Merge reason: Pick up the latest perf fixes.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
L: linux-edac@vger.kernel.org
W: bluesmoke.sourceforge.net
S: Maintained
- F: drivers/edac/i7core_edac.c linux/edac_mce.h drivers/edac/edac_mce.c
+ F: drivers/edac/i7core_edac.c
+ F: drivers/edac/edac_mce.c
+ F: include/linux/edac_mce.h
EDAC-I82975X
M: Ranganathan Desikan <ravi@jetztechnologies.com>
F: mm/kmemleak.c
F: mm/kmemleak-test.c
-KMEMTRACE
-M: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
-S: Maintained
-F: Documentation/trace/kmemtrace.txt
-F: include/linux/kmemtrace.h
-F: kernel/trace/kmemtrace.c
-
KPROBES
M: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-next-2.6.git
S: Maintained
F: arch/sparc/
+ F: drivers/sbus
SPARC SERIAL DRIVERS
M: "David S. Miller" <davem@davemloft.net>
M: Steven Rostedt <rostedt@goodmis.org>
M: Frederic Weisbecker <fweisbec@gmail.com>
M: Ingo Molnar <mingo@redhat.com>
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git tracing/core
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf/core
S: Maintained
F: Documentation/trace/ftrace.txt
F: arch/*/*/*/ftrace.h
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 35
- EXTRAVERSION = -rc4
+ EXTRAVERSION = -rc5
NAME = Sheep on Meth
# *DOCUMENTATION*
no-dot-config-targets := clean mrproper distclean \
cscope TAGS tags help %docs check% \
include/linux/version.h headers_% \
- kernelrelease kernelversion
+ kernelrelease kernelversion %src-pkg
config-targets := 0
mixed-targets := 0
# Store (new) KERNELRELASE string in include/config/kernel.release
include/config/kernel.release: include/config/auto.conf FORCE
$(Q)rm -f $@
- $(Q)echo "$(KERNELVERSION)$$($(CONFIG_SHELL) scripts/setlocalversion $(srctree))" > $@
+ $(Q)echo "$(KERNELVERSION)$$($(CONFIG_SHELL) $(srctree)/scripts/setlocalversion $(srctree))" > $@
# Things we need to do before we recursively start building the kernel
# rpm target kept for backward compatibility
package-dir := $(srctree)/scripts/package
+%src-pkg: FORCE
+ $(Q)$(MAKE) $(build)=$(package-dir) $@
%pkg: include/config/kernel.release FORCE
$(Q)$(MAKE) $(build)=$(package-dir) $@
rpm: include/config/kernel.release FORCE
* Therefore we treat them like NMIs.
*/
do {
- prev = atomic64_read(&event->hw.prev_count);
+ prev = local64_read(&event->hw.prev_count);
barrier();
val = read_pmc(event->hw.idx);
- } while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
+ } while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
/* The counters are only 32 bits wide */
delta = (val - prev) & 0xfffffffful;
- atomic64_add(delta, &event->count);
- atomic64_sub(delta, &event->hw.period_left);
+ local64_add(delta, &event->count);
+ local64_sub(delta, &event->hw.period_left);
}
/*
if (!event->hw.idx)
continue;
val = (event->hw.idx == 5) ? pmc5 : pmc6;
- prev = atomic64_read(&event->hw.prev_count);
+ prev = local64_read(&event->hw.prev_count);
event->hw.idx = 0;
delta = (val - prev) & 0xfffffffful;
- atomic64_add(delta, &event->count);
+ local64_add(delta, &event->count);
}
}
event = cpuhw->limited_counter[i];
event->hw.idx = cpuhw->limited_hwidx[i];
val = (event->hw.idx == 5) ? pmc5 : pmc6;
- atomic64_set(&event->hw.prev_count, val);
+ local64_set(&event->hw.prev_count, val);
perf_event_update_userpage(event);
}
}
}
val = 0;
if (event->hw.sample_period) {
- left = atomic64_read(&event->hw.period_left);
+ left = local64_read(&event->hw.period_left);
if (left < 0x80000000L)
val = 0x80000000L - left;
}
- atomic64_set(&event->hw.prev_count, val);
+ local64_set(&event->hw.prev_count, val);
event->hw.idx = idx;
write_pmc(idx, val);
perf_event_update_userpage(event);
* skip the schedulability test here, it will be peformed
* at commit time(->commit_txn) as a whole
*/
- if (cpuhw->group_flag & PERF_EVENT_TXN_STARTED)
+ if (cpuhw->group_flag & PERF_EVENT_TXN)
goto nocheck;
if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1))
cpuhw = &__get_cpu_var(cpu_hw_events);
for (i = 0; i < cpuhw->n_events; ++i) {
if (event == cpuhw->event[i]) {
- while (++i < cpuhw->n_events)
+ while (++i < cpuhw->n_events) {
cpuhw->event[i-1] = cpuhw->event[i];
+ cpuhw->events[i-1] = cpuhw->events[i];
+ cpuhw->flags[i-1] = cpuhw->flags[i];
+ }
--cpuhw->n_events;
ppmu->disable_pmc(event->hw.idx - 1, cpuhw->mmcr);
if (event->hw.idx) {
if (left < 0x80000000L)
val = 0x80000000L - left;
