diff options
Diffstat (limited to 'arch/x86')
47 files changed, 370 insertions, 697 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e98440371525..0eacb1ffb421 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -102,6 +102,9 @@ config ZONE_DMA config SBUS bool +config NEED_DMA_MAP_STATE + def_bool (X86_64 || DMAR || DMA_API_DEBUG) + config GENERIC_ISA_DMA def_bool y @@ -659,7 +662,7 @@ config GART_IOMMU bool "GART IOMMU support" if EMBEDDED default y select SWIOTLB - depends on X86_64 && PCI + depends on X86_64 && PCI && K8_NB ---help--- Support for full DMA access of devices with 32bit memory access only on systems with more than 3GB. This is usually needed for USB, @@ -2058,7 +2061,7 @@ endif # X86_32 config K8_NB def_bool y - depends on AGP_AMD64 || (X86_64 && (GART_IOMMU || (PCI && NUMA))) + depends on CPU_SUP_AMD && PCI source "drivers/pcmcia/Kconfig" diff --git a/arch/x86/crypto/twofish-i586-asm_32.S b/arch/x86/crypto/twofish-i586-asm_32.S index 39b98ed2c1b9..575331cb2a8a 100644 --- a/arch/x86/crypto/twofish-i586-asm_32.S +++ b/arch/x86/crypto/twofish-i586-asm_32.S @@ -22,7 +22,7 @@ #include <asm/asm-offsets.h> -/* return adress at 0 */ +/* return address at 0 */ #define in_blk 12 /* input byte array address parameter*/ #define out_blk 8 /* output byte array address parameter*/ @@ -230,8 +230,8 @@ twofish_enc_blk: push %edi mov tfm + 16(%esp), %ebp /* abuse the base pointer: set new base bointer to the crypto tfm */ - add $crypto_tfm_ctx_offset, %ebp /* ctx adress */ - mov in_blk+16(%esp),%edi /* input adress in edi */ + add $crypto_tfm_ctx_offset, %ebp /* ctx address */ + mov in_blk+16(%esp),%edi /* input address in edi */ mov (%edi), %eax mov b_offset(%edi), %ebx @@ -286,8 +286,8 @@ twofish_dec_blk: mov tfm + 16(%esp), %ebp /* abuse the base pointer: set new base bointer to the crypto tfm */ - add $crypto_tfm_ctx_offset, %ebp /* ctx adress */ - mov in_blk+16(%esp),%edi /* input adress in edi */ + add $crypto_tfm_ctx_offset, %ebp /* ctx address */ + mov in_blk+16(%esp),%edi /* input address in edi */ mov (%edi), %eax mov b_offset(%edi), %ebx diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S index 35974a586615..573aa102542e 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64.S @@ -221,11 +221,11 @@ twofish_enc_blk: pushq R1 - /* %rdi contains the crypto tfm adress */ - /* %rsi contains the output adress */ - /* %rdx contains the input adress */ - add $crypto_tfm_ctx_offset, %rdi /* set ctx adress */ - /* ctx adress is moved to free one non-rex register + /* %rdi contains the crypto tfm address */ + /* %rsi contains the output address */ + /* %rdx contains the input address */ + add $crypto_tfm_ctx_offset, %rdi /* set ctx address */ + /* ctx address is moved to free one non-rex register as target for the 8bit high operations */ mov %rdi, %r11 @@ -274,11 +274,11 @@ twofish_enc_blk: twofish_dec_blk: pushq R1 - /* %rdi contains the crypto tfm adress */ - /* %rsi contains the output adress */ - /* %rdx contains the input adress */ - add $crypto_tfm_ctx_offset, %rdi /* set ctx adress */ - /* ctx adress is moved to free one non-rex register + /* %rdi contains the crypto tfm address */ + /* %rsi contains the output address */ + /* %rdx contains the input address */ + add $crypto_tfm_ctx_offset, %rdi /* set ctx address */ + /* ctx address is moved to free one non-rex register as target for the 8bit high operations */ mov %rdi, %r11 diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 53147ad85b96..59b4556a5b92 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -563,7 +563,7 @@ ia32_sys_call_table: .quad quiet_ni_syscall /* old mpx syscall holder */ .quad sys_setpgid .quad quiet_ni_syscall /* old ulimit syscall holder */ - .quad sys32_olduname + .quad sys_olduname .quad sys_umask /* 60 */ .quad sys_chroot .quad compat_sys_ustat @@ -586,7 +586,7 @@ ia32_sys_call_table: .quad compat_sys_settimeofday .quad sys_getgroups16 /* 80 */ .quad sys_setgroups16 - .quad sys32_old_select + .quad compat_sys_old_select .quad sys_symlink .quad sys_lstat .quad sys_readlink /* 85 */ @@ -613,7 +613,7 @@ ia32_sys_call_table: .quad compat_sys_newstat .quad compat_sys_newlstat .quad compat_sys_newfstat - .quad sys32_uname + .quad sys_uname .quad stub32_iopl /* 110 */ .quad sys_vhangup .quad quiet_ni_syscall /* old "idle" system call */ diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 422572c77923..74c35431b7d8 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -143,7 +143,7 @@ asmlinkage long sys32_fstatat(unsigned int dfd, char __user *filename, * block for parameter passing.. */ -struct mmap_arg_struct { +struct mmap_arg_struct32 { unsigned int addr; unsigned int len; unsigned int prot; @@ -152,9 +152,9 @@ struct mmap_arg_struct { unsigned int offset; }; -asmlinkage long sys32_mmap(struct mmap_arg_struct __user *arg) +asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) { - struct mmap_arg_struct a; + struct mmap_arg_struct32 a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; @@ -332,24 +332,6 @@ asmlinkage long sys32_alarm(unsigned int seconds) return alarm_setitimer(seconds); } -struct sel_arg_struct { - unsigned int n; - unsigned int inp; - unsigned int outp; - unsigned int exp; - unsigned int tvp; -}; - -asmlinkage long sys32_old_select(struct sel_arg_struct __user *arg) -{ - struct sel_arg_struct a; - - if (copy_from_user(&a, arg, sizeof(a))) - return -EFAULT; - return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), - compat_ptr(a.exp), compat_ptr(a.tvp)); -} - asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr, int options) { @@ -466,58 +448,6 @@ asmlinkage long sys32_sendfile(int out_fd, int in_fd, return ret; } -asmlinkage long sys32_olduname(struct oldold_utsname __user *name) -{ - char *arch = "x86_64"; - int err; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - - err = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - err |= __put_user(0, name->sysname+__OLD_UTS_LEN); - err |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - err |= __put_user(0, name->nodename+__OLD_UTS_LEN); - err |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - err |= __put_user(0, name->release+__OLD_UTS_LEN); - err |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - err |= __put_user(0, name->version+__OLD_UTS_LEN); - - if (personality(current->personality) == PER_LINUX32) - arch = "i686"; - - err |= __copy_to_user(&name->machine, arch, strlen(arch) + 1); - - up_read(&uts_sem); - - err = err ? -EFAULT : 0; - - return err; -} - -long sys32_uname(struct old_utsname __user *name) -{ - int err; - - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - if (personality(current->personality) == PER_LINUX32) - err |= copy_to_user(&name->machine, "i686", 5); - - return err ? -EFAULT : 0; -} - asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs *regs) { diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 9a9c7bdc923d..306160e58b48 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -8,7 +8,8 @@ #include <linux/sched.h> #include <asm/user32.h> -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "i686\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index 0675a7c4c20e..2a1bd8f4f23a 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -10,7 +10,6 @@ * (display/resolving) */ struct arch_hw_breakpoint { - char *name; /* Contains name of the symbol to set bkpt */ unsigned long address; u8 len; u8 type; diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 3e002ca5a287..404a880ea325 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -97,34 +97,6 @@ extern void pci_iommu_alloc(void); #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) -#if defined(CONFIG_X86_64) || defined(CONFIG_DMAR) || defined(CONFIG_DMA_API_DEBUG) - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ - dma_addr_t ADDR_NAME; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ - __u32 LEN_NAME; -#define pci_unmap_addr(PTR, ADDR_NAME) \ - ((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - (((PTR)->ADDR_NAME) = (VAL)) -#define pci_unmap_len(PTR, LEN_NAME) \ - ((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - (((PTR)->LEN_NAME) = (VAL)) - -#else - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME[0]; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0]; -#define pci_unmap_addr(PTR, ADDR_NAME) sizeof((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - do { break; } while (pci_unmap_addr(PTR, ADDR_NAME)) -#define pci_unmap_len(PTR, LEN_NAME) sizeof((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - do { break; } while (pci_unmap_len(PTR, LEN_NAME)) - -#endif - #endif /* __KERNEL__ */ #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index befd172c82ad..db6109a885a7 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -18,7 +18,7 @@ #define MSR_ARCH_PERFMON_EVENTSEL0 0x186 #define MSR_ARCH_PERFMON_EVENTSEL1 0x187 -#define ARCH_PERFMON_EVENTSEL0_ENABLE (1 << 22) +#define ARCH_PERFMON_EVENTSEL_ENABLE (1 << 22) #define ARCH_PERFMON_EVENTSEL_ANY (1 << 21) #define ARCH_PERFMON_EVENTSEL_INT (1 << 20) #define ARCH_PERFMON_EVENTSEL_OS (1 << 17) @@ -50,7 +50,7 @@ INTEL_ARCH_INV_MASK| \ INTEL_ARCH_EDGE_MASK|\ INTEL_ARCH_UNIT_MASK|\ - INTEL_ARCH_EVTSEL_MASK) + INTEL_ARCH_EVENT_MASK) #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) @@ -117,6 +117,18 @@ union cpuid10_edx { */ #define X86_PMC_IDX_FIXED_BTS (X86_PMC_IDX_FIXED + 16) +/* IbsFetchCtl bits/masks */ +#define IBS_FETCH_RAND_EN (1ULL<<57) +#define IBS_FETCH_VAL (1ULL<<49) +#define IBS_FETCH_ENABLE (1ULL<<48) +#define IBS_FETCH_CNT 0xFFFF0000ULL +#define IBS_FETCH_MAX_CNT 0x0000FFFFULL + +/* IbsOpCtl bits */ +#define IBS_OP_CNT_CTL (1ULL<<19) +#define IBS_OP_VAL (1ULL<<18) +#define IBS_OP_ENABLE (1ULL<<17) +#define IBS_OP_MAX_CNT 0x0000FFFFULL #ifdef CONFIG_PERF_EVENTS extern void init_hw_perf_events(void); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 20102808b191..69a686a7dff0 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -274,14 +274,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, return 0; } -/* - * These are defined as per linux/ptrace.h, which see. - */ #define arch_has_single_step() (1) -extern void user_enable_single_step(struct task_struct *); -extern void user_disable_single_step(struct task_struct *); - -extern void user_enable_block_step(struct task_struct *); #ifdef CONFIG_X86_DEBUGCTLMSR #define arch_has_block_step() (1) #else diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index d5f69045c100..3ad421784ae7 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -26,8 +26,8 @@ asmlinkage long sys32_lstat64(char __user *, struct stat64 __user *); asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *); asmlinkage long sys32_fstatat(unsigned int, char __user *, struct stat64 __user *, int); -struct mmap_arg_struct; -asmlinkage long sys32_mmap(struct mmap_arg_struct __user *); +struct mmap_arg_struct32; +asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *); asmlinkage long sys32_mprotect(unsigned long, size_t, unsigned long); struct sigaction32; @@ -40,8 +40,6 @@ asmlinkage long sys32_rt_sigprocmask(int, compat_sigset_t __user *, compat_sigset_t __user *, unsigned int); asmlinkage long sys32_alarm(unsigned int); -struct sel_arg_struct; -asmlinkage long sys32_old_select(struct sel_arg_struct __user *); asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int); asmlinkage long sys32_sysfs(int, u32, u32); @@ -56,11 +54,6 @@ asmlinkage long sys32_pwrite(unsigned int, char __user *, u32, u32, u32); asmlinkage long sys32_personality(unsigned long); asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32); -struct oldold_utsname; -struct old_utsname; -asmlinkage long sys32_olduname(struct oldold_utsname __user *); -long sys32_uname(struct old_utsname __user *); - asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *, compat_uptr_t __user *, struct pt_regs *); asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *); diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 8868b9420b0e..5c044b43e9a7 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -50,18 +50,6 @@ asmlinkage int sys_sigaction(int, const struct old_sigaction __user *, struct old_sigaction __user *); unsigned long sys_sigreturn(struct pt_regs *); -/* kernel/sys_i386_32.c */ -struct mmap_arg_struct; -struct sel_arg_struct; -struct oldold_utsname; -struct old_utsname; - -asmlinkage int old_mmap(struct mmap_arg_struct __user *); -asmlinkage int old_select(struct sel_arg_struct __user *); -asmlinkage int sys_ipc(uint, int, int, int, void __user *, long); -asmlinkage int sys_uname(struct old_utsname __user *); -asmlinkage int sys_olduname(struct oldold_utsname __user *); - /* kernel/vm86_32.c */ int sys_vm86old(struct vm86_struct __user *, struct pt_regs *); int sys_vm86(unsigned long, unsigned long, struct pt_regs *); @@ -73,11 +61,8 @@ int sys_vm86(unsigned long, unsigned long, struct pt_regs *); long sys_arch_prctl(int, unsigned long); /* kernel/sys_x86_64.c */ -struct new_utsname; - asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); -asmlinkage long sys_uname(struct new_utsname __user *); #endif /* CONFIG_X86_32 */ #endif /* _ASM_X86_SYSCALLS_H */ diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index 3baf379fa840..beb9b5f8f8a4 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -354,6 +354,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL @@ -366,6 +367,9 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME +#define __ARCH_WANT_SYS_OLD_MMAP +#define __ARCH_WANT_SYS_OLD_SELECT #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 4843f7ba754a..ff4307b0e81e 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -146,7 +146,7 @@ __SYSCALL(__NR_wait4, sys_wait4) #define __NR_kill 62 __SYSCALL(__NR_kill, sys_kill) #define __NR_uname 63 -__SYSCALL(__NR_uname, sys_uname) +__SYSCALL(__NR_uname, sys_newuname) #define __NR_semget 64 __SYSCALL(__NR_semget, sys_semget) @@ -680,6 +680,7 @@ __SYSCALL(__NR_recvmmsg, sys_recvmmsg) #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index a54d714545ff..0061ea263061 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -490,6 +490,7 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) * ACPI based hotplug support for CPU */ #ifdef CONFIG_ACPI_HOTPLUG_CPU +#include <acpi/processor.h> static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { @@ -567,6 +568,8 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) goto free_new_map; } + acpi_processor_set_pdc(handle); + cpu = cpumask_first(new_map); acpi_map_cpu2node(handle, cpu, physid); @@ -1293,23 +1296,6 @@ static int __init dmi_disable_acpi(const struct dmi_system_id *d) } /* - * Limit ACPI to CPU enumeration for HT - */ -static int __init force_acpi_ht(const struct dmi_system_id *d) -{ - if (!acpi_force) { - printk(KERN_NOTICE "%s detected: force use of acpi=ht\n", - d->ident); - disable_acpi(); - acpi_ht = 1; - } else { - printk(KERN_NOTICE - "Warning: acpi=force overrules DMI blacklist: acpi=ht\n"); - } - return 0; -} - -/* * Force ignoring BIOS IRQ0 pin2 override */ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) @@ -1345,82 +1331,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = { }, /* - * Boxes that need acpi=ht - */ - { - .callback = force_acpi_ht, - .ident = "FSC Primergy T850", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "PRIMERGY T850"), - }, - }, - { - .callback = force_acpi_ht, - .ident = "HP VISUALIZE NT Workstation", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP VISUALIZE NT Workstation"), - }, - }, - { - .callback = force_acpi_ht, - .ident = "Compaq Workstation W8000", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), - DMI_MATCH(DMI_PRODUCT_NAME, "Workstation W8000"), - }, - }, - { - .callback = force_acpi_ht, - .ident = "ASUS CUR-DLS", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), - DMI_MATCH(DMI_BOARD_NAME, "CUR-DLS"), - }, - }, - { - .callback = force_acpi_ht, - .ident = "ABIT i440BX-W83977", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "ABIT <http://www.abit.com>"), - DMI_MATCH(DMI_BOARD_NAME, "i440BX-W83977 (BP6)"), - }, - }, - { - .callback = force_acpi_ht, - .ident = "IBM Bladecenter", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), - DMI_MATCH(DMI_BOARD_NAME, "IBM eServer BladeCenter HS20"), - }, - }, - { - .callback = force_acpi_ht, - .ident = "IBM eServer xSeries 360", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), - DMI_MATCH(DMI_BOARD_NAME, "eServer xSeries 360"), - }, - }, - { - .callback = force_acpi_ht, - .ident = "IBM eserver xSeries 330", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), - DMI_MATCH(DMI_BOARD_NAME, "eserver xSeries 330"), - }, - }, - { - .callback = force_acpi_ht, - .ident = "IBM eserver xSeries 440", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), - DMI_MATCH(DMI_PRODUCT_NAME, "eserver xSeries 440"), - }, - }, - - /* * Boxes that need ACPI PCI IRQ routing disabled */ { @@ -1652,8 +1562,10 @@ static int __init parse_acpi(char *arg) } /* Limit ACPI just to boot-time to enable HT */ else if (strcmp(arg, "ht") == 0) { - if (!acpi_force) + if (!acpi_force) { + printk(KERN_WARNING "acpi=ht will be removed in Linux-2.6.35\n"); disable_acpi(); + } acpi_ht = 1; } /* acpi=rsdt use RSDT instead of XSDT */ diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index f147a95fd84a..3704997e8b25 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -31,7 +31,6 @@ #include <asm/x86_init.h> int gart_iommu_aperture; -EXPORT_SYMBOL_GPL(gart_iommu_aperture); int gart_iommu_aperture_disabled __initdata; int gart_iommu_aperture_allowed __initdata; diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index e3c3d820c325..09d3b17ce0c2 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -223,7 +223,7 @@ struct apic apic_flat = { }; /* - * Physflat mode is used when there are more than 8 CPUs on a AMD system. + * Physflat mode is used when there are more than 8 CPUs on a system. * We cannot use logical delivery in this case because the mask * overflows, so use physical mode. */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 3740c8a4eae7..49dbeaef2a27 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -120,11 +120,9 @@ EXPORT_SYMBOL_GPL(uv_possible_blades); unsigned long sn_rtc_cycles_per_second; EXPORT_SYMBOL(sn_rtc_cycles_per_second); -/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */ - static const struct cpumask *uv_target_cpus(void) { - return cpumask_of(0); + return cpu_online_mask; } static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 879666f4d871..7e1cca13af35 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -70,7 +70,8 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - sched_clock_stable = 1; + if (!check_tsc_unstable()) + sched_clock_stable = 1; } /* diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index eddb1bdd1b8f..b3eeb66c0a51 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -903,7 +903,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops sysfs_ops = { +static const struct sysfs_ops sysfs_ops = { .show = show, .store = store, }; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index a8aacd4b513c..3ab9c886b613 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -46,6 +46,13 @@ #include "mce-internal.h" +static DEFINE_MUTEX(mce_read_mutex); + +#define rcu_dereference_check_mce(p) \ + rcu_dereference_check((p), \ + rcu_read_lock_sched_held() || \ + lockdep_is_held(&mce_read_mutex)) + #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -158,7 +165,7 @@ void mce_log(struct mce *mce) mce->finished = 0; wmb(); for (;;) { - entry = rcu_dereference(mcelog.next); + entry = rcu_dereference_check_mce(mcelog.next); for (;;) { /* * When the buffer fills up discard new entries. @@ -1485,8 +1492,6 @@ static void collect_tscs(void *data) rdtscll(cpu_tsc[smp_processor_id()]); } -static DEFINE_MUTEX(mce_read_mutex); - static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, loff_t *off) { @@ -1500,7 +1505,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, return -ENOMEM; mutex_lock(&mce_read_mutex); - next = rcu_dereference(mcelog.next); + next = rcu_dereference_check_mce(mcelog.next); /* Only supports full reads right now */ if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) { @@ -1565,7 +1570,7 @@ timeout: static unsigned int mce_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_wait, wait); - if (rcu_dereference(mcelog.next)) + if (rcu_dereference_check_mce(mcelog.next)) return POLLIN | POLLRDNORM; return 0; } @@ -2044,6 +2049,7 @@ static __init void mce_init_banks(void) struct mce_bank *b = &mce_banks[i]; struct sysdev_attribute *a = &b->attr; + sysfs_attr_init(&a->attr); a->attr.name = b->attrname; snprintf(b->attrname, ATTR_LEN, "bank%d", i); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 83a3d1f4efca..cda932ca3ade 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -388,7 +388,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops threshold_ops = { +static const struct sysfs_ops threshold_ops = { .show = show, .store = store, }; diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 7c785634af2b..d15df6e49bf0 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -95,7 +95,7 @@ static void cmci_discover(int banks, int boot) /* Already owned by someone else? */ if (val & CMCI_EN) { - if (test_and_clear_bit(i, owned) || boot) + if (test_and_clear_bit(i, owned) && !boot) print_update("SHD", &hdr, i); __clear_bit(i, __get_cpu_var(mce_poll_banks)); continue; @@ -107,7 +107,7 @@ static void cmci_discover(int banks, int boot) /* Did the enable bit stick? -- the bank supports CMCI */ if (val & CMCI_EN) { - if (!test_and_set_bit(i, owned) || boot) + if (!test_and_set_bit(i, owned) && !boot) print_update("CMCI", &hdr, i); __clear_bit(i, __get_cpu_var(mce_poll_banks)); } else { diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index b1fbdeecf6c9..60398a0d947c 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -73,10 +73,10 @@ struct debug_store { struct event_constraint { union { unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - u64 idxmsk64[1]; + u64 idxmsk64; }; - int code; - int cmask; + u64 code; + u64 cmask; int weight; }; @@ -103,7 +103,7 @@ struct cpu_hw_events { }; #define __EVENT_CONSTRAINT(c, n, m, w) {\ - { .idxmsk64[0] = (n) }, \ + { .idxmsk64 = (n) }, \ .code = (c), \ .cmask = (m), \ .weight = (w), \ @@ -116,7 +116,7 @@ struct cpu_hw_events { EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK) #define FIXED_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, n, INTEL_ARCH_FIXED_MASK) + EVENT_CONSTRAINT(c, (1ULL << (32+n)), INTEL_ARCH_FIXED_MASK) #define EVENT_CONSTRAINT_END \ EVENT_CONSTRAINT(0, 0, 0) @@ -133,8 +133,8 @@ struct x86_pmu { int (*handle_irq)(struct pt_regs *); void (*disable_all)(void); void (*enable_all)(void); - void (*enable)(struct hw_perf_event *, int); - void (*disable)(struct hw_perf_event *, int); + void (*enable)(struct perf_event *); + void (*disable)(struct perf_event *); unsigned eventsel; unsigned perfctr; u64 (*event_map)(int); @@ -157,6 +157,11 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); struct event_constraint *event_constraints; + + void (*cpu_prepare)(int cpu); + void (*cpu_starting)(int cpu); + void (*cpu_dying)(int cpu); + void (*cpu_dead)(int cpu); }; static struct x86_pmu x86_pmu __read_mostly; @@ -165,8 +170,7 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; -static int x86_perf_event_set_period(struct perf_event *event, - struct hw_perf_event *hwc, int idx); +static int x86_perf_event_set_period(struct perf_event *event); /* * Generalized hw caching related hw_event