linux/kernel/trace, branch v4.20

Merge tag 'trace-v4.20-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

2018-12-13T02:15:29Z

Pull tracing fixes from Steven Rostedt: "While running various ftrace tests on new development code, the kmemleak detector found some allocations that were not freed correctly. This fixes a couple of leaks in the event trigger code as well as in adding function trace filters in trace instances" * tag 'trace-v4.20-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: tracing: Fix memory leak of instance function hash filters tracing: Fix memory leak in set_trigger_filter() tracing: Fix memory leak in create_filter()

tracing: Fix memory leak of instance function hash filters

2018-12-11T18:50:28Z

The following commands will cause a memory leak: # cd /sys/kernel/tracing # mkdir instances/foo # echo schedule > instance/foo/set_ftrace_filter # rmdir instances/foo The reason is that the hashes that hold the filters to set_ftrace_filter and set_ftrace_notrace are not freed if they contain any data on the instance and the instance is removed. Found by kmemleak detector. Cc: stable@vger.kernel.org Fixes: 591dffdade9f ("ftrace: Allow for function tracing instance to filter functions") Signed-off-by: Steven Rostedt (VMware)

tracing: Fix memory leak in set_trigger_filter()

2018-12-11T18:50:19Z

When create_event_filter() fails in set_trigger_filter(), the filter may still be allocated and needs to be freed. The caller expects the data->filter to be updated with the new filter, even if the new filter failed (we could add an error message by setting set_str parameter of create_event_filter(), but that's another update). But because the error would just exit, filter was left hanging and nothing could free it. Found by kmemleak detector. Cc: stable@vger.kernel.org Fixes: bac5fb97a173a ("tracing: Add and use generic set_trigger_filter() implementation") Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware)

tracing: Fix memory leak in create_filter()

2018-12-11T18:50:01Z

The create_filter() calls create_filter_start() which allocates a "parse_error" descriptor, but fails to call create_filter_finish() that frees it. The op_stack and inverts in predicate_parse() were also not freed. Found by kmemleak detector. Cc: stable@vger.kernel.org Fixes: 80765597bc587 ("tracing: Rewrite filter logic to be simpler and faster") Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware)

Merge tag 'trace-v4.20-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

2018-11-30T18:40:11Z

Pull more tracing fixes from Steven Rostedt: "Two more fixes: - Change idx variable in DO_TRACE macro to __idx to avoid name conflicts. A kvm event had "idx" as a parameter and it confused the macro. - Fix a race where interrupts would be traced when set_graph_function was set. The previous patch set increased a race window that tricked the function graph tracer to think it should trace interrupts when it really should not have. The bug has been there before, but was seldom hit. Only the last patch series made it more common" * tag 'trace-v4.20-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: tracing/fgraph: Fix set_graph_function from showing interrupts tracepoint: Use __idx instead of idx in DO_TRACE macro to make it unique

Merge tag 'trace-v4.20-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

2018-11-30T17:32:34Z

Pull tracing fixes from Steven Rostedt: "While rewriting the function graph tracer, I discovered a design flaw that was introduced by a patch that tried to fix one bug, but by doing so created another bug. As both bugs corrupt the output (but they do not crash the kernel), I decided to fix the design such that it could have both bugs fixed. The original fix, fixed time reporting of the function graph tracer when doing a max_depth of one. This was code that can test how much the kernel interferes with userspace. But in doing so, it could corrupt the time keeping of the function profiler. The issue is that the curr_ret_stack variable was being used for two different meanings. One was to keep track of the stack pointer on the ret_stack (shadow stack used by the function graph tracer), and the other use case was the graph call depth. Although, the two may be closely related, where they got updated was the issue that lead to the two different bugs that required the two use cases to be updated differently. The big issue with this fix is that it requires changing each architecture. The good news is, I was able to remove a lot of code that was duplicated within the architectures and place it into a single location. Then I could make the fix in one place. I pushed this code into linux-next to let it settle over a week, and before doing so, I cross compiled all the affected architectures to make sure that they built fine. In the mean time, I also pulled in a patch that fixes the sched_switch previous tasks state output, that was not actually correct" * tag 'trace-v4.20-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: sched, trace: Fix prev_state output in sched_switch tracepoint function_graph: Have profiler use curr_ret_stack and not depth function_graph: Reverse the order of pushing the ret_stack and the callback function_graph: Move return callback before update of curr_ret_stack function_graph: Use new curr_ret_depth to manage depth instead of curr_ret_stack function_graph: Make ftrace_push_return_trace() static sparc/function_graph: Simplify with function_graph_enter() sh/function_graph: Simplify with function_graph_enter() s390/function_graph: Simplify with function_graph_enter() riscv/function_graph: Simplify with function_graph_enter() powerpc/function_graph: Simplify with function_graph_enter() parisc: function_graph: Simplify with function_graph_enter() nds32: function_graph: Simplify with function_graph_enter() MIPS: function_graph: Simplify with function_graph_enter() microblaze: function_graph: Simplify with function_graph_enter() arm64: function_graph: Simplify with function_graph_enter() ARM: function_graph: Simplify with function_graph_enter() x86/function_graph: Simplify with function_graph_enter() function_graph: Create function_graph_enter() to consolidate architecture code

