summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/cpu/perf_event.c21
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c216
-rw-r--r--arch/x86/kernel/dumpstack_32.c6
-rw-r--r--arch/x86/kernel/dumpstack_64.c8
-rw-r--r--arch/x86/kernel/irq_32.c12
-rw-r--r--arch/x86/kernel/ptrace.c17
-rw-r--r--arch/x86/kernel/reboot.c2
-rw-r--r--arch/x86/kernel/smp.c15
-rw-r--r--arch/x86/kernel/smpboot.c1
9 files changed, 187 insertions, 111 deletions
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c1e8c7a51164..ed6310183efb 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -237,6 +237,7 @@ struct x86_pmu {
* Intel DebugStore bits
*/
int bts, pebs;
+ int bts_active, pebs_active;
int pebs_record_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
@@ -380,7 +381,7 @@ static void release_pmc_hardware(void) {}
#endif
-static int reserve_ds_buffers(void);
+static void reserve_ds_buffers(void);
static void release_ds_buffers(void);
static void hw_perf_event_destroy(struct perf_event *event)
@@ -477,7 +478,7 @@ static int x86_setup_perfctr(struct perf_event *event)
if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
(hwc->sample_period == 1)) {
/* BTS is not supported by this architecture. */
- if (!x86_pmu.bts)
+ if (!x86_pmu.bts_active)
return -EOPNOTSUPP;
/* BTS is currently only allowed for user-mode. */
@@ -496,12 +497,13 @@ static int x86_pmu_hw_config(struct perf_event *event)
int precise = 0;
/* Support for constant skid */
- if (x86_pmu.pebs)
+ if (x86_pmu.pebs_active) {
precise++;
- /* Support for IP fixup */
- if (x86_pmu.lbr_nr)
- precise++;
+ /* Support for IP fixup */
+ if (x86_pmu.lbr_nr)
+ precise++;
+ }
if (event->attr.precise_ip > precise)
return -EOPNOTSUPP;
@@ -543,11 +545,8 @@ static int __x86_pmu_event_init(struct perf_event *event)
if (atomic_read(&active_events) == 0) {
if (!reserve_pmc_hardware())
err = -EBUSY;
- else {
- err = reserve_ds_buffers();
- if (err)
- release_pmc_hardware();
- }
+ else
+ reserve_ds_buffers();
}
if (!err)
atomic_inc(&active_events);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 4977f9c400e5..b7dcd9f2b8a0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -74,6 +74,107 @@ static void fini_debug_store_on_cpu(int cpu)
wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
}
+static int alloc_pebs_buffer(int cpu)
+{
+ struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ int node = cpu_to_node(cpu);
+ int max, thresh = 1; /* always use a single PEBS record */
+ void *buffer;
+
+ if (!x86_pmu.pebs)
+ return 0;
+
+ buffer = kmalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+ if (unlikely(!buffer))
+ return -ENOMEM;
+
+ max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+
+ ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+ ds->pebs_index = ds->pebs_buffer_base;
+ ds->pebs_absolute_maximum = ds->pebs_buffer_base +
+ max * x86_pmu.pebs_record_size;
+
+ ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
+ thresh * x86_pmu.pebs_record_size;
+
+ return 0;
+}
+
+static void release_pebs_buffer(int cpu)
+{
+ struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+ if (!ds || !x86_pmu.pebs)
+ return;
+
+ kfree((void *)(unsigned long)ds->pebs_buffer_base);
+ ds->pebs_buffer_base = 0;
+}
+
+static int alloc_bts_buffer(int cpu)
+{
+ struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ int node = cpu_to_node(cpu);
+ int max, thresh;
+ void *buffer;
+
+ if (!x86_pmu.bts)
+ return 0;
+
+ buffer = kmalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+ if (unlikely(!buffer))
+ return -ENOMEM;
+
+ max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+ thresh = max / 16;
+
+ ds->bts_buffer_base = (u64)(unsigned long)buffer;
+ ds->bts_index = ds->bts_buffer_base;
+ ds->bts_absolute_maximum = ds->bts_buffer_base +
+ max * BTS_RECORD_SIZE;
+ ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+ thresh * BTS_RECORD_SIZE;
+
+ return 0;
+}
+
+static void release_bts_buffer(int cpu)
+{
+ struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+ if (!ds || !x86_pmu.bts)
+ return;
+
+ kfree((void *)(unsigned long)ds->bts_buffer_base);
+ ds->bts_buffer_base = 0;
+}
+
+static int alloc_ds_buffer(int cpu)
+{
+ int node = cpu_to_node(cpu);
+ struct debug_store *ds;
+
+ ds = kmalloc_node(sizeof(*ds), GFP_KERNEL | __GFP_ZERO, node);
+ if (unlikely(!ds))
+ return -ENOMEM;
+
+ per_cpu(cpu_hw_events, cpu).ds = ds;
+
+ return 0;
+}
+
+static void release_ds_buffer(int cpu)
+{
+ struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+ if (!ds)
+ return;
+
+ per_cpu(cpu_hw_events, cpu).ds = NULL;
+ kfree(ds);
+}
+
static void release_ds_buffers(void)
{
int cpu;
@@ -82,93 +183,77 @@ static void release_ds_buffers(void)
return;
get_online_cpus();
-
for_each_online_cpu(cpu)
fini_debug_store_on_cpu(cpu);
for_each_possible_cpu(cpu) {
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
- if (!ds)
- continue;
-
- per_cpu(cpu_hw_events, cpu).ds = NULL;
-
- kfree((void *)(unsigned long)ds->pebs_buffer_base);
- kfree((void *)(unsigned long)ds->bts_buffer_base);
- kfree(ds);
+ release_pebs_buffer(cpu);
+ release_bts_buffer(cpu);
+ release_ds_buffer(cpu);
}
-
put_online_cpus();
}
-static int reserve_ds_buffers(void)
+static void reserve_ds_buffers(void)
{
- int cpu, err = 0;
+ int bts_err = 0, pebs_err = 0;
+ int cpu;
+
+ x86_pmu.bts_active = 0;
+ x86_pmu.pebs_active = 0;
if (!x86_pmu.bts && !x86_pmu.pebs)
- return 0;
+ return;
+
+ if (!x86_pmu.bts)
+ bts_err = 1;
+
+ if (!x86_pmu.pebs)
+ pebs_err = 1;
get_online_cpus();
for_each_possible_cpu(cpu) {
- struct debug_store *ds;
- void *buffer;
- int max, thresh;
+ if (alloc_ds_buffer(cpu)) {
+ bts_err = 1;
+ pebs_err = 1;
+ }
+
+ if (!bts_err && alloc_bts_buffer(cpu))
+ bts_err = 1;
- err = -ENOMEM;
- ds = kzalloc(sizeof(*ds), GFP_KERNEL);
- if (unlikely(!ds))
+ if (!pebs_err && alloc_pebs_buffer(cpu))
+ pebs_err = 1;
+
+ if (bts_err && pebs_err)
break;
- per_cpu(cpu_hw_events, cpu).ds = ds;
-
- if (x86_pmu.bts) {
- buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
- if (unlikely(!buffer))
- break;
-
- max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
- thresh = max / 16;
-
- ds->bts_buffer_base = (u64)(unsigned long)buffer;
- ds->bts_index = ds->bts_buffer_base;
- ds->bts_absolute_maximum = ds->bts_buffer_base +
- max * BTS_RECORD_SIZE;
- ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
- thresh * BTS_RECORD_SIZE;
- }
+ }
- if (x86_pmu.pebs) {
- buffer = kzalloc(PEBS_BUFFER_SIZE, GFP_KERNEL);
- if (unlikely(!buffer))
- break;
-
- max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
-
- ds->pebs_buffer_base = (u64)(unsigned long)buffer;
- ds->pebs_index = ds->pebs_buffer_base;
- ds->pebs_absolute_maximum = ds->pebs_buffer_base +
- max * x86_pmu.pebs_record_size;
- /*
- * Always use single record PEBS
- */
- ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
- x86_pmu.pebs_record_size;
- }
+ if (bts_err) {
+ for_each_possible_cpu(cpu)
+ release_bts_buffer(cpu);
+ }
- err = 0;
+ if (pebs_err) {
+ for_each_possible_cpu(cpu)
+ release_pebs_buffer(cpu);
}
- if (err)
- release_ds_buffers();
- else {
+ if (bts_err && pebs_err) {
+ for_each_possible_cpu(cpu)
