Merge branch 'oprofile/ring_buffer' into oprofile/oprofile-for-tip
This commit is contained in:
Robert Richter
commit
d2852b932f
|
|
@ -6,6 +6,8 @@ config OPROFILE
|
|||
tristate "OProfile system profiling (EXPERIMENTAL)"
|
||||
depends on PROFILING
|
||||
depends on HAVE_OPROFILE
|
||||
select TRACING
|
||||
select RING_BUFFER
|
||||
help
|
||||
OProfile is a profiling system capable of profiling the
|
||||
whole system, include the kernel, kernel modules, libraries,
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
* @file op_model_amd.c
|
||||
* athlon / K7 / K8 / Family 10h model-specific MSR operations
|
||||
*
|
||||
* @remark Copyright 2002-2008 OProfile authors
|
||||
* @remark Copyright 2002-2009 OProfile authors
|
||||
* @remark Read the file COPYING
|
||||
*
|
||||
* @author John Levon
|
||||
|
|
@ -10,7 +10,7 @@
|
|||
* @author Graydon Hoare
|
||||
* @author Robert Richter <robert.richter@amd.com>
|
||||
* @author Barry Kasindorf
|
||||
*/
|
||||
*/
|
||||
|
||||
#include <linux/oprofile.h>
|
||||
#include <linux/device.h>
|
||||
|
|
@ -60,56 +60,10 @@ static unsigned long reset_value[NUM_COUNTERS];
|
|||
#define IBS_OP_LOW_VALID_BIT (1ULL<<18) /* bit 18 */
|
||||
#define IBS_OP_LOW_ENABLE (1ULL<<17) /* bit 17 */
|
||||
|
||||
/* Codes used in cpu_buffer.c */
|
||||
/* This produces duplicate code, need to be fixed */
|
||||
#define IBS_FETCH_BEGIN 3
|
||||
#define IBS_OP_BEGIN 4
|
||||
#define IBS_FETCH_SIZE 6
|
||||
#define IBS_OP_SIZE 12
|
||||
|
||||
/* The function interface needs to be fixed, something like add
|
||||
data. Should then be added to linux/oprofile.h. */
|
||||
extern void
|
||||
oprofile_add_ibs_sample(struct pt_regs *const regs,
|
||||
unsigned int *const ibs_sample, int ibs_code);
|
||||
|
||||
struct ibs_fetch_sample {
|
||||
/* MSRC001_1031 IBS Fetch Linear Address Register */
|
||||
unsigned int ibs_fetch_lin_addr_low;
|
||||
unsigned int ibs_fetch_lin_addr_high;
|
||||
/* MSRC001_1030 IBS Fetch Control Register */
|
||||
unsigned int ibs_fetch_ctl_low;
|
||||
unsigned int ibs_fetch_ctl_high;
|
||||
/* MSRC001_1032 IBS Fetch Physical Address Register */
|
||||
unsigned int ibs_fetch_phys_addr_low;
|
||||
unsigned int ibs_fetch_phys_addr_high;
|
||||
};
|
||||
|
||||
struct ibs_op_sample {
|
||||
/* MSRC001_1034 IBS Op Logical Address Register (IbsRIP) */
|
||||
unsigned int ibs_op_rip_low;
|
||||
unsigned int ibs_op_rip_high;
|
||||
/* MSRC001_1035 IBS Op Data Register */
|
||||
unsigned int ibs_op_data1_low;
|
||||
unsigned int ibs_op_data1_high;
|
||||
/* MSRC001_1036 IBS Op Data 2 Register */
|
||||
unsigned int ibs_op_data2_low;
|
||||
unsigned int ibs_op_data2_high;
|
||||
/* MSRC001_1037 IBS Op Data 3 Register */
|
||||
unsigned int ibs_op_data3_low;
|
||||
unsigned int ibs_op_data3_high;
|
||||
/* MSRC001_1038 IBS DC Linear Address Register (IbsDcLinAd) */
|
||||
unsigned int ibs_dc_linear_low;
|
||||
unsigned int ibs_dc_linear_high;
|
||||
/* MSRC001_1039 IBS DC Physical Address Register (IbsDcPhysAd) */
|
||||
unsigned int ibs_dc_phys_low;
|
||||
unsigned int ibs_dc_phys_high;
|
||||
};
|
||||
|
||||
/*
|
||||
* unitialize the APIC for the IBS interrupts if needed on AMD Family10h+
|
||||
*/
|
||||
static void clear_ibs_nmi(void);
|
||||
|
||||
static int ibs_allowed; /* AMD Family10h and later */
|
||||
static int has_ibs; /* AMD Family10h and later */
|
||||
|
||||
struct op_ibs_config {
|
||||
unsigned long op_enabled;
|
||||
|
|
@ -200,31 +154,29 @@ static inline int
|
|||
op_amd_handle_ibs(struct pt_regs * const regs,
|
||||
struct op_msrs const * const msrs)
|
||||
{
|
||||
unsigned int low, high;
|
||||
struct ibs_fetch_sample ibs_fetch;
|
||||
struct ibs_op_sample ibs_op;
|
||||
u32 low, high;
|
||||
u64 msr;
|
||||
struct op_entry entry;
|
||||
|
||||
if (!ibs_allowed)
|
||||
if (!has_ibs)
|
||||
return 1;
|
||||
|
||||
if (ibs_config.fetch_enabled) {
|
||||
rdmsr(MSR_AMD64_IBSFETCHCTL, low, high);
|
||||
if (high & IBS_FETCH_HIGH_VALID_BIT) {
|
||||
ibs_fetch.ibs_fetch_ctl_high = high;
|
||||
ibs_fetch.ibs_fetch_ctl_low = low;
|
||||
rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high);
|
||||
ibs_fetch.ibs_fetch_lin_addr_high = high;
|
||||
ibs_fetch.ibs_fetch_lin_addr_low = low;
|
||||
rdmsr(MSR_AMD64_IBSFETCHPHYSAD, low, high);
|
||||
ibs_fetch.ibs_fetch_phys_addr_high = high;
|
||||
ibs_fetch.ibs_fetch_phys_addr_low = low;
|
||||
rdmsrl(MSR_AMD64_IBSFETCHLINAD, msr);
|
||||
oprofile_write_reserve(&entry, regs, msr,
|
||||
IBS_FETCH_CODE, IBS_FETCH_SIZE);
|
||||
oprofile_add_data(&entry, (u32)msr);
|
||||
oprofile_add_data(&entry, (u32)(msr >> 32));
|
||||
oprofile_add_data(&entry, low);
|
||||
oprofile_add_data(&entry, high);
|
||||
rdmsrl(MSR_AMD64_IBSFETCHPHYSAD, msr);
|
||||
oprofile_add_data(&entry, (u32)msr);
|
||||
oprofile_add_data(&entry, (u32)(msr >> 32));
|
||||
oprofile_write_commit(&entry);
|
||||
|
||||
oprofile_add_ibs_sample(regs,
|
||||
(unsigned int *)&ibs_fetch,
|
||||
IBS_FETCH_BEGIN);
|
||||
|
||||
/*reenable the IRQ */
|
||||
rdmsr(MSR_AMD64_IBSFETCHCTL, low, high);
|
||||
/* reenable the IRQ */
|
||||
high &= ~IBS_FETCH_HIGH_VALID_BIT;
|
||||
high |= IBS_FETCH_HIGH_ENABLE;
|
||||
low &= IBS_FETCH_LOW_MAX_CNT_MASK;
|
||||
|
|
@ -235,30 +187,29 @@ op_amd_handle_ibs(struct pt_regs * const regs,
|
|||
if (ibs_config.op_enabled) {
|
||||
rdmsr(MSR_AMD64_IBSOPCTL, low, high);
|
||||
if (low & IBS_OP_LOW_VALID_BIT) {
|
||||
rdmsr(MSR_AMD64_IBSOPRIP, low, high);
|
||||
ibs_op.ibs_op_rip_low = low;
|
||||
ibs_op.ibs_op_rip_high = high;
|
||||
rdmsr(MSR_AMD64_IBSOPDATA, low, high);
|
||||
ibs_op.ibs_op_data1_low = low;
|
||||
ibs_op.ibs_op_data1_high = high;
|
||||
rdmsr(MSR_AMD64_IBSOPDATA2, low, high);
|
||||
ibs_op.ibs_op_data2_low = low;
|
||||
ibs_op.ibs_op_data2_high = high;
|
||||
rdmsr(MSR_AMD64_IBSOPDATA3, low, high);
|
||||
ibs_op.ibs_op_data3_low = low;
|
||||
ibs_op.ibs_op_data3_high = high;
|
||||
rdmsr(MSR_AMD64_IBSDCLINAD, low, high);
|
||||
ibs_op.ibs_dc_linear_low = low;
|
||||
ibs_op.ibs_dc_linear_high = high;
|
||||
rdmsr(MSR_AMD64_IBSDCPHYSAD, low, high);
|
||||
ibs_op.ibs_dc_phys_low = low;
|
||||
ibs_op.ibs_dc_phys_high = high;
|
||||
rdmsrl(MSR_AMD64_IBSOPRIP, msr);
|
||||
oprofile_write_reserve(&entry, regs, msr,
|
||||
IBS_OP_CODE, IBS_OP_SIZE);
|
||||
oprofile_add_data(&entry, (u32)msr);
|
||||
oprofile_add_data(&entry, (u32)(msr >> 32));
|
||||
rdmsrl(MSR_AMD64_IBSOPDATA, msr);
|
||||
oprofile_add_data(&entry, (u32)msr);
|
||||
oprofile_add_data(&entry, (u32)(msr >> 32));
|
||||
rdmsrl(MSR_AMD64_IBSOPDATA2, msr);
|
||||
oprofile_add_data(&entry, (u32)msr);
|
||||
oprofile_add_data(&entry, (u32)(msr >> 32));
|
||||
rdmsrl(MSR_AMD64_IBSOPDATA3, msr);
|
||||
oprofile_add_data(&entry, (u32)msr);
|
||||
oprofile_add_data(&entry, (u32)(msr >> 32));
|
||||
rdmsrl(MSR_AMD64_IBSDCLINAD, msr);
|
||||
oprofile_add_data(&entry, (u32)msr);
|
||||
oprofile_add_data(&entry, (u32)(msr >> 32));
|
||||
rdmsrl(MSR_AMD64_IBSDCPHYSAD, msr);
|
||||
oprofile_add_data(&entry, (u32)msr);
|
||||
oprofile_add_data(&entry, (u32)(msr >> 32));
|
||||
oprofile_write_commit(&entry);
|
||||
|
||||
/* reenable the IRQ */
|
||||
oprofile_add_ibs_sample(regs,
|
||||
(unsigned int *)&ibs_op,
|
||||
IBS_OP_BEGIN);
|
||||
rdmsr(MSR_AMD64_IBSOPCTL, low, high);
|
||||
high = 0;
|
||||
low &= ~IBS_OP_LOW_VALID_BIT;
|
||||
low |= IBS_OP_LOW_ENABLE;
|
||||
|
|
@ -308,14 +259,14 @@ static void op_amd_start(struct op_msrs const * const msrs)
|
|||
}
|
||||
|
||||
#ifdef CONFIG_OPROFILE_IBS
|
||||
if (ibs_allowed && ibs_config.fetch_enabled) {
|
||||
if (has_ibs && ibs_config.fetch_enabled) {
|
||||
low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF;
|
||||
high = ((ibs_config.rand_en & 0x1) << 25) /* bit 57 */
|
||||
+ IBS_FETCH_HIGH_ENABLE;
|
||||
wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
|
||||
}
|
||||
|
||||
if (ibs_allowed && ibs_config.op_enabled) {
|
||||
if (has_ibs && ibs_config.op_enabled) {
|
||||
low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF)
|
||||
+ ((ibs_config.dispatched_ops & 0x1) << 19) /* bit 19 */
|
||||
+ IBS_OP_LOW_ENABLE;
|
||||
|
|
@ -331,8 +282,10 @@ static void op_amd_stop(struct op_msrs const * const msrs)
|
|||
unsigned int low, high;
|
||||
int i;
|
||||
|
||||
/* Subtle: stop on all counters to avoid race with
|
||||
* setting our pm callback */
|
||||
/*
|
||||
* Subtle: stop on all counters to avoid race with setting our
|
||||
* pm callback
|
||||
*/
|
||||
for (i = 0 ; i < NUM_COUNTERS ; ++i) {
|
||||
if (!reset_value[i])
|
||||
continue;
|
||||
|
|
@ -342,14 +295,16 @@ static void op_amd_stop(struct op_msrs const * const msrs)
|
|||
}
|
||||
|
||||
#ifdef CONFIG_OPROFILE_IBS
|
||||
if (ibs_allowed && ibs_config.fetch_enabled) {
|
||||
low = 0; /* clear max count and enable */
|
||||
if (has_ibs && ibs_config.fetch_enabled) {
|
||||
/* clear max count and enable */
|
||||
low = 0;
|
||||
high = 0;
|
||||
wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
|
||||
}
|
||||
|
||||
if (ibs_allowed && ibs_config.op_enabled) {
|
||||
low = 0; /* clear max count and enable */
|
||||
if (has_ibs && ibs_config.op_enabled) {
|
||||
/* clear max count and enable */
|
||||
low = 0;
|
||||
high = 0;
|
||||
wrmsr(MSR_AMD64_IBSOPCTL, low, high);
|
||||
}
|
||||
|
|
@ -370,18 +325,7 @@ static void op_amd_shutdown(struct op_msrs const * const msrs)
|
|||
}
|
||||
}
|
||||
|
||||
#ifndef CONFIG_OPROFILE_IBS
|
||||
|
||||
/* no IBS support */
|
||||
|
||||
static int op_amd_init(struct oprofile_operations *ops)
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void op_amd_exit(void) {}
|
||||
|
||||
#else
|
||||
#ifdef CONFIG_OPROFILE_IBS
|
||||
|
||||
static u8 ibs_eilvt_off;
|
||||
|
||||
|
|
@ -395,7 +339,7 @@ static inline void apic_clear_ibs_nmi_per_cpu(void *arg)
|
|||
setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
|
||||
}
|
||||
|
||||
static int pfm_amd64_setup_eilvt(void)
|
||||
static int init_ibs_nmi(void)
|
||||
{
|
||||
#define IBSCTL_LVTOFFSETVAL (1 << 8)
|
||||
#define IBSCTL 0x1cc
|
||||
|
|
@ -419,6 +363,7 @@ static int pfm_amd64_setup_eilvt(void)
|
|||
| IBSCTL_LVTOFFSETVAL);
|
||||
pci_read_config_dword(cpu_cfg, IBSCTL, &value);
|
||||
if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) {
|
||||
pci_dev_put(cpu_cfg);
|
||||
printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
|
||||
"IBSCTL = 0x%08x", value);
|
||||
return 1;
|
||||
|
|
@ -443,33 +388,35 @@ static int pfm_amd64_setup_eilvt(void)
|
|||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* initialize the APIC for the IBS interrupts
|
||||
* if available (AMD Family10h rev B0 and later)
|
||||
*/
|
||||
static void setup_ibs(void)
|
||||
/* uninitialize the APIC for the IBS interrupts if needed */
|
||||
static void clear_ibs_nmi(void)
|
||||
{
|
||||
ibs_allowed = boot_cpu_has(X86_FEATURE_IBS);
|
||||
if (has_ibs)
|
||||
on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1);
|
||||
}
|
||||
|
||||
if (!ibs_allowed)
|
||||
/* initialize the APIC for the IBS interrupts if available */
|
||||
static void ibs_init(void)
|
||||
{
|
||||
has_ibs = boot_cpu_has(X86_FEATURE_IBS);
|
||||
|
||||
if (!has_ibs)
|
||||
return;
|
||||
|
||||
if (pfm_amd64_setup_eilvt()) {
|
||||
ibs_allowed = 0;
|
||||
if (init_ibs_nmi()) {
|
||||
has_ibs = 0;
|
||||
return;
|
||||
}
|
||||
|
||||
printk(KERN_INFO "oprofile: AMD IBS detected\n");
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* unitialize the APIC for the IBS interrupts if needed on AMD Family10h
|
||||
* rev B0 and later */
|
||||
static void clear_ibs_nmi(void)
|
||||
static void ibs_exit(void)
|
||||
{
|
||||
if (ibs_allowed)
|
||||
on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1);
|
||||
if (!has_ibs)
|
||||
return;
|
||||
|
||||
clear_ibs_nmi();
|
||||
}
|
||||
|
||||
static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
|
||||
|
|
@ -486,7 +433,7 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
|
|||
if (ret)
|
||||
return ret;
|
||||
|
||||
if (!ibs_allowed)
|
||||
if (!has_ibs)
|
||||
return ret;
|
||||
|
||||
/* model specific files */
|
||||
|
|
@ -519,7 +466,7 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
|
|||
|
||||
static int op_amd_init(struct oprofile_operations *ops)
|
||||
{
|
||||
setup_ibs();
|
||||
ibs_init();
|
||||
create_arch_files = ops->create_files;
|
||||
ops->create_files = setup_ibs_files;
|
||||
return 0;
|
||||
|
|
@ -527,10 +474,21 @@ static int op_amd_init(struct oprofile_operations *ops)
|
|||
|
||||
static void op_amd_exit(void)
|
||||
{
|
||||
clear_ibs_nmi();
|
||||
ibs_exit();
|
||||
}
|
||||
|
||||
#endif
|
||||
#else
|
||||
|
||||
/* no IBS support */
|
||||
|
||||
static int op_amd_init(struct oprofile_operations *ops)
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void op_amd_exit(void) {}
|
||||
|
||||
#endif /* CONFIG_OPROFILE_IBS */
|
||||
|
||||
struct op_x86_model_spec const op_amd_spec = {
|
||||
.init = op_amd_init,
|
||||
|
|
|
|||
|
|
@ -1,11 +1,12 @@
|
|||
