From b6db80ee1331e7beaeb91b4b3d946dd16c72e388 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 18 May 2008 19:27:48 +0200 Subject: x86: fix setup of cyc2ns in tsc_64.c When the TSC is calibrated against the PIT due to the nonavailability of PMTIMER/HPET or due to SMI interference then the setup of the per CPU cyc2ns variables is skipped. This is unlikely to happen but it would definitely render sched_clock() unusable. This was introduced with commit 53d517cdbaac704352b3d0c10fecb99e0b54572e x86: scale cyc_2_nsec according to CPU frequency Update the per CPU cyc2ns variables in all exit pathes of tsc_calibrate. Signed-off-by: Thomas Gleixner Cc: stable@kernel.org --- arch/x86/kernel/tsc_64.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c index fcc16e58609e..1784b8077a12 100644 --- a/arch/x86/kernel/tsc_64.c +++ b/arch/x86/kernel/tsc_64.c @@ -227,14 +227,14 @@ void __init tsc_calibrate(void) /* hpet or pmtimer available ? */ if (!hpet && !pm1 && !pm2) { printk(KERN_INFO "TSC calibrated against PIT\n"); - return; + goto out; } /* Check, whether the sampling was disturbed by an SMI */ if (tsc1 == ULONG_MAX || tsc2 == ULONG_MAX) { printk(KERN_WARNING "TSC calibration disturbed by SMI, " "using PIT calibration result\n"); - return; + goto out; } tsc2 = (tsc2 - tsc1) * 1000000L; @@ -255,6 +255,7 @@ void __init tsc_calibrate(void) tsc_khz = tsc2 / tsc1; +out: for_each_possible_cpu(cpu) set_cyc2ns_scale(tsc_khz, cpu); } -- cgit v1.2.2 From 9ccc906c97e34fd91dc6aaf5b69b52d824386910 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 13 May 2008 12:31:00 +0200 Subject: x86: distangle user disabled TSC from unstable tsc_enabled is set to 0 from the command line switch "notsc" and from the mark_tsc_unstable code. Seperate those functionalities and replace tsc_enable with tsc_disable. This makes also the native_sched_clock() decision when to use TSC understandable. Preparatory patch to solve the sched_clock() issue on 32 bit. Signed-off-by: Thomas Gleixner --- arch/x86/kernel/tsc_32.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c index e4790728b224..b087d691f165 100644 --- a/arch/x86/kernel/tsc_32.c +++ b/arch/x86/kernel/tsc_32.c @@ -14,7 +14,7 @@ #include "mach_timer.h" -static int tsc_enabled; +static int tsc_disabled; /* * On some systems the TSC frequency does not @@ -28,8 +28,8 @@ EXPORT_SYMBOL_GPL(tsc_khz); static int __init tsc_setup(char *str) { printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, " - "cannot disable TSC completely.\n"); - mark_tsc_unstable("user disabled TSC"); + "cannot disable TSC completely.\n"); + tsc_disabled = 1; return 1; } #else @@ -120,7 +120,7 @@ unsigned long long native_sched_clock(void) * very important for it to be as fast as the platform * can achive it. ) */ - if (unlikely(!tsc_enabled && !tsc_unstable)) + if (unlikely(tsc_disabled)) /* No locking but a rare wrong value is not a big deal: */ return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); @@ -322,7 +322,6 @@ void mark_tsc_unstable(char *reason) { if (!tsc_unstable) { tsc_unstable = 1; - tsc_enabled = 0; printk("Marking TSC unstable due to: %s.\n", reason); /* Can be called before registration */ if (clocksource_tsc.mult) @@ -336,7 +335,7 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable); static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d) { printk(KERN_NOTICE "%s detected: marking TSC unstable.\n", - d->ident); + d->ident); tsc_unstable = 1; return 0; } @@ -403,8 +402,11 @@ void __init tsc_init(void) { int cpu; - if (!cpu_has_tsc) + if (!cpu_has_tsc || tsc_disabled) { + /* Disable the TSC in case of !cpu_has_tsc */ + tsc_disabled = 1; return; + } cpu_khz = calculate_cpu_khz(); tsc_khz = cpu_khz; @@ -441,8 +443,6 @@ void __init tsc_init(void) if (check_tsc_unstable()) { clocksource_tsc.rating = 0; clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; - } else - tsc_enabled = 1; - + } clocksource_register(&clocksource_tsc); } -- cgit v1.2.2 From 74dc51a3de06aa516e3b9fdc4017b2aeb38bf44b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 18 May 2008 22:17:59 +0200 Subject: x86: disable TSC for sched_clock() when calibration failed When the TSC calibration fails then TSC is still used in sched_clock(). Disable it completely in that case. Signed-off-by: Thomas Gleixner Cc: stable@kernel.org --- arch/x86/kernel/tsc_32.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c index b087d691f165..068759db63dd 100644 --- a/arch/x86/kernel/tsc_32.c +++ b/arch/x86/kernel/tsc_32.c @@ -413,6 +413,11 @@ void __init tsc_init(void) if (!cpu_khz) { mark_tsc_unstable("could not calculate TSC khz"); + /* + * We need to disable the TSC completely in this case + * to prevent sched_clock() from using it. + */ + tsc_disabled = 1; return; } -- cgit v1.2.2 From 2584a82deed7196f48066f1b1a7fad4ec5bea961 Mon Sep 17 00:00:00 2001 From: Chuck Ebbert Date: Tue, 20 May 2008 18:18:12 -0400 Subject: x86: don't read maxlvt before checking if APIC is mapped A check for unmapped apic was added before reading maxlvt but the early read of maxlvt wasn't removed. Signed-off-by: Chuck Ebbert Cc: Andi Kleen Signed-off-by: Thomas Gleixner Cc: stable@kernel.org --- arch/x86/kernel/apic_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index 5910020c3f24..0633cfd0dc29 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -534,7 +534,7 @@ int setup_profiling_timer(unsigned int multiplier) */ void clear_local_APIC(void) { - int maxlvt = lapic_get_maxlvt(); + int maxlvt; u32 v; /* APIC hasn't been mapped yet */ -- cgit v1.2.2 From de067814d6b69030d0030e1c5b3dbaf0385aae41 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 15 May 2008 13:24:52 +0100 Subject: x86/xen: fix arbitrary_virt_to_machine() While I realize that the function isn't currently being used, I still think an obvious mistake like this should be corrected. Signed-off-by: Jan Beulich Acked-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/xen/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 126766d43aea..3525ef523a74 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -60,7 +60,7 @@ xmaddr_t arbitrary_virt_to_machine(unsigned long address) { unsigned int level; pte_t *pte = lookup_address(address, &level); - unsigned offset = address & PAGE_MASK; + unsigned offset = address & ~PAGE_MASK; BUG_ON(pte == NULL); -- cgit v1.2.2 From 2ddfd20e7c55421435cbf95a5ed3dd6e423cf934 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 22 May 2008 10:37:48 +0200 Subject: namespacecheck: automated fixes Signed-off-by: Ingo Molnar --- arch/x86/kernel/kvmclock.c | 4 ++-- arch/x86/kvm/mmu.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 4bc1be5d5472..08a30986d472 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -53,7 +53,7 @@ static cycle_t kvm_clock_read(void); * have elapsed since the hypervisor wrote the data. So we try to account for * that with system time */ -unsigned long kvm_get_wallclock(void) +static unsigned long kvm_get_wallclock(void) { u32 wc_sec, wc_nsec; u64 delta; @@ -86,7 +86,7 @@ unsigned long kvm_get_wallclock(void) return ts.tv_sec + 1; } -int kvm_set_wallclock(unsigned long now) +static int kvm_set_wallclock(unsigned long now) { return 0; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 36c5406b1813..7246b60afb96 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1996,7 +1996,7 @@ static struct shrinker mmu_shrinker = { .seeks = DEFAULT_SEEKS * 10, }; -void mmu_destroy_caches(void) +static void mmu_destroy_caches(void) { if (pte_chain_cache) kmem_cache_destroy(pte_chain_cache); -- cgit v1.2.2 From a1289643adb6272c04db9399653ae195072c482a Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 14 May 2008 16:10:42 -0700 Subject: x86: use explicit copy in vdso_gettimeofday() Jeremy's gcc 3.4 seems to be unable to inline a 8 byte memcpy. But the vdso doesn't support external references. Copy the structure members of struct timezone explicitely instead. Signed-off-by: Andi Kleen Cc: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/vdso/vclock_gettime.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 23476c2ebfc4..efa2ba7c6005 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -106,9 +106,9 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) do_realtime((struct timespec *)tv); tv->tv_usec /= 1000; if (unlikely(tz != NULL)) { - /* This relies on gcc inlining the memcpy. We'll notice - if it ever fails to do so. */ - memcpy(tz, >od->sys_tz, sizeof(struct timezone)); + /* Avoid memcpy. Some old compilers fail to inline it */ + tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest; + tz->tz_dsttime = gtod->sys_tz.tz_dsttime; } return 0; } -- cgit v1.2.2 From b1979a5fda7869a790f4fd83fb06c78498d26ba1 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:21:15 +0200 Subject: x86: prevent PGE flush from interruption/preemption CR4 manipulation is not protected against interrupts and preemption, but KVM uses smp_function_call to manipulate the X86_CR4_VMXE bit either from the CPU hotplug code or from the kvm_init call. We need to protect the CR4 manipulation from both interrupts and preemption. Original bug report: http://lkml.org/lkml/2008/5/7/48 Bugzilla entry: http://bugzilla.kernel.org/show_bug.cgi?id=10642 This is not a regression from 2.6.25, it's a long standing and hard to trigger bug. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/asm-x86/tlbflush.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/include/asm-x86/tlbflush.h b/include/asm-x86/tlbflush.h index 0c0674d94255..35c76ceb9f40 100644 --- a/include/asm-x86/tlbflush.h +++ b/include/asm-x86/tlbflush.h @@ -22,12 +22,23 @@ static inline void __native_flush_tlb(void) static inline void __native_flush_tlb_global(void) { - unsigned long cr4 = read_cr4(); + unsigned long flags; + unsigned long cr4; + /* + * Read-modify-write to CR4 - protect it from preemption and + * from interrupts. (Use the raw variant because this code can + * be called from deep inside debugging code.) + */ + raw_local_irq_save(flags); + + cr4 = read_cr4(); /* clear PGE */ write_cr4(cr4 & ~X86_CR4_PGE); /* write old PGE again and flush TLBs */ write_cr4(cr4); + + raw_local_irq_restore(flags); } static inline void __native_flush_tlb_single(unsigned long addr) -- cgit v1.2.2