linux/tools, branch v2.6.39-rc2

perf: mmap 512 kiB by default

2011-03-31T11:02:55Z

The default setting of perf record is to mmap 128 pages if the user did not override with -m. However the page size may vary accross different architecture settings, giving different default size between each. Moreover the kernel side still has a default max number of mlocked pages of 512 kiB + 1 page for unprivileged users. 128 + 1 pages with page size > 4096 overlaps this threshold. Thus, better adapt to this limitation and set the default number of pages to fit those 512 kiB + 1 page. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Stephane Eranian LKML-Reference: <1301535324-9735-1-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar

Merge commits 'ca6a42586fae' and 'c286c419c784' into perf/urgent

2011-03-30T07:08:39Z

Pick up these two commits from Arnaldo's perf/core tree: ca6a42586fae: perf tools: Emit clearer message for sys_perf_event_open ENOENT return c286c419c784: perf tools: Fixup exit path when not able to open events As they are really fixes we want to have sooner than laer. Signed-off-by: Ingo Molnar

perf tools: Fix NO_NEWT=1 python build error

2011-03-29T19:46:57Z

Fix the following build error: GEN python/perf.so In file included from util/evsel.h:10, from util/python.c:6: util/hist.h:106:18: error: newt.h: No such file or directory error: command 'x86_64-pc-linux-gnu-gcc' failed with exit status 1 make: *** [python/perf.so] Error 1 by passing BASIC_CFLAGS to setup.py. BASIC_CFLAGS variable contains the -DNO_NEWT_SUPPORT switch which prevents building python c extension with newt. Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Stephane Eranian LKML-Reference: <20110329180236.GA19366@erda.amd.com> Signed-off-by: Robert Richter Signed-off-by: Arnaldo Carvalho de Melo

perf symbols: Properly align symbol_conf.priv_size

2011-03-29T17:18:39Z

If symbol_conf.priv_size is not a multiple of "sizeof(u64)" we'll bus error on sparc64 in symbol__new because the "struct symbol *" pointer is computed by adding symbol_conf.priv_size to the memory allocated. We cannot isolate the fix to symbol__new and symbol__delete since the private area is computed by subtracting the priv_size value from a "struct symbol" pointer, so then the private area can still be potentially unaligned. So, simply align the symbol_conf.priv_size value in symbol__init() Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra LKML-Reference: <20110328.175849.112593455.davem@davemloft.net> Signed-off-by: David S. Miller Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Emit clearer message for sys_perf_event_open ENOENT return

2011-03-29T16:40:27Z

Resend of patch sent back in January 2011 in light of recent confusion around unsupported events for a given platform. Improve sys_perf_event_open ENOENT return handling in top and record, just like 5a3446b does for stat. Retry of Arnaldo's patch using ui_warning instead of die which allows the fallback from hardware cycles to software clock. Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org LKML-Reference: <1301080271-20945-1-git-send-email-daahern@cisco.com> Signed-off-by: David Ahern [ committer note: Some adjustments to make it apply to newer codebase ] Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Fixup exit path when not able to open events

2011-03-29T16:40:27Z

We have to deal with the TUI mode in perf top, so that we don't end up with a garbled screen when, say, a non root user on a machine with a paranoid setting (the default) tries to use 'perf top'. Introduce a ui__warning_paranoid() routine shared by top and record that tells the user the valid values for /proc/sys/kernel/perf_event_paranoid. Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo

perf symbols: Fix vsyscall symbol lookup

2011-03-28T17:44:15Z

Perf can't currently trace into the vsyscall page. It looks like it was meant to work. Tested on 2.6.38 and today's -git. The bug is easy to reproduce. Compile this: int main() { int i; struct timespec t; for(i = 0; i < 10000000; i++) clock_gettime(CLOCK_MONOTONIC, &t); return 0; } and run it through perf record; perf report. The top entry shows "[unknown]" and you can't zoom in. It looks like there are two issues. The first is a that a test for user mode executing in kernel space is backwards. (That's the first hunk below). The second (I think) is that something's wrong with the code that generates lots of little struct dso objects for different sections -- when it runs on vmlinux it results in bogus long_name values which cause objdump to fail. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra LPU-Reference: Signed-off-by: Andy Lutomirski Signed-off-by: Arnaldo Carvalho de Melo

Merge branch 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

2011-03-26T00:53:09Z

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: perf, x86: Complain louder about BIOSen corrupting CPU/PMU state and continue perf, x86: P4 PMU - Read proper MSR register to catch unflagged overflows perf symbols: Look at .dynsym again if .symtab not found perf build-id: Add quirk to deal with perf.data file format breakage perf session: Pass evsel in event_ops->sample() perf: Better fit max unprivileged mlock pages for tools needs perf_events: Fix stale ->cgrp pointer in update_cgrp_time_from_cpuctx() perf top: Fix uninitialized 'counter' variable tracing: Fix set_ftrace_filter probe function display perf, x86: Fix Intel fixed counters base initialization

perf symbols: Look at .dynsym again if .symtab not found

2011-03-23T22:29:46Z

The original intent of the code was to repeat the search with want_symtab = 0. But as the code stands now, we never hit the "default" case of the switch statement. Which means we never repeat the search. Tested-by: Srikar Dronamraju Reported-by: Arun Sharma Reported-by: Srikar Dronamraju Cc: Dave Martin Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo

perf build-id: Add quirk to deal with perf.data file format breakage

2011-03-23T22:29:40Z

The a1645ce1 changeset: "perf: 'perf kvm' tool for monitoring guest performance from host" Added a field to struct build_id_event that broke the file format. Since the kernel build-id is the first entry, process the table using the old format if the well known '[kernel.kallsyms]' string for the kernel build-id has the first 4 characters chopped off (where the pid_t sits). Reported-by: Han Pingtian Cc: Avi Kivity Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi Cc: Zhang Yanmin Cc: stable@kernel.org LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo