From d223246ef7e6d73c8e3d9b58f27f2eb3fe95e25d Mon Sep 17 00:00:00 2001 From: Anders Kaseorg Date: Wed, 16 Sep 2009 16:44:26 -0400 Subject: x86: fix fragile computation of vsyscall address Previously, the address of the vsyscall page (VSYSCALL_PHYS_ADDR, VSYSCALL_VIRT_ADDR) was computed by arithmetic on the address of the last section. This leads to bugs when new sections are inserted, such as the one fixed by commit d312ceda567ab91acd756cde95ac5fbc6b40ed40. Let's compute it from the current address instead. Signed-off-by: Anders Kaseorg Signed-off-by: H. Peter Anvin --- arch/x86/kernel/vmlinux.lds.S | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 0ccb57d5ee3..b96ca472fa2 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -135,24 +135,21 @@ SECTIONS #ifdef CONFIG_X86_64 #define VSYSCALL_ADDR (-10*1024*1024) -#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data) + SIZEOF(.data) + \ - PAGE_SIZE - 1) & ~(PAGE_SIZE - 1)) -#define VSYSCALL_VIRT_ADDR ((ADDR(.data) + SIZEOF(.data) + \ - PAGE_SIZE - 1) & ~(PAGE_SIZE - 1)) -#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR) +#define VLOAD_OFFSET (VSYSCALL_ADDR - __vsyscall_0 + LOAD_OFFSET) #define VLOAD(x) (ADDR(x) - VLOAD_OFFSET) -#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR) +#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0) #define VVIRT(x) (ADDR(x) - VVIRT_OFFSET) + . = ALIGN(4096); + __vsyscall_0 = .; + . = VSYSCALL_ADDR; - .vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) { + .vsyscall_0 : AT(VLOAD(.vsyscall_0)) { *(.vsyscall_0) } :user - __vsyscall_0 = VSYSCALL_VIRT_ADDR; - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) @@ -192,11 +189,9 @@ SECTIONS *(.vsyscall_3) } - . = VSYSCALL_VIRT_ADDR + PAGE_SIZE; + . = __vsyscall_0 + PAGE_SIZE; #undef VSYSCALL_ADDR -#undef VSYSCALL_PHYS_ADDR -#undef VSYSCALL_VIRT_ADDR #undef VLOAD_OFFSET #undef VLOAD #undef VVIRT_OFFSET -- cgit v1.2.3 From 1dc818c1c574a4caa7b575bd9018d04090fb6c86 Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Wed, 16 Sep 2009 16:44:27 -0400 Subject: x86: convert compressed loader to use __HEAD and HEAD_TEXT macros. This has the consequence of changing the section name use for head code from ".text.head" to ".head.text". Linus suggested that we merge the ".text.head" section with ".text" (presumably while preserving the fact that the head code starts at 0). When I tried this it caused the kernel to not boot. Signed-off-by: Tim Abbott Cc: Ingo Molnar Cc: Sam Ravnborg Cc: Linus Torvalds Signed-off-by: H. Peter Anvin --- arch/x86/boot/compressed/head_32.S | 3 ++- arch/x86/boot/compressed/head_64.S | 3 ++- arch/x86/boot/compressed/vmlinux.lds.S | 6 ++++-- 3 files changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 75e4f001e70..f543b70ffae 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -23,13 +23,14 @@ */ .text +#include #include #include #include #include #include - .section ".text.head","ax",@progbits + __HEAD ENTRY(startup_32) cld /* diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index f62c284db9e..077e1b69198 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -24,6 +24,7 @@ .code32 .text +#include #include #include #include @@ -33,7 +34,7 @@ #include #include - .section ".text.head" + __HEAD .code32 ENTRY(startup_32) cld diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index cc353e1b3ff..f4193bb4878 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -1,3 +1,5 @@ +#include + OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT) #undef i386 @@ -18,9 +20,9 @@ SECTIONS * address 0. */ . = 0; - .text.head : { + .head.text : { _head = . ; - *(.text.head) + HEAD_TEXT _ehead = . ; } .rodata.compressed : { -- cgit v1.2.3 From 4ae59b916d269255800d69a07ac5b0c368a417f8 Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Wed, 16 Sep 2009 16:44:28 -0400 Subject: x86: convert to use __HEAD and HEAD_TEXT macros. This has the consequence of changing the section name use for head code from ".text.head" to ".head.text". It also eliminates the ".text.head" output section (instead placing head code at the start of the .text output section), which should be harmless. This patch only changes the sections in the actual kernel, not those in the compressed boot loader. Signed-off-by: Tim Abbott Cc: Ingo Molnar Cc: Sam Ravnborg Signed-off-by: H. Peter Anvin --- arch/x86/kernel/head_32.S | 2 +- arch/x86/kernel/head_64.S | 2 +- arch/x86/kernel/vmlinux.lds.S | 12 +++--------- 3 files changed, 5 insertions(+), 11 deletions(-) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 7ffec6b3b33..64ad7696786 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -79,7 +79,7 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE) * any particular GDT layout, because we load our own as soon as we * can. */ -.section .text.head,"ax",@progbits +__HEAD ENTRY(startup_32) /* test KEEP_SEGMENTS flag to see if the bootloader is asking us to not reload segments */ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index fa54f78e2a0..26406601031 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -40,7 +40,7 @@ L4_START_KERNEL = pgd_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) .text - .section .text.head + __HEAD .code64 .globl startup_64 startup_64: diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index b96ca472fa2..5c7826dd804 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -65,17 +65,11 @@ SECTIONS #endif /* Text and read-only data */ - - /* bootstrapping code */ - .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) { - _text = .; - *(.text.head) - } :text = 0x9090 - - /* The rest of the text */ .text : AT(ADDR(.text) - LOAD_OFFSET) { + _text = .; + /* bootstrapping code */ + HEAD_TEXT #ifdef CONFIG_X86_32 - /* not really needed, already page aligned */ . = ALIGN(PAGE_SIZE); *(.text.page_aligned) #endif -- cgit v1.2.3 From 07e81d61605f885920f31634a65aace52beb97db Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Wed, 16 Sep 2009 16:44:29 -0400 Subject: x86: Use section .data.page_aligned for the idt_table. The .data.idt section is just squashed into the .data.page_aligned output section by the linker script anyway, so it might as well be in the .data.page_aligned section. This eliminates all references to .data.idt on x86. Signed-off-by: Tim Abbott Cc: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/kernel/traps.c | 6 ++---- arch/x86/kernel/vmlinux.lds.S | 1 - 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 83264922a87..ea23d3b76f9 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -73,11 +73,9 @@ char ignore_fpu_irq; /* * The IDT has to be page-aligned to simplify the Pentium - * F0 0F bug workaround.. We have a special link segment - * for this. + * F0 0F bug workaround. */ -gate_desc idt_table[NR_VECTORS] - __attribute__((__section__(".data.idt"))) = { { { { 0, 0 } } }, }; +gate_desc idt_table[NR_VECTORS] __page_aligned_data = { { { { 0, 0 } } }, }; #endif DECLARE_BITMAP(used_vectors, NR_VECTORS); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 5c7826dd804..7d6cef363c4 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -112,7 +112,6 @@ SECTIONS #endif PAGE_ALIGNED_DATA(PAGE_SIZE) - *(.data.idt) CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES) -- cgit v1.2.3 From 123f3e1d76952759c0fc8b4fec55a3fc8084d56f Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Wed, 16 Sep 2009 16:44:30 -0400 Subject: x86: Cleanup linker script using new linker script macros. Signed-off-by: Tim Abbott Signed-off-by: H. Peter Anvin --- arch/x86/kernel/vmlinux.lds.S | 47 +++---------------------------------------- 1 file changed, 3 insertions(+), 44 deletions(-) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 7d6cef363c4..8d2d0a271e2 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -88,13 +88,7 @@ SECTIONS NOTES :text :note - /* Exception table */ - . = ALIGN(16); - __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { - __start___ex_table = .; - *(__ex_table) - __stop___ex_table = .; - } :text = 0x9090 + EXCEPTION_TABLE(16) :text = 0x9090 RO_DATA(PAGE_SIZE) @@ -207,36 +201,12 @@ SECTIONS PERCPU_VADDR(0, :percpu) #endif - .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { - _sinittext = .; - INIT_TEXT - _einittext = .; - } + INIT_TEXT_SECTION(PAGE_SIZE) #ifdef CONFIG_X86_64 :init #endif - .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) { - INIT_DATA - } - - . = ALIGN(16); - .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) { - __setup_start = .; - *(.init.setup) - __setup_end = .; - } - .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) { - __initcall_start = .; - INITCALLS - __initcall_end = .; - } - - .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) { - __con_initcall_start = .; - *(.con_initcall.init) - __con_initcall_end = .; - } + INIT_DATA_SECTION(16) .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) { __x86_cpu_dev_start = .; @@ -244,8 +214,6 @@ SECTIONS __x86_cpu_dev_end = .; } - SECURITY_INIT - . = ALIGN(8); .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) { __parainstructions = .; @@ -276,15 +244,6 @@ SECTIONS EXIT_DATA } -#ifdef CONFIG_BLK_DEV_INITRD - . = ALIGN(PAGE_SIZE); - .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { - __initramfs_start = .; - *(.init.ramfs) - __initramfs_end = .; - } -#endif - #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP) PERCPU(PAGE_SIZE) #endif -- cgit v1.2.3 From b75fe4e5b869f8dbebd36df64a7fcda0c5b318ed Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Mon, 21 Sep 2009 13:34:06 -0700 Subject: xen: check EFER for NX before setting up GDT mapping x86-64 assumes NX is available by default, so we need to explicitly check for it before using NX. Some first-generation Intel x86-64 processors didn't support NX, and even recent systems allow it to be disabled in BIOS. [ Impact: prevent Xen crash on NX-less 64-bit machines ] Signed-off-by: Jeremy Fitzhardinge Cc: Stable Kernel --- arch/x86/mm/Makefile | 1 + arch/x86/xen/enlighten.c | 10 +++++----- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 9b5a9f59a47..dd313d035de 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -4,6 +4,7 @@ obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_physaddr.o := $(nostackp) +CFLAGS_init.o := $(nostackp) obj-$(CONFIG_SMP) += tlb.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0dd0c2c6cae..5d701bf66a2 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1083,6 +1083,11 @@ asmlinkage void __init xen_start_kernel(void) __supported_pte_mask |= _PAGE_IOMAP; +#ifdef CONFIG_X86_64 + /* Work out if we support NX */ + check_efer(); +#endif + xen_setup_features(); /* Get mfn list */ @@ -1123,11 +1128,6 @@ asmlinkage void __init xen_start_kernel(void) pgd = (pgd_t *)xen_start_info->pt_base; -#ifdef CONFIG_X86_64 - /* Work out if we support NX */ - check_efer(); -#endif - /* Don't do the full vcpu_info placement stuff until we have a possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; -- cgit v1.2.3 From c44c9ec0f38b939b3200436e3aa95c1aa83c41c7 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Mon, 21 Sep 2009 13:40:42 -0700 Subject: x86: split NX setup into separate file to limit unstack-protected code Move the NX setup into a separate file so that it can be compiled without stack-protection while leaving the rest of the mm/init code protected. Signed-off-by: Jeremy Fitzhardinge --- arch/x86/include/asm/pgtable_types.h | 1 + arch/x86/mm/Makefile | 4 +-- arch/x86/mm/init.c | 63 -------------------------------- arch/x86/mm/setup_nx.c | 69 ++++++++++++++++++++++++++++++++++++ 4 files changed, 72 insertions(+), 65 deletions(-) create mode 100644 arch/x86/mm/setup_nx.c diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 54cb697f490..e9918d99f83 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -277,6 +277,7 @@ static inline pteval_t pte_flags(pte_t pte) typedef struct page *pgtable_t; extern pteval_t __supported_pte_mask; +extern void set_nx(void); extern int nx_enabled; #define pgprot_writecombine pgprot_writecombine diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index dd313d035de..06630d26e56 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,10 +1,10 @@ obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o gup.o + pat.o pgtable.o physaddr.o gup.o setup_nx.o # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_physaddr.o := $(nostackp) -CFLAGS_init.o := $(nostackp) +CFLAGS_setup_nx.o := $(nostackp) obj-$(CONFIG_SMP) += tlb.o diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 0607119cef9..73ffd5536f6 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -28,69 +28,6 @@ int direct_gbpages #endif ; -int nx_enabled; - -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) -static int disable_nx __cpuinitdata; - -/* - * noexec = on|off - * - * Control non-executable mappings for processes. - * - * on Enable - * off Disable - */ -static int __init noexec_setup(char *str) -{ - if (!str) - return -EINVAL; - if (!strncmp(str, "on", 2)) { - __supported_pte_mask |= _PAGE_NX; - disable_nx = 0; - } else if (!strncmp(str, "off", 3)) { - disable_nx = 1; - __supported_pte_mask &= ~_PAGE_NX; - } - return 0; -} -early_param("noexec", noexec_setup); -#endif - -#ifdef CONFIG_X86_PAE -static void __init set_nx(void) -{ - unsigned int v[4], l, h; - - if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) { - cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]); - - if ((v[3] & (1 << 20)) && !disable_nx) { - rdmsr(MSR_EFER, l, h); - l |= EFER_NX; - wrmsr(MSR_EFER, l, h); - nx_enabled = 1; - __supported_pte_mask |= _PAGE_NX; - } - } -} -#else -static inline void set_nx(void) -{ -} -#endif - -#ifdef CONFIG_X86_64 -void __cpuinit check_efer(void) -{ - unsigned long efer; - - rdmsrl(MSR_EFER, efer); - if (!(efer & EFER_NX) || disable_nx) - __supported_pte_mask &= ~_PAGE_NX; -} -#endif - static void __init find_early_table_space(unsigned long end, int use_pse, int use_gbpages) { diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c new file mode 100644 index 00000000000..513d8ed5d2e --- /dev/null +++ b/arch/x86/mm/setup_nx.c @@ -0,0 +1,69 @@ +#include +#include +#include + +#include + +int nx_enabled; + +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) +static int disable_nx __cpuinitdata; + +/* + * noexec = on|off + * + * Control non-executable mappings for processes. + * + * on Enable + * off Disable + */ +static int __init noexec_setup(char *str) +{ + if (!str) + return -EINVAL; + if (!strncmp(str, "on", 2)) { + __supported_pte_mask |= _PAGE_NX; + disable_nx = 0; + } else if (!strncmp(str, "off", 3)) { + disable_nx = 1; + __supported_pte_mask &= ~_PAGE_NX; + } + return 0; +} +early_param("noexec", noexec_setup); +#endif + +#ifdef CONFIG_X86_PAE +void __init set_nx(void) +{ + unsigned int v[4], l, h; + + if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) { + cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]); + + if ((v[3] & (1 << 20)) && !disable_nx) { + rdmsr(MSR_EFER, l, h); + l |= EFER_NX; + wrmsr(MSR_EFER, l, h); + nx_enabled = 1; + __supported_pte_mask |= _PAGE_NX; + } + } +} +#else +void set_nx(void) +{ +} +#endif + +#ifdef CONFIG_X86_64 +void __cpuinit check_efer(void) +{ + unsigned long efer; + + rdmsrl(MSR_EFER, efer); + if (!(efer & EFER_NX) || disable_nx) + __supported_pte_mask &= ~_PAGE_NX; +} +#endif + -- cgit v1.2.3 From 3967684006f30c253bc6d4a6604d1bad4a7fc672 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 22 Sep 2009 15:50:24 +0200 Subject: x86: mce: Clean up thermal throttling state tracking code Instead of a mess of three separate percpu variables, consolidate the state into a single structure. Also clean up therm_throt_process(), use cleaner and more understandable variable names and a clearer logic. This, without changing the logic, makes the code more streamlined, more readable and smaller as well: text data bss dec hex filename 1487 169 4 1660 67c therm_throt.o.before 1432 176 4 1612 64c therm_throt.o.after Cc: Hidetoshi Seto Cc: Huang Ying Cc: Andi Kleen LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/therm_throt.c | 63 ++++++++++++++++++++------------ 1 file changed, 39 insertions(+), 24 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 63a56d147e4..db80b577f60 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -34,20 +34,30 @@ /* How long to wait between reporting thermal events */ #define CHECK_INTERVAL (300 * HZ) -static DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES; -static DEFINE_PER_CPU(unsigned long, thermal_throttle_count); -static