* [PATCH v9 2/4] selftests/powerpc: Add test for strlen()
From: Christophe Leroy @ 2018-08-02 8:26 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
wei.guo.simon, segher
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <b3d7b6cdb89a48be06a2630bf0d762d9d17d931f.1533198182.git.christophe.leroy@c-s.fr>
This patch adds a test for strlen()
string.c contains a copy of strlen() from lib/string.c
The test first tests the correctness of strlen() by comparing
the result with libc strlen(). It tests all cases of alignment.
It them tests the duration of an aligned strlen() on a 4 bytes string,
on a 16 bytes string and on a 256 bytes string.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v9: fixed relevant checkpatch warnings
v8: no change
v7: no change
v6: refactorised the benchmark test
v5: no change
v4: new
.../testing/selftests/powerpc/stringloops/Makefile | 5 +-
.../testing/selftests/powerpc/stringloops/string.c | 37 ++++++
.../testing/selftests/powerpc/stringloops/strlen.c | 131 +++++++++++++++++++++
3 files changed, 172 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/powerpc/stringloops/string.c
create mode 100644 tools/testing/selftests/powerpc/stringloops/strlen.c
diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
index 3862256c2b7d..779b644461c4 100644
--- a/tools/testing/selftests/powerpc/stringloops/Makefile
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -10,9 +10,12 @@ $(OUTPUT)/memcmp_64: CFLAGS += -m64 -maltivec
$(OUTPUT)/memcmp_32: memcmp.c
$(OUTPUT)/memcmp_32: CFLAGS += -m32
+$(OUTPUT)/strlen: strlen.c string.o
+$(OUTPUT)/string.o: string.c
+
ASFLAGS = $(CFLAGS)
-TEST_GEN_PROGS := memcmp_32 memcmp_64
+TEST_GEN_PROGS := memcmp_32 memcmp_64 strlen
include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/stringloops/string.c b/tools/testing/selftests/powerpc/stringloops/string.c
new file mode 100644
index 000000000000..9dac5ef4f52c
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/string.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/lib/string.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * stupid library routines.. The optimized versions should generally be found
+ * as inline code in <asm-xx/string.h>
+ *
+ * These are buggy as well..
+ *
+ * * Fri Jun 25 1999, Ingo Oeser <ioe@informatik.tu-chemnitz.de>
+ * - Added strsep() which will replace strtok() soon (because strsep() is
+ * reentrant and should be faster). Use only strsep() in new code, please.
+ *
+ * * Sat Feb 09 2002, Jason Thomas <jason@topic.com.au>,
+ * Matthew Hawkins <matt@mh.dropbear.id.au>
+ * - Kissed strtok() goodbye
+ */
+
+#include <stddef.h>
+
+/**
+ * strlen - Find the length of a string
+ * @s: The string to be sized
+ */
+size_t test_strlen(const char *s)
+{
+ const char *sc;
+
+ for (sc = s; *sc != '\0'; ++sc)
+ ; /* nothing */
+
+ return sc - s;
+}
diff --git a/tools/testing/selftests/powerpc/stringloops/strlen.c b/tools/testing/selftests/powerpc/stringloops/strlen.c
new file mode 100644
index 000000000000..7ea6122ecacb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/strlen.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <malloc.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include "utils.h"
+
+#define SIZE 256
+#define ITERATIONS 1000
+#define ITERATIONS_BENCH 100000
+
+int test_strlen(const void *s);
+
+/* test all offsets and lengths */
+static void test_one(char *s)
+{
+ unsigned long offset;
+
+ for (offset = 0; offset < SIZE; offset++) {
+ int x, y;
+ unsigned long i;
+
+ y = strlen(s + offset);
+ x = test_strlen(s + offset);
+
+ if (x == y)
+ continue;
+
+ printf("strlen() returned %d, should have returned %d (%p offset %ld)\n",
+ x, y, s, offset);
+
+ for (i = offset; i < SIZE; i++)
+ printf("%02x ", s[i]);
+ printf("\n");
+ }
+}
+
+static void bench_test(char *s)
+{
+ struct timespec ts_start, ts_end;
+ int i;
+
+ clock_gettime(CLOCK_MONOTONIC, &ts_start);
+
+ for (i = 0; i < ITERATIONS_BENCH; i++)
+ test_strlen(s);
+
+ clock_gettime(CLOCK_MONOTONIC, &ts_end);
+
+ printf("len %3.3d : time = %.6f\n", test_strlen(s),
+ ts_end.tv_sec - ts_start.tv_sec +
+ (ts_end.tv_nsec - ts_start.tv_nsec) / 1e9);
+}
+
+static int testcase(void)
+{
+ char *s;
+ unsigned long i;
+
+ s = memalign(128, SIZE);
+ if (!s) {
+ perror("memalign");
+ exit(1);
+ }
+
+ srandom(1);
+
+ memset(s, 0, SIZE);
+ for (i = 0; i < SIZE; i++) {
+ char c;
+
+ do {
+ c = random() & 0x7f;
+ } while (!c);
+ s[i] = c;
+ test_one(s);
+ }
+
+ for (i = 0; i < ITERATIONS; i++) {
+ unsigned long j;
+
+ for (j = 0; j < SIZE; j++) {
+ char c;
+
+ do {
+ c = random() & 0x7f;
+ } while (!c);
+ s[j] = c;
+ }
+ for (j = 0; j < sizeof(long); j++) {
+ s[SIZE - 1 - j] = 0;
+ test_one(s);
+ }
+ }
+
+ for (i = 0; i < SIZE; i++) {
+ char c;
+
+ do {
+ c = random() & 0x7f;
+ } while (!c);
+ s[i] = c;
+ }
+
+ bench_test(s);
+
+ s[16] = 0;
+ bench_test(s);
+
+ s[8] = 0;
+ bench_test(s);
+
+ s[4] = 0;
+ bench_test(s);
+
+ s[3] = 0;
+ bench_test(s);
+
+ s[2] = 0;
+ bench_test(s);
+
+ s[1] = 0;
+ bench_test(s);
+
+ return 0;
+}
+
+int main(void)
+{
+ return test_harness(testcase, "strlen");
+}
--
2.13.3
^ permalink raw reply related
* [PATCH v9 1/4] selftests/powerpc: add test for 32 bits memcmp
From: Christophe Leroy @ 2018-08-02 8:26 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
wei.guo.simon, segher
Cc: linux-kernel, linuxppc-dev
This patch renames memcmp test to memcmp_64 and adds
a memcmp_32 test for testing the 32 bits version of memcmp()
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v9: no change
v8: rebased on latest powerpc/merge
v7: no change
v6: no change
v5: no change
v4: new
tools/testing/selftests/powerpc/stringloops/Makefile | 14 +++++++++++---
tools/testing/selftests/powerpc/stringloops/memcmp_32.S | 1 +
2 files changed, 12 insertions(+), 3 deletions(-)
create mode 120000 tools/testing/selftests/powerpc/stringloops/memcmp_32.S
diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
index c60c6172dd3c..3862256c2b7d 100644
--- a/tools/testing/selftests/powerpc/stringloops/Makefile
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -1,10 +1,18 @@
# SPDX-License-Identifier: GPL-2.0
# The loops are all 64-bit code
-CFLAGS += -m64 -maltivec
CFLAGS += -I$(CURDIR)
-TEST_GEN_PROGS := memcmp
-EXTRA_SOURCES := memcmp_64.S ../harness.c
+EXTRA_SOURCES := ../harness.c
+
+$(OUTPUT)/memcmp_64: memcmp.c
+$(OUTPUT)/memcmp_64: CFLAGS += -m64 -maltivec
+
+$(OUTPUT)/memcmp_32: memcmp.c
+$(OUTPUT)/memcmp_32: CFLAGS += -m32
+
+ASFLAGS = $(CFLAGS)
+
+TEST_GEN_PROGS := memcmp_32 memcmp_64
include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/stringloops/memcmp_32.S b/tools/testing/selftests/powerpc/stringloops/memcmp_32.S
new file mode 120000
index 000000000000..056f2b3af789
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/memcmp_32.S
@@ -0,0 +1 @@
+../../../../../arch/powerpc/lib/memcmp_32.S
\ No newline at end of file
--
2.13.3
^ permalink raw reply related
* Re: [GIT PULL 00/21] perf/core improvements and fixes
From: Ingo Molnar @ 2018-08-02 8:03 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Alexander Shishkin, Alexey Budankov, Andi Kleen, Christophe Leroy,
David Ahern, Don Zickus, Ganapatrao Kulkarni, Heiko Carstens,
Hendrik Brueckner, Jan Glauber, Jayachandran C, Jiri Olsa,
Joe Mario, Kan Liang, Kim Phillips, Leo Yan, linux-arm-kernel,
linuxppc-dev, Mark Rutland, Martin Schwidefsky, Mathieu Poirier,
Michael Petlan, Mike Leach, Namhyung Kim, Naveen N . Rao,
Peter Zijlstra, Ravi Bangoria, Robert Richter, Robert Walker,
rodia, Sandipan Das, Stefan Liebler, Sunil K Pandey,
Thomas Richter, Vadim Lomovtsev, Wang Nan, Will Deacon,
Arnaldo Carvalho de Melo
In-Reply-To: <20180801213648.4814-1-acme@kernel.org>
* Arnaldo Carvalho de Melo <acme@kernel.org> wrote:
> Hi Ingo,
>
> Please consider pulling, contains a recently merged
> tip/perf/urgent,
>
> - Arnaldo
>
> Test results at the end of this message, as usual.
>
> The following changes since commit c2586cfbb905939b79b49a9121fb0a59a5668fd6:
>
> Merge remote-tracking branch 'tip/perf/urgent' into perf/core (2018-07-31 09:55:45 -0300)
>
> are available in the Git repository at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo-4.19-20180801
>
> for you to fetch changes up to b912885ab75c7c8aa841c615108afd755d0b97f8:
>
> perf trace: Do not require --no-syscalls to suppress strace like output (2018-08-01 16:20:28 -0300)
>
> ----------------------------------------------------------------
> perf/core improvements and fixes:
>
> perf trace: (Arnaldo Carvalho de Melo)
>
> - Do not require --no-syscalls to suppress strace like output, i.e.
>
> # perf trace -e sched:*switch
>
> will show just sched:sched_switch events, not strace-like formatted
> syscall events, use --syscalls to get the previous behaviour.
>
> If instead:
>
> # perf trace
>
> is used, i.e. no events specified, then --syscalls is implied and
> system wide strace like formatting will be applied to all syscalls.
>
> The behaviour when just a syscall subset is used with '-e' is unchanged:
>
> # perf trace -e *sleep,sched:*switch
>
> will work as before: just the 'nanosleep' syscall will be strace-like
> formatted plus the sched:sched_switch tracepoint event, system wide.
>
> - Allow string table generators to use a default header dir, allowing
> use of them without parameters to see the table it generates on
> stdout, e.g.:
>
> $ tools/perf/trace/beauty/kvm_ioctl.sh
> static const char *kvm_ioctl_cmds[] = {
> [0x00] = "GET_API_VERSION",
> [0x01] = "CREATE_VM",
> [0x02] = "GET_MSR_INDEX_LIST",
> [0x03] = "CHECK_EXTENSION",
> <BIG SNIP>
> [0xe0] = "CREATE_DEVICE",
> [0xe1] = "SET_DEVICE_ATTR",
> [0xe2] = "GET_DEVICE_ATTR",
> [0xe3] = "HAS_DEVICE_ATTR",
> };
> $
>
> See 'ls tools/perf/trace/beauty/*.sh' to see the available string
> table generators.
>
> - Add a generator for IPPROTO_ socket's protocol constants.
>
> perf record: (Kan Liang)
>
> - Fix error out while applying initial delay and using LBR, due to
> the use of a PERF_TYPE_SOFTWARE/PERF_COUNT_SW_DUMMY event to track
> PERF_RECORD_MMAP events while waiting for the initial delay. Such
> events fail when configured asking PERF_SAMPLE_BRANCH_STACK in
> perf_event_attr.sample_type.
>
> perf c2c: (Jiri Olsa)
>
> - Fix report crash for empty browser, when processing a perf.data file
> without events of interest, either because not asked for in
> 'perf record' or because the workload didn't triggered such events.
>
> perf list: (Michael Petlan)
>
> - Align metric group description format with PMU event description.
>
> perf tests: (Sandipan Das)
>
> - Fix indexing when invoking subtests, which caused BPF tests to
> get results for the next test in the list, with the last one
> reporting a failure.
>
> eBPF:
>
> - Fix installation directory for header files included from eBPF proggies,
> avoiding clashing with relative paths used to build other software projects
> such as glibc. (Thomas Richter)
>
> - Show better message when failing to load an object. (Arnaldo Carvalho de Melo)
>
> General: (Christophe Leroy)
>
> - Allow overriding MAX_NR_CPUS at compile time, to make the tooling
> usable in systems with less memory, in time this has to be changed
> to properly allocate based on _NPROCESSORS_ONLN.
>
> Architecture specific:
>
> - Update arm64's ThunderX2 implementation defined pmu core events (Ganapatrao Kulkarni)
>
> - Fix complex event name parsing in 'perf test' for PowerPC, where the 'umask' event
> modifier isn't present. (Sandipan Das)
>
> CoreSight ARM hardware tracing: (Leo Yan)
>
> - Fix start tracing packet handling.
>
> - Support dummy address value for CS_ETM_TRACE_ON packet.
>
> - Generate branch sample when receiving a CS_ETM_TRACE_ON packet.
>
> - Generate branch sample for CS_ETM_TRACE_ON packet.
>
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
>
> ----------------------------------------------------------------
> Arnaldo Carvalho de Melo (9):
> perf trace beauty: Default header_dir to cwd to work without parms
> tools include uapi: Grab a copy of linux/in.h
> perf beauty: Add a generator for IPPROTO_ socket's protocol constants
> perf trace beauty: Do not print NULL strarray entries
> perf trace beauty: Add beautifiers for 'socket''s 'protocol' arg
> perf trace: Beautify the AF_INET & AF_INET6 'socket' syscall 'protocol' args
> perf bpf: Show better message when failing to load an object
> perf bpf: Include uapi/linux/bpf.h from the 'perf trace' script's bpf.h
> perf trace: Do not require --no-syscalls to suppress strace like output
>
> Christophe Leroy (1):
> perf tools: Allow overriding MAX_NR_CPUS at compile time
>
> Ganapatrao Kulkarni (1):
> perf vendor events arm64: Update ThunderX2 implementation defined pmu core events
>
> Jiri Olsa (1):
> perf c2c report: Fix crash for empty browser
>
> Kan Liang (1):
> perf evlist: Fix error out while applying initial delay and LBR
>
> Leo Yan (4):
> perf cs-etm: Fix start tracing packet handling
> perf cs-etm: Support dummy address value for CS_ETM_TRACE_ON packet
> perf cs-etm: Generate branch sample when receiving a CS_ETM_TRACE_ON packet
> perf cs-etm: Generate branch sample for CS_ETM_TRACE_ON packet
>
> Michael Petlan (1):
> perf list: Unify metric group description format with PMU event description
>
> Sandipan Das (2):
> perf tests: Fix complex event name parsing
> perf tests: Fix indexing when invoking subtests
>
> Thomas Richter (1):
> perf build: Fix installation directory for eBPF
>
> tools/include/uapi/linux/in.h | 301 +++++++++++++++++++++
> tools/perf/Makefile.config | 4 +-
> tools/perf/Makefile.perf | 10 +
> tools/perf/builtin-c2c.c | 3 +
> tools/perf/builtin-trace.c | 19 +-
> tools/perf/check-headers.sh | 1 +
> tools/perf/include/bpf/bpf.h | 3 +
> tools/perf/perf.h | 2 +
> .../arch/arm64/cavium/thunderx2/core-imp-def.json | 87 +++++-
> tools/perf/tests/builtin-test.c | 4 +-
> tools/perf/tests/parse-events.c | 2 +-
> tools/perf/trace/beauty/Build | 1 +
> tools/perf/trace/beauty/beauty.h | 3 +
> tools/perf/trace/beauty/drm_ioctl.sh | 9 +-
> tools/perf/trace/beauty/kcmp_type.sh | 2 +-
> tools/perf/trace/beauty/kvm_ioctl.sh | 4 +-
> tools/perf/trace/beauty/madvise_behavior.sh | 2 +-
> tools/perf/trace/beauty/perf_ioctl.sh | 2 +-
> .../perf/trace/beauty/pkey_alloc_access_rights.sh | 2 +-
> tools/perf/trace/beauty/sndrv_ctl_ioctl.sh | 4 +-
> tools/perf/trace/beauty/sndrv_pcm_ioctl.sh | 4 +-
> tools/perf/trace/beauty/socket.c | 28 ++
> tools/perf/trace/beauty/socket_ipproto.sh | 11 +
> tools/perf/trace/beauty/vhost_virtio_ioctl.sh | 6 +-
> tools/perf/util/bpf-loader.c | 4 +-
> tools/perf/util/cs-etm-decoder/cs-etm-decoder.h | 1 +
> tools/perf/util/cs-etm.c | 68 ++++-
> tools/perf/util/evsel.c | 14 +
> tools/perf/util/metricgroup.c | 4 +-
> 29 files changed, 556 insertions(+), 49 deletions(-)
> create mode 100644 tools/include/uapi/linux/in.h
> create mode 100644 tools/perf/trace/beauty/socket.c
> create mode 100755 tools/perf/trace/beauty/socket_ipproto.sh
Pulled, thanks a lot Arnaldo!
Ingo
^ permalink raw reply
* [PATCH v5 3/3] powerpc/time: no steal_time when CONFIG_PPC_SPLPAR is not selected
From: Christophe Leroy @ 2018-08-02 7:54 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <af8fe0a5bebd1745ceec07813fa55f1569930f2b.1533151550.git.christophe.leroy@c-s.fr>
If CONFIG_PPC_SPLPAR is not selected, steal_time will always
be NUL, so accounting it is pointless
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v5: moved the change to the original localtion
v4: removed the check in vtime_account_system(), the compiler removes the code regardless.
v3: new
arch/powerpc/kernel/time.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 3b03731221c1..b0f5cc491f8b 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -412,8 +412,10 @@ void vtime_flush(struct task_struct *tsk)
if (acct->gtime)
account_guest_time(tsk, cputime_to_nsecs(acct->gtime));
- if (acct->steal_time)
+ if (IS_ENABLED(CONFIG_PPC_SPLPAR) && acct->steal_time) {
account_steal_time(cputime_to_nsecs(acct->steal_time));
+ acct->steal_time = 0;
+ }
if (acct->idle_time)
account_idle_time(cputime_to_nsecs(acct->idle_time));
@@ -433,7 +435,6 @@ void vtime_flush(struct task_struct *tsk)
acct->utime = 0;
acct->gtime = 0;
- acct->steal_time = 0;
acct->idle_time = 0;
acct->stime = 0;
acct->hardirq_time = 0;
--
2.13.3
^ permalink raw reply related
* [PATCH v5 2/3] powerpc/time: Only set CONFIG_ARCH_HAS_SCALED_CPUTIME on PPC64
From: Christophe Leroy @ 2018-08-02 7:53 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <af8fe0a5bebd1745ceec07813fa55f1569930f2b.1533151550.git.christophe.leroy@c-s.fr>
scaled cputime is only meaningfull when the processor has
SPURR and/or PURR, which means only on PPC64.
Removing it on PPC32 significantly reduces the size of
vtime_account_system() and vtime_account_idle() on an 8xx:
Before:
00000000 l F .text 000000a8 vtime_delta
00000280 g F .text 0000010c vtime_account_system
0000038c g F .text 00000048 vtime_account_idle
After:
(vtime_delta gets inlined inside the two functions)
000001d8 g F .text 000000a0 vtime_account_system
00000278 g F .text 00000038 vtime_account_idle
In terms of performance, we also get approximatly 7% improvement on
task switch. The following small benchmark app is run with perf stat:
void *thread(void *arg)
{
int i;
for (i = 0; i < atoi((char*)arg); i++)
pthread_yield();
}
int main(int argc, char **argv)
{
pthread_t th1, th2;
pthread_create(&th1, NULL, thread, argv[1]);
pthread_create(&th2, NULL, thread, argv[1]);
pthread_join(th1, NULL);
pthread_join(th2, NULL);
return 0;
}
Before the patch:
Performance counter stats for 'chrt -f 98 ./sched 100000' (50 runs):
8228.476465 task-clock (msec) # 0.954 CPUs utilized ( +- 0.23% )
200004 context-switches # 0.024 M/sec ( +- 0.00% )
After the patch:
Performance counter stats for 'chrt -f 98 ./sched 100000' (50 runs):
7649.070444 task-clock (msec) # 0.955 CPUs utilized ( +- 0.27% )
200004 context-switches # 0.026 M/sec ( +- 0.00% )
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v5: New (previous patch splitted in two parts)
arch/powerpc/Kconfig | 2 +-
arch/powerpc/include/asm/accounting.h | 4 ++++
arch/powerpc/include/asm/cputime.h | 1 -
arch/powerpc/kernel/time.c | 12 ++++++++++--
arch/powerpc/xmon/xmon.c | 4 ++++
5 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 5eb4d969afbf..1f5ce708a650 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -137,7 +137,7 @@ config PPC
select ARCH_HAS_PMEM_API if PPC64
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_MEMBARRIER_CALLBACKS
- select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
+ select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC64
select ARCH_HAS_SG_CHAIN
select ARCH_HAS_STRICT_KERNEL_RWX if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
diff --git a/arch/powerpc/include/asm/accounting.h b/arch/powerpc/include/asm/accounting.h
index 3abcf98ed2e0..c607c5d835cc 100644
--- a/arch/powerpc/include/asm/accounting.h
+++ b/arch/powerpc/include/asm/accounting.h
@@ -15,8 +15,10 @@ struct cpu_accounting_data {
/* Accumulated cputime values to flush on ticks*/
unsigned long utime;
unsigned long stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
unsigned long utime_scaled;
unsigned long stime_scaled;
+#endif
unsigned long gtime;
unsigned long hardirq_time;
unsigned long softirq_time;
@@ -25,8 +27,10 @@ struct cpu_accounting_data {
/* Internal counters */
unsigned long starttime; /* TB value snapshot */
unsigned long starttime_user; /* TB value on exit to usermode */
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
unsigned long startspurr; /* SPURR value snapshot */
unsigned long utime_sspurr; /* ->user_time when ->startspurr set */
+#endif
};
#endif
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 133672744b2e..ae73dc8da2d4 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -61,7 +61,6 @@ static inline void arch_vtime_task_switch(struct task_struct *prev)
struct cpu_accounting_data *acct0 = get_accounting(prev);
acct->starttime = acct0->starttime;
- acct->startspurr = acct0->startspurr;
}
#endif
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 6196bd7393a3..3b03731221c1 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -175,7 +175,7 @@ static void calc_cputime_factors(void)
* Read the SPURR on systems that have it, otherwise the PURR,
* or if that doesn't exist return the timebase value passed in.
*/
-static unsigned long read_spurr(unsigned long tb)
+static inline unsigned long read_spurr(unsigned long tb)
{
if (cpu_has_feature(CPU_FTR_SPURR))
return mfspr(SPRN_SPURR);
@@ -284,7 +284,8 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct,
unsigned long now, unsigned long stime)
{
- unsigned long stime_scaled;
+ unsigned long stime_scaled = 0;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
unsigned long nowscaled, deltascaled;
unsigned long utime, utime_scaled;
@@ -315,6 +316,7 @@ static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct,
}
}
acct->utime_scaled += utime_scaled;
+#endif
return stime_scaled;
}
@@ -351,7 +353,9 @@ void vtime_account_system(struct task_struct *tsk)
if ((tsk->flags & PF_VCPU) && !irq_count()) {
acct->gtime += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
acct->utime_scaled += stime_scaled;
+#endif
} else {
if (hardirq_count())
acct->hardirq_time += stime;
@@ -360,7 +364,9 @@ void vtime_account_system(struct task_struct *tsk)
else
acct->stime += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
acct->stime_scaled += stime_scaled;
+#endif
}
}
EXPORT_SYMBOL_GPL(vtime_account_system);
@@ -377,6 +383,7 @@ void vtime_account_idle(struct task_struct *tsk)
static void vtime_flush_scaled(struct task_struct *tsk,
struct cpu_accounting_data *acct)
{
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
if (acct->utime_scaled)
tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
if (acct->stime_scaled)
@@ -385,6 +392,7 @@ static void vtime_flush_scaled(struct task_struct *tsk,
acct->utime_scaled = 0;
acct->utime_sspurr = 0;
acct->stime_scaled = 0;
+#endif
}
/*
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index c7324e8469ee..cb7d1ce029c6 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2442,11 +2442,15 @@ static void dump_one_paca(int cpu)
DUMP(p, accounting.utime, "%#-*lx");
DUMP(p, accounting.stime, "%#-*lx");
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
DUMP(p, accounting.utime_scaled, "%#-*lx");
+#endif
DUMP(p, accounting.starttime, "%#-*lx");
DUMP(p, accounting.starttime_user, "%#-*lx");
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
DUMP(p, accounting.startspurr, "%#-*lx");
DUMP(p, accounting.utime_sspurr, "%#-*lx");
+#endif
DUMP(p, accounting.steal_time, "%#-*lx");
#undef DUMP
--
2.13.3
^ permalink raw reply related
* [PATCH v5 1/3] powerpc/time: isolate scaled cputime accounting in dedicated functions.
From: Christophe Leroy @ 2018-08-02 7:53 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linux-kernel, linuxppc-dev
scaled cputime is only meaningfull when the processor has
SPURR and/or PURR, which means only on PPC64.
In preparation of the following patch that will remove
CONFIG_ARCH_HAS_SCALED_CPUTIME on PPC32, this patch moves
all scaled cputing accounting logic into dedicated functions.
This patch doesn't change any functionality. It's only code
reorganisation.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v5:
- v4 patch split in two patches. First part isolates scaled cputime accounting
in dedicated functions, second part activates it only on PPC64.
- read_spurr() kept as a separate function.
v4:
- Using the correct symbol CONFIG_ARCH_HAS_SCALED_CPUTIME instead of ARCH_HAS_SCALED_CPUTIME
- Grouped CONFIG_ARCH_HAS_SCALED_CPUTIME related code in dedicated functions to reduce the number of #ifdefs
- Integrated read_spurr() directly into the related function.
v3: Rebased following modifications in xmon.c
v2: added ifdefs in xmon to fix compilation error
arch/powerpc/kernel/time.c | 69 +++++++++++++++++++++++++++++-----------------
1 file changed, 43 insertions(+), 26 deletions(-)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 70f145e02487..6196bd7393a3 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -281,26 +281,16 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
* Account time for a transition between system, hard irq
* or soft irq state.
*/
-static unsigned long vtime_delta(struct task_struct *tsk,
- unsigned long *stime_scaled,
- unsigned long *steal_time)
+static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct,
+ unsigned long now, unsigned long stime)
{
- unsigned long now, nowscaled, deltascaled;
- unsigned long stime;
+ unsigned long stime_scaled;
+ unsigned long nowscaled, deltascaled;
unsigned long utime, utime_scaled;
- struct cpu_accounting_data *acct = get_accounting(tsk);
- WARN_ON_ONCE(!irqs_disabled());
-
- now = mftb();
nowscaled = read_spurr(now);
- stime = now - acct->starttime;
- acct->starttime = now;
deltascaled = nowscaled - acct->startspurr;
acct->startspurr = nowscaled;
-
- *steal_time = calculate_stolen_time(now);
-
utime = acct->utime - acct->utime_sspurr;
acct->utime_sspurr = acct->utime;
@@ -314,18 +304,38 @@ static unsigned long vtime_delta(struct task_struct *tsk,
* the user ticks get saved up in paca->user_time_scaled to be
* used by account_process_tick.
*/
- *stime_scaled = stime;
+ stime_scaled = stime;
utime_scaled = utime;
if (deltascaled != stime + utime) {
if (utime) {
- *stime_scaled = deltascaled * stime / (stime + utime);
- utime_scaled = deltascaled - *stime_scaled;
+ stime_scaled = deltascaled * stime / (stime + utime);
+ utime_scaled = deltascaled - stime_scaled;
} else {
- *stime_scaled = deltascaled;
+ stime_scaled = deltascaled;
}
}
acct->utime_scaled += utime_scaled;
+ return stime_scaled;
+}
+
+static unsigned long vtime_delta(struct task_struct *tsk,
+ unsigned long *stime_scaled,
+ unsigned long *steal_time)
+{
+ unsigned long now, stime;
+ struct cpu_accounting_data *acct = get_accounting(tsk);
+
+ WARN_ON_ONCE(!irqs_disabled());
+
+ now = mftb();
+ stime = now - acct->starttime;
+ acct->starttime = now;
+
+ *stime_scaled = vtime_delta_scaled(acct, now, stime);
+
+ *steal_time = calculate_stolen_time(now);
+
return stime;
}
@@ -364,6 +374,19 @@ void vtime_account_idle(struct task_struct *tsk)
acct->idle_time += stime + steal_time;
}
+static void vtime_flush_scaled(struct task_struct *tsk,
+ struct cpu_accounting_data *acct)
+{
+ if (acct->utime_scaled)
+ tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
+ if (acct->stime_scaled)
+ tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled);
+
+ acct->utime_scaled = 0;
+ acct->utime_sspurr = 0;
+ acct->stime_scaled = 0;
+}
+
/*
* Account the whole cputime accumulated in the paca
* Must be called with interrupts disabled.
@@ -378,9 +401,6 @@ void vtime_flush(struct task_struct *tsk)
if (acct->utime)
account_user_time(tsk, cputime_to_nsecs(acct->utime));
- if (acct->utime_scaled)
- tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
-
if (acct->gtime)
account_guest_time(tsk, cputime_to_nsecs(acct->gtime));
@@ -393,8 +413,6 @@ void vtime_flush(struct task_struct *tsk)
if (acct->stime)
account_system_index_time(tsk, cputime_to_nsecs(acct->stime),
CPUTIME_SYSTEM);
- if (acct->stime_scaled)
- tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled);
if (acct->hardirq_time)
account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time),
@@ -403,14 +421,13 @@ void vtime_flush(struct task_struct *tsk)
account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time),
CPUTIME_SOFTIRQ);
+ vtime_flush_scaled(tsk, acct);
+
acct->utime = 0;
- acct->utime_scaled = 0;
- acct->utime_sspurr = 0;
acct->gtime = 0;
acct->steal_time = 0;
acct->idle_time = 0;
acct->stime = 0;
- acct->stime_scaled = 0;
acct->hardirq_time = 0;
acct->softirq_time = 0;
}
--
2.13.3
^ permalink raw reply related
* Re: [PATCH v6 5/8] powerpc/pseries: flush SLB contents on SLB MCE errors.
From: Nicholas Piggin @ 2018-08-02 7:50 UTC (permalink / raw)
To: Mahesh Jagannath Salgaonkar
Cc: linuxppc-dev, Aneesh Kumar K.V, Laurent Dufour, Michal Suchanek,
Michael Ellerman
In-Reply-To: <69168845-6353-a0bc-47ab-24818eb6c661@linux.vnet.ibm.com>
On Thu, 2 Aug 2018 10:30:08 +0530
Mahesh Jagannath Salgaonkar <mahesh@linux.vnet.ibm.com> wrote:
> On 08/01/2018 11:28 AM, Nicholas Piggin wrote:
> > On Wed, 04 Jul 2018 23:28:21 +0530
> > Mahesh J Salgaonkar <mahesh@linux.vnet.ibm.com> wrote:
> >
> >> From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
> >>
> >> On pseries, as of today system crashes if we get a machine check
> >> exceptions due to SLB errors. These are soft errors and can be fixed by
> >> flushing the SLBs so the kernel can continue to function instead of
> >> system crash. We do this in real mode before turning on MMU. Otherwise
> >> we would run into nested machine checks. This patch now fetches the
> >> rtas error log in real mode and flushes the SLBs on SLB errors.
> >>
> >> Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
> >> ---
> >> arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1
> >> arch/powerpc/include/asm/machdep.h | 1
> >> arch/powerpc/kernel/exceptions-64s.S | 42 +++++++++++++++++++++
> >> arch/powerpc/kernel/mce.c | 16 +++++++-
> >> arch/powerpc/mm/slb.c | 6 +++
> >> arch/powerpc/platforms/pseries/pseries.h | 1
> >> arch/powerpc/platforms/pseries/ras.c | 51 +++++++++++++++++++++++++
> >> arch/powerpc/platforms/pseries/setup.c | 1
> >> 8 files changed, 116 insertions(+), 3 deletions(-)
> >>
> >> diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
> >> index 50ed64fba4ae..cc00a7088cf3 100644
> >> --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
> >> +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
> >> @@ -487,6 +487,7 @@ extern void hpte_init_native(void);
> >>
> >> extern void slb_initialize(void);
> >> extern void slb_flush_and_rebolt(void);
> >> +extern void slb_flush_and_rebolt_realmode(void);
> >>
> >> extern void slb_vmalloc_update(void);
> >> extern void slb_set_size(u16 size);
> >> diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
> >> index ffe7c71e1132..fe447e0d4140 100644
> >> --- a/arch/powerpc/include/asm/machdep.h
> >> +++ b/arch/powerpc/include/asm/machdep.h
> >> @@ -108,6 +108,7 @@ struct machdep_calls {
> >>
> >> /* Early exception handlers called in realmode */
> >> int (*hmi_exception_early)(struct pt_regs *regs);
> >> + int (*machine_check_early)(struct pt_regs *regs);
> >>
> >> /* Called during machine check exception to retrive fixup address. */
> >> bool (*mce_check_early_recovery)(struct pt_regs *regs);
> >> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> >> index f283958129f2..0038596b7906 100644
> >> --- a/arch/powerpc/kernel/exceptions-64s.S
> >> +++ b/arch/powerpc/kernel/exceptions-64s.S
> >> @@ -332,6 +332,9 @@ TRAMP_REAL_BEGIN(machine_check_pSeries)
> >> machine_check_fwnmi:
> >> SET_SCRATCH0(r13) /* save r13 */
> >> EXCEPTION_PROLOG_0(PACA_EXMC)
> >> +BEGIN_FTR_SECTION
> >> + b machine_check_pSeries_early
> >> +END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
> >> machine_check_pSeries_0:
> >> EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST_PR, 0x200)
> >> /*
> >> @@ -343,6 +346,45 @@ machine_check_pSeries_0:
> >>
> >> TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
> >>
> >> +TRAMP_REAL_BEGIN(machine_check_pSeries_early)
> >> +BEGIN_FTR_SECTION
> >> + EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200)
> >> + mr r10,r1 /* Save r1 */
> >> + ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */
> >> + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
> >> + mfspr r11,SPRN_SRR0 /* Save SRR0 */
> >> + mfspr r12,SPRN_SRR1 /* Save SRR1 */
> >> + EXCEPTION_PROLOG_COMMON_1()
> >> + EXCEPTION_PROLOG_COMMON_2(PACA_EXMC)
> >> + EXCEPTION_PROLOG_COMMON_3(0x200)
> >> + addi r3,r1,STACK_FRAME_OVERHEAD
> >> + BRANCH_LINK_TO_FAR(machine_check_early) /* Function call ABI */
> >> +
> >> + /* Move original SRR0 and SRR1 into the respective regs */
> >> + ld r9,_MSR(r1)
> >> + mtspr SPRN_SRR1,r9
> >> + ld r3,_NIP(r1)
> >> + mtspr SPRN_SRR0,r3
> >> + ld r9,_CTR(r1)
> >> + mtctr r9
> >> + ld r9,_XER(r1)
> >> + mtxer r9
> >> + ld r9,_LINK(r1)
> >> + mtlr r9
> >> + REST_GPR(0, r1)
> >> + REST_8GPRS(2, r1)
> >> + REST_GPR(10, r1)
> >> + ld r11,_CCR(r1)
> >> + mtcr r11
> >> + REST_GPR(11, r1)
> >> + REST_2GPRS(12, r1)
> >> + /* restore original r1. */
> >> + ld r1,GPR1(r1)
> >> + SET_SCRATCH0(r13) /* save r13 */
> >> + EXCEPTION_PROLOG_0(PACA_EXMC)
> >> + b machine_check_pSeries_0
> >> +END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
> >> +
> >> EXC_COMMON_BEGIN(machine_check_common)
> >> /*
> >> * Machine check is different because we use a different
> >> diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
> >> index efdd16a79075..221271c96a57 100644
> >> --- a/arch/powerpc/kernel/mce.c
> >> +++ b/arch/powerpc/kernel/mce.c
> >> @@ -488,9 +488,21 @@ long machine_check_early(struct pt_regs *regs)
> >> {
> >> long handled = 0;
> >>
> >> - __this_cpu_inc(irq_stat.mce_exceptions);
> >> + /*
> >> + * For pSeries we count mce when we go into virtual mode machine
> >> + * check handler. Hence skip it. Also, We can't access per cpu
> >> + * variables in real mode for LPAR.
> >> + */
> >> + if (early_cpu_has_feature(CPU_FTR_HVMODE))
> >> + __this_cpu_inc(irq_stat.mce_exceptions);
> >>
> >> - if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
> >> + /*
> >> + * See if platform is capable of handling machine check.
> >> + * Otherwise fallthrough and allow CPU to handle this machine check.
> >> + */
> >> + if (ppc_md.machine_check_early)
> >> + handled = ppc_md.machine_check_early(regs);
> >> + else if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
> >> handled = cur_cpu_spec->machine_check_early(regs);
> >> return handled;
> >> }
> >
> > This looks fine to me after Michal's patch. Not sure if you want to
> > fold them or add his immediately after this one in your series.
>
> I am planning to fold Michal's patch into this patch itself.
>
> >
> >> diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
> >> index 66577cc66dc9..5b1813b98358 100644
> >> --- a/arch/powerpc/mm/slb.c
> >> +++ b/arch/powerpc/mm/slb.c
> >> @@ -145,6 +145,12 @@ void slb_flush_and_rebolt(void)
> >> get_paca()->slb_cache_ptr = 0;
> >> }
> >>
> >> +void slb_flush_and_rebolt_realmode(void)
> >> +{
> >> + __slb_flush_and_rebolt();
> >> + get_paca()->slb_cache_ptr = 0;
> >> +}
> >
> >
> > I think this should do something more like flush_and_reload_slb from
> > powernv machine check code. We are real mode so should invalidate all
> > SLBs.
>
> Yes, and I think even powernv code should use this one instead. But that
> can be a separate patch.
Well I've already got one written for the idle code, so I'll split that
out and send that to powerpc next first, so both our patches can use it.
> > It happens I also need very similar code (without the initial
> > invalidate) for implementing idle wakeup code in C, so we should move
> > that function and variants into mm/slb.c IMO.
>
> So, you looking for only rebolt part ?
Yes it's already flushed after we come back from deep idle state, so
no need for another flush.
Thanks,
Nick
^ permalink raw reply
* Re: linux-next: manual merge of the powerpc tree with the m68k tree
From: Geert Uytterhoeven @ 2018-08-02 7:17 UTC (permalink / raw)
To: Stephen Rothwell
Cc: Michael Ellerman, Benjamin Herrenschmidt, linuxppc-dev,
Linux-Next, Linux Kernel Mailing List, Arnd Bergmann, Finn Thain
In-Reply-To: <20180802094154.6d88f03c@canb.auug.org.au>
Hi Stephen,
On Thu, Aug 2, 2018 at 1:42 AM Stephen Rothwell <sfr@canb.auug.org.au> wrote:
> [forgot the conflict resolution ...]
>
> On Thu, 2 Aug 2018 09:27:20 +1000 Stephen Rothwell <sfr@canb.auug.org.au> wrote:
> >
> > Today's linux-next merge of the powerpc tree got a conflict in:
> >
> > arch/m68k/mac/misc.c
> >
> > between commit:
> >
> > 5b9bfb8ec467 ("m68k: mac: Use time64_t in RTC handling")
> >
> > from the m68k tree and commit:
> >
> > ebd722275f9c ("macintosh/via-pmu: Replace via-pmu68k driver with via-pmu driver")
> >
> > from the powerpc tree.
> >
> > I fixed it up (see below) and can carry the fix as necessary. This
> > is now fixed as far as linux-next is concerned, but any non trivial
> > conflicts should be mentioned to your upstream maintainer when your tree
> > is submitted for merging. You may also want to consider cooperating
> > with the maintainer of the conflicting tree to minimise any particularly
> > complex conflicts.
Ah, now I remember Finn said he was going to rebase his series once the time64_t
patch has entered my tree...
> --- a/arch/m68k/mac/misc.c
> +++ b/arch/m68k/mac/misc.c
> @@@ -90,11 -85,11 +90,11 @@@ static void cuda_write_pram(int offset
> }
> #endif /* CONFIG_ADB_CUDA */
>
> - #ifdef CONFIG_ADB_PMU68K
> + #ifdef CONFIG_ADB_PMU
> -static long pmu_read_time(void)
> +static time64_t pmu_read_time(void)
> {
> struct adb_request req;
> - long time;
> + time64_t time;
>
> if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0)
> return 0;
Thanks, looks good to me!
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org
In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds
^ permalink raw reply
* Re: [PATCH] powerpc/perf: Remove sched_task function defined for thread-imc
From: Joel Stanley @ 2018-08-02 5:53 UTC (permalink / raw)
To: anju; +Cc: Michael Ellerman, Madhavan Srinivasan, linuxppc-dev
In-Reply-To: <1526628925-31075-1-git-send-email-anju@linux.vnet.ibm.com>
On Fri, 18 May 2018 at 17:06, Anju T Sudhakar <anju@linux.vnet.ibm.com> wrote:
>
> Call trace observed while running perf-fuzzer:
>
> [ 329.228068] CPU: 43 PID: 9088 Comm: perf_fuzzer Not tainted 4.13.0-32-generic #35~lp1746225
> [ 329.228070] task: c000003f776ac900 task.stack: c000003f77728000
> [ 329.228071] NIP: c000000000299b70 LR: c0000000002a4534 CTR: c00000000029bb80
> [ 329.228073] REGS: c000003f7772b760 TRAP: 0700 Not tainted (4.13.0-32-generic)
> [ 329.228073] MSR: 900000000282b033 <SF,HV,VEC,VSX,EE,FP,ME,IR,DR,RI,LE>
> [ 329.228079] CR: 24008822 XER: 00000000
> [ 329.228080] CFAR: c000000000299a70 SOFTE: 0
> GPR00: c0000000002a4534 c000003f7772b9e0 c000000001606200 c000003fef858908
> GPR04: c000003f776ac900 0000000000000001 ffffffffffffffff 0000003fee730000
> GPR08: 0000000000000000 0000000000000000 c0000000011220d8 0000000000000002
> GPR12: c00000000029bb80 c000000007a3d900 0000000000000000 0000000000000000
> GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
> GPR20: 0000000000000000 0000000000000000 c000003f776ad090 c000000000c71354
> GPR24: c000003fef716780 0000003fee730000 c000003fe69d4200 c000003f776ad330
> GPR28: c0000000011220d8 0000000000000001 c0000000014c6108 c000003fef858900
> [ 329.228098] NIP [c000000000299b70] perf_pmu_sched_task+0x170/0x180
> [ 329.228100] LR [c0000000002a4534] __perf_event_task_sched_in+0xc4/0x230
> [ 329.228101] Call Trace:
> [ 329.228102] [c000003f7772b9e0] [c0000000002a0678] perf_iterate_sb+0x158/0x2a0 (unreliable)
> [ 329.228105] [c000003f7772ba30] [c0000000002a4534] __perf_event_task_sched_in+0xc4/0x230
> [ 329.228107] [c000003f7772bab0] [c0000000001396dc] finish_task_switch+0x21c/0x310
> [ 329.228109] [c000003f7772bb60] [c000000000c71354] __schedule+0x304/0xb80
> [ 329.228111] [c000003f7772bc40] [c000000000c71c10] schedule+0x40/0xc0
> [ 329.228113] [c000003f7772bc60] [c0000000001033f4] do_wait+0x254/0x2e0
> [ 329.228115] [c000003f7772bcd0] [c000000000104ac0] kernel_wait4+0xa0/0x1a0
> [ 329.228117] [c000003f7772bd70] [c000000000104c24] SyS_wait4+0x64/0xc0
> [ 329.228121] [c000003f7772be30] [c00000000000b184] system_call+0x58/0x6c
> [ 329.228121] Instruction dump:
> [ 329.228123] 3beafea0 7faa4800 409eff18 e8010060 eb610028 ebc10040 7c0803a6 38210050
> [ 329.228127] eb81ffe0 eba1ffe8 ebe1fff8 4e800020 <0fe00000> 4bffffbc 60000000 60420000
> [ 329.228131] ---[ end trace 8c46856d314c1811 ]---
> [ 375.755943] hrtimer: interrupt took 31601 ns
>
>
> The context switch call-backs for thread-imc are defined in sched_task function.
> So when thread-imc events are grouped with software pmu events,
> perf_pmu_sched_task hits the WARN_ON_ONCE condition, since software PMUs are
> assumed not to have a sched_task defined.
>
> Patch to move the thread_imc enable/disable opal call back from sched_task to
> event_[add/del] function
>
> Signed-off-by: Anju T Sudhakar <anju@linux.vnet.ibm.com>
I reproduced the WARN when running -rc7 on a Power9 box. I haven't
seen it since applying this patch.
Tested-by: Joel Stanley <joel@jms.id.au>
Cheers,
Joel
^ permalink raw reply
* Re: [PATCH v4 5/6] powerpc: Add show_user_instructions()
From: Christophe LEROY @ 2018-08-02 5:26 UTC (permalink / raw)
To: Murilo Opsfelder Araujo, linux-kernel
Cc: Alastair D'Silva, Andrew Donnellan, Balbir Singh,
Benjamin Herrenschmidt, Cyril Bur, Eric W . Biederman,
Joe Perches, Michael Ellerman, Michael Neuling, Nicholas Piggin,
Paul Mackerras, Simon Guo, Sukadev Bhattiprolu, Tobin C . Harding,
linuxppc-dev, Segher Boessenkool
In-Reply-To: <20180801213320.11203-6-muriloo@linux.ibm.com>
Le 01/08/2018 à 23:33, Murilo Opsfelder Araujo a écrit :
> show_user_instructions() is a slightly modified version of
> show_instructions() that allows userspace instruction dump.
>
> This will be useful within show_signal_msg() to dump userspace
> instructions of the faulty location.
>
> Here is a sample of what show_user_instructions() outputs:
>
> pandafault[10850]: code: 4bfffeec 4bfffee8 3c401002 38427f00 fbe1fff8 f821ffc1 7c3f0b78 3d22fffe
> pandafault[10850]: code: 392988d0 f93f0020 e93f0020 39400048 <99490000> 39200000 7d234b78 383f0040
>
> The current->comm and current->pid printed can serve as a glue that
> links the instructions dump to its originator, allowing messages to be
> interleaved in the logs.
>
> Signed-off-by: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
> ---
> arch/powerpc/include/asm/stacktrace.h | 13 +++++++++
> arch/powerpc/kernel/process.c | 40 +++++++++++++++++++++++++++
> 2 files changed, 53 insertions(+)
> create mode 100644 arch/powerpc/include/asm/stacktrace.h
>
> diff --git a/arch/powerpc/include/asm/stacktrace.h b/arch/powerpc/include/asm/stacktrace.h
> new file mode 100644
> index 000000000000..6149b53b3bc8
> --- /dev/null
> +++ b/arch/powerpc/include/asm/stacktrace.h
> @@ -0,0 +1,13 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * Stack trace functions.
> + *
> + * Copyright 2018, Murilo Opsfelder Araujo, IBM Corporation.
> + */
> +
> +#ifndef _ASM_POWERPC_STACKTRACE_H
> +#define _ASM_POWERPC_STACKTRACE_H
> +
> +void show_user_instructions(struct pt_regs *regs);
> +
> +#endif /* _ASM_POWERPC_STACKTRACE_H */
> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
> index e9533b4d2f08..364645ac732c 100644
> --- a/arch/powerpc/kernel/process.c
> +++ b/arch/powerpc/kernel/process.c
> @@ -1299,6 +1299,46 @@ static void show_instructions(struct pt_regs *regs)
> pr_cont("\n");
> }
>
> +void show_user_instructions(struct pt_regs *regs)
> +{
> + int i;
> + const char *prefix = KERN_INFO "%s[%d]: code: ";
> + unsigned long pc = regs->nip - (instructions_to_print * 3 / 4 *
> + sizeof(int));
> +
> + printk(prefix, current->comm, current->pid);
Why not use pr_info() and remove KERN_INFO from *prefix ?
> +
> + for (i = 0; i < instructions_to_print; i++) {
> + int instr;
> +
> + if (!(i % 8) && (i > 0)) {
> + pr_cont("\n");
> + printk(prefix, current->comm, current->pid);
> + }
> +
> +#if !defined(CONFIG_BOOKE)
> + /* If executing with the IMMU off, adjust pc rather
> + * than print XXXXXXXX.
> + */
> + if (!(regs->msr & MSR_IR))
> + pc = (unsigned long)phys_to_virt(pc);
Shouldn't this be done outside of the loop, only once ?
Christophe
> +#endif
> +
> + if (probe_kernel_address((unsigned int __user *)pc, instr)) {
> + pr_cont("XXXXXXXX ");
> + } else {
> + if (regs->nip == pc)
> + pr_cont("<%08x> ", instr);
> + else
> + pr_cont("%08x ", instr);
> + }
> +
> + pc += sizeof(int);
> + }
> +
> + pr_cont("\n");
> +}
> +
> struct regbit {
> unsigned long bit;
> const char *name;
>
^ permalink raw reply
* Re: [PATCH v6 5/8] powerpc/pseries: flush SLB contents on SLB MCE errors.
From: Mahesh Jagannath Salgaonkar @ 2018-08-02 5:00 UTC (permalink / raw)
To: Nicholas Piggin
Cc: linuxppc-dev, Aneesh Kumar K.V, Laurent Dufour, Michal Suchanek,
Michael Ellerman
In-Reply-To: <20180801155853.3af801c2@roar.ozlabs.ibm.com>
On 08/01/2018 11:28 AM, Nicholas Piggin wrote:
> On Wed, 04 Jul 2018 23:28:21 +0530
> Mahesh J Salgaonkar <mahesh@linux.vnet.ibm.com> wrote:
>
>> From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
>>
>> On pseries, as of today system crashes if we get a machine check
>> exceptions due to SLB errors. These are soft errors and can be fixed by
>> flushing the SLBs so the kernel can continue to function instead of
>> system crash. We do this in real mode before turning on MMU. Otherwise
>> we would run into nested machine checks. This patch now fetches the
>> rtas error log in real mode and flushes the SLBs on SLB errors.
>>
>> Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
>> ---
>> arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1
>> arch/powerpc/include/asm/machdep.h | 1
>> arch/powerpc/kernel/exceptions-64s.S | 42 +++++++++++++++++++++
>> arch/powerpc/kernel/mce.c | 16 +++++++-
>> arch/powerpc/mm/slb.c | 6 +++
>> arch/powerpc/platforms/pseries/pseries.h | 1
>> arch/powerpc/platforms/pseries/ras.c | 51 +++++++++++++++++++++++++
>> arch/powerpc/platforms/pseries/setup.c | 1
>> 8 files changed, 116 insertions(+), 3 deletions(-)
>>
>> diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
>> index 50ed64fba4ae..cc00a7088cf3 100644
>> --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
>> +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
>> @@ -487,6 +487,7 @@ extern void hpte_init_native(void);
>>
>> extern void slb_initialize(void);
>> extern void slb_flush_and_rebolt(void);
>> +extern void slb_flush_and_rebolt_realmode(void);
>>
>> extern void slb_vmalloc_update(void);
>> extern void slb_set_size(u16 size);
>> diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
>> index ffe7c71e1132..fe447e0d4140 100644
>> --- a/arch/powerpc/include/asm/machdep.h
>> +++ b/arch/powerpc/include/asm/machdep.h
>> @@ -108,6 +108,7 @@ struct machdep_calls {
>>
>> /* Early exception handlers called in realmode */
>> int (*hmi_exception_early)(struct pt_regs *regs);
>> + int (*machine_check_early)(struct pt_regs *regs);
>>
>> /* Called during machine check exception to retrive fixup address. */
>> bool (*mce_check_early_recovery)(struct pt_regs *regs);
>> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
>> index f283958129f2..0038596b7906 100644
>> --- a/arch/powerpc/kernel/exceptions-64s.S
>> +++ b/arch/powerpc/kernel/exceptions-64s.S
>> @@ -332,6 +332,9 @@ TRAMP_REAL_BEGIN(machine_check_pSeries)
>> machine_check_fwnmi:
>> SET_SCRATCH0(r13) /* save r13 */
>> EXCEPTION_PROLOG_0(PACA_EXMC)
>> +BEGIN_FTR_SECTION
>> + b machine_check_pSeries_early
>> +END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
>> machine_check_pSeries_0:
>> EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST_PR, 0x200)
>> /*
>> @@ -343,6 +346,45 @@ machine_check_pSeries_0:
>>
>> TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
>>
>> +TRAMP_REAL_BEGIN(machine_check_pSeries_early)
>> +BEGIN_FTR_SECTION
>> + EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200)
>> + mr r10,r1 /* Save r1 */
>> + ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */
>> + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
>> + mfspr r11,SPRN_SRR0 /* Save SRR0 */
>> + mfspr r12,SPRN_SRR1 /* Save SRR1 */
>> + EXCEPTION_PROLOG_COMMON_1()
>> + EXCEPTION_PROLOG_COMMON_2(PACA_EXMC)
>> + EXCEPTION_PROLOG_COMMON_3(0x200)
>> + addi r3,r1,STACK_FRAME_OVERHEAD
>> + BRANCH_LINK_TO_FAR(machine_check_early) /* Function call ABI */
>> +
>> + /* Move original SRR0 and SRR1 into the respective regs */
>> + ld r9,_MSR(r1)
>> + mtspr SPRN_SRR1,r9
>> + ld r3,_NIP(r1)
>> + mtspr SPRN_SRR0,r3
>> + ld r9,_CTR(r1)
>> + mtctr r9
>> + ld r9,_XER(r1)
>> + mtxer r9
>> + ld r9,_LINK(r1)
>> + mtlr r9
>> + REST_GPR(0, r1)
>> + REST_8GPRS(2, r1)
>> + REST_GPR(10, r1)
>> + ld r11,_CCR(r1)
>> + mtcr r11
>> + REST_GPR(11, r1)
>> + REST_2GPRS(12, r1)
>> + /* restore original r1. */
>> + ld r1,GPR1(r1)
>> + SET_SCRATCH0(r13) /* save r13 */
>> + EXCEPTION_PROLOG_0(PACA_EXMC)
>> + b machine_check_pSeries_0
>> +END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
>> +
>> EXC_COMMON_BEGIN(machine_check_common)
>> /*
>> * Machine check is different because we use a different
>> diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
>> index efdd16a79075..221271c96a57 100644
>> --- a/arch/powerpc/kernel/mce.c
>> +++ b/arch/powerpc/kernel/mce.c
>> @@ -488,9 +488,21 @@ long machine_check_early(struct pt_regs *regs)
>> {
>> long handled = 0;
>>
>> - __this_cpu_inc(irq_stat.mce_exceptions);
>> + /*
>> + * For pSeries we count mce when we go into virtual mode machine
>> + * check handler. Hence skip it. Also, We can't access per cpu
>> + * variables in real mode for LPAR.
>> + */
>> + if (early_cpu_has_feature(CPU_FTR_HVMODE))
>> + __this_cpu_inc(irq_stat.mce_exceptions);
>>
>> - if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
>> + /*
>> + * See if platform is capable of handling machine check.
>> + * Otherwise fallthrough and allow CPU to handle this machine check.
>> + */
>> + if (ppc_md.machine_check_early)
>> + handled = ppc_md.machine_check_early(regs);
>> + else if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
>> handled = cur_cpu_spec->machine_check_early(regs);
>> return handled;
>> }
>
> This looks fine to me after Michal's patch. Not sure if you want to
> fold them or add his immediately after this one in your series.
I am planning to fold Michal's patch into this patch itself.
>
>> diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
>> index 66577cc66dc9..5b1813b98358 100644
>> --- a/arch/powerpc/mm/slb.c
>> +++ b/arch/powerpc/mm/slb.c
>> @@ -145,6 +145,12 @@ void slb_flush_and_rebolt(void)
>> get_paca()->slb_cache_ptr = 0;
>> }
>>
>> +void slb_flush_and_rebolt_realmode(void)
>> +{
>> + __slb_flush_and_rebolt();
>> + get_paca()->slb_cache_ptr = 0;
>> +}
>
>
> I think this should do something more like flush_and_reload_slb from
> powernv machine check code. We are real mode so should invalidate all
> SLBs.
Yes, and I think even powernv code should use this one instead. But that
can be a separate patch.
>
> It happens I also need very similar code (without the initial
> invalidate) for implementing idle wakeup code in C, so we should move
> that function and variants into mm/slb.c IMO.
So, you looking for only rebolt part ?
>
> Thanks,
> Nick
>
^ permalink raw reply
* [RFC PATCH 3/3] cpuidle/powernv: Conditionally save-restore sprs using opal
From: Akshay Adiga @ 2018-08-02 4:51 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev; +Cc: npiggin, mpe, benh, ego, huntbag, Akshay Adiga
In-Reply-To: <20180802045132.12432-1-akshay.adiga@linux.vnet.ibm.com>
From: Abhishek Goel <huntbag@linux.vnet.ibm.com>
If a state has "opal-supported" compat flag in device-tree, an opal call
needs to be made during the entry and exit of the stop state. This patch
passes a hint to the power9_idle_stop and power9_offline_stop.
This patch moves the saving and restoring of sprs for P9 cpuidle
from kernel to opal. This patch still uses existing code to detect
first thread in core.
In an attempt to make the powernv idle code backward compatible,
and to some extent forward compatible, add support for pre-stop entry
and post-stop exit actions in OPAL. If a kernel knows about this
opal call, then just a firmware supporting newer hardware is required,
instead of waiting for kernel updates.
Signed-off-by: Abhishek Goel <huntbag@linux.vnet.ibm.com>
Signed-off-by: Akshay Adiga <akshay.adiga@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/cpuidle.h | 1 +
arch/powerpc/include/asm/opal-api.h | 4 +-
arch/powerpc/include/asm/opal.h | 3 +
arch/powerpc/include/asm/paca.h | 5 +-
arch/powerpc/include/asm/processor.h | 6 +-
arch/powerpc/kernel/asm-offsets.c | 3 +
arch/powerpc/kernel/idle_book3s.S | 55 ++++++++++++++++++-
arch/powerpc/platforms/powernv/idle.c | 41 ++++++++++----
.../powerpc/platforms/powernv/opal-wrappers.S | 2 +
arch/powerpc/xmon/xmon.c | 14 ++---
10 files changed, 109 insertions(+), 25 deletions(-)
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index b965066560cc..2fb2324d15fc 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -96,6 +96,7 @@ struct pnv_idle_states_t {
u64 psscr_val;
u64 psscr_mask;
u32 flags;
+ bool req_opal_call;
enum idle_state_type_t type;
bool valid;
};
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index 3bab299eda49..6792a737bc9a 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -208,7 +208,9 @@
#define OPAL_SENSOR_READ_U64 162
#define OPAL_PCI_GET_PBCQ_TUNNEL_BAR 164
#define OPAL_PCI_SET_PBCQ_TUNNEL_BAR 165
-#define OPAL_LAST 165
+#define OPAL_IDLE_SAVE 168
+#define OPAL_IDLE_RESTORE 169
+#define OPAL_LAST 169
#define QUIESCE_HOLD 1 /* Spin all calls at entry */
#define QUIESCE_REJECT 2 /* Fail all calls with OPAL_BUSY */
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index e1b2910c6e81..12d57aeacde2 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -356,6 +356,9 @@ extern void opal_kmsg_init(void);
extern int opal_event_request(unsigned int opal_event_nr);
+extern int opal_cpuidle_save(u64 *stop_sprs, int scope, u64 psscr);
+extern int opal_cpuidle_restore(u64 *stop_sprs, int scope, u64 psscr, u64 srr1);
+
struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
unsigned long vmalloc_size);
void opal_free_sg_list(struct opal_sg_list *sg);
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 6d34bd71139d..586059594443 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -195,11 +195,14 @@ struct paca_struct {
/* The PSSCR value that the kernel requested before going to stop */
u64 requested_psscr;
+ u64 wakeup_psscr;
+ u8 req_opal_call;
/*
- * Save area for additional SPRs that need to be
+ * Save area for SPRs that need to be
* saved/restored during cpuidle stop.
*/
struct stop_sprs stop_sprs;
+ u64 *opal_stop_sprs;
#endif
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 34f572056add..9f9fb1f11dd6 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -513,8 +513,10 @@ enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
extern int powersave_nap; /* set if nap mode can be used in idle loop */
extern unsigned long power7_idle_insn(unsigned long type); /* PNV_THREAD_NAP/etc*/
extern void power7_idle_type(unsigned long type);
-extern unsigned long power9_idle_stop(unsigned long psscr_val);
-extern unsigned long power9_offline_stop(unsigned long psscr_val);
+extern unsigned long power9_idle_stop(unsigned long psscr_val,
+ bool opal_enabled);
+extern unsigned long power9_offline_stop(unsigned long psscr_val,
+ bool opal_enabled);
extern void power9_idle_type(int index);
extern void flush_instruction_cache(void);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 262c44a90ea1..740ae068ec74 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -768,6 +768,9 @@ int main(void)
OFFSET(PACA_SIBLING_PACA_PTRS, paca_struct, thread_sibling_pacas);
OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr);
OFFSET(PACA_DONT_STOP, paca_struct, dont_stop);
+ OFFSET(PACA_WAKEUP_PSSCR, paca_struct, wakeup_psscr);
+ OFFSET(PACA_REQ_OPAL_CALL, paca_struct, req_opal_call);
+ OFFSET(STOP_SPRS, paca_struct, opal_stop_sprs);
#define STOP_SPR(x, f) OFFSET(x, paca_struct, stop_sprs.f)
STOP_SPR(STOP_PID, pid);
STOP_SPR(STOP_LDBAR, ldbar);
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index e734f6e45abc..b5f5245011a5 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -45,6 +45,9 @@
#define PSSCR_EC_ESL_MASK_SHIFTED (PSSCR_EC | PSSCR_ESL) >> 16
+#define SCOPE_CORE 0
+#define SCOPE_THREAD 1
+
.text
/*
@@ -388,7 +391,18 @@ lwarx_loop_stop:
bne- lwarx_loop_stop
isync
+ ld r6,PACA_REQ_OPAL_CALL(r13)
+ cmpwi r6,1
+ beq opal_save
bl save_sprs_to_stack
+ PPC_STOP
+ b .
+
+opal_save:
+ ld r3,STOP_SPRS(r13)
+ li r4,SCOPE_CORE
+ ld r5,PACA_REQ_PSSCR(r13)
+ bl opal_cpuidle_save
PPC_STOP /* Does not return (system reset interrupt) */
@@ -435,13 +449,14 @@ _GLOBAL(power9_offline_stop)
* between threads, but in that case KVM has a barrier sync in real
* mode before and after switching between radix and hash.
*/
- li r4,KVM_HWTHREAD_IN_IDLE
- stb r4,HSTATE_HWTHREAD_STATE(r13)
+ li r5,KVM_HWTHREAD_IN_IDLE
+ stb r5,HSTATE_HWTHREAD_STATE(r13)
#endif
/* fall through */
_GLOBAL(power9_idle_stop)
std r3, PACA_REQ_PSSCR(r13)
+ std r4, PACA_REQ_OPAL_CALL(r13)
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
BEGIN_FTR_SECTION
sync
@@ -566,6 +581,8 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
#endif
/* Return SRR1 from power7_nap() */
+ rlwinm r11,r12,47-31,30,31
+ cmpwi cr3,r11,2
blt cr3,pnv_wakeup_noloss
b pnv_wakeup_loss
@@ -576,6 +593,8 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
* cr3 - set to gt if waking up with partial/complete hypervisor state loss
*/
pnv_restore_hyp_resource_arch300:
+ mfspr r5, SPRN_PSSCR
+ std r5, PACA_WAKEUP_PSSCR(r13)
/*
* Workaround for POWER9, if we lost resources, the ERAT
* might have been mixed up and needs flushing. We also need
@@ -831,7 +850,24 @@ subcore_state_restored:
bne cr2,clear_lock
first_thread_in_core:
+ ld r6,PACA_REQ_OPAL_CALL(r13)
+ cmpwi r6,1
+ beq opal_restore_core
+ b kernel_restore_core
+
+opal_restore_core:
+ ld r3,STOP_SPRS(r13)
+ li r4,SCOPE_CORE
+ ld r5,PACA_WAKEUP_PSSCR(r13)
+ mr r6,r19 /*r19 contains SRR1*/
+ bl opal_cpuidle_restore
+ ld r1,PACAR1(r13)
+ xoris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ lwsync
+ stw r15,0(r14)
+ b hypervisor_state_restored
+kernel_restore_core:
/*
* First thread in the core waking up from any state which can cause
* partial or complete hypervisor state loss. It needs to
@@ -885,6 +921,21 @@ clear_lock:
stw r15,0(r14)
common_exit:
+ ld r6,PACA_REQ_OPAL_CALL(r13)
+ cmpwi r6,1
+ beq opal_restore_thread
+ b kernel_restore_thread
+
+opal_restore_thread:
+ ld r3,STOP_SPRS(r13)
+ li r4,SCOPE_THREAD
+ ld r5,PACA_WAKEUP_PSSCR(r13)
+ mr r6,r19 /*r19 contains SRR1*/
+ bl opal_cpuidle_restore
+ ld r1,PACAR1(r13)
+ b hypervisor_state_restored
+
+kernel_restore_thread:
/*
* Common to all threads.
*
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index a6ef9b68e27b..e5d38524aec3 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -147,6 +147,7 @@ static int pnv_save_sprs_for_deep_states(void)
return 0;
}
+#define MAX_STOP_SPRS_COUNT 25
static void pnv_alloc_idle_core_states(void)
{
int i, j;
@@ -186,6 +187,9 @@ static void pnv_alloc_idle_core_states(void)
for (j = 0; j < threads_per_core; j++) {
int cpu = first_cpu + j;
+ paca_ptrs[cpu]->opal_stop_sprs = kmalloc_node(
+ MAX_STOP_SPRS_COUNT * sizeof(u64),
+ GFP_KERNEL, node);
paca_ptrs[cpu]->core_idle_state_ptr = core_idle_state;
paca_ptrs[cpu]->thread_idle_state = PNV_THREAD_RUNNING;
paca_ptrs[cpu]->thread_mask = 1 << j;
@@ -372,7 +376,7 @@ static unsigned long __power9_idle_type(struct pnv_idle_states_t *state)
psscr = mfspr(SPRN_PSSCR);
psscr = (psscr & ~stop_psscr_mask) | stop_psscr_val;
__ppc64_runlatch_off();
- srr1 = power9_idle_stop(psscr, state->opal_supported);
+ srr1 = power9_idle_stop(psscr, state->req_opal_call);
__ppc64_runlatch_on();
fini_irq_for_idle_irqsoff();
@@ -518,7 +522,7 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
psscr = mfspr(SPRN_PSSCR);
psscr = (psscr & ~state->psscr_mask) | state->psscr_val;
- srr1 = power9_offline_stop(psscr, state->opal_supported);
+ srr1 = power9_offline_stop(psscr, state->req_opal_call);
} else if ((idle_states & OPAL_PM_WINKLE_ENABLED) &&
(idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) {
@@ -815,6 +819,7 @@ static int pnv_parse_cpuidle_dt(void)
u32 *temp_u32;
u64 *temp_u64;
const char **temp_string;
+ bool fall_back_to_opal = false;
np = of_find_node_by_path("/ibm,opal/power-mgt");
if (!np) {
@@ -929,21 +934,33 @@ static int pnv_parse_cpuidle_dt(void)
/* Parse each child node with appropriate parser_fn */
for_each_child_of_node(np1, dt_node) {
bool found_known_version = false;
- /* we don't have state falling back to opal*/
- for (i = 0; i < nr_known_versions ; i++) {
- if (of_device_is_compatible(dt_node, known_versions[i].name)) {
- rc = known_versions[i].parser_fn(dt_node);
- if (rc) {
- pr_err("%s could not parse\n",known_versions[i].name);
- continue;
+ int idx = nr_pnv_idle_states;
+ if (!fall_back_to_opal) {
+ /* we don't have state falling back to opal*/
+ for (i = 0; i < nr_known_versions ; i++) {
+ if (of_device_is_compatible(dt_node, known_versions[i].name)) {
+ rc = known_versions[i].parser_fn(dt_node);
+ if (rc) {
+ pr_err("%s could not parse\n",known_versions[i].name);
+ continue;
+ }
+ found_known_version = true;
}
- found_known_version = true;
}
}
-
- if (!found_known_version) {
+ if (!found_known_version || fall_back_to_opal) {
+ if (of_device_is_compatible(dt_node, "opal-support")) {
+ rc = known_versions[0].parser_fn(dt_node);
+ if (rc) {
+ pr_err("%s could not parse\n", "opal-support");
+ continue;
+ }
+ pnv_idle_states[idx].req_opal_call = true;
+ fall_back_to_opal = true;
+ } else {
pr_info("Unsupported state, skipping all further state\n");
goto out;
+ }
}
nr_pnv_idle_states++;
}
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index a8d9b4089c31..b75c37d93efd 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -327,3 +327,5 @@ OPAL_CALL(opal_npu_tl_set, OPAL_NPU_TL_SET);
OPAL_CALL(opal_pci_get_pbcq_tunnel_bar, OPAL_PCI_GET_PBCQ_TUNNEL_BAR);
OPAL_CALL(opal_pci_set_pbcq_tunnel_bar, OPAL_PCI_SET_PBCQ_TUNNEL_BAR);
OPAL_CALL(opal_sensor_read_u64, OPAL_SENSOR_READ_U64);
+OPAL_CALL(opal_cpuidle_save, OPAL_IDLE_SAVE);
+OPAL_CALL(opal_cpuidle_restore, OPAL_IDLE_RESTORE);
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 47166ad2a669..8ae34f37e60a 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2431,14 +2431,14 @@ static void dump_one_paca(int cpu)
DUMP(p, subcore_sibling_mask, "%#-*x");
DUMP(p, thread_sibling_pacas, "%-*px");
DUMP(p, requested_psscr, "%#-*llx");
- DUMP(p, stop_sprs.pid, "%#-*llx");
- DUMP(p, stop_sprs.ldbar, "%#-*llx");
- DUMP(p, stop_sprs.fscr, "%#-*llx");
- DUMP(p, stop_sprs.hfscr, "%#-*llx");
- DUMP(p, stop_sprs.mmcr1, "%#-*llx");
- DUMP(p, stop_sprs.mmcr2, "%#-*llx");
- DUMP(p, stop_sprs.mmcra, "%#-*llx");
DUMP(p, dont_stop.counter, "%#-*x");
+
+ /*
+ * TODO Either kernel or opal has sprs stored. If opal stored it,
+ * we can find a way to make the indices available to kernel through
+ * paca.
+ */
+
#endif
DUMP(p, accounting.utime, "%#-*lx");
--
2.18.0.rc2.85.g1fb9df7
^ permalink raw reply related
* [RFC PATCH 2/3] powernv/cpuidle: Pass pointers instead of values to stop loop
From: Akshay Adiga @ 2018-08-02 4:51 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev; +Cc: npiggin, mpe, benh, ego, huntbag, Akshay Adiga
In-Reply-To: <20180802045132.12432-1-akshay.adiga@linux.vnet.ibm.com>
Passing pointer to the pnv_idle_state instead of psscr value and mask.
This helps us to pass more information to the stop loop. This will help to
figure out the method to enter/exit idle state.
Signed-off-by: Akshay Adiga <akshay.adiga@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/processor.h | 3 +-
arch/powerpc/platforms/powernv/idle.c | 58 ++++++++++++---------------
drivers/cpuidle/cpuidle-powernv.c | 16 +++-----
3 files changed, 32 insertions(+), 45 deletions(-)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 5debe337ea9d..34f572056add 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -515,8 +515,7 @@ extern unsigned long power7_idle_insn(unsigned long type); /* PNV_THREAD_NAP/etc
extern void power7_idle_type(unsigned long type);
extern unsigned long power9_idle_stop(unsigned long psscr_val);
extern unsigned long power9_offline_stop(unsigned long psscr_val);
-extern void power9_idle_type(unsigned long stop_psscr_val,
- unsigned long stop_psscr_mask);
+extern void power9_idle_type(int index);
extern void flush_instruction_cache(void);
extern void hard_reset_now(void);
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 93accece92e3..a6ef9b68e27b 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -43,8 +43,7 @@ int nr_pnv_idle_states;
* The default stop state that will be used by ppc_md.power_save
* function on platforms that support stop instruction.
*/
-static u64 pnv_default_stop_val;
-static u64 pnv_default_stop_mask;
+struct pnv_idle_states_t *pnv_default_state;
static bool default_stop_found;
static int parse_dt_v1(struct device_node *np);
@@ -70,9 +69,7 @@ u64 pnv_first_deep_stop_state = MAX_STOP_STATE;
* psscr value and mask of the deepest stop idle state.
* Used when a cpu is offlined.
*/
-static u64 pnv_deepest_stop_psscr_val;
-static u64 pnv_deepest_stop_psscr_mask;
-static u64 pnv_deepest_stop_flag;
+static struct pnv_idle_states_t *pnv_deepest_state;
static bool deepest_stop_found;
static int pnv_save_sprs_for_deep_states(void)
@@ -92,7 +89,7 @@ static int pnv_save_sprs_for_deep_states(void)
uint64_t hid5_val = mfspr(SPRN_HID5);
uint64_t hmeer_val = mfspr(SPRN_HMEER);
uint64_t msr_val = MSR_IDLE;
- uint64_t psscr_val = pnv_deepest_stop_psscr_val;
+ uint64_t psscr_val = pnv_deepest_state->psscr_val;
for_each_present_cpu(cpu) {
uint64_t pir = get_hard_smp_processor_id(cpu);
@@ -218,18 +215,15 @@ static void pnv_alloc_idle_core_states(void)
pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n");
if (cpu_has_feature(CPU_FTR_ARCH_300) &&
- (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) {
+ (pnv_deepest_state->flags & OPAL_PM_LOSE_FULL_CONTEXT)) {
/*
* Use the default stop state for CPU-Hotplug
* if available.
*/
if (default_stop_found) {
- pnv_deepest_stop_psscr_val =
- pnv_default_stop_val;
- pnv_deepest_stop_psscr_mask =
- pnv_default_stop_mask;
+ pnv_deepest_state = pnv_default_state;
pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n",
- pnv_deepest_stop_psscr_val);
+ pnv_deepest_state->psscr_val);
} else { /* Fallback to snooze loop for CPU-Hotplug */
deepest_stop_found = false;
pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n");
@@ -365,20 +359,20 @@ void power7_idle(void)
power7_idle_type(PNV_THREAD_NAP);
}
-static unsigned long __power9_idle_type(unsigned long stop_psscr_val,
- unsigned long stop_psscr_mask)
+static unsigned long __power9_idle_type(struct pnv_idle_states_t *state)
{
- unsigned long psscr;
+ unsigned long psscr, stop_psscr_mask, stop_psscr_val;
unsigned long srr1;
+ stop_psscr_mask = state->psscr_mask;
+ stop_psscr_val = state->psscr_val;
if (!prep_irq_for_idle_irqsoff())
return 0;
psscr = mfspr(SPRN_PSSCR);
psscr = (psscr & ~stop_psscr_mask) | stop_psscr_val;
-
__ppc64_runlatch_off();
- srr1 = power9_idle_stop(psscr);
+ srr1 = power9_idle_stop(psscr, state->opal_supported);
__ppc64_runlatch_on();
fini_irq_for_idle_irqsoff();
@@ -386,12 +380,11 @@ static unsigned long __power9_idle_type(unsigned long stop_psscr_val,
return srr1;
}
-void power9_idle_type(unsigned long stop_psscr_val,
- unsigned long stop_psscr_mask)
+void power9_idle_type(struct pnv_idle_states_t *state)
{
unsigned long srr1;
+ srr1 = __power9_idle_type(state);
- srr1 = __power9_idle_type(stop_psscr_val, stop_psscr_mask);
irq_set_pending_from_srr1(srr1);
}
@@ -400,7 +393,10 @@ void power9_idle_type(unsigned long stop_psscr_val,
*/
void power9_idle(void)
{
- power9_idle_type(pnv_default_stop_val, pnv_default_stop_mask);
+ unsigned long srr1;
+
+ srr1 = __power9_idle_type(pnv_default_state);
+ irq_set_pending_from_srr1(srr1);
}
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
@@ -500,6 +496,7 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
unsigned long srr1;
u32 idle_states = pnv_get_supported_cpuidle_states();
u64 lpcr_val;
+ struct pnv_idle_states_t *state = pnv_deepest_state;
/*
* We don't want to take decrementer interrupts while we are
@@ -520,9 +517,8 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
unsigned long psscr;
psscr = mfspr(SPRN_PSSCR);
- psscr = (psscr & ~pnv_deepest_stop_psscr_mask) |
- pnv_deepest_stop_psscr_val;
- srr1 = power9_offline_stop(psscr);
+ psscr = (psscr & ~state->psscr_mask) | state->psscr_val;
+ srr1 = power9_offline_stop(psscr, state->opal_supported);
} else if ((idle_states & OPAL_PM_WINKLE_ENABLED) &&
(idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) {
@@ -682,16 +678,13 @@ static int __init pnv_power9_idle_init(void)
*/
if (max_residency_ns < state->residency_ns) {
max_residency_ns = state->residency_ns;
- pnv_deepest_stop_psscr_val = state->psscr_val;
- pnv_deepest_stop_psscr_mask = state->psscr_mask;
- pnv_deepest_stop_flag = state->flags;
+ pnv_deepest_state = state;
deepest_stop_found = true;
}
if (!default_stop_found &&
(state->flags & OPAL_PM_STOP_INST_FAST)) {
- pnv_default_stop_val = state->psscr_val;
- pnv_default_stop_mask = state->psscr_mask;
+ pnv_default_state = state;
default_stop_found = true;
}
}
@@ -701,15 +694,16 @@ static int __init pnv_power9_idle_init(void)
} else {
ppc_md.power_save = power9_idle;
pr_info("cpuidle-powernv: Default stop: psscr = 0x%016llx,mask=0x%016llx\n",
- pnv_default_stop_val, pnv_default_stop_mask);
+ pnv_default_state->psscr_val,
+ pnv_default_state->psscr_mask);
}
if (unlikely(!deepest_stop_found)) {
pr_warn("cpuidle-powernv: No suitable stop state for CPU-Hotplug. Offlined CPUs will busy wait");
} else {
pr_info("cpuidle-powernv: Deepest stop: psscr = 0x%016llx,mask=0x%016llx\n",
- pnv_deepest_stop_psscr_val,
- pnv_deepest_stop_psscr_mask);
+ pnv_deepest_state->psscr_val,
+ pnv_deepest_state->psscr_mask);
}
pr_info("cpuidle-powernv: Requested Level (RL) value of first deep stop = 0x%llx\n",
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index f5579f0369d1..b8cb377b774b 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -35,13 +35,7 @@ static struct cpuidle_driver powernv_idle_driver = {
static int max_idle_state __read_mostly;
static struct cpuidle_state *cpuidle_state_table __read_mostly;
-struct stop_psscr_table {
- u64 val;
- u64 mask;
-};
-
-static struct stop_psscr_table stop_psscr_table[CPUIDLE_STATE_MAX] __read_mostly;
-
+struct pnv_idle_states_t idx_to_state_ptr[CPUIDLE_STATE_MAX] __read_mostly;
static u64 default_snooze_timeout __read_mostly;
static bool snooze_timeout_en __read_mostly;
@@ -143,8 +137,9 @@ static int stop_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
- power9_idle_type(stop_psscr_table[index].val,
- stop_psscr_table[index].mask);
+ struct pnv_idle_states_t state;
+ state = idx_to_state_ptr[index];
+ power9_idle_type(state);
return index;
}
@@ -243,8 +238,6 @@ static inline void add_powernv_state(int index, const char *name,
powernv_states[index].exit_latency = exit_latency;
powernv_states[index].enter = idle_fn;
/* For power8 and below psscr_* will be 0 */
- stop_psscr_table[index].val = psscr_val;
- stop_psscr_table[index].mask = psscr_mask;
}
/*
@@ -371,6 +364,7 @@ static int powernv_add_idle_states(void)
target_residency, exit_latency,
state->psscr_val,
state->psscr_mask);
+ idx_to_state_ptr[nr_idle_states] = state;
}
#endif
else {
--
2.18.0.rc2.85.g1fb9df7
^ permalink raw reply related
* [RFC PATCH 1/3] cpuidle/powernv: Add support for states with ibm, cpuidle-state-v1
From: Akshay Adiga @ 2018-08-02 4:51 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev; +Cc: npiggin, mpe, benh, ego, huntbag, Akshay Adiga
In-Reply-To: <20180802045132.12432-1-akshay.adiga@linux.vnet.ibm.com>
This patch adds support for new device-tree format for idle state
description.
Previously if a older kernel runs on a newer firmware, it may enable
all available states irrespective of its capability of handling it.
New device tree format adds a compatible flag, so that only kernel
which has the capability to handle the version of stop state will enable
it.
Older kernel will still see stop0 and stop0_lite in older format and we
will depricate it after some time.
1) Idea is to bump up the version in firmware if we find a bug or
regression in stop states. A fix will be provided in linux which would
now know about the bumped up version of stop states, where as kernel
without fixes would ignore the states.
2) Slowly deprecate cpuidle /cpuhotplug threshold which is hard-coded
into cpuidle-powernv driver. Instead use compatible strings to indicate
if idle state is suitable for cpuidle and hotplug.
New idle state device tree format :
power-mgt {
...
ibm,enabled-stop-levels = <0xec000000>;
ibm,cpu-idle-state-psscr-mask = <0x0 0x3003ff 0x0 0x3003ff>;
ibm,cpu-idle-state-latencies-ns = <0x3e8 0x7d0>;
ibm,cpu-idle-state-psscr = <0x0 0x330 0x0 0x300330>;
ibm,cpu-idle-state-flags = <0x100000 0x101000>;
ibm,cpu-idle-state-residency-ns = <0x2710 0x4e20>;
ibm,idle-states {
stop4 {
flags = <0x207000>;
compatible = "ibm,state-v1",
"cpuidle",
"opal-supported";
psscr-mask = <0x0 0x3003ff>;
handle = <0x102>;
latency-ns = <0x186a0>;
residency-ns = <0x989680>;
psscr = <0x0 0x300374>;
};
...
stop11 {
...
compatible = "ibm,state-v1",
"cpuoffline",
"opal-supported";
...
};
};
compatible strings :
"cpuidle" : indicates it should be used by cpuidle-driver
"cpuoffline" : indicates it should be used by hotplug driver
"ibm,state-v1" : kernel checks if it knows about this version
"opal-supported" : indicates kernel can fall back to use opal
for stop-transitions
Signed-off-by: Akshay Adiga <akshay.adiga@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/cpuidle.h | 11 ++
arch/powerpc/platforms/powernv/idle.c | 139 +++++++++++++++++++++++++-
drivers/cpuidle/cpuidle-powernv.c | 50 +++++----
3 files changed, 175 insertions(+), 25 deletions(-)
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index 43e5f31fe64d..b965066560cc 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -79,17 +79,28 @@ struct stop_sprs {
u64 mmcra;
};
+enum idle_state_type_t {
+ CPUIDLE_TYPE,
+ CPUOFFLINE_TYPE
+};
+
+
+#define POWERNV_THRESHOLD_LATENCY_NS 200000
+#define PNV_VER_NAME_LEN 32
#define PNV_IDLE_NAME_LEN 16
struct pnv_idle_states_t {
char name[PNV_IDLE_NAME_LEN];
+ char version[PNV_VER_NAME_LEN];
u32 latency_ns;
u32 residency_ns;
u64 psscr_val;
u64 psscr_mask;
u32 flags;
+ enum idle_state_type_t type;
bool valid;
};
+
extern struct pnv_idle_states_t *pnv_idle_states;
extern int nr_pnv_idle_states;
extern u32 pnv_fastsleep_workaround_at_entry[];
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 7cf71b3e03a1..93accece92e3 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -47,6 +47,19 @@ static u64 pnv_default_stop_val;
static u64 pnv_default_stop_mask;
static bool default_stop_found;
+static int parse_dt_v1(struct device_node *np);
+struct stop_version_t {
+ const char name[PNV_VER_NAME_LEN];
+ int (*parser_fn)(struct device_node *np);
+};
+struct stop_version_t known_versions[] = {
+ {
+ .name = "ibm,state-v1",
+ .parser_fn = parse_dt_v1,
+ }
+};
+const int nr_known_versions = 1;
+
/*
* First deep stop state. Used to figure out when to save/restore
* hypervisor context.
@@ -659,8 +672,14 @@ static int __init pnv_power9_idle_init(void)
state->valid = false;
report_invalid_psscr_val(state->psscr_val, err);
continue;
+ } else {
+ state->valid = true;
}
+ /*
+ * We pick state with highest residency. We dont care if
+ * its a cpuidle state or a cpuoffline state.
+ */
if (max_residency_ns < state->residency_ns) {
max_residency_ns = state->residency_ns;
pnv_deepest_stop_psscr_val = state->psscr_val;
@@ -720,6 +739,73 @@ static void __init pnv_probe_idle_states(void)
supported_cpuidle_states |= pnv_idle_states[i].flags;
}
+static int parse_dt_v1(struct device_node *dt_node)
+{
+ const char *temp_str;
+ int rc;
+ int i = nr_pnv_idle_states;
+
+ if (!dt_node) {
+ pr_err("Invalid device_node\n");
+ return -EINVAL;
+ }
+
+ rc = of_property_read_string(dt_node, "name", &temp_str);
+ if (rc) {
+ pr_err("error reading names rc= %d\n", rc);
+ return -EINVAL;
+ } else {
+ strncpy(pnv_idle_states[i].name, temp_str,
+ PNV_IDLE_NAME_LEN);
+ }
+ rc = of_property_read_u32(dt_node, "residency-ns",
+ &pnv_idle_states[i].residency_ns);
+ if (rc) {
+ pr_err("error reading residency rc= %d\n", rc);
+ return -EINVAL;
+ }
+ rc = of_property_read_u32(dt_node, "latency-ns",
+ &pnv_idle_states[i].latency_ns);
+ if (rc) {
+ pr_err("error reading latency rc= %d\n", rc);
+ return -EINVAL;
+ }
+ rc = of_property_read_u32(dt_node, "flags",
+ &pnv_idle_states[i].flags);
+ if (rc) {
+ pr_err("error reading flags rc= %d\n", rc);
+ return -EINVAL;
+ }
+
+ /* We are not expecting power8 device-tree in this format */
+ rc = of_property_read_u64(dt_node, "psscr-mask",
+ &pnv_idle_states[i].psscr_mask);
+ if (rc) {
+ pr_err("error reading psscr-mask rc= %d\n", rc);
+ return -EINVAL;
+ }
+ rc = of_property_read_u64(dt_node, "psscr",
+ &pnv_idle_states[i].psscr_val);
+ if (rc) {
+ pr_err("error reading psscr rc= %d\n", rc);
+ return -EINVAL;
+ }
+
+ /*
+ * TODO : save the version strings in data structure
+ */
+ if (of_device_is_compatible(dt_node, "cpuidle"))
+ pnv_idle_states[i].type = CPUIDLE_TYPE;
+ else if (of_device_is_compatible(dt_node, "cpuoffline"))
+ pnv_idle_states[i].type = CPUOFFLINE_TYPE;
+ else {
+ pr_err("Invalid type skipping %s\n",
+ pnv_idle_states[i].name);
+ return -EINVAL;
+ }
+ return 0;
+
+}
/*
* This function parses device-tree and populates all the information
* into pnv_idle_states structure. It also sets up nr_pnv_idle_states
@@ -728,8 +814,9 @@ static void __init pnv_probe_idle_states(void)
static int pnv_parse_cpuidle_dt(void)
{
- struct device_node *np;
+ struct device_node *np, *np1, *dt_node;
int nr_idle_states, i;
+ int additional_states = 0;
int rc = 0;
u32 *temp_u32;
u64 *temp_u64;
@@ -742,9 +829,14 @@ static int pnv_parse_cpuidle_dt(void)
}
nr_idle_states = of_property_count_u32_elems(np,
"ibm,cpu-idle-state-flags");
-
- pnv_idle_states = kcalloc(nr_idle_states, sizeof(*pnv_idle_states),
- GFP_KERNEL);
+ np1 = of_find_node_by_path("/ibm,opal/power-mgt/ibm,idle-states");
+ if (np1) {
+ for_each_child_of_node(np1, dt_node)
+ additional_states++;
+ }
+ pr_info("states in new format : %d\n", additional_states);
+ pnv_idle_states = kcalloc(nr_idle_states + additional_states,
+ sizeof(*pnv_idle_states), GFP_KERNEL);
temp_u32 = kcalloc(nr_idle_states, sizeof(u32), GFP_KERNEL);
temp_u64 = kcalloc(nr_idle_states, sizeof(u64), GFP_KERNEL);
temp_string = kcalloc(nr_idle_states, sizeof(char *), GFP_KERNEL);
@@ -823,8 +915,45 @@ static int pnv_parse_cpuidle_dt(void)
for (i = 0; i < nr_idle_states; i++)
strncpy(pnv_idle_states[i].name, temp_string[i],
PNV_IDLE_NAME_LEN);
+
+ /* Mark states as CPUIDLE_TYPE /CPUOFFLINE for older version*/
+ for (i = 0; i < nr_idle_states; i++) {
+ if (pnv_idle_states[i].latency_ns > POWERNV_THRESHOLD_LATENCY_NS)
+ pnv_idle_states[i].type = CPUOFFLINE_TYPE;
+ else
+ pnv_idle_states[i].type = CPUIDLE_TYPE;
+ }
+
+ /* Setting up global count of parsed state */
nr_pnv_idle_states = nr_idle_states;
- rc = 0;
+
+ /* Parsing node-based idle states device-tree format */
+ if (!np1) {
+ pr_info("dt does not contain ibm,idle_states");
+ goto out;
+ }
+ /* Parse each child node with appropriate parser_fn */
+ for_each_child_of_node(np1, dt_node) {
+ bool found_known_version = false;
+ /* we don't have state falling back to opal*/
+ for (i = 0; i < nr_known_versions ; i++) {
+ if (of_device_is_compatible(dt_node, known_versions[i].name)) {
+ rc = known_versions[i].parser_fn(dt_node);
+ if (rc) {
+ pr_err("%s could not parse\n",known_versions[i].name);
+ continue;
+ }
+ found_known_version = true;
+ }
+ }
+
+ if (!found_known_version) {
+ pr_info("Unsupported state, skipping all further state\n");
+ goto out;
+ }
+ nr_pnv_idle_states++;
+ }
+
out:
kfree(temp_u32);
kfree(temp_u64);
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 47ac37d6c443..f5579f0369d1 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -26,7 +26,6 @@
* Expose only those Hardware idle states via the cpuidle framework
* that have latency value below POWERNV_THRESHOLD_LATENCY_NS.
*/
-#define POWERNV_THRESHOLD_LATENCY_NS 200000
static struct cpuidle_driver powernv_idle_driver = {
.name = "powernv_idle",
@@ -266,7 +265,7 @@ extern u32 pnv_get_supported_cpuidle_states(void);
static int powernv_add_idle_states(void)
{
int nr_idle_states = 1; /* Snooze */
- int dt_idle_states;
+ int dt_idle_states = 0;
u32 has_stop_states = 0;
int i;
u32 supported_flags = pnv_get_supported_cpuidle_states();
@@ -277,16 +276,19 @@ static int powernv_add_idle_states(void)
pr_warn("cpuidle-powernv : Only Snooze is available\n");
goto out;
}
-
- /* TODO: Count only states which are eligible for cpuidle */
- dt_idle_states = nr_pnv_idle_states;
-
+ /* Count only cpuidle states*/
+ for (i = 0; i < nr_pnv_idle_states; i++) {
+ if (pnv_idle_states[i].type == CPUIDLE_TYPE)
+ dt_idle_states++;
+ }
+ pr_info("idle states in dt = %d , states with idle flag = %d",
+ nr_pnv_idle_states, dt_idle_states);
/*
* Since snooze is used as first idle state, max idle states allowed is
* CPUIDLE_STATE_MAX -1
*/
- if (nr_pnv_idle_states > CPUIDLE_STATE_MAX - 1) {
- pr_warn("cpuidle-powernv: discovered idle states more than allowed");
+ if (dt_idle_states > CPUIDLE_STATE_MAX - 1) {
+ pr_warn("cpuidle-powernv: discovered idle states > allowed");
dt_idle_states = CPUIDLE_STATE_MAX - 1;
}
@@ -297,24 +299,28 @@ static int powernv_add_idle_states(void)
has_stop_states = (pnv_idle_states[0].flags &
(OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP));
- for (i = 0; i < dt_idle_states; i++) {
+ for (i = 0; i < nr_pnv_idle_states; i++) {
unsigned int exit_latency, target_residency;
bool stops_timebase = false;
struct pnv_idle_states_t *state = &pnv_idle_states[i];
-
/*
- * Skip the platform idle state whose flag isn't in
- * the supported_cpuidle_states flag mask.
+ * For older version of device-tree the state will be
+ * set as CPUIDLE_TYPE if the latency exceeds
+ * POWERNV_THRESHOLD_LATENCY_NS
*/
- if ((state->flags & supported_flags) != state->flags)
+ if (state->type != CPUIDLE_TYPE) {
+ pr_info("State %d is not idletype, it of %d type\n", i,
+ state->type);
continue;
+ }
/*
- * If an idle state has exit latency beyond
- * POWERNV_THRESHOLD_LATENCY_NS then don't use it
- * in cpu-idle.
+ * Skip the platform idle state whose flag isn't in
+ * the supported_cpuidle_states flag mask.
*/
- if (state->latency_ns > POWERNV_THRESHOLD_LATENCY_NS)
+ if ((state->flags & supported_flags) != state->flags) {
+ pr_warn("State %d is not have supported flag\n", i);
continue;
+ }
/*
* Firmware passes residency and latency values in ns.
* cpuidle expects it in us.
@@ -322,8 +328,10 @@ static int powernv_add_idle_states(void)
exit_latency = DIV_ROUND_UP(state->latency_ns, 1000);
target_residency = DIV_ROUND_UP(state->residency_ns, 1000);
- if (has_stop_states && !(state->valid))
- continue;
+ if (has_stop_states && !(state->valid)) {
+ pr_warn("State %d is invalid\n", i);
+ continue;
+ }
if (state->flags & OPAL_PM_TIMEBASE_STOP)
stops_timebase = true;
@@ -365,8 +373,10 @@ static int powernv_add_idle_states(void)
state->psscr_mask);
}
#endif
- else
+ else {
+ pr_warn("cpuidle-powernv : could not add state\n");
continue;
+ }
nr_idle_states++;
}
out:
--
2.18.0.rc2.85.g1fb9df7
^ permalink raw reply related
* [RFC PATCH 0/3] New device-tree format and Opal based idle save-restore
From: Akshay Adiga @ 2018-08-02 4:51 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev; +Cc: npiggin, mpe, benh, ego, huntbag, Akshay Adiga
Previously if a older kernel runs on a newer firmware, it may enable
all available states irrespective of its capability of handling it.
New device tree format adds a compatible flag, so that only kernel
which has the capability to handle the version of stop state will enable
it.
Older kernel will still see stop0 and stop0_lite in older format and we
will depricate it after some time.
1) Idea is to bump up the version string in firmware if we find a bug or
regression in stop states. A fix will be provided in linux which would
now know about the bumped up version of stop states, where as kernel
without fixes would ignore the states.
2) Slowly deprecate cpuidle/cpuhotplug threshold which is hard-coded
into cpuidle-powernv driver. Instead use compatible strings to indicate
if idle state is suitable for cpuidle and hotplug.
New idle state device tree format :
power-mgt {
...
ibm,enabled-stop-levels = <0xec000000>;
ibm,cpu-idle-state-psscr-mask = <0x0 0x3003ff 0x0 0x3003ff>;
ibm,cpu-idle-state-latencies-ns = <0x3e8 0x7d0>;
ibm,cpu-idle-state-psscr = <0x0 0x330 0x0 0x300330>;
ibm,cpu-idle-state-flags = <0x100000 0x101000>;
ibm,cpu-idle-state-residency-ns = <0x2710 0x4e20>;
ibm,idle-states {
stop4 {
flags = <0x207000>;
compatible = "ibm,state-v1",
"cpuidle",
"opal-supported";
psscr-mask = <0x0 0x3003ff>;
handle = <0x102>;
latency-ns = <0x186a0>;
residency-ns = <0x989680>;
psscr = <0x0 0x300374>;
};
...
stop11 {
...
compatible = "ibm,state-v1",
"cpuoffline",
"opal-supported";
...
};
};
Skiboot patch-set for device-tree is posted here :
https://patchwork.ozlabs.org/project/skiboot/list/?series=58934
High-level parsing algorithm :
Say Known version string = "ibm,state-v1"
for each stop state node in device tree:
if (compatible has known version string)
kernel takes care of stop-transitions
else if (compatible has "opal-supported")
OPAL takes care of stop-transitions
else
Skip All deeper states
When a state does not have both version support and opal support,
Its possible to exit from a shallower state. Hence skipping all
deeper states.
How does it work ?
-------------------
Consider a case that stop4 has a bug. We take the following steps to
mitigate the problem.
1) Change compatible string for stop4 in OPAL to "ibm-state-v2" and
remove "opal-supported". ship the new firmware.
The kernel ignores stop4 and all deeper states. But we will still have
shallower states. Prevents from completely disabling stop states.
2) Implement workaround in OPAL and add "opal-supported". Ship new firmware
The kernel uses opal for stop-transtion , which has workaround implemented.
We get stop4 and deeper states working without kernel changes and backports.
(and considerably less time)
3) Implement workaround in kernel and add "ibm-state-v2" as known versions
The kernel will now be able to handle stop4 and deeper states.
Also includes Abhishek's RFC which was posted there :
https://patchwork.ozlabs.org/patch/947568/
This patch-set is on top of mpe-next
Abhishek Goel (1):
cpuidle/powernv: Conditionally save-restore sprs using opal
Akshay Adiga (2):
cpuidle/powernv: Add support for states with ibm,cpuidle-state-v1
powernv/cpuidle: Pass pointers instead of values to stop loop
arch/powerpc/include/asm/cpuidle.h | 12 +
arch/powerpc/include/asm/opal-api.h | 4 +-
arch/powerpc/include/asm/opal.h | 3 +
arch/powerpc/include/asm/paca.h | 5 +-
arch/powerpc/include/asm/processor.h | 9 +-
arch/powerpc/kernel/asm-offsets.c | 3 +
arch/powerpc/kernel/idle_book3s.S | 55 ++++-
arch/powerpc/platforms/powernv/idle.c | 214 +++++++++++++++---
.../powerpc/platforms/powernv/opal-wrappers.S | 2 +
arch/powerpc/xmon/xmon.c | 14 +-
drivers/cpuidle/cpuidle-powernv.c | 66 +++---
11 files changed, 304 insertions(+), 83 deletions(-)
--
2.18.0.rc2.85.g1fb9df7
^ permalink raw reply
* Re: linux-next: manual merge of the powerpc tree with the m68k tree
From: Stephen Rothwell @ 2018-08-01 23:41 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, PowerPC,
Geert Uytterhoeven
Cc: Linux-Next Mailing List, Linux Kernel Mailing List, Arnd Bergmann,
Finn Thain
In-Reply-To: <20180802092708.10e1a71d@canb.auug.org.au>
[-- Attachment #1: Type: text/plain, Size: 1420 bytes --]
Hi all,
[forgot the conflict resolution ...]
On Thu, 2 Aug 2018 09:27:20 +1000 Stephen Rothwell <sfr@canb.auug.org.au> wrote:
>
> Today's linux-next merge of the powerpc tree got a conflict in:
>
> arch/m68k/mac/misc.c
>
> between commit:
>
> 5b9bfb8ec467 ("m68k: mac: Use time64_t in RTC handling")
>
> from the m68k tree and commit:
>
> ebd722275f9c ("macintosh/via-pmu: Replace via-pmu68k driver with via-pmu driver")
>
> from the powerpc tree.
>
> I fixed it up (see below) and can carry the fix as necessary. This
> is now fixed as far as linux-next is concerned, but any non trivial
> conflicts should be mentioned to your upstream maintainer when your tree
> is submitted for merging. You may also want to consider cooperating
> with the maintainer of the conflicting tree to minimise any particularly
> complex conflicts.
--
Cheers,
Stephen Rothwell
diff --cc arch/m68k/mac/misc.c
index 19e9d8eef1f2,28090a44fa09..3534aa6a4dc2
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@@ -90,11 -85,11 +90,11 @@@ static void cuda_write_pram(int offset
}
#endif /* CONFIG_ADB_CUDA */
- #ifdef CONFIG_ADB_PMU68K
+ #ifdef CONFIG_ADB_PMU
-static long pmu_read_time(void)
+static time64_t pmu_read_time(void)
{
struct adb_request req;
- long time;
+ time64_t time;
if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0)
return 0;
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* linux-next: manual merge of the powerpc tree with the m68k tree
From: Stephen Rothwell @ 2018-08-01 23:27 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, PowerPC,
Geert Uytterhoeven
Cc: Linux-Next Mailing List, Linux Kernel Mailing List, Arnd Bergmann,
Finn Thain
[-- Attachment #1: Type: text/plain, Size: 745 bytes --]
Hi all,
Today's linux-next merge of the powerpc tree got a conflict in:
arch/m68k/mac/misc.c
between commit:
5b9bfb8ec467 ("m68k: mac: Use time64_t in RTC handling")
from the m68k tree and commit:
ebd722275f9c ("macintosh/via-pmu: Replace via-pmu68k driver with via-pmu driver")
from the powerpc tree.
I fixed it up (see below) and can carry the fix as necessary. This
is now fixed as far as linux-next is concerned, but any non trivial
conflicts should be mentioned to your upstream maintainer when your tree
is submitted for merging. You may also want to consider cooperating
with the maintainer of the conflicting tree to minimise any particularly
complex conflicts.
--
Cheers,
Stephen Rothwell
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* Re: [RFC 0/4] Virtio uses DMA API for all devices
From: Michael S. Tsirkin @ 2018-08-01 22:41 UTC (permalink / raw)
To: Will Deacon
Cc: Christoph Hellwig, Benjamin Herrenschmidt, Anshuman Khandual,
virtualization, linux-kernel, linuxppc-dev, aik, robh, joe,
elfring, david, jasowang, mpe, linuxram, haren, paulus, srikar,
robin.murphy, jean-philippe.brucker, marc.zyngier
In-Reply-To: <20180801090535.GB14438@arm.com>
On Wed, Aug 01, 2018 at 10:05:35AM +0100, Will Deacon wrote:
> Hi Christoph,
>
> On Wed, Aug 01, 2018 at 01:36:39AM -0700, Christoph Hellwig wrote:
> > On Wed, Aug 01, 2018 at 09:16:38AM +0100, Will Deacon wrote:
> > > On arm/arm64, the problem we have is that legacy virtio devices on the MMIO
> > > transport (so definitely not PCI) have historically been advertised by qemu
> > > as not being cache coherent, but because the virtio core has bypassed DMA
> > > ops then everything has happened to work. If we blindly enable the arch DMA
> > > ops,
> >
> > No one is suggesting that as far as I can tell.
>
> Apologies: it's me that wants the DMA ops enabled to handle legacy devices
> behind an IOMMU, but see below.
>
> > > we'll plumb in the non-coherent ops and start getting data corruption,
> > > so we do need a way to quirk virtio as being "always coherent" if we want to
> > > use the DMA ops (which we do, because our emulation platforms have an IOMMU
> > > for all virtio devices).
> >
> > From all that I've gather so far: no you do not want that. We really
> > need to figure out virtio "dma" interacts with the host / device.
> >
> > If you look at the current iommu spec it does talk of physical address
> > with a little careveout for VIRTIO_F_IOMMU_PLATFORM.
>
> That's true, although that doesn't exist in the legacy virtio spec, and we
> have an existing emulation platform which puts legacy virtio devices behind
> an IOMMU. Currently, Linux is unable to boot on this platform unless the
> IOMMU is configured as bypass. If we can use the coherent IOMMU DMA ops,
> then it works perfectly.
>
> > So between that and our discussion in this thread and its previous
> > iterations I think we need to stick to the current always physical,
> > bypass system dma ops mode of virtio operation as the default.
>
> As above -- that means we hang during boot because we get stuck trying to
> bring up a virtio-block device whose DMA is aborted by the IOMMU. The easy
> answer is "just upgrade to latest virtio and advertise the presence of the
> IOMMU". I'm pushing for that in future platforms, but it seems a shame not
> to support the current platform, especially given that other systems do have
> hacks in mainline to get virtio working.
>
> > We just need to figure out how to deal with devices that deviate
> > from the default. One things is that VIRTIO_F_IOMMU_PLATFORM really
> > should become VIRTIO_F_PLATFORM_DMA to cover the cases of non-iommu
> > dma tweaks (offsets, cache flushing), which seems well in spirit of
> > the original design. The other issue is VIRTIO_F_IO_BARRIER
> > which is very vaguely defined, and which needs a better definition.
> > And last but not least we'll need some text explaining the challenges
> > of hardware devices - I think VIRTIO_F_PLATFORM_DMA + VIRTIO_F_IO_BARRIER
> > is what would basically cover them, but a good description including
> > an explanation of why these matter.
>
> I agree that this makes sense for future revisions of virtio (or perhaps
> it can just be a clarification to virtio 1.0), but we're still left in the
> dark with legacy devices and it would be nice to have them work on the
> systems which currently exist, even if it's a legacy-only hack in the arch
> code.
>
> Will
Myself I'm sympathetic to this use-case and I see more uses to this
than just legacy support. But more work is required IMHO.
Will post tomorrow though - it's late here ...
--
MST
^ permalink raw reply
* Re: [RFC 0/4] Virtio uses DMA API for all devices
From: Michael S. Tsirkin @ 2018-08-01 22:35 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Will Deacon, Benjamin Herrenschmidt, Anshuman Khandual,
virtualization, linux-kernel, linuxppc-dev, aik, robh, joe,
elfring, david, jasowang, mpe, linuxram, haren, paulus, srikar,
robin.murphy, jean-philippe.brucker, marc.zyngier
In-Reply-To: <20180801083639.GF26378@infradead.org>
On Wed, Aug 01, 2018 at 01:36:39AM -0700, Christoph Hellwig wrote:
> On Wed, Aug 01, 2018 at 09:16:38AM +0100, Will Deacon wrote:
> > On arm/arm64, the problem we have is that legacy virtio devices on the MMIO
> > transport (so definitely not PCI) have historically been advertised by qemu
> > as not being cache coherent, but because the virtio core has bypassed DMA
> > ops then everything has happened to work. If we blindly enable the arch DMA
> > ops,
>
> No one is suggesting that as far as I can tell.
>
> > we'll plumb in the non-coherent ops and start getting data corruption,
> > so we do need a way to quirk virtio as being "always coherent" if we want to
> > use the DMA ops (which we do, because our emulation platforms have an IOMMU
> > for all virtio devices).
>
> >From all that I've gather so far: no you do not want that. We really
> need to figure out virtio "dma" interacts with the host / device.
>
> If you look at the current iommu spec it does talk of physical address
> with a little careveout for VIRTIO_F_IOMMU_PLATFORM.
>
> So between that and our discussion in this thread and its previous
> iterations I think we need to stick to the current always physical,
> bypass system dma ops mode of virtio operation as the default.
>
> We just need to figure out how to deal with devices that deviate
> from the default. One things is that VIRTIO_F_IOMMU_PLATFORM really
> should become VIRTIO_F_PLATFORM_DMA to cover the cases of non-iommu
> dma tweaks (offsets, cache flushing), which seems well in spirit of
> the original design.
Well I wouldn't say that. VIRTIO_F_IOMMU_PLATFORM is for guest
programmable protection which is designed for things like userspace
drivers but still very much which a CPU doing the accesses. I think
VIRTIO_F_IO_BARRIER needs to be extended to VIRTIO_F_PLATFORM_DMA.
> The other issue is VIRTIO_F_IO_BARRIER
> which is very vaguely defined, and which needs a better definition.
> And last but not least we'll need some text explaining the challenges
> of hardware devices - I think VIRTIO_F_PLATFORM_DMA + VIRTIO_F_IO_BARRIER
> is what would basically cover them, but a good description including
> an explanation of why these matter.
I think VIRTIO_F_IOMMU_PLATFORM + VIRTIO_F_PLATFORM_DMA but yea.
--
MST
^ permalink raw reply
* Re: [RFC 0/4] Virtio uses DMA API for all devices
From: Michael S. Tsirkin @ 2018-08-01 21:56 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: Christoph Hellwig, Will Deacon, Anshuman Khandual, virtualization,
linux-kernel, linuxppc-dev, aik, robh, joe, elfring, david,
jasowang, mpe, linuxram, haren, paulus, srikar, robin.murphy,
jean-philippe.brucker, marc.zyngier
In-Reply-To: <3d6e81511571260de1c8047aaffa8ac4df093d2e.camel@kernel.crashing.org>
On Tue, Jul 31, 2018 at 03:36:22PM -0500, Benjamin Herrenschmidt wrote:
> On Tue, 2018-07-31 at 10:30 -0700, Christoph Hellwig wrote:
> > > However the question people raise is that DMA API is already full of
> > > arch-specific tricks the likes of which are outlined in your post linked
> > > above. How is this one much worse?
> >
> > None of these warts is visible to the driver, they are all handled in
> > the architecture (possibly on a per-bus basis).
> >
> > So for virtio we really need to decide if it has one set of behavior
> > as specified in the virtio spec, or if it behaves exactly as if it
> > was on a PCI bus, or in fact probably both as you lined up. But no
> > magic arch specific behavior inbetween.
>
> The only arch specific behaviour is needed in the case where it doesn't
> behave like PCI. In this case, the PCI DMA ops are not suitable, but in
> our secure VMs, we still need to make it use swiotlb in order to bounce
> through non-secure pages.
>
> It would be nice if "real PCI" was the default
I think you are mixing "real PCI" which isn't coded up yet and IOMMU
bypass which is. IOMMU bypass will maybe with time become unnecessary
since it seems that one can just program an IOMMU in a bypass mode
instead.
It's hard to blame you since right now if you disable IOMMU bypass
you get a real PCI mode. But they are distinct and to allow people
to enable IOMMU by default we will need to teach someone
(virtio or DMA API) about this mode that does follow
translation and protection rules in the IOMMU but runs
on a CPU and so does not need cache flushes and whatnot.
OTOH real PCI mode as opposed to default hypervisor mode does not perform as
well when what you actually have is a hypervisor.
So we'll likely have a mix of these two modes for a while.
> but it's not, VMs are
> created in "legacy" mode all the times and we don't know at VM creation
> time whether it will become a secure VM or not. The way our secure VMs
> work is that they start as a normal VM, load a secure "payload" and
> call the Ultravisor to "become" secure.
>
> So we're in a bit of a bind here. We need that one-liner optional arch
> hook to make virtio use swiotlb in that "IOMMU bypass" case.
>
> Ben.
And just to make sure I understand, on your platform DMA APIs do include
some of the cache flushing tricks and this is why you don't want to
declare iommu support in the hypervisor?
--
MST
^ permalink raw reply
* [PATCH 19/21] perf tools: Allow overriding MAX_NR_CPUS at compile time
From: Arnaldo Carvalho de Melo @ 2018-08-01 21:36 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Christophe Leroy,
Alexander Shishkin, Peter Zijlstra, linuxppc-dev,
Arnaldo Carvalho de Melo
In-Reply-To: <20180801213648.4814-1-acme@kernel.org>
From: Christophe Leroy <christophe.leroy@c-s.fr>
After update of kernel, the perf tool doesn't run anymore on my 32MB RAM
powerpc board, but still runs on a 128MB RAM board:
~# strace perf
execve("/usr/sbin/perf", ["perf"], [/* 12 vars */]) = -1 ENOMEM (Cannot allocate memory)
--- SIGSEGV {si_signo=SIGSEGV, si_code=SI_KERNEL, si_addr=0} ---
+++ killed by SIGSEGV +++
Segmentation fault
objdump -x shows that .bss section has a huge size of 24Mbytes:
27 .bss 016baca8 101cebb8 101cebb8 001cd988 2**3
With especially the following objects having quite big size:
10205f80 l O .bss 00140000 runtime_cycles_stats
10345f80 l O .bss 00140000 runtime_stalled_cycles_front_stats
10485f80 l O .bss 00140000 runtime_stalled_cycles_back_stats
105c5f80 l O .bss 00140000 runtime_branches_stats
10705f80 l O .bss 00140000 runtime_cacherefs_stats
10845f80 l O .bss 00140000 runtime_l1_dcache_stats
10985f80 l O .bss 00140000 runtime_l1_icache_stats
10ac5f80 l O .bss 00140000 runtime_ll_cache_stats
10c05f80 l O .bss 00140000 runtime_itlb_cache_stats
10d45f80 l O .bss 00140000 runtime_dtlb_cache_stats
10e85f80 l O .bss 00140000 runtime_cycles_in_tx_stats
10fc5f80 l O .bss 00140000 runtime_transaction_stats
11105f80 l O .bss 00140000 runtime_elision_stats
11245f80 l O .bss 00140000 runtime_topdown_total_slots
11385f80 l O .bss 00140000 runtime_topdown_slots_retired
114c5f80 l O .bss 00140000 runtime_topdown_slots_issued
11605f80 l O .bss 00140000 runtime_topdown_fetch_bubbles
11745f80 l O .bss 00140000 runtime_topdown_recovery_bubbles
This is due to commit 4d255766d28b1 ("perf: Bump max number of cpus
to 1024"), because many tables are sized with MAX_NR_CPUS
This patch gives the opportunity to redefine MAX_NR_CPUS via
$ make EXTRA_CFLAGS=-DMAX_NR_CPUS=1
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/20170922112043.8349468C57@po15668-vm-win7.idsi0.si.c-s.fr
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/perf.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index d215714f48df..21bf7f5a3cf5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -25,7 +25,9 @@ static inline unsigned long long rdclock(void)
return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
}
+#ifndef MAX_NR_CPUS
#define MAX_NR_CPUS 1024
+#endif
extern const char *input_name;
extern bool perf_host, perf_guest;
--
2.14.4
^ permalink raw reply related
* [GIT PULL 00/21] perf/core improvements and fixes
From: Arnaldo Carvalho de Melo @ 2018-08-01 21:36 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users,
Arnaldo Carvalho de Melo, Adrian Hunter, Alexander Shishkin,
Alexey Budankov, Andi Kleen, Christophe Leroy, David Ahern,
Don Zickus, Ganapatrao Kulkarni, Heiko Carstens,
Hendrik Brueckner, Jan Glauber, Jayachandran C, Jiri Olsa,
Joe Mario, Kan Liang, Kim Phillips, Leo Yan, linux-arm-kernel,
linuxppc-dev, Mark Rutland, Martin Schwidefsky, Mathieu Poirier,
Michael Petlan, Mike Leach, Namhyung Kim, Naveen N . Rao,
Peter Zijlstra, Ravi Bangoria, Robert Richter, Robert Walker,
rodia, Sandipan Das, Stefan Liebler, Sunil K Pandey,
Thomas Richter, Vadim Lomovtsev, Wang Nan, Will Deacon,
Arnaldo Carvalho de Melo
Hi Ingo,
Please consider pulling, contains a recently merged
tip/perf/urgent,
- Arnaldo
Test results at the end of this message, as usual.
The following changes since commit c2586cfbb905939b79b49a9121fb0a59a5668fd6:
Merge remote-tracking branch 'tip/perf/urgent' into perf/core (2018-07-31 09:55:45 -0300)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo-4.19-20180801
for you to fetch changes up to b912885ab75c7c8aa841c615108afd755d0b97f8:
perf trace: Do not require --no-syscalls to suppress strace like output (2018-08-01 16:20:28 -0300)
----------------------------------------------------------------
perf/core improvements and fixes:
perf trace: (Arnaldo Carvalho de Melo)
- Do not require --no-syscalls to suppress strace like output, i.e.
# perf trace -e sched:*switch
will show just sched:sched_switch events, not strace-like formatted
syscall events, use --syscalls to get the previous behaviour.
If instead:
# perf trace
is used, i.e. no events specified, then --syscalls is implied and
system wide strace like formatting will be applied to all syscalls.
The behaviour when just a syscall subset is used with '-e' is unchanged:
# perf trace -e *sleep,sched:*switch
will work as before: just the 'nanosleep' syscall will be strace-like
formatted plus the sched:sched_switch tracepoint event, system wide.
- Allow string table generators to use a default header dir, allowing
use of them without parameters to see the table it generates on
stdout, e.g.:
$ tools/perf/trace/beauty/kvm_ioctl.sh
static const char *kvm_ioctl_cmds[] = {
[0x00] = "GET_API_VERSION",
[0x01] = "CREATE_VM",
[0x02] = "GET_MSR_INDEX_LIST",
[0x03] = "CHECK_EXTENSION",
<BIG SNIP>
[0xe0] = "CREATE_DEVICE",
[0xe1] = "SET_DEVICE_ATTR",
[0xe2] = "GET_DEVICE_ATTR",
[0xe3] = "HAS_DEVICE_ATTR",
};
$
See 'ls tools/perf/trace/beauty/*.sh' to see the available string
table generators.
- Add a generator for IPPROTO_ socket's protocol constants.
perf record: (Kan Liang)
- Fix error out while applying initial delay and using LBR, due to
the use of a PERF_TYPE_SOFTWARE/PERF_COUNT_SW_DUMMY event to track
PERF_RECORD_MMAP events while waiting for the initial delay. Such
events fail when configured asking PERF_SAMPLE_BRANCH_STACK in
perf_event_attr.sample_type.
perf c2c: (Jiri Olsa)
- Fix report crash for empty browser, when processing a perf.data file
without events of interest, either because not asked for in
'perf record' or because the workload didn't triggered such events.
perf list: (Michael Petlan)
- Align metric group description format with PMU event description.
perf tests: (Sandipan Das)
- Fix indexing when invoking subtests, which caused BPF tests to
get results for the next test in the list, with the last one
reporting a failure.
eBPF:
- Fix installation directory for header files included from eBPF proggies,
avoiding clashing with relative paths used to build other software projects
such as glibc. (Thomas Richter)
- Show better message when failing to load an object. (Arnaldo Carvalho de Melo)
General: (Christophe Leroy)
- Allow overriding MAX_NR_CPUS at compile time, to make the tooling
usable in systems with less memory, in time this has to be changed
to properly allocate based on _NPROCESSORS_ONLN.
Architecture specific:
- Update arm64's ThunderX2 implementation defined pmu core events (Ganapatrao Kulkarni)
- Fix complex event name parsing in 'perf test' for PowerPC, where the 'umask' event
modifier isn't present. (Sandipan Das)
CoreSight ARM hardware tracing: (Leo Yan)
- Fix start tracing packet handling.
- Support dummy address value for CS_ETM_TRACE_ON packet.
- Generate branch sample when receiving a CS_ETM_TRACE_ON packet.
- Generate branch sample for CS_ETM_TRACE_ON packet.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
----------------------------------------------------------------
Arnaldo Carvalho de Melo (9):
perf trace beauty: Default header_dir to cwd to work without parms
tools include uapi: Grab a copy of linux/in.h
perf beauty: Add a generator for IPPROTO_ socket's protocol constants
perf trace beauty: Do not print NULL strarray entries
perf trace beauty: Add beautifiers for 'socket''s 'protocol' arg
perf trace: Beautify the AF_INET & AF_INET6 'socket' syscall 'protocol' args
perf bpf: Show better message when failing to load an object
perf bpf: Include uapi/linux/bpf.h from the 'perf trace' script's bpf.h
perf trace: Do not require --no-syscalls to suppress strace like output
Christophe Leroy (1):
perf tools: Allow overriding MAX_NR_CPUS at compile time
Ganapatrao Kulkarni (1):
perf vendor events arm64: Update ThunderX2 implementation defined pmu core events
Jiri Olsa (1):
perf c2c report: Fix crash for empty browser
Kan Liang (1):
perf evlist: Fix error out while applying initial delay and LBR
Leo Yan (4):
perf cs-etm: Fix start tracing packet handling
perf cs-etm: Support dummy address value for CS_ETM_TRACE_ON packet
perf cs-etm: Generate branch sample when receiving a CS_ETM_TRACE_ON packet
perf cs-etm: Generate branch sample for CS_ETM_TRACE_ON packet
Michael Petlan (1):
perf list: Unify metric group description format with PMU event description
Sandipan Das (2):
perf tests: Fix complex event name parsing
perf tests: Fix indexing when invoking subtests
Thomas Richter (1):
perf build: Fix installation directory for eBPF
tools/include/uapi/linux/in.h | 301 +++++++++++++++++++++
tools/perf/Makefile.config | 4 +-
tools/perf/Makefile.perf | 10 +
tools/perf/builtin-c2c.c | 3 +
tools/perf/builtin-trace.c | 19 +-
tools/perf/check-headers.sh | 1 +
tools/perf/include/bpf/bpf.h | 3 +
tools/perf/perf.h | 2 +
.../arch/arm64/cavium/thunderx2/core-imp-def.json | 87 +++++-
tools/perf/tests/builtin-test.c | 4 +-
tools/perf/tests/parse-events.c | 2 +-
tools/perf/trace/beauty/Build | 1 +
tools/perf/trace/beauty/beauty.h | 3 +
tools/perf/trace/beauty/drm_ioctl.sh | 9 +-
tools/perf/trace/beauty/kcmp_type.sh | 2 +-
tools/perf/trace/beauty/kvm_ioctl.sh | 4 +-
tools/perf/trace/beauty/madvise_behavior.sh | 2 +-
tools/perf/trace/beauty/perf_ioctl.sh | 2 +-
.../perf/trace/beauty/pkey_alloc_access_rights.sh | 2 +-
tools/perf/trace/beauty/sndrv_ctl_ioctl.sh | 4 +-
tools/perf/trace/beauty/sndrv_pcm_ioctl.sh | 4 +-
tools/perf/trace/beauty/socket.c | 28 ++
tools/perf/trace/beauty/socket_ipproto.sh | 11 +
tools/perf/trace/beauty/vhost_virtio_ioctl.sh | 6 +-
tools/perf/util/bpf-loader.c | 4 +-
tools/perf/util/cs-etm-decoder/cs-etm-decoder.h | 1 +
tools/perf/util/cs-etm.c | 68 ++++-
tools/perf/util/evsel.c | 14 +
tools/perf/util/metricgroup.c | 4 +-
29 files changed, 556 insertions(+), 49 deletions(-)
create mode 100644 tools/include/uapi/linux/in.h
create mode 100644 tools/perf/trace/beauty/socket.c
create mode 100755 tools/perf/trace/beauty/socket_ipproto.sh
Test results:
The first ones are container (docker) based builds of tools/perf with
and without libelf support. Where clang is available, it is also used
to build perf with/without libelf, and building with LIBCLANGLLVM=1
(built-in clang) with gcc and clang when clang and its devel libraries
are installed.
The objtool and samples/bpf/ builds are disabled now that I'm switching from
using the sources in a local volume to fetching them from a http server to
build it inside the container, to make it easier to build in a container cluster.
Those will come back later.
Several are cross builds, the ones with -x-ARCH and the android one, and those
may not have all the features built, due to lack of multi-arch devel packages,
available and being used so far on just a few, like
debian:experimental-x-{arm64,mipsel}.
The 'perf test' one will perform a variety of tests exercising
tools/perf/util/, tools/lib/{bpf,traceevent,etc}, as well as run perf commands
with a variety of command line event specifications to then intercept the
sys_perf_event syscall to check that the perf_event_attr fields are set up as
expected, among a variety of other unit tests.
Then there is the 'make -C tools/perf build-test' ones, that build tools/perf/
with a variety of feature sets, exercising the build with an incomplete set of
features as well as with a complete one. It is planned to have it run on each
of the containers mentioned above, using some container orchestration
infrastructure. Get in contact if interested in helping having this in place.
# dm
1 alpine:3.4 : Ok gcc (Alpine 5.3.0) 5.3.0
2 alpine:3.5 : Ok gcc (Alpine 6.2.1) 6.2.1 20160822
3 alpine:3.6 : Ok gcc (Alpine 6.3.0) 6.3.0
4 alpine:3.7 : Ok gcc (Alpine 6.4.0) 6.4.0
5 alpine:edge : Ok gcc (Alpine 6.4.0) 6.4.0
6 amazonlinux:1 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28)
7 amazonlinux:2 : Ok gcc (GCC) 7.3.1 20180303 (Red Hat 7.3.1-5)
8 android-ndk:r12b-arm : Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease)
9 android-ndk:r15c-arm : Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease)
10 centos:5 : Ok gcc (GCC) 4.1.2 20080704 (Red Hat 4.1.2-55)
11 centos:6 : Ok gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-18)
12 centos:7 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28)
13 debian:7 : Ok gcc (Debian 4.7.2-5) 4.7.2
14 debian:8 : Ok gcc (Debian 4.9.2-10+deb8u1) 4.9.2
15 debian:9 : Ok gcc (Debian 6.3.0-18+deb9u1) 6.3.0 20170516
16 debian:experimental : Ok gcc (Debian 8.2.0-1) 8.2.0
17 debian:experimental-x-arm64 : Ok aarch64-linux-gnu-gcc (Debian 8.1.0-12) 8.1.0
18 debian:experimental-x-mips : Ok mips-linux-gnu-gcc (Debian 8.1.0-12) 8.1.0
19 debian:experimental-x-mips64 : Ok mips64-linux-gnuabi64-gcc (Debian 7.3.0-18) 7.3.0
20 debian:experimental-x-mipsel : Ok mipsel-linux-gnu-gcc (Debian 8.1.0-12) 8.1.0
21 fedora:20 : Ok gcc (GCC) 4.8.3 20140911 (Red Hat 4.8.3-7)
22 fedora:21 : Ok gcc (GCC) 4.9.2 20150212 (Red Hat 4.9.2-6)
23 fedora:22 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6)
24 fedora:23 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6)
25 fedora:24 : Ok gcc (GCC) 6.3.1 20161221 (Red Hat 6.3.1-1)
26 fedora:24-x-ARC-uClibc : Ok arc-linux-gcc (ARCompact ISA Linux uClibc toolchain 2017.09-rc2) 7.1.1 20170710
27 fedora:25 : Ok gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1)
28 fedora:26 : Ok gcc (GCC) 7.3.1 20180130 (Red Hat 7.3.1-2)
29 fedora:27 : Ok gcc (GCC) 7.3.1 20180303 (Red Hat 7.3.1-5)
30 fedora:28 : Ok gcc (GCC) 8.1.1 20180502 (Red Hat 8.1.1-1)
31 fedora:rawhide : Ok gcc (GCC) 8.0.1 20180324 (Red Hat 8.0.1-0.20)
32 gentoo-stage3-amd64:latest : Ok gcc (Gentoo 7.3.0-r3 p1.4) 7.3.0
33 mageia:5 : Ok gcc (GCC) 4.9.2
34 mageia:6 : Ok gcc (Mageia 5.5.0-1.mga6) 5.5.0
35 opensuse:42.1 : Ok gcc (SUSE Linux) 4.8.5
36 opensuse:42.2 : Ok gcc (SUSE Linux) 4.8.5
37 opensuse:42.3 : Ok gcc (SUSE Linux) 4.8.5
38 opensuse:tumbleweed : Ok gcc (SUSE Linux) 7.3.1 20180323 [gcc-7-branch revision 258812]
39 oraclelinux:6 : Ok gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-23.0.1)
40 oraclelinux:7 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28.0.1)
41 ubuntu:12.04.5 : Ok gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3
42 ubuntu:14.04.4 : Ok gcc (Ubuntu 4.8.4-2ubuntu1~14.04.3) 4.8.4
43 ubuntu:14.04.4-x-linaro-arm64 : Ok aarch64-linux-gnu-gcc (Linaro GCC 5.5-2017.10) 5.5.0
44 ubuntu:16.04 : Ok gcc (Ubuntu 5.4.0-6ubuntu1~16.04.10) 5.4.0 20160609
45 ubuntu:16.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
46 ubuntu:16.04-x-arm64 : Ok aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
47 ubuntu:16.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
48 ubuntu:16.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
49 ubuntu:16.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
50 ubuntu:16.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
51 ubuntu:16.10 : Ok gcc (Ubuntu 6.2.0-5ubuntu12) 6.2.0 20161005
52 ubuntu:17.04 : Ok gcc (Ubuntu 6.3.0-12ubuntu2) 6.3.0 20170406
53 ubuntu:17.10 : Ok gcc (Ubuntu 7.2.0-8ubuntu3.2) 7.2.0
54 ubuntu:18.04 : Ok gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0
55 ubuntu:18.10 : Ok gcc (Ubuntu 8.2.0-1ubuntu2) 8.2.0
#
# uname -a
# Linux seventh 4.17.9-100.fc27.x86_64 #1 SMP Mon Jul 23 22:35:38 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux
# git log --oneline -1
b912885ab75c (HEAD -> perf/core) perf trace: Do not require --no-syscalls to suppress strace like output
# perf version --build-options
perf version 4.18.rc7.g822c262
dwarf: [ on ] # HAVE_DWARF_SUPPORT
dwarf_getlocations: [ on ] # HAVE_DWARF_GETLOCATIONS_SUPPORT
glibc: [ on ] # HAVE_GLIBC_SUPPORT
gtk2: [ on ] # HAVE_GTK2_SUPPORT
syscall_table: [ on ] # HAVE_SYSCALL_TABLE_SUPPORT
libbfd: [ on ] # HAVE_LIBBFD_SUPPORT
libelf: [ on ] # HAVE_LIBELF_SUPPORT
libnuma: [ on ] # HAVE_LIBNUMA_SUPPORT
numa_num_possible_cpus: [ on ] # HAVE_LIBNUMA_SUPPORT
libperl: [ on ] # HAVE_LIBPERL_SUPPORT
libpython: [ on ] # HAVE_LIBPYTHON_SUPPORT
libslang: [ on ] # HAVE_SLANG_SUPPORT
libcrypto: [ on ] # HAVE_LIBCRYPTO_SUPPORT
libunwind: [ on ] # HAVE_LIBUNWIND_SUPPORT
libdw-dwarf-unwind: [ on ] # HAVE_DWARF_SUPPORT
zlib: [ on ] # HAVE_ZLIB_SUPPORT
lzma: [ on ] # HAVE_LZMA_SUPPORT
get_cpuid: [ on ] # HAVE_AUXTRACE_SUPPORT
bpf: [ on ] # HAVE_LIBBPF_SUPPORT
# perf test
1: vmlinux symtab matches kallsyms : Ok
2: Detect openat syscall event : Ok
3: Detect openat syscall event on all cpus : Ok
4: Read samples using the mmap interface : Ok
5: Test data source output : Ok
6: Parse event definition strings : Ok
7: Simple expression parser : Ok
8: PERF_RECORD_* events & perf_sample fields : Ok
9: Parse perf pmu format : Ok
10: DSO data read : Ok
11: DSO data cache : Ok
12: DSO data reopen : Ok
13: Roundtrip evsel->name : Ok
14: Parse sched tracepoints fields : Ok
15: syscalls:sys_enter_openat event fields : Ok
16: Setup struct perf_event_attr : Ok
17: Match and link multiple hists : Ok
18: 'import perf' in python : Ok
19: Breakpoint overflow signal handler : Ok
20: Breakpoint overflow sampling : Ok
21: Breakpoint accounting : Ok
22: Number of exit events of a simple workload : Ok
23: Software clock events period values : Ok
24: Object code reading : Ok
25: Sample parsing : Ok
26: Use a dummy software event to keep tracking : Ok
27: Parse with no sample_id_all bit set : Ok
28: Filter hist entries : Ok
29: Lookup mmap thread : Ok
30: Share thread mg : Ok
31: Sort output of hist entries : Ok
32: Cumulate child hist entries : Ok
33: Track with sched_switch : Ok
34: Filter fds with revents mask in a fdarray : Ok
35: Add fd to a fdarray, making it autogrow : Ok
36: kmod_path__parse : Ok
37: Thread map : Ok
38: LLVM search and compile :
38.1: Basic BPF llvm compile : Ok
38.2: kbuild searching : Ok
38.3: Compile source for BPF prologue generation : Ok
38.4: Compile source for BPF relocation : Ok
39: Session topology : Ok
40: BPF filter :
40.1: Basic BPF filtering : Ok
40.2: BPF pinning : Ok
40.3: BPF prologue generation : Ok
40.4: BPF relocation checker : Ok
41: Synthesize thread map : Ok
42: Remove thread map : Ok
43: Synthesize cpu map : Ok
44: Synthesize stat config : Ok
45: Synthesize stat : Ok
46: Synthesize stat round : Ok
47: Synthesize attr update : Ok
48: Event times : Ok
49: Read backward ring buffer : Ok
50: Print cpu map : Ok
51: Probe SDT events : Ok
52: is_printable_array : Ok
53: Print bitmap : Ok
54: perf hooks : Ok
55: builtin clang support : Skip (not compiled in)
56: unit_number__scnprintf : Ok
57: mem2node : Ok
58: x86 rdpmc : Ok
59: Convert perf time to TSC : Ok
60: DWARF unwind : Ok
61: x86 instruction decoder - new instructions : Ok
62: probe libc's inet_pton & backtrace it with ping : Ok
63: Check open filename arg using perf trace + vfs_getname: Ok
64: Use vfs_getname probe to get syscall args filenames : Ok
65: Add vfs_getname probe to get syscall args filenames : Ok
#
$ make -C tools/perf build-test
make: Entering directory '/home/acme/git/perf/tools/perf'
- tarpkg: ./tests/perf-targz-src-pkg .
make_no_libunwind_O: make NO_LIBUNWIND=1
make_no_newt_O: make NO_NEWT=1
make_install_bin_O: make install-bin
make_install_prefix_O: make install prefix=/tmp/krava
make_doc_O: make doc
make_perf_o_O: make perf.o
make_util_map_o_O: make util/map.o
make_no_libbionic_O: make NO_LIBBIONIC=1
make_no_demangle_O: make NO_DEMANGLE=1
make_no_libpython_O: make NO_LIBPYTHON=1
make_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1
make_help_O: make help
make_no_slang_O: make NO_SLANG=1
make_no_libperl_O: make NO_LIBPERL=1
make_with_babeltrace_O: make LIBBABELTRACE=1
make_static_O: make LDFLAGS=-static
make_pure_O: make
make_tags_O: make tags
make_no_ui_O: make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
make_no_libelf_O: make NO_LIBELF=1
make_minimal_O: make NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1
make_install_O: make install
make_with_clangllvm_O: make LIBCLANGLLVM=1
make_install_prefix_slash_O: make install prefix=/tmp/krava/
make_no_libaudit_O: make NO_LIBAUDIT=1
make_no_gtk2_O: make NO_GTK2=1
make_no_libnuma_O: make NO_LIBNUMA=1
make_no_libdw_dwarf_unwind_O: make NO_LIBDW_DWARF_UNWIND=1
make_no_auxtrace_O: make NO_AUXTRACE=1
make_no_libbpf_O: make NO_LIBBPF=1
make_clean_all_O: make clean all
make_no_backtrace_O: make NO_BACKTRACE=1
make_util_pmu_bison_o_O: make util/pmu-bison.o
make_debug_O: make DEBUG=1
make_cscope_O: make cscope
OK
make: Leaving directory '/home/acme/git/perf/tools/perf'
$
^ permalink raw reply
* [PATCH v4 4/6] powerpc/traps: Print VMA for unhandled signals
From: Murilo Opsfelder Araujo @ 2018-08-01 21:33 UTC (permalink / raw)
To: linux-kernel
Cc: Alastair D'Silva, Andrew Donnellan, Balbir Singh,
Benjamin Herrenschmidt, Christophe Leroy, Cyril Bur,
Eric W . Biederman, Joe Perches, Michael Ellerman,
Michael Neuling, Murilo Opsfelder Araujo, Nicholas Piggin,
Paul Mackerras, Simon Guo, Sukadev Bhattiprolu, Tobin C . Harding,
linuxppc-dev, Segher Boessenkool
In-Reply-To: <20180801213320.11203-1-muriloo@linux.ibm.com>
This adds VMA address in the message printed for unhandled signals,
similarly to what other architectures, like x86, print.
Before this patch, a page fault looked like:
pandafault[61470]: unhandled signal 11 at 100007d0 nip 1000061c lr 7fff8d185100 code 2
After this patch, a page fault looks like:
pandafault[6303]: segfault 11 at 100007d0 nip 1000061c lr 7fff93c55100 code 2 in pandafault[10000000+10000]
Signed-off-by: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
---
arch/powerpc/kernel/traps.c | 21 +++++++++++++++++++--
1 file changed, 19 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 4503e22f6ba5..bcefbb1ee771 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -96,6 +96,19 @@ EXPORT_SYMBOL(__debugger_fault_handler);
#define TM_DEBUG(x...) do { } while(0)
#endif
+static const char *signame(int signr)
+{
+ switch (signr) {
+ case SIGBUS: return "bus error";
+ case SIGFPE: return "floating point exception";
+ case SIGILL: return "illegal instruction";
+ case SIGSEGV: return "segfault";
+ case SIGTRAP: return "unhandled trap";
+ }
+
+ return "unknown signal";
+}
+
/*
* Trap & Exception support
*/
@@ -317,9 +330,13 @@ static void show_signal_msg(int signr, struct pt_regs *regs, int code,
if (!show_unhandled_signals_ratelimited())
return;
- pr_info("%s[%d]: unhandled signal %d at %lx nip %lx lr %lx code %x\n",
- current->comm, current->pid, signr,
+ pr_info("%s[%d]: %s (%d) at %lx nip %lx lr %lx code %x",
+ current->comm, current->pid, signame(signr), signr,
addr, regs->nip, regs->link, code);
+
+ print_vma_addr(KERN_CONT " in ", regs->nip);
+
+ pr_cont("\n");
}
void _exception_pkey(int signr, struct pt_regs *regs, int code,
--
2.17.1
^ permalink raw reply related
* [PATCH v4 5/6] powerpc: Add show_user_instructions()
From: Murilo Opsfelder Araujo @ 2018-08-01 21:33 UTC (permalink / raw)
To: linux-kernel
Cc: Alastair D'Silva, Andrew Donnellan, Balbir Singh,
Benjamin Herrenschmidt, Christophe Leroy, Cyril Bur,
Eric W . Biederman, Joe Perches, Michael Ellerman,
Michael Neuling, Murilo Opsfelder Araujo, Nicholas Piggin,
Paul Mackerras, Simon Guo, Sukadev Bhattiprolu, Tobin C . Harding,
linuxppc-dev, Segher Boessenkool
In-Reply-To: <20180801213320.11203-1-muriloo@linux.ibm.com>
show_user_instructions() is a slightly modified version of
show_instructions() that allows userspace instruction dump.
This will be useful within show_signal_msg() to dump userspace
instructions of the faulty location.
Here is a sample of what show_user_instructions() outputs:
pandafault[10850]: code: 4bfffeec 4bfffee8 3c401002 38427f00 fbe1fff8 f821ffc1 7c3f0b78 3d22fffe
pandafault[10850]: code: 392988d0 f93f0020 e93f0020 39400048 <99490000> 39200000 7d234b78 383f0040
The current->comm and current->pid printed can serve as a glue that
links the instructions dump to its originator, allowing messages to be
interleaved in the logs.
Signed-off-by: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
---
arch/powerpc/include/asm/stacktrace.h | 13 +++++++++
arch/powerpc/kernel/process.c | 40 +++++++++++++++++++++++++++
2 files changed, 53 insertions(+)
create mode 100644 arch/powerpc/include/asm/stacktrace.h
diff --git a/arch/powerpc/include/asm/stacktrace.h b/arch/powerpc/include/asm/stacktrace.h
new file mode 100644
index 000000000000..6149b53b3bc8
--- /dev/null
+++ b/arch/powerpc/include/asm/stacktrace.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Stack trace functions.
+ *
+ * Copyright 2018, Murilo Opsfelder Araujo, IBM Corporation.
+ */
+
+#ifndef _ASM_POWERPC_STACKTRACE_H
+#define _ASM_POWERPC_STACKTRACE_H
+
+void show_user_instructions(struct pt_regs *regs);
+
+#endif /* _ASM_POWERPC_STACKTRACE_H */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index e9533b4d2f08..364645ac732c 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1299,6 +1299,46 @@ static void show_instructions(struct pt_regs *regs)
pr_cont("\n");
}
+void show_user_instructions(struct pt_regs *regs)
+{
+ int i;
+ const char *prefix = KERN_INFO "%s[%d]: code: ";
+ unsigned long pc = regs->nip - (instructions_to_print * 3 / 4 *
+ sizeof(int));
+
+ printk(prefix, current->comm, current->pid);
+
+ for (i = 0; i < instructions_to_print; i++) {
+ int instr;
+
+ if (!(i % 8) && (i > 0)) {
+ pr_cont("\n");
+ printk(prefix, current->comm, current->pid);
+ }
+
+#if !defined(CONFIG_BOOKE)
+ /* If executing with the IMMU off, adjust pc rather
+ * than print XXXXXXXX.
+ */
+ if (!(regs->msr & MSR_IR))
+ pc = (unsigned long)phys_to_virt(pc);
+#endif
+
+ if (probe_kernel_address((unsigned int __user *)pc, instr)) {
+ pr_cont("XXXXXXXX ");
+ } else {
+ if (regs->nip == pc)
+ pr_cont("<%08x> ", instr);
+ else
+ pr_cont("%08x ", instr);
+ }
+
+ pc += sizeof(int);
+ }
+
+ pr_cont("\n");
+}
+
struct regbit {
unsigned long bit;
const char *name;
--
2.17.1
^ permalink raw reply related
* [PATCH v4 6/6] powerpc/traps: Show instructions on exceptions
From: Murilo Opsfelder Araujo @ 2018-08-01 21:33 UTC (permalink / raw)
To: linux-kernel
Cc: Alastair D'Silva, Andrew Donnellan, Balbir Singh,
Benjamin Herrenschmidt, Christophe Leroy, Cyril Bur,
Eric W . Biederman, Joe Perches, Michael Ellerman,
Michael Neuling, Murilo Opsfelder Araujo, Nicholas Piggin,
Paul Mackerras, Simon Guo, Sukadev Bhattiprolu, Tobin C . Harding,
linuxppc-dev, Segher Boessenkool
In-Reply-To: <20180801213320.11203-1-muriloo@linux.ibm.com>
Call show_user_instructions() in arch/powerpc/kernel/traps.c to dump
instructions at faulty location, useful to debugging.
Before this patch, an unhandled signal message looked like:
pandafault[10524]: segfault (11) at 100007d0 nip 1000061c lr 7fffbd295100 code 2 in pandafault[10000000+10000]
After this patch, it looks like:
pandafault[10524]: segfault (11) at 100007d0 nip 1000061c lr 7fffbd295100 code 2 in pandafault[10000000+10000]
pandafault[10524]: code: 4bfffeec 4bfffee8 3c401002 38427f00 fbe1fff8 f821ffc1 7c3f0b78 3d22fffe
pandafault[10524]: code: 392988d0 f93f0020 e93f0020 39400048 <99490000> 39200000 7d234b78 383f0040
Signed-off-by: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
---
arch/powerpc/kernel/traps.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index bcefbb1ee771..8494b0ff4904 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -70,6 +70,7 @@
#include <asm/hmi.h>
#include <sysdev/fsl_pci.h>
#include <asm/kprobes.h>
+#include <asm/stacktrace.h>
#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE)
int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -337,6 +338,8 @@ static void show_signal_msg(int signr, struct pt_regs *regs, int code,
print_vma_addr(KERN_CONT " in ", regs->nip);
pr_cont("\n");
+
+ show_user_instructions(regs);
}
void _exception_pkey(int signr, struct pt_regs *regs, int code,
--
2.17.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox