To pick up fixes.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
}
}
cpuhw->bhrb_stack.nr = u_index;
+ cpuhw->bhrb_stack.hw_idx = -1ULL;
return;
}
* intel_bts events don't coexist with intel PMU's BTS events because of
* x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
* disabled around intel PMU's event batching etc, only inside the PMI handler.
+ *
+ * Avoid PEBS_ENABLE MSR access in PMIs.
+ * The GLOBAL_CTRL has been disabled. All the counters do not count anymore.
+ * It doesn't matter if the PEBS is enabled or not.
+ * Usually, the PEBS status are not changed in PMIs. It's unnecessary to
+ * access PEBS_ENABLE MSR in disable_all()/enable_all().
+ * However, there are some cases which may change PEBS status, e.g. PMI
+ * throttle. The PEBS_ENABLE should be updated where the status changes.
*/
static void __intel_pmu_disable_all(void)
{
if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
-
- intel_pmu_pebs_disable_all();
}
static void intel_pmu_disable_all(void)
{
__intel_pmu_disable_all();
+ intel_pmu_pebs_disable_all();
intel_pmu_lbr_disable_all();
}
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- intel_pmu_pebs_enable_all();
intel_pmu_lbr_enable_all(pmi);
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
static void intel_pmu_enable_all(int added)
{
+ intel_pmu_pebs_enable_all();
__intel_pmu_enable_all(added, false);
}
* PEBS overflow sets bit 62 in the global status register
*/
if (__test_and_clear_bit(62, (unsigned long *)&status)) {
+ u64 pebs_enabled = cpuc->pebs_enabled;
+
handled++;
x86_pmu.drain_pebs(regs);
status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
+
+ /*
+ * PMI throttle may be triggered, which stops the PEBS event.
+ * Although cpuc->pebs_enabled is updated accordingly, the
+ * MSR_IA32_PEBS_ENABLE is not updated. Because the
+ * cpuc->enabled has been forced to 0 in PMI.
+ * Update the MSR if pebs_enabled is changed.
+ */
+ if (pebs_enabled != cpuc->pebs_enabled)
+ wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
}
/*
cpuc->lbr_entries[i].reserved = 0;
}
cpuc->lbr_stack.nr = i;
+ cpuc->lbr_stack.hw_idx = tos;
}
/*
out++;
}
cpuc->lbr_stack.nr = out;
+ cpuc->lbr_stack.hw_idx = tos;
}
void intel_pmu_lbr_read(void)
int i;
cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+
+ /* Cannot get TOS for large PEBS */
+ if (cpuc->n_pebs == cpuc->n_large_pebs)
+ cpuc->lbr_stack.hw_idx = -1ULL;
+ else
+ cpuc->lbr_stack.hw_idx = intel_pmu_lbr_tos();
+
for (i = 0; i < x86_pmu.lbr_nr; i++) {
u64 info = lbr->lbr[i].info;
struct perf_branch_entry *e = &cpuc->lbr_entries[i];
.pci_init = skl_uncore_pci_init,
};
+static const struct intel_uncore_init_fun tgl_uncore_init __initconst = {
+ .cpu_init = icl_uncore_cpu_init,
+ .mmio_init = tgl_uncore_mmio_init,
+};
+
+static const struct intel_uncore_init_fun tgl_l_uncore_init __initconst = {
+ .cpu_init = icl_uncore_cpu_init,
+ .mmio_init = tgl_l_uncore_mmio_init,
+};
+
static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
.cpu_init = snr_uncore_cpu_init,
.pci_init = snr_uncore_pci_init,
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, icl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI, icl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE, icl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_TIGERLAKE_L, tgl_l_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_TIGERLAKE, tgl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ATOM_TREMONT_D, snr_uncore_init),
{},
};
void nhm_uncore_cpu_init(void);
void skl_uncore_cpu_init(void);
void icl_uncore_cpu_init(void);
+void tgl_uncore_mmio_init(void);
+void tgl_l_uncore_mmio_init(void);
int snb_pci2phy_map_init(int devid);
/* uncore_snbep.c */
#define PCI_DEVICE_ID_INTEL_WHL_UD_IMC 0x3e35
#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02
#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12
+#define PCI_DEVICE_ID_INTEL_TGL_U1_IMC 0x9a02
+#define PCI_DEVICE_ID_INTEL_TGL_U2_IMC 0x9a04
+#define PCI_DEVICE_ID_INTEL_TGL_U3_IMC 0x9a12
+#define PCI_DEVICE_ID_INTEL_TGL_U4_IMC 0x9a14
+#define PCI_DEVICE_ID_INTEL_TGL_H_IMC 0x9a36
/* SNB event control */
}
/* end of Nehalem uncore support */
+
+/* Tiger Lake MMIO uncore support */
+
+static const struct pci_device_id tgl_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U1_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U2_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U3_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U4_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_H_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ }
+};
+
+enum perf_tgl_uncore_imc_freerunning_types {
+ TGL_MMIO_UNCORE_IMC_DATA_TOTAL,
+ TGL_MMIO_UNCORE_IMC_DATA_READ,
+ TGL_MMIO_UNCORE_IMC_DATA_WRITE,
+ TGL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX
+};
+
+static struct freerunning_counters tgl_l_uncore_imc_freerunning[] = {
+ [TGL_MMIO_UNCORE_IMC_DATA_TOTAL] = { 0x5040, 0x0, 0x0, 1, 64 },
+ [TGL_MMIO_UNCORE_IMC_DATA_READ] = { 0x5058, 0x0, 0x0, 1, 64 },
+ [TGL_MMIO_UNCORE_IMC_DATA_WRITE] = { 0x50A0, 0x0, 0x0, 1, 64 },
+};
+
+static struct freerunning_counters tgl_uncore_imc_freerunning[] = {
+ [TGL_MMIO_UNCORE_IMC_DATA_TOTAL] = { 0xd840, 0x0, 0x0, 1, 64 },
+ [TGL_MMIO_UNCORE_IMC_DATA_READ] = { 0xd858, 0x0, 0x0, 1, 64 },
+ [TGL_MMIO_UNCORE_IMC_DATA_WRITE] = { 0xd8A0, 0x0, 0x0, 1, 64 },
+};
+
+static struct uncore_event_desc tgl_uncore_imc_events[] = {
+ INTEL_UNCORE_EVENT_DESC(data_total, "event=0xff,umask=0x10"),
+ INTEL_UNCORE_EVENT_DESC(data_total.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(data_total.unit, "MiB"),
+
+ INTEL_UNCORE_EVENT_DESC(data_read, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(data_read.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(data_read.unit, "MiB"),
+
+ INTEL_UNCORE_EVENT_DESC(data_write, "event=0xff,umask=0x30"),
+ INTEL_UNCORE_EVENT_DESC(data_write.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(data_write.unit, "MiB"),
+
+ { /* end: all zeroes */ }
+};
+
+static struct pci_dev *tgl_uncore_get_mc_dev(void)
+{
+ const struct pci_device_id *ids = tgl_uncore_pci_ids;
+ struct pci_dev *mc_dev = NULL;
+
+ while (ids && ids->vendor) {
+ mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, ids->device, NULL);
+ if (mc_dev)
+ return mc_dev;
+ ids++;
+ }
+
+ return mc_dev;
+}
+
+#define TGL_UNCORE_MMIO_IMC_MEM_OFFSET 0x10000
+
+static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = tgl_uncore_get_mc_dev();
+ struct intel_uncore_pmu *pmu = box->pmu;
+ resource_size_t addr;
+ u32 mch_bar;
+
+ if (!pdev) {
+ pr_warn("perf uncore: Cannot find matched IMC device.\n");
+ return;
+ }
+
+ pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET, &mch_bar);
+ /* MCHBAR is disabled */
+ if (!(mch_bar & BIT(0))) {
+ pr_warn("perf uncore: MCHBAR is disabled. Failed to map IMC free-running counters.\n");
+ return;
+ }
+ mch_bar &= ~BIT(0);
+ addr = (resource_size_t)(mch_bar + TGL_UNCORE_MMIO_IMC_MEM_OFFSET * pmu->pmu_idx);
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET + 4, &mch_bar);
+ addr |= ((resource_size_t)mch_bar << 32);
+#endif
+
+ box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+}
+
+static struct intel_uncore_ops tgl_uncore_imc_freerunning_ops = {
+ .init_box = tgl_uncore_imc_freerunning_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .read_counter = uncore_mmio_read_counter,
+ .hw_config = uncore_freerunning_hw_config,
+};
+
+static struct attribute *tgl_uncore_imc_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ NULL
+};
+
+static const struct attribute_group tgl_uncore_imc_format_group = {
+ .name = "format",
+ .attrs = tgl_uncore_imc_formats_attr,
+};
+
+static struct intel_uncore_type tgl_uncore_imc_free_running = {
+ .name = "imc_free_running",
+ .num_counters = 3,
+ .num_boxes = 2,
+ .num_freerunning_types = TGL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+ .freerunning = tgl_uncore_imc_freerunning,
+ .ops = &tgl_uncore_imc_freerunning_ops,
+ .event_descs = tgl_uncore_imc_events,
+ .format_group = &tgl_uncore_imc_format_group,
+};
+
+static struct intel_uncore_type *tgl_mmio_uncores[] = {
+ &tgl_uncore_imc_free_running,
+ NULL
+};
+
+void tgl_l_uncore_mmio_init(void)
+{
+ tgl_uncore_imc_free_running.freerunning = tgl_l_uncore_imc_freerunning;
+ uncore_mmio_uncores = tgl_mmio_uncores;
+}
+
+void tgl_uncore_mmio_init(void)
+{
+ uncore_mmio_uncores = tgl_mmio_uncores;
+}
+
+/* end of Tiger Lake MMIO uncore support */
/*
* branch stack layout:
* nr: number of taken branches stored in entries[]
+ * hw_idx: The low level index of raw branch records
+ * for the most recent branch.
+ * -1ULL means invalid/unknown.
*
* Note that nr can vary from sample to sample
* branches (to, from) are stored from most recent
* to least recent, i.e., entries[0] contains the most
* recent branch.
+ * The entries[] is an abstraction of raw branch records,
+ * which may not be stored in age order in HW, e.g. Intel LBR.
+ * The hw_idx is to expose the low level index of raw
+ * branch record for the most recent branch aka entries[0].
+ * The hw_idx index is between -1 (unknown) and max depth,
+ * which can be retrieved in /sys/devices/cpu/caps/branches.
+ * For the architectures whose raw branch records are
+ * already stored in age order, the hw_idx should be 0.
*/
struct perf_branch_stack {
__u64 nr;
+ __u64 hw_idx;
struct perf_branch_entry entries[0];
};
PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT = 16, /* save branch type */
+ PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT = 17, /* save low level index of raw branch records */
+
PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */
};
PERF_SAMPLE_BRANCH_TYPE_SAVE =
1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
+ PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT,
+
PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
};
* char data[size];}&& PERF_SAMPLE_RAW
*
* { u64 nr;
- * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+ * { u64 hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
+ * { u64 from, to, flags } lbr[nr];
+ * } && PERF_SAMPLE_BRANCH_STACK
*
* { u64 abi; # enum perf_sample_regs_abi
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
perf_output_read_one(handle, event, enabled, running);
}
+static inline bool perf_sample_save_hw_index(struct perf_event *event)
+{
+ return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
+}
+
void perf_output_sample(struct perf_output_handle *handle,
struct perf_event_header *header,
struct perf_sample_data *data,
* sizeof(struct perf_branch_entry);
perf_output_put(handle, data->br_stack->nr);
+ if (perf_sample_save_hw_index(event))
+ perf_output_put(handle, data->br_stack->hw_idx);
perf_output_copy(handle, data->br_stack->entries, size);
} else {
/*
if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
int size = sizeof(u64); /* nr */
if (data->br_stack) {
+ if (perf_sample_save_hw_index(event))
+ size += sizeof(u64);
+
size += data->br_stack->nr
* sizeof(struct perf_branch_entry);
}
git.samba.org / sfrench / cifs-2.6.git / commitdiff