9f8a645b4a
commit 5b590160d2cf776b304eb054afafea2bd55e3620 upstream.
If the trace data buffer becomes full, a truncated flag [T] is reported
in PERF_RECORD_AUX. In some cases, the size reported is 0, even though
data must have been added to make the buffer full.
That happens when the buffer fills up from empty to full before the
Intel PT driver has updated the buffer position. Then the driver
calculates the new buffer position before calculating the data size.
If the old and new positions are the same, the data size is reported
as 0, even though it is really the whole buffer size.
Fix by detecting when the buffer position is wrapped, and adjust the
data size calculation accordingly.
Example
Use a very small buffer size (8K) and observe the size of truncated [T]
data. Before the fix, it is possible to see records of 0 size.
Before:
$ perf record -m,8K -e intel_pt// uname
Linux
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.105 MB perf.data ]
$ perf script -D --no-itrace | grep AUX | grep -F '[T]'
Warning:
AUX data lost 2 times out of 3!
5 19462712368111 0x19710 [0x40]: PERF_RECORD_AUX offset: 0 size: 0 flags: 0x1 [T]
5 19462712700046 0x19ba8 [0x40]: PERF_RECORD_AUX offset: 0x170 size: 0xe90 flags: 0x1 [T]
After:
$ perf record -m,8K -e intel_pt// uname
Linux
[ perf record: Woken up 3 times to write data ]
[ perf record: Captured and wrote 0.040 MB perf.data ]
$ perf script -D --no-itrace | grep AUX | grep -F '[T]'
Warning:
AUX data lost 2 times out of 3!
1 113720802995 0x4948 [0x40]: PERF_RECORD_AUX offset: 0 size: 0x2000 flags: 0x1 [T]
1 113720979812 0x6b10 [0x40]: PERF_RECORD_AUX offset: 0x2000 size: 0x2000 flags: 0x1 [T]
Fixes: 52ca9ced3f70 ("perf/x86/intel/pt: Add Intel PT PMU driver")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20241022155920.17511-2-adrian.hunter@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
134 lines
3.4 KiB
C
Executable file
134 lines
3.4 KiB
C
Executable file
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Intel(R) Processor Trace PMU driver for perf
|
|
* Copyright (c) 2013-2014, Intel Corporation.
|
|
*
|
|
* Intel PT is specified in the Intel Architecture Instruction Set Extensions
|
|
* Programming Reference:
|
|
* http://software.intel.com/en-us/intel-isa-extensions
|
|
*/
|
|
|
|
#ifndef __INTEL_PT_H__
|
|
#define __INTEL_PT_H__
|
|
|
|
/*
|
|
* Single-entry ToPA: when this close to region boundary, switch
|
|
* buffers to avoid losing data.
|
|
*/
|
|
#define TOPA_PMI_MARGIN 512
|
|
|
|
#define TOPA_SHIFT 12
|
|
|
|
static inline unsigned int sizes(unsigned int tsz)
|
|
{
|
|
return 1 << (tsz + TOPA_SHIFT);
|
|
};
|
|
|
|
struct topa_entry {
|
|
u64 end : 1;
|
|
u64 rsvd0 : 1;
|
|
u64 intr : 1;
|
|
u64 rsvd1 : 1;
|
|
u64 stop : 1;
|
|
u64 rsvd2 : 1;
|
|
u64 size : 4;
|
|
u64 rsvd3 : 2;
|
|
u64 base : 40;
|
|
u64 rsvd4 : 12;
|
|
};
|
|
|
|
/* TSC to Core Crystal Clock Ratio */
|
|
#define CPUID_TSC_LEAF 0x15
|
|
|
|
struct pt_pmu {
|
|
struct pmu pmu;
|
|
u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
|
|
bool vmx;
|
|
bool branch_en_always_on;
|
|
unsigned long max_nonturbo_ratio;
|
|
unsigned int tsc_art_num;
|
|
unsigned int tsc_art_den;
|
|
};
|
|
|
|
/**
|
|
* struct pt_buffer - buffer configuration; one buffer per task_struct or
|
|
* cpu, depending on perf event configuration
|
|
* @tables: list of ToPA tables in this buffer
|
|
* @first: shorthand for first topa table
|
|
* @last: shorthand for last topa table
|
|
* @cur: current topa table
|
|
* @nr_pages: buffer size in pages
|
|
* @cur_idx: current output region's index within @cur table
|
|
* @output_off: offset within the current output region
|
|
* @data_size: running total of the amount of data in this buffer
|
|
* @lost: if data was lost/truncated
|
|
* @head: logical write offset inside the buffer
|
|
* @snapshot: if this is for a snapshot/overwrite counter
|
|
* @single: use Single Range Output instead of ToPA
|
|
* @wrapped: buffer advance wrapped back to the first topa table
|
|
* @stop_pos: STOP topa entry index
|
|
* @intr_pos: INT topa entry index
|
|
* @stop_te: STOP topa entry pointer
|
|
* @intr_te: INT topa entry pointer
|
|
* @data_pages: array of pages from perf
|
|
* @topa_index: table of topa entries indexed by page offset
|
|
*/
|
|
struct pt_buffer {
|
|
struct list_head tables;
|
|
struct topa *first, *last, *cur;
|
|
unsigned int cur_idx;
|
|
size_t output_off;
|
|
unsigned long nr_pages;
|
|
local_t data_size;
|
|
local64_t head;
|
|
bool snapshot;
|
|
bool single;
|
|
bool wrapped;
|
|
long stop_pos, intr_pos;
|
|
struct topa_entry *stop_te, *intr_te;
|
|
void **data_pages;
|
|
};
|
|
|
|
#define PT_FILTERS_NUM 4
|
|
|
|
/**
|
|
* struct pt_filter - IP range filter configuration
|
|
* @msr_a: range start, goes to RTIT_ADDRn_A
|
|
* @msr_b: range end, goes to RTIT_ADDRn_B
|
|
* @config: 4-bit field in RTIT_CTL
|
|
*/
|
|
struct pt_filter {
|
|
unsigned long msr_a;
|
|
unsigned long msr_b;
|
|
unsigned long config;
|
|
};
|
|
|
|
/**
|
|
* struct pt_filters - IP range filtering context
|
|
* @filter: filters defined for this context
|
|
* @nr_filters: number of defined filters in the @filter array
|
|
*/
|
|
struct pt_filters {
|
|
struct pt_filter filter[PT_FILTERS_NUM];
|
|
unsigned int nr_filters;
|
|
};
|
|
|
|
/**
|
|
* struct pt - per-cpu pt context
|
|
* @handle: perf output handle
|
|
* @filters: last configured filters
|
|
* @handle_nmi: do handle PT PMI on this cpu, there's an active event
|
|
* @vmx_on: 1 if VMX is ON on this cpu
|
|
* @output_base: cached RTIT_OUTPUT_BASE MSR value
|
|
* @output_mask: cached RTIT_OUTPUT_MASK MSR value
|
|
*/
|
|
struct pt {
|
|
struct perf_output_handle handle;
|
|
struct pt_filters filters;
|
|
int handle_nmi;
|
|
int vmx_on;
|
|
u64 output_base;
|
|
u64 output_mask;
|
|
};
|
|
|
|
#endif /* __INTEL_PT_H__ */
|