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') 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 v1.2.3 From 893f38d144a4d96d2483cd7c3801d26e1b2c23e9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 10 Dec 2009 13:07:22 -0800 Subject: x86: Use find_e820() instead of hard coded trampoline address Jens found the following crash/regression: [ 0.000000] found SMP MP-table at [ffff8800000fdd80] fdd80 [ 0.000000] Kernel panic - not syncing: Overlapping early reservations 12-f011 MP-table mpc to 0-fff BIOS data page and [ 0.000000] Kernel panic - not syncing: Overlapping early reservations 12-f011 MP-table mpc to 6000-7fff TRAMPOLINE and bisected it to b24c2a9 ("x86: Move find_smp_config() earlier and avoid bootmem usage"). It turns out the BIOS is using the first 64k for mptable, without reserving it. So try to find good range for the real-mode trampoline instead of hard coding it, in case some bios tries to use that range for sth. Reported-by: Jens Axboe Signed-off-by: Yinghai Lu Tested-by: Jens Axboe Cc: Randy Dunlap LKML-Reference: <4B21630A.6000308@kernel.org> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/trampoline.h | 1 - arch/x86/kernel/e820.c | 11 ++++++++++- arch/x86/kernel/head32.c | 2 -- arch/x86/kernel/head64.c | 2 -- arch/x86/kernel/mpparse.c | 3 --- arch/x86/kernel/setup.c | 13 ++++++++----- arch/x86/kernel/trampoline.c | 20 +++++++++----------- 7 files changed, 27 insertions(+), 25 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h index 90f06c25221d..cb507bb05d79 100644 --- a/arch/x86/include/asm/trampoline.h +++ b/arch/x86/include/asm/trampoline.h @@ -16,7 +16,6 @@ extern unsigned long initial_code; extern unsigned long initial_gs; #define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE) -#define TRAMPOLINE_BASE 0x6000 extern unsigned long setup_trampoline(void); extern void __init reserve_trampoline_memory(void); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d17d482a04f4..f50447d961c0 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -732,7 +732,16 @@ struct early_res { char overlap_ok; }; static struct early_res early_res[MAX_EARLY_RES] __initdata = { - { 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */ + { 0, PAGE_SIZE, "BIOS data page", 1 }, /* BIOS data page */ +#ifdef CONFIG_X86_32 + /* + * But first pinch a few for the stack/trampoline stuff + * FIXME: Don't need the extra page at 4K, but need to fix + * trampoline before removing it. (see the GDT stuff) + */ + { PAGE_SIZE, PAGE_SIZE, "EX TRAMPOLINE", 1 }, +#endif + {} }; diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 4f8e2507e8f3..5051b94c9069 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -29,8 +29,6 @@ static void __init i386_default_early_setup(void) void __init i386_start_kernel(void) { - reserve_trampoline_memory(); - reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 0b06cd778fd9..b5a9896ca1e7 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -98,8 +98,6 @@ void __init x86_64_start_reservations(char *real_mode_data) { copy_bootdata(__va(real_mode_data)); - reserve_trampoline_memory(); - reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 35a57c963df9..40b54ceb68b5 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -945,9 +945,6 @@ void __init early_reserve_e820_mpc_new(void) { if (enable_update_mptable && alloc_mptable) { u64 startt = 0; -#ifdef CONFIG_X86_TRAMPOLINE - startt = TRAMPOLINE_BASE; -#endif mpc_new_phys = early_reserve_e820(startt, mpc_new_length, 4); } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 946a311a25c9..f7b8b9894b22 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -73,6 +73,7 @@ #include #include +#include #include #include #include @@ -875,6 +876,13 @@ void __init setup_arch(char **cmdline_p) reserve_brk(); + /* + * Find and reserve possible boot-time SMP configuration: + */ + find_smp_config(); + + reserve_trampoline_memory(); + #ifdef CONFIG_ACPI_SLEEP /* * Reserve low memory region for sleep support. @@ -921,11 +929,6 @@ void __init setup_arch(char **cmdline_p) early_acpi_boot_init(); - /* - * Find and reserve possible boot-time SMP configuration: - */ - find_smp_config(); - #ifdef CONFIG_ACPI_NUMA /* * Parse SRAT to discover nodes. diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c index cd022121cab6..c652ef62742d 100644 --- a/arch/x86/kernel/trampoline.c +++ b/arch/x86/kernel/trampoline.c @@ -12,21 +12,19 @@ #endif /* ready for x86_64 and x86 */ -unsigned char *__trampinitdata trampoline_base = __va(TRAMPOLINE_BASE); +unsigned char *__trampinitdata trampoline_base; void __init reserve_trampoline_memory(void) { -#ifdef CONFIG_X86_32 - /* - * But first pinch a few for the stack/trampoline stuff - * FIXME: Don't need the extra page at 4K, but need to fix - * trampoline before removing it. (see the GDT stuff) - */ - reserve_early(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE"); -#endif + unsigned long mem; + /* Has to be in very low memory so we can execute real-mode AP code. */ - reserve_early(TRAMPOLINE_BASE, TRAMPOLINE_BASE + TRAMPOLINE_SIZE, - "TRAMPOLINE"); + mem = find_e820_area(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE); + if (mem == -1L) + panic("Cannot allocate trampoline\n"); + + trampoline_base = __va(mem); + reserve_early(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE"); } /* -- cgit v1.2.3 From 505422517d3f126bb939439e9d15dece94e11d2c Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 11 Dec 2009 18:14:40 +0100 Subject: x86, msr: Add support for non-contiguous cpumasks The current rd/wrmsr_on_cpus helpers assume that the supplied cpumasks are contiguous. However, there are machines out there like some K8 multinode Opterons which have a non-contiguous core enumeration on each node (e.g. cores 0,2 on node 0 instead of 0,1), see http://www.gossamer-threads.com/lists/linux/kernel/1160268. This patch fixes out-of-bounds writes (see URL above) by adding per-CPU msr structs which are used on the respective cores. Additionally, two helpers, msrs_{alloc,free}, are provided for use by the callers of the MSR accessors. Cc: H. Peter Anvin Cc: Mauro Carvalho Chehab Cc: Aristeu Rozanski Cc: Randy Dunlap Cc: Doug Thompson Signed-off-by: Borislav Petkov LKML-Reference: <20091211171440.GD31998@aftab> Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/msr.h | 3 +++ arch/x86/lib/msr.c | 26 ++++++++++++++++++++++---- 2 files changed, 25 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 5bef931f8b14..2d228fc9b4b7 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -244,6 +244,9 @@ do { \ #define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0) +struct msr *msrs_alloc(void); +void msrs_free(struct msr *msrs); + #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 41628b104b9e..872834177937 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -7,7 +7,6 @@ struct msr_info { u32 msr_no; struct msr reg; struct msr *msrs; - int off; int err; }; @@ -18,7 +17,7 @@ static void __rdmsr_on_cpu(void *info) int this_cpu = raw_smp_processor_id(); if (rv->msrs) - reg = &rv->msrs[this_cpu - rv->off]; + reg = per_cpu_ptr(rv->msrs, this_cpu); else reg = &rv->reg; @@ -32,7 +31,7 @@ static void __wrmsr_on_cpu(void *info) int this_cpu = raw_smp_processor_id(); if (rv->msrs) - reg = &rv->msrs[this_cpu - rv->off]; + reg = per_cpu_ptr(rv->msrs, this_cpu); else reg = &rv->reg; @@ -80,7 +79,6 @@ static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, memset(&rv, 0, sizeof(rv)); - rv.off = cpumask_first(mask); rv.msrs = msrs; rv.msr_no = msr_no; @@ -120,6 +118,26 @@ void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) } EXPORT_SYMBOL(wrmsr_on_cpus); +struct msr *msrs_alloc(void) +{ + struct msr *msrs = NULL; + + msrs = alloc_percpu(struct msr); + if (!msrs) { + pr_warning("%s: error allocating msrs\n", __func__); + return NULL; + } + + return msrs; +} +EXPORT_SYMBOL(msrs_alloc); + +void msrs_free(struct msr *msrs) +{ + free_percpu(msrs); +} +EXPORT_SYMBOL(msrs_free); + /* These "safe" variants are slower and should be used when the target MSR may not actually exist. */ static void __rdmsr_safe_on_cpu(void *info) -- cgit v1.2.3 From 450b1e8dd10f41b5adad73f48ce8f6707d17c5c4 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Fri, 11 Dec 2009 08:08:50 -0800 Subject: x86: Remove enabling x2apic message for every CPU Print only once that the system is supporting x2apic mode. Signed-off-by: Mike Travis Acked-by: Cyrill Gorcunov LKML-Reference: <4B226E92.5080904@sgi.com> Signed-off-by: H. Peter Anvin --- arch/x86/kernel/apic/apic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index efb2b9cd132c..aa57c079c98f 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1341,7 +1341,7 @@ void enable_x2apic(void) rdmsr(MSR_IA32_APICBASE, msr, msr2); if (!(msr & X2APIC_ENABLE)) { - pr_info("Enabling x2apic\n"); + printk_once(KERN_INFO "Enabling x2apic\n"); wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0); } } -- cgit v1.2.3 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 +-- arch/x86/kernel/smpboot.c | 45 ++++++++++++++++++++---------- 6 files changed, 47 insertions(+), 29 deletions(-) (limited to 'arch') 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); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 29e6744f51e3..678d0b8c26f3 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -671,6 +671,26 @@ static void __cpuinit do_fork_idle(struct work_struct *work) complete(&c_idle->done); } +/* reduce the number of lines printed when booting a large cpu count system */ +static void __cpuinit announce_cpu(int cpu, int apicid) +{ + static int current_node = -1; + int node = cpu_to_node(cpu); + + if (system_state == SYSTEM_BOOTING) { + if (node != current_node) { + if (current_node > (-1)) + pr_cont(" Ok.\n"); + current_node = node; + pr_info("Booting Node %3d, Processors ", node); + } + pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " Ok.\n" : ""); + return; + } else + pr_info("Booting Node %d Processor %d APIC 0x%x\n", + node, cpu, apicid); +} + /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. @@ -737,9 +757,8 @@ do_rest: /* start_ip had better be page-aligned! */ start_ip = setup_trampoline(); - /* So we see what's up */ - printk(KERN_INFO "Booting processor %d APIC 0x%x ip 0x%lx\n", - cpu, apicid, start_ip); + /* So we see what's up */ + announce_cpu(cpu, apicid); /* * This grunge runs the startup process for @@ -788,21 +807,17 @@ do_rest: udelay(100); } - if (cpumask_test_cpu(cpu, cpu_callin_mask)) { - /* number CPUs logically, starting from 1 (BSP is 0) */ - pr_debug("OK.\n"); - printk(KERN_INFO "CPU%d: ", cpu); - print_cpu_info(&cpu_data(cpu)); - pr_debug("CPU has booted.\n"); - } else { + if (cpumask_test_cpu(cpu, cpu_callin_mask)) + pr_debug("CPU%d: has booted.\n", cpu); + else { boot_error = 1; if (*((volatile unsigned char *)trampoline_base) == 0xA5) /* trampoline started but...? */ - printk(KERN_ERR "Stuck ??\n"); + pr_err("CPU%d: Stuck ??\n", cpu); else /* trampoline code not run */ - printk(KERN_ERR "Not responding.\n"); + pr_err("CPU%d: Not responding.\n", cpu); if (apic->inquire_remote_apic) apic->inquire_remote_apic(apicid); } @@ -1293,14 +1308,16 @@ void native_cpu_die(unsigned int cpu) for (i = 0; i < 10; i++) { /* They ack this in play_dead by setting CPU_DEAD */ if (per_cpu(cpu_state, cpu) == CPU_DEAD) { - printk(KERN_INFO "CPU %d is now offline\n", cpu); + if (system_state == SYSTEM_RUNNING) + pr_info("CPU %u is now offline\n", cpu); + if (1 == num_online_cpus()) alternatives_smp_switch(0); return; } msleep(100); } - printk(KERN_ERR "CPU %u didn't die...\n", cpu); + pr_err("CPU %u didn't die...\n", cpu); } void play_dead_common(void) -- cgit v1.2.3 From 1d865fb728bd6bbcdfbd6ec1e2b8ade3b4805641 Mon Sep 17 00:00:00 2001 From: Cliff Wickman Date: Fri, 11 Dec 2009 11:36:18 -0600 Subject: x86: Fix duplicated UV BAU interrupt vector Interrupt vector 0xec has been doubly defined in irq_vectors.h It seems arbitrary whether LOCAL_PENDING_VECTOR or UV_BAU_MESSAGE is the higher number. As long as they are unique. If they are not unique we'll hit a BUG in alloc_system_vector(). Signed-off-by: Cliff Wickman Cc: LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/include/asm/irq_vectors.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 6a635bd39867..4611f085cd43 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -113,7 +113,7 @@ */ #define LOCAL_PENDING_VECTOR 0xec -#define UV_BAU_MESSAGE 0xec +#define UV_BAU_MESSAGE 0xea /* * Self IPI vector for machine checks -- cgit v1.2.3 From eba11d6da7a983cedb0acf32a38e4d0daa8b5d0e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sun, 13 Dec 2009 23:24:03 -0800 Subject: x86: Fix build warning in arch/x86/mm/mmio-mod.c Stephen Rothwell reported these warnings: arch/x86/mm/mmio-mod.c: In function 'print_pte': arch/x86/mm/mmio-mod.c:100: warning: too many arguments for format arch/x86/mm/mmio-mod.c:106: warning: too many arguments for format The 'fmt' was left out accidentally. Reported-by: Stephen Rothwell Signed-off-by: Joe Perches Cc: Peter Zijlstra Cc: Linus LKML-Reference: <1260775443.18538.16.camel@Joe-Laptop.home> Signed-off-by: Ingo Molnar --- arch/x86/mm/mmio-mod.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 4c765e9c4664..34a3291ca103 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -20,7 +20,7 @@ * Derived from the read-mod example from relay-examples by Tom Zanussi. */ -#define pr_fmt(fmt) "mmiotrace: " +#define pr_fmt(fmt) "mmiotrace: " fmt #define DEBUG 1 -- cgit v1.2.3 From f4780ca005404166cc40af77ef0e86132ab98a81 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 14 Dec 2009 11:52:14 +0900 Subject: x86: Move swiotlb initialization before dma32_free_bootmem The commit 75f1cdf1dda92cae037ec848ae63690d91913eac introduced a bug that we initialize SWIOTLB right after dma32_free_bootmem so we wrongly steal memory area allocated for GART with broken BIOS earlier. This moves swiotlb initialization before dma32_free_bootmem(). Signed-off-by: FUJITA Tomonori Cc: yinghai@kernel.org LKML-Reference: <1260759135-6450-2-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar --- arch/x86/kernel/pci-dma.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index afcc58b69c7c..fcc2f2bfa39c 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -120,11 +120,14 @@ static void __init dma32_free_bootmem(void) void __init pci_iommu_alloc(void) { + int use_swiotlb; + + use_swiotlb = pci_swiotlb_init(); #ifdef CONFIG_X86_64 /* free the range so iommu could get some range less than 4G */ dma32_free_bootmem(); #endif - if (pci_swiotlb_init()) + if (use_swiotlb) return; gart_iommu_hole_init(); -- cgit v1.2.3 From f3eee54276dfd1117fd94259f2b4a38388264724 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 14 Dec 2009 11:52:15 +0900 Subject: x86: Gart: fix breakage due to IOMMU initialization cleanup This fixes the following breakage of the commit 75f1cdf1dda92cae037ec848ae63690d91913eac: - GART systems that don't AGP with broken BIOS and more than 4GB memory are forced to use swiotlb. They can allocate aperture by hand and use GART. - GART systems without GAP must disable GART on shutdown. - swiotlb usage is forced by the boot option, gart_iommu_hole_init() is not called, so we disable GART early_gart_iommu_check(). Signed-off-by: Yinghai Lu Signed-off-by: FUJITA Tomonori LKML-Reference: <1260759135-6450-3-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar --- arch/x86/kernel/aperture_64.c | 11 ++++++----- arch/x86/kernel/pci-gart_64.c | 3 ++- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index e0dfb6856aa2..3704997e8b25 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -280,7 +280,8 @@ void __init early_gart_iommu_check(void) * or BIOS forget to put that in reserved. * try to update e820 to make that region as reserved. */ - int i, fix, slot; + u32 agp_aper_base = 0, agp_aper_order = 0; + int i, fix, slot, valid_agp = 0; u32 ctl; u32 aper_size = 0, aper_order = 0, last_aper_order = 0; u64 aper_base = 0, last_aper_base = 0; @@ -290,6 +291,8 @@ void __init early_gart_iommu_check(void) return; /* This is mostly duplicate of iommu_hole_init */ + agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp); + fix = 0; for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { int bus; @@ -342,10 +345,10 @@ void __init early_gart_iommu_check(void) } } - if (!fix) + if (valid_agp) return; - /* different nodes have different setting, disable them all at first*/ + /* disable them all at first */ for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { int bus; int dev_base, dev_limit; @@ -458,8 +461,6 @@ out: if (aper_alloc) { /* Got the aperture from the AGP bridge */ - } else if (!valid_agp) { - /* Do nothing */ } else if ((!no_iommu && max_pfn > MAX_DMA32_PFN) || force_iommu || valid_agp || diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index e6a0d402f171..56c0e730d3fe 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -710,7 +710,8 @@ static void gart_iommu_shutdown(void) struct pci_dev *dev; int i; - if (no_agp) + /* don't shutdown it if there is AGP installed */ + if (!no_agp) return; for (i = 0; i < num_k8_northbridges; i++) { -- cgit v1.2.3 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') 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 v1.2.3 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') 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 v1.2.3