diff options
Diffstat (limited to 'arch')
33 files changed, 225 insertions, 222 deletions
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 5e3f1edf5a29..db1eee5fe502 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -168,6 +168,7 @@ END(EV_Extension) tracesys: ; save EFA in case tracer wants the PC of traced task ; using ERET won't work since next-PC has already committed + lr r12, [efa] GET_CURR_TASK_FIELD_PTR TASK_THREAD, r11 st r12, [r11, THREAD_FAULT_ADDR] ; thread.fault_address @@ -210,9 +211,15 @@ tracesys_exit: ; Breakpoint TRAP ; --------------------------------------------- trap_with_param: - mov r0, r12 ; EFA in case ptracer/gdb wants stop_pc + + ; stop_pc info by gdb needs this info + lr r0, [efa] mov r1, sp + ; Now that we have read EFA, it is safe to do "fake" rtie + ; and get out of CPU exception mode + FAKE_RET_FROM_EXCPN + ; Save callee regs in case gdb wants to have a look ; SP will grow up by size of CALLEE Reg-File ; NOTE: clobbers r12 @@ -239,10 +246,6 @@ ENTRY(EV_Trap) EXCEPTION_PROLOGUE - lr r12, [efa] - - FAKE_RET_FROM_EXCPN - ;============ TRAP 1 :breakpoints ; Check ECR for trap with arg (PROLOGUE ensures r9 has ECR) bmsk.f 0, r9, 7 @@ -250,6 +253,9 @@ ENTRY(EV_Trap) ;============ TRAP (no param): syscall top level + ; First return from Exception to pure K mode (Exception/IRQs renabled) + FAKE_RET_FROM_EXCPN + ; If syscall tracing ongoing, invoke pre-post-hooks GET_CURR_THR_INFO_FLAGS r10 btst r10, TIF_SYSCALL_TRACE diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index 11b50959f20e..5401e2bab3da 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -113,7 +113,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, int (*consumer_fn) (unsigned int, void *), void *arg) { #ifdef CONFIG_ARC_DW2_UNWIND - int ret = 0; + int ret = 0, cnt = 0; unsigned int address; struct unwind_frame_info frame_info; @@ -133,6 +133,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, break; frame_info.regs.r63 = frame_info.regs.r31; + + if (cnt++ > 128) { + printk("unwinder looping too long, aborting !\n"); + return 0; + } } return address; /* return the last address it saw */ diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9755575d4c79..9d6c133691bf 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -717,7 +717,9 @@ config ARCH_S3C24XX select HAVE_S3C_RTC if RTC_CLASS select MULTI_IRQ_HANDLER select NEED_MACH_IO_H + select S3C2410_WATCHDOG select SAMSUNG_ATAGS + select WATCHDOG help Samsung S3C2410, S3C2412, S3C2413, S3C2416, S3C2440, S3C2442, S3C2443 and S3C2450 SoCs based systems, such as the Simtec Electronics BAST diff --git a/arch/arm/boot/dts/s5pv210.dtsi b/arch/arm/boot/dts/s5pv210.dtsi index b03fe747b98c..48bcab25720a 100644 --- a/arch/arm/boot/dts/s5pv210.dtsi +++ b/arch/arm/boot/dts/s5pv210.dtsi @@ -99,19 +99,16 @@ }; clocks: clock-controller@e0100000 { - compatible = "samsung,s5pv210-clock", "simple-bus"; + compatible = "samsung,s5pv210-clock"; reg = <0xe0100000 0x10000>; clock-names = "xxti", "xusbxti"; clocks = <&xxti>, <&xusbxti>; #clock-cells = <1>; - #address-cells = <1>; - #size-cells = <1>; - ranges; + }; - pmu_syscon: syscon@e0108000 { - compatible = "samsung-s5pv210-pmu", "syscon"; - reg = <0xe0108000 0x8000>; - }; + pmu_syscon: syscon@e0108000 { + compatible = "samsung-s5pv210-pmu", "syscon"; + reg = <0xe0108000 0x8000>; }; pinctrl0: pinctrl@e0200000 { @@ -228,43 +225,36 @@ status = "disabled"; }; - audio-subsystem { - compatible = "samsung,s5pv210-audss", "simple-bus"; - #address-cells = <1>; - #size-cells = <1>; - ranges; - - clk_audss: clock-controller@eee10000 { - compatible = "samsung,s5pv210-audss-clock"; - reg = <0xeee10000 0x1000>; - clock-names = "hclk", "xxti", - "fout_epll", - "sclk_audio0"; - clocks = <&clocks DOUT_HCLKP>, <&xxti>, - <&clocks FOUT_EPLL>, - <&clocks SCLK_AUDIO0>; - #clock-cells = <1>; - }; + clk_audss: clock-controller@eee10000 { + compatible = "samsung,s5pv210-audss-clock"; + reg = <0xeee10000 0x1000>; + clock-names = "hclk", "xxti", + "fout_epll", + "sclk_audio0"; + clocks = <&clocks DOUT_HCLKP>, <&xxti>, + <&clocks FOUT_EPLL>, + <&clocks SCLK_AUDIO0>; + #clock-cells = <1>; + }; - i2s0: i2s@eee30000 { - compatible = "samsung,s5pv210-i2s"; - reg = <0xeee30000 0x1000>; - interrupt-parent = <&vic2>; - interrupts = <16>; - dma-names = "rx", "tx", "tx-sec"; - dmas = <&pdma1 9>, <&pdma1 10>, <&pdma1 11>; - clock-names = "iis", - "i2s_opclk0", - "i2s_opclk1"; - clocks = <&clk_audss CLK_I2S>, - <&clk_audss CLK_I2S>, - <&clk_audss CLK_DOUT_AUD_BUS>; - samsung,idma-addr = <0xc0010000>; - pinctrl-names = "default"; - pinctrl-0 = <&i2s0_bus>; - #sound-dai-cells = <0>; - status = "disabled"; - }; + i2s0: i2s@eee30000 { + compatible = "samsung,s5pv210-i2s"; + reg = <0xeee30000 0x1000>; + interrupt-parent = <&vic2>; + interrupts = <16>; + dma-names = "rx", "tx", "tx-sec"; + dmas = <&pdma1 9>, <&pdma1 10>, <&pdma1 11>; + clock-names = "iis", + "i2s_opclk0", + "i2s_opclk1"; + clocks = <&clk_audss CLK_I2S>, + <&clk_audss CLK_I2S>, + <&clk_audss CLK_DOUT_AUD_BUS>; + samsung,idma-addr = <0xc0010000>; + pinctrl-names = "default"; + pinctrl-0 = <&i2s0_bus>; + #sound-dai-cells = <0>; + status = "disabled"; }; i2s1: i2s@e2100000 { diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index aa90f319309b..b8bbc8c18799 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -137,7 +137,7 @@ trips { cpu_alert0: cpu_alert0 { /* milliCelsius */ - temperature = <850000>; + temperature = <85000>; hysteresis = <2000>; type = "passive"; }; diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 5979436048d6..498f5060216c 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1281,7 +1281,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } - if (is_vm_hugetlb_page(vma) && !logging_active) { + if (vma_kernel_pagesize(vma) == PMD_SIZE && !logging_active) { hugetlb = true; gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT; } else { diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 493692d838c6..0b6f8a93d8c6 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -1228,20 +1228,28 @@ static void __init l2c310_of_parse(const struct device_node *np, ret = of_property_read_u32(np, "prefetch-data", &val); if (ret == 0) { - if (val) + if (val) { prefetch |= L310_PREFETCH_CTRL_DATA_PREFETCH; - else + *aux_val |= L310_PREFETCH_CTRL_DATA_PREFETCH; + } else { prefetch &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; + *aux_val &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; + } + *aux_mask &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; } else if (ret != -EINVAL) { pr_err("L2C-310 OF prefetch-data property value is missing\n"); } ret = of_property_read_u32(np, "prefetch-instr", &val); if (ret == 0) { - if (val) + if (val) { prefetch |= L310_PREFETCH_CTRL_INSTR_PREFETCH; - else + *aux_val |= L310_PREFETCH_CTRL_INSTR_PREFETCH; + } else { prefetch &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; + *aux_val &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; + } + *aux_mask &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; } else if (ret != -EINVAL) { pr_err("L2C-310 OF prefetch-instr property value is missing\n"); } diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig index b9396dcf836d..ffdf9f2ca437 100644 --- a/arch/arm/plat-samsung/Kconfig +++ b/arch/arm/plat-samsung/Kconfig @@ -239,6 +239,7 @@ config SAMSUNG_PM_DEBUG bool "Samsung PM Suspend debug" depends on PM && DEBUG_KERNEL depends on DEBUG_EXYNOS_UART || DEBUG_S3C24XX_UART || DEBUG_S3C2410_UART + depends on DEBUG_LL && MMU help Say Y here if you want verbose debugging from the PM Suspend and Resume code. See <file:Documentation/arm/Samsung-S3C24XX/Suspend.txt> diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 3206dc4aec53..4c30bfb9b06f 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -9,6 +9,7 @@ config ARCH_BERLIN bool "Marvell Berlin SoC Family" select ARCH_REQUIRE_GPIOLIB select DW_APB_ICTL + select DW_APB_TIMER_OF help This enables support for Marvell Berlin SoC Family diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 172402cc1a0f..ae2cbbdb634e 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -191,7 +191,7 @@ }; i2c0: i2c@ff020000 { - compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 17 4>; @@ -202,7 +202,7 @@ }; i2c1: i2c@ff030000 { - compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 18 4>; diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 55101bd86b98..dda13e308385 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -171,7 +171,7 @@ alternative_endif .macro user_alt, label, oldinstr, newinstr, cond 9999: alternative_insn "\oldinstr", "\newinstr", \cond - _ASM_EXTABLE 9999b, \label + _asm_extable 9999b, \label .endm /* diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 801a16dbbdf6..7d2a15a0f625 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -23,7 +23,7 @@ struct stackframe { unsigned long sp; unsigned long pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - unsigned int graph; + int graph; #endif }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 50033b91ce4f..2a2bf5231f6a 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -693,7 +693,7 @@ static int __init parse_kpti(char *str) __kpti_forced = enabled ? 1 : -1; return 0; } -__setup("kpti=", parse_kpti); +early_param("kpti", parse_kpti); #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ static const struct arm64_cpu_capabilities arm64_features[] = { diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 310f2f463cd4..acbc65539682 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -13,6 +13,7 @@ #include <linux/sched.h> #include <linux/types.h> +#include <asm/cacheflush.h> #include <asm/fixmap.h> #include <asm/kernel-pgtable.h> #include <asm/memory.h> @@ -42,7 +43,7 @@ static __init u64 get_kaslr_seed(void *fdt) return ret; } -static __init const u8 *get_cmdline(void *fdt) +static __init const u8 *kaslr_get_cmdline(void *fdt) { static __initconst const u8 default_cmdline[] = CONFIG_CMDLINE; @@ -86,6 +87,7 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset) * we end up running with module randomization disabled. */ module_alloc_base = (u64)_etext - MODULES_VSIZE; + __flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base)); /* * Try to map the FDT early. If this fails, we simply bail, @@ -108,7 +110,7 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset) * Check if 'nokaslr' appears on the command line, and * return 0 if that is the case. */ - cmdline = get_cmdline(fdt); + cmdline = kaslr_get_cmdline(fdt); str = strstr(cmdline, "nokaslr"); if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) return 0; @@ -177,5 +179,8 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset) module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21; module_alloc_base &= PAGE_MASK; + __flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base)); + __flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed)); + return offset; } diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 2ac2abe8a494..0edcd34b45d2 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -75,6 +75,11 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk && tsk->ret_stack && (frame->pc == (unsigned long)return_to_handler)) { + if (WARN_ON_ONCE(frame->graph == -1)) + return -EINVAL; + if (frame->graph < -1) + frame->graph += FTRACE_NOTRACE_DEPTH; + /* * This is a case where function graph tracer has * modified a return address (LR) in a stack frame diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 59779699a1a4..5d9076e86200 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -53,7 +53,7 @@ unsigned long profile_pc(struct pt_regs *regs) frame.sp = regs->sp; frame.pc = regs->pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = -1; /* no task info */ + frame.graph = current->curr_ret_stack; #endif do { int ret = unwind_frame(NULL, &frame); diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 232f787a088a..2d705ab815e4 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -18,6 +18,7 @@ #include <linux/elf.h> #include <linux/fs.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/export.h> @@ -104,12 +105,18 @@ EXPORT_SYMBOL_GPL(arch_pick_mmap_layout); */ int valid_phys_addr_range(phys_addr_t addr, size_t size) { - if (addr < PHYS_OFFSET) - return 0; - if (addr + size > __pa(high_memory - 1) + 1) - return 0; - - return 1; + /* + * Check whether addr is covered by a memory region without the + * MEMBLOCK_NOMAP attribute, and whether that region covers the + * entire range. In theory, this could lead to false negatives + * if the range is covered by distinct but adjacent memory regions + * that only differ in other attributes. However, few of such + * attributes have been defined, and it is debatable whether it + * follows that /dev/mem read() calls should be able traverse + * such boundaries. + */ + return memblock_is_region_memory(addr, size) && + memblock_is_map_memory(addr); } /* diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index b5ecf01a1e8d..e8b8590f553a 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1333,13 +1333,18 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) int __init arch_ioremap_pud_supported(void) { - /* only 4k granule supports level 1 block mappings */ - return IS_ENABLED(CONFIG_ARM64_4K_PAGES); + /* + * Only 4k granule supports level 1 block mappings. + * SW table walks can't handle removal of intermediate entries. + */ + return IS_ENABLED(CONFIG_ARM64_4K_PAGES) && + !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); } int __init arch_ioremap_pmd_supported(void) { - return 1; + /* See arch_ioremap_pud_supported() */ + return !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); } int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 9edda5466020..bcd3668f1bb8 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -42,7 +42,7 @@ endif obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o -obj-$(CONFIG_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_ELF_CORE) += elfcore.o # fp_emulate() expects f2-f5,f16-f31 to contain the user-level state. CFLAGS_traps.o += -mfixed-range=f2-f5,f16-f31 diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index ca372bbc0ffe..dd262f09a99e 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -647,7 +647,7 @@ #define THRM1_TIN (1 << 31) #define THRM1_TIV (1 << 30) #define THRM1_THRES(x) ((x&0x7f)<<23) -#define THRM3_SITV(x) ((x&0x3fff)<<1) +#define THRM3_SITV(x) ((x & 0x1fff) << 1) #define THRM1_TID (1<<2) #define THRM1_TIE (1<<1) #define THRM1_V (1<<0) diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index a753b72efbc0..70c9d134a9d4 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -37,8 +37,6 @@ static struct tau_temp struct timer_list tau_timer; -#undef DEBUG - /* TODO: put these in a /proc interface, with some sanity checks, and maybe * dynamic adjustment to minimize # of interrupts */ /* configurable values for step size and how much to expand the window when @@ -71,47 +69,33 @@ void set_thresholds(unsigned long cpu) void TAUupdate(int cpu) { - unsigned thrm; - -#ifdef DEBUG - printk("TAUupdate "); -#endif + u32 thrm; + u32 bits = THRM1_TIV | THRM1_TIN | THRM1_V; /* if both thresholds are crossed, the step_sizes cancel out * and the window winds up getting expanded twice. */ - if((thrm = mfspr(SPRN_THRM1)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed low threshold */ - if (tau[cpu].low >= step_size){ - tau[cpu].low -= step_size; - tau[cpu].high -= (step_size - window_expand); - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("low threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM1); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM1, 0); + + if (tau[cpu].low >= step_size) { + tau[cpu].low -= step_size; + tau[cpu].high -= (step_size - window_expand); } + tau[cpu].grew = 1; + pr_debug("%s: low threshold crossed\n", __func__); } - if((thrm = mfspr(SPRN_THRM2)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed high threshold */ - if (tau[cpu].high <= 127-step_size){ - tau[cpu].low += (step_size - window_expand); - tau[cpu].high += step_size; - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("high threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM2); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM2, 0); + + if (tau[cpu].high <= 127 - step_size) { + tau[cpu].low += (step_size - window_expand); + tau[cpu].high += step_size; } + tau[cpu].grew = 1; + pr_debug("%s: high threshold crossed\n", __func__); } - -#ifdef DEBUG - printk("grew = %d\n", tau[cpu].grew); -#endif - -#ifndef CONFIG_TAU_INT /* tau_timeout will do this if not using interrupts */ - set_thresholds(cpu); -#endif - } #ifdef CONFIG_TAU_INT @@ -136,18 +120,18 @@ void TAUException(struct pt_regs * regs) static void tau_timeout(void * info) { int cpu; - unsigned long flags; int size; int shrink; - /* disabling interrupts *should* be okay */ - local_irq_save(flags); cpu = smp_processor_id(); #ifndef CONFIG_TAU_INT TAUupdate(cpu); #endif + /* Stop thermal sensor comparisons and interrupts */ + mtspr(SPRN_THRM3, 0); + size = tau[cpu].high - tau[cpu].low; if (size > min_window && ! tau[cpu].grew) { /* do an exponential shrink of half the amount currently over size */ @@ -169,22 +153,12 @@ static void tau_timeout(void * info) set_thresholds(cpu); - /* - * Do the enable every time, since otherwise a bunch of (relatively) - * complex sleep code needs to be added. One mtspr every time - * tau_timeout is called is probably not a big deal. - * - * Enable thermal sensor