diff options
Diffstat (limited to 'arch/x86/kernel')
42 files changed, 433 insertions, 340 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 680b7300a489..2cdc9de9371d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -72,7 +72,8 @@ static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return #define PREFIX "ACPI: " int acpi_noirq; /* skip ACPI IRQ initialization */ -int acpi_pci_disabled __initdata; /* skip ACPI PCI scan and IRQ initialization */ +int acpi_pci_disabled; /* skip ACPI PCI scan and IRQ initialization */ +EXPORT_SYMBOL(acpi_pci_disabled); int acpi_ht __initdata = 1; /* enable HT */ int acpi_lapic; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 45d79ea890ae..5fed98ca0e1f 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -65,7 +65,8 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt); get them easily into strings. */ asm("\t.section .rodata, \"a\"\nintelnops: " GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6 - GENERIC_NOP7 GENERIC_NOP8); + GENERIC_NOP7 GENERIC_NOP8 + "\t.previous"); extern const unsigned char intelnops[]; static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = { NULL, @@ -83,7 +84,8 @@ static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = { #ifdef K8_NOP1 asm("\t.section .rodata, \"a\"\nk8nops: " K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6 - K8_NOP7 K8_NOP8); + K8_NOP7 K8_NOP8 + "\t.previous"); extern const unsigned char k8nops[]; static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = { NULL, @@ -101,7 +103,8 @@ static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = { #ifdef K7_NOP1 asm("\t.section .rodata, \"a\"\nk7nops: " K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6 - K7_NOP7 K7_NOP8); + K7_NOP7 K7_NOP8 + "\t.previous"); extern const unsigned char k7nops[]; static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = { NULL, @@ -119,7 +122,8 @@ static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = { #ifdef P6_NOP1 asm("\t.section .rodata, \"a\"\np6nops: " P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6 - P6_NOP7 P6_NOP8); + P6_NOP7 P6_NOP8 + "\t.previous"); extern const unsigned char p6nops[]; static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = { NULL, diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 608152a2a05e..00df126169b4 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -18,6 +18,7 @@ #include <linux/pci.h> #include <linux/bitops.h> #include <linux/ioport.h> +#include <linux/suspend.h> #include <asm/e820.h> #include <asm/io.h> #include <asm/gart.h> @@ -76,6 +77,8 @@ static u32 __init allocate_aperture(void) printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n", aper_size >> 10, __pa(p)); insert_aperture_resource((u32)__pa(p), aper_size); + register_nosave_region((u32)__pa(p) >> PAGE_SHIFT, + (u32)__pa(p+aper_size) >> PAGE_SHIFT); return (u32)__pa(p); } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index a33d53017997..8ea040124f7d 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -128,13 +128,11 @@ void foo(void) OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending); #endif -#ifdef CONFIG_LGUEST_GUEST +#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) BLANK(); OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); OFFSET(LGUEST_DATA_pgdir, lguest_data, pgdir); -#endif -#ifdef CONFIG_LGUEST BLANK(); OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc); OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 027e5c003b16..170d2f5523b2 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -143,14 +143,6 @@ static void __init check_config(void) #endif /* - * If we configured ourselves for a TSC, we'd better have one! - */ -#ifdef CONFIG_X86_TSC - if (!cpu_has_tsc) - panic("Kernel compiled for Pentium+, requires TSC feature!"); -#endif - -/* * If we were told we had a good local APIC, check for buggy Pentia, * i.e. all B steppings and the C2 stepping of P54C when using their * integrated APIC (see 11AP erratum in "Pentium Processor diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f86a3c4a2669..a38aafaefc23 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -504,7 +504,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* Clear all flags overriden by options */ for (i = 0; i < NCAPINTS; i++) - c->x86_capability[i] ^= cleared_cpu_caps[i]; + c->x86_capability[i] &= ~cleared_cpu_caps[i]; /* Init Machine Check Exception if available. */ mcheck_init(c); diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c index 39f8cb18296c..c2f930d86640 100644 --- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c +++ b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c @@ -55,7 +55,6 @@ static int eps_set_state(struct eps_cpu_data *centaur, { struct cpufreq_freqs freqs; u32 lo, hi; - u8 current_multiplier, current_voltage; int err = 0; int i; @@ -95,6 +94,10 @@ postchange: rdmsr(MSR_IA32_PERF_STATUS, lo, hi); freqs.new = centaur->fsb * ((lo >> 8) & 0xff); +#ifdef DEBUG + { + u8 current_multiplier, current_voltage; + /* Print voltage and multiplier */ rdmsr(MSR_IA32_PERF_STATUS, lo, hi); current_voltage = lo & 0xff; @@ -103,7 +106,8 @@ postchange: current_multiplier = (lo >> 8) & 0xff; printk(KERN_INFO "eps: Current multiplier = %d\n", current_multiplier); - + } +#endif cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); return err; } diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c index f2b5a621d27b..8a85c93bd62a 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c @@ -63,7 +63,7 @@ static struct cpufreq_frequency_table speedstep_freqs[] = { */ static int speedstep_smi_ownership (void) { - u32 command, result, magic; + u32 command, result, magic, dummy; u32 function = GET_SPEEDSTEP_OWNER; unsigned char magic_data[] = "Copyright (c) 1999 Intel Corporation"; @@ -73,8 +73,11 @@ static int speedstep_smi_ownership (void) dprintk("trying to obtain ownership with command %x at port %x\n", command, smi_port); __asm__ __volatile__( + "push %%ebp\n" "out %%al, (%%dx)\n" - : "=D" (result) + "pop %%ebp\n" + : "=D" (result), "=a" (dummy), "=b" (dummy), "=c" (dummy), "=d" (dummy), + "=S" (dummy) : "a" (command), "b" (function), "c" (0), "d" (smi_port), "D" (0), "S" (magic) : "memory" @@ -96,7 +99,7 @@ static int speedstep_smi_ownership (void) */ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) { - u32 command, result = 0, edi, high_mhz, low_mhz; + u32 command, result = 0, edi, high_mhz, low_mhz, dummy; u32 state=0; u32 function = GET_SPEEDSTEP_FREQS; @@ -109,10 +112,12 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) dprintk("trying to determine frequencies with command %x at port %x\n", command, smi_port); - __asm__ __volatile__("movl $0, %%edi\n" + __asm__ __volatile__( + "push %%ebp\n" "out %%al, (%%dx)\n" - : "=a" (result), "=b" (high_mhz), "=c" (low_mhz), "=d" (state), "=D" (edi) - : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0) + "pop %%ebp" + : "=a" (result), "=b" (high_mhz), "=c" (low_mhz), "=d" (state), "=D" (edi), "=S" (dummy) + : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0) ); dprintk("result %x, low_freq %u, high_freq %u\n", result, low_mhz, high_mhz); @@ -135,16 +140,18 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) static int speedstep_get_state (void) { u32 function=GET_SPEEDSTEP_STATE; - u32 result, state, edi, command; + u32 result, state, edi, command, dummy; command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); dprintk("trying to determine current setting with command %x at port %x\n", command, smi_port); - __asm__ __volatile__("movl $0, %%edi\n" + __asm__ __volatile__( + "push %%ebp\n" "out %%al, (%%dx)\n" - : "=a" (result), "=b" (state), "=D" (edi) - : "a" (command), "b" (function), "c" (0), "d" (smi_port), "S" (0) + "pop %%ebp\n" + : "=a" (result), "=b" (state), "=D" (edi), "=c" (dummy), "=d" (dummy), "=S" (dummy) + : "a" (command), "b" (function), "c" (0), "d" (smi_port), "S" (0), "D" (0) ); dprintk("state is %x, result is %x\n", state, result); @@ -160,7 +167,7 @@ static int speedstep_get_state (void) */ static void speedstep_set_state (unsigned int state) { - unsigned int result = 0, command, new_state; + unsigned int result = 0, command, new_state, dummy; unsigned long flags; unsigned int function=SET_SPEEDSTEP_STATE; unsigned int retry = 0; @@ -182,10 +189,12 @@ static void speedstep_set_state (unsigned int state) } retry++; __asm__ __volatile__( - "movl $0, %%edi\n" + "push %%ebp\n" "out %%al, (%%dx)\n" - : "=b" (new_state), "=D" (result) - : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0) + "pop %%ebp" + : "=b" (new_state), "=D" (result), "=c" (dummy), "=a" (dummy), + "=d" (dummy), "=S" (dummy) + : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0) ); } while ((new_state != state) && (retry <= SMI_TRIES)); @@ -195,7 +204,7 @@ static void speedstep_set_state (unsigned int state) if (new_state == state) { dprintk("change to %u MHz succeeded after %u tries with result %u\n", (speedstep_freqs[new_state].frequency / 1000), retry, result); } else { - printk(KERN_ERR "cpufreq: change failed with new_state %u and result %u\n", new_state, result); + printk(KERN_ERR "cpufreq: change to state %u failed with new_state %u and result %u\n", state, new_state, result); } return; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 103d61a59b19..3e18db4cefee 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -176,12 +176,13 @@ static inline void k8_enable_fixed_iorrs(void) } /** - * Checks and updates an fixed-range MTRR if it differs from the value it - * should have. If K8 extentions are wanted, update the K8 SYSCFG MSR also. - * see AMD publication no. 24593, chapter 7.8.1, page 233 for more information - * \param msr MSR address of the MTTR which should be checked and updated - * \param changed pointer which indicates whether the MTRR needed to be changed - * \param msrwords pointer to the MSR values which the MSR should have + * set_fixed_range - checks & updates a fixed-range MTRR if it differs from the value it should have + * @msr: MSR address of the MTTR which should be checked and updated + * @changed: pointer which indicates whether the MTRR needed to be changed + * @msrwords: pointer to the MSR values which the MSR should have + * + * If K8 extentions are wanted, update the K8 SYSCFG MSR also. + * See AMD publication no. 24593, chapter 7.8.1, page 233 for more information. */ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords) { @@ -199,12 +200,15 @@ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords) } } +/** + * generic_get_free_region - Get a free MTRR. + * @base: The starting (base) address of the region. + * @size: The size (in bytes) of the region. + * @replace_reg: mtrr index to be replaced; set to invalid value if none. + * + * Returns: The index of the region on success, else negative on error. + */ int generic_get_free_region(unsigned long base, unsigned long size, int replace_reg) -/* [SUMMARY] Get a free MTRR. - <base> The starting (base) address of the region. - <size> The size (in bytes) of the region. - [RETURNS] The index of the region on success, else -1 on error. -*/ { int i, max; mtrr_type ltype; @@ -249,8 +253,8 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, } /** - * Checks and updates the fixed-range MTRRs if they differ from the saved set - * \param frs pointer to fixed-range MTRR values, saved by get_fixed_ranges() + * set_fixed_ranges - checks & updates the fixed-range MTRRs if they differ from the saved set + * @frs: pointer to fixed-range MTRR values, saved by get_fixed_ranges() */ static int set_fixed_ranges(mtrr_type * frs) { @@ -294,13 +298,13 @@ static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr) static u32 deftype_lo, deftype_hi; +/** + * set_mtrr_state - Set the MTRR state for this CPU. + * + * NOTE: The CPU must already be in a safe state for MTRR changes. + * RETURNS: 0 if no changes made, else a mask indicating what was changed. + */ static unsigned long set_mtrr_state(void) -/* [SUMMARY] Set the MTRR state for this CPU. - <state> The MTRR state information to read. - <ctxt> Some relevant CPU context. - [NOTE] The CPU must already be in a safe state for MTRR changes. - [RETURNS] 0 if no changes made, else a mask indication what was changed. -*/ { unsigned int i; unsigned long change_mask = 0; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index b6e136f23d3d..a6450b3ae759 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -43,6 +43,7 @@ #include <asm/uaccess.h> #include <asm/processor.h> #include <asm/msr.h> +#include <asm/kvm_para.h> #include "mtrr.h" u32 num_var_ranges = 0; @@ -649,6 +650,7 @@ static __init int amd_special_default_mtrr(void) /** * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs + * @end_pfn: ending page frame number * * Some buggy BIOSes don't setup the MTRRs properly for systems with certain * memory configurations. This routine checks that the highest MTRR matches @@ -688,8 +690,11 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* kvm/qemu doesn't have mtrr set right, don't trim them all */ if (!highest_pfn) { - printk(KERN_WARNING "WARNING: strange, CPU MTRRs all blank?\n"); - WARN_ON(1); + if (!kvm_para_available()) { + printk(KERN_WARNING + "WARNING: strange, CPU MTRRs all blank?\n"); + WARN_ON(1); + } return 0; } @@ -706,7 +711,8 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) trim_size = end_pfn; trim_size <<= PAGE_SHIFT; trim_size -= trim_start; - add_memory_region(trim_start, trim_size, E820_RESERVED); + update_memory_range(trim_start, trim_size, E820_RAM, + E820_RESERVED); update_e820(); return 1; } diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 9b838324b818..b943e10ad814 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -652,9 +652,6 @@ static void probe_nmi_watchdog(void) wd_ops = &p6_wd_ops; break; case 15: - if (boot_cpu_data.x86_model > 0x4) - return; - wd_ops = &p4_wd_ops; break; default: @@ -670,8 +667,10 @@ int lapic_watchdog_init(unsigned nmi_hz) { if (!wd_ops) { probe_nmi_watchdog(); - if (!wd_ops) + if (!wd_ops) { + printk(KERN_INFO "NMI watchdog: CPU not supported\n"); return -1; + } if (!wd_ops->reserve()) { printk(KERN_ERR diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 200fb3f9ebfb..e8b422c1c512 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -76,13 +76,6 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) /* All Transmeta CPUs have a constant TSC */ set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability); - /* If we can run i686 user-space code, call us an i686 */ -#define USER686 ((1 << X86_FEATURE_TSC)|\ - (1 << X86_FEATURE_CX8)|\ - (1 << X86_FEATURE_CMOV)) - if (c->x86 == 5 && (c->x86_capability[0] & USER686) == USER686) - c->x86 = 6; - #ifdef CONFIG_SYSCTL /* randomize_va_space slows us down enormously; it probably triggers retranslation of x86->native bytecode */ diff --git a/arch/x86/kernel/e820_32.c b/arch/x86/kernel/e820_32.c index 4e16ef4a2659..80444c5c9b14 100644 --- a/arch/x86/kernel/e820_32.c +++ b/arch/x86/kernel/e820_32.c @@ -749,6 +749,32 @@ static int __init parse_memmap(char *arg) return 0; } early_param("memmap", parse_memmap); +void __init update_memory_range(u64 start, u64 size, unsigned old_type, + unsigned new_type) +{ + int i; + + BUG_ON(old_type == new_type); + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + u64 final_start, final_end; + if (ei->type != old_type) + continue; + /* totally covered? */ + if (ei->addr >= start && ei->size <= size) { + ei->type = new_type; + continue; + } + /* partially covered */ + final_start = max(start, ei->addr); + final_end = min(start + size, ei->addr + ei->size); + if (final_start >= final_end) + continue; + add_memory_region(final_start, final_end - final_start, + new_type); + } +} void __init update_e820(void) { u8 nr_map; diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c index 9f65b4cc323c..9be697126013 100644 --- a/arch/x86/kernel/e820_64.c +++ b/arch/x86/kernel/e820_64.c @@ -744,6 +744,33 @@ void __init finish_e820_parsing(void) } } +void __init update_memory_range(u64 start, u64 size, unsigned old_type, + unsigned new_type) +{ + int i; + + BUG_ON(old_type == new_type); + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + u64 final_start, final_end; + if (ei->type != old_type) + continue; + /* totally covered? */ + if (ei->addr >= start && ei->size <= size) { + ei->type = new_type; + continue; + } + /* partially covered */ + final_start = max(start, ei->addr); + final_end = min(start + size, ei->addr + ei->size); + if (final_start >= final_end) + continue; + add_memory_region(final_start, final_end - final_start, + new_type); + } +} + void __init update_e820(void) { u8 nr_map; diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 2ad9a1bc6a73..c20c9e7e08dd 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -453,6 +453,7 @@ ENTRY(stub_execve) CFI_REGISTER rip, r11 SAVE_REST FIXUP_TOP_OF_STACK %r11 + movq %rsp, %rcx call sys_execve RESTORE_TOP_OF_STACK %r11 movq %rax,RAX(%rsp) @@ -1036,15 +1037,16 @@ ENDPROC(child_rip) * rdi: name, rsi: argv, rdx: envp * * We want to fallback into: - * extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs regs) + * extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs *regs) * * do_sys_execve asm fallback arguments: - * rdi: name, rsi: argv, rdx: envp, fake frame on the stack + * rdi: name, rsi: argv, rdx: envp, rcx: fake frame on the stack */ ENTRY(kernel_execve) CFI_STARTPROC FAKE_STACK_FRAME $0 SAVE_ALL + movq %rsp,%rcx call sys_execve movq %rax, RAX(%rsp) RESTORE_REST diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 25eb98540a41..74d87ea85b5c 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -606,7 +606,7 @@ ENTRY(_stext) .section ".bss.page_aligned","wa" .align PAGE_SIZE_asm #ifdef CONFIG_X86_PAE -ENTRY(swapper_pg_pmd) +swapper_pg_pmd: .fill 1024*KPMDS,4,0 #else ENTRY(swapper_pg_dir) @@ -657,7 +657,7 @@ int_msg: .asciz "Unknown interrupt or fault at EIP %p %p %p\n" fault_msg: - .ascii \ + .asciz \ /* fault info: */ "BUG: Int %d: CR2 %p\n" \ /* pusha regs: */ " EDI %p ESI %p EBP %p ESP %p\n" \ " EBX %p EDX %p ECX %p EAX %p\n" \ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index eb415043a929..a007454133a3 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -379,18 +379,24 @@ NEXT_PAGE(level2_ident_pgt) /* Since I easily can, map the first 1G. * Don't set NX because code runs from these pages. */ - PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD) + PMDS(0, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD) NEXT_PAGE(level2_kernel_pgt) - /* 40MB kernel mapping. The kernel code cannot be bigger than that. - When you change this change KERNEL_TEXT_SIZE in page.h too. */ - /* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */ - PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL, KERNEL_TEXT_SIZE/PMD_SIZE) - /* Module mapping starts here */ - .fill (PTRS_PER_PMD - (KERNEL_TEXT_SIZE/PMD_SIZE)),8,0 + /* + * 128 MB kernel mapping. We spend a full page on this pagetable + * anyway. + * + * The kernel code+data+bss must not be bigger than that. + * + * (NOTE: at +128MB starts the module area, see MODULES_VADDR. + * If you want to increase this then increase MODULES_VADDR + * too.) + */ + PMDS(0, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL, + KERNEL_IMAGE_SIZE/PMD_SIZE) NEXT_PAGE(level2_spare_pgt) - .fill 512,8,0 + .fill 512, 8, 0 #undef PMDS #undef NEXT_PAGE diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 429d084e014d..36652ea1a265 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -133,13 +133,16 @@ static void hpet_reserve_platform_timers(unsigned long id) #ifdef CONFIG_HPET_EMULATE_RTC hpet_reserve_timer(&hd, 1); #endif + hd.hd_irq[0] = HPET_LEGACY_8254; hd.hd_irq[1] = HPET_LEGACY_RTC; - for (i = 2; i < nrtimers; timer++, i++) - hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >> - Tn_INT_ROUTE_CNF_SHIFT; + for (i = 2; i < nrtimers; timer++, i++) + hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >> + Tn_INT_ROUTE_CNF_SHIFT; + hpet_alloc(&hd); + } #else static void hpet_reserve_platform_timers(unsigned long id) { } @@ -368,8 +371,8 @@ static int hpet_clocksource_register(void) return 0; } -/* - * Try to setup the HPET timer +/** + * hpet_enable - Try to setup the HPET timer. Returns 1 on success. */ int __init hpet_enable(void) { diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 763dfc407232..d2e39e69aaf8 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -132,7 +132,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, if (!cpu_has_fxsr) return -ENODEV; - unlazy_fpu(target); + init_fpu(target); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.i387.fxsave, 0, -1); @@ -147,7 +147,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (!cpu_has_fxsr) return -ENODEV; - unlazy_fpu(target); + init_fpu(target); set_stopped_child_used_math(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -261,7 +261,7 @@ static void convert_from_fxsr(struct user_i387_ia32_struct *env, } #else env->fip = fxsave->fip; - env->fcs = fxsave->fcs; + env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); env->foo = fxsave->foo; env->fos = fxsave->fos; #endif @@ -307,7 +307,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, if (!HAVE_HWFP) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - unlazy_fpu(target); + init_fpu(target); if (!cpu_has_fxsr) return user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -332,7 +332,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, if (!HAVE_HWFP) return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - unlazy_fpu(target); + init_fpu(target); set_stopped_child_used_math(target); if (!cpu_has_fxsr) diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c index 5b3ce7934363..3d01e47777db 100644 --- a/arch/x86/kernel/init_task.c +++ b/arch/x86/kernel/init_task.c @@ -15,6 +15,7 @@ static struct files_struct init_files = INIT_FILES; static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); struct mm_struct init_mm = INIT_MM(init_mm); +EXPORT_UNUSED_SYMBOL(init_mm); /* will be removed in 2.6.26 */ /* * Initial thread structure. diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c index c706a3061553..5921e5f0a640 100644 --- a/arch/x86/kernel/io_delay.c +++ b/arch/x86/kernel/io_delay.c @@ -78,6 +78,14 @@ static struct dmi_system_id __initdata io_delay_0xed_port_dmi_table[] = { }, { .callback = dmi_io_delay_0xed_port, + .ident = "HP Pavilion dv6000", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), + DMI_MATCH(DMI_BOARD_NAME, "30B8") + } + }, + { + .callback = dmi_io_delay_0xed_port, .ident = "HP Pavilion tx1000", .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 236d2f8f7ddc..576a03db4511 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -233,6 +233,7 @@ NORET_TYPE void machine_kexec(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { + VMCOREINFO_SYMBOL(phys_base); VMCOREINFO_SYMBOL(init_level4_pgt); #ifdef CONFIG_NUMA diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index 027fc067b399..b402c0f3f192 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -30,6 +30,7 @@ #include <linux/kernel.h> #include <linux/interrupt.h> +#include <linux/module.h> #include <asm/geode.h> static struct mfgpt_timer_t { diff --git a/arch/x86/kernel/pci-dma_64.c b/arch/x86/kernel/pci-dma_64.c index a82473d192a3..375cb2bc45be 100644 --- a/arch/x86/kernel/pci-dma_64.c +++ b/arch/x86/kernel/pci-dma_64.c @@ -53,11 +53,6 @@ dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order) int node; node = dev_to_node(dev); - if (node == -1) - node = numa_node_id(); - - if (node < first_node(node_online_map)) - node = first_node(node_online_map); page = alloc_pages_node(node, gfp, order); return page ? page_address(page) : NULL; diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index faf3229f8fb3..700e4647dd30 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -615,8 +615,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info) nommu: /* Should not happen anymore */ - printk(KERN_ERR "PCI-DMA: More than 4GB of RAM and no IOMMU\n" - KERN_ERR "PCI-DMA: 32bit PCI IO may malfunction.\n"); + printk(KERN_WARNING "PCI-DMA: More than 4GB of RAM and no IOMMU\n" + KERN_WARNING "falling back to iommu=soft.\n"); return -1; } @@ -692,9 +692,9 @@ void __init gart_iommu_init(void) !gart_iommu_aperture || (no_agp && init_k8_gatt(&info) < 0)) { if (end_pfn > MAX_DMA32_PFN) { - printk(KERN_ERR "WARNING more than 4GB of memory " - "but GART IOMMU not available.\n" - KERN_ERR "WARNING 32bit PCI may malfunction.\n"); + printk(KERN_WARNING "More than 4GB of memory " + "but GART IOMMU not available.\n" + KERN_WARNING "falling back to iommu=soft.\n"); } return; } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a7d50a547dc2..43930e73f657 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -82,7 +82,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk) */ void (*pm_idle)(void); EXPORT_SYMBOL(pm_idle); -static DEFINE_PER_CPU(unsigned int, cpu_idle_state); void disable_hlt(void) { @@ -190,9 +189,6 @@ void cpu_idle(void) while (!need_resched()) { void (*idle)(void); - if (__get_cpu_var(cpu_idle_state)) - __get_cpu_var(cpu_idle_state) = 0; - check_pgt_cache(); rmb(); idle = pm_idle; @@ -220,40 +216,19 @@ static void do_nothing(void *unused) { } +/* + * cpu_idle_wait - Used to ensure that all the CPUs discard old value of + * pm_idle and update to new pm_idle value. Required while changing pm_idle + * handler on SMP systems. + * + * Caller must have changed pm_idle to the new value before the call. Old + * pm_idle value will not be used by any CPU after the return of this function. + */ void cpu_idle_wait(void) { - unsigned int cpu, this_cpu = get_cpu(); - cpumask_t map, tmp = current->cpus_allowed; - - set_cpus_allowed(current, cpumask_of_cpu(this_cpu)); - put_cpu(); - - cpus_clear(map); - for_each_online_cpu(cpu) { - per_cpu(cpu_idle_state, cpu) = 1; - cpu_set(cpu, map); - } - - __get_cpu_var(cpu_idle_state) = 0; - - wmb(); - do { - ssleep(1); - for_each_online_cpu(cpu) { - if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu)) - cpu_clear(cpu, map); - } - cpus_and(map, map, cpu_online_map); - /* - * We waited 1 sec, if a CPU still did not call idle - * it may be because it is in idle and not waking up - * because it has nothing to do. - * Give all the remaining CPUS a kick. - */ - smp_call_function_mask(map, do_nothing, NULL, 0); - } while (!cpus_empty(map)); - - set_cpus_allowed(current, tmp); + smp_mb(); + /* kick all the CPUs so that they exit out of pm_idle */ + smp_call_function(do_nothing, NULL, 0, 1); } EXPORT_SYMBOL_GPL(cpu_idle_wait); @@ -603,11 +578,13 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, } #endif +#ifdef X86_BTS if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS); if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES); +#endif if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b0cc8f0136d8..46c4c546b499 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -63,7 +63,6 @@ EXPORT_SYMBOL(boot_option_idle_override); */ void (*pm_idle)(void); EXPORT_SYMBOL(pm_idle); -static DEFINE_PER_CPU(unsigned int, cpu_idle_state); static ATOMIC_NOTIFIER_HEAD(idle_notifier); @@ -173,9 +172,6 @@ void cpu_idle(void) while (!need_resched()) { void (*idle)(void); - if (__get_cpu_var(cpu_idle_state)) - __get_cpu_var(cpu_idle_state) = 0; - rmb(); idle = pm_idle; if (!idle) @@ -207,40 +203,19 @@ static void do_nothing(void *unused) { } +/* + * cpu_idle_wait - Used to ensure that all the CPUs discard old value of + * pm_idle and update to new pm_idle value. Required while changing pm_idle + * handler on SMP systems. + * + * Caller must have changed pm_idle to the new value before the call. Old + * pm_idle value will not be used by any CPU after the return of this function. + */ void cpu_idle_wait(void) { - unsigned int cpu, this_cpu = get_cpu(); - cpumask_t map, tmp = current->cpus_allowed; - - set_cpus_allowed(current, cpumask_of_cpu(this_cpu)); - put_cpu(); - - cpus_clear(map); - for_each_online_cpu(cpu) { - per_cpu(cpu_idle_state, cpu) = 1; - cpu_set(cpu, map); - } - - __get_cpu_var(cpu_idle_state) = 0; - - wmb(); - do { - ssleep(1); - for_each_online_cpu(cpu) { - if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu)) - cpu_clear(cpu, map); - } - cpus_and(map, map, cpu_online_map); - /* - * We waited 1 sec, if a CPU still did not call idle - * it may be because it is in idle and not waking up - * because it has nothing to do. - * Give all the remaining CPUS a kick. - */ - smp_call_function_mask(map, do_nothing, 0, 0); - } while (!cpus_empty(map)); - - set_cpus_allowed(current, tmp); + smp_mb(); + /* kick all the CPUs so that they exit out of pm_idle */ + smp_call_function(do_nothing, NULL, 0, 1); } EXPORT_SYMBOL_GPL(cpu_idle_wait); @@ -604,11 +579,13 @@ static inline void __switch_to_xtra(struct task_struct *prev_p, memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } +#ifdef X86_BTS if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS); if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES); +#endif } /* @@ -730,16 +707,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ asmlinkage long sys_execve(char __user *name, char __user * __user *argv, - char __user * __user *envp, struct pt_regs regs) + char __user * __user *envp, struct pt_regs *regs) { long error; char * filename; filename = getname(name); error = PTR_ERR(filename); - if (IS_ERR(filename)) + if (IS_ERR(filename)) return error; - error = do_execve(filename, argv, envp, ®s); + error = do_execve(filename, argv, envp, regs); putname(filename); return error; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 702c33efea84..eb92ccbb3502 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -323,6 +323,16 @@ static int putreg(struct task_struct *child, return set_flags(child, value); #ifdef CONFIG_X86_64 + /* + * Orig_ax is really just a flag with small positive and + * negative values, so make sure to always sign-extend it + * from 32 bits so that it works correctly regardless of + * whether we come from a 32-bit environment or not. + */ + case offsetof(struct user_regs_struct, orig_ax): + value = (long) (s32) value; + break; + case offsetof(struct user_regs_struct,fs_base): if (value >= TASK_SIZE_OF(child)) return -EIO; @@ -544,6 +554,8 @@ static int ptrace_set_debugreg(struct task_struct *child, return 0; } +#ifdef X86_BTS + static int ptrace_bts_get_size(struct task_struct *child) { if (!child->thread.ds_area_msr) @@ -588,21 +600,6 @@ static int ptrace_bts_read_record(struct task_struct *child, return sizeof(ret); } -static int ptrace_bts_write_record(struct task_struct *child, - const struct bts_struct *in) -{ - int retval; - - if (!child->thread.ds_area_msr) - return -ENXIO; - - retval = ds_write_bts((void *)child->thread.ds_area_msr, in); - if (retval) - return retval; - - return sizeof(*in); -} - static int ptrace_bts_clear(struct task_struct *child) { if (!child->thread.ds_area_msr) @@ -645,75 +642,6 @@ static int ptrace_bts_drain(struct task_struct *child, return end; } -static int ptrace_bts_realloc(struct task_struct *child, - int size, int reduce_size) -{ - unsigned long rlim, vm; - int ret, old_size; - - if (size < 0) - return -EINVAL; - - old_size = ds_get_bts_size((void *)child->thread.ds_area_msr); - if (old_size < 0) - return old_size; - - ret = ds_free((void **)&child->thread.ds_area_msr); - if (ret < 0) - goto out; - - size >>= PAGE_SHIFT; - old_size >>= PAGE_SHIFT; - - current->mm->total_vm -= old_size; - current->mm->locked_vm -= old_size; - - if (size == 0) - goto out; - - rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT; - vm = current->mm->total_vm + size; - if (rlim < vm) { - ret = -ENOMEM; - - if (!reduce_size) - goto out; - - size = rlim - current->mm->total_vm; - if (size <= 0) - goto out; - } - - rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT; - vm = current->mm->locked_vm + size; - if (rlim < vm) { - ret = -ENOMEM; - - if (!reduce_size) - goto out; - - size = rlim - current->mm->locked_vm; - if (size <= 0) - goto out; - } - - ret = ds_allocate((void **)&child->thread.ds_area_msr, - size << PAGE_SHIFT); - if (ret < 0) - goto out; - - current->mm->total_vm += size; - current->mm->locked_vm += size; - -out: - if (child->thread.ds_area_msr) - set_tsk_thread_flag(child, TIF_DS_AREA_MSR); - else - clear_tsk_thread_flag(child, TIF_DS_AREA_MSR); - - return ret; -} - static int ptrace_bts_config(struct task_struct *child, long cfg_size, const struct ptrace_bts_config __user *ucfg) @@ -816,6 +744,91 @@ static int ptrace_bts_status(struct task_struct *child, return sizeof(cfg); } + +static int ptrace_bts_write_record(struct task_struct *child, + const struct bts_struct *in) +{ + int retval; + + if (!child->thread.ds_area_msr) + return -ENXIO; + + retval = ds_write_bts((void *)child->thread.ds_area_msr, in); + if (retval) + return retval; + + return sizeof(*in); +} + +static int ptrace_bts_realloc(struct task_struct *child, + int size, int reduce_size) +{ + unsigned long rlim, vm; + int ret, old_size; + + if (size < 0) + return -EINVAL; + + old_size = ds_get_bts_size((void *)child->thread.ds_area_msr); + if (old_size < 0) + return old_size; + + ret = ds_free((void **)&child->thread.ds_area_msr); + if (ret < 0) + goto out; + + size >>= PAGE_SHIFT; + old_size >>= PAGE_SHIFT; + + current->mm->total_vm -= old_size; + current->mm->locked_vm -= old_size; + + if (size == 0) + goto out; + + rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT; + vm = current->mm->total_vm + size; + if (rlim < vm) { + ret = -ENOMEM; + + if (!reduce_size) + goto out; + + size = rlim - current->mm->total_vm; + if (size <= 0) + goto out; + } + + rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT; + vm = current->mm->locked_vm + size; + if (rlim < vm) { + ret = -ENOMEM; + + if (!reduce_size) + goto out; + + size = rlim - current->mm->locked_vm; + if (size <= 0) + goto out; + } + + ret = ds_allocate((void **)&child->thread.ds_area_msr, + size << PAGE_SHIFT); + if (ret < 0) + goto out; + + current->mm->total_vm += size; + current->mm->locked_vm += size; + +out: + if (child->thread.ds_area_msr) + set_tsk_thread_flag(child, TIF_DS_AREA_MSR); + else + clear_tsk_thread_flag(child, TIF_DS_AREA_MSR); + + return ret; +} + void ptrace_bts_take_timestamp(struct task_struct *tsk, enum bts_qualifier qualifier) { @@ -826,6 +839,7 @@ void ptrace_bts_take_timestamp(struct task_struct *tsk, ptrace_bts_write_record(tsk, &rec); } +#endif /* X86_BTS */ /* * Called by kernel/ptrace.c when detaching.. @@ -839,7 +853,9 @@ void ptrace_disable(struct task_struct *child) clear_tsk_thread_flag(child, TIF_SYSCALL_EMU); #endif if (child->thread.ds_area_msr) { +#ifdef X86_BTS ptrace_bts_realloc(child, 0, 0); +#endif child->thread.debugctlmsr &= ~ds_debugctl_mask(); if (!child->thread.debugctlmsr) clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); @@ -961,6 +977,10 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; #endif + /* + * These bits need more cooking - not enabled yet: + */ +#ifdef X86_BTS case PTRACE_BTS_CONFIG: ret = ptrace_bts_config (child, data, (struct ptrace_bts_config __user *)addr); @@ -988,6 +1008,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = ptrace_bts_drain (child, data, (struct bts_struct __user *) addr); break; +#endif default: ret = ptrace_request(child, request, addr, data); @@ -1035,10 +1056,17 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) R32(esi, si); R32(ebp, bp); R32(eax, ax); - R32(orig_eax, orig_ax); R32(eip, ip); R32(esp, sp); + case offsetof(struct user32, regs.orig_eax): + /* + * Sign-extend the value so that orig_eax = -1 + * causes (long)orig_ax < 0 tests to fire correctly. + */ + regs->orig_ax = (long) (s32) value; + break; + case offsetof(struct user32, regs.eflags): return set_flags(child, value); @@ -1160,7 +1188,7 @@ static int genregs32_set(struct task_struct *target, if (kbuf) { const compat_ulong_t *k = kbuf; while (count > 0 && !ret) { - ret = putreg(target, pos, *k++); + ret = putreg32(target, pos, *k++); count -= sizeof(*k); pos += sizeof(*k); } @@ -1171,7 +1199,7 @@ static int genregs32_set(struct task_struct *target, ret = __get_user(word, u++); if (ret) break; - ret = putreg(target, pos, word); + ret = putreg32(target, pos, word); count -= sizeof(*u); pos += sizeof(*u); } @@ -1226,12 +1254,14 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data) case PTRACE_SETOPTIONS: case PTRACE_SET_THREAD_AREA: case PTRACE_GET_THREAD_AREA: +#ifdef X86_BTS case PTRACE_BTS_CONFIG: case PTRACE_BTS_STATUS: case PTRACE_BTS_SIZE: case PTRACE_BTS_GET: case PTRACE_BTS_CLEAR: case PTRACE_BTS_DRAIN: +#endif return sys_ptrace(request, pid, addr, data); default: diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index c47208fc5932..d89a648fe710 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -363,6 +363,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0051, nvidia_force_enable_hpet); /* LPC bridges */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0260, + nvidia_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0360, nvidia_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0361, diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 7fd6ac43e4a1..484c4a80d38a 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -152,6 +152,24 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "0WF810"), }, }, + { /* Handle problems with rebooting on Dell Optiplex 745's DFF*/ + .callback = set_bios_reboot, + .ident = "Dell OptiPlex 745", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), + DMI_MATCH(DMI_BOARD_NAME, "0MM599"), + }, + }, + { /* Handle