- 14 Feb, 2013 2 commits
-
-
Namhyung Kim authored
When perf annotate runs with no vmlinux file it cannot annotate kernel symbols because the kallsyms only provides symbol addresses. So it recommends to run perf buildid-cache to install proper vmlinux image. But running perf buildid-cache -av vmlinux as the message gives me a following error: $ perf buildid-cache -av /home/namhyung/build/kernel/vmlinux Couldn't add v: No such file or directory Since the -a option receives a parameter, 'v' should not be after the option. In addition -a option is not work for this case since the build-id cache already has a kallsyms with same build-id so it'll fail with EEXIST. Use recently added -u (--update) option for it. Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1360227734-375-6-git-send-email-namhyung@kernel.orgSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Namhyung Kim authored
When adding vmlinux file to build-id cache, it'd be fail since kallsyms dso with a same build-id was already added by perf record. So one needs to remove the kallsyms first to add vmlinux into the cache. Add --update option for doing it at once. Signed-off-by:
-
- 11 Feb, 2013 1 commit
-
-
Ingo Molnar authored
Merge branch 'uprobes/core' of git://git.kernel.org/pub/scm/linux/kernel/git/oleg/misc into perf/core Improve uprobes performance by adding 'pre-filtering' support, by Oleg Nesterov: # time perl -e 'syscall -1 for 1..100_000' real 0m0.040s user 0m0.027s sys 0m0.010s # perf probe -x /lib/libc.so.6 syscall # perf record -e probe_libc:syscall sleep 100 & Before this series: # time perl -e 'syscall -1 for 1..100_000' real 0m1.714s user 0m0.103s sys 0m1.607s After: # time perl -e 'syscall -1 for 1..100_000' real 0m0.037s user 0m0.013s sys 0m0.023s Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
- 08 Feb, 2013 37 commits
-
-
Oleg Nesterov authored
uprobe_perf_open/close call the costly uprobe_apply() every time, we can avoid it if: - "nr_systemwide != 0" is not changed. - There is another process/thread with the same ->mm. - copy_proccess() does inherit_event(). dup_mmap() preserves the inserted breakpoints. - event->attr.enable_on_exec == T, we can rely on uprobe_mmap() called by exec/mmap paths. - tp_target is exiting. Only _close() checks PF_EXITING, I don't think TRACE_REG_PERF_OPEN can hit the dying task too often. Signed-off-by:Oleg Nesterov <oleg@redhat.com>
-
Oleg Nesterov authored
Change uprobe_trace_func() and uprobe_perf_func() to return "int". Change uprobe_dispatcher() to return "trace_ret | perf_ret" although this is not needed, currently TP_FLAG_TRACE/TP_FLAG_PROFILE are mutually exclusive. The only functional change is that uprobe_perf_func() checks the filtering too and returns UPROBE_HANDLER_REMOVE if nobody wants to trace current. Testing: # perf probe -x /lib/libc.so.6 syscall # perf record -e probe_libc:syscall -i perl -e 'fork; syscall -1 for 1..10; wait' # perf report --show-total-period 100.00% 10 perl libc-2.8.so [.] syscall Before this patch: # cat /sys/kernel/debug/tracing/uprobe_profile /lib/libc.so.6 syscall 20 A child process doesn't have a counter, but still it hits this breakoint "copied" by dup_mmap(). After the patch: # cat /sys/kernel/debug/tracing/uprobe_profile /lib/libc.so.6 syscall 11 The child process hits this int3 only once and does unapply_uprobe(). Signed-off-by: -
Oleg Nesterov authored
Finally implement uprobe_perf_filter() which checks ->nr_systemwide or ->perf_events to figure out whether we need to insert the breakpoint. uprobe_perf_open/close are changed to do uprobe_apply(true/false) when the new perf event comes or goes away. Note that currently this is very suboptimal: - uprobe_register() called by TRACE_REG_PERF_REGISTER becomes a heavy nop, consumer->filter() always returns F at this stage. As it was already discussed we need uprobe_register_only() to avoid the costly register_for_each_vma() when possible. - uprobe_apply() is oftenly overkill. Unless "nr_systemwide != 0" changes we need uprobe_apply_mm(), unapply_uprobe() is almost what we need. - uprobe_apply() can be simply avoided sometimes, see the next changes. Testing: # perf probe -x /lib/libc.so.6 syscall # perl -e 'syscall -1 while 1' & [1] 530 # perf record -e probe_libc:syscall perl -e 'syscall -1 for 1..10; sleep 1' # perf report --show-total-period 100.00% 10 perl libc-2.8.so [.] syscall Before this patch: # cat /sys/kernel/debug/tracing/uprobe_profile /lib/libc.so.6 syscall 79291 A huge ->nrhit == 79291 reflects the fact that the background process 530 constantly hits this breakpoint too, even if doesn't contribute to the output. After the patch: # cat /sys/kernel/debug/tracing/uprobe_profile /lib/libc.so.6 syscall 10 This shows that only the target process was punished by int3. Signed-off-by: -