and set up sample interval timer - * need 20 us to do the compare.. until a nice 'cpu_speed' function - * call is implemented, just assume a 500 mhz clock. It doesn't really - * matter if we take too long for a compare since it's all interrupt - * driven anyway. - * - * use a extra long time.. (60 us @ 500 mhz) + /* Restart thermal sensor comparisons and interrupts. + * The "PowerPC 740 and PowerPC 750 Microprocessor Datasheet" + * recommends that "the maximum value be set in THRM3 under all + * conditions." */ - mtspr(SPRN_THRM3, THRM3_SITV(500*60) | THRM3_E); - - local_irq_restore(flags); + mtspr(SPRN_THRM3, THRM3_SITV(0x1fff) | THRM3_E); } static void tau_timeout_smp(unsigned long unused) diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h index acd17648cd18..5ea24d16a74a 100644 --- a/arch/powerpc/perf/hv-gpci-requests.h +++ b/arch/powerpc/perf/hv-gpci-requests.h @@ -94,7 +94,7 @@ REQUEST(__field(0, 8, partition_id) #define REQUEST_NAME system_performance_capabilities #define REQUEST_NUM 0x40 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__field(0, 1, perf_collect_privileged) __field(0x1, 1, capability_mask) @@ -222,7 +222,7 @@ REQUEST(__field(0, 2, partition_id) #define REQUEST_NAME system_hypervisor_times #define REQUEST_NUM 0xF0 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) __count(0x8, 8, time_spent_processing_virtual_processor_timers) @@ -233,7 +233,7 @@ REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) #define REQUEST_NAME system_tlbie_count_and_time #define REQUEST_NUM 0xF4 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, tlbie_instructions_issued) /* diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index b7f9c408bf24..0a0281a21ea5 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -242,7 +242,7 @@ config TAU temp is actually what /proc/cpuinfo says it is. config TAU_INT - bool "Interrupt driven TAU driver (DANGEROUS)" + bool "Interrupt driven TAU driver (EXPERIMENTAL)" depends on TAU ---help--- The TAU supports an interrupt driven mode which causes an interrupt @@ -250,12 +250,7 @@ config TAU_INT to get notified the temp has exceeded a range. With this option off, a timer is used to re-check the temperature periodically. - However, on some cpus it appears that the TAU interrupt hardware - is buggy and can cause a situation which would lead unexplained hard - lockups. - - Unless you are extending the TAU driver, or enjoy kernel/hardware - debugging, leave this option off. + If in doubt, say N here. config TAU_AVERAGE bool "Average high and low temp" diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 4c827826c05e..1a8b6e276a11 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -319,15 +319,14 @@ static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj, return count; } -static struct dump_obj *create_dump_obj(uint32_t id, size_t size, - uint32_t type) +static void create_dump_obj(uint32_t id, size_t size, uint32_t type) { struct dump_obj *dump; int rc; dump = kzalloc(sizeof(*dump), GFP_KERNEL); if (!dump) - return NULL; + return; dump->kobj.kset = dump_kset; @@ -347,34 +346,51 @@ static struct dump_obj *create_dump_obj(uint32_t id, size_t size, rc = kobject_add(&dump->kobj, NULL, "0x%x-0x%x", type, id); if (rc) { kobject_put(&dump->kobj); - return NULL; + return; } + /* + * As soon as the sysfs file for this dump is created/activated there is + * a chance the opal_errd daemon (or any userspace) might read and + * acknowledge the dump before kobject_uevent() is called. If that + * happens then there is a potential race between + * dump_ack_store->kobject_put() and kobject_uevent() which leads to a + * use-after-free of a kernfs object resulting in a kernel crash. + * + * To avoid that, we need to take a reference on behalf of the bin file, + * so that our reference remains valid while we call kobject_uevent(). + * We then drop our reference before exiting the function, leaving the + * bin file to drop the last reference (if it hasn't already). + */ + + /* Take a reference for the bin file */ + kobject_get(&dump->kobj); rc = sysfs_create_bin_file(&dump->kobj, &dump->dump_attr); - if (rc) { + if (rc == 0) { + kobject_uevent(&dump->kobj, KOBJ_ADD); + + pr_info("%s: New platform dump. ID = 0x%x Size %u\n", + __func__, dump->id, dump->size); + } else { + /* Drop reference count taken for bin file */ kobject_put(&dump->kobj); - return NULL; } - pr_info("%s: New platform dump. ID = 0x%x Size %u\n", - __func__, dump->id, dump->size); - - kobject_uevent(&dump->kobj, KOBJ_ADD); - - return dump; + /* Drop our reference */ + kobject_put(&dump->kobj); + return; } static irqreturn_t process_dump(int irq, void *data) { int rc; uint32_t dump_id, dump_size, dump_type; - struct dump_obj *dump; char name[22]; struct kobject *kobj; rc = dump_read_info(&dump_id, &dump_size, &dump_type); if (rc != OPAL_SUCCESS) - return rc; + return IRQ_HANDLED; sprintf(name, "0x%x-0x%x", dump_type, dump_id); @@ -386,12 +402,10 @@ static irqreturn_t process_dump(int irq, void *data) if (kobj) { /* Drop reference added by kset_find_obj() */ kobject_put(kobj); - return 0; + return IRQ_HANDLED; } - dump = create_dump_obj(dump_id, dump_size, dump_type); - if (!dump) - return -1; + create_dump_obj(dump_id, dump_size, dump_type); return IRQ_HANDLED; } diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index f2344cbd2f46..3595f3cfefa3 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -183,14 +183,14 @@ static ssize_t raw_attr_read(struct file *filep, struct kobject *kobj, return count; } -static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) +static void create_elog_obj(uint64_t id, size_t size, uint64_t type) { struct elog_obj *elog; int rc; elog = kzalloc(sizeof(*elog), GFP_KERNEL); if (!elog) - return NULL; + return; elog->kobj.kset = elog_kset; @@ -223,18 +223,37 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) rc = kobject_add(&elog->kobj, NULL, "0x%llx", id); if (rc) { kobject_put(&elog->kobj); - return NULL; + return; } + /* + * As soon as the sysfs file for this elog is created/activated there is + * a chance the opal_errd daemon (or any userspace) might read and + * acknowledge the elog before kobject_uevent() is called. If that + * happens then there is a potential race between + * elog_ack_store->kobject_put() and kobject_uevent() which leads to a + * use-after-free of a kernfs object resulting in a kernel crash. + * + * To avoid that, we need to take a reference on behalf of the bin file, + * so that our reference remains valid while we call kobject_uevent(). + * We then drop our reference before exiting the function, leaving the + * bin file to drop the last reference (if it hasn't already). + */ + + /* Take a reference for the bin file */ + kobject_get(&elog->kobj); rc = sysfs_create_bin_file(&elog->kobj, &elog->raw_attr); - if (rc) { + if (rc == 0) { + kobject_uevent(&elog->kobj, KOBJ_ADD); + } else { + /* Drop the reference taken for the bin file */ kobject_put(&elog->kobj); - return NULL; } - kobject_uevent(&elog->kobj, KOBJ_ADD); + /* Drop our reference */ + kobject_put(&elog->kobj); - return elog; + return; } static irqreturn_t elog_event(int irq, void *data) diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index ad7b1a3dbed0..c605c78a8089 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -41,7 +41,7 @@ #include <asm/udbg.h> #define DBG(fmt...) udbg_printf(fmt) #else -#define DBG(fmt...) +#define DBG(fmt...) do { } while (0) #endif static void pnv_smp_setup_cpu(int cpu) diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c index 31ca557af60b..262b8c5e1b9d 100644 --- a/arch/powerpc/platforms/pseries/rng.c +++ b/arch/powerpc/platforms/pseries/rng.c @@ -40,6 +40,7 @@ static __init int rng_init(void) ppc_md.get_random_seed = pseries_get_random_long; + of_node_put(dn); return 0; } machine_subsys_initcall(pseries, rng_init); diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index c1917cf67c3d..3205e64c452b 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -179,6 +179,7 @@ int icp_hv_init(void) icp_ops = &icp_hv_ops; + of_node_put(np); return 0; } diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 46866b2097e8..bd27e86ce36d 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1030,38 +1030,9 @@ void smp_fetch_global_pmu(void) * are flush_tlb_*() routines, and these run after flush_cache_*() * which performs the flushw. * - * The SMP TLB coherency scheme we use works as follows: - * - * 1) mm->cpu_vm_mask is a bit mask of which cpus an address - * space has (potentially) executed on, this is the heuristic - * we use to avoid doing cross calls. - * - * Also, for flushing from kswapd and also for clones, we - * use cpu_vm_mask as the list of cpus to make run the TLB. - * - * 2) TLB context numbers are shared globally across all processors - * in the system, this allows us to play several games to avoid - * cross calls. - * - * One invariant is that when a cpu switches to a process, and - * that processes tsk->active_mm->cpu_vm_mask does not have the - * current cpu's bit set, that tlb context is flushed locally. - * - * If the address space is non-shared (ie. mm->count == 1) we avoid - * cross calls when we want to flush the currently running process's - * tlb state. This is done by clearing all cpu bits except the current - * processor's in current->mm->cpu_vm_mask and performing the - * flush locally only. This will force any subsequent cpus which run - * this task to flush the context from the local tlb if the process - * migrates to another cpu (again). - * - * 3) For shared address spaces (threads) and swapping we bite the - * bullet for most cases and perform the cross call (but only to - * the cpus listed in cpu_vm_mask). - * - * The performance gain from "optimizing" away the cross call for threads is - * questionable (in theory the big win for threads is the massive sharing of - * address space state across processors). + * mm->cpu_vm_mask is a bit mask of which cpus an address + * space has (potentially) executed on, this is the heuristic + * we use to limit cross calls. */ /* This currently is only used by the hugetlb arch pre-fault @@ -1071,18 +1042,13 @@ void smp_fetch_global_pmu(void) void smp_flush_tlb_mm(struct mm_struct *mm) { u32 ctx = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (atomic_read(&mm->mm_users) == 1) { - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - goto local_flush_and_out; - } + get_cpu(); smp_cross_call_masked(&xcall_flush_tlb_mm, ctx, 0, 0, mm_cpumask(mm)); -local_flush_and_out: __flush_tlb_mm(ctx, SECONDARY_CONTEXT); put_cpu(); @@ -1105,17 +1071,15 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long { u32 ctx = CTX_HWBITS(mm->context); struct tlb_pending_info info; - int cpu = get_cpu(); + + get_cpu(); info.ctx = ctx; info.nr = nr; info.vaddrs = vaddrs; - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_call_function_many(mm_cpumask(mm), tlb_pending_func, - &info, 1); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); @@ -1125,14 +1089,13 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) { unsigned long context = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_cross_call_masked(&xcall_flush_tlb_page, - context, vaddr, 0, - mm_cpumask(mm)); + get_cpu(); + + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); put_cpu(); diff --git a/arch/um/kernel/sigio.c b/arch/um/kernel/sigio.c index b5e0cbb34382..476ded92affa 100644 --- a/arch/um/kernel/sigio.c +++ b/arch/um/kernel/sigio.c @@ -36,14 +36,14 @@ int write_sigio_irq(int fd) } /* These are called from os-Linux/sigio.c to protect its pollfds arrays. */ -static DEFINE_SPINLOCK(sigio_spinlock); +static DEFINE_MUTEX(sigio_mutex); void sigio_lock(void) { - spin_lock(&sigio_spinlock); + mutex_lock(&sigio_mutex); } void sigio_unlock(void) { - spin_unlock(&sigio_spinlock); + mutex_unlock(&sigio_mutex); } diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 0bf17576dd2a..299e7fb55f16 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -212,8 +212,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch; /* Copying screen_info will do? */ - memcpy(¶ms->screen_info, &boot_params.screen_info, - sizeof(struct screen_info)); + memcpy(¶ms->screen_info, &screen_info, sizeof(struct screen_info)); /* Fill in memsize later */ params->screen_info.ext_mem_k = 0; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 466028623e1a..0c1e249a7ab6 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3524,7 +3524,7 @@ static int em_rdpid(struct x86_emulate_ctxt *ctxt) u64 tsc_aux = 0; if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) - return emulate_gp(ctxt, 0); + return emulate_ud(ctxt); ctxt->dst.val = tsc_aux; return X86EMUL_CONTINUE; } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0f1c6fc3ddd8..47770ccab6d7 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -15,6 +15,7 @@ #include <linux/debugfs.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/sched.h> #include <linux/seq_file.h> #include <asm/pgtable.h> @@ -407,6 +408,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, } else note_page(m, &st, __pgprot(0), 1); + cond_resched(); start++; } |