From b69edc76539be6a4aa39a22f85365fd4a3b3b9d2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 31 Oct 2008 01:02:41 +0100 Subject: x86 hibernate: Mark ACPI NVS memory region at startup Introduce new initcall for marking the ACPI NVS memory at startup, so that it can be saved/restored during hibernation/resume. Based on a patch by Zhang Rui. Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- arch/x86/kernel/e820.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 7aafeb5263ef..74c6a21fdc8c 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -665,6 +665,27 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) } #endif +#ifdef CONFIG_HIBERNATION +/** + * Mark ACPI NVS memory region, so that we can save/restore it during + * hibernation and the subsequent resume. + */ +static int __init e820_mark_nvs_memory(void) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (ei->type == E820_NVS) + hibernate_nvs_register(ei->addr, ei->size); + } + + return 0; +} +core_initcall(e820_mark_nvs_memory); +#endif + /* * Early reserved memory areas. */ -- cgit v1.2.2 From ba84ed9546e91348fdf3ff2bff859b0ee53b407a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 26 Oct 2008 20:56:30 +0100 Subject: ACPI hibernate: Introduce new kernel parameter acpi_sleep=s4_nonvs On some machines it may be necessary to disable the saving/restoring of the ACPI NVS memory region during hibernation/resume. For this purpose, introduce new ACPI kernel command line option acpi_sleep=s4_nonvs. Based on a patch by Zhang Rui. Signed-off-by: Rafael J. Wysocki Acked-by: Nigel Cunningham Acked-by: Pavel Machek Signed-off-by: Len Brown --- arch/x86/kernel/acpi/sleep.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 806b4e9051b4..707c1f6f95fa 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -159,6 +159,8 @@ static int __init acpi_sleep_setup(char *str) #endif if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); + if (strncmp(str, "s4_nonvs", 8) == 0) + acpi_s4_no_nvs(); str = strchr(str, ','); if (str != NULL) str += strspn(str, ", \t"); -- cgit v1.2.2 From 7b37b5fd9ba32c0c5afc3537eed7e7466f2173e2 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Tue, 23 Dec 2008 01:47:42 -0500 Subject: ACPI: disable MPS when NO APIC-table found When ACPI is asked to find an MADT (APIC table) and fails, then ACPI expects to run in PIC mode. However, if an MP Table is was found, IRQs will be registered as if an IOAPIC is being used, even though ACPI is configuring interrupt links links for PIC mode. In this scenario, disable MPS so that IRQs are registered in PIC mode, consistent with ACPI. http://bugzilla.kernel.org/show_bug.cgi?id=12257 Signed-off-by: Len Brown --- arch/x86/kernel/acpi/boot.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4c51a2f8fd31..de8ce79dd881 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1359,6 +1359,17 @@ static void __init acpi_process_madt(void) "Invalid BIOS MADT, disabling ACPI\n"); disable_acpi(); } + } else { + /* + * ACPI found no MADT, and so ACPI wants UP PIC mode. + * In the event an MPS table was found, forget it. + * Boot with "acpi=off" to use MPS on such a system. + */ + if (smp_found_config) { + printk(KERN_WARNING PREFIX + "No APIC-table, disabling MPS\n"); + smp_found_config = 0; + } } #endif return; -- cgit v1.2.2 From 70a7d3cc1308a55104fbe505d76f2aca8a4cf53e Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Mon, 22 Dec 2008 10:26:05 -0800 Subject: swiotlb: add hwdev to swiotlb_phys_to_bus() / swiotlb_sg_to_bus() Impact: extend functions with a (yet unused) parameter, update callsites Some architectures need it - in preparation for highmem swiotlb. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- arch/x86/kernel/pci-swiotlb_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index 242c3440687f..6cf8a816dc29 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -23,7 +23,7 @@ void *swiotlb_alloc(unsigned order, unsigned long nslabs) return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order); } -dma_addr_t swiotlb_phys_to_bus(phys_addr_t paddr) +dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr) { return paddr; } -- cgit v1.2.2 From 1da4f9894c243a9c58c505fd8f3e6cc0709a8825 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Sun, 28 Dec 2008 15:02:05 +0900 Subject: swiotlb: replace architecture-specific swiotlb.h with linux/swiotlb.h Impact: cleanup This replaces architecture-specific swiotlb.h (X86 and IA64) with linux/swiotlb.h. Signed-off-by: FUJITA Tomonori Signed-off-by: Ingo Molnar --- arch/x86/include/asm/swiotlb.h | 38 +------------------------------------- 1 file changed, 1 insertion(+), 37 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index 51fb2c76ad74..b9e4e20174fb 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -1,46 +1,10 @@ #ifndef _ASM_X86_SWIOTLB_H #define _ASM_X86_SWIOTLB_H -#include +#include /* SWIOTLB interface */ -extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr, - size_t size, int dir); -extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags); -extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir); -extern void swiotlb_sync_single_for_cpu(struct device *hwdev, - dma_addr_t dev_addr, - size_t size, int dir); -extern void swiotlb_sync_single_for_device(struct device *hwdev, - dma_addr_t dev_addr, - size_t size, int dir); -extern void swiotlb_sync_single_range_for_cpu(struct device *hwdev, - dma_addr_t dev_addr, - unsigned long offset, - size_t size, int dir); -extern void swiotlb_sync_single_range_for_device(struct device *hwdev, - dma_addr_t dev_addr, - unsigned long offset, - size_t size, int dir); -extern void swiotlb_sync_sg_for_cpu(struct device *hwdev, - struct scatterlist *sg, int nelems, - int dir); -extern void swiotlb_sync_sg_for_device(struct device *hwdev, - struct scatterlist *sg, int nelems, - int dir); -extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, int direction); -extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, - int nents, int direction); -extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); -extern void swiotlb_free_coherent(struct device *hwdev, size_t size, - void *vaddr, dma_addr_t dma_handle); -extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); -extern void swiotlb_init(void); - extern int swiotlb_force; #ifdef CONFIG_SWIOTLB -- cgit v1.2.2 From 83bd9243956f30d91851b272988a237999b35b10 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Mon, 15 Dec 2008 15:09:50 +0100 Subject: x86/oprofile: fix pci_dev use count for AMD northbridge devices This patch fixes the PCI device use count for AMD northbridge devices. In case of an IBS LVT initialization failure, the PCI device is released now by calling pci_dev_put(). If there are no initialization errors, the devices are released in pci_get_device() while iterating. Signed-off-by: Robert Richter --- arch/x86/oprofile/op_model_amd.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index 98658f25f542..c5b5c7fb3ced 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -409,6 +409,7 @@ static int init_ibs_nmi(void) | IBSCTL_LVTOFFSETVAL); pci_read_config_dword(cpu_cfg, IBSCTL, &value); if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) { + pci_dev_put(cpu_cfg); printk(KERN_DEBUG "Failed to setup IBS LVT offset, " "IBSCTL = 0x%08x", value); return 1; -- cgit v1.2.2 From c2d1cec1c77f7714672c1efeae075424c929e0d5 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sun, 4 Jan 2009 05:18:03 -0800 Subject: x86: cleanup remaining cpumask_t ops in smpboot code Impact: use new cpumask API to reduce memory and stack usage Allocate the following local cpumasks based on the number of cpus that are present. References will use new cpumask API. (Currently only modified for x86_64, x86_32 continues to use the *_map variants.) cpu_callin_mask cpu_callout_mask cpu_initialized_mask cpu_sibling_setup_mask Provide the following accessor functions: struct cpumask *cpu_sibling_mask(int cpu) struct cpumask *cpu_core_mask(int cpu) Other changes are when setting or clearing the cpu online, possible or present maps, use the accessor functions. Signed-off-by: Mike Travis Acked-by: Rusty Russell Signed-off-by: Ingo Molnar --- arch/x86/include/asm/smp.h | 32 ++++++++++- arch/x86/kernel/cpu/common.c | 26 +++++++-- arch/x86/kernel/setup_percpu.c | 25 +++++++- arch/x86/kernel/smp.c | 17 ++++-- arch/x86/kernel/smpboot.c | 128 +++++++++++++++++++++-------------------- 5 files changed, 152 insertions(+), 76 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 830b9fcb6427..19953df61c52 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -18,9 +18,26 @@ #include #include +#ifdef CONFIG_X86_64 + +extern cpumask_var_t cpu_callin_mask; +extern cpumask_var_t cpu_callout_mask; +extern cpumask_var_t cpu_initialized_mask; +extern cpumask_var_t cpu_sibling_setup_mask; + +#else /* CONFIG_X86_32 */ + +extern cpumask_t cpu_callin_map; extern cpumask_t cpu_callout_map; extern cpumask_t cpu_initialized; -extern cpumask_t cpu_callin_map; +extern cpumask_t cpu_sibling_setup_map; + +#define cpu_callin_mask ((struct cpumask *)&cpu_callin_map) +#define cpu_callout_mask ((struct cpumask *)&cpu_callout_map) +#define cpu_initialized_mask ((struct cpumask *)&cpu_initialized) +#define cpu_sibling_setup_mask ((struct cpumask *)&cpu_sibling_setup_map) + +#endif /* CONFIG_X86_32 */ extern void (*mtrr_hook)(void); extern void zap_low_mappings(void); @@ -29,7 +46,6 @@ extern int __cpuinit get_local_pda(int cpu); extern int smp_num_siblings; extern unsigned int num_processors; -extern cpumask_t cpu_initialized; DECLARE_PER_CPU(cpumask_t, cpu_sibling_map); DECLARE_PER_CPU(cpumask_t, cpu_core_map); @@ -38,6 +54,16 @@ DECLARE_PER_CPU(u16, cpu_llc_id); DECLARE_PER_CPU(int, cpu_number); #endif +static inline struct cpumask *cpu_sibling_mask(int cpu) +{ + return &per_cpu(cpu_sibling_map, cpu); +} + +static inline struct cpumask *cpu_core_mask(int cpu) +{ + return &per_cpu(cpu_core_map, cpu); +} + DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid); @@ -149,7 +175,7 @@ void smp_store_cpu_info(int id); /* We don't mark CPUs online until __cpu_up(), so we need another measure */ static inline int num_booting_cpus(void) { - return cpus_weight(cpu_callout_map); + return cpumask_weight(cpu_callout_mask); } #else static inline void prefill_possible_map(void) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 3f95a40f718a..83492b1f93b1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -40,6 +40,26 @@ #include "cpu.h" +#ifdef CONFIG_X86_64 + +/* all of these masks are initialized in setup_cpu_local_masks() */ +cpumask_var_t cpu_callin_mask; +cpumask_var_t cpu_callout_mask; +cpumask_var_t cpu_initialized_mask; + +/* representing cpus for which sibling maps can be computed */ +cpumask_var_t cpu_sibling_setup_mask; + +#else /* CONFIG_X86_32 */ + +cpumask_t cpu_callin_map; +cpumask_t cpu_callout_map; +cpumask_t cpu_initialized; +cpumask_t cpu_sibling_setup_map; + +#endif /* CONFIG_X86_32 */ + + static struct cpu_dev *this_cpu __cpuinitdata; #ifdef CONFIG_X86_64 @@ -856,8 +876,6 @@ static __init int setup_disablecpuid(char *arg) } __setup("clearcpuid=", setup_disablecpuid); -cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; - #ifdef CONFIG_X86_64 struct x8664_pda **_cpu_pda __read_mostly; EXPORT_SYMBOL(_cpu_pda); @@ -976,7 +994,7 @@ void __cpuinit cpu_init(void) me = current; - if (cpu_test_and_set(cpu, cpu_initialized)) + 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); @@ -1085,7 +1103,7 @@ void __cpuinit cpu_init(void) struct tss_struct *t = &per_cpu(init_tss, cpu); struct thread_struct *thread = &curr->thread; - if (cpu_test_and_set(cpu, cpu_initialized)) { + if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) { printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); for (;;) local_irq_enable(); } diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index a4b619c33106..aa55764602b1 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -131,7 +131,27 @@ static void __init setup_cpu_pda_map(void) /* point to new pointer table */ _cpu_pda = new_cpu_pda; } -#endif + +#endif /* CONFIG_SMP && CONFIG_X86_64 */ + +#ifdef CONFIG_X86_64 + +/* correctly size the local cpu masks */ +static void setup_cpu_local_masks(void) +{ + alloc_bootmem_cpumask_var(&cpu_initialized_mask); + alloc_bootmem_cpumask_var(&cpu_callin_mask); + alloc_bootmem_cpumask_var(&cpu_callout_mask); + alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); +} + +#else /* CONFIG_X86_32 */ + +static inline void setup_cpu_local_masks(void) +{ +} + +#endif /* CONFIG_X86_32 */ /* * Great future plan: @@ -187,6 +207,9 @@ void __init setup_per_cpu_areas(void) /* Setup node to cpumask map */ setup_node_to_cpumask_map(); + + /* Setup cpu initialized, callin, callout masks */ + setup_cpu_local_masks(); } #endif diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index beea2649a240..182135ba1eaf 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -128,16 +128,23 @@ void native_send_call_func_single_ipi(int cpu) void native_send_call_func_ipi(const struct cpumask *mask) { - cpumask_t allbutself; + cpumask_var_t allbutself; - allbutself = cpu_online_map; - cpu_clear(smp_processor_id(), allbutself); + if (!alloc_cpumask_var(&allbutself, GFP_ATOMIC)) { + send_IPI_mask(mask, CALL_FUNCTION_VECTOR); + return; + } - if (cpus_equal(*mask, allbutself) && - cpus_equal(cpu_online_map, cpu_callout_map)) + cpumask_copy(allbutself, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), allbutself); + + if (cpumask_equal(mask, allbutself) && + cpumask_equal(cpu_online_mask, cpu_callout_mask)) send_IPI_allbutself(CALL_FUNCTION_VECTOR); else send_IPI_mask(mask, CALL_FUNCTION_VECTOR); + + free_cpumask_var(allbutself); } /* diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6bd4d9b73870..00e17e589482 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -102,9 +102,6 @@ EXPORT_SYMBOL(smp_num_siblings); /* Last level cache ID of each logical CPU */ DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID; -cpumask_t cpu_callin_map; -cpumask_t cpu_callout_map; - /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU(cpumask_t, cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); @@ -120,9 +117,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info); static atomic_t init_deasserted; -/* representing cpus for which sibling maps can be computed */ -static cpumask_t cpu_sibling_setup_map; - /* Set if we find a B stepping CPU */ static int __cpuinitdata smp_b_stepping; @@ -140,7 +134,7 @@ EXPORT_SYMBOL(cpu_to_node_map); static void map_cpu_to_node(int cpu, int node) { printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node); - cpu_set(cpu, node_to_cpumask_map[node]); + cpumask_set_cpu(cpu, &node_to_cpumask_map[node]); cpu_to_node_map[cpu] = node; } @@ -151,7 +145,7 @@ static void unmap_cpu_to_node(int cpu) printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu); for (node = 0; node < MAX_NUMNODES; node++) - cpu_clear(cpu, node_to_cpumask_map[node]); + cpumask_clear_cpu(cpu, &node_to_cpumask_map[node]); cpu_to_node_map[cpu] = 0; } #else /* !