Oleg Nesterov authored
Introduce "struct trace_uprobe_filter" which records the "active" perf_event's attached to ftrace_event_call. For the start we simply use list_head, we can optimize this later if needed. For example, we do not really need to record an event with ->parent != NULL, we can rely on parent->child_list. And we can certainly do some optimizations for the case when 2 events have the same ->tp_target or tp_target->mm. Change trace_uprobe_register() to process TRACE_REG_PERF_OPEN/CLOSE and add/del this perf_event to the list. We can probably avoid any locking, but lets start with the "obvioulsy correct" trace_uprobe_filter->rwlock which protects everything. Signed-off-by: -
Oleg Nesterov authored
Currently it is not possible to change the filtering constraints after uprobe_register(), so a consumer can not, say, start to trace a task/mm which was previously filtered out, or remove the no longer needed bp's. Introduce uprobe_apply() which simply does register_for_each_vma() again to consult uprobe_consumer->filter() and install/remove the breakpoints. The only complication is that register_for_each_vma() can no longer assume that uprobe->consumers should be consulter if is_register == T, so we change it to accept "struct uprobe_consumer *new" instead. Unlike uprobe_register(), uprobe_apply(true) doesn't do "unregister" if register_for_each_vma() fails, it is up to caller to handle the error. Note: we probably need to cleanup the current interface, it is strange that uprobe_apply/unregister need inode/offset. We should either change uprobe_register() to return "struct uprobe *", or add a private ->uprobe member in uprobe_consumer. And in the long term uprobe_apply() should take a single argument, uprobe or consumer, even "bool add" should go away. Signed-off-by: -
Oleg Nesterov authored
sys_perf_event_open()->perf_init_event(event) is called before find_get_context(event), this means that event->ctx == NULL when class->reg(TRACE_REG_PERF_REGISTER/OPEN) is called and thus it can't know if this event is per-task or system-wide. This patch adds hw_perf_event->tp_target for PERF_TYPE_TRACEPOINT, this is analogous to PERF_TYPE_BREAKPOINT/bp_target we already have. The patch also moves ->bp_target up so that it can overlap with the new member, this can help the compiler to generate the better code. trace_uprobe_register() will use it for prefiltering to avoid the unnecessary breakpoints in mm's we do not want to trace. ->tp_target doesn't have its own reference, but we can rely on the fact that either sys_perf_event_open() holds a reference, or it is equal to event->ctx->task. So this pointer is always valid until free_event(). Also add the "struct list_head tp_list" into this union. It is not strictly necessary, but it can simplify the next changes and we can add it for free. Signed-off-by: -
Oleg Nesterov authored
Move tu->nhit++ from uprobe_trace_func() to uprobe_dispatcher(). ->nhit counts how many time we hit the breakpoint inserted by this uprobe, we do not want to loose this info if uprobe was enabled by sys_perf_event_open(). Signed-off-by:
Srikar Dronamraju <srikar@linux.vnet.ibm.com>
-
Oleg Nesterov authored
trace_uprobe->consumer and "struct uprobe_trace_consumer" add the unnecessary indirection and complicate the code for no reason. This patch simply embeds uprobe_consumer into "struct trace_uprobe", all other changes only fix the compilation errors. Signed-off-by: -
Oleg Nesterov authored
probe_event_enable/disable() check tu->consumer != NULL to avoid the wrong uprobe_register/unregister(). We are going to kill this pointer and "struct uprobe_trace_consumer", so we add the new helper, is_trace_uprobe_enabled(), which can rely on TP_FLAG_TRACE/TP_FLAG_PROFILE instead. Note: the current logic doesn't look optimal, it is not clear why TP_FLAG_TRACE/TP_FLAG_PROFILE are mutually exclusive, we will probably change this later. Also kill the unused TP_FLAG_UPROBE. Signed-off-by:
