inode); spin_unlock(&inode->i_lock); - ihold(inode); isw->inode = inode; atomic_inc(&isw_nr_in_flight); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 264f07c..cca7b04 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -480,7 +480,7 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry, struct fuse_conn *fc = get_fuse_conn(dir); struct dentry *res = NULL; - if (d_unhashed(entry)) { + if (d_in_lookup(entry)) { res = fuse_lookup(dir, entry, 0); if (IS_ERR(res)) return PTR_ERR(res); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 21dc784..9bad79f 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1189,7 +1189,7 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry, struct dentry *d; bool excl = !!(flags & O_EXCL); - if (!d_unhashed(dentry)) + if (!d_in_lookup(dentry)) goto skip_lookup; d = __gfs2_lookup(dir, dentry, file, opened); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index d8015a0..19d93d0 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1485,11 +1485,13 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned open_flags, umode_t mode, int *opened) { + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); struct nfs_open_context *ctx; struct dentry *res; struct iattr attr = { .ia_valid = ATTR_OPEN }; struct inode *inode; unsigned int lookup_flags = 0; + bool switched = false; int err; /* Expect a negative dentry */ @@ -1504,7 +1506,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, /* NFS only supports OPEN on regular files */ if ((open_flags & O_DIRECTORY)) { - if (!d_unhashed(dentry)) { + if (!d_in_lookup(dentry)) { /* * Hashed negative dentry with O_DIRECTORY: dentry was * revalidated and is fine, no need to perform lookup @@ -1528,6 +1530,17 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, attr.ia_size = 0; } + if (!(open_flags & O_CREAT) && !d_in_lookup(dentry)) { + d_drop(dentry); + switched = true; + dentry = d_alloc_parallel(dentry->d_parent, + &dentry->d_name, &wq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + if (unlikely(!d_in_lookup(dentry))) + return finish_no_open(file, dentry); + } + ctx = create_nfs_open_context(dentry, open_flags); err = PTR_ERR(ctx); if (IS_ERR(ctx)) @@ -1563,14 +1576,23 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); put_nfs_open_context(ctx); out: + if (unlikely(switched)) { + d_lookup_done(dentry); + dput(dentry); + } return err; no_open: res = nfs_lookup(dir, dentry, lookup_flags); - err = PTR_ERR(res); + if (switched) { + d_lookup_done(dentry); + if (!res) + res = dentry; + else + dput(dentry); + } if (IS_ERR(res)) - goto out; - + return PTR_ERR(res); return finish_no_open(file, res); } EXPORT_SYMBOL_GPL(nfs_atomic_open); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index c2a6b08..5c9d2d8 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -505,6 +505,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) struct dentry *upper; struct dentry *opaquedir = NULL; int err; + int flags = 0; if (WARN_ON(!workdir)) return -EROFS; @@ -534,46 +535,39 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) if (err) goto out_dput; - whiteout = ovl_whiteout(workdir, dentry); - err = PTR_ERR(whiteout); - if (IS_ERR(whiteout)) + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) goto out_unlock; - upper = ovl_dentry_upper(dentry); - if (!upper) { - upper = lookup_one_len(dentry->d_name.name, upperdir, - dentry->d_name.len); - err = PTR_ERR(upper); - if (IS_ERR(upper)) - goto kill_whiteout; - - err = ovl_do_rename(wdir, whiteout, udir, upper, 0); - dput(upper); - if (err) - goto kill_whiteout; - } else { - int flags = 0; + err = -ESTALE; + if ((opaquedir && upper != opaquedir) || + (!opaquedir && ovl_dentry_upper(dentry) && + upper != ovl_dentry_upper(dentry))) { + goto out_dput_upper; + } - if (opaquedir) - upper = opaquedir; - err = -ESTALE; - if (upper->d_parent != upperdir) - goto kill_whiteout; + whiteout = ovl_whiteout(workdir, dentry); + err = PTR_ERR(whiteout); + if (IS_ERR(whiteout)) + goto out_dput_upper; - if (is_dir) - flags |= RENAME_EXCHANGE; + if (d_is_dir(upper)) + flags = RENAME_EXCHANGE; - err = ovl_do_rename(wdir, whiteout, udir, upper, flags); - if (err) - goto kill_whiteout; + err = ovl_do_rename(wdir, whiteout, udir, upper, flags); + if (err) + goto kill_whiteout; + if (flags) + ovl_cleanup(wdir, upper); - if (is_dir) - ovl_cleanup(wdir, upper); - } ovl_dentry_version_inc(dentry->d_parent); out_d_drop: d_drop(dentry); dput(whiteout); +out_dput_upper: + dput(upper); out_unlock: unlock_rename(workdir, upperdir); out_dput: diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index c831c2e..d1cdc60 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -80,6 +80,9 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) goto out_drop_write; } + if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) + attr->ia_valid &= ~ATTR_MODE; + inode_lock(upperdentry->d_inode); err = notify_change(upperdentry, attr, NULL); if (!err) @@ -410,12 +413,11 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, if (!inode) return NULL; - mode &= S_IFMT; - inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_flags |= S_NOATIME | S_NOCMTIME; + mode &= S_IFMT; switch (mode) { case S_IFDIR: inode->i_private = oe; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 4bd9b5b..cfbca53 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -187,6 +187,7 @@ static inline void ovl_copyattr(struct inode *from, struct inode *to) { to->i_uid = from->i_uid; to->i_gid = from->i_gid; + to->i_mode = from->i_mode; } /* dir.c */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index dbca737..63a6ff2 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1575,6 +1575,12 @@ xfs_ioc_swapext( goto out_put_tmp_file; } + if (f.file->f_op != &xfs_file_operations || + tmp.file->f_op != &xfs_file_operations) { + error = -EINVAL; + goto out_put_tmp_file; + } + ip = XFS_I(file_inode(f.file)); tip = XFS_I(file_inode(tmp.file)); diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h index 797ae2e..29c6912 100644 --- a/include/acpi/acpi_drivers.h +++ b/include/acpi/acpi_drivers.h @@ -78,6 +78,7 @@ /* ACPI PCI Interrupt Link (pci_link.c) */ +int acpi_irq_penalty_init(void); int acpi_pci_link_allocate_irq(acpi_handle handle, int index, int *triggering, int *polarity, char **name); int acpi_pci_link_free_irq(acpi_handle handle); diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 4e4c214..1ff3a76 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -192,7 +192,7 @@ ACPI_INIT_GLOBAL(u8, acpi_gbl_do_not_use_xsdt, FALSE); /* * Optionally support group module level code. */ -ACPI_INIT_GLOBAL(u8, acpi_gbl_group_module_level_code, FALSE); +ACPI_INIT_GLOBAL(u8, acpi_gbl_group_module_level_code, TRUE); /* * Optionally use 32-bit FADT addresses if and when there is a conflict diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 6a67ab9..081d0f2 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -542,15 +542,19 @@ #define INIT_TEXT \ *(.init.text) \ + *(.text.startup) \ MEM_DISCARD(init.text) #define EXIT_DATA \ *(.exit.data) \ + *(.fini_array) \ + *(.dtors) \ MEM_DISCARD(exit.data) \ MEM_DISCARD(exit.rodata) #define EXIT_TEXT \ *(.exit.text) \ + *(.text.exit) \ MEM_DISCARD(exit.text) #define EXIT_CALL \ diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index c801d90..4cecb0b 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -316,6 +316,20 @@ ttm_bo_reference(struct ttm_buffer_object *bo) */ extern int ttm_bo_wait(struct ttm_buffer_object *bo, bool interruptible, bool no_wait); + +/** + * ttm_bo_mem_compat - Check if proposed placement is compatible with a bo + * + * @placement: Return immediately if buffer is busy. + * @mem: The struct ttm_mem_reg indicating the region where the bo resides + * @new_flags: Describes compatible placement found + * + * Returns true if the placement is compatible + */ +extern bool ttm_bo_mem_compat(struct ttm_placement *placement, + struct ttm_mem_reg *mem, + uint32_t *new_flags); + /** * ttm_bo_validate * diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index e6b41f4..3db25df 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -159,6 +159,7 @@ struct bcma_host_ops { #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 +#define BCMA_CORE_SIZE 0x1000 /* Chip IDs of PCIe devices */ #define BCMA_CHIP_ID_BCM4313 0x4313 diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c13e92b..1113423 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -211,7 +211,7 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f const struct bpf_func_proto *bpf_get_trace_printk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, - unsigned long len); + unsigned long off, unsigned long len); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); @@ -224,6 +224,7 @@ void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); +struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i); struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); @@ -288,6 +289,10 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, { return ERR_PTR(-EOPNOTSUPP); } +static inline struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) +{ + return ERR_PTR(-EOPNOTSUPP); +} static inline void bpf_prog_put(struct bpf_prog *prog) { diff --git a/include/linux/filter.h b/include/linux/filter.h index 6fc31ef..a16439b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -368,6 +368,11 @@ struct bpf_skb_data_end { void *data_end; }; +struct xdp_buff { + void *data; + void *data_end; +}; + /* compute the linear packet data range [data, data_end) which * will be accessed by cls_bpf and act_bpf programs */ @@ -429,6 +434,18 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, return BPF_PROG_RUN(prog, skb); } +static inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, + struct xdp_buff *xdp) +{ + u32 ret; + + rcu_read_lock(); + ret = BPF_PROG_RUN(prog, (void *)xdp); + rcu_read_unlock(); + + return ret; +} + static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), @@ -467,7 +484,11 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) } #endif /* CONFIG_DEBUG_SET_MODULE_RONX */ -int sk_filter(struct sock *sk, struct sk_buff *skb); +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); +static inline int sk_filter(struct sock *sk, struct sk_buff *skb) +{ + return sk_filter_trim_cap(sk, skb, 1); +} struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); void bpf_prog_free(struct bpf_prog *fp); @@ -509,6 +530,7 @@ bool bpf_helper_changes_skb_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +void bpf_warn_invalid_xdp_action(u32 act); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 419fb9e..f0a7a03 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -94,7 +94,7 @@ static inline int split_huge_page(struct page *page) void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze); + unsigned long address, bool freeze, struct page *page); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ @@ -102,7 +102,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ - false); \ + false, NULL); \ } while (0) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a805474..56e6069 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -97,6 +97,11 @@ enum mem_cgroup_events_target { #define MEM_CGROUP_ID_SHIFT 16 #define MEM_CGROUP_ID_MAX USHRT_MAX +struct mem_cgroup_id { + int id; + atomic_t ref; +}; + struct mem_cgroup_stat_cpu { long count[MEMCG_NR_STAT]; unsigned long events[MEMCG_NR_EVENTS]; @@ -172,6 +177,9 @@ enum memcg_kmem_state { struct mem_cgroup { struct cgroup_subsys_state css; + /* Private memcg ID. Used to ID objects that outlive the cgroup */ + struct mem_cgroup_id id; + /* Accounted resources */ struct page_counter memory; struct page_counter swap; @@ -330,22 +338,9 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) if (mem_cgroup_disabled()) return 0; - return memcg->css.id; -} - -/** - * mem_cgroup_from_id - look up a memcg from an id - * @id: the id to look up - * - * Caller must hold rcu_read_lock() and use css_tryget() as necessary. - */ -static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) -{ - struct cgroup_subsys_state *css; - - css = css_from_id(id, &memory_cgrp_subsys); - return mem_cgroup_from_css(css); + return memcg->id.id; } +struct mem_cgroup *mem_cgroup_from_id(unsigned short id); /** * parent_mem_cgroup - find the accounting parent of a memcg diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 587cdf9..deaa221 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -291,16 +291,18 @@ enum { MLX4_WQE_CTRL_FORCE_LOOPBACK = 1 << 0, }; +union mlx4_wqe_qpn_vlan { + struct { + __be16 vlan_tag; + u8 ins_vlan; + u8 fence_size; + }; + __be32 bf_qpn; +}; + struct mlx4_wqe_ctrl_seg { __be32 owner_opcode; - union { - struct { - __be16 vlan_tag; - u8 ins_vlan; - u8 fence_size; - }; - __be32 bf_qpn; - }; + union mlx4_wqe_qpn_vlan qpn_vlan; /* * High 24 bits are SRC remote buffer; low 8 bits are flags: * [7] SO (strong ordering) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 49736a3..076df53 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -63,6 +63,7 @@ struct wpan_dev; struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; +struct bpf_prog; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -786,6 +787,7 @@ enum { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, + TC_SETUP_MATCHALL, }; struct tc_cls_u32_offload; @@ -796,9 +798,37 @@ struct tc_to_netdev { u8 tc; struct tc_cls_u32_offload *cls_u32; struct tc_cls_flower_offload *cls_flower; + struct tc_cls_matchall_offload *cls_mall; }; }; +/* These structures hold the attributes of xdp state that are being passed + * to the netdevice through the xdp op. + */ +enum xdp_netdev_command { + /* Set or clear a bpf program used in the earliest stages of packet + * rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee + * is responsible for calling bpf_prog_put on any old progs that are + * stored. In case of error, the callee need not release the new prog + * reference, but on success it takes ownership and must bpf_prog_put + * when it is no longer used. + */ + XDP_SETUP_PROG, + /* Check if a bpf program is set on the device. The callee should + * return true if a program is currently attached and running. + */ + XDP_QUERY_PROG, +}; + +struct netdev_xdp { + enum xdp_netdev_command command; + union { + /* XDP_SETUP_PROG */ + struct bpf_prog *prog; + /* XDP_QUERY_PROG */ + bool prog_attached; + }; +}; /* * This structure defines the management hooks for network devices. @@ -1087,6 +1117,9 @@ struct tc_to_netdev { * appropriate rx headroom value allows avoiding skb head copy on * forward. Setting a negative value resets the rx headroom to the * default value. + * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); + * This function is used to set or query state related to XDP on the + * netdevice. See definition of enum xdp_netdev_command for details. * */ struct net_device_ops { @@ -1271,6 +1304,8 @@ struct net_device_ops { struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); + int (*ndo_xdp)(struct net_device *dev, + struct netdev_xdp *xdp); }; /** @@ -3257,6 +3292,7 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); +int dev_change_xdp_fd(struct net_device *dev, int fd); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); @@ -4175,6 +4211,13 @@ static inline void netif_keep_dst(struct net_device *dev) dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM); } +/* return true if dev can't cope with mtu frames that need vlan tag insertion */ +static inline bool netif_reduces_vlan_mtu(struct net_device *dev) +{ + /* TODO: reserve and use an additional IFF bit, if we get more users */ + return dev->priv_flags & IFF_MACSEC; +} + extern struct pernet_operations __net_initdata loopback_net_ops; /* Logging, debugging and troubleshooting/diagnostic helpers. */ diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index e94e81a..2ad1a2b 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -250,6 +250,10 @@ int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); +unsigned int *xt_alloc_entry_offsets(unsigned int size); +bool xt_find_jump_offset(const unsigned int *offsets, + unsigned int target, unsigned int size); + int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto, bool inv_proto); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e79e6c6..15e55b7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -70,7 +70,7 @@ struct perf_callchain_entry_ctx { }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, - unsigned long len); + unsigned long off, unsigned long len); struct perf_raw_frag { union { diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 5b5a80c..c818772 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -43,10 +43,8 @@ struct posix_acl_entry { }; struct posix_acl { - union { - atomic_t a_refcount; - struct rcu_head a_rcu; - }; + atomic_t a_refcount; + struct rcu_head a_rcu; unsigned int a_count; struct posix_acl_entry a_entries[0]; }; diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index cb4b7e8..eca6f62 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -407,6 +407,7 @@ static inline __must_check void **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; + iter->tags = 0; return NULL; } diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 49eb4f8..2b0fad8 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -158,7 +158,7 @@ struct anon_vma *page_get_anon_vma(struct page *page); /* * rmap interfaces called when adding or removing pte of page */ -void page_move_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); +void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, bool); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h index 0a0d568..f229302 100644 --- a/include/linux/ti_wilink_st.h +++ b/include/linux/ti_wilink_st.h @@ -71,7 +71,7 @@ struct st_proto_s { enum proto_type type; long (*recv) (void *, struct sk_buff *); unsigned char (*match_packet) (const unsigned char *data); - void (*reg_complete_cb) (void *, char data); + void (*reg_complete_cb) (void *, int data); long (*write) (struct sk_buff *skb); void *priv_data; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 77d7fe1..ee7fc47 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -372,6 +372,8 @@ struct hci_dev { atomic_t promisc; + const char *hw_info; + const char *fw_info; struct dentry *debugfs; struct device dev; @@ -1022,6 +1024,10 @@ void hci_unregister_dev(struct hci_dev *hdev); int hci_suspend_dev(struct hci_dev *hdev); int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); +int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); +int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); +void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...); +void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...); int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); int hci_dev_do_close(struct hci_dev *hdev); @@ -1098,9 +1104,6 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); -int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); -int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); - void hci_init_sysfs(struct hci_dev *hdev); void hci_conn_init_sysfs(struct hci_conn *conn); void hci_conn_add_sysfs(struct hci_conn *conn); diff --git a/include/net/dsa.h b/include/net/dsa.h index 52ab18b..2217a3f 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -141,6 +141,7 @@ struct dsa_switch_tree { struct dsa_port { struct net_device *netdev; struct device_node *dn; + unsigned int ageing_time; }; struct dsa_switch { @@ -329,6 +330,7 @@ struct dsa_switch_driver { /* * Bridge integration */ + int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct net_device *bridge); void (*port_bridge_leave)(struct dsa_switch *ds, int port); diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h index cf6c745..d15214d 100644 --- a/include/net/gro_cells.h +++ b/include/net/gro_cells.h @@ -14,27 +14,26 @@ struct gro_cells { struct gro_cell __percpu *cells; }; -static inline void gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) +static inline int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) { struct gro_cell *cell; struct net_device *dev = skb->dev; - if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) { - netif_rx(skb); - return; - } + if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) + return netif_rx(skb); cell = this_cpu_ptr(gcells->cells); if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) { atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); - return; + return NET_RX_DROP; } __skb_queue_tail(&cell->napi_skbs, skb); if (skb_queue_len(&cell->napi_skbs) == 1) napi_schedule(&cell->napi); + return NET_RX_SUCCESS; } /* called under BH context */ diff --git a/include/net/ip.h b/include/net/ip.h index 08f36cd..9742b92 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -47,6 +47,7 @@ struct inet_skb_parm { #define IPSKB_REROUTED BIT(4) #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) +#define IPSKB_FRAG_SEGS BIT(7) u16 frag_max_size; }; diff --git a/include/net/ncsi.h b/include/net/ncsi.h new file mode 100644 index 0000000..1dbf42f --- /dev/null +++ b/include/net/ncsi.h @@ -0,0 +1,52 @@ +#ifndef __NET_NCSI_H +#define __NET_NCSI_H + +/* + * The NCSI device states seen from external. More NCSI device states are + * only visible internally (in net/ncsi/internal.h). When the NCSI device + * is registered, it's in ncsi_dev_state_registered state. The state + * ncsi_dev_state_start is used to drive to choose active package and + * channel. After that, its state is changed to ncsi_dev_state_functional. + * + * The state ncsi_dev_state_stop helps to shut down the currently active + * package and channel while ncsi_dev_state_config helps to reconfigure + * them. + */ +enum { + ncsi_dev_state_registered = 0x0000, + ncsi_dev_state_functional = 0x0100, + ncsi_dev_state_probe = 0x0200, + ncsi_dev_state_config = 0x0300, + ncsi_dev_state_suspend = 0x0400, +}; + +struct ncsi_dev { + int state; + int link_up; + struct net_device *dev; + void (*handler)(struct ncsi_dev *ndev); +}; + +#ifdef CONFIG_NET_NCSI +struct ncsi_dev *ncsi_register_dev(struct net_device *dev, + void (*notifier)(struct ncsi_dev *nd)); +int ncsi_start_dev(struct ncsi_dev *nd); +void ncsi_unregister_dev(struct ncsi_dev *nd); +#else /* !CONFIG_NET_NCSI */ +static inline struct ncsi_dev *ncsi_register_dev(struct net_device *dev, + void (*notifier)(struct ncsi_dev *nd)) +{ + return NULL; +} + +static inline int ncsi_start_dev(struct ncsi_dev *nd) +{ + return -ENOTTY; +} + +static inline void ncsi_unregister_dev(struct ncsi_dev *nd) +{ +} +#endif /* CONFIG_NET_NCSI */ + +#endif /* __NET_NCSI_H */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 5d3397f..445b019 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -17,6 +17,7 @@ #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/atomic.h> +#include <linux/rhashtable.h> #include <linux/netfilter/nf_conntrack_tcp.h> #include <linux/netfilter/nf_conntrack_dccp.h> @@ -117,6 +118,9 @@ struct nf_conn { /* Extensions */ struct nf_ct_ext *ext; +#if IS_ENABLED(CONFIG_NF_NAT) + struct rhash_head nat_bysource; +#endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; }; @@ -266,12 +270,12 @@ static inline int nf_ct_is_template(const struct nf_conn *ct) } /* It's confirmed if it is, or has been in the hash table. */ -static inline int nf_ct_is_confirmed(struct nf_conn *ct) +static inline int nf_ct_is_confirmed(const struct nf_conn *ct) { return test_bit(IPS_CONFIRMED_BIT, &ct->status); } -static inline int nf_ct_is_dying(struct nf_conn *ct) +static inline int nf_ct_is_dying(const struct nf_conn *ct) { return test_bit(IPS_DYING_BIT, &ct->status); } @@ -287,6 +291,14 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb) return skb->dev && skb->skb_iif && skb->dev->flags & IFF_LOOPBACK; } +/* jiffies until ct expires, 0 if already expired */ +static inline unsigned long nf_ct_expires(const struct nf_conn *ct) +{ + long timeout = (long)ct->timeout.expires - (long)jiffies; + + return timeout > 0 ? timeout : 0; +} + struct kernel_param; int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); @@ -301,6 +313,7 @@ void nf_ct_tmpl_free(struct nf_conn *tmpl); #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) +#define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v)) #define MODULE_ALIAS_NFCT_HELPER(helper) \ MODULE_ALIAS("nfct-helper-" helper) diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 3e2f332..79d7ac5 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -51,6 +51,8 @@ bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto); +void nf_conntrack_get_ht(struct hlist_nulls_head **hash, unsigned int *hsize); + /* Find a connection corresponding to a tuple. */ struct nf_conntrack_tuple_hash * nf_conntrack_find_get(struct net *net, diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index b925395..1c3035d 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -99,9 +99,6 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id, struct nf_ct_ext_type { /* Destroys relationships (can be NULL). */ void (*destroy)(struct nf_conn *ct); - /* Called when realloacted (can be NULL). - Contents has already been moved. */ - void (*move)(void *new, void *old); enum nf_ct_ext_id id; diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 6cf614bc..1eaac1f 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -58,10 +58,25 @@ struct nf_conntrack_helper *__nf_conntrack_helper_find(const char *name, struct nf_conntrack_helper *nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum); +void nf_ct_helper_init(struct nf_conntrack_helper *helper, + u16 l3num, u16 protonum, const char *name, + u16 default_port, u16 spec_port, u32 id, + const struct nf_conntrack_expect_policy *exp_pol, + u32 expect_class_max, u32 data_len, + int (*help)(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo), + int (*from_nlattr)(struct nlattr *attr, + struct nf_conn *ct), + struct module *module); int nf_conntrack_helper_register(struct nf_conntrack_helper *); void nf_conntrack_helper_unregister(struct nf_conntrack_helper *); +int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int); +void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *, + unsigned int); + struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, struct nf_conntrack_helper *helper, gfp_t gfp); diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index c5f8fc73..4988146 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -10,8 +10,7 @@ #define NF_CT_LABELS_MAX_SIZE ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE) struct nf_conn_labels { - u8 words; - unsigned long bits[]; + unsigned long bits[NF_CT_LABELS_MAX_SIZE / sizeof(long)]; }; static inline struct nf_conn_labels *nf_ct_labels_find(const struct nf_conn *ct) @@ -26,27 +25,18 @@ static inline struct nf_conn_labels *nf_ct_labels_find(const struct nf_conn *ct) static inline struct nf_conn_labels *nf_ct_labels_ext_add(struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_LABELS - struct nf_conn_labels *cl_ext; struct net *net = nf_ct_net(ct); - u8 words; - words = ACCESS_ONCE(net->ct.label_words); - if (words == 0) + if (net->ct.labels_used == 0) return NULL; - cl_ext = nf_ct_ext_add_length(ct, NF_CT_EXT_LABELS, - words * sizeof(long), GFP_ATOMIC); - if (cl_ext != NULL) - cl_ext->words = words; - - return cl_ext; + return nf_ct_ext_add_length(ct, NF_CT_EXT_LABELS, + sizeof(struct nf_conn_labels), GFP_ATOMIC); #else return NULL; #endif } -int nf_connlabel_set(struct nf_conn *ct, u16 bit); - int nf_connlabels_replace(struct nf_conn *ct, const u32 *data, const u32 *mask, unsigned int words); diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index 344b1ab..c327a43 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -1,5 +1,6 @@ #ifndef _NF_NAT_H #define _NF_NAT_H +#include <linux/rhashtable.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter/nf_nat.h> #include <net/netfilter/nf_conntrack_tuple.h> @@ -29,8 +30,6 @@ struct nf_conn; /* The structure embedded in the conntrack structure. */ struct nf_conn_nat { - struct hlist_node bysource; - struct nf_conn *ct; union nf_conntrack_nat_help help; #if IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV4) || \ IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV6) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 30c1d94..f2f1339 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -236,7 +236,8 @@ struct nft_expr; * @features: features supported by the implementation */ struct nft_set_ops { - bool (*lookup)(const struct nft_set *set, + bool (*lookup)(const struct net *net, + const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext); bool (*update)(struct nft_set *set, @@ -248,11 +249,14 @@ struct nft_set_ops { struct nft_regs *regs, const struct nft_set_ext **ext); - int (*insert)(const struct nft_set *set, + int (*insert)(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem); - void (*activate)(const struct nft_set *set, + void (*activate)(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem); - void * (*deactivate)(const struct nft_set *set, + void * (*deactivate)(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem); void (*remove)(const struct nft_set *set, const struct nft_set_elem *elem); @@ -295,7 +299,6 @@ void nft_unregister_set(struct nft_set_ops *ops); * @udlen: user data length * @udata: user data * @ops: set ops - * @pnet: network namespace * @flags: set flags * @genmask: generation mask * @klen: key length @@ -318,7 +321,6 @@ struct nft_set { unsigned char *udata; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; - possible_net_t pnet; u16 flags:14, genmask:2; u8 klen; @@ -804,7 +806,6 @@ struct nft_stats { * struct nft_base_chain - nf_tables base chain * * @ops: netfilter hook ops - * @pnet: net namespace that this chain belongs to * @type: chain type * @policy: default policy * @stats: per-cpu chain stats @@ -813,7 +814,6 @@ struct nft_stats { */ struct nft_base_chain { struct nf_hook_ops ops[NFT_HOOK_OPS_MAX]; - possible_net_t pnet; const struct nf_chain_type *type; u8 policy; u8 flags; @@ -1009,10 +1009,11 @@ static inline bool nft_set_elem_active(const struct nft_set_ext *ext, return !(ext->genmask & genmask); } -static inline void nft_set_elem_change_active(const struct nft_set *set, +static inline void nft_set_elem_change_active(const struct net *net, + const struct nft_set *set, struct nft_set_ext *ext) { - ext->genmask ^= nft_genmask_next(read_pnet(&set->pnet)); + ext->genmask ^= nft_genmask_next(net); } /* diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h index 0ae101e..74fa7eb 100644 --- a/include/net/nfc/digital.h +++ b/include/net/nfc/digital.h @@ -220,12 +220,13 @@ struct nfc_digital_dev { struct list_head cmd_queue; struct mutex cmd_lock; - struct work_struct poll_work; + struct delayed_work poll_work; u8 curr_protocol; u8 curr_rf_tech; u8 curr_nfc_dep_pni; u8 did; + u16 dep_rwt; u8 local_payload_max; u8 remote_payload_max; @@ -237,7 +238,6 @@ struct nfc_digital_dev { int nack_count; struct sk_buff *saved_skb; - unsigned int saved_skb_len; u16 target_fsc; diff --git a/include/net/nfc/llc.h b/include/net/nfc/llc.h index c25fbde..7ecb457 100644 --- a/include/net/nfc/llc.h +++ b/include/net/nfc/llc.h @@ -37,10 +37,6 @@ struct nfc_llc *nfc_llc_allocate(const char *name, struct nfc_hci_dev *hdev, int tx_tailroom, llc_failure_t llc_failure); void nfc_llc_free(struct nfc_llc *llc); -void nfc_llc_get_rx_head_tail_room(struct nfc_llc *llc, int *rx_headroom, - int *rx_tailroom); - - int nfc_llc_start(struct nfc_llc *llc); int nfc_llc_stop(struct nfc_llc *llc); void nfc_llc_rcv_from_drv(struct nfc_llc *llc, struct sk_buff *skb); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 3722dda..6f8d653 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -442,4 +442,15 @@ struct tc_cls_flower_offload { struct tcf_exts *exts; }; +enum tc_matchall_command { + TC_CLSMATCHALL_REPLACE, + TC_CLSMATCHALL_DESTROY, +}; + +struct tc_cls_matchall_offload { + enum tc_matchall_command command; + struct tcf_exts *exts; + unsigned long cookie; +}; + #endif diff --git a/include/net/sock.h b/include/net/sock.h index 649d2a8..ff5be7e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1576,7 +1576,13 @@ static inline void sock_put(struct sock *sk) */ void sock_gen_put(struct sock *sk); -int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested); +int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, + unsigned int trim_cap); +static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, + const int nested) +{ + return __sk_receive_skb(sk, skb, nested, 1); +} static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 9023e3e..62f6a96 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -60,7 +60,7 @@ struct switchdev_attr { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ - u32 ageing_time; /* BRIDGE_AGEING_TIME */ + clock_t ageing_time; /* BRIDGE_AGEING_TIME */ bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ } u; }; diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index e891835..6a13a7c 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -24,6 +24,15 @@ static inline bool is_tcf_mirred_redirect(const struct tc_action *a) return false; } +static inline bool is_tcf_mirred_mirror(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->type == TCA_ACT_MIRRED) + return to_mirred(a)->tcfm_eaction == TCA_EGRESS_MIRROR; +#endif + return false; +} + static inline int tcf_mirred_ifindex(const struct tc_action *a) { return to_mirred(a)->tcfm_ifindex; diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 8bdae34..ec10cfe 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -245,6 +245,7 @@ endif header-y += hw_breakpoint.h header-y += l2tp.h header-y += libc-compat.h +header-y += lirc.h header-y += limits.h header-y += llc.h header-y += loop.h diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c4d9224..2b7076f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -94,6 +94,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SCHED_CLS, BPF_PROG_TYPE_SCHED_ACT, BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, }; #define BPF_PSEUDO_MAP_FD 1 @@ -439,4 +440,24 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will result + * in packet drop. + */ +enum xdp_action { + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md { + __u32 data; + __u32 data_end; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h index c3fdfe7..cb5d1a5 100644 --- a/include/uapi/linux/elf-em.h +++ b/include/uapi/linux/elf-em.h @@ -40,6 +40,7 @@ #define EM_TILEPRO 188 /* Tilera TILEPro */ #define EM_MICROBLAZE 189 /* Xilinx MicroBlaze */ #define EM_TILEGX 191 /* Tilera TILE-Gx */ +#define EM_BPF 247 /* Linux BPF - in-kernel virtual machine */ #define EM_FRV 0x5441 /* Fujitsu FR-V */ #define EM_AVR32 0x18ad /* Atmel AVR32 */ diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index cec849a..117d02e 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -87,6 +87,7 @@ #define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */ #define ETH_P_MVRP 0x88F5 /* 802.1Q MVRP */ #define ETH_P_1588 0x88F7 /* IEEE 1588 Timesync */ +#define ETH_P_NCSI 0x88F8 /* NCSI protocol */ #define ETH_P_PRP 0x88FB /* IEC 62439-3 PRP/HSRv0 */ #define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */ #define ETH_P_TDLS 0x890D /* TDLS */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4285ac3..a1b5202 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -156,6 +156,7 @@ enum { IFLA_GSO_MAX_SEGS, IFLA_GSO_MAX_SIZE, IFLA_PAD, + IFLA_XDP, __IFLA_MAX }; @@ -843,4 +844,15 @@ enum { }; #define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) +/* XDP section */ + +enum { + IFLA_XDP_UNSPEC, + IFLA_XDP_FD, + IFLA_XDP_ATTACHED, + __IFLA_XDP_MAX, +}; + +#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h index f7d4831..02fc49c 100644 --- a/include/uapi/linux/if_macsec.h +++ b/include/uapi/linux/if_macsec.h @@ -26,6 +26,8 @@ #define MACSEC_MIN_ICV_LEN 8 #define MACSEC_MAX_ICV_LEN 32 +/* upper limit for ICV length as recommended by IEEE802.1AE-2006 */ +#define MACSEC_STD_ICV_LEN 16 enum macsec_attrs { MACSEC_ATTR_UNSPEC, diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 737fa32..d6d071f 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -780,6 +780,7 @@ #define SW_ROTATE_LOCK 0x0c /* set = rotate locked/disabled */ #define SW_LINEIN_INSERT 0x0d /* set = inserted */ #define SW_MUTE_DEVICE 0x0e /* set = device disabled */ +#define SW_PEN_INSERTED 0x0f /* set = pen inserted */ #define SW_MAX 0x0f #define SW_CNT (SW_MAX+1) diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 5702e93..d1c1cca 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -433,6 +433,18 @@ enum { #define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1) +/* Match-all classifier */ + +enum { + TCA_MATCHALL_UNSPEC, + TCA_MATCHALL_CLASSID, + TCA_MATCHALL_ACT, + TCA_MATCHALL_FLAGS, + __TCA_MATCHALL_MAX, +}; + +#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1) + /* Extended Matches */ struct tcf_ematch_tree_hdr { diff --git a/init/Kconfig b/init/Kconfig index f755a60..c02d897 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1458,6 +1458,7 @@ config KALLSYMS_ALL config KALLSYMS_ABSOLUTE_PERCPU bool + depends on KALLSYMS default X86_64 && SMP config KALLSYMS_BASE_RELATIVE diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 96d938a..228f962 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -670,14 +670,20 @@ static struct bpf_prog *____bpf_prog_get(struct fd f) return f.file->private_data; } -struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) { - if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) { - atomic_dec(&prog->aux->refcnt); + if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) { + atomic_sub(i, &prog->aux->refcnt); return ERR_PTR(-EBUSY); } return prog; } +EXPORT_SYMBOL_GPL(bpf_prog_add); + +struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +{ + return bpf_prog_add(prog, 1); +} static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e206c21..f72f23b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -653,6 +653,16 @@ static int check_map_access(struct verifier_env *env, u32 regno, int off, #define MAX_PACKET_OFF 0xffff +static bool may_write_pkt_data(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_XDP: + return true; + default: + return false; + } +} + static int check_packet_access(struct verifier_env *env, u32 regno, int off, int size) { @@ -713,6 +723,7 @@ static int check_ptr_alignment(struct verifier_env *env, struct reg_state *reg, switch (env->prog->type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_XDP: break; default: verbose("verifier is misconfigured\n"); @@ -805,10 +816,15 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, err = check_stack_read(state, off, size, value_regno); } } else if (state->regs[regno].type == PTR_TO_PACKET) { - if (t == BPF_WRITE) { + if (t == BPF_WRITE && !may_write_pkt_data(env->prog->type)) { verbose("cannot write into packet\n"); return -EACCES; } + if (t == BPF_WRITE && value_regno >= 0 && + is_pointer_value(env, value_regno)) { + verbose("R%d leaks addr into packet\n", value_regno); + return -EACCES; + } err = check_packet_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown_value(state->regs, value_regno); diff --git a/kernel/cpu.c b/kernel/cpu.c index d948e44..7b61887 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1201,6 +1201,8 @@ static struct cpuhp_step cpuhp_bp_states[] = { .teardown = takedown_cpu, .cant_stop = true, }, +#else + [CPUHP_BRINGUP_CPU] = { }, #endif }; diff --git a/kernel/events/core.c b/kernel/events/core.c index b1891b6..195e765 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1678,12 +1678,33 @@ static bool is_orphaned_event(struct perf_event *event) return event->state == PERF_EVENT_STATE_DEAD; } -static inline int pmu_filter_match(struct perf_event *event) +static inline int __pmu_filter_match(struct perf_event *event) { struct pmu *pmu = event->pmu; return pmu->filter_match ? pmu->filter_match(event) : 1; } +/* + * Check whether we should attempt to schedule an event group based on + * PMU-specific filtering. An event group can consist of HW and SW events, + * potentially with a SW leader, so we must check all the filters, to + * determine whether a group is schedulable: + */ +static inline int pmu_filter_match(struct perf_event *event) +{ + struct perf_event *child; + + if (!__pmu_filter_match(event)) + return 0; + + list_for_each_entry(child, &event->sibling_list, group_entry) { + if (!__pmu_filter_match(child)) + return 0; + } + + return 1; +} + static inline int event_filter_match(struct perf_event *event) { diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 2417eb5..486fd78 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -123,18 +123,19 @@ static inline unsigned long perf_aux_size(struct ring_buffer *rb) return rb->aux_nr_pages << PAGE_SHIFT; } -#define __DEFINE_OUTPUT_COPY_BODY(memcpy_func) \ +#define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...) \ { \ unsigned long size, written; \ \ do { \ size = min(handle->size, len); \ - written = memcpy_func(handle->addr, buf, size); \ + written = memcpy_func(__VA_ARGS__); \ written = size - written; \ \ len -= written; \ handle->addr += written; \ - buf += written; \ + if (advance_buf) \ + buf += written; \ handle->size -= written; \ if (!handle->size) { \ struct ring_buffer *rb = handle->rb; \ @@ -153,12 +154,16 @@ static inline unsigned long perf_aux_size(struct ring_buffer *rb) static inline unsigned long \ func_name(struct perf_output_handle *handle, \ const void *buf, unsigned long len) \ -__DEFINE_OUTPUT_COPY_BODY(memcpy_func) +__DEFINE_OUTPUT_COPY_BODY(true, memcpy_func, handle->addr, buf, size) static inline unsigned long __output_custom(struct perf_output_handle *handle, perf_copy_f copy_func, const void *buf, unsigned long len) -__DEFINE_OUTPUT_COPY_BODY(copy_func) +{ + unsigned long orig_len = len; + __DEFINE_OUTPUT_COPY_BODY(false, copy_func, handle->addr, buf, + orig_len - len, size) +} static inline unsigned long memcpy_common(void *dst, const void *src, unsigned long n) diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index e25e92f..6a5c239 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -18,7 +18,7 @@ #include <linux/vmalloc.h> #include "gcov.h" -#if __GNUC__ == 5 && __GNUC_MINOR__ >= 1 +#if (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1) #define GCOV_COUNTERS 10 #elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9 #define GCOV_COUNTERS 9 diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 51d7105..97ee9ac 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5394,13 +5394,15 @@ void idle_task_exit(void) /* * Since this CPU is going 'away' for a while, fold any nr_active delta * we might have. Assumes we're called after migrate_tasks() so that the - * nr_active count is stable. + * nr_active count is stable. We need to take the teardown thread which + * is calling this into account, so we hand in adjust = 1 to the load + * calculation. * * Also see the comment "Global load-average calculations". */ static void calc_load_migrate(struct rq *rq) { - long delta = calc_load_fold_active(rq); + long delta = calc_load_fold_active(rq, 1); if (delta) atomic_long_add(delta, &calc_load_tasks); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bdcbeea..c8c5d2d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -735,8 +735,6 @@ void post_init_entity_util_avg(struct sched_entity *se) } } -static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq); -static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq); #else void init_entity_runnable_average(struct sched_entity *se) { @@ -2499,28 +2497,22 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) #ifdef CONFIG_FAIR_GROUP_SCHED # ifdef CONFIG_SMP -static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) +static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) { - long tg_weight; + long tg_weight, load, shares; /* - * Use this CPU's real-time load instead of the last load contribution - * as the updating of the contribution is delayed, and we will use the - * the real-time load to calc the share. See update_tg_load_avg(). + * This really should be: cfs_rq->avg.load_avg, but instead we use + * cfs_rq->load.weight, which is its upper bound. This helps ramp up + * the shares for small weight interactive tasks. */ - tg_weight = atomic_long_read(&tg->load_avg); - tg_weight -= cfs_rq->tg_load_avg_contrib; - tg_weight += cfs_rq->load.weight; + load = scale_load_down(cfs_rq->load.weight); - return tg_weight; -} - -static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) -{ - long tg_weight, load, shares; + tg_weight = atomic_long_read(&tg->load_avg); - tg_weight = calc_tg_weight(tg, cfs_rq); - load = cfs_rq->load.weight; + /* Ensure tg_weight >= load */ + tg_weight -= cfs_rq->tg_load_avg_contrib; + tg_weight += load; shares = (tg->shares * load); if (tg_weight) @@ -2539,6 +2531,7 @@ static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) return tg->shares; } # endif /* CONFIG_SMP */ + static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { @@ -4946,19 +4939,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) return wl; for_each_sched_entity(se) { - long w, W; + struct cfs_rq *cfs_rq = se->my_q; + long W, w = cfs_rq_load_avg(cfs_rq); - tg = se->my_q->tg; + tg = cfs_rq->tg; /* * W = @wg + \Sum rw_j */ - W = wg + calc_tg_weight(tg, se->my_q); + W = wg + atomic_long_read(&tg->load_avg); + + /* Ensure \Sum rw_j >= rw_i */ + W -= cfs_rq->tg_load_avg_contrib; + W += w; /* * w = rw_i + @wl */ - w = cfs_rq_load_avg(se->my_q) + wl; + w += wl; /* * wl = S * s'_i; see (2) diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index b0b93fd..a2d6eb7 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -78,11 +78,11 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift) loads[2] = (avenrun[2] + offset) << shift; } -long calc_load_fold_active(struct rq *this_rq) +long calc_load_fold_active(struct rq *this_rq, long adjust) { long nr_active, delta = 0; - nr_active = this_rq->nr_running; + nr_active = this_rq->nr_running - adjust; nr_active += (long)this_rq->nr_uninterruptible; if (nr_active != this_rq->calc_load_active) { @@ -188,7 +188,7 @@ void calc_load_enter_idle(void) * We're going into NOHZ mode, if there's any pending delta, fold it * into the pending idle delta. */ - delta = calc_load_fold_active(this_rq); + delta = calc_load_fold_active(this_rq, 0); if (delta) { int idx = calc_load_write_idx(); @@ -389,7 +389,7 @@ void calc_global_load_tick(struct rq *this_rq) if (time_before(jiffies, this_rq->calc_load_update)) return; - delta = calc_load_fold_active(this_rq); + delta = calc_load_fold_active(this_rq, 0); if (delta) atomic_long_add(delta, &calc_load_tasks); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7cbeb92..898c0d2 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -28,7 +28,7 @@ extern unsigned long calc_load_update; extern atomic_long_t calc_load_tasks; extern void calc_global_load_tick(struct rq *this_rq); -extern long calc_load_fold_active(struct rq *this_rq); +extern long calc_load_fold_active(struct rq *this_rq, long adjust); #ifdef CONFIG_SMP extern void cpu_load_update_active(struct rq *this_rq); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 1cafba8..39008d7 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -777,6 +777,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) timer->it.cpu.expires = 0; sample_to_timespec(timer->it_clock, timer->it.cpu.expires, &itp->it_value); + return; } else { cpu_timer_sample_group(timer->it_clock, p, &now); unlock_task_sighand(p, &flags); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ebfbb7d..a12bbd32 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -309,7 +309,9 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, }; struct perf_raw_record raw = { .frag = { - .next = ctx_size ? &frag : NULL, + { + .next = ctx_size ? &frag : NULL, + }, .size = meta_size, .data = meta, }, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index e1c0e99..97e7b79 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4600,15 +4600,11 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; - /* is @cpu the only online CPU? */ cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); - if (cpumask_weight(&cpumask) != 1) - return; /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) - WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, - pool->attrs->cpumask) < 0); + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } /* diff --git a/mm/compaction.c b/mm/compaction.c index 79bfe0e..7bc0477 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1009,8 +1009,6 @@ static void isolate_freepages(struct compact_control *cc) block_end_pfn = block_start_pfn, block_start_pfn -= pageblock_nr_pages, isolate_start_pfn = block_start_pfn) { - unsigned long isolated; - /* * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check if we need @@ -1034,36 +1032,30 @@ static void isolate_freepages(struct compact_control *cc) continue; /* Found a block suitable for isolating free pages from. */ - isolated = isolate_freepages_block(cc, &isolate_start_pfn, - block_end_pfn, freelist, false); - /* If isolation failed early, do not continue needlessly */ - if (!isolated && isolate_start_pfn < block_end_pfn && - cc->nr_migratepages > cc->nr_freepages) - break; + isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn, + freelist, false); /* - * If we isolated enough freepages, or aborted due to async - * compaction being contended, terminate the loop. - * Remember where the free scanner should restart next time, - * which is where isolate_freepages_block() left off. - * But if it scanned the whole pageblock, isolate_start_pfn - * now points at block_end_pfn, which is the start of the next - * pageblock. - * In that case we will however want to restart at the start - * of the previous pageblock. + * If we isolated enough freepages, or aborted due to lock + * contention, terminate. */ if ((cc->nr_freepages >= cc->nr_migratepages) || cc->contended) { - if (isolate_start_pfn >= block_end_pfn) + if (isolate_start_pfn >= block_end_pfn) { + /* + * Restart at previous pageblock if more + * freepages can be isolated next time. + */ isolate_start_pfn = block_start_pfn - pageblock_nr_pages; + } break; - } else { + } else if (isolate_start_pfn < block_end_pfn) { /* - * isolate_freepages_block() should not terminate - * prematurely unless contended, or isolated enough + * If isolation failed early, do not continue + * needlessly. */ - VM_BUG_ON(isolate_start_pfn < block_end_pfn); + break; } } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9ed5853..343a2b7 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1624,14 +1624,9 @@ int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (next - addr != HPAGE_PMD_SIZE) { get_page(page); spin_unlock(ptl); - if (split_huge_page(page)) { - put_page(page); - unlock_page(page); - goto out_unlocked; - } + split_huge_page(page); put_page(page); unlock_page(page); - ret = 1; goto out_unlocked; } @@ -2989,7 +2984,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze) + unsigned long address, bool freeze, struct page *page) { spinlock_t *ptl; struct mm_struct *mm = vma->vm_mm; @@ -2997,8 +2992,17 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE); ptl = pmd_lock(mm, pmd); + + /* + * If caller asks to setup a migration entries, we need a page to check + * pmd against. Otherwise we can end up replacing wrong page. + */ + VM_BUG_ON(freeze && !page); + if (page && page != pmd_page(*pmd)) + goto out; + if (pmd_trans_huge(*pmd)) { - struct page *page = pmd_page(*pmd); + page = pmd_page(*pmd); if (PageMlocked(page)) clear_page_mlock(page); } else if (!pmd_devmap(*pmd)) @@ -3025,24 +3029,8 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, return; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd) || (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd))) - return; - /* - * If caller asks to setup a migration entries, we need a page to check - * pmd against. Otherwise we can end up replacing wrong page. - */ - VM_BUG_ON(freeze && !page); - if (page && page != pmd_page(*pmd)) - return; - - /* - * Caller holds the mmap_sem write mode or the anon_vma lock, - * so a huge pmd cannot materialize from under us (khugepaged - * holds both the mmap_sem write mode and the anon_vma lock - * write mode). - */ - __split_huge_pmd(vma, pmd, address, freeze); + __split_huge_pmd(vma, pmd, address, freeze, page); } void vma_adjust_trans_huge(struct vm_area_struct *vma, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c1f3c0b..addfe4ac 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3383,7 +3383,7 @@ retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { - page_move_anon_rmap(old_page, vma, address); + page_move_anon_rmap(old_page, vma); set_huge_ptep_writable(vma, address, ptep); return 0; } diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 4973505..65793f1 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -238,30 +238,23 @@ static void qlist_move_cache(struct qlist_head *from, struct qlist_head *to, struct kmem_cache *cache) { - struct qlist_node *prev = NULL, *curr; + struct qlist_node *curr; if (unlikely(qlist_empty(from))) return; curr = from->head; + qlist_init(from); while (curr) { - struct qlist_node *qlink = curr; - struct kmem_cache *obj_cache = qlink_to_cache(qlink); - - if (obj_cache == cache) { - if (unlikely(from->head == qlink)) { - from->head = curr->next; - prev = curr; - } else - prev->next = curr->next; - if (unlikely(from->tail == qlink)) - from->tail = curr->next; - from->bytes -= cache->size; - qlist_put(to, qlink, cache->size); - } else { - prev = curr; - } - curr = curr->next; + struct qlist_node *next = curr->next; + struct kmem_cache *obj_cache = qlink_to_cache(curr); + + if (obj_cache == cache) + qlist_put(to, curr, obj_cache->size); + else + qlist_put(from, curr, obj_cache->size); + + curr = next; } } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ac8664db..5339c89 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4057,6 +4057,60 @@ static struct cftype mem_cgroup_legacy_files[] = { { }, /* terminate */ }; +/* + * Private memory cgroup IDR + * + * Swap-out records and page cache shadow entries need to store memcg + * references in constrained space, so we maintain an ID space that is + * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of + * memory-controlled cgroups to 64k. + * + * However, there usually are many references to the oflline CSS after + * the cgroup has been destroyed, such as page cache or reclaimable + * slab objects, that don't need to hang on to the ID. We want to keep + * those dead CSS from occupying IDs, or we might quickly exhaust the + * relatively small ID space and prevent the creation of new cgroups + * even when there are much fewer than 64k cgroups - possibly none. + * + * Maintain a private 16-bit ID space for memcg, and allow the ID to + * be freed and recycled when it's no longer needed, which is usually + * when the CSS is offlined. + * + * The only exception to that are records of swapped out tmpfs/shmem + * pages that need to be attributed to live ancestors on swapin. But + * those references are manageable from userspace. + */ + +static DEFINE_IDR(mem_cgroup_idr); + +static void mem_cgroup_id_get(struct mem_cgroup *memcg) +{ + atomic_inc(&memcg->id.ref); +} + +static void mem_cgroup_id_put(struct mem_cgroup *memcg) +{ + if (atomic_dec_and_test(&memcg->id.ref)) { + idr_remove(&mem_cgroup_idr, memcg->id.id); + memcg->id.id = 0; + + /* Memcg ID pins CSS */ + css_put(&memcg->css); + } +} + +/** + * mem_cgroup_from_id - look up a memcg from a memcg id + * @id: the memcg id to look up + * + * Caller must hold rcu_read_lock(). + */ +struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return idr_find(&mem_cgroup_idr, id); +} + static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; @@ -4116,6 +4170,12 @@ static struct mem_cgroup *mem_cgroup_alloc(void) if (!memcg) return NULL; + memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, + 1, MEM_CGROUP_ID_MAX, + GFP_KERNEL); + if (memcg->id.id < 0) + goto fail; + memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu); if (!memcg->stat) goto fail; @@ -4142,8 +4202,11 @@ static struct mem_cgroup *mem_cgroup_alloc(void) #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&memcg->cgwb_list); #endif + idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); return memcg; fail: + if (memcg->id.id > 0) + idr_remove(&mem_cgroup_idr, memcg->id.id); mem_cgroup_free(memcg); return NULL; } @@ -4206,12 +4269,11 @@ fail: return ERR_PTR(-ENOMEM); } -static int -mem_cgroup_css_online(struct cgroup_subsys_state *css) +static int mem_cgroup_css_online(struct cgroup_subsys_state *css) { - if (css->id > MEM_CGROUP_ID_MAX) - return -ENOSPC; - + /* Online state pins memcg ID, memcg ID pins CSS */ + mem_cgroup_id_get(mem_cgroup_from_css(css)); + css_get(css); return 0; } @@ -4234,6 +4296,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) memcg_offline_kmem(memcg); wb_memcg_offline(memcg); + + mem_cgroup_id_put(memcg); } static void mem_cgroup_css_released(struct cgroup_subsys_state *css) @@ -5756,6 +5820,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (!memcg) return; + mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); @@ -5774,6 +5839,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) VM_BUG_ON(!irqs_disabled()); mem_cgroup_charge_statistics(memcg, page, false, -1); memcg_check_events(memcg, page); + + if (!mem_cgroup_is_root(memcg)) + css_put(&memcg->css); } /* @@ -5804,11 +5872,11 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) !page_counter_try_charge(&memcg->swap, 1, &counter)) return -ENOMEM; + mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); - css_get(&memcg->css); return 0; } @@ -5837,7 +5905,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry) page_counter_uncharge(&memcg->memsw, 1); } mem_cgroup_swap_statistics(memcg, false); - css_put(&memcg->css); + mem_cgroup_id_put(memcg); } rcu_read_unlock(); } diff --git a/mm/memory.c b/mm/memory.c index cd1f29e..9e04681 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2399,8 +2399,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * Protected against the rmap code by * the page lock. */ - page_move_anon_rmap(compound_head(old_page), - vma, address); + page_move_anon_rmap(old_page, vma); } unlock_page(old_page); return wp_page_reuse(mm, vma, address, page_table, ptl, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6903b69..8b3e134 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -286,7 +286,9 @@ static inline void reset_deferred_meminit(pg_data_t *pgdat) /* Returns true if the struct page for the pfn is uninitialised */ static inline bool __meminit early_page_uninitialised(unsigned long pfn) { - if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn) + int nid = early_pfn_to_nid(pfn); + + if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn) return true; return false; @@ -1273,7 +1275,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn) spin_lock(&early_pfn_lock); nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); if (nid < 0) - nid = 0; + nid = first_online_node; spin_unlock(&early_pfn_lock); return nid; @@ -1084,23 +1084,20 @@ EXPORT_SYMBOL_GPL(page_mkclean); * page_move_anon_rmap - move a page to our anon_vma * @page: the page to move to our anon_vma * @vma: the vma the page belongs to - * @address: the user virtual address mapped * * When a page belongs exclusively to one process after a COW event, * that page can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling * processes. */ -void page_move_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address) +void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; + page = compound_head(page); + VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_VMA(!anon_vma, vma); - if (IS_ENABLED(CONFIG_DEBUG_VM) && PageTransHuge(page)) - address &= HPAGE_PMD_MASK; - VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; /* @@ -1427,7 +1424,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, goto out; } - pte = page_check_address(page, mm, address, &ptl, 0); + pte = page_check_address(page, mm, address, &ptl, + PageTransCompound(page)); if (!pte) goto out; @@ -2225,9 +2225,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, error = shmem_getpage(inode, index, &page, SGP_FALLOC); if (error) { /* Remove the !PageUptodate pages we added */ - shmem_undo_range(inode, - (loff_t)start << PAGE_SHIFT, - ((loff_t)index << PAGE_SHIFT) - 1, true); + if (index > start) { + shmem_undo_range(inode, + (loff_t)start << PAGE_SHIFT, + ((loff_t)index << PAGE_SHIFT) - 1, true); + } goto undone; } diff --git a/mm/slab_common.c b/mm/slab_common.c index a65dad7..82317ab 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -526,8 +526,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, goto out_unlock; cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf)); - cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - css->id, memcg_name_buf); + cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name, + css->serial_nr, memcg_name_buf); if (!cache_name) goto out_unlock; diff --git a/mm/workingset.c b/mm/workingset.c index 8a75f8d..5772775 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -491,7 +491,7 @@ static int __init workingset_init(void) max_order = fls_long(totalram_pages - 1); if (max_order > timestamp_bits) bucket_order = max_order - timestamp_bits; - printk("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", + pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index c8f422c..fbfacd5 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -146,10 +146,12 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) { - /* TODO: gotta make sure the underlying layer can handle it, - * maybe an IFF_VLAN_CAPABLE flag for devices? - */ - if (vlan_dev_priv(dev)->real_dev->mtu < new_mtu) + struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; + unsigned int max_mtu = real_dev->mtu; + + if (netif_reduces_vlan_mtu(real_dev)) + max_mtu -= VLAN_HLEN; + if (max_mtu < new_mtu) return -ERANGE; dev->mtu = new_mtu; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index c92b52f..1270207 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -118,6 +118,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev; + unsigned int max_mtu; __be16 proto; int err; @@ -144,9 +145,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; + max_mtu = netif_reduces_vlan_mtu(real_dev) ? real_dev->mtu - VLAN_HLEN : + real_dev->mtu; if (!tb[IFLA_MTU]) - dev->mtu = real_dev->mtu; - else if (dev->mtu > real_dev->mtu) + dev->mtu = max_mtu; + else if (dev->mtu > max_mtu) return -EINVAL; err = vlan_changelink(dev, tb, data); diff --git a/net/Kconfig b/net/Kconfig index ff40562..c2cdbce 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -237,6 +237,7 @@ source "net/hsr/Kconfig" source "net/switchdev/Kconfig" source "net/l3mdev/Kconfig" source "net/qrtr/Kconfig" +source "net/ncsi/Kconfig" config RPS bool diff --git a/net/Makefile b/net/Makefile index bdd1455..9bd20bb 100644 --- a/net/Makefile +++ b/net/Makefile @@ -79,3 +79,4 @@ ifneq ($(CONFIG_NET_L3_MASTER_DEV),) obj-y += l3mdev/ endif obj-$(CONFIG_QRTR) += qrtr/ +obj-$(CONFIG_NET_NCSI) += ncsi/ diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index e4f7494..ad2ffe1 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -178,10 +178,21 @@ static void batadv_backbone_gw_put(struct batadv_bla_backbone_gw *backbone_gw) static void batadv_claim_release(struct kref *ref) { struct batadv_bla_claim *claim; + struct batadv_bla_backbone_gw *old_backbone_gw; claim = container_of(ref, struct batadv_bla_claim, refcount); - batadv_backbone_gw_put(claim->backbone_gw); + spin_lock_bh(&claim->backbone_lock); + old_backbone_gw = claim->backbone_gw; + claim->backbone_gw = NULL; + spin_unlock_bh(&claim->backbone_lock); + + spin_lock_bh(&old_backbone_gw->crc_lock); + old_backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + spin_unlock_bh(&old_backbone_gw->crc_lock); + + batadv_backbone_gw_put(old_backbone_gw); + kfree_rcu(claim, rcu); } @@ -419,9 +430,12 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, break; } - if (vid & BATADV_VLAN_HAS_TAG) + if (vid & BATADV_VLAN_HAS_TAG) { skb = vlan_insert_tag(skb, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); + if (!skb) + goto out; + } skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, soft_iface); @@ -675,8 +689,10 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, const u8 *mac, const unsigned short vid, struct batadv_bla_backbone_gw *backbone_gw) { + struct batadv_bla_backbone_gw *old_backbone_gw; struct batadv_bla_claim *claim; struct batadv_bla_claim search_claim; + bool remove_crc = false; int hash_added; ether_addr_copy(search_claim.addr, mac); @@ -690,8 +706,10 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, return; ether_addr_copy(claim->addr, mac); + spin_lock_init(&claim->backbone_lock); claim->vid = vid; claim->lasttime = jiffies; + kref_get(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; kref_init(&claim->refcount); @@ -719,15 +737,26 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, "bla_add_claim(): changing ownership for %pM, vid %d\n", mac, BATADV_PRINT_VID(vid)); - spin_lock_bh(&claim->backbone_gw->crc_lock); - claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); - spin_unlock_bh(&claim->backbone_gw->crc_lock); - batadv_backbone_gw_put(claim->backbone_gw); + remove_crc = true; } - /* set (new) backbone gw */ + + /* replace backbone_gw atomically and adjust reference counters */ + spin_lock_bh(&claim->backbone_lock); + old_backbone_gw = claim->backbone_gw; kref_get(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; + spin_unlock_bh(&claim->backbone_lock); + if (remove_crc) { + /* remove claim address from old backbone_gw */ + spin_lock_bh(&old_backbone_gw->crc_lock); + old_backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + spin_unlock_bh(&old_backbone_gw->crc_lock); + } + + batadv_backbone_gw_put(old_backbone_gw); + + /* add claim address to new backbone_gw */ spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); spin_unlock_bh(&backbone_gw->crc_lock); @@ -738,6 +767,26 @@ claim_free_ref: } /** + * batadv_bla_claim_get_backbone_gw - Get valid reference for backbone_gw of + * claim + * @claim: claim whose backbone_gw should be returned + * + * Return: valid reference to claim::backbone_gw + */ +static struct batadv_bla_backbone_gw * +batadv_bla_claim_get_backbone_gw(struct batadv_bla_claim *claim) +{ + struct batadv_bla_backbone_gw *backbone_gw; + + spin_lock_bh(&claim->backbone_lock); + backbone_gw = claim->backbone_gw; + kref_get(&backbone_gw->refcount); + spin_unlock_bh(&claim->backbone_lock); + + return backbone_gw; +} + +/** * batadv_bla_del_claim - delete a claim from the claim hash * @bat_priv: the bat priv with all the soft interface information * @mac: mac address of the claim to be removed @@ -761,10 +810,6 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, batadv_choose_claim, claim); batadv_claim_put(claim); /* reference from the hash is gone */ - spin_lock_bh(&claim->backbone_gw->crc_lock); - claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); - spin_unlock_bh(&claim->backbone_gw->crc_lock); - /* don't need the reference from hash_find() anymore */ batadv_claim_put(claim); } @@ -1217,6 +1262,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, int now) { + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_bla_claim *claim; struct hlist_head *head; struct batadv_hashtable *hash; @@ -1231,14 +1277,17 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); if (now) goto purge_now; - if (!batadv_compare_eth(claim->backbone_gw->orig, + + if (!batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr)) - continue; + goto skip; + if (!batadv_has_timed_out(claim->lasttime, BATADV_BLA_CLAIM_TIMEOUT)) - continue; + goto skip; batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_purge_claims(): %pM, vid %d, time out\n", @@ -1246,8 +1295,10 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, purge_now: batadv_handle_unclaim(bat_priv, primary_if, - claim->backbone_gw->orig, + backbone_gw->orig, claim->addr, claim->vid); +skip: + batadv_backbone_gw_put(backbone_gw); } rcu_read_unlock(); } @@ -1758,9 +1809,11 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, bool is_bcast) { + struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_hard_iface *primary_if; + bool own_claim; bool ret; ethhdr = eth_hdr(skb); @@ -1795,8 +1848,12 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, } /* if it is our own claim ... */ - if (batadv_compare_eth(claim->backbone_gw->orig, - primary_if->net_dev->dev_addr)) { + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + own_claim = batadv_compare_eth(backbone_gw->orig, + primary_if->net_dev->dev_addr); + batadv_backbone_gw_put(backbone_gw); + + if (own_claim) { /* ... allow it in any case */ claim->lasttime = jiffies; goto allow; @@ -1860,7 +1917,9 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, { struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hard_iface *primary_if; + bool client_roamed; bool ret = false; primary_if = batadv_primary_if_get_selected(bat_priv); @@ -1890,8 +1949,12 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto allow; /* check if we are responsible. */ - if (batadv_compare_eth(claim->backbone_gw->orig, - primary_if->net_dev->dev_addr)) { + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + client_roamed = batadv_compare_eth(backbone_gw->orig, + primary_if->net_dev->dev_addr); + batadv_backbone_gw_put(backbone_gw); + + if (client_roamed) { /* if yes, the client has roamed and we have * to unclaim it. */ @@ -1939,6 +2002,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) struct net_device *net_dev = (struct net_device *)seq->private; struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->bla.claim_hash; + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_bla_claim *claim; struct batadv_hard_iface *primary_if; struct hlist_head *head; @@ -1963,17 +2027,21 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { - is_own = batadv_compare_eth(claim->backbone_gw->orig, + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + + is_own = batadv_compare_eth(backbone_gw->orig, primary_addr); - spin_lock_bh(&claim->backbone_gw->crc_lock); - backbone_crc = claim->backbone_gw->crc; - spin_unlock_bh(&claim->backbone_gw->crc_lock); + spin_lock_bh(&backbone_gw->crc_lock); + backbone_crc = backbone_gw->crc; + spin_unlock_bh(&backbone_gw->crc_lock); seq_printf(seq, " * %pM on %5d by %pM [%c] (%#.4x)\n", claim->addr, BATADV_PRINT_VID(claim->vid), - claim->backbone_gw->orig, + backbone_gw->orig, (is_own ? 'x' : ' '), backbone_crc); + + batadv_backbone_gw_put(backbone_gw); } rcu_read_unlock(); } diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index fa76465..b1cc8bf 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1011,9 +1011,12 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, if (!skb_new) goto out; - if (vid & BATADV_VLAN_HAS_TAG) + if (vid & BATADV_VLAN_HAS_TAG) { skb_new = vlan_insert_tag(skb_new, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); + if (!skb_new) + goto out; + } skb_reset_mac_header(skb_new); skb_new->protocol = eth_type_trans(skb_new, @@ -1091,9 +1094,12 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, */ skb_reset_mac_header(skb_new); - if (vid & BATADV_VLAN_HAS_TAG) + if (vid & BATADV_VLAN_HAS_TAG) { skb_new = vlan_insert_tag(skb_new, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); + if (!skb_new) + goto out; + } /* To preserve backwards compatibility, the node has choose the outgoing * format based on the incoming request packet type. The assumption is diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 7d1e542..3940b5d 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -785,6 +785,8 @@ static void batadv_orig_node_release(struct kref *ref) struct batadv_neigh_node *neigh_node; struct batadv_orig_node *orig_node; struct batadv_orig_ifinfo *orig_ifinfo; + struct batadv_orig_node_vlan *vlan; + struct batadv_orig_ifinfo *last_candidate; orig_node = container_of(ref, struct batadv_orig_node, refcount); @@ -802,8 +804,21 @@ static void batadv_orig_node_release(struct kref *ref) hlist_del_rcu(&orig_ifinfo->list); batadv_orig_ifinfo_put(orig_ifinfo); } + + last_candidate = orig_node->last_bonding_candidate; + orig_node->last_bonding_candidate = NULL; spin_unlock_bh(&orig_node->neigh_list_lock); + if (last_candidate) + batadv_orig_ifinfo_put(last_candidate); + + spin_lock_bh(&orig_node->vlan_list_lock); + hlist_for_each_entry_safe(vlan, node_tmp, &orig_node->vlan_list, list) { + hlist_del_rcu(&vlan->list); + batadv_orig_node_vlan_put(vlan); + } + spin_unlock_bh(&orig_node->vlan_list_lock); + /* Free nc_nodes */ batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index af8e119..7602c00 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -470,6 +470,29 @@ static int batadv_check_unicast_packet(struct batadv_priv *bat_priv, } /** + * batadv_last_bonding_replace - Replace last_bonding_candidate of orig_node + * @orig_node: originator node whose bonding candidates should be replaced + * @new_candidate: new bonding candidate or NULL + */ +static void +batadv_last_bonding_replace(struct batadv_orig_node *orig_node, + struct batadv_orig_ifinfo *new_candidate) +{ + struct batadv_orig_ifinfo *old_candidate; + + spin_lock_bh(&orig_node->neigh_list_lock); + old_candidate = orig_node->last_bonding_candidate; + + if (new_candidate) + kref_get(&new_candidate->refcount); + orig_node->last_bonding_candidate = new_candidate; + spin_unlock_bh(&orig_node->neigh_list_lock); + + if (old_candidate) + batadv_orig_ifinfo_put(old_candidate); +} + +/** * batadv_find_router - find a suitable router for this originator * @bat_priv: the bat priv with all the soft interface information * @orig_node: the destination node @@ -576,10 +599,6 @@ next: } rcu_read_unlock(); - /* last_bonding_candidate is reset below, remove the old reference. */ - if (orig_node->last_bonding_candidate) - batadv_orig_ifinfo_put(orig_node->last_bonding_candidate); - /* After finding candidates, handle the three cases: * 1) there is a next candidate, use that * 2) there is no next candidate, use the first of the list @@ -588,21 +607,28 @@ next: if (next_candidate) { batadv_neigh_node_put(router); - /* remove references to first candidate, we don't need it. */ - if (first_candidate) { - batadv_neigh_node_put(first_candidate_router); - batadv_orig_ifinfo_put(first_candidate); - } + kref_get(&next_candidate_router->refcount); router = next_candidate_router; - orig_node->last_bonding_candidate = next_candidate; + batadv_last_bonding_replace(orig_node, next_candidate); } else if (first_candidate) { batadv_neigh_node_put(router); - /* refcounting has already been done in the loop above. */ + kref_get(&first_candidate_router->refcount); router = first_candidate_router; - orig_node->last_bonding_candidate = first_candidate; + batadv_last_bonding_replace(orig_node, first_candidate); } else { - orig_node->last_bonding_candidate = NULL; + batadv_last_bonding_replace(orig_node, NULL); + } + + /* cleanup of candidates */ + if (first_candidate) { + batadv_neigh_node_put(first_candidate_router); + batadv_orig_ifinfo_put(first_candidate); + } + + if (next_candidate) { + batadv_neigh_node_put(next_candidate_router); + batadv_orig_ifinfo_put(next_candidate); } return router; diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 3a10d87..6191159 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -435,8 +435,8 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node *orig_node; orig_node = batadv_gw_get_selected_orig(bat_priv); - return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0, - orig_node, vid); + return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, + BATADV_P_DATA, orig_node, vid); } void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet) diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 43db7b6..a64522c 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -331,7 +331,9 @@ struct batadv_orig_node { DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); u32 last_bcast_seqno; struct hlist_head neigh_list; - /* neigh_list_lock protects: neigh_list and router */ + /* neigh_list_lock protects: neigh_list, ifinfo_list, + * last_bonding_candidate and router + */ spinlock_t neigh_list_lock; struct hlist_node hash_entry; struct batadv_priv *bat_priv; @@ -1171,6 +1173,7 @@ struct batadv_bla_backbone_gw { * @addr: mac address of claimed non-mesh client * @vid: vlan id this client was detected on * @backbone_gw: pointer to backbone gw claiming this client + * @backbone_lock: lock protecting backbone_gw pointer * @lasttime: last time we heard of claim (locals only) * @hash_entry: hlist node for batadv_priv_bla::claim_hash * @refcount: number of contexts the object is used @@ -1180,6 +1183,7 @@ struct batadv_bla_claim { u8 addr[ETH_ALEN]; unsigned short vid; struct batadv_bla_backbone_gw *backbone_gw; + spinlock_t backbone_lock; /* protects backbone_gw */ unsigned long lasttime; struct hlist_node hash_entry; struct rcu_head rcu; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 98f6c37..ddf8432 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3163,6 +3163,8 @@ void hci_unregister_dev(struct hci_dev *hdev) device_del(&hdev->dev); debugfs_remove_recursive(hdev->debugfs); + kfree_const(hdev->hw_info); + kfree_const(hdev->fw_info); destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); @@ -3266,6 +3268,28 @@ int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb) } EXPORT_SYMBOL(hci_recv_diag); +void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...) +{ + va_list vargs; + + va_start(vargs, fmt); + kfree_const(hdev->hw_info); + hdev->hw_info = kvasprintf_const(GFP_KERNEL, fmt, vargs); + va_end(vargs); +} +EXPORT_SYMBOL(hci_set_hw_info); + +void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...) +{ + va_list vargs; + + va_start(vargs, fmt); + kfree_const(hdev->fw_info); + hdev->fw_info = kvasprintf_const(GFP_KERNEL, fmt, vargs); + va_end(vargs); +} +EXPORT_SYMBOL(hci_set_fw_info); + /* ---- Interface to upper protocols ---- */ int hci_register_cb(struct hci_cb *cb) diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 7db4220..63df63e 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -76,6 +76,30 @@ static const struct file_operations __name ## _fops = { \ .llseek = default_llseek, \ } \ +#define DEFINE_INFO_ATTRIBUTE(__name, __field) \ +static int __name ## _show(struct seq_file *f, void *ptr) \ +{ \ + struct hci_dev *hdev = f->private; \ + \ + hci_dev_lock(hdev); \ + seq_printf(f, "%s\n", hdev->__field ? : ""); \ + hci_dev_unlock(hdev); \ + \ + return 0; \ +} \ + \ +static int __name ## _open(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, __name ## _show, inode->i_private); \ +} \ + \ +static const struct file_operations __name ## _fops = { \ + .open = __name ## _open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ +} \ + static int features_show(struct seq_file *f, void *ptr) { struct hci_dev *hdev = f->private; @@ -349,6 +373,9 @@ static const struct file_operations sc_only_mode_fops = { .llseek = default_llseek, }; +DEFINE_INFO_ATTRIBUTE(hardware_info, hw_info); +DEFINE_INFO_ATTRIBUTE(firmware_info, fw_info); + void hci_debugfs_create_common(struct hci_dev *hdev) { debugfs_create_file("features", 0444, hdev->debugfs, hdev, @@ -382,6 +409,14 @@ void hci_debugfs_create_common(struct hci_dev *hdev) if (lmp_sc_capable(hdev) || lmp_le_capable(hdev)) debugfs_create_file("sc_only_mode", 0444, hdev->debugfs, hdev, &sc_only_mode_fops); + + if (hdev->hw_info) + debugfs_create_file("hardware_info", 0444, hdev->debugfs, + hdev, &hardware_info_fops); + + if (hdev->fw_info) + debugfs_create_file("firmware_info", 0444, hdev->debugfs, + hdev, &firmware_info_fops); } static int inquiry_cache_show(struct seq_file *f, void *p) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 388ee8b..1842141 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -927,7 +927,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (get_user(opt, (u32 __user *) optval)) { + if (get_user(opt, (u16 __user *) optval)) { err = -EFAULT; break; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 8b08eec..8e48620 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -283,6 +283,14 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) case 0x01: /* IEEE MAC (Pause) */ goto drop; + case 0x0E: /* 802.1AB LLDP */ + fwd_mask |= p->br->group_fwd_mask; + if (fwd_mask & (1u << dest[5])) + goto forward; + *pskb = skb; + __br_handle_local_finish(skb); + return RX_HANDLER_PASS; + default: /* Allow selective forwarding for most other protocols */ fwd_mask |= p->br->group_fwd_mask; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b308826..aac2a6e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -975,7 +975,7 @@ void __br_set_forward_delay(struct net_bridge *br, unsigned long t); int br_set_forward_delay(struct net_bridge *br, unsigned long x); int br_set_hello_time(struct net_bridge *br, unsigned long x); int br_set_max_age(struct net_bridge *br, unsigned long x); -int br_set_ageing_time(struct net_bridge *br, u32 ageing_time); +int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time); /* br_stp_if.c */ diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 9cb7044..9258b8e 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -570,7 +570,7 @@ int br_set_max_age(struct net_bridge *br, unsigned long val) * * Offloaded switch entries maybe more restrictive */ -int br_set_ageing_time(struct net_bridge *br, u32 ageing_time) +int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time) { struct switchdev_attr attr = { .orig_dev = br->dev, diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 984d462..341caa0 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -55,7 +55,7 @@ void br_init_port(struct net_bridge_port *p) netdev_err(p->dev, "failed to set HW ageing time\n"); } -/* called under bridge lock */ +/* NO locks held */ void br_stp_enable_bridge(struct net_bridge *br) { struct net_bridge_port *p; diff --git a/net/core/dev.c b/net/core/dev.c index 7894e40..2a9c39f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -94,6 +94,7 @@ #include <linux/ethtool.h> #include <linux/notifier.h> #include <linux/skbuff.h> +#include <linux/bpf.