From e207e143e2fb6a2790b1ce3687c8aedc3ddc357b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 30 Sep 2009 07:48:37 -0700 Subject: Revert "x86, mce: do not compile mcelog message on AMD" This reverts commit 22223c9b417be5fd0ab2cf9ad17eb7bd1e19f7b9, as requested by Andi Kleen: "Obviously kernels compiled with AMD support can still run on non AMD systems, so messages like this can never be removed at compile time." Requsted-by: Andi Kleen Cc: Borislav Petkov Signed-off-by: Linus Torvalds --- arch/x86/kernel/cpu/mcheck/mce.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 4b2af86e3e8d..183c3457d2f4 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -204,10 +204,7 @@ static void print_mce_head(void) static void print_mce_tail(void) { printk(KERN_EMERG "This is not a software problem!\n" -#if (!defined(CONFIG_EDAC) || !defined(CONFIG_CPU_SUP_AMD)) - "Run through mcelog --ascii to decode and contact your hardware vendor\n" -#endif - ); + "Run through mcelog --ascii to decode and contact your hardware vendor\n"); } #define PANIC_TIMEOUT 5 /* 5 seconds */ -- cgit v1.2.1 From 79e1dd05d1a22e95ab6d54d21836f478b3b56976 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Wed, 30 Sep 2009 17:07:54 +0200 Subject: x86: Provide an alternative() based cmpxchg64() cmpxchg64() today generates, to quote Linus, "barf bag" code. cmpxchg64() is about to get used in the scheduler to fix a bug there, but it's a prerequisite that cmpxchg64() first be made non-sucking. This patch turns cmpxchg64() into an efficient implementation that uses the alternative() mechanism to just use the raw instruction on all modern systems. Note: the fallback is NOT smp safe, just like the current fallback is not SMP safe. (Interested parties with i486 based SMP systems are welcome to submit fix patches for that.) Signed-off-by: Arjan van de Ven Acked-by: Linus Torvalds [ fixed asm constraint bug ] Fixed-by: Eric Dumazet Cc: Martin Schwidefsky Cc: John Stultz Cc: Peter Zijlstra LKML-Reference: <20090930170754.0886ff2e@infradead.org> Signed-off-by: Ingo Molnar --- arch/x86/kernel/i386_ksyms_32.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 43cec6bdda63..1736c5a725aa 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -10,6 +10,14 @@ EXPORT_SYMBOL(mcount); #endif +/* + * Note, this is a prototype to get at the symbol for + * the export, but dont use it from C code, it is used + * by assembly code and is not using C calling convention! + */ +extern void cmpxchg8b_emu(void); +EXPORT_SYMBOL(cmpxchg8b_emu); + /* Networking helper routines. */ EXPORT_SYMBOL(csum_partial_copy_generic); -- cgit v1.2.1 From 04edbdef02ec4386a2ae38cab7ae7d166e17a756 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 1 Oct 2009 07:30:38 +0200 Subject: x86: Don't generate cmpxchg8b_emu if CONFIG_X86_CMPXCHG64=y Conditionaly compile cmpxchg8b_emu.o and EXPORT_SYMBOL(cmpxchg8b_emu). This reduces the kernel size a bit. Signed-off-by: Eric Dumazet Cc: Arjan van de Ven Cc: Martin Schwidefsky Cc: John Stultz Cc: Peter Zijlstra Cc: Linus Torvalds LKML-Reference: <4AC43E7E.1000600@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/i386_ksyms_32.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 1736c5a725aa..9c3bd4a2050e 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -15,8 +15,10 @@ EXPORT_SYMBOL(mcount); * the export, but dont use it from C code, it is used * by assembly code and is not using C calling convention! */ +#ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); EXPORT_SYMBOL(cmpxchg8b_emu); +#endif /* Networking helper routines. */ EXPORT_SYMBOL(csum_partial_copy_generic); -- cgit v1.2.1 From ea3acb199a5d7e4da1de0a4288eba993b29f33b9 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 24 Sep 2009 09:08:30 -0500 Subject: x86: earlyprintk: Fix regression to handle serial,ttySn as 1 arg Commit c953094 ("early_printk: Allow more than one early console") introduced a regression in the parsing of the earlyprintk= kernel arguments. If you specify "earlyprintk=serial,ttyS0,115200" as a kernel argument, the "serial,ttyS" should be parsed as a single argument and not as "serial" and then "ttyS". Also update the documentation to reflect you can specify the ttyS directly without the "serial" argument. Signed-off-by: Jason Wessel Cc: Len Brown Cc: Greg KH Cc: Linus Torvalds Cc: Andrew Morton Cc: Johannes Weiner LKML-Reference: <4ABB7D5E.6000301@windriver.