From: Chris Wright Date: Wed, 10 Aug 2005 01:51:16 +0000 (-0700) Subject: Fix for x86_64 smpboot timing problem, fwd from Andi. X-Git-Tag: v2.6.12.6~12 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=cc360a5e13e48ab34a584f722135f97997736033;p=thirdparty%2Fkernel%2Fstable-queue.git Fix for x86_64 smpboot timing problem, fwd from Andi. --- diff --git a/queue/series b/queue/series index ae6fa976170..63bea367600 100644 --- a/queue/series +++ b/queue/series @@ -1,2 +1,3 @@ sys_set_mempolicy-mode-check.patch x86_64-srat-dual-core-amd.patch +x86_64-fix-smpboot-timing-problem.patch diff --git a/queue/x86_64-fix-smpboot-timing-problem.patch b/queue/x86_64-fix-smpboot-timing-problem.patch new file mode 100644 index 00000000000..d26893e05e4 --- /dev/null +++ b/queue/x86_64-fix-smpboot-timing-problem.patch @@ -0,0 +1,180 @@ +From stable-bounces@linux.kernel.org Tue Aug 9 18:41:05 2005 +Date: Wed, 10 Aug 2005 03:40:42 +0200 +From: Andi Kleen +To: stable@kernel.org +Subject: [PATCH] x86_64: Fixing smpboot timing problem + +This patch fixes the SMP boot timing problem that hit various people and was +introduced in 2.6.12. Please apply to stable. + +>From Eric Biederman + +sync_tsc was using smp_call_function to ask the boot processor +to report it's tsc value. smp_call_function performs an IPI_send_allbutself +which is a broadcast ipi. There is a window during processor startup during +which the target cpu has started and before it has initialized it's interrupt +vectors so it can properly process an interrupt. Receveing an interrupt +during that window will triple fault the cpu and do other nasty things. + +Why cli does not protect us from that is beyond me. + +The simple fix is to match ia64 and provide a smp_call_function_single. +Which avoids the broadcast and is more efficient. + +This certainly fixes the problem of getting stuck on boot which was +very easy to trigger on my SMP Hyperthreaded Xeon, and I think +it fixes it for the right reasons. + +Signed-off-by: Eric W. Biederman +Signed-off-by: Andi Kleen + +Index: linux-2.6.12/arch/x86_64/kernel/smp.c +=================================================================== +--- linux-2.6.12.orig/arch/x86_64/kernel/smp.c ++++ linux-2.6.12/arch/x86_64/kernel/smp.c +@@ -284,6 +284,71 @@ struct call_data_struct { + static struct call_data_struct * call_data; + + /* ++ * this function sends a 'generic call function' IPI to one other CPU ++ * in the system. ++ */ ++static void __smp_call_function_single (int cpu, void (*func) (void *info), void *info, ++ int nonatomic, int wait) ++{ ++ struct call_data_struct data; ++ int cpus = 1; ++ ++ data.func = func; ++ data.info = info; ++ atomic_set(&data.started, 0); ++ data.wait = wait; ++ if (wait) ++ atomic_set(&data.finished, 0); ++ ++ call_data = &data; ++ wmb(); ++ /* Send a message to all other CPUs and wait for them to respond */ ++ send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_VECTOR); ++ ++ /* Wait for response */ ++ while (atomic_read(&data.started) != cpus) ++ cpu_relax(); ++ ++ if (!wait) ++ return; ++ ++ while (atomic_read(&data.finished) != cpus) ++ cpu_relax(); ++} ++ ++/* ++ * Run a function on another CPU ++ * The function to run. This must be fast and non-blocking. ++ * An arbitrary pointer to pass to the function. ++ * Currently unused. ++ * If true, wait until function has completed on other CPUs. ++ * [RETURNS] 0 on success, else a negative status code. ++ * ++ * Does not return until the remote CPU is nearly ready to execute ++ * or is or has executed. ++ */ ++ ++int smp_call_function_single (int cpu, void (*func) (void *info), void *info, ++ int nonatomic, int wait) ++{ ++ ++ int me = get_cpu(); /* prevent preemption and reschedule on another processor */ ++ ++ if (cpu == me) { ++ printk("%s: trying to call self\n", __func__); ++ put_cpu(); ++ return -EBUSY; ++ } ++ spin_lock_bh(&call_lock); ++ ++ __smp_call_function_single(cpu, func,info,nonatomic,wait); ++ ++ spin_unlock_bh(&call_lock); ++ put_cpu(); ++ return 0; ++} ++ ++/* + * this function sends a 'generic call function' IPI to all other CPUs + * in the system. + */ +Index: linux-2.6.12/arch/x86_64/kernel/smpboot.c +=================================================================== +--- linux-2.6.12.orig/arch/x86_64/kernel/smpboot.c ++++ linux-2.6.12/arch/x86_64/kernel/smpboot.c +@@ -202,9 +202,6 @@ static __cpuinit void sync_master(void * + { + unsigned long flags, i; + +- if (smp_processor_id() != boot_cpu_id) +- return; +- + go[MASTER] = 0; + + local_irq_save(flags); +@@ -253,7 +250,7 @@ get_delta(long *rt, long *master) + return tcenter - best_tm; + } + +-static __cpuinit void sync_tsc(void) ++static __cpuinit void sync_tsc(unsigned int master) + { + int i, done = 0; + long delta, adj, adjust_latency = 0; +@@ -267,9 +264,17 @@ static __cpuinit void sync_tsc(void) + } t[NUM_ROUNDS] __cpuinitdata; + #endif + ++ printk(KERN_INFO "CPU %d: Syncing TSC to CPU %u.\n", ++ smp_processor_id(), master); ++ + go[MASTER] = 1; + +- smp_call_function(sync_master, NULL, 1, 0); ++ /* It is dangerous to broadcast IPI as cpus are coming up, ++ * as they may not be ready to accept them. So since ++ * we only need to send the ipi to the boot cpu direct ++ * the message, and avoid the race. ++ */ ++ smp_call_function_single(master, sync_master, NULL, 1, 0); + + while (go[MASTER]) /* wait for master to be ready */ + no_cpu_relax(); +@@ -313,16 +318,14 @@ static __cpuinit void sync_tsc(void) + printk(KERN_INFO + "CPU %d: synchronized TSC with CPU %u (last diff %ld cycles, " + "maxerr %lu cycles)\n", +- smp_processor_id(), boot_cpu_id, delta, rt); ++ smp_processor_id(), master, delta, rt); + } + + static void __cpuinit tsc_sync_wait(void) + { + if (notscsync || !cpu_has_tsc) + return; +- printk(KERN_INFO "CPU %d: Syncing TSC to CPU %u.\n", smp_processor_id(), +- boot_cpu_id); +- sync_tsc(); ++ sync_tsc(boot_cpu_id); + } + + static __init int notscsync_setup(char *s) +Index: linux-2.6.12/include/asm-x86_64/smp.h +=================================================================== +--- linux-2.6.12.orig/include/asm-x86_64/smp.h ++++ linux-2.6.12/include/asm-x86_64/smp.h +@@ -46,6 +46,8 @@ extern int pic_mode; + extern int smp_num_siblings; + extern void smp_flush_tlb(void); + extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs); ++extern int smp_call_function_single (int cpuid, void (*func) (void *info), void *info, ++ int retry, int wait); + extern void smp_send_reschedule(int cpu); + extern void smp_invalidate_rcv(void); /* Process an NMI */ + extern void zap_low_mappings(void);