summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig3
-rw-r--r--arch/x86/Kconfig.cpu2
-rw-r--r--arch/x86/boot/compressed/misc.c39
-rw-r--r--arch/x86/ia32/ia32entry.S97
-rw-r--r--arch/x86/ia32/sys_ia32.c2
-rw-r--r--arch/x86/kernel/acpi/cstate.c3
-rw-r--r--arch/x86/kernel/acpi/sleep.c4
-rw-r--r--arch/x86/kernel/apm_32.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c16
-rw-r--r--arch/x86/kernel/cpu/cpufreq/p4-clockmod.c6
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k8.c23
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c157
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-ich.c7
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c5
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_64.c20
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd_64.c4
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c1
-rw-r--r--arch/x86/kernel/cpu/proc.c2
-rw-r--r--arch/x86/kernel/cpuid.c4
-rw-r--r--arch/x86/kernel/entry_32.S55
-rw-r--r--arch/x86/kernel/entry_64.S55
-rw-r--r--arch/x86/kernel/genapic_flat_64.c2
-rw-r--r--arch/x86/kernel/genx2apic_uv_x.c4
-rw-r--r--arch/x86/kernel/hpet.c10
-rw-r--r--arch/x86/kernel/io_apic_64.c12
-rw-r--r--arch/x86/kernel/irqinit_64.c5
-rw-r--r--arch/x86/kernel/kprobes.c6
-rw-r--r--arch/x86/kernel/ldt.c6
-rw-r--r--arch/x86/kernel/microcode.c23
-rw-r--r--arch/x86/kernel/module_64.c1
-rw-r--r--arch/x86/kernel/msr.c4
-rw-r--r--arch/x86/kernel/paravirt.c2
-rw-r--r--arch/x86/kernel/pci-calgary_64.c85
-rw-r--r--arch/x86/kernel/pci-dma.c6
-rw-r--r--arch/x86/kernel/pci-gart_64.c4
-rw-r--r--arch/x86/kernel/process_32.c2
-rw-r--r--arch/x86/kernel/process_64.c2
-rw-r--r--arch/x86/kernel/reboot.c14
-rw-r--r--arch/x86/kernel/setup.c7
-rw-r--r--arch/x86/kernel/signal_32.c3
-rw-r--r--arch/x86/kernel/signal_64.c56
-rw-r--r--arch/x86/kernel/smpboot.c8
-rw-r--r--arch/x86/kernel/syscall_table_32.S6
-rw-r--r--arch/x86/mach-es7000/es7000plat.c8
-rw-r--r--arch/x86/mm/discontig_32.c3
-rw-r--r--arch/x86/mm/dump_pagetables.c10
-rw-r--r--arch/x86/mm/hugetlbpage.c78
-rw-r--r--arch/x86/mm/ioremap.c8
-rw-r--r--arch/x86/mm/numa_64.c4
-rw-r--r--arch/x86/oprofile/nmi_int.c36
-rw-r--r--arch/x86/pci/i386.c1
-rw-r--r--arch/x86/xen/enlighten.c2
-rw-r--r--arch/x86/xen/mmu.c8
-rw-r--r--arch/x86/xen/smp.c4
-rw-r--r--arch/x86/xen/xen-asm_64.S2
55 files changed, 676 insertions, 262 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 03980cb04291..e3cba0b45600 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -21,12 +21,15 @@ 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 if !X86_RDC321X
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_EFFICIENT_UNALIGNED_ACCESS
config ARCH_DEFCONFIG
string
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 54b8c02c71e6..2c518fbc52ec 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -414,4 +414,4 @@ config X86_MINIMUM_CPU_FAMILY
config X86_DEBUGCTLMSR
def_bool y
- depends on !(M586MMX || M586TSC || M586 || M486 || M386)
+ depends on !(MK6 || MWINCHIPC6 || MWINCHIP2 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386)
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 3ee338c7d1d1..aaf5a2131efc 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/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 23d146ce676b..ffc1bb4fed7d 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 f00afdf61e67..d3c64088b981 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/cstate.c b/arch/x86/kernel/acpi/cstate.c
index c2502eb9aa83..9220cf46aa10 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -73,6 +73,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
struct cpuinfo_x86 *c = &cpu_data(cpu);
cpumask_t saved_mask;
+ cpumask_of_cpu_ptr(new_mask, cpu);
int retval;
unsigned int eax, ebx, ecx, edx;
unsigned int edx_part;
@@ -91,7 +92,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
/* Make sure we are running on right CPU */
saved_mask = current->cpus_allowed;
- retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ retval = set_cpus_allowed_ptr(current, new_mask);
if (retval)
return -1;
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index a3ddad18aaa3..fa2161d5003b 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/apm_32.c b/arch/x86/kernel/apm_32.c
index bf9b441331e9..9ee24e6bc4b0 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/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index b0c8208df9fa..ff2fff56f0a8 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -200,10 +200,12 @@ static void drv_read(struct drv_cmd *cmd)
static void drv_write(struct drv_cmd *cmd)
{
cpumask_t saved_mask = current->cpus_allowed;
+ cpumask_of_cpu_ptr_declare(cpu_mask);
unsigned int i;
- for_each_cpu_mask(i, cmd->mask) {
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(i));
+ for_each_cpu_mask_nr(i, cmd->mask) {
+ cpumask_of_cpu_ptr_next(cpu_mask, i);
+ set_cpus_allowed_ptr(current, cpu_mask);
do_drv_write(cmd);
}
@@ -267,11 +269,12 @@ static unsigned int get_measured_perf(unsigned int cpu)
} aperf_cur, mperf_cur;
cpumask_t saved_mask;
+ cpumask_of_cpu_ptr(cpu_mask, cpu);
unsigned int perf_percent;
unsigned int retval;
saved_mask = current->cpus_allowed;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ set_cpus_allowed_ptr(current, cpu_mask);
if (get_cpu() != cpu) {
/* We were not able to run on requested processor */
put_cpu();
@@ -337,6 +340,7 @@ static unsigned int get_measured_perf(unsigned int cpu)
static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
{
+ cpumask_of_cpu_ptr(cpu_mask, cpu);
struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu);
unsigned int freq;
unsigned int cached_freq;
@@ -349,7 +353,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
}
cached_freq = data->freq_table[data->acpi_data->state].frequency;
- freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data);
+ freq = extract_freq(get_cur_val(cpu_mask), data);
if (freq != cached_freq) {
/*
* The dreaded BIOS frequency change behind our back.
@@ -451,7 +455,7 @@ 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 +470,7 @@ 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/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 199e4e05e5dc..f1685fb91fbd 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 206791eb46e3..53c7b6936973 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -479,11 +479,12 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvi
static int check_supported_cpu(unsigned int cpu)
{
cpumask_t oldmask;
+ cpumask_of_cpu_ptr(cpu_mask, cpu);
u32 eax, ebx, ecx, edx;
unsigned int rc = 0;
oldmask = current->cpus_allowed;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ set_cpus_allowed_ptr(current, cpu_mask);
if (smp_processor_id() != cpu) {
printk(KERN_ERR PFX "limiting to cpu %u failed\n", cpu);
@@ -966,7 +967,7 @@ 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 +975,7 @@ 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 +998,7 @@ 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 +1006,7 @@ 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);
}
@@ -1016,6 +1017,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i
static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsigned relation)
{
cpumask_t oldmask;
+ cpumask_of_cpu_ptr(cpu_mask, pol->cpu);
struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
u32 checkfid;
u32 checkvid;
@@ -1030,7 +1032,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
/* only run on specific CPU from here on */
oldmask = current->cpus_allowed;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu));
+ set_cpus_allowed_ptr(current, cpu_mask);
if (smp_processor_id() != pol->cpu) {
printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu);
@@ -1105,6 +1107,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
{
struct powernow_k8_data *data;
cpumask_t oldmask;
+ cpumask_of_cpu_ptr_declare(newmask);
int rc;
if (!cpu_online(pol->cpu))
@@ -1156,7 +1159,8 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
/* only run on specific CPU from here on */
oldmask = current->cpus_allowed;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu));
+ cpumask_of_cpu_ptr_next(newmask, pol->cpu);
+ set_cpus_allowed_ptr(current, newmask);
if (smp_processor_id() != pol->cpu) {
printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu);
@@ -1178,7 +1182,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
set_cpus_allowed_ptr(current, &oldmask);
if (cpu_family == CPU_HW_PSTATE)
- pol->cpus = cpumask_of_cpu(pol->cpu);
+ pol->cpus = *newmask;
else
pol->cpus = per_cpu(cpu_core_map, pol->cpu);
data->available_cores = &(pol->cpus);
@@ -1244,6 +1248,7 @@ static unsigned int powernowk8_get (unsigned int cpu)
{
struct powernow_k8_data *data;
cpumask_t oldmask = current->cpus_allowed;
+ cpumask_of_cpu_ptr(newmask, cpu);
unsigned int khz = 0;
unsigned int first;
@@ -1253,7 +1258,7 @@ static unsigned int powernowk8_get (unsigned int cpu)
if (!data)
return -EINVAL;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ set_cpus_allowed_ptr(current, newmask);
if (smp_processor_id() != cpu) {
printk(KERN_ERR PFX
"limiting to CPU %d failed in powernowk8_get\n", cpu);
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index 908dd347c67e..ca2ac13b7af2 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;
}
@@ -313,9 +324,10 @@ static unsigned int get_cur_freq(unsigned int cpu)
unsigned l, h;
unsigned clock_freq;
cpumask_t saved_mask;
+ cpumask_of_cpu_ptr(new_mask, cpu);
saved_mask = current->cpus_allowed;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ set_cpus_allowed_ptr(current, new_mask);
if (smp_processor_id() != cpu)
return 0;
@@ -347,7 +359,8 @@ 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 +374,9 @@ 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 +399,26 @@ 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 +427,12 @@ 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 +446,26 @@ 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 +473,55 @@ 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 +532,7 @@ 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 +549,7 @@ 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 +568,11 @@ 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);
}
@@ -553,10 +585,12 @@ static int centrino_target (struct cpufreq_policy *policy,
* Best effort undo..
*/
- if (!cpus_empty(covered_cpus)) {
- for_each_cpu_mask(j, covered_cpus) {
- set_cpus_allowed_ptr(current,
- &cpumask_of_cpu(j));
+ if (!cpus_empty(*covered_cpus)) {
+ cpumask_of_cpu_ptr_declare(new_mask);
+
+ for_each_cpu_mask_nr(j, *covered_cpus) {
+ cpumask_of_cpu_ptr_next(new_mask, j);
+ set_cpus_allowed_ptr(current, new_mask);
wrmsr(MSR_IA32_PERF_CTL, oldmsr, h);
}
}
@@ -564,19 +598,22 @@ static int centrino_target (struct cpufreq_policy *policy,
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 1b50244b1fdf..2f3728dc24f6 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -244,7 +244,8 @@ static unsigned int _speedstep_get(const cpumask_t *cpus)
static unsigned int speedstep_get(unsigned int cpu)
{
- return _speedstep_get(&cpumask_of_cpu(cpu));
+ cpumask_of_cpu_ptr(newmask, cpu);
+ return _speedstep_get(newmask);
}
/**
@@ -279,7 +280,7 @@ 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 +293,7 @@ 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 ff517f0b8cc4..650d40f7912b 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);
}
@@ -516,6 +516,7 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
unsigned long j;
int retval;
cpumask_t oldmask;
+ cpumask_of_cpu_ptr(newmask, cpu);
if (num_cache_leaves == 0)
return -ENOENT;
@@ -526,7 +527,7 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
return -ENOMEM;
oldmask = current->cpus_allowed;
- retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ retval = set_cpus_allowed_ptr(current, newmask);
if (retval)
goto out;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index c4a7ec31394c..65a339678ece 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;
@@ -762,10 +762,14 @@ DEFINE_PER_CPU(struct sys_device, device_mce);
/* Why are there no generic functions for this? */
#define ACCESSOR(name, var, start) \
- static ssize_t show_ ## name(struct sys_device *s, char *buf) { \
+ static ssize_t show_ ## name(struct sys_device *s, \
+ struct sysdev_attribute *attr, \
+ char *buf) { \
return sprintf(buf, "%lx\n", (unsigned long)var); \
} \
- static ssize_t set_ ## name(struct sys_device *s,const char *buf,size_t siz) { \
+ static ssize_t set_ ## name(struct sys_device *s, \
+ struct sysdev_attribute *attr, \
+ const char *buf, size_t siz) { \
char *end; \
unsigned long new = simple_strtoul(buf, &end, 0); \
if (end == buf) return -EINVAL; \
@@ -786,14 +790,16 @@ ACCESSOR(bank3ctl,bank[3],mce_restart())
ACCESSOR(bank4ctl,bank[4],mce_restart())
ACCESSOR(bank5ctl,bank[5],mce_restart())
-static ssize_t show_trigger(struct sys_device *s, char *buf)
+static ssize_t show_trigger(struct sys_device *s, struct sysdev_attribute *attr,
+ char *buf)
{
strcpy(buf, trigger);
strcat(buf, "\n");
return strlen(trigger) + 1;
}
-static ssize_t set_trigger(struct sys_device *s,const char *buf,size_t siz)
+static ssize_t set_trigger(struct sys_device *s, struct sysdev_attribute *attr,
+ const char *buf,size_t siz)
{
char *p;
int len;
@@ -806,12 +812,12 @@ static ssize_t set_trigger(struct sys_device *s,const char *buf,size_t siz)
}
static SYSDEV_ATTR(trigger, 0644, show_trigger, set_trigger);
-ACCESSOR(tolerant,tolerant,)
+static SYSDEV_INT_ATTR(tolerant, 0644, tolerant);
ACCESSOR(check_interval,check_interval,mce_restart())
static struct sysdev_attribute *mce_attributes[] = {
&attr_bank0ctl, &attr_bank1ctl, &attr_bank2ctl,
&attr_bank3ctl, &attr_bank4ctl, &attr_bank5ctl,
- &attr_tolerant, &attr_check_interval, &attr_trigger,
+ &attr_tolerant.attr, &attr_check_interval, &attr_trigger,
NULL
};
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 7c9a813e1193..88736cadbaa6 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/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 1f4cc48c14c6..d5ae2243f0b9 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -35,6 +35,7 @@ atomic_t therm_throt_en = ATOMIC_INIT(0);
#define define_therm_throt_sysdev_show_func(name) \
static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev, \
+ struct sysdev_attribute *attr, \
char *buf) \
{ \
unsigned int cpu = dev->id; \
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 0d0d9057e7c0..a26c480b9491 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/cpuid.c b/arch/x86/kernel/cpuid.c
index 2de5fa2bbf77..14b11b3be31c 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -141,8 +141,8 @@ static __cpuinit int cpuid_device_create(int cpu)
{
struct device *dev;
- dev = device_create(cpuid_class, NULL, MKDEV(CPUID_MAJOR, cpu),
- "cpu%d", cpu);
+ dev = device_create_drvdata(cpuid_class, NULL, MKDEV(CPUID_MAJOR, cpu),
+ NULL, "cpu%d", cpu);
return IS_ERR(dev) ? PTR_ERR(dev) : 0;
}
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index cdfd94cc6b14..109792bc7cfa 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 8410e26f4183..89434d439605 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_flat_64.c b/arch/x86/kernel/genapic_flat_64.c
index 1a9c68845ee8..786548a62d38 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 3c3929340692..2cfcbded888a 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/hpet.c b/arch/x86/kernel/hpet.c
index 0ea6a19bfdfe..ad2b15a1334d 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_64.c b/arch/x86/kernel/io_apic_64.c
index 64a46affd858..8269434d1707 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -732,7 +732,7 @@ 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 +753,7 @@ 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 +763,7 @@ 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;