(CONFIG_NUMA && CONFIG_X86_32) */ @@ -209,7 +203,7 @@ static void __cpuinit smp_callin(void) */ phys_id = read_apic_id(); cpuid = smp_processor_id(); - if (cpu_isset(cpuid, cpu_callin_map)) { + if (cpumask_test_cpu(cpuid, cpu_callin_mask)) { panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__, phys_id, cpuid); } @@ -231,7 +225,7 @@ static void __cpuinit smp_callin(void) /* * Has the boot CPU finished it's STARTUP sequence? */ - if (cpu_isset(cpuid, cpu_callout_map)) + if (cpumask_test_cpu(cpuid, cpu_callout_mask)) break; cpu_relax(); } @@ -274,7 +268,7 @@ static void __cpuinit smp_callin(void) /* * Allow the master to continue. */ - cpu_set(cpuid, cpu_callin_map); + cpumask_set_cpu(cpuid, cpu_callin_mask); } static int __cpuinitdata unsafe_smp; @@ -332,7 +326,7 @@ notrace static void __cpuinit start_secondary(void *unused) ipi_call_lock(); lock_vector_lock(); __setup_vector_irq(smp_processor_id()); - cpu_set(smp_processor_id(), cpu_online_map); + set_cpu_online(smp_processor_id(), true); unlock_vector_lock(); ipi_call_unlock(); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; @@ -438,50 +432,52 @@ void __cpuinit set_cpu_sibling_map(int cpu) int i; struct cpuinfo_x86 *c = &cpu_data(cpu); - cpu_set(cpu, cpu_sibling_setup_map); + cpumask_set_cpu(cpu, cpu_sibling_setup_mask); if (smp_num_siblings > 1) { - for_each_cpu_mask_nr(i, cpu_sibling_setup_map) { - if (c->phys_proc_id == cpu_data(i).phys_proc_id && - c->cpu_core_id == cpu_data(i).cpu_core_id) { - cpu_set(i, per_cpu(cpu_sibling_map, cpu)); - cpu_set(cpu, per_cpu(cpu_sibling_map, i)); - cpu_set(i, per_cpu(cpu_core_map, cpu)); - cpu_set(cpu, per_cpu(cpu_core_map, i)); - cpu_set(i, c->llc_shared_map); - cpu_set(cpu, cpu_data(i).llc_shared_map); + for_each_cpu(i, cpu_sibling_setup_mask) { + struct cpuinfo_x86 *o = &cpu_data(i); + + if (c->phys_proc_id == o->phys_proc_id && + c->cpu_core_id == o->cpu_core_id) { + cpumask_set_cpu(i, cpu_sibling_mask(cpu)); + cpumask_set_cpu(cpu, cpu_sibling_mask(i)); + cpumask_set_cpu(i, cpu_core_mask(cpu)); + cpumask_set_cpu(cpu, cpu_core_mask(i)); + cpumask_set_cpu(i, &c->llc_shared_map); + cpumask_set_cpu(cpu, &o->llc_shared_map); } } } else { - cpu_set(cpu, per_cpu(cpu_sibling_map, cpu)); + cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); } - cpu_set(cpu, c->llc_shared_map); + cpumask_set_cpu(cpu, &c->llc_shared_map); if (current_cpu_data.x86_max_cores == 1) { - per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu); + cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu)); c->booted_cores = 1; return; } - for_each_cpu_mask_nr(i, cpu_sibling_setup_map) { + for_each_cpu(i, cpu_sibling_setup_mask) { if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { - cpu_set(i, c->llc_shared_map); - cpu_set(cpu, cpu_data(i).llc_shared_map); + cpumask_set_cpu(i, &c->llc_shared_map); + cpumask_set_cpu(cpu, &cpu_data(i).llc_shared_map); } if (c->phys_proc_id == cpu_data(i).phys_proc_id) { - cpu_set(i, per_cpu(cpu_core_map, cpu)); - cpu_set(cpu, per_cpu(cpu_core_map, i)); + cpumask_set_cpu(i, cpu_core_mask(cpu)); + cpumask_set_cpu(cpu, cpu_core_mask(i)); /* * Does this new cpu bringup a new core? */ - if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) { + if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) { /* * for each core in package, increment * the booted_cores for this new cpu */ - if (first_cpu(per_cpu(cpu_sibling_map, i)) == i) + if (cpumask_first(cpu_sibling_mask(i)) == i) c->booted_cores++; /* * increment the core count for all @@ -504,7 +500,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu) * And for power savings, we return cpu_core_map */ if (sched_mc_power_savings || sched_smt_power_savings) - return &per_cpu(cpu_core_map, cpu); + return cpu_core_mask(cpu); else return &c->llc_shared_map; } @@ -523,7 +519,7 @@ static void impress_friends(void) */ pr_debug("Before bogomips.\n"); for_each_possible_cpu(cpu) - if (cpu_isset(cpu, cpu_callout_map)) + if (cpumask_test_cpu(cpu, cpu_callout_mask)) bogosum += cpu_data(cpu).loops_per_jiffy; printk(KERN_INFO "Total of %d processors activated (%lu.%02lu BogoMIPS).\n", @@ -904,19 +900,19 @@ do_rest: * allow APs to start initializing. */ pr_debug("Before Callout %d.\n", cpu); - cpu_set(cpu, cpu_callout_map); + cpumask_set_cpu(cpu, cpu_callout_mask); pr_debug("After Callout %d.\n", cpu); /* * Wait 5s total for a response */ for (timeout = 0; timeout < 50000; timeout++) { - if (cpu_isset(cpu, cpu_callin_map)) + if (cpumask_test_cpu(cpu, cpu_callin_mask)) break; /* It has booted */ udelay(100); } - if (cpu_isset(cpu, cpu_callin_map)) { + 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); @@ -941,9 +937,14 @@ restore_state: if (boot_error) { /* Try to put things back the way they were before ... */ numa_remove_cpu(cpu); /* was set by numa_add_cpu */ - cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */ - cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */ - cpu_clear(cpu, cpu_present_map); + + /* was set by do_boot_cpu() */ + cpumask_clear_cpu(cpu, cpu_callout_mask); + + /* was set by cpu_init() */ + cpumask_clear_cpu(cpu, cpu_initialized_mask); + + set_cpu_present(cpu, false); per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; } @@ -977,7 +978,7 @@ int __cpuinit native_cpu_up(unsigned int cpu) /* * Already booted CPU? */ - if (cpu_isset(cpu, cpu_callin_map)) { + if (cpumask_test_cpu(cpu, cpu_callin_mask)) { pr_debug("do_boot_cpu %d Already started\n", cpu); return -ENOSYS; } @@ -1032,8 +1033,9 @@ int __cpuinit native_cpu_up(unsigned int cpu) */ static __init void disable_smp(void) { - cpu_present_map = cpumask_of_cpu(0); - cpu_possible_map = cpumask_of_cpu(0); + /* use the read/write pointers to the present and possible maps */ + cpumask_copy(&cpu_present_map, cpumask_of(0)); + cpumask_copy(&cpu_possible_map, cpumask_of(0)); smpboot_clear_io_apic_irqs(); if (smp_found_config) @@ -1041,8 +1043,8 @@ static __init void disable_smp(void) else physid_set_mask_of_physid(0, &phys_cpu_present_map); map_cpu_to_logical_apicid(); - cpu_set(0, per_cpu(cpu_sibling_map, 0)); - cpu_set(0, per_cpu(cpu_core_map, 0)); + cpumask_set_cpu(0, cpu_sibling_mask(0)); + cpumask_set_cpu(0, cpu_core_mask(0)); } /* @@ -1064,14 +1066,14 @@ static int __init smp_sanity_check(unsigned max_cpus) nr = 0; for_each_present_cpu(cpu) { if (nr >= 8) - cpu_clear(cpu, cpu_present_map); + set_cpu_present(cpu, false); nr++; } nr = 0; for_each_possible_cpu(cpu) { if (nr >= 8) - cpu_clear(cpu, cpu_possible_map); + set_cpu_possible(cpu, false); nr++; } @@ -1167,7 +1169,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) preempt_disable(); smp_cpu_index_default(); current_cpu_data = boot_cpu_data; - cpu_callin_map = cpumask_of_cpu(0); + cpumask_copy(cpu_callin_mask, cpumask_of(0)); mb(); /* * Setup boot CPU information @@ -1242,8 +1244,8 @@ void __init native_smp_prepare_boot_cpu(void) init_gdt(me); #endif switch_to_new_gdt(); - /* already set me in cpu_online_map in boot_cpu_init() */ - cpu_set(me, cpu_callout_map); + /* already set me in cpu_online_mask in boot_cpu_init() */ + cpumask_set_cpu(me, cpu_callout_mask); per_cpu(cpu_state, me) = CPU_ONLINE; } @@ -1311,7 +1313,7 @@ __init void prefill_possible_map(void) possible, max_t(int, possible - num_processors, 0)); for (i = 0; i < possible; i++) - cpu_set(i, cpu_possible_map); + set_cpu_possible(i, true); nr_cpu_ids = possible; } @@ -1323,31 +1325,31 @@ static void remove_siblinginfo(int cpu) int sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); - for_each_cpu_mask_nr(sibling, per_cpu(cpu_core_map, cpu)) { - cpu_clear(cpu, per_cpu(cpu_core_map, sibling)); + for_each_cpu(sibling, cpu_core_mask(cpu)) { + cpumask_clear_cpu(cpu, cpu_core_mask(sibling)); /*/ * last thread sibling in this cpu core going down */ - if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) + if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) cpu_data(sibling).booted_cores--; } - for_each_cpu_mask_nr(sibling, per_cpu(cpu_sibling_map, cpu)) - cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling)); - cpus_clear(per_cpu(cpu_sibling_map, cpu)); - cpus_clear(per_cpu(cpu_core_map, cpu)); + for_each_cpu(sibling, cpu_sibling_mask(cpu)) + cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + cpumask_clear(cpu_sibling_mask(cpu)); + cpumask_clear(cpu_core_mask(cpu)); c->phys_proc_id = 0; c->cpu_core_id = 0; - cpu_clear(cpu, cpu_sibling_setup_map); + cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); } static void __ref remove_cpu_from_maps(int cpu) { - cpu_clear(cpu, cpu_online_map); - cpu_clear(cpu, cpu_callout_map); - cpu_clear(cpu, cpu_callin_map); + set_cpu_online(cpu, false); + cpumask_clear_cpu(cpu, cpu_callout_mask); + cpumask_clear_cpu(cpu, cpu_callin_mask); /* was set by cpu_init() */ - cpu_clear(cpu, cpu_initialized); + cpumask_clear_cpu(cpu, cpu_initialized_mask); numa_remove_cpu(cpu); } -- cgit v1.2.2 From 5cb0535f1713b51610f2881b17d0fe3656114364 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sun, 4 Jan 2009 05:18:05 -0800 Subject: cpumask: replace CPUMASK_ALLOC etc with cpumask_var_t Impact: cleanup There's only one user, and it's a fairly easy conversion. Signed-off-by: Rusty Russell Signed-off-by: Mike Travis Acked-by: Dave Jones Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c index f0ea6fa2f53c..d2cc4991cbaa 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c @@ -458,11 +458,6 @@ static int centrino_verify (struct cpufreq_policy *policy) * * Sets a new CPUFreq policy. */ -struct allmasks { - cpumask_t saved_mask; - cpumask_t covered_cpus; -}; - static int centrino_target (struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) @@ -472,12 +467,15 @@ static int centrino_target (struct cpufreq_policy *policy, struct cpufreq_freqs freqs; int retval = 0; unsigned int j, k, first_cpu, tmp; - CPUMASK_ALLOC(allmasks); - CPUMASK_PTR(saved_mask, allmasks); - CPUMASK_PTR(covered_cpus, allmasks); + cpumask_var_t saved_mask, covered_cpus; - if (unlikely(allmasks == NULL)) + if (unlikely(!alloc_cpumask_var(&saved_mask, GFP_KERNEL))) return -ENOMEM; + if (unlikely(!alloc_cpumask_var(&covered_cpus, GFP_KERNEL))) { + free_cpumask_var(saved_mask); + return -ENOMEM; + } + cpumask_copy(saved_mask, ¤t->cpus_allowed); if (unlikely(per_cpu(centrino_model, cpu) == NULL)) { retval = -ENODEV; @@ -493,9 +491,7 @@ static int centrino_target (struct cpufreq_policy *policy, goto out; } - *saved_mask = current->cpus_allowed; first_cpu = 1; - cpus_clear(*covered_cpus); for_each_cpu_mask_nr(j, policy->cpus) { const cpumask_t *mask; @@ -605,7 +601,8 @@ migrate_end: preempt_enable(); set_cpus_allowed_ptr(current, saved_mask); out: - CPUMASK_FREE(allmasks); + free_cpumask_var(saved_mask); + free_cpumask_var(covered_cpus); return retval; } -- cgit v1.2.2 From 835481d9bcd65720b473db6b38746a74a3964218 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sun, 4 Jan 2009 05:18:06 -0800 Subject: cpumask: convert struct cpufreq_policy to cpumask_var_t Impact: use new cpumask API to reduce memory usage This is part of an effort to reduce structure sizes for machines configured with large NR_CPUS. cpumask_t gets replaced by cpumask_var_t, which is either struct cpumask[1] (small NR_CPUS) or struct cpumask * (large NR_CPUS). Signed-off-by: Rusty Russell Signed-off-by: Mike Travis Acked-by: Dave Jones Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 10 +++++----- arch/x86/kernel/cpu/cpufreq/p4-clockmod.c | 8 ++++---- arch/x86/kernel/cpu/cpufreq/powernow-k8.c | 6 +++--- arch/x86/kernel/cpu/cpufreq/powernow-k8.h | 2 +- arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c | 14 +++++++------- arch/x86/kernel/cpu/cpufreq/speedstep-ich.c | 18 +++++++++--------- 6 files changed, 29 insertions(+), 29 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 28102ad1a363..0b31939862d6 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -411,7 +411,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, #ifdef CONFIG_HOTPLUG_CPU /* cpufreq holds the hotplug lock, so we are safe from here on */ - cpus_and(online_policy_cpus, cpu_online_map, policy->cpus); + cpumask_and(&online_policy_cpus, cpu_online_mask, policy->cpus); #else online_policy_cpus = policy->cpus; #endif @@ -626,15 +626,15 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) */ if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL || policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) { - cpumask_copy(&policy->cpus, perf->shared_cpu_map); + cpumask_copy(policy->cpus, perf->shared_cpu_map); } - cpumask_copy(&policy->related_cpus, perf->shared_cpu_map); + cpumask_copy(policy->related_cpus, perf->shared_cpu_map); #ifdef CONFIG_SMP dmi_check_system(sw_any_bug_dmi_table); - if (bios_with_sw_any_bug && cpus_weight(policy->cpus) == 1) { + if (bios_with_sw_any_bug && cpumask_weight(policy->cpus) == 1) { policy->shared_type = CPUFREQ_SHARED_TYPE_ALL; - policy->cpus = per_cpu(cpu_core_map, cpu); + cpumask_copy(policy->cpus, cpu_core_mask(cpu)); } #endif diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index beea4466b063..b585e04cbc9e 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -122,7 +122,7 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, return 0; /* notifiers */ - for_each_cpu_mask_nr(i, policy->cpus) { + for_each_cpu(i, policy->cpus) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } @@ -130,11 +130,11 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, /* run on each logical CPU, see section 13.15.3 of IA32 Intel Architecture Software * Developer's Manual, Volume 3 */ - for_each_cpu_mask_nr(i, policy->cpus) + for_each_cpu(i, policy->cpus) cpufreq_p4_setdc(i, p4clockmod_table[newstate].index); /* notifiers */ - for_each_cpu_mask_nr(i, policy->cpus) { + for_each_cpu(i, policy->cpus) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } @@ -203,7 +203,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) unsigned int i; #ifdef CONFIG_SMP - policy->cpus = per_cpu(cpu_sibling_map, policy->cpu); + cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu)); #endif /* Errata workaround */ diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index c3c9adbaa26f..5c28b37dea11 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -1199,10 +1199,10 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) set_cpus_allowed_ptr(current, &oldmask); if (cpu_family == CPU_HW_PSTATE) - pol->cpus = cpumask_of_cpu(pol->cpu); + cpumask_copy(pol->cpus, cpumask_of(pol->cpu)); else - pol->cpus = per_cpu(cpu_core_map, pol->cpu); - data->available_cores = &(pol->cpus); + cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu)); + data->available_cores = pol->cpus; /* Take a crude guess here. * That guess was in microseconds, so multiply with 1000 */ diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h index 65cfb5d7f77f..8ecc75b6c7c3 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h @@ -53,7 +53,7 @@ struct powernow_k8_data { /* we need to keep track of associated cores, but let cpufreq * handle hotplug events - so just point at cpufreq pol->cpus * structure */ - cpumask_t *available_cores; + struct cpumask *available_cores; }; diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c index d2cc4991cbaa..f08998278a3a 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c @@ -492,8 +492,8 @@ static int centrino_target (struct cpufreq_policy *policy, } first_cpu = 1; - for_each_cpu_mask_nr(j, policy->cpus) { - const cpumask_t *mask; + for_each_cpu(j, policy->cpus) { + const struct cpumask *mask; /* cpufreq holds the hotplug lock, so we are safe here */ if (!cpu_online(j)) @@ -504,9 +504,9 @@ static int centrino_target (struct cpufreq_policy *policy, * Make sure we are running on CPU that wants to change freq */ if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) - mask = &policy->cpus; + mask = policy->cpus; else - mask = &cpumask_of_cpu(j); + mask = cpumask_of(j); set_cpus_allowed_ptr(current, mask); preempt_disable(); @@ -538,7 +538,7 @@ static int centrino_target (struct cpufreq_policy *policy, dprintk("target=%dkHz old=%d new=%d msr=%04x\n", target_freq, freqs.old, freqs.new, msr); - for_each_cpu_mask_nr(k, policy->cpus) { + for_each_cpu(k, policy->cpus) { if (!cpu_online(k)) continue; freqs.cpu = k; @@ -563,7 +563,7 @@ static int centrino_target (struct cpufreq_policy *policy, preempt_enable(); } - for_each_cpu_mask_nr(k, policy->cpus) { + for_each_cpu(k, policy->cpus) { if (!cpu_online(k)) continue; freqs.cpu = k; @@ -586,7 +586,7 @@ static int centrino_target (struct cpufreq_policy *policy, tmp = freqs.new; freqs.new = freqs.old; freqs.old = tmp; - for_each_cpu_mask_nr(j, policy->cpus) { + for_each_cpu(j, policy->cpus) { if (!cpu_online(j)) continue; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c index 04d0376b64b0..dedc1e98f168 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c @@ -229,7 +229,7 @@ static unsigned int speedstep_detect_chipset (void) return 0; } -static unsigned int _speedstep_get(const cpumask_t *cpus) +static unsigned int _speedstep_get(const struct cpumask *cpus) { unsigned int speed; cpumask_t cpus_allowed; @@ -244,7 +244,7 @@ static unsigned int _speedstep_get(const cpumask_t *cpus) static unsigned int speedstep_get(unsigned int cpu) { - return _speedstep_get(&cpumask_of_cpu(cpu)); + return _speedstep_get(cpumask_of(cpu)); } /** @@ -267,7 +267,7 @@ static int speedstep_target (struct cpufreq_policy *policy, if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], target_freq, relation, &newstate)) return -EINVAL; - freqs.old = _speedstep_get(&policy->cpus); + freqs.old = _speedstep_get(policy->cpus); freqs.new = speedstep_freqs[newstate].frequency; freqs.cpu = policy->cpu; @@ -279,20 +279,20 @@ static int speedstep_target (struct cpufreq_policy *policy, cpus_allowed = current->cpus_allowed; - for_each_cpu_mask_nr(i, policy->cpus) { + for_each_cpu(i, policy->cpus) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } /* switch to physical CPU where state is to be changed */ - set_cpus_allowed_ptr(current, &policy->cpus); + set_cpus_allowed_ptr(current, policy->cpus); speedstep_set_state(newstate); /* allow to be run on all CPUs */ set_cpus_allowed_ptr(current, &cpus_allowed); - for_each_cpu_mask_nr(i, policy->cpus) { + for_each_cpu(i, policy->cpus) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } @@ -322,11 +322,11 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) /* only run on CPU to be set, or on its sibling */ #ifdef CONFIG_SMP - policy->cpus = per_cpu(cpu_sibling_map, policy->cpu); + cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu)); #endif cpus_allowed = current->cpus_allowed; - set_cpus_allowed_ptr(current, &policy->cpus); + set_cpus_allowed_ptr(current, policy->cpus); /* detect low and high frequency and transition latency */ result = speedstep_get_freqs(speedstep_processor, @@ -339,7 +339,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) return result; /* get current speed setting */ - speed = _speedstep_get(&policy->cpus); + speed = _speedstep_get(policy->cpus); if (!speed) return -EIO; -- cgit v1.2.2 From c74f31c035f46a095a0c72f80246a65b314205a5 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sun, 4 Jan 2009 05:18:07 -0800 Subject: cpumask: use work_on_cpu in acpi/cstate.c Impact: use new cpumask API to reduce stack usage Replace the saving of current->cpus_allowed and set_cpus_allowed_ptr() with a work_on_cpu function for the acpi_processor_ffh_cstate_probe() function. Basically splits acpi_processor_ffh_cstate_probe() into two functions, the other being acpi_processor_ffh_cstate_probe_cpu which is the work function run on the designated cpu. Signed-off-by: Mike Travis Acked-by: Rusty Russell Signed-off-by: Ingo Molnar --- arch/x86/kernel/acpi/cstate.c | 70 +++++++++++++++++++++++-------------------- 1 file changed, 37 insertions(+), 33 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index c2502eb9aa83..cf5ec586f220 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -66,35 +66,15 @@ static short mwait_supported[ACPI_PROCESSOR_MAX_POWER]; #define NATIVE_CSTATE_BEYOND_HALT (2) -int acpi_processor_ffh_cstate_probe(unsigned int cpu, - struct acpi_processor_cx *cx, struct acpi_power_register *reg) +static long acpi_processor_ffh_cstate_probe_cpu(void *_cx) { - struct cstate_entry *percpu_entry; - struct cpuinfo_x86 *c = &cpu_data(cpu); - - cpumask_t saved_mask; - int retval; + struct acpi_processor_cx *cx = _cx; + long retval; unsigned int eax, ebx, ecx, edx; unsigned int edx_part; unsigned int cstate_type; /* C-state type and not ACPI C-state type */ unsigned int num_cstate_subtype; - if (!cpu_cstate_entry || c->cpuid_level < CPUID_MWAIT_LEAF ) - return -1; - - if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT) - return -1; - - percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu); - percpu_entry->states[cx->index].eax = 0; - percpu_entry->states[cx->index].ecx = 0; - - /* Make sure we are running on right CPU */ - saved_mask = current->cpus_allowed; - retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - if (retval) - return -1; - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); /* Check whether this particular cx_type (in CST) is supported or not */ @@ -114,21 +94,45 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, retval = -1; goto out; } - percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK; - - /* Use the hint in CST */ - percpu_entry->states[cx->index].eax = cx->address; if (!mwait_supported[cstate_type]) { mwait_supported[cstate_type] = 1; - printk(KERN_DEBUG "Monitor-Mwait will be used to enter C-%d " - "state\n", cx->type); + printk(KERN_DEBUG + "Monitor-Mwait will be used to enter C-%d " + "state\n", cx->type); } - snprintf(cx->desc, ACPI_CX_DESC_LEN, "ACPI FFH INTEL MWAIT 0x%x", - cx->address); - + snprintf(cx->desc, + ACPI_CX_DESC_LEN, "ACPI FFH INTEL MWAIT 0x%x", + cx->address); out: - set_cpus_allowed_ptr(current, &saved_mask); + return retval; +} + +int acpi_processor_ffh_cstate_probe(unsigned int cpu, + struct acpi_processor_cx *cx, struct acpi_power_register *reg) +{ + struct cstate_entry *percpu_entry; + struct cpuinfo_x86 *c = &cpu_data(cpu); + long retval; + + if (!cpu_cstate_entry || c->cpuid_level < CPUID_MWAIT_LEAF) + return -1; + + if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT) + return -1; + + percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu); + percpu_entry->states[cx->index].eax = 0; + percpu_entry->states[cx->index].ecx = 0; + + /* Make sure we are running on right CPU */ + + retval = work_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx); + if (retval == 0) { + /* Use the hint in CST */ + percpu_entry->states[cx->index].eax = cx->address; + percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK; + } return retval; } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); -- cgit v1.2.2 From 4d8bb5374924fc736ce275bfd1619b87a2106860 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sun, 4 Jan 2009 05:18:08 -0800 Subject: cpumask: use cpumask_var_t in acpi-cpufreq.c Impact: cleanup, reduce stack usage, use new cpumask API. Replace the cpumask_t in struct drv_cmd with a cpumask_var_t. Remove unneeded online_policy_cpus cpumask_t in acpi_cpufreq_target. Update refs to use new cpumask API. Signed-off-by: Mike Travis Acked-by: Rusty Russell Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 58 +++++++++++++++--------------- 1 file changed, 29 insertions(+), 29 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 0b31939862d6..fb594170dc53 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -145,7 +145,7 @@ typedef union { struct drv_cmd { unsigned int type; - cpumask_t mask; + cpumask_var_t mask; drv_addr_union addr; u32 val; }; @@ -193,7 +193,7 @@ static void drv_read(struct drv_cmd *cmd) cpumask_t saved_mask = current->cpus_allowed; cmd->val = 0; - set_cpus_allowed_ptr(current, &cmd->mask); + set_cpus_allowed_ptr(current, cmd->mask); do_drv_read(cmd); set_cpus_allowed_ptr(current, &saved_mask); } @@ -203,8 +203,8 @@ static void drv_write(struct drv_cmd *cmd) cpumask_t saved_mask = current->cpus_allowed; unsigned int i; - for_each_cpu_mask_nr(i, cmd->mask) { - set_cpus_allowed_ptr(current, &cpumask_of_cpu(i)); + for_each_cpu(i, cmd->mask) { + set_cpus_allowed_ptr(current, cpumask_of(i)); do_drv_write(cmd); } @@ -212,22 +212,22 @@ static void drv_write(struct drv_cmd *cmd) return; } -static u32 get_cur_val(const cpumask_t *mask) +static u32 get_cur_val(const struct cpumask *mask) { struct acpi_processor_performance *perf; struct drv_cmd cmd; - if (unlikely(cpus_empty(*mask))) + if (unlikely(cpumask_empty(mask))) return 0; - switch (per_cpu(drv_data, first_cpu(*mask))->cpu_feature) { + switch (per_cpu(drv_data, cpumask_first(mask))->cpu_feature) { case SYSTEM_INTEL_MSR_CAPABLE: cmd.type = SYSTEM_INTEL_MSR_CAPABLE; cmd.addr.msr.reg = MSR_IA32_PERF_STATUS; break; case SYSTEM_IO_CAPABLE: cmd.type = SYSTEM_IO_CAPABLE; - perf = per_cpu(drv_data, first_cpu(*mask))->acpi_data; + perf = per_cpu(drv_data, cpumask_first(mask))->acpi_data; cmd.addr.io.port = perf->control_register.address; cmd.addr.io.bit_width = perf->control_register.bit_width; break; @@ -235,7 +235,7 @@ static u32 get_cur_val(const cpumask_t *mask) return 0; } - cmd.mask = *mask; + cpumask_copy(cmd.mask, mask); drv_read(&cmd); @@ -386,7 +386,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu); struct acpi_processor_performance *perf; struct cpufreq_freqs freqs; - cpumask_t online_policy_cpus; struct drv_cmd cmd; unsigned int next_state = 0; /* Index into freq_table */ unsigned int next_perf_state = 0; /* Index into perf table */ @@ -401,20 +400,18 