diff options
Diffstat (limited to 'arch/x86')
82 files changed, 1587 insertions, 841 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 03980cb..ac2fb06 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -21,12 +21,16 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_IDE select HAVE_OPROFILE + select HAVE_IOREMAP_PROT select HAVE_KPROBES + select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_KRETPROBES select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) select HAVE_ARCH_KGDB if !X86_VOYAGER + select HAVE_GENERIC_DMA_COHERENT if X86_32 + select HAVE_EFFICIENT_UNALIGNED_ACCESS config ARCH_DEFCONFIG string @@ -329,20 +333,6 @@ config X86_BIGSMP endif -config X86_RDC321X - bool "RDC R-321x SoC" - depends on X86_32 - select M486 - select X86_REBOOTFIXUPS - select GENERIC_GPIO - select LEDS_CLASS - select LEDS_GPIO - select NEW_LEDS - help - This option is needed for RDC R-321x system-on-chip, also known - as R-8610-(G). - If you don't have one of these chips, you should say N here. - config X86_VSMP bool "Support for ScaleMP vSMP" select PARAVIRT @@ -366,6 +356,16 @@ config X86_VISWS A kernel compiled for the Visual Workstation will run on general PCs as well. See <file:Documentation/sgi-visws.txt> for details. +config X86_RDC321X + bool "RDC R-321x SoC" + depends on X86_32 + select M486 + select X86_REBOOTFIXUPS + help + This option is needed for RDC R-321x system-on-chip, also known + as R-8610-(G). + If you don't have one of these chips, you should say N here. + config SCHED_NO_NO_OMIT_FRAME_POINTER def_bool y prompt "Single-depth WCHAN output" @@ -1276,6 +1276,14 @@ config CRASH_DUMP (CONFIG_RELOCATABLE=y). For more details see Documentation/kdump/kdump.txt +config KEXEC_JUMP + bool "kexec jump (EXPERIMENTAL)" + depends on EXPERIMENTAL + depends on KEXEC && HIBERNATION && X86_32 + help + Jump between original kernel and kexeced kernel and invoke + code in physical address mode via KEXEC + config PHYSICAL_START hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP) default "0x1000000" if X86_NUMAQ diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 919ce21..f5631da 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -118,11 +118,6 @@ mflags-$(CONFIG_X86_GENERICARCH):= -Iinclude/asm-x86/mach-generic fcore-$(CONFIG_X86_GENERICARCH) += arch/x86/mach-generic/ mcore-$(CONFIG_X86_GENERICARCH) := arch/x86/mach-default/ -# RDC R-321x subarch support -mflags-$(CONFIG_X86_RDC321X) := -Iinclude/asm-x86/mach-rdc321x -mcore-$(CONFIG_X86_RDC321X) := arch/x86/mach-default/ -core-$(CONFIG_X86_RDC321X) += arch/x86/mach-rdc321x/ - # default subarch .h files mflags-y += -Iinclude/asm-x86/mach-default diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index bc5553b..9fea737 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -182,8 +182,6 @@ static unsigned outcnt; static int fill_inbuf(void); static void flush_window(void); static void error(char *m); -static void gzip_mark(void **); -static void gzip_release(void **); /* * This is set up by the setup-routine at boot-time @@ -196,9 +194,6 @@ extern int input_len; static long bytes_out; -static void *malloc(int size); -static void free(void *where); - static void *memset(void *s, int c, unsigned n); static void *memcpy(void *dest, const void *src, unsigned n); @@ -220,40 +215,6 @@ static int lines, cols; #include "../../../../lib/inflate.c" -static void *malloc(int size) -{ - void *p; - - if (size < 0) - error("Malloc error"); - if (free_mem_ptr <= 0) - error("Memory error"); - - free_mem_ptr = (free_mem_ptr + 3) & ~3; /* Align */ - - p = (void *)free_mem_ptr; - free_mem_ptr += size; - - if (free_mem_ptr >= free_mem_end_ptr) - error("Out of memory"); - - return p; -} - -static void free(void *where) -{ /* Don't care */ -} - -static void gzip_mark(void **ptr) -{ - *ptr = (void *) free_mem_ptr; -} - -static void gzip_release(void **ptr) -{ - free_mem_ptr = (memptr) *ptr; -} - static void scroll(void) { int i; diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 58cccb6..a0e1dbe 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -441,12 +441,6 @@ beyond_if: regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; set_fs(USER_DS); - if (unlikely(current->ptrace & PT_PTRACED)) { - if (current->ptrace & PT_TRACE_EXEC) - ptrace_notify((PTRACE_EVENT_EXEC << 8) | SIGTRAP); - else - send_sig(SIGTRAP, current, 0); - } return 0; } diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 23d146c..ffc1bb4 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -15,6 +15,16 @@ #include <asm/irqflags.h> #include <linux/linkage.h> +/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ +#include <linux/elf-em.h> +#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) +#define __AUDIT_ARCH_LE 0x40000000 + +#ifndef CONFIG_AUDITSYSCALL +#define sysexit_audit int_ret_from_sys_call +#define sysretl_audit int_ret_from_sys_call +#endif + #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) .macro IA32_ARG_FIXUP noebp=0 @@ -148,13 +158,15 @@ ENTRY(ia32_sysenter_target) ja ia32_badsys sysenter_do_call: IA32_ARG_FIXUP 1 +sysenter_dispatch: call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) GET_THREAD_INFO(%r10) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF testl $_TIF_ALLWORK_MASK,TI_flags(%r10) - jnz int_ret_from_sys_call + jnz sysexit_audit +sysexit_from_sys_call: andl $~TS_COMPAT,TI_status(%r10) /* clear IF, that popfq doesn't enable interrupts early */ andl $~0x200,EFLAGS-R11(%rsp) @@ -170,9 +182,63 @@ sysenter_do_call: TRACE_IRQS_ON ENABLE_INTERRUPTS_SYSEXIT32 -sysenter_tracesys: +#ifdef CONFIG_AUDITSYSCALL + .macro auditsys_entry_common + movl %esi,%r9d /* 6th arg: 4th syscall arg */ + movl %edx,%r8d /* 5th arg: 3rd syscall arg */ + /* (already in %ecx) 4th arg: 2nd syscall arg */ + movl %ebx,%edx /* 3rd arg: 1st syscall arg */ + movl %eax,%esi /* 2nd arg: syscall number */ + movl $AUDIT_ARCH_I386,%edi /* 1st arg: audit arch */ + call audit_syscall_entry + movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */ + cmpl $(IA32_NR_syscalls-1),%eax + ja ia32_badsys + movl %ebx,%edi /* reload 1st syscall arg */ + movl RCX-ARGOFFSET(%rsp),%esi /* reload 2nd syscall arg */ + movl RDX-ARGOFFSET(%rsp),%edx /* reload 3rd syscall arg */ + movl RSI-ARGOFFSET(%rsp),%ecx /* reload 4th syscall arg */ + movl RDI-ARGOFFSET(%rsp),%r8d /* reload 5th syscall arg */ + .endm + + .macro auditsys_exit exit,ebpsave=RBP + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10) + jnz int_ret_from_sys_call + TRACE_IRQS_ON + sti + movl %eax,%esi /* second arg, syscall return value */ + cmpl $0,%eax /* is it < 0? */ + setl %al /* 1 if so, 0 if not */ + movzbl %al,%edi /* zero-extend that into %edi */ + inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ + call audit_syscall_exit + GET_THREAD_INFO(%r10) + movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall return value */ + movl \ebpsave-ARGOFFSET(%rsp),%ebp /* reload user register value */ + movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi + cli + TRACE_IRQS_OFF + testl %edi,TI_flags(%r10) + jnz int_with_check + jmp \exit + .endm + +sysenter_auditsys: CFI_RESTORE_STATE + auditsys_entry_common + movl %ebp,%r9d /* reload 6th syscall arg */ + jmp sysenter_dispatch + +sysexit_audit: + auditsys_exit sysexit_from_sys_call +#endif + +sysenter_tracesys: xchgl %r9d,%ebp +#ifdef CONFIG_AUDITSYSCALL + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10) + jz sysenter_auditsys +#endif SAVE_REST CLEAR_RREGS movq %r9,R9(%rsp) @@ -252,13 +318,15 @@ cstar_do_call: cmpl $IA32_NR_syscalls-1,%eax ja ia32_badsys IA32_ARG_FIXUP 1 +cstar_dispatch: call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) GET_THREAD_INFO(%r10) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF testl $_TIF_ALLWORK_MASK,TI_flags(%r10) - jnz int_ret_from_sys_call + jnz sysretl_audit +sysretl_from_sys_call: andl $~TS_COMPAT,TI_status(%r10) RESTORE_ARGS 1,-ARG_SKIP,1,1,1 movl RIP-ARGOFFSET(%rsp),%ecx @@ -270,8 +338,23 @@ cstar_do_call: CFI_RESTORE rsp USERGS_SYSRET32 -cstar_tracesys: +#ifdef CONFIG_AUDITSYSCALL +cstar_auditsys: CFI_RESTORE_STATE + movl %r9d,R9-ARGOFFSET(%rsp) /* register to be clobbered by call */ + auditsys_entry_common + movl R9-ARGOFFSET(%rsp),%r9d /* reload 6th syscall arg */ + jmp cstar_dispatch + +sysretl_audit: + auditsys_exit sysretl_from_sys_call, RCX /* user %ebp in RCX slot */ +#endif + +cstar_tracesys: +#ifdef CONFIG_AUDITSYSCALL + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10) + jz cstar_auditsys +#endif xchgl %r9d,%ebp SAVE_REST CLEAR_RREGS @@ -743,4 +826,10 @@ ia32_sys_call_table: .quad sys32_fallocate .quad compat_sys_timerfd_settime /* 325 */ .quad compat_sys_timerfd_gettime + .quad compat_sys_signalfd4 + .quad sys_eventfd2 + .quad sys_epoll_create1 + .quad sys_dup3 /* 330 */ + .quad sys_pipe2 + .quad sys_inotify_init1 ia32_syscall_end: diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index f00afdf..d3c6408 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -238,7 +238,7 @@ asmlinkage long sys32_pipe(int __user *fd) int retval; int fds[2]; - retval = do_pipe(fds); + retval = do_pipe_flags(fds, 0); if (retval) goto out; if (copy_to_user(fd, fds, sizeof(fds))) diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index a3ddad1..fa2161d 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -150,6 +150,10 @@ static int __init acpi_sleep_setup(char *str) acpi_realmode_flags |= 2; if (strncmp(str, "s3_beep", 7) == 0) acpi_realmode_flags |= 4; +#ifdef CONFIG_HIBERNATION + if (strncmp(str, "s4_nohwsig", 10) == 0) + acpi_no_s4_hw_signature(); +#endif if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); str = strchr(str, ','); diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index c25210e..22d7d05 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -29,9 +29,6 @@ #define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28)) -#define to_pages(addr, size) \ - (round_up(((addr) & ~PAGE_MASK) + (size), PAGE_SIZE) >> PAGE_SHIFT) - #define EXIT_LOOP_COUNT 10000000 static DEFINE_RWLOCK(amd_iommu_devtable_lock); @@ -185,7 +182,7 @@ static int iommu_flush_pages(struct amd_iommu *iommu, u16 domid, u64 address, size_t size) { int s = 0; - unsigned pages = to_pages(address, size); + unsigned pages = iommu_num_pages(address, size); address &= PAGE_MASK; @@ -557,8 +554,8 @@ static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu, if (iommu->exclusion_start && iommu->exclusion_start < dma_dom->aperture_size) { unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT; - int pages = to_pages(iommu->exclusion_start, - iommu->exclusion_length); + int pages = iommu_num_pages(iommu->exclusion_start, + iommu->exclusion_length); dma_ops_reserve_addresses(dma_dom, startpage, pages); } @@ -667,7 +664,7 @@ static int get_device_resources(struct device *dev, _bdf = calc_devid(pcidev->bus->number, pcidev->devfn); /* device not translated by any IOMMU in the system? */ - if (_bdf >= amd_iommu_last_bdf) { + if (_bdf > amd_iommu_last_bdf) { *iommu = NULL; *domain = NULL; *bdf = 0xffff; @@ -767,7 +764,7 @@ static dma_addr_t __map_single(struct device *dev, unsigned int pages; int i; - pages = to_pages(paddr, size); + pages = iommu_num_pages(paddr, size); paddr &= PAGE_MASK; address = dma_ops_alloc_addresses(dev, dma_dom, pages); @@ -802,7 +799,7 @@ static void __unmap_single(struct amd_iommu *iommu, if ((dma_addr == 0) || (dma_addr + size > dma_dom->aperture_size)) return; - pages = to_pages(dma_addr, size); + pages = iommu_num_pages(dma_addr, size); dma_addr &= PAGE_MASK; start = dma_addr; @@ -1085,7 +1082,7 @@ void prealloc_protection_domains(void) while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { devid = (dev->bus->number << 8) | dev->devfn; - if (devid >= amd_iommu_last_bdf) + if (devid > amd_iommu_last_bdf) continue; devid = amd_iommu_alias_table[devid]; if (domain_for_device(devid)) diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index c9d8ff2..d9a9da5 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -732,7 +732,7 @@ static int __init init_exclusion_range(struct ivmd_header *m) set_device_exclusion_range(m->devid, m); break; case ACPI_IVMD_TYPE_ALL: - for (i = 0; i < amd_iommu_last_bdf; ++i) + for (i = 0; i <= amd_iommu_last_bdf; ++i) set_device_exclusion_range(i, m); break; case ACPI_IVMD_TYPE_RANGE: @@ -934,7 +934,7 @@ int __init amd_iommu_init(void) /* * let all alias entries point to itself */ - for (i = 0; i < amd_iommu_last_bdf; ++i) + for (i = 0; i <= amd_iommu_last_bdf; ++i) amd_iommu_alias_table[i] = i; /* diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index d6c8983..039a8d4 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -1720,15 +1720,19 @@ static int __init parse_lapic_timer_c2_ok(char *arg) } early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok); -static int __init apic_set_verbosity(char *str) +static int __init apic_set_verbosity(char *arg) { - if (strcmp("debug", str) == 0) + if (!arg) + return -EINVAL; + + if (strcmp(arg, "debug") == 0) apic_verbosity = APIC_DEBUG; - else if (strcmp("verbose", str) == 0) + else if (strcmp(arg, "verbose") == 0) apic_verbosity = APIC_VERBOSE; - return 1; + + return 0; } -__setup("apic=", apic_set_verbosity); +early_param("apic", apic_set_verbosity); static int __init lapic_insert_resource(void) { diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index bf9b441..9ee24e6 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -219,7 +219,6 @@ #include <linux/time.h> #include <linux/sched.h> #include <linux/pm.h> -#include <linux/pm_legacy.h> #include <linux/capability.h> #include <linux/device.h> #include <linux/kernel.h> diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c9b58a8..c8e315f 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -50,6 +50,8 @@ static double __initdata y = 3145727.0; */ static void __init check_fpu(void) { + s32 fdiv_bug; + if (!boot_cpu_data.hard_math) { #ifndef CONFIG_MATH_EMULATION printk(KERN_EMERG "No coprocessor found and no math emulation present.\n"); @@ -74,8 +76,10 @@ static void __init check_fpu(void) "fistpl %0\n\t" "fwait\n\t" "fninit" - : "=m" (*&boot_cpu_data.fdiv_bug) + : "=m" (*&fdiv_bug) : "m" (*&x), "m" (*&y)); + + boot_cpu_data.fdiv_bug = fdiv_bug; if (boot_cpu_data.fdiv_bug) printk("Hmm, FPU with FDIV bug.\n"); } diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig index cb7a571..efae3b2 100644 --- a/arch/x86/kernel/cpu/cpufreq/Kconfig +++ b/arch/x86/kernel/cpu/cpufreq/Kconfig @@ -235,9 +235,9 @@ config X86_LONGHAUL If in doubt, say N. config X86_E_POWERSAVER - tristate "VIA C7 Enhanced PowerSaver (EXPERIMENTAL)" + tristate "VIA C7 Enhanced PowerSaver" select CPU_FREQ_TABLE - depends on X86_32 && EXPERIMENTAL + depends on X86_32 help This adds the CPUFreq driver for VIA C7 processors. diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index b0c8208..dd097b8 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -202,7 +202,7 @@ static void drv_write(struct drv_cmd *cmd) cpumask_t saved_mask = current->cpus_allowed; unsigned int i; - for_each_cpu_mask(i, cmd->mask) { + for_each_cpu_mask_nr(i, cmd->mask) { set_cpus_allowed_ptr(current, &cpumask_of_cpu(i)); do_drv_write(cmd); } @@ -451,7 +451,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, freqs.old = perf->states[perf->state].core_frequency * 1000; freqs.new = data->freq_table[next_state].frequency; - for_each_cpu_mask(i, cmd.mask) { + for_each_cpu_mask_nr(i, cmd.mask) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } @@ -466,7 +466,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, } } - for_each_cpu_mask(i, cmd.mask) { + for_each_cpu_mask_nr(i, cmd.mask) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c index 94619c2..e4a4bf8 100644 --- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c +++ b/arch/x86/kernel/cpu/cpufreq/elanfreq.c @@ -44,7 +44,7 @@ struct s_elan_multiplier { * It is important that the frequencies * are listed in ascending order here! */ -struct s_elan_multiplier elan_multiplier[] = { +static struct s_elan_multiplier elan_multiplier[] = { {1000, 0x02, 0x18}, {2000, 0x02, 0x10}, {4000, 0x02, 0x08}, diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 199e4e0..f1685fb 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -122,7 +122,7 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, return 0; /* notifiers */ - for_each_cpu_mask(i, policy->cpus) { + for_each_cpu_mask_nr(i, policy->cpus) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } @@ -130,11 +130,11 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, /* run on each logical CPU, see section 13.15.3 of IA32 Intel Architecture Software * Developer's Manual, Volume 3 */ - for_each_cpu_mask(i, policy->cpus) + for_each_cpu_mask_nr(i, policy->cpus) cpufreq_p4_setdc(i, p4clockmod_table[newstate].index); /* notifiers */ - for_each_cpu_mask(i, policy->cpus) { + for_each_cpu_mask_nr(i, policy->cpus) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 206791e..4e72719 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -66,7 +66,6 @@ static u32 find_freq_from_fid(u32 fid) return 800 + (fid * 100); } - /* Return a frequency in KHz, given an input fid */ static u32 find_khz_freq_from_fid(u32 fid) { @@ -78,7 +77,6 @@ static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data, u32 p return data[pstate].frequency; } - /* Return the vco fid for an input fid * * Each "low" fid has corresponding "high" fid, and you can get to "low" fids @@ -166,7 +164,6 @@ static void fidvid_msr_init(void) wrmsr(MSR_FIDVID_CTL, lo, hi); } - /* write the new fid value along with the other control fields to the msr */ static int write_new_fid(struct powernow_k8_data *data, u32 fid) { @@ -740,44 +737,63 @@ static int find_psb_table(struct powernow_k8_data *data) #ifdef CONFIG_X86_POWERNOW_K8_ACPI static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { - if (!data->acpi_data.state_count || (cpu_family == CPU_HW_PSTATE)) + if (!data->acpi_data->state_count || (cpu_family == CPU_HW_PSTATE)) return; - data->irt = (data->acpi_data.states[index].control >> IRT_SHIFT) & IRT_MASK; - data->rvo = (data->acpi_data.states[index].control >> RVO_SHIFT) & RVO_MASK; - data->exttype = (data->acpi_data.states[index].control >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK; - data->plllock = (data->acpi_data.states[index].control >> PLL_L_SHIFT) & PLL_L_MASK; - data->vidmvs = 1 << ((data->acpi_data.states[index].control >> MVS_SHIFT) & MVS_MASK); - data->vstable = (data->acpi_data.states[index].control >> VST_SHIFT) & VST_MASK; + data->irt = (data->acpi_data->states[index].control >> IRT_SHIFT) & IRT_MASK; + data->rvo = (data->acpi_data->states[index].control >> RVO_SHIFT) & RVO_MASK; + data->exttype = (data->acpi_data->states[index].control >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK; + data->plllock = (data->acpi_data->states[index].control >> PLL_L_SHIFT) & PLL_L_MASK; + data->vidmvs = 1 << ((data->acpi_data->states[index].control >> MVS_SHIFT) & MVS_MASK); + data->vstable = (data->acpi_data->states[index].control >> VST_SHIFT) & VST_MASK; +} + + +static struct acpi_processor_performance *acpi_perf_data; +static int preregister_valid; + +static int powernow_k8_cpu_preinit_acpi(void) +{ + acpi_perf_data = alloc_percpu(struct acpi_processor_performance); + if (!acpi_perf_data) + return -ENODEV; + + if (acpi_processor_preregister_performance(acpi_perf_data)) + return -ENODEV; + else + preregister_valid = 1; + return 0; } static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { struct cpufreq_frequency_table *powernow_table; int ret_val; + int cpu = 0; - if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) { + data->acpi_data = percpu_ptr(acpi_perf_data, cpu); + if (acpi_processor_register_performance(data->acpi_data, data->cpu)) { dprintk("register performance failed: bad ACPI data\n"); return -EIO; } /* verify the data contained in the ACPI structures */ - if (data->acpi_data.state_count <= 1) { + if (data->acpi_data->state_count <= 1) { dprintk("No ACPI P-States\n"); goto err_out; } - if ((data->acpi_data.control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) || - (data->acpi_data.status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) { + if ((data->acpi_data->control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) || + (data->acpi_data->status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) { dprintk("Invalid control/status registers (%x - %x)\n", - data->acpi_data.control_register.space_id, - data->acpi_data.status_register.space_id); + data->acpi_data->control_register.space_id, + data->acpi_data->status_register.space_id); goto err_out; } /* fill in data->powernow_table */ powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table) - * (data->acpi_data.state_count + 1)), GFP_KERNEL); + * (data->acpi_data->state_count + 1)), GFP_KERNEL); if (!powernow_table) { dprintk("powernow_table memory alloc failure\n"); goto err_out; @@ -790,12 +806,12 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) if (ret_val) goto err_out_mem; - powernow_table[data->acpi_data.state_count].frequency = CPUFREQ_TABLE_END; - powernow_table[data->acpi_data.state_count].index = 0; + powernow_table[data->acpi_data->state_count].frequency = CPUFREQ_TABLE_END; + powernow_table[data->acpi_data->state_count].index = 0; data->powernow_table = powernow_table; /* fill in data */ - data->numps = data->acpi_data.state_count; + data->numps = data->acpi_data->state_count; if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu) print_basics(data); powernow_k8_acpi_pst_values(data, 0); @@ -803,16 +819,31 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) /* notify BIOS that we exist */ acpi_processor_notify_smm(THIS_MODULE); + /* determine affinity, from ACPI if available */ + if (preregister_valid) { + if ((data->acpi_data->shared_type == CPUFREQ_SHARED_TYPE_ALL) || + (data->acpi_data->shared_type == CPUFREQ_SHARED_TYPE_ANY)) + data->starting_core_affinity = data->acpi_data->shared_cpu_map; + else + data->starting_core_affinity = cpumask_of_cpu(data->cpu); + } else { + /* best guess from family if not */ + if (cpu_family == CPU_HW_PSTATE) + data->starting_core_affinity = cpumask_of_cpu(data->cpu); + else + data->starting_core_affinity = per_cpu(cpu_core_map, data->cpu); + } + return 0; err_out_mem: kfree(powernow_table); err_out: - acpi_processor_unregister_performance(&data->acpi_data, data->cpu); + acpi_processor_unregister_performance(data->acpi_data, data->cpu); /* data->acpi_data.state_count informs us at ->exit() whether ACPI was used */ - data->acpi_data.state_count = 0; + data->acpi_data->state_count = 0; return -ENODEV; } @@ -824,10 +855,10 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpuf rdmsr(MSR_PSTATE_CUR_LIMIT, hi, lo); data->max_hw_pstate = (hi & HW_PSTATE_MAX_MASK) >> HW_PSTATE_MAX_SHIFT; - for (i = 0; i < data->acpi_data.state_count; i++) { + for (i = 0; i < data->acpi_data->state_count; i++) { u32 index; - index = data->acpi_data.states[i].control & HW_PSTATE_MASK; + index = data->acpi_data->states[i].control & HW_PSTATE_MASK; if (index > data->max_hw_pstate) { printk(KERN_ERR PFX "invalid pstate %d - bad value %d.\n", i, index); printk(KERN_ERR PFX "Please report to BIOS manufacturer\n"); @@ -843,7 +874,7 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpuf powernow_table[i].index = index; - powernow_table[i].frequency = data->acpi_data.states[i].core_frequency * 1000; + powernow_table[i].frequency = data->acpi_data->states[i].core_frequency * 1000; } return 0; } @@ -852,16 +883,16 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf { int i; int cntlofreq = 0; - for (i = 0; i < data->acpi_data.state_count; i++) { + for (i = 0; i < data->acpi_data->state_count; i++) { u32 fid; u32 vid; if (data->exttype) { - fid = data->acpi_data.states[i].status & EXT_FID_MASK; - vid = (data->acpi_data.states[i].status >> VID_SHIFT) & EXT_VID_MASK; + fid = data->acpi_data->states[i].status & EXT_FID_MASK; + vid = (data->acpi_data->states[i].status >> VID_SHIFT) & EXT_VID_MASK; } else { - fid = data->acpi_data.states[i].control & FID_MASK; - vid = (data->acpi_data.states[i].control >> VID_SHIFT) & VID_MASK; + fid = data->acpi_data->states[i].control & FID_MASK; + vid = (data->acpi_data->states[i].control >> VID_SHIFT) & VID_MASK; } dprintk(" %d : fid 0x%x, vid 0x%x\n", i, fid, vid); @@ -902,10 +933,10 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf cntlofreq = i; } - if (powernow_table[i].frequency != (data->acpi_data.states[i].core_frequency * 1000)) { + if (powernow_table[i].frequency != (data->acpi_data->states[i].core_frequency * 1000)) { printk(KERN_INFO PFX "invalid freq entries %u kHz vs. %u kHz\n", powernow_table[i].frequency, - (unsigned int) (data->acpi_data.states[i].core_frequency * 1000)); + (unsigned int) (data->acpi_data->states[i].core_frequency * 1000)); powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; continue; } @@ -915,11 +946,12 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { - if (data->acpi_data.state_count) - acpi_processor_unregister_performance(&data->acpi_data, data->cpu); + if (data->acpi_data->state_count) + acpi_processor_unregister_performance(data->acpi_data, data->cpu); } #else +static int powernow_k8_cpu_preinit_acpi(void) { return -ENODEV; } static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { return -ENODEV; } static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { return; } static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { return; } @@ -966,7 +998,7 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data, unsigned i freqs.old = find_khz_freq_from_fid(data->currfid); freqs.new = find_khz_freq_from_fid(fid); - for_each_cpu_mask(i, *(data->available_cores)) { + for_each_cpu_mask_nr(i, *(data->available_cores)) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } @@ -974,7 +1006,7 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data, unsigned i res = transition_fid_vid(data, fid, vid); freqs.new = find_khz_freq_from_fid(data->currfid); - for_each_cpu_mask(i, *(data->available_cores)) { + for_each_cpu_mask_nr(i, *(data->available_cores)) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } @@ -997,7 +1029,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i freqs.old = find_khz_freq_from_pstate(data->powernow_table, data->currpstate); freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate); - for_each_cpu_mask(i, *(data->available_cores)) { + for_each_cpu_mask_nr(i, *(data->available_cores)) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } @@ -1005,7 +1037,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i res = transition_pstate(data, pstate); freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate); - for_each_cpu_mask(i, *(data->available_cores)) { + for_each_cpu_mask_nr(i, *(data->available_cores)) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } @@ -1104,7 +1136,7 @@ static int powernowk8_verify(struct cpufreq_policy *pol) static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) { struct powernow_k8_data *data; - cpumask_t oldmask; + cpumask_t oldmask = CPU_MASK_ALL; int rc; if (!cpu_online(pol->cpu)) @@ -1177,10 +1209,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) /* run on any CPU again */ set_cpus_allowed_ptr(current, &oldmask); - if (cpu_family == CPU_HW_PSTATE) - pol->cpus = cpumask_of_cpu(pol->cpu); - else - pol->cpus = per_cpu(cpu_core_map, pol->cpu); + pol->cpus = data->starting_core_affinity; data->available_cores = &(pol->cpus); /* Take a crude guess here. @@ -1303,6 +1332,7 @@ static int __cpuinit powernowk8_init(void) } if (supported_cpus == num_online_cpus()) { + powernow_k8_cpu_preinit_acpi(); printk(KERN_INFO PFX "Found %d %s " "processors (%d cpu cores) (" VERSION ")\n", num_online_nodes(), @@ -1319,6 +1349,10 @@ static void __exit powernowk8_exit(void) dprintk("exit\n"); cpufreq_unregister_driver(&cpufreq_amd64_driver); + +#ifdef CONFIG_X86_POWERNOW_K8_ACPI + free_percpu(acpi_perf_data); +#endif } MODULE_AUTHOR("Paul Devriendt <paul.devriendt@amd.com> and Mark Langsdorf <mark.langsdorf@amd.com>"); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h index ab48cfe..a62612c 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h @@ -33,12 +33,13 @@ struct powernow_k8_data { #ifdef CONFIG_X86_POWERNOW_K8_ACPI /* the acpi table needs to be kept. it's only available if ACPI was * used to determine valid frequency/vid/fid states */ - struct acpi_processor_performance acpi_data; + struct acpi_processor_performance *acpi_data; #endif /* we need to keep track of associated cores, but let cpufreq * handle hotplug events - so just point at cpufreq pol->cpus * structure */ cpumask_t *available_cores; + cpumask_t starting_core_affinity; }; diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c index 908dd34..15e13c0 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c @@ -28,7 +28,8 @@ #define PFX "speedstep-centrino: " #define MAINTAINER "cpufreq@lists.linux.org.uk" -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-centrino", msg) +#define dprintk(msg...) \ + cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-centrino", msg) #define INTEL_MSR_RANGE (0xffff) @@ -66,11 +67,12 @@ struct cpu_model struct cpufreq_frequency_table *op_points; /* clock/voltage pairs */ }; -static int centrino_verify_cpu_id(const struct cpuinfo_x86 *c, const struct cpu_id *x); +static int centrino_verify_cpu_id(const struct cpuinfo_x86 *c, + const struct cpu_id *x); /* Operating points for current CPU */ -static struct cpu_model *centrino_model[NR_CPUS]; -static const struct cpu_id *centrino_cpu[NR_CPUS]; +static DEFINE_PER_CPU(struct cpu_model *, centrino_model); +static DEFINE_PER_CPU(const struct cpu_id *, centrino_cpu); static struct cpufreq_driver centrino_driver; @@ -255,7 +257,7 @@ static int centrino_cpu_init_table(struct cpufreq_policy *policy) return -ENOENT; } - centrino_model[policy->cpu] = model; + per_cpu(centrino_model, policy->cpu) = model; dprintk("found \"%s\": max frequency: %dkHz\n", model->model_name, model->max_freq); @@ -264,10 +266,14 @@ static int centrino_cpu_init_table(struct cpufreq_policy *policy) } #else -static inline int centrino_cpu_init_table(struct cpufreq_policy *policy) { return -ENODEV; } +static inline int centrino_cpu_init_table(struct cpufreq_policy *policy) +{ + return -ENODEV; +} #endif /* CONFIG_X86_SPEEDSTEP_CENTRINO_TABLE */ -static int centrino_verify_cpu_id(const struct cpuinfo_x86 *c, const struct cpu_id *x) +static int centrino_verify_cpu_id(const struct cpuinfo_x86 *c, + const struct cpu_id *x) { if ((c->x86 == x->x86) && (c->x86_model == x->x86_model) && @@ -286,23 +292,28 @@ static unsigned extract_clock(unsigned msr, unsigned int cpu, int failsafe) * for centrino, as some DSDTs are buggy. * Ideally, this can be done using the acpi_data structure. */ - if ((centrino_cpu[cpu] == &cpu_ids[CPU_BANIAS]) || - (centrino_cpu[cpu] == &cpu_ids[CPU_DOTHAN_A1]) || - (centrino_cpu[cpu] == &cpu_ids[CPU_DOTHAN_B0])) { + if ((per_cpu(centrino_cpu, cpu) == &cpu_ids[CPU_BANIAS]) || + (per_cpu(centrino_cpu, cpu) == &cpu_ids[CPU_DOTHAN_A1]) || + (per_cpu(centrino_cpu, cpu) == &cpu_ids[CPU_DOTHAN_B0])) { msr = (msr >> 8) & 0xff; return msr * 100000; } - if ((!centrino_model[cpu]) || (!centrino_model[cpu]->op_points)) + if ((!per_cpu(centrino_model, cpu)) || + (!per_cpu(centrino_model, cpu)->op_points)) return 0; msr &= 0xffff; - for (i=0;centrino_model[cpu]->op_points[i].frequency != CPUFREQ_TABLE_END; i++) { - if (msr == centrino_model[cpu]->op_points[i].index) - return centrino_model[cpu]->op_points[i].frequency; + for (i = 0; + per_cpu(centrino_model, cpu)->op_points[i].frequency + != CPUFREQ_TABLE_END; + i++) { + if (msr == per_cpu(centrino_model, cpu)->op_points[i].index) + return per_cpu(centrino_model, cpu)-> + op_points[i].frequency; } if (failsafe) - return centrino_model[cpu]->op_points[i-1].frequency; + return per_cpu(centrino_model, cpu)->op_points[i-1].frequency; else return 0; } @@ -347,7 +358,8 @@ static int centrino_cpu_init(struct cpufreq_policy *policy) int i; /* Only Intel makes Enhanced Speedstep-capable CPUs */ - if (cpu->x86_vendor != X86_VENDOR_INTEL || !cpu_has(cpu, X86_FEATURE_EST)) + if (cpu->x86_vendor != X86_VENDOR_INTEL || + !cpu_has(cpu, X86_FEATURE_EST)) return -ENODEV; if (cpu_has(cpu, X86_FEATURE_CONSTANT_TSC)) @@ -361,9 +373,9 @@ static int centrino_cpu_init(struct cpufreq_policy *policy) break; if (i != N_IDS) - centrino_cpu[policy->cpu] = &cpu_ids[i]; + per_cpu(centrino_cpu, policy->cpu) = &cpu_ids[i]; - if (!centrino_cpu[policy->cpu]) { + if (!per_cpu(centrino_cpu, policy->cpu)) { dprintk("found unsupported CPU with " "Enhanced SpeedStep: send /proc/cpuinfo to " MAINTAINER "\n"); @@ -386,23 +398,26 @@ static int centrino_cpu_init(struct cpufreq_policy *policy) /* check to see if it stuck */ rdmsr(MSR_IA32_MISC_ENABLE, l, h); if (!(l & (1<<16))) { - printk(KERN_INFO PFX "couldn't enable Enhanced SpeedStep\n"); + printk(KERN_INFO PFX + "couldn't enable Enhanced SpeedStep\n"); return -ENODEV; } } freq = get_cur_freq(policy->cpu); - - policy->cpuinfo.transition_latency = 10000; /* 10uS transition latency */ + policy->cpuinfo.transition_latency = 10000; + /* 10uS transition latency */ policy->cur = freq; dprintk("centrino_cpu_init: cur=%dkHz\n", policy->cur); - ret = cpufreq_frequency_table_cpuinfo(policy, centrino_model[policy->cpu]->op_points); + ret = cpufreq_frequency_table_cpuinfo(policy, + per_cpu(centrino_model, policy->cpu)->op_points); if (ret) return (ret); - cpufreq_frequency_table_get_attr(centrino_model[policy->cpu]->op_points, policy->cpu); + cpufreq_frequency_table_get_attr( + per_cpu(centrino_model, policy->cpu)->op_points, policy->cpu); return 0; } @@ -411,12 +426,12 @@ static int centrino_cpu_exit(struct cpufreq_policy *policy) { unsigned int cpu = policy->cpu; - if (!centrino_model[cpu]) + if (!per_cpu(centrino_model, cpu)) return -ENODEV; cpufreq_frequency_table_put_attr(cpu); - centrino_model[cpu] = NULL; + per_cpu(centrino_model, cpu) = NULL; return 0; } @@ -430,17 +445,26 @@ static int centrino_cpu_exit(struct cpufreq_policy *policy) */ static int centrino_verify (struct cpufreq_policy *policy) { - return cpufreq_frequency_table_verify(policy, centrino_model[policy->cpu]->op_points); + return cpufreq_frequency_table_verify(policy, + per_cpu(centrino_model, policy->cpu)->op_points); } /** * centrino_setpolicy - set a new CPUFreq policy * @policy: new policy * @target_freq: the target frequency - * @relation: how that frequency relates to achieved frequency (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) + * @relation: how that frequency relates to achieved frequency + * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) * * Sets a new CPUFreq policy. */ +struct allmasks { + cpumask_t online_policy_cpus; + cpumask_t saved_mask; + cpumask_t set_mask; + cpumask_t covered_cpus; +}; + static int centrino_target (struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) @@ -448,48 +472,55 @@ static int centrino_target (struct cpufreq_policy *policy, unsigned int newstate = 0; unsigned int msr, oldmsr = 0, h = 0, cpu = policy->cpu; struct cpufreq_freqs freqs; - cpumask_t online_policy_cpus; - cpumask_t saved_mask; - cpumask_t set_mask; - cpumask_t covered_cpus; int retval = 0; unsigned int j, k, first_cpu, tmp; - - if (unlikely(centrino_model[cpu] == NULL)) - return -ENODEV; + CPUMASK_ALLOC(allmasks); + CPUMASK_PTR(online_policy_cpus, allmasks); + CPUMASK_PTR(saved_mask, allmasks); + CPUMASK_PTR(set_mask, allmasks); + CPUMASK_PTR(covered_cpus, allmasks); + + if (unlikely(allmasks == NULL)) + return -ENOMEM; + + if (unlikely(per_cpu(centrino_model, cpu) == NULL)) { + retval = -ENODEV; + goto out; + } if (unlikely(cpufreq_frequency_table_target(policy, - centrino_model[cpu]->op_points, + per_cpu(centrino_model, cpu)->op_points, target_freq, relation, &newstate))) { - return -EINVAL; + retval = -EINVAL; + goto out; } #ifdef CONFIG_HOTPLUG_CPU /* cpufreq holds the hotplug lock, so we are safe from here on */ - cpus_and(online_policy_cpus, cpu_online_map, policy->cpus); + cpus_and(*online_policy_cpus, cpu_online_map, policy->cpus); #else - online_policy_cpus = policy->cpus; + *online_policy_cpus = policy->cpus; #endif - saved_mask = current->cpus_allowed; + *saved_mask = current->cpus_allowed; first_cpu = 1; - cpus_clear(covered_cpus); - for_each_cpu_mask(j, online_policy_cpus) { + cpus_clear(*covered_cpus); + for_each_cpu_mask_nr(j, *online_policy_cpus) { /* * Support for SMP systems. * Make sure we are running on CPU that wants to change freq */ - cpus_clear(set_mask); + cpus_clear(*set_mask); if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) - cpus_or(set_mask, set_mask, online_policy_cpus); + cpus_or(*set_mask, *set_mask, *online_policy_cpus); else - cpu_set(j, set_mask); + cpu_set(j, *set_mask); - set_cpus_allowed_ptr(current, &set_mask); + set_cpus_allowed_ptr(current, set_mask); preempt_disable(); - if (unlikely(!cpu_isset(smp_processor_id(), set_mask))) { + if (unlikely(!cpu_isset(smp_processor_id(), *set_mask))) { dprintk("couldn't limit to CPUs in this domain\n"); retval = -EAGAIN; if (first_cpu) { @@ -500,7 +531,7 @@ static int centrino_target (struct cpufreq_policy *policy, break; } - msr = centrino_model[cpu]->op_points[newstate].index; + msr = per_cpu(centrino_model, cpu)->op_points[newstate].index; if (first_cpu) { rdmsr(MSR_IA32_PERF_CTL, oldmsr, h); @@ -517,7 +548,7 @@ static int centrino_target (struct cpufreq_policy *policy, dprintk("target=%dkHz old=%d new=%d msr=%04x\n", target_freq, freqs.old, freqs.new, msr); - for_each_cpu_mask(k, online_policy_cpus) { + for_each_cpu_mask_nr(k, *online_policy_cpus) { freqs.cpu = k; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); @@ -536,11 +567,11 @@ static int centrino_target (struct cpufreq_policy *policy, break; } - cpu_set(j, covered_cpus); + cpu_set(j, *covered_cpus); preempt_enable(); } - for_each_cpu_mask(k, online_policy_cpus) { + for_each_cpu_mask_nr(k, *online_policy_cpus) { freqs.cpu = k; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } @@ -553,30 +584,32 @@ static int centrino_target (struct cpufreq_policy *policy, * Best effort undo.. */ - if (!cpus_empty(covered_cpus)) { - for_each_cpu_mask(j, covered_cpus) { + if (!cpus_empty(*covered_cpus)) + for_each_cpu_mask_nr(j, *covered_cpus) { set_cpus_allowed_ptr(current, &cpumask_of_cpu(j)); wrmsr(MSR_IA32_PERF_CTL, oldmsr, h); } - } tmp = freqs.new; freqs.new = freqs.old; freqs.old = tmp; - for_each_cpu_mask(j, online_policy_cpus) { + for_each_cpu_mask_nr(j, *online_policy_cpus) { freqs.cpu = j; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } } - set_cpus_allowed_ptr(current, &saved_mask); - return 0; + set_cpus_allowed_ptr(current, saved_mask); + retval = 0; + goto out; migrate_end: preempt_enable(); - set_cpus_allowed_ptr(current, &saved_mask); - return 0; + set_cpus_allowed_ptr(current, saved_mask); +out: + CPUMASK_FREE(allmasks); + return retval; } static struct freq_attr* centrino_attr[] = { diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c index 1b50244..191f726 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c @@ -279,7 +279,7 @@ static int speedstep_target (struct cpufreq_policy *policy, cpus_allowed = current->cpus_allowed; - for_each_cpu_mask(i, policy->cpus) { + for_each_cpu_mask_nr(i, policy->cpus) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } @@ -292,7 +292,7 @@ static int speedstep_target (struct cpufreq_policy *policy, /* allow to be run on all CPUs */ set_cpus_allowed_ptr(current, &cpus_allowed); - for_each_cpu_mask(i, policy->cpus) { + for_each_cpu_mask_nr(i, policy->cpus) { freqs.cpu = i; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index ff517f0b..6b0a10b 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -489,7 +489,7 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index) int sibling; this_leaf = CPUID4_INFO_IDX(cpu, index); - for_each_cpu_mask(sibling, this_leaf->shared_cpu_map) { + for_each_cpu_mask_nr(sibling, this_leaf->shared_cpu_map) { sibling_leaf = CPUID4_INFO_IDX(sibling, index); cpu_clear(cpu, sibling_leaf->shared_cpu_map); } diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index 9ab65be..65a3396 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -580,7 +580,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, char __user *buf = ubuf; int i, err; - cpu_tsc = kmalloc(NR_CPUS * sizeof(long), GFP_KERNEL); + cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL); if (!cpu_tsc) return -ENOMEM; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c index 7c9a813..88736ca 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c @@ -527,7 +527,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (err) goto out_free; - for_each_cpu_mask(i, b->cpus) { + for_each_cpu_mask_nr(i, b->cpus) { if (i == cpu) continue; @@ -617,7 +617,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) #endif /* remove all sibling symlinks before unregistering */ - for_each_cpu_mask(i, b->cpus) { + for_each_cpu_mask_nr(i, b->cpus) { if (i == cpu) continue; diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 0d0d905..a26c480 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -160,7 +160,7 @@ static void *c_start(struct seq_file *m, loff_t *pos) { if (*pos == 0) /* just in case, cpu 0 is not the first */ *pos = first_cpu(cpu_online_map); - if ((*pos) < NR_CPUS && cpu_online(*pos)) + if ((*pos) < nr_cpu_ids && cpu_online(*pos)) return &cpu_data(*pos); return NULL; } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index cdfd94c..109792b 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -54,6 +54,16 @@ #include <asm/ftrace.h> #include <asm/irq_vectors.h> +/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ +#include <linux/elf-em.h> +#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) +#define __AUDIT_ARCH_LE 0x40000000 + +#ifndef CONFIG_AUDITSYSCALL +#define sysenter_audit syscall_trace_entry +#define sysexit_audit syscall_exit_work +#endif + /* * We use macros for low-level operations which need to be overridden * for paravirtualization. The following will never clobber any registers: @@ -333,7 +343,8 @@ sysenter_past_esp: /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ testw $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) - jnz syscall_trace_entry + jnz sysenter_audit +sysenter_do_call: cmpl $(nr_syscalls), %eax jae syscall_badsys call *sys_call_table(,%eax,4) @@ -343,7 +354,8 @@ sysenter_past_esp: TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx testw $_TIF_ALLWORK_MASK, %cx - jne syscall_exit_work + jne sysexit_audit +sysenter_exit: /* if something modifies registers it must also disable sysexit */ movl PT_EIP(%esp), %edx movl PT_OLDESP(%esp), %ecx @@ -351,6 +363,45 @@ sysenter_past_esp: TRACE_IRQS_ON 1: mov PT_FS(%esp), %fs ENABLE_INTERRUPTS_SYSEXIT + +#ifdef CONFIG_AUDITSYSCALL +sysenter_audit: + testw $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) + jnz syscall_trace_entry + addl $4,%esp + CFI_ADJUST_CFA_OFFSET -4 + /* %esi already in 8(%esp) 6th arg: 4th syscall arg */ + /* %edx already in 4(%esp) 5th arg: 3rd syscall arg */ + /* %ecx already in 0(%esp) 4th arg: 2nd syscall arg */ + movl %ebx,%ecx /* 3rd arg: 1st syscall arg */ + movl %eax,%edx /* 2nd arg: syscall number */ + movl $AUDIT_ARCH_I386,%eax /* 1st arg: audit arch */ + call audit_syscall_entry + pushl %ebx + CFI_ADJUST_CFA_OFFSET 4 + movl PT_EAX(%esp),%eax /* reload syscall number */ + jmp sysenter_do_call + +sysexit_audit: + testw $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %cx + jne syscall_exit_work + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_ANY) + movl %eax,%edx /* second arg, syscall return value */ + cmpl $0,%eax /* is it < 0? */ + setl %al /* 1 if so, 0 if not */ + movzbl %al,%eax /* zero-extend that */ + inc %eax /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ + call audit_syscall_exit + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + testw $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %cx + jne syscall_exit_work + movl PT_EAX(%esp),%eax /* reload syscall return value */ + jmp sysenter_exit +#endif + CFI_ENDPROC .pushsection .fixup,"ax" 2: movl $0,PT_FS(%esp) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 8410e26..89434d4 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -53,6 +53,12 @@ #include <asm/paravirt.h> #include <asm/ftrace.h> +/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ +#include <linux/elf-em.h> +#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) +#define __AUDIT_ARCH_64BIT 0x80000000 +#define __AUDIT_ARCH_LE 0x40000000 + .code64 #ifdef CONFIG_FTRACE @@ -351,6 +357,7 @@ ENTRY(system_call_after_swapgs) GET_THREAD_INFO(%rcx) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%rcx) jnz tracesys +system_call_fastpath: cmpq $__NR_syscall_max,%rax ja badsys movq %r10,%rcx @@ -402,16 +409,16 @@ sysret_careful: sysret_signal: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) - testl $_TIF_DO_NOTIFY_MASK,%edx - jz 1f - - /* Really a signal */ +#ifdef CONFIG_AUDITSYSCALL + bt $TIF_SYSCALL_AUDIT,%edx + jc sysret_audit +#endif /* edx: work flags (arg3) */ leaq do_notify_resume(%rip),%rax leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1 xorl %esi,%esi # oldset -> arg2 call ptregscall_common -1: movl $_TIF_WORK_MASK,%edi + movl $_TIF_WORK_MASK,%edi /* Use IRET because user could have changed frame. This works because ptregscall_common has called FIXUP_TOP_OF_STACK. */ DISABLE_INTERRUPTS(CLBR_NONE) @@ -422,8 +429,45 @@ badsys: movq $-ENOSYS,RAX-ARGOFFSET(%rsp) jmp ret_from_sys_call +#ifdef CONFIG_AUDITSYSCALL + /* + * Fast path for syscall audit without full syscall trace. + * We just call audit_syscall_entry() directly, and then + * jump back to the normal fast path. + */ +auditsys: + movq %r10,%r9 /* 6th arg: 4th syscall arg */ + movq %rdx,%r8 /* 5th arg: 3rd syscall arg */ + movq %rsi,%rcx /* 4th arg: 2nd syscall arg */ + movq %rdi,%rdx /* 3rd arg: 1st syscall arg */ + movq %rax,%rsi /* 2nd arg: syscall number */ + movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */ + call audit_syscall_entry + LOAD_ARGS 0 /* reload call-clobbered registers */ + jmp system_call_fastpath + + /* + * Return fast path for syscall audit. Call audit_syscall_exit() + * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT + * masked off. + */ +sysret_audit: + movq %rax,%rsi /* second arg, syscall return value */ + cmpq $0,%rax /* is it < 0? */ + setl %al /* 1 if so, 0 if not */ + movzbl %al,%edi /* zero-extend that into %edi */ + inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ + call audit_syscall_exit + movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi + jmp sysret_check +#endif /* CONFIG_AUDITSYSCALL */ + /* Do syscall tracing */ tracesys: +#ifdef CONFIG_AUDITSYSCALL + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%rcx) + jz auditsys +#endif SAVE_REST movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ FIXUP_TOP_OF_STACK %rdi @@ -448,6 +492,7 @@ tracesys: * Has correct top of stack, but partial stack frame. */ .globl int_ret_from_sys_call + .globl int_with_check int_ret_from_sys_call: DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c index 1fa8be5..eaff0bb 100644 --- a/arch/x86/kernel/genapic_64.c +++ b/arch/x86/kernel/genapic_64.c @@ -99,3 +99,4 @@ int is_uv_system(void) { return uv_system_type != UV_NONE; } +EXPORT_SYMBOL_GPL(is_uv_system); diff --git a/arch/x86/kernel/genapic_flat_64.c b/arch/x86/kernel/genapic_flat_64.c index 1a9c688..786548a 100644 --- a/arch/x86/kernel/genapic_flat_64.c +++ b/arch/x86/kernel/genapic_flat_64.c @@ -168,7 +168,7 @@ static unsigned int physflat_cpu_mask_to_apicid(cpumask_t cpumask) * May as well be the first. */ cpu = first_cpu(cpumask); - if ((unsigned)cpu < NR_CPUS) + if ((unsigned)cpu < nr_cpu_ids) return per_cpu(x86_cpu_to_apicid, cpu); else return BAD_APICID; diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c index 3c39293..2cfcbde 100644 --- a/arch/x86/kernel/genx2apic_uv_x.c +++ b/arch/x86/kernel/genx2apic_uv_x.c @@ -98,7 +98,7 @@ static void uv_send_IPI_mask(cpumask_t mask, int vector) { unsigned int cpu; - for (cpu = 0; cpu < NR_CPUS; ++cpu) + for_each_possible_cpu(cpu) if (cpu_isset(cpu, mask)) uv_send_IPI_one(cpu, vector); } @@ -132,7 +132,7 @@ static unsigned int uv_cpu_mask_to_apicid(cpumask_t cpumask) * May as well be the first. */ cpu = first_cpu(cpumask); - if ((unsigned)cpu < NR_CPUS) + if ((unsigned)cpu < nr_cpu_ids) return per_cpu(x86_cpu_to_apicid, cpu); else return BAD_APICID; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index f67e934..a7010c3 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -456,9 +456,6 @@ is386: movl $2,%ecx # set MP 1: #endif /* CONFIG_SMP */ jmp *(initial_code) -.align 4 -ENTRY(initial_code) - .long i386_start_kernel /* * We depend on ET to be correct. This checks for 287/387. @@ -601,6 +598,11 @@ ignore_int: #endif iret +.section .cpuinit.data,"wa" +.align 4 +ENTRY(initial_code) + .long i386_start_kernel + .section .text /* * Real beginning of normal "text" segment diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 0ea6a19..ad2b15a 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -468,7 +468,7 @@ void hpet_disable(void) #define RTC_NUM_INTS 1 static unsigned long hpet_rtc_flags; -static unsigned long hpet_prev_update_sec; +static int hpet_prev_update_sec; static struct rtc_time hpet_alarm_time; static unsigned long hpet_pie_count; static unsigned long hpet_t1_cmp; @@ -575,6 +575,9 @@ int hpet_set_rtc_irq_bit(unsigned long bit_mask) hpet_rtc_flags |= bit_mask; + if ((bit_mask & RTC_UIE) && !(oldbits & RTC_UIE)) + hpet_prev_update_sec = -1; + if (!oldbits) hpet_rtc_timer_init(); @@ -652,7 +655,7 @@ static void hpet_rtc_timer_reinit(void) if (hpet_rtc_flags & RTC_PIE) hpet_pie_count += lost_ints; if (printk_ratelimit()) - printk(KERN_WARNING "rtc: lost %d interrupts\n", + printk(KERN_WARNING "hpet1: lost %d rtc interrupts\n", lost_ints); } } @@ -670,7 +673,8 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) if (hpet_rtc_flags & RTC_UIE && curr_time.tm_sec != hpet_prev_update_sec) { - rtc_int_flag = RTC_UF; + if (hpet_prev_update_sec >= 0) + rtc_int_flag = RTC_UF; hpet_prev_update_sec = curr_time.tm_sec; } diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c index de9aa0e..09cddb5 100644 --- a/arch/x86/kernel/io_apic_32.c +++ b/arch/x86/kernel/io_apic_32.c @@ -57,7 +57,7 @@ atomic_t irq_mis_count; static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; static DEFINE_SPINLOCK(ioapic_lock); -static DEFINE_SPINLOCK(vector_lock); +DEFINE_SPINLOCK(vector_lock); int timer_through_8259 __initdata; @@ -1209,10 +1209,6 @@ static int assign_irq_vector(int irq) return vector; } -void setup_vector_irq(int cpu) -{ -} - static struct irq_chip ioapic_chip; #define IOAPIC_AUTO -1 diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c index 64a46af..61a83b7 100644 --- a/arch/x86/kernel/io_apic_64.c +++ b/arch/x86/kernel/io_apic_64.c @@ -101,7 +101,7 @@ int timer_through_8259 __initdata; static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; static DEFINE_SPINLOCK(ioapic_lock); -DEFINE_SPINLOCK(vector_lock); +static DEFINE_SPINLOCK(vector_lock); /* * # of IRQ routing registers @@ -697,6 +697,19 @@ static int pin_2_irq(int idx, int apic, int pin) return irq; } +void lock_vector_lock(void) +{ + /* Used to the online set of cpus does not change + * during assign_irq_vector. + */ + spin_lock(&vector_lock); +} + +void unlock_vector_lock(void) +{ + spin_unlock(&vector_lock); +} + static int __assign_irq_vector(int irq, cpumask_t mask) { /* @@ -732,7 +745,7 @@ static int __assign_irq_vector(int irq, cpumask_t mask) return 0; } - for_each_cpu_mask(cpu, mask) { + for_each_cpu_mask_nr(cpu, mask) { cpumask_t domain, new_mask; int new_cpu; int vector, offset; @@ -753,7 +766,7 @@ next: continue; if (vector == IA32_SYSCALL_VECTOR) goto next; - for_each_cpu_mask(new_cpu, new_mask) + for_each_cpu_mask_nr(new_cpu, new_mask) if (per_cpu(vector_irq, new_cpu)[vector] != -1) goto next; /* Found one! */ @@ -763,7 +776,7 @@ next: cfg->move_in_progress = 1; cfg->old_domain = cfg->domain; } - for_each_cpu_mask(new_cpu, new_mask) + for_each_cpu_mask_nr(new_cpu, new_mask) per_cpu(vector_irq, new_cpu)[vector] = irq; cfg->vector = vector; cfg->domain = domain; @@ -795,14 +808,14 @@ static void __clear_irq_vector(int irq) vector = cfg->vector; cpus_and(mask, cfg->domain, cpu_online_map); - for_each_cpu_mask(cpu, mask) + for_each_cpu_mask_nr(cpu, mask) per_cpu(vector_irq, cpu)[vector] = -1; cfg->vector = 0; cpus_clear(cfg->domain); } -static void __setup_vector_irq(int cpu) +void __setup_vector_irq(int cpu) { /* Initialize vector_irq on a new cpu */ /* This function must be called with vector_lock held */ @@ -825,14 +838,6 @@ static void __setup_vector_irq(int cpu) } } -void setup_vector_irq(int cpu) -{ - spin_lock(&vector_lock); - __setup_vector_irq(smp_processor_id()); - spin_unlock(&vector_lock); -} - - static struct irq_chip ioapic_chip; static void ioapic_register_intr(int irq, unsigned long trigger) @@ -1373,12 +1378,10 @@ static unsigned int startup_ioapic_irq(unsigned int irq) static int ioapic_retrigger_irq(unsigned int irq) { struct irq_cfg *cfg = &irq_cfg[irq]; - cpumask_t mask; unsigned long flags; spin_lock_irqsave(&vector_lock, flags); - mask = cpumask_of_cpu(first_cpu(cfg->domain)); - send_IPI_mask(mask, cfg->vector); + send_IPI_mask(cpumask_of_cpu(first_cpu(cfg->domain)), cfg->vector); spin_unlock_irqrestore(&vector_lock, flags); return 1; diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c index 0373e88..1f26fd9 100644 --- a/arch/x86/kernel/irqinit_64.c +++ b/arch/x86/kernel/irqinit_64.c @@ -43,10 +43,11 @@ #define BUILD_IRQ(nr) \ asmlinkage void IRQ_NAME(nr); \ - asm("\n.p2align\n" \ + asm("\n.text\n.p2align\n" \ "IRQ" #nr "_interrupt:\n\t" \ "push $~(" #nr ") ; " \ - "jmp common_interrupt"); + "jmp common_interrupt\n" \ + ".previous"); #define BI(x,y) \ BUILD_IRQ(x##y) diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 43c019f..6c27679 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -431,7 +431,6 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) regs->ip = (unsigned long)p->ainsn.insn; } -/* Called with kretprobe_lock held */ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { @@ -682,8 +681,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; INIT_HLIST_HEAD(&empty_rp); - spin_lock_irqsave(&kretprobe_lock, flags); - head = kretprobe_inst_table_head(current); + kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; @@ -732,7 +730,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) kretprobe_assert(ri, orig_ret_address, trampoline_address); - spin_unlock_irqrestore(&kretprobe_lock, flags); + kretprobe_hash_unlock(current, &flags); hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index a844957..b68e21f 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -62,12 +62,10 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload) if (reload) { #ifdef CONFIG_SMP - cpumask_t mask; - preempt_disable(); load_LDT(pc); - mask = cpumask_of_cpu(smp_processor_id()); - if (!cpus_equal(current->mm->cpu_vm_mask, mask)) + if (!cpus_equal(current->mm->cpu_vm_mask, + cpumask_of_cpu(smp_processor_id()))) smp_call_function(flush_ldt, current->mm, 1); preempt_enable(); #else diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 8864230..9fe478d 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -22,6 +22,7 @@ #include <asm/cpufeature.h> #include <asm/desc.h> #include <asm/system.h> +#include <asm/cacheflush.h> #define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE))) static u32 kexec_pgd[1024] PAGE_ALIGNED; @@ -85,10 +86,12 @@ static void load_segments(void) * reboot code buffer to allow us to avoid allocations * later. * - * Currently nothing. + * Make control page executable. */ int machine_kexec_prepare(struct kimage *image) { + if (nx_enabled) + set_pages_x(image->control_code_page, 1); return 0; } @@ -98,27 +101,48 @@ int machine_kexec_prepare(struct kimage *image) */ void machine_kexec_cleanup(struct kimage *image) { + if (nx_enabled) + set_pages_nx(image->control_code_page, 1); } /* * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. */ -NORET_TYPE void machine_kexec(struct kimage *image) +void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; void *control_page; + asmlinkage unsigned long + (*relocate_kernel_ptr)(unsigned long indirection_page, + unsigned long control_page, + unsigned long start_address, + unsigned int has_pae, + unsigned int preserve_context); tracer_disable(); /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); + if (image->preserve_context) { +#ifdef CONFIG_X86_IO_APIC + /* We need to put APICs in legacy mode so that we can + * get timer interrupts in second kernel. kexec/kdump + * paths already have calls to disable_IO_APIC() in + * one form or other. kexec jump path also need + * one. + */ + disable_IO_APIC(); +#endif + } + control_page = page_address(image->control_code_page); - memcpy(control_page, relocate_kernel, PAGE_SIZE); + memcpy(control_page, relocate_kernel, PAGE_SIZE/2); + relocate_kernel_ptr = control_page; page_list[PA_CONTROL_PAGE] = __pa(control_page); - page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel; + page_list[VA_CONTROL_PAGE] = (unsigned long)control_page; page_list[PA_PGD] = __pa(kexec_pgd); page_list[VA_PGD] = (unsigned long)kexec_pgd; #ifdef CONFIG_X86_PAE @@ -131,6 +155,7 @@ NORET_TYPE void machine_kexec(struct kimage *image) page_list[VA_PTE_0] = (unsigned long)kexec_pte0; page_list[PA_PTE_1] = __pa(kexec_pte1); page_list[VA_PTE_1] = (unsigned long)kexec_pte1; + page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT); /* The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is @@ -149,8 +174,10 @@ NORET_TYPE void machine_kexec(struct kimage *image) set_idt(phys_to_virt(0),0); /* now call it */ - relocate_kernel((unsigned long)image->head, (unsigned long)page_list, - image->start, cpu_has_pae); + image->start = relocate_kernel_ptr((unsigned long)image->head, + (unsigned long)page_list, + image->start, cpu_has_pae, + image->preserve_context); } void arch_crash_save_vmcoreinfo(void) diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 9dd9262..c43caa3 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -181,7 +181,7 @@ void machine_kexec_cleanup(struct kimage *image) * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. */ -NORET_TYPE void machine_kexec(struct kimage *image) +void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; void *control_page; diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c index fc47906..652fa5c 100644 --- a/arch/x86/kernel/microcode.c +++ b/arch/x86/kernel/microcode.c @@ -657,9 +657,7 @@ static ssize_t reload_store(struct sys_device *dev, if (end == buf) return -EINVAL; if (val == 1) { - cpumask_t old; - - old = current->cpus_allowed; + cpumask_t old = current->cpus_allowed; get_online_cpus(); set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); diff --git a/arch/x86/kernel/module_64.c b/arch/x86/kernel/module_64.c index 0e86767..6ba8783 100644 --- a/arch/x86/kernel/module_64.c +++ b/arch/x86/kernel/module_64.c @@ -22,6 +22,7 @@ #include <linux/fs.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/mm.h> #include <linux/slab.h> #include <linux/bug.h> diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 6ae005c..6780905 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -83,7 +83,7 @@ static void __init MP_bus_info(struct mpc_config_bus *m) if (x86_quirks->mpc_oem_bus_info) x86_quirks->mpc_oem_bus_info(m, str); else - printk(KERN_INFO "Bus #%d is %s\n", m->mpc_busid, str); + apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->mpc_busid, str); #if MAX_MP_BUSSES < 256 if (m->mpc_busid >= MAX_MP_BUSSES) { @@ -154,7 +154,7 @@ static void __init MP_ioapic_info(struct mpc_config_ioapic *m) static void print_MP_intsrc_info(struct mpc_config_intsrc *m) { - printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x," + apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x," " IRQ %02x, APIC ID %x, APIC INT %02x\n", m->mpc_irqtype, m->mpc_irqflag & 3, (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus, @@ -163,7 +163,7 @@ static void print_MP_intsrc_info(struct mpc_config_intsrc *m) static void __init print_mp_irq_info(struct mp_config_intsrc *mp_irq) { - printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x," + apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x," " IRQ %02x, APIC ID %x, APIC INT %02x\n", mp_irq->mp_irqtype, mp_irq->mp_irqflag & 3, (mp_irq->mp_irqflag >> 2) & 3, mp_irq->mp_srcbus, @@ -235,7 +235,7 @@ static void __init MP_intsrc_info(struct mpc_config_intsrc *m) static void __init MP_lintsrc_info(struct mpc_config_lintsrc *m) { - printk(KERN_INFO "Lint: type %d, pol %d, trig %d, bus %02x," + apic_printk(APIC_VERBOSE, "Lint: type %d, pol %d, trig %d, bus %02x," " IRQ %02x, APIC ID %x, APIC LINT %02x\n", m->mpc_irqtype, m->mpc_irqflag & 3, (m->mpc_irqflag >> 2) & 3, m->mpc_srcbusid, @@ -695,7 +695,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, unsigned int *bp = phys_to_virt(base); struct intel_mp_floating *mpf; - printk(KERN_DEBUG "Scan SMP from %p for %ld bytes.\n", bp, length); + apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n", + bp, length); BUILD_BUG_ON(sizeof(*mpf) != 16); while (length > 0) { diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 151f2d1..02d1932 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -29,6 +29,7 @@ #include <linux/mm.h> #include <linux/spinlock.h> #include <linux/string.h> +#include <linux/crash_dump.h> #include <linux/dma-mapping.h> #include <linux/bitops.h> #include <linux/pci_ids.h> @@ -36,6 +37,7 @@ #include <linux/delay.h> #include <linux/scatterlist.h> #include <linux/iommu-helper.h> + #include <asm/iommu.h> #include <asm/calgary.h> #include <asm/tce.h> @@ -167,6 +169,8 @@ static void calgary_dump_error_regs(struct iommu_table *tbl); static void calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev); static void calioc2_tce_cache_blast(struct iommu_table *tbl); static void calioc2_dump_error_regs(struct iommu_table *tbl); +static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl); +static void get_tce_space_from_tar(void); static struct cal_chipset_ops calgary_chip_ops = { .handle_quirks = calgary_handle_quirks, @@ -410,22 +414,6 @@ static void calgary_unmap_sg(struct device *dev, } } -static int calgary_nontranslate_map_sg(struct device* dev, - struct scatterlist *sg, int nelems, int direction) -{ - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nelems, i) { - struct page *p = sg_page(s); - - BUG_ON(!p); - s->dma_address = virt_to_bus(sg_virt(s)); - s->dma_length = s->length; - } - return nelems; -} - static int calgary_map_sg(struct device *dev, struct scatterlist *sg, int nelems, int direction) { @@ -436,9 +424,6 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, unsigned long entry; int i; - if (!translation_enabled(tbl)) - return calgary_nontranslate_map_sg(dev, sg, nelems, direction); - for_each_sg(sg, s, nelems, i) { BUG_ON(!sg_page(s)); @@ -474,7 +459,6 @@ error: static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr, size_t size, int direction) { - dma_addr_t dma_handle = bad_dma_address; void *vaddr = phys_to_virt(paddr); unsigned long uaddr; unsigned int npages; @@ -483,12 +467,7 @@ static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr, uaddr = (unsigned long)vaddr; npages = num_dma_pages(uaddr, size); - if (translation_enabled(tbl)) - dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction); - else - dma_handle = virt_to_bus(vaddr); - - return dma_handle; + return iommu_alloc(dev, tbl, vaddr, npages, direction); } static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle, @@ -497,9 +476,6 @@ static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle, struct iommu_table *tbl = find_iommu_table(dev); unsigned int npages; - if (!translation_enabled(tbl)) - return; - npages = num_dma_pages(dma_handle, size); iommu_free(tbl, dma_handle, npages); } @@ -522,18 +498,12 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size, goto error; memset(ret, 0, size); - if (translation_enabled(tbl)) { - /* set up tces to cover the allocated range */ - mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL); - if (mapping == bad_dma_address) - goto free; - - *dma_handle = mapping; - } else /* non translated slot */ - *dma_handle = virt_to_bus(ret); - + /* set up tces to cover the allocated range */ + mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL); + if (mapping == bad_dma_address) + goto free; + *dma_handle = mapping; return ret; - free: free_pages((unsigned long)ret, get_order(size)); ret = NULL; @@ -541,7 +511,7 @@ error: return ret; } -static const struct dma_mapping_ops calgary_dma_ops = { +static struct dma_mapping_ops calgary_dma_ops = { .alloc_coherent = calgary_alloc_coherent, .map_single = calgary_map_single, .unmap_single = calgary_unmap_single, @@ -830,7 +800,11 @@ static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar) tbl = pci_iommu(dev->bus); tbl->it_base = (unsigned long)bus_info[dev->bus->number].tce_space; - tce_free(tbl, 0, tbl->it_size); + + if (is_kdump_kernel()) + calgary_init_bitmap_from_tce_table(tbl); + else + tce_free(tbl, 0, tbl->it_size); if (is_calgary(dev->device)) tbl->chip_ops = &calgary_chip_ops; @@ -1209,6 +1183,10 @@ static int __init calgary_init(void) if (ret) return ret; + /* Purely for kdump kernel case */ + if (is_kdump_kernel()) + get_tce_space_from_tar(); + do { dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev); if (!dev) @@ -1230,6 +1208,16 @@ static int __init calgary_init(void) goto error; } while (1); + dev = NULL; + for_each_pci_dev(dev) { + struct iommu_table *tbl; + + tbl = find_iommu_table(&dev->dev); + + if (translation_enabled(tbl)) + dev->dev.archdata.dma_ops = &calgary_dma_ops; + } + return ret; error: @@ -1251,6 +1239,7 @@ error: calgary_disable_translation(dev); calgary_free_bus(dev); pci_dev_put(dev); /* Undo calgary_init_one()'s pci_dev_get() */ + dev->dev.archdata.dma_ops = NULL; } while (1); return ret; @@ -1339,6 +1328,61 @@ static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev) return (val != 0xffffffff); } +/* + * calgary_init_bitmap_from_tce_table(): + * Funtion for kdump case. In the second/kdump kernel initialize + * the bitmap based on the tce table entries obtained from first kernel + */ +static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl) +{ + u64 *tp; + unsigned int index; + tp = ((u64 *)tbl->it_base); + for (index = 0 ; index < tbl->it_size; index++) { + if (*tp != 0x0) + set_bit(index, tbl->it_map); + tp++; + } +} + +/* + * 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 + */ +static void get_tce_space_from_tar(void) +{ + int bus; + void __iomem *target; + unsigned long tce_space; + + for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) { + struct calgary_bus_info *info = &bus_info[bus]; + unsigned short pci_device; + u32 val; + + val = read_pci_config(bus, 0, 0, 0); + pci_device = (val & 0xFFFF0000) >> 16; + + if (!is_cal_pci_dev(pci_device)) + continue; + if (info->translation_disabled) + continue; + + if (calgary_bus_has_devices(bus, pci_device) || + translate_empty_slots) { + target = calgary_reg(bus_info[bus].bbar, + tar_offset(bus)); + tce_space = be64_to_cpu(readq(target)); + tce_space = tce_space & TAR_SW_BITS; + + tce_space = tce_space & (~specified_table_size); + info->tce_space = (u64 *)__va(tce_space); + } + } + return; +} + void __init detect_calgary(void) { int bus; @@ -1394,7 +1438,8 @@ void __init detect_calgary(void) return; } - specified_table_size = determine_tce_table_size(max_pfn * PAGE_SIZE); + specified_table_size = determine_tce_table_size((is_kdump_kernel() ? + saved_max_pfn : max_pfn) * PAGE_SIZE); for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) { struct calgary_bus_info *info = &bus_info[bus]; @@ -1412,10 +1457,16 @@ void __init detect_calgary(void) if (calgary_bus_has_devices(bus, pci_device) || translate_empty_slots) { - tbl = alloc_tce_table(); - if (!tbl) - goto cleanup; - info->tce_space = tbl; + /* + * If it is kdump kernel, find and use tce tables + * from first kernel, else allocate tce tables here + */ + if (!is_kdump_kernel()) { + tbl = alloc_tce_table(); + if (!tbl) + goto cleanup; + info->tce_space = tbl; + } calgary_found = 1; } } @@ -1430,6 +1481,10 @@ void __init detect_calgary(void) printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d, " "CONFIG_IOMMU_DEBUG is %s.\n", specified_table_size, debugging ? "enabled" : "disabled"); + + /* swiotlb for devices that aren't behind the Calgary. */ + if (max_pfn > MAX_DMA32_PFN) + swiotlb = 1; } return; @@ -1446,7 +1501,7 @@ int __init calgary_iommu_init(void) { int ret; - if (no_iommu || swiotlb) + if (no_iommu || (swiotlb && !calgary_detected)) return -ENODEV; if (!calgary_detected) @@ -1459,15 +1514,14 @@ int __init calgary_iommu_init(void) if (ret) { printk(KERN_ERR "PCI-DMA: Calgary init failed %d, " "falling back to no_iommu\n", ret); - if (max_pfn > MAX_DMA32_PFN) - printk(KERN_ERR "WARNING more than 4GB of memory, " - "32bit PCI may malfunction.\n"); return ret; } force_iommu = 1; bad_dma_address = 0x0; - dma_ops = &calgary_dma_ops; + /* dma_ops is set to swiotlb or nommu */ + if (!dma_ops) + dma_ops = &nommu_dma_ops; return 0; } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index cbecb05..87d4d69 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -11,7 +11,7 @@ static int forbid_dac __read_mostly; -const struct dma_mapping_ops *dma_ops; +struct dma_mapping_ops *dma_ops; EXPORT_SYMBOL(dma_ops); static int iommu_sac_force __read_mostly; @@ -123,6 +123,14 @@ void __init pci_iommu_alloc(void) pci_swiotlb_init(); } + +unsigned long iommu_num_pages(unsigned long addr, unsigned long len) +{ + unsigned long size = roundup((addr & ~PAGE_MASK) + len, PAGE_SIZE); + + return size >> PAGE_SHIFT; +} +EXPORT_SYMBOL(iommu_num_pages); #endif /* @@ -192,126 +200,10 @@ static __init int iommu_setup(char *p) } early_param("iommu", iommu_setup); -#ifdef CONFIG_X86_32 -int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, - dma_addr_t device_addr, size_t size, int flags) -{ - void __iomem *mem_base = NULL; - int pages = size >> PAGE_SHIFT; - int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long); - - if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0) - goto out; - if (!size) - goto out; - if (dev->dma_mem) - goto out; - - /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */ - - mem_base = ioremap(bus_addr, size); - if (!mem_base) - goto out; - - dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL); - if (!dev->dma_mem) - goto out; - dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL); - if (!dev->dma_mem->bitmap) - goto free1_out; - - dev->dma_mem->virt_base = mem_base; - dev->dma_mem->device_base = device_addr; - dev->dma_mem->size = pages; - dev->dma_mem->flags = flags; - - if (flags & DMA_MEMORY_MAP) - return DMA_MEMORY_MAP; - - return DMA_MEMORY_IO; - - free1_out: - kfree(dev->dma_mem); - out: - if (mem_base) - iounmap(mem_base); - return 0; -} -EXPORT_SYMBOL(dma_declare_coherent_memory); - -void dma_release_declared_memory(struct device *dev) -{ - struct dma_coherent_mem *mem = dev->dma_mem; - - if (!mem) - return; - dev->dma_mem = NULL; - iounmap(mem->virt_base); - kfree(mem->bitmap); - kfree(mem); -} -EXPORT_SYMBOL(dma_release_declared_memory); - -void *dma_mark_declared_memory_occupied(struct device *dev, - dma_addr_t device_addr, size_t size) -{ - struct dma_coherent_mem *mem = dev->dma_mem; - int pos, err; - int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1); - - pages >>= PAGE_SHIFT; - - if (!mem) - return ERR_PTR(-EINVAL); - - pos = (device_addr - mem->device_base) >> PAGE_SHIFT; - err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages)); - if (err != 0) - return ERR_PTR(err); - return mem->virt_base + (pos << PAGE_SHIFT); -} -EXPORT_SYMBOL(dma_mark_declared_memory_occupied); - -static int dma_alloc_from_coherent_mem(struct device *dev, ssize_t size, - dma_addr_t *dma_handle, void **ret) -{ - struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; - int order = get_order(size); - - if (mem) { - int page = bitmap_find_free_region(mem->bitmap, mem->size, - order); - if (page >= 0) { - *dma_handle = mem->device_base + (page << PAGE_SHIFT); - *ret = mem->virt_base + (page << PAGE_SHIFT); - memset(*ret, 0, size); - } - if (mem->flags & DMA_MEMORY_EXCLUSIVE) - *ret = NULL; - } - return (mem != NULL); -} - -static int dma_release_coherent(struct device *dev, int order, void *vaddr) -{ - struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; - - if (mem && vaddr >= mem->virt_base && vaddr < - (mem->virt_base + (mem->size << PAGE_SHIFT))) { - int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; - - bitmap_release_region(mem->bitmap, page, order); - return 1; - } - return 0; -} -#else -#define dma_alloc_from_coherent_mem(dev, size, handle, ret) (0) -#define dma_release_coherent(dev, order, vaddr) (0) -#endif /* CONFIG_X86_32 */ - int dma_supported(struct device *dev, u64 mask) { + struct dma_mapping_ops *ops = get_dma_ops(dev); + #ifdef CONFIG_PCI if (mask > 0xffffffff && forbid_dac > 0) { dev_info(dev, "PCI: Disallowing DAC for device\n"); @@ -319,8 +211,8 @@ int dma_supported(struct device *dev, u64 mask) } #endif - if (dma_ops->dma_supported) - return dma_ops->dma_supported(dev, mask); + if (ops->dma_supported) + return ops->dma_supported(dev, mask); /* Copied from i386. Doesn't make much sense, because it will only work for pci_alloc_coherent. @@ -367,6 +259,7 @@ void * dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { + struct dma_mapping_ops *ops = get_dma_ops(dev); void *memory = NULL; struct page *page; unsigned long dma_mask = 0; @@ -376,7 +269,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, /* ignore region specifiers */ gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); - if (dma_alloc_from_coherent_mem(dev, size, dma_handle, &memory)) + if (dma_alloc_from_coherent(dev, size, dma_handle, &memory)) return memory; if (!dev) { @@ -435,8 +328,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, /* Let low level make its own zone decisions */ gfp &= ~(GFP_DMA32|GFP_DMA); - if (dma_ops->alloc_coherent) - return dma_ops->alloc_coherent(dev, size, + if (ops->alloc_coherent) + return ops->alloc_coherent(dev, size, dma_handle, gfp); return NULL; } @@ -448,14 +341,14 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, } } - if (dma_ops->alloc_coherent) { + if (ops->alloc_coherent) { free_pages((unsigned long)memory, get_order(size)); gfp &= ~(GFP_DMA|GFP_DMA32); - return dma_ops->alloc_coherent(dev, size, dma_handle, gfp); + return ops->alloc_coherent(dev, size, dma_handle, gfp); } - if (dma_ops->map_simple) { - *dma_handle = dma_ops->map_simple(dev, virt_to_phys(memory), + if (ops->map_simple) { + *dma_handle = ops->map_simple(dev, virt_to_phys(memory), size, PCI_DMA_BIDIRECTIONAL); if (*dma_handle != bad_dma_address) @@ -477,12 +370,14 @@ EXPORT_SYMBOL(dma_alloc_coherent); void dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t bus) { + struct dma_mapping_ops *ops = get_dma_ops(dev); + int order = get_order(size); WARN_ON(irqs_disabled()); /* for portability */ - if (dma_release_coherent(dev, order, vaddr)) + if (dma_release_from_coherent(dev, order, vaddr)) return; - if (dma_ops->unmap_single) - dma_ops->unmap_single(dev, bus, size, 0); + if (ops->unmap_single) + ops->unmap_single(dev, bus, size, 0); free_pages((unsigned long)vaddr, order); } EXPORT_SYMBOL(dma_free_coherent); diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 1062dc1..cdab678 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -67,9 +67,6 @@ static u32 gart_unmapped_entry; (((x) & 0xfffff000) | (((x) >> 32) << 4) | GPTE_VALID | GPTE_COHERENT) #define GPTE_DECODE(x) (((x) & 0xfffff000) | (((u64)(x) & 0xff0) << 28)) -#define to_pages(addr, size) \ - (round_up(((addr) & ~PAGE_MASK) + (size), PAGE_SIZE) >> PAGE_SHIFT) - #define EMERGENCY_PAGES 32 /* = 128KB */ #ifdef CONFIG_AGP @@ -241,7 +238,7 @@ nonforced_iommu(struct device *dev, unsigned long addr, size_t size) static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem, size_t size, int dir) { - unsigned long npages = to_pages(phys_mem, size); + unsigned long npages = iommu_num_pages(phys_mem, size); unsigned long iommu_page = alloc_iommu(dev, npages); int i; @@ -304,7 +301,7 @@ static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr, return; iommu_page = (dma_addr - iommu_bus_base)>>PAGE_SHIFT; - npages = to_pages(dma_addr, size); + npages = iommu_num_pages(dma_addr, size); for (i = 0; i < npages; i++) { iommu_gatt_base[iommu_page + i] = gart_unmapped_entry; CLEAR_LEAK(iommu_page + i); @@ -387,7 +384,7 @@ static int __dma_map_cont(struct device *dev, struct scatterlist *start, } addr = phys_addr; - pages = to_pages(s->offset, s->length); + pages = iommu_num_pages(s->offset, s->length); while (pages--) { iommu_gatt_base[iommu_page] = GPTE_ENCODE(addr); SET_LEAK(iommu_page); @@ -470,7 +467,7 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) seg_size += s->length; need = nextneed; - pages += to_pages(s->offset, s->length); + pages += iommu_num_pages(s->offset, s->length); ps = s; } if (dma_map_cont(dev, start_sg, i - start, sgmap, pages, need) < 0) @@ -692,8 +689,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info) extern int agp_amd64_init(void); -static const struct dma_mapping_ops gart_dma_ops = { - .mapping_error = NULL, +static struct dma_mapping_ops gart_dma_ops = { .map_single = gart_map_single, .map_simple = gart_map_simple, .unmap_single = gart_unmap_single, diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 792b917..3f91f71 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -72,21 +72,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, return nents; } -/* Make sure we keep the same behaviour */ -static int nommu_mapping_error(dma_addr_t dma_addr) -{ -#ifdef CONFIG_X86_32 - return 0; -#else - return (dma_addr == bad_dma_address); -#endif -} - - -const struct dma_mapping_ops nommu_dma_ops = { +struct dma_mapping_ops nommu_dma_ops = { .map_single = nommu_map_single, .map_sg = nommu_map_sg, - .mapping_error = nommu_mapping_error, .is_phys = 1, }; diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index 20df839..c4ce033 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -18,7 +18,7 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction); } -const struct dma_mapping_ops swiotlb_dma_ops = { +struct dma_mapping_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc_coherent = swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 0c3927a..53bc653 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -128,7 +128,7 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(); + tick_nohz_stop_sched_tick(1); while (!need_resched()) { check_pgt_cache(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e8a8e1b..3fb62a7 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -120,7 +120,7 @@ void cpu_idle(void) current_thread_info()->status |= TS_POLLING; /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(); + tick_nohz_stop_sched_tick(1); while (!need_resched()) { rmb(); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 9dcf39c..724adfc 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -411,10 +411,9 @@ void native_machine_shutdown(void) { /* Stop the cpus and apics */ #ifdef CONFIG_SMP - int reboot_cpu_id; /* The boot cpu is always logical cpu 0 */ - reboot_cpu_id = 0; + int reboot_cpu_id = 0; #ifdef CONFIG_X86_32 /* See if there has been given a command line override */ diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index c30fe25..703310a 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -20,11 +20,44 @@ #define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) #define PAE_PGD_ATTR (_PAGE_PRESENT) +/* control_page + PAGE_SIZE/2 ~ control_page + PAGE_SIZE * 3/4 are + * used to save some data for jumping back + */ +#define DATA(offset) (PAGE_SIZE/2+(offset)) + +/* Minimal CPU state */ +#define ESP DATA(0x0) +#define CR0 DATA(0x4) +#define CR3 DATA(0x8) +#define CR4 DATA(0xc) + +/* other data */ +#define CP_VA_CONTROL_PAGE DATA(0x10) +#define CP_PA_PGD DATA(0x14) +#define CP_PA_SWAP_PAGE DATA(0x18) +#define CP_PA_BACKUP_PAGES_MAP DATA(0x1c) + .text .align PAGE_SIZE .globl relocate_kernel relocate_kernel: - movl 8(%esp), %ebp /* list of pages */ + /* Save the CPU context, used for jumping back */ + + pushl %ebx + pushl %esi + pushl %edi + pushl %ebp + pushf + + movl 20+8(%esp), %ebp /* list of pages */ + movl PTR(VA_CONTROL_PAGE)(%ebp), %edi + movl %esp, ESP(%edi) + movl %cr0, %eax + movl %eax, CR0(%edi) + movl %cr3, %eax + movl %eax, CR3(%edi) + movl %cr4, %eax + movl %eax, CR4(%edi) #ifdef CONFIG_X86_PAE /* map the control page at its virtual address */ @@ -138,15 +171,25 @@ relocate_kernel: relocate_new_kernel: /* read the arguments and say goodbye to the stack */ - movl 4(%esp), %ebx /* page_list */ - movl 8(%esp), %ebp /* list of pages */ - movl 12(%esp), %edx /* start address */ - movl 16(%esp), %ecx /* cpu_has_pae */ + movl 20+4(%esp), %ebx /* page_list */ + movl 20+8(%esp), %ebp /* list of pages */ + movl 20+12(%esp), %edx /* start address */ + movl 20+16(%esp), %ecx /* cpu_has_pae */ + movl 20+20(%esp), %esi /* preserve_context */ /* zero out flags, and disable interrupts */ pushl $0 popfl + /* save some information for jumping back */ + movl PTR(VA_CONTROL_PAGE)(%ebp), %edi + movl %edi, CP_VA_CONTROL_PAGE(%edi) + movl PTR(PA_PGD)(%ebp), %eax + movl %eax, CP_PA_PGD(%edi) + movl PTR(PA_SWAP_PAGE)(%ebp), %eax + movl %eax, CP_PA_SWAP_PAGE(%edi) + movl %ebx, CP_PA_BACKUP_PAGES_MAP(%edi) + /* get physical address of control page now */ /* this is impossible after page table switch */ movl PTR(PA_CONTROL_PAGE)(%ebp), %edi @@ -197,8 +240,90 @@ identity_mapped: xorl %eax, %eax movl %eax, %cr3 + movl CP_PA_SWAP_PAGE(%edi), %eax + pushl %eax + pushl %ebx + call swap_pages + addl $8, %esp + + /* To be certain of avoiding problems with self-modifying code + * I need to execute a serializing instruction here. + * So I flush the TLB, it's handy, and not processor dependent. + */ + xorl %eax, %eax + movl %eax, %cr3 + + /* set all of the registers to known values */ + /* leave %esp alone */ + + testl %esi, %esi + jnz 1f + xorl %edi, %edi + xorl %eax, %eax + xorl %ebx, %ebx + xorl %ecx, %ecx + xorl %edx, %edx + xorl %esi, %esi + xorl %ebp, %ebp + ret +1: + popl %edx + movl CP_PA_SWAP_PAGE(%edi), %esp + addl $PAGE_SIZE, %esp +2: + call *%edx + + /* get the re-entry point of the peer system */ + movl 0(%esp), %ebp + call 1f +1: + popl %ebx + subl $(1b - relocate_kernel), %ebx + movl CP_VA_CONTROL_PAGE(%ebx), %edi + lea PAGE_SIZE(%ebx), %esp + movl CP_PA_SWAP_PAGE(%ebx), %eax + movl CP_PA_BACKUP_PAGES_MAP(%ebx), %edx + pushl %eax + pushl %edx + call swap_pages + addl $8, %esp + movl CP_PA_PGD(%ebx), %eax + movl %eax, %cr3 + movl %cr0, %eax + orl $(1<<31), %eax + movl %eax, %cr0 + lea PAGE_SIZE(%edi), %esp + movl %edi, %eax + addl $(virtual_mapped - relocate_kernel), %eax + pushl %eax + ret + +virtual_mapped: + movl CR4(%edi), %eax + movl %eax, %cr4 + movl CR3(%edi), %eax + movl %eax, %cr3 + movl CR0(%edi), %eax + movl %eax, %cr0 + movl ESP(%edi), %esp + movl %ebp, %eax + + popf + popl %ebp + popl %edi + popl %esi + popl %ebx + ret + /* Do the copies */ - movl %ebx, %ecx +swap_pages: + movl 8(%esp), %edx + movl 4(%esp), %ecx + pushl %ebp + pushl %ebx + pushl %edi + pushl %esi + movl %ecx, %ebx jmp 1f 0: /* top, read another word from the indirection page */ @@ -226,27 +351,28 @@ identity_mapped: movl %ecx, %esi /* For every source page do a copy */ andl $0xfffff000, %esi + movl %edi, %eax + movl %esi, %ebp + + movl %edx, %edi movl $1024, %ecx rep ; movsl - jmp 0b -3: - - /* To be certain of avoiding problems with self-modifying code - * I need to execute a serializing instruction here. - * So I flush the TLB, it's handy, and not processor dependent. - */ - xorl %eax, %eax - movl %eax, %cr3 + movl %ebp, %edi + movl %eax, %esi + movl $1024, %ecx + rep ; movsl - /* set all of the registers to known values */ - /* leave %esp alone */ + movl %eax, %edi + movl %edx, %esi + movl $1024, %ecx + rep ; movsl - xorl %eax, %eax - xorl %ebx, %ebx - xorl %ecx, %ecx - xorl %edx, %edx - xorl %esi, %esi - xorl %edi, %edi - xorl %ebp, %ebp + lea PAGE_SIZE(%ebp), %esi + jmp 0b +3: + popl %esi + popl %edi + popl %ebx + popl %ebp ret diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b4aacb9..68b48e3 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -597,13 +597,21 @@ void __init setup_arch(char **cmdline_p) memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); visws_early_detect(); pre_setup_arch_hook(); - early_cpu_init(); #else printk(KERN_INFO "Command line: %s\n", boot_command_line); #endif + early_cpu_init(); early_ioremap_init(); +#if defined(CONFIG_VMI) && defined(CONFIG_X86_32) + /* + * Must be before kernel pagetables are setup + * or fixmap area is touched. + */ + vmi_init(); +#endif + ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); screen_info = boot_params.screen_info; edid_info = boot_params.edid_info; @@ -665,9 +673,6 @@ void __init setup_arch(char **cmdline_p) bss_resource.start = virt_to_phys(&__bss_start); bss_resource.end = virt_to_phys(&__bss_stop)-1; -#ifdef CONFIG_X86_64 - early_cpu_init(); -#endif strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; @@ -791,10 +796,6 @@ void __init setup_arch(char **cmdline_p) initmem_init(0, max_pfn); -#ifdef CONFIG_X86_64 - dma32_reserve_bootmem(); -#endif - #ifdef CONFIG_ACPI_SLEEP /* * Reserve low memory region for sleep support. @@ -809,20 +810,21 @@ void __init setup_arch(char **cmdline_p) #endif reserve_crashkernel(); +#ifdef CONFIG_X86_64 + /* + * dma32_reserve_bootmem() allocates bootmem which may conflict + * with the crashkernel command line, so do that after + * reserve_crashkernel() + */ + dma32_reserve_bootmem(); +#endif + reserve_ibft_region(); #ifdef CONFIG_KVM_CLOCK kvmclock_init(); #endif -#if defined(CONFIG_VMI) && defined(CONFIG_X86_32) - /* - * Must be after max_low_pfn is determined, and before kernel - * pagetables are setup. - */ - vmi_init(); -#endif - paravirt_pagetable_setup_start(swapper_pg_dir); paging_init(); paravirt_pagetable_setup_done(swapper_pg_dir); @@ -859,12 +861,6 @@ void __init setup_arch(char **cmdline_p) init_apic_mappings(); ioapic_init_mappings(); -#if defined(CONFIG_SMP) && defined(CONFIG_X86_PC) && defined(CONFIG_X86_32) - if (def_to_bigsmp) - printk(KERN_WARNING "More than 8 CPUs detected and " - "CONFIG_X86_PC cannot handle it.\nUse " - "CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n"); -#endif kvm_guest_init(); e820_reserve_resources(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index f7745f9..76e305e 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -80,24 +80,6 @@ static void __init setup_per_cpu_maps(void) #endif } -#ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP -cpumask_t *cpumask_of_cpu_map __read_mostly; -EXPORT_SYMBOL(cpumask_of_cpu_map); - -/* requires nr_cpu_ids to be initialized */ -static void __init setup_cpumask_of_cpu(void) -{ - int i; - - /* alloc_bootmem zeroes memory */ - cpumask_of_cpu_map = alloc_bootmem_low(sizeof(cpumask_t) * nr_cpu_ids); - for (i = 0; i < nr_cpu_ids; i++) - cpu_set(i, cpumask_of_cpu_map[i]); -} -#else -static inline void setup_cpumask_of_cpu(void) { } -#endif - #ifdef CONFIG_X86_32 /* * Great future not-so-futuristic plan: make i386 and x86_64 do it @@ -197,9 +179,6 @@ void __init setup_per_cpu_areas(void) /* Setup node to cpumask map */ setup_node_to_cpumask_map(); - - /* Setup cpumask_of_cpu map */ - setup_cpumask_of_cpu(); } #endif diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c index 07faaa5..6fb5bcd 100644 --- a/arch/x86/kernel/signal_32.c +++ b/arch/x86/kernel/signal_32.c @@ -661,8 +661,5 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs); - if (thread_info_flags & _TIF_HRTICK_RESCHED) - hrtick_resched(); - clear_thread_flag(TIF_IRET); } diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index bf87684..b45ef8d 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -53,6 +53,59 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, return do_sigaltstack(uss, uoss, regs->sp); } +/* + * Signal frame handlers. + */ + +static inline int save_i387(struct _fpstate __user *buf) +{ + struct task_struct *tsk = current; + int err = 0; + + BUILD_BUG_ON(sizeof(struct user_i387_struct) != + sizeof(tsk->thread.xstate->fxsave)); + + if ((unsigned long)buf % 16) + printk("save_i387: bad fpstate %p\n", buf); + + if (!used_math()) + return 0; + clear_used_math(); /* trigger finit */ + if (task_thread_info(tsk)->status & TS_USEDFPU) { + err = save_i387_checking((struct i387_fxsave_struct __user *) + buf); + if (err) + return err; + task_thread_info(tsk)->status &= ~TS_USEDFPU; + stts(); + } else { + if (__copy_to_user(buf, &tsk->thread.xstate->fxsave, + sizeof(struct i387_fxsave_struct))) + return -1; + } + return 1; +} + +/* + * This restores directly out of user space. Exceptions are handled. + */ +static inline int restore_i387(struct _fpstate __user *buf) +{ + struct task_struct *tsk = current; + int err; + + if (!used_math()) { + err = init_fpu(tsk); + if (err) + return err; + } + + if (!