-
Oleg Nesterov authored
probe_event_enable/disable() check tu->inode != NULL at the start. This is ugly, if igrab() can fail create_trace_uprobe() should not succeed and "postpone" the failure. And S_ISREG(inode->i_mode) check added by d24d7dbf is not safe. Note: alloc_uprobe() should probably check igrab() != NULL as well. Signed-off-by:
-
Oleg Nesterov authored
probe_event_enable() does uprobe_register() and only after that sets utc->tu and tu->consumer/flags. This can race with uprobe_dispatcher() which can miss these assignments or see them out of order. Nothing really bad can happen, but this doesn't look clean/safe. And this does not allow to use uprobe_consumer->filter() we are going to add, it is called by uprobe_register() and it needs utc->tu. Change this code to initialize everything before uprobe_register(), and reset tu->consumer/flags if it fails. We can't race with event_disable(), the caller holds event_mutex, and if we could the code would be wrong anyway. In fact I think uprobe_trace_consumer should die, it buys nothing but complicates the code. We can simply add uprobe_consumer into trace_uprobe. Signed-off-by:
-
Oleg Nesterov authored
create_trace_uprobe() does kern_path() to find ->d_inode, but forgets to do path_put(). We can do this right after igrab(). Signed-off-by:
-
Josh Stone authored
The original pull message for uprobes (commit 654443e2) noted: This tree includes uprobes support in 'perf probe' - but SystemTap (and other tools) can take advantage of user probe points as well. In order to actually be usable in module-based tools like SystemTap, the interface needs to be exported. This patch first adds the obvious exports for uprobe_register and uprobe_unregister. Then it also adds one for task_user_regset_view, which is necessary to get the correct state of userspace registers. Signed-off-by:
Josh Stone <jistone@redhat.com> Signed-off-by:
-
Oleg Nesterov authored
utask->xol_vaddr is either zero or valid, remove the bogus IS_ERR_VALUE() check in xol_free_insn_slot(). Signed-off-by:
Anton Arapov <anton@redhat.com> Acked-by:
-
Oleg Nesterov authored
handle_swbp() does get_utask() before can_skip_sstep() for no reason, we do not need ->utask if can_skip_sstep() succeeds. Move get_utask() to pre_ssout() who actually starts to use it. Move the initialization of utask->active_uprobe/state as well. This way the whole initialization is consolidated in pre_ssout(). Signed-off-by:
-
Oleg Nesterov authored
pre_ssout() should do xol_free_insn_slot() if arch_uprobe_pre_xol() fails, otherwise nobody will free the allocated slot. Signed-off-by:
-
Oleg Nesterov authored
pre_ssout()->xol_get_insn_slot() path is confusing and buggy. This patch cleanups the code, the next one fixes the bug. Change xol_get_insn_slot() to only allocate the slot and do nothing more, move the initialization of utask->xol_vaddr/vaddr into pre_ssout(). Signed-off-by:
-
Oleg Nesterov authored
Rename add_utask() into get_utask() and change it to allocate on demand to simplify the caller. Like get_xol_area() it will have more users. Signed-off-by:
-
Oleg Nesterov authored
Currently only xol_get_insn_slot() does get_xol_area() + xol_alloc_area(), but this will have more users and we do not want to copy-and-paste this code. This patch simply moves xol_alloc_area() into get_xol_area() to simplify the current and future code. Signed-off-by:
-
Oleg Nesterov authored
Move alloc_page() from xol_add_vma() to xol_alloc_area() to cleanup the code. This separates the memory allocations and consolidates the -EALREADY cleanups and the error handling. Signed-off-by:
-
Oleg Nesterov authored
Change handle_swbp() to set regs->ip = bp_vaddr in advance, this is what consumer->handler() needs but uprobe_get_swbp_addr() is not exported. This also simplifies the code and makes it more consistent across the supported architectures. handle_swbp() becomes the only caller of uprobe_get_swbp_addr(). Signed-off-by:
Ananth N Mavinakayanahalli <ananth@in.ibm.com>
-
Oleg Nesterov authored
__skip_sstep() doesn't update regs->ip. Currently this is correct but only "by accident" and it doesn't skip the whole insn. Change it to advance ->ip by the length of the detected 0x66*0x90 sequence. Signed-off-by:
-
Oleg Nesterov authored