write_pmc(event->hw.idx, val);
- atomic64_set(&event->hw.prev_count, val);
- atomic64_set(&event->hw.period_left, left);
+ local64_set(&event->hw.prev_count, val);
+ local64_set(&event->hw.period_left, left);
perf_event_update_userpage(event);
perf_enable();
local_irq_restore(flags);
{
struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
- cpuhw->group_flag |= PERF_EVENT_TXN_STARTED;
+ cpuhw->group_flag |= PERF_EVENT_TXN;
cpuhw->n_txn_start = cpuhw->n_events;
}
{
struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
- cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED;
+ cpuhw->group_flag &= ~PERF_EVENT_TXN;
}
/*
for (i = cpuhw->n_txn_start; i < n; ++i)
cpuhw->event[i]->hw.config = cpuhw->events[i];
+ cpuhw->group_flag &= ~PERF_EVENT_TXN;
return 0;
}
event->hw.config = events[n];
event->hw.event_base = cflags[n];
event->hw.last_period = event->hw.sample_period;
- atomic64_set(&event->hw.period_left, event->hw.last_period);
+ local64_set(&event->hw.period_left, event->hw.last_period);
/*
* See if we need to reserve the PMU.
int record = 0;
/* we don't have to worry about interrupts here */
- prev = atomic64_read(&event->hw.prev_count);
+ prev = local64_read(&event->hw.prev_count);
delta = (val - prev) & 0xfffffffful;
- atomic64_add(delta, &event->count);
+ local64_add(delta, &event->count);
/*
* See if the total period for this event has expired,
* and update for the next period.
*/
val = 0;
- left = atomic64_read(&event->hw.period_left) - delta;
+ left = local64_read(&event->hw.period_left) - delta;
if (period) {
if (left <= 0) {
left += period;
}
write_pmc(event->hw.idx, val);
- atomic64_set(&event->hw.prev_count, val);
- atomic64_set(&event->hw.period_left, left);
+ local64_set(&event->hw.prev_count, val);
+ local64_set(&event->hw.period_left, left);
perf_event_update_userpage(event);
}
s64 delta;
again:
- prev_raw_count = atomic64_read(&hwc->prev_count);
+ prev_raw_count = local64_read(&hwc->prev_count);
new_raw_count = read_pmc(idx);
- if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+ if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
new_raw_count) != prev_raw_count)
goto again;
delta = (new_raw_count << shift) - (prev_raw_count << shift);
delta >>= shift;
- atomic64_add(delta, &event->count);
- atomic64_sub(delta, &hwc->period_left);
+ local64_add(delta, &event->count);
+ local64_sub(delta, &hwc->period_left);
return new_raw_count;
}
static int sparc_perf_event_set_period(struct perf_event *event,
struct hw_perf_event *hwc, int idx)
{
- s64 left = atomic64_read(&hwc->period_left);
+ s64 left = local64_read(&hwc->period_left);
s64 period = hwc->sample_period;
int ret = 0;
if (unlikely(left <= -period)) {
left = period;
- atomic64_set(&hwc->period_left, left);
+ local64_set(&hwc->period_left, left);
hwc->last_period = period;
ret = 1;
}
if (unlikely(left <= 0)) {
left += period;
- atomic64_set(&hwc->period_left, left);
+ local64_set(&hwc->period_left, left);
hwc->last_period = period;
ret = 1;
}
if (left > MAX_PERIOD)
left = MAX_PERIOD;
- atomic64_set(&hwc->prev_count, (u64)-left);
+ local64_set(&hwc->prev_count, (u64)-left);
write_pmc(idx, (u64)(-left) & 0xffffffff);
cpuc->current_idx[i] = idx;
enc = perf_event_get_enc(cpuc->events[i]);
+ pcr &= ~mask_for_index(idx);
pcr |= event_encoding(enc, idx);
}
out:
* skip the schedulability test here, it will be peformed
* at commit time(->commit_txn) as a whole
*/
- if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+ if (cpuc->group_flag & PERF_EVENT_TXN)
goto nocheck;
if (check_excludes(cpuc->event, n0, 1))
if (!hwc->sample_period) {
hwc->sample_period = MAX_PERIOD;
hwc->last_period = hwc->sample_period;
- atomic64_set(&hwc->period_left, hwc->sample_period);
+ local64_set(&hwc->period_left, hwc->sample_period);
}
return 0;
{
struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
- cpuhw->group_flag |= PERF_EVENT_TXN_STARTED;
+ cpuhw->group_flag |= PERF_EVENT_TXN;
}
/*
{
struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
- cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED;
+ cpuhw->group_flag &= ~PERF_EVENT_TXN;
}
/*
if (sparc_check_constraints(cpuc->event, cpuc->events, n))
return -EAGAIN;
+ cpuc->group_flag &= ~PERF_EVENT_TXN;
return 0;
}
}
/*
- * Check for the REX prefix which can only exist on X86_64
- * X86_32 always returns 0
+ * Skip the prefixes of the instruction.
*/
-static int __kprobes is_REX_prefix(kprobe_opcode_t *insn)
+static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
{
+ insn_attr_t attr;
+
+ attr = inat_get_opcode_attribute((insn_byte_t)*insn);
+ while (inat_is_legacy_prefix(attr)) {
+ insn++;
+ attr = inat_get_opcode_attribute((insn_byte_t)*insn);
+ }
#ifdef CONFIG_X86_64
- if ((*insn & 0xf0) == 0x40)
- return 1;
+ if (inat_is_rex_prefix(attr))
+ insn++;
#endif
- return 0;
+ return insn;
}
/*
*/
static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
{
+ /* Skip prefixes */
+ insn = skip_prefixes(insn);
+
switch (*insn) {
case 0xfa: /* cli */
case 0xfb: /* sti */
return 1;
}
- /*
- * on X86_64, 0x40-0x4f are REX prefixes so we need to look
- * at the next byte instead.. but of course not recurse infinitely
- */
- if (is_REX_prefix(insn))
- return is_IF_modifier(++insn);
-
return 0;
}
/* Skip cs, ip, orig_ax and gs. */ \
" subl $16, %esp\n" \
" pushl %fs\n" \
- " pushl %ds\n" \
" pushl %es\n" \
+ " pushl %ds\n" \
" pushl %eax\n" \
" pushl %ebp\n" \
" pushl %edi\n" \
unsigned long orig_ip = (unsigned long)p->addr;
kprobe_opcode_t *insn = p->ainsn.insn;
- /*skip the REX prefix*/
- if (is_REX_prefix(insn))
- insn++;
+ /* Skip prefixes */
+ insn = skip_prefixes(insn);
regs->flags &= ~X86_EFLAGS_TF;
switch (*insn) {
extern struct trace_event_functions exit_syscall_print_funcs;
#define SYSCALL_TRACE_ENTER_EVENT(sname) \
- static struct syscall_metadata __syscall_meta_##sname; \
+ static struct syscall_metadata \
+ __attribute__((__aligned__(4))) __syscall_meta_##sname; \
static struct ftrace_event_call \
__attribute__((__aligned__(4))) event_enter_##sname; \
static struct ftrace_event_call __used \
}
#define SYSCALL_TRACE_EXIT_EVENT(sname) \
- static struct syscall_metadata __syscall_meta_##sname; \
+ static struct syscall_metadata \
+ __attribute__((__aligned__(4))) __syscall_meta_##sname; \
static struct ftrace_event_call \
__attribute__((__aligned__(4))) event_exit_##sname; \
static struct ftrace_event_call __used \
.enter_event = &event_enter_##sname, \
.exit_event = &event_exit_##sname, \
.enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
- .exit_fields = LIST_HEAD_INIT(__syscall_meta_##sname.exit_fields), \
};
#define SYSCALL_DEFINE0(sname) \
.enter_event = &event_enter__##sname, \
.exit_event = &event_exit__##sname, \
.enter_fields = LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \
- .exit_fields = LIST_HEAD_INIT(__syscall_meta__##sname.exit_fields), \
}; \
asmlinkage long sys_##sname(void)
#else
goto out_free_syms;
err = 0;
if (symbol_conf.use_callchain) {
- err = append_chain(he->callchain, data->callchain, syms);
+ err = append_chain(he->callchain, data->callchain, syms, data->period);
if (err)
goto out_free_syms;
}
struct addr_location al;
struct perf_event_attr *attr;
- event__parse_sample(event, session->sample_type, &data);
-
- dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
- data.pid, data.tid, data.ip, data.period);
-
- if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
- unsigned int i;
-
- dump_printf("... chain: nr:%Lu\n", data.callchain->nr);
-
- if (!ip_callchain__valid(data.callchain, event)) {
- pr_debug("call-chain problem with event, "
- "skipping it.\n");
- return 0;
- }
-
- if (dump_trace) {
- for (i = 0; i < data.callchain->nr; i++)
- dump_printf("..... %2d: %016Lx\n",
- i, data.callchain->ips[i]);
- }
- }
-
- if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+ if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
fprintf(stderr, "problem processing %d event, skipping it.\n",
