| Message ID | 1396965637-4802-2-git-send-email-fathi.boudra@linaro.org |
|---|---|
| State | New |
| Headers | show |
On Tue, Apr 8, 2014 at 7:00 AM, Fathi Boudra <fathi.boudra@linaro.org> wrote: > do_install() { > - oe_runmake prefix="${prefix}" DESTDIR="${D}" install > + ${MAKE} NO_PYTHON=1 prefix=${prefix} plugin_dir=${libdir}/trace-cmd/plugins DESTDIR=${D} install > } can you explain/document this change
On 8 April 2014 20:05, Khem Raj <raj.khem@gmail.com> wrote: > On Tue, Apr 8, 2014 at 7:00 AM, Fathi Boudra <fathi.boudra@linaro.org> wrote: >> do_install() { >> - oe_runmake prefix="${prefix}" DESTDIR="${D}" install >> + ${MAKE} NO_PYTHON=1 prefix=${prefix} plugin_dir=${libdir}/trace-cmd/plugins DESTDIR=${D} install >> } > > can you explain/document this change sure. trace-cmd doesn't have a build system generated Makefile. It's hand written. To do the install properly, one has to pass prefix/plugin_dir. In addition, the previous command in the recipe doesn't do the right thing anymore (you'll end with duplicated prefix /usr/usr/). I've included NO_PYTHON since the build system is still broken for cross-compilation in some way. I found it acceptable because the old version available in oe doesn't have this support anyway. In short, I took some shortcut. The right thing to do is to revisit upstream build system and fix it. Time that I can't afford right now.
On Tue, Apr 8, 2014 at 10:16 AM, Fathi Boudra <fathi.boudra@linaro.org>wrote: > On 8 April 2014 20:05, Khem Raj <raj.khem@gmail.com> wrote: > > On Tue, Apr 8, 2014 at 7:00 AM, Fathi Boudra <fathi.boudra@linaro.org> > wrote: > >> do_install() { > >> - oe_runmake prefix="${prefix}" DESTDIR="${D}" install > >> + ${MAKE} NO_PYTHON=1 prefix=${prefix} > plugin_dir=${libdir}/trace-cmd/plugins DESTDIR=${D} install > >> } > > > > can you explain/document this change > > sure. trace-cmd doesn't have a build system generated Makefile. It's > hand written. > To do the install properly, one has to pass prefix/plugin_dir. > In addition, the previous command in the recipe doesn't do the right > thing anymore (you'll end with duplicated prefix /usr/usr/). You don't need to avoid the use of oe_runmake to pass variables in, that's what EXTRA_OEMAKE is for :) See https://github.com/MentorEmbedded/meta-mentor/commit/4639877 for a version of this fix that uses it instead.
On 9 April 2014 18:02, Chris Larson <clarson@kergoth.com> wrote: > > On Tue, Apr 8, 2014 at 10:16 AM, Fathi Boudra <fathi.boudra@linaro.org> > wrote: >> >> On 8 April 2014 20:05, Khem Raj <raj.khem@gmail.com> wrote: >> > On Tue, Apr 8, 2014 at 7:00 AM, Fathi Boudra <fathi.boudra@linaro.org> >> > wrote: >> >> do_install() { >> >> - oe_runmake prefix="${prefix}" DESTDIR="${D}" install >> >> + ${MAKE} NO_PYTHON=1 prefix=${prefix} >> >> plugin_dir=${libdir}/trace-cmd/plugins DESTDIR=${D} install >> >> } >> > >> > can you explain/document this change >> >> sure. trace-cmd doesn't have a build system generated Makefile. It's >> hand written. >> To do the install properly, one has to pass prefix/plugin_dir. >> In addition, the previous command in the recipe doesn't do the right >> thing anymore (you'll end with duplicated prefix /usr/usr/). > > > You don't need to avoid the use of oe_runmake to pass variables in, that's > what EXTRA_OEMAKE is for :) See > https://github.com/MentorEmbedded/meta-mentor/commit/4639877 for a version > of this fix that uses it instead. You don't need oe_runmake or EXTRA_OEMAKE to properly build and install the files in the right path either :) You can even drop inherit pkgconfig pythonnative since they aren't used. My version is also slightly shorter to achieve the same goal. All in all, I don't mind which version is taken as long as we update the one in oe-core. Cheers, Fathi
