diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2009-09-25 11:47:26 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2009-09-25 11:47:26 +1000 |
commit | 3bfb1f1f68b19b4ef1e06f568fb2c449949a14fe (patch) | |
tree | 83e5af22742400c9765dcc707a584d598a935aee | |
parent | b7a7f4d29ce4038d76db8163b805192755c3b4d8 (diff) | |
parent | 0320071d4e5bbc5700734457152e2e510b58b77c (diff) |
Merge remote branch 'tip/auto-latest'
-rw-r--r-- | arch/x86/Kconfig | 5 | ||||
-rw-r--r-- | arch/x86/boot/compressed/head_32.S | 3 | ||||
-rw-r--r-- | arch/x86/boot/compressed/head_64.S | 3 | ||||
-rw-r--r-- | arch/x86/boot/compressed/vmlinux.lds.S | 6 | ||||
-rw-r--r-- | arch/x86/include/asm/hpet.h | 7 | ||||
-rw-r--r-- | arch/x86/include/asm/msr.h | 4 | ||||
-rw-r--r-- | arch/x86/kernel/acpi/boot.c | 1 | ||||
-rw-r--r-- | arch/x86/kernel/apic/io_apic.c | 49 | ||||
-rw-r--r-- | arch/x86/kernel/head_32.S | 2 | ||||
-rw-r--r-- | arch/x86/kernel/head_64.S | 2 | ||||
-rw-r--r-- | arch/x86/kernel/hpet.c | 60 | ||||
-rw-r--r-- | arch/x86/kernel/traps.c | 6 | ||||
-rw-r--r-- | arch/x86/kernel/tsc.c | 8 | ||||
-rw-r--r-- | arch/x86/kernel/vmlinux.lds.S | 79 | ||||
-rw-r--r-- | arch/x86/lib/msr.c | 46 | ||||
-rw-r--r-- | drivers/pci/intr_remapping.c | 89 | ||||
-rw-r--r-- | drivers/pci/intr_remapping.h | 7 | ||||
-rw-r--r-- | fs/proc/array.c | 11 | ||||
-rw-r--r-- | include/linux/clocksource.h | 1 | ||||
-rw-r--r-- | include/linux/dmar.h | 10 | ||||
-rw-r--r-- | include/linux/hpet.h | 2 | ||||
-rw-r--r-- | include/linux/poison.h | 16 | ||||
-rw-r--r-- | include/linux/timex.h | 5 | ||||
-rw-r--r-- | kernel/cpuset.c | 8 | ||||
-rw-r--r-- | kernel/hrtimer.c | 53 | ||||
-rw-r--r-- | kernel/irq/manage.c | 2 |
26 files changed, 305 insertions, 180 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 93698794aa3a..45a9921695a9 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1226,6 +1226,11 @@ config ARCH_MEMORY_PROBE def_bool X86_64 depends on MEMORY_HOTPLUG +config ILLEGAL_POINTER_VALUE + hex + default 0 if X86_32 + default 0xdead000000000000 if X86_64 + source "mm/Kconfig" config HIGHPTE diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 75e4f001e706..f543b70ffae2 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -23,13 +23,14 @@ */ .text +#include <linux/init.h> #include <linux/linkage.h> #include <asm/segment.h> #include <asm/page_types.h> #include <asm/boot.h> #include <asm/asm-offsets.h> - .section ".text.head","ax",@progbits + __HEAD ENTRY(startup_32) cld /* diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index f62c284db9eb..077e1b69198e 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -24,6 +24,7 @@ .code32 .text +#include <linux/init.h> #include <linux/linkage.h> #include <asm/segment.h> #include <asm/pgtable_types.h> @@ -33,7 +34,7 @@ #include <asm/processor-flags.h> #include <asm/asm-offsets.h> - .section ".text.head" + __HEAD .code32 ENTRY(startup_32) cld diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index cc353e1b3ffd..f4193bb48782 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -1,3 +1,5 @@ +#include <asm-generic/vmlinux.lds.h> + OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT) #undef i386 @@ -18,9 +20,9 @@ SECTIONS * address 0. */ . = 0; - .text.head : { + .head.text : { _head = . ; - *(.text.head) + HEAD_TEXT _ehead = . ; } .rodata.compressed : { diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 1c22cb05ad6a..5d89fd2a3690 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -65,11 +65,12 @@ /* hpet memory map physical address */ extern unsigned long hpet_address; extern unsigned long force_hpet_address; +extern u8 hpet_blockid; extern int hpet_force_user; extern int is_hpet_enabled(void); extern int hpet_enable(void); extern void hpet_disable(void); -extern unsigned long hpet_readl(unsigned long a); +extern unsigned int hpet_readl(unsigned int a); extern void force_hpet_resume(void); extern void hpet_msi_unmask(unsigned int irq); @@ -78,9 +79,9 @@ extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg); extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg); #ifdef CONFIG_PCI_MSI -extern int arch_setup_hpet_msi(unsigned int irq); +extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id); #else -static inline int