[V12,07/10] arm64/perf: Add PERF_ATTACH_TASK_DATA to events with has_branch_stack()
Commit Message
Short running processes i.e those getting very small cpu run time each time
when they get scheduled on, might not accumulate much branch records before
a PMU IRQ really happens. This increases possibility, for such processes to
loose much of its branch records, while being scheduled in-out of various
cpus on the system.
There is a need to save all occurred branch records during the cpu run time
while the process gets scheduled out. It requires an event context specific
buffer for such storage.
This adds PERF_ATTACH_TASK_DATA flag unconditionally, for all branch stack
sampling events, which would allocate task_ctx_data during its event init.
This also creates a platform specific task_ctx_data kmem cache which will
serve such allocation requests.
This adds a new structure 'arm64_perf_task_context' which encapsulates brbe
register set for maximum possible BRBE entries on the HW along with a valid
records tracking element.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Tested-by: James Clark <james.clark@arm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
---
arch/arm64/include/asm/perf_event.h | 4 ++++
drivers/perf/arm_brbe.c | 21 +++++++++++++++++++++
drivers/perf/arm_brbe.h | 13 +++++++++++++
drivers/perf/arm_pmuv3.c | 16 +++++++++++++---
4 files changed, 51 insertions(+), 3 deletions(-)
Comments
Hi Anshuman,
kernel test robot noticed the following build errors:
[auto build test ERROR on arm64/for-next/core]
[also build test ERROR on tip/perf/core acme/perf/core linus/master v6.4-rc6 next-20230615]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Anshuman-Khandual/drivers-perf-arm_pmu-Add-new-sched_task-callback/20230615-223352
base: https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/core
patch link: https://lore.kernel.org/r/20230615133239.442736-8-anshuman.khandual%40arm.com
patch subject: [PATCH V12 07/10] arm64/perf: Add PERF_ATTACH_TASK_DATA to events with has_branch_stack()
config: arm-randconfig-r004-20230615 (https://download.01.org/0day-ci/archive/20230616/202306161016.jJeqG6mc-lkp@intel.com/config)
compiler: clang version 17.0.0 (https://github.com/llvm/llvm-project.git 4a5ac14ee968ff0ad5d2cc1ffa0299048db4c88a)
reproduce (this is a W=1 build):
mkdir -p ~/bin
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install arm cross compiling tool for clang build
# apt-get install binutils-arm-linux-gnueabi
git remote add arm64 https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git
git fetch arm64 for-next/core
git checkout arm64/for-next/core
b4 shazam https://lore.kernel.org/r/20230615133239.442736-8-anshuman.khandual@arm.com
# save the config file
mkdir build_dir && cp config build_dir/.config
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang ~/bin/make.cross W=1 O=build_dir ARCH=arm olddefconfig
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang ~/bin/make.cross W=1 O=build_dir ARCH=arm SHELL=/bin/bash drivers/perf/
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202306161016.jJeqG6mc-lkp@intel.com/
All errors (new ones prefixed by >>):
drivers/perf/arm_pmuv3.c:148:45: warning: initializer overrides prior initialization of this subobject [-Winitializer-overrides]
148 | [C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmuv3.h:134:44: note: expanded from macro 'ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR'
134 | #define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR 0x004F
| ^~~~~~
drivers/perf/arm_pmuv3.c:140:2: note: previous initialization is here
140 | PERF_CACHE_MAP_ALL_UNSUPPORTED,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmu.h:43:31: note: expanded from macro 'PERF_CACHE_MAP_ALL_UNSUPPORTED'
43 | [0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED, \
| ^~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmu.h:35:31: note: expanded from macro 'CACHE_OP_UNSUPPORTED'
35 | #define CACHE_OP_UNSUPPORTED 0xFFFF
