diff options
Diffstat (limited to 'arch/x86')
77 files changed, 1063 insertions, 697 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3be2305709b..6c70fed0f9a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -21,7 +21,8 @@ config X86 select HAVE_IDE select HAVE_OPROFILE select HAVE_KPROBES - select HAVE_KVM + select HAVE_KRETPROBES + select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) config GENERIC_LOCKBREAK @@ -65,9 +66,6 @@ config MMU config ZONE_DMA def_bool y -config QUICKLIST - def_bool X86_32 - config SBUS bool @@ -1054,7 +1052,7 @@ config SECCOMP config CC_STACKPROTECTOR bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)" - depends on X86_64 && EXPERIMENTAL + depends on X86_64 && EXPERIMENTAL && BROKEN help This option turns on the -fstack-protector GCC feature. This feature puts, at the beginning of critical functions, a canary @@ -1261,7 +1259,7 @@ menuconfig APM machines with more than one CPU. In order to use APM, you will need supporting software. For location - and more information, read <file:Documentation/pm.txt> and the + and more information, read <file:Documentation/power/pm.txt> and the Battery Powered Linux mini-HOWTO, available from <http://www.tldp.org/docs.html#howto>. diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index e09a6b73a1a..9304bfba7d4 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -377,6 +377,19 @@ config X86_OOSTORE def_bool y depends on (MWINCHIP3D || MWINCHIP2 || MWINCHIPC6) && MTRR +# +# P6_NOPs are a relatively minor optimization that require a family >= +# 6 processor, except that it is broken on certain VIA chips. +# Furthermore, AMD chips prefer a totally different sequence of NOPs +# (which work on all CPUs). As a result, disallow these if we're +# compiling X86_GENERIC but not X86_64 (these NOPs do work on all +# x86-64 capable chips); the list of processors in the right-hand clause +# are the cores that benefit from this optimization. +# +config X86_P6_NOP + def_bool y + depends on (X86_64 || !X86_GENERIC) && (M686 || MPENTIUMII || MPENTIUMIII || MPENTIUMM || MCORE2 || MPENTIUM4) + config X86_TSC def_bool y depends on ((MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64 @@ -390,6 +403,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 + default "6" if X86_32 && X86_P6_NOP default "4" if X86_32 && (X86_XADD || X86_CMPXCHG || X86_BSWAP || X86_WP_WORKS_OK) default "3" diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index 378353956b5..e77d89f9e8a 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -37,6 +37,12 @@ static int detect_memory_e820(void) "=m" (*desc) : "D" (desc), "d" (SMAP), "a" (0xe820)); + /* BIOSes which terminate the chain with CF = 1 as opposed + to %ebx = 0 don't always report the SMAP signature on + the final, failing, probe. */ + if (err) + break; + /* Some BIOSes stop returning SMAP in the middle of the search loop. We don't know exactly how the BIOS screwed up the map at that point, we might have a @@ -47,9 +53,6 @@ static int detect_memory_e820(void) break; } - if (err) - break; - count++; desc++; } while (next && count < E820MAX); diff --git a/arch/x86/boot/vesa.h b/arch/x86/boot/vesa.h index ff5b73cd406..468e444622c 100644 --- a/arch/x86/boot/vesa.h +++ b/arch/x86/boot/vesa.h @@ -26,17 +26,10 @@ struct vesa_general_info { far_ptr video_mode_ptr; /* 14 */ u16 total_memory; /* 18 */ - u16 oem_software_rev; /* 20 */ - far_ptr oem_vendor_name_ptr; /* 22 */ - far_ptr oem_product_name_ptr; /* 26 */ - far_ptr oem_product_rev_ptr; /* 30 */ - - u8 reserved[222]; /* 34 */ - u8 oem_data[256]; /* 256 */ + u8 reserved[236]; /* 20 */ } __attribute__ ((packed)); #define VESA_MAGIC ('V' + ('E' << 8) + ('S' << 16) + ('A' << 24)) -#define VBE2_MAGIC ('V' + ('B' << 8) + ('E' << 16) + ('2' << 24)) struct vesa_mode_info { u16 mode_attr; /* 0 */ diff --git a/arch/x86/boot/video-vesa.c b/arch/x86/boot/video-vesa.c index 662dd2f1306..419b5c27337 100644 --- a/arch/x86/boot/video-vesa.c +++ b/arch/x86/boot/video-vesa.c @@ -37,8 +37,6 @@ static int vesa_probe(void) video_vesa.modes = GET_HEAP(struct mode_info, 0); - vginfo.signature = VBE2_MAGIC; - ax = 0x4f00; di = (size_t)&vginfo; asm(INT10 diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 1c0503bdfb1..5e7771a3ba2 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -500,7 +500,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, regs->ss = __USER32_DS; 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); @@ -600,7 +600,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->ss = __USER32_DS; 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); diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 680b7300a48..2cdc9de9371 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 45d79ea890a..5fed98ca0e1 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 608152a2a05..00df126169b 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 a33d5301799..8ea040124f7 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 027e5c003b1..170d2f5523b 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 f86a3c4a266..a38aafaefc2 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 39f8cb18296..c2f930d8664 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 f2b5a621d27..8a85c93bd62 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 103d61a59b1..3e18db4cefe 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 b6e136f23d3..a6450b3ae75 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 9b838324b81..b943e10ad81 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 200fb3f9ebf..e8b422c1c51 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 4e16ef4a265..80444c5c9b1 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 9f65b4cc323..9be69712601 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 2ad9a1bc6a7..c20c9e7e08d 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 25eb98540a4..74d87ea85b5 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 eb415043a92..a007454133a 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 429d084e014..36652ea1a26 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 763dfc40723..d2e39e69aaf 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 5b3ce793436..3d01e47777d 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 c706a306155..5921e5f0a64 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 236d2f8f7dd..576a03db451 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 027fc067b39..b402c0f3f19 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 a82473d192a..375cb2bc45b 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 faf3229f8fb..700e4647dd3 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 a7d50a547dc..43930e73f65 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 b0cc8f0136d..46c4c546b49 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 702c33efea8..eb92ccbb350 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 c47208fc593..d89a648fe71 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 7fd6ac43e4a..484c4a80d38 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 309366f8f60..e24c4567709 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 a1d7071a51c..2b3e5d45176 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 6fd804f0782..f4f7ecfb898 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 caee1f002fe..0157a6f0f41 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 7347bb14e30..1c83e5124c6 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 d53bd6fcb42..0880f2c388a 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 02f0f61f5b1..c28c342c162 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 2ef1a5f8d67..071ff479823 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 6dfd4e76661..ab6bf375a30 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 43517e324be..c2241e04ea5 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 947554ddabb..d3bebaaad84 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 3f824277458..edff4c98548 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 diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 2cbee9479ce..68a6b151193 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -647,6 +647,10 @@ static void start_apic_timer(struct kvm_lapic *apic) apic->timer.period = apic_get_reg(apic, APIC_TMICT) * APIC_BUS_CYCLE_NS * apic->timer.divide_count; atomic_set(&apic->timer.pending, 0); + + if (!apic->timer.period) + return; + hrtimer_start(&apic->timer.dev, ktime_add_ns(now, apic->timer.period), HRTIMER_MODE_ABS); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8efdcdbebb0..e55af12e11b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -222,8 +222,7 @@ static int is_io_pte(unsigned long pte) static int is_rmap_pte(u64 pte) { - return pte != shadow_trap_nonpresent_pte - && pte != shadow_notrap_nonpresent_pte; + return is_shadow_present_pte(pte); } static gfn_t pse36_gfn_delta(u32 gpte) @@ -681,8 +680,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, unsigned level, int metaphysical, unsigned access, - u64 *parent_pte, - bool *new_page) + u64 *parent_pte) { union kvm_mmu_page_role role; unsigned index; @@ -722,8 +720,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, vcpu->arch.mmu.prefetch_page(vcpu, sp); if (!metaphysical) rmap_write_protect(vcpu->kvm, gfn); - if (new_page) - *new_page = 1; return sp; } @@ -876,11 +872,18 @@ static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn) struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva) { + struct page *page; + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva); if (gpa == UNMAPPED_GVA) return NULL; - return gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + + down_read(¤t->mm->mmap_sem); + page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + up_read(¤t->mm->mmap_sem); + + return page; } static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, @@ -889,14 +892,25 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, int *ptwrite, gfn_t gfn, struct page *page) { u64 spte; - int was_rmapped = is_rmap_pte(*shadow_pte); + int was_rmapped = 0; int was_writeble = is_writeble_pte(*shadow_pte); + hfn_t host_pfn = (*shadow_pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; pgprintk("%s: spte %llx access %x write_fault %d" " user_fault %d gfn %lx\n", __FUNCTION__, *shadow_pte, pt_access, write_fault, user_fault, gfn); + if (is_rmap_pte(*shadow_pte)) { + if (host_pfn != page_to_pfn(page)) { + pgprintk("hfn old %lx new %lx\n", + host_pfn, page_to_pfn(page)); + rmap_remove(vcpu->kvm, shadow_pte); + } + else + was_rmapped = 1; + } + /* * We don't set the accessed bit, since we sometimes want to see * whether the guest actually used the pte (in order to detect @@ -999,8 +1013,7 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, >> PAGE_SHIFT; new_table = kvm_mmu_get_page(vcpu, pseudo_gfn, v, level - 1, - 1, ACC_ALL, &table[index], - NULL); + 1, ACC_ALL, &table[index]); if (!new_table) { pgprintk("nonpaging_map: ENOMEM\n"); kvm_release_page_clean(page); @@ -1020,15 +1033,18 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) struct page *page; + down_read(&vcpu->kvm->slots_lock); + down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, gfn); + up_read(¤t->mm->mmap_sem); spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); r = __nonpaging_map(vcpu, v, write, gfn, page); spin_unlock(&vcpu->kvm->mmu_lock); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return r; } @@ -1090,7 +1106,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); sp = kvm_mmu_get_page(vcpu, root_gfn, 0, - PT64_ROOT_LEVEL, 0, ACC_ALL, NULL, NULL); + PT64_ROOT_LEVEL, 0, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; vcpu->arch.mmu.root_hpa = root; @@ -1111,7 +1127,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) root_gfn = 0; sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, !is_paging(vcpu), - ACC_ALL, NULL, NULL); + ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK; @@ -1172,7 +1188,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) static void paging_new_cr3(struct kvm_vcpu *vcpu) { - pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->cr3); + pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->arch.cr3); mmu_free_roots(vcpu); } @@ -1362,6 +1378,7 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, gfn_t gfn; int r; u64 gpte = 0; + struct page *page; if (bytes != 4 && bytes != 8) return; @@ -1389,8 +1406,13 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if (!is_present_pte(gpte)) return; gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; + + down_read(¤t->mm->mmap_sem); + page = gfn_to_page(vcpu->kvm, gfn); + up_read(¤t->mm->mmap_sem); + vcpu->arch.update_pte.gfn = gfn; - vcpu->arch.update_pte.page = gfn_to_page(vcpu->kvm, gfn); + vcpu->arch.update_pte.page = page; } void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -1496,9 +1518,9 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) gpa_t gpa; int r; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); spin_lock(&vcpu->kvm->mmu_lock); r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 03ba8608fe0..ecc0856268c 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -91,7 +91,10 @@ static bool FNAME(cmpxchg_gpte)(struct kvm *kvm, pt_element_t *table; struct page *page; + down_read(¤t->mm->mmap_sem); page = gfn_to_page(kvm, table_gfn); + up_read(¤t->mm->mmap_sem); + table = kmap_atomic(page, KM_USER0); ret = CMPXCHG(&table[index], orig_pte, new_pte); @@ -140,7 +143,7 @@ walk: } #endif ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) || - (vcpu->cr3 & CR3_NONPAE_RESERVED_BITS) == 0); + (vcpu->arch.cr3 & CR3_NONPAE_RESERVED_BITS) == 0); pt_access = ACC_ALL; @@ -297,7 +300,6 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, u64 shadow_pte; int metaphysical; gfn_t table_gfn; - bool new_page = 0; shadow_ent = ((u64 *)__va(shadow_addr)) + index; if (level == PT_PAGE_TABLE_LEVEL) @@ -319,8 +321,8 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, } shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1, metaphysical, access, - shadow_ent, &new_page); - if (new_page && !metaphysical) { + shadow_ent); + if (!metaphysical) { int r; pt_element_t curr_pte; r = kvm_read_guest_atomic(vcpu->kvm, @@ -378,7 +380,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, if (r) return r; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); /* * Look up the shadow pte for the faulting address. */ @@ -392,11 +394,13 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, pgprintk("%s: guest page fault\n", __FUNCTION__); inject_page_fault(vcpu, addr, walker.error_code); vcpu->arch.last_pt_write_count = 0; /* reset fork detector */ - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return 0; } + down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, walker.gfn); + up_read(¤t->mm->mmap_sem); spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); @@ -413,14 +417,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, */ if (shadow_pte && is_io_pte(*shadow_pte)) { spin_unlock(&vcpu->kvm->mmu_lock); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return 1; } ++vcpu->stat.pf_fixed; kvm_mmu_audit(vcpu, "post page fault (fixed)"); spin_unlock(&vcpu->kvm->mmu_lock); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return write_pt; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index de755cb1431..1a582f1090e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -792,6 +792,10 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) vcpu->arch.cr0 = cr0; cr0 |= X86_CR0_PG | X86_CR0_WP; cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + if (!vcpu->fpu_active) { + svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR); + cr0 |= X86_CR0_TS; + } svm->vmcb->save.cr0 = cr0; } @@ -1096,6 +1100,24 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) case MSR_IA32_SYSENTER_ESP: *data = svm->vmcb->save.sysenter_esp; break; + /* Nobody will change the following 5 values in the VMCB so + we can safely return them on rdmsr. They will always be 0 + until LBRV is implemented. */ + case MSR_IA32_DEBUGCTLMSR: + *data = svm->vmcb->save.dbgctl; + break; + case MSR_IA32_LASTBRANCHFROMIP: + *data = svm->vmcb->save.br_from; + break; + case MSR_IA32_LASTBRANCHTOIP: + *data = svm->vmcb->save.br_to; + break; + case MSR_IA32_LASTINTFROMIP: + *data = svm->vmcb->save.last_excp_from; + break; + case MSR_IA32_LASTINTTOIP: + *data = svm->vmcb->save.last_excp_to; + break; default: return kvm_get_msr_common(vcpu, ecx, data); } @@ -1156,6 +1178,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) case MSR_IA32_SYSENTER_ESP: svm->vmcb->save.sysenter_esp = data; break; + case MSR_IA32_DEBUGCTLMSR: + pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __FUNCTION__, data); + break; case MSR_K7_EVNTSEL0: case MSR_K7_EVNTSEL1: case MSR_K7_EVNTSEL2: diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ad36447e696..8e1462880d1 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -349,8 +349,6 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) static void reload_tss(void) { -#ifndef CONFIG_X86_64 - /* * VT restores TR but not its size. Useless. */ @@ -361,7 +359,6 @@ static void reload_tss(void) descs = (void *)gdt.base; descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ load_TR_desc(); -#endif } static void load_transition_efer(struct vcpu_vmx *vmx) @@ -638,6 +635,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) { int save_nmsrs; + vmx_load_host_state(vmx); save_nmsrs = 0; #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) { @@ -1435,7 +1433,7 @@ static int init_rmode_tss(struct kvm *kvm) int ret = 0; int r; - down_read(¤t->mm->mmap_sem); + down_read(&kvm->slots_lock); r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -1458,7 +1456,7 @@ static int init_rmode_tss(struct kvm *kvm) ret = 1; out: - up_read(¤t->mm->mmap_sem); + up_read(&kvm->slots_lock); return ret; } @@ -1477,7 +1475,7 @@ static int alloc_apic_access_page(struct kvm *kvm) struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; - down_write(¤t->mm->mmap_sem); + down_write(&kvm->slots_lock); if (kvm->arch.apic_access_page) goto out; kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; @@ -1487,9 +1485,12 @@ static int alloc_apic_access_page(struct kvm *kvm) r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); if (r) goto out; + + down_read(¤t->mm->mmap_sem); kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00); + up_read(¤t->mm->mmap_sem); out: - up_write(¤t->mm->mmap_sem); + up_write(&kvm->slots_lock); return r; } @@ -1602,9 +1603,6 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); - if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) - if (alloc_apic_access_page(vmx->vcpu.kvm) != 0) - return -ENOMEM; return 0; } @@ -2534,6 +2532,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) put_cpu(); if (err) goto free_vmcs; + if (vm_need_virtualize_apic_accesses(kvm)) + if (alloc_apic_access_page(kvm) != 0) + goto free_vmcs; return &vmx->vcpu; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cf530814868..6b01552bd1f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -46,6 +46,9 @@ #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); + struct kvm_x86_ops *kvm_x86_ops; struct kvm_stats_debugfs_item debugfs_entries[] = { @@ -181,7 +184,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) int ret; u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)]; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte, offset * sizeof(u64), sizeof(pdpte)); if (ret < 0) { @@ -198,7 +201,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs)); out: - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return ret; } @@ -212,13 +215,13 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu) if (is_long_mode(vcpu) || !is_pae(vcpu)) return false; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte)); if (r < 0) goto out; changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0; out: - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return changed; } @@ -356,7 +359,7 @@ void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) */ } - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); /* * Does the new cr3 value map to physical memory? (Note, we * catch an invalid cr3 even in real-mode, because it would @@ -372,7 +375,7 @@ void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) vcpu->arch.cr3 = cr3; vcpu->arch.mmu.new_cr3(vcpu); } - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); } EXPORT_SYMBOL_GPL(set_cr3); @@ -484,6 +487,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n", __FUNCTION__, data); break; + case MSR_IA32_MCG_CTL: + pr_unimpl(vcpu, "%s: MSR_IA32_MCG_CTL 0x%llx, nop\n", + __FUNCTION__, data); + break; case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: case 0x200 ... 0x2ff: /* MTRRs */ @@ -526,6 +533,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_MC0_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MCG_CAP: + case MSR_IA32_MCG_CTL: case MSR_IA32_MC0_MISC: case MSR_IA32_MC0_MISC+4: case MSR_IA32_MC0_MISC+8: @@ -727,6 +735,24 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } + case KVM_GET_SUPPORTED_CPUID: { + struct kvm_cpuid2 __user *cpuid_arg = argp; + struct kvm_cpuid2 cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + r = kvm_dev_ioctl_get_supported_cpuid(&cpuid, + cpuid_arg->entries); + if (r) + goto out; + + r = -EFAULT; + if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid)) + goto out; + r = 0; + break; + } default: r = -EINVAL; } @@ -974,8 +1000,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, put_cpu(); } -static int kvm_vm_ioctl_get_supported_cpuid(struct kvm *kvm, - struct kvm_cpuid2 *cpuid, +static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { struct kvm_cpuid_entry2 *cpuid_entries; @@ -1207,12 +1232,12 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; - down_write(¤t->mm->mmap_sem); + down_write(&kvm->slots_lock); kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages; - up_write(¤t->mm->mmap_sem); + up_write(&kvm->slots_lock); return 0; } @@ -1261,7 +1286,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, < alias->target_phys_addr) goto out; - down_write(¤t->mm->mmap_sem); + down_write(&kvm->slots_lock); p = &kvm->arch.aliases[alias->slot]; p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT; @@ -1275,7 +1300,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, kvm_mmu_zap_all(kvm); - up_write(¤t->mm->mmap_sem); + up_write(&kvm->slots_lock); return 0; @@ -1351,7 +1376,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot; int is_dirty = 0; - down_write(¤t->mm->mmap_sem); + down_write(&kvm->slots_lock); r = kvm_get_dirty_log(kvm, log, &is_dirty); if (r) @@ -1367,7 +1392,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, } r = 0; out: - up_write(¤t->mm->mmap_sem); + up_write(&kvm->slots_lock); return r; } @@ -1487,24 +1512,6 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } - case KVM_GET_SUPPORTED_CPUID: { - struct kvm_cpuid2 __user *cpuid_arg = argp; - struct kvm_cpuid2 cpuid; - - r = -EFAULT; - if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) - goto out; - r = kvm_vm_ioctl_get_supported_cpuid(kvm, &cpuid, - cpuid_arg->entries); - if (r) - goto out; - - r = -EFAULT; - if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid)) - goto out; - r = 0; - break; - } default: ; } @@ -1563,7 +1570,7 @@ int emulator_read_std(unsigned long addr, void *data = val; int r = X86EMUL_CONTINUE; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); while (bytes) { gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); unsigned offset = addr & (PAGE_SIZE-1); @@ -1585,7 +1592,7 @@ int emulator_read_std(unsigned long addr, addr += tocopy; } out: - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return r; } EXPORT_SYMBOL_GPL(emulator_read_std); @@ -1604,9 +1611,9 @@ static int emulator_read_emulated(unsigned long addr, return X86EMUL_CONTINUE; } - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); /* For APIC access vmexit */ if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) @@ -1644,14 +1651,14 @@ static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, { int ret; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); if (ret < 0) { - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return 0; } kvm_mmu_pte_write(vcpu, gpa, val, bytes); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return 1; } @@ -1663,9 +1670,9 @@ static int emulator_write_emulated_onepage(unsigned long addr, struct kvm_io_device *mmio_dev; gpa_t gpa; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); if (gpa == UNMAPPED_GVA) { kvm_inject_page_fault(vcpu, addr, 2); @@ -1742,7 +1749,7 @@ static int emulator_cmpxchg_emulated(unsigned long addr, char *kaddr; u64 val; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); if (gpa == UNMAPPED_GVA || @@ -1753,13 +1760,17 @@ static int emulator_cmpxchg_emulated(unsigned long addr, goto emul_write; val = *(u64 *)new; + + down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + up_read(¤t->mm->mmap_sem); + kaddr = kmap_atomic(page, KM_USER0); set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val); kunmap_atomic(kaddr, KM_USER0); kvm_release_page_dirty(page); emul_write: - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); } #endif @@ -2152,10 +2163,10 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, kvm_x86_ops->skip_emulated_instruction(vcpu); for (i = 0; i < nr_pages; ++i) { - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); page = gva_to_page(vcpu, address + i * PAGE_SIZE); vcpu->arch.pio.guest_pages[i] = page; - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); if (!page) { kvm_inject_gp(vcpu, 0); free_pio_guest_pages(vcpu); @@ -2478,8 +2489,9 @@ static void vapic_enter(struct kvm_vcpu *vcpu) down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); - vcpu->arch.apic->vapic_page = page; up_read(¤t->mm->mmap_sem); + + vcpu->arch.apic->vapic_page = page; } static void vapic_exit(struct kvm_vcpu *vcpu) @@ -2861,8 +2873,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, kvm_x86_ops->decache_cr4_guest_bits(vcpu); mmu_reset_needed |= vcpu->arch.cr0 != sregs->cr0; - vcpu->arch.cr0 = sregs->cr0; kvm_x86_ops->set_cr0(vcpu, sregs->cr0); + vcpu->arch.cr0 = sregs->cr0; mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); @@ -2952,9 +2964,9 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, gpa_t gpa; vcpu_load(vcpu); - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vaddr); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); tr->physical_address = gpa; tr->valid = gpa != UNMAPPED_GVA; tr->writeable = 1; @@ -3227,11 +3239,13 @@ int kvm_arch_set_memory_region(struct kvm *kvm, */ if (!user_alloc) { if (npages && !old.rmap) { + down_write(¤t->mm->mmap_sem); memslot->userspace_addr = do_mmap(NULL, 0, npages * PAGE_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, 0); + up_write(¤t->mm->mmap_sem); if (IS_ERR((void *)memslot->userspace_addr)) return PTR_ERR((void *)memslot->userspace_addr); @@ -3239,8 +3253,10 @@ int kvm_arch_set_memory_region(struct kvm *kvm, if (!old.user_alloc && old.rmap) { int ret; + down_write(¤t->mm->mmap_sem); ret = do_munmap(current->mm, old.userspace_addr, old.npages * PAGE_SIZE); + up_write(¤t->mm->mmap_sem); if (ret < 0) printk(KERN_WARNING "kvm_vm_ioctl_set_memory_region: " diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 5afdde4895d..3335b4595ef 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -10,21 +10,19 @@ * (such as the example in Documentation/lguest/lguest.c) is called the * Launcher. * - * Secondly, we only run specially modified Guests, not normal kernels. When - * you set CONFIG_LGUEST to 'y' or 'm', this automatically sets - * CONFIG_LGUEST_GUEST=y, which compiles this file into the kernel so it knows - * how to be a Guest. This means that you can use the same kernel you boot - * normally (ie. as a Host) as a Guest. + * Secondly, we only run specially modified Guests, not normal kernels: setting + * CONFIG_LGUEST_GUEST to "y" compiles this file into the kernel so it knows + * how to be a Guest at boot time. This means that you can use the same kernel + * you boot normally (ie. as a Host) as a Guest. * * These Guests know that they cannot do privileged operations, such as disable * interrupts, and that they have to ask the Host to do such things explicitly. * This file consists of all the replacements for such low-level native * hardware operations: these special Guest versions call the Host. * - * So how does the kernel know it's a Guest? The Guest starts at a special - * entry point marked with a magic string, which sets up a few things then - * calls here. We replace the native functions various "paravirt" structures - * with our Guest versions, then boot like normal. :*/ + * So how does the kernel know it's a Guest? We'll see that later, but let's + * just say that we end up here where we replace the native functions various + * "paravirt" structures with our Guest versions, then boot like normal. :*/ /* * Copyright (C) 2006, Rusty Russell <rusty@rustcorp.com.au> IBM Corporation. @@ -57,6 +55,7 @@ #include <linux/lguest_launcher.h> #include <linux/virtio_console.h> #include <linux/pm.h> +#include <asm/lguest.h> #include <asm/paravirt.h> #include <asm/param.h> #include <asm/page.h> @@ -75,15 +74,6 @@ * behaving in simplified but equivalent ways. In particular, the Guest is the * same kernel as the Host (or at least, built from the same source code). :*/ -/* Declarations for definitions in lguest_guest.S */ -extern char lguest_noirq_start[], lguest_noirq_end[]; -extern const char lgstart_cli[], lgend_cli[]; -extern const char lgstart_sti[], lgend_sti[]; -extern const char lgstart_popf[], lgend_popf[]; -extern const char lgstart_pushf[], lgend_pushf[]; -extern const char lgstart_iret[], lgend_iret[]; -extern void lguest_iret(void); - struct lguest_data lguest_data = { .hcall_status = { [0 ... LHCALL_RING_SIZE-1] = 0xFF }, .noirq_start = (u32)lguest_noirq_start, @@ -92,7 +82,6 @@ struct lguest_data lguest_data = { .blocked_interrupts = { 1 }, /* Block timer interrupts */ .syscall_vec = SYSCALL_VECTOR, }; -static cycle_t clock_base; /*G:037 async_hcall() is pretty simple: I'm quite proud of it really. We have a * ring buffer of stored hypercalls which the Host will run though next time we @@ -143,7 +132,7 @@ static void async_hcall(unsigned long call, unsigned long arg1, * lguest_leave_lazy_mode(). * * So, when we're in lazy mode, we call async_hcall() to store the call for - * future processing. */ + * future processing: */ static void lazy_hcall(unsigned long call, unsigned long arg1, unsigned long arg2, @@ -156,7 +145,7 @@ static void lazy_hcall(unsigned long call, } /* When lazy mode is turned off reset the per-cpu lazy mode variable and then - * issue a hypercall to flush any stored calls. */ + * issue the do-nothing hypercall to flush any stored calls. */ static void lguest_leave_lazy_mode(void) { paravirt_leave_lazy(paravirt_get_lazy_mode()); @@ -173,7 +162,7 @@ static void lguest_leave_lazy_mode(void) * * So instead we keep an "irq_enabled" field inside our "struct lguest_data", * which the Guest can update with a single instruction. The Host knows to - * check there when it wants to deliver an interrupt. + * check there before it tries to deliver an interrupt. */ /* save_flags() is expected to return the processor state (ie. "flags"). The @@ -205,10 +194,15 @@ static void irq_enable(void) /*M:003 Note that we don't check for outstanding interrupts when we re-enable * them (or when we unmask an interrupt). This seems to work for the moment, * since interrupts are rare and we'll just get the interrupt on the next timer - * tick, but when we turn on CONFIG_NO_HZ, we should revisit this. One way + * tick, but now we can run with CONFIG_NO_HZ, we should revisit this. One way * would be to put the "irq_enabled" field in a page by itself, and have the * Host write-protect it when an interrupt comes in when irqs are disabled. - * There will then be a page fault as soon as interrupts are re-enabled. :*/ + * There will then be a page fault as soon as interrupts are re-enabled. + * + * A better method is to implement soft interrupt disable generally for x86: + * instead of disabling interrupts, we set a flag. If an interrupt does come + * in, we then disable them for real. This is uncommon, so we could simply use + * a hypercall for interrupt control and not worry about efficiency. :*/ /*G:034 * The Interrupt Descriptor Table (IDT). @@ -221,6 +215,10 @@ static void irq_enable(void) static void lguest_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g) { + /* The gate_desc structure is 8 bytes long: we hand it to the Host in + * two 32-bit chunks. The whole 32-bit kernel used to hand descriptors + * around like this; typesafety wasn't a big concern in Linux's early + * years. */ u32 *desc = (u32 *)g; /* Keep the local copy up to date. */ native_write_idt_entry(dt, entrynum, g); @@ -252,7 +250,8 @@ static void lguest_load_idt(const struct desc_ptr *desc) * * This is the opposite of the IDT code where we have a LOAD_IDT_ENTRY * hypercall and use that repeatedly to load a new IDT. I don't think it - * really matters, but wouldn't it be nice if they were the same? + * really matters, but wouldn't it be nice if they were the same? Wouldn't + * it be even better if you were the one to send the patch to fix it? */ static void lguest_load_gdt(const struct desc_ptr *desc) { @@ -307,9 +306,9 @@ static void lguest_load_tr_desc(void) /* The "cpuid" instruction is a way of querying both the CPU identity * (manufacturer, model, etc) and its features. It was introduced before the - * Pentium in 1993 and keeps getting extended by both Intel and AMD. As you - * might imagine, after a decade and a half this treatment, it is now a giant - * ball of hair. Its entry in the current Intel manual runs to 28 pages. + * Pentium in 1993 and keeps getting extended by both Intel, AMD and others. + * As you might imagine, after a decade and a half this treatment, it is now a + * giant ball of hair. Its entry in the current Intel manual runs to 28 pages. * * This instruction even it has its own Wikipedia entry. The Wikipedia entry * has been translated into 4 languages. I am not making this up! @@ -335,8 +334,8 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, case 1: /* Basic feature request. */ /* We only allow kernel to see SSE3, CMPXCHG16B and SSSE3 */ *cx &= 0x00002201; - /* SSE, SSE2, FXSR, MMX, CMOV, CMPXCHG8B, FPU. */ - *dx &= 0x07808101; + /* SSE, SSE2, FXSR, MMX, CMOV, CMPXCHG8B, TSC, FPU. */ + *dx &= 0x07808111; /* The Host can do a nice optimization if it knows that the * kernel mappings (addresses above 0xC0000000 or whatever * PAGE_OFFSET is set to) haven't changed. But Linux calls @@ -603,19 +602,25 @@ static unsigned long lguest_get_wallclock(void) return lguest_data.time.tv_sec; } +/* The TSC is an Intel thing called the Time Stamp Counter. The Host tells us + * what speed it runs at, or 0 if it's unusable as a reliable clock source. + * This matches what we want here: if we return 0 from this function, the x86 + * TSC clock will give up and not register itself. */ +static unsigned long lguest_cpu_khz(void) +{ + return lguest_data.tsc_khz; +} + +/* If we can't use the TSC, the kernel falls back to our lower-priority + * "lguest_clock", where we read the time value given to us by the Host. */ static cycle_t lguest_clock_read(void) { unsigned long sec, nsec; - /* If the Host tells the TSC speed, we can trust that. */ - if (lguest_data.tsc_khz) - return native_read_tsc(); - - /* If we can't use the TSC, we read the time value written by the Host. - * Since it's in two parts (seconds and nanoseconds), we risk reading - * it just as it's changing from 99 & 0.999999999 to 100 and 0, and - * getting 99 and 0. As Linux tends to come apart under the stress of - * time travel, we must be careful: */ + /* Since the time is in two parts (seconds and nanoseconds), we risk + * reading it just as it's changing from 99 & 0.999999999 to 100 and 0, + * and getting 99 and 0. As Linux tends to come apart under the stress + * of time travel, we must be careful: */ do { /* First we read the seconds part. */ sec = lguest_data.time.tv_sec; @@ -630,14 +635,14 @@ static cycle_t lguest_clock_read(void) /* Now if the seconds part has changed, try again. */ } while (unlikely(lguest_data.time.tv_sec != sec)); - /* Our non-TSC clock is in real nanoseconds. */ + /* Our lguest clock is in real nanoseconds. */ return sec*1000000000ULL + nsec; } -/* This is what we tell the kernel is our clocksource. */ +/* This is the fallback clocksource: lower priority than the TSC clocksource. */ static struct clocksource lguest_clock = { .name = "lguest", - .rating = 400, + .rating = 200, .read = lguest_clock_read, .mask = CLOCKSOURCE_MASK(64), .mult = 1 << 22, @@ -645,24 +650,22 @@ static struct clocksource lguest_clock = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -/* The "scheduler clock" is just our real clock, adjusted to start at zero */ -static unsigned long long lguest_sched_clock(void) -{ - return cyc2ns(&lguest_clock, lguest_clock_read() - clock_base); -} - /* We also need a "struct clock_event_device": Linux asks us to set it to go * off some time in the future. Actually, James Morris figured all this out, I * just applied the patch. */ static int lguest_clockevent_set_next_event(unsigned long delta, struct clock_event_device *evt) { + /* FIXME: I don't think this can ever happen, but James tells me he had + * to put this code in. Maybe we should remove it now. Anyone? */ if (delta < LG_CLOCK_MIN_DELTA) { if (printk_ratelimit()) printk(KERN_DEBUG "%s: small delta %lu ns\n", __FUNCTION__, delta); return -ETIME; } + + /* Please wake us this far in the future. */ hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0); return 0; } @@ -720,19 +723,8 @@ static void lguest_time_init(void) /* Set up the timer interrupt (0) to go to our simple timer routine */ set_irq_handler(0, lguest_time_irq); - /* Our clock structure looks like arch/x86/kernel/tsc_32.c if we can - * use the TSC, otherwise it's a dumb nanosecond-resolution clock. - * Either way, the "rating" is set so high that it's always chosen over - * any other clocksource. */ - if (lguest_data.tsc_khz) - lguest_clock.mult = clocksource_khz2mult(lguest_data.tsc_khz, - lguest_clock.shift); - clock_base = lguest_clock_read(); clocksource_register(&lguest_clock); - /* Now we've set up our clock, we can use it as the scheduler clock */ - pv_time_ops.sched_clock = lguest_sched_clock; - /* We can't set cpumask in the initializer: damn C limitations! Set it * here and register our timer device. */ lguest_clockevent.cpumask = cpumask_of_cpu(0); @@ -758,7 +750,7 @@ static void lguest_time_init(void) * will not tolerate us trying to use that), the stack pointer, and the number * of pages in the stack. */ static void lguest_load_sp0(struct tss_struct *tss, - struct thread_struct *thread) + struct thread_struct *thread) { lazy_hcall(LHCALL_SET_STACK, __KERNEL_DS|0x1, thread->sp0, THREAD_SIZE/PAGE_SIZE); @@ -806,9 +798,8 @@ static void lguest_safe_halt(void) hcall(LHCALL_HALT, 0, 0, 0); } -/* Perhaps CRASH isn't the best name for this hypercall, but we use it to get a - * message out when we're crashing as well as elegant termination like powering - * off. +/* The SHUTDOWN hypercall takes a string to describe what's happening, and + * an argument which says whether this to restart (reboot) the Guest or not. * * Note that the Host always prefers that the Guest speak in physical addresses * rather than virtual addresses, so we use __pa() here. */ @@ -836,8 +827,9 @@ static struct notifier_block paniced = { /* Setting up memory is fairly easy. */ static __init char *lguest_memory_setup(void) { - /* We do this here and not earlier because lockcheck barfs if we do it - * before start_kernel() */ + /* We do this here and not earlier because lockcheck used to barf if we + * did it before start_kernel(). I think we fixed that, so it'd be + * nice to move it back to lguest_init. Patch welcome... */ atomic_notifier_chain_register(&panic_notifier_list, &paniced); /* The Linux bootloader header contains an "e820" memory map: the @@ -870,12 +862,19 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) return len; } +/* Rebooting also tells the Host we're finished, but the RESTART flag tells the + * Launcher to reboot us. */ +static void lguest_restart(char *reason) +{ + hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0); +} + /*G:050 * Patching (Powerfully Placating Performance Pedants) * - * We have already seen that pv_ops structures let us replace simple - * native instructions with calls to the appropriate back end all throughout - * the kernel. This allows the same kernel to run as a Guest and as a native + * We have already seen that pv_ops structures let us replace simple native + * instructions with calls to the appropriate back end all throughout the + * kernel. This allows the same kernel to run as a Guest and as a native * kernel, but it's slow because of all the indirect branches. * * Remember that David Wheeler quote about "Any problem in computer science can @@ -928,14 +927,9 @@ static unsigned lguest_patch(u8 type, u16 clobber, void *ibuf, return insn_len; } -static void lguest_restart(char *reason) -{ - hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0); -} - -/*G:030 Once we get to lguest_init(), we know we're a Guest. The pv_ops - * structures in the kernel provide points for (almost) every routine we have - * to override to avoid privileged instructions. */ +/*G:030 Once we get to lguest_init(), we know we're a Guest. The various + * pv_ops structures in the kernel provide points for (almost) every routine we + * have to override to avoid privileged instructions. */ __init void lguest_init(void) { /* We're under lguest, paravirt is enabled, and we're running at @@ -1003,6 +997,7 @@ __init void lguest_init(void) /* time operations */ pv_time_ops.get_wallclock = lguest_get_wallclock; pv_time_ops.time_init = lguest_time_init; + pv_time_ops.get_cpu_khz = lguest_cpu_khz; /* Now is a good time to look at the implementations of these functions * before returning to the rest of lguest_init(). */ @@ -1022,9 +1017,9 @@ __init void lguest_init(void) * the normal data segment to get through booting. */ asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_DS) : "memory"); - /* The Host uses the top of the Guest's virtual address space for the - * Host<->Guest Switcher, and it tells us how big that is in - * lguest_data.reserve_mem, set up on the LGUEST_INIT hypercall. */ + /* The Host<->Guest Switcher lives at the top of our address space, and + * the Host told us how big it is when we made LGUEST_INIT hypercall: + * it put the answer in lguest_data.reserve_mem */ reserve_top_address(lguest_data.reserve_mem); /* If we don't initialize the lock dependency checker now, it crashes @@ -1046,6 +1041,7 @@ __init void lguest_init(void) /* Math is always hard! */ new_cpu_data.hard_math = 1; + /* We don't have features. We have puppies! Puppies! */ #ifdef CONFIG_X86_MCE mce_disabled = 1; #endif @@ -1063,10 +1059,11 @@ __init void lguest_init(void) virtio_cons_early_init(early_put_chars); /* Last of all, we set the power management poweroff hook to point to - * the Guest routine to power off. */ + * the Guest routine to power off, and the reboot hook to our restart + * routine. */ pm_power_off = lguest_power_off; - machine_ops.restart = lguest_restart; + /* Now we're set up, call start_kernel() in init/main.c and we proceed * to boot as normal. It never returns. */ start_kernel(); diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S index 95b6fbcded6..5c7cef34c9e 100644 --- a/arch/x86/lguest/i386_head.S +++ b/arch/x86/lguest/i386_head.S @@ -5,13 +5,20 @@ #include <asm/thread_info.h> #include <asm/processor-flags.h> -/*G:020 This is where we begin: head.S notes that the boot header's platform - * type field is "1" (lguest), so calls us here. +/*G:020 Our story starts with the kernel booting into startup_32 in + * arch/x86/kernel/head_32.S. It expects a boot header, which is created by + * the bootloader (the Launcher in our case). + * + * The startup_32 function does very little: it clears the uninitialized global + * C variables which we expect to be zero (ie. BSS) and then copies the boot + * header and kernel command line somewhere safe. Finally it checks the + * 'hardware_subarch' field. This was introduced in 2.6.24 for lguest and Xen: + * if it's set to '1' (lguest's assigned number), then it calls us here. * * WARNING: be very careful here! We're running at addresses equal to physical * addesses (around 0), not above PAGE_OFFSET as most code expectes * (eg. 0xC0000000). Jumps are relative, so they're OK, but we can't touch any - * data. + * data without remembering to subtract __PAGE_OFFSET! * * The .section line puts this code in .init.text so it will be discarded after * boot. */ @@ -24,7 +31,7 @@ ENTRY(lguest_entry) int $LGUEST_TRAP_ENTRY /* The Host put the toplevel pagetable in lguest_data.pgdir. The movsl - * instruction uses %esi implicitly as the source for the copy we' + * instruction uses %esi implicitly as the source for the copy we're * about to do. */ movl lguest_data - __PAGE_OFFSET + LGUEST_DATA_pgdir, %esi diff --git a/arch/x86/mach-rdc321x/gpio.c b/arch/x86/mach-rdc321x/gpio.c index 031269163bd..247f33d3a40 100644 --- a/arch/x86/mach-rdc321x/gpio.c +++ b/arch/x86/mach-rdc321x/gpio.c @@ -1,91 +1,194 @@ /* - * Copyright (C) 2007, OpenWrt.org, Florian Fainelli <florian@openwrt.org> - * RDC321x architecture specific GPIO support + * GPIO support for RDC SoC R3210/R8610 + * + * Copyright (C) 2007, Florian Fainelli <florian@openwrt.org> + * Copyright (C) 2008, Volker Weiss <dev@tintuc.