Currrently the are 2 problems with pre-filtering: 1. It is not possible to add/remove a task (mm) after uprobe_register() 2. A forked child inherits all breakpoints and uprobe_consumer can not control this. This patch does the first step to improve the filtering. handler_chain() removes the breakpoints installed by this uprobe from current->mm if all handlers return UPROBE_HANDLER_REMOVE. Note that handler_chain() relies on ->register_rwsem to avoid the race with uprobe_register/unregister which can add/del a consumer, or even remove and then insert the new uprobe at the same address. Perhaps we will add uprobe_apply_mm(uprobe, mm, is_register) and teach copy_mm() to do filter(UPROBE_FILTER_FORK), but I think this change makes sense anyway. Note: instead of checking the retcode from uc->handler, we could add uc->filter(UPROBE_FILTER_BPHIT). But I think this is not optimal to call 2 hooks in a row. This buys nothing, and if handler/filter do something nontrivial they will probably do the same work twice. Signed-off-by:
-
Oleg Nesterov authored
Finally add uprobe_consumer->filter() and change consumer_filter() to actually call this method. Note that ->filter() accepts mm_struct, not task_struct. Because: 1. We do not have for_each_mm_user(mm, task). 2. Even if we implement for_each_mm_user(), ->filter() can use it itself. 3. It is not clear who will actually need this interface to do the "nontrivial" filtering. Another argument is "enum uprobe_filter_ctx", consumer->filter() can use it to figure out why/where it was called. For example, perhaps we can add UPROBE_FILTER_PRE_REGISTER used by build_map_info() to quickly "nack" the unwanted mm's. In this case consumer should know that it is called under ->i_mmap_mutex. See the previous discussion at http://marc.info/?t=135214229700002 Perhaps we should pass more arguments, vma/vaddr? Note: this patch obviously can't help to filter out the child created by fork(), this will be addressed later. Signed-off-by:
-
Oleg Nesterov authored
filter_chain() was added into install_breakpoint/remove_breakpoint to simplify the initial changes but this is sub-optimal. This patch shifts the callsite to the callers, register_for_each_vma() and uprobe_mmap(). This way: - It will be easier to add the new arguments. This is the main reason, we can do more optimizations later. - register_for_each_vma(is_register => true) can be optimized, we only need to consult the new consumer. The previous consumers were already asked when they called uprobe_register(). This patch also moves the MMF_HAS_UPROBES check from remove_breakpoint(), this allows to avoid the potentionally costly filter_chain(). Note that register_for_each_vma(is_register => false) doesn't really need to take ->consumer_rwsem, but I don't think it makes sense to optimize this and introduce filter_chain_lockless(). Signed-off-by:
-
Oleg Nesterov authored
uprobe_register() and uprobe_unregister() are the only users of mutex_lock(uprobes_hash(inode)), and the only reason why we can't simply remove it is that we need to ensure that delete_uprobe() is not possible after alloc_uprobe() and before consumer_add(). IOW, we need to ensure that when we take uprobe->register_rwsem this uprobe is still valid and we didn't race with _unregister() which called delete_uprobe() in between. With this patch uprobe_register() simply checks uprobe_is_active() and retries if it hits this very unlikely race. uprobes_mutex[] is no longer needed and can be removed. There is another reason for this change, prepare_uprobe() should be folded into alloc_uprobe() and we do not want to hold the extra locks around read_mapping_page/etc. Signed-off-by:
-
Oleg Nesterov authored
The lifetime of uprobe->rb_node and uprobe->inode is not refcounted, delete_uprobe() is called when we detect that uprobe has no consumers, and it would be deadly wrong to do this twice. Change delete_uprobe() to WARN() if it was already called. We use RB_CLEAR_NODE() to mark uprobe "inactive", then RB_EMPTY_NODE() can be used to detect this case. RB_EMPTY_NODE() is not used directly, we add the trivial helper for the next change. Signed-off-by:
-
Oleg Nesterov authored
uprobe_events counts the number of uprobes in uprobes_tree but it is used as a boolean. We can use RB_EMPTY_ROOT() instead. Probably no_uprobe_events() added by this patch can have more callers, say, mmf_recalc_uprobes(). Signed-off-by:
-