| ^~~~~~
drivers/perf/arm_pmuv3.c:149:42: warning: initializer overrides prior initialization of this subobject [-Winitializer-overrides]
149 | [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmuv3.h:131:50: note: expanded from macro 'ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD'
131 | #define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD 0x004C
| ^~~~~~
drivers/perf/arm_pmuv3.c:140:2: note: previous initialization is here
140 | PERF_CACHE_MAP_ALL_UNSUPPORTED,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmu.h:43:31: note: expanded from macro 'PERF_CACHE_MAP_ALL_UNSUPPORTED'
43 | [0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED, \
| ^~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmu.h:35:31: note: expanded from macro 'CACHE_OP_UNSUPPORTED'
35 | #define CACHE_OP_UNSUPPORTED 0xFFFF
| ^~~~~~
drivers/perf/arm_pmuv3.c:150:43: warning: initializer overrides prior initialization of this subobject [-Winitializer-overrides]
150 | [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmuv3.h:132:50: note: expanded from macro 'ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR'
132 | #define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR 0x004D
| ^~~~~~
drivers/perf/arm_pmuv3.c:140:2: note: previous initialization is here
140 | PERF_CACHE_MAP_ALL_UNSUPPORTED,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmu.h:43:31: note: expanded from macro 'PERF_CACHE_MAP_ALL_UNSUPPORTED'
43 | [0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED, \
| ^~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmu.h:35:31: note: expanded from macro 'CACHE_OP_UNSUPPORTED'
35 | #define CACHE_OP_UNSUPPORTED 0xFFFF
| ^~~~~~
drivers/perf/arm_pmuv3.c:152:44: warning: initializer overrides prior initialization of this subobject [-Winitializer-overrides]
152 | [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmuv3.h:148:46: note: expanded from macro 'ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD'
148 | #define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD 0x0060
| ^~~~~~
drivers/perf/arm_pmuv3.c:140:2: note: previous initialization is here
140 | PERF_CACHE_MAP_ALL_UNSUPPORTED,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmu.h:43:31: note: expanded from macro 'PERF_CACHE_MAP_ALL_UNSUPPORTED'
43 | [0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED, \
| ^~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmu.h:35:31: note: expanded from macro 'CACHE_OP_UNSUPPORTED'
35 | #define CACHE_OP_UNSUPPORTED 0xFFFF
| ^~~~~~
drivers/perf/arm_pmuv3.c:153:45: warning: initializer overrides prior initialization of this subobject [-Winitializer-overrides]
153 | [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmuv3.h:149:46: note: expanded from macro 'ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR'
149 | #define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR 0x0061
| ^~~~~~
drivers/perf/arm_pmuv3.c:140:2: note: previous initialization is here
140 | PERF_CACHE_MAP_ALL_UNSUPPORTED,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmu.h:43:31: note: expanded from macro 'PERF_CACHE_MAP_ALL_UNSUPPORTED'
43 | [0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED, \
| ^~~~~~~~~~~~~~~~~~~~
include/linux/perf/arm_pmu.h:35:31: note: expanded from macro 'CACHE_OP_UNSUPPORTED'
35 | #define CACHE_OP_UNSUPPORTED 0xFFFF
| ^~~~~~
drivers/perf/arm_pmuv3.c:714:3: error: call to undeclared function 'armv8pmu_branch_enable'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
714 | armv8pmu_branch_enable(event);
| ^
drivers/perf/arm_pmuv3.c:720:3: error: call to undeclared function 'armv8pmu_branch_disable'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
720 | armv8pmu_branch_disable(event);
| ^
drivers/perf/arm_pmuv3.c:805:4: error: call to undeclared function 'armv8pmu_branch_read'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
805 | armv8pmu_branch_read(cpuc, event);
| ^
drivers/perf/arm_pmuv3.c:805:4: note: did you mean 'armv8pmu_pmcr_read'?
