Merge branch 'perf/core-v3' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks into perf/hw_breakpoints

Pull AMD range breakpoints support from Frederic Weisbecker:

" - Extend breakpoint tools and core to support address range through perf
    event with initial backend support for AMD extended breakpoints.

    Syntax is:

           perf record -e mem:addr/len:type

    For example set write breakpoint from 0x1000 to 0x1200 (0x1000 + 512)

           perf record -e mem:0x1000/512:w

 - Clean up a bit breakpoint code validation

 It has been acked by Jiri and Oleg. "

Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 115 insertions, 57 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 813d29d00a17..abe4ec760db3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -870,3 +870,22 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 
         return false;
 }
+
+void set_dr_addr_mask(unsigned long mask, int dr)
+{
+        if (!cpu_has_bpext)
+                return;
+
+        switch (dr) {
+        case 0:
+                wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0);
+                break;
+        case 1:
+        case 2:
+        case 3:
+                wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0);
+                break;
+        default:
+                break;
+        }
+}
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fc5eb390b368..4e6cdb0ddc70 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -253,6 +253,10 @@ struct cpu_hw_events {
 #define INTEL_UEVENT_CONSTRAINT(c, n)   \
         EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
+/* Like UEVENT_CONSTRAINT, but match flags too */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n)     \
+        EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
 #define INTEL_PLD_CONSTRAINT(c, n)      \
         __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
                            HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index cbb1be3ed9e4..a61f5c6911da 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -565,6 +565,21 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
                                        perf_ibs->offset_max,
                                        offset + 1);
         } while (offset < offset_max);
+        if (event->attr.sample_type & PERF_SAMPLE_RAW) {
+                /*
+                 * Read IbsBrTarget and IbsOpData4 separately
+                 * depending on their availability.
+                 * Can't add to offset_max as they are staggered
+                 */
+                if (ibs_caps & IBS_CAPS_BRNTRGT) {
+                        rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++);
+                        size++;
+                }
+                if (ibs_caps & IBS_CAPS_OPDATA4) {
+                        rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++);
+                        size++;
+                }
+        }
         ibs_data.size = sizeof(u64) * size;
 
         regs = *iregs;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 46211bcc813e..495ae9793628 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -552,18 +552,18 @@ int intel_pmu_drain_bts_buffer(void)
  * PEBS
  */
 struct event_constraint intel_core2_pebs_event_constraints[] = {
-        INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
-        INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
-        INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
-        INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
-        INTEL_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
         EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_atom_pebs_event_constraints[] = {
-        INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
-        INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
-        INTEL_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
         EVENT_CONSTRAINT_END
 };
 
@@ -577,36 +577,36 @@ struct event_constraint intel_slm_pebs_event_constraints[] = {
 
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
         INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
-        INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
-        INTEL_EVENT_CONSTRAINT(0xc0, 0xf),    /* INST_RETIRED.ANY */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf),    /* INST_RETIRED.ANY */
         INTEL_EVENT_CONSTRAINT(0xc2, 0xf),    /* UOPS_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
-        INTEL_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
-        INTEL_EVENT_CONSTRAINT(0xc7, 0xf),    /* SSEX_UOPS_RETIRED.* */
-        INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
-        INTEL_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf),    /* SSEX_UOPS_RETIRED.* */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
         EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_westmere_pebs_event_constraints[] = {
         INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
-        INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
-        INTEL_EVENT_CONSTRAINT(0xc0, 0xf),    /* INSTR_RETIRED.* */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf),    /* INSTR_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xc2, 0xf),    /* UOPS_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xc7, 0xf),    /* SSEX_UOPS_RETIRED.* */
-        INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
-        INTEL_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf),    /* SSEX_UOPS_RETIRED.* */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
         EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_snb_pebs_event_constraints[] = {
-        INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
         INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
         INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
         /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
@@ -617,7 +617,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_ivb_pebs_event_constraints[] = {
-        INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
         INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
         INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
         /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
@@ -628,7 +628,7 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_hsw_pebs_event_constraints[] = {
-        INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
         INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
         /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
         INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
@@ -886,6 +886,29 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
         regs.bp = pebs->bp;
         regs.sp = pebs->sp;
 
+        if (sample_type & PERF_SAMPLE_REGS_INTR) {
+                regs.ax = pebs->ax;
+                regs.bx = pebs->bx;
+                regs.cx = pebs->cx;
+                regs.dx = pebs->dx;
+                regs.si = pebs->si;
+                regs.di = pebs->di;
+                regs.bp = pebs->bp;
+                regs.sp = pebs->sp;
+
+                regs.flags = pebs->flags;
+#ifndef CONFIG_X86_32
+                regs.r8 = pebs->r8;
+                regs.r9 = pebs->r9;
+                regs.r10 = pebs->r10;
+                regs.r11 = pebs->r11;
+                regs.r12 = pebs->r12;
+                regs.r13 = pebs->r13;
+                regs.r14 = pebs->r14;
+                regs.r15 = pebs->r15;
+#endif
+        }
+
         if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
                 regs.ip = pebs->real_ip;
                 regs.flags |= PERF_EFLAGS_EXACT;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index f9ed429d6e4f..745b158e9a65 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -449,7 +449,11 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = {
 static struct uncore_event_desc snbep_uncore_imc_events[] = {
         INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0xff,umask=0x00"),
         INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x03"),
+        INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+        INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
         INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+        INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+        INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
         { /* end: all zeroes */ },
 };
 
@@ -2036,7 +2040,11 @@ static struct intel_uncore_type hswep_uncore_ha = {
 static struct uncore_event_desc hswep_uncore_imc_events[] = {
         INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0x00,umask=0x00"),
         INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x03"),
+        INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+        INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
         INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+        INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+        INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
         { /* end: all zeroes */ },
 };
 
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 3d5fb509bdeb..7114ba220fd4 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -126,6 +126,8 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
         *dr7 |= encode_dr7(i, info->len, info->type);
 
         set_debugreg(*dr7, 7);
+        if (info->mask)
+                set_dr_addr_mask(info->mask, i);
 
         return 0;
 }
@@ -161,29 +163,8 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
         *dr7 &= ~__encode_dr7(i, info->len, info->type);
 
         set_debugreg(*dr7, 7);
-}
-
-static int get_hbp_len(u8 hbp_len)
-{
-        unsigned int len_in_bytes = 0;
-
-        switch (hbp_len) {
-        case X86_BREAKPOINT_LEN_1:
-                len_in_bytes = 1;
-                break;
-        case X86_BREAKPOINT_LEN_2:
-                len_in_bytes = 2;
-                break;
-        case X86_BREAKPOINT_LEN_4:
-                len_in_bytes = 4;
-                break;
-#ifdef CONFIG_X86_64
-        case X86_BREAKPOINT_LEN_8:
-                len_in_bytes = 8;
-                break;
-#endif
-        }
-        return len_in_bytes;
+        if (info->mask)
+                set_dr_addr_mask(0, i);
 }
 
 /*
@@ -196,7 +177,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
         struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
         va = info->address;
-        len = get_hbp_len(info->len);
+        len = bp->attr.bp_len;
 
         return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -277,6 +258,8 @@ static int arch_build_bp_info(struct perf_event *bp)
         }
 
         /* Len */
+        info->mask = 0;
+
         switch (bp->attr.bp_len) {
         case HW_BREAKPOINT_LEN_1:
                 info->len = X86_BREAKPOINT_LEN_1;
@@ -293,11 +276,17 @@ static int arch_build_bp_info(struct perf_event *bp)
                 break;
 #endif
         default:
-                return -EINVAL;
+                if (!is_power_of_2(bp->attr.bp_len))
+                        return -EINVAL;
+                if (!cpu_has_bpext)
+                        return -EOPNOTSUPP;
+                info->mask = bp->attr.bp_len - 1;
+                info->len = X86_BREAKPOINT_LEN_1;
         }
 
         return 0;
 }
+
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
@@ -312,11 +301,11 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
         if (ret)
                 return ret;
 
-        ret = -EINVAL;
-
         switch (info->len) {
         case X86_BREAKPOINT_LEN_1:
                 align = 0;
+                if (info->mask)
+                        align = info->mask;
                 break;
         case X86_BREAKPOINT_LEN_2:
                 align = 1;
@@ -330,7 +319,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
                 break;
 #endif
         default:
-                return ret;
+                WARN_ON_ONCE(1);
         }
 
         /*