DEFINE_PER_CPU(bool, thermal_throttle_active); +/* + * Current thermal throttling state: + */ +struct thermal_state { + bool is_throttled; + + u64 next_check; + unsigned long throttle_count; +}; + +static DEFINE_PER_CPU(struct thermal_state, thermal_state); -static atomic_t therm_throt_en = ATOMIC_INIT(0); +static atomic_t therm_throt_en = ATOMIC_INIT(0); #ifdef CONFIG_SYSFS #define define_therm_throt_sysdev_one_ro(_name) \ static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL) #define define_therm_throt_sysdev_show_func(name) \ -static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev, \ - struct sysdev_attribute *attr, \ - char *buf) \ + \ +static ssize_t therm_throt_sysdev_show_##name( \ + struct sys_device *dev, \ + struct sysdev_attribute *attr, \ + char *buf) \ { \ unsigned int cpu = dev->id; \ ssize_t ret; \ @@ -55,7 +65,7 @@ static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev, \ preempt_disable(); /* CPU hotplug */ \ if (cpu_online(cpu)) \ ret = sprintf(buf, "%lu\n", \ - per_cpu(thermal_throttle_##name, cpu)); \ + per_cpu(thermal_state, cpu).name); \ else \ ret = 0; \ preempt_enable(); \ @@ -63,11 +73,11 @@ static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev, \ return ret; \ } -define_therm_throt_sysdev_show_func(count); -define_therm_throt_sysdev_one_ro(count); +define_therm_throt_sysdev_show_func(throttle_count); +define_therm_throt_sysdev_one_ro(throttle_count); static struct attribute *thermal_throttle_attrs[] = { - &attr_count.attr, + &attr_throttle_count.attr, NULL }; @@ -93,33 +103,38 @@ static struct attribute_group thermal_throttle_attr_group = { * 1 : Event should be logged further, and a message has been * printed to the syslog. */ -static int therm_throt_process(int curr) +static int therm_throt_process(bool is_throttled) { - unsigned int cpu = smp_processor_id(); - __u64 tmp_jiffs = get_jiffies_64(); - bool was_throttled = __get_cpu_var(thermal_throttle_active); - bool is_throttled = __get_cpu_var(thermal_throttle_active) = curr; + struct thermal_state *state; + unsigned int this_cpu; + bool was_throttled; + u64 now; + + this_cpu = smp_processor_id(); + now = get_jiffies_64(); + state = &per_cpu(thermal_state, this_cpu); + + was_throttled = state->is_throttled; + state->is_throttled = is_throttled; if (is_throttled) - __get_cpu_var(thermal_throttle_count)++; + state->throttle_count++; if (!(was_throttled ^ is_throttled) && - time_before64(tmp_jiffs, __get_cpu_var(next_check))) + time_before64(now, state->next_check)) return 0; - __get_cpu_var(next_check) = tmp_jiffs + CHECK_INTERVAL; + state->next_check = now + CHECK_INTERVAL; /* if we just entered the thermal event */ if (is_throttled) { - printk(KERN_CRIT "CPU%d: Temperature above threshold, " - "cpu clock throttled (total events = %lu)\n", - cpu, __get_cpu_var(thermal_throttle_count)); + printk(KERN_CRIT "CPU%d: Temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, state->throttle_count); add_taint(TAINT_MACHINE_CHECK); return 1; } if (was_throttled) { - printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu); + printk(KERN_INFO "CPU%d: Temperature/speed normal\n", this_cpu); return 1; } @@ -213,7 +228,7 @@ static void intel_thermal_interrupt(void) __u64 msr_val; rdmsrl(MSR_IA32_THERM_STATUS, msr_val); - if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT)) + if (therm_throt_process((msr_val & THERM_STATUS_PROCHOT) != 0)) mce_log_therm_throt_event(msr_val); } -- cgit v1.2.3 From b417c9fd8690637f0c91479435ab3e2bf450c038 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 22 Sep 2009 15:50:24 +0200 Subject: x86: mce: Fix thermal throttling message storm If a system switches back and forth between hot and cold mode, the MCE code will print a stream of critical kernel messages. Extend the throttling code to properly notice this, by only printing the first hot + cold transition and omitting the rest up to CHECK_INTERVAL (5 minutes). This way we'll only get a single incident of: [ 102.356584] CPU0: Temperature above threshold, cpu clock throttled (total events = 1) [ 102.357000] Disabling lock debugging due to kernel taint [ 102.369223] CPU0: Temperature/speed normal Every 5 minutes. The 'total events' count tells the number of cold/hot transitions detected, should overheating occur after 5 minutes again: [ 402.357580] CPU0: Temperature above threshold, cpu clock throttled (total events = 24891) [ 402.358001] CPU0: Temperature/speed normal [ 450.704142] Machine check events logged Cc: Hidetoshi Seto Cc: Huang Ying Cc: Andi Kleen LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/therm_throt.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index db80b577f60..b3a1dba7533 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -42,6 +42,7 @@ struct thermal_state { u64 next_check; unsigned long throttle_count; + unsigned long last_throttle_count; }; static DEFINE_PER_CPU(struct thermal_state, thermal_state); @@ -120,11 +121,12 @@ static int therm_throt_process(bool is_throttled) if (is_throttled) state->throttle_count++; - if (!(was_throttled ^ is_throttled) && - time_before64(now, state->next_check)) + if (time_before64(now, state->next_check) && + state->throttle_count != state->last_throttle_count) return 0; state->next_check = now + CHECK_INTERVAL; + state->last_throttle_count = state->throttle_count; /* if we just entered the thermal event */ if (is_throttled) { -- cgit v1.2.3 From 14c0abf14a5e67e793131116bd97f57da37ccce3 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 22 Sep 2009 14:35:57 +0800 Subject: x86: mce, inject: Use real inject-msg in raise_local Current raise_local() uses a struct mce that comes from mce_write() as a parameter instead of the real inject-msg, so when we set mce.finished = 0 to clear injected MCE, the real inject stays valid. This will cause the remaining inject-msg affect the next injection, which is not desired. To fix this, real inject-msg is used in raise_local instead of the one on the stack. This patch is based on the diagnosis and the fixes by Dean Nelson. Reported-by: Dean Nelson Signed-off-by: Huang Ying Cc: Hidetoshi Seto Cc: Andi Kleen LKML-Reference: <1253601357.15717.757.camel@yhuang-dev.sh.intel.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/mce-inject.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 7029f0e2aca..472763d9209 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -98,8 +98,9 @@ static struct notifier_block mce_raise_nb = { }; /* Inject mce on current CPU */ -static int raise_local(struct mce *m) +static int raise_local(void) { + struct mce *m = &__get_cpu_var(injectm); int context = MCJ_CTX(m->inject_flags); int ret = 0; int cpu = m->extcpu; @@ -167,12 +168,12 @@ static void raise_mce(struct mce *m) } cpu_relax(); } - raise_local(m); + raise_local(); put_cpu(); put_online_cpus(); } else #endif - raise_local(m); + raise_local(); } /* Error injection interface */ -- cgit v1.2.3 From 11868a2dc4f5e4f2f652bfd259e1360193fcee62 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 23 Sep 2009 17:49:55 +0200 Subject: x86: mce: Use safer ways to access MCE registers Use rdmsrl_safe() when accessing MCE registers. While in theory we always 'know' which ones are safe to access from the capability bits, there's a lot of hardware variations and reality might differ from theory, as it did in this case: http://bugzilla.kernel.org/show_bug.cgi?id=14204 [ 0.010016] mce: CPU supports 5 MCE banks [ 0.011029] general protection fault: 0000 [#1] [ 0.011998] last sysfs file: [ 0.011998] Modules linked in: [ 0.011998] [ 0.011998] Pid: 0, comm: swapper Not tainted (2.6.31_router #1) HP Vectra [ 0.011998] EIP: 0060:[] EFLAGS: 00010246 CPU: 0 [ 0.011998] EIP is at mce_rdmsrl+0x19/0x60 [ 0.011998] EAX: 00000000 EBX: 00000001 ECX: 00000407 EDX: 08000000 [ 0.011998] ESI: 00000000 EDI: 8c000000 EBP: 00000405 ESP: c17d5eac So WARN_ONCE() instead of crashing the box. ( also fix a number of stylistic inconsistencies in the code. ) Note, we might still crash in wrmsrl() if we get that far, but we shouldnt if the registers are truly inaccessible. Reported-by: GNUtoo Cc: Hidetoshi Seto Cc: Huang Ying Cc: Andi Kleen LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/mce.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 2f5aab26320..4b2af86e3e8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -305,13 +305,25 @@ static int msr_to_offset(u32 msr) static u64 mce_rdmsrl(u32 msr) { u64 v; + if (__get_cpu_var(injectm).finished) { int offset = msr_to_offset(msr); + if (offset < 0) return 0; return *(u64 *)((char *)&__get_cpu_var(injectm) + offset); } - rdmsrl(msr, v); + + if (rdmsrl_safe(msr, &v)) { + WARN_ONCE(1, "mce: Unable to read msr %d!\n", msr); + /* + * Return zero in case the access faulted. This should + * not happen normally but can happen if the CPU does + * something weird, or if the code is buggy. + */ + v = 0; + } + return v; } @@ -319,6 +331,7 @@ static void mce_wrmsrl(u32 msr, u64 v) { if (__get_cpu_var(injectm).finished) { int offset = msr_to_offset(msr); + if (offset >= 0) *(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v; return; @@ -415,7 +428,7 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs) m->ip = mce_rdmsrl(rip_msr); } -#ifdef CONFIG_X86_LOCAL_APIC +#ifdef CONFIG_X86_LOCAL_APIC /* * Called after interrupts have been reenabled again * when a MCE happened during an interrupts off region @@ -1172,6 +1185,7 @@ static int mce_banks_init(void) return -ENOMEM; for (i = 0; i < banks; i++) { struct mce_bank *b = &mce_banks[i]; + b->ctl = -1ULL; b->init = 1; } @@ -1203,6 +1217,7 @@ static int __cpuinit mce_cap_init(void) banks = b; if (!mce_banks) { int err = mce_banks_init(); + if (err) return err; } @@ -1237,6 +1252,7 @@ static void mce_init(void) for (i = 0; i < banks; i++) { struct mce_bank *b = &mce_banks[i]; + if (!b->init) continue; wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); @@ -1626,6 +1642,7 @@ static int mce_disable(void) for (i = 0; i < banks; i++) { struct mce_bank *b = &mce_banks[i]; + if (b->init) wrmsrl(MSR_IA32_MCx_CTL(i), 0); } @@ -1911,6 +1928,7 @@ static void mce_disable_cpu(void *h) cmci_clear(); for (i = 0; i < banks; i++) { struct mce_bank *b = &mce_banks[i]; + if (b->init) wrmsrl(MSR_IA32_MCx_CTL(i), 0); } @@ -1928,6 +1946,7 @@ static void mce_reenable_cpu(void *h) cmci_reenable(); for (i = 0; i < banks; i++) { struct mce_bank *b = &mce_banks[i]; + if (b->init) wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); } -- cgit v1.2.3 From ea01c0d7315d6e3218fd22a6947c5b09305fcf65 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Wed, 23 Sep 2009 15:33:23 -0700 Subject: x86: Reduce verbosity of "TSC is reliable" message On modern systems, the kernel prints the message Skipping synchronization checks as TSC is reliable. once for every non-boot CPU. This gets kind of ridiculous on huge systems; for example, on a 64-thread system I was lucky enough to get: $ dmesg | grep 'TSC is reliable' | wc 63 567 4221 There's no point to doing this for every CPU, since the code is just checking the boot CPU anyway, so change this to a printk_once() to make the message appears only once. Signed-off-by: Roland Dreier LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/kernel/tsc_sync.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 027b5b49899..f37930954d1 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -114,7 +114,7 @@ void __cpuinit check_tsc_sync_source(int cpu) return; if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) { - pr_info("Skipping synchronization checks as TSC is reliable.\n"); + printk_once(KERN_INFO "Skipping synchronization checks as TSC is reliable.\n"); return; } -- cgit v1.2.3 From e23a8b6a8f319c0f08b6ccef2dccbb37e7603dc2 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Wed, 23 Sep 2009 15:35:35 -0700 Subject: x86: Reduce verbosity of "PAT enabled" kernel message On modern systems, the kernel prints the message x86 PAT enabled: cpu 0, old 0x7040600070406, new 0x7010600070106 once for every CPU. This gets kind of ridiculous on huge systems; for example, on a 64-thread system I was lucky enough to get: dmesg| grep 'PAT enabled' | wc 64 704 5174 There is already a BUG() if non-boot CPUs have PAT capabilities that don't match the boot CPU, so just print the message on the boot CPU. (I kept the print after the wrmsrl() that enables PAT, so that the log output continues to mean that the system survived enabling PAT on the boot CPU) Signed-off-by: Roland Dreier Cc: Suresh Siddha Cc: Venkatesh Pallipadi LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 7257cf3decf..e78cd0ec2bc 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -81,6 +81,7 @@ enum { void pat_init(void) { u64 pat; + bool boot_cpu = !boot_pat_state; if (!pat_enabled) return; @@ -122,8 +123,10 @@ void pat_init(void) rdmsrl(MSR_IA32_CR_PAT, boot_pat_state); wrmsrl(MSR_IA32_CR_PAT, pat); - printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n", - smp_processor_id(), boot_pat_state, pat); + + if (boot_cpu) + printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n", + smp_processor_id(), boot_pat_state, pat); } #undef PAT -- cgit v1.2.3 From 429a6e5e2c1fbe5d805aad123efbdb5f0c14769f Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Wed, 23 Sep 2009 18:13:13 -0500 Subject: x86: early_printk: Protect against using the same device twice If you use the kernel argument: earlyprintk=serial,ttyS0,115200 This will cause a recursive hang printing the same line again and again: BIOS-e820: 000000003fff3000 - 0000000040000000 (ACPI data) BIOS-e820: 00000000e0000000 - 00000000f0000000 (reserved) BIOS-e820: 00000000fec00000 - 0000000100000000 (reserved) bootconsole [earlyser0] enabled Linux version 2.6.31-07863-gb64ada6 (mingo@sirius) (gcc version 4.3.2 20081105 (Red Hat 4.3.2-7) (GCC) ) #16789 SMP Wed Sep 23 21:09:43 CEST 2009 Linux version 2.6.31-07863-gb64ada6 (mingo@sirius) (gcc version 4.3.2 20081105 (Red Hat 4.3.2-7) (GCC) ) #16789 SMP Wed Sep 23 21:09:43 CEST 2009 Linux version 2.6.31-07863-gb64ada6 (mingo@sirius) (gcc version 4.3.2 20081105 (Red Hat 4.3.2-7) (GCC) ) #16789 SMP Wed Sep 23 21:09:43 CEST 2009 Linux version 2.6.31-07863-gb64ada6 (mingo@sirius) (gcc version 4.3.2 20081105 (Red Hat 4.3.2-7) (GCC) ) #16789 SMP Wed Sep 23 21:09:43 CEST 2009 Linux version 2.6.31-07863-gb64ada6 (mingo@sirius) (gcc version 4.3.2 20081105 (Red Hat 4.3.2-7) (GCC) ) #16789 SMP Wed Sep 23 21:09:43 CEST 2009 Instead warn the end user that they specified the device a second time, and ignore that second console. Reported-by: Ingo Molnar Signed-off-by: Jason Wessel Cc: Len Brown Cc: Greg KH Cc: Andrew Morton Cc: Linus Torvalds LKML-Reference: <4ABAAB89.1080407@windriver.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/early_printk.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 2acfd3fdc0c..41fd965c80c 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -178,6 +178,11 @@ asmlinkage void early_printk(const char *fmt, ...) static inline void early_console_register(struct console *con, int keep_early) { + if (early_console->index != -1) { + printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n", + con->name); + return; + } early_console = con; if (keep_early) early_console->flags &= ~CON_BOOT; -- cgit v1.2.3 From b0c6fbe458183cc7e1cab17be6efcbe7e435bad3 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 24 Sep 2009 17:48:44 +0930 Subject: x86: Remove redundant non-NUMA topology functions arch/x86/include/asm/topology.h declares inline fns cpu_to_node and cpumask_of_node for !NUMA, even though they are then declared as macros by asm-generic/topology.h, which is #included just below. The macros (which are the same) end up being used; these functions are just confusing. Noticed-by: Linus Torvalds Signed-off-by: Rusty Russell Cc: Jesse Barnes Cc: "Greg Kroah-Hartman" Cc: Yinghai Lu Cc: Tejun Heo LKML-Reference: <200909241748.45629.rusty@rustcorp.com.au> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/topology.h | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 6f0695d744b..25a92842dd9 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -165,21 +165,11 @@ static inline int numa_node_id(void) return 0; } -static inline int cpu_to_node(int cpu) -{ - return 0; -} - static inline int early_cpu_to_node(int cpu) { return 0; } -static inline const struct cpumask *cpumask_of_node(int node) -{ - return cpu_online_mask; -} - static inline void setup_node_to_cpumask_map(void) { } #endif -- cgit v1.2.3