@@ -795,7 +795,7 @@ 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;
@@ -1373,12 +1373,10 @@ 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 0373e88de95a..1f26fd9ec4f4 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 43c019f85f0d..6c27679ec6aa 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 a8449571858a..3fee2aa50f3f 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -62,12 +62,12 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
if (reload) {
#ifdef CONFIG_SMP
- cpumask_t mask;
+ cpumask_of_cpu_ptr_declare(mask);
preempt_disable();
load_LDT(pc);
- mask = cpumask_of_cpu(smp_processor_id());
- if (!cpus_equal(current->mm->cpu_vm_mask, mask))
+ cpumask_of_cpu_ptr_next(mask, smp_processor_id());
+ if (!cpus_equal(current->mm->cpu_vm_mask, *mask))
smp_call_function(flush_ldt, current->mm, 1);
preempt_enable();
#else
diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c
index 56b933119a04..6994c751590e 100644
--- a/arch/x86/kernel/microcode.c
+++ b/arch/x86/kernel/microcode.c
@@ -388,6 +388,7 @@ static int do_microcode_update (void)
void *new_mc = NULL;
int cpu;
cpumask_t old;
+ cpumask_of_cpu_ptr_declare(newmask);
old = current->cpus_allowed;
@@ -404,7 +405,8 @@ static int do_microcode_update (void)
if (!uci->valid)
continue;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ cpumask_of_cpu_ptr_next(newmask, cpu);
+ set_cpus_allowed_ptr(current, newmask);
error = get_maching_microcode(new_mc, cpu);
if (error < 0)
goto out;
@@ -574,6 +576,7 @@ static int apply_microcode_check_cpu(int cpu)
struct cpuinfo_x86 *c = &cpu_data(cpu);
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
cpumask_t old;
+ cpumask_of_cpu_ptr(newmask, cpu);
unsigned int val[2];
int err = 0;
@@ -582,7 +585,7 @@ static int apply_microcode_check_cpu(int cpu)
return 0;
old = current->cpus_allowed;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ set_cpus_allowed_ptr(current, newmask);
/* Check if the microcode we have in memory matches the CPU */
if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
@@ -620,11 +623,12 @@ static int apply_microcode_check_cpu(int cpu)
static void microcode_init_cpu(int cpu, int resume)
{
cpumask_t old;
+ cpumask_of_cpu_ptr(newmask, cpu);
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
old = current->cpus_allowed;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ set_cpus_allowed_ptr(current, newmask);
mutex_lock(&microcode_mutex);
collect_cpu_info(cpu);
if (uci->valid && system_state == SYSTEM_RUNNING && !resume)
@@ -644,7 +648,9 @@ static void microcode_fini_cpu(int cpu)
mutex_unlock(&microcode_mutex);
}
-static ssize_t reload_store(struct sys_device *dev, const char *buf, size_t sz)
+static ssize_t reload_store(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ const char *buf, size_t sz)
{
struct ucode_cpu_info *uci = ucode_cpu_info + dev->id;
char *end;
@@ -656,11 +662,12 @@ static ssize_t reload_store(struct sys_device *dev, const char *buf, size_t sz)
return -EINVAL;
if (val == 1) {
cpumask_t old;
+ cpumask_of_cpu_ptr(newmask, cpu);
old = current->cpus_allowed;
get_online_cpus();
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+ set_cpus_allowed_ptr(current, newmask);
mutex_lock(&microcode_mutex);
if (uci->valid)
@@ -674,14 +681,16 @@ static ssize_t reload_store(struct sys_device *dev, const char *buf, size_t sz)
return sz;
}
-static ssize_t version_show(struct sys_device *dev, char *buf)
+static ssize_t version_show(struct sys_device *dev,
+ struct sysdev_attribute *attr, char *buf)
{
struct ucode_cpu_info *uci = ucode_cpu_info + dev->id;
return sprintf(buf, "0x%x\n", uci->rev);
}
-static ssize_t pf_show(struct sys_device *dev, char *buf)
+static ssize_t pf_show(struct sys_device *dev,
+ struct sysdev_attribute *attr, char *buf)
{
struct ucode_cpu_info *uci = ucode_cpu_info + dev->id;
diff --git a/arch/x86/kernel/module_64.c b/arch/x86/kernel/module_64.c
