summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorIngo Molnar <mingo@elte.hu>2011-05-27 14:08:09 +0200
committerIngo Molnar <mingo@elte.hu>2011-05-27 14:08:09 +0200
commitb1d2dc3c06d8da7d58fb43d7123a91c1d6a4f576 (patch)
tree425e774abcf88bad87ba4e25ccae7a9f49b56aab /arch
parent75911c9bd1134f8c0b682aa1e8a8dbefec3ca07a (diff)
parentb76a06e08d94b2a63e47837dfe46bbbf0a3af6c2 (diff)
Merge branch 'urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/rric/oprofile into perf/urgent
Diffstat (limited to 'arch')
-rw-r--r--arch/powerpc/oprofile/op_model_power4.c24
-rw-r--r--arch/x86/oprofile/op_model_amd.c95
2 files changed, 77 insertions, 42 deletions
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
index 8ee51a252cf1..e6bec74be131 100644
--- a/arch/powerpc/oprofile/op_model_power4.c
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -261,6 +261,28 @@ static int get_kernel(unsigned long pc, unsigned long mmcra)
return is_kernel;
}
+static bool pmc_overflow(unsigned long val)
+{
+ if ((int)val < 0)
+ return true;
+
+ /*
+ * Events on POWER7 can roll back if a speculative event doesn't
+ * eventually complete. Unfortunately in some rare cases they will
+ * raise a performance monitor exception. We need to catch this to
+ * ensure we reset the PMC. In all cases the PMC will be 256 or less
+ * cycles from overflow.
+ *
+ * We only do this if the first pass fails to find any overflowing
+ * PMCs because a user might set a period of less than 256 and we
+ * don't want to mistakenly reset them.
+ */
+ if (__is_processor(PV_POWER7) && ((0x80000000 - val) <= 256))
+ return true;
+
+ return false;
+}
+
static void power4_handle_interrupt(struct pt_regs *regs,
struct op_counter_config *ctr)
{
@@ -281,7 +303,7 @@ static void power4_handle_interrupt(struct pt_regs *regs,
for (i = 0; i < cur_cpu_spec->num_pmcs; ++i) {
val = classic_ctr_read(i);
- if (val < 0) {
+ if (pmc_overflow(val)) {
if (oprofile_running && ctr[i].enabled) {
oprofile_add_ext_sample(pc, regs, i, is_kernel);
classic_ctr_write(i, reset_value[i]);
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index c3b8e24f2b16..9fd8a567fe1e 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -316,16 +316,23 @@ static void op_amd_stop_ibs(void)
wrmsrl(MSR_AMD64_IBSOPCTL, 0);
}
-static inline int eilvt_is_available(int offset)
+static inline int get_eilvt(int offset)
{
- /* check if we may assign a vector */
return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
}
+static inline int put_eilvt(int offset)
+{
+ return !setup_APIC_eilvt(offset, 0, 0, 1);
+}
+
static inline int ibs_eilvt_valid(void)
{
int offset;
u64 val;
+ int valid = 0;
+
+ preempt_disable();
rdmsrl(MSR_AMD64_IBSCTL, val);
offset = val & IBSCTL_LVT_OFFSET_MASK;
@@ -333,16 +340,20 @@ static inline int ibs_eilvt_valid(void)
if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n",
smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
- return 0;
+ goto out;
}
- if (!eilvt_is_available(offset)) {
+ if (!get_eilvt(offset)) {
pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n",
smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
- return 0;
+ goto out;
}
- return 1;
+ valid = 1;
+out:
+ preempt_enable();
+
+ return valid;
}
static inline int get_ibs_offset(void)
@@ -600,67 +611,69 @@ static int setup_ibs_ctl(int ibs_eilvt_off)
static int force_ibs_eilvt_setup(void)
{
- int i;
+ int offset;
int ret;
- /* find the next free available EILVT entry */
- for (i = 1; i < 4; i++) {
- if (!eilvt_is_available(i))
- continue;
- ret = setup_ibs_ctl(i);
- if (ret)
- return ret;
- pr_err(FW_BUG "using offset %d for IBS interrupts\n", i);
- return 0;
+ /*
+ * find the next free available EILVT entry, skip offset 0,
+ * pin search to this cpu
+ */
+ preempt_disable();
+ for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) {
+ if (get_eilvt(offset))
+ break;
}
+ preempt_enable();
- printk(KERN_DEBUG "No EILVT entry available\n");
-
- return -EBUSY;
-}
-
-static int __init_ibs_nmi(void)
-{
- int ret;
-
- if (ibs_eilvt_valid())
- return 0;
+ if (offset == APIC_EILVT_NR_MAX) {
+ printk(KERN_DEBUG "No EILVT entry available\n");
+ return -EBUSY;
+ }
- ret = force_ibs_eilvt_setup();
+ ret = setup_ibs_ctl(offset);
if (ret)
- return ret;
+ goto out;
- if (!ibs_eilvt_valid())
- return -EFAULT;
+ if (!ibs_eilvt_valid()) {
+ ret = -EFAULT;
+ goto out;
+ }
+ pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
return 0;
+out:
+ preempt_disable();
+ put_eilvt(offset);
+ preempt_enable();
+ return ret;
}
/*
* check and reserve APIC extended interrupt LVT offset for IBS if
* available
- *
- * init_ibs() preforms implicitly cpu-local operations, so pin this
- * thread to its current CPU
*/
static void init_ibs(void)
{
- preempt_disable();
-
ibs_caps = get_ibs_caps();
+
if (!ibs_caps)
+ return;
+
+ if (ibs_eilvt_valid())
goto out;
- if (__init_ibs_nmi() < 0)
- ibs_caps = 0;
- else
- printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
+ if (!force_ibs_eilvt_setup())
+ goto out;
+
+ /* Failed to setup ibs */
+ ibs_caps = 0;
+ return;
out:
- preempt_enable();
+ printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
}
static int (*create_arch_files)(struct super_block *sb, struct dentry *root);