+ release_ds_buffer(cpu);
+ } else {
+ if (x86_pmu.bts && !bts_err)
+ x86_pmu.bts_active = 1;
+
+ if (x86_pmu.pebs && !pebs_err)
+ x86_pmu.pebs_active = 1;
+
for_each_online_cpu(cpu)
init_debug_store_on_cpu(cpu);
}
put_online_cpus();
-
- return err;
}
/*
@@ -233,7 +318,7 @@ static int intel_pmu_drain_bts_buffer(void)
if (!event)
return 0;
- if (!ds)
+ if (!x86_pmu.bts_active)
return 0;
at = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
@@ -503,7 +588,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
struct pebs_record_core *at, *top;
int n;
- if (!ds || !x86_pmu.pebs)
+ if (!x86_pmu.pebs_active)
return;
at = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base;
@@ -545,7 +630,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
u64 status = 0;
int bit, n;
- if (!ds || !x86_pmu.pebs)
+ if (!x86_pmu.pebs_active)
return;
at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
@@ -630,9 +715,8 @@ static void intel_ds_init(void)
#else /* CONFIG_CPU_SUP_INTEL */
-static int reserve_ds_buffers(void)
+static void reserve_ds_buffers(void)
{
- return 0;
}
static void release_ds_buffers(void)
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 0f6376ffa2d9..1bc7f75a5bda 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -82,11 +82,11 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
if (kstack_end(stack))
break;
if (i && ((i % STACKSLOTS_PER_LINE) == 0))
- printk("\n%s", log_lvl);
- printk(" %08lx", *stack++);
+ printk(KERN_CONT "\n");
+ printk(KERN_CONT " %08lx", *stack++);
touch_nmi_watchdog();
}
- printk("\n");
+ printk(KERN_CONT "\n");
show_trace_log_lvl(task, regs, sp, bp, log_lvl);
}
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 57a21f11c791..6a340485249a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -265,20 +265,20 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
if (stack >= irq_stack && stack <= irq_stack_end) {
if (stack == irq_stack_end) {
stack = (unsigned long *) (irq_stack_end[-1]);
- printk(" <EOI> ");
+ printk(KERN_CONT " <EOI> ");
}
} else {
if (((long) stack & (THREAD_SIZE-1)) == 0)
break;
}
if (i && ((i % STACKSLOTS_PER_LINE) == 0))
- printk("\n%s", log_lvl);
- printk(" %016lx", *stack++);
+ printk(KERN_CONT "\n");
+ printk(KERN_CONT " %016lx", *stack++);
touch_nmi_watchdog();
}
preempt_enable();
- printk("\n");
+ printk(KERN_CONT "\n");
show_trace_log_lvl(task, regs, sp, bp, log_lvl);
}
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 50fbbe60e507..64668dbf00a4 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -60,9 +60,6 @@ union irq_ctx {
static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
-static DEFINE_PER_CPU_MULTIPAGE_ALIGNED(union irq_ctx, hardirq_stack, THREAD_SIZE);
-static DEFINE_PER_CPU_MULTIPAGE_ALIGNED(union irq_ctx, softirq_stack, THREAD_SIZE);
-
static void call_on_stack(void *func, void *stack)
{
asm volatile("xchgl %%ebx,%%esp \n"
@@ -128,7 +125,7 @@ void __cpuinit irq_ctx_init(int cpu)
if (per_cpu(hardirq_ctx, cpu))
return;
- irqctx = &per_cpu(hardirq_stack, cpu);
+ irqctx = (union irq_ctx *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER);
irqctx->tinfo.task = NULL;
irqctx->tinfo.exec_domain = NULL;
irqctx->tinfo.cpu = cpu;
@@ -137,7 +134,7 @@ void __cpuinit irq_ctx_init(int cpu)
per_cpu(hardirq_ctx, cpu) = irqctx;
- irqctx = &per_cpu(softirq_stack, cpu);
+ irqctx = (union irq_ctx *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER);
irqctx->tinfo.task = NULL;
irqctx->tinfo.exec_domain = NULL;
irqctx->tinfo.cpu = cpu;
@@ -150,11 +147,6 @@ void __cpuinit irq_ctx_init(int cpu)
cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu));
}
-void irq_ctx_exit(int cpu)
-{
- per_cpu(hardirq_ctx, cpu) = NULL;
-}
-
asmlinkage void do_softirq(void)
{
unsigned long flags;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 70c4872cd8aa..45892dc4b72a 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -801,7 +801,8 @@ void ptrace_disable(struct task_struct *child)
static const struct user_regset_view user_x86_32_view; /* Initialized below. */
#endif
-long arch_ptrace(struct task_struct *child, long request, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request,
+ unsigned long addr, unsigned long data)
{
int ret;
unsigned long __user *datap = (unsigned long __user *)data;
@@ -812,8 +813,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
unsigned long tmp;
ret = -EIO;
- if ((addr & (sizeof(data) - 1)) || addr < 0 ||
- addr >= sizeof(struct user))
+ if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user))
break;
tmp = 0; /* Default return condition */
@@ -830,8 +830,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
ret = -EIO;
- if ((addr & (sizeof(data) - 1)) || addr < 0 ||
- addr >= sizeof(struct user))
+ if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user))
break;
if (addr < sizeof(struct user_regs_struct))
@@ -888,17 +887,17 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
case PTRACE_GET_THREAD_AREA:
- if (addr < 0)
+ if ((int) addr < 0)
return -EIO;
ret = do_get_thread_area(child, addr,
- (struct user_desc __user *) data);
+ (struct user_desc __user *)data);
break;
case PTRACE_SET_THREAD_AREA:
- if (addr < 0)
+ if ((int) addr < 0)
return -EIO;
ret = do_set_thread_area(child, addr,
- (struct user_desc __user *) data, 0);
+ (struct user_desc __user *)data, 0);
break;
#endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f7f53dcd3e0a..c495aa8d4815 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -635,7 +635,7 @@ void native_machine_shutdown(void)
/* O.K Now that I'm on the appropriate processor,
* stop all of the others.
*/
- smp_send_stop();
+ stop_other_cpus();
#endif
lapic_shutdown();
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index d801210945d6..513deac7228d 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -159,10 +159,10 @@ asmlinkage void smp_reboot_interrupt(void)
irq_exit();
}
-static void native_smp_send_stop(void)
+static void native_stop_other_cpus(int wait)
{
unsigned long flags;
- unsigned long wait;
+ unsigned long timeout;
if (reboot_force)
return;
@@ -179,9 +179,12 @@ static void native_smp_send_stop(void)
if (num_online_cpus() > 1) {
apic->send_IPI_allbutself(REBOOT_VECTOR);
- /* Don't wait longer than a second */
- wait = USEC_PER_SEC;
- while (num_online_cpus() > 1 && wait--)
+ /*
+ * Don't wait longer than a second if the caller
+ * didn't ask us to wait.
+ */
+ timeout = USEC_PER_SEC;
+ while (num_online_cpus() > 1 && (wait || timeout--))
udelay(1);
}
@@ -227,7 +230,7 @@ struct smp_ops smp_ops = {
.smp_prepare_cpus = native_smp_prepare_cpus,
.smp_cpus_done = native_smp_cpus_done,
- .smp_send_stop = native_smp_send_stop,
+ .stop_other_cpus = native_stop_other_cpus,
.smp_send_reschedule = native_smp_send_reschedule,
.cpu_up = native_cpu_up,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6c7faecd9e4a..083e99d1b7df 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1373,7 +1373,6 @@ void play_dead_common(void)
{
idle_task_exit();
reset_lazy_tlbstate();
- irq_ctx_exit(raw_smp_processor_id());
c1e_remove_cpu(raw_smp_processor_id());
mb();
generated by cgit v1.2.3 (git 2.0.4) at 2025-12-13 13:39:23 +0000