From 6bbfe4e602691b90ac866712bd4c43c51e546a60 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 1 Aug 2019 16:26:42 +0200 Subject: perf bench numa: Fix cpu0 binding Michael reported an issue with perf bench numa failing with binding to cpu0 with '-0' option. # perf bench numa mem -p 3 -t 1 -P 512 -s 100 -zZcm0 --thp 1 -M 1 -ddd # Running 'numa/mem' benchmark: # Running main, "perf bench numa numa-mem -p 3 -t 1 -P 512 -s 100 -zZcm0 --thp 1 -M 1 -ddd" binding to node 0, mask: 0000000000000001 => -1 perf: bench/numa.c:356: bind_to_memnode: Assertion `!(ret)' failed. Aborted (core dumped) This happens when the cpu0 is not part of node0, which is the benchmark assumption and we can see that's not the case for some powerpc servers. Using correct node for cpu0 binding. Reported-by: Michael Petlan Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Satheesh Rajendran Link: http://lkml.kernel.org/r/20190801142642.28004-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/numa.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index a640ca7aaadaf..513cb2f2fa32e 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -379,8 +379,10 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags, /* Allocate and initialize all memory on CPU#0: */ if (init_cpu0) { - orig_mask = bind_to_node(0); - bind_to_memnode(0); + int node = numa_node_of_cpu(0); + + orig_mask = bind_to_node(node); + bind_to_memnode(node); } bytes = bytes0 + HPSIZE; -- cgit v1.2.3 From 85127775a65fc58e69af0c44513937d471ccbe7b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 6 Aug 2019 11:24:09 -0300 Subject: perf annotate: Fix printing of unaugmented disassembled instructions from BPF The code to disassemble BPF programs uses binutil's disassembling routines, and those use in turn fprintf to print to a memstream FILE, adding a newline at the end of each line, which ends up confusing the TUI routines called from: annotate_browser__write() annotate_line__write() annotate_browser__printf() ui_browser__vprintf() SLsmg_vprintf() The SLsmg_vprintf() function in the slang library gets confused with the terminating newline, so make the disasm_line__parse() function that parses the lines produced by the BPF specific disassembler (that uses binutil's libopcodes) and the lines produced by the objdump based disassembler used for everything else (and that doesn't adds this terminating newline) trim the end of the line in addition of the beginning. This way when disasm_line->ops.raw, i.e. for instructions without a special scnprintf() method, we'll not have that \n getting in the way of filling the screen right after the instruction with spaces to avoid leaving what was on the screen before and thus garbling the annotation screen, breaking scrolling, etc. Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Cc: Song Liu Fixes: 6987561c9e86 ("perf annotate: Enable annotation of BPF programs") Link: https://lkml.kernel.org/n/tip-unbr5a5efakobfr6rhxq99ta@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ac9ad2330f930..163536720149b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1122,7 +1122,7 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp) goto out; (*rawp)[0] = tmp; - *rawp = skip_spaces(*rawp); + *rawp = strim(*rawp); return 0; -- cgit v1.2.3 From 3de7ae0b2a1d86dbb23d0cb135150534fdb2e836 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 8 Aug 2019 09:48:23 +0300 Subject: perf db-export: Fix thread__exec_comm() Threads synthesized from /proc have comms with a start time of zero, and not marked as "exec". Currently, there can be 2 such comms. The first is created by processing a synthesized fork event and is set to the parent's comm string, and the second by processing a synthesized comm event set to the thread's current comm string. In the absence of an "exec" comm, thread__exec_comm() picks the last (oldest) comm, which, in the case above, is the parent's comm string. For a main thread, that is very probably wrong. Use the second-to-last in that case. This affects only db-export because it is the only user of thread__exec_comm(). Example: $ sudo perf record -a -o pt-a-sleep-1 -e intel_pt//u -- sleep 1 $ sudo chown ahunter pt-a-sleep-1 Before: $ perf script -i pt-a-sleep-1 --itrace=bep -s tools/perf/scripts/python/export-to-sqlite.py pt-a-sleep-1.db branches calls $ sqlite3 -header -column pt-a-sleep-1.db 'select * from comm_threads_view' comm_id command thread_id pid tid ---------- ---------- ---------- ---------- ---------- 1 swapper 1 0 0 2 rcu_sched 2 10 10 3 kthreadd 3 78 78 5 sudo 4 15180 15180 5 sudo 5 15180 15182 7 kworker/4: 6 10335 10335 8 kthreadd 7 55 55 10 systemd 8 865 865 10 systemd 9 865 875 13 perf 10 