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, return -ENODEV; } + if (unlikely(!alloc_cpumask_var(&cmd.mask, GFP_KERNEL))) + return -ENOMEM; + perf = data->acpi_data; result = cpufreq_frequency_table_target(policy, data->freq_table, target_freq, relation, &next_state); - if (unlikely(result)) - return -ENODEV; - -#ifdef CONFIG_HOTPLUG_CPU - /* cpufreq holds the hotplug lock, so we are safe from here on */ - cpumask_and(&online_policy_cpus, cpu_online_mask, policy->cpus); -#else - online_policy_cpus = policy->cpus; -#endif + if (unlikely(result)) { + result = -ENODEV; + goto out; + } next_perf_state = data->freq_table[next_state].index; if (perf->state == next_perf_state) { @@ -425,7 +422,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, } else { dprintk("Already at target state (P%d)\n", next_perf_state); - return 0; + goto out; } } @@ -444,19 +441,19 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, cmd.val = (u32) perf->states[next_perf_state].control; break; default: - return -ENODEV; + result = -ENODEV; + goto out; } - cpus_clear(cmd.mask); - + /* cpufreq holds the hotplug lock, so we are safe from here on */ if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY) - cmd.mask = online_policy_cpus; + cpumask_and(cmd.mask, cpu_online_mask, policy->cpus); else - cpu_set(policy->cpu, cmd.mask); + cpumask_copy(cmd.mask, cpumask_of(policy->cpu)); freqs.old = perf->states[perf->state].core_frequency * 1000; freqs.new = data->freq_table[next_state].frequency; - for_each_cpu_mask_nr(i, cmd.mask) { + for_each_cpu(i, cmd.mask) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } @@ -464,19 +461,22 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, drv_write(&cmd); if (acpi_pstate_strict) { - if (!check_freqs(&cmd.mask, freqs.new, data)) { + if (!check_freqs(cmd.mask, freqs.new, data)) { dprintk("acpi_cpufreq_target failed (%d)\n", policy->cpu); - return -EAGAIN; + result = -EAGAIN; + goto out; } } - for_each_cpu_mask_nr(i, cmd.mask) { + for_each_cpu(i, cmd.mask) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } perf->state = next_perf_state; +out: + free_cpumask_var(cmd.mask); return result; } -- cgit v1.2.2 From 7503bfbae89eba07b46441a5d1594647f6b8ab7d Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sun, 4 Jan 2009 05:18:09 -0800 Subject: cpumask: use work_on_cpu in acpi-cpufreq.c for drv_read and drv_write Impact: use new cpumask API to reduce stack usage Replace the saving of current->cpus_allowed and set_cpus_allowed_ptr() with a work_on_cpu function for drv_read() and drv_write(). Basically converts do_drv_{read,write} into "work_on_cpu" functions that are now called by drv_read and drv_write. Signed-off-by: Mike Travis Acked-by: Rusty Russell Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index fb594170dc53..4e4f2b04dac2 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -150,8 +150,9 @@ struct drv_cmd { u32 val; }; -static void do_drv_read(struct drv_cmd *cmd) +static long do_drv_read(void *_cmd) { + struct drv_cmd *cmd = _cmd; u32 h; switch (cmd->type) { @@ -166,10 +167,12 @@ static void do_drv_read(struct drv_cmd *cmd) default: break; } + return 0; } -static void do_drv_write(struct drv_cmd *cmd) +static long do_drv_write(void *_cmd) { + struct drv_cmd *cmd = _cmd; u32 lo, hi; switch (cmd->type) { @@ -186,30 +189,23 @@ static void do_drv_write(struct drv_cmd *cmd) default: break; } + return 0; } static void drv_read(struct drv_cmd *cmd) { - cpumask_t saved_mask = current->cpus_allowed; cmd->val = 0; - set_cpus_allowed_ptr(current, cmd->mask); - do_drv_read(cmd); - set_cpus_allowed_ptr(current, &saved_mask); + work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd); } static void drv_write(struct drv_cmd *cmd) { - cpumask_t saved_mask = current->cpus_allowed; unsigned int i; for_each_cpu(i, cmd->mask) { - set_cpus_allowed_ptr(current, cpumask_of(i)); - do_drv_write(cmd); + work_on_cpu(i, do_drv_write, cmd); } - - set_cpus_allowed_ptr(current, &saved_mask); - return; } static u32 get_cur_val(const struct cpumask *mask) @@ -235,10 +231,15 @@ static u32 get_cur_val(const struct cpumask *mask) return 0; } + if (unlikely(!alloc_cpumask_var(&cmd.mask, GFP_KERNEL))) + return 0; + cpumask_copy(cmd.mask, mask); drv_read(&cmd); + free_cpumask_var(cmd.mask); + dprintk("get_cur_val = %u\n", cmd.val); return cmd.val; -- cgit v1.2.2 From e39ad415ac15116df213dfa2aa2a4f1b0857af9c Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sun, 4 Jan 2009 05:18:10 -0800 Subject: cpumask: use work_on_cpu in acpi-cpufreq.c for read_measured_perf_ctrs Impact: use new cpumask API to reduce stack usage Replace the saving of current->cpus_allowed and set_cpus_allowed_ptr() with a work_on_cpu function for read_measured_perf_ctrs(). Basically splits off the work function from get_measured_perf which is run on the designated cpu. Moves definition of struct perf_cur out of function local namespace, and is used as the work function argument. References in get_measured_perf use values in the perf_cur struct. Signed-off-by: Mike Travis Acked-by: Rusty Russell Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 83 ++++++++++++++++-------------- 1 file changed, 43 insertions(+), 40 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 4e4f2b04dac2..06fcd8f9323c 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -245,6 +245,30 @@ static u32 get_cur_val(const struct cpumask *mask) return cmd.val; } +struct perf_cur { + union { + struct { + u32 lo; + u32 hi; + } split; + u64 whole; + } aperf_cur, mperf_cur; +}; + + +static long read_measured_perf_ctrs(void *_cur) +{ + struct perf_cur *cur = _cur; + + rdmsr(MSR_IA32_APERF, cur->aperf_cur.split.lo, cur->aperf_cur.split.hi); + rdmsr(MSR_IA32_MPERF, cur->mperf_cur.split.lo, cur->mperf_cur.split.hi); + + wrmsr(MSR_IA32_APERF, 0, 0); + wrmsr(MSR_IA32_MPERF, 0, 0); + + return 0; +} + /* * Return the measured active (C0) frequency on this CPU since last call * to this function. @@ -261,31 +285,12 @@ static u32 get_cur_val(const struct cpumask *mask) static unsigned int get_measured_perf(struct cpufreq_policy *policy, unsigned int cpu) { - union { - struct { - u32 lo; - u32 hi; - } split; - u64 whole; - } aperf_cur, mperf_cur; - - cpumask_t saved_mask; + struct perf_cur cur; unsigned int perf_percent; unsigned int retval; - saved_mask = current->cpus_allowed; - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - if (get_cpu() != cpu) { - /* We were not able to run on requested processor */ - put_cpu(); + if (!work_on_cpu(cpu, read_measured_perf_ctrs, &cur)) return 0; - } - - rdmsr(MSR_IA32_APERF, aperf_cur.split.lo, aperf_cur.split.hi); - rdmsr(MSR_IA32_MPERF, mperf_cur.split.lo, mperf_cur.split.hi); - - wrmsr(MSR_IA32_APERF, 0,0); - wrmsr(MSR_IA32_MPERF, 0,0); #ifdef __i386__ /* @@ -293,37 +298,39 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy, * Get an approximate value. Return failure in case we cannot get * an approximate value. */ - if (unlikely(aperf_cur.split.hi || mperf_cur.split.hi)) { + if (unlikely(cur.aperf_cur.split.hi || cur.mperf_cur.split.hi)) { int shift_count; u32 h; - h = max_t(u32, aperf_cur.split.hi, mperf_cur.split.hi); + h = max_t(u32, cur.aperf_cur.split.hi, cur.mperf_cur.split.hi); shift_count = fls(h); - aperf_cur.whole >>= shift_count; - mperf_cur.whole >>= shift_count; + cur.aperf_cur.whole >>= shift_count; + cur.mperf_cur.whole >>= shift_count; } - if (((unsigned long)(-1) / 100) < aperf_cur.split.lo) { + if (((unsigned long)(-1) / 100) < cur.aperf_cur.split.lo) { int shift_count = 7; - aperf_cur.split.lo >>= shift_count; - mperf_cur.split.lo >>= shift_count; + cur.aperf_cur.split.lo >>= shift_count; + cur.mperf_cur.split.lo >>= shift_count; } - if (aperf_cur.split.lo && mperf_cur.split.lo) - perf_percent = (aperf_cur.split.lo * 100) / mperf_cur.split.lo; + if (cur.aperf_cur.split.lo && cur.mperf_cur.split.lo) + perf_percent = (cur.aperf_cur.split.lo * 100) / + cur.mperf_cur.split.lo; else perf_percent = 0; #else - if (unlikely(((unsigned long)(-1) / 100) < aperf_cur.whole)) { + if (unlikely(((unsigned long)(-1) / 100) < cur.aperf_cur.whole)) { int shift_count = 7; - aperf_cur.whole >>= shift_count; - mperf_cur.whole >>= shift_count; + cur.aperf_cur.whole >>= shift_count; + cur.mperf_cur.whole >>= shift_count; } - if (aperf_cur.whole && mperf_cur.whole) - perf_percent = (aperf_cur.whole * 100) / mperf_cur.whole; + if (cur.aperf_cur.whole && cur.mperf_cur.whole) + perf_percent = (cur.aperf_cur.whole * 100) / + cur.mperf_cur.whole; else perf_percent = 0; @@ -331,10 +338,6 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy, retval = per_cpu(drv_data, policy->cpu)->max_freq * perf_percent / 100; - put_cpu(); - set_cpus_allowed_ptr(current, &saved_mask); - - dprintk("cpu %d: performance percent %d\n", cpu, perf_percent); return retval; } @@ -352,7 +355,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu) } cached_freq = data->freq_table[data->acpi_data->state].frequency; - freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data); + freq = extract_freq(get_cur_val(cpumask_of(cpu)), data); if (freq != cached_freq) { /* * The dreaded BIOS frequency change behind our back. -- cgit v1.2.2 From 025dfdafe77f20b3890981a394774baab7b9c827 Mon Sep 17 00:00:00 2001 From: Frederik Schwarzer Date: Thu, 16 Oct 2008 19:02:37 +0200 Subject: trivial: fix then -> than typos in comments and documentation - (better, more, bigger ...) then -> (...) than Signed-off-by: Frederik Schwarzer Signed-off-by: Jiri Kosina --- arch/x86/kernel/kprobes.c | 2 +- arch/x86/kernel/mfgpt_32.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 6c27679ec6aa..a116e6d5726c 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -694,7 +694,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) /* * It is possible to have multiple instances associated with a given * task either because multiple functions in the call path have - * return probes installed on them, and/or more then one + * return probes installed on them, and/or more than one * return probe was registered for a target function. * * We can handle this because: diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index c12314c9e86f..8815f3c7fec7 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -252,7 +252,7 @@ EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer); /* * The MFPGT timers on the CS5536 provide us with suitable timers to use * as clock event sources - not as good as a HPET or APIC, but certainly - * better then the PIT. This isn't a general purpose MFGPT driver, but + * better than the PIT. This isn't a general purpose MFGPT driver, but * a simplified one designed specifically to act as a clock event source. * For full details about the MFGPT, please consult the CS5536 data sheet. */ -- cgit v1.2.2 From 4d9f94319c485f5af6717dfd7a333949636aed16 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Mon, 5 Jan 2009 17:09:41 -0800 Subject: x86: fix x86_32 builds for summit and es7000 arch's Fix the following build errors reported by Yinghai Lu: | In file included from arch/x86/mach-generic/summit.c:16: | tip/linux-2.6/arch/x86/include/asm/summit/apic.h: | In function 'cpu_mask_to_apicid_and': | tip/linux-2.6/arch/x86/include/asm/summit/apic.h:179: | error: 'GFP_ATOMIC' undeclared (first use in this function) Reported-by: Yinghai Lu Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar --- arch/x86/include/asm/es7000/apic.h | 2 ++ arch/x86/include/asm/summit/apic.h | 1 + 2 files changed, 3 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/es7000/apic.h b/arch/x86/include/asm/es7000/apic.h index bc53d5ef1386..c58b9cc74465 100644 --- a/arch/x86/include/asm/es7000/apic.h +++ b/arch/x86/include/asm/es7000/apic.h @@ -1,6 +1,8 @@ #ifndef __ASM_ES7000_APIC_H #define __ASM_ES7000_APIC_H +#include + #define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu) #define esr_disable (1) diff --git a/arch/x86/include/asm/summit/apic.h b/arch/x86/include/asm/summit/apic.h index 4bb5fb34f030..93d2c8667cfe 100644 --- a/arch/x86/include/asm/summit/apic.h +++ b/arch/x86/include/asm/summit/apic.h @@ -2,6 +2,7 @@ #define __ASM_SUMMIT_APIC_H #include +#include #define esr_disable (1) #define NO_BALANCE_IRQ (0) -- cgit v1.2.2 From 1c0fe6e3bda0464728c23c8d84aa47567e8b716c Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 6 Jan 2009 14:38:59 -0800 Subject: mm: invoke oom-killer from page fault Rather than have the pagefault handler kill a process directly if it gets a VM_FAULT_OOM, have it call into the OOM killer. With increasingly sophisticated oom behaviour (cpusets, memory cgroups, oom killing throttling, oom priority adjustment or selective disabling, panic on oom, etc), it's silly to unconditionally kill the faulting process at page fault time. Create a hook for pagefault oom path to call into instead. Only converted x86 and uml so far. [akpm@linux-foundation.org: make __out_of_memory() static] [akpm@linux-foundation.org: fix comment] Signed-off-by: Nick Piggin Cc: Jeff Dike Acked-by: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/fault.c | 24 ++++++------------------ 1 file changed, 6 insertions(+), 18 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 57ec8c86a877..9e268b6b204e 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -667,7 +667,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(in_atomic() || !mm)) goto bad_area_nosemaphore; -again: /* * When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the @@ -859,25 +858,14 @@ no_context: oops_end(flags, regs, sig); #endif -/* - * We ran out of memory, or some other thing happened to us that made - * us unable to handle the page fault gracefully. - */ out_of_memory: + /* + * We ran out of memory, call the OOM killer, and return the userspace + * (which will retry the fault, or kill us if we got oom-killed). + */ up_read(&mm->mmap_sem); - if (is_global_init(tsk)) { - yield(); - /* - * Re-lookup the vma - in theory the vma tree might - * have changed: - */ - goto again; - } - - printk("VM: killing process %s\n", tsk->comm); - if (error_code & PF_USER) - do_group_exit(SIGKILL); - goto no_context; + pagefault_out_of_memory(); + return; do_sigbus: up_read(&mm->mmap_sem); -- cgit v1.2.2 From c04fc586c1a480ba198f03ae7b6cbd7b57380b91 Mon Sep 17 00:00:00 2001 From: Gary Hade Date: Tue, 6 Jan 2009 14:39:14 -0800 Subject: mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade Signed-off-by: Badari Pulavarty Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/init_32.c | 2 +- arch/x86/mm/init_64.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index f99a6c6c432e..544d724caeee 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -1079,7 +1079,7 @@ int arch_add_memory(int nid, u64 start, u64 size) unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - return __add_pages(zone, start_pfn, nr_pages); + return __add_pages(nid, zone, start_pfn, nr_pages); } #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 9f7a0d24d42a..54c437e96541 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -857,7 +857,7 @@ int arch_add_memory(int nid, u64 start, u64 size) if (last_mapped_pfn > max_pfn_mapped) max_pfn_mapped = last_mapped_pfn; - ret = __add_pages(zone, start_pfn, nr_pages); + ret = __add_pages(nid, zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); return ret; -- cgit v1.2.2 From ea435467500612636f8f4fb639ff6e76b2496e4b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 6 Jan 2009 14:40:39 -0800 Subject: atomic_t: unify all arch definitions The atomic_t type cannot currently be used in some header files because it would create an include loop with asm/atomic.h. Move the type definition to linux/types.h to break the loop. Signed-off-by: Matthew Wilcox Cc: Huang Ying Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/atomic_32.h | 10 +--------- arch/x86/include/asm/atomic_64.h | 18 ++---------------- 2 files changed, 3 insertions(+), 25 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h index ad5b9f6ecddf..85b46fba4229 100644 --- a/arch/x86/include/asm/atomic_32.h +++ b/arch/x86/include/asm/atomic_32.h @@ -2,6 +2,7 @@ #define _ASM_X86_ATOMIC_32_H #include +#include #include #include @@ -10,15 +11,6 @@ * resource counting etc.. */ -/* - * Make sure gcc doesn't try to be clever and move things around - * on us. We need to use _exactly_ the address the user gave us, - * not some alias that contains the same information. - */ -typedef struct { - int counter; -} atomic_t; - #define ATOMIC_INIT(i) { (i) } /** diff --git a/arch/x86/include/asm/atomic_64.h b/arch/x86/include/asm/atomic_64.h index 279d2a731f3f..8c21731984da 100644 --- a/arch/x86/include/asm/atomic_64.h +++ b/arch/x86/include/asm/atomic_64.h @@ -1,25 +1,15 @@ #ifndef _ASM_X86_ATOMIC_64_H #define _ASM_X86_ATOMIC_64_H +#include #include #include -/* atomic_t should be 32 bit signed type */ - /* * Atomic operations that C can't guarantee us. Useful for * resource counting etc.. */ -/* - * Make sure gcc doesn't try to be clever and move things around - * on us. We need to use _exactly_ the address the user gave us, - * not some alias that contains the same information. - */ -typedef struct { - int counter; -} atomic_t; - #define ATOMIC_INIT(i) { (i) } /** @@ -191,11 +181,7 @@ static inline int atomic_sub_return(int i, atomic_t *v) #define atomic_inc_return(v) (atomic_add_return(1, v)) #define atomic_dec_return(v) (atomic_sub_return(1, v)) -/* An 64bit atomic type */ - -typedef struct { - long counter; -} atomic64_t; +/* The 64-bit atomic type */ #define ATOMIC64_INIT(i) { (i) } -- cgit v1.2.2 From f1883f86dea84fe47a71a39fc1afccc005915ed8 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 6 Jan 2009 14:40:45 -0800 Subject: Remove remaining unwinder code Signed-off-by: Alexey Dobriyan Cc: Gabor Gombas Cc: Jan Beulich Cc: Andi Kleen Cc: Ingo Molnar , Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/unwind.h | 13 ------------- arch/x86/kernel/traps.c | 2 -- 2 files changed, 15 deletions(-) delete mode 100644 arch/x86/include/asm/unwind.h (limited to 'arch/x86') diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h deleted file mode 100644 index 8b064bd9c553..000000000000 --- a/arch/x86/include/asm/unwind.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef _ASM_X86_UNWIND_H -#define _ASM_X86_UNWIND_H - -#define UNW_PC(frame) ((void)(frame), 0UL) -#define UNW_SP(frame) ((void)(frame), 0UL) -#define UNW_FP(frame) ((void)(frame), 0UL) - -static inline int arch_unw_user_mode(const void *info) -{ - return 0; -} - -#endif /* _ASM_X86_UNWIND_H */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ce6650eb64e9..c9a666cdd3db 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include @@ -51,7 +50,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.2 From 129415607845d4daea11ddcba706005c69dcb942 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 6 Jan 2009 14:41:50 -0800 Subject: kprobes: add kprobe_insn_mutex and cleanup arch_remove_kprobe() Add kprobe_insn_mutex for protecting kprobe_insn_pages hlist, and remove kprobe_mutex from architecture dependent code. This allows us to call arch_remove_kprobe() (and free_insn_slot) while holding kprobe_mutex. Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: Russell King Cc: "Luck, Tony" Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/kprobes.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 6c27679ec6aa..eead6f8f9218 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -376,9 +376,10 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p) void __kprobes arch_remove_kprobe(struct kprobe *p) { - mutex_lock(&kprobe_mutex); - free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1)); - mutex_unlock(&kprobe_mutex); + if (p->ainsn.insn) { + free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1)); + p->ainsn.insn = NULL; + } } static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) -- cgit v1.2.2 From 5d30a683888c60b8f93bef3ddc139d1a91ca58f4 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Tue, 6 Jan 2009 14:56:28 -0800 Subject: x86: introduce asm/swab.h Signed-off-by: Harvey Harrison Signed-off-by: Linus Torvalds --- arch/x86/include/asm/Kbuild | 1 + arch/x86/include/asm/byteorder.h | 62 ++-------------------------------------- arch/x86/include/asm/swab.h | 61 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 64 insertions(+), 60 deletions(-) create mode 100644 arch/x86/include/asm/swab.h (limited to 'arch/x86') diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 4a8e80cdcfa5..a9f8a814a1f7 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -22,3 +22,4 @@ unifdef-y += unistd_32.h unifdef-y += unistd_64.h unifdef-y += vm86.h unifdef-y += vsyscall.h +unifdef-y += swab.h diff --git a/arch/x86/include/asm/byteorder.h b/arch/x86/include/asm/byteorder.h index f110ad417df3..7c49917e3d9d 100644 --- a/arch/x86/include/asm/byteorder.h +++ b/arch/x86/include/asm/byteorder.h @@ -1,65 +1,7 @@ #ifndef _ASM_X86_BYTEORDER_H #define _ASM_X86_BYTEORDER_H -#include -#include - -#define __LITTLE_ENDIAN - -static inline __attribute_const__ __u32 __arch_swab32(__u32 val) -{ -#ifdef __i386__ -# ifdef CONFIG_X86_BSWAP - asm("bswap %0" : "=r" (val) : "0" (val)); -# else - asm("xchgb %b0,%h0\n\t" /* swap lower bytes */ - "rorl $16,%0\n\t" /* swap words */ - "xchgb %b0,%h0" /* swap higher bytes */ - : "=q" (val) - : "0" (val)); -# endif - -#else /* __i386__ */ - asm("bswapl %0" - : "=r" (val) - : "0" (val)); -#endif - return val; -} -#define __arch_swab32 __arch_swab32 - -static inline __attribute_const__ __u64 __arch_swab64(__u64 val) -{ -#ifdef __i386__ - union { - struct { - __u32 a; - __u32 b; - } s; - __u64 u; - } v; - v.u = val; -# ifdef CONFIG_X86_BSWAP - asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1" - : "=r" (v.s.a), "=r" (v.s.b) - : "0" (v.s.a), "1" (v.s.b)); -# else - v.s.a = __arch_swab32(v.s.a); - v.s.b = __arch_swab32(v.s.b); - asm("xchgl %0,%1" - : "=r" (v.s.a), "=r" (v.s.b) - : "0" (v.s.a), "1" (v.s.b)); -# endif - return v.u; -#else /* __i386__ */ - asm("bswapq %0" - : "=r" (val) - : "0" (val)); - return val; -#endif -} -#define __arch_swab64 __arch_swab64 - -#include +#include +#include #endif /* _ASM_X86_BYTEORDER_H */ diff --git a/arch/x86/include/asm/swab.h b/arch/x86/include/asm/swab.h new file mode 100644 index 000000000000..306d4178ffc9 --- /dev/null +++ b/arch/x86/include/asm/swab.h @@ -0,0 +1,61 @@ +#ifndef _ASM_X86_SWAB_H +#define _ASM_X86_SWAB_H + +#include +#include + +static inline __attribute_const__ __u32 __arch_swab32(__u32 val) +{ +#ifdef __i386__ +# ifdef CONFIG_X86_BSWAP + asm("bswap %0" : "=r" (val) : "0" (val)); +# else + asm("xchgb %b0,%h0\n\t" /* swap lower bytes */ + "rorl $16,%0\n\t" /* swap words */ + "xchgb %b0,%h0" /* swap higher bytes */ + : "=q" (val) + : "0" (val)); +# endif + +#else /* __i386__ */ + asm("bswapl %0" + : "=r" (val) + : "0" (val)); +#endif + return val; +} +#define __arch_swab32 __arch_swab32 + +static inline __attribute_const__ __u64 __arch_swab64(__u64 val) +{ +#ifdef __i386__ + union { + struct { + __u32 a; + __u32 b; + } s; + __u64 u; + } v; + v.u = val; +# ifdef CONFIG_X86_BSWAP + asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1" + : "=r" (v.s.a), "=r" (v.s.b) + : "0" (v.s.a), "1" (v.s.b)); +# else + v.s.a = __arch_swab32(v.s.a); + v.s.b = __arch_swab32(v.s.b); + asm("xchgl %0,%1" + : "=r" (v.s.a), "=r" (v.s.b) + : "0" (v.s.a), "1" (v.s.b)); +# endif + return v.u; +#else /* __i386__ */ + asm("bswapq %0" + : "=r" (val) + : "0" (val)); + return val; +#endif +} +#define __arch_swab64 __arch_swab64 + +#endif /* _ASM_X86_SWAB_H */ -- cgit v1.2.2 From 1a9271331ab663f3c7cda78d86b884f2ea86d4d7 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Thu, 30 Oct 2008 02:17:49 +0100 Subject: PCI: struct device - replace bus_id with dev_name(), dev_set_name() This patch is part of a larger patch series which will remove the "char bus_id[20]" name string from struct device. The device name is managed in the kobject anyway, and without any size limitation, and just needlessly copied into "struct device". To set and read the device name dev_name(dev) and dev_set_name(dev) must be used. If your code uses static kobjects, which it shouldn't do, "const char *init_name" can be used to statically provide the name the registered device should have. At registration time, the init_name field is cleared, to enforce the use of dev_name(dev) to access the device name at a later time. We need to get rid of all occurrences of bus_id in the entire tree to be able to enable the new interface. Please apply this patch, and possibly convert any remaining remaining occurrences of bus_id. Acked-by: Greg Kroah-Hartman Signed-Off-By: Kay Sievers Signed-off-by: Jesse Barnes --- arch/x86/kernel/pci-dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 19a1044a0cd9..b25428533141 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -38,7 +38,7 @@ EXPORT_SYMBOL(bad_dma_address); be probably a smaller DMA mask, but this is bug-to-bug compatible to older i386. */ struct device x86_dma_fallback_dev = { - .bus_id = "fallback device", + .init_name = "fallback device", .coherent_dma_mask = DMA_32BIT_MASK, .dma_mask = &x86_dma_fallback_dev.coherent_dma_mask, }; -- cgit v1.2.2 From 0ef5f8f6159e44b4faa997be08d1a3bcbf44ad08 Mon Sep 17 00:00:00 2001 From: Andrew Patterson Date: Mon, 10 Nov 2008 15:30:50 -0700 Subject: ACPI/PCI: PCI extended config _OSC support called when root bridge added The _OSC capability OSC_EXT_PCI_CONFIG_SUPPORT is set when the root bridge is added with pci_acpi_osc_support() if we can access PCI extended config space. This adds the function pci_ext_cfg_avail which returns true if we can access PCI extended config space (offset greater than 0xff). It currently only returns false if arch=x86 and raw_pci_ext_ops is not set (which might happen if pci=nommcfg is set on the kernel command-line). Signed-off-by: Andrew Patterson Signed-off-by: Jesse Barnes --- arch/x86/pci/common.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 62ddb73e09ed..9ab8509f7b15 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -562,6 +562,14 @@ void pcibios_disable_device (struct pci_dev *dev) pcibios_disable_irq(dev); } +int pci_ext_cfg_avail(struct pci_dev *dev) +{ + if (raw_pci_ext_ops) + return 1; + else + return 0; +} + struct pci_bus * __devinit pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node) { struct pci_bus *bus = NULL; -- cgit v1.2.2 From e8de1481fd7126ee9e93d6889da6f00c05e1e019 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Wed, 22 Oct 2008 19:55:31 -0700 Subject: resource: allow MMIO exclusivity for device drivers Device drivers that use pci_request_regions() (and similar APIs) have a reasonable expectation that they are the only ones accessing their device. As part of the e1000e hunt, we were afraid that some userland (X or some bootsplash stuff) was mapping the MMIO region that the driver thought it had exclusively via /dev/mem or via various sysfs resource mappings. This patch adds the option for device drivers to cause their reserved regions to the "banned from /dev/mem use" list, so now both kernel memory and device-exclusive MMIO regions are banned. NOTE: This is only active when CONFIG_STRICT_DEVMEM is set. In addition to the config option, a kernel parameter iomem=relaxed is provided for the cases where developers want to diagnose, in the field, drivers issues from userspace. Reviewed-by: Matthew Wilcox Signed-off-by: Arjan van de Ven Signed-off-by: Jesse Barnes --- arch/x86/mm/init_32.c | 2 ++ arch/x86/mm/init_64.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 544d724caeee..88f1b10de3be 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -328,6 +328,8 @@ int devmem_is_allowed(unsigned long pagenr) { if (pagenr <= 256) return 1; + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + return 0; if (!page_is_ram(pagenr)) return 1; return 0; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 54c437e96541..23f68e77ad1f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -888,6 +888,8 @@ int devmem_is_allowed(unsigned long pagenr) { if (pagenr <= 256) return 1; + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + return 0; if (!page_is_ram(pagenr)) return 1; return 0; -- cgit v1.2.2 From 104bafcfab7ce3031399e60069949f10acecc022 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 12 Dec 2008 06:49:40 +0100 Subject: PCI: Don't carp about BAR allocation failures in quiet boot These are easy to trigger (more or less harmlessly) with multiple video cards, since the ROM BAR will typically not be given any space by the BIOS bridge setup. No reason to punish quiet boot for this. Signed-off-by: Adam Jackson Signed-off-by: Jesse Barnes --- arch/x86/pci/i386.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index e51bf2cda4b0..f884740da318 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -129,7 +129,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) pr = pci_find_parent_resource(dev, r); if (!r->start || !pr || request_resource(pr, r) < 0) { - dev_err(&dev->dev, "BAR %d: can't allocate resource\n", idx); + dev_info(&dev->dev, "BAR %d: can't allocate resource\n", idx); /* * Something is wrong with the region. * Invalidate the resource to prevent @@ -170,7 +170,7 @@ static void __init pcibios_allocate_resources(int pass) r->flags, disabled, pass); pr = pci_find_parent_resource(dev, r); if (!pr || request_resource(pr, r) < 0) { - dev_err(&dev->dev, "BAR %d: can't allocate resource\n", idx); + dev_info(&dev->dev, "BAR %d: can't allocate resource\n", idx); /* We'll assign a new address later */ r->end -= r->start; r->start = 0; -- cgit v1.2.2 From 0663a36284586ac9a9781be8aa7e8ca9fff16d06 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 10 Dec 2008 13:12:00 -0700 Subject: x86/PCI: make PCI bus locality messages more meaningful Change PCI bus locality messages so they have a bit more context and look like the rest of PCI, e.g., - bus 01 -> node 0 - bus 04 -> node 0 + pci 0000:01: bus on NUMA node 0 + pci 0000:04: bus on NUMA node 0 Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- arch/x86/pci/acpi.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 9e5752fe4d15..6c7683709c44 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -210,11 +210,12 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do if (bus && node != -1) { #ifdef CONFIG_ACPI_NUMA if (pxm >= 0) - printk(KERN_DEBUG "bus %02x -> pxm %d -> node %d\n", - busnum, pxm, node); + printk(KERN_DEBUG + "pci %04x:%02x: bus on NUMA node %d (pxm %d)\n", + domain, busnum, node, pxm); #else - printk(KERN_DEBUG "bus %02x -> node %d\n", - busnum, node); + printk(KERN_DEBUG "pci %04x:%02x: bus on NUMA node %d\n", + domain, busnum, node); #endif } -- cgit v1.2.2 From 23a36002742bca87510201770a7d931c4aa63e97 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Mon, 8 Dec 2008 09:44:16 -0800 Subject: PCI: avoid early PCI mmconfig init if pci=noearly is given in cmdline Early type 1 accesses can cause problems on some platforms, and pci=noearly is supposed to prevent them from occurring. However, early mcfg probing code uses type 1 and isn't protected by a check for noearly. This patch fixes that problem. Signed-off-by: Jacob Pan Signed-off-by: Jesse Barnes --- arch/x86/pci/init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c index bec3b048e72b..25a1f8efed4a 100644 --- a/arch/x86/pci/init.c +++ b/arch/x86/pci/init.c @@ -12,7 +12,8 @@ static __init int pci_arch_init(void) type = pci_direct_probe(); #endif - pci_mmcfg_early_init(); + if (!(pci_probe & PCI_PROBE_NOEARLY)) + pci_mmcfg_early_init(); #ifdef CONFIG_PCI_OLPC if (!pci_olpc_init()) -- cgit v1.2.2 From 878f2e50fd1cfea575cdca5bf019c2175dc64131 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 9 Dec 2008 16:11:46 -0700 Subject: PCI: use config space encoding in pci_get_interrupt_pin() This patch makes pci_get_interrupt_pin() return values encoded the same way as the "Interrupt Pin" value in PCI config space, i.e., 1=INTA, ..., 4=INTD. pirq_bios_set() is the only in-tree caller of pci_get_interrupt_pin() and pci_get_interrupt_pin() is not exported. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: hpa@zytor.com Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- arch/x86/pci/irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 373b9afe6d44..399a172f047d 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -533,7 +533,7 @@ static int pirq_bios_set(struct pci_dev *router, struct pci_dev *dev, int pirq, { struct pci_dev *bridge; int pin = pci_get_interrupt_pin(dev, &bridge); - return pcibios_set_irq_routing(bridge, pin, irq); + return pcibios_set_irq_routing(bridge, pin - 1, irq); } #endif -- cgit v1.2.2 From f672c392b9c61bcdfb1247561d404b2c3ed4b0b3 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 9 Dec 2008 16:11:51 -0700 Subject: x86/PCI: use config space encoding for interrupt pins Keep "pin" encoded as it is in the "Interrupt Pin" value in PCI config space, i.e., 0=device doesn't use interrupts, 1=INTA, ..., 4=INTD. This makes the bridge INTx swizzle match other architectures. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: hpa@zytor.com Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- arch/x86/pci/irq.c | 44 ++++++++++++++++++++------------------------ 1 file changed, 20 insertions(+), 24 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 399a172f047d..cc9d5e254060 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -887,7 +887,6 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) dev_dbg(&dev->dev, "no interrupt pin\n"); return 0; } - pin = pin - 1; /* Find IRQ routing entry */ @@ -897,17 +896,17 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) info = pirq_get_info(dev); if (!info) { dev_dbg(&dev->dev, "PCI INT %c not found in routing table\n", - 'A' + pin); + 'A' + pin - 1); return 0; } - pirq = info->irq[pin].link; - mask = info->irq[pin].bitmap; + pirq = info->irq[pin - 1].link; + mask = info->irq[pin - 1].bitmap; if (!pirq) { - dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + pin); + dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + pin - 1); return 0; } dev_dbg(&dev->dev, "PCI INT %c -> PIRQ %02x, mask %04x, excl %04x", - 'A' + pin, pirq, mask, pirq_table->exclusive_irqs); + 'A' + pin - 1, pirq, mask, pirq_table->exclusive_irqs); mask &= pcibios_irq_mask; /* Work around broken HP Pavilion Notebooks which assign USB to @@ -949,7 +948,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) newirq = i; } } - dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + pin, newirq); + dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + pin - 1, newirq); /* Check if it is hardcoded */ if ((pirq & 0xf0) == 0xf0) { @@ -977,18 +976,18 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) return 0; } } - dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin, irq); + dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin - 1, irq); /* Update IRQ for all devices with the same pirq value */ while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) { pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &pin); if (!pin) continue; - pin--; + info = pirq_get_info(dev2); if (!info) continue; - if (info->irq[pin].link == pirq) { + if (info->irq[pin - 1].link == pirq) { /* * We refuse to override the dev->irq * information. Give a warning! @@ -1055,9 +1054,8 @@ static void __init pcibios_fixup_irqs(void) /* * interrupt pins are numbered starting from 1 */ - pin--; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, - PCI_SLOT(dev->devfn), pin); + PCI_SLOT(dev->devfn), pin - 1); /* * Busses behind bridges are typically not listed in the * MP-table. In this case we have to look up the IRQ @@ -1070,22 +1068,22 @@ static void __init pcibios_fixup_irqs(void) struct pci_dev *bridge = dev->bus->self; int bus; - pin = (pin + PCI_SLOT(dev->devfn)) % 4; + pin = (((pin - 1) + PCI_SLOT(dev->devfn)) % 4) + 1; bus = bridge->bus->number; irq = IO_APIC_get_PCI_irq_vector(bus, - PCI_SLOT(bridge->devfn), pin); + PCI_SLOT(bridge->devfn), pin - 1); if (irq >= 0) dev_warn(&dev->dev, "using bridge %s INT %c to " "get IRQ %d\n", pci_name(bridge), - 'A' + pin, irq); + 'A' + pin - 1, irq); } if (irq >= 0) { dev_info(&dev->dev, "PCI->APIC IRQ transform: INT %c " "-> IRQ %d\n", - 'A' + pin, irq); + 'A' + pin - 1, irq); dev->irq = irq; } } @@ -1220,12 +1218,10 @@ static int pirq_enable_irq(struct pci_dev *dev) if (pin && !pcibios_lookup_irq(dev, 1) && !dev->irq) { char *msg = ""; - pin--; /* interrupt pins are numbered starting from 1 */ - if (io_apic_assign_pci_irqs) { int irq; - irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin); + irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin - 1); /* * Busses behind bridges are typically not listed in the MP-table. * In this case we have to look up the IRQ based on the parent bus, @@ -1236,20 +1232,20 @@ static int pirq_enable_irq(struct pci_dev *dev) while (irq < 0 && dev->bus->parent) { /* go back to the bridge */ struct pci_dev *bridge = dev->bus->self; - pin = (pin + PCI_SLOT(dev->devfn)) % 4; + pin = (((pin - 1) + PCI_SLOT(dev->devfn)) % 4) + 1; irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, - PCI_SLOT(bridge->devfn), pin); + PCI_SLOT(bridge->devfn), pin - 1); if (irq >= 0) dev_warn(&dev->dev, "using bridge %s " "INT %c to get IRQ %d\n", - pci_name(bridge), 'A' + pin, + pci_name(bridge), 'A' + pin - 1, irq); dev = bridge; } dev = temp_dev; if (irq >= 0) { dev_info(&dev->dev, "PCI->APIC IRQ transform: " - "INT %c -> IRQ %d\n", 'A' + pin, irq); + "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); dev->irq = irq; return 0; } else @@ -1268,7 +1264,7 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; dev_warn(&dev->dev, "can't find IRQ for PCI INT %c%s\n", - 'A' + pin, msg); + 'A' + pin - 1, msg); } return 0; } -- cgit v1.2.2 From 12b955ff63db0b75cfc2d4939696c57b31891ec6 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 9 Dec 2008 16:11:57 -0700 Subject: x86/PCI: minor logic simplications Test "pin" immediately to simplify the subsequent code. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: hpa@zytor.com Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- arch/x86/pci/irq.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index cc9d5e254060..e1d605bfeb47 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1041,6 +1041,9 @@ static void __init pcibios_fixup_irqs(void) dev = NULL; while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); + if (!pin) + continue; + #ifdef CONFIG_X86_IO_APIC /* * Recalculate IRQ numbers if we use the I/O APIC. @@ -1048,9 +1051,6 @@ static void __init pcibios_fixup_irqs(void) if (io_apic_assign_pci_irqs) { int irq; - if (!pin) - continue; - /* * interrupt pins are numbered starting from 1 */ @@ -1091,7 +1091,7 @@ static void __init pcibios_fixup_irqs(void) /* * Still no IRQ? Try to lookup one... */ - if (pin && !dev->irq) + if (!dev->irq) pcibios_lookup_irq(dev, 0); } } -- cgit v1.2.2 From b1c86792a0f3cf24a12c1ac7d452d665d90284b1 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 9 Dec 2008 16:12:37 -0700 Subject: PCI: x86: use generic pci_swizzle_interrupt_pin() Use the generic pci_swizzle_interrupt_pin() instead of arch-specific code. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: hpa@zytor.com Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- arch/x86/pci/irq.c | 4 ++-- arch/x86/pci/visws.c | 7 +------ 2 files changed, 3 insertions(+), 8 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index e1d605bfeb47..4064345cf144 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1068,7 +1068,7 @@ static void __init pcibios_fixup_irqs(void) struct pci_dev *bridge = dev->bus->self; int bus; - pin = (((pin - 1) + PCI_SLOT(dev->devfn)) % 4) + 1; + pin = pci_swizzle_interrupt_pin(dev, pin); bus = bridge->bus->number; irq = IO_APIC_get_PCI_irq_vector(bus, PCI_SLOT(bridge->devfn), pin - 1); @@ -1232,7 +1232,7 @@ static int pirq_enable_irq(struct pci_dev *dev) while (irq < 0 && dev->bus->parent) { /* go back to the bridge */ struct pci_dev *bridge = dev->bus->self; - pin = (((pin - 1) + PCI_SLOT(dev->devfn)) % 4) + 1; + pin = pci_swizzle_interrupt_pin(dev, pin); irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, PCI_SLOT(bridge->devfn), pin - 1); if (irq >= 0) diff --git a/arch/x86/pci/visws.c b/arch/x86/pci/visws.c index 16d0c0eb0d19..2c54e7e03f53 100644 --- a/arch/x86/pci/visws.c +++ b/arch/x86/pci/visws.c @@ -24,17 +24,12 @@ static void pci_visws_disable_irq(struct pci_dev *dev) { } unsigned int pci_bus0, pci_bus1; -static inline u8 bridge_swizzle(u8 pin, u8 slot) -{ - return (((pin - 1) + slot) % 4) + 1; -} - static u8 __init visws_swizzle(struct pci_dev *dev, u8 *pinp) { u8 pin = *pinp; while (dev->bus->self) { /* Move up the chain of bridges. */ - pin = bridge_swizzle(pin, PCI_SLOT(dev->devfn)); + pin = pci_swizzle_interrupt_pin(dev, pin); dev = dev->bus->self; } *pinp = pin; -- cgit v1.2.2 From 904d6a303361a85bfa4c8181ef62a24edb8da0a8 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 16 Dec 2008 21:37:20 -0700 Subject: PCI: x86/visws: use generic INTx swizzle from PCI core Use the generic pci_common_swizzle() instead of arch-specific code. Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- arch/x86/pci/visws.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/visws.c b/arch/x86/pci/visws.c index 2c54e7e03f53..bcead7a46871 100644 --- a/arch/x86/pci/visws.c +++ b/arch/x86/pci/visws.c @@ -24,19 +24,6 @@ static void pci_visws_disable_irq(struct pci_dev *dev) { } unsigned int pci_bus0, pci_bus1; -static u8 __init visws_swizzle(struct pci_dev *dev, u8 *pinp) -{ - u8 pin = *pinp; - - while (dev->bus->self) { /* Move up the chain of bridges. */ - pin = pci_swizzle_interrupt_pin(dev, pin); - dev = dev->bus->self; - } - *pinp = pin; - - return PCI_SLOT(dev->devfn); -} - static int __init visws_map_irq(struct pci_dev *dev, u8 slot, u8 pin) { int irq, bus = dev->bus->number; @@ -101,7 +88,7 @@ int __init pci_visws_init(void) raw_pci_ops = &pci_direct_conf1; pci_scan_bus_with_sysdata(pci_bus0); pci_scan_bus_with_sysdata(pci_bus1); - pci_fixup_irqs(visws_swizzle, visws_map_irq); + pci_fixup_irqs(pci_common_swizzle, visws_map_irq); pcibios_resource_survey(); return 0; } -- cgit v1.2.2 From 2b8c2efe44ed897fc958131d70addc89876d806b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 18 Dec 2008 16:34:51 -0700 Subject: x86/PCI: use dev_printk for PCI bus locality messages Since pci_bus has a struct device, use dev_printk directly instead of faking it by hand. Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- arch/x86/pci/acpi.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 6c7683709c44..c0ecf250fe51 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -210,12 +210,10 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do if (bus && node != -1) { #ifdef CONFIG_ACPI_NUMA if (pxm >= 0) - printk(KERN_DEBUG - "pci %04x:%02x: bus on NUMA node %d (pxm %d)\n", - domain, busnum, node, pxm); + dev_printk(KERN_DEBUG, &bus->dev, + "on NUMA node %d (pxm %d)\n", node, pxm); #else - printk(KERN_DEBUG "pci %04x:%02x: bus on NUMA node %d\n", - domain, busnum, node); + dev_printk(KERN_DEBUG, &bus->dev, "on NUMA node %d\n", node); #endif } -- cgit v1.2.2 From 16cf0ebc35dd63f72628ba1246132a6fd17bced2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 5 Jan 2009 14:50:27 +0100 Subject: x86/PCI: Do not use interrupt links for devices using MSI-X pcibios_enable_device() and pcibios_disable_device() don't handle IRQs for devices that have MSI enabled and it should treat the devices with MSI-X enabled in the same way. Signed-off-by: Rafael J. Wysocki Acked-by: Ingo Molnar Signed-off-by: Jesse Barnes --- arch/x86/pci/common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 9ab8509f7b15..82d22fc601ae 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -551,14 +551,14 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) if ((err = pci_enable_resources(dev, mask)) < 0) return err; - if (!dev->msi_enabled) + if (!pci_dev_msi_enabled(dev)) return pcibios_enable_irq(dev); return 0; } void pcibios_disable_device (struct pci_dev *dev) { - if (!dev->msi_enabled && pcibios_disable_irq) + if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) pcibios_disable_irq(dev); } -- cgit v1.2.2 From fc81be8ca29e28bfb89aa23359036a8ad4118d0f Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Thu, 18 Dec 2008 00:28:27 +0100 Subject: oprofile: rename variable ibs_allowed to has_ibs in op_model_amd.c This patch renames ibs_allowed to has_ibs. Varible name fits better now. Signed-off-by: Robert Richter --- arch/x86/oprofile/op_model_amd.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index c5b5c7fb3ced..423a95438cbc 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -106,7 +106,7 @@ struct ibs_op_sample { unsigned int ibs_dc_phys_high; }; -static int ibs_allowed; /* AMD Family10h and later */ +static int has_ibs; /* AMD Family10h and later */ struct op_ibs_config { unsigned long op_enabled; @@ -201,7 +201,7 @@ op_amd_handle_ibs(struct pt_regs * const regs, struct ibs_fetch_sample ibs_fetch; struct ibs_op_sample ibs_op; - if (!ibs_allowed) + if (!has_ibs) return 1; if (ibs_config.fetch_enabled) { @@ -305,14 +305,14 @@ static void op_amd_start(struct op_msrs const * const msrs) } #ifdef CONFIG_OPROFILE_IBS - if (ibs_allowed && ibs_config.fetch_enabled) { + if (has_ibs && ibs_config.fetch_enabled) { low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF; high = ((ibs_config.rand_en & 0x1) << 25) /* bit 57 */ + IBS_FETCH_HIGH_ENABLE; wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); } - if (ibs_allowed && ibs_config.op_enabled) { + if (has_ibs && ibs_config.op_enabled) { low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + ((ibs_config.dispatched_ops & 0x1) << 19) /* bit 19 */ + IBS_OP_LOW_ENABLE; @@ -341,14 +341,14 @@ static void op_amd_stop(struct op_msrs const * const msrs) } #ifdef CONFIG_OPROFILE_IBS - if (ibs_allowed && ibs_config.fetch_enabled) { + if (has_ibs && ibs_config.fetch_enabled) { /* clear max count and enable */ low = 0; high = 0; wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); } - if (ibs_allowed && ibs_config.op_enabled) { + if (has_ibs && ibs_config.op_enabled) { /* clear max count and enable */ low = 0; high = 0; @@ -437,20 +437,20 @@ static int init_ibs_nmi(void) /* uninitialize the APIC for the IBS interrupts if needed */ static void clear_ibs_nmi(void) { - if (ibs_allowed) + if (has_ibs) on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1); } /* initialize the APIC for the IBS interrupts if available */ static void ibs_init(void) { - ibs_allowed = boot_cpu_has(X86_FEATURE_IBS); + has_ibs = boot_cpu_has(X86_FEATURE_IBS); - if (!ibs_allowed) + if (!has_ibs) return; if (init_ibs_nmi()) { - ibs_allowed = 0; + has_ibs = 0; return; } @@ -459,7 +459,7 @@ static void ibs_init(void) static void ibs_exit(void) { - if (!ibs_allowed) + if (!has_ibs) return; clear_ibs_nmi(); @@ -479,7 +479,7 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root) if (ret) return ret; - if (!ibs_allowed) + if (!has_ibs) return ret; /* model specific files */ -- cgit v1.2.2 From ae735e9964b4584923f2997d98a8d80ae9c1a75c Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Thu, 25 Dec 2008 17:26:07 +0100 Subject: oprofile: rework implementation of cpu buffer events Special events such as task or context switches are marked with an escape code in the cpu buffer followed by an event code or a task identifier. There is one escape code per event. To make escape sequences also available for data samples the internal cpu buffer format must be changed. The current implementation does not allow the extension of event codes since this would lead to collisions with the task identifiers. To avoid this, this patch introduces an event mask that allows the storage of multiple events with one escape code. Now, task identifiers are stored in the data section of the sample. The implementation also allows the usage of custom data in a sample. As a side effect the new code is much more readable and easier to understand. Signed-off-by: Robert Richter --- arch/x86/oprofile/op_model_amd.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index 423a95438cbc..f101724db80a 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -2,7 +2,7 @@ * @file op_model_amd.c * athlon / K7 / K8 / Family 10h model-specific MSR operations * - * @remark Copyright 2002-2008 OProfile authors + * @remark Copyright 2002-2009 OProfile authors * @remark Read the file COPYING * * @author John Levon @@ -10,7 +10,7 @@ * @author Graydon Hoare * @author Robert Richter * @author Barry Kasindorf -*/ + */ #include #include @@ -62,8 +62,8 @@ static unsigned long reset_value[NUM_COUNTERS]; /* Codes used in cpu_buffer.c */ /* This produces duplicate code, need to be fixed */ -#define IBS_FETCH_BEGIN 3 -#define IBS_OP_BEGIN 4 +#define IBS_FETCH_BEGIN (1UL << 4) +#define IBS_OP_BEGIN (1UL << 5) /* * The function interface needs to be fixed, something like add -- cgit v1.2.2 From 1acda878e20ea0cd3708ba66dca67d52eaafdd2b Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Mon, 5 Jan 2009 10:35:31 +0100 Subject: oprofile: use new data sample format for ibs The new ring buffer implementation allows the storage of samples with different size. This patch implements the usage of the new sample format to store ibs samples in the cpu buffer. Until now, writing to the cpu buffer could lead to incomplete sampling sequences since IBS samples were transfered in multiple samples. Due to a full buffer, data could be lost at any time. This can't happen any more since the complete data is reserved in advance and then stored in a single sample. Signed-off-by: Robert Richter --- arch/x86/oprofile/op_model_amd.c | 119 ++++++++++++++------------------------- 1 file changed, 41 insertions(+), 78 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index f101724db80a..cf310aeb462c 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -22,6 +22,7 @@ #include "op_x86_model.h" #include "op_counter.h" +#include "../../../drivers/oprofile/cpu_buffer.h" #define NUM_COUNTERS 4 #define NUM_CONTROLS 4 @@ -60,51 +61,16 @@ static unsigned long reset_value[NUM_COUNTERS]; #define IBS_OP_LOW_VALID_BIT (1ULL<<18) /* bit 18 */ #define IBS_OP_LOW_ENABLE (1ULL<<17) /* bit 17 */ -/* Codes used in cpu_buffer.c */ -/* This produces duplicate code, need to be fixed */ -#define IBS_FETCH_BEGIN (1UL << 4) -#define IBS_OP_BEGIN (1UL << 5) - /* * The function interface needs to be fixed, something like add * data. Should then be added to linux/oprofile.h. */ -extern void -oprofile_add_ibs_sample(struct pt_regs * const regs, - unsigned int * const ibs_sample, int ibs_code); - -struct ibs_fetch_sample { - /* MSRC001_1031 IBS Fetch Linear Address Register */ - unsigned int ibs_fetch_lin_addr_low; - unsigned int ibs_fetch_lin_addr_high; - /* MSRC001_1030 IBS Fetch Control Register */ - unsigned int ibs_fetch_ctl_low; - unsigned int ibs_fetch_ctl_high; - /* MSRC001_1032 IBS Fetch Physical Address Register */ - unsigned int ibs_fetch_phys_addr_low; - unsigned int ibs_fetch_phys_addr_high; -}; +extern +void oprofile_add_data(struct op_entry *entry, struct pt_regs * const regs, + unsigned long pc, int code, int size); -struct ibs_op_sample { - /* MSRC001_1034 IBS Op Logical Address Register (IbsRIP) */ - unsigned int ibs_op_rip_low; - unsigned int ibs_op_rip_high; - /* MSRC001_1035 IBS Op Data Register */ - unsigned int ibs_op_data1_low; - unsigned int ibs_op_data1_high; - /* MSRC001_1036 IBS Op Data 2 Register */ - unsigned int ibs_op_data2_low; - unsigned int ibs_op_data2_high; - /* MSRC001_1037 IBS Op Data 3 Register */ - unsigned int ibs_op_data3_low; - unsigned int ibs_op_data3_high; - /* MSRC001_1038 IBS DC Linear Address Register (IbsDcLinAd) */ - unsigned int ibs_dc_linear_low; - unsigned int ibs_dc_linear_high; - /* MSRC001_1039 IBS DC Physical Address Register (IbsDcPhysAd) */ - unsigned int ibs_dc_phys_low; - unsigned int ibs_dc_phys_high; -}; +#define IBS_FETCH_SIZE 6 +#define IBS_OP_SIZE 12 static int has_ibs; /* AMD Family10h and later */ @@ -197,9 +163,9 @@ static inline int op_amd_handle_ibs(struct pt_regs * const regs, struct op_msrs const * const msrs) { - unsigned int low, high; - struct ibs_fetch_sample ibs_fetch; - struct ibs_op_sample ibs_op; + u32 low, high; + u64 msr; + struct op_entry entry; if (!has_ibs) return 1; @@ -207,21 +173,19 @@ op_amd_handle_ibs(struct pt_regs * const regs, if (ibs_config.fetch_enabled) { rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); if (high & IBS_FETCH_HIGH_VALID_BIT) { - ibs_fetch.ibs_fetch_ctl_high = high; - ibs_fetch.ibs_fetch_ctl_low = low; - rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high); - ibs_fetch.ibs_fetch_lin_addr_high = high; - ibs_fetch.ibs_fetch_lin_addr_low = low; - rdmsr(MSR_AMD64_IBSFETCHPHYSAD, low, high); - ibs_fetch.ibs_fetch_phys_addr_high = high; - ibs_fetch.ibs_fetch_phys_addr_low = low; - - oprofile_add_ibs_sample(regs, - (unsigned int *)&ibs_fetch, - IBS_FETCH_BEGIN); + rdmsrl(MSR_AMD64_IBSFETCHLINAD, msr); + oprofile_add_data(&entry, regs, msr, IBS_FETCH_CODE, + IBS_FETCH_SIZE); + op_cpu_buffer_add_data(&entry, (u32)msr); + op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + op_cpu_buffer_add_data(&entry, low); + op_cpu_buffer_add_data(&entry, high); + rdmsrl(MSR_AMD64_IBSFETCHPHYSAD, msr); + op_cpu_buffer_add_data(&entry, (u32)msr); + op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + op_cpu_buffer_write_commit(&entry); /* reenable the IRQ */ - rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); high &= ~IBS_FETCH_HIGH_VALID_BIT; high |= IBS_FETCH_HIGH_ENABLE; low &= IBS_FETCH_LOW_MAX_CNT_MASK; @@ -232,30 +196,29 @@ op_amd_handle_ibs(struct pt_regs * const regs, if (ibs_config.op_enabled) { rdmsr(MSR_AMD64_IBSOPCTL, low, high); if (low & IBS_OP_LOW_VALID_BIT) { - rdmsr(MSR_AMD64_IBSOPRIP, low, high); - ibs_op.ibs_op_rip_low = low; - ibs_op.ibs_op_rip_high = high; - rdmsr(MSR_AMD64_IBSOPDATA, low, high); - ibs_op.ibs_op_data1_low = low; - ibs_op.ibs_op_data1_high = high; - rdmsr(MSR_AMD64_IBSOPDATA2, low, high); - ibs_op.ibs_op_data2_low = low; - ibs_op.ibs_op_data2_high = high; - rdmsr(MSR_AMD64_IBSOPDATA3, low, high); - ibs_op.ibs_op_data3_low = low; - ibs_op.ibs_op_data3_high = high; - rdmsr(MSR_AMD64_IBSDCLINAD, low, high); - ibs_op.ibs_dc_linear_low = low; - ibs_op.ibs_dc_linear_high = high; - rdmsr(MSR_AMD64_IBSDCPHYSAD, low, high); - ibs_op.ibs_dc_phys_low = low; - ibs_op.ibs_dc_phys_high = high; + rdmsrl(MSR_AMD64_IBSOPRIP, msr); + oprofile_add_data(&entry, regs, msr, IBS_OP_CODE, + IBS_OP_SIZE); + op_cpu_buffer_add_data(&entry, (u32)msr); + op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + rdmsrl(MSR_AMD64_IBSOPDATA, msr); + op_cpu_buffer_add_data(&entry, (u32)msr); + op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + rdmsrl(MSR_AMD64_IBSOPDATA2, msr); + op_cpu_buffer_add_data(&entry, (u32)msr); + op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + rdmsrl(MSR_AMD64_IBSOPDATA3, msr); + op_cpu_buffer_add_data(&entry, (u32)msr); + op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + rdmsrl(MSR_AMD64_IBSDCLINAD, msr); + op_cpu_buffer_add_data(&entry, (u32)msr); + op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + rdmsrl(MSR_AMD64_IBSDCPHYSAD, msr); + op_cpu_buffer_add_data(&entry, (u32)msr); + op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + op_cpu_buffer_write_commit(&entry); /* reenable the IRQ */ - oprofile_add_ibs_sample(regs, - (unsigned int *)&ibs_op, - IBS_OP_BEGIN); - rdmsr(MSR_AMD64_IBSOPCTL, low, high); high = 0; low &= ~IBS_OP_LOW_VALID_BIT; low |= IBS_OP_LOW_ENABLE; -- cgit v1.2.2 From 14f0ca8eaea42a5b5a69cfcb699665dd2618db5f Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 7 Jan 2009 21:50:22 +0100 Subject: oprofile: make new cpu buffer functions part of the api This patch creates the new functions oprofile_write_reserve() oprofile_add_data() oprofile_write_commit() and makes them part of the oprofile api. Signed-off-by: Robert Richter --- arch/x86/oprofile/op_model_amd.c | 57 +++++++++++++++++----------------------- 1 file changed, 24 insertions(+), 33 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index cf310aeb462c..8fdf06e4edf9 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -22,7 +22,6 @@ #include "op_x86_model.h" #include "op_counter.h" -#include "../../../drivers/oprofile/cpu_buffer.h" #define NUM_COUNTERS 4 #define NUM_CONTROLS 4 @@ -61,14 +60,6 @@ static unsigned long reset_value[NUM_COUNTERS]; #define IBS_OP_LOW_VALID_BIT (1ULL<<18) /* bit 18 */ #define IBS_OP_LOW_ENABLE (1ULL<<17) /* bit 17 */ -/* - * The function interface needs to be fixed, something like add - * data. Should then be added to linux/oprofile.h. - */ -extern -void oprofile_add_data(struct op_entry *entry, struct pt_regs * const regs, - unsigned long pc, int code, int size); - #define IBS_FETCH_SIZE 6 #define IBS_OP_SIZE 12 @@ -174,16 +165,16 @@ op_amd_handle_ibs(struct pt_regs * const regs, rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); if (high & IBS_FETCH_HIGH_VALID_BIT) { rdmsrl(MSR_AMD64_IBSFETCHLINAD, msr); - oprofile_add_data(&entry, regs, msr, IBS_FETCH_CODE, - IBS_FETCH_SIZE); - op_cpu_buffer_add_data(&entry, (u32)msr); - op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); - op_cpu_buffer_add_data(&entry, low); - op_cpu_buffer_add_data(&entry, high); + oprofile_write_reserve(&entry, regs, msr, + IBS_FETCH_CODE, IBS_FETCH_SIZE); + oprofile_add_data(&entry, (u32)msr); + oprofile_add_data(&entry, (u32)(msr >> 32)); + oprofile_add_data(&entry, low); + oprofile_add_data(&entry, high); rdmsrl(MSR_AMD64_IBSFETCHPHYSAD, msr); - op_cpu_buffer_add_data(&entry, (u32)msr); - op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); - op_cpu_buffer_write_commit(&entry); + oprofile_add_data(&entry, (u32)msr); + oprofile_add_data(&entry, (u32)(msr >> 32)); + oprofile_write_commit(&entry); /* reenable the IRQ */ high &= ~IBS_FETCH_HIGH_VALID_BIT; @@ -197,26 +188,26 @@ op_amd_handle_ibs(struct pt_regs * const regs, rdmsr(MSR_AMD64_IBSOPCTL, low, high); if (low & IBS_OP_LOW_VALID_BIT) { rdmsrl(MSR_AMD64_IBSOPRIP, msr); - oprofile_add_data(&entry, regs, msr, IBS_OP_CODE, - IBS_OP_SIZE); - op_cpu_buffer_add_data(&entry, (u32)msr); - op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + oprofile_write_reserve(&entry, regs, msr, + IBS_OP_CODE, IBS_OP_SIZE); + oprofile_add_data(&entry, (u32)msr); + oprofile_add_data(&entry, (u32)(msr >> 32)); rdmsrl(MSR_AMD64_IBSOPDATA, msr); - op_cpu_buffer_add_data(&entry, (u32)msr); - op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + oprofile_add_data(&entry, (u32)msr); + oprofile_add_data(&entry, (u32)(msr >> 32)); rdmsrl(MSR_AMD64_IBSOPDATA2, msr); - op_cpu_buffer_add_data(&entry, (u32)msr); - op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + oprofile_add_data(&entry, (u32)msr); + oprofile_add_data(&entry, (u32)(msr >> 32)); rdmsrl(MSR_AMD64_IBSOPDATA3, msr); - op_cpu_buffer_add_data(&entry, (u32)msr); - op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + oprofile_add_data(&entry, (u32)msr); + oprofile_add_data(&entry, (u32)(msr >> 32)); rdmsrl(MSR_AMD64_IBSDCLINAD, msr); - op_cpu_buffer_add_data(&entry, (u32)msr); - op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); + oprofile_add_data(&entry, (u32)msr); + oprofile_add_data(&entry, (u32)(msr >> 32)); rdmsrl(MSR_AMD64_IBSDCPHYSAD, msr); - op_cpu_buffer_add_data(&entry, (u32)msr); - op_cpu_buffer_add_data(&entry, (u32)(msr >> 32)); - op_cpu_buffer_write_commit(&entry); + oprofile_add_data(&entry, (u32)msr); + oprofile_add_data(&entry, (u32)(msr >> 32)); + oprofile_write_commit(&entry); /* reenable the IRQ */ high = 0; -- cgit v1.2.2 From 9b4778f680aa79d838ae2be6ab958938f744ce5f Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Wed, 7 Jan 2009 14:42:41 -0800 Subject: trivial: replace last usages of __FUNCTION__ in kernel __FUNCTION__ is gcc-specific, use __func__ Signed-off-by: Harvey Harrison Acked-by: Mauro Carvalho Chehab Signed-off-by: Linus Torvalds --- arch/x86/mm/numa_32.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 8518c678d83f..d1f7439d173c 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -239,7 +239,7 @@ void resume_map_numa_kva(pgd_t *pgd_base) start_pfn = node_remap_start_pfn[node]; size = node_remap_size[node]; - printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node); + printk(KERN_DEBUG "%s: node %d\n", __func__, node); for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) { unsigned long vaddr = start_va + (pfn << PAGE_SHIFT); @@ -251,7 +251,7 @@ void resume_map_numa_kva(pgd_t *pgd_base) PAGE_KERNEL_LARGE_EXEC)); printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n", - __FUNCTION__, vaddr, start_pfn + pfn); + __func__, vaddr, start_pfn + pfn); } } } -- cgit v1.2.2 From c19a28e1193a6c854738d609ae9b2fe2f6e6bea4 Mon Sep 17 00:00:00 2001 From: Fernando Carrijo Date: Wed, 7 Jan 2009 18:09:08 -0800 Subject: remove lots of double-semicolons Cc: Ingo Molnar Cc: Thomas Gleixner Acked-by: Theodore Ts'o Acked-by: Mark Fasheh Acked-by: David S. Miller Cc: James Morris Acked-by: Casey Schaufler Acked-by: Takashi Iwai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/cpu/cpufreq/longhaul.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c index b0461856acfb..a4cff5d6e380 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.c +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c @@ -982,7 +982,7 @@ static int __init longhaul_init(void) case 10: printk(KERN_ERR PFX "Use acpi-cpufreq driver for VIA C7\n"); default: - ;; + ; } return -ENODEV; -- cgit v1.2.2 From 13b40a1a065824d2d4e55c8b48ea9f3f9d162929 Mon Sep 17 00:00:00 2001 From: Zhao Yakui Date: Sun, 4 Jan 2009 12:04:21 +0800 Subject: ACPI: Avoid array address overflow when _CST MWAIT hint bits are set The Cx Register address obtained from the _CST object is used as the MWAIT hints if the register type is FFixedHW. And it is used to check whether the Cx type is supported or not. On some boxes the following Cx state package is obtained from _CST object: >{ ResourceTemplate () { Register (FFixedHW, 0x01, // Bit Width 0x02, // Bit Offset 0x0000000000889759, // Address 0x03, // Access Size ) }, 0x03, 0xF5, 0x015E } In such case we should use the bit[7:4] of Cx address to check whether the Cx type is supported or not. mask the MWAIT hint to avoid array address overflow Signed-off-by: Zhao Yakui Acked-by:Venki Pallipadi Signed-off-by: Len Brown --- arch/x86/kernel/acpi/cstate.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index c2502eb9aa83..a4805b3b4095 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -56,6 +56,7 @@ static struct cstate_entry *cpu_cstate_entry; /* per CPU ptr */ static short mwait_supported[ACPI_PROCESSOR_MAX_POWER]; #define MWAIT_SUBSTATE_MASK (0xf) +#define MWAIT_CSTATE_MASK (0xf) #define MWAIT_SUBSTATE_SIZE (4) #define CPUID_MWAIT_LEAF (5) @@ -98,7 +99,8 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); /* Check whether this particular cx_type (in CST) is supported or not */ - cstate_type = (cx->address >> MWAIT_SUBSTATE_SIZE) + 1; + cstate_type = ((cx->address >> MWAIT_SUBSTATE_SIZE) & + MWAIT_CSTATE_MASK) + 1; edx_part = edx >> (cstate_type * MWAIT_SUBSTATE_SIZE); num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK; -- cgit v1.2.2 From 237889bf0a62f1399fb2ba0c2a259e6a96597131 Mon Sep 17 00:00:00 2001 From: Zhao Yakui Date: Wed, 17 Dec 2008 16:55:18 +0800 Subject: ACPI : Use RSDT instead of XSDT by adding boot option of "acpi=rsdt" On some boxes there exist both RSDT and XSDT table. But unfortunately sometimes there exists the following error when XSDT table is used: a. 32/64X address mismatch b. The 32/64X FACS address mismatch In such case the boot option of "acpi=rsdt" is provided so that RSDT is tried instead of XSDT table when the system can't work well. http://bugzilla.kernel.org/show_bug.cgi?id=8246 Signed-off-by: Zhao Yakui cc:Thomas Renninger Signed-off-by: Len Brown --- arch/x86/kernel/acpi/boot.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4c51a2f8fd31..db1a90a76b3e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -47,7 +47,7 @@ #endif static int __initdata acpi_force = 0; - +u32 acpi_rsdt_forced; #ifdef CONFIG_ACPI int acpi_disabled = 0; #else @@ -1783,6 +1783,10 @@ static int __init parse_acpi(char *arg) disable_acpi(); acpi_ht = 1; } + /* acpi=rsdt use RSDT instead of XSDT */ + else if (strcmp(arg, "rsdt") == 0) { + acpi_rsdt_forced = 1; + } /* "acpi=noirq" disables ACPI interrupt routing */ else if (strcmp(arg, "noirq") == 0) { acpi_noirq_set(); -- cgit v1.2.2 From 8659c406ade32f47da2c95889094801921d6330a Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 9 Jan 2009 12:17:39 -0800 Subject: x86: only scan the root bus in early PCI quirks We found a situation on Linus' machine that the Nvidia timer quirk hit on a Intel chipset system. The problem is that the system has a fancy Nvidia card with an own PCI bridge, and the early-quirks code looking for any NVidia bridge triggered on it incorrectly. This didn't lead a boot failure by luck, but the timer routing code selecting the wrong timer first and some ugly messages. It might lead to real problems on other systems. I checked all the devices which are currently checked for by early_quirks and it turns out they are all located in the root bus zero. So change the early-quirks loop to only scan bus 0. This incidently also saves quite some unnecessary scanning work, because early_quirks doesn't go through all the non root busses. The graphics card is not on bus 0, so it is not matched anymore. Signed-off-by: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Jesse Barnes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/early-quirks.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 744aa7fc49d5..76b8cd953dee 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -201,6 +201,12 @@ struct chipset { void (*f)(int num, int slot, int func); }; +/* + * Only works for devices on the root bus. If you add any devices + * not on bus 0 readd another loop level in early_quirks(). But + * be careful because at least the Nvidia quirk here relies on + * only matching on bus 0. + */ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs }, @@ -267,17 +273,17 @@ static int __init check_dev_quirk(int num, int slot, int func) void __init early_quirks(void) { - int num, slot, func; + int slot, func; if (!early_pci_allowed()) return; /* Poor man's PCI discovery */ - for (num = 0; num < 32; num++) - for (slot = 0; slot < 32; slot++) - for (func = 0; func < 8; func++) { - /* Only probe function 0 on single fn devices */ - if (check_dev_quirk(num, slot, func)) - break; - } + /* Only scan the root bus */ + for (slot = 0; slot < 32; slot++) + for (func = 0; func < 8; func++) { + /* Only probe function 0 on single fn devices */ + if (check_dev_quirk(0, slot, func)) + break; + } } -- cgit v1.2.2 From c4295fbb6048d85f0b41c5ced5cbf63f6811c46c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 9 Jan 2009 12:49:50 -0800 Subject: x86: make 'constant_test_bit()' take an unsigned bit number Ingo noticed that using signed arithmetic seems to confuse the gcc inliner, and make it potentially decide that it's all too complicated. (Yeah, yeah, it's a constant. It's always positive. Still..) Based-on: Ingo Molnar Signed-off-by: Linus Torvalds --- arch/x86/include/asm/bitops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 9fa9dcdf344b..e02a359d2aa5 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -300,7 +300,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr) return oldbit; } -static inline int constant_test_bit(int nr, const volatile unsigned long *addr) +static inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr) { return ((1UL << (nr % BITS_PER_LONG)) & (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0; -- cgit v1.2.2