table, filled @@ -189,11 +193,12 @@ static u64 __read_mostly hw_cache_event_ids * Returns the delta events processed. */ static u64 -x86_perf_event_update(struct perf_event *event, - struct hw_perf_event *hwc, int idx) +x86_perf_event_update(struct perf_event *event) { + struct hw_perf_event *hwc = &event->hw; int shift = 64 - x86_pmu.event_bits; u64 prev_raw_count, new_raw_count; + int idx = hwc->idx; s64 delta; if (idx == X86_PMC_IDX_FIXED_BTS) @@ -293,7 +298,7 @@ static inline bool bts_available(void) return x86_pmu.enable_bts != NULL; } -static inline void init_debug_store_on_cpu(int cpu) +static void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -305,7 +310,7 @@ static inline void init_debug_store_on_cpu(int cpu) (u32)((u64)(unsigned long)ds >> 32)); } -static inline void fini_debug_store_on_cpu(int cpu) +static void fini_debug_store_on_cpu(int cpu) { if (!per_cpu(cpu_hw_events, cpu).ds) return; @@ -503,6 +508,9 @@ static int __hw_perf_event_init(struct perf_event *event) */ if (attr->type == PERF_TYPE_RAW) { hwc->config |= x86_pmu.raw_event(attr->config); + if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) && + perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) + return -EACCES; return 0; } @@ -553,9 +561,9 @@ static void x86_pmu_disable_all(void) if (!test_bit(idx, cpuc->active_mask)) continue; rdmsrl(x86_pmu.eventsel + idx, val); - if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE)) + if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE)) continue; - val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE; + val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(x86_pmu.eventsel + idx, val); } } @@ -590,7 +598,7 @@ static void x86_pmu_enable_all(void) continue; val = event->hw.config; - val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + val |= ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(x86_pmu.eventsel + idx, val); } } @@ -612,8 +620,8 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) bitmap_zero(used_mask, X86_PMC_IDX_MAX); for (i = 0; i < n; i++) { - constraints[i] = - x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]); + c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]); + constraints[i] = c; } /* @@ -635,7 +643,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (test_bit(hwc->idx, used_mask)) break; - set_bit(hwc->idx, used_mask); + __set_bit(hwc->idx, used_mask); if (assign) assign[i] = hwc->idx; } @@ -684,7 +692,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (j == X86_PMC_IDX_MAX) break; - set_bit(j, used_mask); + __set_bit(j, used_mask); if (assign) assign[i] = j; @@ -777,6 +785,7 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc, hwc->last_tag == cpuc->tags[i]; } +static int x86_pmu_start(struct perf_event *event); static void x86_pmu_stop(struct perf_event *event); void hw_perf_enable(void) @@ -793,6 +802,7 @@ void hw_perf_enable(void) return; if (cpuc->n_added) { + int n_running = cpuc->n_events - cpuc->n_added; /* * apply assignment obtained either from * hw_perf_group_sched_in() or x86_pmu_enable() @@ -800,8 +810,7 @@ void hw_perf_enable(void) * step1: save events moving to new counters * step2: reprogram moved events into new counters */ - for (i = 0; i < cpuc->n_events; i++) { - + for (i = 0; i < n_running; i++) { event = cpuc->event_list[i]; hwc = &event->hw; @@ -816,29 +825,18 @@ void hw_perf_enable(void) continue; x86_pmu_stop(event); - - hwc->idx = -1; } for (i = 0; i < cpuc->n_events; i++) { - event = cpuc->event_list[i]; hwc = &event->hw; - if (hwc->idx == -1) { + if (!match_prev_assignment(hwc, cpuc, i)) x86_assign_hw_event(event, cpuc, i); - x86_perf_event_set_period(event, hwc, hwc->idx); - } - /* - * need to mark as active because x86_pmu_disable() - * clear active_mask and events[] yet it preserves - * idx - */ - set_bit(hwc->idx, cpuc->active_mask); - cpuc->events[hwc->idx] = event; + else if (i < n_running) + continue; - x86_pmu.enable(hwc, hwc->idx); - perf_event_update_userpage(event); + x86_pmu_start(event); } cpuc->n_added = 0; perf_events_lapic_init(); @@ -850,15 +848,16 @@ void hw_perf_enable(void) x86_pmu.enable_all(); } -static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, int idx) +static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc) { - (void)checking_wrmsrl(hwc->config_base + idx, - hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE); + (void)checking_wrmsrl(hwc->config_base + hwc->idx, + hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE); } -static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx) +static inline void x86_pmu_disable_event(struct perf_event *event) { - (void)checking_wrmsrl(hwc->config_base + idx, hwc->config); + struct hw_perf_event *hwc = &event->hw; + (void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config); } static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); @@ -868,12 +867,12 @@ static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); * To be called with the event disabled in hw: */ static int -x86_perf_event_set_period(struct perf_event *event, - struct hw_perf_event *hwc, int idx) +x86_perf_event_set_period(struct perf_event *event) { + struct hw_perf_event *hwc = &event->hw; s64 left = atomic64_read(&hwc->period_left); s64 period = hwc->sample_period; - int err, ret = 0; + int err, ret = 0, idx = hwc->idx; if (idx == X86_PMC_IDX_FIXED_BTS) return 0; @@ -919,11 +918,11 @@ x86_perf_event_set_period(struct perf_event *event, return ret; } -static void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx) +static void x86_pmu_enable_event(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); if (cpuc->enabled) - __x86_pmu_enable_event(hwc, idx); + __x86_pmu_enable_event(&event->hw); } /* @@ -959,34 +958,32 @@ static int x86_pmu_enable(struct perf_event *event) memcpy(cpuc->assign, assign, n*sizeof(int)); cpuc->n_events = n; - cpuc->n_added = n - n0; + cpuc->n_added += n - n0; return 0; } static int x86_pmu_start(struct perf_event *event) { - struct hw_perf_event *hwc = &event->hw; + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx = event->hw.idx; - if (hwc->idx == -1) + if (idx == -1) return -EAGAIN; - x86_perf_event_set_period(event, hwc, hwc->idx); - x86_pmu.enable(hwc, hwc->idx); + x86_perf_event_set_period(event); + cpuc->events[idx] = event; + __set_bit(idx, cpuc->active_mask); + x86_pmu.enable(event); + perf_event_update_userpage(event); return 0; } static void x86_pmu_unthrottle(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct hw_perf_event *hwc = &event->hw; - - if (WARN_ON_ONCE(hwc->idx >= X86_PMC_IDX_MAX || - cpuc->events[hwc->idx] != event)) - return; - - x86_pmu.enable(hwc, hwc->idx); + int ret = x86_pmu_start(event); + WARN_ON_ONCE(ret); } void perf_event_print_debug(void) @@ -1046,18 +1043,16 @@ static void x86_pmu_stop(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; - /* - * Must be done before we disable, otherwise the nmi handler - * could reenable again: - */ - clear_bit(idx, cpuc->active_mask); - x86_pmu.disable(hwc, idx); + if (!__test_and_clear_bit(idx, cpuc->active_mask)) + return; + + x86_pmu.disable(event); /* * Drain the remaining delta count out of a event * that we are disabling: */ - x86_perf_event_update(event, hwc, idx); + x86_perf_event_update(event); cpuc->events[idx] = NULL; } @@ -1094,8 +1089,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) int idx, handled = 0; u64 val; - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); @@ -1106,7 +1100,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) event = cpuc->events[idx]; hwc = &event->hw; - val = x86_perf_event_update(event, hwc, idx); + val = x86_perf_event_update(event); if (val & (1ULL << (x86_pmu.event_bits - 1))) continue; @@ -1116,11 +1110,11 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) handled = 1; data.period = event->hw.last_period; - if (!x86_perf_event_set_period(event, hwc, idx)) + if (!x86_perf_event_set_period(event)) continue; if (perf_event_overflow(event, 1, &data, regs)) - x86_pmu.disable(hwc, idx); + x86_pmu_stop(event); } if (handled) @@ -1307,7 +1301,7 @@ int hw_perf_group_sched_in(struct perf_event *leader, memcpy(cpuc->assign, assign, n0*sizeof(int)); cpuc->n_events = n0; - cpuc->n_added = n1; + cpuc->n_added += n1; ctx->nr_active += n1; /* @@ -1335,6 +1329,39 @@ undo: #include "perf_event_p6.c" #include "perf_event_intel.c" +static int __cpuinit +x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + if (x86_pmu.cpu_prepare) + x86_pmu.cpu_prepare(cpu); + break; + + case CPU_STARTING: + if (x86_pmu.cpu_starting) + x86_pmu.cpu_starting(cpu); + break; + + case CPU_DYING: + if (x86_pmu.cpu_dying) + x86_pmu.cpu_dying(cpu); + break; + + case CPU_DEAD: + if (x86_pmu.cpu_dead) + x86_pmu.cpu_dead(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + static void __init pmu_check_apic(void) { if (cpu_has_apic) @@ -1347,6 +1374,7 @@ static void __init pmu_check_apic(void) void __init init_hw_perf_events(void) { + struct event_constraint *c; int err; pr_info("Performance Events: "); @@ -1395,6 +1423,16 @@ void __init init_hw_perf_events(void) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1, 0, x86_pmu.num_events); + if (x86_pmu.event_constraints) { + for_each_event_constraint(c, x86_pmu.event_constraints) { + if (c->cmask != INTEL_ARCH_FIXED_MASK) + continue; + + c->idxmsk64 |= (1ULL << x86_pmu.num_events) - 1; + c->weight += x86_pmu.num_events; + } + } + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.event_bits); pr_info("... generic registers: %d\n", x86_pmu.num_events); @@ -1402,11 +1440,13 @@ void __init init_hw_perf_events(void) pr_info("... max period: %016Lx\n", x86_pmu.max_period); pr_info("... fixed-purpose events: %d\n", x86_pmu.num_events_fixed); pr_info("... event mask: %016Lx\n", perf_event_mask); + + perf_cpu_notifier(x86_pmu_notifier); } static inline void x86_pmu_read(struct perf_event *event) { - x86_perf_event_update(event, &event->hw, event->hw.idx); + x86_perf_event_update(event); } static const struct pmu pmu = { @@ -1662,28 +1702,16 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return entry; } -void hw_perf_event_setup_online(int cpu) +#ifdef CONFIG_EVENT_TRACING +void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) { - init_debug_store_on_cpu(cpu); - - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - amd_pmu_cpu_online(cpu); - break; - default: - return; - } -} - -void hw_perf_event_setup_offline(int cpu) -{ - init_debug_store_on_cpu(cpu); - - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - amd_pmu_cpu_offline(cpu); - break; - default: - return; - } + regs->ip = ip; + /* + * perf_arch_fetch_caller_regs adds another call, we need to increment + * the skip level + */ + regs->bp = rewind_frame_pointer(skip + 1); + regs->cs = __KERNEL_CS; + local_save_flags(regs->flags); } +#endif diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 8f3dbfda3c4f..573458f1caf2 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -271,28 +271,6 @@ done: return &emptyconstraint; } -static __initconst struct x86_pmu amd_pmu = { - .name = "AMD", - .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, - .enable_all = x86_pmu_enable_all, - .enable = x86_pmu_enable_event, - .disable = x86_pmu_disable_event, - .eventsel = MSR_K7_EVNTSEL0, - .perfctr = MSR_K7_PERFCTR0, - .event_map = amd_pmu_event_map, - .raw_event = amd_pmu_raw_event, - .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_events = 4, - .event_bits = 48, - .event_mask = (1ULL << 48) - 1, - .apic = 1, - /* use highest bit to detect overflow */ - .max_period = (1ULL << 47) - 1, - .get_event_constraints = amd_get_event_constraints, - .put_event_constraints = amd_put_event_constraints -}; - static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) { struct amd_nb *nb; @@ -309,7 +287,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) * initialize all possible NB constraints */ for (i = 0; i < x86_pmu.num_events; i++) { - set_bit(i, nb->event_constraints[i].idxmsk); + __set_bit(i, nb->event_constraints[i].idxmsk); nb->event_constraints[i].weight = 1; } return nb; @@ -378,6 +356,31 @@ static void amd_pmu_cpu_offline(int cpu) raw_spin_unlock(&amd_nb_lock); } +static __initconst struct x86_pmu amd_pmu = { + .name = "AMD", + .handle_irq = x86_pmu_handle_irq, + .disable_all = x86_pmu_disable_all, + .enable_all = x86_pmu_enable_all, + .enable = x86_pmu_enable_event, + .disable = x86_pmu_disable_event, + .eventsel = MSR_K7_EVNTSEL0, + .perfctr = MSR_K7_PERFCTR0, + .event_map = amd_pmu_event_map, + .raw_event = amd_pmu_raw_event, + .max_events = ARRAY_SIZE(amd_perfmon_event_map), + .num_events = 4, + .event_bits = 48, + .event_mask = (1ULL << 48) - 1, + .apic = 1, + /* use highest bit to detect overflow */ + .max_period = (1ULL << 47) - 1, + .get_event_constraints = amd_get_event_constraints, + .put_event_constraints = amd_put_event_constraints, + + .cpu_prepare = amd_pmu_cpu_online, + .cpu_dead = amd_pmu_cpu_offline, +}; + static __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ @@ -390,11 +393,6 @@ static __init int amd_pmu_init(void) memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - /* - * explicitly initialize the boot cpu, other cpus will get - * the cpu hotplug callbacks from smp_init() - */ - amd_pmu_cpu_online(smp_processor_id()); return 0; } @@ -405,12 +403,4 @@ static int amd_pmu_init(void) return 0; } -static void amd_pmu_cpu_online(int cpu) -{ -} - -static void amd_pmu_cpu_offline(int cpu) -{ -} - #endif diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 977e7544738c..84bfde64a337 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1,7 +1,7 @@ #ifdef CONFIG_CPU_SUP_INTEL /* - * Intel PerfMon v3. Used on Core2 and later. + * Intel PerfMon, used on Core and later. */ static const u64 intel_perfmon_event_map[] = { @@ -27,8 +27,14 @@ static struct event_constraint intel_core_event_constraints[] = static struct event_constraint intel_core2_event_constraints[] = { - FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */ - FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */ + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + /* + * Core2 has Fixed Counter 2 listed as CPU_CLK_UNHALTED.REF and event + * 0x013c as CPU_CLK_UNHALTED.BUS and specifies there is a fixed + * ratio between these counters. + */ + /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */ INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ @@ -37,14 +43,16 @@ static struct event_constraint intel_core2_event_constraints[] = INTEL_EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */ INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */ INTEL_EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */ + INTEL_EVENT_CONSTRAINT(0xc9, 0x1), /* ITLB_MISS_RETIRED (T30-9) */ INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */ EVENT_CONSTRAINT_END }; static struct event_constraint intel_nehalem_event_constraints[] = { - FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */ - FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */ + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */ INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */ INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */ @@ -58,8 +66,9 @@ static struct event_constraint intel_nehalem_event_constraints[] = static struct event_constraint intel_westmere_event_constraints[] = { - FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */ - FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */ + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */ INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */ INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */ @@ -68,8 +77,9 @@ static struct event_constraint