summaryrefslogtreecommitdiffstats
path: root/arch/x86/oprofile/op_model_amd.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/oprofile/op_model_amd.c')
-rw-r--r--arch/x86/oprofile/op_model_amd.c261
1 files changed, 206 insertions, 55 deletions
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index b67a6b5aa8d..a011bcc0f94 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -48,31 +48,53 @@ static unsigned long reset_value[NUM_VIRT_COUNTERS];
static u32 ibs_caps;
-struct op_ibs_config {
+struct ibs_config {
unsigned long op_enabled;
unsigned long fetch_enabled;
unsigned long max_cnt_fetch;
unsigned long max_cnt_op;
unsigned long rand_en;
unsigned long dispatched_ops;
+ unsigned long branch_target;
};
-static struct op_ibs_config ibs_config;
-static u64 ibs_op_ctl;
+struct ibs_state {
+ u64 ibs_op_ctl;
+ int branch_target;
+ unsigned long sample_size;
+};
+
+static struct ibs_config ibs_config;
+static struct ibs_state ibs_state;
/*
* IBS cpuid feature detection
*/
-#define IBS_CPUID_FEATURES 0x8000001b
+#define IBS_CPUID_FEATURES 0x8000001b
/*
* Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
* bit 0 is used to indicate the existence of IBS.
*/
-#define IBS_CAPS_AVAIL (1LL<<0)
-#define IBS_CAPS_RDWROPCNT (1LL<<3)
-#define IBS_CAPS_OPCNT (1LL<<4)
+#define IBS_CAPS_AVAIL (1U<<0)
+#define IBS_CAPS_FETCHSAM (1U<<1)
+#define IBS_CAPS_OPSAM (1U<<2)
+#define IBS_CAPS_RDWROPCNT (1U<<3)
+#define IBS_CAPS_OPCNT (1U<<4)
+#define IBS_CAPS_BRNTRGT (1U<<5)
+#define IBS_CAPS_OPCNTEXT (1U<<6)
+
+#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \
+ | IBS_CAPS_FETCHSAM \
+ | IBS_CAPS_OPSAM)
+
+/*
+ * IBS APIC setup
+ */
+#define IBSCTL 0x1cc
+#define IBSCTL_LVT_OFFSET_VALID (1ULL<<8)
+#define IBSCTL_LVT_OFFSET_MASK 0x0F
/*
* IBS randomization macros
@@ -92,12 +114,12 @@ static u32 get_ibs_caps(void)
/* check IBS cpuid feature flags */
max_level = cpuid_eax(0x80000000);
if (max_level < IBS_CPUID_FEATURES)
- return IBS_CAPS_AVAIL;
+ return IBS_CAPS_DEFAULT;
ibs_caps = cpuid_eax(IBS_CPUID_FEATURES);
if (!(ibs_caps & IBS_CAPS_AVAIL))
/* cpuid flags not valid */
- return IBS_CAPS_AVAIL;
+ return IBS_CAPS_DEFAULT;
return ibs_caps;
}
@@ -190,8 +212,8 @@ op_amd_handle_ibs(struct pt_regs * const regs,
rdmsrl(MSR_AMD64_IBSOPCTL, ctl);
if (ctl & IBS_OP_VAL) {
rdmsrl(MSR_AMD64_IBSOPRIP, val);
- oprofile_write_reserve(&entry, regs, val,
- IBS_OP_CODE, IBS_OP_SIZE);
+ oprofile_write_reserve(&entry, regs, val, IBS_OP_CODE,
+ ibs_state.sample_size);
oprofile_add_data64(&entry, val);
rdmsrl(MSR_AMD64_IBSOPDATA, val);
oprofile_add_data64(&entry, val);
@@ -203,10 +225,14 @@ op_amd_handle_ibs(struct pt_regs * const regs,
oprofile_add_data64(&entry, val);
rdmsrl(MSR_AMD64_IBSDCPHYSAD, val);
oprofile_add_data64(&entry, val);
+ if (ibs_state.branch_target) {
+ rdmsrl(MSR_AMD64_IBSBRTARGET, val);
+ oprofile_add_data(&entry, (unsigned long)val);
+ }
oprofile_write_commit(&entry);
/* reenable the IRQ */
- ctl = op_amd_randomize_ibs_op(ibs_op_ctl);
+ ctl = op_amd_randomize_ibs_op(ibs_state.ibs_op_ctl);
wrmsrl(MSR_AMD64_IBSOPCTL, ctl);
}
}
@@ -219,21 +245,32 @@ static inline void op_amd_start_ibs(void)
if (!ibs_caps)
return;
+ memset(&ibs_state, 0, sizeof(ibs_state));
+
+ /*
+ * Note: Since the max count settings may out of range we
+ * write back the actual used values so that userland can read
+ * it.