index 0e867676b5a5..6ba87830d4b1 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/msr.c b/arch/x86/kernel/msr.c
index a153b3905f60..9fd809552447 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -149,8 +149,8 @@ static int __cpuinit msr_device_create(int cpu)
{
struct device *dev;
- dev = device_create(msr_class, NULL, MKDEV(MSR_MAJOR, cpu),
- "msr%d", cpu);
+ dev = device_create_drvdata(msr_class, NULL, MKDEV(MSR_MAJOR, cpu),
+ NULL, "msr%d", cpu);
return IS_ERR(dev) ? PTR_ERR(dev) : 0;
}
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 097d8a6797fa..94da4d52d798 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -443,7 +443,7 @@ struct pv_mmu_ops pv_mmu_ops = {
#endif /* PAGETABLE_LEVELS >= 3 */
.pte_val = native_pte_val,
- .pte_flags = native_pte_val,
+ .pte_flags = native_pte_flags,
.pgd_val = native_pgd_val,
.make_pte = native_make_pte,
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 151f2d171f7c..19e7fc7c2c4f 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>
@@ -167,6 +168,8 @@ 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,
@@ -830,7 +833,11 @@ 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 +1216,10 @@ 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)
@@ -1339,6 +1350,61 @@ 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()
+{
+ 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 +1460,8 @@ 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 +1479,16 @@ 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;
}
}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index a4213c00dffc..cbecb05551bb 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -314,8 +314,7 @@ int dma_supported(struct device *dev, u64 mask)
{
#ifdef CONFIG_PCI
if (mask > 0xffffffff && forbid_dac > 0) {
- printk(KERN_INFO "PCI: Disallowing DAC for device %s\n",
- dev->bus_id);
+ dev_info(dev, "PCI: Disallowing DAC for device\n");
return 0;
}
#endif
@@ -342,8 +341,7 @@ int dma_supported(struct device *dev, u64 mask)
type. Normally this doesn't make any difference, but gives
more gentle handling of IOMMU overflow. */
if (iommu_sac_force && (mask >= DMA_40BIT_MASK)) {
- printk(KERN_INFO "%s: Force SAC with mask %Lx\n",
- dev->bus_id, mask);
+ dev_info(dev, "Force SAC with mask %Lx\n", mask);
return 0;
}
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index be60961f8695..df5f142657d2 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -198,9 +198,7 @@ static void iommu_full(struct device *dev, size_t size, int dir)
* out. Hopefully no network devices use single mappings that big.
*/
- printk(KERN_ERR
- "PCI-DMA: Out of IOMMU space for %lu bytes at device %s\n",
- size, dev->bus_id);
+ dev_err(dev, "PCI-DMA: Out of IOMMU space for %lu bytes\n", size);
if (size > PAGE_SIZE*EMERGENCY_PAGES) {
if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0c3927accb00..53bc653ed5ca 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 e8a8e1b99817..3fb62a7d9a16 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 9dcf39c02972..06a9f643817e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -411,24 +411,28 @@ 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;
+ cpumask_of_cpu_ptr(newmask, reboot_cpu_id);
#ifdef CONFIG_X86_32
/* See if there has been given a command line override */
if ((reboot_cpu != -1) && (reboot_cpu < NR_CPUS) &&
- cpu_online(reboot_cpu))
+ cpu_online(reboot_cpu)) {
reboot_cpu_id = reboot_cpu;
+ cpumask_of_cpu_ptr_next(newmask, reboot_cpu_id);
+ }
#endif
/* Make certain the cpu I'm about to reboot on is online */
- if (!cpu_online(reboot_cpu_id))
+ if (!cpu_online(reboot_cpu_id)) {
reboot_cpu_id = smp_processor_id();
+ cpumask_of_cpu_ptr_next(newmask, reboot_cpu_id);
+ }
/* Make certain I only run on the appropriate processor */
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(reboot_cpu_id));
+ set_cpus_allowed_ptr(current, newmask);
/* O.K Now that I'm on the appropriate processor,
* stop all of the others.
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ec952aa5394a..b520dae02bf4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -597,11 +597,11 @@ 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();
ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
@@ -665,9 +665,6 @@ 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;
@@ -680,7 +677,7 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_X86_LOCAL_APIC
disable_apic = 1;
#endif
- clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+ setup_clear_cpu_cap(X86_FEATURE_APIC);
}
#ifdef CONFIG_PCI
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 07faaa5109cb..6fb5bcdd8933 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 bf87684474f1..b45ef8ddd651 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 4b53a647bc0a..332512767f4f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -438,7 +438,7 @@ 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 +461,7 @@ 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);
@@ -1219,7 +1219,7 @@ 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 +1228,7 @@ 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));
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index adff5562f5fd..d44395ff34c3 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/mach-es7000/es7000plat.c b/arch/x86/mach-es7000/es7000plat.c
index 4354ce804889..50189af14b85 100644
--- a/arch/x86/mach-es7000/es7000plat.c
+++ b/arch/x86/mach-es7000/es7000plat.c
@@ -130,10 +130,10 @@ parse_unisys_oem (char *oemptr)
mip_addr = val;
mip = (struct mip_reg *)val;
mip_reg = __va(mip);
- Dprintk("es7000_mipcfg: host_reg = 0x%lx \n",
- (unsigned long)host_reg);
- Dprintk("es7000_mipcfg: mip_reg = 0x%lx \n",
- (unsigned long)mip_reg);
+ pr_debug("es7000_mipcfg: host_reg = 0x%lx \n",
+ (unsigned long)host_reg);
+ pr_debug("es7000_mipcfg: mip_reg = 0x%lx \n",
+ (unsigned long)mip_reg);
success++;
break;
case MIP_PSAI_REG:
diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c
index 5dfef9fa061a..62fa440678d8 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/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0bb0caed8971..a20d1fa64b4e 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -148,8 +148,8 @@ static void note_page(struct seq_file *m, struct pg_state *st,
* we have now. "break" is either changing perms, levels or
* address space marker.
*/
- prot = pgprot_val(new_prot) & ~(PTE_MASK);
- cur = pgprot_val(st->current_prot) & ~(PTE_MASK);
+ prot = pgprot_val(new_prot) & ~(PTE_PFN_MASK);
+ cur = pgprot_val(st->current_prot) & ~(PTE_PFN_MASK);
if (!st->level) {
/* First entry */
@@ -221,7 +221,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
for (i = 0; i < PTRS_PER_PMD; i++) {
st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT);
if (!pmd_none(*start)) {
- pgprotval_t prot = pmd_val(*start) & ~PTE_MASK;
+ pgprotval_t prot = pmd_val(*start) & PTE_FLAGS_MASK;
if (pmd_large(*start) || !pmd_present(*start))
note_page(m, st, __pgprot(prot), 3);
@@ -253,7 +253,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
for (i = 0; i < PTRS_PER_PUD; i++) {
st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
if (!pud_none(*start)) {
- pgprotval_t prot = pud_val(*start) & ~PTE_MASK;
+ pgprotval_t prot = pud_val(*start) & PTE_FLAGS_MASK;
if (pud_large(*start) || !pud_present(*start))
note_page(m, st, __pgprot(prot), 2);
@@ -288,7 +288,7 @@ static void walk_pgd_level(struct seq_file *m)
for (i = 0; i < PTRS_PER_PGD; i++) {
st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
if (!pgd_none(*start)) {
- pgprotval_t prot = pgd_val(*start) & ~PTE_MASK;
+ pgprotval_t prot = pgd_val(*start) & PTE_FLAGS_MASK;
if (pgd_large(*start) || !pgd_present(*start))
note_page(m, &st, __pgprot(prot), 1);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 0b3d567e686d..8f307d914c2e 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/ioremap.c b/arch/x86/mm/ioremap.c
index 24c1d3c30186..016f335bbeea 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 9782f42dd319..a4dd793d6003 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/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 7f3329b55d2e..3f90289410e6 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/i386.c b/arch/x86/pci/i386.c
index 2aafb67dc5f1..a09505806b82 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -280,6 +280,7 @@ 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/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 194bbd6e3241..9ff6e3cbf08f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1435,7 +1435,7 @@ static unsigned long m2p(phys_addr_t maddr)
{
phys_addr_t paddr;
- maddr &= PTE_MASK;
+ maddr &= PTE_PFN_MASK;
paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
return paddr;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index a44d56e38bd1..aa37469da696 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -343,8 +343,8 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
static pteval_t pte_mfn_to_pfn(pteval_t val)
{
if (val & _PAGE_PRESENT) {
- unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT;
- pteval_t flags = val & ~PTE_MASK;
+ unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+ pteval_t flags = val & PTE_FLAGS_MASK;
val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
}
@@ -354,8 +354,8 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
static pteval_t pte_pfn_to_mfn(pteval_t val)
{
if (val & _PAGE_PRESENT) {
- unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT;
- pteval_t flags = val & ~PTE_MASK;
+ unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+ pteval_t flags = val & PTE_FLAGS_MASK;
val = ((pteval_t)pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
}
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index e693812ac59a..d8faf79a0a1d 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 4038cbfe3331..7f58304fafb3 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)