tracing/fgraph: Fix set_graph_function from showing interrupts

2018-11-30T03:09:00Z

The tracefs file set_graph_function is used to only function graph functions that are listed in that file (or all functions if the file is empty). The way this is implemented is that the function graph tracer looks at every function, and if the current depth is zero and the function matches something in the file then it will trace that function. When other functions are called, the depth will be greater than zero (because the original function will be at depth zero), and all functions will be traced where the depth is greater than zero. The issue is that when a function is first entered, and the handler that checks this logic is called, the depth is set to zero. If an interrupt comes in and a function in the interrupt handler is traced, its depth will be greater than zero and it will automatically be traced, even if the original function was not. But because the logic only looks at depth it may trace interrupts when it should not be. The recent design change of the function graph tracer to fix other bugs caused the depth to be zero while the function graph callback handler is being called for a longer time, widening the race of this happening. This bug was actually there for a longer time, but because the race window was so small it seldom happened. The Fixes tag below is for the commit that widen the race window, because that commit belongs to a series that will also help fix the original bug. Cc: stable@kernel.org Fixes: 39eb456dacb5 ("function_graph: Use new curr_ret_depth to manage depth instead of curr_ret_stack") Reported-by: Joe Lawrence Tested-by: Joe Lawrence Signed-off-by: Steven Rostedt (VMware)

function_graph: Have profiler use curr_ret_stack and not depth

2018-11-28T01:31:55Z

The profiler uses trace->depth to find its entry on the ret_stack, but the depth may not match the actual location of where its entry is (if an interrupt were to preempt the processing of the profiler for another function, the depth and the curr_ret_stack will be different). Have it use the curr_ret_stack as the index to find its ret_stack entry instead of using the depth variable, as that is no longer guaranteed to be the same. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware)

function_graph: Reverse the order of pushing the ret_stack and the callback

2018-11-28T01:31:54Z

The function graph profiler uses the ret_stack to store the "subtime" and reuse it by nested functions and also on the return. But the current logic has the profiler callback called before the ret_stack is updated, and it is just modifying the ret_stack that will later be allocated (it's just lucky that the "subtime" is not touched when it is allocated). This could also cause a crash if we are at the end of the ret_stack when this happens. By reversing the order of the allocating the ret_stack and then calling the callbacks attached to a function being traced, the ret_stack entry is no longer used before it is allocated. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware)

function_graph: Move return callback before update of curr_ret_stack

2018-11-28T01:31:54Z

In the past, curr_ret_stack had two functions. One was to denote the depth of the call graph, the other is to keep track of where on the ret_stack the data is used. Although they may be slightly related, there are two cases where they need to be used differently. The one case is that it keeps the ret_stack data from being corrupted by an interrupt coming in and overwriting the data still in use. The other is just to know where the depth of the stack currently is. The function profiler uses the ret_stack to save a "subtime" variable that is part of the data on the ret_stack. If curr_ret_stack is modified too early, then this variable can be corrupted. The "max_depth" option, when set to 1, will record the first functions going into the kernel. To see all top functions (when dealing with timings), the depth variable needs to be lowered before calling the return hook. But by lowering the curr_ret_stack, it makes the data on the ret_stack still being used by the return hook susceptible to being overwritten. Now that there's two variables to handle both cases (curr_ret_depth), we can move them to the locations where they can handle both cases. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware)