From ebb682f522411abbe358059a256a8672ec0bd55b Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Wed, 9 Dec 2009 13:36:45 -0500 Subject: x86, AMD: Fix stale cpuid4_info shared_map data in shared_cpu_map cpumasks The per_cpu cpuid4_info shared_map can contain stale data when CPUs are added and removed. The stale data can lead to a NULL pointer derefernce panic on a remove of a CPU that has had siblings previously removed. This patch resolves the panic by verifying a cpu is actually online before adding it to the shared_cpu_map, only examining cpus that are part of the same lower level cache, and by updating other siblings lowest level cache maps when a cpu is added. Signed-off-by: Prarit Bhargava LKML-Reference: <20091209183336.17855.98708.sendpatchset@prarit.bos.redhat.com> Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/intel_cacheinfo.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 6c40f6b5b340..63ada177b40c 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -507,18 +507,19 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) { struct _cpuid4_info *this_leaf, *sibling_leaf; unsigned long num_threads_sharing; - int index_msb, i; + int index_msb, i, sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) { - struct cpuinfo_x86 *d; - for_each_online_cpu(i) { + for_each_cpu(i, c->llc_shared_map) { if (!per_cpu(cpuid4_info, i)) continue; - d = &cpu_data(i); this_leaf = CPUID4_INFO_IDX(i, index); - cpumask_copy(to_cpumask(this_leaf->shared_cpu_map), - d->llc_shared_map); + for_each_cpu(sibling, c->llc_shared_map) { + if (!cpu_online(sibling)) + continue; + set_bit(sibling, this_leaf->shared_cpu_map); + } } return; } -- cgit v1.2.2 From 2eaad1fddd7450a48ad464229775f97fbfe8af36 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Thu, 10 Dec 2009 17:19:36 -0800 Subject: x86: Limit the number of processor bootup messages When there are a large number of processors in a system, there is an excessive amount of messages sent to the system console. It's estimated that with 4096 processors in a system, and the console baudrate set to 56K, the startup messages will take about 84 minutes to clear the serial port. This set of patches limits the number of repetitious messages which contain no additional information. Much of this information is obtainable from the /proc and /sysfs. Some of the messages are also sent to the kernel log buffer as KERN_DEBUG messages so dmesg can be used to examine more closely any details specific to a problem. The new cpu bootup sequence for system_state == SYSTEM_BOOTING: Booting Node 0, Processors #1 #2 #3 #4 #5 #6 #7 Ok. Booting Node 1, Processors #8 #9 #10 #11 #12 #13 #14 #15 Ok. ... Booting Node 3, Processors #56 #57 #58 #59 #60 #61 #62 #63 Ok. Brought up 64 CPUs After the system is running, a single line boot message is displayed when CPU's are hotplugged on: Booting Node %d Processor %d APIC 0x%x Status of the following lines: CPU: Physical Processor ID: printed once (for boot cpu) CPU: Processor Core ID: printed once (for boot cpu) CPU: Hyper-Threading is disabled printed once (for boot cpu) CPU: Thermal monitoring enabled printed once (for boot cpu) CPU %d/0x%x -> Node %d: removed CPU %d is now offline: only if system_state == RUNNING Initializing CPU#%d: KERN_DEBUG Signed-off-by: Mike Travis LKML-Reference: <4B219E28.8080601@sgi.com> Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/addon_cpuid_features.c | 15 +++++++++------ arch/x86/kernel/cpu/amd.c | 2 -- arch/x86/kernel/cpu/common.c | 8 +++++--- arch/x86/kernel/cpu/intel.c | 2 -- arch/x86/kernel/cpu/mcheck/therm_throt.c | 4 ++-- 5 files changed, 16 insertions(+), 15 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index c965e5212714..468489b57aae 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -74,6 +74,7 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c) unsigned int eax, ebx, ecx, edx, sub_index; unsigned int ht_mask_width, core_plus_mask_width; unsigned int core_select_mask, core_level_siblings; + static bool printed; if (c->cpuid_level < 0xb) return; @@ -127,12 +128,14 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c) c->x86_max_cores = (core_level_siblings / smp_num_siblings); - - printk(KERN_INFO "CPU: Physical Processor ID: %d\n", - c->phys_proc_id); - if (c->x86_max_cores > 1) - printk(KERN_INFO "CPU: Processor Core ID: %d\n", - c->cpu_core_id); + if (!printed) { + printk(KERN_INFO "CPU: Physical Processor ID: %d\n", + c->phys_proc_id); + if (c->x86_max_cores > 1) + printk(KERN_INFO "CPU: Processor Core ID: %d\n", + c->cpu_core_id); + printed = 1; + } return; #endif } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7128b3799cec..8dc3ea145c97 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -375,8 +375,6 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) node = nearby_node(apicid); } numa_set_node(cpu, node); - - printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node); #endif } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c1afa990a6c8..0ee9a3254eec 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -427,6 +427,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_HT u32 eax, ebx, ecx, edx; int index_msb, core_bits; + static bool printed; if (!cpu_has(c, X86_FEATURE_HT)) return; @@ -442,7 +443,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) smp_num_siblings = (ebx & 0xff0000) >> 16; if (smp_num_siblings == 1) { - printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); + printk_once(KERN_INFO "CPU0: Hyper-Threading is disabled\n"); goto out; } @@ -469,11 +470,12 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) ((1 << core_bits) - 1); out: - if ((c->x86_max_cores * smp_num_siblings) > 1) { + if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) { printk(KERN_INFO "CPU: Physical Processor ID: %d\n", c->phys_proc_id); printk(KERN_INFO "CPU: Processor Core ID: %d\n", c->cpu_core_id); + printed = 1; } #endif } @@ -1115,7 +1117,7 @@ void __cpuinit cpu_init(void) if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) panic("CPU#%d already initialized!\n", cpu); - printk(KERN_INFO "Initializing CPU#%d\n", cpu); + pr_debug("Initializing CPU#%d\n", cpu); clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c900b73f9224..9c31e8b09d2c 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -270,8 +270,6 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) node = cpu_to_node(cpu); } numa_set_node(cpu, node); - - printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node); #endif } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 4fef985fc221..1003ed4bbce4 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -339,8 +339,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c) l = apic_read(APIC_LVTTHMR); apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - printk(KERN_INFO "CPU%d: Thermal monitoring enabled (%s)\n", - cpu, tm2 ? "TM2" : "TM1"); + printk_once(KERN_INFO "CPU0: Thermal monitoring enabled (%s)\n", + tm2 ? "TM2" : "TM1"); /* enable thermal throttle processing */ atomic_set(&therm_throt_en, 1); -- cgit v1.2.2 From 485a2e1973fd9f98c2c6776e66ac4721882b69e0 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Mon, 14 Dec 2009 17:56:34 +0900 Subject: x86, mce: Thermal monitoring depends on APIC being enabled Add check if APIC is not disabled since thermal monitoring depends on it. As only apic gets disabled we should not try to install "thermal monitor" vector, print out that thermal monitoring is enabled and etc... Note that "Intel Correct Machine Check Interrupts" already has such a check. Also I decided to not add cpu_has_apic check into mcheck_intel_therm_init since even if it'll call apic_read on disabled apic -- it's safe here and allow us to save a few code bytes. Reported-by: Thomas Gleixner Signed-off-by: Cyrill Gorcunov Signed-off-by: Hidetoshi Seto LKML-Reference: <4B25FDC2.3020401@jp.fujitsu.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/therm_throt.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 1003ed4bbce4..0a9b57702be4 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -274,8 +274,9 @@ void intel_init_thermal(struct cpuinfo_x86 *c) int tm2 = 0; u32 l, h; - /* Thermal monitoring depends on ACPI and clock modulation*/ - if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC)) + /* Thermal monitoring depends on APIC, ACPI and clock modulation */ + if (!cpu_has_apic || !cpu_has(c, X86_FEATURE_ACPI) || + !cpu_has(c, X86_FEATURE_ACC)) return; /* -- cgit v1.2.2 From 70fe440718d9f42bf963c2cffe12008eb5556165 Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Mon, 14 Dec 2009 17:57:00 +0900 Subject: x86, mce: Clean up thermal init by introducing intel_thermal_supported() It looks better to have a common function. No change in functionality. Signed-off-by: Hidetoshi Seto Cc: Cyrill Gorcunov LKML-Reference: <4B25FDDC.407@jp.fujitsu.com> Signed-off-by: Ingo Molnar Cc: Cyrill Gorcunov --- arch/x86/kernel/cpu/mcheck/therm_throt.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 0a9b57702be4..81c499eceb21 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -256,6 +256,16 @@ asmlinkage void smp_thermal_interrupt(struct pt_regs *regs) ack_APIC_irq(); } +/* Thermal monitoring depends on APIC, ACPI and clock modulation */ +static int intel_thermal_supported(struct cpuinfo_x86 *c) +{ + if (!cpu_has_apic) + return 0; + if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC)) + return 0; + return 1; +} + void __init mcheck_intel_therm_init(void) { /* @@ -263,8 +273,7 @@ void __init mcheck_intel_therm_init(void) * LVT value on BSP and use that value to restore APs' thermal LVT * entry BIOS programmed later */ - if (cpu_has(&boot_cpu_data, X86_FEATURE_ACPI) && - cpu_has(&boot_cpu_data, X86_FEATURE_ACC)) + if (intel_thermal_supported(&boot_cpu_data)) lvtthmr_init = apic_read(APIC_LVTTHMR); } @@ -274,9 +283,7 @@ void intel_init_thermal(struct cpuinfo_x86 *c) int tm2 = 0; u32 l, h; - /* Thermal monitoring depends on APIC, ACPI and clock modulation */ - if (!cpu_has_apic || !cpu_has(c, X86_FEATURE_ACPI) || - !cpu_has(c, X86_FEATURE_ACC)) + if (!intel_thermal_supported(c)) return; /* -- cgit v1.2.2