Oleg Nesterov authored
Now that ->register_rwsem is safe under ->mmap_sem we can kill ->copy_mutex and abuse down_write(&uprobe->consumer_rwsem). This makes prepare_uprobe() even more ugly, but we should kill it anyway. Signed-off-by:
-
Oleg Nesterov authored
Simply remove UPROBE_RUN_HANDLER and the corresponding code. It can only help if uprobe has a single consumer, and in fact it is no longer needed after handler_chain() was changed to use ->register_rwsem, we simply can not race with uprobe_register(). Signed-off-by:
-
Oleg Nesterov authored
Now that it safe to use ->consumer_rwsem under ->mmap_sem we can almost finish the implementation of filter_chain(). It still lacks the actual uc->filter(...) call but othewrwise it is ready, just it pretends that ->filter() always returns true. Signed-off-by:
-
Oleg Nesterov authored
Introduce uprobe->register_rwsem. It is taken for writing around __uprobe_register/unregister. Change handler_chain() to use this sem rather than consumer_rwsem. The main reason for this change is that we have the nasty problem with mmap_sem/consumer_rwsem dependency. filter_chain() needs to protect uprobe->consumers like handler_chain(), but they can not use the same lock. filter_chain() can be called under ->mmap_sem (currently this is always true), but we want to allow ->handler() to play with the probed task's memory, and this needs ->mmap_sem. Alternatively we could use srcu, but synchronize_srcu() is very slow and ->register_rwsem allows us to do more. In particular, we can teach handler_chain() to do remove_breakpoint() if this bp is "nacked" by all consumers, we know that we can't race with the new consumer which does uprobe_register(). See also the next patches. uprobes_mutex[] is almost ready to die. Signed-off-by:
-
Oleg Nesterov authored
To support the filtering uprobe_register() should do register_for_each_vma(true) every time the new consumer comes, we need to install the previously nacked breakpoints. Note: - uprobes_mutex[] should die, what it actually protects is alloc_uprobe(). - UPROBE_RUN_HANDLER should die too, obviously it can't work unless uprobe has a single consumer. The consumer should serialize with _register/_unregister itself. Or this flag should live in uprobe_consumer->state. - Perhaps we can do some optimizations later. For example, if filter_chain() never returns false uprobe can record this fact and avoid the unnecessary register_for_each_vma(). Signed-off-by:
-
Oleg Nesterov authored
uprobe_unregister() removes the breakpoints only if the last consumer goes away. To support the filtering it should do this every time, we want to remove the breakpoints which nobody else want to keep. Note: given that filter_chain() is not actually implemented, this patch itself doesn't change the behaviour yet, register_for_each_vma(false) is a heavy "nop" unless there are no more consumers. Signed-off-by:
-
Oleg Nesterov authored
Add the new helper filter_chain(). Currently it is only placeholder, the comment explains what is should do. We will change it later to consult every consumer to decide whether we need to install the swbp. Until then it works as if any consumer returns true, this matches the current behavior. Change install_breakpoint() to call filter_chain() instead of checking uprobe->consumers != NULL. We obviously need this, and this equally closes the race with _unregister(). Change remove_breakpoint() to call this helper too. Currently this is pointless because remove_breakpoint() is only called when the last consumer goes away, but we will change this. Signed-off-by:
-
Oleg Nesterov authored
uprobe_consumer->filter() is pointless in its current form, kill it. We will add it back, but with the different signature/semantics. Perhaps we will even re-introduce the callsite in handler_chain(), but not to just skip uc->handler(). Signed-off-by:
-
Oleg Nesterov authored
register/unregister verifies that inode/uc != NULL. For what? This really looks like "hide the potential problem", the caller should pass the valid data. register() also checks uc->next == NULL, probably to prevent the double-register but the caller can do other stupid/wrong things. If we do this check, then we should document that uc->next should be cleared before register() and add BUG_ON(). Also add the small comment about the i_size_read() check. Signed-off-by:
-
