diff options
103 files changed, 920 insertions, 1327 deletions
diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt index cd29083e16ec..48ffb38f699e 100644 --- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt +++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt @@ -7,7 +7,15 @@ connected to the IPMMU through a port called micro-TLB. Required Properties: - - compatible: Must contain "renesas,ipmmu-vmsa". + - compatible: Must contain SoC-specific and generic entries from below. + + - "renesas,ipmmu-r8a73a4" for the R8A73A4 (R-Mobile APE6) IPMMU. + - "renesas,ipmmu-r8a7790" for the R8A7790 (R-Car H2) IPMMU. + - "renesas,ipmmu-r8a7791" for the R8A7791 (R-Car M2-W) IPMMU. + - "renesas,ipmmu-r8a7793" for the R8A7793 (R-Car M2-N) IPMMU. + - "renesas,ipmmu-r8a7794" for the R8A7794 (R-Car E2) IPMMU. + - "renesas,ipmmu-vmsa" for generic R-Car Gen2 VMSA-compatible IPMMU. + - reg: Base address and size of the IPMMU registers. - interrupts: Specifiers for the MMU fault interrupts. For instances that support secure mode two interrupts must be specified, for non-secure and @@ -27,7 +35,7 @@ node with the following property: Example: R8A7791 IPMMU-MX and VSP1-D0 bus master ipmmu_mx: mmu@fe951000 { - compatible = "renasas,ipmmu-vmsa"; + compatible = "renasas,ipmmu-r8a7791", "renasas,ipmmu-vmsa"; reg = <0 0xfe951000 0 0x1000>; interrupts = <0 222 IRQ_TYPE_LEVEL_HIGH>, <0 221 IRQ_TYPE_LEVEL_HIGH>; @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc8 +EXTRAVERSION = NAME = Blurry Fish Butt # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index 314f59c12162..d0c743853318 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -25,9 +25,9 @@ cache-sets = <512>; cache-line-size = <32>; /* At full speed latency must be >=2 */ - arm,tag-latency = <2>; - arm,data-latency = <2 2>; - arm,dirty-latency = <2>; + arm,tag-latency = <8>; + arm,data-latency = <8 8>; + arm,dirty-latency = <8>; }; mtu0: mtu@101e2000 { diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts index 01f40197ea13..3279bf1a17a1 100644 --- a/arch/arm/boot/dts/versatile-ab.dts +++ b/arch/arm/boot/dts/versatile-ab.dts @@ -110,7 +110,11 @@ interrupt-parent = <&vic>; interrupts = <31>; /* Cascaded to vic */ clear-mask = <0xffffffff>; - valid-mask = <0xffc203f8>; + /* + * Valid interrupt lines mask according to + * table 4-36 page 4-50 of ARM DUI 0225D + */ + valid-mask = <0x0760031b>; }; dma@10130000 { @@ -266,8 +270,8 @@ }; mmc@5000 { compatible = "arm,pl180", "arm,primecell"; - reg = < 0x5000 0x1000>; - interrupts-extended = <&vic 22 &sic 2>; + reg = <0x5000 0x1000>; + interrupts-extended = <&vic 22 &sic 1>; clocks = <&xtal24mhz>, <&pclk>; clock-names = "mclk", "apb_pclk"; }; diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index b83137f66034..33a8eb28374e 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -5,6 +5,16 @@ compatible = "arm,versatile-pb"; amba { + /* The Versatile PB is using more SIC IRQ lines than the AB */ + sic: intc@10003000 { + clear-mask = <0xffffffff>; + /* + * Valid interrupt lines mask according to + * figure 3-30 page 3-74 of ARM DUI 0224B + */ + valid-mask = <0x7fe003ff>; + }; + gpio2: gpio@101e6000 { compatible = "arm,pl061", "arm,primecell"; reg = <0x101e6000 0x1000>; @@ -67,6 +77,13 @@ }; fpga { + mmc@5000 { + /* + * Overrides the interrupt assignment from + * the Versatile AB board file. + */ + interrupts-extended = <&sic 22 &sic 23>; + }; uart@9000 { compatible = "arm,pl011", "arm,primecell"; reg = <0x9000 0x1000>; @@ -86,7 +103,8 @@ mmc@b000 { compatible = "arm,pl180", "arm,primecell"; reg = <0xb000 0x1000>; - interrupts-extended = <&vic 23 &sic 2>; + interrupt-parent = <&sic>; + interrupts = <1>, <2>; clocks = <&xtal24mhz>, <&pclk>; clock-names = "mclk", "apb_pclk"; }; diff --git a/arch/arm/boot/dts/wm8650.dtsi b/arch/arm/boot/dts/wm8650.dtsi index b1c59a766a13..e12213d16693 100644 --- a/arch/arm/boot/dts/wm8650.dtsi +++ b/arch/arm/boot/dts/wm8650.dtsi @@ -187,6 +187,15 @@ interrupts = <43>; }; + sdhc@d800a000 { + compatible = "wm,wm8505-sdhc"; + reg = <0xd800a000 0x400>; + interrupts = <20>, <21>; + clocks = <&clksdhc>; + bus-width = <4>; + sdon-inverted; + }; + fb: fb@d8050800 { compatible = "wm,wm8505-fb"; reg = <0xd8050800 0x200>; diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 69a22fdb52a5..cd7b198fc79e 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -366,6 +366,7 @@ CONFIG_BATTERY_MAX17042=m CONFIG_CHARGER_MAX14577=m CONFIG_CHARGER_MAX77693=m CONFIG_CHARGER_TPS65090=y +CONFIG_AXP20X_POWER=m CONFIG_POWER_RESET_AS3722=y CONFIG_POWER_RESET_GPIO=y CONFIG_POWER_RESET_GPIO_RESTART=y diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index 3c36e16fcacf..b503a89441bf 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -84,6 +84,7 @@ CONFIG_SPI_SUN4I=y CONFIG_SPI_SUN6I=y CONFIG_GPIO_SYSFS=y CONFIG_POWER_SUPPLY=y +CONFIG_AXP20X_POWER=y CONFIG_THERMAL=y CONFIG_CPU_THERMAL=y CONFIG_WATCHDOG=y diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 17a6f752a436..7b76ce01c21d 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -149,8 +149,8 @@ static int omap2_onenand_get_freq(struct omap_onenand_platform_data *cfg, freq = 104; break; default: - freq = 54; - break; + pr_err("onenand rate not detected, bad GPMC async timings?\n"); + freq = 0; } return freq; @@ -271,6 +271,11 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) struct gpmc_timings t; int ret; + /* + * Note that we need to keep sync_write set for the call to + * omap2_onenand_set_async_mode() to work to detect the onenand + * supported clock rate for the sync timings. + */ if (gpmc_onenand_data->of_node) { gpmc_read_settings_dt(gpmc_onenand_data->of_node, &onenand_async); @@ -281,12 +286,9 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) else gpmc_onenand_data->flags |= ONENAND_SYNC_READ; onenand_async.sync_read = false; - onenand_async.sync_write = false; } } - omap2_onenand_set_async_mode(onenand_base); - omap2_onenand_calc_async_timings(&t); ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async); @@ -310,6 +312,8 @@ static int omap2_onenand_setup_sync(void __iomem *onenand_base, int *freq_ptr) if (!freq) { /* Very first call freq is not known */ freq = omap2_onenand_get_freq(gpmc_onenand_data, onenand_base); + if (!freq) + return -ENODEV; set_onenand_cfg(onenand_base); } diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 591f9db3bf40..93d0b6d0b63e 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -187,19 +187,6 @@ static inline int mem_words_used(struct jit_ctx *ctx) return fls(ctx->seen & SEEN_MEM); } -static inline bool is_load_to_a(u16 inst) -{ - switch (inst) { - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - return true; - default: - return false; - } -} - static void jit_fill_hole(void *area, unsigned int size) { u32 *ptr; @@ -211,7 +198,6 @@ static void jit_fill_hole(void *area, unsigned int size) static void build_prologue(struct jit_ctx *ctx) { u16 reg_set = saved_regs(ctx); - u16 first_inst = ctx->skf->insns[0].code; u16 off; #ifdef CONFIG_FRAME_POINTER @@ -241,7 +227,7 @@ static void build_prologue(struct jit_ctx *ctx) emit(ARM_MOV_I(r_X, 0), ctx); /* do not leak kernel data to userspace */ - if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst))) + if (bpf_needs_clear_a(&ctx->skf->insns[0])) emit(ARM_MOV_I(r_A, 0), ctx); /* stack space for the BPF_MEM words */ @@ -770,7 +756,8 @@ load_ind: case BPF_ALU | BPF_RSH | BPF_K: if (unlikely(k > 31)) return -1; - emit(ARM_LSR_I(r_A, r_A, k), ctx); + if (k) + emit(ARM_LSR_I(r_A, r_A, k), ctx); break; case BPF_ALU | BPF_RSH | BPF_X: update_on_xread(ctx); diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 77cb27309db2..1a8c96035716 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -521,19 +521,6 @@ static inline u16 align_sp(unsigned int num) return num; } -static bool is_load_to_a(u16 inst) -{ - switch (inst) { - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - return true; - default: - return false; - } -} - static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset) { int i = 0, real_off = 0; @@ -614,7 +601,6 @@ static unsigned int get_stack_depth(struct jit_ctx *ctx) static void build_prologue(struct jit_ctx *ctx) { - u16 first_inst = ctx->skf->insns[0].code; int sp_off; /* Calculate the total offset for the stack pointer */ @@ -641,7 +627,7 @@ static void build_prologue(struct jit_ctx *ctx) emit_jit_reg_move(r_X, r_zero, ctx); /* Do not leak kernel data to userspace */ - if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst))) + if (bpf_needs_clear_a(&ctx->skf->insns[0])) emit_jit_reg_move(r_A, r_zero, ctx); } diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 04782164ee67..2d66a8446198 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -78,18 +78,9 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image, PPC_LI(r_X, 0); } - switch (filter[0].code) { - case BPF_RET | BPF_K: - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - /* first instruction sets A register (or is RET 'constant') */ - break; - default: - /* make sure we dont leak kernel information to user */ + /* make sure we dont leak kernel information to user */ + if (bpf_needs_clear_a(&filter[0])) PPC_LI(r_A, 0); - } } static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index 22564f5f2364..3e6e05a7c4c2 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -420,22 +420,9 @@ void bpf_jit_compile(struct bpf_prog *fp) } emit_reg_move(O7, r_saved_O7); - switch (filter[0].code) { - case BPF_RET | BPF_K: - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - /* The first instruction sets the A register (or is - * a "RET 'constant'") - */ - break; - default: - /* Make sure we dont leak kernel information to the - * user. - */ + /* Make sure we dont leak kernel information to the user. */ + if (bpf_needs_clear_a(&filter[0])) emit_clear(r_A); /* A = 0 */ - } for (i = 0; i < flen; i++) { unsigned int K = filter[i].k; diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 106c21bd7f44..8ec7a4599c08 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -176,8 +176,6 @@ config NR_CPUS smaller kernel memory footprint results from using a smaller value on chips with fewer tiles. -if TILEGX - choice prompt "Kernel page size" default PAGE_SIZE_64KB @@ -188,8 +186,11 @@ choice connections, etc., it may be better to select 16KB, which uses memory more efficiently at some cost in TLB performance. - Note that this option is TILE-Gx specific; currently - TILEPro page size is set by rebuilding the hypervisor. + Note that for TILEPro, you must also rebuild the hypervisor + with a matching page size. + +config PAGE_SIZE_4KB + bool "4KB" if TILEPRO config PAGE_SIZE_16KB bool "16KB" @@ -199,8 +200,6 @@ config PAGE_SIZE_64KB endchoice -endif - source "kernel/Kconfig.hz" config KEXEC diff --git a/arch/tile/include/asm/page.h b/arch/tile/include/asm/page.h index a213a8d84a95..8eca6a0e1762 100644 --- a/arch/tile/include/asm/page.h +++ b/arch/tile/include/asm/page.h @@ -20,15 +20,17 @@ #include <arch/chip.h> /* PAGE_SHIFT and HPAGE_SHIFT determine the page sizes. */ -#if defined(CONFIG_PAGE_SIZE_16KB) +#if defined(CONFIG_PAGE_SIZE_4KB) /* tilepro only */ +#define PAGE_SHIFT 12 +#define CTX_PAGE_FLAG HV_CTX_PG_SM_4K +#elif defined(CONFIG_PAGE_SIZE_16KB) #define PAGE_SHIFT 14 #define CTX_PAGE_FLAG HV_CTX_PG_SM_16K #elif defined(CONFIG_PAGE_SIZE_64KB) #define PAGE_SHIFT 16 #define CTX_PAGE_FLAG HV_CTX_PG_SM_64K #else -#define PAGE_SHIFT HV_LOG2_DEFAULT_PAGE_SIZE_SMALL -#define CTX_PAGE_FLAG 0 +#error Page size not specified in Kconfig #endif #define HPAGE_SHIFT HV_LOG2_DEFAULT_PAGE_SIZE_LARGE diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index a89fdbc1f0be..03663740c866 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -421,7 +421,7 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) regs->ip = landing_pad; /* - * Fetch ECX from where the vDSO stashed it. + * Fetch EBP from where the vDSO stashed it. * * WARNING: We are in CONTEXT_USER and RCU isn't paying attention! */ @@ -432,10 +432,10 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) * Micro-optimization: the pointer we're following is explicitly * 32 bits, so it can't be out of range. */ - __get_user(*(u32 *)®s->cx, + __get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp) #else - get_user(*(u32 *)®s->cx, + get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp) #endif ) { diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 3eb572ed3d7a..f3b6d54e0042 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -292,7 +292,7 @@ ENTRY(entry_SYSENTER_32) movl TSS_sysenter_sp0(%esp), %esp sysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ - pushl %ecx /* pt_regs->cx */ + pushl %ebp /* pt_regs->sp (stashed in bp) */ pushfl /* pt_regs->flags (except IF = 0) */ orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ @@ -308,8 +308,9 @@ sysenter_past_esp: movl %esp, %eax call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV /* Opportunistic SYSEXIT */ TRACE_IRQS_ON /* User mode traces as IRQs on. */ diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index c3201830a85e..6a1ae3751e82 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -63,7 +63,7 @@ ENTRY(entry_SYSENTER_compat) /* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ - pushq %rcx /* pt_regs->sp */ + pushq %rbp /* pt_regs->sp (stashed in bp) */ /* * Push flags. This is nasty. First, interrupts are currently @@ -82,14 +82,14 @@ ENTRY(entry_SYSENTER_compat) pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx (will be overwritten) */ + pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 = 0 */ pushq %r8 /* pt_regs->r9 = 0 */ pushq %r8 /* pt_regs->r10 = 0 */ pushq %r8 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ pushq %r8 /* pt_regs->r12 = 0 */ pushq %r8 /* pt_regs->r13 = 0 */ pushq %r8 /* pt_regs->r14 = 0 */ @@ -121,8 +121,9 @@ sysenter_flags_fixed: movq %rsp, %rdi call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV jmp sysret32_from_system_call sysenter_fix_flags: @@ -178,7 +179,7 @@ ENTRY(entry_SYSCALL_compat) pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx (will be overwritten) */ + pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ xorq %r8,%r8 pushq %r8 /* pt_regs->r8 = 0 */ @@ -186,7 +187,7 @@ ENTRY(entry_SYSCALL_compat) pushq %r8 /* pt_regs->r10 = 0 */ pushq %r8 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ pushq %r8 /* pt_regs->r12 = 0 */ pushq %r8 /* pt_regs->r13 = 0 */ pushq %r8 /* pt_regs->r14 = 0 */ @@ -200,8 +201,9 @@ ENTRY(entry_SYSCALL_compat) movq %rsp, %rdi call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV /* Opportunistic SYSRET */ sysret32_from_system_call: diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index 93bd8452383f..3a1d9297074b 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -1,5 +1,5 @@ /* - * Code for the vDSO. This version uses the old int $0x80 method. + * AT_SYSINFO entry point */ #include <asm/dwarf2.h> @@ -21,35 +21,67 @@ __kernel_vsyscall: /* * Reshuffle regs so that all of any of the entry instructions * will preserve enough state. + * + * A really nice entry sequence would be: + * pushl %edx + * pushl %ecx + * movl %esp, %ecx + * + * Unfortunately, naughty Android versions between July and December + * 2015 actually hardcode the traditional Linux SYSENTER entry + * sequence. That is severely broken for a number of reasons (ask + * anyone with an AMD CPU, for example). Nonetheless, we try to keep + * it working approximately as well as it ever worked. + * + * This link may eludicate some of the history: + * https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7 + * personally, I find it hard to understand what's going on there. + * + * Note to future user developers: DO NOT USE SYSENTER IN YOUR CODE. + * Execute an indirect call to the address in the AT_SYSINFO auxv + * entry. That is the ONLY correct way to make a fast 32-bit system + * call on Linux. (Open-coding int $0x80 is also fine, but it's + * slow.) */ + pushl %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx, 0 pushl %edx CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET edx, 0 - pushl %ecx + pushl %ebp CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET ecx, 0 - movl %esp, %ecx + CFI_REL_OFFSET ebp, 0 + + #define SYSENTER_SEQUENCE "movl %esp, %ebp; sysenter" + #define SYSCALL_SEQUENCE "movl %ecx, %ebp; syscall" #ifdef CONFIG_X86_64 /* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */ - ALTERNATIVE_2 "", "sysenter", X86_FEATURE_SYSENTER32, \ - "syscall", X86_FEATURE_SYSCALL32 + ALTERNATIVE_2 "", SYSENTER_SEQUENCE, X86_FEATURE_SYSENTER32, \ + SYSCALL_SEQUENCE, X86_FEATURE_SYSCALL32 #else - ALTERNATIVE "", "sysenter", X86_FEATURE_SEP + ALTERNATIVE "", SYSENTER_SEQUENCE, X86_FEATURE_SEP #endif /* Enter using int $0x80 */ - movl (%esp), %ecx int $0x80 GLOBAL(int80_landing_pad) - /* Restore ECX and EDX in case they were clobbered. */ - popl %ecx - CFI_RESTORE ecx + /* + * Restore EDX and ECX in case they were clobbered. EBP is not + * clobbered (the kernel restores it), but it's cleaner and + * probably faster to pop it than to adjust ESP using addl. + */ + popl %ebp + CFI_RESTORE ebp CFI_ADJUST_CFA_OFFSET -4 popl %edx CFI_RESTORE edx CFI_ADJUST_CFA_OFFSET -4 + popl %ecx + CFI_RESTORE ecx + CFI_ADJUST_CFA_OFFSET -4 ret CFI_ENDPROC diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index e4f8010f22e0..f7ba9fbf12ee 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -216,6 +216,7 @@ #define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 10d0596433f8..c759b3cca663 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -19,6 +19,12 @@ static inline int paravirt_enabled(void) return pv_info.paravirt_enabled; } +static inline int paravirt_has_feature(unsigned int feature) +{ + WARN_ON_ONCE(!pv_info.paravirt_enabled); + return (pv_info.features & feature); +} + static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 31247b5bff7c..3d44191185f8 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -70,9 +70,14 @@ struct pv_info { #endif int paravirt_enabled; + unsigned int features; /* valid only if paravirt_enabled is set */ const char *name; }; +#define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x) +/* Supported features */ +#define PV_SUPPORTED_RTC (1<<0) + struct pv_init_ops { /* * Patch may replace one of the defined code sequences with diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 67522256c7ff..2d5a50cb61a2 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -472,6 +472,7 @@ static inline unsigned long current_top_of_stack(void) #else #define __cpuid native_cpuid #define paravirt_enabled() 0 +#define paravirt_has(x) 0 static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 38dd5efdd04c..2bd2292a316d 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -193,20 +193,17 @@ static int __init numachip_system_init(void) case 1: init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); numachip_apic_icr_write = numachip1_apic_icr_write; - x86_init.pci.arch_init = pci_numachip_init; break; case 2: init_extra_mapping_uc(NUMACHIP2_LCSR_BASE, NUMACHIP2_LCSR_SIZE); numachip_apic_icr_write = numachip2_apic_icr_write; - - /* Use MCFG config cycles rather than locked CF8 cycles */ - raw_pci_ops = &pci_mmcfg; break; default: return 0; } x86_cpuinit.fixup_cpu_id = fixup_cpu_id; + x86_init.pci.arch_init = pci_numachip_init; return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index c5b0d562dbf5..7e8a736d09db 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -999,6 +999,17 @@ void do_machine_check(struct pt_regs *regs, long error_code) int flags = MF_ACTION_REQUIRED; int lmce = 0; + /* If this CPU is offline, just bail out. */ + if (cpu_is_offline(smp_processor_id())) { + u64 mcgstatus; + + mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (mcgstatus & MCG_STATUS_RIPV) { + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + return; + } + } + ist_enter(regs); this_cpu_inc(mce_exception_count); diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index cd9685235df9..4af8d063fb36 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -200,6 +200,9 @@ static __init int add_rtc_cmos(void) } #endif + if (paravirt_enabled() && !paravirt_has(RTC)) + return -ENODEV; + platform_device_register(&rtc_device); dev_info(&rtc_device.dev, "registered platform RTC device (no PNP device found)\n"); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 08116ff227cc..b0ea42b78ccd 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -420,6 +420,7 @@ void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_s u8 saved_mode; if (hpet_legacy_start) { /* save existing mode for later reenablement */ + WARN_ON(channel != 0); saved_mode = kvm->arch.vpit->pit_state.channels[0].mode; kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */ pit_load_count(kvm, channel, val); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7ffc224bbe41..97592e190413 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3606,7 +3606,8 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) sizeof(kvm->arch.vpit->pit_state.channels)); kvm->arch.vpit->pit_state.flags = ps->flags; for (i = 0; i < 3; i++) - kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, start); + kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, + start && i == 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); return 0; } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index a0d09f6c6533..a43b2eafc466 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1414,6 +1414,7 @@ __init void lguest_init(void) pv_info.kernel_rpl = 1; /* Everyone except Xen runs with this set. */ pv_info.shared_kernel_pmd = 1; + pv_info.features = 0; /* * We set up all the lguest overrides for sensitive operations. These diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 5774800ff583..b7de78bdc09c 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1192,7 +1192,7 @@ static const struct pv_info xen_info __initconst = { #ifdef CONFIG_X86_64 .extra_user_64bit_cs = FLAT_USER_CS64, #endif - + .features = 0, .name = "Xen", }; @@ -1535,6 +1535,8 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; + if (xen_initial_domain()) + pv_info.features |= PV_SUPPORTED_RTC; pv_init_ops = xen_init_ops; pv_apic_ops = xen_apic_ops; if (!xen_pvh_domain()) { @@ -1886,8 +1888,10 @@ EXPORT_SYMBOL_GPL(xen_hvm_need_lapic); static void xen_set_cpu_features(struct cpuinfo_x86 *c) { - if (xen_pv_domain()) + if (xen_pv_domain()) { clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + set_cpu_cap(c, X86_FEATURE_XENPV); + } } const struct hypervisor_x86 x86_hyper_xen = { diff --git a/block/blk-merge.c b/block/blk-merge.c index e73846a3d08a..e01405a3e8b3 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -81,7 +81,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *new = NULL; bio_for_each_segment(bv, bio, iter) { - if (sectors + (bv.bv_len >> 9) > blk_max_size_offset(q, bio->bi_iter.bi_sector)) + if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q)) goto split; /* diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c index f8c0b8dbeb75..88bc8e6b2a54 100644 --- a/crypto/async_tx/async_memcpy.c +++ b/crypto/async_tx/async_memcpy.c @@ -53,7 +53,7 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, struct dmaengine_unmap_data *unmap = NULL; if (device) - unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOIO); + unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT); if (unmap && is_dma_copy_aligned(device, src_offset, dest_offset, len)) { unsigned long dma_prep_flags = 0; diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c index 5d355e0c2633..c0748bbd4c08 100644 --- a/crypto/async_tx/async_pq.c +++ b/crypto/async_tx/async_pq.c @@ -188,7 +188,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks, BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks))); if (device) - unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO); + unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT); /* XORing P/Q is only implemented in software */ if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) && @@ -307,7 +307,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks, BUG_ON(disks < 4); if (device) - unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO); + unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT); if (unmap && disks <= dma_maxpq(device, 0) && is_dma_pq_aligned(device, offset, 0, len)) { diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c index 934a84981495..8fab6275ea1f 100644 --- a/crypto/async_tx/async_raid6_recov.c +++ b/crypto/async_tx/async_raid6_recov.c @@ -41,7 +41,7 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef, u8 *a, *b, *c; if (dma) - unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO); + unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOWAIT); if (unmap) { struct device *dev = dma->dev; @@ -105,7 +105,7 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len, u8 *d, *s; if (dma) - unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO); + unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOWAIT); if (unmap) { dma_addr_t dma_dest[2]; diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index e1bce26cd4f9..da75777f2b3f 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -182,7 +182,7 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset, BUG_ON(src_cnt <= 1); if (device) - unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOIO); + unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOWAIT); if (unmap && is_dma_xor_aligned(device, offset, 0, len)) { struct dma_async_tx_descriptor *tx; @@ -278,7 +278,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, BUG_ON(src_cnt <= 1); if (device) - unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOIO); + unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOWAIT); if (unmap && src_cnt <= device->max_xor && is_dma_xor_aligned(device, offset, 0, len)) { diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c index 707cf6213bc2..b9afb47db7ed 100644 --- a/drivers/acpi/device_sysfs.c +++ b/drivers/acpi/device_sysfs.c @@ -104,7 +104,7 @@ static void acpi_expose_nondev_subnodes(struct kobject *kobj, init_completion(&dn->kobj_done); ret = kobject_init_and_add(&dn->kobj, &acpi_data_node_ktype, - kobj, dn->name); + kobj, "%s", dn->name); if (ret) acpi_handle_err(dn->handle, "Failed to expose (%d)\n", ret); else diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index d7373ca69c99..25693b045371 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -179,26 +179,21 @@ static int cn_call_callback(struct sk_buff *skb) * * It checks skb, netlink header and msg sizes, and calls callback helper. */ -static void cn_rx_skb(struct sk_buff *__skb) +static void cn_rx_skb(struct sk_buff *skb) { struct nlmsghdr *nlh; - struct sk_buff *skb; int len, err; - skb = skb_get(__skb); - if (skb->len >= NLMSG_HDRLEN) { nlh = nlmsg_hdr(skb); len = nlmsg_len(nlh); if (len < (int)sizeof(struct cn_msg) || skb->len < nlh->nlmsg_len || - len > CONNECTOR_MAX_MSG_SIZE) { - kfree_skb(skb); + len > CONNECTOR_MAX_MSG_SIZE) return; - } - err = cn_call_callback(skb); + err = cn_call_callback(skb_get(skb)); if (err < 0) kfree_skb(skb); } diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c index cddfa8dbf4bd..068e920ecb68 100644 --- a/drivers/dma/mic_x100_dma.c +++ b/drivers/dma/mic_x100_dma.c @@ -317,7 +317,6 @@ mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest, struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); struct device *dev = mic_dma_ch_to_device(mic_ch); int result; - struct dma_async_tx_descriptor *tx = NULL; if (!len && !flags) return NULL; @@ -325,13 +324,10 @@ mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest, spin_lock(&mic_ch->prep_lock); result = mic_dma_do_dma(mic_ch, flags, dma_src, dma_dest, len); if (result >= 0) - tx = allocate_tx(mic_ch); - - if (!tx) - dev_err(dev, "Error enqueueing dma, error=%d\n", result); - + return allocate_tx(mic_ch); + dev_err(dev, "Error enqueueing dma, error=%d\n", result); spin_unlock(&mic_ch->prep_lock); - return tx; + return NULL; } static struct dma_async_tx_descriptor * @@ -339,14 +335,13 @@ mic_dma_prep_interrupt_lock(struct dma_chan *ch, unsigned long flags) { struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); int ret; - struct dma_async_tx_descriptor *tx = NULL; spin_lock(&mic_ch->prep_lock); ret = mic_dma_do_dma(mic_ch, flags, 0, 0, 0); if (!ret) - tx = allocate_tx(mic_ch); + return allocate_tx(mic_ch); spin_unlock(&mic_ch->prep_lock); - return tx; + return NULL; } /* Return the status of the transaction */ diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c index 9dfa2b0fa5da..9cb93c5b655d 100644 --- a/drivers/dma/xgene-dma.c +++ b/drivers/dma/xgene-dma.c @@ -29,6 +29,7 @@ #include <linux/dmapool.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/irq.h> #include <linux/module.h> #include <linux/of_device.h> @@ -1610,6 +1611,7 @@ static int xgene_dma_request_irqs(struct xgene_dma *pdma) /* Register DMA channel rx irq */ for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) { chan = &pdma->chan[i]; + irq_set_status_flags(chan->rx_irq, IRQ_DISABLE_UNLAZY); ret = devm_request_irq(chan->dev, chan->rx_irq, xgene_dma_chan_ring_isr, 0, chan->name, chan); @@ -1620,6 +1622,7 @@ static int xgene_dma_request_irqs(struct xgene_dma *pdma) for (j = 0; j < i; j++) { chan = &pdma->chan[i]; + irq_clear_status_flags(chan->rx_irq, IRQ_DISABLE_UNLAZY); devm_free_irq(chan->dev, chan->rx_irq, chan); } @@ -1640,6 +1643,7 @@ static void xgene_dma_free_irqs(struct xgene_dma *pdma) for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) { chan = &pdma->chan[i]; + irq_clear_status_flags(chan->rx_irq, IRQ_DISABLE_UNLAZY); devm_free_irq(chan->dev, chan->rx_irq, chan); } } diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index ac1ce4a73edf..0e08e665f715 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -521,6 +521,7 @@ static int __init dmi_present(const u8 *buf) dmi_ver = smbios_ver; else dmi_ver = (buf[14] & 0xF0) << 4 | (buf[14] & 0x0F); + dmi_ver <<= 8; dmi_num = get_unaligned_le16(buf + 12); dmi_len = get_unaligned_le16(buf + 6); dmi_base = get_unaligned_le32(buf + 8); @@ -528,15 +529,14 @@ static int __init dmi_present(const u8 *buf) if (dmi_walk_early(dmi_decode) == 0) { if (smbios_ver) { pr_info("SMBIOS %d.%d present.\n", - dmi_ver >> 8, dmi_ver & 0xFF); + dmi_ver >> 16, (dmi_ver >> 8) & 0xFF); } else { smbios_entry_point_size = 15; memcpy(smbios_entry_point, buf, smbios_entry_point_size); pr_info("Legacy DMI %d.%d present.\n", - dmi_ver >> 8, dmi_ver & 0xFF); + dmi_ver >> 16, (dmi_ver >> 8) & 0xFF); } - dmi_ver <<= 8; dmi_format_ids(dmi_ids_string, sizeof(dmi_ids_string)); printk(KERN_DEBUG "DMI: %s\n", dmi_ids_string); return 0; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c index ffa902ece872..05a895496fc6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c @@ -156,6 +156,7 @@ nv40_gr_chan_new(struct nvkm_gr *base, struct nvkm_fifo_chan *fifoch, return -ENOMEM; nvkm_object_ctor(&nv40_gr_chan, oclass, &chan->object); chan->gr = gr; + chan->fifo = fifoch; *pobject = &chan->object; spin_lock_irqsave(&chan->gr->base.engine.lock, flags); diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index b9094e9da537..a1e75cba18e0 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -263,81 +263,6 @@ config EXYNOS_IOMMU_DEBUG Say N unless you need kernel log message for IOMMU debugging. -config SHMOBILE_IPMMU - bool - -config SHMOBILE_IPMMU_TLB - bool - -config SHMOBILE_IOMMU - bool "IOMMU for Renesas IPMMU/IPMMUI" - default n - depends on ARM && MMU - depends on ARCH_SHMOBILE || COMPILE_TEST - select IOMMU_API - select ARM_DMA_USE_IOMMU - select SHMOBILE_IPMMU - select SHMOBILE_IPMMU_TLB - help - Support for Renesas IPMMU/IPMMUI. This option enables - remapping of DMA memory accesses from all of the IP blocks - on the ICB. - - Warning: Drivers (including userspace drivers of UIO - devices) of the IP blocks on the ICB *must* use addresses - allocated from the IPMMU (iova) for DMA with this option - enabled. - - If unsure, say N. - -choice - prompt "IPMMU/IPMMUI address space size" - default SHMOBILE_IOMMU_ADDRSIZE_2048MB - depends on SHMOBILE_IOMMU - help - This option sets IPMMU/IPMMUI address space size by - adjusting the 1st level page table size. The page table size - is calculated as follows: - - page table size = number of page table entries * 4 bytes - number of page table entries = address space size / 1 MiB - - For example, when the address space size is 2048 MiB, the - 1st level page table size is 8192 bytes. - - config SHMOBILE_IOMMU_ADDRSIZE_2048MB - bool "2 GiB" - - config SHMOBILE_IOMMU_ADDRSIZE_1024MB - bool "1 GiB" - - config SHMOBILE_IOMMU_ADDRSIZE_512MB - bool "512 MiB" - - config SHMOBILE_IOMMU_ADDRSIZE_256MB - bool "256 MiB" - - config SHMOBILE_IOMMU_ADDRSIZE_128MB - bool "128 MiB" - - config SHMOBILE_IOMMU_ADDRSIZE_64MB - bool "64 MiB" - - config SHMOBILE_IOMMU_ADDRSIZE_32MB - bool "32 MiB" - -endchoice - -config SHMOBILE_IOMMU_L1SIZE - int - default 8192 if SHMOBILE_IOMMU_ADDRSIZE_2048MB - default 4096 if SHMOBILE_IOMMU_ADDRSIZE_1024MB - default 2048 if SHMOBILE_IOMMU_ADDRSIZE_512MB - default 1024 if SHMOBILE_IOMMU_ADDRSIZE_256MB - default 512 if SHMOBILE_IOMMU_ADDRSIZE_128MB - default 256 if SHMOBILE_IOMMU_ADDRSIZE_64MB - default 128 if SHMOBILE_IOMMU_ADDRSIZE_32MB - config IPMMU_VMSA bool "Renesas VMSA-compatible IPMMU" depends on ARM_LPAE diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 68faca02225d..42fc0c25cf1a 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -22,7 +22,5 @@ obj-$(CONFIG_ROCKCHIP_IOMMU) += rockchip-iommu.o obj-$(CONFIG_TEGRA_IOMMU_GART) += tegra-gart.o obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o -obj-$(CONFIG_SHMOBILE_IOMMU) += shmobile-iommu.o -obj-$(CONFIG_SHMOBILE_IPMMU) += shmobile-ipmmu.o obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o obj-$(CONFIG_S390_IOMMU) += s390-iommu.o diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 8b2be1e7714f..539b0dea8034 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -35,6 +35,7 @@ #include <linux/msi.h> #include <linux/dma-contiguous.h> #include <linux/irqdomain.h> +#include <linux/percpu.h> #include <asm/irq_remapping.h> #include <asm/io_apic.h> #include <asm/apic.h> @@ -114,6 +115,45 @@ struct kmem_cache *amd_iommu_irq_cache; static void update_domain(struct protection_domain *domain); static int protection_domain_init(struct protection_domain *domain); +/* + * For dynamic growth the aperture size is split into ranges of 128MB of + * DMA address space each. This struct represents one such range. + */ +struct aperture_range { + + spinlock_t bitmap_lock; + + /* address allocation bitmap */ + unsigned long *bitmap; + unsigned long offset; + unsigned long next_bit; + + /* + * Array of PTE pages for the aperture. In this array we save all the + * leaf pages of the domain page table used for the aperture. This way + * we don't need to walk the page table to find a specific PTE. We can + * just calculate its address in constant time. + */ + u64 *pte_pages[64]; +}; + +/* + * Data container for a dma_ops specific protection domain + */ +struct dma_ops_domain { + /* generic protection domain information */ + struct protection_domain domain; + + /* size of the aperture for the mappings */ + unsigned long aperture_size; + + /* aperture index we start searching for free addresses */ + u32 __percpu *next_index; + + /* address space relevant data */ + struct aperture_range *aperture[APERTURE_MAX_RANGES]; +}; + /**************************************************************************** * * Helper functions @@ -1167,11 +1207,21 @@ static u64 *alloc_pte(struct protection_domain *domain, end_lvl = PAGE_SIZE_LEVEL(page_size); while (level > end_lvl) { - if (!IOMMU_PTE_PRESENT(*pte)) { + u64 __pte, __npte; + + __pte = *pte; + + if (!IOMMU_PTE_PRESENT(__pte)) { page = (u64 *)get_zeroed_page(gfp); if (!page) return NULL; - *pte = PM_LEVEL_PDE(level, virt_to_phys(page)); + + __npte = PM_LEVEL_PDE(level, virt_to_phys(page)); + + if (cmpxchg64(pte, __pte, __npte)) { + free_page((unsigned long)page); + continue; + } } /* No level skipping support yet */ @@ -1376,8 +1426,10 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom, bool populate, gfp_t gfp) { int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT; - struct amd_iommu *iommu; unsigned long i, old_size, pte_pgsize; + struct aperture_range *range; + struct amd_iommu *iommu; + unsigned long flags; #ifdef CONFIG_IOMMU_STRESS populate = false; @@ -1386,15 +1438,17 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom, if (index >= APERTURE_MAX_RANGES) return -ENOMEM; - dma_dom->aperture[index] = kzalloc(sizeof(struct aperture_range), gfp); - if (!dma_dom->aperture[index]) + range = kzalloc(sizeof(struct aperture_range), gfp); + if (!range) return -ENOMEM; - dma_dom->aperture[index]->bitmap = (void *)get_zeroed_page(gfp); - if (!dma_dom->aperture[index]->bitmap) + range->bitmap = (void *)get_zeroed_page(gfp); + if (!range->bitmap) goto out_free; - dma_dom->aperture[index]->offset = dma_dom->aperture_size; + range->offset = dma_dom->aperture_size; + + spin_lock_init(&range->bitmap_lock); if (populate) { unsigned long address = dma_dom->aperture_size; @@ -1407,14 +1461,20 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom, if (!pte) goto out_free; - dma_dom->aperture[index]->pte_pages[i] = pte_page; + range->pte_pages[i] = pte_page; address += APERTURE_RANGE_SIZE / 64; } } - old_size = dma_dom->aperture_size; - dma_dom->aperture_size += APERTURE_RANGE_SIZE; + spin_lock_irqsave(&dma_dom->domain.lock, flags); + + /* First take the bitmap_lock and then publish the range */ + spin_lock(&range->bitmap_lock); + + old_size = dma_dom->aperture_size; + dma_dom->aperture[index] = range; + dma_dom->aperture_size += APERTURE_RANGE_SIZE; /* Reserve address range used for MSI messages */ if (old_size < MSI_ADDR_BASE_LO && @@ -1461,62 +1521,123 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom, update_domain(&dma_dom->domain); + spin_unlock(&range->bitmap_lock); + + spin_unlock_irqrestore(&dma_dom->domain.lock, flags); + return 0; out_free: update_domain(&dma_dom->domain); - free_page((unsigned long)dma_dom->aperture[index]->bitmap); + free_page((unsigned long)range->bitmap); - kfree(dma_dom->aperture[index]); - dma_dom->aperture[index] = NULL; + kfree(range); return -ENOMEM; } +static dma_addr_t dma_ops_aperture_alloc(struct dma_ops_domain *dom, + struct aperture_range *range, + unsigned long pages, + unsigned long dma_mask, + unsigned long boundary_size, + unsigned long align_mask, + bool trylock) +{ + unsigned long offset, limit, flags; + dma_addr_t address; + bool flush = false; + + offset = range->offset >> PAGE_SHIFT; + limit = iommu_device_max_index(APERTURE_RANGE_PAGES, offset, + dma_mask >> PAGE_SHIFT); + + if (trylock) { + if (!spin_trylock_irqsave(&range->bitmap_lock, flags)) + return -1; + } else { + spin_lock_irqsave(&range->bitmap_lock, flags); + } + + address = iommu_area_alloc(range->bitmap, limit, range->next_bit, + pages, offset, boundary_size, align_mask); + if (address == -1) { + /* Nothing found, retry one time */ + address = iommu_area_alloc(range->bitmap, limit, + 0, pages, offset, boundary_size, + align_mask); + flush = true; + } + + if (address != -1) + range->next_bit = address + pages; + + spin_unlock_irqrestore(&range->bitmap_lock, flags); + + if (flush) { + domain_flush_tlb(&dom->domain); + domain_flush_complete(&dom->domain); + } + + return address; +} + static unsigned long dma_ops_area_alloc(struct device *dev, struct dma_ops_domain *dom, unsigned int pages, unsigned long align_mask, - u64 dma_mask, - unsigned long start) + u64 dma_mask) { - unsigned long next_bit = dom->next_address % APERTURE_RANGE_SIZE; - int max_index = dom->aperture_size >> APERTURE_RANGE_SHIFT; - int i = start >> APERTURE_RANGE_SHIFT; unsigned long boundary_size, mask; unsigned long address = -1; - unsigned long limit; + bool first = true; + u32 start, i; - next_bit >>= PAGE_SHIFT; + preempt_disable(); mask = dma_get_seg_boundary(dev); +again: + start = this_cpu_read(*dom->next_index); + + /* Sanity check - is it really necessary? */ + if (unlikely(start > APERTURE_MAX_RANGES)) { + start = 0; + this_cpu_write(*dom->next_index, 0); + } + boundary_size = mask + 1 ? ALIGN(mask + 1, PAGE_SIZE) >> PAGE_SHIFT : 1UL << (BITS_PER_LONG - PAGE_SHIFT); - for (;i < max_index; ++i) { - unsigned long offset = dom->aperture[i]->offset >> PAGE_SHIFT; + for (i = 0; i < APERTURE_MAX_RANGES; ++i) { + struct aperture_range *range; + int index; - if (dom->aperture[i]->offset >= dma_mask) - break; + index = (start + i) % APERTURE_MAX_RANGES; - limit = iommu_device_max_index(APERTURE_RANGE_PAGES, offset, - dma_mask >> PAGE_SHIFT); + range = dom->aperture[index]; - address = iommu_area_alloc(dom->aperture[i]->bitmap, - limit, next_bit, pages, 0, - boundary_size, align_mask); + if (!range || range->offset >= dma_mask) + continue; + + address = dma_ops_aperture_alloc(dom, range, pages, + dma_mask, boundary_size, + align_mask, first); if (address != -1) { - address = dom->aperture[i]->offset + - (address << PAGE_SHIFT); - dom->next_address = address + (pages << PAGE_SHIFT); + address = range->offset + (address << PAGE_SHIFT); + this_cpu_write(*dom->next_index, index); break; } + } - next_bit = 0; + if (address == -1 && first) { + first = false; + goto again; } + preempt_enable(); + return address; } @@ -1526,21 +1647,14 @@ static unsigned long dma_ops_alloc_addresses(struct device *dev, unsigned long align_mask, u64 dma_mask) { - unsigned long address; - -#ifdef CONFIG_IOMMU_STRESS - dom->next_address = 0; - dom->need_flush = true; -#endif + unsigned long address = -1; - address = dma_ops_area_alloc(dev, dom, pages, align_mask, - dma_mask, dom->next_address); + while (address == -1) { + address = dma_ops_area_alloc(dev, dom, pages, + align_mask, dma_mask); - if (address == -1) { - dom->next_address = 0; - address = dma_ops_area_alloc(dev, dom, pages, align_mask, - dma_mask, 0); - dom->need_flush = true; + if (address == -1 && alloc_new_range(dom, false, GFP_ATOMIC)) + break; } if (unlikely(address == -1)) @@ -1562,6 +1676,7 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom, { unsigned i = address >> APERTURE_RANGE_SHIFT; struct aperture_range *range = dom->aperture[i]; + unsigned long flags; BUG_ON(i >= APERTURE_MAX_RANGES || range == NULL); @@ -1570,12 +1685,18 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom, return; #endif - if (address >= dom->next_address) - dom->need_flush = true; + if (amd_iommu_unmap_flush) { + domain_flush_tlb(&dom->domain); + domain_flush_complete(&dom->domain); + } address = (address % APERTURE_RANGE_SIZE) >> PAGE_SHIFT; + spin_lock_irqsave(&range->bitmap_lock, flags); + if (address + pages > range->next_bit) + range->next_bit = address + pages; bitmap_clear(range->bitmap, address, pages); + spin_unlock_irqrestore(&range->bitmap_lock, flags); } @@ -1755,6 +1876,8 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom) if (!dom) return; + free_percpu(dom->next_index); + del_domain_from_list(&dom->domain); free_pagetable(&dom->domain); @@ -1769,6 +1892,23 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom) kfree(dom); } +static int dma_ops_domain_alloc_apertures(struct dma_ops_domain *dma_dom, + int max_apertures) +{ + int ret, i, apertures; + + apertures = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT; + ret = 0; + + for (i = apertures; i < max_apertures; ++i) { + ret = alloc_new_range(dma_dom, false, GFP_KERNEL); + if (ret) + break; + } + + return ret; +} + /* * Allocates a new protection domain usable for the dma_ops functions. * It also initializes the page table and the address allocator data @@ -1777,6 +1917,7 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom) static struct dma_ops_domain *dma_ops_domain_alloc(void) { struct dma_ops_domain *dma_dom; + int cpu; dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL); if (!dma_dom) @@ -1785,6 +1926,10 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void) if (protection_domain_init(&dma_dom->domain)) goto free_dma_dom; + dma_dom->next_index = alloc_percpu(u32); + if (!dma_dom->next_index) + goto free_dma_dom; + dma_dom->domain.mode = PAGE_MODE_2_LEVEL; dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL); dma_dom->domain.flags = PD_DMA_OPS_MASK; @@ -1792,8 +1937,6 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void) if (!dma_dom->domain.pt_root) goto free_dma_dom; - dma_dom->need_flush = false; - add_domain_to_list(&dma_dom->domain); if (alloc_new_range(dma_dom, true, GFP_KERNEL)) @@ -1804,8 +1947,9 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void) * a valid dma-address. So we can use 0 as error value */ dma_dom->aperture[0]->bitmap[0] = 1; - dma_dom->next_address = 0; + for_each_possible_cpu(cpu) + *per_cpu_ptr(dma_dom->next_index, cpu) = 0; return dma_dom; @@ -2328,7 +2472,7 @@ static dma_addr_t dma_ops_domain_map(struct dma_ops_domain *dom, else if (direction == DMA_BIDIRECTIONAL) __pte |= IOMMU_PTE_IR | IOMMU_PTE_IW; - WARN_ON(*pte); + WARN_ON_ONCE(*pte); *pte = __pte; @@ -2357,7 +2501,7 @@ static void dma_ops_domain_unmap(struct dma_ops_domain *dom, pte += PM_LEVEL_INDEX(0, address); - WARN_ON(!*pte); + WARN_ON_ONCE(!*pte); *pte = 0ULL; } @@ -2393,26 +2537,11 @@ static dma_addr_t __map_single(struct device *dev, if (align) align_mask = (1UL << get_order(size)) - 1; -retry: address = dma_ops_alloc_addresses(dev, dma_dom, pages, align_mask, dma_mask); - if (unlikely(address == DMA_ERROR_CODE)) { - /* - * setting next_address here will let the address - * allocator only scan the new allocated range in the - * first run. This is a small optimization. - */ - dma_dom->next_address = dma_dom->aperture_size; - if (alloc_new_range(dma_dom, false, GFP_ATOMIC)) - goto out; - - /* - * aperture was successfully enlarged by 128 MB, try - * allocation again - */ - goto retry; - } + if (address == DMA_ERROR_CODE) + goto out; start = address; for (i = 0; i < pages; ++i) { @@ -2427,11 +2556,10 @@ retry: ADD_STATS_COUNTER(alloced_io_mem, size); - if (unlikely(dma_dom->need_flush && !amd_iommu_unmap_flush)) { - domain_flush_tlb(&dma_dom->domain); - dma_dom->need_flush = false; - } else if (unlikely(amd_iommu_np_cache)) + if (unlikely(amd_iommu_np_cache)) { domain_flush_pages(&dma_dom->domain, address, size); + domain_flush_complete(&dma_dom->domain); + } out: return address; @@ -2478,11 +2606,6 @@ static void __unmap_single(struct dma_ops_domain *dma_dom, SUB_STATS_COUNTER(alloced_io_mem, size); dma_ops_free_addresses(dma_dom, dma_addr, pages); - - if (amd_iommu_unmap_flush || dma_dom->need_flush) { - domain_flush_pages(&dma_dom->domain, flush_addr, size); - dma_dom->need_flush = false; - } } /* @@ -2493,11 +2616,9 @@ static dma_addr_t map_page(struct device *dev, struct page *page, enum dma_data_direction dir, struct dma_attrs *attrs) { - unsigned long flags; + phys_addr_t paddr = page_to_phys(page) + offset; struct protection_domain *domain; - dma_addr_t addr; u64 dma_mask; - phys_addr_t paddr = page_to_phys(page) + offset; INC_STATS_COUNTER(cnt_map_single); @@ -2509,19 +2630,8 @@ static dma_addr_t map_page(struct device *dev, struct page *page, dma_mask = *dev->dma_mask; - spin_lock_irqsave(&domain->lock, flags); - - addr = __map_single(dev, domain->priv, paddr, size, dir, false, + return __map_single(dev, domain->priv, paddr, size, dir, false, dma_mask); - if (addr == DMA_ERROR_CODE) - goto out; - - domain_flush_complete(domain); - -out: - spin_unlock_irqrestore(&domain->lock, flags); - - return addr; } /* @@ -2530,7 +2640,6 @@ out: static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - unsigned long flags; struct protection_domain *domain; INC_STATS_COUNTER(cnt_unmap_single); @@ -2539,13 +2648,7 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, if (IS_ERR(domain)) return; - spin_lock_irqsave(&domain->lock, flags); - __unmap_single(domain->priv, dma_addr, size, dir); - - domain_flush_complete(domain); - - spin_unlock_irqrestore(&domain->lock, flags); } /* @@ -2556,7 +2659,6 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction dir, struct dma_attrs *attrs) { - unsigned long flags; struct protection_domain *domain; int i; struct scatterlist *s; @@ -2572,8 +2674,6 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, dma_mask = *dev->dma_mask; - spin_lock_irqsave(&domain->lock, flags); - for_each_sg(sglist, s, nelems, i) { paddr = sg_phys(s); @@ -2588,12 +2688,8 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, goto unmap; } - domain_flush_complete(domain); - -out: - spin_unlock_irqrestore(&domain->lock, flags); - return mapped_elems; + unmap: for_each_sg(sglist, s, mapped_elems, i) { if (s->dma_address) @@ -2602,9 +2698,7 @@ unmap: s->dma_address = s->dma_length = 0; } - mapped_elems = 0; - - goto out; + return 0; } /* @@ -2615,7 +2709,6 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction dir, struct dma_attrs *attrs) { - unsigned long flags; struct protection_domain *domain; struct scatterlist *s; int i; @@ -2626,17 +2719,11 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist, if (IS_ERR(domain)) return; - spin_lock_irqsave(&domain->lock, flags); - for_each_sg(sglist, s, nelems, i) { __unmap_single(domain->priv, s->dma_address, s->dma_length, dir); s->dma_address = s->dma_length = 0; } - - domain_flush_complete(domain); - - spin_unlock_irqrestore(&domain->lock, flags); } /* @@ -2648,7 +2735,6 @@ static void *alloc_coherent(struct device *dev, size_t size, { u64 dma_mask = dev->coherent_dma_mask; struct protection_domain *domain; - unsigned long flags; struct page *page; INC_STATS_COUNTER(cnt_alloc_coherent); @@ -2680,19 +2766,11 @@ static void *alloc_coherent(struct device *dev, size_t size, if (!dma_mask) dma_mask = *dev->dma_mask; - spin_lock_irqsave(&domain->lock, flags); - *dma_addr = __map_single(dev, domain->priv, page_to_phys(page), size, DMA_BIDIRECTIONAL, true, dma_mask); - if (*dma_addr == DMA_ERROR_CODE) { - spin_unlock_irqrestore(&domain->lock, flags); + if (*dma_addr == DMA_ERROR_CODE) goto out_free; - } - - domain_flush_complete(domain); - - spin_unlock_irqrestore(&domain->lock, flags); return page_address(page); @@ -2712,7 +2790,6 @@ static void free_coherent(struct device *dev, size_t size, struct dma_attrs *attrs) { struct protection_domain *domain; - unsigned long flags; struct page *page; INC_STATS_COUNTER(cnt_free_coherent); @@ -2724,14 +2801,8 @@ static void free_coherent(struct device *dev, size_t size, if (IS_ERR(domain)) goto free_mem; - spin_lock_irqsave(&domain->lock, flags); - __unmap_single(domain->priv, dma_addr, size, DMA_BIDIRECTIONAL); - domain_flush_complete(domain); - - spin_unlock_irqrestore(&domain->lock, flags); - free_mem: if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT)) __free_pages(page, get_order(size)); @@ -2746,14 +2817,43 @@ static int amd_iommu_dma_supported(struct device *dev, u64 mask) return check_device(dev); } +static int set_dma_mask(struct device *dev, u64 mask) +{ + struct protection_domain *domain; + int max_apertures = 1; + + domain = get_domain(dev); + if (IS_ERR(domain)) + return PTR_ERR(domain); + + if (mask == DMA_BIT_MASK(64)) + max_apertures = 8; + else if (mask > DMA_BIT_MASK(32)) + max_apertures = 4; + + /* + * To prevent lock contention it doesn't make sense to allocate more + * apertures than online cpus + */ + if (max_apertures > num_online_cpus()) + max_apertures = num_online_cpus(); + + if (dma_ops_domain_alloc_apertures(domain->priv, max_apertures)) + dev_err(dev, "Can't allocate %d iommu apertures\n", + max_apertures); + + return 0; +} + static struct dma_map_ops amd_iommu_dma_ops = { - .alloc = alloc_coherent, - .free = free_coherent, - .map_page = map_page, - .unmap_page = unmap_page, - .map_sg = map_sg, - .unmap_sg = unmap_sg, - .dma_supported = amd_iommu_dma_supported, + .alloc = alloc_coherent, + .free = free_coherent, + .map_page = map_page, + .unmap_page = unmap_page, + .map_sg = map_sg, + .unmap_sg = unmap_sg, + .dma_supported = amd_iommu_dma_supported, + .set_dma_mask = set_dma_mask, }; int __init amd_iommu_init_api(void) @@ -3757,11 +3857,9 @@ static struct irq_domain *get_irq_domain(struct irq_alloc_info *info) case X86_IRQ_ALLOC_TYPE_MSI: case X86_IRQ_ALLOC_TYPE_MSIX: devid = get_device_id(&info->msi_dev->dev); - if (devid >= 0) { - iommu = amd_iommu_rlookup_table[devid]; - if (iommu) - return iommu->msi_domain; - } + iommu = amd_iommu_rlookup_table[devid]; + if (iommu) + return iommu->msi_domain; break; default: break; diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index b08cf57bf455..9d32b20a5e9a 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -425,46 +425,6 @@ struct protection_domain { }; /* - * For dynamic growth the aperture size is split into ranges of 128MB of - * DMA address space each. This struct represents one such range. - */ -struct aperture_range { - - /* address allocation bitmap */ - unsigned long *bitmap; - - /* - * Array of PTE pages for the aperture. In this array we save all the - * leaf pages of the domain page table used for the aperture. This way - * we don't need to walk the page table to find a specific PTE. We can - * just calculate its address in constant time. - */ - u64 *pte_pages[64]; - - unsigned long offset; -}; - -/* - * Data container for a dma_ops specific protection domain - */ -struct dma_ops_domain { - /* generic protection domain information */ - struct protection_domain domain; - - /* size of the aperture for the mappings */ - unsigned long aperture_size; - - /* address we start to search for free addresses */ - unsigned long next_address; - - /* address space relevant data */ - struct aperture_range *aperture[APERTURE_MAX_RANGES]; - - /* This will be set to true when TLB needs to be flushed */ - bool need_flush; -}; - -/* * Structure where we save information about one hardware AMD IOMMU in the * system. */ diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 7caf2fa237f2..c865737326e1 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -432,7 +432,7 @@ static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm) unbind_pasid(pasid_state); } -static struct mmu_notifier_ops iommu_mn = { +static const struct mmu_notifier_ops iommu_mn = { .release = mn_release, .clear_flush_young = mn_clear_flush_young, .invalidate_page = mn_invalidate_page, @@ -513,43 +513,39 @@ static bool access_error(struct vm_area_struct *vma, struct fault *fault) static void do_fault(struct work_struct *work) { struct fault *fault = container_of(work, struct fault, work); - struct mm_struct *mm; struct vm_area_struct *vma; + int ret = VM_FAULT_ERROR; + unsigned int flags = 0; + struct mm_struct *mm; u64 address; - int ret, write; - - write = !!(fault->flags & PPR_FAULT_WRITE); mm = fault->state->mm; address = fault->address; + if (fault->flags & PPR_FAULT_USER) + flags |= FAULT_FLAG_USER; + if (fault->flags & PPR_FAULT_WRITE) + flags |= FAULT_FLAG_WRITE; + down_read(&mm->mmap_sem); vma = find_extend_vma(mm, address); - if (!vma || address < vma->vm_start) { + if (!vma || address < vma->vm_start) /* failed to get a vma in the right range */ - up_read(&mm->mmap_sem); - handle_fault_error(fault); goto out; - } /* Check if we have the right permissions on the vma */ - if (access_error(vma, fault)) { - up_read(&mm->mmap_sem); - handle_fault_error(fault); + if (access_error(vma, fault)) goto out; - } - ret = handle_mm_fault(mm, vma, address, write); - if (ret & VM_FAULT_ERROR) { - /* failed to service fault */ - up_read(&mm->mmap_sem); - handle_fault_error(fault); - goto out; - } + ret = handle_mm_fault(mm, vma, address, flags); +out: up_read(&mm->mmap_sem); -out: + if (ret & VM_FAULT_ERROR) + /* failed to service fault */ + handle_fault_error(fault); + finish_pri_tag(fault->dev_state, fault->state, fault->tag); put_pasid_state(fault->state); diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 4e5118a4cd30..20875341c865 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -40,7 +40,10 @@ #define IDR0_ST_LVL_SHIFT 27 #define IDR0_ST_LVL_MASK 0x3 #define IDR0_ST_LVL_2LVL (1 << IDR0_ST_LVL_SHIFT) -#define IDR0_STALL_MODEL (3 << 24) +#define IDR0_STALL_MODEL_SHIFT 24 +#define IDR0_STALL_MODEL_MASK 0x3 +#define IDR0_STALL_MODEL_STALL (0 << IDR0_STALL_MODEL_SHIFT) +#define IDR0_STALL_MODEL_FORCE (2 << IDR0_STALL_MODEL_SHIFT) #define IDR0_TTENDIAN_SHIFT 21 #define IDR0_TTENDIAN_MASK 0x3 #define IDR0_TTENDIAN_LE (2 << IDR0_TTENDIAN_SHIFT) @@ -253,6 +256,9 @@ #define STRTAB_STE_1_STRW_EL2 2UL #define STRTAB_STE_1_STRW_SHIFT 30 +#define STRTAB_STE_1_SHCFG_INCOMING 1UL +#define STRTAB_STE_1_SHCFG_SHIFT 44 + #define STRTAB_STE_2_S2VMID_SHIFT 0 #define STRTAB_STE_2_S2VMID_MASK 0xffffUL #define STRTAB_STE_2_VTCR_SHIFT 32 @@ -378,7 +384,6 @@ #define PRIQ_0_SID_MASK 0xffffffffUL #define PRIQ_0_SSID_SHIFT 32 #define PRIQ_0_SSID_MASK 0xfffffUL -#define PRIQ_0_OF (1UL << 57) #define PRIQ_0_PERM_PRIV (1UL << 58) #define PRIQ_0_PERM_EXEC (1UL << 59) #define PRIQ_0_PERM_READ (1UL << 60) @@ -855,15 +860,17 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) }; dev_err(smmu->dev, "CMDQ error (cons 0x%08x): %s\n", cons, - cerror_str[idx]); + idx < ARRAY_SIZE(cerror_str) ? cerror_str[idx] : "Unknown"); switch (idx) { - case CMDQ_ERR_CERROR_ILL_IDX: - break; case CMDQ_ERR_CERROR_ABT_IDX: dev_err(smmu->dev, "retrying command fetch\n"); case CMDQ_ERR_CERROR_NONE_IDX: return; + case CMDQ_ERR_CERROR_ILL_IDX: + /* Fallthrough */ + default: + break; } /* @@ -1042,6 +1049,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT : STRTAB_STE_0_CFG_BYPASS; dst[0] = cpu_to_le64(val); + dst[1] = cpu_to_le64(STRTAB_STE_1_SHCFG_INCOMING + << STRTAB_STE_1_SHCFG_SHIFT); dst[2] = 0; /* Nuke the VMID */ if (ste_live) arm_smmu_sync_ste_for_sid(smmu, sid); @@ -1056,12 +1065,14 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, STRTAB_STE_1_S1C_CACHE_WBRA << STRTAB_STE_1_S1COR_SHIFT | STRTAB_STE_1_S1C_SH_ISH << STRTAB_STE_1_S1CSH_SHIFT | - STRTAB_STE_1_S1STALLD | #ifdef CONFIG_PCI_ATS STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT | #endif STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT); + if (smmu->features & ARM_SMMU_FEAT_STALLS) + dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD); + val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK << STRTAB_STE_0_S1CTXPTR_SHIFT) | STRTAB_STE_0_CFG_S1_TRANS; @@ -1123,8 +1134,8 @@ static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid) strtab = &cfg->strtab[(sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS]; desc->span = STRTAB_SPLIT + 1; - desc->l2ptr = dma_zalloc_coherent(smmu->dev, size, &desc->l2ptr_dma, - GFP_KERNEL); + desc->l2ptr = dmam_alloc_coherent(smmu->dev, size, &desc->l2ptr_dma, + GFP_KERNEL | __GFP_ZERO); if (!desc->l2ptr) { dev_err(smmu->dev, "failed to allocate l2 stream table for SID %u\n", @@ -1250,50 +1261,50 @@ static int arm_smmu_device_disable(struct arm_smmu_device *smmu); static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev) { - u32 gerror, gerrorn; + u32 gerror, gerrorn, active; struct arm_smmu_device *smmu = dev; gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR); gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN); - gerror ^= gerrorn; - if (!(gerror & GERROR_ERR_MASK)) + active = gerror ^ gerrorn; + if (!(active & GERROR_ERR_MASK)) return IRQ_NONE; /* No errors pending */ dev_warn(smmu->dev, "unexpected global error reported (0x%08x), this could be serious\n", - gerror); + active); - if (gerror & GERROR_SFM_ERR) { + if (active & GERROR_SFM_ERR) { dev_err(smmu->dev, "device has entered Service Failure Mode!\n"); arm_smmu_device_disable(smmu); } - if (gerror & GERROR_MSI_GERROR_ABT_ERR) + if (active & GERROR_MSI_GERROR_ABT_ERR) dev_warn(smmu->dev, "GERROR MSI write aborted\n"); - if (gerror & GERROR_MSI_PRIQ_ABT_ERR) { + if (active & GERROR_MSI_PRIQ_ABT_ERR) { dev_warn(smmu->dev, "PRIQ MSI write aborted\n"); arm_smmu_priq_handler(irq, smmu->dev); } - if (gerror & GERROR_MSI_EVTQ_ABT_ERR) { + if (active & GERROR_MSI_EVTQ_ABT_ERR) { dev_warn(smmu->dev, "EVTQ MSI write aborted\n"); arm_smmu_evtq_handler(irq, smmu->dev); } - if (gerror & GERROR_MSI_CMDQ_ABT_ERR) { + if (active & GERROR_MSI_CMDQ_ABT_ERR) { dev_warn(smmu->dev, "CMDQ MSI write aborted\n"); arm_smmu_cmdq_sync_handler(irq, smmu->dev); } - if (gerror & GERROR_PRIQ_ABT_ERR) + if (active & GERROR_PRIQ_ABT_ERR) dev_err(smmu->dev, "PRIQ write aborted -- events may have been lost\n"); - if (gerror & GERROR_EVTQ_ABT_ERR) + if (active & GERROR_EVTQ_ABT_ERR) dev_err(smmu->dev, "EVTQ write aborted -- events may have been lost\n"); - if (gerror & GERROR_CMDQ_ERR) + if (active & GERROR_CMDQ_ERR) arm_smmu_cmdq_skip_err(smmu); writel(gerror, smmu->base + ARM_SMMU_GERRORN); @@ -1335,7 +1346,7 @@ static void arm_smmu_tlb_inv_context(void *cookie) } static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, - bool leaf, void *cookie) + size_t granule, bool leaf, void *cookie) { struct arm_smmu_domain *smmu_domain = cookie; struct arm_smmu_device *smmu = smmu_domain->smmu; @@ -1354,7 +1365,10 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; } - arm_smmu_cmdq_issue_cmd(smmu, &cmd); + do { + arm_smmu_cmdq_issue_cmd(smmu, &cmd); + cmd.tlbi.addr += granule; + } while (size -= granule); } static struct iommu_gather_ops arm_smmu_gather_ops = { @@ -1429,10 +1443,10 @@ static void arm_smmu_domain_free(struct iommu_domain *domain) struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg; if (cfg->cdptr) { - dma_free_coherent(smmu_domain->smmu->dev, - CTXDESC_CD_DWORDS << 3, - cfg->cdptr, - cfg->cdptr_dma); + dmam_free_coherent(smmu_domain->smmu->dev, + CTXDESC_CD_DWORDS << 3, + cfg->cdptr, + cfg->cdptr_dma); arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid); } @@ -1457,8 +1471,9 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain, if (IS_ERR_VALUE(asid)) return asid; - cfg->cdptr = dma_zalloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3, - &cfg->cdptr_dma, GFP_KERNEL); + cfg->cdptr = dmam_alloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3, + &cfg->cdptr_dma, + GFP_KERNEL | __GFP_ZERO); if (!cfg->cdptr) { dev_warn(smmu->dev, "failed to allocate context descriptor\n"); ret = -ENOMEM; @@ -1804,13 +1819,13 @@ static int arm_smmu_add_device(struct device *dev) smmu = arm_smmu_get_for_pci_dev(pdev); if (!smmu) { ret = -ENOENT; - goto out_put_group; + goto out_remove_dev; } smmu_group = kzalloc(sizeof(*smmu_group), GFP_KERNEL); if (!smmu_group) { ret = -ENOMEM; - goto out_put_group; + goto out_remove_dev; } smmu_group->ste.valid = true; @@ -1826,20 +1841,20 @@ static int arm_smmu_add_device(struct device *dev) for (i = 0; i < smmu_group->num_sids; ++i) { /* If we already know about this SID, then we're done */ if (smmu_group->sids[i] == sid) - return 0; + goto out_put_group; } /* Check the SID is in range of the SMMU and our stream table */ if (!arm_smmu_sid_in_range(smmu, sid)) { ret = -ERANGE; - goto out_put_group; + goto out_remove_dev; } /* Ensure l2 strtab is initialised */ if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) { ret = arm_smmu_init_l2_strtab(smmu, sid); if (ret) - goto out_put_group; + goto out_remove_dev; } /* Resize the SID array for the group */ @@ -1849,16 +1864,20 @@ static int arm_smmu_add_device(struct device *dev) if (!sids) { smmu_group->num_sids--; ret = -ENOMEM; - goto out_put_group; + goto out_remove_dev; } /* Add the new SID */ sids[smmu_group->num_sids - 1] = sid; smmu_group->sids = sids; - return 0; out_put_group: iommu_group_put(group); + return 0; + +out_remove_dev: + iommu_group_remove_device(dev); + iommu_group_put(group); return ret; } @@ -1937,7 +1956,7 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu, { size_t qsz = ((1 << q->max_n_shift) * dwords) << 3; - q->base = dma_alloc_coherent(smmu->dev, qsz, &q->base_dma, GFP_KERNEL); + q->base = dmam_alloc_coherent(smmu->dev, qsz, &q->base_dma, GFP_KERNEL); if (!q->base) { dev_err(smmu->dev, "failed to allocate queue (0x%zx bytes)\n", qsz); @@ -1957,23 +1976,6 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu, return 0; } -static void arm_smmu_free_one_queue(struct arm_smmu_device *smmu, - struct arm_smmu_queue *q) -{ - size_t qsz = ((1 << q->max_n_shift) * q->ent_dwords) << 3; - - dma_free_coherent(smmu->dev, qsz, q->base, q->base_dma); -} - -static void arm_smmu_free_queues(struct arm_smmu_device *smmu) -{ - arm_smmu_free_one_queue(smmu, &smmu->cmdq.q); - arm_smmu_free_one_queue(smmu, &smmu->evtq.q); - - if (smmu->features & ARM_SMMU_FEAT_PRI) - arm_smmu_free_one_queue(smmu, &smmu->priq.q); -} - static int arm_smmu_init_queues(struct arm_smmu_device *smmu) { int ret; @@ -1983,49 +1985,20 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu) ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD, ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS); if (ret) - goto out; + return ret; /* evtq */ ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, ARM_SMMU_EVTQ_PROD, ARM_SMMU_EVTQ_CONS, EVTQ_ENT_DWORDS); if (ret) - goto out_free_cmdq; + return ret; /* priq */ if (!(smmu->features & ARM_SMMU_FEAT_PRI)) return 0; - ret = arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD, - ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS); - if (ret) - goto out_free_evtq; - - return 0; - -out_free_evtq: - arm_smmu_free_one_queue(smmu, &smmu->evtq.q); -out_free_cmdq: - arm_smmu_free_one_queue(smmu, &smmu->cmdq.q); -out: - return ret; -} - -static void arm_smmu_free_l2_strtab(struct arm_smmu_device *smmu) -{ - int i; - size_t size; - struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg; - - size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3); - for (i = 0; i < cfg->num_l1_ents; ++i) { - struct arm_smmu_strtab_l1_desc *desc = &cfg->l1_desc[i]; - - if (!desc->l2ptr) - continue; - - dma_free_coherent(smmu->dev, size, desc->l2ptr, - desc->l2ptr_dma); - } + return arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD, + ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS); } static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu) @@ -2054,7 +2027,6 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu) void *strtab; u64 reg; u32 size, l1size; - int ret; struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg; /* @@ -2077,8 +2049,8 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu) size, smmu->sid_bits); l1size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3); - strtab = dma_zalloc_coherent(smmu->dev, l1size, &cfg->strtab_dma, - GFP_KERNEL); + strtab = dmam_alloc_coherent(smmu->dev, l1size, &cfg->strtab_dma, + GFP_KERNEL | __GFP_ZERO); if (!strtab) { dev_err(smmu->dev, "failed to allocate l1 stream table (%u bytes)\n", @@ -2095,13 +2067,7 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu) << STRTAB_BASE_CFG_SPLIT_SHIFT; cfg->strtab_base_cfg = reg; - ret = arm_smmu_init_l1_strtab(smmu); - if (ret) - dma_free_coherent(smmu->dev, - l1size, - strtab, - cfg->strtab_dma); - return ret; + return arm_smmu_init_l1_strtab(smmu); } static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu) @@ -2112,8 +2078,8 @@ static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu) struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg; size = (1 << smmu->sid_bits) * (STRTAB_STE_DWORDS << 3); - strtab = dma_zalloc_coherent(smmu->dev, size, &cfg->strtab_dma, - GFP_KERNEL); + strtab = dmam_alloc_coherent(smmu->dev, size, &cfg->strtab_dma, + GFP_KERNEL | __GFP_ZERO); if (!strtab) { dev_err(smmu->dev, "failed to allocate linear stream table (%u bytes)\n", @@ -2157,21 +2123,6 @@ static int arm_smmu_init_strtab(struct arm_smmu_device *smmu) return 0; } -static void arm_smmu_free_strtab(struct arm_smmu_device *smmu) -{ - struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg; - u32 size = cfg->num_l1_ents; - - if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) { - arm_smmu_free_l2_strtab(smmu); - size *= STRTAB_L1_DESC_DWORDS << 3; - } else { - size *= STRTAB_STE_DWORDS * 3; - } - - dma_free_coherent(smmu->dev, size, cfg->strtab, cfg->strtab_dma); -} - static int arm_smmu_init_structures(struct arm_smmu_device *smmu) { int ret; @@ -2180,21 +2131,7 @@ static int arm_smmu_init_structures(struct arm_smmu_device *smmu) if (ret) return ret; - ret = arm_smmu_init_strtab(smmu); - if (ret) - goto out_free_queues; - - return 0; - -out_free_queues: - arm_smmu_free_queues(smmu); - return ret; -} - -static void arm_smmu_free_structures(struct arm_smmu_device *smmu) -{ - arm_smmu_free_strtab(smmu); - arm_smmu_free_queues(smmu); + return arm_smmu_init_strtab(smmu); } static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val, @@ -2532,8 +2469,12 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu) dev_warn(smmu->dev, "IDR0.COHACC overridden by dma-coherent property (%s)\n", coherent ? "true" : "false"); - if (reg & IDR0_STALL_MODEL) + switch (reg & IDR0_STALL_MODEL_MASK << IDR0_STALL_MODEL_SHIFT) { + case IDR0_STALL_MODEL_STALL: + /* Fallthrough */ + case IDR0_STALL_MODEL_FORCE: smmu->features |= ARM_SMMU_FEAT_STALLS; + } if (reg & IDR0_S1P) smmu->features |= ARM_SMMU_FEAT_TRANS_S1; @@ -2699,15 +2640,7 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev) platform_set_drvdata(pdev, smmu); /* Reset the device */ - ret = arm_smmu_device_reset(smmu); - if (ret) - goto out_free_structures; - - return 0; - -out_free_structures: - arm_smmu_free_structures(smmu); - return ret; + return arm_smmu_device_reset(smmu); } static int arm_smmu_device_remove(struct platform_device *pdev) @@ -2715,7 +2648,6 @@ static int arm_smmu_device_remove(struct platform_device *pdev) struct arm_smmu_device *smmu = platform_get_drvdata(pdev); arm_smmu_device_disable(smmu); - arm_smmu_free_structures(smmu); return 0; } diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 47dc7a793f5c..59ee4b8a3236 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -582,7 +582,7 @@ static void arm_smmu_tlb_inv_context(void *cookie) } static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, - bool leaf, void *cookie) + size_t granule, bool leaf, void *cookie) { struct arm_smmu_domain *smmu_domain = cookie; struct arm_smmu_cfg *cfg = &smmu_domain->cfg; @@ -597,12 +597,18 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, if (!IS_ENABLED(CONFIG_64BIT) || smmu->version == ARM_SMMU_V1) { iova &= ~12UL; iova |= ARM_SMMU_CB_ASID(cfg); - writel_relaxed(iova, reg); + do { + writel_relaxed(iova, reg); + iova += granule; + } while (size -= granule); #ifdef CONFIG_64BIT } else { iova >>= 12; iova |= (u64)ARM_SMMU_CB_ASID(cfg) << 48; - writeq_relaxed(iova, reg); + do { + writeq_relaxed(iova, reg); + iova += granule >> 12; + } while (size -= granule); #endif } #ifdef CONFIG_64BIT @@ -610,7 +616,11 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, reg = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx); reg += leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L : ARM_SMMU_CB_S2_TLBIIPAS2; - writeq_relaxed(iova >> 12, reg); + iova >>= 12; + do { + writeq_relaxed(iova, reg); + iova += granule >> 12; + } while (size -= granule); #endif } else { reg = ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_TLBIVMID; @@ -945,9 +955,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain) free_irq(irq, domain); } - if (smmu_domain->pgtbl_ops) - free_io_pgtable_ops(smmu_domain->pgtbl_ops); - + free_io_pgtable_ops(smmu_domain->pgtbl_ops); __arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx); } @@ -1357,6 +1365,7 @@ static int arm_smmu_add_device(struct device *dev) if (IS_ERR(group)) return PTR_ERR(group); + iommu_group_put(group); return 0; } diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 3a20db4f8604..72d6182666cb 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -21,10 +21,13 @@ #include <linux/device.h> #include <linux/dma-iommu.h> +#include <linux/gfp.h> #include <linux/huge_mm.h> #include <linux/iommu.h> #include <linux/iova.h> #include <linux/mm.h> +#include <linux/scatterlist.h> +#include <linux/vmalloc.h> int iommu_dma_init(void) { @@ -191,6 +194,7 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count, gfp_t gfp) { struct page **pages; unsigned int i = 0, array_size = count * sizeof(*pages); + unsigned int order = MAX_ORDER; if (array_size <= PAGE_SIZE) pages = kzalloc(array_size, GFP_KERNEL); @@ -204,14 +208,15 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count, gfp_t gfp) while (count) { struct page *page = NULL; - int j, order = __fls(count); + int j; /* * Higher-order allocations are a convenience rather * than a necessity, hence using __GFP_NORETRY until * falling back to single-page allocations. */ - for (order = min(order, MAX_ORDER); order > 0; order--) { + for (order = min_t(unsigned int, order, __fls(count)); + order > 0; order--) { page = alloc_pages(gfp | __GFP_NORETRY, order); if (!page) continue; @@ -453,7 +458,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, size_t s_offset = iova_offset(iovad, s->offset); size_t s_length = s->length; - sg_dma_address(s) = s->offset; + sg_dma_address(s) = s_offset; sg_dma_len(s) = s_length; s->offset -= s_offset; s_length = iova_align(iovad, s_length + s_offset); diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 7df97777662d..8bbcbfe7695c 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -38,9 +38,6 @@ #define io_pgtable_to_data(x) \ container_of((x), struct arm_lpae_io_pgtable, iop) -#define io_pgtable_ops_to_pgtable(x) \ - container_of((x), struct io_pgtable, ops) - #define io_pgtable_ops_to_data(x) \ io_pgtable_to_data(io_pgtable_ops_to_pgtable(x)) @@ -58,8 +55,10 @@ ((((d)->levels - ((l) - ARM_LPAE_START_LVL(d) + 1)) \ * (d)->bits_per_level) + (d)->pg_shift) +#define ARM_LPAE_GRANULE(d) (1UL << (d)->pg_shift) + #define ARM_LPAE_PAGES_PER_PGD(d) \ - DIV_ROUND_UP((d)->pgd_size, 1UL << (d)->pg_shift) + DIV_ROUND_UP((d)->pgd_size, ARM_LPAE_GRANULE(d)) /* * Calculate the index at level l used to map virtual address a using the @@ -169,7 +168,7 @@ /* IOPTE accessors */ #define iopte_deref(pte,d) \ (__va((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1) \ - & ~((1ULL << (d)->pg_shift) - 1))) + & ~(ARM_LPAE_GRANULE(d) - 1ULL))) #define iopte_type(pte,l) \ (((pte) >> ARM_LPAE_PTE_TYPE_SHIFT) & ARM_LPAE_PTE_TYPE_MASK) @@ -326,7 +325,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, /* Grab a pointer to the next level */ pte = *ptep; if (!pte) { - cptep = __arm_lpae_alloc_pages(1UL << data->pg_shift, + cptep = __arm_lpae_alloc_pages(ARM_LPAE_GRANULE(data), GFP_ATOMIC, cfg); if (!cptep) return -ENOMEM; @@ -405,17 +404,18 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl, arm_lpae_iopte *start, *end; unsigned long table_size; - /* Only leaf entries at the last level */ - if (lvl == ARM_LPAE_MAX_LEVELS - 1) - return; - if (lvl == ARM_LPAE_START_LVL(data)) table_size = data->pgd_size; else - table_size = 1UL << data->pg_shift; + table_size = ARM_LPAE_GRANULE(data); start = ptep; - end = (void *)ptep + table_size; + + /* Only leaf entries at the last level */ + if (lvl == ARM_LPAE_MAX_LEVELS - 1) + end = ptep; + else + end = (void *)ptep + table_size; while (ptep != end) { arm_lpae_iopte pte = *ptep++; @@ -473,7 +473,7 @@ static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, __arm_lpae_set_pte(ptep, table, cfg); iova &= ~(blk_size - 1); - cfg->tlb->tlb_add_flush(iova, blk_size, true, data->iop.cookie); + cfg->tlb->tlb_add_flush(iova, blk_size, blk_size, true, data->iop.cookie); return size; } @@ -486,11 +486,13 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, void *cookie = data->iop.cookie; size_t blk_size = ARM_LPAE_BLOCK_SIZE(lvl, data); + /* Something went horribly wrong and we ran out of page table */ + if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS)) + return 0; + ptep += ARM_LPAE_LVL_IDX(iova, lvl, data); pte = *ptep; - - /* Something went horribly wrong and we ran out of page table */ - if (WARN_ON(!pte || (lvl == ARM_LPAE_MAX_LEVELS))) + if (WARN_ON(!pte)) return 0; /* If the size matches this level, we're in the right place */ @@ -499,12 +501,13 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, if (!iopte_leaf(pte, lvl)) { /* Also flush any partial walks */ - tlb->tlb_add_flush(iova, size, false, cookie); + tlb->tlb_add_flush(iova, size, ARM_LPAE_GRANULE(data), + false, cookie); tlb->tlb_sync(cookie); ptep = iopte_deref(pte, data); __arm_lpae_free_pgtable(data, lvl + 1, ptep); } else { - tlb->tlb_add_flush(iova, size, true, cookie); + tlb->tlb_add_flush(iova, size, size, true, cookie); } return size; @@ -570,7 +573,7 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops, return 0; found_translation: - iova &= ((1 << data->pg_shift) - 1); + iova &= (ARM_LPAE_GRANULE(data) - 1); return ((phys_addr_t)iopte_to_pfn(pte,data) << data->pg_shift) | iova; } @@ -668,7 +671,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) | (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT); - switch (1 << data->pg_shift) { + switch (ARM_LPAE_GRANULE(data)) { case SZ_4K: reg |= ARM_LPAE_TCR_TG0_4K; break; @@ -769,7 +772,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) sl = ARM_LPAE_START_LVL(data); - switch (1 << data->pg_shift) { + switch (ARM_LPAE_GRANULE(data)) { case SZ_4K: reg |= ARM_LPAE_TCR_TG0_4K; sl++; /* SL0 format is different for 4K granule size */ @@ -889,8 +892,8 @@ static void dummy_tlb_flush_all(void *cookie) WARN_ON(cookie != cfg_cookie); } -static void dummy_tlb_add_flush(unsigned long iova, size_t size, bool leaf, - void *cookie) +static void dummy_tlb_add_flush(unsigned long iova, size_t size, + size_t granule, bool leaf, void *cookie) { WARN_ON(cookie != cfg_cookie); WARN_ON(!(size & cfg_cookie->pgsize_bitmap)); diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h index ac9e2341a633..36673c83de58 100644 --- a/drivers/iommu/io-pgtable.h +++ b/drivers/iommu/io-pgtable.h @@ -26,8 +26,8 @@ enum io_pgtable_fmt { */ struct iommu_gather_ops { void (*tlb_flush_all)(void *cookie); - void (*tlb_add_flush)(unsigned long iova, size_t size, bool leaf, - void *cookie); + void (*tlb_add_flush)(unsigned long iova, size_t size, size_t granule, + bool leaf, void *cookie); void (*tlb_sync)(void *cookie); }; @@ -131,6 +131,8 @@ struct io_pgtable { struct io_pgtable_ops ops; }; +#define io_pgtable_ops_to_pgtable(x) container_of((x), struct io_pgtable, ops) + /** * struct io_pgtable_init_fns - Alloc/free a set of page tables for a * particular format. diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 8cf605fa9946..2fdbac67a77f 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -277,8 +277,8 @@ static void ipmmu_tlb_flush_all(void *cookie) ipmmu_tlb_invalidate(domain); } -static void ipmmu_tlb_add_flush(unsigned long iova, size_t size, bool leaf, - void *cookie) +static void ipmmu_tlb_add_flush(unsigned long iova, size_t size, + size_t granule, bool leaf, void *cookie) { /* The hardware doesn't support selective TLB flush. */ } @@ -295,7 +295,7 @@ static struct iommu_gather_ops ipmmu_gather_ops = { static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain) { - phys_addr_t ttbr; + u64 ttbr; /* * Allocate the page table operations. diff --git a/drivers/iommu/msm_iommu_dev.c b/drivers/iommu/msm_iommu_dev.c index b6d01f97e537..4b09e815accf 100644 --- a/drivers/iommu/msm_iommu_dev.c +++ b/drivers/iommu/msm_iommu_dev.c @@ -359,30 +359,19 @@ static struct platform_driver msm_iommu_ctx_driver = { .remove = msm_iommu_ctx_remove, }; +static struct platform_driver * const drivers[] = { + &msm_iommu_driver, + &msm_iommu_ctx_driver, +}; + static int __init msm_iommu_driver_init(void) { - int ret; - ret = platform_driver_register(&msm_iommu_driver); - if (ret != 0) { - pr_err("Failed to register IOMMU driver\n"); - goto error; - } - - ret = platform_driver_register(&msm_iommu_ctx_driver); - if (ret != 0) { - platform_driver_unregister(&msm_iommu_driver); - pr_err("Failed to register IOMMU context driver\n"); - goto error; - } - -error: - return ret; + return platform_register_drivers(drivers, ARRAY_SIZE(drivers)); } static void __exit msm_iommu_driver_exit(void) { - platform_driver_unregister(&msm_iommu_ctx_driver); - platform_driver_unregister(&msm_iommu_driver); + platform_unregister_drivers(drivers, ARRAY_SIZE(drivers)); } subsys_initcall(msm_iommu_driver_init); diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index 471ee36b9c6e..a04d491cf431 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -49,7 +49,7 @@ static bool s390_iommu_capable(enum iommu_cap cap) } } -struct iommu_domain *s390_domain_alloc(unsigned domain_type) +static struct iommu_domain *s390_domain_alloc(unsigned domain_type) { struct s390_domain *s390_domain; @@ -73,7 +73,7 @@ struct iommu_domain *s390_domain_alloc(unsigned domain_type) return &s390_domain->domain; } -void s390_domain_free(struct iommu_domain *domain) +static void s390_domain_free(struct iommu_domain *domain) { struct s390_domain *s390_domain = to_s390_domain(domain); diff --git a/drivers/iommu/shmobile-iommu.c b/drivers/iommu/shmobile-iommu.c deleted file mode 100644 index a0287519a1d4..000000000000 --- a/drivers/iommu/shmobile-iommu.c +++ /dev/null @@ -1,402 +0,0 @@ -/* - * IOMMU for IPMMU/IPMMUI - * Copyright (C) 2012 Hideki EIRAKU - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - */ - -#include <linux/dma-mapping.h> -#include <linux/io.h> -#include <linux/iommu.h> -#include <linux/platform_device.h> -#include <linux/sizes.h> -#include <linux/slab.h> -#include <asm/dma-iommu.h> -#include "shmobile-ipmmu.h" - -#define L1_SIZE CONFIG_SHMOBILE_IOMMU_L1SIZE -#define L1_LEN (L1_SIZE / 4) -#define L1_ALIGN L1_SIZE -#define L2_SIZE SZ_1K -#define L2_LEN (L2_SIZE / 4) -#define L2_ALIGN L2_SIZE - -struct shmobile_iommu_domain_pgtable { - uint32_t *pgtable; - dma_addr_t handle; -}; - -struct shmobile_iommu_archdata { - struct list_head attached_list; - struct dma_iommu_mapping *iommu_mapping; - spinlock_t attach_lock; - struct shmobile_iommu_domain *attached; - int num_attached_devices; - struct shmobile_ipmmu *ipmmu; -}; - -struct shmobile_iommu_domain { - struct shmobile_iommu_domain_pgtable l1, l2[L1_LEN]; - spinlock_t map_lock; - spinlock_t attached_list_lock; - struct list_head attached_list; - struct iommu_domain domain; -}; - -static struct shmobile_iommu_archdata *ipmmu_archdata; -static struct kmem_cache *l1cache, *l2cache; - -static struct shmobile_iommu_domain *to_sh_domain(struct iommu_domain *dom) -{ - return container_of(dom, struct shmobile_iommu_domain, domain); -} - -static int pgtable_alloc(struct shmobile_iommu_domain_pgtable *pgtable, - struct kmem_cache *cache, size_t size) -{ - pgtable->pgtable = kmem_cache_zalloc(cache, GFP_ATOMIC); - if (!pgtable->pgtable) - return -ENOMEM; - pgtable->handle = dma_map_single(NULL, pgtable->pgtable, size, - DMA_TO_DEVICE); - return 0; -} - -static void pgtable_free(struct shmobile_iommu_domain_pgtable *pgtable, - struct kmem_cache *cache, size_t size) -{ - dma_unmap_single(NULL, pgtable->handle, size, DMA_TO_DEVICE); - kmem_cache_free(cache, pgtable->pgtable); -} - -static uint32_t pgtable_read(struct shmobile_iommu_domain_pgtable *pgtable, - unsigned int index) -{ - return pgtable->pgtable[index]; -} - -static void pgtable_write(struct shmobile_iommu_domain_pgtable *pgtable, - unsigned int index, unsigned int count, uint32_t val) -{ - unsigned int i; - - for (i = 0; i < count; i++) - pgtable->pgtable[index + i] = val; - dma_sync_single_for_device(NULL, pgtable->handle + index * sizeof(val), - sizeof(val) * count, DMA_TO_DEVICE); -} - -static struct iommu_domain *shmobile_iommu_domain_alloc(unsigned type) -{ - struct shmobile_iommu_domain *sh_domain; - int i, ret; - - if (type != IOMMU_DOMAIN_UNMANAGED) - return NULL; - - sh_domain = kzalloc(sizeof(*sh_domain), GFP_KERNEL); - if (!sh_domain) - return NULL; - ret = pgtable_alloc(&sh_domain->l1, l1cache, L1_SIZE); - if (ret < 0) { - kfree(sh_domain); - return NULL; - } - for (i = 0; i < L1_LEN; i++) - sh_domain->l2[i].pgtable = NULL; - spin_lock_init(&sh_domain->map_lock); - spin_lock_init(&sh_domain->attached_list_lock); - INIT_LIST_HEAD(&sh_domain->attached_list); - return &sh_domain->domain; -} - -static void shmobile_iommu_domain_free(struct iommu_domain *domain) -{ - struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); - int i; - - for (i = 0; i < L1_LEN; i++) { - if (sh_domain->l2[i].pgtable) - pgtable_free(&sh_domain->l2[i], l2cache, L2_SIZE); - } - pgtable_free(&sh_domain->l1, l1cache, L1_SIZE); - kfree(sh_domain); -} - -static int shmobile_iommu_attach_device(struct iommu_domain *domain, - struct device *dev) -{ - struct shmobile_iommu_archdata *archdata = dev->archdata.iommu; - struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); - int ret = -EBUSY; - - if (!archdata) - return -ENODEV; - spin_lock(&sh_domain->attached_list_lock); - spin_lock(&archdata->attach_lock); - if (archdata->attached != sh_domain) { - if (archdata->attached) - goto err; - ipmmu_tlb_set(archdata->ipmmu, sh_domain->l1.handle, L1_SIZE, - 0); - ipmmu_tlb_flush(archdata->ipmmu); - archdata->attached = sh_domain; - archdata->num_attached_devices = 0; - list_add(&archdata->attached_list, &sh_domain->attached_list); - } - archdata->num_attached_devices++; - ret = 0; -err: - spin_unlock(&archdata->attach_lock); - spin_unlock(&sh_domain->attached_list_lock); - return ret; -} - -static void shmobile_iommu_detach_device(struct iommu_domain *domain, - struct device *dev) -{ - struct shmobile_iommu_archdata *archdata = dev->archdata.iommu; - struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); - - if (!archdata) - return; - spin_lock(&sh_domain->attached_list_lock); - spin_lock(&archdata->attach_lock); - archdata->num_attached_devices--; - if (!archdata->num_attached_devices) { - ipmmu_tlb_set(archdata->ipmmu, 0, 0, 0); - ipmmu_tlb_flush(archdata->ipmmu); - archdata->attached = NULL; - list_del(&archdata->attached_list); - } - spin_unlock(&archdata->attach_lock); - spin_unlock(&sh_domain->attached_list_lock); -} - -static void domain_tlb_flush(struct shmobile_iommu_domain *sh_domain) -{ - struct shmobile_iommu_archdata *archdata; - - spin_lock(&sh_domain->attached_list_lock); - list_for_each_entry(archdata, &sh_domain->attached_list, attached_list) - ipmmu_tlb_flush(archdata->ipmmu); - spin_unlock(&sh_domain->attached_list_lock); -} - -static int l2alloc(struct shmobile_iommu_domain *sh_domain, - unsigned int l1index) -{ - int ret; - - if (!sh_domain->l2[l1index].pgtable) { - ret = pgtable_alloc(&sh_domain->l2[l1index], l2cache, L2_SIZE); - if (ret < 0) - return ret; - } - pgtable_write(&sh_domain->l1, l1index, 1, - sh_domain->l2[l1index].handle | 0x1); - return 0; -} - -static void l2realfree(struct shmobile_iommu_domain_pgtable *l2) -{ - if (l2->pgtable) - pgtable_free(l2, l2cache, L2_SIZE); -} - -static void l2free(struct shmobile_iommu_domain *sh_domain, - unsigned int l1index, - struct shmobile_iommu_domain_pgtable *l2) -{ - pgtable_write(&sh_domain->l1, l1index, 1, 0); - if (sh_domain->l2[l1index].pgtable) { - *l2 = sh_domain->l2[l1index]; - sh_domain->l2[l1index].pgtable = NULL; - } -} - -static int shmobile_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) -{ - struct shmobile_iommu_domain_pgtable l2 = { .pgtable = NULL }; - struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); - unsigned int l1index, l2index; - int ret; - - l1index = iova >> 20; - switch (size) { - case SZ_4K: - l2index = (iova >> 12) & 0xff; - spin_lock(&sh_domain->map_lock); - ret = l2alloc(sh_domain, l1index); - if (!ret) - pgtable_write(&sh_domain->l2[l1index], l2index, 1, - paddr | 0xff2); - spin_unlock(&sh_domain->map_lock); - break; - case SZ_64K: - l2index = (iova >> 12) & 0xf0; - spin_lock(&sh_domain->map_lock); - ret = l2alloc(sh_domain, l1index); - if (!ret) - pgtable_write(&sh_domain->l2[l1index], l2index, 0x10, - paddr | 0xff1); - spin_unlock(&sh_domain->map_lock); - break; - case SZ_1M: - spin_lock(&sh_domain->map_lock); - l2free(sh_domain, l1index, &l2); - pgtable_write(&sh_domain->l1, l1index, 1, paddr | 0xc02); - spin_unlock(&sh_domain->map_lock); - ret = 0; - break; - default: - ret = -EINVAL; - } - if (!ret) - domain_tlb_flush(sh_domain); - l2realfree(&l2); - return ret; -} - -static size_t shmobile_iommu_unmap(struct iommu_domain *domain, - unsigned long iova, size_t size) -{ - struct shmobile_iommu_domain_pgtable l2 = { .pgtable = NULL }; - struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); - unsigned int l1index, l2index; - uint32_t l2entry = 0; - size_t ret = 0; - - l1index = iova >> 20; - if (!(iova & 0xfffff) && size >= SZ_1M) { - spin_lock(&sh_domain->map_lock); - l2free(sh_domain, l1index, &l2); - spin_unlock(&sh_domain->map_lock); - ret = SZ_1M; - goto done; - } - l2index = (iova >> 12) & 0xff; - spin_lock(&sh_domain->map_lock); - if (sh_domain->l2[l1index].pgtable) - l2entry = pgtable_read(&sh_domain->l2[l1index], l2index); - switch (l2entry & 3) { - case 1: - if (l2index & 0xf) - break; - pgtable_write(&sh_domain->l2[l1index], l2index, 0x10, 0); - ret = SZ_64K; - break; - case 2: - pgtable_write(&sh_domain->l2[l1index], l2index, 1, 0); - ret = SZ_4K; - break; - } - spin_unlock(&sh_domain->map_lock); -done: - if (ret) - domain_tlb_flush(sh_domain); - l2realfree(&l2); - return ret; -} - -static phys_addr_t shmobile_iommu_iova_to_phys(struct iommu_domain *domain, - dma_addr_t iova) -{ - struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); - uint32_t l1entry = 0, l2entry = 0; - unsigned int l1index, l2index; - - l1index = iova >> 20; - l2index = (iova >> 12) & 0xff; - spin_lock(&sh_domain->map_lock); - if (sh_domain->l2[l1index].pgtable) - l2entry = pgtable_read(&sh_domain->l2[l1index], l2index); - else - l1entry = pgtable_read(&sh_domain->l1, l1index); - spin_unlock(&sh_domain->map_lock); - switch (l2entry & 3) { - case 1: - return (l2entry & ~0xffff) | (iova & 0xffff); - case 2: - return (l2entry & ~0xfff) | (iova & 0xfff); - default: - if ((l1entry & 3) == 2) - return (l1entry & ~0xfffff) | (iova & 0xfffff); - return 0; - } -} - -static int find_dev_name(struct shmobile_ipmmu *ipmmu, const char *dev_name) -{ - unsigned int i, n = ipmmu->num_dev_names; - - for (i = 0; i < n; i++) { - if (strcmp(ipmmu->dev_names[i], dev_name) == 0) - return 1; - } - return 0; -} - -static int shmobile_iommu_add_device(struct device *dev) -{ - struct shmobile_iommu_archdata *archdata = ipmmu_archdata; - struct dma_iommu_mapping *mapping; - - if (!find_dev_name(archdata->ipmmu, dev_name(dev))) - return 0; - mapping = archdata->iommu_mapping; - if (!mapping) { - mapping = arm_iommu_create_mapping(&platform_bus_type, 0, - L1_LEN << 20); - if (IS_ERR(mapping)) - return PTR_ERR(mapping); - archdata->iommu_mapping = mapping; - } - dev->archdata.iommu = archdata; - if (arm_iommu_attach_device(dev, mapping)) - pr_err("arm_iommu_attach_device failed\n"); - return 0; -} - -static const struct iommu_ops shmobile_iommu_ops = { - .domain_alloc = shmobile_iommu_domain_alloc, - .domain_free = shmobile_iommu_domain_free, - .attach_dev = shmobile_iommu_attach_device, - .detach_dev = shmobile_iommu_detach_device, - .map = shmobile_iommu_map, - .unmap = shmobile_iommu_unmap, - .map_sg = default_iommu_map_sg, - .iova_to_phys = shmobile_iommu_iova_to_phys, - .add_device = shmobile_iommu_add_device, - .pgsize_bitmap = SZ_1M | SZ_64K | SZ_4K, -}; - -int ipmmu_iommu_init(struct shmobile_ipmmu *ipmmu) -{ - static struct shmobile_iommu_archdata *archdata; - - l1cache = kmem_cache_create("shmobile-iommu-pgtable1", L1_SIZE, - L1_ALIGN, SLAB_HWCACHE_ALIGN, NULL); - if (!l1cache) - return -ENOMEM; - l2cache = kmem_cache_create("shmobile-iommu-pgtable2", L2_SIZE, - L2_ALIGN, SLAB_HWCACHE_ALIGN, NULL); - if (!l2cache) { - kmem_cache_destroy(l1cache); - return -ENOMEM; - } - archdata = kzalloc(sizeof(*archdata), GFP_KERNEL); - if (!archdata) { - kmem_cache_destroy(l1cache); - kmem_cache_destroy(l2cache); - return -ENOMEM; - } - spin_lock_init(&archdata->attach_lock); - archdata->ipmmu = ipmmu; - ipmmu_archdata = archdata; - bus_set_iommu(&platform_bus_type, &shmobile_iommu_ops); - return 0; -} diff --git a/drivers/iommu/shmobile-ipmmu.c b/drivers/iommu/shmobile-ipmmu.c deleted file mode 100644 index 951651a9746b..000000000000 --- a/drivers/iommu/shmobile-ipmmu.c +++ /dev/null @@ -1,129 +0,0 @@ -/* - * IPMMU/IPMMUI - * Copyright (C) 2012 Hideki EIRAKU - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - */ - -#include <linux/err.h> -#include <linux/export.h> -#include <linux/io.h> -#include <linux/platform_device.h> -#include <linux/slab.h> -#include <linux/platform_data/sh_ipmmu.h> -#include "shmobile-ipmmu.h" - -#define IMCTR1 0x000 -#define IMCTR2 0x004 -#define IMASID 0x010 -#define IMTTBR 0x014 -#define IMTTBCR 0x018 - -#define IMCTR1_TLBEN (1 << 0) -#define IMCTR1_FLUSH (1 << 1) - -static void ipmmu_reg_write(struct shmobile_ipmmu *ipmmu, unsigned long reg_off, - unsigned long data) -{ - iowrite32(data, ipmmu->ipmmu_base + reg_off); -} - -void ipmmu_tlb_flush(struct shmobile_ipmmu *ipmmu) -{ - if (!ipmmu) - return; - - spin_lock(&ipmmu->flush_lock); - if (ipmmu->tlb_enabled) - ipmmu_reg_write(ipmmu, IMCTR1, IMCTR1_FLUSH | IMCTR1_TLBEN); - else - ipmmu_reg_write(ipmmu, IMCTR1, IMCTR1_FLUSH); - spin_unlock(&ipmmu->flush_lock); -} - -void ipmmu_tlb_set(struct shmobile_ipmmu *ipmmu, unsigned long phys, int size, - int asid) -{ - if (!ipmmu) - return; - - spin_lock(&ipmmu->flush_lock); - switch (size) { - default: - ipmmu->tlb_enabled = 0; - break; - case 0x2000: - ipmmu_reg_write(ipmmu, IMTTBCR, 1); - ipmmu->tlb_enabled = 1; - break; - case 0x1000: - ipmmu_reg_write(ipmmu, IMTTBCR, 2); - ipmmu->tlb_enabled = 1; - break; - case 0x800: - ipmmu_reg_write(ipmmu, IMTTBCR, 3); - ipmmu->tlb_enabled = 1; - break; - case 0x400: - ipmmu_reg_write(ipmmu, IMTTBCR, 4); - ipmmu->tlb_enabled = 1; - break; - case 0x200: - ipmmu_reg_write(ipmmu, IMTTBCR, 5); - ipmmu->tlb_enabled = 1; - break; - case 0x100: - ipmmu_reg_write(ipmmu, IMTTBCR, 6); - ipmmu->tlb_enabled = 1; - break; - case 0x80: - ipmmu_reg_write(ipmmu, IMTTBCR, 7); - ipmmu->tlb_enabled = 1; - break; - } - ipmmu_reg_write(ipmmu, IMTTBR, phys); - ipmmu_reg_write(ipmmu, IMASID, asid); - spin_unlock(&ipmmu->flush_lock); -} - -static int ipmmu_probe(struct platform_device *pdev) -{ - struct shmobile_ipmmu *ipmmu; - struct resource *res; - struct shmobile_ipmmu_platform_data *pdata = pdev->dev.platform_data; - - ipmmu = devm_kzalloc(&pdev->dev, sizeof(*ipmmu), GFP_KERNEL); - if (!ipmmu) { - dev_err(&pdev->dev, "cannot allocate device data\n"); - return -ENOMEM; - } - spin_lock_init(&ipmmu->flush_lock); - ipmmu->dev = &pdev->dev; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ipmmu->ipmmu_base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(ipmmu->ipmmu_base)) - return PTR_ERR(ipmmu->ipmmu_base); - - ipmmu->dev_names = pdata->dev_names; - ipmmu->num_dev_names = pdata->num_dev_names; - platform_set_drvdata(pdev, ipmmu); - ipmmu_reg_write(ipmmu, IMCTR1, 0x0); /* disable TLB */ - ipmmu_reg_write(ipmmu, IMCTR2, 0x0); /* disable PMB */ - return ipmmu_iommu_init(ipmmu); -} - -static struct platform_driver ipmmu_driver = { - .probe = ipmmu_probe, - .driver = { - .name = "ipmmu", - }, -}; - -static int __init ipmmu_init(void) -{ - return platform_driver_register(&ipmmu_driver); -} -subsys_initcall(ipmmu_init); diff --git a/drivers/iommu/shmobile-ipmmu.h b/drivers/iommu/shmobile-ipmmu.h deleted file mode 100644 index 9524743ca1fb..000000000000 --- a/drivers/iommu/shmobile-ipmmu.h +++ /dev/null @@ -1,34 +0,0 @@ -/* shmobile-ipmmu.h - * - * Copyright (C) 2012 Hideki EIRAKU - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - */ - -#ifndef __SHMOBILE_IPMMU_H__ -#define __SHMOBILE_IPMMU_H__ - -struct shmobile_ipmmu { - struct device *dev; - void __iomem *ipmmu_base; - int tlb_enabled; - spinlock_t flush_lock; - const char * const *dev_names; - unsigned int num_dev_names; -}; - -#ifdef CONFIG_SHMOBILE_IPMMU_TLB -void ipmmu_tlb_flush(struct shmobile_ipmmu *ipmmu); -void ipmmu_tlb_set(struct shmobile_ipmmu *ipmmu, unsigned long phys, int size, - int asid); -int ipmmu_iommu_init(struct shmobile_ipmmu *ipmmu); -#else -static inline int ipmmu_iommu_init(struct shmobile_ipmmu *ipmmu) -{ - return -EINVAL; -} -#endif - -#endif /* __SHMOBILE_IPMMU_H__ */ diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 95c13b2ffa79..ffa288474820 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -426,15 +426,6 @@ int add_mtd_device(struct mtd_info *mtd) mtd->erasesize_mask = (1 << mtd->erasesize_shift) - 1; mtd->writesize_mask = (1 << mtd->writesize_shift) - 1; - if (mtd->dev.parent) { - if (!mtd->owner && mtd->dev.parent->driver) - mtd->owner = mtd->dev.parent->driver->owner; - if (!mtd->name) - mtd->name = dev_name(mtd->dev.parent); - } else { - pr_debug("mtd device won't show a device symlink in sysfs\n"); - } - /* Some chips always power up locked. Unlock them now */ if ((mtd->flags & MTD_WRITEABLE) && (mtd->flags & MTD_POWERUP_LOCK)) { error = mtd_unlock(mtd, 0, mtd->size); @@ -549,6 +540,21 @@ static int mtd_add_device_partitions(struct mtd_info *mtd, return 0; } +/* + * Set a few defaults based on the parent devices, if not provided by the + * driver + */ +static void mtd_set_dev_defaults(struct mtd_info *mtd) +{ + if (mtd->dev.parent) { + if (!mtd->owner && mtd->dev.parent->driver) + mtd->owner = mtd->dev.parent->driver->owner; + if (!mtd->name) + mtd->name = dev_name(mtd->dev.parent); + } else { + pr_debug("mtd device won't show a device symlink in sysfs\n"); + } +} /** * mtd_device_parse_register - parse partitions and register an MTD device. @@ -587,6 +593,8 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types, int ret; struct mtd_partition *real_parts = NULL; + mtd_set_dev_defaults(mtd); + ret = parse_mtd_partitions(mtd, types, &real_parts, parser_data); if (ret <= 0 && nr_parts && parts) { real_parts = kmemdup(parts, sizeof(*parts) * nr_parts, diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 49883905a434..32477c4eb421 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -516,8 +516,8 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len) status_old = read_sr(nor); /* Cannot unlock; would unlock larger region than requested */ - if (stm_is_locked_sr(nor, status_old, ofs - mtd->erasesize, - mtd->erasesize)) + if (stm_is_locked_sr(nor, ofs - mtd->erasesize, mtd->erasesize, + status_old)) return -EINVAL; /* @@ -1200,8 +1200,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) if (JEDEC_MFR(info) == SNOR_MFR_ATMEL || JEDEC_MFR(info) == SNOR_MFR_INTEL || - JEDEC_MFR(info) == SNOR_MFR_SST || - JEDEC_MFR(info) == SNOR_MFR_WINBOND) { + JEDEC_MFR(info) == SNOR_MFR_SST) { write_enable(nor); write_sr(nor, 0); } @@ -1217,8 +1216,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) mtd->_read = spi_nor_read; /* NOR protection support for STmicro/Micron chips and similar */ - if (JEDEC_MFR(info) == SNOR_MFR_MICRON || - JEDEC_MFR(info) == SNOR_MFR_WINBOND) { + if (JEDEC_MFR(info) == SNOR_MFR_MICRON) { nor->flash_lock = stm_lock; nor->flash_unlock = stm_unlock; nor->flash_is_locked = stm_is_locked; diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c index c308429dd9c7..11dd91e4db56 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c +++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c @@ -295,6 +295,10 @@ struct clip_tbl *t4_init_clip_tbl(unsigned int clipt_start, INIT_LIST_HEAD(&ctbl->hash_list[i]); cl_list = t4_alloc_mem(clipt_size*sizeof(struct clip_entry)); + if (!cl_list) { + t4_free_mem(ctbl); + return NULL; + } ctbl->cl_list = (void *)cl_list; for (i = 0; i < clipt_size; i++) { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c index a5f422f26cb4..daf05155b732 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c @@ -772,8 +772,10 @@ int qlcnic_82xx_config_intrpt(struct qlcnic_adapter *adapter, u8 op_type) int i, err = 0; for (i = 0; i < ahw->num_msix; i++) { - qlcnic_alloc_mbx_args(&cmd, adapter, - QLCNIC_CMD_MQ_TX_CONFIG_INTR); + err = qlcnic_alloc_mbx_args(&cmd, adapter, + QLCNIC_CMD_MQ_TX_CONFIG_INTR); + if (err) + return err; type = op_type ? QLCNIC_INTRPT_ADD : QLCNIC_INTRPT_DEL; val = type | (ahw->intr_tbl[i].type << 4); if (ahw->intr_tbl[i].type == QLCNIC_INTRPT_MSIX) diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 9f0b1c342b77..5a1e98547031 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -683,6 +683,12 @@ static void sixpack_close(struct tty_struct *tty) if (!atomic_dec_and_test(&sp->refcnt)) down(&sp->dead_sem); + /* We must stop the queue to avoid potentially scribbling + * on the free buffers. The sp->dead_sem is not sufficient + * to protect us from sp->xbuff access. + */ + netif_stop_queue(sp->dev); + del_timer_sync(&sp->tx_t); del_timer_sync(&sp->resync_t); diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 0b72b9de5207..85828f153445 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -797,6 +797,11 @@ static void mkiss_close(struct tty_struct *tty) */ if (!atomic_dec_and_test(&ax->refcnt)) down(&ax->dead_sem); + /* + * Halt the transmit queue so that a new transmit cannot scribble + * on our buffers + */ + netif_stop_queue(ax->dev); /* Free all AX25 frame buffers. */ kfree(ax->rbuff); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 9a5be8b85186..5fccc5a8153f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -742,6 +742,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81b1, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ + {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 2e32c41536ae..2fb637ad594a 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3525,6 +3525,14 @@ static int rtl8152_resume(struct usb_interface *intf) return 0; } +static int rtl8152_reset_resume(struct usb_interface *intf) +{ + struct r8152 *tp = usb_get_intfdata(intf); + + clear_bit(SELECTIVE_SUSPEND, &tp->flags); + return rtl8152_resume(intf); +} + static void rtl8152_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct r8152 *tp = netdev_priv(dev); @@ -4276,7 +4284,7 @@ static struct usb_driver rtl8152_driver = { .disconnect = rtl8152_disconnect, .suspend = rtl8152_suspend, .resume = rtl8152_resume, - .reset_resume = rtl8152_resume, + .reset_resume = rtl8152_reset_resume, .pre_reset = rtl8152_pre_reset, .post_reset = rtl8152_post_reset, .supports_autosuspend = 1, diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 417903715437..0cbf520cea77 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1380,10 +1380,10 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, skip_page_frags = true; goto rcd_done; } - new_dma_addr = dma_map_page(&adapter->pdev->dev - , rbi->page, - 0, PAGE_SIZE, - PCI_DMA_FROMDEVICE); + new_dma_addr = dma_map_page(&adapter->pdev->dev, + new_page, + 0, PAGE_SIZE, + PCI_DMA_FROMDEVICE); if (dma_mapping_error(&adapter->pdev->dev, new_dma_addr)) { put_page(new_page); diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 4c58c83dc225..bdb8a6c0f8aa 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.4.4.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.4.5.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01040400 +#define VMXNET3_DRIVER_VERSION_NUM 0x01040500 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 4f9748457f5a..0a242b200df4 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -800,7 +800,7 @@ static struct rtable *vrf_get_rtable(const struct net_device *dev, } /* called under rcu_read_lock */ -static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) +static int vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) { struct fib_result res = { .tclassid = 0 }; struct net *net = dev_net(dev); @@ -808,9 +808,10 @@ static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) u8 flags = fl4->flowi4_flags; u8 scope = fl4->flowi4_scope; u8 tos = RT_FL_TOS(fl4); + int rc; if (unlikely(!fl4->daddr)) - return; + return 0; fl4->flowi4_flags |= FLOWI_FLAG_SKIP_NH_OIF; fl4->flowi4_iif = LOOPBACK_IFINDEX; @@ -818,7 +819,8 @@ static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) fl4->flowi4_scope = ((tos & RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); - if (!fib_lookup(net, fl4, &res, 0)) { + rc = fib_lookup(net, fl4, &res, 0); + if (!rc) { if (res.type == RTN_LOCAL) fl4->saddr = res.fi->fib_prefsrc ? : fl4->daddr; else @@ -828,6 +830,8 @@ static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) fl4->flowi4_flags = flags; fl4->flowi4_tos = orig_tos; fl4->flowi4_scope = scope; + + return rc; } #if IS_ENABLED(CONFIG_IPV6) diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig index f131ba947dc6..c0ad9aaa16a7 100644 --- a/drivers/pci/host/Kconfig +++ b/drivers/pci/host/Kconfig @@ -5,6 +5,7 @@ config PCI_DRA7XX bool "TI DRA7xx PCIe controller" select PCIE_DW depends on OF && HAS_IOMEM && TI_PIPE3 + depends on BROKEN help Enables support for the PCIe controller in the DRA7xx SoC. There are two instances of PCIe controller in DRA7xx. This controller can diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 3d22fc3e3c1a..4e08d1cd704d 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2885,10 +2885,13 @@ static int sd_revalidate_disk(struct gendisk *disk) /* * Use the device's preferred I/O size for reads and writes - * unless the reported value is unreasonably large (or garbage). + * unless the reported value is unreasonably small, large, or + * garbage. */ - if (sdkp->opt_xfer_blocks && sdkp->opt_xfer_blocks <= dev_max && - sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS) + if (sdkp->opt_xfer_blocks && + sdkp->opt_xfer_blocks <= dev_max && + sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS && + sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_CACHE_SIZE) rw_max = q->limits.io_opt = logical_to_sectors(sdp, sdkp->opt_xfer_blocks); else diff --git a/include/linux/filter.h b/include/linux/filter.h index 4165e9ac9e36..5972ffe5719a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -493,6 +493,25 @@ static inline void bpf_jit_free(struct bpf_prog *fp) #define BPF_ANC BIT(15) +static inline bool bpf_needs_clear_a(const struct sock_filter *first) +{ + switch (first->code) { + case BPF_RET | BPF_K: + case BPF_LD | BPF_W | BPF_LEN: + return false; + + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: + if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) + return true; + return false; + + default: + return true; + } +} + static inline u16 bpf_anc_helper(const struct sock_filter *ftest) { BUG_ON(ftest->code & BPF_ANC); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index eae6548efbf0..60048c50404e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -586,6 +586,7 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size); extern int skip_trace(unsigned long ip); extern void ftrace_module_init(struct module *mod); +extern void ftrace_release_mod(struct module *mod); extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index c8723b62c4cd..bc742dac7d3a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -25,7 +25,7 @@ #define SNOR_MFR_MACRONIX CFI_MFR_MACRONIX #define SNOR_MFR_SPANSION CFI_MFR_AMD #define SNOR_MFR_SST CFI_MFR_SST -#define SNOR_MFR_WINBOND 0xef +#define SNOR_MFR_WINBOND 0xef /* Also used by some Spansion */ /* * Note on opcode nomenclature: some opcodes have a format like diff --git a/include/linux/sched.h b/include/linux/sched.h index edad7a43edea..fa39434e3fdd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1455,14 +1455,15 @@ struct task_struct { /* Used for emulating ABI behavior of previous Linux versions */ unsigned int personality; - unsigned in_execve:1; /* Tell the LSMs that the process is doing an - * execve */ - unsigned in_iowait:1; - - /* Revert to default priority/policy when forking */ + /* scheduler bits, serialized by scheduler locks */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned :0; /* force alignment to the next boundary */ + + /* unserialized, strictly 'current' */ + unsigned in_execve:1; /* bit to tell LSMs we're in execve */ + unsigned in_iowait:1; #ifdef CONFIG_MEMCG unsigned memcg_may_oom:1; #endif @@ -2002,7 +2003,8 @@ static inline int pid_alive(const struct task_struct *p) } /** - * is_global_init - check if a task structure is init + * is_global_init - check if a task structure is init. Since init + * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. @@ -2011,7 +2013,7 @@ static inline int pid_alive(const struct task_struct *p) */ static inline int is_global_init(struct task_struct *tsk) { - return tsk->pid == 1; + return task_tgid_nr(tsk) == 1; } extern struct pid *cad_pid; diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 774d85b2d5d9..5689a0c749f7 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -29,7 +29,7 @@ struct l3mdev_ops { /* IPv4 ops */ struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev, const struct flowi4 *fl4); - void (*l3mdev_get_saddr)(struct net_device *dev, + int (*l3mdev_get_saddr)(struct net_device *dev, struct flowi4 *fl4); /* IPv6 ops */ @@ -112,10 +112,11 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) return rc; } -static inline void l3mdev_get_saddr(struct net *net, int ifindex, - struct flowi4 *fl4) +static inline int l3mdev_get_saddr(struct net *net, int ifindex, + struct flowi4 *fl4) { struct net_device *dev; + int rc = 0; if (ifindex) { @@ -124,11 +125,13 @@ static inline void l3mdev_get_saddr(struct net *net, int ifindex, dev = dev_get_by_index_rcu(net, ifindex); if (dev && netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_get_saddr) { - dev->l3mdev_ops->l3mdev_get_saddr(dev, fl4); + rc = dev->l3mdev_ops->l3mdev_get_saddr(dev, fl4); } rcu_read_unlock(); } + + return rc; } static inline struct dst_entry *l3mdev_get_rt6_dst(const struct net_device *dev, @@ -200,9 +203,10 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) return false; } -static inline void l3mdev_get_saddr(struct net *net, int ifindex, - struct flowi4 *fl4) +static inline int l3mdev_get_saddr(struct net *net, int ifindex, + struct flowi4 *fl4) { + return 0; } static inline diff --git a/include/net/route.h b/include/net/route.h index ee81307863d5..a3b9ef74a389 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -283,7 +283,12 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, sport, dport, sk); if (!src && oif) { - l3mdev_get_saddr(net, oif, fl4); + int rc; + + rc = l3mdev_get_saddr(net, oif, fl4); + if (rc < 0) + return ERR_PTR(rc); + src = fl4->saddr; } if (!dst || !src) { diff --git a/include/sound/soc.h b/include/sound/soc.h index a8b4b9c8b1d2..fb955e69a78e 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1655,7 +1655,7 @@ extern const struct dev_pm_ops snd_soc_pm_ops; /* Helper functions */ static inline void snd_soc_dapm_mutex_lock(struct snd_soc_dapm_context *dapm) { - mutex_lock(&dapm->card->dapm_mutex); + mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); } static inline void snd_soc_dapm_mutex_unlock(struct snd_soc_dapm_context *dapm) diff --git a/kernel/events/core.c b/kernel/events/core.c index ef2d6ea10736..cfc227ccfceb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3154,15 +3154,16 @@ static int event_enable_on_exec(struct perf_event *event, * Enable all of a task's events that have been marked enable-on-exec. * This expects task == current. */ -static void perf_event_enable_on_exec(struct perf_event_context *ctx) +static void perf_event_enable_on_exec(int ctxn) { - struct perf_event_context *clone_ctx = NULL; + struct perf_event_context *ctx, *clone_ctx = NULL; struct perf_event *event; unsigned long flags; int enabled = 0; int ret; local_irq_save(flags); + ctx = current->perf_event_ctxp[ctxn]; if (!ctx || !ctx->nr_events) goto out; @@ -3205,17 +3206,11 @@ out: void perf_event_exec(void) { - struct perf_event_context *ctx; int ctxn; rcu_read_lock(); - for_each_task_context_nr(ctxn) { - ctx = current->perf_event_ctxp[ctxn]; - if (!ctx) - continue; - - perf_event_enable_on_exec(ctx); - } + for_each_task_context_nr(ctxn) + perf_event_enable_on_exec(ctxn); rcu_read_unlock(); } @@ -6493,9 +6488,6 @@ struct swevent_htable { /* Recursion avoidance in each contexts */ int recursion[PERF_NR_CONTEXTS]; - - /* Keeps track of cpu being initialized/exited */ - bool online; }; static DEFINE_PER_CPU(struct swevent_htable, swevent_htable); @@ -6753,14 +6745,8 @@ static int perf_swevent_add(struct perf_event *event, int flags) hwc->state = !(flags & PERF_EF_START); head = find_swevent_head(swhash, event); - if (!head) { - /* - * We can race with cpu hotplug code. Do not - * WARN if the cpu just got unplugged. - */ - WARN_ON_ONCE(swhash->online); + if (WARN_ON_ONCE(!head)) return -EINVAL; - } hlist_add_head_rcu(&event->hlist_entry, head); perf_event_update_userpage(event); @@ -6828,7 +6814,6 @@ static int swevent_hlist_get_cpu(struct perf_event *event, int cpu) int err = 0; mutex_lock(&swhash->hlist_mutex); - if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) { struct swevent_hlist *hlist; @@ -9291,7 +9276,6 @@ static void perf_event_init_cpu(int cpu) struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); mutex_lock(&swhash->hlist_mutex); - swhash->online = true; if (swhash->hlist_refcount > 0) { struct swevent_hlist *hlist; @@ -9333,14 +9317,7 @@ static void perf_event_exit_cpu_context(int cpu) static void perf_event_exit_cpu(int cpu) { - struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); - perf_event_exit_cpu_context(cpu); - - mutex_lock(&swhash->hlist_mutex); - swhash->online = false; - swevent_hlist_release(swhash); - mutex_unlock(&swhash->hlist_mutex); } #else static inline void perf_event_exit_cpu(int cpu) { } diff --git a/kernel/fork.c b/kernel/fork.c index fce002ee3ddf..1155eac61687 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -380,6 +380,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; + tsk->wake_q.next = NULL; account_kernel_stack(ti, 1); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0eebaeef317b..6ead200370da 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1434,6 +1434,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) if (!desc) return NULL; + chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, flags); /* @@ -1447,7 +1448,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) if (!action) { WARN(1, "Trying to free already-free IRQ %d\n", irq); raw_spin_unlock_irqrestore(&desc->lock, flags); - + chip_bus_sync_unlock(desc); return NULL; } @@ -1475,6 +1476,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) #endif raw_spin_unlock_irqrestore(&desc->lock, flags); + chip_bus_sync_unlock(desc); unregister_handler_proc(irq, action); @@ -1553,9 +1555,7 @@ void free_irq(unsigned int irq, void *dev_id) desc->affinity_notify = NULL; #endif - chip_bus_lock(desc); kfree(__free_irq(irq, dev_id)); - chip_bus_sync_unlock(desc); } EXPORT_SYMBOL(free_irq); diff --git a/kernel/module.c b/kernel/module.c index 8f051a106676..38c7bd5583ff 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3571,6 +3571,12 @@ static int load_module(struct load_info *info, const char __user *uargs, synchronize_sched(); mutex_unlock(&module_mutex); free_module: + /* + * Ftrace needs to clean up what it initialized. + * This does nothing if ftrace_module_init() wasn't called, + * but it must be called outside of module_mutex. + */ + ftrace_release_mod(mod); /* Free lock-classes; relies on the preceding sync_rcu() */ lockdep_free_key_range(mod->module_core, mod->core_size); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 90e26b11deaa..cfdc0e61066c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2689,7 +2689,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) int decayed, removed = 0; if (atomic_long_read(&cfs_rq->removed_load_avg)) { - long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); + s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); sa->load_avg = max_t(long, sa->load_avg - r, 0); sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0); removed = 1; diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 1c2b28536feb..060df67dbdd1 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -273,6 +273,7 @@ static const char **find_next(void *v, loff_t *pos) if (*pos < last_index + start_index) return __start___tracepoint_str + (*pos - last_index); + start_index += last_index; return find_next_mod_format(start_index, v, fmt, pos); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 4ebc17d948cb..c54fd2924f25 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1483,6 +1483,7 @@ static void __init start_shepherd_timer(void) BUG(); cpumask_copy(cpu_stat_off, cpu_online_mask); + vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); } @@ -1550,7 +1551,6 @@ static int __init setup_vmstat(void) start_shepherd_timer(); cpu_notifier_register_done(); - vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); #endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 12045dea276c..8a7ada8bb947 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -142,7 +142,10 @@ static void br_stp_start(struct net_bridge *br) char *envp[] = { NULL }; struct net_bridge_port *p; - r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + if (net_eq(dev_net(br->dev), &init_net)) + r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + else + r = -ENOENT; spin_lock_bh(&br->lock); diff --git a/net/core/dst.c b/net/core/dst.c index e6dc77252fe9..a1656e3b8d72 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -301,12 +301,13 @@ void dst_release(struct dst_entry *dst) { if (dst) { int newrefcnt; + unsigned short nocache = dst->flags & DST_NOCACHE; newrefcnt = atomic_dec_return(&dst->__refcnt); if (unlikely(newrefcnt < 0)) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); - if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE)) + if (!newrefcnt && unlikely(nocache)) call_rcu(&dst->rcu_head, dst_destroy_rcu); } } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 63e5be0abd86..bc35f1842512 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -601,8 +601,11 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); - if (!saddr && ipc.oif) - l3mdev_get_saddr(net, ipc.oif, &fl4); + if (!saddr && ipc.oif) { + err = l3mdev_get_saddr(net, ipc.oif, &fl4); + if (err < 0) + goto done; + } if (!inet->hdrincl) { rfv.msg = msg; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2d656eef7f8e..d4c51158470f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2478,6 +2478,9 @@ static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, int newly_acked_sacked = prior_unsacked - (tp->packets_out - tp->sacked_out); + if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd)) + return; + tp->prr_delivered += newly_acked_sacked; if (delta < 0) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0c7b0e61b917..c43890848641 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1025,8 +1025,11 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flow_flags, faddr, saddr, dport, inet->inet_sport); - if (!saddr && ipc.oif) - l3mdev_get_saddr(net, ipc.oif, fl4); + if (!saddr && ipc.oif) { + err = l3mdev_get_saddr(net, ipc.oif, fl4); + if (err < 0) + goto out; + } security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index e82a1ad80aa5..16bc83b2842a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -658,8 +658,10 @@ static void qdisc_rcu_free(struct rcu_head *head) { struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head); - if (qdisc_is_percpu_stats(qdisc)) + if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); + free_percpu(qdisc->cpu_qstats); + } kfree((char *) qdisc - qdisc->padded); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index a4631477cedf..ef05cd9403d4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -953,32 +953,20 @@ fail: return NULL; } -static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) +static int unix_mknod(struct dentry *dentry, struct path *path, umode_t mode, + struct path *res) { - struct dentry *dentry; - struct path path; - int err = 0; - /* - * Get the parent directory, calculate the hash for last - * component. - */ - dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); - err = PTR_ERR(dentry); - if (IS_ERR(dentry)) - return err; + int err; - /* - * All right, let's create it. - */ - err = security_path_mknod(&path, dentry, mode, 0); + err = security_path_mknod(path, dentry, mode, 0); if (!err) { - err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0); + err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0); if (!err) { - res->mnt = mntget(path.mnt); + res->mnt = mntget(path->mnt); res->dentry = dget(dentry); } } - done_path_create(&path, dentry); + return err; } @@ -989,10 +977,12 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; char *sun_path = sunaddr->sun_path; - int err; + int err, name_err; unsigned int hash; struct unix_address *addr; struct hlist_head *list; + struct path path; + struct dentry *dentry; err = -EINVAL; if (sunaddr->sun_family != AF_UNIX) @@ -1008,14 +998,34 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; + name_err = 0; + dentry = NULL; + if (sun_path[0]) { + /* Get the parent directory, calculate the hash for last + * component. + */ + dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); + + if (IS_ERR(dentry)) { + /* delay report until after 'already bound' check */ + name_err = PTR_ERR(dentry); + dentry = NULL; + } + } + err = mutex_lock_interruptible(&u->readlock); if (err) - goto out; + goto out_path; err = -EINVAL; if (u->addr) goto out_up; + if (name_err) { + err = name_err == -EEXIST ? -EADDRINUSE : name_err; + goto out_up; + } + err = -ENOMEM; addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL); if (!addr) @@ -1026,11 +1036,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) addr->hash = hash ^ sk->sk_type; atomic_set(&addr->refcnt, 1); - if (sun_path[0]) { - struct path path; + if (dentry) { + struct path u_path; umode_t mode = S_IFSOCK | (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(sun_path, mode, &path); + err = unix_mknod(dentry, &path, mode, &u_path); if (err) { if (err == -EEXIST) err = -EADDRINUSE; @@ -1038,9 +1048,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out_up; } addr->hash = UNIX_HASH_SIZE; - hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE-1); + hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); - u->path = path; + u->path = u_path; list = &unix_socket_table[hash]; } else { spin_lock(&unix_table_lock); @@ -1063,6 +1073,10 @@ out_unlock: spin_unlock(&unix_table_lock); out_up: mutex_unlock(&u->readlock); +out_path: + if (dentry) + done_path_create(&path, dentry); + out: return err; } diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 301d70b0174f..e167592793a7 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -586,7 +586,7 @@ main(int argc, char *argv[]) do_file(file); break; case SJ_FAIL: /* error in do_file or below */ - sprintf("%s: failed\n", file); + fprintf(stderr, "%s: failed\n", file); ++n_error; break; case SJ_SUCCEED: /* premature success */ diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index fe96428aa403..3a89d82f8057 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -67,6 +67,10 @@ enum { ALC_HEADSET_TYPE_OMTP, }; +enum { + ALC_KEY_MICMUTE_INDEX, +}; + struct alc_customize_define { unsigned int sku_cfg; unsigned char port_connectivity; @@ -123,6 +127,7 @@ struct alc_spec { unsigned int pll_coef_idx, pll_coef_bit; unsigned int coef0; struct input_dev *kb_dev; + u8 alc_mute_keycode_map[1]; }; /* @@ -3462,12 +3467,43 @@ static void gpio2_mic_hotkey_event(struct hda_codec *codec, /* GPIO2 just toggles on a keypress/keyrelease cycle. Therefore send both key on and key off event for every interrupt. */ - input_report_key(spec->kb_dev, KEY_MICMUTE, 1); + input_report_key(spec->kb_dev, spec->alc_mute_keycode_map[ALC_KEY_MICMUTE_INDEX], 1); input_sync(spec->kb_dev); - input_report_key(spec->kb_dev, KEY_MICMUTE, 0); + input_report_key(spec->kb_dev, spec->alc_mute_keycode_map[ALC_KEY_MICMUTE_INDEX], 0); input_sync(spec->kb_dev); } +static int alc_register_micmute_input_device(struct hda_codec *codec) +{ + struct alc_spec *spec = codec->spec; + int i; + + spec->kb_dev = input_allocate_device(); + if (!spec->kb_dev) { + codec_err(codec, "Out of memory (input_allocate_device)\n"); + return -ENOMEM; + } + + spec->alc_mute_keycode_map[ALC_KEY_MICMUTE_INDEX] = KEY_MICMUTE; + + spec->kb_dev->name = "Microphone Mute Button"; + spec->kb_dev->evbit[0] = BIT_MASK(EV_KEY); + spec->kb_dev->keycodesize = sizeof(spec->alc_mute_keycode_map[0]); + spec->kb_dev->keycodemax = ARRAY_SIZE(spec->alc_mute_keycode_map); + spec->kb_dev->keycode = spec->alc_mute_keycode_map; + for (i = 0; i < ARRAY_SIZE(spec->alc_mute_keycode_map); i++) + set_bit(spec->alc_mute_keycode_map[i], spec->kb_dev->keybit); + + if (input_register_device(spec->kb_dev)) { + codec_err(codec, "input_register_device failed\n"); + input_free_device(spec->kb_dev); + spec->kb_dev = NULL; + return -ENOMEM; + } + + return 0; +} + static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -3485,20 +3521,8 @@ static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec, struct alc_spec *spec = codec->spec; if (action == HDA_FIXUP_ACT_PRE_PROBE) { - spec->kb_dev = input_allocate_device(); - if (!spec->kb_dev) { - codec_err(codec, "Out of memory (input_allocate_device)\n"); + if (alc_register_micmute_input_device(codec) != 0) return; - } - spec->kb_dev->name = "Microphone Mute Button"; - spec->kb_dev->evbit[0] = BIT_MASK(EV_KEY); - spec->kb_dev->keybit[BIT_WORD(KEY_MICMUTE)] = BIT_MASK(KEY_MICMUTE); - if (input_register_device(spec->kb_dev)) { - codec_err(codec, "input_register_device failed\n"); - input_free_device(spec->kb_dev); - spec->kb_dev = NULL; - return; - } snd_hda_add_verbs(codec, gpio_init); snd_hda_codec_write_cache(codec, codec->core.afg, 0, @@ -3528,6 +3552,47 @@ static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec, } } +static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + /* Line2 = mic mute hotkey + GPIO2 = mic mute LED */ + static const struct hda_verb gpio_init[] = { + { 0x01, AC_VERB_SET_GPIO_MASK, 0x04 }, + { 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04 }, + {} + }; + + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + if (alc_register_micmute_input_device(codec) != 0) + return; + + snd_hda_add_verbs(codec, gpio_init); + snd_hda_jack_detect_enable_callback(codec, 0x1b, + gpio2_mic_hotkey_event); + + spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook; + spec->gpio_led = 0; + spec->mute_led_polarity = 0; + spec->gpio_mic_led_mask = 0x04; + return; + } + + if (!spec->kb_dev) + return; + + switch (action) { + case HDA_FIXUP_ACT_PROBE: + spec->init_amp = ALC_INIT_DEFAULT; + break; + case HDA_FIXUP_ACT_FREE: + input_unregister_device(spec->kb_dev); + spec->kb_dev = NULL; + } +} + static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -4628,6 +4693,7 @@ enum { ALC275_FIXUP_DELL_XPS, ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, ALC293_FIXUP_LENOVO_SPK_NOISE, + ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, }; static const struct hda_fixup alc269_fixups[] = { @@ -5237,6 +5303,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_THINKPAD_ACPI }, + [ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc233_fixup_lenovo_line2_mic_hotkey, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5386,6 +5456,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE), + SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c index b3ea24d64c50..93b400800905 100644 --- a/sound/soc/codecs/arizona.c +++ b/sound/soc/codecs/arizona.c @@ -1537,7 +1537,7 @@ static int arizona_hw_params(struct snd_pcm_substream *substream, bool reconfig; unsigned int aif_tx_state, aif_rx_state; - if (params_rate(params) % 8000) + if (params_rate(params) % 4000) rates = &arizona_44k1_bclk_rates[0]; else rates = &arizona_48k_bclk_rates[0]; diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index ef76940f9dcb..3e3c7f6be29d 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -1667,9 +1667,13 @@ static int rt5645_spk_event(struct snd_soc_dapm_widget *w, RT5645_PWR_CLS_D_L, RT5645_PWR_CLS_D | RT5645_PWR_CLS_D_R | RT5645_PWR_CLS_D_L); + snd_soc_update_bits(codec, RT5645_GEN_CTRL3, + RT5645_DET_CLK_MASK, RT5645_DET_CLK_MODE1); break; case SND_SOC_DAPM_PRE_PMD: + snd_soc_update_bits(codec, RT5645_GEN_CTRL3, + RT5645_DET_CLK_MASK, RT5645_DET_CLK_DIS); snd_soc_write(codec, RT5645_EQ_CTRL2, 0); snd_soc_update_bits(codec, RT5645_PWR_DIG1, RT5645_PWR_CLS_D | RT5645_PWR_CLS_D_R | diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h index 093e46d559fb..205e0715c99a 100644 --- a/sound/soc/codecs/rt5645.h +++ b/sound/soc/codecs/rt5645.h @@ -2122,6 +2122,10 @@ enum { /* General Control3 (0xfc) */ #define RT5645_JD_PSV_MODE (0x1 << 12) #define RT5645_IRQ_CLK_GATE_CTRL (0x1 << 11) +#define RT5645_DET_CLK_MASK (0x3 << 9) +#define RT5645_DET_CLK_DIS (0x0 << 9) +#define RT5645_DET_CLK_MODE1 (0x1 << 9) +#define RT5645_DET_CLK_MODE2 (0x2 << 9) #define RT5645_MICINDET_MANU (0x1 << 7) #define RT5645_RING2_SLEEVE_GND (0x1 << 5) diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index ffea427aeca8..ad4d0f82603e 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -1240,7 +1240,6 @@ int skl_tplg_init(struct snd_soc_platform *platform, struct hdac_ext_bus *ebus) */ ret = snd_soc_tplg_component_load(&platform->component, &skl_tplg_ops, fw, 0); - release_firmware(fw); if (ret < 0) { dev_err(bus->dev, "tplg component load failed%d\n", ret); return -EINVAL; @@ -1249,5 +1248,7 @@ int skl_tplg_init(struct snd_soc_platform *platform, struct hdac_ext_bus *ebus) skl->resource.max_mcps = SKL_MAX_MCPS; skl->resource.max_mem = SKL_FW_MAX_MEM; + skl->tplg = fw; + return 0; } diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 5319529aedf7..caa69c4598a6 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -25,6 +25,7 @@ #include <linux/pci.h> #include <linux/pm_runtime.h> #include <linux/platform_device.h> +#include <linux/firmware.h> #include <sound/pcm.h> #include "skl.h" @@ -520,6 +521,9 @@ static void skl_remove(struct pci_dev *pci) struct hdac_ext_bus *ebus = pci_get_drvdata(pci); struct skl *skl = ebus_to_skl(ebus); + if (skl->tplg) + release_firmware(skl->tplg); + if (pci_dev_run_wake(pci)) pm_runtime_get_noresume(&pci->dev); pci_dev_put(pci); diff --git a/sound/soc/intel/skylake/skl.h b/sound/soc/intel/skylake/skl.h index dd2e79ae45a8..a0709e344d44 100644 --- a/sound/soc/intel/skylake/skl.h +++ b/sound/soc/intel/skylake/skl.h @@ -68,6 +68,8 @@ struct skl { struct skl_dsp_resource resource; struct list_head ppl_list; struct list_head dapm_path_list; + + const struct firmware *tplg; }; #define skl_to_ebus(s) (&(s)->ebus) diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 918b4de29de4..6419f57b0850 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -110,7 +110,7 @@ int cmd_buildid_list(int argc, const char **argv, setup_pager(); if (show_kernel) - return sysfs__fprintf_build_id(stdout); + return !(sysfs__fprintf_build_id(stdout) > 0); return perf_session__list_build_ids(force, with_hits); } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index fa9eb92c9e24..81def6c3f24b 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -298,6 +298,9 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser) struct callchain_list *cl = container_of(ms, struct callchain_list, ms); bool has_children; + if (!he || !ms) + return false; + if (ms == &he->ms) has_children = hist_entry__toggle_fold(he); else @@ -928,6 +931,8 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser) } ui_browser__hists_init_top(browser); + hb->he_selection = NULL; + hb->selection = NULL; for (nd = browser->top; nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); @@ -1033,6 +1038,9 @@ static void ui_browser__hists_seek(struct ui_browser *browser, * and stop when we printed enough lines to fill the screen. */ do_offset: + if (!nd) + return; + if (offset > 0) { do { h = rb_entry(nd, struct hist_entry, rb_node); diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 217b5a60e2ab..6a7e273a514a 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -91,7 +91,7 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf) bid += 2; } - return raw - build_id; + return (bid - bf) + 1; } int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index e48d9da75707..6fc8cd753e1a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -124,6 +124,10 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { .symbol = "dummy", .alias = "", }, + [PERF_COUNT_SW_BPF_OUTPUT] = { + .symbol = "bpf-output", + .alias = "", + }, }; #define __PERF_EVENT_FIELD(config, name) \ @@ -1879,7 +1883,7 @@ restart: for (i = 0; i < max; i++, syms++) { - if (event_glob != NULL && + if (event_glob != NULL && syms->symbol != NULL && !(strglobmatch(syms->symbol, event_glob) || (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; |