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/busy_poll.h> @@ -6615,6 +6616,38 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) EXPORT_SYMBOL(dev_change_proto_down); /** + * dev_change_xdp_fd - set or clear a bpf program for a device rx path + * @dev: device + * @fd: new program fd or negative value to clear + * + * Set or clear a bpf program for a device + */ +int dev_change_xdp_fd(struct net_device *dev, int fd) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct bpf_prog *prog = NULL; + struct netdev_xdp xdp = {}; + int err; + + if (!ops->ndo_xdp) + return -EOPNOTSUPP; + if (fd >= 0) { + prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); + if (IS_ERR(prog)) + return PTR_ERR(prog); + } + + xdp.command = XDP_SETUP_PROG; + xdp.prog = prog; + err = ops->ndo_xdp(dev, &xdp); + if (err < 0 && prog) + bpf_prog_put(prog); + + return err; +} +EXPORT_SYMBOL(dev_change_xdp_fd); + +/** * dev_new_index - allocate an ifindex * @net: the applicable net namespace * diff --git a/net/core/filter.c b/net/core/filter.c index 22e3992..5708999 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -53,9 +53,10 @@ #include <net/sock_reuseport.h> /** - * sk_filter - run a packet through a socket filter + * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter + * @cap: limit on how short the eBPF program may trim the packet * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller @@ -64,7 +65,7 @@ * be accepted or -EPERM if the packet should be tossed. * */ -int sk_filter(struct sock *sk, struct sk_buff *skb) +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) { int err; struct sk_filter *filter; @@ -85,14 +86,13 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) filter = rcu_dereference(sk->sk_filter); if (filter) { unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb); - - err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; + err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; } rcu_read_unlock(); return err; } -EXPORT_SYMBOL(sk_filter); +EXPORT_SYMBOL(sk_filter_trim_cap); static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { @@ -2026,9 +2026,9 @@ bool bpf_helper_changes_skb_data(void *func) } static unsigned long bpf_skb_copy(void *dst_buff, const void *skb, - unsigned long len) + unsigned long off, unsigned long len) { - void *ptr = skb_header_pointer(skb, 0, len, dst_buff); + void *ptr = skb_header_pointer(skb, off, len, dst_buff); if (unlikely(!ptr)) return len; @@ -2410,6 +2410,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) } } +static const struct bpf_func_proto * +xdp_func_proto(enum bpf_func_id func_id) +{ + return sk_filter_func_proto(func_id); +} + static bool __is_valid_access(int off, int size, enum bpf_access_type type) { if (off < 0 || off >= sizeof(struct __sk_buff)) @@ -2477,6 +2483,44 @@ static bool tc_cls_act_is_valid_access(int off, int size, return __is_valid_access(off, size, type); } +static bool __is_valid_xdp_access(int off, int size, + enum bpf_access_type type) +{ + if (off < 0 || off >= sizeof(struct xdp_md)) + return false; + if (off % size != 0) + return false; + if (size != 4) + return false; + + return true; +} + +static bool xdp_is_valid_access(int off, int size, + enum bpf_access_type type, + enum bpf_reg_type *reg_type) +{ + if (type == BPF_WRITE) + return false; + + switch (off) { + case offsetof(struct xdp_md, data): + *reg_type = PTR_TO_PACKET; + break; + case offsetof(struct xdp_md, data_end): + *reg_type = PTR_TO_PACKET_END; + break; + } + + return __is_valid_xdp_access(off, size, type); +} + +void bpf_warn_invalid_xdp_action(u32 act) +{ + WARN_ONCE(1, "Illegal XDP return value %u, expect packet loss\n", act); +} +EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); + static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, struct bpf_insn *insn_buf, @@ -2628,6 +2672,29 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, return insn - insn_buf; } +static u32 xdp_convert_ctx_access(enum bpf_access_type type, int dst_reg, + int src_reg, int ctx_off, + struct bpf_insn *insn_buf, + struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + + switch (ctx_off) { + case offsetof(struct xdp_md, data): + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct xdp_buff, data)), + dst_reg, src_reg, + offsetof(struct xdp_buff, data)); + break; + case offsetof(struct xdp_md, data_end): + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct xdp_buff, data_end)), + dst_reg, src_reg, + offsetof(struct xdp_buff, data_end)); + break; + } + + return insn - insn_buf; +} + static const struct bpf_verifier_ops sk_filter_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, @@ -2640,6 +2707,12 @@ static const struct bpf_verifier_ops tc_cls_act_ops = { .convert_ctx_access = bpf_net_convert_ctx_access, }; +static const struct bpf_verifier_ops xdp_ops = { + .get_func_proto = xdp_func_proto, + .is_valid_access = xdp_is_valid_access, + .convert_ctx_access = xdp_convert_ctx_access, +}; + static struct bpf_prog_type_list sk_filter_type __read_mostly = { .ops = &sk_filter_ops, .type = BPF_PROG_TYPE_SOCKET_FILTER, @@ -2655,11 +2728,17 @@ static struct bpf_prog_type_list sched_act_type __read_mostly = { .type = BPF_PROG_TYPE_SCHED_ACT, }; +static struct bpf_prog_type_list xdp_type __read_mostly = { + .ops = &xdp_ops, + .type = BPF_PROG_TYPE_XDP, +}; + static int __init register_sk_filter_ops(void) { bpf_register_prog_type(&sk_filter_type); bpf_register_prog_type(&sched_cls_type); bpf_register_prog_type(&sched_act_type); + bpf_register_prog_type(&xdp_type); return 0; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a9e3805..189cc78 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -891,6 +891,16 @@ static size_t rtnl_port_size(const struct net_device *dev, return port_self_size; } +static size_t rtnl_xdp_size(const struct net_device *dev) +{ + size_t xdp_size = nla_total_size(1); /* XDP_ATTACHED */ + + if (!dev->netdev_ops->ndo_xdp) + return 0; + else + return xdp_size; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -927,6 +937,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + + rtnl_xdp_size(dev) /* IFLA_XDP */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } @@ -1211,6 +1222,33 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) return 0; } +static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) +{ + struct netdev_xdp xdp_op = {}; + struct nlattr *xdp; + int err; + + if (!dev->netdev_ops->ndo_xdp) + return 0; + xdp = nla_nest_start(skb, IFLA_XDP); + if (!xdp) + return -EMSGSIZE; + xdp_op.command = XDP_QUERY_PROG; + err = dev->netdev_ops->ndo_xdp(dev, &xdp_op); + if (err) + goto err_cancel; + err = nla_put_u8(skb, IFLA_XDP_ATTACHED, xdp_op.prog_attached); + if (err) + goto err_cancel; + + nla_nest_end(skb, xdp); + return 0; + +err_cancel: + nla_nest_cancel(skb, xdp); + return err; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask) @@ -1307,6 +1345,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_port_fill(skb, dev, ext_filter_mask)) goto nla_put_failure; + if (rtnl_xdp_fill(skb, dev)) + goto nla_put_failure; + if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) { if (rtnl_link_fill(skb, dev) < 0) goto nla_put_failure; @@ -1392,6 +1433,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, [IFLA_LINK_NETNSID] = { .type = NLA_S32 }, [IFLA_PROTO_DOWN] = { .type = NLA_U8 }, + [IFLA_XDP] = { .type = NLA_NESTED }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -1429,6 +1471,11 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { [IFLA_PORT_RESPONSE] = { .type = NLA_U16, }, }; +static const struct nla_policy ifla_xdp_policy[IFLA_XDP_MAX + 1] = { + [IFLA_XDP_FD] = { .type = NLA_S32 }, + [IFLA_XDP_ATTACHED] = { .type = NLA_U8 }, +}; + static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla) { const struct rtnl_link_ops *ops = NULL; @@ -2054,6 +2101,27 @@ static int do_setlink(const struct sk_buff *skb, status |= DO_SETLINK_NOTIFY; } + if (tb[IFLA_XDP]) { + struct nlattr *xdp[IFLA_XDP_MAX + 1]; + + err = nla_parse_nested(xdp, IFLA_XDP_MAX, tb[IFLA_XDP], + ifla_xdp_policy); + if (err < 0) + goto errout; + + if (xdp[IFLA_XDP_ATTACHED]) { + err = -EINVAL; + goto errout; + } + if (xdp[IFLA_XDP_FD]) { + err = dev_change_xdp_fd(dev, + nla_get_s32(xdp[IFLA_XDP_FD])); + if (err) + goto errout; + status |= DO_SETLINK_NOTIFY; + } + } + errout: if (status & DO_SETLINK_MODIFIED) { if (status & DO_SETLINK_NOTIFY) diff --git a/net/core/sock.c b/net/core/sock.c index 08bf97e..25dab8b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -452,11 +452,12 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(sock_queue_rcv_skb); -int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) +int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, + const int nested, unsigned int trim_cap) { int rc = NET_RX_SUCCESS; - if (sk_filter(sk, skb)) + if (sk_filter_trim_cap(sk, skb, trim_cap)) goto discard_and_relse; skb->dev = NULL; @@ -492,7 +493,7 @@ discard_and_relse: kfree_skb(skb); goto out; } -EXPORT_SYMBOL(sk_receive_skb); +EXPORT_SYMBOL(__sk_receive_skb); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { @@ -1938,6 +1939,10 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; sockc->tsflags |= tsflags; break; + /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ + case SCM_RIGHTS: + case SCM_CREDENTIALS: + break; default: return -EINVAL; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5c7e413..345a3ae 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -462,7 +462,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { - __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } @@ -527,17 +527,19 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) rxiph->daddr); skb_dst_set(skb, dst_clone(dst)); + local_bh_disable(); bh_lock_sock(ctl_sk); err = ip_build_and_send_pkt(skb, ctl_sk, rxiph->daddr, rxiph->saddr, NULL); bh_unlock_sock(ctl_sk); if (net_xmit_eval(err) == 0) { - DCCP_INC_STATS(DCCP_MIB_OUTSEGS); - DCCP_INC_STATS(DCCP_MIB_OUTRSTS); + __DCCP_INC_STATS(DCCP_MIB_OUTSEGS); + __DCCP_INC_STATS(DCCP_MIB_OUTRSTS); } + local_bh_enable(); out: - dst_release(dst); + dst_release(dst); } static void dccp_v4_reqsk_destructor(struct request_sock *req) @@ -866,7 +868,7 @@ lookup: goto discard_and_relse; nf_reset(skb); - return sk_receive_skb(sk, skb, 1); + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4); no_dccp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index d176f4e..3ff137d9 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -732,7 +732,7 @@ lookup: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - return sk_receive_skb(sk, skb, 1) ? -1 : 0; + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0; no_dccp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7236eb2..fc91967 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -333,6 +333,44 @@ static int dsa_slave_vlan_filtering(struct net_device *dev, return 0; } +static int dsa_fastest_ageing_time(struct dsa_switch *ds, + unsigned int ageing_time) +{ + int i; + + for (i = 0; i < DSA_MAX_PORTS; ++i) { + struct dsa_port *dp = &ds->ports[i]; + + if (dp && dp->ageing_time && dp->ageing_time < ageing_time) + ageing_time = dp->ageing_time; + } + + return ageing_time; +} + +static int dsa_slave_ageing_time(struct net_device *dev, + const struct switchdev_attr *attr, + struct switchdev_trans *trans) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + unsigned long ageing_jiffies = clock_t_to_jiffies(attr->u.ageing_time); + unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies); + + /* bridge skips -EOPNOTSUPP, so skip the prepare phase */ + if (switchdev_trans_ph_prepare(trans)) + return 0; + + /* Keep the fastest ageing time in case of multiple bridges */ + ds->ports[p->port].ageing_time = ageing_time; + ageing_time = dsa_fastest_ageing_time(ds, ageing_time); + + if (ds->drv->set_ageing_time) + return ds->drv->set_ageing_time(ds, ageing_time); + + return 0; +} + static int dsa_slave_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) @@ -346,6 +384,9 @@ static int dsa_slave_port_attr_set(struct net_device *dev, case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: ret = dsa_slave_vlan_filtering(dev, attr, trans); break; + case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + ret = dsa_slave_ageing_time(dev, attr, trans); + break; default: ret = -EOPNOTSUPP; break; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index d09173b..539fa26 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -479,6 +479,9 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (!rtnh_ok(rtnh, remaining)) return -EINVAL; + if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + return -EINVAL; + nexthop_nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; nexthop_nh->nh_oif = rtnh->rtnh_ifindex; @@ -1003,6 +1006,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (fib_props[cfg->fc_type].scope > cfg->fc_scope) goto err_inval; + if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + goto err_inval; + #ifdef CONFIG_IP_ROUTE_MULTIPATH if (cfg->fc_mp) { nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 9f0a7b9..8b4ffd2 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; - IPCB(skb)->flags |= IPSKB_FORWARDED; + IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); if (ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e23f141..dde37fb 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -223,8 +223,10 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *segs; int ret = 0; - /* common case: locally created skb or seglen is <= mtu */ - if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) || + /* common case: fragmentation of segments is not allowed, + * or seglen is <= mtu + */ + if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) || skb_gso_validate_mtu(skb, mtu)) return ip_finish_output2(net, sk, skb); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index afd6b59..9d847c3 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -63,6 +63,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); struct net_device *dev = skb->dev; + int skb_iif = skb->skb_iif; struct iphdr *iph; int err; @@ -72,6 +73,14 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + if (skb_iif && proto == IPPROTO_UDP) { + /* Arrived from an ingress interface and got udp encapuslated. + * The encapsulated network segment length may exceed dst mtu. + * Allow IP Fragmentation of segments. + */ + IPCB(skb)->flags |= IPSKB_FRAG_SEGS; + } + /* Push down and install the IP header. */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index e0d76f5..eec2341 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1749,7 +1749,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, vif->dev->stats.tx_bytes += skb->len; } - IPCB(skb)->flags |= IPSKB_FORWARDED; + IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS; /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index c8dd9e2..b31df59 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -299,23 +299,12 @@ static inline bool unconditional(const struct arpt_entry *e) memcmp(&e->arp, &uncond, sizeof(uncond)) == 0; } -static bool find_jump_target(const struct xt_table_info *t, - const struct arpt_entry *target) -{ - struct arpt_entry *iter; - - xt_entry_foreach(iter, t->entries, t->size) { - if (iter == target) - return true; - } - return false; -} - /* Figures out from what hook each rule can be called: returns 0 if * there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, - unsigned int valid_hooks, void *entry0) + unsigned int valid_hooks, void *entry0, + unsigned int *offsets) { unsigned int hook; @@ -388,10 +377,11 @@ static int mark_source_chains(const struct xt_table_info *newinfo, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ + if (!xt_find_jump_offset(offsets, newpos, + newinfo->number)) + return 0; e = (struct arpt_entry *) (entry0 + newpos); - if (!find_jump_target(newinfo, e)) - return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; @@ -543,6 +533,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, const struct arpt_replace *repl) { struct arpt_entry *iter; + unsigned int *offsets; unsigned int i; int ret = 0; @@ -555,6 +546,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, newinfo->underflow[i] = 0xFFFFFFFF; } + offsets = xt_alloc_entry_offsets(newinfo->number); + if (!offsets) + return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ @@ -565,17 +559,20 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, repl->underflow, repl->valid_hooks); if (ret != 0) - break; + goto out_free; + if (i < repl->num_entries) + offsets[i] = (void *)iter - entry0; ++i; if (strcmp(arpt_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } if (ret != 0) - return ret; + goto out_free; + ret = -EINVAL; if (i != repl->num_entries) - return -EINVAL; + goto out_free; /* Check hooks all assigned */ for (i = 0; i < NF_ARP_NUMHOOKS; i++) { @@ -583,13 +580,16 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, if (!(repl->valid_hooks & (1 << i))) continue; if (newinfo->hook_entry[i] == 0xFFFFFFFF) - return -EINVAL; + goto out_free; if (newinfo->underflow[i] == 0xFFFFFFFF) - return -EINVAL; + goto out_free; } - if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) - return -ELOOP; + if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { + ret = -ELOOP; + goto out_free; + } + kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; @@ -610,6 +610,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, } return ret; + out_free: + kvfree(offsets); + return ret; } static void get_counters(const struct xt_table_info *t, diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index f0df66f..f993545 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -373,23 +373,12 @@ ipt_do_table(struct sk_buff *skb, else return verdict; } -static bool find_jump_target(const struct xt_table_info *t, - const struct ipt_entry *target) -{ - struct ipt_entry *iter; - - xt_entry_foreach(iter, t->entries, t->size) { - if (iter == target) - return true; - } - return false; -} - /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, - unsigned int valid_hooks, void *entry0) + unsigned int valid_hooks, void *entry0, + unsigned int *offsets) { unsigned int hook; @@ -458,10 +447,11 @@ mark_source_chains(const struct xt_table_info *newinfo, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ + if (!xt_find_jump_offset(offsets, newpos, + newinfo->number)) + return 0; e = (struct ipt_entry *) (entry0 + newpos); - if (!find_jump_target(newinfo, e)) - return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; @@ -694,6 +684,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ipt_replace *repl) { struct ipt_entry *iter; + unsigned int *offsets; unsigned int i; int ret = 0; @@ -706,6 +697,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, newinfo->underflow[i] = 0xFFFFFFFF; } + offsets = xt_alloc_entry_offsets(newinfo->number); + if (!offsets) + return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { @@ -715,15 +709,18 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, repl->underflow, repl->valid_hooks); if (ret != 0) - return ret; + goto out_free; + if (i < repl->num_entries) + offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ipt_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } + ret = -EINVAL; if (i != repl->num_entries) - return -EINVAL; + goto out_free; /* Check hooks all assigned */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { @@ -731,13 +728,16 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, if (!(repl->valid_hooks & (1 << i))) continue; if (newinfo->hook_entry[i] == 0xFFFFFFFF) - return -EINVAL; + goto out_free; if (newinfo->underflow[i] == 0xFFFFFFFF) - return -EINVAL; + goto out_free; } - if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) - return -ELOOP; + if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { + ret = -ELOOP; + goto out_free; + } + kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; @@ -758,6 +758,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, } return ret; + out_free: + kvfree(offsets); + return ret; } static void diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index c6f3c40..6392371 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -26,6 +26,8 @@ struct ct_iter_state { struct seq_net_private p; + struct hlist_nulls_head *hash; + unsigned int htable_size; unsigned int bucket; }; @@ -35,10 +37,10 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) struct hlist_nulls_node *n; for (st->bucket = 0; - st->bucket < nf_conntrack_htable_size; + st->bucket < st->htable_size; st->bucket++) { n = rcu_dereference( - hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket])); + hlist_nulls_first_rcu(&st->hash[st->bucket])); if (!is_a_nulls(n)) return n; } @@ -53,11 +55,11 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, head = rcu_dereference(hlist_nulls_next_rcu(head)); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { - if (++st->bucket >= nf_conntrack_htable_size) + if (++st->bucket >= st->htable_size) return NULL; } head = rcu_dereference( - hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket])); + hlist_nulls_first_rcu(&st->hash[st->bucket])); } return head; } @@ -75,7 +77,11 @@ static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos) static void *ct_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { + struct ct_iter_state *st = seq->private; + rcu_read_lock(); + + nf_conntrack_get_ht(&st->hash, &st->htable_size); return ct_get_idx(seq, *pos); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 94d4aff..f9f9e37 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -87,7 +87,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); /* rfc5961 challenge ack rate limiting */ -int sysctl_tcp_challenge_ack_limit = 100; +int sysctl_tcp_challenge_ack_limit = 1000; int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; @@ -3424,6 +3424,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } +static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, + u32 *last_oow_ack_time) +{ + if (*last_oow_ack_time) { + s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + + if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + NET_INC_STATS(net, mib_idx); + return true; /* rate-limited: don't send yet! */ + } + } + + *last_oow_ack_time = tcp_time_stamp; + + return false; /* not rate-limited: go ahead, send dupack now! */ +} + /* Return true if we're currently rate-limiting out-of-window ACKs and * thus shouldn't send a dupack right now. We rate-limit dupacks in * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS @@ -3437,21 +3454,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, /* Data packets without SYNs are not likely part of an ACK loop. */ if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; + return false; -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ + return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time); } /* RFC 5961 7 [ACK Throttling] */ @@ -3461,21 +3466,26 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) static u32 challenge_timestamp; static unsigned int challenge_count; struct tcp_sock *tp = tcp_sk(sk); - u32 now; + u32 count, now; /* First check our per-socket dupack rate limit. */ - if (tcp_oow_rate_limited(sock_net(sk), skb, - LINUX_MIB_TCPACKSKIPPEDCHALLENGE, - &tp->last_oow_ack_time)) + if (__tcp_oow_rate_limited(sock_net(sk), + LINUX_MIB_TCPACKSKIPPEDCHALLENGE, + &tp->last_oow_ack_time)) return; - /* Then check the check host-wide RFC 5961 rate limit. */ + /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != challenge_timestamp) { + u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1; + challenge_timestamp = now; - challenge_count = 0; + WRITE_ONCE(challenge_count, half + + prandom_u32_max(sysctl_tcp_challenge_ack_limit)); } - if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + count = READ_ONCE(challenge_count); + if (count > 0) { + WRITE_ONCE(challenge_count, count - 1); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack(sk); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ca5e8ea..4aed8fc 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1583,6 +1583,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (sk_filter(sk, skb)) goto drop; + if (unlikely(skb->len < sizeof(struct udphdr))) + goto drop; udp_csum_pull_header(skb); if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 61ed950..552fac2 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -402,23 +402,12 @@ ip6t_do_table(struct sk_buff *skb, else return verdict; } -static bool find_jump_target(const struct xt_table_info *t, - const struct ip6t_entry *target) -{ - struct ip6t_entry *iter; - - xt_entry_foreach(iter, t->entries, t->size) { - if (iter == target) - return true; - } - return false; -} - /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, - unsigned int valid_hooks, void *entry0) + unsigned int valid_hooks, void *entry0, + unsigned int *offsets) { unsigned int hook; @@ -487,10 +476,11 @@ mark_source_chains(const struct xt_table_info *newinfo, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ + if (!xt_find_jump_offset(offsets, newpos, + newinfo->number)) + return 0; e = (struct ip6t_entry *) (entry0 + newpos); - if (!find_jump_target(newinfo, e)) - return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; @@ -724,6 +714,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ip6t_replace *repl) { struct ip6t_entry *iter; + unsigned int *offsets; unsigned int i; int ret = 0; @@ -736,6 +727,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, newinfo->underflow[i] = 0xFFFFFFFF; } + offsets = xt_alloc_entry_offsets(newinfo->number); + if (!offsets) + return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { @@ -745,15 +739,18 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, repl->underflow, repl->valid_hooks); if (ret != 0) - return ret; + goto out_free; + if (i < repl->num_entries) + offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ip6t_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } + ret = -EINVAL; if (i != repl->num_entries) - return -EINVAL; + goto out_free; /* Check hooks all assigned */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { @@ -761,13 +758,16 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, if (!(repl->valid_hooks & (1 << i))) continue; if (newinfo->hook_entry[i] == 0xFFFFFFFF) - return -EINVAL; + goto out_free; if (newinfo->underflow[i] == 0xFFFFFFFF) - return -EINVAL; + goto out_free; } - if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) - return -ELOOP; + if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { + ret = -ELOOP; + goto out_free; + } + kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; @@ -788,6 +788,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, } return ret; + out_free: + kvfree(offsets); + return ret; } static void diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 0a71a312d..ad5292b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -620,6 +620,8 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (sk_filter(sk, skb)) goto drop; + if (unlikely(skb->len < sizeof(struct udphdr))) + goto drop; udp_csum_pull_header(skb); if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { diff --git a/net/ncsi/Kconfig b/net/ncsi/Kconfig new file mode 100644 index 0000000..08a8a60 --- /dev/null +++ b/net/ncsi/Kconfig @@ -0,0 +1,12 @@ +# +# Configuration for NCSI support +# + +config NET_NCSI + bool "NCSI interface support" + depends on INET + ---help--- + This module provides NCSI (Network Controller Sideband Interface) + support. Enable this only if your system connects to a network + device via NCSI and the ethernet driver you're using supports + the protocol explicitly. diff --git a/net/ncsi/Makefile b/net/ncsi/Makefile new file mode 100644 index 0000000..dd12b56 --- /dev/null +++ b/net/ncsi/Makefile @@ -0,0 +1,4 @@ +# +# Makefile for NCSI API +# +obj-$(CONFIG_NET_NCSI) += ncsi-cmd.o ncsi-rsp.o ncsi-aen.o ncsi-manage.o diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h new file mode 100644 index 0000000..33738c0 --- /dev/null +++ b/net/ncsi/internal.h @@ -0,0 +1,328 @@ +/* + * Copyright Gavin Shan, IBM Corporation 2016. + * + * 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 __NCSI_INTERNAL_H__ +#define __NCSI_INTERNAL_H__ + +enum { + NCSI_CAP_BASE = 0, + NCSI_CAP_GENERIC = 0, + NCSI_CAP_BC, + NCSI_CAP_MC, + NCSI_CAP_BUFFER, + NCSI_CAP_AEN, + NCSI_CAP_VLAN, + NCSI_CAP_MAX +}; + +enum { + NCSI_CAP_GENERIC_HWA = 0x01, /* HW arbitration */ + NCSI_CAP_GENERIC_HDS = 0x02, /* HNC driver status change */ + NCSI_CAP_GENERIC_FC = 0x04, /* HNC to MC flow control */ + NCSI_CAP_GENERIC_FC1 = 0x08, /* MC to HNC flow control */ + NCSI_CAP_GENERIC_MC = 0x10, /* Global MC filtering */ + NCSI_CAP_GENERIC_HWA_UNKNOWN = 0x00, /* Unknown HW arbitration */ + NCSI_CAP_GENERIC_HWA_SUPPORT = 0x20, /* Supported HW arbitration */ + NCSI_CAP_GENERIC_HWA_NOT_SUPPORT = 0x40, /* No HW arbitration */ + NCSI_CAP_GENERIC_HWA_RESERVED = 0x60, /* Reserved HW arbitration */ + NCSI_CAP_GENERIC_HWA_MASK = 0x60, /* Mask for HW arbitration */ + NCSI_CAP_GENERIC_MASK = 0x7f, + NCSI_CAP_BC_ARP = 0x01, /* ARP packet filtering */ + NCSI_CAP_BC_DHCPC = 0x02, /* DHCP client filtering */ + NCSI_CAP_BC_DHCPS = 0x04, /* DHCP server filtering */ + NCSI_CAP_BC_NETBIOS = 0x08, /* NetBIOS packet filtering */ + NCSI_CAP_BC_MASK = 0x0f, + NCSI_CAP_MC_IPV6_NEIGHBOR = 0x01, /* IPv6 neighbor filtering */ + NCSI_CAP_MC_IPV6_ROUTER = 0x02, /* IPv6 router filering */ + NCSI_CAP_MC_DHCPV6_RELAY = 0x04, /* DHCPv6 relay / server MC */ + NCSI_CAP_MC_DHCPV6_WELL_KNOWN = 0x08, /* DHCPv6 well-known MC */ + NCSI_CAP_MC_IPV6_MLD = 0x10, /* IPv6 MLD filtering */ + NCSI_CAP_MC_IPV6_NEIGHBOR_S = 0x20, /* IPv6 neighbour filtering */ + NCSI_CAP_MC_MASK = 0x3f, + NCSI_CAP_AEN_LSC = 0x01, /* Link status change */ + NCSI_CAP_AEN_CR = 0x02, /* Configuration required */ + NCSI_CAP_AEN_HDS = 0x04, /* HNC driver status */ + NCSI_CAP_AEN_MASK = 0x07, + NCSI_CAP_VLAN_ONLY = 0x01, /* Filter VLAN packet only */ + NCSI_CAP_VLAN_NO = 0x02, /* Filter VLAN and non-VLAN */ + NCSI_CAP_VLAN_ANY = 0x04, /* Filter Any-and-non-VLAN */ + NCSI_CAP_VLAN_MASK = 0x07 +}; + +enum { + NCSI_MODE_BASE = 0, + NCSI_MODE_ENABLE = 0, + NCSI_MODE_TX_ENABLE, + NCSI_MODE_LINK, + NCSI_MODE_VLAN, + NCSI_MODE_BC, + NCSI_MODE_MC, + NCSI_MODE_AEN, + NCSI_MODE_FC, + NCSI_MODE_MAX +}; + +enum { + NCSI_FILTER_BASE = 0, + NCSI_FILTER_VLAN = 0, + NCSI_FILTER_UC, + NCSI_FILTER_MC, + NCSI_FILTER_MIXED, + NCSI_FILTER_MAX +}; + +struct ncsi_channel_version { + u32 version; /* Supported BCD encoded NCSI version */ + u32 alpha2; /* Supported BCD encoded NCSI version */ + u8 fw_name[12]; /* Firware name string */ + u32 fw_version; /* Firmware version */ + u16 pci_ids[4]; /* PCI identification */ + u32 mf_id; /* Manufacture ID */ +}; + +struct ncsi_channel_cap { + u32 index; /* Index of channel capabilities */ + u32 cap; /* NCSI channel capability */ +}; + +struct ncsi_channel_mode { + u32 index; /* Index of channel modes */ + u32 enable; /* Enabled or disabled */ + u32 size; /* Valid entries in ncm_data[] */ + u32 data[8]; /* Data entries */ +}; + +struct ncsi_channel_filter { + u32 index; /* Index of channel filters */ + u32 total; /* Total entries in the filter table */ + u64 bitmap; /* Bitmap of valid entries */ + u32 data[]; /* Data for the valid entries */ +}; + +struct ncsi_channel_stats { + u32 hnc_cnt_hi; /* Counter cleared */ + u32 hnc_cnt_lo; /* Counter cleared */ + u32 hnc_rx_bytes; /* Rx bytes */ + u32 hnc_tx_bytes; /* Tx bytes */ + u32 hnc_rx_uc_pkts; /* Rx UC packets */ + u32 hnc_rx_mc_pkts; /* Rx MC packets */ + u32 hnc_rx_bc_pkts; /* Rx BC packets */ + u32 hnc_tx_uc_pkts; /* Tx UC packets */ + u32 hnc_tx_mc_pkts; /* Tx MC packets */ + u32 hnc_tx_bc_pkts; /* Tx BC packets */ + u32 hnc_fcs_err; /* FCS errors */ + u32 hnc_align_err; /* Alignment errors */ + u32 hnc_false_carrier; /* False carrier detection */ + u32 hnc_runt_pkts; /* Rx runt packets */ + u32 hnc_jabber_pkts; /* Rx jabber packets */ + u32 hnc_rx_pause_xon; /* Rx pause XON frames */ + u32 hnc_rx_pause_xoff; /* Rx XOFF frames */ + u32 hnc_tx_pause_xon; /* Tx XON frames */ + u32 hnc_tx_pause_xoff; /* Tx XOFF frames */ + u32 hnc_tx_s_collision; /* Single collision frames */ + u32 hnc_tx_m_collision; /* Multiple collision frames */ + u32 hnc_l_collision; /* Late collision frames */ + u32 hnc_e_collision; /* Excessive collision frames */ + u32 hnc_rx_ctl_frames; /* Rx control frames */ + u32 hnc_rx_64_frames; /* Rx 64-bytes frames */ + u32 hnc_rx_127_frames; /* Rx 65-127 bytes frames */ + u32 hnc_rx_255_frames; /* Rx 128-255 bytes frames */ + u32 hnc_rx_511_frames; /* Rx 256-511 bytes frames */ + u32 hnc_rx_1023_frames; /* Rx 512-1023 bytes frames */ + u32 hnc_rx_1522_frames; /* Rx 1024-1522 bytes frames */ + u32 hnc_rx_9022_frames; /* Rx 1523-9022 bytes frames */ + u32 hnc_tx_64_frames; /* Tx 64-bytes frames */ + u32 hnc_tx_127_frames; /* Tx 65-127 bytes frames */ + u32 hnc_tx_255_frames; /* Tx 128-255 bytes frames */ + u32 hnc_tx_511_frames; /* Tx 256-511 bytes frames */ + u32 hnc_tx_1023_frames; /* Tx 512-1023 bytes frames */ + u32 hnc_tx_1522_frames; /* Tx 1024-1522 bytes frames */ + u32 hnc_tx_9022_frames; /* Tx 1523-9022 bytes frames */ + u32 hnc_rx_valid_bytes; /* Rx valid bytes */ + u32 hnc_rx_runt_pkts; /* Rx error runt packets */ + u32 hnc_rx_jabber_pkts; /* Rx error jabber packets */ + u32 ncsi_rx_cmds; /* Rx NCSI commands */ + u32 ncsi_dropped_cmds; /* Dropped commands */ + u32 ncsi_cmd_type_errs; /* Command type errors */ + u32 ncsi_cmd_csum_errs; /* Command checksum errors */ + u32 ncsi_rx_pkts; /* Rx NCSI packets */ + u32 ncsi_tx_pkts; /* Tx NCSI packets */ + u32 ncsi_tx_aen_pkts; /* Tx AEN packets */ + u32 pt_tx_pkts; /* Tx packets */ + u32 pt_tx_dropped; /* Tx dropped packets */ + u32 pt_tx_channel_err; /* Tx channel errors */ + u32 pt_tx_us_err; /* Tx undersize errors */ + u32 pt_rx_pkts; /* Rx packets */ + u32 pt_rx_dropped; /* Rx dropped packets */ + u32 pt_rx_channel_err; /* Rx channel errors */ + u32 pt_rx_us_err; /* Rx undersize errors */ + u32 pt_rx_os_err; /* Rx oversize errors */ +}; + +struct ncsi_dev_priv; +struct ncsi_package; + +#define NCSI_PACKAGE_SHIFT 5 +#define NCSI_PACKAGE_INDEX(c) (((c) >> NCSI_PACKAGE_SHIFT) & 0x7) +#define NCSI_CHANNEL_INDEX(c) ((c) & ((1 << NCSI_PACKAGE_SHIFT) - 1)) +#define NCSI_TO_CHANNEL(p, c) (((p) << NCSI_PACKAGE_SHIFT) | (c)) + +struct ncsi_channel { + unsigned char id; + int state; +#define NCSI_CHANNEL_INACTIVE 1 +#define NCSI_CHANNEL_ACTIVE 2 +#define NCSI_CHANNEL_INVISIBLE 3 + spinlock_t lock; /* Protect filters etc */ + struct ncsi_package *package; + struct ncsi_channel_version version; + struct ncsi_channel_cap caps[NCSI_CAP_MAX]; + struct ncsi_channel_mode modes[NCSI_MODE_MAX]; + struct ncsi_channel_filter *filters[NCSI_FILTER_MAX]; + struct ncsi_channel_stats stats; + struct timer_list timer; /* Link monitor timer */ + bool enabled; /* Timer is enabled */ + unsigned int timeout; /* Times of timeout */ + struct list_head node; + struct list_head link; +}; + +struct ncsi_package { + unsigned char id; /* NCSI 3-bits package ID */ + unsigned char uuid[16]; /* UUID */ + struct ncsi_dev_priv *ndp; /* NCSI device */ + spinlock_t lock; /* Protect the package */ + unsigned int channel_num; /* Number of channels */ + struct list_head channels; /* List of chanels */ + struct list_head node; /* Form list of packages */ +}; + +struct ncsi_request { + unsigned char id; /* Request ID - 0 to 255 */ + bool used; /* Request that has been assigned */ + bool driven; /* Drive state machine */ + struct ncsi_dev_priv *ndp; /* Associated NCSI device */ + struct sk_buff *cmd; /* Associated NCSI command packet */ + struct sk_buff *rsp; /* Associated NCSI response packet */ + struct timer_list timer; /* Timer on waiting for response */ + bool enabled; /* Time has been enabled or not */ +}; + +enum { + ncsi_dev_state_major = 0xff00, + ncsi_dev_state_minor = 0x00ff, + ncsi_dev_state_probe_deselect = 0x0201, + ncsi_dev_state_probe_package, + ncsi_dev_state_probe_channel, + ncsi_dev_state_probe_cis, + ncsi_dev_state_probe_gvi, + ncsi_dev_state_probe_gc, + ncsi_dev_state_probe_gls, + ncsi_dev_state_probe_dp, + ncsi_dev_state_config_sp = 0x0301, + ncsi_dev_state_config_cis, + ncsi_dev_state_config_sma, + ncsi_dev_state_config_ebf, +#if IS_ENABLED(CONFIG_IPV6) + ncsi_dev_state_config_egmf, +#endif + ncsi_dev_state_config_ecnt, + ncsi_dev_state_config_ec, + ncsi_dev_state_config_ae, + ncsi_dev_state_config_gls, + ncsi_dev_state_config_done, + ncsi_dev_state_suspend_select = 0x0401, + ncsi_dev_state_suspend_dcnt, + ncsi_dev_state_suspend_dc, + ncsi_dev_state_suspend_deselect, + ncsi_dev_state_suspend_done +}; + +struct ncsi_dev_priv { + struct ncsi_dev ndev; /* Associated NCSI device */ + unsigned int flags; /* NCSI device flags */ +#define NCSI_DEV_PROBED 1 /* Finalized NCSI topology */ +#define NCSI_DEV_HWA 2 /* Enabled HW arbitration */ +#define NCSI_DEV_RESHUFFLE 4 + spinlock_t lock; /* Protect the NCSI device */ +#if IS_ENABLED(CONFIG_IPV6) + unsigned int inet6_addr_num; /* Number of IPv6 addresses */ +#endif + unsigned int package_num; /* Number of packages */ + struct list_head packages; /* List of packages */ + struct ncsi_request requests[256]; /* Request table */ + unsigned int request_id; /* Last used request ID */ + unsigned int pending_req_num; /* Number of pending requests */ + struct ncsi_package *active_package; /* Currently handled package */ + struct ncsi_channel *active_channel; /* Currently handled channel */ + struct list_head channel_queue; /* Config queue of channels */ + struct work_struct work; /* For channel management */ + struct packet_type ptype; /* NCSI packet Rx handler */ + struct list_head node; /* Form NCSI device list */ +}; + +struct ncsi_cmd_arg { + struct ncsi_dev_priv *ndp; /* Associated NCSI device */ + unsigned char type; /* Command in the NCSI packet */ + unsigned char id; /* Request ID (sequence number) */ + unsigned char package; /* Destination package ID */ + unsigned char channel; /* Detination channel ID or 0x1f */ + unsigned short payload; /* Command packet payload length */ + bool driven; /* Drive the state machine? */ + union { + unsigned char bytes[16]; /* Command packet specific data */ + unsigned short words[8]; + unsigned int dwords[4]; + }; +}; + +extern struct list_head ncsi_dev_list; +extern spinlock_t ncsi_dev_lock; + +#define TO_NCSI_DEV_PRIV(nd) \ + container_of(nd, struct ncsi_dev_priv, ndev) +#define NCSI_FOR_EACH_DEV(ndp) \ + list_for_each_entry_rcu(ndp, &ncsi_dev_list, node) +#define NCSI_FOR_EACH_PACKAGE(ndp, np) \ + list_for_each_entry_rcu(np, &ndp->packages, node) +#define NCSI_FOR_EACH_CHANNEL(np, nc) \ + list_for_each_entry_rcu(nc, &np->channels, node) + +/* Resources */ +int ncsi_find_filter(struct ncsi_channel *nc, int table, void *data); +int ncsi_add_filter(struct ncsi_channel *nc, int table, void *data); +int ncsi_remove_filter(struct ncsi_channel *nc, int table, int index); +void ncsi_start_channel_monitor(struct ncsi_channel *nc); +void ncsi_stop_channel_monitor(struct ncsi_channel *nc); +struct ncsi_channel *ncsi_find_channel(struct ncsi_package *np, + unsigned char id); +struct ncsi_channel *ncsi_add_channel(struct ncsi_package *np, + unsigned char id); +struct ncsi_package *ncsi_find_package(struct ncsi_dev_priv *ndp, + unsigned char id); +struct ncsi_package *ncsi_add_package(struct ncsi_dev_priv *ndp, + unsigned char id); +void ncsi_remove_package(struct ncsi_package *np); +void ncsi_find_package_and_channel(struct ncsi_dev_priv *ndp, + unsigned char id, + struct ncsi_package **np, + struct ncsi_channel **nc); +struct ncsi_request *ncsi_alloc_request(struct ncsi_dev_priv *ndp, bool driven); +void ncsi_free_request(struct ncsi_request *nr); +struct ncsi_dev *ncsi_find_dev(struct net_device *dev); +int ncsi_process_next_channel(struct ncsi_dev_priv *ndp); + +/* Packet handlers */ +u32 ncsi_calculate_checksum(unsigned char *data, int len); +int ncsi_xmit_cmd(struct ncsi_cmd_arg *nca); +int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev); +int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb); + +#endif /* __NCSI_INTERNAL_H__ */ diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c new file mode 100644 index 0000000..d463468 --- /dev/null +++ b/net/ncsi/ncsi-aen.c @@ -0,0 +1,193 @@ +/* + * Copyright Gavin Shan, IBM Corporation 2016. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> + +#include <net/ncsi.h> +#include <net/net_namespace.h> +#include <net/sock.h> + +#include "internal.h" +#include "ncsi-pkt.h" + +static int ncsi_validate_aen_pkt(struct ncsi_aen_pkt_hdr *h, + const unsigned short payload) +{ + u32 checksum; + __be32 *pchecksum; + + if (h->common.revision != NCSI_PKT_REVISION) + return -EINVAL; + if (ntohs(h->common.length) != payload) + return -EINVAL; + + /* Validate checksum, which might be zeroes if the + * sender doesn't support checksum according to NCSI + * specification. + */ + pchecksum = (__be32 *)((void *)(h + 1) + payload - 4); + if (ntohl(*pchecksum) == 0) + return 0; + + checksum = ncsi_calculate_checksum((unsigned char *)h, + sizeof(*h) + payload - 4); + if (*pchecksum != htonl(checksum)) + return -EINVAL; + + return 0; +} + +static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp, + struct ncsi_aen_pkt_hdr *h) +{ + struct ncsi_aen_lsc_pkt *lsc; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + unsigned long old_data; + unsigned long flags; + + /* Find the NCSI channel */ + ncsi_find_package_and_channel(ndp, h->common.channel, NULL, &nc); + if (!nc) + return -ENODEV; + + /* Update the link status */ + ncm = &nc->modes[NCSI_MODE_LINK]; + lsc = (struct ncsi_aen_lsc_pkt *)h; + old_data = ncm->data[2]; + ncm->data[2] = ntohl(lsc->status); + ncm->data[4] = ntohl(lsc->oem_status); + if (!((old_data ^ ncm->data[2]) & 0x1) || + !list_empty(&nc->link)) + return 0; + if (!(nc->state == NCSI_CHANNEL_INACTIVE && (ncm->data[2] & 0x1)) && + !(nc->state == NCSI_CHANNEL_ACTIVE && !(ncm->data[2] & 0x1))) + return 0; + + if (!(ndp->flags & NCSI_DEV_HWA) && + nc->state == NCSI_CHANNEL_ACTIVE) + ndp->flags |= NCSI_DEV_RESHUFFLE; + + ncsi_stop_channel_monitor(nc); + spin_lock_irqsave(&ndp->lock, flags); + list_add_tail_rcu(&nc->link, &ndp->channel_queue); + spin_unlock_irqrestore(&ndp->lock, flags); + + return ncsi_process_next_channel(ndp); +} + +static int ncsi_aen_handler_cr(struct ncsi_dev_priv *ndp, + struct ncsi_aen_pkt_hdr *h) +{ + struct ncsi_channel *nc; + unsigned long flags; + + /* Find the NCSI channel */ + ncsi_find_package_and_channel(ndp, h->common.channel, NULL, &nc); + if (!nc) + return -ENODEV; + + if (!list_empty(&nc->link) || + nc->state != NCSI_CHANNEL_ACTIVE) + return 0; + + ncsi_stop_channel_monitor(nc); + spin_lock_irqsave(&ndp->lock, flags); + xchg(&nc->state, NCSI_CHANNEL_INACTIVE); + list_add_tail_rcu(&nc->link, &ndp->channel_queue); + spin_unlock_irqrestore(&ndp->lock, flags); + + return ncsi_process_next_channel(ndp); +} + +static int ncsi_aen_handler_hncdsc(struct ncsi_dev_priv *ndp, + struct ncsi_aen_pkt_hdr *h) +{ + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + struct ncsi_aen_hncdsc_pkt *hncdsc; + unsigned long flags; + + /* Find the NCSI channel */ + ncsi_find_package_and_channel(ndp, h->common.channel, NULL, &nc); + if (!nc) + return -ENODEV; + + /* If the channel is active one, we need reconfigure it */ + ncm = &nc->modes[NCSI_MODE_LINK]; + hncdsc = (struct ncsi_aen_hncdsc_pkt *)h; + ncm->data[3] = ntohl(hncdsc->status); + if (!list_empty(&nc->link) || + nc->state != NCSI_CHANNEL_ACTIVE || + (ncm->data[3] & 0x1)) + return 0; + + if (ndp->flags & NCSI_DEV_HWA) + ndp->flags |= NCSI_DEV_RESHUFFLE; + + /* If this channel is the active one and the link doesn't + * work, we have to choose another channel to be active one. + * The logic here is exactly similar to what we do when link + * is down on the active channel. + */ + ncsi_stop_channel_monitor(nc); + spin_lock_irqsave(&ndp->lock, flags); + list_add_tail_rcu(&nc->link, &ndp->channel_queue); + spin_unlock_irqrestore(&ndp->lock, flags); + + ncsi_process_next_channel(ndp); + + return 0; +} + +static struct ncsi_aen_handler { + unsigned char type; + int payload; + int (*handler)(struct ncsi_dev_priv *ndp, + struct ncsi_aen_pkt_hdr *h); +} ncsi_aen_handlers[] = { + { NCSI_PKT_AEN_LSC, 12, ncsi_aen_handler_lsc }, + { NCSI_PKT_AEN_CR, 4, ncsi_aen_handler_cr }, + { NCSI_PKT_AEN_HNCDSC, 4, ncsi_aen_handler_hncdsc } +}; + +int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb) +{ + struct ncsi_aen_pkt_hdr *h; + struct ncsi_aen_handler *nah = NULL; + int i, ret; + + /* Find the handler */ + h = (struct ncsi_aen_pkt_hdr *)skb_network_header(skb); + for (i = 0; i < ARRAY_SIZE(ncsi_aen_handlers); i++) { + if (ncsi_aen_handlers[i].type == h->type) { + nah = &ncsi_aen_handlers[i]; + break; + } + } + + if (!nah) { + netdev_warn(ndp->ndev.dev, "Invalid AEN (0x%x) received\n", + h->type); + return -ENOENT; + } + + ret = ncsi_validate_aen_pkt(h, nah->payload); + if (ret) + goto out; + + ret = nah->handler(ndp, h); +out: + consume_skb(skb); + return ret; +} diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c new file mode 100644 index 0000000..21057a8 --- /dev/null +++ b/net/ncsi/ncsi-cmd.c @@ -0,0 +1,367 @@ +/* + * Copyright Gavin Shan, IBM Corporation 2016. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/etherdevice.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> + +#include <net/ncsi.h> +#include <net/net_namespace.h> +#include <net/sock.h> + +#include "internal.h" +#include "ncsi-pkt.h" + +u32 ncsi_calculate_checksum(unsigned char *data, int len) +{ + u32 checksum = 0; + int i; + + for (i = 0; i < len; i += 2) + checksum += (((u32)data[i] << 8) | data[i + 1]); + + checksum = (~checksum + 1); + return checksum; +} + +/* This function should be called after the data area has been + * populated completely. + */ +static void ncsi_cmd_build_header(struct ncsi_pkt_hdr *h, + struct ncsi_cmd_arg *nca) +{ + u32 checksum; + __be32 *pchecksum; + + h->mc_id = 0; + h->revision = NCSI_PKT_REVISION; + h->reserved = 0; + h->id = nca->id; + h->type = nca->type; + h->channel = NCSI_TO_CHANNEL(nca->package, + nca->channel); + h->length = htons(nca->payload); + h->reserved1[0] = 0; + h->reserved1[1] = 0; + + /* Fill with calculated checksum */ + checksum = ncsi_calculate_checksum((unsigned char *)h, + sizeof(*h) + nca->payload); + pchecksum = (__be32 *)((void *)h + sizeof(struct ncsi_pkt_hdr) + + nca->payload); + *pchecksum = htonl(checksum); +} + +static int ncsi_cmd_handler_default(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_pkt *cmd; + + cmd = (struct ncsi_cmd_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_sp(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_sp_pkt *cmd; + + cmd = (struct ncsi_cmd_sp_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + cmd->hw_arbitration = nca->bytes[0]; + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_dc(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_dc_pkt *cmd; + + cmd = (struct ncsi_cmd_dc_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + cmd->ald = nca->bytes[0]; + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_rc(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_rc_pkt *cmd; + + cmd = (struct ncsi_cmd_rc_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_ae(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_ae_pkt *cmd; + + cmd = (struct ncsi_cmd_ae_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + cmd->mc_id = nca->bytes[0]; + cmd->mode = htonl(nca->dwords[1]); + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_sl(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_sl_pkt *cmd; + + cmd = (struct ncsi_cmd_sl_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + cmd->mode = htonl(nca->dwords[0]); + cmd->oem_mode = htonl(nca->dwords[1]); + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_svf(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_svf_pkt *cmd; + + cmd = (struct ncsi_cmd_svf_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + cmd->vlan = htons(nca->words[0]); + cmd->index = nca->bytes[2]; + cmd->enable = nca->bytes[3]; + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_ev(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_ev_pkt *cmd; + + cmd = (struct ncsi_cmd_ev_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + cmd->mode = nca->bytes[0]; + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_sma(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_sma_pkt *cmd; + int i; + + cmd = (struct ncsi_cmd_sma_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + for (i = 0; i < 6; i++) + cmd->mac[i] = nca->bytes[i]; + cmd->index = nca->bytes[6]; + cmd->at_e = nca->bytes[7]; + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_ebf(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_ebf_pkt *cmd; + + cmd = (struct ncsi_cmd_ebf_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + cmd->mode = htonl(nca->dwords[0]); + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_egmf(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_egmf_pkt *cmd; + + cmd = (struct ncsi_cmd_egmf_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + cmd->mode = htonl(nca->dwords[0]); + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static int ncsi_cmd_handler_snfc(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_snfc_pkt *cmd; + + cmd = (struct ncsi_cmd_snfc_pkt *)skb_put(skb, sizeof(*cmd)); + memset(cmd, 0, sizeof(*cmd)); + cmd->mode = nca->bytes[0]; + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + +static struct ncsi_cmd_handler { + unsigned char type; + int payload; + int (*handler)(struct sk_buff *skb, + struct ncsi_cmd_arg *nca); +} ncsi_cmd_handlers[] = { + { NCSI_PKT_CMD_CIS, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_SP, 4, ncsi_cmd_handler_sp }, + { NCSI_PKT_CMD_DP, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_EC, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_DC, 4, ncsi_cmd_handler_dc }, + { NCSI_PKT_CMD_RC, 4, ncsi_cmd_handler_rc }, + { NCSI_PKT_CMD_ECNT, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_DCNT, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_AE, 8, ncsi_cmd_handler_ae }, + { NCSI_PKT_CMD_SL, 8, ncsi_cmd_handler_sl }, + { NCSI_PKT_CMD_GLS, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_SVF, 4, ncsi_cmd_handler_svf }, + { NCSI_PKT_CMD_EV, 4, ncsi_cmd_handler_ev }, + { NCSI_PKT_CMD_DV, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_SMA, 8, ncsi_cmd_handler_sma }, + { NCSI_PKT_CMD_EBF, 4, ncsi_cmd_handler_ebf }, + { NCSI_PKT_CMD_DBF, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_EGMF, 4, ncsi_cmd_handler_egmf }, + { NCSI_PKT_CMD_DGMF, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_SNFC, 4, ncsi_cmd_handler_snfc }, + { NCSI_PKT_CMD_GVI, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_GC, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_GP, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_GCPS, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_GNS, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_GNPTS, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_GPS, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_OEM, 0, NULL }, + { NCSI_PKT_CMD_PLDM, 0, NULL }, + { NCSI_PKT_CMD_GPUUID, 0, ncsi_cmd_handler_default } +}; + +static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) +{ + struct ncsi_dev_priv *ndp = nca->ndp; + struct ncsi_dev *nd = &ndp->ndev; + struct net_device *dev = nd->dev; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; + int len = hlen + tlen; + struct sk_buff *skb; + struct ncsi_request *nr; + + nr = ncsi_alloc_request(ndp, nca->driven); + if (!nr) + return NULL; + + /* NCSI command packet has 16-bytes header, payload, 4 bytes checksum. + * The packet needs padding if its payload is less than 26 bytes to + * meet 64 bytes minimal ethernet frame length. + */ + len += sizeof(struct ncsi_cmd_pkt_hdr) + 4; + if (nca->payload < 26) + len += 26; + else + len += nca->payload; + + /* Allocate skb */ + skb = alloc_skb(len, GFP_ATOMIC); + if (!skb) { + ncsi_free_request(nr); + return NULL; + } + + nr->cmd = skb; + skb_reserve(skb, hlen); + skb_reset_network_header(skb); + + skb->dev = dev; + skb->protocol = htons(ETH_P_NCSI); + + return nr; +} + +int ncsi_xmit_cmd(struct ncsi_cmd_arg *nca) +{ + struct ncsi_request *nr; + struct ethhdr *eh; + struct ncsi_cmd_handler *nch = NULL; + int i, ret; + + /* Search for the handler */ + for (i = 0; i < ARRAY_SIZE(ncsi_cmd_handlers); i++) { + if (ncsi_cmd_handlers[i].type == nca->type) { + if (ncsi_cmd_handlers[i].handler) + nch = &ncsi_cmd_handlers[i]; + else + nch = NULL; + + break; + } + } + + if (!nch) { + netdev_err(nca->ndp->ndev.dev, + "Cannot send packet with type 0x%02x\n", nca->type); + return -ENOENT; + } + + /* Get packet payload length and allocate the request */ + nca->payload = nch->payload; + nr = ncsi_alloc_command(nca); + if (!nr) + return -ENOMEM; + + /* Prepare the packet */ + nca->id = nr->id; + ret = nch->handler(nr->cmd, nca); + if (ret) { + ncsi_free_request(nr); + return ret; + } + + /* Fill the ethernet header */ + eh = (struct ethhdr *)skb_push(nr->cmd, sizeof(*eh)); + eh->h_proto = htons(ETH_P_NCSI); + eth_broadcast_addr(eh->h_dest); + eth_broadcast_addr(eh->h_source); + + /* Start the timer for the request that might not have + * corresponding response. Given NCSI is an internal + * connection a 1 second delay should be sufficient. + */ + nr->enabled = true; + mod_timer(&nr->timer, jiffies + 1 * HZ); + + /* Send NCSI packet */ + skb_get(nr->cmd); + ret = dev_queue_xmit(nr->cmd); + if (ret < 0) { + ncsi_free_request(nr); + return ret; + } + + return 0; +} diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c new file mode 100644 index 0000000..ef017b8 --- /dev/null +++ b/net/ncsi/ncsi-manage.c @@ -0,0 +1,1205 @@ +/* + * Copyright Gavin Shan, IBM Corporation 2016. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/netlink.h> + +#include <net/ncsi.h> +#include <net/net_namespace.h> +#include <net/sock.h> +#include <net/addrconf.h> +#include <net/ipv6.h> +#include <net/if_inet6.h> + +#include "internal.h" +#include "ncsi-pkt.h" + +LIST_HEAD(ncsi_dev_list); +DEFINE_SPINLOCK(ncsi_dev_lock); + +static inline int ncsi_filter_size(int table) +{ + int sizes[] = { 2, 6, 6, 6 }; + + BUILD_BUG_ON(ARRAY_SIZE(sizes) != NCSI_FILTER_MAX); + if (table < NCSI_FILTER_BASE || table >= NCSI_FILTER_MAX) + return -EINVAL; + + return sizes[table]; +} + +int ncsi_find_filter(struct ncsi_channel *nc, int table, void *data) +{ + struct ncsi_channel_filter *ncf; + void *bitmap; + int index, size; + unsigned long flags; + + ncf = nc->filters[table]; + if (!ncf) + return -ENXIO; + + size = ncsi_filter_size(table); + if (size < 0) + return size; + + spin_lock_irqsave(&nc->lock, flags); + bitmap = (void *)&ncf->bitmap; + index = -1; + while ((index = find_next_bit(bitmap, ncf->total, index + 1)) + < ncf->total) { + if (!memcmp(ncf->data + size * index, data, size)) { + spin_unlock_irqrestore(&nc->lock, flags); + return index; + } + } + spin_unlock_irqrestore(&nc->lock, flags); + + return -ENOENT; +} + +int ncsi_add_filter(struct ncsi_channel *nc, int table, void *data) +{ + struct ncsi_channel_filter *ncf; + int index, size; + void *bitmap; + unsigned long flags; + + size = ncsi_filter_size(table); + if (size < 0) + return size; + + index = ncsi_find_filter(nc, table, data); + if (index >= 0) + return index; + + ncf = nc->filters[table]; + if (!ncf) + return -ENODEV; + + spin_lock_irqsave(&nc->lock, flags); + bitmap = (void *)&ncf->bitmap; + do { + index = find_next_zero_bit(bitmap, ncf->total, 0); + if (index >= ncf->total) { + spin_unlock_irqrestore(&nc->lock, flags); + return -ENOSPC; + } + } while (test_and_set_bit(index, bitmap)); + + memcpy(ncf->data + size * index, data, size); + spin_unlock_irqrestore(&nc->lock, flags); + + return index; +} + +int ncsi_remove_filter(struct ncsi_channel *nc, int table, int index) +{ + struct ncsi_channel_filter *ncf; + int size; + void *bitmap; + unsigned long flags; + + size = ncsi_filter_size(table); + if (size < 0) + return size; + + ncf = nc->filters[table]; + if (!ncf || index >= ncf->total) + return -ENODEV; + + spin_lock_irqsave(&nc->lock, flags); + bitmap = (void *)&ncf->bitmap; + if (test_and_clear_bit(index, bitmap)) + memset(ncf->data + size * index, 0, size); + spin_unlock_irqrestore(&nc->lock, flags); + + return 0; +} + +static void ncsi_report_link(struct ncsi_dev_priv *ndp, bool force_down) +{ + struct ncsi_dev *nd = &ndp->ndev; + struct ncsi_package *np; + struct ncsi_channel *nc; + + nd->state = ncsi_dev_state_functional; + if (force_down) { + nd->link_up = 0; + goto report; + } + + nd->link_up = 0; + NCSI_FOR_EACH_PACKAGE(ndp, np) { + NCSI_FOR_EACH_CHANNEL(np, nc) { + if (!list_empty(&nc->link) || + nc->state != NCSI_CHANNEL_ACTIVE) + continue; + + if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1) { + nd->link_up = 1; + goto report; + } + } + } + +report: + nd->handler(nd); +} + +static void ncsi_channel_monitor(unsigned long data) +{ + struct ncsi_channel *nc = (struct ncsi_channel *)data; + struct ncsi_package *np = nc->package; + struct ncsi_dev_priv *ndp = np->ndp; + struct ncsi_cmd_arg nca; + bool enabled; + unsigned int timeout; + unsigned long flags; + int ret; + + spin_lock_irqsave(&nc->lock, flags); + timeout = nc->timeout; + enabled = nc->enabled; + spin_unlock_irqrestore(&nc->lock, flags); + + if (!enabled || !list_empty(&nc->link)) + return; + if (nc->state != NCSI_CHANNEL_INACTIVE && + nc->state != NCSI_CHANNEL_ACTIVE) + return; + + if (!(timeout % 2)) { + nca.ndp = ndp; + nca.package = np->id; + nca.channel = nc->id; + nca.type = NCSI_PKT_CMD_GLS; + nca.driven = false; + ret = ncsi_xmit_cmd(&nca); + if (ret) { + netdev_err(ndp->ndev.dev, "Error %d sending GLS\n", + ret); + return; + } + } + + if (timeout + 1 >= 3) { + if (!(ndp->flags & NCSI_DEV_HWA) && + nc->state == NCSI_CHANNEL_ACTIVE) + ncsi_report_link(ndp, true); + + spin_lock_irqsave(&ndp->lock, flags); + xchg(&nc->state, NCSI_CHANNEL_INACTIVE); + list_add_tail_rcu(&nc->link, &ndp->channel_queue); + spin_unlock_irqrestore(&ndp->lock, flags); + ncsi_process_next_channel(ndp); + return; + } + + spin_lock_irqsave(&nc->lock, flags); + nc->timeout = timeout + 1; + nc->enabled = true; + spin_unlock_irqrestore(&nc->lock, flags); + mod_timer(&nc->timer, jiffies + HZ * (1 << (nc->timeout / 2))); +} + +void ncsi_start_channel_monitor(struct ncsi_channel *nc) +{ + unsigned long flags; + + spin_lock_irqsave(&nc->lock, flags); + WARN_ON_ONCE(nc->enabled); + nc->timeout = 0; + nc->enabled = true; + spin_unlock_irqrestore(&nc->lock, flags); + + mod_timer(&nc->timer, jiffies + HZ * (1 << (nc->timeout / 2))); +} + +void ncsi_stop_channel_monitor(struct ncsi_channel *nc) +{ + unsigned long flags; + + spin_lock_irqsave(&nc->lock, flags); + if (!nc->enabled) { + spin_unlock_irqrestore(&nc->lock, flags); + return; + } + nc->enabled = false; + spin_unlock_irqrestore(&nc->lock, flags); + + del_timer_sync(&nc->timer); +} + +struct ncsi_channel *ncsi_find_channel(struct ncsi_package *np, + unsigned char id) +{ + struct ncsi_channel *nc; + + NCSI_FOR_EACH_CHANNEL(np, nc) { + if (nc->id == id) + return nc; + } + + return NULL; +} + +struct ncsi_channel *ncsi_add_channel(struct ncsi_package *np, unsigned char id) +{ + struct ncsi_channel *nc, *tmp; + int index; + unsigned long flags; + + nc = kzalloc(sizeof(*nc), GFP_ATOMIC); + if (!nc) + return NULL; + + nc->id = id; + nc->package = np; + nc->state = NCSI_CHANNEL_INACTIVE; + nc->enabled = false; + setup_timer(&nc->timer, ncsi_channel_monitor, (unsigned long)nc); + spin_lock_init(&nc->lock); + INIT_LIST_HEAD(&nc->link); + for (index = 0; index < NCSI_CAP_MAX; index++) + nc->caps[index].index = index; + for (index = 0; index < NCSI_MODE_MAX; index++) + nc->modes[index].index = index; + + spin_lock_irqsave(&np->lock, flags); + tmp = ncsi_find_channel(np, id); + if (tmp) { + spin_unlock_irqrestore(&np->lock, flags); + kfree(nc); + return tmp; + } + + list_add_tail_rcu(&nc->node, &np->channels); + np->channel_num++; + spin_unlock_irqrestore(&np->lock, flags); + + return nc; +} + +static void ncsi_remove_channel(struct ncsi_channel *nc) +{ + struct ncsi_package *np = nc->package; + struct ncsi_channel_filter *ncf; + unsigned long flags; + int i; + + /* Release filters */ + spin_lock_irqsave(&nc->lock, flags); + for (i = 0; i < NCSI_FILTER_MAX; i++) { + ncf = nc->filters[i]; + if (!ncf) + continue; + + nc->filters[i] = NULL; + kfree(ncf); + } + + nc->state = NCSI_CHANNEL_INACTIVE; + spin_unlock_irqrestore(&nc->lock, flags); + ncsi_stop_channel_monitor(nc); + + /* Remove and free channel */ + spin_lock_irqsave(&np->lock, flags); + list_del_rcu(&nc->node); + np->channel_num--; + spin_unlock_irqrestore(&np->lock, flags); + + kfree(nc); +} + +struct ncsi_package *ncsi_find_package(struct ncsi_dev_priv *ndp, + unsigned char id) +{ + struct ncsi_package *np; + + NCSI_FOR_EACH_PACKAGE(ndp, np) { + if (np->id == id) + return np; + } + + return NULL; +} + +struct ncsi_package *ncsi_add_package(struct ncsi_dev_priv *ndp, + unsigned char id) +{ + struct ncsi_package *np, *tmp; + unsigned long flags; + + np = kzalloc(sizeof(*np), GFP_ATOMIC); + if (!np) + return NULL; + + np->id = id; + np->ndp = ndp; + spin_lock_init(&np->lock); + INIT_LIST_HEAD(&np->channels); + + spin_lock_irqsave(&ndp->lock, flags); + tmp = ncsi_find_package(ndp, id); + if (tmp) { + spin_unlock_irqrestore(&ndp->lock, flags); + kfree(np); + return tmp; + } + + list_add_tail_rcu(&np->node, &ndp->packages); + ndp->package_num++; + spin_unlock_irqrestore(&ndp->lock, flags); + + return np; +} + +void ncsi_remove_package(struct ncsi_package *np) +{ + struct ncsi_dev_priv *ndp = np->ndp; + struct ncsi_channel *nc, *tmp; + unsigned long flags; + + /* Release all child channels */ + list_for_each_entry_safe(nc, tmp, &np->channels, node) + ncsi_remove_channel(nc); + + /* Remove and free package */ + spin_lock_irqsave(&ndp->lock, flags); + list_del_rcu(&np->node); + ndp->package_num--; + spin_unlock_irqrestore(&ndp->lock, flags); + + kfree(np); +} + +void ncsi_find_package_and_channel(struct ncsi_dev_priv *ndp, + unsigned char id, + struct ncsi_package **np, + struct ncsi_channel **nc) +{ + struct ncsi_package *p; + struct ncsi_channel *c; + + p = ncsi_find_package(ndp, NCSI_PACKAGE_INDEX(id)); + c = p ? ncsi_find_channel(p, NCSI_CHANNEL_INDEX(id)) : NULL; + + if (np) + *np = p; + if (nc) + *nc = c; +} + +/* For two consecutive NCSI commands, the packet IDs shouldn't + * be same. Otherwise, the bogus response might be replied. So + * the available IDs are allocated in round-robin fashion. + */ +struct ncsi_request *ncsi_alloc_request(struct ncsi_dev_priv *ndp, bool driven) +{ + struct ncsi_request *nr = NULL; + int i, limit = ARRAY_SIZE(ndp->requests); + unsigned long flags; + + /* Check if there is one available request until the ceiling */ + spin_lock_irqsave(&ndp->lock, flags); + for (i = ndp->request_id; !nr && i < limit; i++) { + if (ndp->requests[i].used) + continue; + + nr = &ndp->requests[i]; + nr->used = true; + nr->driven = driven; + if (++ndp->request_id >= limit) + ndp->request_id = 0; + } + + /* Fail back to check from the starting cursor */ + for (i = 0; !nr && i < ndp->request_id; i++) { + if (ndp->requests[i].used) + continue; + + nr = &ndp->requests[i]; + nr->used = true; + nr->driven = driven; + if (++ndp->request_id >= limit) + ndp->request_id = 0; + } + spin_unlock_irqrestore(&ndp->lock, flags); + + return nr; +} + +void ncsi_free_request(struct ncsi_request *nr) +{ + struct ncsi_dev_priv *ndp = nr->ndp; + struct sk_buff *cmd, *rsp; + unsigned long flags; + bool driven; + + if (nr->enabled) { + nr->enabled = false; + del_timer_sync(&nr->timer); + } + + spin_lock_irqsave(&ndp->lock, flags); + cmd = nr->cmd; + rsp = nr->rsp; + nr->cmd = NULL; + nr->rsp = NULL; + nr->used = false; + driven = nr->driven; + spin_unlock_irqrestore(&ndp->lock, flags); + + if (driven && cmd && --ndp->pending_req_num == 0) + schedule_work(&ndp->work); + + /* Release command and response */ + consume_skb(cmd); + consume_skb(rsp); +} + +struct ncsi_dev *ncsi_find_dev(struct net_device *dev) +{ + struct ncsi_dev_priv *ndp; + + NCSI_FOR_EACH_DEV(ndp) { + if (ndp->ndev.dev == dev) + return &ndp->ndev; + } + + return NULL; +} + +static void ncsi_request_timeout(unsigned long data) +{ + struct ncsi_request *nr = (struct ncsi_request *)data; + struct ncsi_dev_priv *ndp = nr->ndp; + unsigned long flags; + + /* If the request already had associated response, + * let the response handler to release it. + */ + spin_lock_irqsave(&ndp->lock, flags); + nr->enabled = false; + if (nr->rsp || !nr->cmd) { + spin_unlock_irqrestore(&ndp->lock, flags); + return; + } + spin_unlock_irqrestore(&ndp->lock, flags); + + /* Release the request */ + ncsi_free_request(nr); +} + +static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp) +{ + struct ncsi_dev *nd = &ndp->ndev; + struct ncsi_package *np = ndp->active_package; + struct ncsi_channel *nc = ndp->active_channel; + struct ncsi_cmd_arg nca; + int ret; + + nca.ndp = ndp; + nca.driven = true; + switch (nd->state) { + case ncsi_dev_state_suspend: + nd->state = ncsi_dev_state_suspend_select; + /* Fall through */ + case ncsi_dev_state_suspend_select: + case ncsi_dev_state_suspend_dcnt: + case ncsi_dev_state_suspend_dc: + case ncsi_dev_state_suspend_deselect: + ndp->pending_req_num = 1; + + np = ndp->active_package; + nc = ndp->active_channel; + nca.package = np->id; + if (nd->state == ncsi_dev_state_suspend_select) { + nca.type = NCSI_PKT_CMD_SP; + nca.channel = 0x1f; + if (ndp->flags & NCSI_DEV_HWA) + nca.bytes[0] = 0; + else + nca.bytes[0] = 1; + nd->state = ncsi_dev_state_suspend_dcnt; + } else if (nd->state == ncsi_dev_state_suspend_dcnt) { + nca.type = NCSI_PKT_CMD_DCNT; + nca.channel = nc->id; + nd->state = ncsi_dev_state_suspend_dc; + } else if (nd->state == ncsi_dev_state_suspend_dc) { + nca.type = NCSI_PKT_CMD_DC; + nca.channel = nc->id; + nca.bytes[0] = 1; + nd->state = ncsi_dev_state_suspend_deselect; + } else if (nd->state == ncsi_dev_state_suspend_deselect) { + nca.type = NCSI_PKT_CMD_DP; + nca.channel = 0x1f; + nd->state = ncsi_dev_state_suspend_done; + } + + ret = ncsi_xmit_cmd(&nca); + if (ret) { + nd->state = ncsi_dev_state_functional; + return; + } + + break; + case ncsi_dev_state_suspend_done: + xchg(&nc->state, NCSI_CHANNEL_INACTIVE); + ncsi_process_next_channel(ndp); + + break; + default: + netdev_warn(nd->dev, "Wrong NCSI state 0x%x in suspend\n", + nd->state); + } +} + +static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) +{ + struct ncsi_dev *nd = &ndp->ndev; + struct net_device *dev = nd->dev; + struct ncsi_package *np = ndp->active_package; + struct ncsi_channel *nc = ndp->active_channel; + struct ncsi_cmd_arg nca; + unsigned char index; + int ret; + + nca.ndp = ndp; + nca.driven = true; + switch (nd->state) { + case ncsi_dev_state_config: + case ncsi_dev_state_config_sp: + ndp->pending_req_num = 1; + + /* Select the specific package */ + nca.type = NCSI_PKT_CMD_SP; + if (ndp->flags & NCSI_DEV_HWA) + nca.bytes[0] = 0; + else + nca.bytes[0] = 1; + nca.package = np->id; + nca.channel = 0x1f; + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + + nd->state = ncsi_dev_state_config_cis; + break; + case ncsi_dev_state_config_cis: + ndp->pending_req_num = 1; + + /* Clear initial state */ + nca.type = NCSI_PKT_CMD_CIS; + nca.package = np->id; + nca.channel = nc->id; + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + + nd->state = ncsi_dev_state_config_sma; + break; + case ncsi_dev_state_config_sma: + case ncsi_dev_state_config_ebf: +#if IS_ENABLED(CONFIG_IPV6) + case ncsi_dev_state_config_egmf: +#endif + case ncsi_dev_state_config_ecnt: + case ncsi_dev_state_config_ec: + case ncsi_dev_state_config_ae: + case ncsi_dev_state_config_gls: + ndp->pending_req_num = 1; + + nca.package = np->id; + nca.channel = nc->id; + + /* Use first entry in unicast filter table. Note that + * the MAC filter table starts from entry 1 instead of + * 0. + */ + if (nd->state == ncsi_dev_state_config_sma) { + nca.type = NCSI_PKT_CMD_SMA; + for (index = 0; index < 6; index++) + nca.bytes[index] = dev->dev_addr[index]; + nca.bytes[6] = 0x1; + nca.bytes[7] = 0x1; + nd->state = ncsi_dev_state_config_ebf; + } else if (nd->state == ncsi_dev_state_config_ebf) { + nca.type = NCSI_PKT_CMD_EBF; + nca.dwords[0] = nc->caps[NCSI_CAP_BC].cap; + nd->state = ncsi_dev_state_config_ecnt; +#if IS_ENABLED(CONFIG_IPV6) + if (ndp->inet6_addr_num > 0 && + (nc->caps[NCSI_CAP_GENERIC].cap & + NCSI_CAP_GENERIC_MC)) + nd->state = ncsi_dev_state_config_egmf; + else + nd->state = ncsi_dev_state_config_ecnt; + } else if (nd->state == ncsi_dev_state_config_egmf) { + nca.type = NCSI_PKT_CMD_EGMF; + nca.dwords[0] = nc->caps[NCSI_CAP_MC].cap; + nd->state = ncsi_dev_state_config_ecnt; +#endif /* CONFIG_IPV6 */ + } else if (nd->state == ncsi_dev_state_config_ecnt) { + nca.type = NCSI_PKT_CMD_ECNT; + nd->state = ncsi_dev_state_config_ec; + } else if (nd->state == ncsi_dev_state_config_ec) { + /* Enable AEN if it's supported */ + nca.type = NCSI_PKT_CMD_EC; + nd->state = ncsi_dev_state_config_ae; + if (!(nc->caps[NCSI_CAP_AEN].cap & NCSI_CAP_AEN_MASK)) + nd->state = ncsi_dev_state_config_gls; + } else if (nd->state == ncsi_dev_state_config_ae) { + nca.type = NCSI_PKT_CMD_AE; + nca.bytes[0] = 0; + nca.dwords[1] = nc->caps[NCSI_CAP_AEN].cap; + nd->state = ncsi_dev_state_config_gls; + } else if (nd->state == ncsi_dev_state_config_gls) { + nca.type = NCSI_PKT_CMD_GLS; + nd->state = ncsi_dev_state_config_done; + } + + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + break; + case ncsi_dev_state_config_done: + if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1) + xchg(&nc->state, NCSI_CHANNEL_ACTIVE); + else + xchg(&nc->state, NCSI_CHANNEL_INACTIVE); + + ncsi_start_channel_monitor(nc); + ncsi_process_next_channel(ndp); + break; + default: + netdev_warn(dev, "Wrong NCSI state 0x%x in config\n", + nd->state); + } + + return; + +error: + ncsi_report_link(ndp, true); +} + +static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp) +{ + struct ncsi_package *np; + struct ncsi_channel *nc, *found; + struct ncsi_channel_mode *ncm; + unsigned long flags; + + /* The search is done once an inactive channel with up + * link is found. + */ + found = NULL; + NCSI_FOR_EACH_PACKAGE(ndp, np) { + NCSI_FOR_EACH_CHANNEL(np, nc) { + if (!list_empty(&nc->link) || + nc->state != NCSI_CHANNEL_INACTIVE) + continue; + + if (!found) + found = nc; + + ncm = &nc->modes[NCSI_MODE_LINK]; + if (ncm->data[2] & 0x1) { + found = nc; + goto out; + } + } + } + + if (!found) { + ncsi_report_link(ndp, true); + return -ENODEV; + } + +out: + spin_lock_irqsave(&ndp->lock, flags); + list_add_tail_rcu(&found->link, &ndp->channel_queue); + spin_unlock_irqrestore(&ndp->lock, flags); + + return ncsi_process_next_channel(ndp); +} + +static bool ncsi_check_hwa(struct ncsi_dev_priv *ndp) +{ + struct ncsi_package *np; + struct ncsi_channel *nc; + unsigned int cap; + + /* The hardware arbitration is disabled if any one channel + * doesn't support explicitly. + */ + NCSI_FOR_EACH_PACKAGE(ndp, np) { + NCSI_FOR_EACH_CHANNEL(np, nc) { + cap = nc->caps[NCSI_CAP_GENERIC].cap; + if (!(cap & NCSI_CAP_GENERIC_HWA) || + (cap & NCSI_CAP_GENERIC_HWA_MASK) != + NCSI_CAP_GENERIC_HWA_SUPPORT) { + ndp->flags &= ~NCSI_DEV_HWA; + return false; + } + } + } + + ndp->flags |= NCSI_DEV_HWA; + return true; +} + +static int ncsi_enable_hwa(struct ncsi_dev_priv *ndp) +{ + struct ncsi_package *np; + struct ncsi_channel *nc; + unsigned long flags; + + /* Move all available channels to processing queue */ + spin_lock_irqsave(&ndp->lock, flags); + NCSI_FOR_EACH_PACKAGE(ndp, np) { + NCSI_FOR_EACH_CHANNEL(np, nc) { + WARN_ON_ONCE(nc->state != NCSI_CHANNEL_INACTIVE || + !list_empty(&nc->link)); + ncsi_stop_channel_monitor(nc); + list_add_tail_rcu(&nc->link, &ndp->channel_queue); + } + } + spin_unlock_irqrestore(&ndp->lock, flags); + + /* We can have no channels in extremely case */ + if (list_empty(&ndp->channel_queue)) { + ncsi_report_link(ndp, false); + return -ENOENT; + } + + return ncsi_process_next_channel(ndp); +} + +static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) +{ + struct ncsi_dev *nd = &ndp->ndev; + struct ncsi_package *np; + struct ncsi_channel *nc; + struct ncsi_cmd_arg nca; + unsigned char index; + int ret; + + nca.ndp = ndp; + nca.driven = true; + switch (nd->state) { + case ncsi_dev_state_probe: + nd->state = ncsi_dev_state_probe_deselect; + /* Fall through */ + case ncsi_dev_state_probe_deselect: + ndp->pending_req_num = 8; + + /* Deselect all possible packages */ + nca.type = NCSI_PKT_CMD_DP; + nca.channel = 0x1f; + for (index = 0; index < 8; index++) { + nca.package = index; + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + } + + nd->state = ncsi_dev_state_probe_package; + break; + case ncsi_dev_state_probe_package: + ndp->pending_req_num = 16; + + /* Select all possible packages */ + nca.type = NCSI_PKT_CMD_SP; + nca.bytes[0] = 1; + nca.channel = 0x1f; + for (index = 0; index < 8; index++) { + nca.package = index; + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + } + + /* Disable all possible packages */ + nca.type = NCSI_PKT_CMD_DP; + for (index = 0; index < 8; index++) { + nca.package = index; + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + } + + nd->state = ncsi_dev_state_probe_channel; + break; + case ncsi_dev_state_probe_channel: + if (!ndp->active_package) + ndp->active_package = list_first_or_null_rcu( + &ndp->packages, struct ncsi_package, node); + else if (list_is_last(&ndp->active_package->node, + &ndp->packages)) + ndp->active_package = NULL; + else + ndp->active_package = list_next_entry( + ndp->active_package, node); + + /* All available packages and channels are enumerated. The + * enumeration happens for once when the NCSI interface is + * started. So we need continue to start the interface after + * the enumeration. + * + * We have to choose an active channel before configuring it. + * Note that we possibly don't have active channel in extreme + * situation. + */ + if (!ndp->active_package) { + ndp->flags |= NCSI_DEV_PROBED; + if (ncsi_check_hwa(ndp)) + ncsi_enable_hwa(ndp); + else + ncsi_choose_active_channel(ndp); + return; + } + + /* Select the active package */ + ndp->pending_req_num = 1; + nca.type = NCSI_PKT_CMD_SP; + nca.bytes[0] = 1; + nca.package = ndp->active_package->id; + nca.channel = 0x1f; + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + + nd->state = ncsi_dev_state_probe_cis; + break; + case ncsi_dev_state_probe_cis: + ndp->pending_req_num = 32; + + /* Clear initial state */ + nca.type = NCSI_PKT_CMD_CIS; + nca.package = ndp->active_package->id; + for (index = 0; index < 0x20; index++) { + nca.channel = index; + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + } + + nd->state = ncsi_dev_state_probe_gvi; + break; + case ncsi_dev_state_probe_gvi: + case ncsi_dev_state_probe_gc: + case ncsi_dev_state_probe_gls: + np = ndp->active_package; + ndp->pending_req_num = np->channel_num; + + /* Retrieve version, capability or link status */ + if (nd->state == ncsi_dev_state_probe_gvi) + nca.type = NCSI_PKT_CMD_GVI; + else if (nd->state == ncsi_dev_state_probe_gc) + nca.type = NCSI_PKT_CMD_GC; + else + nca.type = NCSI_PKT_CMD_GLS; + + nca.package = np->id; + NCSI_FOR_EACH_CHANNEL(np, nc) { + nca.channel = nc->id; + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + } + + if (nd->state == ncsi_dev_state_probe_gvi) + nd->state = ncsi_dev_state_probe_gc; + else if (nd->state == ncsi_dev_state_probe_gc) + nd->state = ncsi_dev_state_probe_gls; + else + nd->state = ncsi_dev_state_probe_dp; + break; + case ncsi_dev_state_probe_dp: + ndp->pending_req_num = 1; + + /* Deselect the active package */ + nca.type = NCSI_PKT_CMD_DP; + nca.package = ndp->active_package->id; + nca.channel = 0x1f; + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + + /* Scan channels in next package */ + nd->state = ncsi_dev_state_probe_channel; + break; + default: + netdev_warn(nd->dev, "Wrong NCSI state 0x%0x in enumeration\n", + nd->state); + } + + return; +error: + ncsi_report_link(ndp, true); +} + +static void ncsi_dev_work(struct work_struct *work) +{ + struct ncsi_dev_priv *ndp = container_of(work, + struct ncsi_dev_priv, work); + struct ncsi_dev *nd = &ndp->ndev; + + switch (nd->state & ncsi_dev_state_major) { + case ncsi_dev_state_probe: + ncsi_probe_channel(ndp); + break; + case ncsi_dev_state_suspend: + ncsi_suspend_channel(ndp); + break; + case ncsi_dev_state_config: + ncsi_configure_channel(ndp); + break; + default: + netdev_warn(nd->dev, "Wrong NCSI state 0x%x in workqueue\n", + nd->state); + } +} + +int ncsi_process_next_channel(struct ncsi_dev_priv *ndp) +{ + struct ncsi_channel *nc; + int old_state; + unsigned long flags; + + spin_lock_irqsave(&ndp->lock, flags); + nc = list_first_or_null_rcu(&ndp->channel_queue, + struct ncsi_channel, link); + if (!nc) { + spin_unlock_irqrestore(&ndp->lock, flags); + goto out; + } + + old_state = xchg(&nc->state, NCSI_CHANNEL_INVISIBLE); + list_del_init(&nc->link); + + spin_unlock_irqrestore(&ndp->lock, flags); + + ndp->active_channel = nc; + ndp->active_package = nc->package; + + switch (old_state) { + case NCSI_CHANNEL_INACTIVE: + ndp->ndev.state = ncsi_dev_state_config; + ncsi_configure_channel(ndp); + break; + case NCSI_CHANNEL_ACTIVE: + ndp->ndev.state = ncsi_dev_state_suspend; + ncsi_suspend_channel(ndp); + break; + default: + netdev_err(ndp->ndev.dev, "Invalid state 0x%x on %d:%d\n", + nc->state, nc->package->id, nc->id); + ncsi_report_link(ndp, false); + return -EINVAL; + } + + return 0; + +out: + ndp->active_channel = NULL; + ndp->active_package = NULL; + if (ndp->flags & NCSI_DEV_RESHUFFLE) { + ndp->flags &= ~NCSI_DEV_RESHUFFLE; + return ncsi_choose_active_channel(ndp); + } + + ncsi_report_link(ndp, false); + return -ENODEV; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int ncsi_inet6addr_event(struct notifier_block *this, + unsigned long event, void *data) +{ + struct inet6_ifaddr *ifa = data; + struct net_device *dev = ifa->idev->dev; + struct ncsi_dev *nd = ncsi_find_dev(dev); + struct ncsi_dev_priv *ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL; + struct ncsi_package *np; + struct ncsi_channel *nc; + struct ncsi_cmd_arg nca; + bool action; + int ret; + + if (!ndp || (ipv6_addr_type(&ifa->addr) & + (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK))) + return NOTIFY_OK; + + switch (event) { + case NETDEV_UP: + action = (++ndp->inet6_addr_num) == 1; + nca.type = NCSI_PKT_CMD_EGMF; + break; + case NETDEV_DOWN: + action = (--ndp->inet6_addr_num == 0); + nca.type = NCSI_PKT_CMD_DGMF; + break; + default: + return NOTIFY_OK; + } + + /* We might not have active channel or packages. The IPv6 + * required multicast will be enabled when active channel + * or packages are chosen. + */ + np = ndp->active_package; + nc = ndp->active_channel; + if (!action || !np || !nc) + return NOTIFY_OK; + + /* We needn't enable or disable it if the function isn't supported */ + if (!(nc->caps[NCSI_CAP_GENERIC].cap & NCSI_CAP_GENERIC_MC)) + return NOTIFY_OK; + + nca.ndp = ndp; + nca.driven = false; + nca.package = np->id; + nca.channel = nc->id; + nca.dwords[0] = nc->caps[NCSI_CAP_MC].cap; + ret = ncsi_xmit_cmd(&nca); + if (ret) { + netdev_warn(dev, "Fail to %s global multicast filter (%d)\n", + (event == NETDEV_UP) ? "enable" : "disable", ret); + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + +static struct notifier_block ncsi_inet6addr_notifier = { + .notifier_call = ncsi_inet6addr_event, +}; +#endif /* CONFIG_IPV6 */ + +struct ncsi_dev *ncsi_register_dev(struct net_device *dev, + void (*handler)(struct ncsi_dev *ndev)) +{ + struct ncsi_dev_priv *ndp; + struct ncsi_dev *nd; + unsigned long flags; + int i; + + /* Check if the device has been registered or not */ + nd = ncsi_find_dev(dev); + if (nd) + return nd; + + /* Create NCSI device */ + ndp = kzalloc(sizeof(*ndp), GFP_ATOMIC); + if (!ndp) + return NULL; + + nd = &ndp->ndev; + nd->state = ncsi_dev_state_registered; + nd->dev = dev; + nd->handler = handler; + ndp->pending_req_num = 0; + INIT_LIST_HEAD(&ndp->channel_queue); + INIT_WORK(&ndp->work, ncsi_dev_work); + + /* Initialize private NCSI device */ + spin_lock_init(&ndp->lock); + INIT_LIST_HEAD(&ndp->packages); + ndp->request_id = 0; + for (i = 0; i < ARRAY_SIZE(ndp->requests); i++) { + ndp->requests[i].id = i; + ndp->requests[i].ndp = ndp; + setup_timer(&ndp->requests[i].timer, + ncsi_request_timeout, + (unsigned long)&ndp->requests[i]); + } + + spin_lock_irqsave(&ncsi_dev_lock, flags); +#if IS_ENABLED(CONFIG_IPV6) + ndp->inet6_addr_num = 0; + if (list_empty(&ncsi_dev_list)) + register_inet6addr_notifier(&ncsi_inet6addr_notifier); +#endif + list_add_tail_rcu(&ndp->node, &ncsi_dev_list); + spin_unlock_irqrestore(&ncsi_dev_lock, flags); + + /* Register NCSI packet Rx handler */ + ndp->ptype.type = cpu_to_be16(ETH_P_NCSI); + ndp->ptype.func = ncsi_rcv_rsp; + ndp->ptype.dev = dev; + dev_add_pack(&ndp->ptype); + + return nd; +} +EXPORT_SYMBOL_GPL(ncsi_register_dev); + +int ncsi_start_dev(struct ncsi_dev *nd) +{ + struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd); + struct ncsi_package *np; + struct ncsi_channel *nc; + int old_state, ret; + + if (nd->state != ncsi_dev_state_registered && + nd->state != ncsi_dev_state_functional) + return -ENOTTY; + + if (!(ndp->flags & NCSI_DEV_PROBED)) { + nd->state = ncsi_dev_state_probe; + schedule_work(&ndp->work); + return 0; + } + + /* Reset channel's state and start over */ + NCSI_FOR_EACH_PACKAGE(ndp, np) { + NCSI_FOR_EACH_CHANNEL(np, nc) { + old_state = xchg(&nc->state, NCSI_CHANNEL_INACTIVE); + WARN_ON_ONCE(!list_empty(&nc->link) || + old_state == NCSI_CHANNEL_INVISIBLE); + } + } + + if (ndp->flags & NCSI_DEV_HWA) + ret = ncsi_enable_hwa(ndp); + else + ret = ncsi_choose_active_channel(ndp); + + return ret; +} +EXPORT_SYMBOL_GPL(ncsi_start_dev); + +void ncsi_unregister_dev(struct ncsi_dev *nd) +{ + struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd); + struct ncsi_package *np, *tmp; + unsigned long flags; + + dev_remove_pack(&ndp->ptype); + + list_for_each_entry_safe(np, tmp, &ndp->packages, node) + ncsi_remove_package(np); + + spin_lock_irqsave(&ncsi_dev_lock, flags); + list_del_rcu(&ndp->node); +#if IS_ENABLED(CONFIG_IPV6) + if (list_empty(&ncsi_dev_list)) + unregister_inet6addr_notifier(&ncsi_inet6addr_notifier); +#endif + spin_unlock_irqrestore(&ncsi_dev_lock, flags); + + kfree(ndp); +} +EXPORT_SYMBOL_GPL(ncsi_unregister_dev); diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h new file mode 100644 index 0000000..3ea49ed --- /dev/null +++ b/net/ncsi/ncsi-pkt.h @@ -0,0 +1,415 @@ +/* + * Copyright Gavin Shan, IBM Corporation 2016. + * + * 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 __NCSI_PKT_H__ +#define __NCSI_PKT_H__ + +struct ncsi_pkt_hdr { + unsigned char mc_id; /* Management controller ID */ + unsigned char revision; /* NCSI version - 0x01 */ + unsigned char reserved; /* Reserved */ + unsigned char id; /* Packet sequence number */ + unsigned char type; /* Packet type */ + unsigned char channel; /* Network controller ID */ + __be16 length; /* Payload length */ + __be32 reserved1[2]; /* Reserved */ +}; + +struct ncsi_cmd_pkt_hdr { + struct ncsi_pkt_hdr common; /* Common NCSI packet header */ +}; + +struct ncsi_rsp_pkt_hdr { + struct ncsi_pkt_hdr common; /* Common NCSI packet header */ + __be16 code; /* Response code */ + __be16 reason; /* Response reason */ +}; + +struct ncsi_aen_pkt_hdr { + struct ncsi_pkt_hdr common; /* Common NCSI packet header */ + unsigned char reserved2[3]; /* Reserved */ + unsigned char type; /* AEN packet type */ +}; + +/* NCSI common command packet */ +struct ncsi_cmd_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + __be32 checksum; /* Checksum */ + unsigned char pad[26]; +}; + +struct ncsi_rsp_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Response header */ + __be32 checksum; /* Checksum */ + unsigned char pad[22]; +}; + +/* Select Package */ +struct ncsi_cmd_sp_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + unsigned char reserved[3]; /* Reserved */ + unsigned char hw_arbitration; /* HW arbitration */ + __be32 checksum; /* Checksum */ + unsigned char pad[22]; +}; + +/* Disable Channel */ +struct ncsi_cmd_dc_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + unsigned char reserved[3]; /* Reserved */ + unsigned char ald; /* Allow link down */ + __be32 checksum; /* Checksum */ + unsigned char pad[22]; +}; + +/* Reset Channel */ +struct ncsi_cmd_rc_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + __be32 reserved; /* Reserved */ + __be32 checksum; /* Checksum */ + unsigned char pad[22]; +}; + +/* AEN Enable */ +struct ncsi_cmd_ae_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + unsigned char reserved[3]; /* Reserved */ + unsigned char mc_id; /* MC ID */ + __be32 mode; /* AEN working mode */ + __be32 checksum; /* Checksum */ + unsigned char pad[18]; +}; + +/* Set Link */ +struct ncsi_cmd_sl_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + __be32 mode; /* Link working mode */ + __be32 oem_mode; /* OEM link mode */ + __be32 checksum; /* Checksum */ + unsigned char pad[18]; +}; + +/* Set VLAN Filter */ +struct ncsi_cmd_svf_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + __be16 reserved; /* Reserved */ + __be16 vlan; /* VLAN ID */ + __be16 reserved1; /* Reserved */ + unsigned char index; /* VLAN table index */ + unsigned char enable; /* Enable or disable */ + __be32 checksum; /* Checksum */ + unsigned char pad[14]; +}; + +/* Enable VLAN */ +struct ncsi_cmd_ev_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + unsigned char reserved[3]; /* Reserved */ + unsigned char mode; /* VLAN filter mode */ + __be32 checksum; /* Checksum */ + unsigned char pad[22]; +}; + +/* Set MAC Address */ +struct ncsi_cmd_sma_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + unsigned char mac[6]; /* MAC address */ + unsigned char index; /* MAC table index */ + unsigned char at_e; /* Addr type and operation */ + __be32 checksum; /* Checksum */ + unsigned char pad[18]; +}; + +/* Enable Broadcast Filter */ +struct ncsi_cmd_ebf_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + __be32 mode; /* Filter mode */ + __be32 checksum; /* Checksum */ + unsigned char pad[22]; +}; + +/* Enable Global Multicast Filter */ +struct ncsi_cmd_egmf_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + __be32 mode; /* Global MC mode */ + __be32 checksum; /* Checksum */ + unsigned char pad[22]; +}; + +/* Set NCSI Flow Control */ +struct ncsi_cmd_snfc_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + unsigned char reserved[3]; /* Reserved */ + unsigned char mode; /* Flow control mode */ + __be32 checksum; /* Checksum */ + unsigned char pad[22]; +}; + +/* Get Link Status */ +struct ncsi_rsp_gls_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Response header */ + __be32 status; /* Link status */ + __be32 other; /* Other indications */ + __be32 oem_status; /* OEM link status */ + __be32 checksum; + unsigned char pad[10]; +}; + +/* Get Version ID */ +struct ncsi_rsp_gvi_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Response header */ + __be32 ncsi_version; /* NCSI version */ + unsigned char reserved[3]; /* Reserved */ + unsigned char alpha2; /* NCSI version */ + unsigned char fw_name[12]; /* f/w name string */ + __be32 fw_version; /* f/w version */ + __be16 pci_ids[4]; /* PCI IDs */ + __be32 mf_id; /* Manufacture ID */ + __be32 checksum; +}; + +/* Get Capabilities */ +struct ncsi_rsp_gc_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Response header */ + __be32 cap; /* Capabilities */ + __be32 bc_cap; /* Broadcast cap */ + __be32 mc_cap; /* Multicast cap */ + __be32 buf_cap; /* Buffering cap */ + __be32 aen_cap; /* AEN cap */ + unsigned char vlan_cnt; /* VLAN filter count */ + unsigned char mixed_cnt; /* Mix filter count */ + unsigned char mc_cnt; /* MC filter count */ + unsigned char uc_cnt; /* UC filter count */ + unsigned char reserved[2]; /* Reserved */ + unsigned char vlan_mode; /* VLAN mode */ + unsigned char channel_cnt; /* Channel count */ + __be32 checksum; /* Checksum */ +}; + +/* Get Parameters */ +struct ncsi_rsp_gp_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Response header */ + unsigned char mac_cnt; /* Number of MAC addr */ + unsigned char reserved[2]; /* Reserved */ + unsigned char mac_enable; /* MAC addr enable flags */ + unsigned char vlan_cnt; /* VLAN tag count */ + unsigned char reserved1; /* Reserved */ + __be16 vlan_enable; /* VLAN tag enable flags */ + __be32 link_mode; /* Link setting */ + __be32 bc_mode; /* BC filter mode */ + __be32 valid_modes; /* Valid mode parameters */ + unsigned char vlan_mode; /* VLAN mode */ + unsigned char fc_mode; /* Flow control mode */ + unsigned char reserved2[2]; /* Reserved */ + __be32 aen_mode; /* AEN mode */ + unsigned char mac[6]; /* Supported MAC addr */ + __be16 vlan; /* Supported VLAN tags */ + __be32 checksum; /* Checksum */ +}; + +/* Get Controller Packet Statistics */ +struct ncsi_rsp_gcps_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Response header */ + __be32 cnt_hi; /* Counter cleared */ + __be32 cnt_lo; /* Counter cleared */ + __be32 rx_bytes; /* Rx bytes */ + __be32 tx_bytes; /* Tx bytes */ + __be32 rx_uc_pkts; /* Rx UC packets */ + __be32 rx_mc_pkts; /* Rx MC packets */ + __be32 rx_bc_pkts; /* Rx BC packets */ + __be32 tx_uc_pkts; /* Tx UC packets */ + __be32 tx_mc_pkts; /* Tx MC packets */ + __be32 tx_bc_pkts; /* Tx BC packets */ + __be32 fcs_err; /* FCS errors */ + __be32 align_err; /* Alignment errors */ + __be32 false_carrier; /* False carrier detection */ + __be32 runt_pkts; /* Rx runt packets */ + __be32 jabber_pkts; /* Rx jabber packets */ + __be32 rx_pause_xon; /* Rx pause XON frames */ + __be32 rx_pause_xoff; /* Rx XOFF frames */ + __be32 tx_pause_xon; /* Tx XON frames */ + __be32 tx_pause_xoff; /* Tx XOFF frames */ + __be32 tx_s_collision; /* Single collision frames */ + __be32 tx_m_collision; /* Multiple collision frames */ + __be32 l_collision; /* Late collision frames */ + __be32 e_collision; /* Excessive collision frames */ + __be32 rx_ctl_frames; /* Rx control frames */ + __be32 rx_64_frames; /* Rx 64-bytes frames */ + __be32 rx_127_frames; /* Rx 65-127 bytes frames */ + __be32 rx_255_frames; /* Rx 128-255 bytes frames */ + __be32 rx_511_frames; /* Rx 256-511 bytes frames */ + __be32 rx_1023_frames; /* Rx 512-1023 bytes frames */ + __be32 rx_1522_frames; /* Rx 1024-1522 bytes frames */ + __be32 rx_9022_frames; /* Rx 1523-9022 bytes frames */ + __be32 tx_64_frames; /* Tx 64-bytes frames */ + __be32 tx_127_frames; /* Tx 65-127 bytes frames */ + __be32 tx_255_frames; /* Tx 128-255 bytes frames */ + __be32 tx_511_frames; /* Tx 256-511 bytes frames */ + __be32 tx_1023_frames; /* Tx 512-1023 bytes frames */ + __be32 tx_1522_frames; /* Tx 1024-1522 bytes frames */ + __be32 tx_9022_frames; /* Tx 1523-9022 bytes frames */ + __be32 rx_valid_bytes; /* Rx valid bytes */ + __be32 rx_runt_pkts; /* Rx error runt packets */ + __be32 rx_jabber_pkts; /* Rx error jabber packets */ + __be32 checksum; /* Checksum */ +}; + +/* Get NCSI Statistics */ +struct ncsi_rsp_gns_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Response header */ + __be32 rx_cmds; /* Rx NCSI commands */ + __be32 dropped_cmds; /* Dropped commands */ + __be32 cmd_type_errs; /* Command type errors */ + __be32 cmd_csum_errs; /* Command checksum errors */ + __be32 rx_pkts; /* Rx NCSI packets */ + __be32 tx_pkts; /* Tx NCSI packets */ + __be32 tx_aen_pkts; /* Tx AEN packets */ + __be32 checksum; /* Checksum */ +}; + +/* Get NCSI Pass-through Statistics */ +struct ncsi_rsp_gnpts_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Response header */ + __be32 tx_pkts; /* Tx packets */ + __be32 tx_dropped; /* Tx dropped packets */ + __be32 tx_channel_err; /* Tx channel errors */ + __be32 tx_us_err; /* Tx undersize errors */ + __be32 rx_pkts; /* Rx packets */ + __be32 rx_dropped; /* Rx dropped packets */ + __be32 rx_channel_err; /* Rx channel errors */ + __be32 rx_us_err; /* Rx undersize errors */ + __be32 rx_os_err; /* Rx oversize errors */ + __be32 checksum; /* Checksum */ +}; + +/* Get package status */ +struct ncsi_rsp_gps_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Response header */ + __be32 status; /* Hardware arbitration status */ + __be32 checksum; +}; + +/* Get package UUID */ +struct ncsi_rsp_gpuuid_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Response header */ + unsigned char uuid[16]; /* UUID */ + __be32 checksum; +}; + +/* AEN: Link State Change */ +struct ncsi_aen_lsc_pkt { + struct ncsi_aen_pkt_hdr aen; /* AEN header */ + __be32 status; /* Link status */ + __be32 oem_status; /* OEM link status */ + __be32 checksum; /* Checksum */ + unsigned char pad[14]; +}; + +/* AEN: Configuration Required */ +struct ncsi_aen_cr_pkt { + struct ncsi_aen_pkt_hdr aen; /* AEN header */ + __be32 checksum; /* Checksum */ + unsigned char pad[22]; +}; + +/* AEN: Host Network Controller Driver Status Change */ +struct ncsi_aen_hncdsc_pkt { + struct ncsi_aen_pkt_hdr aen; /* AEN header */ + __be32 status; /* Status */ + __be32 checksum; /* Checksum */ + unsigned char pad[18]; +}; + +/* NCSI packet revision */ +#define NCSI_PKT_REVISION 0x01 + +/* NCSI packet commands */ +#define NCSI_PKT_CMD_CIS 0x00 /* Clear Initial State */ +#define NCSI_PKT_CMD_SP 0x01 /* Select Package */ +#define NCSI_PKT_CMD_DP 0x02 /* Deselect Package */ +#define NCSI_PKT_CMD_EC 0x03 /* Enable Channel */ +#define NCSI_PKT_CMD_DC 0x04 /* Disable Channel */ +#define NCSI_PKT_CMD_RC 0x05 /* Reset Channel */ +#define NCSI_PKT_CMD_ECNT 0x06 /* Enable Channel Network Tx */ +#define NCSI_PKT_CMD_DCNT 0x07 /* Disable Channel Network Tx */ +#define NCSI_PKT_CMD_AE 0x08 /* AEN Enable */ +#define NCSI_PKT_CMD_SL 0x09 /* Set Link */ +#define NCSI_PKT_CMD_GLS 0x0a /* Get Link */ +#define NCSI_PKT_CMD_SVF 0x0b /* Set VLAN Filter */ +#define NCSI_PKT_CMD_EV 0x0c /* Enable VLAN */ +#define NCSI_PKT_CMD_DV 0x0d /* Disable VLAN */ +#define NCSI_PKT_CMD_SMA 0x0e /* Set MAC address */ +#define NCSI_PKT_CMD_EBF 0x10 /* Enable Broadcast Filter */ +#define NCSI_PKT_CMD_DBF 0x11 /* Disable Broadcast Filter */ +#define NCSI_PKT_CMD_EGMF 0x12 /* Enable Global Multicast Filter */ +#define NCSI_PKT_CMD_DGMF 0x13 /* Disable Global Multicast Filter */ +#define NCSI_PKT_CMD_SNFC 0x14 /* Set NCSI Flow Control */ +#define NCSI_PKT_CMD_GVI 0x15 /* Get Version ID */ +#define NCSI_PKT_CMD_GC 0x16 /* Get Capabilities */ +#define NCSI_PKT_CMD_GP 0x17 /* Get Parameters */ +#define NCSI_PKT_CMD_GCPS 0x18 /* Get Controller Packet Statistics */ +#define NCSI_PKT_CMD_GNS 0x19 /* Get NCSI Statistics */ +#define NCSI_PKT_CMD_GNPTS 0x1a /* Get NCSI Pass-throu Statistics */ +#define NCSI_PKT_CMD_GPS 0x1b /* Get package status */ +#define NCSI_PKT_CMD_OEM 0x50 /* OEM */ +#define NCSI_PKT_CMD_PLDM 0x51 /* PLDM request over NCSI over RBT */ +#define NCSI_PKT_CMD_GPUUID 0x52 /* Get package UUID */ + +/* NCSI packet responses */ +#define NCSI_PKT_RSP_CIS (NCSI_PKT_CMD_CIS + 0x80) +#define NCSI_PKT_RSP_SP (NCSI_PKT_CMD_SP + 0x80) +#define NCSI_PKT_RSP_DP (NCSI_PKT_CMD_DP + 0x80) +#define NCSI_PKT_RSP_EC (NCSI_PKT_CMD_EC + 0x80) +#define NCSI_PKT_RSP_DC (NCSI_PKT_CMD_DC + 0x80) +#define NCSI_PKT_RSP_RC (NCSI_PKT_CMD_RC + 0x80) +#define NCSI_PKT_RSP_ECNT (NCSI_PKT_CMD_ECNT + 0x80) +#define NCSI_PKT_RSP_DCNT (NCSI_PKT_CMD_DCNT + 0x80) +#define NCSI_PKT_RSP_AE (NCSI_PKT_CMD_AE + 0x80) +#define NCSI_PKT_RSP_SL (NCSI_PKT_CMD_SL + 0x80) +#define NCSI_PKT_RSP_GLS (NCSI_PKT_CMD_GLS + 0x80) +#define NCSI_PKT_RSP_SVF (NCSI_PKT_CMD_SVF + 0x80) +#define NCSI_PKT_RSP_EV (NCSI_PKT_CMD_EV + 0x80) +#define NCSI_PKT_RSP_DV (NCSI_PKT_CMD_DV + 0x80) +#define NCSI_PKT_RSP_SMA (NCSI_PKT_CMD_SMA + 0x80) +#define NCSI_PKT_RSP_EBF (NCSI_PKT_CMD_EBF + 0x80) +#define NCSI_PKT_RSP_DBF (NCSI_PKT_CMD_DBF + 0x80) +#define NCSI_PKT_RSP_EGMF (NCSI_PKT_CMD_EGMF + 0x80) +#define NCSI_PKT_RSP_DGMF (NCSI_PKT_CMD_DGMF + 0x80) +#define NCSI_PKT_RSP_SNFC (NCSI_PKT_CMD_SNFC + 0x80) +#define NCSI_PKT_RSP_GVI (NCSI_PKT_CMD_GVI + 0x80) +#define NCSI_PKT_RSP_GC (NCSI_PKT_CMD_GC + 0x80) +#define NCSI_PKT_RSP_GP (NCSI_PKT_CMD_GP + 0x80) +#define NCSI_PKT_RSP_GCPS (NCSI_PKT_CMD_GCPS + 0x80) +#define NCSI_PKT_RSP_GNS (NCSI_PKT_CMD_GNS + 0x80) +#define NCSI_PKT_RSP_GNPTS (NCSI_PKT_CMD_GNPTS + 0x80) +#define NCSI_PKT_RSP_GPS (NCSI_PKT_CMD_GPS + 0x80) +#define NCSI_PKT_RSP_OEM (NCSI_PKT_CMD_OEM + 0x80) +#define NCSI_PKT_RSP_PLDM (NCSI_PKT_CMD_PLDM + 0x80) +#define NCSI_PKT_RSP_GPUUID (NCSI_PKT_CMD_GPUUID + 0x80) + +/* NCSI response code/reason */ +#define NCSI_PKT_RSP_C_COMPLETED 0x0000 /* Command Completed */ +#define NCSI_PKT_RSP_C_FAILED 0x0001 /* Command Failed */ +#define NCSI_PKT_RSP_C_UNAVAILABLE 0x0002 /* Command Unavailable */ +#define NCSI_PKT_RSP_C_UNSUPPORTED 0x0003 /* Command Unsupported */ +#define NCSI_PKT_RSP_R_NO_ERROR 0x0000 /* No Error */ +#define NCSI_PKT_RSP_R_INTERFACE 0x0001 /* Interface not ready */ +#define NCSI_PKT_RSP_R_PARAM 0x0002 /* Invalid Parameter */ +#define NCSI_PKT_RSP_R_CHANNEL 0x0003 /* Channel not Ready */ +#define NCSI_PKT_RSP_R_PACKAGE 0x0004 /* Package not Ready */ +#define NCSI_PKT_RSP_R_LENGTH 0x0005 /* Invalid payload length */ +#define NCSI_PKT_RSP_R_UNKNOWN 0x7fff /* Command type unsupported */ + +/* NCSI AEN packet type */ +#define NCSI_PKT_AEN 0xFF /* AEN Packet */ +#define NCSI_PKT_AEN_LSC 0x00 /* Link status change */ +#define NCSI_PKT_AEN_CR 0x01 /* Configuration required */ +#define NCSI_PKT_AEN_HNCDSC 0x02 /* HNC driver status change */ + +#endif /* __NCSI_PKT_H__ */ diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c new file mode 100644 index 0000000..af84389 --- /dev/null +++ b/net/ncsi/ncsi-rsp.c @@ -0,0 +1,1035 @@ +/* + * Copyright Gavin Shan, IBM Corporation 2016. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> + +#include <net/ncsi.h> +#include <net/net_namespace.h> +#include <net/sock.h> + +#include "internal.h" +#include "ncsi-pkt.h" + +static int ncsi_validate_rsp_pkt(struct ncsi_request *nr, + unsigned short payload) +{ + struct ncsi_rsp_pkt_hdr *h; + u32 checksum; + __be32 *pchecksum; + + /* Check NCSI packet header. We don't need validate + * the packet type, which should have been checked + * before calling this function. + */ + h = (struct ncsi_rsp_pkt_hdr *)skb_network_header(nr->rsp); + if (h->common.revision != NCSI_PKT_REVISION) + return -EINVAL; + if (ntohs(h->common.length) != payload) + return -EINVAL; + + /* Check on code and reason */ + if (ntohs(h->code) != NCSI_PKT_RSP_C_COMPLETED || + ntohs(h->reason) != NCSI_PKT_RSP_R_NO_ERROR) + return -EINVAL; + + /* Validate checksum, which might be zeroes if the + * sender doesn't support checksum according to NCSI + * specification. + */ + pchecksum = (__be32 *)((void *)(h + 1) + payload - 4); + if (ntohl(*pchecksum) == 0) + return 0; + + checksum = ncsi_calculate_checksum((unsigned char *)h, + sizeof(*h) + payload - 4); + if (*pchecksum != htonl(checksum)) + return -EINVAL; + + return 0; +} + +static int ncsi_rsp_handler_cis(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_package *np; + struct ncsi_channel *nc; + unsigned char id; + + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, &np, &nc); + if (!nc) { + if (ndp->flags & NCSI_DEV_PROBED) + return -ENXIO; + + id = NCSI_CHANNEL_INDEX(rsp->rsp.common.channel); + nc = ncsi_add_channel(np, id); + } + + return nc ? 0 : -ENODEV; +} + +static int ncsi_rsp_handler_sp(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_package *np; + unsigned char id; + + /* Add the package if it's not existing. Otherwise, + * to change the state of its child channels. + */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + &np, NULL); + if (!np) { + if (ndp->flags & NCSI_DEV_PROBED) + return -ENXIO; + + id = NCSI_PACKAGE_INDEX(rsp->rsp.common.channel); + np = ncsi_add_package(ndp, id); + if (!np) + return -ENODEV; + } + + return 0; +} + +static int ncsi_rsp_handler_dp(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_package *np; + struct ncsi_channel *nc; + unsigned long flags; + + /* Find the package */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + &np, NULL); + if (!np) + return -ENODEV; + + /* Change state of all channels attached to the package */ + NCSI_FOR_EACH_CHANNEL(np, nc) { + spin_lock_irqsave(&nc->lock, flags); + nc->state = NCSI_CHANNEL_INACTIVE; + spin_unlock_irqrestore(&nc->lock, flags); + } + + return 0; +} + +static int ncsi_rsp_handler_ec(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + ncm = &nc->modes[NCSI_MODE_ENABLE]; + if (ncm->enable) + return -EBUSY; + + ncm->enable = 1; + return 0; +} + +static int ncsi_rsp_handler_dc(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + int ret; + + ret = ncsi_validate_rsp_pkt(nr, 4); + if (ret) + return ret; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + ncm = &nc->modes[NCSI_MODE_ENABLE]; + if (!ncm->enable) + return -EBUSY; + + ncm->enable = 0; + return 0; +} + +static int ncsi_rsp_handler_rc(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + unsigned long flags; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Update state for the specified channel */ + spin_lock_irqsave(&nc->lock, flags); + nc->state = NCSI_CHANNEL_INACTIVE; + spin_unlock_irqrestore(&nc->lock, flags); + + return 0; +} + +static int ncsi_rsp_handler_ecnt(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + ncm = &nc->modes[NCSI_MODE_TX_ENABLE]; + if (ncm->enable) + return -EBUSY; + + ncm->enable = 1; + return 0; +} + +static int ncsi_rsp_handler_dcnt(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + ncm = &nc->modes[NCSI_MODE_TX_ENABLE]; + if (!ncm->enable) + return -EBUSY; + + ncm->enable = 1; + return 0; +} + +static int ncsi_rsp_handler_ae(struct ncsi_request *nr) +{ + struct ncsi_cmd_ae_pkt *cmd; + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Check if the AEN has been enabled */ + ncm = &nc->modes[NCSI_MODE_AEN]; + if (ncm->enable) + return -EBUSY; + + /* Update to AEN configuration */ + cmd = (struct ncsi_cmd_ae_pkt *)skb_network_header(nr->cmd); + ncm->enable = 1; + ncm->data[0] = cmd->mc_id; + ncm->data[1] = ntohl(cmd->mode); + + return 0; +} + +static int ncsi_rsp_handler_sl(struct ncsi_request *nr) +{ + struct ncsi_cmd_sl_pkt *cmd; + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + cmd = (struct ncsi_cmd_sl_pkt *)skb_network_header(nr->cmd); + ncm = &nc->modes[NCSI_MODE_LINK]; + ncm->data[0] = ntohl(cmd->mode); + ncm->data[1] = ntohl(cmd->oem_mode); + + return 0; +} + +static int ncsi_rsp_handler_gls(struct ncsi_request *nr) +{ + struct ncsi_rsp_gls_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + unsigned long flags; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_gls_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + ncm = &nc->modes[NCSI_MODE_LINK]; + ncm->data[2] = ntohl(rsp->status); + ncm->data[3] = ntohl(rsp->other); + ncm->data[4] = ntohl(rsp->oem_status); + + if (nr->driven) + return 0; + + /* Reset the channel monitor if it has been enabled */ + spin_lock_irqsave(&nc->lock, flags); + nc->timeout = 0; + spin_unlock_irqrestore(&nc->lock, flags); + + return 0; +} + +static int ncsi_rsp_handler_svf(struct ncsi_request *nr) +{ + struct ncsi_cmd_svf_pkt *cmd; + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_filter *ncf; + unsigned short vlan; + int ret; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + cmd = (struct ncsi_cmd_svf_pkt *)skb_network_header(nr->cmd); + ncf = nc->filters[NCSI_FILTER_VLAN]; + if (!ncf) + return -ENOENT; + if (cmd->index >= ncf->total) + return -ERANGE; + + /* Add or remove the VLAN filter */ + if (!(cmd->enable & 0x1)) { + ret = ncsi_remove_filter(nc, NCSI_FILTER_VLAN, cmd->index); + } else { + vlan = ntohs(cmd->vlan); + ret = ncsi_add_filter(nc, NCSI_FILTER_VLAN, &vlan); + } + + return ret; +} + +static int ncsi_rsp_handler_ev(struct ncsi_request *nr) +{ + struct ncsi_cmd_ev_pkt *cmd; + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Check if VLAN mode has been enabled */ + ncm = &nc->modes[NCSI_MODE_VLAN]; + if (ncm->enable) + return -EBUSY; + + /* Update to VLAN mode */ + cmd = (struct ncsi_cmd_ev_pkt *)skb_network_header(nr->cmd); + ncm->enable = 1; + ncm->data[0] = ntohl(cmd->mode); + + return 0; +} + +static int ncsi_rsp_handler_dv(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Check if VLAN mode has been enabled */ + ncm = &nc->modes[NCSI_MODE_VLAN]; + if (!ncm->enable) + return -EBUSY; + + /* Update to VLAN mode */ + ncm->enable = 0; + return 0; +} + +static int ncsi_rsp_handler_sma(struct ncsi_request *nr) +{ + struct ncsi_cmd_sma_pkt *cmd; + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_filter *ncf; + void *bitmap; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* According to NCSI spec 1.01, the mixed filter table + * isn't supported yet. + */ + cmd = (struct ncsi_cmd_sma_pkt *)skb_network_header(nr->cmd); + switch (cmd->at_e >> 5) { + case 0x0: /* UC address */ + ncf = nc->filters[NCSI_FILTER_UC]; + break; + case 0x1: /* MC address */ + ncf = nc->filters[NCSI_FILTER_MC]; + break; + default: + return -EINVAL; + } + + /* Sanity check on the filter */ + if (!ncf) + return -ENOENT; + else if (cmd->index >= ncf->total) + return -ERANGE; + + bitmap = &ncf->bitmap; + if (cmd->at_e & 0x1) { + if (test_and_set_bit(cmd->index, bitmap)) + return -EBUSY; + memcpy(ncf->data + 6 * cmd->index, cmd->mac, 6); + } else { + if (!test_and_clear_bit(cmd->index, bitmap)) + return -EBUSY; + + memset(ncf->data + 6 * cmd->index, 0, 6); + } + + return 0; +} + +static int ncsi_rsp_handler_ebf(struct ncsi_request *nr) +{ + struct ncsi_cmd_ebf_pkt *cmd; + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + /* Find the package and channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, NULL, &nc); + if (!nc) + return -ENODEV; + + /* Check if broadcast filter has been enabled */ + ncm = &nc->modes[NCSI_MODE_BC]; + if (ncm->enable) + return -EBUSY; + + /* Update to broadcast filter mode */ + cmd = (struct ncsi_cmd_ebf_pkt *)skb_network_header(nr->cmd); + ncm->enable = 1; + ncm->data[0] = ntohl(cmd->mode); + + return 0; +} + +static int ncsi_rsp_handler_dbf(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Check if broadcast filter isn't enabled */ + ncm = &nc->modes[NCSI_MODE_BC]; + if (!ncm->enable) + return -EBUSY; + + /* Update to broadcast filter mode */ + ncm->enable = 0; + ncm->data[0] = 0; + + return 0; +} + +static int ncsi_rsp_handler_egmf(struct ncsi_request *nr) +{ + struct ncsi_cmd_egmf_pkt *cmd; + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + /* Find the channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Check if multicast filter has been enabled */ + ncm = &nc->modes[NCSI_MODE_MC]; + if (ncm->enable) + return -EBUSY; + + /* Update to multicast filter mode */ + cmd = (struct ncsi_cmd_egmf_pkt *)skb_network_header(nr->cmd); + ncm->enable = 1; + ncm->data[0] = ntohl(cmd->mode); + + return 0; +} + +static int ncsi_rsp_handler_dgmf(struct ncsi_request *nr) +{ + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Check if multicast filter has been enabled */ + ncm = &nc->modes[NCSI_MODE_MC]; + if (!ncm->enable) + return -EBUSY; + + /* Update to multicast filter mode */ + ncm->enable = 0; + ncm->data[0] = 0; + + return 0; +} + +static int ncsi_rsp_handler_snfc(struct ncsi_request *nr) +{ + struct ncsi_cmd_snfc_pkt *cmd; + struct ncsi_rsp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_mode *ncm; + + /* Find the channel */ + rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Check if flow control has been enabled */ + ncm = &nc->modes[NCSI_MODE_FC]; + if (ncm->enable) + return -EBUSY; + + /* Update to flow control mode */ + cmd = (struct ncsi_cmd_snfc_pkt *)skb_network_header(nr->cmd); + ncm->enable = 1; + ncm->data[0] = cmd->mode; + + return 0; +} + +static int ncsi_rsp_handler_gvi(struct ncsi_request *nr) +{ + struct ncsi_rsp_gvi_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_version *ncv; + int i; + + /* Find the channel */ + rsp = (struct ncsi_rsp_gvi_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Update to channel's version info */ + ncv = &nc->version; + ncv->version = ntohl(rsp->ncsi_version); + ncv->alpha2 = rsp->alpha2; + memcpy(ncv->fw_name, rsp->fw_name, 12); + ncv->fw_version = ntohl(rsp->fw_version); + for (i = 0; i < ARRAY_SIZE(ncv->pci_ids); i++) + ncv->pci_ids[i] = ntohs(rsp->pci_ids[i]); + ncv->mf_id = ntohl(rsp->mf_id); + + return 0; +} + +static int ncsi_rsp_handler_gc(struct ncsi_request *nr) +{ + struct ncsi_rsp_gc_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_filter *ncf; + size_t size, entry_size; + int cnt, i; + + /* Find the channel */ + rsp = (struct ncsi_rsp_gc_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Update channel's capabilities */ + nc->caps[NCSI_CAP_GENERIC].cap = ntohl(rsp->cap) & + NCSI_CAP_GENERIC_MASK; + nc->caps[NCSI_CAP_BC].cap = ntohl(rsp->bc_cap) & + NCSI_CAP_BC_MASK; + nc->caps[NCSI_CAP_MC].cap = ntohl(rsp->mc_cap) & + NCSI_CAP_MC_MASK; + nc->caps[NCSI_CAP_BUFFER].cap = ntohl(rsp->buf_cap); + nc->caps[NCSI_CAP_AEN].cap = ntohl(rsp->aen_cap) & + NCSI_CAP_AEN_MASK; + nc->caps[NCSI_CAP_VLAN].cap = rsp->vlan_mode & + NCSI_CAP_VLAN_MASK; + + /* Build filters */ + for (i = 0; i < NCSI_FILTER_MAX; i++) { + switch (i) { + case NCSI_FILTER_VLAN: + cnt = rsp->vlan_cnt; + entry_size = 2; + break; + case NCSI_FILTER_MIXED: + cnt = rsp->mixed_cnt; + entry_size = 6; + break; + case NCSI_FILTER_MC: + cnt = rsp->mc_cnt; + entry_size = 6; + break; + case NCSI_FILTER_UC: + cnt = rsp->uc_cnt; + entry_size = 6; + break; + default: + continue; + } + + if (!cnt || nc->filters[i]) + continue; + + size = sizeof(*ncf) + cnt * entry_size; + ncf = kzalloc(size, GFP_ATOMIC); + if (!ncf) { + pr_warn("%s: Cannot alloc filter table (%d)\n", + __func__, i); + return -ENOMEM; + } + + ncf->index = i; + ncf->total = cnt; + ncf->bitmap = 0x0ul; + nc->filters[i] = ncf; + } + + return 0; +} + +static int ncsi_rsp_handler_gp(struct ncsi_request *nr) +{ + struct ncsi_rsp_gp_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + unsigned short enable, vlan; + unsigned char *pdata; + int table, i; + + /* Find the channel */ + rsp = (struct ncsi_rsp_gp_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Modes with explicit enabled indications */ + if (ntohl(rsp->valid_modes) & 0x1) { /* BC filter mode */ + nc->modes[NCSI_MODE_BC].enable = 1; + nc->modes[NCSI_MODE_BC].data[0] = ntohl(rsp->bc_mode); + } + if (ntohl(rsp->valid_modes) & 0x2) /* Channel enabled */ + nc->modes[NCSI_MODE_ENABLE].enable = 1; + if (ntohl(rsp->valid_modes) & 0x4) /* Channel Tx enabled */ + nc->modes[NCSI_MODE_TX_ENABLE].enable = 1; + if (ntohl(rsp->valid_modes) & 0x8) /* MC filter mode */ + nc->modes[NCSI_MODE_MC].enable = 1; + + /* Modes without explicit enabled indications */ + nc->modes[NCSI_MODE_LINK].enable = 1; + nc->modes[NCSI_MODE_LINK].data[0] = ntohl(rsp->link_mode); + nc->modes[NCSI_MODE_VLAN].enable = 1; + nc->modes[NCSI_MODE_VLAN].data[0] = rsp->vlan_mode; + nc->modes[NCSI_MODE_FC].enable = 1; + nc->modes[NCSI_MODE_FC].data[0] = rsp->fc_mode; + nc->modes[NCSI_MODE_AEN].enable = 1; + nc->modes[NCSI_MODE_AEN].data[0] = ntohl(rsp->aen_mode); + + /* MAC addresses filter table */ + pdata = (unsigned char *)rsp + 48; + enable = rsp->mac_enable; + for (i = 0; i < rsp->mac_cnt; i++, pdata += 6) { + if (i >= (nc->filters[NCSI_FILTER_UC]->total + + nc->filters[NCSI_FILTER_MC]->total)) + table = NCSI_FILTER_MIXED; + else if (i >= nc->filters[NCSI_FILTER_UC]->total) + table = NCSI_FILTER_MC; + else + table = NCSI_FILTER_UC; + + if (!(enable & (0x1 << i))) + continue; + + if (ncsi_find_filter(nc, table, pdata) >= 0) + continue; + + ncsi_add_filter(nc, table, pdata); + } + + /* VLAN filter table */ + enable = ntohs(rsp->vlan_enable); + for (i = 0; i < rsp->vlan_cnt; i++, pdata += 2) { + if (!(enable & (0x1 << i))) + continue; + + vlan = ntohs(*(__be16 *)pdata); + if (ncsi_find_filter(nc, NCSI_FILTER_VLAN, &vlan) >= 0) + continue; + + ncsi_add_filter(nc, NCSI_FILTER_VLAN, &vlan); + } + + return 0; +} + +static int ncsi_rsp_handler_gcps(struct ncsi_request *nr) +{ + struct ncsi_rsp_gcps_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_stats *ncs; + + /* Find the channel */ + rsp = (struct ncsi_rsp_gcps_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Update HNC's statistics */ + ncs = &nc->stats; + ncs->hnc_cnt_hi = ntohl(rsp->cnt_hi); + ncs->hnc_cnt_lo = ntohl(rsp->cnt_lo); + ncs->hnc_rx_bytes = ntohl(rsp->rx_bytes); + ncs->hnc_tx_bytes = ntohl(rsp->tx_bytes); + ncs->hnc_rx_uc_pkts = ntohl(rsp->rx_uc_pkts); + ncs->hnc_rx_mc_pkts = ntohl(rsp->rx_mc_pkts); + ncs->hnc_rx_bc_pkts = ntohl(rsp->rx_bc_pkts); + ncs->hnc_tx_uc_pkts = ntohl(rsp->tx_uc_pkts); + ncs->hnc_tx_mc_pkts = ntohl(rsp->tx_mc_pkts); + ncs->hnc_tx_bc_pkts = ntohl(rsp->tx_bc_pkts); + ncs->hnc_fcs_err = ntohl(rsp->fcs_err); + ncs->hnc_align_err = ntohl(rsp->align_err); + ncs->hnc_false_carrier = ntohl(rsp->false_carrier); + ncs->hnc_runt_pkts = ntohl(rsp->runt_pkts); + ncs->hnc_jabber_pkts = ntohl(rsp->jabber_pkts); + ncs->hnc_rx_pause_xon = ntohl(rsp->rx_pause_xon); + ncs->hnc_rx_pause_xoff = ntohl(rsp->rx_pause_xoff); + ncs->hnc_tx_pause_xon = ntohl(rsp->tx_pause_xon); + ncs->hnc_tx_pause_xoff = ntohl(rsp->tx_pause_xoff); + ncs->hnc_tx_s_collision = ntohl(rsp->tx_s_collision); + ncs->hnc_tx_m_collision = ntohl(rsp->tx_m_collision); + ncs->hnc_l_collision = ntohl(rsp->l_collision); + ncs->hnc_e_collision = ntohl(rsp->e_collision); + ncs->hnc_rx_ctl_frames = ntohl(rsp->rx_ctl_frames); + ncs->hnc_rx_64_frames = ntohl(rsp->rx_64_frames); + ncs->hnc_rx_127_frames = ntohl(rsp->rx_127_frames); + ncs->hnc_rx_255_frames = ntohl(rsp->rx_255_frames); + ncs->hnc_rx_511_frames = ntohl(rsp->rx_511_frames); + ncs->hnc_rx_1023_frames = ntohl(rsp->rx_1023_frames); + ncs->hnc_rx_1522_frames = ntohl(rsp->rx_1522_frames); + ncs->hnc_rx_9022_frames = ntohl(rsp->rx_9022_frames); + ncs->hnc_tx_64_frames = ntohl(rsp->tx_64_frames); + ncs->hnc_tx_127_frames = ntohl(rsp->tx_127_frames); + ncs->hnc_tx_255_frames = ntohl(rsp->tx_255_frames); + ncs->hnc_tx_511_frames = ntohl(rsp->tx_511_frames); + ncs->hnc_tx_1023_frames = ntohl(rsp->tx_1023_frames); + ncs->hnc_tx_1522_frames = ntohl(rsp->tx_1522_frames); + ncs->hnc_tx_9022_frames = ntohl(rsp->tx_9022_frames); + ncs->hnc_rx_valid_bytes = ntohl(rsp->rx_valid_bytes); + ncs->hnc_rx_runt_pkts = ntohl(rsp->rx_runt_pkts); + ncs->hnc_rx_jabber_pkts = ntohl(rsp->rx_jabber_pkts); + + return 0; +} + +static int ncsi_rsp_handler_gns(struct ncsi_request *nr) +{ + struct ncsi_rsp_gns_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_stats *ncs; + + /* Find the channel */ + rsp = (struct ncsi_rsp_gns_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Update HNC's statistics */ + ncs = &nc->stats; + ncs->ncsi_rx_cmds = ntohl(rsp->rx_cmds); + ncs->ncsi_dropped_cmds = ntohl(rsp->dropped_cmds); + ncs->ncsi_cmd_type_errs = ntohl(rsp->cmd_type_errs); + ncs->ncsi_cmd_csum_errs = ntohl(rsp->cmd_csum_errs); + ncs->ncsi_rx_pkts = ntohl(rsp->rx_pkts); + ncs->ncsi_tx_pkts = ntohl(rsp->tx_pkts); + ncs->ncsi_tx_aen_pkts = ntohl(rsp->tx_aen_pkts); + + return 0; +} + +static int ncsi_rsp_handler_gnpts(struct ncsi_request *nr) +{ + struct ncsi_rsp_gnpts_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_channel *nc; + struct ncsi_channel_stats *ncs; + + /* Find the channel */ + rsp = (struct ncsi_rsp_gnpts_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + NULL, &nc); + if (!nc) + return -ENODEV; + + /* Update HNC's statistics */ + ncs = &nc->stats; + ncs->pt_tx_pkts = ntohl(rsp->tx_pkts); + ncs->pt_tx_dropped = ntohl(rsp->tx_dropped); + ncs->pt_tx_channel_err = ntohl(rsp->tx_channel_err); + ncs->pt_tx_us_err = ntohl(rsp->tx_us_err); + ncs->pt_rx_pkts = ntohl(rsp->rx_pkts); + ncs->pt_rx_dropped = ntohl(rsp->rx_dropped); + ncs->pt_rx_channel_err = ntohl(rsp->rx_channel_err); + ncs->pt_rx_us_err = ntohl(rsp->rx_us_err); + ncs->pt_rx_os_err = ntohl(rsp->rx_os_err); + + return 0; +} + +static int ncsi_rsp_handler_gps(struct ncsi_request *nr) +{ + struct ncsi_rsp_gps_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_package *np; + + /* Find the package */ + rsp = (struct ncsi_rsp_gps_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + &np, NULL); + if (!np) + return -ENODEV; + + return 0; +} + +static int ncsi_rsp_handler_gpuuid(struct ncsi_request *nr) +{ + struct ncsi_rsp_gpuuid_pkt *rsp; + struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_package *np; + + /* Find the package */ + rsp = (struct ncsi_rsp_gpuuid_pkt *)skb_network_header(nr->rsp); + ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, + &np, NULL); + if (!np) + return -ENODEV; + + memcpy(np->uuid, rsp->uuid, sizeof(rsp->uuid)); + + return 0; +} + +static struct ncsi_rsp_handler { + unsigned char type; + int payload; + int (*handler)(struct ncsi_request *nr); +} ncsi_rsp_handlers[] = { + { NCSI_PKT_RSP_CIS, 4, ncsi_rsp_handler_cis }, + { NCSI_PKT_RSP_SP, 4, ncsi_rsp_handler_sp }, + { NCSI_PKT_RSP_DP, 4, ncsi_rsp_handler_dp }, + { NCSI_PKT_RSP_EC, 4, ncsi_rsp_handler_ec }, + { NCSI_PKT_RSP_DC, 4, ncsi_rsp_handler_dc }, + { NCSI_PKT_RSP_RC, 4, ncsi_rsp_handler_rc }, + { NCSI_PKT_RSP_ECNT, 4, ncsi_rsp_handler_ecnt }, + { NCSI_PKT_RSP_DCNT, 4, ncsi_rsp_handler_dcnt }, + { NCSI_PKT_RSP_AE, 4, ncsi_rsp_handler_ae }, + { NCSI_PKT_RSP_SL, 4, ncsi_rsp_handler_sl }, + { NCSI_PKT_RSP_GLS, 16, ncsi_rsp_handler_gls }, + { NCSI_PKT_RSP_SVF, 4, ncsi_rsp_handler_svf }, + { NCSI_PKT_RSP_EV, 4, ncsi_rsp_handler_ev }, + { NCSI_PKT_RSP_DV, 4, ncsi_rsp_handler_dv }, + { NCSI_PKT_RSP_SMA, 4, ncsi_rsp_handler_sma }, + { NCSI_PKT_RSP_EBF, 4, ncsi_rsp_handler_ebf }, + { NCSI_PKT_RSP_DBF, 4, ncsi_rsp_handler_dbf }, + { NCSI_PKT_RSP_EGMF, 4, ncsi_rsp_handler_egmf }, + { NCSI_PKT_RSP_DGMF, 4, ncsi_rsp_handler_dgmf }, + { NCSI_PKT_RSP_SNFC, 4, ncsi_rsp_handler_snfc }, + { NCSI_PKT_RSP_GVI, 36, ncsi_rsp_handler_gvi }, + { NCSI_PKT_RSP_GC, 32, ncsi_rsp_handler_gc }, + { NCSI_PKT_RSP_GP, -1, ncsi_rsp_handler_gp }, + { NCSI_PKT_RSP_GCPS, 172, ncsi_rsp_handler_gcps }, + { NCSI_PKT_RSP_GNS, 172, ncsi_rsp_handler_gns }, + { NCSI_PKT_RSP_GNPTS, 172, ncsi_rsp_handler_gnpts }, + { NCSI_PKT_RSP_GPS, 8, ncsi_rsp_handler_gps }, + { NCSI_PKT_RSP_OEM, 0, NULL }, + { NCSI_PKT_RSP_PLDM, 0, NULL }, + { NCSI_PKT_RSP_GPUUID, 20, ncsi_rsp_handler_gpuuid } +}; + +int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct ncsi_rsp_handler *nrh = NULL; + struct ncsi_dev *nd; + struct ncsi_dev_priv *ndp; + struct ncsi_request *nr; + struct ncsi_pkt_hdr *hdr; + unsigned long flags; + int payload, i, ret; + + /* Find the NCSI device */ + nd = ncsi_find_dev(dev); + ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL; + if (!ndp) + return -ENODEV; + + /* Check if it is AEN packet */ + hdr = (struct ncsi_pkt_hdr *)skb_network_header(skb); + if (hdr->type == NCSI_PKT_AEN) + return ncsi_aen_handler(ndp, skb); + + /* Find the handler */ + for (i = 0; i < ARRAY_SIZE(ncsi_rsp_handlers); i++) { + if (ncsi_rsp_handlers[i].type == hdr->type) { + if (ncsi_rsp_handlers[i].handler) + nrh = &ncsi_rsp_handlers[i]; + else + nrh = NULL; + + break; + } + } + + if (!nrh) { + netdev_err(nd->dev, "Received unrecognized packet (0x%x)\n", + hdr->type); + return -ENOENT; + } + + /* Associate with the request */ + spin_lock_irqsave(&ndp->lock, flags); + nr = &ndp->requests[hdr->id]; + if (!nr->used) { + spin_unlock_irqrestore(&ndp->lock, flags); + return -ENODEV; + } + + nr->rsp = skb; + if (!nr->enabled) { + spin_unlock_irqrestore(&ndp->lock, flags); + ret = -ENOENT; + goto out; + } + + /* Validate the packet */ + spin_unlock_irqrestore(&ndp->lock, flags); + payload = nrh->payload; + if (payload < 0) + payload = ntohs(hdr->length); + ret = ncsi_validate_rsp_pkt(nr, payload); + if (ret) + goto out; + + /* Process the packet */ + ret = nrh->handler(nr); +out: + ncsi_free_request(nr); + return ret; +} diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index d7024b2..5117bcb 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -395,6 +395,20 @@ static const char *const tcp_state_name_table[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_LAST] = "BUG!", }; +static const bool tcp_state_active_table[IP_VS_TCP_S_LAST] = { + [IP_VS_TCP_S_NONE] = false, + [IP_VS_TCP_S_ESTABLISHED] = true, + [IP_VS_TCP_S_SYN_SENT] = true, + [IP_VS_TCP_S_SYN_RECV] = true, + [IP_VS_TCP_S_FIN_WAIT] = false, + [IP_VS_TCP_S_TIME_WAIT] = false, + [IP_VS_TCP_S_CLOSE] = false, + [IP_VS_TCP_S_CLOSE_WAIT] = false, + [IP_VS_TCP_S_LAST_ACK] = false, + [IP_VS_TCP_S_LISTEN] = false, + [IP_VS_TCP_S_SYNACK] = true, +}; + #define sNO IP_VS_TCP_S_NONE #define sES IP_VS_TCP_S_ESTABLISHED #define sSS IP_VS_TCP_S_SYN_SENT @@ -418,6 +432,13 @@ static const char * tcp_state_name(int state) return tcp_state_name_table[state] ? tcp_state_name_table[state] : "?"; } +static bool tcp_state_active(int state) +{ + if (state >= IP_VS_TCP_S_LAST) + return false; + return tcp_state_active_table[state]; +} + static struct tcp_states_t tcp_states [] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ @@ -540,12 +561,12 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && - (new_state != IP_VS_TCP_S_ESTABLISHED)) { + !tcp_state_active(new_state)) { atomic_dec(&dest->activeconns); atomic_inc(&dest->inactconns); cp->flags |= IP_VS_CONN_F_INACTIVE; } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && - (new_state == IP_VS_TCP_S_ESTABLISHED)) { + tcp_state_active(new_state)) { atomic_inc(&dest->activeconns); atomic_dec(&dest->inactconns); cp->flags &= ~IP_VS_CONN_F_INACTIVE; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 803001a..1b07578 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1545,7 +1545,8 @@ error: /* * Set up receiving multicast socket over UDP */ -static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id) +static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, + int ifindex) { /* multicast addr */ union ipvs_sockaddr mcast_addr; @@ -1566,6 +1567,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id) set_sock_size(sock->sk, 0, result); get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); + sock->sk->sk_bound_dev_if = ifindex; result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); @@ -1868,7 +1870,7 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, if (state == IP_VS_STATE_MASTER) sock = make_send_sock(ipvs, id); else - sock = make_receive_sock(ipvs, id); + sock = make_receive_sock(ipvs, id, dev->ifindex); if (IS_ERR(sock)) { result = PTR_ERR(sock); goto outtinfo; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 153e33f..9198e69 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -460,6 +460,23 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, net_eq(net, nf_ct_net(ct)); } +/* must be called with rcu read lock held */ +void nf_conntrack_get_ht(struct hlist_nulls_head **hash, unsigned int *hsize) +{ + struct hlist_nulls_head *hptr; + unsigned int sequence, hsz; + + do { + sequence = read_seqcount_begin(&nf_conntrack_generation); + hsz = nf_conntrack_htable_size; + hptr = nf_conntrack_hash; + } while (read_seqcount_retry(&nf_conntrack_generation, sequence)); + + *hash = hptr; + *hsize = hsz; +} +EXPORT_SYMBOL_GPL(nf_conntrack_get_ht); + /* * Warning : * - Caller must take a reference on returned object @@ -640,6 +657,7 @@ static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); if (l4proto->allow_clash && + !nfct_nat(ct) && !nf_ct_is_dying(ct) && atomic_inc_not_zero(&ct->ct_general.use)) { nf_ct_acct_merge(ct, ctinfo, (struct nf_conn *)skb->nfct); @@ -817,67 +835,69 @@ EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken); /* There's a small race here where we may free a just-assured connection. Too bad: we're in trouble anyway. */ -static noinline int early_drop(struct net *net, unsigned int _hash) +static unsigned int early_drop_list(struct net *net, + struct hlist_nulls_head *head) { - /* Use oldest entry, which is roughly LRU */ struct nf_conntrack_tuple_hash *h; - struct nf_conn *tmp; struct hlist_nulls_node *n; - unsigned int i, hash, sequence; - struct nf_conn *ct = NULL; - spinlock_t *lockp; - bool ret = false; + unsigned int drops = 0; + struct nf_conn *tmp; - i = 0; + hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) { + tmp = nf_ct_tuplehash_to_ctrack(h); - local_bh_disable(); -restart: - sequence = read_seqcount_begin(&nf_conntrack_generation); - for (; i < NF_CT_EVICTION_RANGE; i++) { - hash = scale_hash(_hash++); - lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS]; - nf_conntrack_lock(lockp); - if (read_seqcount_retry(&nf_conntrack_generation, sequence)) { - spin_unlock(lockp); - goto restart; - } - hlist_nulls_for_each_entry_rcu(h, n, &nf_conntrack_hash[hash], - hnnode) { - tmp = nf_ct_tuplehash_to_ctrack(h); - - if (test_bit(IPS_ASSURED_BIT, &tmp->status) || - !net_eq(nf_ct_net(tmp), net) || - nf_ct_is_dying(tmp)) - continue; - - if (atomic_inc_not_zero(&tmp->ct_general.use)) { - ct = tmp; - break; - } - } + if (test_bit(IPS_ASSURED_BIT, &tmp->status) || + !net_eq(nf_ct_net(tmp), net) || + nf_ct_is_dying(tmp)) + continue; - spin_unlock(lockp); - if (ct) - break; + if (!atomic_inc_not_zero(&tmp->ct_general.use)) + continue; + + /* kill only if still in same netns -- might have moved due to + * SLAB_DESTROY_BY_RCU rules. + * + * We steal the timer reference. If that fails timer has + * already fired or someone else deleted it. Just drop ref + * and move to next entry. + */ + if (net_eq(nf_ct_net(tmp), net) && + nf_ct_is_confirmed(tmp) && + del_timer(&tmp->timeout) && + nf_ct_delete(tmp, 0, 0)) + drops++; + + nf_ct_put(tmp); } - local_bh_enable(); + return drops; +} - if (!ct) - return false; +static noinline int early_drop(struct net *net, unsigned int _hash) +{ + unsigned int i; - /* kill only if in same netns -- might have moved due to - * SLAB_DESTROY_BY_RCU rules - */ - if (net_eq(nf_ct_net(ct), net) && del_timer(&ct->timeout)) { - if (nf_ct_delete(ct, 0, 0)) { - NF_CT_STAT_INC_ATOMIC(net, early_drop); - ret = true; + for (i = 0; i < NF_CT_EVICTION_RANGE; i++) { + struct hlist_nulls_head *ct_hash; + unsigned hash, sequence, drops; + + rcu_read_lock(); + do { + sequence = read_seqcount_begin(&nf_conntrack_generation); + hash = scale_hash(_hash++); + ct_hash = nf_conntrack_hash; + } while (read_seqcount_retry(&nf_conntrack_generation, sequence)); + + drops = early_drop_list(net, &ct_hash[hash]); + rcu_read_unlock(); + + if (drops) { + NF_CT_STAT_ADD_ATOMIC(net, early_drop, drops); + return true; } } - nf_ct_put(ct); - return ret; + return false; } static struct nf_conn * @@ -1581,8 +1601,15 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) unsigned int nr_slots, i; size_t sz; + if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head))) + return NULL; + BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); + + if (nr_slots > (UINT_MAX / sizeof(struct hlist_nulls_head))) + return NULL; + sz = nr_slots * sizeof(struct hlist_nulls_head); hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 1a95459..02bcf00 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -73,7 +73,7 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id, size_t var_alloc_len, gfp_t gfp) { struct nf_ct_ext *old, *new; - int i, newlen, newoff; + int newlen, newoff; struct nf_ct_ext_type *t; /* Conntrack must not be confirmed to avoid races on reallocation. */ @@ -99,19 +99,8 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id, return NULL; if (new != old) { - for (i = 0; i < NF_CT_EXT_NUM; i++) { - if (!__nf_ct_ext_exist(old, i)) - continue; - - rcu_read_lock(); - t = rcu_dereference(nf_ct_ext_types[i]); - if (t && t->move) - t->move((void *)new + new->offset[i], - (void *)old + old->offset[i]); - rcu_read_unlock(); - } kfree_rcu(old, rcu); - ct->ext = new; + rcu_assign_pointer(ct->ext, new); } new->offset[id] = newoff; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 19efeba..4314700 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -572,7 +572,7 @@ static int nf_ct_ftp_from_nlattr(struct nlattr *attr, struct nf_conn *ct) return 0; } -static struct nf_conntrack_helper ftp[MAX_PORTS][2] __read_mostly; +static struct nf_conntrack_helper ftp[MAX_PORTS * 2] __read_mostly; static const struct nf_conntrack_expect_policy ftp_exp_policy = { .max_expected = 1, @@ -582,24 +582,13 @@ static const struct nf_conntrack_expect_policy ftp_exp_policy = { /* don't make this __exit, since it's called from __init ! */ static void nf_conntrack_ftp_fini(void) { - int i, j; - for (i = 0; i < ports_c; i++) { - for (j = 0; j < 2; j++) { - if (ftp[i][j].me == NULL) - continue; - - pr_debug("unregistering helper for pf: %d port: %d\n", - ftp[i][j].tuple.src.l3num, ports[i]); - nf_conntrack_helper_unregister(&ftp[i][j]); - } - } - + nf_conntrack_helpers_unregister(ftp, ports_c * 2); kfree(ftp_buffer); } static int __init nf_conntrack_ftp_init(void) { - int i, j = -1, ret = 0; + int i, ret = 0; ftp_buffer = kmalloc(65536, GFP_KERNEL); if (!ftp_buffer) @@ -611,32 +600,21 @@ static int __init nf_conntrack_ftp_init(void) /* FIXME should be configurable whether IPv4 and IPv6 FTP connections are tracked or not - YK */ for (i = 0; i < ports_c; i++) { - ftp[i][0].tuple.src.l3num = PF_INET; - ftp[i][1].tuple.src.l3num = PF_INET6; - for (j = 0; j < 2; j++) { - ftp[i][j].data_len = sizeof(struct nf_ct_ftp_master); - ftp[i][j].tuple.src.u.tcp.port = htons(ports[i]); - ftp[i][j].tuple.dst.protonum = IPPROTO_TCP; - ftp[i][j].expect_policy = &ftp_exp_policy; - ftp[i][j].me = THIS_MODULE; - ftp[i][j].help = help; - ftp[i][j].from_nlattr = nf_ct_ftp_from_nlattr; - if (ports[i] == FTP_PORT) - sprintf(ftp[i][j].name, "ftp"); - else - sprintf(ftp[i][j].name, "ftp-%d", ports[i]); - - pr_debug("registering helper for pf: %d port: %d\n", - ftp[i][j].tuple.src.l3num, ports[i]); - ret = nf_conntrack_helper_register(&ftp[i][j]); - if (ret) { - pr_err("failed to register helper for pf: %d port: %d\n", - ftp[i][j].tuple.src.l3num, ports[i]); - ports_c = i; - nf_conntrack_ftp_fini(); - return ret; - } - } + nf_ct_helper_init(&ftp[2 * i], AF_INET, IPPROTO_TCP, "ftp", + FTP_PORT, ports[i], ports[i], &ftp_exp_policy, + 0, sizeof(struct nf_ct_ftp_master), help, + nf_ct_ftp_from_nlattr, THIS_MODULE); + nf_ct_helper_init(&ftp[2 * i + 1], AF_INET6, IPPROTO_TCP, "ftp", + FTP_PORT, ports[i], ports[i], &ftp_exp_policy, + 0, sizeof(struct nf_ct_ftp_master), help, + nf_ct_ftp_from_nlattr, THIS_MODULE); + } + + ret = nf_conntrack_helpers_register(ftp, ports_c * 2); + if (ret < 0) { + pr_err("failed to register helpers\n"); + kfree(ftp_buffer); + return ret; } return 0; diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index bcd5ed6..89b2e46 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -846,9 +846,10 @@ int DecodeQ931(unsigned char *buf, size_t sz, Q931 *q931) sz -= len; /* Message Type */ - if (sz < 1) + if (sz < 2) return H323_ERROR_BOUND; q931->MessageType = *p++; + sz--; PRINT("MessageType = %02X\n", q931->MessageType); if (*p & 0x80) { p++; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 9511af0..bb77a97 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1273,19 +1273,6 @@ static struct nf_conntrack_expect *find_expect(struct nf_conn *ct, } /****************************************************************************/ -static int set_expect_timeout(struct nf_conntrack_expect *exp, - unsigned int timeout) -{ - if (!exp || !del_timer(&exp->timeout)) - return 0; - - exp->timeout.expires = jiffies + timeout * HZ; - add_timer(&exp->timeout); - - return 1; -} - -/****************************************************************************/ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int protoff, unsigned char **data, @@ -1486,7 +1473,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, "timeout to %u seconds for", info->timeout); nf_ct_dump_tuple(&exp->tuple); - set_expect_timeout(exp, info->timeout); + mod_timer(&exp->timeout, jiffies + info->timeout * HZ); } spin_unlock_bh(&nf_conntrack_expect_lock); } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 3a1a88b..b989b81 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -409,6 +409,8 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) struct nf_conntrack_expect *exp; const struct hlist_node *next; const struct hlist_nulls_node *nn; + unsigned int last_hsize; + spinlock_t *lock; struct net *net; unsigned int i; @@ -446,18 +448,80 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) rtnl_unlock(); local_bh_disable(); - for (i = 0; i < nf_conntrack_htable_size; i++) { - nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); - if (i < nf_conntrack_htable_size) { - hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) - unhelp(h, me); +restart: + last_hsize = nf_conntrack_htable_size; + for (i = 0; i < last_hsize; i++) { + lock = &nf_conntrack_locks[i % CONNTRACK_LOCKS]; + nf_conntrack_lock(lock); + if (last_hsize != nf_conntrack_htable_size) { + spin_unlock(lock); + goto restart; } - spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) + unhelp(h, me); + spin_unlock(lock); } local_bh_enable(); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); +void nf_ct_helper_init(struct nf_conntrack_helper *helper, + u16 l3num, u16 protonum, const char *name, + u16 default_port, u16 spec_port, u32 id, + const struct nf_conntrack_expect_policy *exp_pol, + u32 expect_class_max, u32 data_len, + int (*help)(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo), + int (*from_nlattr)(struct nlattr *attr, + struct nf_conn *ct), + struct module *module) +{ + helper->tuple.src.l3num = l3num; + helper->tuple.dst.protonum = protonum; + helper->tuple.src.u.all = htons(spec_port); + helper->expect_policy = exp_pol; + helper->expect_class_max = expect_class_max; + helper->data_len = data_len; + helper->help = help; + helper->from_nlattr = from_nlattr; + helper->me = module; + + if (spec_port == default_port) + snprintf(helper->name, sizeof(helper->name), "%s", name); + else + snprintf(helper->name, sizeof(helper->name), "%s-%u", name, id); +} +EXPORT_SYMBOL_GPL(nf_ct_helper_init); + +int nf_conntrack_helpers_register(struct nf_conntrack_helper *helper, + unsigned int n) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < n; i++) { + err = nf_conntrack_helper_register(&helper[i]); + if (err < 0) + goto err; + } + + return err; +err: + if (i > 0) + nf_conntrack_helpers_unregister(helper, i); + return err; +} +EXPORT_SYMBOL_GPL(nf_conntrack_helpers_register); + +void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *helper, + unsigned int n) +{ + while (n-- > 0) + nf_conntrack_helper_unregister(&helper[n]); +} +EXPORT_SYMBOL_GPL(nf_conntrack_helpers_unregister); + static struct nf_ct_ext_type helper_extend __read_mostly = { .len = sizeof(struct nf_conn_help), .align = __alignof__(struct nf_conn_help), diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index f97ac61..1972a14 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -255,27 +255,18 @@ static int __init nf_conntrack_irc_init(void) ports[ports_c++] = IRC_PORT; for (i = 0; i < ports_c; i++) { - irc[i].tuple.src.l3num = AF_INET; - irc[i].tuple.src.u.tcp.port = htons(ports[i]); - irc[i].tuple.dst.protonum = IPPROTO_TCP; - irc[i].expect_policy = &irc_exp_policy; - irc[i].me = THIS_MODULE; - irc[i].help = help; - - if (ports[i] == IRC_PORT) - sprintf(irc[i].name, "irc"); - else - sprintf(irc[i].name, "irc-%u", i); - - ret = nf_conntrack_helper_register(&irc[i]); - if (ret) { - pr_err("failed to register helper for pf: %u port: %u\n", - irc[i].tuple.src.l3num, ports[i]); - ports_c = i; - nf_conntrack_irc_fini(); - return ret; - } + nf_ct_helper_init(&irc[i], AF_INET, IPPROTO_TCP, "irc", + IRC_PORT, ports[i], i, &irc_exp_policy, + 0, 0, help, NULL, THIS_MODULE); + } + + ret = nf_conntrack_helpers_register(&irc[0], ports_c); + if (ret) { + pr_err("failed to register helpers\n"); + kfree(irc_buffer); + return ret; } + return 0; } @@ -283,10 +274,7 @@ static int __init nf_conntrack_irc_init(void) * it is needed by the init function */ static void nf_conntrack_irc_fini(void) { - int i; - - for (i = 0; i < ports_c; i++) - nf_conntrack_helper_unregister(&irc[i]); + nf_conntrack_helpers_unregister(irc, ports_c); kfree(irc_buffer); } diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index 252e6a7..bcab8bd 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -16,23 +16,6 @@ static spinlock_t nf_connlabels_lock; -int nf_connlabel_set(struct nf_conn *ct, u16 bit) -{ - struct nf_conn_labels *labels = nf_ct_labels_find(ct); - - if (!labels || BIT_WORD(bit) >= labels->words) - return -ENOSPC; - - if (test_bit(bit, labels->bits)) - return 0; - - if (!test_and_set_bit(bit, labels->bits)) - nf_conntrack_event_cache(IPCT_LABEL, ct); - - return 0; -} -EXPORT_SYMBOL_GPL(nf_connlabel_set); - static int replace_u32(u32 *address, u32 mask, u32 new) { u32 old, tmp; @@ -60,7 +43,7 @@ int nf_connlabels_replace(struct nf_conn *ct, if (!labels) return -ENOSPC; - size = labels->words * sizeof(long); + size = sizeof(labels->bits); if (size < (words32 * sizeof(u32))) words32 = size / sizeof(u32); @@ -80,16 +63,11 @@ EXPORT_SYMBOL_GPL(nf_connlabels_replace); int nf_connlabels_get(struct net *net, unsigned int bits) { - size_t words; - - words = BIT_WORD(bits) + 1; - if (words > NF_CT_LABELS_MAX_SIZE / sizeof(long)) + if (BIT_WORD(bits) >= NF_CT_LABELS_MAX_SIZE / sizeof(long)) return -ERANGE; spin_lock(&nf_connlabels_lock); net->ct.labels_used++; - if (words > net->ct.label_words) - net->ct.label_words = words; spin_unlock(&nf_connlabels_lock); return 0; @@ -100,8 +78,6 @@ void nf_connlabels_put(struct net *net) { spin_lock(&nf_connlabels_lock); net->ct.labels_used--; - if (net->ct.labels_used == 0) - net->ct.label_words = 0; spin_unlock(&nf_connlabels_lock); } EXPORT_SYMBOL_GPL(nf_connlabels_put); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index a18d1ce..050bb34 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -346,25 +346,25 @@ static inline int ctnetlink_label_size(const struct nf_conn *ct) if (!labels) return 0; - return nla_total_size(labels->words * sizeof(long)); + return nla_total_size(sizeof(labels->bits)); } static int ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); - unsigned int len, i; + unsigned int i; if (!labels) return 0; - len = labels->words * sizeof(long); i = 0; do { if (labels->bits[i] != 0) - return nla_put(skb, CTA_LABELS, len, labels->bits); + return nla_put(skb, CTA_LABELS, sizeof(labels->bits), + labels->bits); i++; - } while (i < labels->words); + } while (i < ARRAY_SIZE(labels->bits)); return 0; } diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index 3fcbaab..9dcb9ee 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -166,7 +166,7 @@ out: return ret; } -static struct nf_conntrack_helper sane[MAX_PORTS][2] __read_mostly; +static struct nf_conntrack_helper sane[MAX_PORTS * 2] __read_mostly; static const struct nf_conntrack_expect_policy sane_exp_policy = { .max_expected = 1, @@ -176,22 +176,13 @@ static const struct nf_conntrack_expect_policy sane_exp_policy = { /* don't make this __exit, since it's called from __init ! */ static void nf_conntrack_sane_fini(void) { - int i, j; - - for (i = 0; i < ports_c; i++) { - for (j = 0; j < 2; j++) { - pr_debug("unregistering helper for pf: %d port: %d\n", - sane[i][j].tuple.src.l3num, ports[i]); - nf_conntrack_helper_unregister(&sane[i][j]); - } - } - + nf_conntrack_helpers_unregister(sane, ports_c * 2); kfree(sane_buffer); } static int __init nf_conntrack_sane_init(void) { - int i, j = -1, ret = 0; + int i, ret = 0; sane_buffer = kmalloc(65536, GFP_KERNEL); if (!sane_buffer) @@ -203,31 +194,23 @@ static int __init nf_conntrack_sane_init(void) /* FIXME should be configurable whether IPv4 and IPv6 connections are tracked or not - YK */ for (i = 0; i < ports_c; i++) { - sane[i][0].tuple.src.l3num = PF_INET; - sane[i][1].tuple.src.l3num = PF_INET6; - for (j = 0; j < 2; j++) { - sane[i][j].data_len = sizeof(struct nf_ct_sane_master); - sane[i][j].tuple.src.u.tcp.port = htons(ports[i]); - sane[i][j].tuple.dst.protonum = IPPROTO_TCP; - sane[i][j].expect_policy = &sane_exp_policy; - sane[i][j].me = THIS_MODULE; - sane[i][j].help = help; - if (ports[i] == SANE_PORT) - sprintf(sane[i][j].name, "sane"); - else - sprintf(sane[i][j].name, "sane-%d", ports[i]); - - pr_debug("registering helper for pf: %d port: %d\n", - sane[i][j].tuple.src.l3num, ports[i]); - ret = nf_conntrack_helper_register(&sane[i][j]); - if (ret) { - pr_err("failed to register helper for pf: %d port: %d\n", - sane[i][j].tuple.src.l3num, ports[i]); - ports_c = i; - nf_conntrack_sane_fini(); - return ret; - } - } + nf_ct_helper_init(&sane[2 * i], AF_INET, IPPROTO_TCP, "sane", + SANE_PORT, ports[i], ports[i], + &sane_exp_policy, 0, + sizeof(struct nf_ct_sane_master), help, NULL, + THIS_MODULE); + nf_ct_helper_init(&sane[2 * i + 1], AF_INET6, IPPROTO_TCP, "sane", + SANE_PORT, ports[i], ports[i], + &sane_exp_policy, 0, + sizeof(struct nf_ct_sane_master), help, NULL, + THIS_MODULE); + } + + ret = nf_conntrack_helpers_register(sane, ports_c * 2); + if (ret < 0) { + pr_err("failed to register helpers\n"); + kfree(sane_buffer); + return ret; } return 0; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index f72ba55..8d9db9d 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1589,7 +1589,7 @@ static int sip_help_udp(struct sk_buff *skb, unsigned int protoff, return process_sip_msg(skb, ct, protoff, dataoff, &dptr, &datalen); } -static struct nf_conntrack_helper sip[MAX_PORTS][4] __read_mostly; +static struct nf_conntrack_helper sip[MAX_PORTS * 4] __read_mostly; static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1] = { [SIP_EXPECT_SIGNALLING] = { @@ -1616,20 +1616,12 @@ static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1 static void nf_conntrack_sip_fini(void) { - int i, j; - - for (i = 0; i < ports_c; i++) { - for (j = 0; j < ARRAY_SIZE(sip[i]); j++) { - if (sip[i][j].me == NULL) - continue; - nf_conntrack_helper_unregister(&sip[i][j]); - } - } + nf_conntrack_helpers_unregister(sip, ports_c * 4); } static int __init nf_conntrack_sip_init(void) { - int i, j, ret; + int i, ret; if (ports_c == 0) ports[ports_c++] = SIP_PORT; @@ -1637,43 +1629,32 @@ static int __init nf_conntrack_sip_init(void) for (i = 0; i < ports_c; i++) { memset(&sip[i], 0, sizeof(sip[i])); - sip[i][0].tuple.src.l3num = AF_INET; - sip[i][0].tuple.dst.protonum = IPPROTO_UDP; - sip[i][0].help = sip_help_udp; - sip[i][1].tuple.src.l3num = AF_INET; - sip[i][1].tuple.dst.protonum = IPPROTO_TCP; - sip[i][1].help = sip_help_tcp; - - sip[i][2].tuple.src.l3num = AF_INET6; - sip[i][2].tuple.dst.protonum = IPPROTO_UDP; - sip[i][2].help = sip_help_udp; - sip[i][3].tuple.src.l3num = AF_INET6; - sip[i][3].tuple.dst.protonum = IPPROTO_TCP; - sip[i][3].help = sip_help_tcp; - - for (j = 0; j < ARRAY_SIZE(sip[i]); j++) { - sip[i][j].data_len = sizeof(struct nf_ct_sip_master); - sip[i][j].tuple.src.u.udp.port = htons(ports[i]); - sip[i][j].expect_policy = sip_exp_policy; - sip[i][j].expect_class_max = SIP_EXPECT_MAX; - sip[i][j].me = THIS_MODULE; - - if (ports[i] == SIP_PORT) - sprintf(sip[i][j].name, "sip"); - else - sprintf(sip[i][j].name, "sip-%u", i); - - pr_debug("port #%u: %u\n", i, ports[i]); + nf_ct_helper_init(&sip[4 * i], AF_INET, IPPROTO_UDP, "sip", + SIP_PORT, ports[i], i, sip_exp_policy, + SIP_EXPECT_MAX, + sizeof(struct nf_ct_sip_master), sip_help_udp, + NULL, THIS_MODULE); + nf_ct_helper_init(&sip[4 * i + 1], AF_INET, IPPROTO_TCP, "sip", + SIP_PORT, ports[i], i, sip_exp_policy, + SIP_EXPECT_MAX, + sizeof(struct nf_ct_sip_master), sip_help_tcp, + NULL, THIS_MODULE); + nf_ct_helper_init(&sip[4 * i + 2], AF_INET6, IPPROTO_UDP, "sip", + SIP_PORT, ports[i], i, sip_exp_policy, + SIP_EXPECT_MAX, + sizeof(struct nf_ct_sip_master), sip_help_udp, + NULL, THIS_MODULE); + nf_ct_helper_init(&sip[4 * i + 3], AF_INET6, IPPROTO_TCP, "sip", + SIP_PORT, ports[i], i, sip_exp_policy, + SIP_EXPECT_MAX, + sizeof(struct nf_ct_sip_master), sip_help_tcp, + NULL, THIS_MODULE); + } - ret = nf_conntrack_helper_register(&sip[i][j]); - if (ret) { - pr_err("failed to register helper for pf: %u port: %u\n", - sip[i][j].tuple.src.l3num, ports[i]); - ports_c = i; - nf_conntrack_sip_fini(); - return ret; - } - } + ret = nf_conntrack_helpers_register(sip, ports_c * 4); + if (ret < 0) { + pr_err("failed to register helpers\n"); + return ret; } return 0; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 2aaa188..958a145 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -48,6 +48,8 @@ EXPORT_SYMBOL_GPL(print_tuple); struct ct_iter_state { struct seq_net_private p; + struct hlist_nulls_head *hash; + unsigned int htable_size; unsigned int bucket; u_int64_t time_now; }; @@ -58,9 +60,10 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) struct hlist_nulls_node *n; for (st->bucket = 0; - st->bucket < nf_conntrack_htable_size; + st->bucket < st->htable_size; st->bucket++) { - n = rcu_dereference(hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket])); + n = rcu_dereference( + hlist_nulls_first_rcu(&st->hash[st->bucket])); if (!is_a_nulls(n)) return n; } @@ -75,12 +78,11 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, head = rcu_dereference(hlist_nulls_next_rcu(head)); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { - if (++st->bucket >= nf_conntrack_htable_size) + if (++st->bucket >= st->htable_size) return NULL; } head = rcu_dereference( - hlist_nulls_first_rcu( - &nf_conntrack_hash[st->bucket])); + hlist_nulls_first_rcu(&st->hash[st->bucket])); } return head; } @@ -102,6 +104,8 @@ static void *ct_seq_start(struct seq_file *seq, loff_t *pos) st->time_now = ktime_get_real_ns(); rcu_read_lock(); + + nf_conntrack_get_ht(&st->hash, &st->htable_size); return ct_get_idx(seq, *pos); } diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index 2e65b543..b1227dc 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -97,7 +97,7 @@ static int tftp_help(struct sk_buff *skb, return ret; } -static struct nf_conntrack_helper tftp[MAX_PORTS][2] __read_mostly; +static struct nf_conntrack_helper tftp[MAX_PORTS * 2] __read_mostly; static const struct nf_conntrack_expect_policy tftp_exp_policy = { .max_expected = 1, @@ -106,47 +106,29 @@ static const struct nf_conntrack_expect_policy tftp_exp_policy = { static void nf_conntrack_tftp_fini(void) { - int i, j; - - for (i = 0; i < ports_c; i++) { - for (j = 0; j < 2; j++) - nf_conntrack_helper_unregister(&tftp[i][j]); - } + nf_conntrack_helpers_unregister(tftp, ports_c * 2); } static int __init nf_conntrack_tftp_init(void) { - int i, j, ret; + int i, ret; if (ports_c == 0) ports[ports_c++] = TFTP_PORT; for (i = 0; i < ports_c; i++) { - memset(&tftp[i], 0, sizeof(tftp[i])); - - tftp[i][0].tuple.src.l3num = AF_INET; - tftp[i][1].tuple.src.l3num = AF_INET6; - for (j = 0; j < 2; j++) { - tftp[i][j].tuple.dst.protonum = IPPROTO_UDP; - tftp[i][j].tuple.src.u.udp.port = htons(ports[i]); - tftp[i][j].expect_policy = &tftp_exp_policy; - tftp[i][j].me = THIS_MODULE; - tftp[i][j].help = tftp_help; - - if (ports[i] == TFTP_PORT) - sprintf(tftp[i][j].name, "tftp"); - else - sprintf(tftp[i][j].name, "tftp-%u", i); - - ret = nf_conntrack_helper_register(&tftp[i][j]); - if (ret) { - pr_err("failed to register helper for pf: %u port: %u\n", - tftp[i][j].tuple.src.l3num, ports[i]); - ports_c = i; - nf_conntrack_tftp_fini(); - return ret; - } - } + nf_ct_helper_init(&tftp[2 * i], AF_INET, IPPROTO_UDP, "tftp", + TFTP_PORT, ports[i], i, &tftp_exp_policy, + 0, 0, tftp_help, NULL, THIS_MODULE); + nf_ct_helper_init(&tftp[2 * i + 1], AF_INET6, IPPROTO_UDP, "tftp", + TFTP_PORT, ports[i], i, &tftp_exp_policy, + 0, 0, tftp_help, NULL, THIS_MODULE); + } + + ret = nf_conntrack_helpers_register(tftp, ports_c * 2); + if (ret < 0) { + pr_err("failed to register helpers\n"); + return ret; } return 0; } diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 6877a39..de31818 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -30,17 +30,19 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <linux/netfilter/nf_nat.h> -static DEFINE_SPINLOCK(nf_nat_lock); - static DEFINE_MUTEX(nf_nat_proto_mutex); static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO] __read_mostly; static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO] __read_mostly; -static struct hlist_head *nf_nat_bysource __read_mostly; -static unsigned int nf_nat_htable_size __read_mostly; -static unsigned int nf_nat_hash_rnd __read_mostly; +struct nf_nat_conn_key { + const struct net *net; + const struct nf_conntrack_tuple *tuple; + const struct nf_conntrack_zone *zone; +}; + +static struct rhashtable nf_nat_bysource_table; inline const struct nf_nat_l3proto * __nf_nat_l3proto_find(u8 family) @@ -119,19 +121,17 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) EXPORT_SYMBOL(nf_xfrm_me_harder); #endif /* CONFIG_XFRM */ -/* We keep an extra hash for each conntrack, for fast searching. */ -static inline unsigned int -hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) +static u32 nf_nat_bysource_hash(const void *data, u32 len, u32 seed) { - unsigned int hash; - - get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd)); + const struct nf_conntrack_tuple *t; + const struct nf_conn *ct = data; + t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* Original src, to ensure we map it consistently if poss. */ - hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32), - tuple->dst.protonum ^ nf_nat_hash_rnd ^ net_hash_mix(n)); - return reciprocal_scale(hash, nf_nat_htable_size); + seed ^= net_hash_mix(nf_ct_net(ct)); + return jhash2((const u32 *)&t->src, sizeof(t->src) / sizeof(u32), + t->dst.protonum ^ seed); } /* Is this tuple already taken? (not by us) */ @@ -187,6 +187,26 @@ same_src(const struct nf_conn *ct, t->src.u.all == tuple->src.u.all); } +static int nf_nat_bysource_cmp(struct rhashtable_compare_arg *arg, + const void *obj) +{ + const struct nf_nat_conn_key *key = arg->key; + const struct nf_conn *ct = obj; + + return same_src(ct, key->tuple) && + net_eq(nf_ct_net(ct), key->net) && + nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL); +} + +static struct rhashtable_params nf_nat_bysource_params = { + .head_offset = offsetof(struct nf_conn, nat_bysource), + .obj_hashfn = nf_nat_bysource_hash, + .obj_cmpfn = nf_nat_bysource_cmp, + .nelem_hint = 256, + .min_size = 1024, + .nulls_base = (1U << RHT_BASE_SHIFT), +}; + /* Only called for SRC manip */ static int find_appropriate_src(struct net *net, @@ -197,25 +217,23 @@ find_appropriate_src(struct net *net, struct nf_conntrack_tuple *result, const struct nf_nat_range *range) { - unsigned int h = hash_by_src(net, tuple); - const struct nf_conn_nat *nat; const struct nf_conn *ct; + struct nf_nat_conn_key key = { + .net = net, + .tuple = tuple, + .zone = zone + }; - hlist_for_each_entry_rcu(nat, &nf_nat_bysource[h], bysource) { - ct = nat->ct; - if (same_src(ct, tuple) && - net_eq(net, nf_ct_net(ct)) && - nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) { - /* Copy source part from reply tuple. */ - nf_ct_invert_tuplepr(result, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - result->dst = tuple->dst; - - if (in_range(l3proto, l4proto, result, range)) - return 1; - } - } - return 0; + ct = rhashtable_lookup_fast(&nf_nat_bysource_table, &key, + nf_nat_bysource_params); + if (!ct) + return 0; + + nf_ct_invert_tuplepr(result, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + result->dst = tuple->dst; + + return in_range(l3proto, l4proto, result, range); } /* For [FUTURE] fragmentation handling, we want the least-used @@ -387,7 +405,6 @@ nf_nat_setup_info(struct nf_conn *ct, const struct nf_nat_range *range, enum nf_nat_manip_type maniptype) { - struct net *net = nf_ct_net(ct); struct nf_conntrack_tuple curr_tuple, new_tuple; struct nf_conn_nat *nat; @@ -428,17 +445,13 @@ nf_nat_setup_info(struct nf_conn *ct, } if (maniptype == NF_NAT_MANIP_SRC) { - unsigned int srchash; - - srchash = hash_by_src(net, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - spin_lock_bh(&nf_nat_lock); - /* nf_conntrack_alter_reply might re-allocate extension aera */ - nat = nfct_nat(ct); - nat->ct = ct; - hlist_add_head_rcu(&nat->bysource, - &nf_nat_bysource[srchash]); - spin_unlock_bh(&nf_nat_lock); + int err; + + err = rhashtable_insert_fast(&nf_nat_bysource_table, + &ct->nat_bysource, + nf_nat_bysource_params); + if (err) + return NF_DROP; } /* It's done. */ @@ -543,7 +556,7 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) if (nf_nat_proto_remove(ct, data)) return 1; - if (!nat || !nat->ct) + if (!nat) return 0; /* This netns is being destroyed, and conntrack has nat null binding. @@ -555,11 +568,10 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) if (!del_timer(&ct->timeout)) return 1; - spin_lock_bh(&nf_nat_lock); - hlist_del_rcu(&nat->bysource); ct->status &= ~IPS_NAT_DONE_MASK; - nat->ct = NULL; - spin_unlock_bh(&nf_nat_lock); + + rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); add_timer(&ct->timeout); @@ -688,35 +700,17 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) { struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT); - if (nat == NULL || nat->ct == NULL) - return; - - NF_CT_ASSERT(nat->ct->status & IPS_SRC_NAT_DONE); - - spin_lock_bh(&nf_nat_lock); - hlist_del_rcu(&nat->bysource); - spin_unlock_bh(&nf_nat_lock); -} - -static void nf_nat_move_storage(void *new, void *old) -{ - struct nf_conn_nat *new_nat = new; - struct nf_conn_nat *old_nat = old; - struct nf_conn *ct = old_nat->ct; - - if (!ct || !(ct->status & IPS_SRC_NAT_DONE)) + if (!nat) return; - spin_lock_bh(&nf_nat_lock); - hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); - spin_unlock_bh(&nf_nat_lock); + rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); } static struct nf_ct_ext_type nat_extend __read_mostly = { .len = sizeof(struct nf_conn_nat), .align = __alignof__(struct nf_conn_nat), .destroy = nf_nat_cleanup_conntrack, - .move = nf_nat_move_storage, .id = NF_CT_EXT_NAT, .flags = NF_CT_EXT_F_PREALLOC, }; @@ -845,16 +839,13 @@ static int __init nf_nat_init(void) { int ret; - /* Leave them the same for the moment. */ - nf_nat_htable_size = nf_conntrack_htable_size; - - nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0); - if (!nf_nat_bysource) - return -ENOMEM; + ret = rhashtable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); + if (ret) + return ret; ret = nf_ct_extend_register(&nat_extend); if (ret < 0) { - nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + rhashtable_destroy(&nf_nat_bysource_table); printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); return ret; } @@ -878,7 +869,7 @@ static int __init nf_nat_init(void) return 0; cleanup_extend: - nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + rhashtable_destroy(&nf_nat_bysource_table); nf_ct_extend_unregister(&nat_extend); return ret; } @@ -896,8 +887,8 @@ static void __exit nf_nat_cleanup(void) #endif for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); - synchronize_net(); - nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + + rhashtable_destroy(&nf_nat_bysource_table); } MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 18b7f85..7e1c876 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1405,7 +1405,6 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, rcu_assign_pointer(basechain->stats, stats); } - write_pnet(&basechain->pnet, net); basechain->type = type; chain = &basechain->chain; @@ -1706,9 +1705,11 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, err = nf_tables_newexpr(ctx, &info, expr); if (err < 0) - goto err2; + goto err3; return expr; +err3: + kfree(expr); err2: module_put(info.ops->type->owner); err1: @@ -1858,10 +1859,16 @@ err: return err; } +struct nft_rule_dump_ctx { + char table[NFT_TABLE_MAXNAMELEN]; + char chain[NFT_CHAIN_MAXNAMELEN]; +}; + static int nf_tables_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + const struct nft_rule_dump_ctx *ctx = cb->data; const struct nft_af_info *afi; const struct nft_table *table; const struct nft_chain *chain; @@ -1878,7 +1885,15 @@ static int nf_tables_dump_rules(struct sk_buff *skb, continue; list_for_each_entry_rcu(table, &afi->tables, list) { + if (ctx && ctx->table[0] && + strcmp(ctx->table, table->name) != 0) + continue; + list_for_each_entry_rcu(chain, &table->chains, list) { + if (ctx && ctx->chain[0] && + strcmp(ctx->chain, chain->name) != 0) + continue; + list_for_each_entry_rcu(rule, &chain->rules, list) { if (!nft_is_active(net, rule)) goto cont; @@ -1908,6 +1923,12 @@ done: return skb->len; } +static int nf_tables_dump_rules_done(struct netlink_callback *cb) +{ + kfree(cb->data); + return 0; +} + static int nf_tables_getrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -1925,7 +1946,25 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_rules, + .done = nf_tables_dump_rules_done, }; + + if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { + struct nft_rule_dump_ctx *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + if (nla[NFTA_RULE_TABLE]) + nla_strlcpy(ctx->table, nla[NFTA_RULE_TABLE], + sizeof(ctx->table)); + if (nla[NFTA_RULE_CHAIN]) + nla_strlcpy(ctx->chain, nla[NFTA_RULE_CHAIN], + sizeof(ctx->chain)); + c.data = ctx; + } + return netlink_dump_start(nlsk, skb, nlh, &c); } @@ -2841,7 +2880,6 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, } INIT_LIST_HEAD(&set->bindings); - write_pnet(&set->pnet, net); set->ops = ops; set->ktype = ktype; set->klen = desc.klen; @@ -3520,7 +3558,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err4; ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; - err = set->ops->insert(set, &elem); + err = set->ops->insert(ctx->net, set, &elem); if (err < 0) goto err5; @@ -3644,7 +3682,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, goto err3; } - priv = set->ops->deactivate(set, &elem); + priv = set->ops->deactivate(ctx->net, set, &elem); if (priv == NULL) { err = -ENOENT; goto err4; @@ -4018,7 +4056,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWSETELEM: te = (struct nft_trans_elem *)trans->data; - te->set->ops->activate(te->set, &te->elem); + te->set->ops->activate(net, te->set, &te->elem); nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, NFT_MSG_NEWSETELEM, 0); @@ -4143,7 +4181,7 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) case NFT_MSG_DELSETELEM: te = (struct nft_trans_elem *)trans->data; - te->set->ops->activate(te->set, &te->elem); + te->set->ops->activate(net, te->set, &te->elem); te->set->ndeact--; nft_trans_destroy(trans); diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 3c84f14..4cdcd96 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -303,16 +303,24 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) { struct nf_conntrack_tuple_hash *h; const struct hlist_nulls_node *nn; + unsigned int last_hsize; + spinlock_t *lock; int i; local_bh_disable(); - for (i = 0; i < nf_conntrack_htable_size; i++) { - nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); - if (i < nf_conntrack_htable_size) { - hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) - untimeout(h, timeout); +restart: + last_hsize = nf_conntrack_htable_size; + for (i = 0; i < last_hsize; i++) { + lock = &nf_conntrack_locks[i % CONNTRACK_LOCKS]; + nf_conntrack_lock(lock); + if (last_hsize != nf_conntrack_htable_size) { + spin_unlock(lock); + goto restart; } - spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + + hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode) + untimeout(h, timeout); + spin_unlock(lock); } local_bh_enable(); } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 6228c42..c21e7eb 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -23,6 +23,20 @@ #include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> +struct nft_xt { + struct list_head head; + struct nft_expr_ops ops; + unsigned int refcnt; +}; + +static void nft_xt_put(struct nft_xt *xt) +{ + if (--xt->refcnt == 0) { + list_del(&xt->head); + kfree(xt); + } +} + static int nft_compat_chain_validate_dependency(const char *tablename, const struct nft_chain *chain) { @@ -260,6 +274,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) if (par.target->destroy != NULL) par.target->destroy(&par); + nft_xt_put(container_of(expr->ops, struct nft_xt, ops)); module_put(target->me); } @@ -442,6 +457,7 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) if (par.match->destroy != NULL) par.match->destroy(&par); + nft_xt_put(container_of(expr->ops, struct nft_xt, ops)); module_put(match->me); } @@ -612,11 +628,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { static LIST_HEAD(nft_match_list); -struct nft_xt { - struct list_head head; - struct nft_expr_ops ops; -}; - static struct nft_expr_type nft_match_type; static bool nft_match_cmp(const struct xt_match *match, @@ -634,6 +645,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, struct xt_match *match; char *mt_name; u32 rev, family; + int err; if (tb[NFTA_MATCH_NAME] == NULL || tb[NFTA_MATCH_REV] == NULL || @@ -652,6 +664,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, if (!try_module_get(match->me)) return ERR_PTR(-ENOENT); + nft_match->refcnt++; return &nft_match->ops; } } @@ -660,14 +673,19 @@ nft_match_select_ops(const struct nft_ctx *ctx, if (IS_ERR(match)) return ERR_PTR(-ENOENT); - if (match->matchsize > nla_len(tb[NFTA_MATCH_INFO])) - return ERR_PTR(-EINVAL); + if (match->matchsize > nla_len(tb[NFTA_MATCH_INFO])) { + err = -EINVAL; + goto err; + } /* This is the first time we use this match, allocate operations */ nft_match = kzalloc(sizeof(struct nft_xt), GFP_KERNEL); - if (nft_match == NULL) - return ERR_PTR(-ENOMEM); + if (nft_match == NULL) { + err = -ENOMEM; + goto err; + } + nft_match->refcnt = 1; nft_match->ops.type = &nft_match_type; nft_match->ops.size = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize)); nft_match->ops.eval = nft_match_eval; @@ -680,14 +698,9 @@ nft_match_select_ops(const struct nft_ctx *ctx, list_add(&nft_match->head, &nft_match_list); return &nft_match->ops; -} - -static void nft_match_release(void) -{ - struct nft_xt *nft_match, *tmp; - - list_for_each_entry_safe(nft_match, tmp, &nft_match_list, head) - kfree(nft_match); +err: + module_put(match->me); + return ERR_PTR(err); } static struct nft_expr_type nft_match_type __read_mostly = { @@ -717,6 +730,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, struct xt_target *target; char *tg_name; u32 rev, family; + int err; if (tb[NFTA_TARGET_NAME] == NULL || tb[NFTA_TARGET_REV] == NULL || @@ -735,6 +749,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, if (!try_module_get(target->me)) return ERR_PTR(-ENOENT); + nft_target->refcnt++; return &nft_target->ops; } } @@ -743,14 +758,19 @@ nft_target_select_ops(const struct nft_ctx *ctx, if (IS_ERR(target)) return ERR_PTR(-ENOENT); - if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) - return ERR_PTR(-EINVAL); + if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) { + err = -EINVAL; + goto err; + } /* This is the first time we use this target, allocate operations */ nft_target = kzalloc(sizeof(struct nft_xt), GFP_KERNEL); - if (nft_target == NULL) - return ERR_PTR(-ENOMEM); + if (nft_target == NULL) { + err = -ENOMEM; + goto err; + } + nft_target->refcnt = 1; nft_target->ops.type = &nft_target_type; nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); nft_target->ops.init = nft_target_init; @@ -767,14 +787,9 @@ nft_target_select_ops(const struct nft_ctx *ctx, list_add(&nft_target->head, &nft_target_list); return &nft_target->ops; -} - -static void nft_target_release(void) -{ - struct nft_xt *nft_target, *tmp; - - list_for_each_entry_safe(nft_target, tmp, &nft_target_list, head) - kfree(nft_target); +err: + module_put(target->me); + return ERR_PTR(err); } static struct nft_expr_type nft_target_type __read_mostly = { @@ -819,8 +834,6 @@ static void __exit nft_compat_module_exit(void) nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); - nft_match_release(); - nft_target_release(); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 137e308..51e180f 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -54,7 +54,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr, const struct nf_conn_help *help; const struct nf_conntrack_tuple *tuple; const struct nf_conntrack_helper *helper; - long diff; unsigned int state; ct = nf_ct_get(pkt->skb, &ctinfo); @@ -94,10 +93,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; #endif case NFT_CT_EXPIRATION: - diff = (long)jiffies - (long)ct->timeout.expires; - if (diff < 0) - diff = 0; - *dest = jiffies_to_msecs(diff); + *dest = jiffies_to_msecs(nf_ct_expires(ct)); return; case NFT_CT_HELPER: if (ct->master == NULL) @@ -113,18 +109,11 @@ static void nft_ct_get_eval(const struct nft_expr *expr, #ifdef CONFIG_NF_CONNTRACK_LABELS case NFT_CT_LABELS: { struct nf_conn_labels *labels = nf_ct_labels_find(ct); - unsigned int size; - if (!labels) { + if (labels) + memcpy(dest, labels->bits, NF_CT_LABELS_MAX_SIZE); + else memset(dest, 0, NF_CT_LABELS_MAX_SIZE); - return; - } - - size = labels->words * sizeof(long); - memcpy(dest, labels->bits, size); - if (size < NF_CT_LABELS_MAX_SIZE) - memset(((char *) dest) + size, 0, - NF_CT_LABELS_MAX_SIZE - size); return; } #endif @@ -355,6 +344,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, if (err < 0) return err; + if (priv->key == NFT_CT_BYTES || priv->key == NFT_CT_PKTS) + nf_ct_set_acct(ctx->net, true); + return 0; } @@ -363,6 +355,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_ct *priv = nft_expr_priv(expr); + bool label_got = false; unsigned int len; int err; @@ -381,6 +374,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, err = nf_connlabels_get(ctx->net, (len * BITS_PER_BYTE) - 1); if (err) return err; + label_got = true; break; #endif default: @@ -390,17 +384,28 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, priv->sreg = nft_parse_register(tb[NFTA_CT_SREG]); err = nft_validate_register_load(priv->sreg, len); if (err < 0) - return err; + goto err1; err = nft_ct_l3proto_try_module_get(ctx->afi->family); if (err < 0) - return err; + goto err1; return 0; + +err1: + if (label_got) + nf_connlabels_put(ctx->net); + return err; +} + +static void nft_ct_get_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + nft_ct_l3proto_module_put(ctx->afi->family); } -static void nft_ct_destroy(const struct nft_ctx *ctx, - const struct nft_expr *expr) +static void nft_ct_set_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { struct nft_ct *priv = nft_expr_priv(expr); @@ -472,7 +477,7 @@ static const struct nft_expr_ops nft_ct_get_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), .eval = nft_ct_get_eval, .init = nft_ct_get_init, - .destroy = nft_ct_destroy, + .destroy = nft_ct_get_destroy, .dump = nft_ct_get_dump, }; @@ -481,7 +486,7 @@ static const struct nft_expr_ops nft_ct_set_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), .eval = nft_ct_set_eval, .init = nft_ct_set_init, - .destroy = nft_ct_destroy, + .destroy = nft_ct_set_destroy, .dump = nft_ct_set_dump, }; diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index ea92481..564fa79 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -71,13 +71,13 @@ static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg, return 0; } -static bool nft_hash_lookup(const struct nft_set *set, const u32 *key, - const struct nft_set_ext **ext) +static bool nft_hash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_hash *priv = nft_set_priv(set); const struct nft_hash_elem *he; struct nft_hash_cmp_arg arg = { - .genmask = nft_genmask_cur(read_pnet(&set->pnet)), + .genmask = nft_genmask_cur(net), .set = set, .key = key, }; @@ -125,13 +125,13 @@ err1: return false; } -static int nft_hash_insert(const struct nft_set *set, +static int nft_hash_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_hash *priv = nft_set_priv(set); struct nft_hash_elem *he = elem->priv; struct nft_hash_cmp_arg arg = { - .genmask = nft_genmask_next(read_pnet(&set->pnet)), + .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, }; @@ -140,20 +140,20 @@ static int nft_hash_insert(const struct nft_set *set, nft_hash_params); } -static void nft_hash_activate(const struct nft_set *set, +static void nft_hash_activate(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_hash_elem *he = elem->priv; - nft_set_elem_change_active(set, &he->ext); + nft_set_elem_change_active(net, set, &he->ext); nft_set_elem_clear_busy(&he->ext); } -static void *nft_hash_deactivate(const struct nft_set *set, +static void *nft_hash_deactivate(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_hash *priv = nft_set_priv(set); - struct net *net = read_pnet(&set->pnet); struct nft_hash_elem *he; struct nft_hash_cmp_arg arg = { .genmask = nft_genmask_next(net), @@ -166,7 +166,7 @@ static void *nft_hash_deactivate(const struct nft_set *set, if (he != NULL) { if (!nft_set_elem_mark_busy(&he->ext) || !nft_is_active(net, &he->ext)) - nft_set_elem_change_active(set, &he->ext); + nft_set_elem_change_active(net, set, &he->ext); else he = NULL; } diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 713d668..24a73bb 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -52,6 +52,14 @@ static int nft_log_init(const struct nft_ctx *ctx, struct nft_log *priv = nft_expr_priv(expr); struct nf_loginfo *li = &priv->loginfo; const struct nlattr *nla; + int err; + + li->type = NF_LOG_TYPE_LOG; + if (tb[NFTA_LOG_LEVEL] != NULL && + tb[NFTA_LOG_GROUP] != NULL) + return -EINVAL; + if (tb[NFTA_LOG_GROUP] != NULL) + li->type = NF_LOG_TYPE_ULOG; nla = tb[NFTA_LOG_PREFIX]; if (nla != NULL) { @@ -63,13 +71,6 @@ static int nft_log_init(const struct nft_ctx *ctx, priv->prefix = (char *)nft_log_null_prefix; } - li->type = NF_LOG_TYPE_LOG; - if (tb[NFTA_LOG_LEVEL] != NULL && - tb[NFTA_LOG_GROUP] != NULL) - return -EINVAL; - if (tb[NFTA_LOG_GROUP] != NULL) - li->type = NF_LOG_TYPE_ULOG; - switch (li->type) { case NF_LOG_TYPE_LOG: if (tb[NFTA_LOG_LEVEL] != NULL) { @@ -78,6 +79,11 @@ static int nft_log_init(const struct nft_ctx *ctx, } else { li->u.log.level = LOGLEVEL_WARNING; } + if (li->u.log.level > LOGLEVEL_DEBUG) { + err = -EINVAL; + goto err1; + } + if (tb[NFTA_LOG_FLAGS] != NULL) { li->u.log.logflags = ntohl(nla_get_be32(tb[NFTA_LOG_FLAGS])); @@ -86,6 +92,7 @@ static int nft_log_init(const struct nft_ctx *ctx, case NF_LOG_TYPE_ULOG: li->u.ulog.group = ntohs(nla_get_be16(tb[NFTA_LOG_GROUP])); if (tb[NFTA_LOG_SNAPLEN] != NULL) { + li->u.ulog.flags |= NF_LOG_F_COPY_LEN; li->u.ulog.copy_len = ntohl(nla_get_be32(tb[NFTA_LOG_SNAPLEN])); } @@ -96,7 +103,16 @@ static int nft_log_init(const struct nft_ctx *ctx, break; } - return nf_logger_find_get(ctx->afi->family, li->type); + err = nf_logger_find_get(ctx->afi->family, li->type); + if (err < 0) + goto err1; + + return 0; + +err1: + if (priv->prefix != nft_log_null_prefix) + kfree(priv->prefix); + return err; } static void nft_log_destroy(const struct nft_ctx *ctx, @@ -134,7 +150,7 @@ static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr) if (nla_put_be16(skb, NFTA_LOG_GROUP, htons(li->u.ulog.group))) goto nla_put_failure; - if (li->u.ulog.copy_len) { + if (li->u.ulog.flags & NF_LOG_F_COPY_LEN) { if (nla_put_be32(skb, NFTA_LOG_SNAPLEN, htonl(li->u.ulog.copy_len))) goto nla_put_failure; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index b8d18f5..e164325 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -35,7 +35,7 @@ static void nft_lookup_eval(const struct nft_expr *expr, const struct nft_set_ext *ext; bool found; - found = set->ops->lookup(set, ®s->data[priv->sreg], &ext) ^ + found = set->ops->lookup(pkt->net, set, ®s->data[priv->sreg], &ext) ^ priv->invert; if (!found) { diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 03e5e33..2863f34 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -220,7 +220,7 @@ void nft_meta_set_eval(const struct nft_expr *expr, skb->pkt_type = value; break; case NFT_META_NFTRACE: - skb->nf_trace = 1; + skb->nf_trace = !!value; break; default: WARN_ON(1); diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index c0f6387..6473936 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -41,13 +41,13 @@ static bool nft_rbtree_equal(const struct nft_set *set, const void *this, return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0; } -static bool nft_rbtree_lookup(const struct nft_set *set, const u32 *key, - const struct nft_set_ext **ext) +static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { const struct nft_rbtree *priv = nft_set_priv(set); const struct nft_rbtree_elem *rbe, *interval = NULL; + u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; - u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); const void *this; int d; @@ -93,13 +93,13 @@ out: return false; } -static int __nft_rbtree_insert(const struct nft_set *set, +static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new) { struct nft_rbtree *priv = nft_set_priv(set); + u8 genmask = nft_genmask_next(net); struct nft_rbtree_elem *rbe; struct rb_node *parent, **p; - u8 genmask = nft_genmask_next(read_pnet(&set->pnet)); int d; parent = NULL; @@ -132,14 +132,14 @@ static int __nft_rbtree_insert(const struct nft_set *set, return 0; } -static int nft_rbtree_insert(const struct nft_set *set, +static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_rbtree_elem *rbe = elem->priv; int err; spin_lock_bh(&nft_rbtree_lock); - err = __nft_rbtree_insert(set, rbe); + err = __nft_rbtree_insert(net, set, rbe); spin_unlock_bh(&nft_rbtree_lock); return err; @@ -156,21 +156,23 @@ static void nft_rbtree_remove(const struct nft_set *set, spin_unlock_bh(&nft_rbtree_lock); } -static void nft_rbtree_activate(const struct nft_set *set, +static void nft_rbtree_activate(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_rbtree_elem *rbe = elem->priv; - nft_set_elem_change_active(set, &rbe->ext); + nft_set_elem_change_active(net, set, &rbe->ext); } -static void *nft_rbtree_deactivate(const struct nft_set *set, +static void *nft_rbtree_deactivate(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem) { const struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; struct nft_rbtree_elem *rbe, *this = elem->priv; - u8 genmask = nft_genmask_next(read_pnet(&set->pnet)); + u8 genmask = nft_genmask_next(net); int d; while (parent != NULL) { @@ -196,7 +198,7 @@ static void *nft_rbtree_deactivate(const struct nft_set *set, parent = parent->rb_right; continue; } - nft_set_elem_change_active(set, &rbe->ext); + nft_set_elem_change_active(net, set, &rbe->ext); return rbe; } } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index fe0e2db..e0aa7c1 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -702,6 +702,56 @@ int xt_check_entry_offsets(const void *base, } EXPORT_SYMBOL(xt_check_entry_offsets); +/** + * xt_alloc_entry_offsets - allocate array to store rule head offsets + * + * @size: number of entries + * + * Return: NULL or kmalloc'd or vmalloc'd array + */ +unsigned int *xt_alloc_entry_offsets(unsigned int size) +{ + unsigned int *off; + + off = kcalloc(size, sizeof(unsigned int), GFP_KERNEL | __GFP_NOWARN); + + if (off) + return off; + + if (size < (SIZE_MAX / sizeof(unsigned int))) + off = vmalloc(size * sizeof(unsigned int)); + + return off; +} +EXPORT_SYMBOL(xt_alloc_entry_offsets); + +/** + * xt_find_jump_offset - check if target is a valid jump offset + * + * @offsets: array containing all valid rule start offsets of a rule blob + * @target: the jump target to search for + * @size: entries in @offset + */ +bool xt_find_jump_offset(const unsigned int *offsets, + unsigned int target, unsigned int size) +{ + int m, low = 0, hi = size; + + while (hi > low) { + m = (low + hi) / 2u; + + if (offsets[m] > target) + hi = m; + else if (offsets[m] < target) + low = m + 1; + else + return true; + } + + return false; +} +EXPORT_SYMBOL(xt_find_jump_offset); + int xt_check_target(struct xt_tgchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { diff --git a/net/netfilter/xt_connlabel.c b/net/netfilter/xt_connlabel.c index a79af25..03d66f1 100644 --- a/net/netfilter/xt_connlabel.c +++ b/net/netfilter/xt_connlabel.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_labels.h> #include <linux/netfilter/x_tables.h> @@ -18,21 +19,12 @@ MODULE_DESCRIPTION("Xtables: add/match connection trackling labels"); MODULE_ALIAS("ipt_connlabel"); MODULE_ALIAS("ip6t_connlabel"); -static bool connlabel_match(const struct nf_conn *ct, u16 bit) -{ - struct nf_conn_labels *labels = nf_ct_labels_find(ct); - - if (!labels) - return false; - - return BIT_WORD(bit) < labels->words && test_bit(bit, labels->bits); -} - static bool connlabel_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_connlabel_mtinfo *info = par->matchinfo; enum ip_conntrack_info ctinfo; + struct nf_conn_labels *labels; struct nf_conn *ct; bool invert = info->options & XT_CONNLABEL_OP_INVERT; @@ -40,10 +32,21 @@ connlabel_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ct == NULL || nf_ct_is_untracked(ct)) return invert; - if (info->options & XT_CONNLABEL_OP_SET) - return (nf_connlabel_set(ct, info->bit) == 0) ^ invert; + labels = nf_ct_labels_find(ct); + if (!labels) + return invert; + + if (test_bit(info->bit, labels->bits)) + return !invert; + + if (info->options & XT_CONNLABEL_OP_SET) { + if (!test_and_set_bit(info->bit, labels->bits)) + nf_conntrack_event_cache(IPCT_LABEL, ct); + + return !invert; + } - return connlabel_match(ct, info->bit) ^ invert; + return invert; } static int connlabel_mt_check(const struct xt_mtchk_param *par) diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index 1caaccb..e5f1898 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -102,14 +102,14 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || info->bitmask & ~XT_PHYSDEV_OP_MASK) return -EINVAL; - if (info->bitmask & XT_PHYSDEV_OP_OUT && + if (info->bitmask & (XT_PHYSDEV_OP_OUT | XT_PHYSDEV_OP_ISOUT) && (!(info->bitmask & XT_PHYSDEV_OP_BRIDGED) || info->invert & XT_PHYSDEV_OP_BRIDGED) && par->hook_mask & ((1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_POST_ROUTING))) { - pr_info("using --physdev-out in the OUTPUT, FORWARD and " - "POSTROUTING chains for non-bridged traffic is not " - "supported anymore.\n"); + pr_info("using --physdev-out and --physdev-is-out are only" + "supported in the FORWARD and POSTROUTING chains with" + "bridged traffic.\n"); if (par->hook_mask & (1 << NF_INET_LOCAL_OUT)) return -EINVAL; } diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index dd9003f..0fd5518 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -30,6 +30,9 @@ #define DIGITAL_PROTO_ISO15693_RF_TECH NFC_PROTO_ISO15693_MASK +/* Delay between each poll frame (ms) */ +#define DIGITAL_POLL_INTERVAL 10 + struct digital_cmd { struct list_head queue; @@ -173,6 +176,8 @@ static void digital_wq_cmd(struct work_struct *work) return; } + cmd->pending = 1; + mutex_unlock(&ddev->cmd_lock); if (cmd->req) @@ -419,7 +424,8 @@ void digital_poll_next_tech(struct nfc_digital_dev *ddev) mutex_unlock(&ddev->poll_lock); - schedule_work(&ddev->poll_work); + schedule_delayed_work(&ddev->poll_work, + msecs_to_jiffies(DIGITAL_POLL_INTERVAL)); } static void digital_wq_poll(struct work_struct *work) @@ -428,7 +434,7 @@ static void digital_wq_poll(struct work_struct *work) struct digital_poll_tech *poll_tech; struct nfc_digital_dev *ddev = container_of(work, struct nfc_digital_dev, - poll_work); + poll_work.work); mutex_lock(&ddev->poll_lock); if (!ddev->poll_tech_count) { @@ -543,7 +549,7 @@ static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols, return -EINVAL; } - schedule_work(&ddev->poll_work); + schedule_delayed_work(&ddev->poll_work, 0); return 0; } @@ -564,7 +570,7 @@ static void digital_stop_poll(struct nfc_dev *nfc_dev) mutex_unlock(&ddev->poll_lock); - cancel_work_sync(&ddev->poll_work); + cancel_delayed_work_sync(&ddev->poll_work); digital_abort_cmd(ddev); } @@ -606,6 +612,8 @@ static int digital_dep_link_down(struct nfc_dev *nfc_dev) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); + digital_abort_cmd(ddev); + ddev->curr_protocol = 0; return 0; @@ -770,7 +778,7 @@ struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops, INIT_WORK(&ddev->cmd_complete_work, digital_wq_cmd_complete); mutex_init(&ddev->poll_lock); - INIT_WORK(&ddev->poll_work, digital_wq_poll); + INIT_DELAYED_WORK(&ddev->poll_work, digital_wq_poll); if (supported_protocols & NFC_PROTO_JEWEL_MASK) ddev->protocols |= NFC_PROTO_JEWEL_MASK; @@ -832,12 +840,20 @@ void nfc_digital_unregister_device(struct nfc_digital_dev *ddev) ddev->poll_tech_count = 0; mutex_unlock(&ddev->poll_lock); - cancel_work_sync(&ddev->poll_work); + cancel_delayed_work_sync(&ddev->poll_work); cancel_work_sync(&ddev->cmd_work); cancel_work_sync(&ddev->cmd_complete_work); list_for_each_entry_safe(cmd, n, &ddev->cmd_queue, queue) { list_del(&cmd->queue); + + /* Call the command callback if any and pass it a ENODEV error. + * This gives a chance to the command issuer to free any + * allocated buffer. + */ + if (cmd->cmd_cb) + cmd->cmd_cb(ddev, cmd->cb_context, ERR_PTR(-ENODEV)); + kfree(cmd->mdaa_params); kfree(cmd); } diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c index f72be74..f864ce1 100644 --- a/net/nfc/digital_dep.c +++ b/net/nfc/digital_dep.c @@ -35,6 +35,8 @@ #define DIGITAL_ATR_REQ_MIN_SIZE 16 #define DIGITAL_ATR_REQ_MAX_SIZE 64 +#define DIGITAL_ATR_RES_TO_WT(s) ((s) & 0xF) + #define DIGITAL_DID_MAX 14 #define DIGITAL_PAYLOAD_SIZE_MAX 254 @@ -63,6 +65,9 @@ #define DIGITAL_NFC_DEP_DID_BIT_SET(pfb) ((pfb) & DIGITAL_NFC_DEP_PFB_DID_BIT) #define DIGITAL_NFC_DEP_PFB_PNI(pfb) ((pfb) & 0x03) +#define DIGITAL_NFC_DEP_RTOX_VALUE(data) ((data) & 0x3F) +#define DIGITAL_NFC_DEP_RTOX_MAX 59 + #define DIGITAL_NFC_DEP_PFB_I_PDU 0x00 #define DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU 0x40 #define DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU 0x80 @@ -122,6 +127,37 @@ static const u8 digital_payload_bits_map[4] = { [3] = 254 }; +/* Response Waiting Time for ATR_RES PDU in ms + * + * RWT(ATR_RES) = RWT(nfcdep,activation) + dRWT(nfcdep) + dT(nfcdep,initiator) + * + * with: + * RWT(nfcdep,activation) = 4096 * 2^12 / f(c) s + * dRWT(nfcdep) = 16 / f(c) s + * dT(nfcdep,initiator) = 100 ms + * f(c) = 13560000 Hz + */ +#define DIGITAL_ATR_RES_RWT 1337 + +/* Response Waiting Time for other DEP PDUs in ms + * + * max_rwt = rwt + dRWT(nfcdep) + dT(nfcdep,initiator) + * + * with: + * rwt = (256 * 16 / f(c)) * 2^wt s + * dRWT(nfcdep) = 16 / f(c) s + * dT(nfcdep,initiator) = 100 ms + * f(c) = 13560000 Hz + * 0 <= wt <= 14 (given by the target by the TO field of ATR_RES response) + */ +#define DIGITAL_NFC_DEP_IN_MAX_WT 14 +#define DIGITAL_NFC_DEP_TG_MAX_WT 8 +static const u16 digital_rwt_map[DIGITAL_NFC_DEP_IN_MAX_WT + 1] = { + 100, 101, 101, 102, 105, + 110, 119, 139, 177, 255, + 409, 719, 1337, 2575, 5049, +}; + static u8 digital_payload_bits_to_size(u8 payload_bits) { if (payload_bits >= ARRAY_SIZE(digital_payload_bits_map)) @@ -190,8 +226,6 @@ digital_send_dep_data_prep(struct nfc_digital_dev *ddev, struct sk_buff *skb, return ERR_PTR(-ENOMEM); } - skb_reserve(new_skb, ddev->tx_headroom + NFC_HEADER_SIZE + - DIGITAL_NFC_DEP_REQ_RES_HEADROOM); memcpy(skb_put(new_skb, ddev->remote_payload_max), skb->data, ddev->remote_payload_max); skb_pull(skb, ddev->remote_payload_max); @@ -368,8 +402,8 @@ static int digital_in_send_psl_req(struct nfc_digital_dev *ddev, ddev->skb_add_crc(skb); - rc = digital_in_send_cmd(ddev, skb, 500, digital_in_recv_psl_res, - target); + rc = digital_in_send_cmd(ddev, skb, ddev->dep_rwt, + digital_in_recv_psl_res, target); if (rc) kfree_skb(skb); @@ -382,6 +416,7 @@ static void digital_in_recv_atr_res(struct nfc_digital_dev *ddev, void *arg, struct nfc_target *target = arg; struct digital_atr_res *atr_res; u8 gb_len, payload_bits; + u8 wt; int rc; if (IS_ERR(resp)) { @@ -411,6 +446,11 @@ static void digital_in_recv_atr_res(struct nfc_digital_dev *ddev, void *arg, atr_res = (struct digital_atr_res *)resp->data; + wt = DIGITAL_ATR_RES_TO_WT(atr_res->to); + if (wt > DIGITAL_NFC_DEP_IN_MAX_WT) + wt = DIGITAL_NFC_DEP_IN_MAX_WT; + ddev->dep_rwt = digital_rwt_map[wt]; + payload_bits = DIGITAL_PAYLOAD_PP_TO_BITS(atr_res->pp); ddev->remote_payload_max = digital_payload_bits_to_size(payload_bits); @@ -492,8 +532,8 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev, ddev->skb_add_crc(skb); - rc = digital_in_send_cmd(ddev, skb, 500, digital_in_recv_atr_res, - target); + rc = digital_in_send_cmd(ddev, skb, DIGITAL_ATR_RES_RWT, + digital_in_recv_atr_res, target); if (rc) kfree_skb(skb); @@ -524,11 +564,10 @@ static int digital_in_send_ack(struct nfc_digital_dev *ddev, ddev->skb_add_crc(skb); - ddev->saved_skb = skb_get(skb); - ddev->saved_skb_len = skb->len; + ddev->saved_skb = pskb_copy(skb, GFP_KERNEL); - rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res, - data_exch); + rc = digital_in_send_cmd(ddev, skb, ddev->dep_rwt, + digital_in_recv_dep_res, data_exch); if (rc) { kfree_skb(skb); kfree_skb(ddev->saved_skb); @@ -562,8 +601,8 @@ static int digital_in_send_nack(struct nfc_digital_dev *ddev, ddev->skb_add_crc(skb); - rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res, - data_exch); + rc = digital_in_send_cmd(ddev, skb, ddev->dep_rwt, + digital_in_recv_dep_res, data_exch); if (rc) kfree_skb(skb); @@ -593,8 +632,8 @@ static int digital_in_send_atn(struct nfc_digital_dev *ddev, ddev->skb_add_crc(skb); - rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res, - data_exch); + rc = digital_in_send_cmd(ddev, skb, ddev->dep_rwt, + digital_in_recv_dep_res, data_exch); if (rc) kfree_skb(skb); @@ -607,6 +646,11 @@ static int digital_in_send_rtox(struct nfc_digital_dev *ddev, struct digital_dep_req_res *dep_req; struct sk_buff *skb; int rc; + u16 rwt_int; + + rwt_int = ddev->dep_rwt * rtox; + if (rwt_int > digital_rwt_map[DIGITAL_NFC_DEP_IN_MAX_WT]) + rwt_int = digital_rwt_map[DIGITAL_NFC_DEP_IN_MAX_WT]; skb = digital_skb_alloc(ddev, 1); if (!skb) @@ -627,16 +671,10 @@ static int digital_in_send_rtox(struct nfc_digital_dev *ddev, ddev->skb_add_crc(skb); - ddev->saved_skb = skb_get(skb); - ddev->saved_skb_len = skb->len; - - rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res, - data_exch); - if (rc) { + rc = digital_in_send_cmd(ddev, skb, rwt_int, + digital_in_recv_dep_res, data_exch); + if (rc) kfree_skb(skb); - kfree_skb(ddev->saved_skb); - ddev->saved_skb = NULL; - } return rc; } @@ -644,11 +682,19 @@ static int digital_in_send_rtox(struct nfc_digital_dev *ddev, static int digital_in_send_saved_skb(struct nfc_digital_dev *ddev, struct digital_data_exch *data_exch) { + int rc; + + if (!ddev->saved_skb) + return -EINVAL; + skb_get(ddev->saved_skb); - skb_push(ddev->saved_skb, ddev->saved_skb_len); - return digital_in_send_cmd(ddev, ddev->saved_skb, 1500, - digital_in_recv_dep_res, data_exch); + rc = digital_in_send_cmd(ddev, ddev->saved_skb, ddev->dep_rwt, + digital_in_recv_dep_res, data_exch); + if (rc) + kfree_skb(ddev->saved_skb); + + return rc; } static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg, @@ -659,12 +705,13 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg, u8 pfb; uint size; int rc; + u8 rtox; if (IS_ERR(resp)) { rc = PTR_ERR(resp); resp = NULL; - if (((rc != -ETIMEDOUT) || ddev->nack_count) && + if ((rc == -EIO || (rc == -ETIMEDOUT && ddev->nack_count)) && (ddev->nack_count++ < DIGITAL_NFC_DEP_N_RETRY_NACK)) { ddev->atn_count = 0; @@ -783,6 +830,12 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg, break; case DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU: + if (DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) { + PROTOCOL_ERR("14.12.4.5"); + rc = -EIO; + goto exit; + } + if (DIGITAL_NFC_DEP_PFB_PNI(pfb) != ddev->curr_nfc_dep_pni) { PROTOCOL_ERR("14.12.3.3"); rc = -EIO; @@ -792,43 +845,53 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg, ddev->curr_nfc_dep_pni = DIGITAL_NFC_DEP_PFB_PNI(ddev->curr_nfc_dep_pni + 1); - if (ddev->chaining_skb && !DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) { - kfree_skb(ddev->saved_skb); - ddev->saved_skb = NULL; + if (!ddev->chaining_skb) { + PROTOCOL_ERR("14.12.4.3"); + rc = -EIO; + goto exit; + } - rc = digital_in_send_dep_req(ddev, NULL, - ddev->chaining_skb, - ddev->data_exch); - if (rc) - goto error; + /* The initiator has received a valid ACK. Free the last sent + * PDU and keep on sending chained skb. + */ + kfree_skb(ddev->saved_skb); + ddev->saved_skb = NULL; - return; - } + rc = digital_in_send_dep_req(ddev, NULL, + ddev->chaining_skb, + ddev->data_exch); + if (rc) + goto error; - pr_err("Received a ACK/NACK PDU\n"); - rc = -EINVAL; - goto exit; + goto free_resp; case DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU: if (!DIGITAL_NFC_DEP_PFB_IS_TIMEOUT(pfb)) { /* ATN */ rc = digital_in_send_saved_skb(ddev, data_exch); - if (rc) { - kfree_skb(ddev->saved_skb); + if (rc) goto error; - } - return; + goto free_resp; } - kfree_skb(ddev->saved_skb); - ddev->saved_skb = NULL; + if (ddev->atn_count || ddev->nack_count) { + PROTOCOL_ERR("14.12.4.4"); + rc = -EIO; + goto error; + } + + rtox = DIGITAL_NFC_DEP_RTOX_VALUE(resp->data[0]); + if (!rtox || rtox > DIGITAL_NFC_DEP_RTOX_MAX) { + PROTOCOL_ERR("14.8.4.1"); + rc = -EIO; + goto error; + } - rc = digital_in_send_rtox(ddev, data_exch, resp->data[0]); + rc = digital_in_send_rtox(ddev, data_exch, rtox); if (rc) goto error; - kfree_skb(resp); - return; + goto free_resp; } exit: @@ -845,6 +908,11 @@ error: if (rc) kfree_skb(resp); + + return; + +free_resp: + dev_kfree_skb(resp); } int digital_in_send_dep_req(struct nfc_digital_dev *ddev, @@ -876,11 +944,10 @@ int digital_in_send_dep_req(struct nfc_digital_dev *ddev, ddev->skb_add_crc(tmp_skb); - ddev->saved_skb = skb_get(tmp_skb); - ddev->saved_skb_len = tmp_skb->len; + ddev->saved_skb = pskb_copy(tmp_skb, GFP_KERNEL); - rc = digital_in_send_cmd(ddev, tmp_skb, 1500, digital_in_recv_dep_res, - data_exch); + rc = digital_in_send_cmd(ddev, tmp_skb, ddev->dep_rwt, + digital_in_recv_dep_res, data_exch); if (rc) { if (tmp_skb != skb) kfree_skb(tmp_skb); @@ -956,8 +1023,7 @@ static int digital_tg_send_ack(struct nfc_digital_dev *ddev, ddev->skb_add_crc(skb); - ddev->saved_skb = skb_get(skb); - ddev->saved_skb_len = skb->len; + ddev->saved_skb = pskb_copy(skb, GFP_KERNEL); rc = digital_tg_send_cmd(ddev, skb, 1500, digital_tg_recv_dep_req, data_exch); @@ -1009,11 +1075,19 @@ static int digital_tg_send_atn(struct nfc_digital_dev *ddev) static int digital_tg_send_saved_skb(struct nfc_digital_dev *ddev) { + int rc; + + if (!ddev->saved_skb) + return -EINVAL; + skb_get(ddev->saved_skb); - skb_push(ddev->saved_skb, ddev->saved_skb_len); - return digital_tg_send_cmd(ddev, ddev->saved_skb, 1500, - digital_tg_recv_dep_req, NULL); + rc = digital_tg_send_cmd(ddev, ddev->saved_skb, 1500, + digital_tg_recv_dep_req, NULL); + if (rc) + kfree_skb(ddev->saved_skb); + + return rc; } static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg, @@ -1086,22 +1160,38 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg, case DIGITAL_NFC_DEP_PFB_I_PDU: pr_debug("DIGITAL_NFC_DEP_PFB_I_PDU\n"); - if ((ddev->atn_count && (DIGITAL_NFC_DEP_PFB_PNI(pfb - 1) != - ddev->curr_nfc_dep_pni)) || - (DIGITAL_NFC_DEP_PFB_PNI(pfb) != ddev->curr_nfc_dep_pni)) { - PROTOCOL_ERR("14.12.3.4"); - rc = -EIO; - goto exit; - } - if (ddev->atn_count) { + /* The target has received (and replied to) at least one + * ATN DEP_REQ. + */ ddev->atn_count = 0; - rc = digital_tg_send_saved_skb(ddev); - if (rc) - goto exit; + /* pni of resp PDU equal to the target current pni - 1 + * means resp is the previous DEP_REQ PDU received from + * the initiator so the target replies with saved_skb + * which is the previous DEP_RES saved in + * digital_tg_send_dep_res(). + */ + if (DIGITAL_NFC_DEP_PFB_PNI(pfb) == + DIGITAL_NFC_DEP_PFB_PNI(ddev->curr_nfc_dep_pni - 1)) { + rc = digital_tg_send_saved_skb(ddev); + if (rc) + goto exit; - return; + goto free_resp; + } + + /* atn_count > 0 and PDU pni != curr_nfc_dep_pni - 1 + * means the target probably did not received the last + * DEP_REQ PDU sent by the initiator. The target + * fallbacks to normal processing then. + */ + } + + if (DIGITAL_NFC_DEP_PFB_PNI(pfb) != ddev->curr_nfc_dep_pni) { + PROTOCOL_ERR("14.12.3.4"); + rc = -EIO; + goto exit; } kfree_skb(ddev->saved_skb); @@ -1125,51 +1215,64 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg, rc = 0; break; case DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU: - if (!DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) { /* ACK */ - if ((ddev->atn_count && - (DIGITAL_NFC_DEP_PFB_PNI(pfb - 1) != - ddev->curr_nfc_dep_pni)) || - (DIGITAL_NFC_DEP_PFB_PNI(pfb) != - ddev->curr_nfc_dep_pni) || - !ddev->chaining_skb || !ddev->saved_skb) { + if (DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) { /* NACK */ + if (DIGITAL_NFC_DEP_PFB_PNI(pfb + 1) != + ddev->curr_nfc_dep_pni) { rc = -EIO; goto exit; } - if (ddev->atn_count) { - ddev->atn_count = 0; + ddev->atn_count = 0; + rc = digital_tg_send_saved_skb(ddev); + if (rc) + goto exit; + + goto free_resp; + } + + /* ACK */ + if (ddev->atn_count) { + /* The target has previously recevied one or more ATN + * PDUs. + */ + ddev->atn_count = 0; + + /* If the ACK PNI is equal to the target PNI - 1 means + * that the initiator did not receive the previous PDU + * sent by the target so re-send it. + */ + if (DIGITAL_NFC_DEP_PFB_PNI(pfb + 1) == + ddev->curr_nfc_dep_pni) { rc = digital_tg_send_saved_skb(ddev); if (rc) goto exit; - return; + goto free_resp; } - kfree_skb(ddev->saved_skb); - ddev->saved_skb = NULL; + /* Otherwise, the target did not receive the previous + * ACK PDU from the initiator. Fallback to normal + * processing of chained PDU then. + */ + } - rc = digital_tg_send_dep_res(ddev, ddev->chaining_skb); - if (rc) - goto exit; - } else { /* NACK */ - if ((DIGITAL_NFC_DEP_PFB_PNI(pfb + 1) != - ddev->curr_nfc_dep_pni) || - !ddev->saved_skb) { - rc = -EIO; - goto exit; - } + /* Keep on sending chained PDU */ + if (!ddev->chaining_skb || + DIGITAL_NFC_DEP_PFB_PNI(pfb) != + ddev->curr_nfc_dep_pni) { + rc = -EIO; + goto exit; + } - ddev->atn_count = 0; + kfree_skb(ddev->saved_skb); + ddev->saved_skb = NULL; - rc = digital_tg_send_saved_skb(ddev); - if (rc) { - kfree_skb(ddev->saved_skb); - goto exit; - } - } + rc = digital_tg_send_dep_res(ddev, ddev->chaining_skb); + if (rc) + goto exit; - return; + goto free_resp; case DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU: if (DIGITAL_NFC_DEP_PFB_IS_TIMEOUT(pfb)) { rc = -EINVAL; @@ -1182,8 +1285,7 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg, ddev->atn_count++; - kfree_skb(resp); - return; + goto free_resp; } rc = nfc_tm_data_received(ddev->nfc_dev, resp); @@ -1199,6 +1301,11 @@ exit: if (rc) kfree_skb(resp); + + return; + +free_resp: + dev_kfree_skb(resp); } int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb) @@ -1235,8 +1342,7 @@ int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb) ddev->skb_add_crc(tmp_skb); - ddev->saved_skb = skb_get(tmp_skb); - ddev->saved_skb_len = tmp_skb->len; + ddev->saved_skb = pskb_copy(tmp_skb, GFP_KERNEL); rc = digital_tg_send_cmd(ddev, tmp_skb, 1500, digital_tg_recv_dep_req, NULL); @@ -1420,7 +1526,7 @@ static int digital_tg_send_atr_res(struct nfc_digital_dev *ddev, atr_res->dir = DIGITAL_NFC_DEP_FRAME_DIR_IN; atr_res->cmd = DIGITAL_CMD_ATR_RES; memcpy(atr_res->nfcid3, atr_req->nfcid3, sizeof(atr_req->nfcid3)); - atr_res->to = 8; + atr_res->to = DIGITAL_NFC_DEP_TG_MAX_WT; ddev->local_payload_max = DIGITAL_PAYLOAD_SIZE_MAX; payload_bits = digital_payload_size_to_bits(ddev->local_payload_max); diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c index fb58ed2d..d9080de 100644 --- a/net/nfc/digital_technology.c +++ b/net/nfc/digital_technology.c @@ -1257,21 +1257,12 @@ static int digital_tg_config_nfcf(struct nfc_digital_dev *ddev, u8 rf_tech) int digital_tg_listen_nfcf(struct nfc_digital_dev *ddev, u8 rf_tech) { int rc; - u8 *nfcid2; rc = digital_tg_config_nfcf(ddev, rf_tech); if (rc) return rc; - nfcid2 = kzalloc(NFC_NFCID2_MAXSIZE, GFP_KERNEL); - if (!nfcid2) - return -ENOMEM; - - nfcid2[0] = DIGITAL_SENSF_NFCID2_NFC_DEP_B1; - nfcid2[1] = DIGITAL_SENSF_NFCID2_NFC_DEP_B2; - get_random_bytes(nfcid2 + 2, NFC_NFCID2_MAXSIZE - 2); - - return digital_tg_listen(ddev, 300, digital_tg_recv_sensf_req, nfcid2); + return digital_tg_listen(ddev, 300, digital_tg_recv_sensf_req, NULL); } void digital_tg_recv_md_req(struct nfc_digital_dev *ddev, void *arg, diff --git a/net/nfc/hci/llc.c b/net/nfc/hci/llc.c index 1399a03..3d699cb 100644 --- a/net/nfc/hci/llc.c +++ b/net/nfc/hci/llc.c @@ -133,36 +133,29 @@ void nfc_llc_free(struct nfc_llc *llc) kfree(llc); } -inline void nfc_llc_get_rx_head_tail_room(struct nfc_llc *llc, int *rx_headroom, - int *rx_tailroom) -{ - *rx_headroom = llc->rx_headroom; - *rx_tailroom = llc->rx_tailroom; -} - -inline int nfc_llc_start(struct nfc_llc *llc) +int nfc_llc_start(struct nfc_llc *llc) { return llc->ops->start(llc); } EXPORT_SYMBOL(nfc_llc_start); -inline int nfc_llc_stop(struct nfc_llc *llc) +int nfc_llc_stop(struct nfc_llc *llc) { return llc->ops->stop(llc); } EXPORT_SYMBOL(nfc_llc_stop); -inline void nfc_llc_rcv_from_drv(struct nfc_llc *llc, struct sk_buff *skb) +void nfc_llc_rcv_from_drv(struct nfc_llc *llc, struct sk_buff *skb) { llc->ops->rcv_from_drv(llc, skb); } -inline int nfc_llc_xmit_from_hci(struct nfc_llc *llc, struct sk_buff *skb) +int nfc_llc_xmit_from_hci(struct nfc_llc *llc, struct sk_buff *skb) { return llc->ops->xmit_from_hci(llc, skb); } -inline void *nfc_llc_get_data(struct nfc_llc *llc) +void *nfc_llc_get_data(struct nfc_llc *llc) { return llc->data; } diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 3425532..c5959ce 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -438,19 +438,17 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) goto error_tlv; } - if (service_name_tlv != NULL) - skb = llcp_add_tlv(skb, service_name_tlv, - service_name_tlv_length); - - skb = llcp_add_tlv(skb, miux_tlv, miux_tlv_length); - skb = llcp_add_tlv(skb, rw_tlv, rw_tlv_length); + llcp_add_tlv(skb, service_name_tlv, service_name_tlv_length); + llcp_add_tlv(skb, miux_tlv, miux_tlv_length); + llcp_add_tlv(skb, rw_tlv, rw_tlv_length); skb_queue_tail(&local->tx_queue, skb); - return 0; + err = 0; error_tlv: - pr_err("error %d\n", err); + if (err) + pr_err("error %d\n", err); kfree(service_name_tlv); kfree(miux_tlv); @@ -493,15 +491,16 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) goto error_tlv; } - skb = llcp_add_tlv(skb, miux_tlv, miux_tlv_length); - skb = llcp_add_tlv(skb, rw_tlv, rw_tlv_length); + llcp_add_tlv(skb, miux_tlv, miux_tlv_length); + llcp_add_tlv(skb, rw_tlv, rw_tlv_length); skb_queue_tail(&local->tx_queue, skb); - return 0; + err = 0; error_tlv: - pr_err("error %d\n", err); + if (err) + pr_err("error %d\n", err); kfree(miux_tlv); kfree(rw_tlv); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 9887627..e69786c 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -732,9 +732,8 @@ static void nfc_llcp_tx_work(struct work_struct *work) int ret; pr_debug("Sending pending skb\n"); - print_hex_dump(KERN_DEBUG, "LLCP Tx: ", - DUMP_PREFIX_OFFSET, 16, 1, - skb->data, skb->len, true); + print_hex_dump_debug("LLCP Tx: ", DUMP_PREFIX_OFFSET, + 16, 1, skb->data, skb->len, true); if (ptype == LLCP_PDU_DISC && sk != NULL && sk->sk_state == LLCP_DISCONNECTING) { @@ -1412,8 +1411,8 @@ static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb) pr_debug("ptype 0x%x dsap 0x%x ssap 0x%x\n", ptype, dsap, ssap); if (ptype != LLCP_PDU_SYMM) - print_hex_dump(KERN_DEBUG, "LLCP Rx: ", DUMP_PREFIX_OFFSET, - 16, 1, skb->data, skb->len, true); + print_hex_dump_debug("LLCP Rx: ", DUMP_PREFIX_OFFSET, 16, 1, + skb->data, skb->len, true); switch (ptype) { case LLCP_PDU_SYMM: diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index b4069a9..c644c78 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -135,7 +135,7 @@ static void ovs_ct_get_labels(const struct nf_conn *ct, struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL; if (cl) { - size_t len = cl->words * sizeof(long); + size_t len = sizeof(cl->bits); if (len > OVS_CT_LABELS_LEN) len = OVS_CT_LABELS_LEN; @@ -274,7 +274,7 @@ static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key, nf_ct_labels_ext_add(ct); cl = nf_ct_labels_find(ct); } - if (!cl || cl->words * sizeof(long) < OVS_CT_LABELS_LEN) + if (!cl || sizeof(cl->bits) < OVS_CT_LABELS_LEN) return -ENOSPC; err = nf_connlabels_replace(ct, (u32 *)labels, (u32 *)mask, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 9d92c4c..33a4697 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1923,13 +1923,11 @@ retry: goto out_unlock; } - sockc.tsflags = 0; + sockc.tsflags = sk->sk_tsflags; if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); - if (unlikely(err)) { - err = -EINVAL; + if (unlikely(err)) goto out_unlock; - } } skb->protocol = proto; @@ -2642,7 +2640,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); } - sockc.tsflags = 0; + sockc.tsflags = po->sk.sk_tsflags; if (msg->msg_controllen) { err = sock_cmsg_send(&po->sk, msg, &sockc); if (unlikely(err)) @@ -2845,7 +2843,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; - sockc.tsflags = 0; + sockc.tsflags = sk->sk_tsflags; sockc.mark = sk->sk_mark; if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c index 79c4abc..0a63947 100644 --- a/net/rose/rose_in.c +++ b/net/rose/rose_in.c @@ -164,7 +164,8 @@ static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int framety rose_frames_acked(sk, nr); if (ns == rose->vr) { rose_start_idletimer(sk); - if (sock_queue_rcv_skb(sk, skb) == 0) { + if (sk_filter_trim_cap(sk, skb, ROSE_MIN_LEN) == 0 && + __sock_queue_rcv_skb(sk, skb) == 0) { rose->vr = (rose->vr + 1) % ROSE_MODULUS; queued = 1; } else { diff --git a/net/sched/Kconfig b/net/sched/Kconfig index b148302..ccf931b 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -494,6 +494,16 @@ config NET_CLS_FLOWER To compile this code as a module, choose M here: the module will be called cls_flower. +config NET_CLS_MATCHALL + tristate "Match-all classifier" + select NET_CLS + ---help--- + If you say Y here, you will be able to classify packets based on + nothing. Every packet will match. + + To compile this code as a module, choose M here: the module will + be called cls_matchall. + config NET_EMATCH bool "Extended Matches" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index 84bddb3..ae088a5 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -60,6 +60,7 @@ obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o obj-$(CONFIG_NET_CLS_BPF) += cls_bpf.o obj-$(CONFIG_NET_CLS_FLOWER) += cls_flower.o +obj-$(CONFIG_NET_CLS_MATCHALL) += cls_matchall.o obj-$(CONFIG_NET_EMATCH) += ematch.o obj-$(CONFIG_NET_EMATCH_CMP) += em_cmp.o obj-$(CONFIG_NET_EMATCH_NBYTE) += em_nbyte.o diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c new file mode 100644 index 0000000..25927b6 --- /dev/null +++ b/net/sched/cls_matchall.c @@ -0,0 +1,318 @@ +/* + * net/sched/cls_matchll.c Match-all classifier + * + * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.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. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> + +#include <net/sch_generic.h> +#include <net/pkt_cls.h> + +struct cls_mall_filter { + struct tcf_exts exts; + struct tcf_result res; + u32 handle; + struct rcu_head rcu; + u32 flags; +}; + +struct cls_mall_head { + struct cls_mall_filter *filter; + struct rcu_head rcu; +}; + +static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res) +{ + struct cls_mall_head *head = rcu_dereference_bh(tp->root); + struct cls_mall_filter *f = head->filter; + + if (tc_skip_sw(f->flags)) + return -1; + + return tcf_exts_exec(skb, &f->exts, res); +} + +static int mall_init(struct tcf_proto *tp) +{ + struct cls_mall_head *head; + + head = kzalloc(sizeof(*head), GFP_KERNEL); + if (!head) + return -ENOBUFS; + + rcu_assign_pointer(tp->root, head); + + return 0; +} + +static void mall_destroy_filter(struct rcu_head *head) +{ + struct cls_mall_filter *f = container_of(head, struct cls_mall_filter, rcu); + + tcf_exts_destroy(&f->exts); + + kfree(f); +} + +static int mall_replace_hw_filter(struct tcf_proto *tp, + struct cls_mall_filter *f, + unsigned long cookie) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_to_netdev offload; + struct tc_cls_matchall_offload mall_offload = {0}; + + offload.type = TC_SETUP_MATCHALL; + offload.cls_mall = &mall_offload; + offload.cls_mall->command = TC_CLSMATCHALL_REPLACE; + offload.cls_mall->exts = &f->exts; + offload.cls_mall->cookie = cookie; + + return dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, + &offload); +} + +static void mall_destroy_hw_filter(struct tcf_proto *tp, + struct cls_mall_filter *f, + unsigned long cookie) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_to_netdev offload; + struct tc_cls_matchall_offload mall_offload = {0}; + + offload.type = TC_SETUP_MATCHALL; + offload.cls_mall = &mall_offload; + offload.cls_mall->command = TC_CLSMATCHALL_DESTROY; + offload.cls_mall->exts = NULL; + offload.cls_mall->cookie = cookie; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, + &offload); +} + +static bool mall_destroy(struct tcf_proto *tp, bool force) +{ + struct cls_mall_head *head = rtnl_dereference(tp->root); + struct net_device *dev = tp->q->dev_queue->dev; + struct cls_mall_filter *f = head->filter; + + if (!force && f) + return false; + + if (f) { + if (tc_should_offload(dev, tp, f->flags)) + mall_destroy_hw_filter(tp, f, (unsigned long) f); + + call_rcu(&f->rcu, mall_destroy_filter); + } + RCU_INIT_POINTER(tp->root, NULL); + kfree_rcu(head, rcu); + return true; +} + +static unsigned long mall_get(struct tcf_proto *tp, u32 handle) +{ + struct cls_mall_head *head = rtnl_dereference(tp->root); + struct cls_mall_filter *f = head->filter; + + if (f && f->handle == handle) + return (unsigned long) f; + return 0; +} + +static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { + [TCA_MATCHALL_UNSPEC] = { .type = NLA_UNSPEC }, + [TCA_MATCHALL_CLASSID] = { .type = NLA_U32 }, +}; + +static int mall_set_parms(struct net *net, struct tcf_proto *tp, + struct cls_mall_filter *f, + unsigned long base, struct nlattr **tb, + struct nlattr *est, bool ovr) +{ + struct tcf_exts e; + int err; + + tcf_exts_init(&e, TCA_MATCHALL_ACT, 0); + err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + if (err < 0) + return err; + + if (tb[TCA_MATCHALL_CLASSID]) { + f->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); + tcf_bind_filter(tp, &f->res, base); + } + + tcf_exts_change(tp, &f->exts, &e); + + return 0; +} + +static int mall_change(struct net *net, struct sk_buff *in_skb, + struct tcf_proto *tp, unsigned long base, + u32 handle, struct nlattr **tca, + unsigned long *arg, bool ovr) +{ + struct cls_mall_head *head = rtnl_dereference(tp->root); + struct cls_mall_filter *fold = (struct cls_mall_filter *) *arg; + struct net_device *dev = tp->q->dev_queue->dev; + struct cls_mall_filter *f; + struct nlattr *tb[TCA_MATCHALL_MAX + 1]; + u32 flags = 0; + int err; + + if (!tca[TCA_OPTIONS]) + return -EINVAL; + + if (head->filter) + return -EBUSY; + + if (fold) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_MATCHALL_MAX, + tca[TCA_OPTIONS], mall_policy); + if (err < 0) + return err; + + if (tb[TCA_MATCHALL_FLAGS]) { + flags = nla_get_u32(tb[TCA_MATCHALL_FLAGS]); + if (!tc_flags_valid(flags)) + return -EINVAL; + } + + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return -ENOBUFS; + + tcf_exts_init(&f->exts, TCA_MATCHALL_ACT, 0); + + if (!handle) + handle = 1; + f->handle = handle; + f->flags = flags; + + err = mall_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr); + if (err) + goto errout; + + if (tc_should_offload(dev, tp, flags)) { + err = mall_replace_hw_filter(tp, f, (unsigned long) f); + if (err) { + if (tc_skip_sw(flags)) + goto errout; + else + err = 0; + } + } + + *arg = (unsigned long) f; + rcu_assign_pointer(head->filter, f); + + return 0; + +errout: + kfree(f); + return err; +} + +static int mall_delete(struct tcf_proto *tp, unsigned long arg) +{ + struct cls_mall_head *head = rtnl_dereference(tp->root); + struct cls_mall_filter *f = (struct cls_mall_filter *) arg; + struct net_device *dev = tp->q->dev_queue->dev; + + if (tc_should_offload(dev, tp, f->flags)) + mall_destroy_hw_filter(tp, f, (unsigned long) f); + + RCU_INIT_POINTER(head->filter, NULL); + tcf_unbind_filter(tp, &f->res); + call_rcu(&f->rcu, mall_destroy_filter); + return 0; +} + +static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg) +{ + struct cls_mall_head *head = rtnl_dereference(tp->root); + struct cls_mall_filter *f = head->filter; + + if (arg->count < arg->skip) + goto skip; + if (arg->fn(tp, (unsigned long) f, arg) < 0) + arg->stop = 1; +skip: + arg->count++; +} + +static int mall_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, + struct sk_buff *skb, struct tcmsg *t) +{ + struct cls_mall_filter *f = (struct cls_mall_filter *) fh; + struct nlattr *nest; + + if (!f) + return skb->len; + + t->tcm_handle = f->handle; + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + if (f->res.classid && + nla_put_u32(skb, TCA_MATCHALL_CLASSID, f->res.classid)) + goto nla_put_failure; + + if (tcf_exts_dump(skb, &f->exts)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + + if (tcf_exts_dump_stats(skb, &f->exts) < 0) + goto nla_put_failure; + + return skb->len; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static struct tcf_proto_ops cls_mall_ops __read_mostly = { + .kind = "matchall", + .classify = mall_classify, + .init = mall_init, + .destroy = mall_destroy, + .get = mall_get, + .change = mall_change, + .delete = mall_delete, + .walk = mall_walk, + .dump = mall_dump, + .owner = THIS_MODULE, +}; + +static int __init cls_mall_init(void) +{ + return register_tcf_proto_ops(&cls_mall_ops); +} + +static void __exit cls_mall_exit(void) +{ + unregister_tcf_proto_ops(&cls_mall_ops); +} + +module_init(cls_mall_init); +module_exit(cls_mall_exit); + +MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>"); +MODULE_DESCRIPTION("Match-all classifier"); +MODULE_LICENSE("GPL v2"); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 91982d9..53dbfa1 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1122,8 +1122,10 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) qlen = cl->un.leaf.q->q.qlen; qs.backlog = cl->un.leaf.q->qstats.backlog; } - cl->xstats.tokens = PSCHED_NS2TICKS(cl->tokens); - cl->xstats.ctokens = PSCHED_NS2TICKS(cl->ctokens); + cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens), + INT_MIN, INT_MAX); + cl->xstats.ctokens = clamp_t(s64, PSCHED_NS2TICKS(cl->ctokens), + INT_MIN, INT_MAX); if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index ae6f1a2..f473779 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -560,6 +560,7 @@ static int sctp_v6_is_any(const union sctp_addr *addr) static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) { int type; + struct net *net = sock_net(&sp->inet.sk); const struct in6_addr *in6 = (const struct in6_addr *)&addr->v6.sin6_addr; type = ipv6_addr_type(in6); @@ -574,7 +575,8 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) if (!(type & IPV6_ADDR_UNICAST)) return 0; - return ipv6_chk_addr(sock_net(&sp->inet.sk), in6, NULL, 0); + return sp->inet.freebind || net->ipv6.sysctl.ip_nonlocal_bind || + ipv6_chk_addr(net, in6, NULL, 0); } /* This function checks if the address is a valid address to be used for @@ -954,7 +956,7 @@ static const struct proto_ops inet6_seqpacket_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 1adb927..7b523e3 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1028,7 +1028,7 @@ static const struct proto_ops inet_seqpacket_ops = { .setsockopt = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */ .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 8584cc4..4131d5a 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -335,6 +335,21 @@ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b) return 0; } +/* tipc_bearer_reset_all - reset all links on all bearers + */ +void tipc_bearer_reset_all(struct net *net) +{ + struct tipc_net *tn = tipc_net(net); + struct tipc_bearer *b; + int i; + + for (i = 0; i < MAX_BEARERS; i++) { + b = rcu_dereference_rtnl(tn->bearer_list[i]); + if (b) + tipc_reset_bearer(net, b); + } +} + /** * bearer_disable * diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 0d337c7..f1e6db5 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -198,6 +198,7 @@ void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest); void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest); struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name); struct tipc_media *tipc_media_find(const char *name); +void tipc_bearer_reset_all(struct net *net); int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); diff --git a/net/tipc/link.c b/net/tipc/link.c index c1df33f..877d94f 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -350,6 +350,8 @@ void tipc_link_remove_bc_peer(struct tipc_link *snd_l, u16 ack = snd_l->snd_nxt - 1; snd_l->ackers--; + rcv_l->bc_peer_is_up = true; + rcv_l->state = LINK_ESTABLISHED; tipc_link_bc_ack_rcv(rcv_l, ack, xmitq); tipc_link_reset(rcv_l); rcv_l->state = LINK_RESET; @@ -1582,7 +1584,12 @@ void tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, if (!msg_peer_node_is_up(hdr)) return; - l->bc_peer_is_up = true; + /* Open when peer ackowledges our bcast init msg (pkt #1) */ + if (msg_ack(hdr)) + l->bc_peer_is_up = true; + + if (!l->bc_peer_is_up) + return; /* Ignore if peers_snd_nxt goes beyond receive window */ if (more(peers_snd_nxt, l->rcv_nxt + l->window)) diff --git a/net/tipc/node.c b/net/tipc/node.c index a3fc0a3..95cc78b 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1297,10 +1297,6 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id rc = tipc_bcast_rcv(net, be->link, skb); - /* Broadcast link reset may happen at reassembly failure */ - if (rc & TIPC_LINK_DOWN_EVT) - tipc_node_reset_links(n); - /* Broadcast ACKs are sent on a unicast link */ if (rc & TIPC_LINK_SND_BC_ACK) { tipc_node_read_lock(n); @@ -1320,6 +1316,17 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id spin_unlock_bh(&be->inputq2.lock); tipc_sk_mcast_rcv(net, &be->arrvq, &be->inputq2); } + + if (rc & TIPC_LINK_DOWN_EVT) { + /* Reception reassembly failure => reset all links to peer */ + if (!tipc_link_is_up(be->link)) + tipc_node_reset_links(n); + + /* Retransmission failure => reset all links to all peers */ + if (!tipc_link_is_up(tipc_bc_sndlink(net))) + tipc_bearer_reset_all(net); + } + tipc_node_put(n); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5782f71..46417f9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3568,16 +3568,16 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) params.smps_mode = NL80211_SMPS_OFF; } + params.pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]); + if (params.pbss && !rdev->wiphy.bands[NL80211_BAND_60GHZ]) + return -EOPNOTSUPP; + if (info->attrs[NL80211_ATTR_ACL_POLICY]) { params.acl = parse_acl_data(&rdev->wiphy, info); if (IS_ERR(params.acl)) return PTR_ERR(params.acl); } - params.pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]); - if (params.pbss && !rdev->wiphy.bands[NL80211_BAND_60GHZ]) - return -EOPNOTSUPP; - wdev_lock(wdev); err = rdev_start_ap(rdev, dev, ¶ms); if (!err) { diff --git a/net/wireless/util.c b/net/wireless/util.c index 2443ee3..b7d1592 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -721,6 +721,8 @@ __ieee80211_amsdu_copy(struct sk_buff *skb, unsigned int hlen, * alignment since sizeof(struct ethhdr) is 14. */ frame = dev_alloc_skb(hlen + sizeof(struct ethhdr) + 2 + cur_len); + if (!frame) + return NULL; skb_reserve(frame, hlen + sizeof(struct ethhdr) + 2); skb_copy_bits(skb, offset, skb_put(frame, cur_len), cur_len); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index a98b780..d2d2b35 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -21,6 +21,8 @@ hostprogs-y += spintest hostprogs-y += map_perf_test hostprogs-y += test_overhead hostprogs-y += test_cgrp2_array_pin +hostprogs-y += xdp1 +hostprogs-y += xdp2 test_verifier-objs := test_verifier.o libbpf.o test_maps-objs := test_maps.o libbpf.o @@ -42,6 +44,9 @@ spintest-objs := bpf_load.o libbpf.o spintest_user.o map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o +xdp1-objs := bpf_load.o libbpf.o xdp1_user.o +# reuse xdp1 source intentionally +xdp2-objs := bpf_load.o libbpf.o xdp1_user.o # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -64,6 +69,8 @@ always += test_overhead_tp_kern.o always += test_overhead_kprobe_kern.o always += parse_varlen.o parse_simple.o parse_ldabs.o always += test_cgrp2_tc_kern.o +always += xdp1_kern.o +always += xdp2_kern.o HOSTCFLAGS += -I$(objtree)/usr/include @@ -84,6 +91,8 @@ HOSTLOADLIBES_offwaketime += -lelf HOSTLOADLIBES_spintest += -lelf HOSTLOADLIBES_map_perf_test += -lelf -lrt HOSTLOADLIBES_test_overhead += -lelf -lrt +HOSTLOADLIBES_xdp1 += -lelf +HOSTLOADLIBES_xdp2 += -lelf # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: # make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 022af71..0cfda23 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -50,6 +50,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) bool is_kprobe = strncmp(event, "kprobe/", 7) == 0; bool is_kretprobe = strncmp(event, "kretprobe/", 10) == 0; bool is_tracepoint = strncmp(event, "tracepoint/", 11) == 0; + bool is_xdp = strncmp(event, "xdp", 3) == 0; enum bpf_prog_type prog_type; char buf[256]; int fd, efd, err, id; @@ -66,6 +67,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) prog_type = BPF_PROG_TYPE_KPROBE; } else if (is_tracepoint) { prog_type = BPF_PROG_TYPE_TRACEPOINT; + } else if (is_xdp) { + prog_type = BPF_PROG_TYPE_XDP; } else { printf("Unknown event '%s'\n", event); return -1; @@ -79,6 +82,9 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) prog_fd[prog_cnt++] = fd; + if (is_xdp) + return 0; + if (is_socket) { event += 6; if (*event != '/') @@ -319,6 +325,7 @@ int load_bpf_file(char *path) if (memcmp(shname_prog, "kprobe/", 7) == 0 || memcmp(shname_prog, "kretprobe/", 10) == 0 || memcmp(shname_prog, "tracepoint/", 11) == 0 || + memcmp(shname_prog, "xdp", 3) == 0 || memcmp(shname_prog, "socket", 6) == 0) load_and_attach(shname_prog, insns, data_prog->d_size); } @@ -336,6 +343,7 @@ int load_bpf_file(char *path) if (memcmp(shname, "kprobe/", 7) == 0 || memcmp(shname, "kretprobe/", 10) == 0 || memcmp(shname, "tracepoint/", 11) == 0 || + memcmp(shname, "xdp", 3) == 0 || memcmp(shname, "socket", 6) == 0) load_and_attach(shname, data->d_buf, data->d_size); } diff --git a/samples/bpf/xdp1_kern.c b/samples/bpf/xdp1_kern.c new file mode 100644 index 0000000..2197421 --- /dev/null +++ b/samples/bpf/xdp1_kern.c @@ -0,0 +1,93 @@ +/* Copyright (c) 2016 PLUMgrid + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") rxcnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = 256, +}; + +static int parse_ipv4(void *data, u64 nh_off, void *data_end) +{ + struct iphdr *iph = data + nh_off; + + if (iph + 1 > data_end) + return 0; + return iph->protocol; +} + +static int parse_ipv6(void *data, u64 nh_off, void *data_end) +{ + struct ipv6hdr *ip6h = data + nh_off; + + if (ip6h + 1 > data_end) + return 0; + return ip6h->nexthdr; +} + +SEC("xdp1") +int xdp_prog1(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + int rc = XDP_DROP; + long *value; + u16 h_proto; + u64 nh_off; + u32 ipproto; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return rc; + + h_proto = eth->h_proto; + + if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return rc; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return rc; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + + if (h_proto == htons(ETH_P_IP)) + ipproto = parse_ipv4(data, nh_off, data_end); + else if (h_proto == htons(ETH_P_IPV6)) + ipproto = parse_ipv6(data, nh_off, data_end); + else + ipproto = 0; + + value = bpf_map_lookup_elem(&rxcnt, &ipproto); + if (value) + *value += 1; + + return rc; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c new file mode 100644 index 0000000..a5e109e --- /dev/null +++ b/samples/bpf/xdp1_user.c @@ -0,0 +1,181 @@ +/* Copyright (c) 2016 PLUMgrid + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <assert.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <unistd.h> +#include "bpf_load.h" +#include "libbpf.h" + +static int set_link_xdp_fd(int ifindex, int fd) +{ + struct sockaddr_nl sa; + int sock, seq = 0, len, ret = -1; + char buf[4096]; + struct nlattr *nla, *nla_xdp; + struct { + struct nlmsghdr nh; + struct ifinfomsg ifinfo; + char attrbuf[64]; + } req; + struct nlmsghdr *nh; + struct nlmsgerr *err; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) { + printf("open netlink socket: %s\n", strerror(errno)); + return -1; + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + printf("bind to netlink: %s\n", strerror(errno)); + goto cleanup; + } + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_SETLINK; + req.nh.nlmsg_pid = 0; + req.nh.nlmsg_seq = ++seq; + req.ifinfo.ifi_family = AF_UNSPEC; + req.ifinfo.ifi_index = ifindex; + nla = (struct nlattr *)(((char *)&req) + + NLMSG_ALIGN(req.nh.nlmsg_len)); + nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/; + + nla_xdp = (struct nlattr *)((char *)nla + NLA_HDRLEN); + nla_xdp->nla_type = 1/*IFLA_XDP_FD*/; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); + memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); + nla->nla_len = NLA_HDRLEN + nla_xdp->nla_len; + + req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); + + if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { + printf("send to netlink: %s\n", strerror(errno)); + goto cleanup; + } + + len = recv(sock, buf, sizeof(buf), 0); + if (len < 0) { + printf("recv from netlink: %s\n", strerror(errno)); + goto cleanup; + } + + for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_pid != getpid()) { + printf("Wrong pid %d, expected %d\n", + nh->nlmsg_pid, getpid()); + goto cleanup; + } + if (nh->nlmsg_seq != seq) { + printf("Wrong seq %d, expected %d\n", + nh->nlmsg_seq, seq); + goto cleanup; + } + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + printf("nlmsg error %s\n", strerror(-err->error)); + goto cleanup; + case NLMSG_DONE: + break; + } + } + + ret = 0; + +cleanup: + close(sock); + return ret; +} + +static int ifindex; + +static void int_exit(int sig) +{ + set_link_xdp_fd(ifindex, -1); + exit(0); +} + +/* simple per-protocol drop counter + */ +static void poll_stats(int interval) +{ + unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + const unsigned int nr_keys = 256; + __u64 values[nr_cpus], prev[nr_keys][nr_cpus]; + __u32 key; + int i; + + memset(prev, 0, sizeof(prev)); + + while (1) { + sleep(interval); + + for (key = 0; key < nr_keys; key++) { + __u64 sum = 0; + + assert(bpf_lookup_elem(map_fd[0], &key, values) == 0); + for (i = 0; i < nr_cpus; i++) + sum += (values[i] - prev[key][i]); + if (sum) + printf("proto %u: %10llu pkt/s\n", + key, sum / interval); + memcpy(prev[key], values, sizeof(values)); + } + } +} + +int main(int ac, char **argv) +{ + char filename[256]; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + if (ac != 2) { + printf("usage: %s IFINDEX\n", argv[0]); + return 1; + } + + ifindex = strtoul(argv[1], NULL, 0); + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + if (!prog_fd[0]) { + printf("load_bpf_file: %s\n", strerror(errno)); + return 1; + } + + signal(SIGINT, int_exit); + + if (set_link_xdp_fd(ifindex, prog_fd[0]) < 0) { + printf("link set xdp fd failed\n"); + return 1; + } + + poll_stats(2); + + return 0; +} diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c new file mode 100644 index 0000000..e012888 --- /dev/null +++ b/samples/bpf/xdp2_kern.c @@ -0,0 +1,114 @@ +/* Copyright (c) 2016 PLUMgrid + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") rxcnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = 256, +}; + +static void swap_src_dst_mac(void *data) +{ + unsigned short *p = data; + unsigned short dst[3]; + + dst[0] = p[0]; + dst[1] = p[1]; + dst[2] = p[2]; + p[0] = p[3]; + p[1] = p[4]; + p[2] = p[5]; + p[3] = dst[0]; + p[4] = dst[1]; + p[5] = dst[2]; +} + +static int parse_ipv4(void *data, u64 nh_off, void *data_end) +{ + struct iphdr *iph = data + nh_off; + + if (iph + 1 > data_end) + return 0; + return iph->protocol; +} + +static int parse_ipv6(void *data, u64 nh_off, void *data_end) +{ + struct ipv6hdr *ip6h = data + nh_off; + + if (ip6h + 1 > data_end) + return 0; + return ip6h->nexthdr; +} + +SEC("xdp1") +int xdp_prog1(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + int rc = XDP_DROP; + long *value; + u16 h_proto; + u64 nh_off; + u32 ipproto; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return rc; + + h_proto = eth->h_proto; + + if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return rc; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return rc; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + + if (h_proto == htons(ETH_P_IP)) + ipproto = parse_ipv4(data, nh_off, data_end); + else if (h_proto == htons(ETH_P_IPV6)) + ipproto = parse_ipv6(data, nh_off, data_end); + else + ipproto = 0; + + value = bpf_map_lookup_elem(&rxcnt, &ipproto); + if (value) + *value += 1; + + if (ipproto == IPPROTO_UDP) { + swap_src_dst_mac(data); + rc = XDP_TX; + } + + return rc; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/pktgen/parameters.sh b/samples/pktgen/parameters.sh index 33b70fd..f70ea7d 100644 --- a/samples/pktgen/parameters.sh +++ b/samples/pktgen/parameters.sh @@ -14,12 +14,13 @@ function usage() { echo " -b : (\$BURST) HW level bursting of SKBs" echo " -v : (\$VERBOSE) verbose" echo " -x : (\$DEBUG) debug" + echo " -6 : (\$IP6) IPv6" echo "" } ## --- Parse command line arguments / parameters --- ## echo "Commandline options:" -while getopts "s:i:d:m:t:c:b:vxh" option; do +while getopts "s:i:d:m:t:c:b:vxh6" option; do case $option in i) # interface export DEV=$OPTARG @@ -59,6 +60,10 @@ while getopts "s:i:d:m:t:c:b:vxh" option; do export DEBUG=yes info "Debug mode: DEBUG=$DEBUG" ;; + 6) + export IP6=6 + info "IP6: IP6=$IP6" + ;; h|?|*) usage; err 2 "[ERROR] Unknown parameters!!!" diff --git a/samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh b/samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh index cb15903..f3e1bedf 100755 --- a/samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh +++ b/samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh @@ -34,7 +34,9 @@ root_check_run_with_sudo "$@" source ${basedir}/parameters.sh # Using invalid DST_MAC will cause the packets to get dropped in # ip_rcv() which is part of the test -[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42" +if [ -z "$DEST_IP" ]; then + [ -z "$IP6" ] && DEST_IP="198.18.0.42" || DEST_IP="FD00::1" +fi [ -z "$DST_MAC" ] && DST_MAC="90:e2:ba:ff:ff:ff" [ -z "$BURST" ] && BURST=1024 @@ -64,7 +66,7 @@ for ((thread = 0; thread < $THREADS; thread++)); do # Destination pg_set $dev "dst_mac $DST_MAC" - pg_set $dev "dst $DEST_IP" + pg_set $dev "dst$IP6 $DEST_IP" # Inject packet into RX path of stack pg_set $dev "xmit_mode netif_receive" diff --git a/samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh b/samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh index 4e4e92b..cc102e9 100755 --- a/samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh +++ b/samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh @@ -13,7 +13,9 @@ root_check_run_with_sudo "$@" # Parameter parsing via include source ${basedir}/parameters.sh -[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42" +if [ -z "$DEST_IP" ]; then + [ -z "$IP6" ] && DEST_IP="198.18.0.42" || DEST_IP="FD00::1" +fi [ -z "$DST_MAC" ] && DST_MAC="90:e2:ba:ff:ff:ff" # Burst greater than 1 are invalid for queue_xmit mode @@ -47,7 +49,7 @@ for ((thread = 0; thread < $THREADS; thread++)); do # Destination pg_set $dev "dst_mac $DST_MAC" - pg_set $dev "dst $DEST_IP" + pg_set $dev "dst$IP6 $DEST_IP" # Inject packet into TX qdisc egress path of stack pg_set $dev "xmit_mode queue_xmit" diff --git a/samples/pktgen/pktgen_sample01_simple.sh b/samples/pktgen/pktgen_sample01_simple.sh index 8c9d318..29ef4ba 100755 --- a/samples/pktgen/pktgen_sample01_simple.sh +++ b/samples/pktgen/pktgen_sample01_simple.sh @@ -14,7 +14,9 @@ root_check_run_with_sudo "$@" source ${basedir}/parameters.sh # # Set some default params, if they didn't get set -[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42" +if [ -z "$DEST_IP" ]; then + [ -z "$IP6" ] && DEST_IP="198.18.0.42" || DEST_IP="FD00::1" +fi [ -z "$CLONE_SKB" ] && CLONE_SKB="0" # Example enforce param "-m" for dst_mac [ -z "$DST_MAC" ] && usage && err 2 "Must specify -m dst_mac" @@ -54,7 +56,7 @@ pg_set $DEV "flag NO_TIMESTAMP" # Destination pg_set $DEV "dst_mac $DST_MAC" -pg_set $DEV "dst $DEST_IP" +pg_set $DEV "dst$IP6 $DEST_IP" # Setup random UDP port src range pg_set $DEV "flag UDPSRC_RND" diff --git a/samples/pktgen/pktgen_sample02_multiqueue.sh b/samples/pktgen/pktgen_sample02_multiqueue.sh index 32467ae..c88a161 100755 --- a/samples/pktgen/pktgen_sample02_multiqueue.sh +++ b/samples/pktgen/pktgen_sample02_multiqueue.sh @@ -23,7 +23,9 @@ UDP_MIN=9 UDP_MAX=109 # (example of setting default params in your script) -[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42" +if [ -z "$DEST_IP" ]; then + [ -z "$IP6" ] && DEST_IP="198.18.0.42" || DEST_IP="FD00::1" +fi [ -z "$DST_MAC" ] && DST_MAC="90:e2:ba:ff:ff:ff" # General cleanup everything since last run @@ -54,7 +56,7 @@ for ((thread = 0; thread < $THREADS; thread++)); do # Destination pg_set $dev "dst_mac $DST_MAC" - pg_set $dev "dst $DEST_IP" + pg_set $dev "dst$IP6 $DEST_IP" # Setup random UDP port src range pg_set $dev "flag UDPSRC_RND" diff --git a/samples/pktgen/pktgen_sample03_burst_single_flow.sh b/samples/pktgen/pktgen_sample03_burst_single_flow.sh index 775f5d0..80cf8f5 100755 --- a/samples/pktgen/pktgen_sample03_burst_single_flow.sh +++ b/samples/pktgen/pktgen_sample03_burst_single_flow.sh @@ -25,7 +25,9 @@ root_check_run_with_sudo "$@" # Parameter parsing via include source ${basedir}/parameters.sh # Set some default params, if they didn't get set -[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42" +if [ -z "$DEST_IP" ]; then + [ -z "$IP6" ] && DEST_IP="198.18.0.42" || DEST_IP="FD00::1" +fi [ -z "$DST_MAC" ] && DST_MAC="90:e2:ba:ff:ff:ff" [ -z "$BURST" ] && BURST=32 [ -z "$CLONE_SKB" ] && CLONE_SKB="100000" @@ -55,7 +57,7 @@ for ((thread = 0; thread < $THREADS; thread++)); do # Destination pg_set $dev "dst_mac $DST_MAC" - pg_set $dev "dst $DEST_IP" + pg_set $dev "dst$IP6 $DEST_IP" # Setup burst, for easy testing -b 0 disable bursting # (internally in pktgen default and minimum burst=1) diff --git a/scripts/gdb/linux/.gitignore b/scripts/gdb/linux/.gitignore index 52e4e61..2573543 100644 --- a/scripts/gdb/linux/.gitignore +++ b/scripts/gdb/linux/.gitignore @@ -1,2 +1,3 @@ *.pyc *.pyo +constants.py diff --git a/scripts/gdb/linux/Makefile b/scripts/gdb/linux/Makefile index cd129e6..8b00031 100644 --- a/scripts/gdb/linux/Makefile +++ b/scripts/gdb/linux/Makefile @@ -13,9 +13,11 @@ quiet_cmd_gen_constants_py = GEN $@ $(CPP) -E -x c -P $(c_flags) $< > $@ ;\ sed -i '1,/<!-- end-c-headers -->/d;' $@ -$(obj)/constants.py: $(SRCTREE)/$(obj)/constants.py.in - $(call if_changed,gen_constants_py) +targets += constants.py +$(obj)/constants.py: $(SRCTREE)/$(obj)/constants.py.in FORCE + $(call if_changed_dep,gen_constants_py) build_constants_py: $(obj)/constants.py + @: clean-files := *.pyc *.pyo $(if $(KBUILD_SRC),*.py) $(obj)/constants.py diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index 07e6c2b..7986f4e 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -14,7 +14,6 @@ #include <linux/fs.h> #include <linux/mount.h> -#include <linux/radix-tree.h> /* We need to stringify expanded macros so that they can be parsed */ @@ -51,9 +50,3 @@ LX_VALUE(MNT_NOEXEC) LX_VALUE(MNT_NOATIME) LX_VALUE(MNT_NODIRATIME) LX_VALUE(MNT_RELATIME) - -/* linux/radix-tree.h */ -LX_VALUE(RADIX_TREE_INDIRECT_PTR) -LX_GDBPARSED(RADIX_TREE_HEIGHT_MASK) -LX_GDBPARSED(RADIX_TREE_MAP_SHIFT) -LX_GDBPARSED(RADIX_TREE_MAP_MASK) diff --git a/scripts/gdb/linux/radixtree.py b/scripts/gdb/linux/radixtree.py deleted file mode 100644 index 0fdef4e..0000000 --- a/scripts/gdb/linux/radixtree.py +++ /dev/null @@ -1,97 +0,0 @@ -# -# gdb helper commands and functions for Linux kernel debugging -# -# Radix Tree Parser -# -# Copyright (c) 2016 Linaro Ltd -# -# Authors: -# Kieran Bingham <kieran.bingham@linaro.org> -# -# This work is licensed under the terms of the GNU GPL version 2. -# - -import gdb - -from linux import utils -from linux import constants - -radix_tree_root_type = utils.CachedType("struct radix_tree_root") -radix_tree_node_type = utils.CachedType("struct radix_tree_node") - - -def is_indirect_ptr(node): - long_type = utils.get_long_type() - return (node.cast(long_type) & constants.LX_RADIX_TREE_INDIRECT_PTR) - - -def indirect_to_ptr(node): - long_type = utils.get_long_type() - node_type = node.type - indirect_ptr = node.cast(long_type) & ~constants.LX_RADIX_TREE_INDIRECT_PTR - return indirect_ptr.cast(node_type) - - -def maxindex(height): - height = height & constants.LX_RADIX_TREE_HEIGHT_MASK - return gdb.parse_and_eval("height_to_maxindex["+str(height)+"]") - - -def lookup(root, index): - if root.type == radix_tree_root_type.get_type().pointer(): - root = root.dereference() - elif root.type != radix_tree_root_type.get_type(): - raise gdb.GdbError("Must be struct radix_tree_root not {}" - .format(root.type)) - - node = root['rnode'] - if node is 0: - return None - - if not (is_indirect_ptr(node)): - if (index > 0): - return None - return node - - node = indirect_to_ptr(node) - - height = node['path'] & constants.LX_RADIX_TREE_HEIGHT_MASK - if (index > maxindex(height)): - return None - - shift = (height-1) * constants.LX_RADIX_TREE_MAP_SHIFT - - while True: - new_index = (index >> shift) & constants.LX_RADIX_TREE_MAP_MASK - slot = node['slots'][new_index] - - node = slot.cast(node.type.pointer()).dereference() - if node is 0: - return None - - shift -= constants.LX_RADIX_TREE_MAP_SHIFT - height -= 1 - - if (height <= 0): - break - - return node - - -class LxRadixTree(gdb.Function): - """ Lookup and return a node from a RadixTree. - -$lx_radix_tree_lookup(root_node [, index]): Return the node at the given index. -If index is omitted, the root node is dereferenced and returned.""" - - def __init__(self): - super(LxRadixTree, self).__init__("lx_radix_tree_lookup") - - def invoke(self, root, index=0): - result = lookup(root, index) - if result is None: - raise gdb.GdbError("No entry in tree at index {}".format(index)) - - return result - -LxRadixTree() diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index 9a0f892..004b0ac 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -153,7 +153,7 @@ lx-symbols command.""" saved_state['breakpoint'].enabled = saved_state['enabled'] def invoke(self, arg, from_tty): - self.module_paths = arg.split() + self.module_paths = [os.path.expanduser(p) for p in arg.split()] self.module_paths.append(os.getcwd()) # enforce update diff --git a/scripts/gdb/vmlinux-gdb.py b/scripts/gdb/vmlinux-gdb.py index 3a80ad6..6e0b0af 100644 --- a/scripts/gdb/vmlinux-gdb.py +++ b/scripts/gdb/vmlinux-gdb.py @@ -31,4 +31,3 @@ else: import linux.lists import linux.proc import linux.constants - import linux.radixtree diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 2660fbc..7798e16 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -500,34 +500,34 @@ static int apparmor_setprocattr(struct task_struct *task, char *name, { struct common_audit_data sa; struct apparmor_audit_data aad = {0,}; - char *command, *args = value; + char *command, *largs = NULL, *args = value; size_t arg_size; int error; if (size == 0) return -EINVAL; - /* args points to a PAGE_SIZE buffer, AppArmor requires that - * the buffer must be null terminated or have size <= PAGE_SIZE -1 - * so that AppArmor can null terminate them - */ - if (args[size - 1] != '\0') { - if (size == PAGE_SIZE) - return -EINVAL; - args[size] = '\0'; - } - /* task can only write its own attributes */ if (current != task) return -EACCES; - args = value; + /* AppArmor requires that the buffer must be null terminated atm */ + if (args[size - 1] != '\0') { + /* null terminate */ + largs = args = kmalloc(size + 1, GFP_KERNEL); + if (!args) + return -ENOMEM; + memcpy(args, value, size); + args[size] = '\0'; + } + + error = -EINVAL; args = strim(args); command = strsep(&args, " "); if (!args) - return -EINVAL; + goto out; args = skip_spaces(args); if (!*args) - return -EINVAL; + goto out; arg_size = size - (args - (char *) value); if (strcmp(name, "current") == 0) { @@ -553,10 +553,12 @@ static int apparmor_setprocattr(struct task_struct *task, char *name, goto fail; } else /* only support the "current" and "exec" process attributes */ - return -EINVAL; + goto fail; if (!error) error = size; +out: + kfree(largs); return error; fail: @@ -565,9 +567,9 @@ fail: aad.profile = aa_current_profile(); aad.op = OP_SETPROCATTR; aad.info = name; - aad.error = -EINVAL; + aad.error = error = -EINVAL; aa_audit_msg(AUDIT_APPARMOR_DENIED, &sa, NULL); - return -EINVAL; + goto out; } static int apparmor_task_setrlimit(struct task_struct *task, diff --git a/sound/core/control.c b/sound/core/control.c index a85d455..b4fe9b0 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -160,6 +160,8 @@ void snd_ctl_notify(struct snd_card *card, unsigned int mask, if (snd_BUG_ON(!card || !id)) return; + if (card->shutdown) + return; read_lock(&card->ctl_files_rwlock); #if IS_ENABLED(CONFIG_SND_MIXER_OSS) card->mixer_oss_change_count++; diff --git a/sound/core/pcm.c b/sound/core/pcm.c index 308c9ec..8e980aa 100644 --- a/sound/core/pcm.c +++ b/sound/core/pcm.c @@ -849,6 +849,14 @@ int snd_pcm_new_internal(struct snd_card *card, const char *id, int device, } EXPORT_SYMBOL(snd_pcm_new_internal); +static void free_chmap(struct snd_pcm_str *pstr) +{ + if (pstr->chmap_kctl) { + snd_ctl_remove(pstr->pcm->card, pstr->chmap_kctl); + pstr->chmap_kctl = NULL; + } +} + static void snd_pcm_free_stream(struct snd_pcm_str * pstr) { struct snd_pcm_substream *substream, *substream_next; @@ -871,6 +879,7 @@ static void snd_pcm_free_stream(struct snd_pcm_str * pstr) kfree(setup); } #endif + free_chmap(pstr); if (pstr->substream_count) put_device(&pstr->dev); } @@ -1135,10 +1144,7 @@ static int snd_pcm_dev_disconnect(struct snd_device *device) for (cidx = 0; cidx < 2; cidx++) { if (!pcm->internal) snd_unregister_device(&pcm->streams[cidx].dev); - if (pcm->streams[cidx].chmap_kctl) { - snd_ctl_remove(pcm->card, pcm->streams[cidx].chmap_kctl); - pcm->streams[cidx].chmap_kctl = NULL; - } + free_chmap(&pcm->streams[cidx]); } mutex_unlock(&pcm->open_mutex); mutex_unlock(®ister_mutex); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e320c44..6f8ea13 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -1218,8 +1218,10 @@ static int azx_free(struct azx *chip) if (use_vga_switcheroo(hda)) { if (chip->disabled && hda->probe_continued) snd_hda_unlock_devices(&chip->bus); - if (hda->vga_switcheroo_registered) + if (hda->vga_switcheroo_registered) { vga_switcheroo_unregister_client(chip->pci); + vga_switcheroo_fini_domain_pm_ops(chip->card->dev); + } } if (bus->chip_init) { @@ -2267,6 +2269,8 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, { PCI_DEVICE(0x1002, 0x157a), .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, + { PCI_DEVICE(0x1002, 0x15b3), + .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, { PCI_DEVICE(0x1002, 0x793b), .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI }, { PCI_DEVICE(0x1002, 0x7919), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 5fac786..abcb5a6 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5738,7 +5738,6 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {} }; #define ALC225_STANDARD_PINS \ - {0x12, 0xb7a60130}, \ {0x21, 0x04211020} #define ALC256_STANDARD_PINS \ @@ -5763,10 +5762,24 @@ static const struct hda_model_fixup alc269_fixup_models[] = { static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC225_STANDARD_PINS, + {0x12, 0xb7a60130}, {0x14, 0x901701a0}), SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC225_STANDARD_PINS, + {0x12, 0xb7a60130}, {0x14, 0x901701b0}), + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC225_STANDARD_PINS, + {0x12, 0xb7a60150}, + {0x14, 0x901701a0}), + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC225_STANDARD_PINS, + {0x12, 0xb7a60150}, + {0x14, 0x901701b0}), + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC225_STANDARD_PINS, + {0x12, 0xb7a60130}, + {0x1b, 0x90170110}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x02211020}), diff --git a/sound/usb/card.c b/sound/usb/card.c index 69860da..9e5276d6 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -556,7 +556,6 @@ static int usb_audio_probe(struct usb_interface *intf, goto __error; } chip = usb_chip[i]; - dev_set_drvdata(&dev->dev, chip); atomic_inc(&chip->active); /* avoid autopm */ break; } @@ -582,6 +581,7 @@ static int usb_audio_probe(struct usb_interface *intf, goto __error; } } + dev_set_drvdata(&dev->dev, chip); /* * For devices with more than one control interface, we assume the diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index e8a1e69..25d8031 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -122,10 +122,14 @@ static bool ignore_func(struct objtool_file *file, struct symbol *func) /* check for STACK_FRAME_NON_STANDARD */ if (file->whitelist && file->whitelist->rela) - list_for_each_entry(rela, &file->whitelist->rela->rela_list, list) - if (rela->sym->sec == func->sec && + list_for_each_entry(rela, &file->whitelist->rela->rela_list, list) { + if (rela->sym->type == STT_SECTION && + rela->sym->sec == func->sec && rela->addend == func->offset) return true; + if (rela->sym->type == STT_FUNC && rela->sym == func) + return true; + } /* check if it has a context switching instruction */ func_for_each_insn(file, func, insn) diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c index b7447ce..b0ac057 100644 --- a/tools/testing/radix-tree/tag_check.c +++ b/tools/testing/radix-tree/tag_check.c @@ -122,7 +122,7 @@ enum { NODE_TAGGED = 2, }; -#define THRASH_SIZE 1000 * 1000 +#define THRASH_SIZE (1000 * 1000) #define N 127 #define BATCH 33 diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c index 7cf6e17..b9d34b3 100644 --- a/tools/vm/slabinfo.c +++ b/tools/vm/slabinfo.c @@ -510,10 +510,11 @@ static void slab_stats(struct slabinfo *s) s->alloc_node_mismatch, (s->alloc_node_mismatch * 100) / total); } - if (s->cmpxchg_double_fail || s->cmpxchg_double_cpu_fail) + if (s->cmpxchg_double_fail || s->cmpxchg_double_cpu_fail) { printf("\nCmpxchg_double Looping\n------------------------\n"); printf("Locked Cmpxchg Double redos %lu\nUnlocked Cmpxchg Double redos %lu\n", s->cmpxchg_double_fail, s->cmpxchg_double_cpu_fail); + } } static void report(struct slabinfo *s) |