+ */
+
if (ibs_config.fetch_enabled) {
- val = (ibs_config.max_cnt_fetch >> 4) & IBS_FETCH_MAX_CNT;
+ val = ibs_config.max_cnt_fetch >> 4;
+ val = min(val, IBS_FETCH_MAX_CNT);
+ ibs_config.max_cnt_fetch = val << 4;
val |= ibs_config.rand_en ? IBS_FETCH_RAND_EN : 0;
val |= IBS_FETCH_ENABLE;
wrmsrl(MSR_AMD64_IBSFETCHCTL, val);
}
if (ibs_config.op_enabled) {
- ibs_op_ctl = ibs_config.max_cnt_op >> 4;
+ val = ibs_config.max_cnt_op >> 4;
if (!(ibs_caps & IBS_CAPS_RDWROPCNT)) {
/*
* IbsOpCurCnt not supported. See
* op_amd_randomize_ibs_op() for details.
*/
- ibs_op_ctl = clamp(ibs_op_ctl, 0x0081ULL, 0xFF80ULL);
+ val = clamp(val, 0x0081ULL, 0xFF80ULL);
+ ibs_config.max_cnt_op = val << 4;
} else {
/*
* The start value is randomized with a
@@ -241,13 +278,24 @@ static inline void op_amd_start_ibs(void)
* with the half of the randomized range. Also
* avoid underflows.
*/
- ibs_op_ctl = min(ibs_op_ctl + IBS_RANDOM_MAXCNT_OFFSET,
- IBS_OP_MAX_CNT);
+ val += IBS_RANDOM_MAXCNT_OFFSET;
+ if (ibs_caps & IBS_CAPS_OPCNTEXT)
+ val = min(val, IBS_OP_MAX_CNT_EXT);
+ else
+ val = min(val, IBS_OP_MAX_CNT);
+ ibs_config.max_cnt_op =
+ (val - IBS_RANDOM_MAXCNT_OFFSET) << 4;
+ }
+ val = ((val & ~IBS_OP_MAX_CNT) << 4) | (val & IBS_OP_MAX_CNT);
+ val |= ibs_config.dispatched_ops ? IBS_OP_CNT_CTL : 0;
+ val |= IBS_OP_ENABLE;
+ ibs_state.ibs_op_ctl = val;
+ ibs_state.sample_size = IBS_OP_SIZE;
+ if (ibs_config.branch_target) {
+ ibs_state.branch_target = 1;
+ ibs_state.sample_size++;
}
- if (ibs_caps & IBS_CAPS_OPCNT && ibs_config.dispatched_ops)
- ibs_op_ctl |= IBS_OP_CNT_CTL;
- ibs_op_ctl |= IBS_OP_ENABLE;
- val = op_amd_randomize_ibs_op(ibs_op_ctl);
+ val = op_amd_randomize_ibs_op(ibs_state.ibs_op_ctl);
wrmsrl(MSR_AMD64_IBSOPCTL, val);
}
}
@@ -266,6 +314,70 @@ static void op_amd_stop_ibs(void)
wrmsrl(MSR_AMD64_IBSOPCTL, 0);
}
+static inline int eilvt_is_available(int offset)
+{
+ /* check if we may assign a vector */
+ return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
+}
+
+static inline int ibs_eilvt_valid(void)
+{
+ int offset;
+ u64 val;
+
+ rdmsrl(MSR_AMD64_IBSCTL, val);
+ offset = val & IBSCTL_LVT_OFFSET_MASK;
+
+ 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;
+ }
+
+ if (!eilvt_is_available(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;
+ }
+
+ return 1;
+}
+
+static inline int get_ibs_offset(void)
+{
+ u64 val;
+
+ rdmsrl(MSR_AMD64_IBSCTL, val);
+ if (!(val & IBSCTL_LVT_OFFSET_VALID))
+ return -EINVAL;
+
+ return val & IBSCTL_LVT_OFFSET_MASK;
+}
+
+static void setup_APIC_ibs(void)
+{
+ int offset;
+
+ offset = get_ibs_offset();
+ if (offset < 0)
+ goto failed;
+
+ if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0))
+ return;
+failed:
+ pr_warn("oprofile: IBS APIC setup failed on cpu #%d\n",
+ smp_processor_id());
+}
+
+static void clear_APIC_ibs(void)
+{
+ int offset;
+
+ offset = get_ibs_offset();
+ if (offset >= 0)
+ setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
+}
+
#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
@@ -376,13 +488,13 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
}
if (ibs_caps)
- setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0);
+ setup_APIC_ibs();
}
static void op_amd_cpu_shutdown(void)
{
if (ibs_caps)
- setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
+ clear_APIC_ibs();
}
static int op_amd_check_ctrs(struct pt_regs * const regs,
@@ -445,16 +557,11 @@ static void op_amd_stop(struct op_msrs const * const msrs)
op_amd_stop_ibs();
}
-static int __init_ibs_nmi(void)
+static int setup_ibs_ctl(int ibs_eilvt_off)
{
-#define IBSCTL_LVTOFFSETVAL (1 << 8)
-#define IBSCTL 0x1cc
struct pci_dev *cpu_cfg;
int nodes;
u32 value = 0;
- u8 ibs_eilvt_off;
-
- ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
nodes = 0;
cpu_cfg = NULL;
@@ -466,24 +573,63 @@ static int __init_ibs_nmi(void)
break;
++nodes;
pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off
- | IBSCTL_LVTOFFSETVAL);
+ | IBSCTL_LVT_OFFSET_VALID);
pci_read_config_dword(cpu_cfg, IBSCTL, &value);
- if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) {
+ if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) {
pci_dev_put(cpu_cfg);
printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
- "IBSCTL = 0x%08x", value);
- return 1;
+ "IBSCTL = 0x%08x\n", value);
+ return -EINVAL;
}
} while (1);
if (!nodes) {
- printk(KERN_DEBUG "No CPU node configured for IBS");
- return 1;
+ printk(KERN_DEBUG "No CPU node configured for IBS\n");
+ return -ENODEV;
}
return 0;
}
+static int force_ibs_eilvt_setup(void)
+{
+ int i;
+ 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;
+ return 0;
+ }
+
+ printk(KERN_DEBUG "No EILVT entry available\n");
+
+ return -EBUSY;
+}
+
+static int __init_ibs_nmi(void)
+{
+ int ret;
+
+ if (ibs_eilvt_valid())
+ return 0;
+
+ ret = force_ibs_eilvt_setup();
+ if (ret)
+ return ret;
+
+ if (!ibs_eilvt_valid())
+ return -EFAULT;
+
+ pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
+
+ return 0;
+}
+
/* initialize the APIC for the IBS interrupts if available */
static void init_ibs(void)
{
@@ -521,28 +667,33 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
/* model specific files */
/* setup some reasonable defaults */
+ memset(&ibs_config, 0, sizeof(ibs_config));
ibs_config.max_cnt_fetch = 250000;
- ibs_config.fetch_enabled = 0;
ibs_config.max_cnt_op = 250000;
- ibs_config.op_enabled = 0;
- ibs_config.dispatched_ops = 0;
-
- dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
- oprofilefs_create_ulong(sb, dir, "enable",
- &ibs_config.fetch_enabled);
- oprofilefs_create_ulong(sb, dir, "max_count",
- &ibs_config.max_cnt_fetch);
- oprofilefs_create_ulong(sb, dir, "rand_enable",
- &ibs_config.rand_en);
-
- dir = oprofilefs_mkdir(sb, root, "ibs_op");
- oprofilefs_create_ulong(sb, dir, "enable",
- &ibs_config.op_enabled);
- oprofilefs_create_ulong(sb, dir, "max_count",
- &ibs_config.max_cnt_op);
- if (ibs_caps & IBS_CAPS_OPCNT)
- oprofilefs_create_ulong(sb, dir, "dispatched_ops",
- &ibs_config.dispatched_ops);
+
+ if (ibs_caps & IBS_CAPS_FETCHSAM) {
+ dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
+ oprofilefs_create_ulong(sb, dir, "enable",
+ &ibs_config.fetch_enabled);
+ oprofilefs_create_ulong(sb, dir, "max_count",
+ &ibs_config.max_cnt_fetch);
+ oprofilefs_create_ulong(sb, dir, "rand_enable",
+ &ibs_config.rand_en);
+ }
+
+ if (ibs_caps & IBS_CAPS_OPSAM) {
+ dir = oprofilefs_mkdir(sb, root, "ibs_op");
+ oprofilefs_create_ulong(sb, dir, "enable",
+ &ibs_config.op_enabled);
+ oprofilefs_create_ulong(sb, dir, "max_count",
+ &ibs_config.max_cnt_op);
+ if (ibs_caps & IBS_CAPS_OPCNT)
+ oprofilefs_create_ulong(sb, dir, "dispatched_ops",
+ &ibs_config.dispatched_ops);
+ if (ibs_caps & IBS_CAPS_BRNTRGT)
+ oprofilefs_create_ulong(sb, dir, "branch_target",
+ &ibs_config.branch_target);
+ }
return 0;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-12 07:35:37 +0000