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/early_printk.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 41fd965c80c6..b9c830c12b4a 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -206,8 +206,11 @@ static int __init setup_early_printk(char *buf) while (*buf != '\0') { if (!strncmp(buf, "serial", 6)) { - early_serial_init(buf + 6); + buf += 6; + early_serial_init(buf); early_console_register(&early_serial_console, keep); + if (!strncmp(buf, ",ttyS", 5)) + buf += 5; } if (!strncmp(buf, "ttyS", 4)) { early_serial_init(buf + 4); -- cgit v1.2.1 From f436f8bb73138bc74eb1c6527723e00988ad8a8a Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 1 Oct 2009 16:14:32 +0200 Subject: x86: EDAC: MCE: Fix MCE decoding callback logic Make decoding of MCEs happen only on AMD hardware by registering a non-default callback only on CPU families which support it. While looking at the interaction of decode_mce() with the other MCE code i also noticed a few other things and made the following cleanups/fixes: - Fixed the mce_decode() weak alias - a weak alias is really not good here, it should be a proper callback. A weak alias will be overriden if a piece of code is built into the kernel - not good, obviously. - The patch initializes the callback on AMD family 10h and 11h. - Added the more correct fallback printk of: No support for human readable MCE decoding on this CPU type. Transcribe the message and run it through 'mcelog --ascii' to decode. On CPUs that dont have a decoder. - Made the surrounding code more readable. Note that the callback allows us to have a default fallback - without having to check the CPU versions during the printout itself. When an EDAC module registers itself, it can install the decode-print function. (there's no unregister needed as this is core code.) version -v2 by Borislav Petkov: - add K8 to the set of supported CPUs - always build in edac_mce_amd since we use an early_initcall now - fix checkpatch warnings Signed-off-by: Borislav Petkov Cc: Linus Torvalds Cc: Andi Kleen LKML-Reference: <20091001141432.GA11410@aftab> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/mce.c | 58 +++++++++++++++++++++++++--------------- 1 file changed, 36 insertions(+), 22 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 183c3457d2f4..b1598a9436d0 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -85,6 +85,18 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait); static DEFINE_PER_CPU(struct mce, mces_seen); static int cpu_missing; +static void default_decode_mce(struct mce *m) +{ + pr_emerg("No human readable MCE decoding support on this CPU type.\n"); + pr_emerg("Run the message through 'mcelog --ascii' to decode.\n"); +} + +/* + * CPU/chipset specific EDAC code can register a callback here to print + * MCE errors in a human-readable form: + */ +void (*x86_mce_decode_callback)(struct mce *m) = default_decode_mce; +EXPORT_SYMBOL(x86_mce_decode_callback); /* MCA banks polled by the period polling timer for corrected events */ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { @@ -165,46 +177,46 @@ void mce_log(struct mce *mce) set_bit(0, &mce_need_notify); } -void __weak decode_mce(struct mce *m) -{ - return; -} - static void print_mce(struct mce *m) { - printk(KERN_EMERG - "CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n", + pr_emerg("CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n", m->extcpu, m->mcgstatus, m->bank, m->status); + if (m->ip) { - printk(KERN_EMERG "RIP%s %02x:<%016Lx> ", - !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", - m->cs, m->ip); + pr_emerg("RIP%s %02x:<%016Lx> ", + !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", + m->cs, m->ip); + if (m->cs == __KERNEL_CS) print_symbol("{%s}", m->ip); - printk(KERN_CONT "\n"); + pr_cont("\n"); } - printk(KERN_EMERG "TSC %llx ", m->tsc); + + pr_emerg("TSC %llx ", m->tsc); if (m->addr) - printk(KERN_CONT "ADDR %llx ", m->addr); + pr_cont("ADDR %llx ", m->addr); if (m->misc) - printk(KERN_CONT "MISC %llx ", m->misc); - printk(KERN_CONT "\n"); - printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n", - m->cpuvendor, m->cpuid, m->time, m->socketid, - m->apicid); + pr_cont("MISC %llx ", m->misc); + + pr_cont("\n"); + pr_emerg("PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n", + m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid); - decode_mce(m); + /* + * Print out human-readable details about the MCE error, + * (if the CPU has an implementation for that): + */ + x86_mce_decode_callback(m); } static void print_mce_head(void) { - printk(KERN_EMERG "\nHARDWARE ERROR\n"); + pr_emerg("\nHARDWARE ERROR\n"); } static void print_mce_tail(void) { - printk(KERN_EMERG "This is not a software problem!\n" - "Run through mcelog --ascii to decode and contact your hardware vendor\n"); + pr_emerg("This is not a software problem!\n"); } #define PANIC_TIMEOUT 5 /* 5 seconds */ @@ -218,6 +230,7 @@ static atomic_t mce_fake_paniced; static void wait_for_panic(void) { long timeout = PANIC_TIMEOUT*USEC_PER_SEC; + preempt_disable(); local_irq_enable(); while (timeout-- > 0) @@ -285,6 +298,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp) static int msr_to_offset(u32 msr) { unsigned bank = __get_cpu_var(injectm.bank); + if (msr == rip_msr) return offsetof(struct mce, ip); if (msr == MSR_IA32_MCx_STATUS(bank)) -- cgit v1.2.1 From 11879ba5d9ab8174af9b9cefbb2396a54dfbf8c1 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Sat, 26 Sep 2009 20:51:50 +0200 Subject: x86: Simplify bound checks in the MTRR code The current bound checks for copy_from_user in the MTRR driver are not as obvious as they could be, and gcc agrees with that. This patch simplifies the boundary checks to the point that gcc can now prove to itself that the copy_from_user() is never going past its bounds. Signed-off-by: Arjan van de Ven Cc: Yinghai Lu Cc: Linus Torvalds LKML-Reference: <20090926205150.30797709@infradead.org> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mtrr/if.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index f04e72527604..3c1b12d461d1 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -96,17 +96,24 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) unsigned long long base, size; char *ptr; char line[LINE_SIZE]; + int length; size_t linelen; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!len) - return -EINVAL; memset(line, 0, LINE_SIZE); - if (len > LINE_SIZE) - len = LINE_SIZE; - if (copy_from_user(line, buf, len - 1)) + + length = len; + length--; + + if (length > LINE_SIZE - 1) + length = LINE_SIZE - 1; + + if (length < 0) + return -EINVAL; + + if (copy_from_user(line, buf, length)) return -EFAULT; linelen = strlen(line); -- cgit v1.2.1 From e3be785fb59f92c0df685037062d041619653b7a Mon Sep 17 00:00:00 2001 From: Marin Mitov Date: Sat, 3 Oct 2009 20:45:02 +0300 Subject: x86, pci: Correct spelling in a comment Signed-off-by: Marin Mitov Cc: Joerg Roedel Cc: Jesse Brandeburg LKML-Reference: <200910032045.02523.mitov@issp.bas.bg> Signed-off-by: Ingo Molnar ====================================================== --- arch/x86/kernel/pci-dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 64b838eac18c..d20009b4e6ef 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -35,7 +35,7 @@ int iommu_detected __read_mostly = 0; /* * This variable becomes 1 if iommu=pt is passed on the kernel command line. - * If this variable is 1, IOMMU implementations do no DMA ranslation for + * If this variable is 1, IOMMU implementations do no DMA translation for * devices and allow every device to access to whole physical memory. This is * useful if a user want to use an IOMMU only for KVM device assignment to * guests and not for driver dma translation. -- cgit v1.2.1 From 9bcbdd9c58617f1301dd4f17c738bb9bc73aca70 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Thu, 8 Oct 2009 06:40:41 -0700 Subject: x86, timers: Check for pending timers after (device) interrupts Now that range timers and deferred timers are common, I found a problem with these using the "perf timechart" tool. Frans Pop also reported high scheduler latencies via LatencyTop, when using iwlagn. It turns out that on x86, these two 'opportunistic' timers only get checked when another "real" timer happens. These opportunistic timers have the objective to save power by hitchhiking on other wakeups, as to avoid CPU wakeups by themselves as much as possible. The change in this patch runs this check not only at timer interrupts, but at all (device) interrupts. The effect is that: 1) the deferred timers/range timers get delayed less 2) the range timers cause less wakeups by themselves because the percentage of hitchhiking on existing wakeup events goes up. I've verified the working of the patch using "perf timechart", the original exposed bug is gone with this patch. Frans also reported success - the latencies are now down in the expected ~10 msec range. Signed-off-by: Arjan van de Ven Tested-by: Frans Pop Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Mike Galbraith LKML-Reference: <20091008064041.67219b13@infradead.org> Signed-off-by: Ingo Molnar --- arch/x86/kernel/irq.c | 2 ++ arch/x86/kernel/smp.c | 1 + 2 files changed, 3 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 74656d1d4e30..391206199515 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -244,6 +244,7 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs) __func__, smp_processor_id(), vector, irq); } + run_local_timers(); irq_exit(); set_irq_regs(old_regs); @@ -268,6 +269,7 @@ void smp_generic_interrupt(struct pt_regs *regs) if (generic_interrupt_extension) generic_interrupt_extension(); + run_local_timers(); irq_exit(); set_irq_regs(old_regs); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index ec1de97600e7..d915d956e66d 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -198,6 +198,7 @@ void smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); inc_irq_stat(irq_resched_count); + run_local_timers(); /* * KVM uses this interrupt to force a cpu out of guest mode */ -- cgit v1.2.1 From d43c36dc6b357fa1806800f18aa30123c747a6d1 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 7 Oct 2009 17:09:06 +0400 Subject: headers: remove sched.h from interrupt.h After m68k's task_thread_info() doesn't refer to current, it's possible to remove sched.h from interrupt.h and not break m68k! Many thanks to Heiko Carstens for allowing this. Signed-off-by: Alexey Dobriyan --- arch/x86/kernel/cpu/mcheck/mce_intel.c | 1 + arch/x86/kernel/pci-gart_64.c | 1 + arch/x86/kernel/reboot.c | 1 + 3 files changed, 3 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 889f665fe93d..7c785634af2b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 98a827ee9ed7..a7f1b64f86e0 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 27349f92a6d7..a1a3cdda06e1 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.1 From 15b812f1d0a5ca8f5efe7f5882f468af10682ca8 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 11 Oct 2009 14:17:16 -0700 Subject: pci: increase alignment to make more space for hidden code As reported in http://bugzilla.kernel.org/show_bug.cgi?id=13940 on some system when acpi are enabled, acpi clears some BAR for some devices without reason, and kernel will need to allocate devices for them. It then apparently hits some undocumented resource conflict, resulting in non-working devices. Try to increase alignment to get more safe range for unassigned devices. Signed-off-by: Yinghai Lu Signed-off-by: Linus Torvalds --- arch/x86/kernel/e820.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 85419bb7d4ab..d17d482a04f4 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1378,8 +1378,8 @@ static unsigned long ram_alignment(resource_size_t pos) if (mb < 16) return 1024*1024; - /* To 32MB for anything above that */ - return 32*1024*1024; + /* To 64MB for anything above that */ + return 64*1024*1024; } #define MAX_RESOURCE_SIZE ((resource_size_t)-1) -- cgit v1.2.1