15181 15181 15 sleep 10 15181 15181 16 kworker/3: 11 14179 14179 17 kthreadd 12 29376 29376 19 systemd 13 746 746 21 systemd 14 401 401 23 systemd 15 879 879 23 systemd 16 879 945 25 kthreadd 17 556 556 27 kworker/u1 18 14136 14136 28 kworker/u1 19 15021 15021 29 kthreadd 20 509 509 31 systemd 21 836 836 31 systemd 22 836 967 33 systemd 23 1148 1148 33 systemd 24 1148 1163 35 kworker/2: 25 17988 17988 36 kworker/0: 26 13478 13478 After: $ perf script -i pt-a-sleep-1 --itrace=bep -s tools/perf/scripts/python/export-to-sqlite.py pt-a-sleep-1b.db branches calls $ sqlite3 -header -column pt-a-sleep-1b.db 'select * from comm_threads_view' comm_id command thread_id pid tid ---------- ---------- ---------- ---------- ---------- 1 swapper 1 0 0 2 rcu_sched 2 10 10 3 kswapd0 3 78 78 4 perf 4 15180 15180 4 perf 5 15180 15182 6 kworker/4: 6 10335 10335 7 kcompactd0 7 55 55 8 accounts-d 8 865 865 8 accounts-d 9 865 875 10 perf 10 15181 15181 12 sleep 10 15181 15181 13 kworker/3: 11 14179 14179 14 kworker/1: 12 29376 29376 15 haveged 13 746 746 16 systemd-jo 14 401 401 17 NetworkMan 15 879 879 17 NetworkMan 16 879 945 19 irq/131-iw 17 556 556 20 kworker/u1 18 14136 14136 21 kworker/u1 19 15021 15021 22 kworker/u1 20 509 509 23 thermald 21 836 836 23 thermald 22 836 967 25 unity-sett 23 1148 1148 25 unity-sett 24 1148 1163 27 kworker/2: 25 17988 17988 28 kworker/0: 26 13478 13478 Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: stable@vger.kernel.org Fixes: 65de51f93ebf ("perf tools: Identify which comms are from exec") Link: http://lkml.kernel.org/r/20190808064823.14846-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/thread.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 873ab505ca807..590793cc51424 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -214,14 +214,24 @@ struct comm *thread__comm(const struct thread *thread) struct comm *thread__exec_comm(const struct thread *thread) { - struct comm *comm, *last = NULL; + struct comm *comm, *last = NULL, *second_last = NULL; list_for_each_entry(comm, &thread->comm_list, list) { if (comm->exec) return comm; + second_last = last; last = comm; } + /* + * 'last' with no start time might be the parent's comm of a synthesized + * thread (created by processing a synthesized fork event). For a main + * thread, that is very probably wrong. Prefer a later comm to avoid + * that case. + */ + if (second_last && !last->start && thread->pid_ == thread->tid) + return second_last; + return last; } -- cgit v1.2.3 From cf30ae726c011e0372fd4c2d588466c8b50a8907 Mon Sep 17 00:00:00 2001 From: He Zhe Date: Fri, 2 Aug 2019 16:29:51 +0800 Subject: perf ftrace: Fix failure to set cpumask when only one cpu is present The buffer containing the string used to set cpumask is overwritten at the end of the string later in cpu_map__snprint_mask due to not enough memory space, when there is only one cpu. And thus causes the following failure: $ perf ftrace ls failed to reset ftrace $ This patch fixes the calculation of the cpumask string size. Signed-off-by: He Zhe Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Fixes: dc23103278c5 ("perf ftrace: Add support for -a and -C option") Link: http://lkml.kernel.org/r/1564734592-15624-1-git-send-email-zhe.he@windriver.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 66d5a6658daf5..0193128104056 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -173,7 +173,7 @@ static int set_tracing_cpumask(struct cpu_map *cpumap) int last_cpu; last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1); - mask_size = (last_cpu + 3) / 4 + 1; + mask_size = last_cpu / 4 + 2; /* one more byte for EOS */ mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */ cpumask = malloc(mask_size); -- cgit v1.2.3 From 5f5e25f1c7933a6e1673515c0b1d5acd82fea1ed Mon Sep 17 00:00:00 2001 From: He Zhe Date: Fri, 2 Aug 2019 16:29:52 +0800 Subject: perf cpumap: Fix writing to illegal memory in handling cpumap mask cpu_map__snprint_mask() would write to illegal memory pointed by zalloc(0) when there is only one cpu. This patch fixes the calculation and adds sanity check against the input parameters. Signed-off-by: He Zhe Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Fixes: 4400ac8a9a90 ("perf cpumap: Introduce cpu_map__snprint_mask()") Link: http://lkml.kernel.org/r/1564734592-15624-2-git-send-email-zhe.he@windriver.