From 0264c8c9e1b53e9dbb41fae5e54756e84644bc60 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 5 Nov 2020 21:32:36 -0500 Subject: ftrace: Move the recursion testing into global headers Currently, if a callback is registered to a ftrace function and its ftrace_ops does not have the RECURSION flag set, it is encapsulated in a helper function that does the recursion for it. Really, all the callbacks should have their own recursion protection for performance reasons. But they should not all implement their own. Move the recursion helpers to global headers, so that all callbacks can use them. Link: https://lkml.kernel.org/r/20201028115612.460535535@goodmis.org Link: https://lkml.kernel.org/r/20201106023546.166456258@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_recursion.h | 187 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 187 insertions(+) create mode 100644 include/linux/trace_recursion.h (limited to 'include/linux/trace_recursion.h') diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h new file mode 100644 index 000000000000..dbb7b6d4c94c --- /dev/null +++ b/include/linux/trace_recursion.h @@ -0,0 +1,187 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TRACE_RECURSION_H +#define _LINUX_TRACE_RECURSION_H + +#include +#include + +#ifdef CONFIG_TRACING + +/* Only current can touch trace_recursion */ + +/* + * For function tracing recursion: + * The order of these bits are important. + * + * When function tracing occurs, the following steps are made: + * If arch does not support a ftrace feature: + * call internal function (uses INTERNAL bits) which calls... + * If callback is registered to the "global" list, the list + * function is called and recursion checks the GLOBAL bits. + * then this function calls... + * The function callback, which can use the FTRACE bits to + * check for recursion. + * + * Now if the arch does not support a feature, and it calls + * the global list function which calls the ftrace callback + * all three of these steps will do a recursion protection. + * There's no reason to do one if the previous caller already + * did. The recursion that we are protecting against will + * go through the same steps again. + * + * To prevent the multiple recursion checks, if a recursion + * bit is set that is higher than the MAX bit of the current + * check, then we know that the check was made by the previous + * caller, and we can skip the current check. + */ +enum { + /* Function recursion bits */ + TRACE_FTRACE_BIT, + TRACE_FTRACE_NMI_BIT, + TRACE_FTRACE_IRQ_BIT, + TRACE_FTRACE_SIRQ_BIT, + + /* INTERNAL_BITs must be greater than FTRACE_BITs */ + TRACE_INTERNAL_BIT, + TRACE_INTERNAL_NMI_BIT, + TRACE_INTERNAL_IRQ_BIT, + TRACE_INTERNAL_SIRQ_BIT, + + TRACE_BRANCH_BIT, +/* + * Abuse of the trace_recursion. + * As we need a way to maintain state if we are tracing the function + * graph in irq because we want to trace a particular function that + * was called in irq context but we have irq tracing off. Since this + * can only be modified by current, we can reuse trace_recursion. + */ + TRACE_IRQ_BIT, + + /* Set if the function is in the set_graph_function file */ + TRACE_GRAPH_BIT, + + /* + * In the very unlikely case that an interrupt came in + * at a start of graph tracing, and we want to trace + * the function in that interrupt, the depth can be greater + * than zero, because of the preempted start of a previous + * trace. In an even more unlikely case, depth could be 2 + * if a softirq interrupted the start of graph tracing, + * followed by an interrupt preempting a start of graph + * tracing in the softirq, and depth can even be 3 + * if an NMI came in at the start of an interrupt function + * that preempted a softirq start of a function that + * preempted normal context!!!! Luckily, it can't be + * greater than 3, so the next two bits are a mask + * of what the depth is when we set TRACE_GRAPH_BIT + */ + + TRACE_GRAPH_DEPTH_START_BIT, + TRACE_GRAPH_DEPTH_END_BIT, + + /* + * To implement set_graph_notrace, if this bit is set, we ignore + * function graph tracing of called functions, until the return + * function is called to clear it. + */ + TRACE_GRAPH_NOTRACE_BIT, + + /* + * When transitioning between context, the preempt_count() may + * not be correct. Allow for a single recursion to cover this case. + */ + TRACE_TRANSITION_BIT, +}; + +#define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) +#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) +#define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) + +#define trace_recursion_depth() \ + (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3) +#define trace_recursion_set_depth(depth) \ + do { \ + current->trace_recursion &= \ + ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \ + current->trace_recursion |= \ + ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \ + } while (0) + +#define TRACE_CONTEXT_BITS 4 + +#define TRACE_FTRACE_START TRACE_FTRACE_BIT +#define TRACE_FTRACE_MAX ((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1) + +#define TRACE_LIST_START TRACE_INTERNAL_BIT +#define TRACE_LIST_MAX ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) + +#define TRACE_CONTEXT_MASK TRACE_LIST_MAX + +static __always_inline int trace_get_context_bit(void) +{ + int bit; + + if (in_interrupt()) { + if (in_nmi()) + bit = 0; + + else if (in_irq()) + bit = 1; + else + bit = 2; + } else + bit = 3; + + return bit; +} + +static __always_inline int trace_test_and_set_recursion(int start, int max) +{ + unsigned int val = current->trace_recursion; + int bit; + + /* A previous recursion check was made */ + if ((val & TRACE_CONTEXT_MASK) > max) + return 0; + + bit = trace_get_context_bit() + start; + if (unlikely(val & (1 << bit))) { + /* + * It could be that preempt_count has not been updated during + * a switch between contexts. Allow for a single recursion. + */ + bit = TRACE_TRANSITION_BIT; + if (trace_recursion_test(bit)) + return -1; + trace_recursion_set(bit); + barrier(); + return bit + 1; + } + + /* Normal check passed, clear the transition to allow it again */ + trace_recursion_clear(TRACE_TRANSITION_BIT); + + val |= 1 << bit; + current->trace_recursion = val; + barrier(); + + return bit + 1; +} + +static __always_inline void trace_clear_recursion(int bit) +{ + unsigned int val = current->trace_recursion; + + if (!bit) + return; + + bit--; + bit = 1 << bit; + val &= ~bit; + + barrier(); + current->trace_recursion = val; +} + +#endif /* CONFIG_TRACING */ +#endif /* _LINUX_TRACE_RECURSION_H */ -- cgit From 6e4eb9cb22fc8a893cb708ed42644de5ee7c3827 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 5 Nov 2020 21:32:37 -0500 Subject: ftrace: Add ftrace_test_recursion_trylock() helper function To make it easier for ftrace callbacks to have recursion protection, provide a ftrace_test_recursion_trylock() and ftrace_test_recursion_unlock() helper that tests for recursion. Link: https://lkml.kernel.org/r/20201028115612.634927593@goodmis.org Link: https://lkml.kernel.org/r/20201106023546.378584067@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_recursion.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux/trace_recursion.h') diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index dbb7b6d4c94c..f2a949dbfec7 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -183,5 +183,30 @@ static __always_inline void trace_clear_recursion(int bit) current->trace_recursion = val; } +/** + * ftrace_test_recursion_trylock - tests for recursion in same context + * + * Use this for ftrace callbacks. This will detect if the function + * tracing recursed in the same context (normal vs interrupt), + * + * Returns: -1 if a recursion happened. + * >= 0 if no recursion + */ +static __always_inline int ftrace_test_recursion_trylock(void) +{ + return trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX); +} + +/** + * ftrace_test_recursion_unlock - called when function callback is complete + * @bit: The return of a successful ftrace_test_recursion_trylock() + * + * This is used at the end of a ftrace callback. + */ +static __always_inline void ftrace_test_recursion_unlock(int bit) +{ + trace_clear_recursion(bit); +} + #endif /* CONFIG_TRACING */ #endif /* _LINUX_TRACE_RECURSION_H */ -- cgit From da5afbeb1724609996ca7bb4fbce2cd104c95914 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 5 Nov 2020 21:32:38 -0500 Subject: ftrace: Optimize testing what context current is in The preempt_count() is not a simple location in memory, it could be part of per_cpu code or more. Each access to preempt_count(), or one of its accessor functions (like in_interrupt()) takes several cycles. By reading preempt_count() once, and then doing tests to find the context against the value return is slightly faster than using in_nmi() and in_interrupt(). Link: https://lkml.kernel.org/r/20201028115612.780796355@goodmis.org Link: https://lkml.kernel.org/r/20201106023546.558881845@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_recursion.h | 33 ++++++++++++++++++++------------- 1 file changed, 20 insertions(+), 13 deletions(-) (limited to 'include/linux/trace_recursion.h') diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index f2a949dbfec7..ac3d73484cb2 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -117,22 +117,29 @@ enum { #define TRACE_CONTEXT_MASK TRACE_LIST_MAX +/* + * Used for setting context + * NMI = 0 + * IRQ = 1 + * SOFTIRQ = 2 + * NORMAL = 3 + */ +enum { + TRACE_CTX_NMI, + TRACE_CTX_IRQ, + TRACE_CTX_SOFTIRQ, + TRACE_CTX_NORMAL, +}; + static __always_inline int trace_get_context_bit(void) { - int bit; - - if (in_interrupt()) { - if (in_nmi()) - bit = 0; - - else if (in_irq()) - bit = 1; - else - bit = 2; - } else - bit = 3; + unsigned long pc = preempt_count(); - return bit; + if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) + return TRACE_CTX_NORMAL; + else + return pc & NMI_MASK ? TRACE_CTX_NMI : + pc & HARDIRQ_MASK ? TRACE_CTX_IRQ : TRACE_CTX_SOFTIRQ; } static __always_inline int trace_test_and_set_recursion(int start, int max) -- cgit From 773c16705058e9be7b0f4ce124e89cd231c120a2 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 5 Nov 2020 21:32:46 -0500 Subject: ftrace: Add recording of functions that caused recursion This adds CONFIG_FTRACE_RECORD_RECURSION that will record to a file "recursed_functions" all the functions that caused recursion while a callback to the function tracer was running. Link: https://lkml.kernel.org/r/20201106023548.102375687@goodmis.org Cc: Masami Hiramatsu Cc: Andrew Morton Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Guo Ren Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Thomas Gleixner Cc: Borislav Petkov Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Kees Cook Cc: Anton Vorontsov Cc: Colin Cross Cc: Tony Luck Cc: Josh Poimboeuf Cc: Jiri Kosina Cc: Miroslav Benes Cc: Petr Mladek Cc: Joe Lawrence Cc: Kamalesh Babulal Cc: Mauro Carvalho Chehab Cc: Sebastian Andrzej Siewior Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-csky@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-s390@vger.kernel.org Cc: live-patching@vger.kernel.org Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_recursion.h | 29 +++++++++++++++++++++++++---- 1 file changed, 25 insertions(+), 4 deletions(-) (limited to 'include/linux/trace_recursion.h') diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index ac3d73484cb2..228cc56ed66e 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -91,6 +91,9 @@ enum { * not be correct. Allow for a single recursion to cover this case. */ TRACE_TRANSITION_BIT, + + /* Used to prevent recursion recording from recursing. */ + TRACE_RECORD_RECURSION_BIT, }; #define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) @@ -142,7 +145,22 @@ static __always_inline int trace_get_context_bit(void) pc & HARDIRQ_MASK ? TRACE_CTX_IRQ : TRACE_CTX_SOFTIRQ; } -static __always_inline int trace_test_and_set_recursion(int start, int max) +#ifdef CONFIG_FTRACE_RECORD_RECURSION +extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip); +# define do_ftrace_record_recursion(ip, pip) \ + do { \ + if (!trace_recursion_test(TRACE_RECORD_RECURSION_BIT)) { \ + trace_recursion_set(TRACE_RECORD_RECURSION_BIT); \ + ftrace_record_recursion(ip, pip); \ + trace_recursion_clear(TRACE_RECORD_RECURSION_BIT); \ + } \ + } while (0) +#else +# define do_ftrace_record_recursion(ip, pip) do { } while (0) +#endif + +static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip, + int start, int max) { unsigned int val = current->trace_recursion; int bit; @@ -158,8 +176,10 @@ static __always_inline int trace_test_and_set_recursion(int start, int max) * a switch between contexts. Allow for a single recursion. */ bit = TRACE_TRANSITION_BIT; - if (trace_recursion_test(bit)) + if (trace_recursion_test(bit)) { + do_ftrace_record_recursion(ip, pip); return -1; + } trace_recursion_set(bit); barrier(); return bit + 1; @@ -199,9 +219,10 @@ static __always_inline void trace_clear_recursion(int bit) * Returns: -1 if a recursion happened. * >= 0 if no recursion */ -static __always_inline int ftrace_test_recursion_trylock(void) +static __always_inline int ftrace_test_recursion_trylock(unsigned long ip, + unsigned long parent_ip) { - return trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX); + return trace_test_and_set_recursion(ip, parent_ip, TRACE_FTRACE_START, TRACE_FTRACE_MAX); } /** -- cgit From 7b68621f8d16689cbb4203aceaca86ffb165f1d0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 30 Oct 2020 17:21:00 -0400 Subject: ftrace: Clean up the recursion code a bit In trace_test_and_set_recursion(), current->trace_recursion is placed into a variable, and that variable should be used for the processing, as there's no reason to dereference current multiple times. On trace_clear_recursion(), current->trace_recursion is modified and there's no reason to copy it over to a variable. Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_recursion.h | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) (limited to 'include/linux/trace_recursion.h') diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index 228cc56ed66e..a9f9c5714e65 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -162,7 +162,7 @@ extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip); static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip, int start, int max) { - unsigned int val = current->trace_recursion; + unsigned int val = READ_ONCE(current->trace_recursion); int bit; /* A previous recursion check was made */ @@ -176,18 +176,15 @@ static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsign * a switch between contexts. Allow for a single recursion. */ bit = TRACE_TRANSITION_BIT; - if (trace_recursion_test(bit)) { + if (val & (1 << bit)) { do_ftrace_record_recursion(ip, pip); return -1; } - trace_recursion_set(bit); - barrier(); - return bit + 1; + } else { + /* Normal check passed, clear the transition to allow it again */ + val &= ~(1 << TRACE_TRANSITION_BIT); } - /* Normal check passed, clear the transition to allow it again */ - trace_recursion_clear(TRACE_TRANSITION_BIT); - val |= 1 << bit; current->trace_recursion = val; barrier(); @@ -197,17 +194,12 @@ static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsign static __always_inline void trace_clear_recursion(int bit) { - unsigned int val = current->trace_recursion; - if (!bit) return; - bit--; - bit = 1 << bit; - val &= ~bit; - barrier(); - current->trace_recursion = val; + bit--; + trace_recursion_clear(bit); } /** -- cgit