/**
|
||||
* @file buffer_sync.c
|
||||
*
|
||||
* @remark Copyright 2002 OProfile authors
|
||||
* @remark Copyright 2002-2009 OProfile authors
|
||||
* @remark Read the file COPYING
|
||||
*
|
||||
* @author John Levon <levon@movementarian.org>
|
||||
* @author Barry Kasindorf
|
||||
* @author Robert Richter <robert.richter@amd.com>
|
||||
*
|
||||
* This is the core of the buffer management. Each
|
||||
* CPU buffer is processed and entered into the
|
||||
|
|
@ -268,18 +269,6 @@ lookup_dcookie(struct mm_struct *mm, unsigned long addr, off_t *offset)
|
|||
return cookie;
|
||||
}
|
||||
|
||||
static void increment_tail(struct oprofile_cpu_buffer *b)
|
||||
{
|
||||
unsigned long new_tail = b->tail_pos + 1;
|
||||
|
||||
rmb(); /* be sure fifo pointers are synchromized */
|
||||
|
||||
if (new_tail < b->buffer_size)
|
||||
b->tail_pos = new_tail;
|
||||
else
|
||||
b->tail_pos = 0;
|
||||
}
|
||||
|
||||
static unsigned long last_cookie = INVALID_COOKIE;
|
||||
|
||||
static void add_cpu_switch(int i)
|
||||
|
|
@ -327,84 +316,73 @@ static void add_trace_begin(void)
|
|||
add_event_entry(TRACE_BEGIN_CODE);
|
||||
}
|
||||
|
||||
#ifdef CONFIG_OPROFILE_IBS
|
||||
|
||||
#define IBS_FETCH_CODE_SIZE 2
|
||||
#define IBS_OP_CODE_SIZE 5
|
||||
#define IBS_EIP(offset) \
|
||||
(((struct op_sample *)&cpu_buf->buffer[(offset)])->eip)
|
||||
#define IBS_EVENT(offset) \
|
||||
(((struct op_sample *)&cpu_buf->buffer[(offset)])->event)
|
||||
|
||||
/*
|
||||
* Add IBS fetch and op entries to event buffer
|
||||
*/
|
||||
static void add_ibs_begin(struct oprofile_cpu_buffer *cpu_buf, int code,
|
||||
struct mm_struct *mm)
|
||||
static void add_data(struct op_entry *entry, struct mm_struct *mm)
|
||||
{
|
||||
unsigned long rip;
|
||||
int i, count;
|
||||
unsigned long ibs_cookie = 0;
|
||||
unsigned long code, pc, val;
|
||||
unsigned long cookie;
|
||||
off_t offset;
|
||||
|
||||
increment_tail(cpu_buf); /* move to RIP entry */
|
||||
|
||||
rip = IBS_EIP(cpu_buf->tail_pos);
|
||||
|
||||
#ifdef __LP64__
|
||||
rip += IBS_EVENT(cpu_buf->tail_pos) << 32;
|
||||
#endif
|
||||
if (!op_cpu_buffer_get_data(entry, &code))
|
||||
return;
|
||||
if (!op_cpu_buffer_get_data(entry, &pc))
|
||||
return;
|
||||
if (!op_cpu_buffer_get_size(entry))
|
||||
return;
|
||||
|
||||
if (mm) {
|
||||
ibs_cookie = lookup_dcookie(mm, rip, &offset);
|
||||
cookie = lookup_dcookie(mm, pc, &offset);
|
||||
|
||||
if (ibs_cookie == NO_COOKIE)
|
||||
offset = rip;
|
||||
if (ibs_cookie == INVALID_COOKIE) {
|
||||
if (cookie == NO_COOKIE)
|
||||
offset = pc;
|
||||
if (cookie == INVALID_COOKIE) {
|
||||
atomic_inc(&oprofile_stats.sample_lost_no_mapping);
|
||||
offset = rip;
|
||||
offset = pc;
|
||||
}
|
||||
if (ibs_cookie != last_cookie) {
|
||||
add_cookie_switch(ibs_cookie);
|
||||
last_cookie = ibs_cookie;
|
||||
if (cookie != last_cookie) {
|
||||
add_cookie_switch(cookie);
|
||||
last_cookie = cookie;
|
||||
}
|
||||
} else
|
||||
offset = rip;
|
||||
offset = pc;
|
||||
|
||||
add_event_entry(ESCAPE_CODE);
|
||||
add_event_entry(code);
|
||||
add_event_entry(offset); /* Offset from Dcookie */
|
||||
|
||||
/* we send the Dcookie offset, but send the raw Linear Add also*/
|
||||
add_event_entry(IBS_EIP(cpu_buf->tail_pos));
|
||||
add_event_entry(IBS_EVENT(cpu_buf->tail_pos));
|
||||
|
||||
if (code == IBS_FETCH_CODE)
|
||||
count = IBS_FETCH_CODE_SIZE; /*IBS FETCH is 2 int64s*/
|
||||
else
|
||||
count = IBS_OP_CODE_SIZE; /*IBS OP is 5 int64s*/
|
||||
|
||||
for (i = 0; i < count; i++) {
|
||||
increment_tail(cpu_buf);
|
||||
add_event_entry(IBS_EIP(cpu_buf->tail_pos));
|
||||
add_event_entry(IBS_EVENT(cpu_buf->tail_pos));
|
||||
}
|
||||
while (op_cpu_buffer_get_data(entry, &val))
|
||||
add_event_entry(val);
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
static void add_sample_entry(unsigned long offset, unsigned long event)
|
||||
static inline void add_sample_entry(unsigned long offset, unsigned long event)
|
||||
{
|
||||
add_event_entry(offset);
|
||||
add_event_entry(event);
|
||||
}
|
||||
|
||||
|
||||
static int add_us_sample(struct mm_struct *mm, struct op_sample *s)
|
||||
/*
|
||||
* Add a sample to the global event buffer. If possible the
|
||||
* sample is converted into a persistent dentry/offset pair
|
||||
* for later lookup from userspace. Return 0 on failure.
|
||||
*/
|
||||
static int
|
||||
add_sample(struct mm_struct *mm, struct op_sample *s, int in_kernel)
|
||||
{
|
||||
unsigned long cookie;
|
||||
off_t offset;
|
||||
|
||||
if (in_kernel) {
|
||||
add_sample_entry(s->eip, s->event);
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* add userspace sample */
|
||||
|
||||
if (!mm) {
|
||||
atomic_inc(&oprofile_stats.sample_lost_no_mm);
|
||||
return 0;
|
||||
}
|
||||
|
||||
cookie = lookup_dcookie(mm, s->eip, &offset);
|
||||
|
||||
if (cookie == INVALID_COOKIE) {
|
||||
|
|
@ -423,25 +401,6 @@ static int add_us_sample(struct mm_struct *mm, struct op_sample *s)
|
|||
}
|
||||
|
||||
|
||||
/* Add a sample to the global event buffer. If possible the
|
||||
* sample is converted into a persistent dentry/offset pair
|
||||
* for later lookup from userspace.
|
||||
*/
|
||||
static int
|
||||
add_sample(struct mm_struct *mm, struct op_sample *s, int in_kernel)
|
||||
{
|
||||
if (in_kernel) {
|
||||
add_sample_entry(s->eip, s->event);
|
||||
return 1;
|
||||
} else if (mm) {
|
||||
return add_us_sample(mm, s);
|
||||
} else {
|
||||
atomic_inc(&oprofile_stats.sample_lost_no_mm);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
||||
static void release_mm(struct mm_struct *mm)
|
||||
{
|
||||
if (!mm)
|
||||
|
|
@ -466,33 +425,6 @@ static inline int is_code(unsigned long val)
|
|||
}
|
||||
|
||||
|
||||
/* "acquire" as many cpu buffer slots as we can */
|
||||
static unsigned long get_slots(struct oprofile_cpu_buffer *b)
|
||||
{
|
||||
unsigned long head = b->head_pos;
|
||||
unsigned long tail = b->tail_pos;
|
||||
|
||||
/*
|
||||
* Subtle. This resets the persistent last_task
|
||||
* and in_kernel values used for switching notes.
|
||||
* BUT, there is a small window between reading
|
||||
* head_pos, and this call, that means samples
|
||||
* can appear at the new head position, but not
|
||||
* be prefixed with the notes for switching
|
||||
* kernel mode or a task switch. This small hole
|
||||
* can lead to mis-attribution or samples where
|
||||
* we don't know if it's in the kernel or not,
|
||||
* at the start of an event buffer.
|
||||
*/
|
||||
cpu_buffer_reset(b);
|
||||
|
||||
if (head >= tail)
|
||||
return head - tail;
|
||||
|
||||
return head + (b->buffer_size - tail);
|
||||
}
|
||||
|
||||
|
||||
/* Move tasks along towards death. Any tasks on dead_tasks
|
||||
* will definitely have no remaining references in any
|
||||
* CPU buffers at this point, because we use two lists,
|
||||
|
|
@ -559,71 +491,72 @@ typedef enum {
|
|||
*/
|
||||
void sync_buffer(int cpu)
|
||||
{
|
||||
struct oprofile_cpu_buffer *cpu_buf = &per_cpu(cpu_buffer, cpu);
|
||||
struct mm_struct *mm = NULL;
|
||||
struct mm_struct *oldmm;
|
||||
unsigned long val;
|
||||
struct task_struct *new;
|
||||
unsigned long cookie = 0;
|
||||
int in_kernel = 1;
|
||||
sync_buffer_state state = sb_buffer_start;
|
||||
#ifndef CONFIG_OPROFILE_IBS
|
||||
unsigned int i;
|
||||
unsigned long available;
|
||||
#endif
|
||||
unsigned long flags;
|
||||
struct op_entry entry;
|
||||
struct op_sample *sample;
|
||||
|
||||
mutex_lock(&buffer_mutex);
|
||||
|
||||
add_cpu_switch(cpu);
|
||||
|
||||
/* Remember, only we can modify tail_pos */
|
||||
|
||||
#ifndef CONFIG_OPROFILE_IBS
|
||||
available = get_slots(cpu_buf);
|
||||
op_cpu_buffer_reset(cpu);
|
||||
available = op_cpu_buffer_entries(cpu);
|
||||
|
||||
for (i = 0; i < available; ++i) {
|
||||
#else
|
||||
while (get_slots(cpu_buf)) {
|
||||
#endif
|
||||
struct op_sample *s = &cpu_buf->buffer[cpu_buf->tail_pos];
|
||||
sample = op_cpu_buffer_read_entry(&entry, cpu);
|
||||
if (!sample)
|
||||
break;
|
||||
|
||||
if (is_code(s->eip)) {
|
||||
if (s->event <= CPU_IS_KERNEL) {
|
||||
/* kernel/userspace switch */
|
||||
in_kernel = s->event;
|
||||
if (state == sb_buffer_start)
|
||||
state = sb_sample_start;
|
||||
add_kernel_ctx_switch(s->event);
|
||||
} else if (s->event == CPU_TRACE_BEGIN) {
|
||||
if (is_code(sample->eip)) {
|
||||
flags = sample->event;
|
||||
if (flags & TRACE_BEGIN) {
|
||||
state = sb_bt_start;
|
||||
add_trace_begin();
|
||||
#ifdef CONFIG_OPROFILE_IBS
|
||||
} else if (s->event == IBS_FETCH_BEGIN) {
|
||||
state = sb_bt_start;
|
||||
add_ibs_begin(cpu_buf, IBS_FETCH_CODE, mm);
|
||||
} else if (s->event == IBS_OP_BEGIN) {
|
||||
state = sb_bt_start;
|
||||
add_ibs_begin(cpu_buf, IBS_OP_CODE, mm);
|
||||
#endif
|
||||
} else {
|
||||
struct mm_struct *oldmm = mm;
|
||||
|
||||
}
|
||||
if (flags & KERNEL_CTX_SWITCH) {
|
||||
/* kernel/userspace switch */
|
||||
in_kernel = flags & IS_KERNEL;
|
||||
if (state == sb_buffer_start)
|
||||
state = sb_sample_start;
|
||||
add_kernel_ctx_switch(flags & IS_KERNEL);
|
||||
}
|
||||
if (flags & USER_CTX_SWITCH
|
||||
&& op_cpu_buffer_get_data(&entry, &val)) {
|
||||
/* userspace context switch */
|
||||
new = (struct task_struct *)s->event;
|
||||
|
||||
new = (struct task_struct *)val;
|
||||
oldmm = mm;
|
||||
release_mm(oldmm);
|
||||
mm = take_tasks_mm(new);
|
||||
if (mm != oldmm)
|
||||
cookie = get_exec_dcookie(mm);
|
||||
add_user_ctx_switch(new, cookie);
|
||||
}
|
||||
} else if (state >= sb_bt_start &&
|
||||
!add_sample(mm, s, in_kernel)) {
|
||||
if (state == sb_bt_start) {
|
||||
state = sb_bt_ignore;
|
||||
atomic_inc(&oprofile_stats.bt_lost_no_mapping);
|
||||
}
|
||||
if (op_cpu_buffer_get_size(&entry))
|
||||
add_data(&entry, mm);
|
||||
continue;
|
||||
}
|
||||
|
||||
increment_tail(cpu_buf);
|
||||
if (state < sb_bt_start)
|
||||
/* ignore sample */
|
||||
continue;
|
||||
|
||||
if (add_sample(mm, sample, in_kernel))
|
||||
continue;
|
||||
|
||||
/* ignore backtraces if failed to add a sample */
|
||||
if (state == sb_bt_start) {
|
||||
state = sb_bt_ignore;
|
||||
atomic_inc(&oprofile_stats.bt_lost_no_mapping);
|
||||
}
|
||||
}
|
||||
release_mm(mm);
|
||||
|
||||
|
|
|
|||
|
|
@ -1,11 +1,12 @@
|
|||
/**
|
||||
* @file cpu_buffer.c
|
||||
*
|
||||
* @remark Copyright 2002 OProfile authors
|
||||
* @remark Copyright 2002-2009 OProfile authors
|
||||
* @remark Read the file COPYING
|
||||
*
|
||||
* @author John Levon <levon@movementarian.org>
|
||||
* @author Barry Kasindorf <barry.kasindorf@amd.com>
|
||||
* @author Robert Richter <robert.richter@amd.com>
|
||||
*
|
||||
* Each CPU has a local buffer that stores PC value/event
|
||||
* pairs. We also log context switches when we notice them.
|
||||
|
|
@ -28,6 +29,25 @@
|
|||
#include "buffer_sync.h"
|
||||
#include "oprof.h"
|
||||
|
||||
#define OP_BUFFER_FLAGS 0
|
||||
|
||||
/*
|
||||
* Read and write access is using spin locking. Thus, writing to the
|
||||
* buffer by NMI handler (x86) could occur also during critical
|
||||
* sections when reading the buffer. To avoid this, there are 2
|
||||
* buffers for independent read and write access. Read access is in
|
||||
* process context only, write access only in the NMI handler. If the
|
||||
* read buffer runs empty, both buffers are swapped atomically. There
|
||||
* is potentially a small window during swapping where the buffers are
|
||||
* disabled and samples could be lost.
|
||||
*
|
||||
* Using 2 buffers is a little bit overhead, but the solution is clear
|
||||
* and does not require changes in the ring buffer implementation. It
|
||||
* can be changed to a single buffer solution when the ring buffer
|
||||
* access is implemented as non-locking atomic code.
|
||||
*/
|
||||
static struct ring_buffer *op_ring_buffer_read;
|
||||
static struct ring_buffer *op_ring_buffer_write;
|
||||
DEFINE_PER_CPU(struct oprofile_cpu_buffer, cpu_buffer);
|
||||
|
||||
static void wq_sync_buffer(struct work_struct *work);
|
||||
|
|
@ -35,19 +55,9 @@ static void wq_sync_buffer(struct work_struct *work);
|
|||
#define DEFAULT_TIMER_EXPIRE (HZ / 10)
|
||||
static int work_enabled;
|
||||
|
||||
void free_cpu_buffers(void)
|
||||
{
|
||||
int i;
|
||||
|
||||
for_each_possible_cpu(i) {
|
||||
vfree(per_cpu(cpu_buffer, i).buffer);
|
||||
per_cpu(cpu_buffer, i).buffer = NULL;
|
||||
}
|
||||
}
|
||||
|
||||
unsigned long oprofile_get_cpu_buffer_size(void)
|
||||
{
|
||||
return fs_cpu_buffer_size;
|
||||
return oprofile_cpu_buffer_size;
|
||||
}
|
||||
|
||||
void oprofile_cpu_buffer_inc_smpl_lost(void)
|
||||
|
|
@ -58,26 +68,36 @@ void oprofile_cpu_buffer_inc_smpl_lost(void)
|
|||
cpu_buf->sample_lost_overflow++;
|
||||
}
|
||||
|
||||
void free_cpu_buffers(void)
|
||||
{
|
||||
if (op_ring_buffer_read)
|
||||
ring_buffer_free(op_ring_buffer_read);
|
||||
op_ring_buffer_read = NULL;
|
||||
if (op_ring_buffer_write)
|
||||
ring_buffer_free(op_ring_buffer_write);
|
||||
op_ring_buffer_write = NULL;
|
||||
}
|
||||
|
||||
int alloc_cpu_buffers(void)
|
||||
{
|
||||
int i;
|
||||
|
||||
unsigned long buffer_size = fs_cpu_buffer_size;
|
||||
unsigned long buffer_size = oprofile_cpu_buffer_size;
|
||||
|
||||
op_ring_buffer_read = ring_buffer_alloc(buffer_size, OP_BUFFER_FLAGS);
|
||||
if (!op_ring_buffer_read)
|
||||
goto fail;
|
||||
op_ring_buffer_write = ring_buffer_alloc(buffer_size, OP_BUFFER_FLAGS);
|
||||
if (!op_ring_buffer_write)
|
||||
goto fail;
|
||||
|
||||
for_each_possible_cpu(i) {
|
||||
struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
|
||||
|
||||
b->buffer = vmalloc_node(sizeof(struct op_sample) * buffer_size,
|
||||
cpu_to_node(i));
|
||||
if (!b->buffer)
|
||||
goto fail;
|
||||
|
||||
b->last_task = NULL;
|
||||
b->last_is_kernel = -1;
|
||||
b->tracing = 0;
|
||||
b->buffer_size = buffer_size;
|
||||
b->tail_pos = 0;
|
||||
b->head_pos = 0;
|
||||
b->sample_received = 0;
|
||||
b->sample_lost_overflow = 0;
|
||||
b->backtrace_aborted = 0;
|
||||
|
|
@ -124,73 +144,156 @@ void end_cpu_work(void)
|
|||
flush_scheduled_work();
|
||||
}
|
||||
|
||||
/* Resets the cpu buffer to a sane state. */
|
||||
void cpu_buffer_reset(struct oprofile_cpu_buffer *cpu_buf)
|
||||
/*
|
||||
* This function prepares the cpu buffer to write a sample.
|
||||
*
|
||||
* Struct op_entry is used during operations on the ring buffer while
|
||||
* struct op_sample contains the data that is stored in the ring
|
||||
* buffer. Struct entry can be uninitialized. The function reserves a
|
||||
* data array that is specified by size. Use
|
||||
* op_cpu_buffer_write_commit() after preparing the sample. In case of
|
||||
* errors a null pointer is returned, otherwise the pointer to the
|
||||
* sample.
|
||||
*
|
||||
*/
|
||||
struct op_sample
|
||||
*op_cpu_buffer_write_reserve(struct op_entry *entry, unsigned long size)
|
||||
{
|
||||
/* reset these to invalid values; the next sample
|
||||
* collected will populate the buffer with proper
|
||||
* values to initialize the buffer
|
||||
*/
|
||||
cpu_buf->last_is_kernel = -1;
|
||||
cpu_buf->last_task = NULL;
|
||||
}
|
||||
|
||||
/* compute number of available slots in cpu_buffer queue */
|
||||
static unsigned long nr_available_slots(struct oprofile_cpu_buffer const *b)
|
||||
{
|
||||
unsigned long head = b->head_pos;
|
||||
unsigned long tail = b->tail_pos;
|
||||
|
||||
if (tail > head)
|
||||
return (tail - head) - 1;
|
||||
|
||||
return tail + (b->buffer_size - head) - 1;
|
||||
}
|
||||
|
||||
static void increment_head(struct oprofile_cpu_buffer *b)
|
||||
{
|
||||
unsigned long new_head = b->head_pos + 1;
|
||||
|
||||
/* Ensure anything written to the slot before we
|
||||
* increment is visible */
|
||||
wmb();
|
||||
|
||||
if (new_head < b->buffer_size)
|
||||
b->head_pos = new_head;
|
||||
entry->event = ring_buffer_lock_reserve
|
||||
(op_ring_buffer_write, sizeof(struct op_sample) +
|
||||
size * sizeof(entry->sample->data[0]), &entry->irq_flags);
|
||||
if (entry->event)
|
||||
entry->sample = ring_buffer_event_data(entry->event);
|
||||
else
|
||||
b->head_pos = 0;
|
||||
entry->sample = NULL;
|
||||
|
||||
if (!entry->sample)
|
||||
return NULL;
|
||||
|
||||
entry->size = size;
|
||||
entry->data = entry->sample->data;
|
||||
|
||||
return entry->sample;
|
||||
}
|
||||
|
||||
static inline void
|
||||
add_sample(struct oprofile_cpu_buffer *cpu_buf,
|
||||
unsigned long pc, unsigned long event)
|
||||
int op_cpu_buffer_write_commit(struct op_entry *entry)
|
||||
{
|
||||
struct op_sample *entry = &cpu_buf->buffer[cpu_buf->head_pos];
|
||||
entry->eip = pc;
|
||||
entry->event = event;
|
||||
increment_head(cpu_buf);
|
||||
return ring_buffer_unlock_commit(op_ring_buffer_write, entry->event,
|
||||
entry->irq_flags);
|
||||
}
|
||||
|
||||
static inline void
|
||||
add_code(struct oprofile_cpu_buffer *buffer, unsigned long value)
|
||||
struct op_sample *op_cpu_buffer_read_entry(struct op_entry *entry, int cpu)
|
||||
{
|
||||
add_sample(buffer, ESCAPE_CODE, value);
|
||||
struct ring_buffer_event *e;
|
||||
e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL);
|
||||
if (e)
|
||||
goto event;
|
||||
if (ring_buffer_swap_cpu(op_ring_buffer_read,
|
||||
op_ring_buffer_write,
|
||||
cpu))
|
||||
return NULL;
|
||||
e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL);
|
||||
if (e)
|
||||
goto event;
|
||||
return NULL;
|
||||
|
||||
event:
|
||||
entry->event = e;
|
||||
entry->sample = ring_buffer_event_data(e);
|
||||
entry->size = (ring_buffer_event_length(e) - sizeof(struct op_sample))
|
||||
/ sizeof(entry->sample->data[0]);
|
||||
entry->data = entry->sample->data;
|
||||
return entry->sample;
|
||||
}
|
||||
|
||||
/* This must be safe from any context. It's safe writing here
|
||||
* because of the head/tail separation of the writer and reader
|
||||
* of the CPU buffer.
|
||||
unsigned long op_cpu_buffer_entries(int cpu)
|
||||
{
|
||||
return ring_buffer_entries_cpu(op_ring_buffer_read, cpu)
|
||||
+ ring_buffer_entries_cpu(op_ring_buffer_write, cpu);
|
||||
}
|
||||
|
||||
static int
|
||||
op_add_code(struct oprofile_cpu_buffer *cpu_buf, unsigned long backtrace,
|
||||
int is_kernel, struct task_struct *task)
|
||||
{
|
||||
struct op_entry entry;
|
||||
struct op_sample *sample;
|
||||
unsigned long flags;
|
||||
int size;
|
||||
|
||||
flags = 0;
|
||||
|
||||
if (backtrace)
|
||||
flags |= TRACE_BEGIN;
|
||||
|
||||
/* notice a switch from user->kernel or vice versa */
|
||||
is_kernel = !!is_kernel;
|
||||
if (cpu_buf->last_is_kernel != is_kernel) {
|
||||
cpu_buf->last_is_kernel = is_kernel;
|
||||
flags |= KERNEL_CTX_SWITCH;
|
||||
if (is_kernel)
|
||||
flags |= IS_KERNEL;
|
||||
}
|
||||
|
||||
/* notice a task switch */
|
||||
if (cpu_buf->last_task != task) {
|
||||
cpu_buf->last_task = task;
|
||||
flags |= USER_CTX_SWITCH;
|
||||
}
|
||||
|
||||
if (!flags)
|
||||
/* nothing to do */
|
||||
return 0;
|
||||
|
||||
if (flags & USER_CTX_SWITCH)
|
||||
size = 1;
|
||||
else
|
||||
size = 0;
|
||||
|
||||
sample = op_cpu_buffer_write_reserve(&entry, size);
|
||||
if (!sample)
|
||||
return -ENOMEM;
|
||||
|
||||
sample->eip = ESCAPE_CODE;
|
||||
sample->event = flags;
|
||||
|
||||
if (size)
|
||||
op_cpu_buffer_add_data(&entry, (unsigned long)task);
|
||||
|
||||
op_cpu_buffer_write_commit(&entry);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static inline int
|
||||
op_add_sample(struct oprofile_cpu_buffer *cpu_buf,
|
||||
unsigned long pc, unsigned long event)
|
||||
{
|
||||
struct op_entry entry;
|
||||
struct op_sample *sample;
|
||||
|
||||
sample = op_cpu_buffer_write_reserve(&entry, 0);
|
||||
if (!sample)
|
||||
return -ENOMEM;
|
||||
|
||||
sample->eip = pc;
|
||||
sample->event = event;
|
||||
|
||||
return op_cpu_buffer_write_commit(&entry);
|
||||
}
|
||||
|
||||
/*
|
||||
* This must be safe from any context.
|
||||
*
|
||||
* is_kernel is needed because on some architectures you cannot
|
||||
* tell if you are in kernel or user space simply by looking at
|
||||
* pc. We tag this in the buffer by generating kernel enter/exit
|
||||
* events whenever is_kernel changes
|
||||
*/
|
||||
static int log_sample(struct oprofile_cpu_buffer *cpu_buf, unsigned long pc,
|
||||
int is_kernel, unsigned long event)
|
||||
static int
|
||||
log_sample(struct oprofile_cpu_buffer *cpu_buf, unsigned long pc,
|
||||
unsigned long backtrace, int is_kernel, unsigned long event)
|
||||
{
|
||||
struct task_struct *task;
|
||||
|
||||
cpu_buf->sample_received++;
|
||||
|
||||
if (pc == ESCAPE_CODE) {
|
||||
|
|
@ -198,131 +301,115 @@ static int log_sample(struct oprofile_cpu_buffer *cpu_buf, unsigned long pc,
|
|||
return 0;
|
||||
}
|
||||
|
||||
if (nr_available_slots(cpu_buf) < 3) {
|
||||
cpu_buf->sample_lost_overflow++;
|
||||
return 0;
|
||||
}
|
||||
if (op_add_code(cpu_buf, backtrace, is_kernel, current))
|
||||
goto fail;
|
||||
|
||||
is_kernel = !!is_kernel;
|
||||
if (op_add_sample(cpu_buf, pc, event))
|
||||
goto fail;
|
||||
|
||||
task = current;
|
||||
|
||||
/* notice a switch from user->kernel or vice versa */
|
||||
if (cpu_buf->last_is_kernel != is_kernel) {
|
||||
cpu_buf->last_is_kernel = is_kernel;
|
||||
add_code(cpu_buf, is_kernel);
|
||||
}
|
||||
|
||||
/* notice a task switch */
|
||||
if (cpu_buf->last_task != task) {
|
||||
cpu_buf->last_task = task;
|
||||
add_code(cpu_buf, (unsigned long)task);
|
||||
}
|
||||
|
||||
add_sample(cpu_buf, pc, event);
|
||||
return 1;
|
||||
|
||||
fail:
|
||||
cpu_buf->sample_lost_overflow++;
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int oprofile_begin_trace(struct oprofile_cpu_buffer *cpu_buf)
|
||||
static inline void oprofile_begin_trace(struct oprofile_cpu_buffer *cpu_buf)
|
||||
{
|
||||
if (nr_available_slots(cpu_buf) < 4) {
|
||||
cpu_buf->sample_lost_overflow++;
|
||||
return 0;
|
||||
}
|
||||
|
||||
add_code(cpu_buf, CPU_TRACE_BEGIN);
|
||||
cpu_buf->tracing = 1;
|
||||
return 1;
|
||||
}
|
||||
|
||||
static void oprofile_end_trace(struct oprofile_cpu_buffer *cpu_buf)
|
||||
static inline void oprofile_end_trace(struct oprofile_cpu_buffer *cpu_buf)
|
||||
{
|
||||
cpu_buf->tracing = 0;
|
||||
}
|
||||
|
||||
void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
|
||||
unsigned long event, int is_kernel)
|
||||
static inline void
|
||||
__oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
|
||||
unsigned long event, int is_kernel)
|
||||
{
|
||||
struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
|
||||
unsigned long backtrace = oprofile_backtrace_depth;
|
||||
|
||||
if (!backtrace_depth) {
|
||||
log_sample(cpu_buf, pc, is_kernel, event);
|
||||
return;
|
||||
}
|
||||
|
||||
if (!oprofile_begin_trace(cpu_buf))
|
||||
/*
|
||||
* if log_sample() fail we can't backtrace since we lost the
|
||||
* source of this event
|
||||
*/
|
||||
if (!log_sample(cpu_buf, pc, backtrace, is_kernel, event))
|
||||
/* failed */
|
||||
return;
|
||||
|
||||
/* if log_sample() fail we can't backtrace since we lost the source
|
||||
* of this event */
|
||||
if (log_sample(cpu_buf, pc, is_kernel, event))
|
||||
oprofile_ops.backtrace(regs, backtrace_depth);
|
||||
if (!backtrace)
|
||||
return;
|
||||
|
||||
oprofile_begin_trace(cpu_buf);
|
||||
oprofile_ops.backtrace(regs, backtrace);
|
||||
oprofile_end_trace(cpu_buf);
|
||||
}
|
||||
|
||||
void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
|
||||
unsigned long event, int is_kernel)
|
||||
{
|
||||
__oprofile_add_ext_sample(pc, regs, event, is_kernel);
|
||||
}
|
||||
|
||||
void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
|
||||
{
|
||||
int is_kernel = !user_mode(regs);
|
||||
unsigned long pc = profile_pc(regs);
|
||||
|
||||
oprofile_add_ext_sample(pc, regs, event, is_kernel);
|
||||
__oprofile_add_ext_sample(pc, regs, event, is_kernel);
|
||||
}
|
||||
|
||||
#ifdef CONFIG_OPROFILE_IBS
|
||||
|
||||
#define MAX_IBS_SAMPLE_SIZE 14
|
||||
|
||||
void oprofile_add_ibs_sample(struct pt_regs *const regs,
|
||||
unsigned int *const ibs_sample, int ibs_code)
|
||||
/*
|
||||
* Add samples with data to the ring buffer.
|
||||
*
|
||||
* Use oprofile_add_data(&entry, val) to add data and
|
||||
* oprofile_write_commit(&entry) to commit the sample.
|
||||
*/
|
||||
void
|
||||
oprofile_write_reserve(struct op_entry *entry, struct pt_regs * const regs,
|
||||
unsigned long pc, int code, int size)
|
||||
{
|
||||
struct op_sample *sample;
|
||||
int is_kernel = !user_mode(regs);
|
||||
struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
|
||||
struct task_struct *task;
|
||||
|
||||
cpu_buf->sample_received++;
|
||||
|
||||
if (nr_available_slots(cpu_buf) < MAX_IBS_SAMPLE_SIZE) {
|
||||
/* we can't backtrace since we lost the source of this event */
|
||||
cpu_buf->sample_lost_overflow++;
|
||||
return;
|
||||
}
|
||||
/* no backtraces for samples with data */
|
||||
if (op_add_code(cpu_buf, 0, is_kernel, current))
|
||||
goto fail;
|
||||
|
||||
/* notice a switch from user->kernel or vice versa */
|
||||
if (cpu_buf->last_is_kernel != is_kernel) {
|
||||
cpu_buf->last_is_kernel = is_kernel;
|
||||
add_code(cpu_buf, is_kernel);
|
||||
}
|
||||
sample = op_cpu_buffer_write_reserve(entry, size + 2);
|
||||
if (!sample)
|
||||
goto fail;
|
||||
sample->eip = ESCAPE_CODE;
|
||||
sample->event = 0; /* no flags */
|
||||
|
||||
/* notice a task switch */
|
||||
if (!is_kernel) {
|
||||
task = current;
|
||||
if (cpu_buf->last_task != task) {
|
||||
cpu_buf->last_task = task;
|
||||
add_code(cpu_buf, (unsigned long)task);
|
||||
}
|
||||
}
|
||||
op_cpu_buffer_add_data(entry, code);
|
||||
op_cpu_buffer_add_data(entry, pc);
|
||||
|
||||
add_code(cpu_buf, ibs_code);
|
||||
add_sample(cpu_buf, ibs_sample[0], ibs_sample[1]);
|
||||
add_sample(cpu_buf, ibs_sample[2], ibs_sample[3]);
|
||||
add_sample(cpu_buf, ibs_sample[4], ibs_sample[5]);
|
||||
return;
|
||||
|
||||
if (ibs_code == IBS_OP_BEGIN) {
|
||||
add_sample(cpu_buf, ibs_sample[6], ibs_sample[7]);
|
||||
add_sample(cpu_buf, ibs_sample[8], ibs_sample[9]);
|
||||
add_sample(cpu_buf, ibs_sample[10], ibs_sample[11]);
|
||||
}
|
||||
|
||||
if (backtrace_depth)
|
||||
oprofile_ops.backtrace(regs, backtrace_depth);
|
||||
fail:
|
||||
cpu_buf->sample_lost_overflow++;
|
||||
}
|
||||
|
||||
#endif
|
||||
int oprofile_add_data(struct op_entry *entry, unsigned long val)
|
||||
{
|
||||
return op_cpu_buffer_add_data(entry, val);
|
||||
}
|
||||
|
||||
int oprofile_write_commit(struct op_entry *entry)
|
||||
{
|
||||
return op_cpu_buffer_write_commit(entry);
|
||||
}
|
||||
|
||||
void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
|
||||
{
|
||||
struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
|
||||
log_sample(cpu_buf, pc, is_kernel, event);
|
||||
log_sample(cpu_buf, pc, 0, is_kernel, event);
|
||||
}
|
||||
|
||||
void oprofile_add_trace(unsigned long pc)
|
||||
|
|
@ -332,21 +419,21 @@ void oprofile_add_trace(unsigned long pc)
|
|||
if (!cpu_buf->tracing)
|
||||
return;
|
||||
|
||||
if (nr_available_slots(cpu_buf) < 1) {
|
||||
cpu_buf->tracing = 0;
|
||||
cpu_buf->sample_lost_overflow++;
|
||||
return;
|
||||
}
|
||||
/*
|
||||
* broken frame can give an eip with the same value as an
|
||||
* escape code, abort the trace if we get it
|
||||
*/
|
||||
if (pc == ESCAPE_CODE)
|
||||
goto fail;
|
||||
|
||||
/* broken frame can give an eip with the same value as an escape code,
|
||||
* abort the trace if we get it */
|
||||
if (pc == ESCAPE_CODE) {
|
||||
cpu_buf->tracing = 0;
|
||||
cpu_buf->backtrace_aborted++;
|
||||
return;
|
||||
}
|
||||
if (op_add_sample(cpu_buf, pc, 0))
|
||||
goto fail;
|
||||
|
||||
add_sample(cpu_buf, pc, 0);
|
||||
return;
|
||||
fail:
|
||||
cpu_buf->tracing = 0;
|
||||
cpu_buf->backtrace_aborted++;
|
||||
return;
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
|
|||
|
|
@ -1,10 +1,11 @@
|
|||
/**
|
||||
* @file cpu_buffer.h
|
||||
*
|
||||
* @remark Copyright 2002 OProfile authors
|
||||
* @remark Copyright 2002-2009 OProfile authors
|
||||
* @remark Read the file COPYING
|
||||
*
|
||||
* @author John Levon <levon@movementarian.org>
|
||||
* @author Robert Richter <robert.richter@amd.com>
|
||||
*/
|
||||
|
||||
#ifndef OPROFILE_CPU_BUFFER_H
|
||||
|
|
@ -15,6 +16,7 @@
|
|||
#include <linux/workqueue.h>
|
||||
#include <linux/cache.h>
|
||||
#include <linux/sched.h>
|
||||
#include <linux/ring_buffer.h>
|
||||
|
||||
struct task_struct;
|
||||
|
||||
|
|
@ -30,16 +32,16 @@ void end_cpu_work(void);
|
|||
struct op_sample {
|
||||
unsigned long eip;
|
||||
unsigned long event;
|
||||
unsigned long data[0];
|
||||
};
|
||||
|
||||
struct op_entry;
|
||||
|
||||
struct oprofile_cpu_buffer {
|
||||
volatile unsigned long head_pos;
|
||||
volatile unsigned long tail_pos;
|
||||
unsigned long buffer_size;
|
||||
struct task_struct *last_task;
|
||||
int last_is_kernel;
|
||||
int tracing;
|
||||
struct op_sample *buffer;
|
||||
unsigned long sample_received;
|
||||
unsigned long sample_lost_overflow;
|
||||
unsigned long backtrace_aborted;
|
||||
|
|
@ -50,12 +52,62 @@ struct oprofile_cpu_buffer {
|
|||
|
||||
DECLARE_PER_CPU(struct oprofile_cpu_buffer, cpu_buffer);
|
||||
|
||||
void cpu_buffer_reset(struct oprofile_cpu_buffer *cpu_buf);
|
||||
/*
|
||||
* Resets the cpu buffer to a sane state.
|
||||
*
|
||||
* reset these to invalid values; the next sample collected will
|
||||
* populate the buffer with proper values to initialize the buffer
|
||||
*/
|
||||
static inline void op_cpu_buffer_reset(int cpu)
|
||||
{
|
||||
struct oprofile_cpu_buffer *cpu_buf = &per_cpu(cpu_buffer, cpu);
|
||||
|
||||
/* transient events for the CPU buffer -> event buffer */
|
||||
#define CPU_IS_KERNEL 1
|
||||
#define CPU_TRACE_BEGIN 2
|
||||
#define IBS_FETCH_BEGIN 3
|
||||
#define IBS_OP_BEGIN 4
|
||||
cpu_buf->last_is_kernel = -1;
|
||||
cpu_buf->last_task = NULL;
|
||||
}
|
||||
|
||||
struct op_sample
|
||||
*op_cpu_buffer_write_reserve(struct op_entry *entry, unsigned long size);
|
||||
int op_cpu_buffer_write_commit(struct op_entry *entry);
|
||||
struct op_sample *op_cpu_buffer_read_entry(struct op_entry *entry, int cpu);
|
||||
unsigned long op_cpu_buffer_entries(int cpu);
|
||||
|
||||
/* returns the remaining free size of data in the entry */
|
||||
static inline
|
||||
int op_cpu_buffer_add_data(struct op_entry *entry, unsigned long val)
|
||||
{
|
||||
if (!entry->size)
|
||||
return 0;
|
||||
*entry->data = val;
|
||||
entry->size--;
|
||||
entry->data++;
|
||||
return entry->size;
|
||||
}
|
||||
|
||||
/* returns the size of data in the entry */
|
||||
static inline
|
||||
int op_cpu_buffer_get_size(struct op_entry *entry)
|
||||
{
|
||||
return entry->size;
|
||||
}
|
||||
|
||||
/* returns 0 if empty or the size of data including the current value */
|
||||
static inline
|
||||
int op_cpu_buffer_get_data(struct op_entry *entry, unsigned long *val)
|
||||
{
|
||||
int size = entry->size;
|
||||
if (!size)
|
||||
return 0;
|
||||
*val = *entry->data;
|
||||
entry->size--;
|
||||
entry->data++;
|
||||
return size;
|
||||
}
|
||||
|
||||
/* extra data flags */
|
||||
#define KERNEL_CTX_SWITCH (1UL << 0)
|
||||
#define IS_KERNEL (1UL << 1)
|
||||
#define TRACE_BEGIN (1UL << 2)
|
||||
#define USER_CTX_SWITCH (1UL << 3)
|
||||
|
||||
#endif /* OPROFILE_CPU_BUFFER_H */
|
||||
|
|
|
|||
|
|
@ -73,8 +73,8 @@ int alloc_event_buffer(void)
|
|||
unsigned long flags;
|
||||
|
||||
spin_lock_irqsave(&oprofilefs_lock, flags);
|
||||
buffer_size = fs_buffer_size;
|
||||
buffer_watershed = fs_buffer_watershed;
|
||||
buffer_size = oprofile_buffer_size;
|
||||
buffer_watershed = oprofile_buffer_watershed;
|
||||
spin_unlock_irqrestore(&oprofilefs_lock, flags);
|
||||
|
||||
if (buffer_watershed >= buffer_size)
|
||||
|
|
|
|||
|
|
@ -23,7 +23,7 @@
|
|||
struct oprofile_operations oprofile_ops;
|
||||
|
||||
unsigned long oprofile_started;
|
||||
unsigned long backtrace_depth;
|
||||
unsigned long oprofile_backtrace_depth;
|
||||
static unsigned long is_setup;
|
||||
static DEFINE_MUTEX(start_mutex);
|
||||
|
||||
|
|
@ -172,7 +172,7 @@ int oprofile_set_backtrace(unsigned long val)
|
|||
goto out;
|
||||
}
|
||||
|
||||
backtrace_depth = val;
|
||||
oprofile_backtrace_depth = val;
|
||||
|
||||
out:
|
||||
mutex_unlock(&start_mutex);
|
||||
|
|
|
|||
|
|
@ -21,12 +21,12 @@ void oprofile_stop(void);
|
|||
|
||||
struct oprofile_operations;
|
||||
|
||||
extern unsigned long fs_buffer_size;
|
||||
extern unsigned long fs_cpu_buffer_size;
|
||||
extern unsigned long fs_buffer_watershed;
|
||||
extern unsigned long oprofile_buffer_size;
|
||||
extern unsigned long oprofile_cpu_buffer_size;
|
||||
extern unsigned long oprofile_buffer_watershed;
|
||||
extern struct oprofile_operations oprofile_ops;
|
||||
extern unsigned long oprofile_started;
|
||||
extern unsigned long backtrace_depth;
|
||||
extern unsigned long oprofile_backtrace_depth;
|
||||
|
||||
struct super_block;
|
||||
struct dentry;
|
||||
|
|
|
|||
|
|
@ -14,13 +14,18 @@
|
|||
#include "oprofile_stats.h"
|
||||
#include "oprof.h"
|
||||
|
||||
unsigned long fs_buffer_size = 131072;
|
||||
unsigned long fs_cpu_buffer_size = 8192;
|
||||
unsigned long fs_buffer_watershed = 32768; /* FIXME: tune */
|
||||
#define BUFFER_SIZE_DEFAULT 131072
|
||||
#define CPU_BUFFER_SIZE_DEFAULT 8192
|
||||
#define BUFFER_WATERSHED_DEFAULT 32768 /* FIXME: tune */
|
||||
|
||||
unsigned long oprofile_buffer_size;
|
||||
unsigned long oprofile_cpu_buffer_size;
|
||||
unsigned long oprofile_buffer_watershed;
|
||||
|
||||
static ssize_t depth_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
|
||||
{
|
||||
return oprofilefs_ulong_to_user(backtrace_depth, buf, count, offset);
|
||||
return oprofilefs_ulong_to_user(oprofile_backtrace_depth, buf, count,
|
||||
offset);
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -120,12 +125,17 @@ static const struct file_operations dump_fops = {
|
|||
|
||||
void oprofile_create_files(struct super_block *sb, struct dentry *root)
|
||||
{
|
||||
/* reinitialize default values */
|
||||
oprofile_buffer_size = BUFFER_SIZE_DEFAULT;
|
||||
oprofile_cpu_buffer_size = CPU_BUFFER_SIZE_DEFAULT;
|
||||
oprofile_buffer_watershed = BUFFER_WATERSHED_DEFAULT;
|
||||
|
||||
oprofilefs_create_file(sb, root, "enable", &enable_fops);
|
||||
oprofilefs_create_file_perm(sb, root, "dump", &dump_fops, 0666);
|
||||
oprofilefs_create_file(sb, root, "buffer", &event_buffer_fops);
|
||||
oprofilefs_create_ulong(sb, root, "buffer_size", &fs_buffer_size);
|
||||
oprofilefs_create_ulong(sb, root, "buffer_watershed", &fs_buffer_watershed);
|
||||
oprofilefs_create_ulong(sb, root, "cpu_buffer_size", &fs_cpu_buffer_size);
|
||||
oprofilefs_create_ulong(sb, root, "buffer_size", &oprofile_buffer_size);
|
||||
oprofilefs_create_ulong(sb, root, "buffer_watershed", &oprofile_buffer_watershed);
|
||||
oprofilefs_create_ulong(sb, root, "cpu_buffer_size", &oprofile_cpu_buffer_size);
|
||||
oprofilefs_create_file(sb, root, "cpu_type", &cpu_type_fops);
|
||||
oprofilefs_create_file(sb, root, "backtrace_depth", &depth_fops);
|
||||
oprofilefs_create_file(sb, root, "pointer_size", &pointer_size_fops);
|
||||
|
|
|
|||
|
|
@ -86,8 +86,7 @@ int oprofile_arch_init(struct oprofile_operations * ops);
|
|||
void oprofile_arch_exit(void);
|
||||
|
||||
/**
|
||||
* Add a sample. This may be called from any context. Pass
|
||||
* smp_processor_id() as cpu.
|
||||
* Add a sample. This may be called from any context.
|
||||
*/
|
||||
void oprofile_add_sample(struct pt_regs * const regs, unsigned long event);
|
||||
|
||||
|
|
@ -165,4 +164,22 @@ void oprofile_put_buff(unsigned long *buf, unsigned int start,
|
|||
unsigned long oprofile_get_cpu_buffer_size(void);
|
||||
void oprofile_cpu_buffer_inc_smpl_lost(void);
|
||||
|
||||
/* cpu buffer functions */
|
||||
|
||||
struct op_sample;
|
||||
|
||||
struct op_entry {
|
||||
struct ring_buffer_event *event;
|
||||
struct op_sample *sample;
|
||||
unsigned long irq_flags;
|
||||
unsigned long size;
|
||||
unsigned long *data;
|
||||
};
|
||||
|
||||
void oprofile_write_reserve(struct op_entry *entry,
|
||||
struct pt_regs * const regs,
|
||||
unsigned long pc, int code, int size);
|
||||
int oprofile_add_data(struct op_entry *entry, unsigned long val);
|
||||
int oprofile_write_commit(struct op_entry *entry);
|
||||
|
||||
#endif /* OPROFILE_H */
|
||||
|
|
|
|||
|
|
@ -116,6 +116,8 @@ void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
|
|||
|
||||
unsigned long ring_buffer_entries(struct ring_buffer *buffer);
|
||||
unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
|
||||
unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
|
||||
unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
|
||||
|
||||
u64 ring_buffer_time_stamp(int cpu);
|
||||
void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
|
||||
|
|
|
|||
|
|
@ -31,6 +31,7 @@ void tracing_on(void)
|
|||
{
|
||||
ring_buffers_off = 0;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(tracing_on);
|
||||
|
||||
/**
|
||||
* tracing_off - turn off all tracing buffers
|
||||
|
|
@ -44,6 +45,7 @@ void tracing_off(void)
|
|||
{
|
||||
ring_buffers_off = 1;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(tracing_off);
|
||||
|
||||
/* Up this if you want to test the TIME_EXTENTS and normalization */
|
||||
#define DEBUG_SHIFT 0
|
||||
|
|
@ -60,12 +62,14 @@ u64 ring_buffer_time_stamp(int cpu)
|
|||
|
||||
return time;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_time_stamp);
|
||||
|
||||
void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
|
||||
{
|
||||
/* Just stupid testing the normalize function and deltas */
|
||||
*ts >>= DEBUG_SHIFT;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
|
||||
|
||||
#define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
|
||||
#define RB_ALIGNMENT_SHIFT 2
|
||||
|
|
@ -113,8 +117,15 @@ rb_event_length(struct ring_buffer_event *event)
|
|||
*/
|
||||
unsigned ring_buffer_event_length(struct ring_buffer_event *event)
|
||||
{
|
||||
return rb_event_length(event);
|
||||
unsigned length = rb_event_length(event);
|
||||
if (event->type != RINGBUF_TYPE_DATA)
|
||||
return length;
|
||||
length -= RB_EVNT_HDR_SIZE;
|
||||
if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]))
|
||||
length -= sizeof(event->array[0]);
|
||||
return length;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_event_length);
|
||||
|
||||
/* inline for ring buffer fast paths */
|
||||
static inline void *
|
||||
|
|
@ -136,6 +147,7 @@ void *ring_buffer_event_data(struct ring_buffer_event *event)
|
|||
{
|
||||
return rb_event_data(event);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_event_data);
|
||||
|
||||
#define for_each_buffer_cpu(buffer, cpu) \
|
||||
for_each_cpu_mask(cpu, buffer->cpumask)
|
||||
|
|
@ -381,7 +393,7 @@ extern int ring_buffer_page_too_big(void);
|
|||
|
||||
/**
|
||||
* ring_buffer_alloc - allocate a new ring_buffer
|
||||
* @size: the size in bytes that is needed.
|
||||
* @size: the size in bytes per cpu that is needed.
|
||||
* @flags: attributes to set for the ring buffer.
|
||||
*
|
||||
* Currently the only flag that is available is the RB_FL_OVERWRITE
|
||||
|
|
@ -444,6 +456,7 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
|
|||
kfree(buffer);
|
||||
return NULL;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_alloc);
|
||||
|
||||
/**
|
||||
* ring_buffer_free - free a ring buffer.
|
||||
|
|
@ -459,6 +472,7 @@ ring_buffer_free(struct ring_buffer *buffer)
|
|||
|
||||
kfree(buffer);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_free);
|
||||
|
||||
static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
|
||||
|
||||
|
|
@ -620,6 +634,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
|
|||
mutex_unlock(&buffer->mutex);
|
||||
return -ENOMEM;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_resize);
|
||||
|
||||
static inline int rb_null_event(struct ring_buffer_event *event)
|
||||
{
|
||||
|
|
@ -1220,6 +1235,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
|
|||
preempt_enable_notrace();
|
||||
return NULL;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
|
||||
|
||||
static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
|
||||
struct ring_buffer_event *event)
|
||||
|
|
@ -1269,6 +1285,7 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
|
|||
|
||||
return 0;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
|
||||
|
||||
/**
|
||||
* ring_buffer_write - write data to the buffer without reserving
|
||||
|
|
@ -1334,6 +1351,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
|
|||
|
||||
return ret;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_write);
|
||||
|
||||
static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
|
||||
{
|
||||
|
|
@ -1360,6 +1378,7 @@ void ring_buffer_record_disable(struct ring_buffer *buffer)
|
|||
{
|
||||
atomic_inc(&buffer->record_disabled);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
|
||||
|
||||
/**
|
||||
* ring_buffer_record_enable - enable writes to the buffer
|
||||
|
|
@ -1372,6 +1391,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer)
|
|||
{
|
||||
atomic_dec(&buffer->record_disabled);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_record_enable);
|
||||
|
||||
/**
|
||||
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
|
||||
|
|
@ -1393,6 +1413,7 @@ void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu)
|
|||
cpu_buffer = buffer->buffers[cpu];
|
||||
atomic_inc(&cpu_buffer->record_disabled);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
|
||||
|
||||
/**
|
||||
* ring_buffer_record_enable_cpu - enable writes to the buffer
|
||||
|
|
@ -1412,6 +1433,7 @@ void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
|
|||
cpu_buffer = buffer->buffers[cpu];
|
||||
atomic_dec(&cpu_buffer->record_disabled);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
|
||||
|
||||
/**
|
||||
* ring_buffer_entries_cpu - get the number of entries in a cpu buffer
|
||||
|
|
@ -1428,6 +1450,7 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
|
|||
cpu_buffer = buffer->buffers[cpu];
|
||||
return cpu_buffer->entries;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
|
||||
|
||||
/**
|
||||
* ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer
|
||||
|
|
@ -1444,6 +1467,7 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
|
|||
cpu_buffer = buffer->buffers[cpu];
|
||||
return cpu_buffer->overrun;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
|
||||
|
||||
/**
|
||||
* ring_buffer_entries - get the number of entries in a buffer
|
||||
|
|
@ -1466,6 +1490,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
|
|||
|
||||
return entries;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_entries);
|
||||
|
||||
/**
|
||||
* ring_buffer_overrun_cpu - get the number of overruns in buffer
|
||||
|
|
@ -1488,6 +1513,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
|
|||
|
||||
return overruns;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_overruns);
|
||||
|
||||
/**
|
||||
* ring_buffer_iter_reset - reset an iterator
|
||||
|
|
@ -1513,6 +1539,7 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
|
|||
else
|
||||
iter->read_stamp = iter->head_page->time_stamp;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
|
||||
|
||||
/**
|
||||
* ring_buffer_iter_empty - check if an iterator has no more to read
|
||||
|
|
@ -1527,6 +1554,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
|
|||
return iter->head_page == cpu_buffer->commit_page &&
|
||||
iter->head == rb_commit_index(cpu_buffer);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);
|
||||
|
||||
static void
|
||||
rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
|
||||
|
|
@ -1797,6 +1825,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
|
|||
|
||||
return NULL;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_peek);
|
||||
|
||||
/**
|
||||
* ring_buffer_iter_peek - peek at the next event to be read
|
||||
|
|
@ -1867,6 +1896,7 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
|
|||
|
||||
return NULL;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
|
||||
|
||||
/**
|
||||
* ring_buffer_consume - return an event and consume it
|
||||
|
|
@ -1894,6 +1924,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
|
|||
|
||||
return event;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_consume);
|
||||
|
||||
/**
|
||||
* ring_buffer_read_start - start a non consuming read of the buffer
|
||||
|
|
@ -1934,6 +1965,7 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
|
|||
|
||||
return iter;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_read_start);
|
||||
|
||||
/**
|
||||
* ring_buffer_finish - finish reading the iterator of the buffer
|
||||
|
|
@ -1950,6 +1982,7 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter)
|
|||
atomic_dec(&cpu_buffer->record_disabled);
|
||||
kfree(iter);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_read_finish);
|
||||
|
||||
/**
|
||||
* ring_buffer_read - read the next item in the ring buffer by the iterator
|
||||
|
|
@ -1971,6 +2004,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
|
|||
|
||||
return event;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_read);
|
||||
|
||||
/**
|
||||
* ring_buffer_size - return the size of the ring buffer (in bytes)
|
||||
|
|
@ -1980,6 +2014,7 @@ unsigned long ring_buffer_size(struct ring_buffer *buffer)
|
|||
{
|
||||
return BUF_PAGE_SIZE * buffer->pages;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_size);
|
||||
|
||||
static void
|
||||
rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
|
||||
|
|
@ -2022,6 +2057,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
|
|||
|
||||
spin_unlock_irqrestore(&cpu_buffer->lock, flags);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
|
||||
|
||||
/**
|
||||
* ring_buffer_reset - reset a ring buffer
|
||||
|
|
@ -2034,6 +2070,7 @@ void ring_buffer_reset(struct ring_buffer *buffer)
|
|||
for_each_buffer_cpu(buffer, cpu)
|
||||
ring_buffer_reset_cpu(buffer, cpu);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_reset);
|
||||
|
||||
/**
|
||||
* rind_buffer_empty - is the ring buffer empty?
|
||||
|
|
@ -2052,6 +2089,7 @@ int ring_buffer_empty(struct ring_buffer *buffer)
|
|||
}
|
||||
return 1;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_empty);
|
||||
|
||||
/**
|
||||
* ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty?
|
||||
|
|
@ -2068,6 +2106,7 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
|
|||
cpu_buffer = buffer->buffers[cpu];
|
||||
return rb_per_cpu_empty(cpu_buffer);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu);
|
||||
|
||||
/**
|
||||
* ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
|
||||
|
|
@ -2117,6 +2156,7 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
|
|||
|
||||
return 0;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
|
||||
|
||||
static ssize_t
|
||||
rb_simple_read(struct file *filp, char __user *ubuf,
|
||||
|
|
|
|||
|
|
@ -914,7 +914,7 @@ enum trace_file_type {
|
|||
TRACE_FILE_LAT_FMT = 1,
|
||||
};
|
||||
|
||||
static void trace_iterator_increment(struct trace_iterator *iter, int cpu)
|
||||
static void trace_iterator_increment(struct trace_iterator *iter)
|
||||
{
|
||||
/* Don't allow ftrace to trace into the ring buffers */
|
||||
ftrace_disable_cpu();
|
||||
|
|
@ -993,7 +993,7 @@ static void *find_next_entry_inc(struct trace_iterator *iter)
|
|||
iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
|
||||
|
||||
if (iter->ent)
|
||||
trace_iterator_increment(iter, iter->cpu);
|
||||
trace_iterator_increment(iter);
|
||||
|
||||
return iter->ent ? iter : NULL;
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue