Hi James,

Sorry, some local patch caused inaccurate information. Please allow me to reintroduce the question:

If you use perf with 1G AUX buffer, you can get 1G perf data. Perf workload is kernel build here:

perf record -C 0 -m ,1G -e cs_etm// taskset -c 0 make

[ perf record: Captured and wrote 1025.557 MB perf.data ]

But if you use 2G AUX buffer, perf was executed unexpectedly：

perf record -C 0 -m ,2G -e cs_etm// taskset -c 0 make

[ perf record: Captured and wrote 2.615 MB perf.data ]

There are just 2.615 MB perf data rather than 2G, if you probe function "tmc_alloc_etr_buf" in

coresight_tmc module, you can find some clues:

perf probe -m coresight_tmc "tmc_alloc_etr_buf size:s64"

perf record -e probe:tmc_alloc_etr_buf -aR -- perf record -C 0 -m ,2G -e cs_etm// -o cs.data taskset -c 0 make

perf script             perf 118267 [064]  4640.324670: probe:tmc_alloc_etr_buf: (ffff80007a9dce60) size_s64=-2147483648             perf 118267 [064]  4640.324681: probe:tmc_alloc_etr_buf: (ffff80007a9dce60) size_s64=1048576

It's pretty obvious what's going on here. The first call of tmc_alloc_etr_buf in alloc_etr_buf was

failed because of overflow, the second call of tmc_alloc_etr_buf just alloc 1M AUX buffer which

is default ETR buffer size rather than 2G. That is why we can just get 2.615MB ( 1M AUX data

+ perf header ).

It is necessary to check the conversion from int to s64 in coresight_tmc driver. The issue[1] also

exists in coresight/perf, but it's different from this topic.

[1]: https://lore.kernel.org/bpf/20230711014120.53461-1-xueshuai@linux.alibaba.co...

Thanks Ruidong

On 2023/7/24 23:38, James Clark wrote:

On 14/07/2023 09:43, Ruidong Tian wrote:

...

Perf cs_etm session will failed when AUX buffer > 1G.

perf record -C 0 -m ,2G -e cs_etm// -- taskset -c 0 ls failed to mmap with 12 (Cannot allocate memory)

In coresight tmc driver, "nr_pages << PAGE_SHIFT" will overflow when nr_pages >= 0x80000(correspond to 1G AUX buffer). Explicit convert nr_pages to 64 bit to avoid overflow.

Hi Ruidong,

I couldn't reproduce this exact issue with the error message in the commit message. Is it not another manifestation related to this change [1]? I don't actually get any error message, but I was able to get a warning in dmesg even with [1] applied.

Does the overflow not result in a successful session but with the wrong buffer size?

I think the change makes sense, but maybe we also need a check for MAX_ORDER because I can trigger the same WARN_ON from [1]. Or maybe I'm a bit confused because of the other change and not being able to reproduce this exactly coming at the same time.

Thanks James

...

Signed-off-by: Ruidong Tian tianruidong@linux.alibaba.com

drivers/hwtracing/coresight/coresight-tmc-etr.c | 2 +- drivers/hwtracing/coresight/coresight-tmc.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 766325de0e29..1425ecd1cf78 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1267,7 +1267,7 @@ alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event, * than the size requested via sysfs. */ if ((nr_pages << PAGE_SHIFT) > drvdata->size) {

• etr_buf = tmc_alloc_etr_buf(drvdata, (nr_pages << PAGE_SHIFT),
  

• etr_buf = tmc_alloc_etr_buf(drvdata, ((ssize_t)nr_pages << PAGE_SHIFT),
  		    0, node, NULL);
  

  if (!IS_ERR(etr_buf)) goto done;

diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index b97da39652d2..0ee48c5ba764 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -325,7 +325,7 @@ ssize_t tmc_sg_table_get_data(struct tmc_sg_table *sg_table, static inline unsigned long tmc_sg_table_buf_size(struct tmc_sg_table *sg_table) {

• return sg_table->data_pages.nr_pages << PAGE_SHIFT;

• return (unsigned long)sg_table->data_pages.nr_pages << PAGE_SHIFT; }

struct coresight_device *tmc_etr_get_catu_device(struct tmc_drvdata *drvdata);

Sure, I will put them all to patch v3.

Ruidong

On 2023/8/4 00:19, Suzuki K Poulose wrote:

On 03/08/2023 03:33, Ruidong Tian wrote:

...

Perf cs_etm session executed unexpectedly when AUX buffer > 1G.

perf record -C 0 -m ,2G -e cs_etm// -- <workload>    [ perf record: Captured and wrote 2.615 MB perf.data ]

Perf only collect about 2M perf data rather than 2G. This is becasuse the operation, "nr_pages << PAGE_SHIFT", in coresight tmc driver, will overflow when nr_pages >= 0x80000(correspond to 1G AUX buffer). The overflow cause buffer allocation to fail, and TMC driver will alloc minimal buffer size(1M). You can just get about 2M perf data(1M AUX buffer + perf data header) at least.

Explicit convert nr_pages to 64 bit to avoid overflow.

Signed-off-by: Ruidong Tian tianruidong@linux.alibaba.com Reviewed-by: James Clark james.clark@arm.com

Fixes: 22f429f19c41 ("coresight: etm-perf: Add support for ETR backend")

...

---

drivers/hwtracing/coresight/coresight-tmc-etr.c | 2 +-   drivers/hwtracing/coresight/coresight-tmc.h     | 2 +-   2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 766325de0e29..1425ecd1cf78 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1267,7 +1267,7 @@ alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event,        * than the size requested via sysfs.        */       if ((nr_pages << PAGE_SHIFT) > drvdata->size) { -        etr_buf = tmc_alloc_etr_buf(drvdata, (nr_pages << PAGE_SHIFT), +        etr_buf = tmc_alloc_etr_buf(drvdata, ((ssize_t)nr_pages << PAGE_SHIFT),                           0, node, NULL);           if (!IS_ERR(etr_buf))               goto done; diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index b97da39652d2..0ee48c5ba764 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -325,7 +325,7 @@ ssize_t tmc_sg_table_get_data(struct tmc_sg_table *sg_table,   static inline unsigned long   tmc_sg_table_buf_size(struct tmc_sg_table *sg_table)   { -    return sg_table->data_pages.nr_pages << PAGE_SHIFT; +    return (unsigned long)sg_table->data_pages.nr_pages << PAGE_SHIFT;   }     struct coresight_device *tmc_etr_get_catu_device(struct tmc_drvdata *drvdata);

There are other places where such a fix is needed. e.g.,

$ git grep "nr_pages << PAGE_SHIFT" drivers/hwtracing/coresight/coresight-tmc* drivers/hwtracing/coresight/coresight-tmc-etf.c:        head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); drivers/hwtracing/coresight/coresight-tmc-etr.c:#define PERF_IDX2OFF(idx, buf)  ((idx) % ((buf)->nr_pages << PAGE_SHIFT)) drivers/hwtracing/coresight/coresight-tmc-etr.c:        if ((nr_pages << PAGE_SHIFT) > drvdata->size) { drivers/hwtracing/coresight/coresight-tmc-etr.c: etr_buf = tmc_alloc_etr_buf(drvdata, (nr_pages << PAGE_SHIFT), drivers/hwtracing/coresight/coresight-tmc.h:    return sg_table->data_pages.nr_pages << PAGE_SHIFT;

Are you able to fix all of them ?

Suzuki

Perf cs_etm session executed unexpectedly when AUX buffer > 1G.

perf record -C 0 -m ,2G -e cs_etm// -- <workload> [ perf record: Captured and wrote 2.615 MB perf.data ]

Perf only collect about 2M perf data rather than 2G. This is becasuse the operation, "nr_pages << PAGE_SHIFT", in coresight tmc driver, will overflow when nr_pages >= 0x80000(correspond to 1G AUX buffer). The overflow cause buffer allocation to fail, and TMC driver will alloc minimal buffer size(1M). You can just get about 2M perf data(1M AUX buffer + perf data header) at least.

Explicit convert nr_pages to 64 bit to avoid overflow.

Fixes: 22f429f19c41 ("coresight: etm-perf: Add support for ETR backend") Signed-off-by: Ruidong Tian tianruidong@linux.alibaba.com Reviewed-by: James Clark james.clark@arm.com --- drivers/hwtracing/coresight/coresight-tmc-etf.c | 2 +- drivers/hwtracing/coresight/coresight-tmc-etr.c | 5 +++-- drivers/hwtracing/coresight/coresight-tmc.h | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index 79d8c64eac49..7406b65e2cdd 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -452,7 +452,7 @@ static int tmc_set_etf_buffer(struct coresight_device *csdev, return -EINVAL;

/* wrap head around to the amount of space we have */ - head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); + head = handle->head & (((unsigned long)buf->nr_pages << PAGE_SHIFT) - 1);

/* find the page to write to */ buf->cur = head / PAGE_SIZE; diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 766325de0e29..66dc5f97a009 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -45,7 +45,8 @@ struct etr_perf_buffer { };

/* Convert the perf index to an offset within the ETR buffer */ -#define PERF_IDX2OFF(idx, buf) ((idx) % ((buf)->nr_pages << PAGE_SHIFT)) +#define PERF_IDX2OFF(idx, buf) \ + ((idx) % ((unsigned long)(buf)->nr_pages << PAGE_SHIFT))

/* Lower limit for ETR hardware buffer */ #define TMC_ETR_PERF_MIN_BUF_SIZE SZ_1M @@ -1267,7 +1268,7 @@ alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event, * than the size requested via sysfs. */ if ((nr_pages << PAGE_SHIFT) > drvdata->size) { - etr_buf = tmc_alloc_etr_buf(drvdata, (nr_pages << PAGE_SHIFT), + etr_buf = tmc_alloc_etr_buf(drvdata, ((ssize_t)nr_pages << PAGE_SHIFT), 0, node, NULL); if (!IS_ERR(etr_buf)) goto done; diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index b97da39652d2..0ee48c5ba764 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -325,7 +325,7 @@ ssize_t tmc_sg_table_get_data(struct tmc_sg_table *sg_table, static inline unsigned long tmc_sg_table_buf_size(struct tmc_sg_table *sg_table) { - return sg_table->data_pages.nr_pages << PAGE_SHIFT; + return (unsigned long)sg_table->data_pages.nr_pages << PAGE_SHIFT; }

struct coresight_device *tmc_etr_get_catu_device(struct tmc_drvdata *drvdata);