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cpumap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 3acfbe34ebafb..39cce66b4ebcc 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -751,7 +751,10 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) unsigned char *bitmap; int last_cpu = cpu_map__cpu(map, map->nr - 1); - bitmap = zalloc((last_cpu + 7) / 8); + if (buf == NULL) + return 0; + + bitmap = zalloc(last_cpu / 8 + 1); if (bitmap == NULL) { buf[0] = '\0'; return 0; -- cgit v1.2.3 From 89b66500f739e0033ef59011e3df694f2053679d Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Thu, 1 Aug 2019 12:28:12 +0900 Subject: perf tools: Fix a typo in a variable name in the Documentation Makefile This patch fix a spelling typo in a variable name in the Documentation Makefile. Signed-off-by: Masanari Iida Reviewed-by: Mukesh Ojha Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20190801032812.25018-1-standby24x7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 6d148a40551ce..adc5a7e44b982 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -242,7 +242,7 @@ $(OUTPUT)doc.dep : $(wildcard *.txt) build-docdep.perl $(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \ mv $@+ $@ --include $(OUPTUT)doc.dep +-include $(OUTPUT)doc.dep _cmds_txt = cmds-ancillaryinterrogators.txt \ cmds-ancillarymanipulators.txt \ -- cgit v1.2.3 From fa37bab6d7154658d8a35920513f9396587754cc Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 31 Jul 2019 15:54:41 -0700 Subject: perf tools: Fix include paths in ui directory These paths point to the wrong location but still work because they get picked up by a -I flag that happens to direct to the correct file. Fix paths to point to the correct location without -I flags. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190731225441.233800-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browser.c | 9 +++++---- tools/perf/ui/tui/progress.c | 2 +- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index f80c51d535655..d227d74b28f81 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../string2.h" -#include "../config.h" -#include "../../perf.h" +#include "../util/util.h" +#include "../util/string2.h" +#include "../util/config.h" +#include "../perf.h" #include "libslang.h" #include "ui.h" #include "util.h" @@ -14,7 +15,7 @@ #include "browser.h" #include "helpline.h" #include "keysyms.h" -#include "../color.h" +#include "../util/color.h" #include #include diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c index bc134b82829d6..5a24dd3ce4db9 100644 --- a/tools/perf/ui/tui/progress.c +++ b/tools/perf/ui/tui/progress.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include "../cache.h" +#include "../../util/cache.h" #include "../progress.h" #include "../libslang.h" #include "../ui.h" -- cgit v1.2.3 From 12a6d2940b5f02b4b9f71ce098e3bb02bc24a9ea Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 24 Jul 2019 14:27:02 +0200 Subject: perf record: Fix module size on s390 On s390 the modules loaded in memory have the text segment located after the GOT and Relocation table. This can be seen with this output: [root@m35lp76 perf]# fgrep qeth /proc/modules qeth 151552 1 qeth_l2, Live 0x000003ff800b2000 ... [root@m35lp76 perf]# cat /sys/module/qeth/sections/.text 0x000003ff800b3990 [root@m35lp76 perf]# There is an offset of 0x1990 bytes. The size of the qeth module is 151552 bytes (0x25000 in hex). The location of the GOT/relocation table at the beginning of a module is unique to s390. commit 203d8a4aa6ed ("perf s390: Fix 'start' address of module's map") adjusts the start address of a module in the map structures, but does not adjust the size of the modules. This leads to overlapping of module maps as this example shows: [root@m35lp76 perf] # ./perf report -D 0 0 0xfb0 [0xa0]: PERF_RECORD_MMAP -1/0: [0x3ff800b3990(0x25000) @ 0]: x /lib/modules/.../qeth.ko.xz 0 0 0x1050 [0xb0]: PERF_RECORD_MMAP -1/0: [0x3ff800d85a0(0x8000) @ 0]: x /lib/modules/.../ip6_tables.ko.xz The module qeth.ko has an adjusted start address modified to b3990, but its size is unchanged and the module ends at 0x3ff800d8990. This end address overlaps with the next modules start address of 0x3ff800d85a0. When the size of the leading GOT/Relocation table stored in the beginning of the text segment (0x1990 bytes) is subtracted from module qeth end address, there are no overlaps anymore: 0x3ff800d8990 - 0x1990 = 0x0x3ff800d7000 which is the same as 0x3ff800b2000 + 0x25000 = 0x0x3ff800d7000. To fix this issue, also adjust the modules size in function arch__fix_module_text_start(). Add another function parameter named size and reduce the size of the module when the text segment start address is changed. Output after: 0 0 0xfb0 [0xa0]: PERF_RECORD_MMAP -1/0: [0x3ff800b3990(0x23670) @ 0]: x /lib/modules/.../qeth.ko.xz 0 0 0x1050 [0xb0]: PERF_RECORD_MMAP -1/0: [0x3ff800d85a0(0x7a60) @ 0]: x /lib/modules/.../ip6_tables.ko.xz Reported-by: Stefan Liebler Signed-off-by: Thomas Richter Acked-by: Heiko Carstens Cc: Hendrik Brueckner Cc: Vasily Gorbik Cc: stable@vger.kernel.org Fixes: 203d8a4aa6ed ("perf s390: Fix 'start' address of module's map") Link: http://lkml.kernel.org/r/20190724122703.3996-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/machine.c | 14 +++++++++++++- tools/perf/util/machine.c | 3 ++- tools/perf/util/machine.h | 2 +- 3 files changed, 16 insertions(+), 3 deletions(-) diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index a19690a17291e..de26b1441a485 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -7,7 +7,7 @@ #include "api/fs/fs.h" #include "debug.h" -int arch__fix_module_text_start(u64 *start, const char *name) +int arch__fix_module_text_start(u64 *start, u64 *size, const char *name) { u64 m_start = *start; char path[PATH_MAX]; @@ -17,6 +17,18 @@ int arch__fix_module_text_start(u64 *start, const char *name) if (sysfs__read_ull(path, (unsigned long long *)start) < 0) { pr_debug2("Using module %s start:%#lx\n", path, m_start); *start = m_start; + } else { + /* Successful read of the modules segment text start address. + * Calculate difference between module start address + * in memory and module text segment start address. + * For example module load address is 0x3ff8011b000 + * (from /proc/modules) and module text segment start + * address is 0x3ff8011b870 (from file above). + * + * Adjust the module size and subtract the GOT table + * size located at the beginning of the module. + */ + *size -= (*start - m_start); } return 0; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index cf826eca3aafd..83b2fbbeeb900 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1378,6 +1378,7 @@ static int machine__set_modules_path(struct machine *machine) return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0); } int __weak arch__fix_module_text_start(u64 *start __maybe_unused, + u64 *size __maybe_unused, const char *name __maybe_unused) { return 0; @@ -1389,7 +1390,7 @@ static int machine__create_module(void *arg, const char *name, u64 start, struct machine *machine = arg; struct map *map; - if (arch__fix_module_text_start(&start, name) < 0) + if (arch__fix_module_text_start(&start, &size, name) < 0) return -1; map = machine__findnew_module_map(machine, start, name); diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index f70ab98a7bde5..7aa38da264270 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -222,7 +222,7 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, struct map *machine__findnew_module_map(struct machine *machine, u64 start, const char *filename); -int arch__fix_module_text_start(u64 *start, const char *name); +int arch__fix_module_text_start(u64 *start, u64 *size, const char *name); int machine__load_kallsyms(struct machine *machine, const char *filename); -- cgit v1.2.3 From b9c0a64901d5bdec6eafd38d1dc8fa0e2974fccb Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 24 Jul 2019 14:27:03 +0200 Subject: perf annotate: Fix s390 gap between kernel end and module start During execution of command 'perf top' the error message: Not enough memory for annotating '__irf_end' symbol!) is emitted from this call sequence: __cmd_top perf_top__mmap_read perf_top__mmap_read_idx perf_event__process_sample hist_entry_iter__add hist_iter__top_callback perf_top__record_precise_ip hist_entry__inc_addr_samples symbol__inc_addr_samples symbol__get_annotation symbol__alloc_hist In this function the size of symbol __irf_end is calculated. The size of a symbol is the difference between its start and end address. When the symbol was read the first time, its start and end was set to: symbol__new: __irf_end 0xe954d0-0xe954d0 which is correct and maps with /proc/kallsyms: root@s8360046:~/linux-4.15.0/tools/perf# fgrep _irf_end /proc/kallsyms 0000000000e954d0 t __irf_end root@s8360046:~/linux-4.15.0/tools/perf# In function symbol__alloc_hist() the end of symbol __irf_end is symbol__alloc_hist sym:__irf_end start:0xe954d0 end:0x3ff80045a8 which is identical with the first module entry in /proc/kallsyms This results in a symbol size of __irf_req for histogram analyses of 70334140059072 bytes and a malloc() for this requested size fails. The root cause of this is function __dso__load_kallsyms() +-> symbols__fixup_end() Function symbols__fixup_end() enlarges the last symbol in the kallsyms map: # fgrep __irf_end /proc/kallsyms 0000000000e954d0 t __irf_end # to the start address of the first module: # cat /proc/kallsyms | sort | egrep ' [tT] ' .... 0000000000e952d0 T __security_initcall_end 0000000000e954d0 T __initramfs_size 0000000000e954d0 t __irf_end 000003ff800045a8 T fc_get_event_number [scsi_transport_fc] 000003ff800045d0 t store_fc_vport_disable [scsi_transport_fc] 000003ff800046a8 T scsi_is_fc_rport [scsi_transport_fc] 000003ff800046d0 t fc_target_setup [scsi_transport_fc] On s390 the kernel is located around memory address 0x200, 0x10000 or 0x100000, depending on linux version. Modules however start some- where around 0x3ff xxxx xxxx. This is different than x86 and produces a large gap for which histogram allocation fails. Fix this by detecting the kernel's last symbol and do no adjustment for it. Introduce a weak function and handle s390 specifics. Reported-by: Klaus Theurich Signed-off-by: Thomas Richter Acked-by: Heiko Carstens Cc: Hendrik Brueckner Cc: Vasily Gorbik Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20190724122703.3996-2-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/machine.c | 17 +++++++++++++++++ tools/perf/util/symbol.c | 7 ++++++- tools/perf/util/symbol.h | 1 + 3 files changed, 24 insertions(+), 1 deletion(-) diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index de26b1441a485..c8c86a0c9b793 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -6,6 +6,7 @@ #include "machine.h" #include "api/fs/fs.h" #include "debug.h" +#include "symbol.h" int arch__fix_module_text_start(u64 *start, u64 *size, const char *name) { @@ -33,3 +34,19 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name) return 0; } + +/* On s390 kernel text segment start is located at very low memory addresses, + * for example 0x10000. Modules are located at very high memory addresses, + * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment + * and beginning of first module's text segment is very big. + * Therefore do not fill this gap and do not assign it to the kernel dso map. + */ +void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) +{ + if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) + /* Last kernel symbol mapped to end of page */ + p->end = roundup(p->end, page_size); + else + p->end = c->start; + pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end); +} diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 173f3378aaa06..4efde7879474c 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -92,6 +92,11 @@ static int prefix_underscores_count(const char *str) return tail - str; } +void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c) +{ + p->end = c->start; +} + const char * __weak arch__normalize_symbol_name(const char *name) { return name; @@ -218,7 +223,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols) curr = rb_entry(nd, struct symbol, rb_node); if (prev->end == prev->start && prev->end != curr->start) - prev->end = curr->start; + arch__symbols__fixup_end(prev, curr); } /* Last entry */ diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 12755b42ea93c..183f630cb5f1b 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -288,6 +288,7 @@ const char *arch__normalize_symbol_name(const char *name); #define SYMBOL_A 0 #define SYMBOL_B 1 +void arch__symbols__fixup_end(struct symbol *p, struct symbol *c); int arch__compare_symbol_names(const char *namea, const char *nameb); int arch__compare_symbol_names_n(const char *namea, const char *nameb, unsigned int n); -- cgit v1.2.3 From 8e6e5bea2e34c61291d00cb3f47560341aa84bc3 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Mon, 29 Jul 2019 15:27:55 +0800 Subject: perf pmu-events: Fix missing "cpu_clk_unhalted.core" event The events defined in pmu-events JSON are parsed and added into perf tool. For fixed counters, we handle the encodings between JSON and perf by using a static array fixed[]. But the fixed[] has missed an important event "cpu_clk_unhalted.core". For example, on the Tremont platform, [root@localhost ~]# perf stat -e cpu_clk_unhalted.core -a event syntax error: 'cpu_clk_unhalted.core' \___ parser error With this patch, the event cpu_clk_unhalted.core can be parsed. [root@localhost perf]# ./perf stat -e cpu_clk_unhalted.core -a -vvv ------------------------------------------------------------ perf_event_attr: type 4 size 112 config 0x3c sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 inherit 1 exclude_guest 1 ------------------------------------------------------------ ... Signed-off-by: Jin Yao Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20190729072755.2166-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 1a91a197cafb0..d413761621b09 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -453,6 +453,7 @@ static struct fixed { { "inst_retired.any_p", "event=0xc0" }, { "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" }, { "cpu_clk_unhalted.thread", "event=0x3c" }, + { "cpu_clk_unhalted.core", "event=0x3c" }, { "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" }, { NULL, NULL}, }; -- cgit v1.2.3