arch_setup_hpet_msi(unsigned int irq) +static inline int arch_setup_hpet_msi(unsigned int irq, unsigned int id) { return -EINVAL; } diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 7e2b6ba962ff..9a00219b331a 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -247,8 +247,8 @@ do { \ #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); -void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs); -void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs); +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 67e929b89875..87eee07da21f 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -624,6 +624,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) } hpet_address = hpet_tbl->address.address; + hpet_blockid = hpet_tbl->sequence; /* * Some broken BIOSes advertise HPET at 0x0. We really do not diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index dc69f28489f5..6027b5cf7d6a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3211,7 +3211,8 @@ void destroy_irq(unsigned int irq) * MSI message composition */ #ifdef CONFIG_PCI_MSI -static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg) +static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, + struct msi_msg *msg, u8 hpet_id) { struct irq_cfg *cfg; int err; @@ -3245,7 +3246,10 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms irte.dest_id = IRTE_DEST(dest); /* Set source-id of interrupt request */ - set_msi_sid(&irte, pdev); + if (pdev) + set_msi_sid(&irte, pdev); + else + set_hpet_sid(&irte, hpet_id); modify_irte(irq, &irte); @@ -3410,7 +3414,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) int ret; struct msi_msg msg; - ret = msi_compose_msg(dev, irq, &msg); + ret = msi_compose_msg(dev, irq, &msg, -1); if (ret < 0) return ret; @@ -3543,7 +3547,7 @@ int arch_setup_dmar_msi(unsigned int irq) int ret; struct msi_msg msg; - ret = msi_compose_msg(NULL, irq, &msg); + ret = msi_compose_msg(NULL, irq, &msg, -1); if (ret < 0) return ret; dmar_msi_write(irq, &msg); @@ -3583,6 +3587,19 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask) #endif /* CONFIG_SMP */ +static struct irq_chip ir_hpet_msi_type = { + .name = "IR-HPET_MSI", + .unmask = hpet_msi_unmask, + .mask = hpet_msi_mask, +#ifdef CONFIG_INTR_REMAP + .ack = ir_ack_apic_edge, +#ifdef CONFIG_SMP + .set_affinity = ir_set_msi_irq_affinity, +#endif +#endif + .retrigger = ioapic_retrigger_irq, +}; + static struct irq_chip hpet_msi_type = { .name = "HPET_MSI", .unmask = hpet_msi_unmask, @@ -3594,20 +3611,36 @@ static struct irq_chip hpet_msi_type = { .retrigger = ioapic_retrigger_irq, }; -int arch_setup_hpet_msi(unsigned int irq) +int arch_setup_hpet_msi(unsigned int irq, unsigned int id) { int ret; struct msi_msg msg; struct irq_desc *desc = irq_to_desc(irq); - ret = msi_compose_msg(NULL, irq, &msg); + if (intr_remapping_enabled) { + struct intel_iommu *iommu = map_hpet_to_ir(id); + int index; + + if (!iommu) + return -1; + + index = alloc_irte(iommu, irq, 1); + if (index < 0) + return -1; + } + + ret = msi_compose_msg(NULL, irq, &msg, id); if (ret < 0) return ret; hpet_msi_write(irq, &msg); desc->status |= IRQ_MOVE_PCNTXT; - set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq, - "edge"); + if (irq_remapped(irq)) + set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type, + handle_edge_irq, "edge"); + else + set_irq_chip_and_handler_name(irq, &hpet_msi_type, + handle_edge_irq, "edge"); return 0; } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 218aad7ee76e..050c278481b1 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -79,7 +79,7 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE) * any particular GDT layout, because we load our own as soon as we * can. */ -.section .text.head,"ax",@progbits +__HEAD ENTRY(startup_32) /* test KEEP_SEGMENTS flag to see if the bootloader is asking us to not reload segments */ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index d0bc0a13a437..780cd928fcd5 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -40,7 +40,7 @@ L4_START_KERNEL = pgd_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) .text - .section .text.head + __HEAD .code64 .globl startup_64 startup_64: diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dedc2bddf7a5..7f024ff47d1d 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -33,6 +33,7 @@ * HPET address is set in acpi/boot.c, when an ACPI entry exists */ unsigned long hpet_address; +u8 hpet_blockid; /* OS timer block num */ #ifdef CONFIG_PCI_MSI static unsigned long hpet_num_timers; #endif @@ -47,12 +48,12 @@ struct hpet_dev { char name[10]; }; -unsigned long hpet_readl(unsigned long a) +inline unsigned int hpet_readl(unsigned int a) { return readl(hpet_virt_address + a); } -static inline void hpet_writel(unsigned long d, unsigned long a) +static inline void hpet_writel(unsigned int d, unsigned int a) { writel(d, hpet_virt_address + a); } @@ -167,7 +168,7 @@ do { \ static void hpet_reserve_msi_timers(struct hpet_data *hd); -static void hpet_reserve_platform_timers(unsigned long id) +static void hpet_reserve_platform_timers(unsigned int id) { struct hpet __iomem *hpet = hpet_virt_address; struct hpet_timer __iomem *timer = &hpet->hpet_timers[2]; @@ -205,7 +206,7 @@ static void hpet_reserve_platform_timers(unsigned long id) } #else -static void hpet_reserve_platform_timers(unsigned long id) { } +static void hpet_reserve_platform_timers(unsigned int id) { } #endif /* @@ -246,7 +247,7 @@ static void hpet_reset_counter(void) static void hpet_start_counter(void) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); } @@ -271,7 +272,7 @@ static void hpet_resume_counter(void) static void hpet_enable_legacy_int(void) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_LEGACY; hpet_writel(cfg, HPET_CFG); @@ -314,7 +315,7 @@ static int hpet_setup_msi_irq(unsigned int irq); static void hpet_set_mode(enum clock_event_mode mode, struct clock_event_device *evt, int timer) { - unsigned long cfg, cmp, now; + unsigned int cfg, cmp, now; uint64_t delta; switch (mode) { @@ -323,7 +324,7 @@ static void hpet_set_mode(enum clock_event_mode mode, delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult; delta >>= evt->shift; now = hpet_readl(HPET_COUNTER); - cmp = now + (unsigned long) delta; + cmp = now + (unsigned int) delta; cfg = hpet_readl(HPET_Tn_CFG(timer)); /* Make sure we use edge triggered interrupts */ cfg &= ~HPET_TN_LEVEL; @@ -339,7 +340,7 @@ static void hpet_set_mode(enum clock_event_mode mode, * (See AMD-8111 HyperTransport I/O Hub Data Sheet, * Publication # 24674) */ - hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer)); + hpet_writel((unsigned int) delta, HPET_Tn_CMP(timer)); hpet_start_counter(); hpet_print_config(); break; @@ -387,9 +388,9 @@ static int hpet_next_event(unsigned long delta, * what we wrote hit the chip before we compare it to the * counter. */ - WARN_ON_ONCE((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt); + WARN_ON_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt); - return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; + return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; } static void hpet_legacy_set_mode(enum clock_event_mode mode, @@ -415,7 +416,7 @@ static struct hpet_dev *hpet_devs; void hpet_msi_unmask(unsigned int irq) { struct hpet_dev *hdev = get_irq_data(irq); - unsigned long cfg; + unsigned int cfg; /* unmask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); @@ -425,7 +426,7 @@ void hpet_msi_unmask(unsigned int irq) void hpet_msi_mask(unsigned int irq) { - unsigned long cfg; + unsigned int cfg; struct hpet_dev *hdev = get_irq_data(irq); /* mask it */ @@ -467,7 +468,7 @@ static int hpet_msi_next_event(unsigned long delta, static int hpet_setup_msi_irq(unsigned int irq) { - if (arch_setup_hpet_msi(irq)) { + if (arch_setup_hpet_msi(irq, hpet_blockid)) { destroy_irq(irq); return -EINVAL; } @@ -584,6 +585,8 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) unsigned int num_timers_used = 0; int i; + if (boot_cpu_has(X86_FEATURE_ARAT)) + return; id = hpet_readl(HPET_ID); num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT); @@ -598,7 +601,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) for (i = start_timer; i < num_timers - RESERVE_TIMERS; i++) { struct hpet_dev *hdev = &hpet_devs[num_timers_used]; - unsigned long cfg = hpet_readl(HPET_Tn_CFG(i)); + unsigned int cfg = hpet_readl(HPET_Tn_CFG(i)); /* Only consider HPET timer with MSI support */ if (!(cfg & HPET_TN_FSB_CAP)) @@ -813,7 +816,7 @@ static int hpet_clocksource_register(void) */ int __init hpet_enable(void) { - unsigned long id; + unsigned int id; int i; if (!is_hpet_capable()) @@ -872,10 +875,8 @@ int __init hpet_enable(void) if (id & HPET_ID_LEGSUP) { hpet_legacy_clockevent_register(); - hpet_msi_capability_lookup(2); return 1; } - hpet_msi_capability_lookup(0); return 0; out_nohpet: @@ -908,9 +909,17 @@ static __init int hpet_late_init(void) if (!hpet_virt_address) return -ENODEV; + if (hpet_readl(HPET_ID) & HPET_ID_LEGSUP) + hpet_msi_capability_lookup(2); + else + hpet_msi_capability_lookup(0); + hpet_reserve_platform_timers(hpet_readl(HPET_ID)); hpet_print_config(); + if (boot_cpu_has(X86_FEATURE_ARAT)) + return 0; + for_each_online_cpu(cpu) { hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu); } @@ -925,7 +934,7 @@ fs_initcall(hpet_late_init); void hpet_disable(void) { if (is_hpet_capable()) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); if (hpet_legacy_int_enabled) { cfg &= ~HPET_CFG_LEGACY; @@ -965,8 +974,8 @@ static int hpet_prev_update_sec; static struct rtc_time hpet_alarm_time; static unsigned long hpet_pie_count; static u32 hpet_t1_cmp; -static unsigned long hpet_default_delta; -static unsigned long hpet_pie_delta; +static u32 hpet_default_delta; +static u32 hpet_pie_delta; static unsigned long hpet_pie_limit; static rtc_irq_handler irq_handler; @@ -1017,7 +1026,8 @@ EXPORT_SYMBOL_GPL(hpet_unregister_irq_handler); */ int hpet_rtc_timer_init(void) { - unsigned long cfg, cnt, delta, flags; + unsigned int cfg, cnt, delta; + unsigned long flags; if (!is_hpet_enabled()) return 0; @@ -1027,7 +1037,7 @@ int hpet_rtc_timer_init(void) clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC; clc >>= hpet_clockevent.shift + DEFAULT_RTC_SHIFT; - hpet_default_delta = (unsigned long) clc; + hpet_default_delta = clc; } if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit) @@ -1113,7 +1123,7 @@ int hpet_set_periodic_freq(unsigned long freq) clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC; do_div(clc, freq); clc >>= hpet_clockevent.shift; - hpet_pie_delta = (unsigned long) clc; + hpet_pie_delta = clc; } return 1; } @@ -1127,7 +1137,7 @@ EXPORT_SYMBOL_GPL(hpet_rtc_dropped_irq); static void hpet_rtc_timer_reinit(void) { - unsigned long cfg, delta; + unsigned int cfg, delta; int lost_ints = -1; if (unlikely(!hpet_rtc_flags)) { diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index a665c71352b8..7e37dcee0cc3 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -72,11 +72,9 @@ char ignore_fpu_irq; /* * The IDT has to be page-aligned to simplify the Pentium - * F0 0F bug workaround.. We have a special link segment - * for this. + * F0 0F bug workaround. */ -gate_desc idt_table[NR_VECTORS] - __attribute__((__section__(".data.idt"))) = { { { { 0, 0 } } }, }; +gate_desc idt_table[NR_VECTORS] __page_aligned_data = { { { { 0, 0 } } }, }; #endif DECLARE_BITMAP(used_vectors, NR_VECTORS); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cd982f48e23e..f67bfaa1adc2 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -763,14 +763,12 @@ void mark_tsc_unstable(char *reason) { if (!tsc_unstable) { tsc_unstable = 1; - printk(KERN_INFO "Marking TSC unstable due to %s\n", reason); + printk("Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ if (clocksource_tsc.mult) - clocksource_mark_unstable(&clocksource_tsc); - else { - clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; + clocksource_change_rating(&clocksource_tsc, 0); + else clocksource_tsc.rating = 0; - } } } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index a46acccec38a..92929fb3f9fa 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -65,17 +65,11 @@ SECTIONS #endif /* Text and read-only data */ - - /* bootstrapping code */ - .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) { - _text = .; - *(.text.head) - } :text = 0x9090 - - /* The rest of the text */ .text : AT(ADDR(.text) - LOAD_OFFSET) { + _text = .; + /* bootstrapping code */ + HEAD_TEXT #ifdef CONFIG_X86_32 - /* not really needed, already page aligned */ . = ALIGN(PAGE_SIZE); *(.text.page_aligned) #endif @@ -94,13 +88,7 @@ SECTIONS NOTES :text :note - /* Exception table */ - . = ALIGN(16); - __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { - __start___ex_table = .; - *(__ex_table) - __stop___ex_table = .; - } :text = 0x9090 + EXCEPTION_TABLE(16) :text = 0x9090 RO_DATA(PAGE_SIZE) @@ -118,7 +106,6 @@ SECTIONS #endif PAGE_ALIGNED_DATA(PAGE_SIZE) - *(.data.idt) CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES) @@ -135,24 +122,21 @@ SECTIONS #ifdef CONFIG_X86_64 #define VSYSCALL_ADDR (-10*1024*1024) -#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data) + SIZEOF(.data) + \ - PAGE_SIZE - 1) & ~(PAGE_SIZE - 1)) -#define VSYSCALL_VIRT_ADDR ((ADDR(.data) + SIZEOF(.data) + \ - PAGE_SIZE - 1) & ~(PAGE_SIZE - 1)) -#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR) +#define VLOAD_OFFSET (VSYSCALL_ADDR - __vsyscall_0 + LOAD_OFFSET) #define VLOAD(x) (ADDR(x) - VLOAD_OFFSET) -#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR) +#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0) #define VVIRT(x) (ADDR(x) - VVIRT_OFFSET) + . = ALIGN(4096); + __vsyscall_0 = .; + . = VSYSCALL_ADDR; - .vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) { + .vsyscall_0 : AT(VLOAD(.vsyscall_0)) { *(.vsyscall_0) } :user - __vsyscall_0 = VSYSCALL_VIRT_ADDR; - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) @@ -192,11 +176,9 @@ SECTIONS *(.vsyscall_3) } - . = VSYSCALL_VIRT_ADDR + PAGE_SIZE; + . = __vsyscall_0 + PAGE_SIZE; #undef VSYSCALL_ADDR -#undef VSYSCALL_PHYS_ADDR -#undef VSYSCALL_VIRT_ADDR #undef VLOAD_OFFSET #undef VLOAD #undef VVIRT_OFFSET @@ -219,36 +201,12 @@ SECTIONS PERCPU_VADDR(0, :percpu) #endif - .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { - _sinittext = .; - INIT_TEXT - _einittext = .; - } + INIT_TEXT_SECTION(PAGE_SIZE) #ifdef CONFIG_X86_64 :init #endif - .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) { - INIT_DATA - } - - . = ALIGN(16); - .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) { - __setup_start = .; - *(.init.setup) - __setup_end = .; - } - .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) { - __initcall_start = .; - INITCALLS - __initcall_end = .; - } - - .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) { - __con_initcall_start = .; - *(.con_initcall.init) - __con_initcall_end = .; - } + INIT_DATA_SECTION(16) .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) { __x86_cpu_dev_start = .; @@ -256,8 +214,6 @@ SECTIONS __x86_cpu_dev_end = .; } - SECURITY_INIT - . = ALIGN(8); .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) { __parainstructions = .; @@ -288,15 +244,6 @@ SECTIONS EXIT_DATA } -#ifdef CONFIG_BLK_DEV_INITRD - . = ALIGN(PAGE_SIZE); - .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { - __initramfs_start = .; - *(.init.ramfs) - __initramfs_end = .; - } -#endif - #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP) PERCPU(PAGE_SIZE) #endif diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 33a1e3ca22d8..41628b104b9e 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -71,14 +71,9 @@ int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) } EXPORT_SYMBOL(wrmsr_on_cpu); -/* rdmsr on a bunch of CPUs - * - * @mask: which CPUs - * @msr_no: which MSR - * @msrs: array of MSR values - * - */ -void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) +static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, + struct msr *msrs, + void (*msr_func) (void *info)) { struct msr_info rv; int this_cpu; @@ -92,11 +87,23 @@ void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) this_cpu = get_cpu(); if (cpumask_test_cpu(this_cpu, mask)) - __rdmsr_on_cpu(&rv); + msr_func(&rv); - smp_call_function_many(mask, __rdmsr_on_cpu, &rv, 1); + smp_call_function_many(mask, msr_func, &rv, 1); put_cpu(); } + +/* rdmsr on a bunch of CPUs + * + * @mask: which CPUs + * @msr_no: which MSR + * @msrs: array of MSR values + * + */ +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) +{ + __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu); +} EXPORT_SYMBOL(rdmsr_on_cpus); /* @@ -107,24 +114,9 @@ EXPORT_SYMBOL(rdmsr_on_cpus); * @msrs: array of MSR values * */ -void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) { - struct msr_info rv; - int this_cpu; - - memset(&rv, 0, sizeof(rv)); - - rv.off = cpumask_first(mask); - rv.msrs = msrs; - rv.msr_no = msr_no; - - this_cpu = get_cpu(); - - if (cpumask_test_cpu(this_cpu, mask)) - __wrmsr_on_cpu(&rv); - - smp_call_function_many(mask, __wrmsr_on_cpu, &rv, 1); - put_cpu(); + __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu); } EXPORT_SYMBOL(wrmsr_on_cpus); diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c index 0ed78a764ded..3b3658669bee 100644 --- a/drivers/pci/intr_remapping.c +++ b/drivers/pci/intr_remapping.c @@ -2,6 +2,7 @@ #include <linux/dmar.h> #include <linux/spinlock.h> #include <linux/jiffies.h> +#include <linux/hpet.h> #include <linux/pci.h> #include <linux/irq.h> #include <asm/io_apic.h> @@ -14,7 +15,8 @@ #include "pci.h" static struct ioapic_scope ir_ioapic[MAX_IO_APICS]; -static int ir_ioapic_num; +static struct hpet_scope ir_hpet[MAX_HPET_TBS]; +static int ir_ioapic_num, ir_hpet_num; int intr_remapping_enabled; static int disable_intremap; @@ -343,6 +345,16 @@ int flush_irte(int irq) return rc; } +struct intel_iommu *map_hpet_to_ir(u8 hpet_id) +{ + int i; + + for (i = 0; i < MAX_HPET_TBS; i++) + if (ir_hpet[i].id == hpet_id) + return ir_hpet[i].iommu; + return NULL; +} + struct intel_iommu *map_ioapic_to_ir(int apic) { int i; @@ -470,6 +482,36 @@ int set_ioapic_sid(struct irte *irte, int apic) return 0; } +int set_hpet_sid(struct irte *irte, u8 id) +{ + int i; + u16 sid = 0; + + if (!irte) + return -1; + + for (i = 0; i < MAX_HPET_TBS; i++) { + if (ir_hpet[i].id == id) { + sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn; + break; + } + } + + if (sid == 0) { + pr_warning("Failed to set source-id of HPET block (%d)\n", id); + return -1; + } + + /* + * Should really use SQ_ALL_16. Some platforms are broken. + * While we figure out the right quirks for these broken platforms, use + * SQ_13_IGNORE_3 for now. + */ + set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_13_IGNORE_3, sid); + + return 0; +} + int set_msi_sid(struct irte *irte, struct pci_dev *dev) { struct pci_dev *bridge; @@ -711,6 +753,34 @@ error: return -1; } +static void ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope, + struct intel_iommu *iommu) +{ + struct acpi_dmar_pci_path *path; + u8 bus; + int count; + + bus = scope->bus; + path = (struct acpi_dmar_pci_path *)(scope + 1); + count = (scope->length - sizeof(struct acpi_dmar_device_scope)) + / sizeof(struct acpi_dmar_pci_path); + + while (--count > 0) { + /* + * Access PCI directly due to the PCI + * subsystem isn't initialized yet. + */ + bus = read_pci_config_byte(bus, path->dev, path->fn, + PCI_SECONDARY_BUS); + path++; + } + ir_hpet[ir_hpet_num].bus = bus; + ir_hpet[ir_hpet_num].devfn = PCI_DEVFN(path->dev, path->fn); + ir_hpet[ir_hpet_num].iommu = iommu; + ir_hpet[ir_hpet_num].id = scope->enumeration_id; + ir_hpet_num++; +} + static void ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope, struct intel_iommu *iommu) { @@ -740,8 +810,8 @@ static void ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope, ir_ioapic_num++; } -static int ir_parse_ioapic_scope(struct acpi_dmar_header *header, - struct intel_iommu *iommu) +static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header, + struct intel_iommu *iommu) { struct acpi_dmar_hardware_unit *drhd; struct acpi_dmar_device_scope *scope; @@ -765,6 +835,17 @@ static int ir_parse_ioapic_scope(struct acpi_dmar_header *header, drhd->address); ir_parse_one_ioapic_scope(scope, iommu); + } else if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_HPET) { + if (ir_hpet_num == MAX_HPET_TBS) { + printk(KERN_WARNING "Exceeded Max HPET blocks\n"); + return -1; + } + + printk(KERN_INFO "HPET id %d under DRHD base" + " 0x%Lx\n", scope->enumeration_id, + drhd->address); + + ir_parse_one_hpet_scope(scope, iommu); } start += scope->length; } @@ -785,7 +866,7 @@ int __init parse_ioapics_under_ir(void) struct intel_iommu *iommu = drhd->iommu; if (ecap_ir_support(iommu->ecap)) { - if (ir_parse_ioapic_scope(drhd->hdr, iommu)) + if (ir_parse_ioapic_hpet_scope(drhd->hdr, iommu)) return -1; ir_supported = 1; diff --git a/drivers/pci/intr_remapping.h b/drivers/pci/intr_remapping.h index 63a263c18415..5662fecfee60 100644 --- a/drivers/pci/intr_remapping.h +++ b/drivers/pci/intr_remapping.h @@ -7,4 +7,11 @@ struct ioapic_scope { unsigned int devfn; /* PCI devfn number */ }; +struct hpet_scope { + struct intel_iommu *iommu; + u8 id; + unsigned int bus; + unsigned int devfn; +}; + #define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0) diff --git a/fs/proc/array.c b/fs/proc/array.c index 0c6bc602e6c4..bd9127f5bcf0 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -403,6 +403,16 @@ static inline void task_show_stack_usage(struct seq_file *m, } } +static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) +{ + seq_printf(m, "Cpus_allowed:\t"); + seq_cpumask(m, &task->cpus_allowed); + seq_printf(m, "\n"); + seq_printf(m, "Cpus_allowed_list:\t"); + seq_cpumask_list(m, &task->cpus_allowed); + seq_printf(m, "\n"); +} + int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { @@ -417,6 +427,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, } task_sig(m, task); task_cap(m, task); + task_cpus_allowed(m, task); cpuset_task_status_allowed(m, task); #if defined(CONFIG_S390) task_show_regs(m, task); diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 83d2fbd81b93..9ea40ff26f0e 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -277,7 +277,6 @@ extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_resume(void); extern struct clocksource * __init __weak clocksource_default_clock(void); -extern void clocksource_mark_unstable(struct clocksource *cs); #ifdef CONFIG_GENERIC_TIME_VSYSCALL extern void update_vsyscall(struct timespec *ts, struct clocksource *c); diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 4a2b162c256a..69a6fbac0921 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -126,7 +126,9 @@ extern int free_irte(int irq); extern int irq_remapped(int irq); extern struct intel_iommu *map_dev_to_ir(struct pci_dev *dev); extern struct intel_iommu *map_ioapic_to_ir(int apic); +extern struct intel_iommu *map_hpet_to_ir(u8 id); extern int set_ioapic_sid(struct irte *irte, int apic); +extern int set_hpet_sid(struct irte *irte, u8 id); extern int set_msi_sid(struct irte *irte, struct pci_dev *dev); #else static inline int alloc_irte(struct intel_iommu *iommu, int irq, u16 count) @@ -158,10 +160,18 @@ static inline struct intel_iommu *map_ioapic_to_ir(int apic) { return NULL; } +static inline struct intel_iommu *map_hpet_to_ir(unsigned int hpet_id) +{ + return NULL; +} static inline int set_ioapic_sid(struct irte *irte, int apic) { return 0; } +static inline int set_hpet_sid(struct irte *irte, u8 id) +{ + return -1; +} static inline int set_msi_sid(struct irte *irte, struct pci_dev *dev) { return 0; diff --git a/include/linux/hpet.h b/include/linux/hpet.h index 79f63a27bcef..219ca4f6bea6 100644 --- a/include/linux/hpet.h +++ b/include/linux/hpet.h @@ -126,4 +126,6 @@ struct hpet_info { #define HPET_DPI _IO('h', 0x05) /* disable periodic */ #define HPET_IRQFREQ _IOW('h', 0x6, unsigned long) /* IRQFREQ usec */ +#define MAX_HPET_TBS 8 /* maximum hpet timer blocks */ + #endif /* !__HPET__ */ diff --git a/include/linux/poison.h b/include/linux/poison.h index 7fc194aef8c2..2110a81c5e2a 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -2,13 +2,25 @@ #define _LINUX_POISON_H /********** include/linux/list.h **********/ + +/* + * Architectures might want to move the poison pointer offset + * into some well-recognized area such as 0xdead000000000000, + * that is also not mappable by user-space exploits: + */ +#ifdef CONFIG_ILLEGAL_POINTER_VALUE +# define POISON_POINTER_DELTA _AC(CONFIG_ILLEGAL_POINTER_VALUE, UL) +#else +# define POISON_POINTER_DELTA 0 +#endif + /* * These are non-NULL pointers that will result in page faults * under normal circumstances, used to verify that nobody uses * non-initialized list entries. */ -#define LIST_POISON1 ((void *) 0x00100100) -#define LIST_POISON2 ((void *) 0x00200200) +#define LIST_POISON1 ((void *) 0x00100100 + POISON_POINTER_DELTA) +#define LIST_POISON2 ((void *) 0x00200200 + POISON_POINTER_DELTA) /********** include/linux/timer.h **********/ /* diff --git a/include/linux/timex.h b/include/linux/timex.h index e6967d10d9e5..782ccd45c0d9 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -115,13 +115,16 @@ struct timex { #define ADJ_OFFSET_SS_READ 0xa001 /* read-only adjtime */ #endif -/* xntp 3.4 compatibility names */ +/* NTP userland likes the MOD_ prefix better */ #define MOD_OFFSET ADJ_OFFSET #define MOD_FREQUENCY ADJ_FREQUENCY #define MOD_MAXERROR ADJ_MAXERROR #define MOD_ESTERROR ADJ_ESTERROR #define MOD_STATUS ADJ_STATUS #define MOD_TIMECONST ADJ_TIMECONST +#define MOD_TAI ADJ_TAI +#define MOD_MICRO ADJ_MICRO +#define MOD_NANO ADJ_NANO /* diff --git a/kernel/cpuset.c b/kernel/cpuset.c index b5cb469d2545..d247381e7371 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2537,15 +2537,9 @@ const struct file_operations proc_cpuset_operations = { }; #endif /* CONFIG_PROC_PID_CPUSET */ -/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */ +/* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { - seq_printf(m, "Cpus_allowed:\t"); - seq_cpumask(m, &task->cpus_allowed); - seq_printf(m, "\n"); - seq_printf(m, "Cpus_allowed_list:\t"); - seq_cpumask_list(m, &task->cpus_allowed); - seq_printf(m, "\n"); seq_printf(m, "Mems_allowed:\t"); seq_nodemask(m, &task->mems_allowed); seq_printf(m, "\n"); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index e5d98ce50f89..6d7020490f94 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -509,13 +509,14 @@ static inline int hrtimer_hres_active(void) * next event * Called with interrupts disabled and base->lock held */ -static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base) +static void +hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { int i; struct hrtimer_clock_base *base = cpu_base->clock_base; - ktime_t expires; + ktime_t expires, expires_next; - cpu_base->expires_next.tv64 = KTIME_MAX; + expires_next.tv64 = KTIME_MAX; for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { struct hrtimer *timer; @@ -531,10 +532,15 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base) */ if (expires.tv64 < 0) expires.tv64 = 0; - if (expires.tv64 < cpu_base->expires_next.tv64) - cpu_base->expires_next = expires; + if (expires.tv64 < expires_next.tv64) + expires_next = expires; } + if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64) + return; + + cpu_base->expires_next.tv64 = expires_next.tv64; + if (cpu_base->expires_next.tv64 != KTIME_MAX) tick_program_event(cpu_base->expires_next, 1); } @@ -617,7 +623,7 @@ static void retrigger_next_event(void *arg) base->clock_base[CLOCK_REALTIME].offset = timespec_to_ktime(realtime_offset); - hrtimer_force_reprogram(base); + hrtimer_force_reprogram(base, 0); spin_unlock(&base->lock); } @@ -730,7 +736,8 @@ static int hrtimer_switch_to_hres(void) static inline int hrtimer_hres_active(void) { return 0; } static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline int hrtimer_switch_to_hres(void) { return 0; } -static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { } +static inline void +hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, struct hrtimer_clock_base *base, int wakeup) @@ -873,19 +880,29 @@ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, unsigned long newstate, int reprogram) { - if (timer->state & HRTIMER_STATE_ENQUEUED) { - /* - * Remove the timer from the rbtree and replace the - * first entry pointer if necessary. - */ - if (base->first == &timer->node) { - base->first = rb_next(&timer->node); - /* Reprogram the clock event device. if enabled */ - if (reprogram && hrtimer_hres_active()) - hrtimer_force_reprogram(base->cpu_base); + if (!(timer->state & HRTIMER_STATE_ENQUEUED)) + goto out; + + /* + * Remove the timer from the rbtree and replace the first + * entry pointer if necessary. + */ + if (base->first == &timer->node) { + base->first = rb_next(&timer->node); +#ifdef CONFIG_HIGH_RES_TIMERS + /* Reprogram the clock event device. if enabled */ + if (reprogram && hrtimer_hres_active()) { + ktime_t expires; + + expires = ktime_sub(hrtimer_get_expires(timer), + base->offset); + if (base->cpu_base->expires_next.tv64 == expires.tv64) + hrtimer_force_reprogram(base->cpu_base, 1); } - rb_erase(&timer->node, &base->active); +#endif } + rb_erase(&timer->node, &base->active); +out: timer->state = newstate; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index bde4c667d24d..7305b297d1eb 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1067,7 +1067,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, kfree(action); #ifdef CONFIG_DEBUG_SHIRQ - if (irqflags & IRQF_SHARED) { + if (!retval && (irqflags & IRQF_SHARED)) { /* * It's a shared IRQ -- the driver ought to be prepared for it * to happen immediately, so let's make sure.... |