From 6d545a632fbbce79492ba535b15ea0142aa3e80d Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 7 Jul 2015 14:13:38 +0300
Subject: perf tools: Fix lockup using 32-bit compat vdso
The __machine__findnew_compat() function is called only from
__machine__findnew_vdso_compat() which is called only from
machine__findnew_vdso() which already holds machine->dsos.lock, so
remove locking from __machine__findnew_compat().
This manifests itself tracing 32-bit programs with a 64-bit perf.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1436267618-20521-1-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/vdso.c | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
(limited to 'tools')
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 4b89118f158d..44d440da15dc 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -236,18 +236,16 @@ static struct dso *__machine__findnew_compat(struct machine *machine,
const char *file_name;
struct dso *dso;
- pthread_rwlock_wrlock(&machine->dsos.lock);
dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
if (dso)
- goto out_unlock;
+ goto out;
file_name = vdso__get_compat_file(vdso_file);
if (!file_name)
- goto out_unlock;
+ goto out;
dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
-out_unlock:
- pthread_rwlock_unlock(&machine->dsos.lock);
+out:
return dso;
}
--
cgit v1.2.3
From 5fc472a628edb8ad83016a063329e8b589a04060 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 8 Jul 2015 13:17:31 +0200
Subject: perf stat: Fix shadow declaration of close
Vinson reported shadow declaration of close introduced
by the following commit:
106a94a0f8c2 perf stat: Introduce read_counters function
Using close_counters name instead.
Reported-by: Vinson Lee <vlee@twopensource.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Fixes: 106a94a0f8c2 ("perf stat: Introduce read_counters function")
Link: http://lkml.kernel.org/r/20150708111731.GA3512@krava.redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-stat.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 37e301a32f43..d99d850e1444 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -343,7 +343,7 @@ static int read_counter(struct perf_evsel *counter)
return 0;
}
-static void read_counters(bool close)
+static void read_counters(bool close_counters)
{
struct perf_evsel *counter;
@@ -354,7 +354,7 @@ static void read_counters(bool close)
if (process_counter(counter))
pr_warning("failed to process counter %s\n", counter->name);
- if (close) {
+ if (close_counters) {
perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
thread_map__nr(evsel_list->threads));
}
--
cgit v1.2.3
From c867b150de8514d8682978d8e8874c3940ae781b Mon Sep 17 00:00:00 2001
From: Riku Voipio <riku.voipio@linaro.org>
Date: Thu, 18 Jun 2015 15:52:18 +0300
Subject: tools lib: Improve clean target
The clean targets miss some .cmd and .d files.
Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: linux-kbuild@vger.kernel.org
Link: http://lkml.kernel.org/r/1434631938-12681-1-git-send-email-riku.voipio@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/lib/api/Makefile | 2 +-
tools/lib/traceevent/Makefile | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 8bd960658463..fe1b02c2c95b 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -36,7 +36,7 @@ $(LIBFILE): $(API_IN)
clean:
$(call QUIET_CLEAN, libapi) $(RM) $(LIBFILE); \
- find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o | xargs $(RM)
+ find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM)
FORCE:
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 6daaff652aff..7851df1490e0 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -268,7 +268,7 @@ install: install_lib
clean:
$(call QUIET_CLEAN, libtraceevent) \
- $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
+ $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd \
$(RM) TRACEEVENT-CFLAGS tags TAGS
PHONY += force plugins
--
cgit v1.2.3
From 08ae217b8d44986062fe3648c5bb83816d5bc00f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 9 Jul 2015 12:14:43 -0300
Subject: perf thread_map: Fix the sizeof() calculation for map entries
When we started adding extra stuff per array entry, growing the size of
those entries to more than sizeof(pid_t), we had to convert those sizeof
operations to the more robust sizeof(map->map[0]) idiom, that is future
proof, i.e. if/when we add more stuff to those entries, that expression
will produce the new per-entry size.
And besides that, we need to zero out those extra fields, that sometimes
may not get filled, like when we couldn't care less about the comms,
since we don't need those, but since we will try freeing it at
thread_map__delete(), we better fix it.
That is why a thread_map__realloc() was provided.
But that method wasn't used in thread_map__new_by_uid(), fix it.