drivers/perf/arm_pmuv3.c:430:19: note: 'armv8pmu_pmcr_read' declared here
430 | static inline u32 armv8pmu_pmcr_read(void)
| ^
drivers/perf/arm_pmuv3.c:912:3: error: call to undeclared function 'armv8pmu_branch_reset'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
912 | armv8pmu_branch_reset();
| ^
drivers/perf/arm_pmuv3.c:987:3: error: call to undeclared function 'armv8pmu_branch_reset'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
987 | armv8pmu_branch_reset();
| ^
drivers/perf/arm_pmuv3.c:1026:8: error: call to undeclared function 'armv8pmu_branch_attr_valid'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
1026 | if (!armv8pmu_branch_attr_valid(event))
| ^
drivers/perf/arm_pmuv3.c:1148:2: error: call to undeclared function 'armv8pmu_branch_probe'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
1148 | armv8pmu_branch_probe(cpu_pmu);
| ^
>> drivers/perf/arm_pmuv3.c:1195:9: error: call to undeclared function 'armv8pmu_task_ctx_cache_alloc'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
1195 | ret = armv8pmu_task_ctx_cache_alloc(cpu_pmu);
| ^
>> drivers/perf/arm_pmuv3.c:1201:4: error: call to undeclared function 'armv8pmu_task_ctx_cache_free'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
1201 | armv8pmu_task_ctx_cache_free(cpu_pmu);
| ^
55 warnings and 9 errors generated.
vim +/armv8pmu_task_ctx_cache_alloc +1195 drivers/perf/arm_pmuv3.c
1176
1177 static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
1178 {
1179 struct armv8pmu_probe_info probe = {
1180 .pmu = cpu_pmu,
1181 .present = false,
1182 };
1183 int ret;
1184
1185 ret = smp_call_function_any(&cpu_pmu->supported_cpus,
1186 __armv8pmu_probe_pmu,
1187 &probe, 1);
1188 if (ret)
1189 return ret;
1190
1191 if (!probe.present)
1192 return -ENODEV;
1193
1194 if (cpu_pmu->has_branch_stack) {
> 1195 ret = armv8pmu_task_ctx_cache_alloc(cpu_pmu);
1196 if (ret)
1197 return ret;
1198
1199 ret = branch_records_alloc(cpu_pmu);
1200 if (ret) {
> 1201 armv8pmu_task_ctx_cache_free(cpu_pmu);
1202 return ret;
1203 }
1204 }
1205 return 0;
1206 }
1207
On 6/16/23 08:08, kernel test robot wrote:
> Hi Anshuman,
>
> kernel test robot noticed the following build errors:
>
> [auto build test ERROR on arm64/for-next/core]
> [also build test ERROR on tip/perf/core acme/perf/core linus/master v6.4-rc6 next-20230615]
> [If your patch is applied to the wrong git tree, kindly drop us a note.
> And when submitting patch, we suggest to use '--base' as documented in
> https://git-scm.com/docs/git-format-patch#_base_tree_information]
>
> url: https://github.com/intel-lab-lkp/linux/commits/Anshuman-Khandual/drivers-perf-arm_pmu-Add-new-sched_task-callback/20230615-223352
> base: https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/core
> patch link: https://lore.kernel.org/r/20230615133239.442736-8-anshuman.khandual%40arm.com
> patch subject: [PATCH V12 07/10] arm64/perf: Add PERF_ATTACH_TASK_DATA to events with has_branch_stack()
> config: arm-randconfig-r004-20230615 (https://download.01.org/0day-ci/archive/20230616/202306161016.jJeqG6mc-lkp@intel.com/config)
> compiler: clang version 17.0.0 (https://github.com/llvm/llvm-project.git 4a5ac14ee968ff0ad5d2cc1ffa0299048db4c88a)
> reproduce (this is a W=1 build):
> mkdir -p ~/bin
> wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
> chmod +x ~/bin/make.cross
> # install arm cross compiling tool for clang build
> # apt-get install binutils-arm-linux-gnueabi
> git remote add arm64 https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git
> git fetch arm64 for-next/core
> git checkout arm64/for-next/core
> b4 shazam https://lore.kernel.org/r/20230615133239.442736-8-anshuman.khandual@arm.com
> # save the config file
> mkdir build_dir && cp config build_dir/.config
> COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang ~/bin/make.cross W=1 O=build_dir ARCH=arm olddefconfig
> COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang ~/bin/make.cross W=1 O=build_dir ARCH=arm SHELL=/bin/bash drivers/perf/
This build failure too gets solved via the header code block movement as mentioned earlier.
@@ -38,6 +38,8 @@ void armv8pmu_branch_enable(struct perf_event *event);
void armv8pmu_branch_disable(struct perf_event *event);
void armv8pmu_branch_probe(struct arm_pmu *arm_pmu);
void armv8pmu_branch_reset(void);
+int armv8pmu_task_ctx_cache_alloc(struct arm_pmu *arm_pmu);
+void armv8pmu_task_ctx_cache_free(struct arm_pmu *arm_pmu);
#else
static inline void armv8pmu_branch_read(struct pmu_hw_events *cpuc, struct perf_event *event)
{
@@ -62,6 +64,8 @@ static inline void armv8pmu_branch_disable(struct perf_event *event)
static inline void armv8pmu_branch_probe(struct arm_pmu *arm_pmu) { }
static inline void armv8pmu_branch_reset(void) { }
+static inline int armv8pmu_task_ctx_cache_alloc(struct arm_pmu *arm_pmu) { return 0; }
+static inline void armv8pmu_task_ctx_cache_free(struct arm_pmu *arm_pmu) { }
#endif
#endif
#endif
@@ -109,6 +109,27 @@ bool armv8pmu_branch_attr_valid(struct perf_event *event)
return true;
}
+static inline struct kmem_cache *
+arm64_create_brbe_task_ctx_kmem_cache(size_t size)
+{
+ return kmem_cache_create("arm64_brbe_task_ctx", size, 0, 0, NULL);
+}
+
+int armv8pmu_task_ctx_cache_alloc(struct arm_pmu *arm_pmu)
+{
+ size_t size = sizeof(struct arm64_perf_task_context);
+
+ arm_pmu->pmu.task_ctx_cache = arm64_create_brbe_task_ctx_kmem_cache(size);
+ if (!arm_pmu->pmu.task_ctx_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void armv8pmu_task_ctx_cache_free(struct arm_pmu *arm_pmu)
+{
+ kmem_cache_destroy(arm_pmu->pmu.task_ctx_cache);
+}
+
static int brbe_attributes_probe(struct arm_pmu *armpmu, u32 brbe)
{
u64 brbidr = read_sysreg_s(SYS_BRBIDR0_EL1);
@@ -80,12 +80,25 @@
* --------------------------------- ------
*/
#define BRBE_BANK_MAX_ENTRIES 32
+#define BRBE_MAX_BANK 2
+#define BRBE_MAX_ENTRIES (BRBE_BANK_MAX_ENTRIES * BRBE_MAX_BANK)
#define BRBE_BANK0_IDX_MIN 0
#define BRBE_BANK0_IDX_MAX 31
#define BRBE_BANK1_IDX_MIN 32
#define BRBE_BANK1_IDX_MAX 63
+struct brbe_regset {
+ unsigned long brbsrc;
+ unsigned long brbtgt;
+ unsigned long brbinf;
+};
+
+struct arm64_perf_task_context {
+ struct brbe_regset store[BRBE_MAX_ENTRIES];
+ int nr_brbe_records;
+};
+
struct brbe_hw_attr {
int brbe_version;
int brbe_cc;
@@ -1022,8 +1022,12 @@ static int __armv8_pmuv3_map_event(struct perf_event *event,
hw_event_id = __armv8_pmuv3_map_event_id(armpmu, event);
- if (has_branch_stack(event) && !armv8pmu_branch_attr_valid(event))
- return -EOPNOTSUPP;
+ if (has_branch_stack(event)) {
+ if (!armv8pmu_branch_attr_valid(event))
+ return -EOPNOTSUPP;
+
+ event->attach_state |= PERF_ATTACH_TASK_DATA;
+ }
/*
* CHAIN events only work when paired with an adjacent counter, and it
@@ -1188,9 +1192,15 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
return -ENODEV;
if (cpu_pmu->has_branch_stack) {
- ret = branch_records_alloc(cpu_pmu);
+ ret = armv8pmu_task_ctx_cache_alloc(cpu_pmu);
if (ret)
return ret;
+
+ ret = branch_records_alloc(cpu_pmu);
+ if (ret) {
+ armv8pmu_task_ctx_cache_free(cpu_pmu);
+ return ret;
+ }
}
return 0;
}