intel_westmere_event_constraints[] = static struct event_constraint intel_gen_event_constraints[] = { - FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */ - FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */ + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ EVENT_CONSTRAINT_END }; @@ -538,9 +548,9 @@ static inline void intel_pmu_ack_status(u64 ack) } static inline void -intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx) +intel_pmu_disable_fixed(struct hw_perf_event *hwc) { - int idx = __idx - X86_PMC_IDX_FIXED; + int idx = hwc->idx - X86_PMC_IDX_FIXED; u64 ctrl_val, mask; mask = 0xfULL << (idx * 4); @@ -580,10 +590,9 @@ static void intel_pmu_drain_bts_buffer(void) ds->bts_index = ds->bts_buffer_base; + perf_sample_data_init(&data, 0); data.period = event->hw.last_period; - data.addr = 0; - data.raw = NULL; regs.ip = 0; /* @@ -612,26 +621,28 @@ static void intel_pmu_drain_bts_buffer(void) } static inline void -intel_pmu_disable_event(struct hw_perf_event *hwc, int idx) +intel_pmu_disable_event(struct perf_event *event) { - if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) { + struct hw_perf_event *hwc = &event->hw; + + if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) { intel_pmu_disable_bts(); intel_pmu_drain_bts_buffer(); return; } if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { - intel_pmu_disable_fixed(hwc, idx); + intel_pmu_disable_fixed(hwc); return; } - x86_pmu_disable_event(hwc, idx); + x86_pmu_disable_event(event); } static inline void -intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx) +intel_pmu_enable_fixed(struct hw_perf_event *hwc) { - int idx = __idx - X86_PMC_IDX_FIXED; + int idx = hwc->idx - X86_PMC_IDX_FIXED; u64 ctrl_val, bits, mask; int err; @@ -661,9 +672,11 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx) err = checking_wrmsrl(hwc->config_base, ctrl_val); } -static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx) +static void intel_pmu_enable_event(struct perf_event *event) { - if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) { + struct hw_perf_event *hwc = &event->hw; + + if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) { if (!__get_cpu_var(cpu_hw_events).enabled) return; @@ -672,11 +685,11 @@ static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx) } if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { - intel_pmu_enable_fixed(hwc, idx); + intel_pmu_enable_fixed(hwc); return; } - __x86_pmu_enable_event(hwc, idx); + __x86_pmu_enable_event(hwc); } /* @@ -685,14 +698,8 @@ static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx) */ static int intel_pmu_save_and_restart(struct perf_event *event) { - struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; - int ret; - - x86_perf_event_update(event, hwc, idx); - ret = x86_perf_event_set_period(event, hwc, idx); - - return ret; + x86_perf_event_update(event); + return x86_perf_event_set_period(event); } static void intel_pmu_reset(void) @@ -732,16 +739,15 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) int bit, loops; u64 ack, status; - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); - perf_disable(); + intel_pmu_disable_all(); intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); if (!status) { - perf_enable(); + intel_pmu_enable_all(); return 0; } @@ -751,8 +757,7 @@ again: WARN_ONCE(1, "perfevents: irq loop stuck!\n"); perf_event_print_debug(); intel_pmu_reset(); - perf_enable(); - return 1; + goto done; } inc_irq_stat(apic_perf_irqs); @@ -760,7 +765,6 @@ again: for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { struct perf_event *event = cpuc->events[bit]; - clear_bit(bit, (unsigned long *) &status); if (!test_bit(bit, cpuc->active_mask)) continue; @@ -770,7 +774,7 @@ again: data.period = event->hw.last_period; if (perf_event_overflow(event, 1, &data, regs)) - intel_pmu_disable_event(&event->hw, bit); + x86_pmu_stop(event); } intel_pmu_ack_status(ack); @@ -782,8 +786,8 @@ again: if (status) goto again; - perf_enable(); - +done: + intel_pmu_enable_all(); return 1; } @@ -862,7 +866,10 @@ static __initconst struct x86_pmu intel_pmu = { .max_period = (1ULL << 31) - 1, .enable_bts = intel_pmu_enable_bts, .disable_bts = intel_pmu_disable_bts, - .get_event_constraints = intel_get_event_constraints + .get_event_constraints = intel_get_event_constraints, + + .cpu_starting = init_debug_store_on_cpu, + .cpu_dying = fini_debug_store_on_cpu, }; static __init int intel_pmu_init(void) @@ -935,7 +942,7 @@ static __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_nehalem_event_constraints; pr_cont("Nehalem/Corei7 events, "); break; - case 28: + case 28: /* Atom */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -951,6 +958,7 @@ static __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_westmere_event_constraints; pr_cont("Westmere events, "); break; + default: /* * default constraints for v2 and up diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 1ca5ba078afd..a330485d14da 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -62,7 +62,7 @@ static void p6_pmu_disable_all(void) /* p6 only has one enable register */ rdmsrl(MSR_P6_EVNTSEL0, val); - val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE; + val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(MSR_P6_EVNTSEL0, val); } @@ -72,32 +72,34 @@ static void p6_pmu_enable_all(void) /* p6 only has one enable register */ rdmsrl(MSR_P6_EVNTSEL0, val); - val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + val |= ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(MSR_P6_EVNTSEL0, val); } static inline void -p6_pmu_disable_event(struct hw_perf_event *hwc, int idx) +p6_pmu_disable_event(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; u64 val = P6_NOP_EVENT; if (cpuc->enabled) - val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)checking_wrmsrl(hwc->config_base + idx, val); + (void)checking_wrmsrl(hwc->config_base + hwc->idx, val); } -static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx) +static void p6_pmu_enable_event(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; u64 val; val = hwc->config; if (cpuc->enabled) - val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)checking_wrmsrl(hwc->config_base + idx, val); + (void)checking_wrmsrl(hwc->config_base + hwc->idx, val); } static __initconst struct x86_pmu p6_pmu = { diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 74f4e85a5727..fb329e9f8494 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -680,7 +680,7 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz) cpu_nmi_set_wd_enabled(); apic_write(APIC_LVTPC, APIC_DM_NMI); - evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE; + evntsel |= ARCH_PERFMON_EVENTSEL_ENABLE; wrmsr(evntsel_msr, evntsel, 0); intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1); return 1; diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h index 4fd1420faffa..29e5f7c845b2 100644 --- a/arch/x86/kernel/dumpstack.h +++ b/arch/x86/kernel/dumpstack.h @@ -29,4 +29,19 @@ struct stack_frame { struct stack_frame *next_frame; unsigned long return_address; }; + +static inline unsigned long rewind_frame_pointer(int n) +{ + struct stack_frame *frame; + + get_bp(frame); + +#ifdef CONFIG_FRAME_POINTER + while (n--) + frame = frame->next_frame; #endif + + return (unsigned long)frame; +} + +#endif /* DUMPSTACK_H */ diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index dce99abb4496..272c9f1f05f3 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -120,9 +120,15 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack, { #ifdef CONFIG_FRAME_POINTER struct stack_frame *frame = (struct stack_frame *)bp; + unsigned long next; - if (!in_irq_stack(stack, irq_stack, irq_stack_end)) - return (unsigned long)frame->next_frame; + if (!in_irq_stack(stack, irq_stack, irq_stack_end)) { + if (!probe_kernel_address(&frame->next_frame, next)) + return next; + else + WARN_ONCE(1, "Perf: bad frame pointer = %p in " + "callchain\n", &frame->next_frame); + } #endif return bp; } @@ -202,7 +208,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (in_irq_stack(stack, irq_stack, irq_stack_end)) { if (ops->stack(data, "IRQ") < 0) break; - bp = print_context_stack(tinfo, stack, bp, + bp = ops->walk_stack(tinfo, stack, bp, ops, data, irq_stack_end, &graph); /* * We link to the next stack (which would be @@ -223,7 +229,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, /* * This handles the process stack: */ - bp = print_context_stack(tinfo, stack, bp, ops, data, NULL, &graph); + bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph); put_cpu(); } EXPORT_SYMBOL(dump_trace); diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 2d8b5035371c..3d1e6f16b7a6 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -27,7 +27,7 @@ #define GET_CR2_INTO_RCX movq %cr2, %rcx #endif -/* we are not able to switch in one step to the final KERNEL ADRESS SPACE +/* we are not able to switch in one step to the final KERNEL ADDRESS SPACE * because we need identity-mapped pages. * */ diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index dca2802c666f..d6cc065f519f 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -344,13 +344,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp, } /* - * For kernel-addresses, either the address or symbol name can be - * specified. - */ - if (info->name) - info->address = (unsigned long) - kallsyms_lookup_name(info->name); - /* * Check that the low-order bits of the address are appropriate * for the alignment implied by len. */ @@ -535,8 +528,3 @@ void hw_breakpoint_pmu_read(struct perf_event *bp) { /* TODO */ } - -void hw_breakpoint_pmu_unthrottle(struct perf_event *bp) -{ - /* TODO */ -} diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/k8.c index cbc4332a77b2..9b895464dd03 100644 --- a/arch/x86/kernel/k8.c +++ b/arch/x86/kernel/k8.c @@ -121,3 +121,17 @@ void k8_flush_garts(void) } EXPORT_SYMBOL_GPL(k8_flush_garts); +static __init int init_k8_nbs(void) +{ + int err = 0; + + err = cache_k8_northbridges(); + + if (err < 0) + printk(KERN_NOTICE "K8 NB: Cannot enumerate AMD northbridges.\n"); + + return err; +} + +/* This has to go after the PCI subsystem */ +fs_initcall(init_k8_nbs); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 2bbde6078143..fb99f7edb341 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -1309,7 +1309,7 @@ static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl) /* * get_tce_space_from_tar(): * Function for kdump case. Get the tce tables from first kernel - * by reading the contents of the base adress register of calgary iommu + * by reading the contents of the base address register of calgary iommu */ static void __init get_tce_space_from_tar(void) { diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 1aa966c565f9..a4ac764a6880 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -38,7 +38,7 @@ int iommu_detected __read_mostly = 0; * This variable becomes 1 if iommu=pt is passed on the kernel command line. * If this variable is 1, IOMMU implementations do no DMA translation for * devices and allow every device to access to whole physical memory. This is - * useful if a user want to use an IOMMU only for KVM device assignment to + * useful if a user wants to use an IOMMU only for KVM device assignment to * guests and not for driver dma translation. */ int iommu_pass_through __read_mostly; diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 34de53b46f87..f3af115a573a 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -735,7 +735,7 @@ int __init gart_iommu_init(void) unsigned long scratch; long i; - if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) + if (num_k8_northbridges == 0) return 0; #ifndef CONFIG_AGP_AMD64 diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 02d678065d7d..ad9540676fcc 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -607,7 +607,7 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP if (pm_idle == poll_idle && smp_num_siblings > 1) { - printk(KERN_WARNING "WARNING: polling idle and HT enabled," + printk_once(KERN_WARNING "WARNING: polling idle and HT enabled," " performance may degrade.\n"); } #endif diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 2d96aab82a48..a503b1fd04e5 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -581,7 +581,7 @@ ptrace_modify_breakpoint(struct perf_event *bp, int len, int type, struct perf_event_attr attr; /* - * We shoud have at least an inactive breakpoint at this + * We should have at least an inactive breakpoint at this * slot. It means the user is writing dr7 without having * written the address register first */ diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index dee1ff7cba58..196552bb412c 100644 --- a/arch/x86/kernel/sys_i386_32.c +++ b/arch/x86/kernel/sys_i386_32.c @@ -25,191 +25,6 @@ #include <asm/syscalls.h> /* - * Perform the select(nd, in, out, ex, tv) and mmap() system - * calls. Linux/i386 didn't use to be able to handle more than - * 4 system call parameters, so these system calls used a memory - * block for parameter passing.. - */ - -struct mmap_arg_struct { - unsigned long addr; - unsigned long len; - unsigned long prot; - unsigned long flags; - unsigned long fd; - unsigned long offset; -}; - -asmlinkage int old_mmap(struct mmap_arg_struct __user *arg) -{ - struct mmap_arg_struct a; - int err = -EFAULT; - - if (copy_from_user(&a, arg, sizeof(a))) - goto out; - - err = -EINVAL; - if (a.offset & ~PAGE_MASK) - goto out; - - err = sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, - a.fd, a.offset >> PAGE_SHIFT); -out: - return err; -} - - -struct sel_arg_struct { - unsigned long n; - fd_set __user *inp, *outp, *exp; - struct timeval __user *tvp; -}; - -asmlinkage int old_select(struct sel_arg_struct __user *arg) -{ - struct sel_arg_struct a; - - if (copy_from_user(&a, arg, sizeof(a))) - return -EFAULT; - /* sys_select() does the appropriate kernel locking */ - return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp); -} - -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - - case SEMGET: - return sys_semget(first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl(first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd(first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof(tmp))) - return -EFAULT; - return sys_msgrcv(first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv(first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget((key_t) first, second); - case MSGCTL: - return sys_msgctl(first, second, (struct msqid_ds __user *) ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat(first, (char __user *) ptr, second, &raddr); - if (ret) - return ret; - return put_user(raddr, (ulong __user *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - /* The "(ulong *) third" is valid _only_ because of the kernel segment thing */ - return do_shmat(first, (char __user *) ptr, second, (ulong *) third); - } - case SHMDT: - return sys_shmdt((char __user *)ptr); - case SHMGET: - return sys_shmget(first, second, third); - case SHMCTL: - return sys_shmctl(first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} - -/* - * Old cruft - */ -asmlinkage int sys_uname(struct old_utsname __user *name) -{ - int err; - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - return err? -EFAULT:0; -} - -asmlinkage int sys_olduname(struct oldold_utsname __user *name) -{ - int error; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - - error = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - error |= __put_user(0, name->sysname + __OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - error |= __put_user(0, name->nodename + __OLD_UTS_LEN); - error |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - error |= __put_user(0, name->release + __OLD_UTS_LEN); - error |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - error |= __put_user(0, name->version + __OLD_UTS_LEN); - error |= __copy_to_user(&name->machine, &utsname()->machine, - __OLD_UTS_LEN); - error |= __put_user(0, name->machine + __OLD_UTS_LEN); - - up_read(&uts_sem); - - error = error ? -EFAULT : 0; - - return error; -} - - -/* * Do a system call from kernel instead of calling sys_execve so we * end up with proper pt_regs. */ diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 8aa2057efd12..ff14a5044ce6 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -209,15 +209,3 @@ bottomup: return addr; } - - -SYSCALL_DEFINE1(uname, struct new_utsname __user *, name) -{ - int err; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - if (personality(current->personality) == PER_LINUX32) - err |= copy_to_user(&name->machine, "i686", 5); - return err ? -EFAULT : 0; -} diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 15228b5d3eb7..8b3729341216 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -81,7 +81,7 @@ ENTRY(sys_call_table) .long sys_settimeofday .long sys_getgroups16 /* 80 */ .long sys_setgroups16 - .long old_select + .long sys_old_select .long sys_symlink .long sys_lstat .long sys_readlink /* 85 */ @@ -89,7 +89,7 @@ ENTRY(sys_call_table) .long sys_swapon .long sys_reboot .long sys_old_readdir - .long old_mmap /* 90 */ + .long sys_old_mmap /* 90 */ .long sys_munmap .long sys_truncate .long sys_ftruncate diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 208a857c679f..9faf91ae1841 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -50,7 +50,7 @@ u64 native_sched_clock(void) * unstable. We do this because unlike Time Of Day, * the scheduler clock tolerates small errors and it's * very important for it to be as fast as the platform - * can achive it. ) + * can achieve it. ) */ if (unlikely(tsc_disabled)) { /* No locking but a rare wrong value is not a big deal: */ diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index 2f1ca5614292..5e1ff66ecd73 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -167,7 +167,7 @@ static int vmi_timer_next_event(unsigned long delta, { /* Unfortunately, set_next_event interface only passes relative * expiry, but we want absolute expiry. It'd be better if were - * were passed an aboslute expiry, since a bunch of time may + * were passed an absolute expiry, since a bunch of time may * have been stolen between the time the delta is computed and * when we set the alarm below. */ cycle_t now = vmi_timer_ops.get_cycle_counter(vmi_counter(VMI_ONESHOT)); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 1d4eb93d333c..cf07c26d9a4a 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -291,8 +291,29 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, */ if (kernel_set_to_readonly && within(address, (unsigned long)_text, - (unsigned long)__end_rodata_hpage_align)) - pgprot_val(forbidden) |= _PAGE_RW; + (unsigned long)__end_rodata_hpage_align)) { + unsigned int level; + + /* + * Don't enforce the !RW mapping for the kernel text mapping, + * if the current mapping is already using small page mapping. + * No need to work hard to preserve large page mappings in this + * case. + * + * This also fixes the Linux Xen paravirt guest boot failure + * (because of unexpected read-only mappings for kernel identity + * mappings). In this paravirt guest case, the kernel text + * mapping and the kernel identity mapping share the same + * page-table pages. Thus we can't really use different + * protections for the kernel text and identity mappings. Also, + * these shared mappings are made of small page mappings. + * Thus this don't enforce !RW mapping for small page kernel + * text mapping logic will help Linux Xen parvirt guest boot + * aswell. + */ + if (lookup_address(address, &level) && (level != PG_LEVEL_4K)) + pgprot_val(forbidden) |= _PAGE_RW; + } #endif prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden)); diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index 6a58256dce9f..090cbbec7dbd 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -46,17 +46,6 @@ static unsigned long reset_value[NUM_VIRT_COUNTERS]; -/* IbsFetchCtl bits/masks */ -#define IBS_FETCH_RAND_EN (1ULL<<57) -#define IBS_FETCH_VAL (1ULL<<49) -#define IBS_FETCH_ENABLE (1ULL<<48) -#define IBS_FETCH_CNT_MASK 0xFFFF0000ULL - -/* IbsOpCtl bits */ -#define IBS_OP_CNT_CTL (1ULL<<19) -#define IBS_OP_VAL (1ULL<<18) -#define IBS_OP_ENABLE (1ULL<<17) - #define IBS_FETCH_SIZE 6 #define IBS_OP_SIZE 12 @@ -182,7 +171,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, continue; } rdmsrl(msrs->controls[i].addr, val); - if (val & ARCH_PERFMON_EVENTSEL0_ENABLE) + if (val & ARCH_PERFMON_EVENTSEL_ENABLE) op_x86_warn_in_use(i); val &= model->reserved; wrmsrl(msrs->controls[i].addr, val); @@ -290,7 +279,7 @@ op_amd_handle_ibs(struct pt_regs * const regs, oprofile_write_commit(&entry); /* reenable the IRQ */ - ctl &= ~(IBS_FETCH_VAL | IBS_FETCH_CNT_MASK); + ctl &= ~(IBS_FETCH_VAL | IBS_FETCH_CNT); ctl |= IBS_FETCH_ENABLE; wrmsrl(MSR_AMD64_IBSFETCHCTL, ctl); } @@ -330,7 +319,7 @@ static inline void op_amd_start_ibs(void) return; if (ibs_config.fetch_enabled) { - val = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF; + val = (ibs_config.max_cnt_fetch >> 4) & IBS_FETCH_MAX_CNT; val |= ibs_config.rand_en ? IBS_FETCH_RAND_EN : 0; val |= IBS_FETCH_ENABLE; wrmsrl(MSR_AMD64_IBSFETCHCTL, val); @@ -352,7 +341,7 @@ static inline void op_amd_start_ibs(void) * avoid underflows. */ ibs_op_ctl = min(ibs_op_ctl + IBS_RANDOM_MAXCNT_OFFSET, - 0xFFFFULL); + IBS_OP_MAX_CNT); } if (ibs_caps & IBS_CAPS_OPCNT && ibs_config.dispatched_ops) ibs_op_ctl |= IBS_OP_CNT_CTL; @@ -409,7 +398,7 @@ static void op_amd_start(struct op_msrs const * const msrs) if (!reset_value[op_x86_phys_to_virt(i)]) continue; rdmsrl(msrs->controls[i].addr, val); - val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + val |= ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(msrs->controls[i].addr, val); } @@ -429,7 +418,7 @@ static void op_amd_stop(struct op_msrs const * const msrs) if (!reset_value[op_x86_phys_to_virt(i)]) continue; rdmsrl(msrs->controls[i].addr, val); - val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE; + val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(msrs->controls[i].addr, val); } diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index 5d1727ba409e..2bf90fafa7b5 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -88,7 +88,7 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model, continue; } rdmsrl(msrs->controls[i].addr, val); - if (val & ARCH_PERFMON_EVENTSEL0_ENABLE) + if (val & ARCH_PERFMON_EVENTSEL_ENABLE) op_x86_warn_in_use(i); val &= model->reserved; wrmsrl(msrs->controls[i].addr, val); @@ -166,7 +166,7 @@ static void ppro_start(struct op_msrs const * const msrs) for (i = 0; i < num_counters; ++i) { if (reset_value[i]) { rdmsrl(msrs->controls[i].addr, val); - val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + val |= ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(msrs->controls[i].addr, val); } } @@ -184,7 +184,7 @@ static void ppro_stop(struct op_msrs const * const msrs) if (!reset_value[i]) continue; rdmsrl(msrs->controls[i].addr, val); - val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE; + val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(msrs->controls[i].addr, val); } } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 563d20504988..deafb65ef44e 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -361,7 +361,7 @@ static void xen_cpu_die(unsigned int cpu) alternatives_smp_switch(0); } -static void __cpuinit xen_play_dead(void) /* used only with CPU_HOTPLUG */ +static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */ { play_dead_common(); HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL); |