Reported-by: Ingo Molnar <mingo@kernel.org>
Fixes: 792402fd5c0a ("perf thrad_map: Add comm string into array")
Fixes: 9d7e8c3a96e5 ("perf tools: Add thread_map__(alloc|realloc) helpers")
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-6a0swlm6m8lnu3wpjv284hkb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/thread_map.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
(limited to 'tools')
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index da7646d767fe..292ae2c90e06 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -136,8 +136,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
if (grow) {
struct thread_map *tmp;
- tmp = realloc(threads, (sizeof(*threads) +
- max_threads * sizeof(pid_t)));
+ tmp = thread_map__realloc(threads, max_threads);
if (tmp == NULL)
goto out_free_namelist;
--
cgit v1.2.3
From f3efe3a07e0060dc5d6c41644733e49c7bd50a5b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 9 Jul 2015 16:23:57 -0300
Subject: perf tools: Fix the detached tarball wrt rbtree copy
The python binding build process was still looking at the kernel
rbtree.c file, so, when doing a in-tree build it would work, but when
creating a tarball using tools/perf/MANIFEST as the contents list and
then trying to build the resulting detached sources, it failed.
Fix it by removing one level of indirection from rbtree.c in the
tools/perf/util/python-ext-sources file.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-8u83c2k5guyhxdlkaaqis8k4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/python-ext-sources | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index e23ded40c79e..de05e04b79c8 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -19,5 +19,5 @@ util/rblist.c
util/stat.c
util/strlist.c
util/trace-event.c
-../../lib/rbtree.c
+../lib/rbtree.c
util/string.c
--
cgit v1.2.3
From 0aefc3590afcc9ecbe173fc01fccbda0869d2f0a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 9 Jul 2015 16:27:25 -0300
Subject: tools: Copy lib/hweight.c from the kernel sources
Instead of accessing it directly, as it uses EXPORT_SYMBOL, that has
no meaning in tools/perf and because we removed the stubs for it, i.e.
we removed the tools/include/linux/export.h file.
This fixes the build for the detached tarball sources cases and removes
one more source of entanglement with the kernel sources.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-oyqx541o7apa2cskjhcxi6nx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/lib/hweight.c | 62 ++++++++++++++++++++++++++++++++++++++
tools/perf/MANIFEST | 2 +-
tools/perf/util/Build | 2 +-
tools/perf/util/python-ext-sources | 2 +-
4 files changed, 65 insertions(+), 3 deletions(-)
create mode 100644 tools/lib/hweight.c
(limited to 'tools')
diff --git a/tools/lib/hweight.c b/tools/lib/hweight.c
new file mode 100644
index 000000000000..0b859b884339
--- /dev/null
+++ b/tools/lib/hweight.c
@@ -0,0 +1,62 @@
+#include <linux/bitops.h>
+#include <asm/types.h>
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+unsigned int __sw_hweight32(unsigned int w)
+{
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+ w -= (w >> 1) & 0x55555555;
+ w = (w & 0x33333333) + ((w >> 2) & 0x33333333);
+ w = (w + (w >> 4)) & 0x0f0f0f0f;
+ return (w * 0x01010101) >> 24;
+#else
+ unsigned int res = w - ((w >> 1) & 0x55555555);
+ res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
+ res = (res + (res >> 4)) & 0x0F0F0F0F;
+ res = res + (res >> 8);
+ return (res + (res >> 16)) & 0x000000FF;
+#endif
+}
+
+unsigned int __sw_hweight16(unsigned int w)
+{
+ unsigned int res = w - ((w >> 1) & 0x5555);
+ res = (res & 0x3333) + ((res >> 2) & 0x3333);
+ res = (res + (res >> 4)) & 0x0F0F;
+ return (res + (res >> 8)) & 0x00FF;
+}
+
+unsigned int __sw_hweight8(unsigned int w)
+{
+ unsigned int res = w - ((w >> 1) & 0x55);
+ res = (res & 0x33) + ((res >> 2) & 0x33);
+ return (res + (res >> 4)) & 0x0F;
+}
+
+unsigned long __sw_hweight64(__u64 w)
+{
+#if BITS_PER_LONG == 32
+ return __sw_hweight32((unsigned int)(w >> 32)) +
+ __sw_hweight32((unsigned int)w);
+#elif BITS_PER_LONG == 64
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+ w -= (w >> 1) & 0x5555555555555555ul;
+ w = (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
+ w = (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;
+ return (w * 0x0101010101010101ul) >> 56;
+#else
+ __u64 res = w - ((w >> 1) & 0x5555555555555555ul);
+ res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
+ res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
+ res = res + (res >> 8);
+ res = res + (res >> 16);
+ return (res + (res >> 32)) & 0x00000000000000FFul;
+#endif
+#endif
+}
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 09dc0aabb515..d01a0aad5a01 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -18,6 +18,7 @@ tools/arch/x86/include/asm/atomic.h
tools/arch/x86/include/asm/rmwcc.h
tools/lib/traceevent
tools/lib/api
+tools/lib/hweight.c
tools/lib/rbtree.c
tools/lib/symbol/kallsyms.c
tools/lib/symbol/kallsyms.h
@@ -57,7 +58,6 @@ include/linux/perf_event.h
include/linux/list.h
include/linux/hash.h
include/linux/stringify.h
-lib/hweight.c
include/linux/swab.h
arch/*/include/asm/unistd*.h
arch/*/include/uapi/asm/unistd*.h
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 601d11440596..d2d318c59b37 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -143,6 +143,6 @@ $(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
-$(OUTPUT)util/hweight.o: ../../lib/hweight.c FORCE
+$(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index de05e04b79c8..0766d98c5da5 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,7 +10,7 @@ util/ctype.c
util/evlist.c
util/evsel.c
util/cpumap.c
-../../lib/hweight.c
+../lib/hweight.c
util/thread_map.c
util/util.c
util/xyarray.c
--
cgit v1.2.3
From 0bc2f2f7d080561cc484d2d0a162a9396bed3383 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 13 Jul 2015 08:21:57 -0300
Subject: perf symbols: Store if there is a filter in place
When setting yup the symbols library we setup several filter lists,
for dsos, comms, symbols, etc, and there is code that, if there are
filters, do certain operations, like recalculate the number of non
filtered histogram entries in the top/report TUI.
But they were considering just the "Zoom" filters, when they need to
take into account as well the above mentioned filters (perf top --comms,
--dsos, etc).
So store in symbol_conf.has_filter true if any of those filters is in
place.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-f5edfmhq69vfvs1kmikq1wep@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/symbol.c | 2 ++
tools/perf/util/symbol.h | 3 ++-
2 files changed, 4 insertions(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 48b588c6951a..60f11414bb5c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1911,6 +1911,8 @@ int setup_list(struct strlist **list, const char *list_str,
pr_err("problems parsing %s list\n", list_name);
return -1;
}
+
+ symbol_conf.has_filter = true;
return 0;
}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index bef47ead1d9b..b98ce51af142 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -105,7 +105,8 @@ struct symbol_conf {
demangle_kernel,
filter_relative,
show_hist_headers,
- branch_callstack;
+ branch_callstack,
+ has_filter;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
--
cgit v1.2.3
From 9c0fa8dd3d58de8b688fda758eea1719949c7f0a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 13 Jul 2015 08:26:35 -0300
Subject: perf hists browser: Take the --comm, --dsos, etc filters into account
At some point:
commit 2c86c7ca7606
Author: Namhyung Kim <namhyung@kernel.org>
Date: Mon Mar 17 18:18:54 2014 -0300
perf report: Merge al->filtered with hist_entry->filtered
We stopped dropping samples for things filtered via the --comms, --dsos,
--symbols, etc, i.e. things marked as filtered in the symbol resolution
routines (thread__find_addr_map(), perf_event__preprocess_sample(),
etc).
But then, in:
commit 268397cb2a47
Author: Namhyung Kim <namhyung@kernel.org>
Date: Tue Apr 22 14:49:31 2014 +0900
perf top/tui: Update nr_entries properly after a filter is applied
We don't take into account entries that were filtered in
perf_event__preprocess_sample() and friends, which leads to
inconsistency in the browser seek routines, that expects the number of
hist_entry->filtered entries to match what it thinks is the number of
unfiltered, browsable entries.
So, for instance, when we do:
perf top --symbols ___non_existent_symbol___
the hist_browser__nr_entries() routine thinks there are no filters in
place, uses the hists->nr_entries but all entries are filtered, leading
to a segfault.
Tested with:
perf top --symbols malloc,free --percentage=relative
Freezing, by pressing 'f', at any time and doing the math on the
percentages ends up with 100%, ditto for:
perf top --dsos libpthread-2.20.so,libxul.so --percentage=relative
Both were segfaulting, all fixed now.