On Wed, Apr 9, 2014 at 9:18 AM, Fathi Boudra <fathi.boudra@linaro.org>wrote: > On 9 April 2014 18:02, Chris Larson <clarson@kergoth.com> wrote: > > > > On Tue, Apr 8, 2014 at 10:16 AM, Fathi Boudra <fathi.boudra@linaro.org> > > wrote: > >> > >> On 8 April 2014 20:05, Khem Raj <raj.khem@gmail.com> wrote: > >> > On Tue, Apr 8, 2014 at 7:00 AM, Fathi Boudra <fathi.boudra@linaro.org > > > >> > wrote: > >> >> do_install() { > >> >> - oe_runmake prefix="${prefix}" DESTDIR="${D}" install > >> >> + ${MAKE} NO_PYTHON=1 prefix=${prefix} > >> >> plugin_dir=${libdir}/trace-cmd/plugins DESTDIR=${D} install > >> >> } > >> > > >> > can you explain/document this change > >> > >> sure. trace-cmd doesn't have a build system generated Makefile. It's > >> hand written. > >> To do the install properly, one has to pass prefix/plugin_dir. > >> In addition, the previous command in the recipe doesn't do the right > >> thing anymore (you'll end with duplicated prefix /usr/usr/). > > > > > > You don't need to avoid the use of oe_runmake to pass variables in, > that's > > what EXTRA_OEMAKE is for :) See > > https://github.com/MentorEmbedded/meta-mentor/commit/4639877 for a > version > > of this fix that uses it instead. > > You don't need oe_runmake or EXTRA_OEMAKE to properly build and > install the files in the right path either :) > You can even drop inherit pkgconfig pythonnative since they aren't > used. My version is also slightly shorter to achieve the same goal. > oe_runmake is the convention used by nearly every recipe in oe-core. Breaking that convention for no good reason accomplishes nothing.
On 9 April 2014 22:15, Chris Larson <clarson@kergoth.com> wrote: > > On Wed, Apr 9, 2014 at 9:18 AM, Fathi Boudra <fathi.boudra@linaro.org> > wrote: >> >> On 9 April 2014 18:02, Chris Larson <clarson@kergoth.com> wrote: >> > >> > On Tue, Apr 8, 2014 at 10:16 AM, Fathi Boudra <fathi.boudra@linaro.org> >> > wrote: >> >> >> >> On 8 April 2014 20:05, Khem Raj <raj.khem@gmail.com> wrote: >> >> > On Tue, Apr 8, 2014 at 7:00 AM, Fathi Boudra >> >> > <fathi.boudra@linaro.org> >> >> > wrote: >> >> >> do_install() { >> >> >> - oe_runmake prefix="${prefix}" DESTDIR="${D}" install >> >> >> + ${MAKE} NO_PYTHON=1 prefix=${prefix} >> >> >> plugin_dir=${libdir}/trace-cmd/plugins DESTDIR=${D} install >> >> >> } >> >> > >> >> > can you explain/document this change >> >> >> >> sure. trace-cmd doesn't have a build system generated Makefile. It's >> >> hand written. >> >> To do the install properly, one has to pass prefix/plugin_dir. >> >> In addition, the previous command in the recipe doesn't do the right >> >> thing anymore (you'll end with duplicated prefix /usr/usr/). >> > >> > >> > You don't need to avoid the use of oe_runmake to pass variables in, >> > that's >> > what EXTRA_OEMAKE is for :) See >> > https://github.com/MentorEmbedded/meta-mentor/commit/4639877 for a >> > version >> > of this fix that uses it instead. >> >> You don't need oe_runmake or EXTRA_OEMAKE to properly build and >> install the files in the right path either :) >> You can even drop inherit pkgconfig pythonnative since they aren't >> used. My version is also slightly shorter to achieve the same goal. > > > oe_runmake is the convention used by nearly every recipe in oe-core. > Breaking that convention for no good reason accomplishes nothing. you can argue as you prefer. reality is that using oe_runmake on this particular software accomplishes nothing. my 2cts.
Hi,
Does anyone know if OE supports qtwebsockets?
Thanks,
Sanjay Dorairaj
Comcast Silicon Valley Innovation Center
1050 Enterprise Way, Suite 100
Sunnyvale, CA 94089
Desk: (408)900-8737 Cell:(215)900-2349
Skype: dorairajsanjay
>
On Wednesday 09 April 2014 22:25:31 Fathi Boudra wrote: > On 9 April 2014 22:15, Chris Larson <clarson@kergoth.com> wrote: > > On Wed, Apr 9, 2014 at 9:18 AM, Fathi Boudra <fathi.boudra@linaro.org> > > > > wrote: > >> On 9 April 2014 18:02, Chris Larson <clarson@kergoth.com> wrote: > >> > On Tue, Apr 8, 2014 at 10:16 AM, Fathi Boudra <fathi.boudra@linaro.org> > >> > > >> > wrote: > >> >> On 8 April 2014 20:05, Khem Raj <raj.khem@gmail.com> wrote: > >> >> > On Tue, Apr 8, 2014 at 7:00 AM, Fathi Boudra > >> >> > <fathi.boudra@linaro.org> > >> >> > > >> >> > wrote: > >> >> >> do_install() { > >> >> >> > >> >> >> - oe_runmake prefix="${prefix}" DESTDIR="${D}" install > >> >> >> + ${MAKE} NO_PYTHON=1 prefix=${prefix} > >> >> >> plugin_dir=${libdir}/trace-cmd/plugins DESTDIR=${D} install > >> >> >> > >> >> >> } > >> >> > > >> >> > can you explain/document this change > >> >> > >> >> sure. trace-cmd doesn't have a build system generated Makefile. It's > >> >> hand written. > >> >> To do the install properly, one has to pass prefix/plugin_dir. > >> >> In addition, the previous command in the recipe doesn't do the right > >> >> thing anymore (you'll end with duplicated prefix /usr/usr/). > >> > > >> > You don't need to avoid the use of oe_runmake to pass variables in, > >> > that's > >> > what EXTRA_OEMAKE is for :) See > >> > https://github.com/MentorEmbedded/meta-mentor/commit/4639877 for a > >> > version > >> > of this fix that uses it instead. > >> > >> You don't need oe_runmake or EXTRA_OEMAKE to properly build and > >> install the files in the right path either :) > >> You can even drop inherit pkgconfig pythonnative since they aren't > >> used. My version is also slightly shorter to achieve the same goal. > > > > oe_runmake is the convention used by nearly every recipe in oe-core. > > Breaking that convention for no good reason accomplishes nothing. > > you can argue as you prefer. reality is that using oe_runmake on this > particular software accomplishes nothing. It accomplishes as much as it does anywhere else. I don't see that this recipe needs to be special by not using it. In any case, you've run the recipe through oe-stylize to make it conform to OE style guidelines that that script handles, surely it's not a big thing to conform to this expected style as well? Cheers, Paul
On 15 April 2014 20:04, Paul Eggleton <paul.eggleton@linux.intel.com> wrote: > On Wednesday 09 April 2014 22:25:31 Fathi Boudra wrote: >> On 9 April 2014 22:15, Chris Larson <clarson@kergoth.com> wrote: >> > On Wed, Apr 9, 2014 at 9:18 AM, Fathi Boudra <fathi.boudra@linaro.org> >> > >> > wrote: >> >> On 9 April 2014 18:02, Chris Larson <clarson@kergoth.com> wrote: >> >> > On Tue, Apr 8, 2014 at 10:16 AM, Fathi Boudra <fathi.boudra@linaro.org> >> >> > >> >> > wrote: >> >> >> On 8 April 2014 20:05, Khem Raj <raj.khem@gmail.com> wrote: >> >> >> > On Tue, Apr 8, 2014 at 7:00 AM, Fathi Boudra >> >> >> > <fathi.boudra@linaro.org> >> >> >> > >> >> >> > wrote: >> >> >> >> do_install() { >> >> >> >> >> >> >> >> - oe_runmake prefix="${prefix}" DESTDIR="${D}" install >> >> >> >> + ${MAKE} NO_PYTHON=1 prefix=${prefix} >> >> >> >> plugin_dir=${libdir}/trace-cmd/plugins DESTDIR=${D} install >> >> >> >> >> >> >> >> } >> >> >> > >> >> >> > can you explain/document this change >> >> >> >> >> >> sure. trace-cmd doesn't have a build system generated Makefile. It's >> >> >> hand written. >> >> >> To do the install properly, one has to pass prefix/plugin_dir. >> >> >> In addition, the previous command in the recipe doesn't do the right >> >> >> thing anymore (you'll end with duplicated prefix /usr/usr/). >> >> > >> >> > You don't need to avoid the use of oe_runmake to pass variables in, >> >> > that's >> >> > what EXTRA_OEMAKE is for :) See >> >> > https://github.com/MentorEmbedded/meta-mentor/commit/4639877 for a >> >> > version >> >> > of this fix that uses it instead. >> >> >> >> You don't need oe_runmake or EXTRA_OEMAKE to properly build and >> >> install the files in the right path either :) >> >> You can even drop inherit pkgconfig pythonnative since they aren't >> >> used. My version is also slightly shorter to achieve the same goal. >> > >> > oe_runmake is the convention used by nearly every recipe in oe-core. >> > Breaking that convention for no good reason accomplishes nothing. >> >> you can argue as you prefer. reality is that using oe_runmake on this >> particular software accomplishes nothing. > > It accomplishes as much as it does anywhere else. I don't see that this recipe > needs to be special by not using it. In any case, you've run the recipe > through oe-stylize to make it conform to OE style guidelines that that script > handles, surely it's not a big thing to conform to this expected style as > well? In that case, you might be able to replace ${MAKE} by oe_runmake in the patchset and everybody will be happy. > Cheers, > Paul > > -- > > Paul Eggleton > Intel Open Source Technology Centre
diff --git a/meta/recipes-kernel/trace-cmd/kernelshark_1.2.bb b/meta/recipes-kernel/trace-cmd/kernelshark_2.3.2.bb similarity index 48% rename from meta/recipes-kernel/trace-cmd/kernelshark_1.2.bb rename to meta/recipes-kernel/trace-cmd/kernelshark_2.3.2.bb index 9268a50..f455707 100644 --- a/meta/recipes-kernel/trace-cmd/kernelshark_1.2.bb +++ b/meta/recipes-kernel/trace-cmd/kernelshark_2.3.2.bb @@ -3,27 +3,22 @@ LICENSE = "GPLv2" LIC_FILES_CHKSUM = "file://COPYING;md5=751419260aa954499f7abaabaa882bbe \ file://kernel-shark.c;beginline=6;endline=8;md5=2c22c965a649ddd7973d7913c5634a5e" -SRCREV = "7055ffd37beeb44714e86a4abc703f7e175a0db5" -PR = "r3" -PV = "1.2+git${SRCPV}" +SRCREV = "79e08f8edb38c4c5098486caaa87ca90ba00f547" +PV = "2.3.2" DEPENDS = "gtk+" RDEPENDS_${PN} = "trace-cmd" -inherit pkgconfig pythonnative - -SRC_URI = "git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git \ - file://addldflags.patch \ - file://make-docs-optional.patch \ - file://blktrace-api-compatibility.patch" +SRC_URI = "git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git;branch=trace-cmd-stable-v2.3" S = "${WORKDIR}/git" -EXTRA_OEMAKE = "'CC=${CC}' 'AR=${AR}' 'prefix=${prefix}' gui" - FILESPATH = "${FILE_DIRNAME}/trace-cmd" do_install() { - oe_runmake CC="${CC}" AR="${AR}" prefix="${prefix}" DESTDIR="${D}" install_gui - rm -rf ${D}${datadir}/trace-cmd - rmdir ${D}${datadir} + ${MAKE} NO_PYTHON=1 prefix=${prefix} plugin_dir=${libdir}/trace-cmd/plugins DESTDIR=${D} install_gui + + # remove files already shipped in trace-cmd package + rm -f ${D}${bindir}/trace-cmd + rm -rf ${D}${libdir}/trace-cmd + rmdir ${D}${libdir} } diff --git a/meta/recipes-kernel/trace-cmd/trace-cmd/addldflags.patch b/meta/recipes-kernel/trace-cmd/trace-cmd/addldflags.patch deleted file mode 100644 index 14730db..0000000 --- a/meta/recipes-kernel/trace-cmd/trace-cmd/addldflags.patch +++ /dev/null @@ -1,51 +0,0 @@ -trace-cmd: Cross-compile fixes for LDFLAGS and include path - -Add ability for the Makefile to respect LDFLAGS. -Also remove hardcoded /usr/local/include include path. - -Upstream-Status: Accepted [Post 1.2: 5f576e9af7ad706774d9764a9ae3989376797c0e] - -Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org> -Signed-off-by: Darren Hart <dvhart@linux.intel.com> - ---- - Makefile | 7 ++++--- - 1 file changed, 4 insertions(+), 3 deletions(-) - -Index: git/Makefile -=================================================================== ---- git.orig/Makefile -+++ git/Makefile -@@ -202,12 +202,13 @@ export Q VERBOSE - TRACECMD_VERSION = $(TC_VERSION).$(TC_PATCHLEVEL).$(TC_EXTRAVERSION) - KERNELSHARK_VERSION = $(KS_VERSION).$(KS_PATCHLEVEL).$(KS_EXTRAVERSION) - --INCLUDES = -I. -I/usr/local/include $(CONFIG_INCLUDES) -+INCLUDES = -I. $(CONFIG_INCLUDES) - - include features.mk - - # Set compile option CFLAGS if not set elsewhere - CFLAGS ?= -g -Wall -+LDFLAGS ?= - - ifndef NO_PTRACE - ifneq ($(call try-cc,$(SOURCE_PTRACE),),y) -@@ -251,7 +252,7 @@ do_fpic_compile = \ - - do_app_build = \ - ($(print_app_build) \ -- $(CC) $^ -rdynamic -o $@ $(CONFIG_LIBS) $(LIBS)) -+ $(CC) $^ -rdynamic -o $@ $(LDFLAGS) $(CONFIG_LIBS) $(LIBS)) - - do_compile_shared_library = \ - ($(print_shared_lib_compile) \ -@@ -263,7 +264,7 @@ do_compile_plugin_obj = \ - - do_plugin_build = \ - ($(print_plugin_build) \ -- $(CC) $(CFLAGS) -shared -nostartfiles -o $@ $<) -+ $(CC) $(CFLAGS) $(LDFLAGS) -shared -nostartfiles -o $@ $<) - - do_build_static_lib = \ - ($(print_static_lib_build) \ diff --git a/meta/recipes-kernel/trace-cmd/trace-cmd/blktrace-api-compatibility.patch b/meta/recipes-kernel/trace-cmd/trace-cmd/blktrace-api-compatibility.patch deleted file mode 100644 index 0789e9f..0000000 --- a/meta/recipes-kernel/trace-cmd/trace-cmd/blktrace-api-compatibility.patch +++ /dev/null @@ -1,29 +0,0 @@ -trace-cmd: Add blktrace_api compatibility for TC_BARRIER - -Newer kernels replace TC_BARRIER with TC_FLUSH. Ensure trace-cmd -can build regardless of the linux-kernel-headers version. - -Upstream-Status: Innapropriate [Stop gap] - -Signed-off-by: Darren Hart <dvhart@linux.intel.com> - -diff --git a/plugin_blk.c b/plugin_blk.c -index 9327b17..c8e5e1c 100644 ---- a/plugin_blk.c -+++ b/plugin_blk.c -@@ -44,6 +44,15 @@ struct blk_data { - unsigned short pdu_len; - }; - -+/* -+ * Newer kernels don't define BLK_TC_BARRIER and have replaced it with -+ * BLK_TC_FLUSH. In this case, define it here and report FLUSHES as BARRIERS as -+ * a workaround, as described in: -+ * http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=commit;h=c09c47caedc9854d59378d6e34c989e51cfdd2b4 -+ */ -+#ifndef BLK_TC_BARRIER -+#define BLK_TC_BARRIER 1<<2 -+#endif - static void fill_rwbs(char *rwbs, int action, unsigned int bytes) - { - int i = 0; diff --git a/meta/recipes-kernel/trace-cmd/trace-cmd/make-docs-optional.patch b/meta/recipes-kernel/trace-cmd/trace-cmd/make-docs-optional.patch deleted file mode 100644 index 8402426..0000000 --- a/meta/recipes-kernel/trace-cmd/trace-cmd/make-docs-optional.patch +++ /dev/null @@ -1,36 +0,0 @@ -Disable building docs until we have asciidocs available as a recipe. - -Upstream-Status: Inappropriate [Account for missing dependency, the lazy way] - -Signed-off-by: Darren Hart <dvhart@linux.intel.com> - ---- - Makefile | 8 ++++++-- - 1 file changed, 6 insertions(+), 2 deletions(-) - -Index: git/Makefile -=================================================================== ---- git.orig/Makefile -+++ git/Makefile -@@ -327,7 +327,9 @@ TARGETS = $(CMD_TARGETS) $(GUI_TARGETS) - # If you want kernelshark, then do: make gui - ### - --all: all_cmd doc show_gui_make -+# Make doc optional -+#all: all_cmd doc show_gui_make -+all: all_cmd show_gui_make - - all_cmd: $(CMD_TARGETS) - -@@ -503,7 +505,9 @@ install_python: $(PYTHON_SO_INSTALL) $(P - install_cmd: all_cmd install_plugins install_python - $(Q)$(call do_install,trace-cmd,$(bindir_SQ)) - --install: install_cmd install_doc -+# Make doc optional -+#install: install_cmd install_doc -+install: install_cmd - @echo "Note: to install the gui, type \"make install_gui\"" - - install_gui: install_cmd gui diff --git a/meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Add-checks-for-invalid-pointers-to-fix-seg.patch b/meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Add-checks-for-invalid-pointers-to-fix-seg.patch deleted file mode 100644 index 8fdeedb..0000000 --- a/meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Add-checks-for-invalid-pointers-to-fix-seg.patch +++ /dev/null @@ -1,61 +0,0 @@ -From a6e259b2cd43db3c0f69441f627a8cf214f88506 Mon Sep 17 00:00:00 2001 -From: Mark Asselstine <mark.asselstine@windriver.com> -Date: Thu, 5 Apr 2012 15:19:44 -0400 -Subject: [PATCH] trace-cmd: Add checks for invalid pointers to fix segfaults - -Upstream-Status: Backport - -Running 'trace-cmd report' after running latency tracers will cause a -segfault due to invalid pointers. Adding checks to ensure -pointers/lists are initialized before attempting to use them prevents -these segfaults. - -Link: http://lkml.kernel.org/r/1333653586-3379-2-git-send-email-mark.asselstine@windriver.com - -Signed-off-by: Mark Asselstine <mark.asselstine@windriver.com> -Signed-off-by: Steven Rostedt <rostedt@goodmis.org> ---- - trace-input.c | 12 +++++++++--- - 1 file changed, 9 insertions(+), 3 deletions(-) - -diff --git a/trace-input.c b/trace-input.c -index b6af1e6..5151c1e 100644 ---- a/trace-input.c -+++ b/trace-input.c -@@ -695,7 +695,8 @@ static void __free_page(struct tracecmd_input *handle, struct page *page) - - static void free_page(struct tracecmd_input *handle, int cpu) - { -- if (!handle->cpu_data[cpu].page) -+ if (!handle->cpu_data || cpu >= handle->cpus || -+ !handle->cpu_data[cpu].page) - return; - - __free_page(handle, handle->cpu_data[cpu].page); -@@ -746,8 +747,12 @@ void tracecmd_record_ref(struct record *record) - - static void free_next(struct tracecmd_input *handle, int cpu) - { -- struct record *record = handle->cpu_data[cpu].next; -+ struct record *record; -+ -+ if (!handle->cpu_data || cpu >= handle->cpus) -+ return; - -+ record = handle->cpu_data[cpu].next; - if (!record) - return; - -@@ -2337,7 +2342,8 @@ void tracecmd_close(struct tracecmd_input *handle) - /* The tracecmd_peek_data may have cached a record */ - free_next(handle, cpu); - free_page(handle, cpu); -- if (!list_empty(&handle->cpu_data[cpu].pages)) -+ if (handle->cpu_data && -+ !list_empty(&handle->cpu_data[cpu].pages)) - warning("pages still allocated on cpu %d%s", - cpu, show_records(&handle->cpu_data[cpu].pages)); - } --- -1.7.10.4 - diff --git a/meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Do-not-call-stop_threads-if-doing-latency-.patch b/meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Do-not-call-stop_threads-if-doing-latency-.patch deleted file mode 100644 index 4c00c51..0000000 --- a/meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Do-not-call-stop_threads-if-doing-latency-.patch +++ /dev/null @@ -1,38 +0,0 @@ -From 356dee73d9ced3e019dea2883a7f357fd4664b3e Mon Sep 17 00:00:00 2001 -From: Mark Asselstine <mark.asselstine@windriver.com> -Date: Thu, 5 Apr 2012 15:19:45 -0400 -Subject: [PATCH] trace-cmd: Do not call stop_threads() if doing latency - tracing - -Upstream-Status: Backport - -If we are using a latency tracer we do not call start_threads() we -should therefore not call stop_threads() if 'latency'. Attempting -to call stop_threads() without first calling start_threads() will -cause a segfault since pids will be uninitialized. - -Link: http://lkml.kernel.org/r/1333653586-3379-3-git-send-email-mark.asselstine@windriver.com - -Signed-off-by: Mark Asselstine <mark.asselstine@windriver.com> -Signed-off-by: Steven Rostedt <rostedt@goodmis.org> ---- - trace-record.c | 3 ++- - 1 file changed, 2 insertions(+), 1 deletion(-) - -diff --git a/trace-record.c b/trace-record.c -index fcec28b..1c56fa9 100644 ---- a/trace-record.c -+++ b/trace-record.c -@@ -2216,7 +2216,8 @@ void trace_record (int argc, char **argv) - } - - disable_tracing(); -- stop_threads(); -+ if (!latency) -+ stop_threads(); - } - - for (cpu = 0; cpu < cpu_count; cpu++) { --- -1.7.10.4 - diff --git a/meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Setting-plugin-to-nop-clears-data-before-i.patch b/meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Setting-plugin-to-nop-clears-data-before-i.patch deleted file mode 100644 index 724e1e8..0000000 --- a/meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Setting-plugin-to-nop-clears-data-before-i.patch +++ /dev/null @@ -1,96 +0,0 @@ -From d65740d61e7a4ea6d8d77237954b33dd18e3276c Mon Sep 17 00:00:00 2001 -From: Mark Asselstine <mark.asselstine@windriver.com> -Date: Sun, 8 Apr 2012 11:38:45 -0400 -Subject: [PATCH] trace-cmd: Setting plugin to 'nop' clears data before it's - recorded - -Upstream-Status: Backport - -commit e09a5db1a929ab668c273b87c4f0a32b81e1c21a -[trace-cmd: Add trace-cmd record --date option] - -moved the call to disable_all() in trace_record() from after record_data() -to before it. Unfortunately disable_all() sets 'nop' in 'current_tracer' -which has the side affect of clearing 'trace', thus all the latency tracer -reports are empty/useless. Here we make disable_all() optionally call -set_plugin() thus, where we need to, we can delay the disabling of the tracer -until we have had a chance to capture 'trace'. We have added this delayed -behavior to trace_record() to fix the latency reports, for all other calls to -disable_all() we continue to have set_plugin() called. - -Link: http://lkml.kernel.org/r/1333899525-6436-1-git-send-email-mark.asselstine@windriver.com - -Signed-off-by: Mark Asselstine <mark.asselstine@windriver.com> -Signed-off-by: Steven Rostedt <rostedt@goodmis.org> ---- - trace-record.c | 16 ++++++++++------ - 1 file changed, 10 insertions(+), 6 deletions(-) - -diff --git a/trace-record.c b/trace-record.c -index 1c56fa9..95d4a2a 100644 ---- a/trace-record.c -+++ b/trace-record.c -@@ -897,11 +897,13 @@ static void disable_tracing(void) - write_tracing_on(0); - } - --static void disable_all(void) -+static void disable_all(int disable_tracer) - { - disable_tracing(); - -- set_plugin("nop"); -+ if (disable_tracer) -+ set_plugin("nop"); -+ - reset_events(); - - /* Force close and reset of ftrace pid file */ -@@ -1573,7 +1575,7 @@ static void set_funcs(void) - /* make sure we are filtering functions */ - if (func_stack) { - if (!functions_filtered()) { -- disable_all(); -+ disable_all(1); - die("Function stack trace set, but functions not filtered"); - } - save_option(FUNC_STACK_TRACE); -@@ -1938,7 +1940,7 @@ void trace_record (int argc, char **argv) - break; - } - } -- disable_all(); -+ disable_all(1); - set_buffer_size(); - exit(0); - } else -@@ -2147,7 +2149,7 @@ void trace_record (int argc, char **argv) - - if (!extract) { - fset = set_ftrace(!disable); -- disable_all(); -+ disable_all(1); - - /* Record records the date first */ - if (record && date) -@@ -2227,7 +2229,7 @@ void trace_record (int argc, char **argv) - } - - if (!keep) -- disable_all(); -+ disable_all(0); - - printf("Kernel buffer statistics:\n" - " Note: \"entries\" are the entries left in the kernel ring buffer and are not\n" -@@ -2249,6 +2251,8 @@ void trace_record (int argc, char **argv) - if (keep) - exit(0); - -+ set_plugin("nop"); -+ - /* If tracing_on was enabled before we started, set it on now */ - if (tracing_on_init_val) - write_tracing_on(tracing_on_init_val); --- -1.7.10.4 - diff --git a/meta/recipes-kernel/trace-cmd/trace-cmd_1.2.bb b/meta/recipes-kernel/trace-cmd/trace-cmd_2.3.2.bb similarity index 41% rename from meta/recipes-kernel/trace-cmd/trace-cmd_1.2.bb rename to meta/recipes-kernel/trace-cmd/trace-cmd_2.3.2.bb index 74eafbb..eed1010 100644 --- a/meta/recipes-kernel/trace-cmd/trace-cmd_1.2.bb +++ b/meta/recipes-kernel/trace-cmd/trace-cmd_2.3.2.bb @@ -3,28 +3,16 @@ LICENSE = "GPLv2 & LGPLv2.1" LIC_FILES_CHKSUM = "file://COPYING;md5=751419260aa954499f7abaabaa882bbe \ file://trace-cmd.c;beginline=6;endline=8;md5=2c22c965a649ddd7973d7913c5634a5e \ file://COPYING.LIB;md5=bbb461211a33b134d42ed5ee802b37ff \ - file://trace-input.c;beginline=5;endine=8;md5=6ad47cc2b03385d8456771eec5eeea0b" + file://trace-input.c;beginline=5;endine=8;md5=dafd8a1cade30b847a8686dd3628cea4" -SRCREV = "7055ffd37beeb44714e86a4abc703f7e175a0db5" -PR = "r3" -PV = "1.2+git${SRCPV}" +SRCREV = "79e08f8edb38c4c5098486caaa87ca90ba00f547" +PV = "2.3.2" -inherit pkgconfig pythonnative - -SRC_URI = "git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git \ - file://addldflags.patch \ - file://make-docs-optional.patch \ - file://blktrace-api-compatibility.patch \ - file://trace-cmd-Add-checks-for-invalid-pointers-to-fix-seg.patch \ - file://trace-cmd-Do-not-call-stop_threads-if-doing-latency-.patch \ - file://trace-cmd-Setting-plugin-to-nop-clears-data-before-i.patch \ -" +SRC_URI = "git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git;branch=trace-cmd-stable-v2.3" S = "${WORKDIR}/git" -EXTRA_OEMAKE = "'prefix=${prefix}'" - -FILES_${PN}-dbg += "${datadir}/trace-cmd/plugins/.debug/" +FILES_${PN}-dbg += "${libdir}/trace-cmd/plugins/.debug/" do_install() { - oe_runmake prefix="${prefix}" DESTDIR="${D}" install + ${MAKE} NO_PYTHON=1 prefix=${prefix} plugin_dir=${libdir}/trace-cmd/plugins DESTDIR=${D} install }
* drop all the patches - not needed anymore - addldflags.patch - fixed upstream in some other way - blktrace-api-compatibility.patch - backport - make-docs-optional.patch- useless since upstream has now an explicit build targets for the docs (doc/install_doc) - trace-cmd-Add-checks-for-invalid-pointers-to-fix-seg.patch - backport - trace-cmd-Do-not-call-stop_threads-if-doing-latency-.patch - backport - trace-cmd-Setting-plugin-to-nop-clears-data-before-i.patch - backport * update SRCREV and PV to 2.3.2 tag * drop PR * update SRC_URI to use trace-cmd-stable-v2.3 branch * drop EXTRA_OEMAKE - not needed * update do_install and pass NO_PYTHON/prefix/plugin_dir * update trace-input.c md5 sum - FSF address has been updated Signed-off-by: Fathi Boudra <fathi.boudra@linaro.org> --- .../{kernelshark_1.2.bb => kernelshark_2.3.2.bb} | 23 ++---- .../trace-cmd/trace-cmd/addldflags.patch | 51 ------------ .../trace-cmd/blktrace-api-compatibility.patch | 29 ------- .../trace-cmd/trace-cmd/make-docs-optional.patch | 36 -------- ...dd-checks-for-invalid-pointers-to-fix-seg.patch | 61 -------------- ...o-not-call-stop_threads-if-doing-latency-.patch | 38 --------- ...etting-plugin-to-nop-clears-data-before-i.patch | 96 ---------------------- .../{trace-cmd_1.2.bb => trace-cmd_2.3.2.bb} | 24 ++---- 8 files changed, 15 insertions(+), 343 deletions(-) rename meta/recipes-kernel/trace-cmd/{kernelshark_1.2.bb => kernelshark_2.3.2.bb} (48%) delete mode 100644 meta/recipes-kernel/trace-cmd/trace-cmd/addldflags.patch delete mode 100644 meta/recipes-kernel/trace-cmd/trace-cmd/blktrace-api-compatibility.patch delete mode 100644 meta/recipes-kernel/trace-cmd/trace-cmd/make-docs-optional.patch delete mode 100644 meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Add-checks-for-invalid-pointers-to-fix-seg.patch delete mode 100644 meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Do-not-call-stop_threads-if-doing-latency-.patch delete mode 100644 meta/recipes-kernel/trace-cmd/trace-cmd/trace-cmd-Setting-plugin-to-nop-clears-data-before-i.patch rename meta/recipes-kernel/trace-cmd/{trace-cmd_1.2.bb => trace-cmd_2.3.2.bb} (41%)