mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-21 20:47:12 +07:00
b24413180f
Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
587 lines
18 KiB
C
587 lines
18 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* ARMv6 Performance counter handling code.
|
|
*
|
|
* Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
|
|
*
|
|
* ARMv6 has 2 configurable performance counters and a single cycle counter.
|
|
* They all share a single reset bit but can be written to zero so we can use
|
|
* that for a reset.
|
|
*
|
|
* The counters can't be individually enabled or disabled so when we remove
|
|
* one event and replace it with another we could get spurious counts from the
|
|
* wrong event. However, we can take advantage of the fact that the
|
|
* performance counters can export events to the event bus, and the event bus
|
|
* itself can be monitored. This requires that we *don't* export the events to
|
|
* the event bus. The procedure for disabling a configurable counter is:
|
|
* - change the counter to count the ETMEXTOUT[0] signal (0x20). This
|
|
* effectively stops the counter from counting.
|
|
* - disable the counter's interrupt generation (each counter has it's
|
|
* own interrupt enable bit).
|
|
* Once stopped, the counter value can be written as 0 to reset.
|
|
*
|
|
* To enable a counter:
|
|
* - enable the counter's interrupt generation.
|
|
* - set the new event type.
|
|
*
|
|
* Note: the dedicated cycle counter only counts cycles and can't be
|
|
* enabled/disabled independently of the others. When we want to disable the
|
|
* cycle counter, we have to just disable the interrupt reporting and start
|
|
* ignoring that counter. When re-enabling, we have to reset the value and
|
|
* enable the interrupt.
|
|
*/
|
|
|
|
#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
|
|
|
|
#include <asm/cputype.h>
|
|
#include <asm/irq_regs.h>
|
|
|
|
#include <linux/of.h>
|
|
#include <linux/perf/arm_pmu.h>
|
|
#include <linux/platform_device.h>
|
|
|
|
enum armv6_perf_types {
|
|
ARMV6_PERFCTR_ICACHE_MISS = 0x0,
|
|
ARMV6_PERFCTR_IBUF_STALL = 0x1,
|
|
ARMV6_PERFCTR_DDEP_STALL = 0x2,
|
|
ARMV6_PERFCTR_ITLB_MISS = 0x3,
|
|
ARMV6_PERFCTR_DTLB_MISS = 0x4,
|
|
ARMV6_PERFCTR_BR_EXEC = 0x5,
|
|
ARMV6_PERFCTR_BR_MISPREDICT = 0x6,
|
|
ARMV6_PERFCTR_INSTR_EXEC = 0x7,
|
|
ARMV6_PERFCTR_DCACHE_HIT = 0x9,
|
|
ARMV6_PERFCTR_DCACHE_ACCESS = 0xA,
|
|
ARMV6_PERFCTR_DCACHE_MISS = 0xB,
|
|
ARMV6_PERFCTR_DCACHE_WBACK = 0xC,
|
|
ARMV6_PERFCTR_SW_PC_CHANGE = 0xD,
|
|
ARMV6_PERFCTR_MAIN_TLB_MISS = 0xF,
|
|
ARMV6_PERFCTR_EXPL_D_ACCESS = 0x10,
|
|
ARMV6_PERFCTR_LSU_FULL_STALL = 0x11,
|
|
ARMV6_PERFCTR_WBUF_DRAINED = 0x12,
|
|
ARMV6_PERFCTR_CPU_CYCLES = 0xFF,
|
|
ARMV6_PERFCTR_NOP = 0x20,
|
|
};
|
|
|
|
enum armv6_counters {
|
|
ARMV6_CYCLE_COUNTER = 0,
|
|
ARMV6_COUNTER0,
|
|
ARMV6_COUNTER1,
|
|
};
|
|
|
|
/*
|
|
* The hardware events that we support. We do support cache operations but
|
|
* we have harvard caches and no way to combine instruction and data
|
|
* accesses/misses in hardware.
|
|
*/
|
|
static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
|
|
PERF_MAP_ALL_UNSUPPORTED,
|
|
[PERF_COUNT_HW_CPU_CYCLES] = ARMV6_PERFCTR_CPU_CYCLES,
|
|
[PERF_COUNT_HW_INSTRUCTIONS] = ARMV6_PERFCTR_INSTR_EXEC,
|
|
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC,
|
|
[PERF_COUNT_HW_BRANCH_MISSES] = ARMV6_PERFCTR_BR_MISPREDICT,
|
|
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV6_PERFCTR_IBUF_STALL,
|
|
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV6_PERFCTR_LSU_FULL_STALL,
|
|
};
|
|
|
|
static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
|
|
[PERF_COUNT_HW_CACHE_OP_MAX]
|
|
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
|
|
PERF_CACHE_MAP_ALL_UNSUPPORTED,
|
|
|
|
/*
|
|
* The performance counters don't differentiate between read and write
|
|
* accesses/misses so this isn't strictly correct, but it's the best we
|
|
* can do. Writes and reads get combined.
|
|
*/
|
|
[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
|
|
[C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
|
|
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
|
|
[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
|
|
|
|
[C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS,
|
|
|
|
/*
|
|
* The ARM performance counters can count micro DTLB misses, micro ITLB
|
|
* misses and main TLB misses. There isn't an event for TLB misses, so
|
|
* use the micro misses here and if users want the main TLB misses they
|
|
* can use a raw counter.
|
|
*/
|
|
[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
|
|
[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
|
|
|
|
[C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
|
|
[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
|
|
};
|
|
|
|
enum armv6mpcore_perf_types {
|
|
ARMV6MPCORE_PERFCTR_ICACHE_MISS = 0x0,
|
|
ARMV6MPCORE_PERFCTR_IBUF_STALL = 0x1,
|
|
ARMV6MPCORE_PERFCTR_DDEP_STALL = 0x2,
|
|
ARMV6MPCORE_PERFCTR_ITLB_MISS = 0x3,
|
|
ARMV6MPCORE_PERFCTR_DTLB_MISS = 0x4,
|
|
ARMV6MPCORE_PERFCTR_BR_EXEC = 0x5,
|
|
ARMV6MPCORE_PERFCTR_BR_NOTPREDICT = 0x6,
|
|
ARMV6MPCORE_PERFCTR_BR_MISPREDICT = 0x7,
|
|
ARMV6MPCORE_PERFCTR_INSTR_EXEC = 0x8,
|
|
ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA,
|
|
ARMV6MPCORE_PERFCTR_DCACHE_RDMISS = 0xB,
|
|
ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC,
|
|
ARMV6MPCORE_PERFCTR_DCACHE_WRMISS = 0xD,
|
|
ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE,
|
|
ARMV6MPCORE_PERFCTR_SW_PC_CHANGE = 0xF,
|
|
ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS = 0x10,
|
|
ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11,
|
|
ARMV6MPCORE_PERFCTR_LSU_FULL_STALL = 0x12,
|
|
ARMV6MPCORE_PERFCTR_WBUF_DRAINED = 0x13,
|
|
ARMV6MPCORE_PERFCTR_CPU_CYCLES = 0xFF,
|
|
};
|
|
|
|
/*
|
|
* The hardware events that we support. We do support cache operations but
|
|
* we have harvard caches and no way to combine instruction and data
|
|
* accesses/misses in hardware.
|
|
*/
|
|
static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
|
|
PERF_MAP_ALL_UNSUPPORTED,
|
|
[PERF_COUNT_HW_CPU_CYCLES] = ARMV6MPCORE_PERFCTR_CPU_CYCLES,
|
|
[PERF_COUNT_HW_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_INSTR_EXEC,
|
|
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC,
|
|
[PERF_COUNT_HW_BRANCH_MISSES] = ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
|
|
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV6MPCORE_PERFCTR_IBUF_STALL,
|
|
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV6MPCORE_PERFCTR_LSU_FULL_STALL,
|
|
};
|
|
|
|
static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
|
|
[PERF_COUNT_HW_CACHE_OP_MAX]
|
|
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
|
|
PERF_CACHE_MAP_ALL_UNSUPPORTED,
|
|
|
|
[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
|
|
[C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
|
|
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
|
|
[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
|
|
|
|
[C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
|
|
|
|
/*
|
|
* The ARM performance counters can count micro DTLB misses, micro ITLB
|
|
* misses and main TLB misses. There isn't an event for TLB misses, so
|
|
* use the micro misses here and if users want the main TLB misses they
|
|
* can use a raw counter.
|
|
*/
|
|
[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
|
|
[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
|
|
|
|
[C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
|
|
[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
|
|
};
|
|
|
|
static inline unsigned long
|
|
armv6_pmcr_read(void)
|
|
{
|
|
u32 val;
|
|
asm volatile("mrc p15, 0, %0, c15, c12, 0" : "=r"(val));
|
|
return val;
|
|
}
|
|
|
|
static inline void
|
|
armv6_pmcr_write(unsigned long val)
|
|
{
|
|
asm volatile("mcr p15, 0, %0, c15, c12, 0" : : "r"(val));
|
|
}
|
|
|
|
#define ARMV6_PMCR_ENABLE (1 << 0)
|
|
#define ARMV6_PMCR_CTR01_RESET (1 << 1)
|
|
#define ARMV6_PMCR_CCOUNT_RESET (1 << 2)
|
|
#define ARMV6_PMCR_CCOUNT_DIV (1 << 3)
|
|
#define ARMV6_PMCR_COUNT0_IEN (1 << 4)
|
|
#define ARMV6_PMCR_COUNT1_IEN (1 << 5)
|
|
#define ARMV6_PMCR_CCOUNT_IEN (1 << 6)
|
|
#define ARMV6_PMCR_COUNT0_OVERFLOW (1 << 8)
|
|
#define ARMV6_PMCR_COUNT1_OVERFLOW (1 << 9)
|
|
#define ARMV6_PMCR_CCOUNT_OVERFLOW (1 << 10)
|
|
#define ARMV6_PMCR_EVT_COUNT0_SHIFT 20
|
|
#define ARMV6_PMCR_EVT_COUNT0_MASK (0xFF << ARMV6_PMCR_EVT_COUNT0_SHIFT)
|
|
#define ARMV6_PMCR_EVT_COUNT1_SHIFT 12
|
|
#define ARMV6_PMCR_EVT_COUNT1_MASK (0xFF << ARMV6_PMCR_EVT_COUNT1_SHIFT)
|
|
|
|
#define ARMV6_PMCR_OVERFLOWED_MASK \
|
|
(ARMV6_PMCR_COUNT0_OVERFLOW | ARMV6_PMCR_COUNT1_OVERFLOW | \
|
|
ARMV6_PMCR_CCOUNT_OVERFLOW)
|
|
|
|
static inline int
|
|
armv6_pmcr_has_overflowed(unsigned long pmcr)
|
|
{
|
|
return pmcr & ARMV6_PMCR_OVERFLOWED_MASK;
|
|
}
|
|
|
|
static inline int
|
|
armv6_pmcr_counter_has_overflowed(unsigned long pmcr,
|
|
enum armv6_counters counter)
|
|
{
|
|
int ret = 0;
|
|
|
|
if (ARMV6_CYCLE_COUNTER == counter)
|
|
ret = pmcr & ARMV6_PMCR_CCOUNT_OVERFLOW;
|
|
else if (ARMV6_COUNTER0 == counter)
|
|
ret = pmcr & ARMV6_PMCR_COUNT0_OVERFLOW;
|
|
else if (ARMV6_COUNTER1 == counter)
|
|
ret = pmcr & ARMV6_PMCR_COUNT1_OVERFLOW;
|
|
else
|
|
WARN_ONCE(1, "invalid counter number (%d)\n", counter);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static inline u32 armv6pmu_read_counter(struct perf_event *event)
|
|
{
|
|
struct hw_perf_event *hwc = &event->hw;
|
|
int counter = hwc->idx;
|
|
unsigned long value = 0;
|
|
|
|
if (ARMV6_CYCLE_COUNTER == counter)
|
|
asm volatile("mrc p15, 0, %0, c15, c12, 1" : "=r"(value));
|
|
else if (ARMV6_COUNTER0 == counter)
|
|
asm volatile("mrc p15, 0, %0, c15, c12, 2" : "=r"(value));
|
|
else if (ARMV6_COUNTER1 == counter)
|
|
asm volatile("mrc p15, 0, %0, c15, c12, 3" : "=r"(value));
|
|
else
|
|
WARN_ONCE(1, "invalid counter number (%d)\n", counter);
|
|
|
|
return value;
|
|
}
|
|
|
|
static inline void armv6pmu_write_counter(struct perf_event *event, u32 value)
|
|
{
|
|
struct hw_perf_event *hwc = &event->hw;
|
|
int counter = hwc->idx;
|
|
|
|
if (ARMV6_CYCLE_COUNTER == counter)
|
|
asm volatile("mcr p15, 0, %0, c15, c12, 1" : : "r"(value));
|
|
else if (ARMV6_COUNTER0 == counter)
|
|
asm volatile("mcr p15, 0, %0, c15, c12, 2" : : "r"(value));
|
|
else if (ARMV6_COUNTER1 == counter)
|
|
asm volatile("mcr p15, 0, %0, c15, c12, 3" : : "r"(value));
|
|
else
|
|
WARN_ONCE(1, "invalid counter number (%d)\n", counter);
|
|
}
|
|
|
|
static void armv6pmu_enable_event(struct perf_event *event)
|
|
{
|
|
unsigned long val, mask, evt, flags;
|
|
struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
|
|
struct hw_perf_event *hwc = &event->hw;
|
|
struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
|
|
int idx = hwc->idx;
|
|
|
|
if (ARMV6_CYCLE_COUNTER == idx) {
|
|
mask = 0;
|
|
evt = ARMV6_PMCR_CCOUNT_IEN;
|
|
} else if (ARMV6_COUNTER0 == idx) {
|
|
mask = ARMV6_PMCR_EVT_COUNT0_MASK;
|
|
evt = (hwc->config_base << ARMV6_PMCR_EVT_COUNT0_SHIFT) |
|
|
ARMV6_PMCR_COUNT0_IEN;
|
|
} else if (ARMV6_COUNTER1 == idx) {
|
|
mask = ARMV6_PMCR_EVT_COUNT1_MASK;
|
|
evt = (hwc->config_base << ARMV6_PMCR_EVT_COUNT1_SHIFT) |
|
|
ARMV6_PMCR_COUNT1_IEN;
|
|
} else {
|
|
WARN_ONCE(1, "invalid counter number (%d)\n", idx);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Mask out the current event and set the counter to count the event
|
|
* that we're interested in.
|
|
*/
|
|
raw_spin_lock_irqsave(&events->pmu_lock, flags);
|
|
val = armv6_pmcr_read();
|
|
val &= ~mask;
|
|
val |= evt;
|
|
armv6_pmcr_write(val);
|
|
raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
|
|
}
|
|
|
|
static irqreturn_t
|
|
armv6pmu_handle_irq(int irq_num,
|
|
void *dev)
|
|
{
|
|
unsigned long pmcr = armv6_pmcr_read();
|
|
struct perf_sample_data data;
|
|
struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
|
|
struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
|
|
struct pt_regs *regs;
|
|
int idx;
|
|
|
|
if (!armv6_pmcr_has_overflowed(pmcr))
|
|
return IRQ_NONE;
|
|
|
|
regs = get_irq_regs();
|
|
|
|
/*
|
|
* The interrupts are cleared by writing the overflow flags back to
|
|
* the control register. All of the other bits don't have any effect
|
|
* if they are rewritten, so write the whole value back.
|
|
*/
|
|
armv6_pmcr_write(pmcr);
|
|
|
|
for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
|
|
struct perf_event *event = cpuc->events[idx];
|
|
struct hw_perf_event *hwc;
|
|
|
|
/* Ignore if we don't have an event. */
|
|
if (!event)
|
|
continue;
|
|
|
|
/*
|
|
* We have a single interrupt for all counters. Check that
|
|
* each counter has overflowed before we process it.
|
|
*/
|
|
if (!armv6_pmcr_counter_has_overflowed(pmcr, idx))
|
|
continue;
|
|
|
|
hwc = &event->hw;
|
|
armpmu_event_update(event);
|
|
perf_sample_data_init(&data, 0, hwc->last_period);
|
|
if (!armpmu_event_set_period(event))
|
|
continue;
|
|
|
|
if (perf_event_overflow(event, &data, regs))
|
|
cpu_pmu->disable(event);
|
|
}
|
|
|
|
/*
|
|
* Handle the pending perf events.
|
|
*
|
|
* Note: this call *must* be run with interrupts disabled. For
|
|
* platforms that can have the PMU interrupts raised as an NMI, this
|
|
* will not work.
|
|
*/
|
|
irq_work_run();
|
|
|
|
return IRQ_HANDLED;
|
|
}
|
|
|
|
static void armv6pmu_start(struct arm_pmu *cpu_pmu)
|
|
{
|
|
unsigned long flags, val;
|
|
struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
|
|
|
|
raw_spin_lock_irqsave(&events->pmu_lock, flags);
|
|
val = armv6_pmcr_read();
|
|
val |= ARMV6_PMCR_ENABLE;
|
|
armv6_pmcr_write(val);
|
|
raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
|
|
}
|
|
|
|
static void armv6pmu_stop(struct arm_pmu *cpu_pmu)
|
|
{
|
|
unsigned long flags, val;
|
|
struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
|
|
|
|
raw_spin_lock_irqsave(&events->pmu_lock, flags);
|
|
val = armv6_pmcr_read();
|
|
val &= ~ARMV6_PMCR_ENABLE;
|
|
armv6_pmcr_write(val);
|
|
raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
|
|
}
|
|
|
|
static int
|
|
armv6pmu_get_event_idx(struct pmu_hw_events *cpuc,
|
|
struct perf_event *event)
|
|
{
|
|
struct hw_perf_event *hwc = &event->hw;
|
|
/* Always place a cycle counter into the cycle counter. */
|
|
if (ARMV6_PERFCTR_CPU_CYCLES == hwc->config_base) {
|
|
if (test_and_set_bit(ARMV6_CYCLE_COUNTER, cpuc->used_mask))
|
|
return -EAGAIN;
|
|
|
|
return ARMV6_CYCLE_COUNTER;
|
|
} else {
|
|
/*
|
|
* For anything other than a cycle counter, try and use
|
|
* counter0 and counter1.
|
|
*/
|
|
if (!test_and_set_bit(ARMV6_COUNTER1, cpuc->used_mask))
|
|
return ARMV6_COUNTER1;
|
|
|
|
if (!test_and_set_bit(ARMV6_COUNTER0, cpuc->used_mask))
|
|
return ARMV6_COUNTER0;
|
|
|
|
/* The counters are all in use. */
|
|
return -EAGAIN;
|
|
}
|
|
}
|
|
|
|
static void armv6pmu_disable_event(struct perf_event *event)
|
|
{
|
|
unsigned long val, mask, evt, flags;
|
|
struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
|
|
struct hw_perf_event *hwc = &event->hw;
|
|
struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
|
|
int idx = hwc->idx;
|
|
|
|
if (ARMV6_CYCLE_COUNTER == idx) {
|
|
mask = ARMV6_PMCR_CCOUNT_IEN;
|
|
evt = 0;
|
|
} else if (ARMV6_COUNTER0 == idx) {
|
|
mask = ARMV6_PMCR_COUNT0_IEN | ARMV6_PMCR_EVT_COUNT0_MASK;
|
|
evt = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT0_SHIFT;
|
|
} else if (ARMV6_COUNTER1 == idx) {
|
|
mask = ARMV6_PMCR_COUNT1_IEN | ARMV6_PMCR_EVT_COUNT1_MASK;
|
|
evt = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT1_SHIFT;
|
|
} else {
|
|
WARN_ONCE(1, "invalid counter number (%d)\n", idx);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Mask out the current event and set the counter to count the number
|
|
* of ETM bus signal assertion cycles. The external reporting should
|
|
* be disabled and so this should never increment.
|
|
*/
|
|
raw_spin_lock_irqsave(&events->pmu_lock, flags);
|
|
val = armv6_pmcr_read();
|
|
val &= ~mask;
|
|
val |= evt;
|
|
armv6_pmcr_write(val);
|
|
raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
|
|
}
|
|
|
|
static void armv6mpcore_pmu_disable_event(struct perf_event *event)
|
|
{
|
|
unsigned long val, mask, flags, evt = 0;
|
|
struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
|
|
struct hw_perf_event *hwc = &event->hw;
|
|
struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
|
|
int idx = hwc->idx;
|
|
|
|
if (ARMV6_CYCLE_COUNTER == idx) {
|
|
mask = ARMV6_PMCR_CCOUNT_IEN;
|
|
} else if (ARMV6_COUNTER0 == idx) {
|
|
mask = ARMV6_PMCR_COUNT0_IEN;
|
|
} else if (ARMV6_COUNTER1 == idx) {
|
|
mask = ARMV6_PMCR_COUNT1_IEN;
|
|
} else {
|
|
WARN_ONCE(1, "invalid counter number (%d)\n", idx);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Unlike UP ARMv6, we don't have a way of stopping the counters. We
|
|
* simply disable the interrupt reporting.
|
|
*/
|
|
raw_spin_lock_irqsave(&events->pmu_lock, flags);
|
|
val = armv6_pmcr_read();
|
|
val &= ~mask;
|
|
val |= evt;
|
|
armv6_pmcr_write(val);
|
|
raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
|
|
}
|
|
|
|
static int armv6_map_event(struct perf_event *event)
|
|
{
|
|
return armpmu_map_event(event, &armv6_perf_map,
|
|
&armv6_perf_cache_map, 0xFF);
|
|
}
|
|
|
|
static void armv6pmu_init(struct arm_pmu *cpu_pmu)
|
|
{
|
|
cpu_pmu->handle_irq = armv6pmu_handle_irq;
|
|
cpu_pmu->enable = armv6pmu_enable_event;
|
|
cpu_pmu->disable = armv6pmu_disable_event;
|
|
cpu_pmu->read_counter = armv6pmu_read_counter;
|
|
cpu_pmu->write_counter = armv6pmu_write_counter;
|
|
cpu_pmu->get_event_idx = armv6pmu_get_event_idx;
|
|
cpu_pmu->start = armv6pmu_start;
|
|
cpu_pmu->stop = armv6pmu_stop;
|
|
cpu_pmu->map_event = armv6_map_event;
|
|
cpu_pmu->num_events = 3;
|
|
cpu_pmu->max_period = (1LLU << 32) - 1;
|
|
}
|
|
|
|
static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
|
|
{
|
|
armv6pmu_init(cpu_pmu);
|
|
cpu_pmu->name = "armv6_1136";
|
|
return 0;
|
|
}
|
|
|
|
static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu)
|
|
{
|
|
armv6pmu_init(cpu_pmu);
|
|
cpu_pmu->name = "armv6_1156";
|
|
return 0;
|
|
}
|
|
|
|
static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
|
|
{
|
|
armv6pmu_init(cpu_pmu);
|
|
cpu_pmu->name = "armv6_1176";
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* ARMv6mpcore is almost identical to single core ARMv6 with the exception
|
|
* that some of the events have different enumerations and that there is no
|
|
* *hack* to stop the programmable counters. To stop the counters we simply
|
|
* disable the interrupt reporting and update the event. When unthrottling we
|
|
* reset the period and enable the interrupt reporting.
|
|
*/
|
|
|
|
static int armv6mpcore_map_event(struct perf_event *event)
|
|
{
|
|
return armpmu_map_event(event, &armv6mpcore_perf_map,
|
|
&armv6mpcore_perf_cache_map, 0xFF);
|
|
}
|
|
|
|
static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
|
|
{
|
|
cpu_pmu->name = "armv6_11mpcore";
|
|
cpu_pmu->handle_irq = armv6pmu_handle_irq;
|
|
cpu_pmu->enable = armv6pmu_enable_event;
|
|
cpu_pmu->disable = armv6mpcore_pmu_disable_event;
|
|
cpu_pmu->read_counter = armv6pmu_read_counter;
|
|
cpu_pmu->write_counter = armv6pmu_write_counter;
|
|
cpu_pmu->get_event_idx = armv6pmu_get_event_idx;
|
|
cpu_pmu->start = armv6pmu_start;
|
|
cpu_pmu->stop = armv6pmu_stop;
|
|
cpu_pmu->map_event = armv6mpcore_map_event;
|
|
cpu_pmu->num_events = 3;
|
|
cpu_pmu->max_period = (1LLU << 32) - 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct of_device_id armv6_pmu_of_device_ids[] = {
|
|
{.compatible = "arm,arm11mpcore-pmu", .data = armv6mpcore_pmu_init},
|
|
{.compatible = "arm,arm1176-pmu", .data = armv6_1176_pmu_init},
|
|
{.compatible = "arm,arm1136-pmu", .data = armv6_1136_pmu_init},
|
|
{ /* sentinel value */ }
|
|
};
|
|
|
|
static const struct pmu_probe_info armv6_pmu_probe_table[] = {
|
|
ARM_PMU_PROBE(ARM_CPU_PART_ARM1136, armv6_1136_pmu_init),
|
|
ARM_PMU_PROBE(ARM_CPU_PART_ARM1156, armv6_1156_pmu_init),
|
|
ARM_PMU_PROBE(ARM_CPU_PART_ARM1176, armv6_1176_pmu_init),
|
|
ARM_PMU_PROBE(ARM_CPU_PART_ARM11MPCORE, armv6mpcore_pmu_init),
|
|
{ /* sentinel value */ }
|
|
};
|
|
|
|
static int armv6_pmu_device_probe(struct platform_device *pdev)
|
|
{
|
|
return arm_pmu_device_probe(pdev, armv6_pmu_of_device_ids,
|
|
armv6_pmu_probe_table);
|
|
}
|
|
|
|
static struct platform_driver armv6_pmu_driver = {
|
|
.driver = {
|
|
.name = "armv6-pmu",
|
|
.of_match_table = armv6_pmu_of_device_ids,
|
|
},
|
|
.probe = armv6_pmu_device_probe,
|
|
};
|
|
|
|
builtin_platform_driver(armv6_pmu_driver);
|
|
#endif /* CONFIG_CPU_V6 || CONFIG_CPU_V6K */
|