problems with rebooting on Dell Optiplex 745 with 0KW626 */ + .callback = set_bios_reboot, + .ident = "Dell OptiPlex 745", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), + DMI_MATCH(DMI_BOARD_NAME, "0KW626"), + }, + }, { /* Handle problems with rebooting on Dell 2400's */ .callback = set_bios_reboot, .ident = "Dell PowerEdge 2400", @@ -326,6 +344,10 @@ static inline void kb_wait(void) } } +void __attribute__((weak)) mach_reboot_fixups(void) +{ +} + static void native_machine_emergency_restart(void) { int i; @@ -337,6 +359,8 @@ static void native_machine_emergency_restart(void) /* Could also try the reset bit in the Hammer NB */ switch (reboot_type) { case BOOT_KBD: + mach_reboot_fixups(); /* for board specific fixups */ + for (i = 0; i < 10; i++) { kb_wait(); udelay(50); diff --git a/arch/x86/kernel/setup64.c b/arch/x86/kernel/setup64.c index 309366f8f603..e24c45677094 100644 --- a/arch/x86/kernel/setup64.c +++ b/arch/x86/kernel/setup64.c @@ -142,14 +142,16 @@ void __init setup_per_cpu_areas(void) printk(KERN_INFO "PERCPU: Allocating %lu bytes of per cpu data\n", size); for_each_cpu_mask (i, cpu_possible_map) { char *ptr; +#ifndef CONFIG_NEED_MULTIPLE_NODES + ptr = alloc_bootmem_pages(size); +#else + int node = early_cpu_to_node(i); - if (!NODE_DATA(early_cpu_to_node(i))) { - printk("cpu with no node %d, num_online_nodes %d\n", - i, num_online_nodes()); + if (!node_online(node) || !NODE_DATA(node)) ptr = alloc_bootmem_pages(size); - } else { - ptr = alloc_bootmem_pages_node(NODE_DATA(early_cpu_to_node(i)), size); - } + else + ptr = alloc_bootmem_pages_node(NODE_DATA(node), size); +#endif if (!ptr) panic("Cannot allocate cpu data for CPU %d\n", i); cpu_pda(i)->data_offset = ptr - __per_cpu_start; diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c index a1d7071a51c9..2b3e5d45176b 100644 --- a/arch/x86/kernel/setup_32.c +++ b/arch/x86/kernel/setup_32.c @@ -406,8 +406,6 @@ static unsigned long __init setup_memory(void) */ min_low_pfn = PFN_UP(init_pg_tables_end); - find_max_pfn(); - max_low_pfn = find_max_low_pfn(); #ifdef CONFIG_HIGHMEM @@ -764,12 +762,13 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled) efi_init(); - max_low_pfn = setup_memory(); - /* update e820 for memory not covered by WB MTRRs */ + find_max_pfn(); mtrr_bp_init(); if (mtrr_trim_uncached_memory(max_pfn)) - max_low_pfn = setup_memory(); + find_max_pfn(); + + max_low_pfn = setup_memory(); #ifdef CONFIG_VMI /* diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index 6fd804f07821..f4f7ecfb898c 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -801,7 +801,7 @@ static void __cpuinit srat_detect_node(void) /* Don't do the funky fallback heuristics the AMD version employs for now. */ node = apicid_to_node[apicid]; - if (node == NUMA_NO_NODE) + if (node == NUMA_NO_NODE || !node_online(node)) node = first_node(node_online_map); numa_set_node(cpu, node); @@ -1021,7 +1021,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* Clear all flags overriden by options */ for (i = 0; i < NCAPINTS; i++) - c->x86_capability[i] ^= cleared_cpu_caps[i]; + c->x86_capability[i] &= ~cleared_cpu_caps[i]; #ifdef CONFIG_X86_MCE mcheck_init(c); diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c index caee1f002fed..0157a6f0f41f 100644 --- a/arch/x86/kernel/signal_32.c +++ b/arch/x86/kernel/signal_32.c @@ -407,7 +407,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, * The tracer may want to single-step inside the * handler too. */ - regs->flags &= ~TF_MASK; + regs->flags &= ~(TF_MASK | X86_EFLAGS_DF); if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); @@ -500,7 +500,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, * The tracer may want to single-step inside the * handler too. */ - regs->flags &= ~TF_MASK; + regs->flags &= ~(TF_MASK | X86_EFLAGS_DF); if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index 7347bb14e306..1c83e5124c65 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -295,7 +295,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, see include/asm-x86_64/uaccess.h for details. */ set_fs(USER_DS); - regs->flags &= ~X86_EFLAGS_TF; + regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF); if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); #ifdef DEBUG_SIG @@ -311,6 +311,35 @@ give_sigsegv: } /* + * Return -1L or the syscall number that @regs is executing. + */ +static long current_syscall(struct pt_regs *regs) +{ + /* + * We always sign-extend a -1 value being set here, + * so this is always either -1L or a syscall number. + */ + return regs->orig_ax; +} + +/* + * Return a value that is -EFOO if the system call in @regs->orig_ax + * returned an error. This only works for @regs from @current. + */ +static long current_syscall_ret(struct pt_regs *regs) +{ +#ifdef CONFIG_IA32_EMULATION + if (test_thread_flag(TIF_IA32)) + /* + * Sign-extend the value so (int)-EFOO becomes (long)-EFOO + * and will match correctly in comparisons. + */ + return (int) regs->ax; +#endif + return regs->ax; +} + +/* * OK, we're invoking a handler */ @@ -327,9 +356,9 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, #endif /* Are we from a system call? */ - if ((long)regs->orig_ax >= 0) { + if (current_syscall(regs) >= 0) { /* If so, check system call restarting.. */ - switch (regs->ax) { + switch (current_syscall_ret(regs)) { case -ERESTART_RESTARTBLOCK: case -ERESTARTNOHAND: regs->ax = -EINTR; @@ -426,10 +455,9 @@ static void do_signal(struct pt_regs *regs) } /* Did we come from a system call? */ - if ((long)regs->orig_ax >= 0) { + if (current_syscall(regs) >= 0) { /* Restart the system call - no handlers present */ - long res = regs->ax; - switch (res) { + switch (current_syscall_ret(regs)) { case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c index d53bd6fcb428..0880f2c388a9 100644 --- a/arch/x86/kernel/smpboot_64.c +++ b/arch/x86/kernel/smpboot_64.c @@ -554,10 +554,10 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid) int timeout; unsigned long start_rip; struct create_idle c_idle = { - .work = __WORK_INITIALIZER(c_idle.work, do_fork_idle), .cpu = cpu, .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), }; + INIT_WORK(&c_idle.work, do_fork_idle); /* allocate memory for gdts of secondary cpus. Hotplug is considered */ if (!cpu_gdt_descr[cpu].address && diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 02f0f61f5b11..c28c342c162f 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -25,6 +25,8 @@ static int save_stack_stack(void *data, char *name) static void save_stack_address(void *data, unsigned long addr, int reliable) { struct stack_trace *trace = data; + if (!reliable) + return; if (trace->skip > 0) { trace->skip--; return; @@ -37,6 +39,8 @@ static void save_stack_address_nosched(void *data, unsigned long addr, int reliable) { struct stack_trace *trace = (struct stack_trace *)data; + if (!reliable) + return; if (in_sched_functions(addr)) return; if (trace->skip > 0) { diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 2ef1a5f8d675..071ff4798236 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -140,6 +140,9 @@ static int enable_single_step(struct task_struct *child) */ static void write_debugctlmsr(struct task_struct *child, unsigned long val) { + if (child->thread.debugctlmsr == val) + return; + child->thread.debugctlmsr = val; if (child != current) @@ -165,11 +168,11 @@ static void enable_step(struct task_struct *child, bool block) write_debugctlmsr(child, child->thread.debugctlmsr | DEBUGCTLMSR_BTF); } else { - write_debugctlmsr(child, - child->thread.debugctlmsr & ~TIF_DEBUGCTLMSR); + write_debugctlmsr(child, + child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF); - if (!child->thread.debugctlmsr) - clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); + if (!child->thread.debugctlmsr) + clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); } } @@ -189,7 +192,7 @@ void user_disable_single_step(struct task_struct *child) * Make sure block stepping (BTF) is disabled. */ write_debugctlmsr(child, - child->thread.debugctlmsr & ~TIF_DEBUGCTLMSR); + child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF); if (!child->thread.debugctlmsr) clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 6dfd4e76661a..ab6bf375a307 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -91,7 +91,9 @@ int do_set_thread_area(struct task_struct *p, int idx, asmlinkage int sys_set_thread_area(struct user_desc __user *u_info) { - return do_set_thread_area(current, -1, u_info, 1); + int ret = do_set_thread_area(current, -1, u_info, 1); + asmlinkage_protect(1, ret, u_info); + return ret; } @@ -139,7 +141,9 @@ int do_get_thread_area(struct task_struct *p, int idx, asmlinkage int sys_get_thread_area(struct user_desc __user *u_info) { - return do_get_thread_area(current, -1, u_info); + int ret = do_get_thread_area(current, -1, u_info); + asmlinkage_protect(1, ret, u_info); + return ret; } int regset_tls_active(struct task_struct *target, diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c index 43517e324be8..c2241e04ea5f 100644 --- a/arch/x86/kernel/tsc_32.c +++ b/arch/x86/kernel/tsc_32.c @@ -28,7 +28,8 @@ EXPORT_SYMBOL_GPL(tsc_khz); static int __init tsc_setup(char *str) { printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, " - "cannot disable TSC.\n"); + "cannot disable TSC completely.\n"); + mark_tsc_unstable("user disabled TSC"); return 1; } #else @@ -255,9 +256,7 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) ref_freq, freq->new); if (!(freq->flags & CPUFREQ_CONST_LOOPS)) { tsc_khz = cpu_khz; - preempt_disable(); - set_cyc2ns_scale(cpu_khz, smp_processor_id()); - preempt_enable(); + set_cyc2ns_scale(cpu_khz, freq->cpu); /* * TSC based sched_clock turns * to junk w/ cpufreq diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c index 947554ddabb6..d3bebaaad842 100644 --- a/arch/x86/kernel/tsc_64.c +++ b/arch/x86/kernel/tsc_64.c @@ -148,9 +148,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, mark_tsc_unstable("cpufreq changes"); } - preempt_disable(); - set_cyc2ns_scale(tsc_khz_ref, smp_processor_id()); - preempt_enable(); + set_cyc2ns_scale(tsc_khz_ref, freq->cpu); return 0; } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 3f8242774580..edff4c985485 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -44,11 +44,6 @@ #define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr))) #define __syscall_clobber "r11","cx","memory" -#define __pa_vsymbol(x) \ - ({unsigned long v; \ - extern char __vsyscall_0; \ - asm("" : "=r" (v) : "0" (x)); \ - ((v - VSYSCALL_START) + __pa_symbol(&__vsyscall_0)); }) /* * vsyscall_gtod_data contains data that is : @@ -102,7 +97,7 @@ static __always_inline void do_get_tz(struct timezone * tz) static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz) { int ret; - asm volatile("vsysc2: syscall" + asm volatile("syscall" : "=a" (ret) : "0" (__NR_gettimeofday),"D" (tv),"S" (tz) : __syscall_clobber ); @@ -112,7 +107,7 @@ static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz) static __always_inline long time_syscall(long *t) { long secs; - asm volatile("vsysc1: syscall" + asm volatile("syscall" : "=a" (secs) : "0" (__NR_time),"D" (t) : __syscall_clobber); return secs; @@ -228,42 +223,11 @@ long __vsyscall(3) venosys_1(void) #ifdef CONFIG_SYSCTL -#define SYSCALL 0x050f -#define NOP2 0x9090 - -/* - * NOP out syscall in vsyscall page when not needed. - */ -static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int +vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, + void __user *buffer, size_t *lenp, loff_t *ppos) { - extern u16 vsysc1, vsysc2; - u16 __iomem *map1; - u16 __iomem *map2; - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); - if (!write) - return ret; - /* gcc has some trouble with __va(__pa()), so just do it this - way. */ - map1 = ioremap(__pa_vsymbol(&vsysc1), 2); - if (!map1) - return -ENOMEM; - map2 = ioremap(__pa_vsymbol(&vsysc2), 2); - if (!map2) { - ret = -ENOMEM; - goto out; - } - if (!vsyscall_gtod_data.sysctl_enabled) { - writew(SYSCALL, map1); - writew(SYSCALL, map2); - } else { - writew(NOP2, map1); - writew(NOP2, map2); - } - iounmap(map2); -out: - iounmap(map1); - return ret; + return proc_dointvec(ctl, write, filp, buffer, lenp, ppos); } static ctl_table kernel_table2[] = { @@ -279,7 +243,6 @@ static ctl_table kernel_root_table2[] = { .child = kernel_table2 }, {} }; - #endif /* Assume __initcall executes before all user space. Hopefully kmod |