ARC: perf: Accommodate big-endian CPU
diff mbox series

Message ID 20191127080123.21890-1-abrodkin@synopsys.com
State New
Headers show
Series
  • ARC: perf: Accommodate big-endian CPU
Related show

Commit Message

Alexey Brodkin Nov. 27, 2019, 8:01 a.m. UTC
8-letter strings representing ARC perf events are stores in two
32-bit registers as ASCII characters like that: "IJMP", "IALL", "IJMPTAK" etc.

And the same order of bytes in the word is used regardless CPU endianness.

Which means in case of big-endian CPU core we need to swap bytes to get
the same order as if it was on little-endian CPU.

Otherwise we're seeing the following error message on boot:
------------------------->8----------------------
ARC perf        : 8 counters (32 bits), 40 conditions, [overflow IRQ support]
sysfs: cannot create duplicate filename '/devices/arc_pct/events/pmji'
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.2.18 #3
Stack Trace:
  arc_unwind_core+0xd4/0xfc
  dump_stack+0x64/0x80
  sysfs_warn_dup+0x46/0x58
  sysfs_add_file_mode_ns+0xb2/0x168
  create_files+0x70/0x2a0
------------[ cut here ]------------
WARNING: CPU: 0 PID: 1 at kernel/events/core.c:12144 perf_event_sysfs_init+0x70/0xa0
Failed to register pmu: arc_pct, reason -17
Modules linked in:
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.2.18 #3
Stack Trace:
  arc_unwind_core+0xd4/0xfc
  dump_stack+0x64/0x80
  __warn+0x9c/0xd4
  warn_slowpath_fmt+0x22/0x2c
  perf_event_sysfs_init+0x70/0xa0
---[ end trace a75fb9a9837bd1ec ]---
------------------------->8----------------------

What happens here we're trying to register more than one raw perf event
with the same name "PMJI". Why? Because ARC perf events are 4 to 8 letters
and encoded into two 32-bit words. In this particular case we deal with 2
events:
 * "IJMP____" which counts all jump & branch instructions
 * "IJMPC___" which counts only conditional jumps & branches

Those strings are split in two 32-bit words this way "IJMP" + "____" &
"IJMP" + "C___" correspondingly. Now if we read them swapped due to CPU core
being big-endian then we read "PMJI" + "____" & "PMJI" + "___C".

And since we interpret read array of ASCII letters as a null-terminated string
on big-endian CPU we end up with 2 events of the same name "PMJI".

Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
Cc: stable@vger.kernel.org
---

Greg, Sasha, this is the same patch as
commit 5effc09c4907 ("ARC: perf: Accommodate big-endian CPU")
but fine-tuned to be applicable to kernels 4.19 and older.

 arch/arc/kernel/perf_event.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Comments

Greg Kroah-Hartman Nov. 27, 2019, 8:32 a.m. UTC | #1
On Wed, Nov 27, 2019 at 11:01:23AM +0300, Alexey Brodkin wrote:
> 8-letter strings representing ARC perf events are stores in two
> 32-bit registers as ASCII characters like that: "IJMP", "IALL", "IJMPTAK" etc.
> 
> And the same order of bytes in the word is used regardless CPU endianness.
> 
> Which means in case of big-endian CPU core we need to swap bytes to get
> the same order as if it was on little-endian CPU.
> 
> Otherwise we're seeing the following error message on boot:
> ------------------------->8----------------------
> ARC perf        : 8 counters (32 bits), 40 conditions, [overflow IRQ support]
> sysfs: cannot create duplicate filename '/devices/arc_pct/events/pmji'
> CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.2.18 #3
> Stack Trace:
>   arc_unwind_core+0xd4/0xfc
>   dump_stack+0x64/0x80
>   sysfs_warn_dup+0x46/0x58
>   sysfs_add_file_mode_ns+0xb2/0x168
>   create_files+0x70/0x2a0
> ------------[ cut here ]------------
> WARNING: CPU: 0 PID: 1 at kernel/events/core.c:12144 perf_event_sysfs_init+0x70/0xa0
> Failed to register pmu: arc_pct, reason -17
> Modules linked in:
> CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.2.18 #3
> Stack Trace:
>   arc_unwind_core+0xd4/0xfc
>   dump_stack+0x64/0x80
>   __warn+0x9c/0xd4
>   warn_slowpath_fmt+0x22/0x2c
>   perf_event_sysfs_init+0x70/0xa0
> ---[ end trace a75fb9a9837bd1ec ]---
> ------------------------->8----------------------
> 
> What happens here we're trying to register more than one raw perf event
> with the same name "PMJI". Why? Because ARC perf events are 4 to 8 letters
> and encoded into two 32-bit words. In this particular case we deal with 2
> events:
>  * "IJMP____" which counts all jump & branch instructions
>  * "IJMPC___" which counts only conditional jumps & branches
> 
> Those strings are split in two 32-bit words this way "IJMP" + "____" &
> "IJMP" + "C___" correspondingly. Now if we read them swapped due to CPU core
> being big-endian then we read "PMJI" + "____" & "PMJI" + "___C".
> 
> And since we interpret read array of ASCII letters as a null-terminated string
> on big-endian CPU we end up with 2 events of the same name "PMJI".
> 
> Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
> Cc: stable@vger.kernel.org
> ---
> 
> Greg, Sasha, this is the same patch as
> commit 5effc09c4907 ("ARC: perf: Accommodate big-endian CPU")
> but fine-tuned to be applicable to kernels 4.19 and older.

Thanks, now queued up.

greg k-h

Patch
diff mbox series

diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 8aec462d90fb..30f66b123541 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -490,8 +490,8 @@  static int arc_pmu_device_probe(struct platform_device *pdev)
 	/* loop thru all available h/w condition indexes */
 	for (j = 0; j < cc_bcr.c; j++) {
 		write_aux_reg(ARC_REG_CC_INDEX, j);
-		cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0);
-		cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1);
+		cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0));
+		cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1));
 
 		/* See if it has been mapped to a perf event_id */
 		for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {