kernel.git/tools/perf/util, branch linux-2.6.33.y

perf tools: do not look at ./config for configuration

2011-08-29T21:32:57Z

commit aba8d056078e47350d85b06a9cabd5afcc4b72ea upstream. In addition to /etc/perfconfig and $HOME/.perfconfig, perf looks for configuration in the file ./config, imitating git which looks at $GIT_DIR/config. If ./config is not a perf configuration file, it fails, or worse, treats it as a configuration file and changes behavior in some unexpected way. "config" is not an unusual name for a file to be lying around and perf does not have a private directory dedicated for its own use, so let's just stop looking for configuration in the cwd. Callers needing context-sensitive configuration can use the PERF_CONFIG environment variable. Requested-by: Christian Ohm Cc: 632923@bugs.debian.org Cc: Ben Hutchings Cc: Christian Ohm Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20110805165838.GA7237@elie.gateway.2wire.net Signed-off-by: Jonathan Nieder Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman

perf: Resurrect flat callchains

2010-08-02T17:26:36Z

commit 97aa1052739c6a06cb6b0467dbf410613d20bc97 upstream. Initialize the callchain radix tree root correctly. When we walk through the parents, we must stop after the root, but since it wasn't well initialized, its parent pointer was random. Also the number of hits was random because uninitialized, hence it was part of the callchain while the root doesn't contain anything. This fixes segfaults and percentages followed by empty callchains while running: perf report -g flat Reported-by: Ingo Molnar Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Signed-off-by: Greg Kroah-Hartman

perf probe: Fix probe_point buffer overrun

2010-04-01T23:01:30Z

commit 594087a04eea544356f9c52e83c1a9bc380ce80f upstream. Fix probe_point array-size overrun problem. In some cases (e.g. inline function), one user-specified probe-point can be translated to many probe address, and it overruns pre-defined array-size. This also removes redundant MAX_PROBES macro definition. Signed-off-by: Masami Hiramatsu Cc: systemtap Cc: DLE LKML-Reference: <20100312232217.2017.45017.stgit@localhost6.localdomain6> [ Note that only root can create new probes. Eventually we should remove the MAX_PROBES limit, but that is a larger patch not eligible to perf/urgent treatment. ] Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman

perf annotate: Defer allocating sym_priv->hist array

2010-04-01T23:01:23Z

commit 628ada0cb03666dd463f7c25947eaccdf440c309 upstream Because symbol->end is not fixed up at symbol_filter time, only after all symbols for a DSO are loaded, and that, for asm symbols, may be bogus, causing segfaults when hits happen in these symbols. Backported-from: 628ada0 Reported-by: David Miller Reported-by: Anton Blanchard Acked-by: David Miller Cc: Frédéric Weisbecker Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras LKML-Reference: <20100225155740.GB8553@ghostprotocols.net> Signed-off-by: Ingo Molnar Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman

perf symbols: Check the right return variable

2010-03-15T16:06:12Z

commit 37fe5fcb7a5b5235c8b71bf5469ce4c7246e3fab upstream. In function dso__split_kallsyms(), curr_map saves the return value of map__new2. So check it instead of var map after the call returns. Signed-off-by: Zhang Yanmin Acked-by: David S. Miller Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: <1267066851.1726.9.camel@localhost> Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman

perf probe: Init struct probe_point and set counter correctly

2010-02-22T10:42:27Z

Clear struct probe_point before using it in show_perf_probe_events(), and set pp->found counter correctly in synthesize_perf_probe_point(). Without this initialization, clear_probe_point() will free random addresses. Signed-off-by: Masami Hiramatsu Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: systemtap Cc: DLE LKML-Reference: <20100218181652.26547.57790.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar

perf: Fix hypervisor sample reporting

2010-02-09T09:52:40Z

cpumode bits are defined as such: #define PERF_RECORD_MISC_KERNEL (1 << 0) #define PERF_RECORD_MISC_USER (2 << 0) #define PERF_RECORD_MISC_HYPERVISOR (3 << 0) We need to compare against the complete value of cpumode, otherwise hypervisor samples get incorrectly attributed as userspace. Signed-off-by: Anton Blanchard Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: fweisbec@gmail.com LKML-Reference: <20100209034304.GA3702@kryten> Signed-off-by: Ingo Molnar

perf session: Make events_stats u64 to avoid overflow on 32-bit arches

2009-12-18T15:22:52Z

Pekka Enberg reported weird percentages in perf report. It turns out we are overflowing a 32-bit variables in struct events_stats on 32-bit architectures. Before: [acme@ana linux-2.6-tip]$ perf report -i pekka.perf.data 2> /dev/null | head -10 281.96% Xorg b710a561 [.] 0x000000b710a561 140.15% Xorg [kernel] [k] __initramfs_end 51.56% metacity libgobject-2.0.so.0.2000.1 [.] 0x00000000026e46 35.12% evolution libcairo.so.2.10800.6 [.] 0x000000000203bd 33.84% metacity libpthread-2.9.so [.] 0x00000000007a3d After: [acme@ana linux-2.6-tip]$ perf report -i pekka.perf.data 2> /dev/null | head -10 30.04% Xorg b710a561 [.] 0x000000b710a561 14.93% Xorg [kernel] [k] __initramfs_end 5.49% metacity libgobject-2.0.so.0.2000.1 [.] 0x00000000026e46 3.74% evolution libcairo.so.2.10800.6 [.] 0x000000000203bd 3.61% metacity libpthread-2.9.so [.] 0x00000000007a3d Reported-by: Pekka Enberg Tested-by: Pekka Enberg Signed-off-by: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras LKML-Reference: <1261148583-20395-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar

perf probe: Check new event name

2009-12-17T08:42:44Z

Check new event name is same syntax as a C symbol in perf command. In other words, checking the name is as like as other tracepoint events. This can prevent user to create an event with useless name (e.g. foo|bar, foo*bar). Signed-off-by: Masami Hiramatsu Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Steven Rostedt Cc: Jim Keniston Cc: Ananth N Mavinakayanahalli Cc: Christoph Hellwig Cc: Jason Baron Cc: K.Prasad Cc: Peter Zijlstra Cc: Srikar Dronamraju Cc: Frederic Weisbecker Cc: systemtap Cc: DLE LKML-Reference: <20091216222415.14459.71383.stgit@dhcp-100-2-132.bos.redhat.com> [ v2: minor cleanups ] Signed-off-by: Ingo Molnar

perf probe: Fix libdwarf include path for Debian

2009-12-17T07:06:41Z

Fix libdwarf include path to fit debian-like systems too. Borislav Petkov reported: > even after installing libdwarf-dev on my debian box here, > make in tools/perf/ still complains that it cannot find libdwarf: > > Makefile:491: No libdwarf.h found or old libdwarf.h found, disables dwarf > support. Please install libdwarf-dev/libdwarf-devel >= 20081231 > > The problem is that the include path on debian is not > /usr/include/libdwarf/ but simply /usr/include because the debian > package libdwarf-dev puts the headers straight into > /usr/include. This patch adds -I/usr/include/libdwarf to BASIC_CFLAGS and fix probe-finder.h to include just libdwarf.h/dwarf.h. This patch also adds a workaround for the undefined _MIPS_SZLONG bug in libdwarf.h. Reported-by: Borislav Petkov Signed-off-by: Masami Hiramatsu Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Cc: Srikar Dronamraju Cc: Gabor Gombas Cc: systemtap Cc: DLE LKML-Reference: <20091216221618.13816.83296.stgit@dhcp-100-2-132.bos.redhat.com> [ v2: small stylistic fixlets to probe-finder.h ] Signed-off-by: Ingo Molnar