(task_thread_info(current)->status & TS_USEDFPU)) { + clts(); + task_thread_info(current)->status |= TS_USEDFPU; + } + return restore_fpu_checking((__force struct i387_fxsave_struct *)buf); +} /* * Do a signal return; undo the signal stack. @@ -496,9 +549,6 @@ void do_notify_resume(struct pt_regs *regs, void *unused, /* deal with pending signal delivery */ if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs); - - if (thread_info_flags & _TIF_HRTICK_RESCHED) - hrtick_resched(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 4b53a64..91055d7 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -326,12 +326,16 @@ static void __cpuinit start_secondary(void *unused) * for which cpus receive the IPI. Holding this * lock helps us to not include this cpu in a currently in progress * smp_call_function(). + * + * We need to hold vector_lock so there the set of online cpus + * does not change while we are assigning vectors to cpus. Holding + * this lock ensures we don't half assign or remove an irq from a cpu. */ ipi_call_lock_irq(); -#ifdef CONFIG_X86_IO_APIC - setup_vector_irq(smp_processor_id()); -#endif + lock_vector_lock(); + __setup_vector_irq(smp_processor_id()); cpu_set(smp_processor_id(), cpu_online_map); + unlock_vector_lock(); ipi_call_unlock_irq(); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; @@ -438,7 +442,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) cpu_set(cpu, cpu_sibling_setup_map); if (smp_num_siblings > 1) { - for_each_cpu_mask(i, cpu_sibling_setup_map) { + for_each_cpu_mask_nr(i, cpu_sibling_setup_map) { if (c->phys_proc_id == cpu_data(i).phys_proc_id && c->cpu_core_id == cpu_data(i).cpu_core_id) { cpu_set(i, per_cpu(cpu_sibling_map, cpu)); @@ -461,7 +465,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) return; } - for_each_cpu_mask(i, cpu_sibling_setup_map) { + for_each_cpu_mask_nr(i, cpu_sibling_setup_map) { if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { cpu_set(i, c->llc_shared_map); @@ -990,7 +994,17 @@ int __cpuinit native_cpu_up(unsigned int cpu) flush_tlb_all(); low_mappings = 1; +#ifdef CONFIG_X86_PC + if (def_to_bigsmp && apicid > 8) { + printk(KERN_WARNING + "More than 8 CPUs detected - skipping them.\n" + "Use CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.\n"); + err = -1; + } else + err = do_boot_cpu(apicid, cpu); +#else err = do_boot_cpu(apicid, cpu); +#endif zap_low_mappings(); low_mappings = 0; @@ -1219,7 +1233,7 @@ static void remove_siblinginfo(int cpu) int sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); - for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) { + for_each_cpu_mask_nr(sibling, per_cpu(cpu_core_map, cpu)) { cpu_clear(cpu, per_cpu(cpu_core_map, sibling)); /*/ * last thread sibling in this cpu core going down @@ -1228,7 +1242,7 @@ static void remove_siblinginfo(int cpu) cpu_data(sibling).booted_cores--; } - for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu)) + for_each_cpu_mask_nr(sibling, per_cpu(cpu_sibling_map, cpu)) cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling)); cpus_clear(per_cpu(cpu_sibling_map, cpu)); cpus_clear(per_cpu(cpu_core_map, cpu)); @@ -1336,7 +1350,9 @@ int __cpu_disable(void) remove_siblinginfo(cpu); /* It's now safe to remove this processor from the online map */ + lock_vector_lock(); remove_cpu_from_maps(cpu); + unlock_vector_lock(); fixup_irqs(cpu_online_map); return 0; } diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index adff556..d44395f 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -326,3 +326,9 @@ ENTRY(sys_call_table) .long sys_fallocate .long sys_timerfd_settime /* 325 */ .long sys_timerfd_gettime + .long sys_signalfd4 + .long sys_eventfd2 + .long sys_epoll_create1 + .long sys_dup3 /* 330 */ + .long sys_pipe2 + .long sys_inotify_init1 diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 0a1b1a9..6ca515d 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -37,6 +37,7 @@ #include <asm/timer.h> #include <asm/vmi_time.h> #include <asm/kmap_types.h> +#include <asm/setup.h> /* Convenient for calling VMI functions indirectly in the ROM */ typedef u32 __attribute__((regparm(1))) (VROMFUNC)(void); @@ -683,7 +684,7 @@ void vmi_bringup(void) { /* We must establish the lowmem mapping for MMU ops to work */ if (vmi_ops.set_linear_mapping) - vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, max_low_pfn, 0); + vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, MAXMEM_PFN, 0); } /* diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 8d45fab..ce3251c 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM tristate "Kernel-based Virtual Machine (KVM) support" depends on HAVE_KVM select PREEMPT_NOTIFIERS + select MMU_NOTIFIER select ANON_INODES ---help--- Support hosting fully virtualized guest machines using hardware diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b0e4ddc..0bfe2bd 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -653,6 +653,84 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn) account_shadowed(kvm, gfn); } +static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp) +{ + u64 *spte; + int need_tlb_flush = 0; + + while ((spte = rmap_next(kvm, rmapp, NULL))) { + BUG_ON(!(*spte & PT_PRESENT_MASK)); + rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte); + rmap_remove(kvm, spte); + set_shadow_pte(spte, shadow_trap_nonpresent_pte); + need_tlb_flush = 1; + } + return need_tlb_flush; +} + +static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, + int (*handler)(struct kvm *kvm, unsigned long *rmapp)) +{ + int i; + int retval = 0; + + /* + * If mmap_sem isn't taken, we can look the memslots with only + * the mmu_lock by skipping over the slots with userspace_addr == 0. + */ + for (i = 0; i < kvm->nmemslots; i++) { + struct kvm_memory_slot *memslot = &kvm->memslots[i]; + unsigned long start = memslot->userspace_addr; + unsigned long end; + + /* mmu_lock protects userspace_addr */ + if (!start) + continue; + + end = start + (memslot->npages << PAGE_SHIFT); + if (hva >= start && hva < end) { + gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT; + retval |= handler(kvm, &memslot->rmap[gfn_offset]); + retval |= handler(kvm, + &memslot->lpage_info[ + gfn_offset / + KVM_PAGES_PER_HPAGE].rmap_pde); + } + } + + return retval; +} + +int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) +{ + return kvm_handle_hva(kvm, hva, kvm_unmap_rmapp); +} + +static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp) +{ + u64 *spte; + int young = 0; + + spte = rmap_next(kvm, rmapp, NULL); + while (spte) { + int _young; + u64 _spte = *spte; + BUG_ON(!(_spte & PT_PRESENT_MASK)); + _young = _spte & PT_ACCESSED_MASK; + if (_young) { + young = 1; + clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte); + } + spte = rmap_next(kvm, rmapp, spte); + } + return young; +} + +int kvm_age_hva(struct kvm *kvm, unsigned long hva) +{ + return kvm_handle_hva(kvm, hva, kvm_age_rmapp); +} + #ifdef MMU_DEBUG static int is_empty_shadow_page(u64 *spt) { @@ -1203,6 +1281,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) int r; int largepage = 0; pfn_t pfn; + unsigned long mmu_seq; down_read(¤t->mm->mmap_sem); if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) { @@ -1210,6 +1289,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) largepage = 1; } + mmu_seq = vcpu->kvm->mmu_notifier_seq; + /* implicit mb(), we'll read before PT lock is unlocked */ pfn = gfn_to_pfn(vcpu->kvm, gfn); up_read(¤t->mm->mmap_sem); @@ -1220,6 +1301,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) } spin_lock(&vcpu->kvm->mmu_lock); + if (mmu_notifier_retry(vcpu, mmu_seq)) + goto out_unlock; kvm_mmu_free_some_pages(vcpu); r = __direct_map(vcpu, v, write, largepage, gfn, pfn, PT32E_ROOT_LEVEL); @@ -1227,6 +1310,11 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) return r; + +out_unlock: + spin_unlock(&vcpu->kvm->mmu_lock); + kvm_release_pfn_clean(pfn); + return 0; } @@ -1345,6 +1433,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, int r; int largepage = 0; gfn_t gfn = gpa >> PAGE_SHIFT; + unsigned long mmu_seq; ASSERT(vcpu); ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa)); @@ -1358,6 +1447,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, gfn &= ~(KVM_PAGES_PER_HPAGE-1); largepage = 1; } + mmu_seq = vcpu->kvm->mmu_notifier_seq; + /* implicit mb(), we'll read before PT lock is unlocked */ pfn = gfn_to_pfn(vcpu->kvm, gfn); up_read(¤t->mm->mmap_sem); if (is_error_pfn(pfn)) { @@ -1365,12 +1456,19 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, return 1; } spin_lock(&vcpu->kvm->mmu_lock); + if (mmu_notifier_retry(vcpu, mmu_seq)) + goto out_unlock; kvm_mmu_free_some_pages(vcpu); r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK, largepage, gfn, pfn, kvm_x86_ops->get_tdp_level()); spin_unlock(&vcpu->kvm->mmu_lock); return r; + +out_unlock: + spin_unlock(&vcpu->kvm->mmu_lock); + kvm_release_pfn_clean(pfn); + return 0; } static void nonpaging_free(struct kvm_vcpu *vcpu) @@ -1670,6 +1768,8 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, gfn &= ~(KVM_PAGES_PER_HPAGE-1); vcpu->arch.update_pte.largepage = 1; } + vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq; + /* implicit mb(), we'll read before PT lock is unlocked */ pfn = gfn_to_pfn(vcpu->kvm, gfn); up_read(¤t->mm->mmap_sem); @@ -1814,6 +1914,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) spin_unlock(&vcpu->kvm->mmu_lock); return r; } +EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) { @@ -1870,6 +1971,12 @@ void kvm_enable_tdp(void) } EXPORT_SYMBOL_GPL(kvm_enable_tdp); +void kvm_disable_tdp(void) +{ + tdp_enabled = false; +} +EXPORT_SYMBOL_GPL(kvm_disable_tdp); + static void free_mmu_pages(struct kvm_vcpu *vcpu) { struct kvm_mmu_page *sp; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 4d91822..f72ac1f 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -263,6 +263,8 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, pfn = vcpu->arch.update_pte.pfn; if (is_error_pfn(pfn)) return; + if (mmu_notifier_retry(vcpu, vcpu->arch.update_pte.mmu_seq)) + return; kvm_get_pfn(pfn); mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0, gpte & PT_DIRTY_MASK, NULL, largepage, gpte_to_gfn(gpte), @@ -380,6 +382,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, int r; pfn_t pfn; int largepage = 0; + unsigned long mmu_seq; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); kvm_mmu_audit(vcpu, "pre page fault"); @@ -413,6 +416,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, largepage = 1; } } + mmu_seq = vcpu->kvm->mmu_notifier_seq; + /* implicit mb(), we'll read before PT lock is unlocked */ pfn = gfn_to_pfn(vcpu->kvm, walker.gfn); up_read(¤t->mm->mmap_sem); @@ -424,6 +429,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, } spin_lock(&vcpu->kvm->mmu_lock); + if (mmu_notifier_retry(vcpu, mmu_seq)) + goto out_unlock; kvm_mmu_free_some_pages(vcpu); shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, largepage, &write_pt, pfn); @@ -439,6 +446,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, spin_unlock(&vcpu->kvm->mmu_lock); return write_pt; + +out_unlock: + spin_unlock(&vcpu->kvm->mmu_lock); + kvm_release_pfn_clean(pfn); + return 0; } static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b756e87..e2ee264 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -453,7 +453,8 @@ static __init int svm_hardware_setup(void) if (npt_enabled) { printk(KERN_INFO "kvm: Nested Paging enabled\n"); kvm_enable_tdp(); - } + } else + kvm_disable_tdp(); return 0; @@ -1007,10 +1008,13 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) struct kvm *kvm = svm->vcpu.kvm; u64 fault_address; u32 error_code; + bool event_injection = false; if (!irqchip_in_kernel(kvm) && - is_external_interrupt(exit_int_info)) + is_external_interrupt(exit_int_info)) { + event_injection = true; push_irq(&svm->vcpu, exit_int_info & SVM_EVTINJ_VEC_MASK); + } fault_address = svm->vmcb->control.exit_info_2; error_code = svm->vmcb->control.exit_info_1; @@ -1024,6 +1028,8 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) (u32)fault_address, (u32)(fault_address >> 32), handler); + if (event_injection) + kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address); return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 0cac637..2a69773 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2298,6 +2298,8 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) cr2 = vmcs_readl(EXIT_QUALIFICATION); KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2, (u32)((u64)cr2 >> 32), handler); + if (vect_info & VECTORING_INFO_VALID_MASK) + kvm_mmu_unprotect_page_virt(vcpu, cr2); return kvm_mmu_page_fault(vcpu, cr2, error_code); } @@ -3116,15 +3118,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return ERR_PTR(-ENOMEM); allocate_vpid(vmx); - if (id == 0 && vm_need_ept()) { - kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK | - VMX_EPT_WRITABLE_MASK | - VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT); - kvm_mmu_set_mask_ptes(0ull, VMX_EPT_FAKE_ACCESSED_MASK, - VMX_EPT_FAKE_DIRTY_MASK, 0ull, - VMX_EPT_EXECUTABLE_MASK); - kvm_enable_tdp(); - } err = kvm_vcpu_init(&vmx->vcpu, kvm, id); if (err) @@ -3303,8 +3296,17 @@ static int __init vmx_init(void) vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP); vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP); - if (cpu_has_vmx_ept()) + if (vm_need_ept()) { bypass_guest_pf = 0; + kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK | + VMX_EPT_WRITABLE_MASK | + VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT); + kvm_mmu_set_mask_ptes(0ull, VMX_EPT_FAKE_ACCESSED_MASK, + VMX_EPT_FAKE_DIRTY_MASK, 0ull, + VMX_EPT_EXECUTABLE_MASK); + kvm_enable_tdp(); + } else + kvm_disable_tdp(); if (bypass_guest_pf) kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9f1cdb0..0d682fc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -883,6 +883,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PIT: case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: + case KVM_CAP_SYNC_MMU: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -1495,6 +1496,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, goto out; down_write(&kvm->slots_lock); + spin_lock(&kvm->mmu_lock); p = &kvm->arch.aliases[alias->slot]; p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT; @@ -1506,6 +1508,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, break; kvm->arch.naliases = n; + spin_unlock(&kvm->mmu_lock); kvm_mmu_zap_all(kvm); up_write(&kvm->slots_lock); @@ -3184,6 +3187,10 @@ static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector, kvm_desct->base |= seg_desc->base2 << 24; kvm_desct->limit = seg_desc->limit0; kvm_desct->limit |= seg_desc->limit << 16; + if (seg_desc->g) { + kvm_desct->limit <<= 12; + kvm_desct->limit |= 0xfff; + } kvm_desct->selector = selector; kvm_desct->type = seg_desc->type; kvm_desct->present = seg_desc->p; @@ -3223,6 +3230,7 @@ static void get_segment_descritptor_dtable(struct kvm_vcpu *vcpu, static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, struct desc_struct *seg_desc) { + gpa_t gpa; struct descriptor_table dtable; u16 index = selector >> 3; @@ -3232,13 +3240,16 @@ static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc); return 1; } - return kvm_read_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8); + gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, dtable.base); + gpa += index * 8; + return kvm_read_guest(vcpu->kvm, gpa, seg_desc, 8); } /* allowed just for 8 bytes segments */ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, struct desc_struct *seg_desc) { + gpa_t gpa; struct descriptor_table dtable; u16 index = selector >> 3; @@ -3246,7 +3257,9 @@ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, if (dtable.limit < index * 8 + 7) return 1; - return kvm_write_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8); + gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, dtable.base); + gpa += index * 8; + return kvm_write_guest(vcpu->kvm, gpa, seg_desc, 8); } static u32 get_tss_base_addr(struct kvm_vcpu *vcpu, @@ -3258,55 +3271,7 @@ static u32 get_tss_base_addr(struct kvm_vcpu *vcpu, base_addr |= (seg_desc->base1 << 16); base_addr |= (seg_desc->base2 << 24); - return base_addr; -} - -static int load_tss_segment32(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc, - struct tss_segment_32 *tss) -{ - u32 base_addr; - - base_addr = get_tss_base_addr(vcpu, seg_desc); - - return kvm_read_guest(vcpu->kvm, base_addr, tss, - sizeof(struct tss_segment_32)); -} - -static int save_tss_segment32(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc, - struct tss_segment_32 *tss) -{ - u32 base_addr; - - base_addr = get_tss_base_addr(vcpu, seg_desc); - - return kvm_write_guest(vcpu->kvm, base_addr, tss, - sizeof(struct tss_segment_32)); -} - -static int load_tss_segment16(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc, - struct tss_segment_16 *tss) -{ - u32 base_addr; - - base_addr = get_tss_base_addr(vcpu, seg_desc); - - return kvm_read_guest(vcpu->kvm, base_addr, tss, - sizeof(struct tss_segment_16)); -} - -static int save_tss_segment16(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc, - struct tss_segment_16 *tss) -{ - u32 base_addr; - - base_addr = get_tss_base_addr(vcpu, seg_desc); - - return kvm_write_guest(vcpu->kvm, base_addr, tss, - sizeof(struct tss_segment_16)); + return vcpu->arch.mmu.gva_to_gpa(vcpu, base_addr); } static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg) @@ -3466,20 +3431,26 @@ static int load_state_from_tss16(struct kvm_vcpu *vcpu, } static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector, - struct desc_struct *cseg_desc, + u32 old_tss_base, struct desc_struct *nseg_desc) { struct tss_segment_16 tss_segment_16; int ret = 0; - if (load_tss_segment16(vcpu, cseg_desc, &tss_segment_16)) + if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_16, + sizeof tss_segment_16)) goto out; save_state_to_tss16(vcpu, &tss_segment_16); - save_tss_segment16(vcpu, cseg_desc, &tss_segment_16); - if (load_tss_segment16(vcpu, nseg_desc, &tss_segment_16)) + if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_16, + sizeof tss_segment_16)) + goto out; + + if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc), + &tss_segment_16, sizeof tss_segment_16)) goto out; + if (load_state_from_tss16(vcpu, &tss_segment_16)) goto out; @@ -3489,20 +3460,26 @@ out: } static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector, - struct desc_struct *cseg_desc, + u32 old_tss_base, struct desc_struct *nseg_desc) { struct tss_segment_32 tss_segment_32; int ret = 0; - if (load_tss_segment32(vcpu, cseg_desc, &tss_segment_32)) + if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_32, + sizeof tss_segment_32)) goto out; save_state_to_tss32(vcpu, &tss_segment_32); - save_tss_segment32(vcpu, cseg_desc, &tss_segment_32); - if (load_tss_segment32(vcpu, nseg_desc, &tss_segment_32)) + if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_32, + sizeof tss_segment_32)) goto out; + + if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc), + &tss_segment_32, sizeof tss_segment_32)) + goto out; + if (load_state_from_tss32(vcpu, &tss_segment_32)) goto out; @@ -3517,16 +3494,20 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) struct desc_struct cseg_desc; struct desc_struct nseg_desc; int ret = 0; + u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR); + u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR); - kvm_get_segment(vcpu, &tr_seg, VCPU_SREG_TR); + old_tss_base = vcpu->arch.mmu.gva_to_gpa(vcpu, old_tss_base); + /* FIXME: Handle errors. Failure to read either TSS or their + * descriptors should generate a pagefault. + */ if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc)) goto out; - if (load_guest_segment_descriptor(vcpu, tr_seg.selector, &cseg_desc)) + if (load_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc)) goto out; - if (reason != TASK_SWITCH_IRET) { int cpl; @@ -3544,8 +3525,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) { cseg_desc.type &= ~(1 << 1); //clear the B flag - save_guest_segment_descriptor(vcpu, tr_seg.selector, - &cseg_desc); + save_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc); } if (reason == TASK_SWITCH_IRET) { @@ -3557,10 +3537,10 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) kvm_x86_ops->cache_regs(vcpu); if (nseg_desc.type & 8) - ret = kvm_task_switch_32(vcpu, tss_selector, &cseg_desc, + ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_base, &nseg_desc); else - ret = kvm_task_switch_16(vcpu, tss_selector, &cseg_desc, + ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_base, &nseg_desc); if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) { @@ -3995,16 +3975,23 @@ int kvm_arch_set_memory_region(struct kvm *kvm, */ if (!user_alloc) { if (npages && !old.rmap) { + unsigned long userspace_addr; + 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); + 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); + if (IS_ERR((void *)userspace_addr)) + return PTR_ERR((void *)userspace_addr); + + /* set userspace_addr atomically for kvm_hva_to_rmapp */ + spin_lock(&kvm->mmu_lock); + memslot->userspace_addr = userspace_addr; + spin_unlock(&kvm->mmu_lock); } else { if (!old.user_alloc && old.rmap) { int ret; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 0313a5e..d9249a8 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1014,6 +1014,9 @@ __init void lguest_init(void) init_pg_tables_start = __pa(pg0); init_pg_tables_end = __pa(pg0); + /* As described in head_32.S, we map the first 128M of memory. */ + max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT; + /* Load the %fs segment register (the per-cpu segment register) with * the normal data segment to get through booting. */ asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_DS) : "memory"); diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index dfdf428..f118c11 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -52,7 +52,7 @@ jnz 100b 102: .section .fixup,"ax" -103: addl %r8d,%edx /* ecx is zerorest also */ +103: addl %ecx,%edx /* ecx is zerorest also */ jmp copy_user_handle_tail .previous diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S index 40e0e30..cb0c112 100644 --- a/arch/x86/lib/copy_user_nocache_64.S +++ b/arch/x86/lib/copy_user_nocache_64.S @@ -32,7 +32,7 @@ jnz 100b 102: .section .fixup,"ax" -103: addl %r8d,%edx /* ecx is zerorest also */ +103: addl %ecx,%edx /* ecx is zerorest also */ jmp copy_user_handle_tail .previous @@ -108,7 +108,6 @@ ENTRY(__copy_user_nocache) jmp 60f 50: movl %ecx,%edx 60: sfence - movl %r8d,%ecx jmp copy_user_handle_tail .previous diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 1fbb844..dfb932d 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,5 +1,5 @@ obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o + pat.o pgtable.o gup.o obj-$(CONFIG_X86_32) += pgtable_32.o diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c index 5dfef9f..62fa440 100644 --- a/arch/x86/mm/discontig_32.c +++ b/arch/x86/mm/discontig_32.c @@ -42,7 +42,6 @@ struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); -static bootmem_data_t node0_bdata; /* * numa interface - we expect the numa architecture specific code to have @@ -385,7 +384,7 @@ void __init initmem_init(unsigned long start_pfn, for_each_online_node(nid) memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); - NODE_DATA(0)->bdata = &node0_bdata; + NODE_DATA(0)->bdata = &bootmem_node_data[0]; setup_bootmem_allocator(); } diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c new file mode 100644 index 0000000..007bb06 --- /dev/null +++ b/arch/x86/mm/gup.c @@ -0,0 +1,298 @@ +/* + * Lockless get_user_pages_fast for x86 + * + * Copyright (C) 2008 Nick Piggin + * Copyright (C) 2008 Novell Inc. + */ +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmstat.h> +#include <linux/highmem.h> + +#include <asm/pgtable.h> + +static inline pte_t gup_get_pte(pte_t *ptep) +{ +#ifndef CONFIG_X86_PAE + return *ptep; +#else + /* + * With get_user_pages_fast, we walk down the pagetables without taking + * any locks. For this we would like to load the pointers atoimcally, + * but that is not possible (without expensive cmpxchg8b) on PAE. What + * we do have is the guarantee that a pte will only either go from not + * present to present, or present to not present or both -- it will not + * switch to a completely different present page without a TLB flush in + * between; something that we are blocking by holding interrupts off. + * + * Setting ptes from not present to present goes: + * ptep->pte_high = h; + * smp_wmb(); + * ptep->pte_low = l; + * + * And present to not present goes: + * ptep->pte_low = 0; + * smp_wmb(); + * ptep->pte_high = 0; + * + * We must ensure here that the load of pte_low sees l iff pte_high + * sees h. We load pte_high *after* loading pte_low, which ensures we + * don't see an older value of pte_high. *Then* we recheck pte_low, + * which ensures that we haven't picked up a changed pte high. We might + * have got rubbish values from pte_low and pte_high, but we are + * guaranteed that pte_low will not have the present bit set *unless* + * it is 'l'. And get_user_pages_fast only operates on present ptes, so + * we're safe. + * + * gup_get_pte should not be used or copied outside gup.c without being + * very careful -- it does not atomically load the pte or anything that + * is likely to be useful for you. + */ + pte_t pte; + +retry: + pte.pte_low = ptep->pte_low; + smp_rmb(); + pte.pte_high = ptep->pte_high; + smp_rmb(); + if (unlikely(pte.pte_low != ptep->pte_low)) + goto retry; + + return pte; +#endif +} + +/* + * The performance critical leaf functions are made noinline otherwise gcc + * inlines everything into a single function which results in too much + * register pressure. + */ +static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask; + pte_t *ptep; + + mask = _PAGE_PRESENT|_PAGE_USER; + if (write) + mask |= _PAGE_RW; + + ptep = pte_offset_map(&pmd, addr); + do { + pte_t pte = gup_get_pte(ptep); + struct page *page; + + if ((pte_val(pte) & (mask | _PAGE_SPECIAL)) != mask) { + pte_unmap(ptep); + return 0; + } + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + page = pte_page(pte); + get_page(page); + pages[*nr] = page; + (*nr)++; + + } while (ptep++, addr += PAGE_SIZE, addr != end); + pte_unmap(ptep - 1); + + return 1; +} + +static inline void get_head_page_multiple(struct page *page, int nr) +{ + VM_BUG_ON(page != compound_head(page)); + VM_BUG_ON(page_count(page) == 0); + atomic_add(nr, &page->_count); +} + +static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask; + pte_t pte = *(pte_t *)&pmd; + struct page *head, *page; + int refs; + + mask = _PAGE_PRESENT|_PAGE_USER; + if (write) + mask |= _PAGE_RW; + if ((pte_val(pte) & mask) != mask) + return 0; + /* hugepages are never "special" */ + VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + refs = 0; + head = pte_page(pte); + page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + do { + VM_BUG_ON(compound_head(page) != head); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + get_head_page_multiple(head, refs); + + return 1; +} + +static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pmd_t *pmdp; + + pmdp = pmd_offset(&pud, addr); + do { + pmd_t pmd = *pmdp; + + next = pmd_addr_end(addr, end); + if (pmd_none(pmd)) + return 0; + if (unlikely(pmd_large(pmd))) { + if (!gup_huge_pmd(pmd, addr, next, write, pages, nr)) + return 0; + } else { + if (!gup_pte_range(pmd, addr, next, write, pages, nr)) + return 0; + } + } while (pmdp++, addr = next, addr != end); + + return 1; +} + +static noinline int gup_huge_pud(pud_t pud, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask; + pte_t pte = *(pte_t *)&pud; + struct page *head, *page; + int refs; + + mask = _PAGE_PRESENT|_PAGE_USER; + if (write) + mask |= _PAGE_RW; + if ((pte_val(pte) & mask) != mask) + return 0; + /* hugepages are never "special" */ + VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + refs = 0; + head = pte_page(pte); + page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + do { + VM_BUG_ON(compound_head(page) != head); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + get_head_page_multiple(head, refs); + + return 1; +} + +static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pud_t *pudp; + + pudp = pud_offset(&pgd, addr); + do { + pud_t pud = *pudp; + + next = pud_addr_end(addr, end); + if (pud_none(pud)) + return 0; + if (unlikely(pud_large(pud))) { + if (!gup_huge_pud(pud, addr, next, write, pages, nr)) + return 0; + } else { + if (!gup_pmd_range(pud, addr, next, write, pages, nr)) + return 0; + } + } while (pudp++, addr = next, addr != end); + + return 1; +} + +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long addr, len, end; + unsigned long next; + pgd_t *pgdp; + int nr = 0; + + start &= PAGE_MASK; + addr = start; + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, + start, len))) + goto slow_irqon; + + /* + * XXX: batch / limit 'nr', to avoid large irq off latency + * needs some instrumenting to determine the common sizes used by + * important workloads (eg. DB2), and whether limiting the batch size + * will decrease performance. + * + * It seems like we're in the clear for the moment. Direct-IO is + * the main guy that batches up lots of get_user_pages, and even + * they are limited to 64-at-a-time which is not so many. + */ + /* + * This doesn't prevent pagetable teardown, but does prevent + * the pagetables and pages from being freed on x86. + * + * So long as we atomically load page table pointers versus teardown + * (which we do on x86, with the above PAE exception), we can follow the + * address down to the the page and take a ref on it. + */ + local_irq_disable(); + pgdp = pgd_offset(mm, addr); + do { + pgd_t pgd = *pgdp; + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + goto slow; + if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + goto slow; + } while (pgdp++, addr = next, addr != end); + local_irq_enable(); + + VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); + return nr; + + { + int ret; + +slow: + local_irq_enable(); +slow_irqon: + /* Try to get the remaining pages with get_user_pages */ + start += nr << PAGE_SHIFT; + pages += nr; + + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, start, + (end - start) >> PAGE_SHIFT, write, 0, pages, NULL); + up_read(&mm->mmap_sem); + + /* Have to be a bit careful with return values */ + if (nr > 0) { + if (ret < 0) + ret = nr; + else + ret += nr; + } + + return ret; + } +} diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 0b3d567..8f307d9 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -124,7 +124,8 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 1; } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgd; pud_t *pud; @@ -133,9 +134,14 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) pgd = pgd_offset(mm, addr); pud = pud_alloc(mm, pgd, addr); if (pud) { - if (pud_none(*pud)) - huge_pmd_share(mm, addr, pud); - pte = (pte_t *) pmd_alloc(mm, pud, addr); + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + } else { + BUG_ON(sz != PMD_SIZE); + if (pud_none(*pud)) + huge_pmd_share(mm, addr, pud); + pte = (pte_t *) pmd_alloc(mm, pud, addr); + } } BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); @@ -151,8 +157,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) pgd = pgd_offset(mm, addr); if (pgd_present(*pgd)) { pud = pud_offset(pgd, addr); - if (pud_present(*pud)) + if (pud_present(*pud)) { + if (pud_large(*pud)) + return (pte_t *)pud; pmd = pmd_offset(pud, addr); + } } return (pte_t *) pmd; } @@ -188,6 +197,11 @@ int pmd_huge(pmd_t pmd) return 0; } +int pud_huge(pud_t pud) +{ + return 0; +} + struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) @@ -208,6 +222,11 @@ int pmd_huge(pmd_t pmd) return !!(pmd_val(pmd) & _PAGE_PSE); } +int pud_huge(pud_t pud) +{ + return !!(pud_val(pud) & _PAGE_PSE); +} + struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) @@ -216,9 +235,22 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, page = pte_page(*(pte_t *)pmd); if (page) - page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT); + page += ((address & ~PMD_MASK) >> PAGE_SHIFT); + return page; +} + +struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + struct page *page; + + page = pte_page(*(pte_t *)pud); + if (page) + page += ((address & ~PUD_MASK) >> PAGE_SHIFT); return page; } + #endif /* x86_64 also uses this file */ @@ -228,6 +260,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long start_addr; @@ -240,7 +273,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, } full_search: - addr = ALIGN(start_addr, HPAGE_SIZE); + addr = ALIGN(start_addr, huge_page_size(h)); for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { /* At this point: (!vma || addr < vma->vm_end). */ @@ -262,7 +295,7 @@ full_search: } if (addr + mm->cached_hole_size < vma->vm_start) mm->cached_hole_size = vma->vm_start - addr; - addr = ALIGN(vma->vm_end, HPAGE_SIZE); + addr = ALIGN(vma->vm_end, huge_page_size(h)); } } @@ -270,6 +303,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr0, unsigned long len, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev_vma; unsigned long base = mm->mmap_base, addr = addr0; @@ -290,7 +324,7 @@ try_again: goto fail; /* either no address requested or cant fit in requested address hole */ - addr = (mm->free_area_cache - len) & HPAGE_MASK; + addr = (mm->free_area_cache - len) & huge_page_mask(h); do { /* * Lookup failure means no vma is above this address, @@ -321,7 +355,7 @@ try_again: largest_hole = vma->vm_start - addr; /* try just below the current vma->vm_start */ - addr = (vma->vm_start - len) & HPAGE_MASK; + addr = (vma->vm_start - len) & huge_page_mask(h); } while (len <= vma->vm_start); fail: @@ -359,22 +393,23 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - if (len & ~HPAGE_MASK) + if (len & ~huge_page_mask(h)) return -EINVAL; if (len > TASK_SIZE) return -ENOMEM; if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } if (addr) { - addr = ALIGN(addr, HPAGE_SIZE); + addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && (!vma || addr + len <= vma->vm_start)) @@ -390,3 +425,20 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, #endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/ +#ifdef CONFIG_X86_64 +static __init int setup_hugepagesz(char *opt) +{ + unsigned long ps = memparse(opt, &opt); + if (ps == PMD_SIZE) { + hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); + } else if (ps == PUD_SIZE && cpu_has_gbpages) { + hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + } else { + printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n", + ps >> 20); + return 0; + } + return 1; +} +__setup("hugepagesz=", setup_hugepagesz); +#endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ec37121..129618c 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -86,43 +86,6 @@ early_param("gbpages", parse_direct_gbpages_on); * around without checking the pgd every time. */ -void show_mem(void) -{ - long i, total = 0, reserved = 0; - long shared = 0, cached = 0; - struct page *page; - pg_data_t *pgdat; - - printk(KERN_INFO "Mem-info:\n"); - show_free_areas(); - for_each_online_pgdat(pgdat) { - for (i = 0; i < pgdat->node_spanned_pages; ++i) { - /* - * This loop can take a while with 256 GB and - * 4k pages so defer the NMI watchdog: - */ - if (unlikely(i % MAX_ORDER_NR_PAGES == 0)) - touch_nmi_watchdog(); - - if (!pfn_valid(pgdat->node_start_pfn + i)) - continue; - - page = pfn_to_page(pgdat->node_start_pfn + i); - total++; - if (PageReserved(page)) - reserved++; - else if (PageSwapCache(page)) - cached++; - else if (page_count(page)) - shared += page_count(page) - 1; - } - } - printk(KERN_INFO "%lu pages of RAM\n", total); - printk(KERN_INFO "%lu reserved pages\n", reserved); - printk(KERN_INFO "%lu pages shared\n", shared); - printk(KERN_INFO "%lu pages swap cached\n", cached); -} - int after_bootmem; static __init void *spp_getpage(void) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 24c1d3c..016f335 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -330,6 +330,14 @@ static void __iomem *ioremap_default(resource_size_t phys_addr, return (void __iomem *)ret; } +void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size, + unsigned long prot_val) +{ + return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK), + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_prot); + /** * iounmap - Free a IO remapping * @addr: virtual address from ioremap_* diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 9782f42..a4dd793 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -23,8 +23,6 @@ struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); -static bootmem_data_t plat_node_bdata[MAX_NUMNODES]; - struct memnode memnode; s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { @@ -198,7 +196,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, nodedata_phys + pgdat_size - 1); memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t)); - NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid]; + NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid]; NODE_DATA(nodeid)->node_start_pfn = start_pfn; NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 557b2ab..d503027 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -207,6 +207,9 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) unsigned long addr; int i; + if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */ + return; + pud = pud_offset(pgd, 0); for (addr = i = 0; i < PREALLOCATED_PMDS; diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index b4becbf..cab0abb 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -20,53 +20,6 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> -void show_mem(void) -{ - int total = 0, reserved = 0; - int shared = 0, cached = 0; - int highmem = 0; - struct page *page; - pg_data_t *pgdat; - unsigned long i; - unsigned long flags; - - printk(KERN_INFO "Mem-info:\n"); - show_free_areas(); - for_each_online_pgdat(pgdat) { - pgdat_resize_lock(pgdat, &flags); - for (i = 0; i < pgdat->node_spanned_pages; ++i) { - if (unlikely(i % MAX_ORDER_NR_PAGES == 0)) - touch_nmi_watchdog(); - page = pgdat_page_nr(pgdat, i); - total++; - if (PageHighMem(page)) - highmem++; - if (PageReserved(page)) - reserved++; - else if (PageSwapCache(page)) - cached++; - else if (page_count(page)) - shared += page_count(page) - 1; - } - pgdat_resize_unlock(pgdat, &flags); - } - printk(KERN_INFO "%d pages of RAM\n", total); - printk(KERN_INFO "%d pages of HIGHMEM\n", highmem); - printk(KERN_INFO "%d reserved pages\n", reserved); - printk(KERN_INFO "%d pages shared\n", shared); - printk(KERN_INFO "%d pages swap cached\n", cached); - - printk(KERN_INFO "%lu pages dirty\n", global_page_state(NR_FILE_DIRTY)); - printk(KERN_INFO "%lu pages writeback\n", - global_page_state(NR_WRITEBACK)); - printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED)); - printk(KERN_INFO "%lu pages slab\n", - global_page_state(NR_SLAB_RECLAIMABLE) + - global_page_state(NR_SLAB_UNRECLAIMABLE)); - printk(KERN_INFO "%lu pages pagetables\n", - global_page_state(NR_PAGETABLE)); -} - /* * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 7f3329b..3f90289 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -369,20 +369,34 @@ static int __init ppro_init(char **cpu_type) { __u8 cpu_model = boot_cpu_data.x86_model; - if (cpu_model == 14) + switch (cpu_model) { + case 0 ... 2: + *cpu_type = "i386/ppro"; + break; + case 3 ... 5: + *cpu_type = "i386/pii"; + break; + case 6 ... 8: + *cpu_type = "i386/piii"; + break; + case 9: + *cpu_type = "i386/p6_mobile"; + break; + case 10 ... 13: + *cpu_type = "i386/p6"; + break; + case 14: *cpu_type = "i386/core"; - else if (cpu_model == 15 || cpu_model == 23) + break; + case 15: case 23: + *cpu_type = "i386/core_2"; + break; + case 26: *cpu_type = "i386/core_2"; - else if (cpu_model > 0xd) + break; + default: + /* Unknown */ return 0; - else if (cpu_model == 9) { - *cpu_type = "i386/p6_mobile"; - } else if (cpu_model > 5) { - *cpu_type = "i386/piii"; - } else if (cpu_model > 2) { - *cpu_type = "i386/pii"; - } else { - *cpu_type = "i386/ppro"; } model = &op_ppro_spec; diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index ff3a6a3..4bdaa59 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -23,7 +23,8 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d) pci_read_config_byte(d, reg++, &busno); pci_read_config_byte(d, reg++, &suba); pci_read_config_byte(d, reg++, &subb); - DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb); + dev_dbg(&d->dev, "i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, + suba, subb); if (busno) pci_scan_bus_with_sysdata(busno); /* Bus A */ if (suba < subb) diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 2aafb67..5807d1b 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -128,10 +128,8 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) pr = pci_find_parent_resource(dev, r); if (!r->start || !pr || request_resource(pr, r) < 0) { - printk(KERN_ERR "PCI: Cannot allocate " - "resource region %d " - "of bridge %s\n", - idx, pci_name(dev)); + dev_err(&dev->dev, "BAR %d: can't " + "allocate resource\n", idx); /* * Something is wrong with the region. * Invalidate the resource to prevent @@ -166,15 +164,15 @@ static void __init pcibios_allocate_resources(int pass) else disabled = !(command & PCI_COMMAND_MEMORY); if (pass == disabled) { - DBG("PCI: Resource %08lx-%08lx " - "(f=%lx, d=%d, p=%d)\n", - r->start, r->end, r->flags, disabled, pass); + dev_dbg(&dev->dev, "resource %#08llx-%#08llx " + "(f=%lx, d=%d, p=%d)\n", + (unsigned long long) r->start, + (unsigned long long) r->end, + r->flags, disabled, pass); pr = pci_find_parent_resource(dev, r); if (!pr || request_resource(pr, r) < 0) { - printk(KERN_ERR "PCI: Cannot allocate " - "resource region %d " - "of device %s\n", - idx, pci_name(dev)); + dev_err(&dev->dev, "BAR %d: can't " + "allocate resource\n", idx); /* We'll assign a new address later */ r->end -= r->start; r->start = 0; @@ -187,8 +185,7 @@ static void __init pcibios_allocate_resources(int pass) /* Turn the ROM off, leave the resource region, * but keep it unregistered. */ u32 reg; - DBG("PCI: Switching off ROM of %s\n", - pci_name(dev)); + dev_dbg(&dev->dev, "disabling ROM\n"); r->flags &= ~IORESOURCE_ROM_ENABLE; pci_read_config_dword(dev, dev->rom_base_reg, ®); @@ -257,8 +254,7 @@ void pcibios_set_master(struct pci_dev *dev) lat = pcibios_max_latency; else return; - printk(KERN_DEBUG "PCI: Setting latency timer of device %s to %d\n", - pci_name(dev), lat); + dev_printk(KERN_DEBUG, &dev->dev, "setting latency timer to %d\n", lat); pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); } @@ -280,6 +276,7 @@ static void pci_track_mmap_page_range(struct vm_area_struct *vma) static struct vm_operations_struct pci_mmap_ops = { .open = pci_track_mmap_page_range, .close = pci_unmap_page_range, + .access = generic_access_phys, }; int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 6a06a2e..fec0123 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -436,7 +436,7 @@ static int pirq_vlsi_get(struct pci_dev *router, struct pci_dev *dev, int pirq) { WARN_ON_ONCE(pirq >= 9); if (pirq > 8) { - printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq); + dev_info(&dev->dev, "VLSI router PIRQ escape (%d)\n", pirq); return 0; } return read_config_nybble(router, 0x74, pirq-1); @@ -446,7 +446,7 @@ static int pirq_vlsi_set(struct pci_dev *router, struct pci_dev *dev, int pirq, { WARN_ON_ONCE(pirq >= 9); if (pirq > 8) { - printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq); + dev_info(&dev->dev, "VLSI router PIRQ escape (%d)\n", pirq); return 0; } write_config_nybble(router, 0x74, pirq-1, irq); @@ -492,15 +492,17 @@ static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq irq = 0; if (pirq <= 4) irq = read_config_nybble(router, 0x56, pirq - 1); - printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d get irq : %2d\n", - dev->vendor, dev->device, pirq, irq); + dev_info(&dev->dev, + "AMD756: dev [%04x/%04x], router PIRQ %d get IRQ %d\n", + dev->vendor, dev->device, pirq, irq); return irq; } static int pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { - printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n", - dev->vendor, dev->device, pirq, irq); + dev_info(&dev->dev, + "AMD756: dev [%04x/%04x], router PIRQ %d set IRQ %d\n", + dev->vendor, dev->device, pirq, irq); if (pirq <= 4) write_config_nybble(router, 0x56, pirq - 1, irq); return 1; @@ -730,7 +732,6 @@ static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, switch (device) { case PCI_DEVICE_ID_AL_M1533: case PCI_DEVICE_ID_AL_M1563: - printk(KERN_DEBUG "PCI: Using ALI IRQ Router\n"); r->name = "ALI"; r->get = pirq_ali_get; r->set = pirq_ali_set; @@ -840,11 +841,9 @@ static void __init pirq_find_router(struct irq_router *r) h->probe(r, pirq_router_dev, pirq_router_dev->device)) break; } - printk(KERN_INFO "PCI: Using IRQ router %s [%04x/%04x] at %s\n", - pirq_router.name, - pirq_router_dev->vendor, - pirq_router_dev->device, - pci_name(pirq_router_dev)); + dev_info(&pirq_router_dev->dev, "%s IRQ router [%04x/%04x]\n", + pirq_router.name, + pirq_router_dev->vendor, pirq_router_dev->device); /* The device remains referenced for the kernel lifetime */ } @@ -877,7 +876,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) /* Find IRQ pin */ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); if (!pin) { - DBG(KERN_DEBUG " -> no interrupt pin\n"); + dev_dbg(&dev->dev, "no interrupt pin\n"); return 0; } pin = pin - 1; @@ -887,20 +886,20 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) if (!pirq_table) return 0; - DBG(KERN_DEBUG "IRQ for %s[%c]", pci_name(dev), 'A' + pin); info = pirq_get_info(dev); if (!info) { - DBG(" -> not found in routing table\n" KERN_DEBUG); + dev_dbg(&dev->dev, "PCI INT %c not found in routing table\n", + 'A' + pin); return 0; } pirq = info->irq[pin].link; mask = info->irq[pin].bitmap; if (!pirq) { - DBG(" -> not routed\n" KERN_DEBUG); + dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + pin); return 0; } - DBG(" -> PIRQ %02x, mask %04x, excl %04x", pirq, mask, - pirq_table->exclusive_irqs); + dev_dbg(&dev->dev, "PCI INT %c -> PIRQ %02x, mask %04x, excl %04x", + 'A' + pin, pirq, mask, pirq_table->exclusive_irqs); mask &= pcibios_irq_mask; /* Work around broken HP Pavilion Notebooks which assign USB to @@ -930,10 +929,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) if (pci_probe & PCI_USE_PIRQ_MASK) newirq = 0; else - printk("\n" KERN_WARNING - "PCI: IRQ %i for device %s doesn't match PIRQ mask - try pci=usepirqmask\n" - KERN_DEBUG, newirq, - pci_name(dev)); + dev_warn(&dev->dev, "IRQ %d doesn't match PIRQ mask " + "%#x; try pci=usepirqmask\n", newirq, mask); } if (!newirq && assign) { for (i = 0; i < 16; i++) { @@ -944,39 +941,35 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) newirq = i; } } - DBG(" -> newirq=%d", newirq); + dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + pin, newirq); /* Check if it is hardcoded */ if ((pirq & 0xf0) == 0xf0) { irq = pirq & 0xf; - DBG(" -> hardcoded IRQ %d\n", irq); - msg = "Hardcoded"; + msg = "hardcoded"; } else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) { - DBG(" -> got IRQ %d\n", irq); - msg = "Found"; + msg = "found"; eisa_set_level_irq(irq); } else if (newirq && r->set && (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { - DBG(" -> assigning IRQ %d", newirq); if (r->set(pirq_router_dev, dev, pirq, newirq)) { eisa_set_level_irq(newirq); - DBG(" ... OK\n"); - msg = "Assigned"; + msg = "assigned"; irq = newirq; } } if (!irq) { - DBG(" ... failed\n"); if (newirq && mask == (1 << newirq)) { - msg = "Guessed"; + msg = "guessed"; irq = newirq; - } else + } else { + dev_dbg(&dev->dev, "can't route interrupt\n"); return 0; + } } - printk(KERN_INFO "PCI: %s IRQ %d for device %s\n", msg, irq, - pci_name(dev)); + dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin, irq); /* Update IRQ for all devices with the same pirq value */ while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) { @@ -996,17 +989,17 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) (!(pci_probe & PCI_USE_PIRQ_MASK) || \ ((1 << dev2->irq) & mask))) { #ifndef CONFIG_PCI_MSI - printk(KERN_INFO "IRQ routing conflict for %s, have irq %d, want irq %d\n", - pci_name(dev2), dev2->irq, irq); + dev_info(&dev2->dev, "IRQ routing conflict: " + "have IRQ %d, want IRQ %d\n", + dev2->irq, irq); #endif continue; } dev2->irq = irq; pirq_penalty[irq]++; if (dev != dev2) - printk(KERN_INFO - "PCI: Sharing IRQ %d with %s\n", - irq, pci_name(dev2)); + dev_info(&dev->dev, "sharing IRQ %d with %s\n", + irq, pci_name(dev2)); } } return 1; @@ -1025,8 +1018,7 @@ static void __init pcibios_fixup_irqs(void) * already in use. */ if (dev->irq >= 16) { - DBG(KERN_DEBUG "%s: ignoring bogus IRQ %d\n", - pci_name(dev), dev->irq); + dev_dbg(&dev->dev, "ignoring bogus IRQ %d\n", dev->irq); dev->irq = 0; } /* @@ -1070,12 +1062,12 @@ static void __init pcibios_fixup_irqs(void) irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, PCI_SLOT(bridge->devfn), pin); if (irq >= 0) - printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n", - pci_name(bridge), 'A' + pin, irq); + dev_warn(&dev->dev, "using bridge %s INT %c to get IRQ %d\n", + pci_name(bridge), + 'A' + pin, irq); } if (irq >= 0) { - printk(KERN_INFO "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", - pci_name(dev), 'A' + pin, irq); + dev_info(&dev->dev, "PCI->APIC IRQ transform: INT %c -> IRQ %d\n", 'A' + pin, irq); dev->irq = irq; } } @@ -1231,25 +1223,24 @@ static int pirq_enable_irq(struct pci_dev *dev) irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, PCI_SLOT(bridge->devfn), pin); if (irq >= 0) - printk(KERN_WARNING - "PCI: using PPB %s[%c] to get irq %d\n", - pci_name(bridge), - 'A' + pin, irq); + dev_warn(&dev->dev, "using bridge %s " + "INT %c to get IRQ %d\n", + pci_name(bridge), 'A' + pin, + irq); dev = bridge; } dev = temp_dev; if (irq >= 0) { - printk(KERN_INFO - "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", - pci_name(dev), 'A' + pin, irq); + dev_info(&dev->dev, "PCI->APIC IRQ transform: " + "INT %c -> IRQ %d\n", 'A' + pin, irq); dev->irq = irq; return 0; } else - msg = " Probably buggy MP table."; + msg = "; probably buggy MP table"; } else if (pci_probe & PCI_BIOS_IRQ_SCAN) msg = ""; else - msg = " Please try using pci=biosirq."; + msg = "; please try using pci=biosirq"; /* * With IDE legacy devices the IRQ lookup failure is not @@ -1259,9 +1250,8 @@ static int pirq_enable_irq(struct pci_dev *dev) !(dev->class & 0x5)) return 0; - printk(KERN_WARNING - "PCI: No IRQ known for interrupt pin %c of device %s.%s\n", - 'A' + pin, pci_name(dev), msg); + dev_warn(&dev->dev, "can't find IRQ for PCI INT %c%s\n", + 'A' + pin, msg); } return 0; } diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c index f4b16dc..1177845 100644 --- a/arch/x86/pci/numaq_32.c +++ b/arch/x86/pci/numaq_32.c @@ -131,13 +131,14 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d) u8 busno, suba, subb; int quad = BUS2QUAD(d->bus->number); - printk("PCI: Searching for i450NX host bridges on %s\n", pci_name(d)); + dev_info(&d->dev, "searching for i450NX host bridges\n"); reg = 0xd0; for(pxb=0; pxb<2; pxb++) { pci_read_config_byte(d, reg++, &busno); pci_read_config_byte(d, reg++, &suba); pci_read_config_byte(d, reg++, &subb); - DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb); + dev_dbg(&d->dev, "i450NX PXB %d: %02x/%02x/%02x\n", + pxb, busno, suba, subb); if (busno) { /* Bus A */ pci_scan_bus_with_sysdata(QUADLOCAL2BUS(quad, busno)); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index e693812..d8faf79 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -367,7 +367,7 @@ static void xen_send_IPI_mask(cpumask_t mask, enum ipi_vector vector) cpus_and(mask, mask, cpu_online_map); - for_each_cpu_mask(cpu, mask) + for_each_cpu_mask_nr(cpu, mask) xen_send_IPI_one(cpu, vector); } @@ -378,7 +378,7 @@ static void xen_smp_send_call_function_ipi(cpumask_t mask) xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR); /* Make sure other vcpus get a chance to run if they need to. */ - for_each_cpu_mask(cpu, mask) { + for_each_cpu_mask_nr(cpu, mask) { if (xen_vcpu_stolen(cpu)) { HYPERVISOR_sched_op(SCHEDOP_yield, 0); break; diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 4038cbf..7f58304 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -173,7 +173,7 @@ ENTRY(xen_sysexit) pushq $__USER32_CS pushq %rdx - pushq $VGCF_in_syscall + pushq $0 1: jmp hypercall_iret ENDPATCH(xen_sysexit) RELOC(xen_sysexit, 1b+1) |