event->header.type);
return -1;
#include "util.h"
#include "callchain.h"
-bool ip_callchain__valid(struct ip_callchain *chain, event_t *event)
+bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event)
{
unsigned int chain_size = event->header.size;
chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
static void
add_child(struct callchain_node *parent, struct resolved_chain *chain,
- int start)
+ int start, u64 period)
{
struct callchain_node *new;
fill_node(new, chain, start);
new->children_hit = 0;
- new->hit = 1;
+ new->hit = period;
}
/*
*/
static void
split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
- struct callchain_list *to_split, int idx_parents, int idx_local)
+ struct callchain_list *to_split, int idx_parents, int idx_local,
+ u64 period)
{
struct callchain_node *new;
struct list_head *old_tail;
/* create a new child for the new branch if any */
if (idx_total < chain->nr) {
parent->hit = 0;
- add_child(parent, chain, idx_total);
- parent->children_hit++;
+ add_child(parent, chain, idx_total, period);
+ parent->children_hit += period;
} else {
- parent->hit = 1;
+ parent->hit = period;
}
}
static int
__append_chain(struct callchain_node *root, struct resolved_chain *chain,
- unsigned int start);
+ unsigned int start, u64 period);
static void
__append_chain_children(struct callchain_node *root,
struct resolved_chain *chain,
- unsigned int start)
+ unsigned int start, u64 period)
{
struct callchain_node *rnode;
/* lookup in childrens */
chain_for_each_child(rnode, root) {
- unsigned int ret = __append_chain(rnode, chain, start);
+ unsigned int ret = __append_chain(rnode, chain, start, period);
if (!ret)
goto inc_children_hit;
}
/* nothing in children, add to the current node */
- add_child(root, chain, start);
+ add_child(root, chain, start, period);
inc_children_hit:
- root->children_hit++;
+ root->children_hit += period;
}
static int
__append_chain(struct callchain_node *root, struct resolved_chain *chain,
- unsigned int start)
+ unsigned int start, u64 period)
{
struct callchain_list *cnode;
unsigned int i = start;
/* we match only a part of the node. Split it and add the new chain */
if (i - start < root->val_nr) {
- split_add_child(root, chain, cnode, start, i - start);
+ split_add_child(root, chain, cnode, start, i - start, period);
return 0;
}
/* we match 100% of the path, increment the hit */
if (i - start == root->val_nr && i == chain->nr) {
- root->hit++;
+ root->hit += period;
return 0;
}
/* We match the node and still have a part remaining */
- __append_chain_children(root, chain, i);
+ __append_chain_children(root, chain, i, period);
return 0;
}
int append_chain(struct callchain_node *root, struct ip_callchain *chain,
- struct map_symbol *syms)
+ struct map_symbol *syms, u64 period)
{
struct resolved_chain *filtered;
if (!filtered->nr)
goto end;
- __append_chain_children(root, filtered, 0);
+ __append_chain_children(root, filtered, 0, period);
end:
free(filtered);
INIT_LIST_HEAD(&node->brothers);
INIT_LIST_HEAD(&node->children);
INIT_LIST_HEAD(&node->val);
+
+ node->parent = NULL;
+ node->hit = 0;
}
static inline u64 cumul_hits(struct callchain_node *node)
int register_callchain_param(struct callchain_param *param);
int append_chain(struct callchain_node *root, struct ip_callchain *chain,
- struct map_symbol *syms);
+ struct map_symbol *syms, u64 period);
-bool ip_callchain__valid(struct ip_callchain *chain, event_t *event);
+bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event);
#endif /* __PERF_CALLCHAIN_H */