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. */ -#include <linux/autoconf.h> -#include <linux/init.h> + +#include <linux/spinlock.h> #include <linux/io.h> #include <linux/types.h> #include <linux/module.h> -#include <linux/delay.h> +#include <asm/gpio.h> #include <asm/mach-rdc321x/rdc321x_defs.h> -static inline int rdc_gpio_is_valid(unsigned gpio) + +/* spin lock to protect our private copy of GPIO data register plus + the access to PCI conf registers. */ +static DEFINE_SPINLOCK(gpio_lock); + +/* copy of GPIO data registers */ +static u32 gpio_data_reg1; +static u32 gpio_data_reg2; + +static u32 gpio_request_data[2]; + + +static inline void rdc321x_conf_write(unsigned addr, u32 value) { - return (gpio <= RDC_MAX_GPIO); + outl((1 << 31) | (7 << 11) | addr, RDC3210_CFGREG_ADDR); + outl(value, RDC3210_CFGREG_DATA); } -static unsigned int rdc_gpio_read(unsigned gpio) +static inline void rdc321x_conf_or(unsigned addr, u32 value) { - unsigned int val; - - val = 0x80000000 | (7 << 11) | ((gpio&0x20?0x84:0x48)); - outl(val, RDC3210_CFGREG_ADDR); - udelay(10); - val = inl(RDC3210_CFGREG_DATA); - val |= (0x1 << (gpio & 0x1F)); - outl(val, RDC3210_CFGREG_DATA); - udelay(10); - val = 0x80000000 | (7 << 11) | ((gpio&0x20?0x88:0x4C)); - outl(val, RDC3210_CFGREG_ADDR); - udelay(10); - val = inl(RDC3210_CFGREG_DATA); - - return val; + outl((1 << 31) | (7 << 11) | addr, RDC3210_CFGREG_ADDR); + value |= inl(RDC3210_CFGREG_DATA); + outl(value, RDC3210_CFGREG_DATA); } -static void rdc_gpio_write(unsigned int val) +static inline u32 rdc321x_conf_read(unsigned addr) { - if (val) { - outl(val, RDC3210_CFGREG_DATA); - udelay(10); - } + outl((1 << 31) | (7 << 11) | addr, RDC3210_CFGREG_ADDR); + + return inl(RDC3210_CFGREG_DATA); } -int rdc_gpio_get_value(unsigned gpio) +/* configure pin as GPIO */ +static void rdc321x_configure_gpio(unsigned gpio) +{ + unsigned long flags; + + spin_lock_irqsave(&gpio_lock, flags); + rdc321x_conf_or(gpio < 32 + ? RDC321X_GPIO_CTRL_REG1 : RDC321X_GPIO_CTRL_REG2, + 1 << (gpio & 0x1f)); + spin_unlock_irqrestore(&gpio_lock, flags); +} + +/* initially setup the 2 copies of the gpio data registers. + This function must be called by the platform setup code. */ +void __init rdc321x_gpio_setup() +{ + /* this might not be, what others (BIOS, bootloader, etc.) + wrote to these registers before, but it's a good guess. Still + better than just using 0xffffffff. */ + + gpio_data_reg1 = rdc321x_conf_read(RDC321X_GPIO_DATA_REG1); + gpio_data_reg2 = rdc321x_conf_read(RDC321X_GPIO_DATA_REG2); +} + +/* determine, if gpio number is valid */ +static inline int rdc321x_is_gpio(unsigned gpio) +{ + return gpio <= RDC321X_MAX_GPIO; +} + +/* request GPIO */ +int rdc_gpio_request(unsigned gpio, const char *label) { - if (rdc_gpio_is_valid(gpio)) - return (int)rdc_gpio_read(gpio); - else + unsigned long flags; + + if (!rdc321x_is_gpio(gpio)) return -EINVAL; + + spin_lock_irqsave(&gpio_lock, flags); + if (gpio_request_data[(gpio & 0x20) ? 1 : 0] & (1 << (gpio & 0x1f))) + goto inuse; + gpio_request_data[(gpio & 0x20) ? 1 : 0] |= (1 << (gpio & 0x1f)); + spin_unlock_irqrestore(&gpio_lock, flags); + + return 0; +inuse: + spin_unlock_irqrestore(&gpio_lock, flags); + return -EINVAL; } -EXPORT_SYMBOL(rdc_gpio_get_value); +EXPORT_SYMBOL(rdc_gpio_request); -void rdc_gpio_set_value(unsigned gpio, int value) +/* release previously-claimed GPIO */ +void rdc_gpio_free(unsigned gpio) { - unsigned int val; + unsigned long flags; - if (!rdc_gpio_is_valid(gpio)) + if (!rdc321x_is_gpio(gpio)) return; - val = rdc_gpio_read(gpio); + spin_lock_irqsave(&gpio_lock, flags); + gpio_request_data[(gpio & 0x20) ? 1 : 0] &= ~(1 << (gpio & 0x1f)); + spin_unlock_irqrestore(&gpio_lock, flags); +} +EXPORT_SYMBOL(rdc_gpio_free); + +/* read GPIO pin */ +int rdc_gpio_get_value(unsigned gpio) +{ + u32 reg; + unsigned long flags; + + spin_lock_irqsave(&gpio_lock, flags); + reg = rdc321x_conf_read(gpio < 32 + ? RDC321X_GPIO_DATA_REG1 : RDC321X_GPIO_DATA_REG2); + spin_unlock_irqrestore(&gpio_lock, flags); - if (value) - val &= ~(0x1 << (gpio & 0x1F)); - else - val |= (0x1 << (gpio & 0x1F)); + return (1 << (gpio & 0x1f)) & reg ? 1 : 0; +} +EXPORT_SYMBOL(rdc_gpio_get_value); - rdc_gpio_write(val); +/* set GPIO pin to value */ +void rdc_gpio_set_value(unsigned gpio, int value) +{ + unsigned long flags; + u32 reg; + + reg = 1 << (gpio & 0x1f); + if (gpio < 32) { + spin_lock_irqsave(&gpio_lock, flags); + if (value) + gpio_data_reg1 |= reg; + else + gpio_data_reg1 &= ~reg; + rdc321x_conf_write(RDC321X_GPIO_DATA_REG1, gpio_data_reg1); + spin_unlock_irqrestore(&gpio_lock, flags); + } else { + spin_lock_irqsave(&gpio_lock, flags); + if (value) + gpio_data_reg2 |= reg; + else + gpio_data_reg2 &= ~reg; + rdc321x_conf_write(RDC321X_GPIO_DATA_REG2, gpio_data_reg2); + spin_unlock_irqrestore(&gpio_lock, flags); + } } EXPORT_SYMBOL(rdc_gpio_set_value); +/* configure GPIO pin as input */ int rdc_gpio_direction_input(unsigned gpio) { + if (!rdc321x_is_gpio(gpio)) + return -EINVAL; + + rdc321x_configure_gpio(gpio); + return 0; } EXPORT_SYMBOL(rdc_gpio_direction_input); +/* configure GPIO pin as output and set value */ int rdc_gpio_direction_output(unsigned gpio, int value) { + if (!rdc321x_is_gpio(gpio)) + return -EINVAL; + + gpio_set_value(gpio, value); + rdc321x_configure_gpio(gpio); + return 0; } EXPORT_SYMBOL(rdc_gpio_direction_output); - - diff --git a/arch/x86/mach-rdc321x/platform.c b/arch/x86/mach-rdc321x/platform.c index dda6024a586..a037041817c 100644 --- a/arch/x86/mach-rdc321x/platform.c +++ b/arch/x86/mach-rdc321x/platform.c @@ -62,6 +62,8 @@ static struct platform_device *rdc321x_devs[] = { static int __init rdc_board_setup(void) { + rdc321x_gpio_setup(); + return platform_add_devices(rdc321x_devs, ARRAY_SIZE(rdc321x_devs)); } diff --git a/arch/x86/mach-visws/traps.c b/arch/x86/mach-visws/traps.c index 843b67acf43..bfac6ba10f8 100644 --- a/arch/x86/mach-visws/traps.c +++ b/arch/x86/mach-visws/traps.c @@ -46,8 +46,9 @@ static __init void cobalt_init(void) */ set_fixmap(FIX_APIC_BASE, APIC_DEFAULT_PHYS_BASE); setup_local_APIC(); - printk(KERN_INFO "Local APIC Version %#lx, ID %#lx\n", - apic_read(APIC_LVR), apic_read(APIC_ID)); + printk(KERN_INFO "Local APIC Version %#x, ID %#x\n", + (unsigned int)apic_read(APIC_LVR), + (unsigned int)apic_read(APIC_ID)); set_fixmap(FIX_CO_CPU, CO_CPU_PHYS); set_fixmap(FIX_CO_APIC, CO_APIC_PHYS); diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c index c394ca0720b..8e25e06ff73 100644 --- a/arch/x86/mm/discontig_32.c +++ b/arch/x86/mm/discontig_32.c @@ -324,7 +324,6 @@ unsigned long __init setup_memory(void) * this space and use it to adjust the boundary between ZONE_NORMAL * and ZONE_HIGHMEM. */ - find_max_pfn(); get_memcfg_numa(); kva_pages = calculate_numa_remap_pages(); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fdc667422df..ec08d838985 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -91,12 +91,10 @@ static int is_prefetch(struct pt_regs *regs, unsigned long addr, int prefetch = 0; unsigned char *max_instr; -#ifdef CONFIG_X86_32 - if (!(__supported_pte_mask & _PAGE_NX)) - return 0; -#endif - - /* If it was a exec fault on NX page, ignore */ + /* + * If it was a exec (instruction fetch) fault on NX page, then + * do not ignore the fault: + */ if (error_code & PF_INSTR) return 0; diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 3d936f23270..9cf33d3ee5b 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -73,15 +73,15 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) { enum fixed_addresses idx; unsigned long vaddr; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ - - debug_kmap_atomic_prot(type); + /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ pagefault_disable(); if (!PageHighMem(page)) return page_address(page); + debug_kmap_atomic_prot(type); + idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); BUG_ON(!pte_none(*(kmap_pte-idx))); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 4fbafb4bc2f..0b3d567e686 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -178,7 +178,7 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)]; - WARN_ON(!PageCompound(page)); + WARN_ON(!PageHead(page)); return page; } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index bb652f5a93f..a02a14f0f32 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -172,8 +172,9 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot) } /* - * The head.S code sets up the kernel high mapping from: - * __START_KERNEL_map to __START_KERNEL_map + KERNEL_TEXT_SIZE + * The head.S code sets up the kernel high mapping: + * + * from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text) * * phys_addr holds the negative offset to the kernel, which is added * to the compile time generated pmds. This results in invalid pmds up @@ -515,14 +516,6 @@ void __init mem_init(void) /* clear_bss() already clear the empty_zero_page */ - /* temporary debugging - double check it's true: */ - { - int i; - - for (i = 0; i < 1024; i++) - WARN_ON_ONCE(empty_zero_page[i]); - } - reservedpages = 0; /* this will put all low memory onto the freelists */ diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 882328efc3d..794895c6dcc 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -106,7 +106,7 @@ static int ioremap_change_attr(unsigned long vaddr, unsigned long size, * have to convert them into an offset in a page-aligned mapping, but the * caller shouldn't need to know that small detail. */ -static void __iomem *__ioremap(unsigned long phys_addr, unsigned long size, +static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size, enum ioremap_mode mode) { unsigned long pfn, offset, last_addr, vaddr; @@ -134,12 +134,14 @@ static void __iomem *__ioremap(unsigned long phys_addr, unsigned long size, return NULL; } - WARN_ON_ONCE(page_is_ram(pfn)); - switch (mode) { case IOR_MODE_UNCACHED: default: - prot = PAGE_KERNEL_NOCACHE; + /* + * FIXME: we will use UC MINUS for now, as video fb drivers + * depend on it. Upcoming ioremap_wc() will fix this behavior. + */ + prot = PAGE_KERNEL_UC_MINUS; break; case IOR_MODE_CACHED: prot = PAGE_KERNEL; @@ -162,7 +164,7 @@ static void __iomem *__ioremap(unsigned long phys_addr, unsigned long size, area->phys_addr = phys_addr; vaddr = (unsigned long) area->addr; if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) { - remove_vm_area((void *)(vaddr & PAGE_MASK)); + free_vm_area(area); return NULL; } @@ -195,13 +197,13 @@ static void __iomem *__ioremap(unsigned long phys_addr, unsigned long size, * * Must be freed with iounmap. */ -void __iomem *ioremap_nocache(unsigned long phys_addr, unsigned long size) +void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) { return __ioremap(phys_addr, size, IOR_MODE_UNCACHED); } EXPORT_SYMBOL(ioremap_nocache); -void __iomem *ioremap_cache(unsigned long phys_addr, unsigned long size) +void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size) { return __ioremap(phys_addr, size, IOR_MODE_CACHED); } diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 59898fb0a4a..16b82ad34b9 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -221,8 +221,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, bootmap_pages<<PAGE_SHIFT, PAGE_SIZE); if (bootmap == NULL) { if (nodedata_phys < start || nodedata_phys >= end) - free_bootmem((unsigned long)node_data[nodeid], - pgdat_size); + free_bootmem(nodedata_phys, pgdat_size); node_data[nodeid] = NULL; return; } @@ -622,13 +621,17 @@ void __init init_cpu_to_node(void) int i; for (i = 0; i < NR_CPUS; i++) { + int node; u16 apicid = x86_cpu_to_apicid_init[i]; if (apicid == BAD_APICID) continue; - if (apicid_to_node[apicid] == NUMA_NO_NODE) + node = apicid_to_node[apicid]; + if (node == NUMA_NO_NODE) continue; - numa_set_node(i, apicid_to_node[apicid]); + if (!node_online(node)) + continue; + numa_set_node(i, node); } } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index e2a74ea11a5..7b79f6be4e7 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -44,6 +44,12 @@ static inline unsigned long highmap_end_pfn(void) #endif +#ifdef CONFIG_DEBUG_PAGEALLOC +# define debug_pagealloc 1 +#else +# define debug_pagealloc 0 +#endif + static inline int within(unsigned long addr, unsigned long start, unsigned long end) { @@ -355,45 +361,48 @@ out_unlock: static LIST_HEAD(page_pool); static unsigned long pool_size, pool_pages, pool_low; -static unsigned long pool_used, pool_failed, pool_refill; +static unsigned long pool_used, pool_failed; -static void cpa_fill_pool(void) +static void cpa_fill_pool(struct page **ret) { - struct page *p; gfp_t gfp = GFP_KERNEL; + unsigned long flags; + struct page *p; - /* Do not allocate from interrupt context */ - if (in_irq() || irqs_disabled()) - return; /* - * Check unlocked. I does not matter when we have one more - * page in the pool. The bit lock avoids recursive pool - * allocations: + * Avoid recursion (on debug-pagealloc) and also signal + * our priority to get to these pagetables: */ - if (pool_pages >= pool_size || test_and_set_bit_lock(0, &pool_refill)) + if (current->flags & PF_MEMALLOC) return; + current->flags |= PF_MEMALLOC; -#ifdef CONFIG_DEBUG_PAGEALLOC /* - * We could do: - * gfp = in_atomic() ? GFP_ATOMIC : GFP_KERNEL; - * but this fails on !PREEMPT kernels + * Allocate atomically from atomic contexts: */ - gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; -#endif + if (in_atomic() || irqs_disabled() || debug_pagealloc) + gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; - while (pool_pages < pool_size) { + while (pool_pages < pool_size || (ret && !*ret)) { p = alloc_pages(gfp, 0); if (!p) { pool_failed++; break; } - spin_lock_irq(&pgd_lock); + /* + * If the call site needs a page right now, provide it: + */ + if (ret && !*ret) { + *ret = p; + continue; + } + spin_lock_irqsave(&pgd_lock, flags); list_add(&p->lru, &page_pool); pool_pages++; - spin_unlock_irq(&pgd_lock); + spin_unlock_irqrestore(&pgd_lock, flags); } - clear_bit_unlock(0, &pool_refill); + + current->flags &= ~PF_MEMALLOC; } #define SHIFT_MB (20 - PAGE_SHIFT) @@ -414,11 +423,15 @@ void __init cpa_init(void) * GiB. Shift MiB to Gib and multiply the result by * POOL_PAGES_PER_GB: */ - gb = ((si.totalram >> SHIFT_MB) + ROUND_MB_GB) >> SHIFT_MB_GB; - pool_size = POOL_PAGES_PER_GB * gb; + if (debug_pagealloc) { + gb = ((si.totalram >> SHIFT_MB) + ROUND_MB_GB) >> SHIFT_MB_GB; + pool_size = POOL_PAGES_PER_GB * gb; + } else { + pool_size = 1; + } pool_low = pool_size; - cpa_fill_pool(); + cpa_fill_pool(NULL); printk(KERN_DEBUG "CPA: page pool initialized %lu of %lu pages preallocated\n", pool_pages, pool_size); @@ -440,16 +453,20 @@ static int split_large_page(pte_t *kpte, unsigned long address) spin_lock_irqsave(&pgd_lock, flags); if (list_empty(&page_pool)) { spin_unlock_irqrestore(&pgd_lock, flags); - return -ENOMEM; + base = NULL; + cpa_fill_pool(&base); + if (!base) + return -ENOMEM; + spin_lock_irqsave(&pgd_lock, flags); + } else { + base = list_first_entry(&page_pool, struct page, lru); + list_del(&base->lru); + pool_pages--; + + if (pool_pages < pool_low) + pool_low = pool_pages; } - base = list_first_entry(&page_pool, struct page, lru); - list_del(&base->lru); - pool_pages--; - - if (pool_pages < pool_low) - pool_low = pool_pages; - /* * Check for races, another CPU might have split this page * up for us already: @@ -734,7 +751,8 @@ static int change_page_attr_set_clr(unsigned long addr, int numpages, cpa_flush_all(cache); out: - cpa_fill_pool(); + cpa_fill_pool(NULL); + return ret; } @@ -753,7 +771,7 @@ static inline int change_page_attr_clear(unsigned long addr, int numpages, int set_memory_uc(unsigned long addr, int numpages) { return change_page_attr_set(addr, numpages, - __pgprot(_PAGE_PCD | _PAGE_PWT)); + __pgprot(_PAGE_PCD)); } EXPORT_SYMBOL(set_memory_uc); @@ -897,9 +915,26 @@ void kernel_map_pages(struct page *page, int numpages, int enable) * Try to refill the page pool here. We can do this only after * the tlb flush. */ - cpa_fill_pool(); + cpa_fill_pool(NULL); } -#endif + +#ifdef CONFIG_HIBERNATION + +bool kernel_page_present(struct page *page) +{ + unsigned int level; + pte_t *pte; + + if (PageHighMem(page)) + return false; + + pte = lookup_address((unsigned long)page_address(page), &level); + return (pte_val(*pte) & _PAGE_PRESENT); +} + +#endif /* CONFIG_HIBERNATION */ + +#endif /* CONFIG_DEBUG_PAGEALLOC */ /* * The testcases use internal knowledge of the implementation that shouldn't diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 73aba712520..2f9e9afcb9f 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -342,12 +342,16 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *pgd = quicklist_alloc(0, GFP_KERNEL, pgd_ctor); + pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - mm->pgd = pgd; /* so that alloc_pd can use it */ + /* so that alloc_pd can use it */ + mm->pgd = pgd; + if (pgd) + pgd_ctor(pgd); if (pgd && !pgd_prepopulate_pmd(mm, pgd)) { - quicklist_free(0, pgd_dtor, pgd); + pgd_dtor(pgd); + free_page((unsigned long)pgd); pgd = NULL; } @@ -357,12 +361,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm) void pgd_free(struct mm_struct *mm, pgd_t *pgd) { pgd_mop_up_pmds(mm, pgd); - quicklist_free(0, pgd_dtor, pgd); -} - -void check_pgt_cache(void) -{ - quicklist_trim(0, pgd_dtor, 25, 16); + pgd_dtor(pgd); + free_page((unsigned long)pgd); } void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte) diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 0234f2831bf..378136fb504 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -219,8 +219,21 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do if (pxm >= 0) sd->node = pxm_to_node(pxm); #endif + /* + * Maybe the desired pci bus has been already scanned. In such case + * it is unnecessary to scan the pci bus with the given domain,busnum. + */ + bus = pci_find_bus(domain, busnum); + if (bus) { + /* + * If the desired bus exits, the content of bus->sysdata will + * be replaced by sd. + */ + memcpy(bus->sysdata, sd, sizeof(*sd)); + kfree(sd); + } else + bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd); - bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd); if (!bus) kfree(sd); @@ -228,7 +241,7 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do if (bus != NULL) { if (pxm >= 0) { printk("bus %d -> pxm %d -> node %d\n", - busnum, pxm, sd->node); + busnum, pxm, pxm_to_node(pxm)); } } #endif diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index ed07ce6c171..a8715861877 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -583,6 +583,10 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route case PCI_DEVICE_ID_INTEL_ICH9_4: case PCI_DEVICE_ID_INTEL_ICH9_5: case PCI_DEVICE_ID_INTEL_TOLAPAI_0: + case PCI_DEVICE_ID_INTEL_ICH10_0: + case PCI_DEVICE_ID_INTEL_ICH10_1: + case PCI_DEVICE_ID_INTEL_ICH10_2: + case PCI_DEVICE_ID_INTEL_ICH10_3: r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 10ac8c316c4..2f7109ac4c1 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -198,6 +198,11 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, "b" (bx), "D" ((long)reg), "S" (&pci_indirect)); + /* + * Zero-extend the result beyond 8 bits, do not trust the + * BIOS having done it: + */ + *value &= 0xff; break; case 2: __asm__("lcall *(%%esi); cld\n\t" @@ -210,6 +215,11 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, "b" (bx), "D" ((long)reg), "S" (&pci_indirect)); + /* + * Zero-extend the result beyond 16 bits, do not trust the + * BIOS having done it: + */ + *value &= 0xffff; break; case 4: __asm__("lcall *(%%esi); cld\n\t" diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index f385a4b4a48..0a8f4742ef5 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -50,7 +50,9 @@ obj-$(VDSO64-y) += vdso-syms.lds sed-vdsosym := -e 's/^00*/0/' \ -e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p' quiet_cmd_vdsosym = VDSOSYM $@ - cmd_vdsosym = $(NM) $< | sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ +define cmd_vdsosym + $(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ +endef $(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE $(call if_changed,vdsosym) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 49e5358f481..27ee26aedf9 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -95,7 +95,7 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&dummy_shared_info; * * 0: not available, 1: available */ -static int have_vcpu_info_placement = 0; +static int have_vcpu_info_placement = 1; static void __init xen_vcpu_setup(int cpu) { @@ -103,6 +103,7 @@ static void __init xen_vcpu_setup(int cpu) int err; struct vcpu_info *vcpup; + BUG_ON(HYPERVISOR_shared_info == &dummy_shared_info); per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; if (!have_vcpu_info_placement) @@ -153,6 +154,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, if (*ax == 1) maskedx = ~((1 << X86_FEATURE_APIC) | /* disable APIC */ (1 << X86_FEATURE_ACPI) | /* disable ACPI */ + (1 << X86_FEATURE_SEP) | /* disable SEP */ (1 << X86_FEATURE_ACC)); /* thermal monitoring */ asm(XEN_EMULATE_PREFIX "cpuid" @@ -665,10 +667,10 @@ static void xen_release_pt_init(u32 pfn) make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } -static void pin_pagetable_pfn(unsigned level, unsigned long pfn) +static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) { struct mmuext_op op; - op.cmd = level; + op.cmd = cmd; op.arg1.mfn = pfn_to_mfn(pfn); if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) BUG(); @@ -685,7 +687,8 @@ static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level) if (!PageHighMem(page)) { make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); - pin_pagetable_pfn(level, pfn); + if (level == PT_PTE) + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); } else /* make sure there are no stray mappings of this page */ @@ -695,27 +698,39 @@ static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level) static void xen_alloc_pt(struct mm_struct *mm, u32 pfn) { - xen_alloc_ptpage(mm, pfn, MMUEXT_PIN_L1_TABLE); + xen_alloc_ptpage(mm, pfn, PT_PTE); } static void xen_alloc_pd(struct mm_struct *mm, u32 pfn) { - xen_alloc_ptpage(mm, pfn, MMUEXT_PIN_L2_TABLE); + xen_alloc_ptpage(mm, pfn, PT_PMD); } /* This should never happen until we're OK to use struct page */ -static void xen_release_pt(u32 pfn) +static void xen_release_ptpage(u32 pfn, unsigned level) { struct page *page = pfn_to_page(pfn); if (PagePinned(page)) { if (!PageHighMem(page)) { - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); + if (level == PT_PTE) + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } + ClearPagePinned(page); } } +static void xen_release_pt(u32 pfn) +{ + xen_release_ptpage(pfn, PT_PTE); +} + +static void xen_release_pd(u32 pfn) +{ + xen_release_ptpage(pfn, PT_PMD); +} + #ifdef CONFIG_HIGHPTE static void *xen_kmap_atomic_pte(struct page *page, enum km_type type) { @@ -804,33 +819,43 @@ static __init void xen_pagetable_setup_start(pgd_t *base) PFN_DOWN(__pa(xen_start_info->pt_base))); } -static __init void xen_pagetable_setup_done(pgd_t *base) +static __init void setup_shared_info(void) { - /* This will work as long as patching hasn't happened yet - (which it hasn't) */ - pv_mmu_ops.alloc_pt = xen_alloc_pt; - pv_mmu_ops.alloc_pd = xen_alloc_pd; - pv_mmu_ops.release_pt = xen_release_pt; - pv_mmu_ops.release_pd = xen_release_pt; - pv_mmu_ops.set_pte = xen_set_pte; - if (!xen_feature(XENFEAT_auto_translated_physmap)) { + unsigned long addr = fix_to_virt(FIX_PARAVIRT_BOOTMAP); + /* * Create a mapping for the shared info page. * Should be set_fixmap(), but shared_info is a machine * address with no corresponding pseudo-phys address. */ - set_pte_mfn(fix_to_virt(FIX_PARAVIRT_BOOTMAP), + set_pte_mfn(addr, PFN_DOWN(xen_start_info->shared_info), PAGE_KERNEL); - HYPERVISOR_shared_info = - (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); - + HYPERVISOR_shared_info = (struct shared_info *)addr; } else HYPERVISOR_shared_info = (struct shared_info *)__va(xen_start_info->shared_info); +#ifndef CONFIG_SMP + /* In UP this is as good a place as any to set up shared info */ + xen_setup_vcpu_info_placement(); +#endif +} + +static __init void xen_pagetable_setup_done(pgd_t *base) +{ + /* This will work as long as patching hasn't happened yet + (which it hasn't) */ + pv_mmu_ops.alloc_pt = xen_alloc_pt; + pv_mmu_ops.alloc_pd = xen_alloc_pd; + pv_mmu_ops.release_pt = xen_release_pt; + pv_mmu_ops.release_pd = xen_release_pd; + pv_mmu_ops.set_pte = xen_set_pte; + + setup_shared_info(); + /* Actually pin the pagetable down, but we can't set PG_pinned yet because the page structures don't exist yet. */ { @@ -1181,15 +1206,9 @@ asmlinkage void __init xen_start_kernel(void) x86_write_percpu(xen_cr3, __pa(pgd)); x86_write_percpu(xen_current_cr3, __pa(pgd)); -#ifdef CONFIG_SMP /* Don't do the full vcpu_info placement stuff until we have a - possible map. */ + possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; -#else - /* May as well do it now, since there's no good time to call - it later on UP. */ - xen_setup_vcpu_info_placement(); -#endif pv_info.kernel_rpl = 1; if (xen_feature(XENFEAT_supervisor_mode_kernel)) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 0144395448a..2a054ef2a3d 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -310,13 +310,6 @@ pgd_t xen_make_pgd(unsigned long pgd) } #endif /* CONFIG_X86_PAE */ -enum pt_level { - PT_PGD, - PT_PUD, - PT_PMD, - PT_PTE -}; - /* (Yet another) pagetable walker. This one is intended for pinning a pagetable. This means that it walks a pagetable and calls the diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index c9ff27f3ac3..b5e189b1519 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -3,6 +3,13 @@ #include <linux/linkage.h> #include <asm/page.h> +enum pt_level { + PT_PGD, + PT_PUD, + PT_PMD, + PT_PTE +}; + /* * Page-directory addresses above 4GB do not fit into architectural %cr3. * When accessing %cr3, or equivalent field in vcpu_guest_context, guests diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 3bad4773a2f..2341492bf7a 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -38,7 +38,8 @@ char * __init xen_memory_setup(void) unsigned long max_pfn = xen_start_info->nr_pages; e820.nr_map = 0; - add_memory_region(0, PFN_PHYS(max_pfn), E820_RAM); + add_memory_region(0, LOWMEMSIZE(), E820_RAM); + add_memory_region(HIGH_MEMORY, PFN_PHYS(max_pfn)-HIGH_MEMORY, E820_RAM); return "Xen"; } diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 1a43b60c0c6..6b7190449d0 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -33,12 +33,17 @@ events, then enter the hypervisor to get them handled. */ ENTRY(xen_irq_enable_direct) - /* Clear mask and test pending */ - andw $0x00ff, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_pending + /* Unmask events */ + movb $0, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask + /* Preempt here doesn't matter because that will deal with any pending interrupts. The pending check may end up being run on the wrong CPU, but that doesn't hurt. */ + + /* Test for pending */ + testb $0xff, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_pending jz 1f + 2: call check_events 1: ENDPATCH(xen_irq_enable_direct) |