aboutsummaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorAndi Kleen <ak@linux.intel.com>2013-09-20 10:40:39 -0400
committerIngo Molnar <mingo@kernel.org>2013-10-04 04:06:08 -0400
commitfdfbbd07e91f8fe387140776f3fd94605f0c89e5 (patch)
treede5b64bcd5b814e8a392ef362a439082dbcb11df /include
parent4cabc3d1cb6a46f581a2628d1d11c483d5f300e5 (diff)
perf: Add generic transaction flags
Add a generic qualifier for transaction events, as a new sample type that returns a flag word. This is particularly useful for qualifying aborts: to distinguish aborts which happen due to asynchronous events (like conflicts caused by another CPU) versus instructions that lead to an abort. The tuning strategies are very different for those cases, so it's important to distinguish them easily and early. Since it's inconvenient and inflexible to filter for this in the kernel we report all the events out and allow some post processing in user space. The flags are based on the Intel TSX events, but should be fairly generic and mostly applicable to other HTM architectures too. In addition to various flag words there's also reserved space to report an program supplied abort code. For TSX this is used to distinguish specific classes of aborts, like a lock busy abort when doing lock elision. Flags: Elision and generic transactions (ELISION vs TRANSACTION) (HLE vs RTM on TSX; IBM etc. would likely only use TRANSACTION) Aborts caused by current thread vs aborts caused by others (SYNC vs ASYNC) Retryable transaction (RETRY) Conflicts with other threads (CONFLICT) Transaction write capacity overflow (CAPACITY WRITE) Transaction read capacity overflow (CAPACITY READ) Transactions implicitely aborted can also return an abort code. This can be used to signal specific events to the profiler. A common case is abort on lock busy in a RTM eliding library (code 0xff) To handle this case we include the TSX abort code Common example aborts in TSX would be: - Data conflict with another thread on memory read. Flags: TRANSACTION|ASYNC|CONFLICT - executing a WRMSR in a transaction. Flags: TRANSACTION|SYNC - HLE transaction in user space is too large Flags: ELISION|SYNC|CAPACITY-WRITE The only flag that is somewhat TSX specific is ELISION. This adds the perf core glue needed for reporting the new flag word out. v2: Add MEM/MISC v3: Move transaction to the end v4: Separate capacity-read/write and remove misc v5: Remove _SAMPLE. Move abort flags to 32bit. Rename transaction to txn Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1379688044-14173-2-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'include')
-rw-r--r--include/linux/perf_event.h5
-rw-r--r--include/uapi/linux/perf_event.h25
2 files changed, 29 insertions, 1 deletions
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c8ba627c1d60..2e069d1288df 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -584,6 +584,10 @@ struct perf_sample_data {
584 struct perf_regs_user regs_user; 584 struct perf_regs_user regs_user;
585 u64 stack_user_size; 585 u64 stack_user_size;
586 u64 weight; 586 u64 weight;
587 /*
588 * Transaction flags for abort events:
589 */
590 u64 txn;
587}; 591};
588 592
589static inline void perf_sample_data_init(struct perf_sample_data *data, 593static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -599,6 +603,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
599 data->stack_user_size = 0; 603 data->stack_user_size = 0;
600 data->weight = 0; 604 data->weight = 0;
601 data->data_src.val = 0; 605 data->data_src.val = 0;
606 data->txn = 0;
602} 607}
603 608
604extern void perf_output_sample(struct perf_output_handle *handle, 609extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 009a655a5d35..da48837d617d 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -136,8 +136,9 @@ enum perf_event_sample_format {
136 PERF_SAMPLE_WEIGHT = 1U << 14, 136 PERF_SAMPLE_WEIGHT = 1U << 14,
137 PERF_SAMPLE_DATA_SRC = 1U << 15, 137 PERF_SAMPLE_DATA_SRC = 1U << 15,
138 PERF_SAMPLE_IDENTIFIER = 1U << 16, 138 PERF_SAMPLE_IDENTIFIER = 1U << 16,
139 PERF_SAMPLE_TRANSACTION = 1U << 17,
139 140
140 PERF_SAMPLE_MAX = 1U << 17, /* non-ABI */ 141 PERF_SAMPLE_MAX = 1U << 18, /* non-ABI */
141}; 142};
142 143
143/* 144/*
@@ -181,6 +182,28 @@ enum perf_sample_regs_abi {
181}; 182};
182 183
183/* 184/*
185 * Values for the memory transaction event qualifier, mostly for
186 * abort events. Multiple bits can be set.
187 */
188enum {
189 PERF_TXN_ELISION = (1 << 0), /* From elision */
190 PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */
191 PERF_TXN_SYNC = (1 << 2), /* Instruction is related */
192 PERF_TXN_ASYNC = (1 << 3), /* Instruction not related */
193 PERF_TXN_RETRY = (1 << 4), /* Retry possible */
194 PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */
195 PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */
196 PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */
197
198 PERF_TXN_MAX = (1 << 8), /* non-ABI */
199
200 /* bits 32..63 are reserved for the abort code */
201
202 PERF_TXN_ABORT_MASK = (0xffffffffULL << 32),
203 PERF_TXN_ABORT_SHIFT = 32,
204};
205
206/*
184 * The format of the data returned by read() on a perf event fd, 207 * The format of the data returned by read() on a perf event fd,
185 * as specified by attr.read_format: 208 * as specified by attr.read_format:
186 * 209 *