| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20250415114428.341182-12-dapeng1.mi@linux.intel.com>
Date: Tue, 15 Apr 2025 11:44:17 +0000
From: Dapeng Mi <dapeng1.mi@...ux.intel.com>
To: Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Ian Rogers <irogers@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Kan Liang <kan.liang@...ux.intel.com>,
Andi Kleen <ak@...ux.intel.com>,
Eranian Stephane <eranian@...gle.com>
Cc: linux-kernel@...r.kernel.org,
linux-perf-users@...r.kernel.org,
Dapeng Mi <dapeng1.mi@...el.com>,
Dapeng Mi <dapeng1.mi@...ux.intel.com>
Subject: [Patch v3 11/22] perf/x86/intel: Allocate arch-PEBS buffer and initialize PEBS_BASE MSR
Arch-PEBS introduces a new MSR IA32_PEBS_BASE to store the arch-PEBS
buffer physical address. This patch allocates arch-PEBS buffer and then
initialize IA32_PEBS_BASE MSR with the buffer physical address.
Co-developed-by: Kan Liang <kan.liang@...ux.intel.com>
Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@...ux.intel.com>
---
arch/x86/events/intel/core.c | 2 +
arch/x86/events/intel/ds.c | 69 ++++++++++++++++++++++++++-------
arch/x86/events/perf_event.h | 7 +++-
arch/x86/include/asm/intel_ds.h | 3 +-
4 files changed, 66 insertions(+), 15 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 0f911e974e02..e0be6be50936 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -5448,6 +5448,7 @@ static void intel_pmu_cpu_starting(int cpu)
return;
init_debug_store_on_cpu(cpu);
+ init_arch_pebs_buf_on_cpu(cpu);
/*
* Deal with CPUs that don't clear their LBRs on power-up, and that may
* even boot with LBRs enabled.
@@ -5545,6 +5546,7 @@ static void free_excl_cntrs(struct cpu_hw_events *cpuc)
static void intel_pmu_cpu_dying(int cpu)
{
fini_debug_store_on_cpu(cpu);
+ fini_arch_pebs_buf_on_cpu(cpu);
}
void intel_cpuc_finish(struct cpu_hw_events *cpuc)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index ed0bccb04b95..7437a52ba5f0 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -624,13 +624,18 @@ static int alloc_pebs_buffer(int cpu)
int max, node = cpu_to_node(cpu);
void *buffer, *insn_buff, *cea;
- if (!x86_pmu.ds_pebs)
+ if (!intel_pmu_has_pebs())
return 0;
- buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
+ buffer = dsalloc_pages(bsiz, preemptible() ? GFP_KERNEL : GFP_ATOMIC, cpu);
if (unlikely(!buffer))
return -ENOMEM;
+ if (x86_pmu.arch_pebs) {
+ hwev->pebs_vaddr = buffer;
+ return 0;
+ }
+
/*
* HSW+ already provides us the eventing ip; no need to allocate this
* buffer then.
@@ -643,7 +648,7 @@ static int alloc_pebs_buffer(int cpu)
}
per_cpu(insn_buffer, cpu) = insn_buff;
}
- hwev->ds_pebs_vaddr = buffer;
+ hwev->pebs_vaddr = buffer;
/* Update the cpu entry area mapping */
cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
ds->pebs_buffer_base = (unsigned long) cea;
@@ -659,17 +664,20 @@ static void release_pebs_buffer(int cpu)
struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
void *cea;
- if (!x86_pmu.ds_pebs)
+ if (!intel_pmu_has_pebs())
return;
- kfree(per_cpu(insn_buffer, cpu));
- per_cpu(insn_buffer, cpu) = NULL;
+ if (x86_pmu.ds_pebs) {
+ kfree(per_cpu(insn_buffer, cpu));
+ per_cpu(insn_buffer, cpu) = NULL;
- /* Clear the fixmap */
- cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
- ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
- dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size);
- hwev->ds_pebs_vaddr = NULL;
+ /* Clear the fixmap */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+ ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
+ }
+
+ dsfree_pages(hwev->pebs_vaddr, x86_pmu.pebs_buffer_size);
+ hwev->pebs_vaddr = NULL;
}
static int alloc_bts_buffer(int cpu)
@@ -822,6 +830,41 @@ void reserve_ds_buffers(void)
}
}
+void init_arch_pebs_buf_on_cpu(int cpu)
+{
+ struct cpu_hw_events *cpuc = per_cpu_ptr(&cpu_hw_events, cpu);
+ u64 arch_pebs_base;
+
+ if (!x86_pmu.arch_pebs)
+ return;
+
+ if (alloc_pebs_buffer(cpu) < 0 || !cpuc->pebs_vaddr) {
+ WARN(1, "Fail to allocate PEBS buffer on CPU %d\n", cpu);
+ x86_pmu.pebs_active = 0;
+ return;
+ }
+
+ /*
+ * 4KB-aligned pointer of the output buffer
+ * (__alloc_pages_node() return page aligned address)
+ * Buffer Size = 4KB * 2^SIZE
+ * contiguous physical buffer (__alloc_pages_node() with order)
+ */
+ arch_pebs_base = virt_to_phys(cpuc->pebs_vaddr) | PEBS_BUFFER_SHIFT;
+ wrmsr_on_cpu(cpu, MSR_IA32_PEBS_BASE, (u32)arch_pebs_base,
+ (u32)(arch_pebs_base >> 32));
+ x86_pmu.pebs_active = 1;
+}
+
+void fini_arch_pebs_buf_on_cpu(int cpu)
+{
+ if (!x86_pmu.arch_pebs)
+ return;
+
+ release_pebs_buffer(cpu);
+ wrmsr_on_cpu(cpu, MSR_IA32_PEBS_BASE, 0, 0);
+}
+
/*
* BTS
*/
@@ -2862,8 +2905,8 @@ static void intel_pmu_drain_arch_pebs(struct pt_regs *iregs,
return;
}
- base = cpuc->ds_pebs_vaddr;
- top = (void *)((u64)cpuc->ds_pebs_vaddr +
+ base = cpuc->pebs_vaddr;
+ top = (void *)((u64)cpuc->pebs_vaddr +
(index.split.wr << ARCH_PEBS_INDEX_WR_SHIFT));
mask = hybrid(cpuc->pmu, arch_pebs_cap).counters & cpuc->pebs_enabled;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 23ffad67a927..d93d4c7a9876 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -275,8 +275,9 @@ struct cpu_hw_events {
* Intel DebugStore bits
*/
struct debug_store *ds;
- void *ds_pebs_vaddr;
void *ds_bts_vaddr;
+ /* DS based PEBS or arch-PEBS buffer address */
+ void *pebs_vaddr;
u64 pebs_enabled;
int n_pebs;
int n_large_pebs;
@@ -1610,6 +1611,10 @@ extern void intel_cpuc_finish(struct cpu_hw_events *cpuc);
int intel_pmu_init(void);
+void init_arch_pebs_buf_on_cpu(int cpu);
+
+void fini_arch_pebs_buf_on_cpu(int cpu);
+
void init_debug_store_on_cpu(int cpu);
void fini_debug_store_on_cpu(int cpu);
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index 5dbeac48a5b9..023c2883f9f3 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -4,7 +4,8 @@
#include <linux/percpu-defs.h>
#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
+#define PEBS_BUFFER_SHIFT 4
+#define PEBS_BUFFER_SIZE (PAGE_SIZE << PEBS_BUFFER_SHIFT)
/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS_FMT4 8
--
2.40.1
Powered by blists - more mailing lists