More work needed to do away with checking if filters are in place, we
should just use the nr_non_filtered_samples counter, no need to
conditionally use it or hists.nr_filter, as what the browser does is
just show unfiltered stuff. An audit of how it is being accounted is
needed, this is the minimal fix.
Reported-by: Michael Petlan <mpetlan@redhat.com>
Fixes: 268397cb2a47 ("perf top/tui: Update nr_entries properly after a filter is applied")
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-6w01d5q97qk0d64kuojme5in@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/ui/browsers/hists.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'tools')
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 7629bef2fd79..fa67613976a8 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -48,7 +48,7 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
static bool hist_browser__has_filter(struct hist_browser *hb)
{
- return hists__has_filter(hb->hists) || hb->min_pcnt;
+ return hists__has_filter(hb->hists) || hb->min_pcnt || symbol_conf.has_filter;
}
static int hist_browser__get_folding(struct hist_browser *browser)
--
cgit v1.2.3
From a7fde09a78a8ae40b81cfb5096c3cefef6c078c9 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 14 Jul 2015 15:32:41 +0300
Subject: perf auxtrace: Fix misplaced check for
HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT
Move the checking for HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT for AUX area mmaps
until after checking if such mmaps are used anyway.
Reported-by: Alexey Brodkin <Alexey.Brodkin@synopsys.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Alexey Brodkin <Alexey.Brodkin@synopsys.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/55A5023C.7020907@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/auxtrace.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
(limited to 'tools')
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 7e7405c9b936..83d9dd96fe08 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -53,11 +53,6 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
{
struct perf_event_mmap_page *pc = userpg;
-#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
- pr_err("Cannot use AUX area tracing mmaps\n");
- return -1;
-#endif
-
WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
mm->userpg = userpg;
@@ -73,6 +68,11 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
return 0;
}
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ pr_err("Cannot use AUX area tracing mmaps\n");
+ return -1;
+#endif
+
pc->aux_offset = mp->offset;
pc->aux_size = mp->len;
--
cgit v1.2.3
From 3c71ba3f80bbd476bbfb2a008da9b676031cbd32 Mon Sep 17 00:00:00 2001
From: Alexey Brodkin <Alexey.Brodkin@synopsys.com>
Date: Tue, 14 Jul 2015 12:05:20 +0300
Subject: perf tools: Really allow to specify custom CC, AR or LD
Commit 5ef7bbb09f7b ("perf tools: Allow to specify custom linker
command") was meant to enable usage non $(CROSS_COMPILE)ld linker during
perf building.
But implementation didn't take into account the fact that LD is a
pre-defined variable in GNU Make. I.e. it is always defined.
Which means there's no point to check "LD ?= ..." because it will never
succeed.
And so LD will be either that explicitly passed to make like this:
------->8-------
make LD=path_to_my_ld ...
------->8-------
or default value, which is host's "ld".
Latter leads to failure of cross-linkage because instead of cross linker
"$(CROSS_COMPILE)ld" host's "ld" is used.
Fortunately there's a way to do correct substitution of $(CROSS_COMPILE)ld
with user defined LD on command-line.
As a reference was used implementation in "tools/lib/traceevent/Makefile".
Build tested for x86_64 and ARC.
Thanks Jiri for this hint.
Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
Fixes: 5ef7bbb09f7b ("perf tools: Allow to specify custom linker command")
Cc: Aaro Koskinen <aaro.koskinen@nokia.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/1436864720-26316-1-git-send-email-abrodkin@synopsys.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Makefile.perf | 19 ++++++++++++++++---
1 file changed, 16 insertions(+), 3 deletions(-)
(limited to 'tools')
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 7a4b549214e3..bba34636b733 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -109,9 +109,22 @@ $(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
$(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
$(Q)touch $(OUTPUT)PERF-VERSION-FILE
-CC = $(CROSS_COMPILE)gcc
-LD ?= $(CROSS_COMPILE)ld
-AR = $(CROSS_COMPILE)ar
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+ $(if $(or $(findstring environment,$(origin $(1))),\
+ $(findstring command line,$(origin $(1)))),,\
+ $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
+
PKG_CONFIG = $(CROSS_COMPILE)pkg-config
RM = rm -f
--
cgit v1.2.3