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/ftrace.h | 1 + include/linux/trace_recursion.h | 187 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 188 insertions(+) create mode 100644 include/linux/trace_recursion.h (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 1bd3a0356ae4..0e4164a7f56d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -7,6 +7,7 @@ #ifndef _LINUX_FTRACE_H #define _LINUX_FTRACE_H +#include #include #include #include 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 v1.2.3 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') 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 v1.2.3 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') 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 v1.2.3 From a25d036d939a30623ff73ecad9c8b9116b02e823 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 5 Nov 2020 21:32:45 -0500 Subject: ftrace: Reverse what the RECURSION flag means in the ftrace_ops Now that all callbacks are recursion safe, reverse the meaning of the RECURSION flag and rename it from RECURSION_SAFE to simply RECURSION. Now only callbacks that request to have recursion protecting it will have the added trampoline to do so. Also remove the outdated comment about "PER_CPU" when determining to use the ftrace_ops_assist_func. Link: https://lkml.kernel.org/r/20201028115613.742454631@goodmis.org Link: https://lkml.kernel.org/r/20201106023547.904270143@goodmis.org Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Josh Poimboeuf Cc: Jiri Kosina Cc: Masami Hiramatsu Cc: Andrew Morton Cc: Jonathan Corbet Cc: Sebastian Andrzej Siewior Cc: Miroslav Benes Cc: Kamalesh Babulal Cc: Petr Mladek Cc: linux-doc@vger.kernel.org Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0e4164a7f56d..806196345c3f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -98,7 +98,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); /* * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are * set in the flags member. - * CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION_SAFE, STUB and + * CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION, STUB and * IPMODIFY are a kind of attribute flags which can be set only before * registering the ftrace_ops, and can not be modified while registered. * Changing those attribute flags after registering ftrace_ops will @@ -121,10 +121,10 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * passing regs to the handler. * Note, if this flag is set, the SAVE_REGS flag will automatically * get set upon registering the ftrace_ops, if the arch supports it. - * RECURSION_SAFE - The ftrace_ops can set this to tell the ftrace infrastructure - * that the call back has its own recursion protection. If it does - * not set this, then the ftrace infrastructure will add recursion - * protection for the caller. + * RECURSION - The ftrace_ops can set this to tell the ftrace infrastructure + * that the call back needs recursion protection. If it does + * not set this, then the ftrace infrastructure will assume + * that the callback can handle recursion on its own. * STUB - The ftrace_ops is just a place holder. * INITIALIZED - The ftrace_ops has already been initialized (first use time * register_ftrace_function() is called, it will initialized the ops) @@ -156,7 +156,7 @@ enum { FTRACE_OPS_FL_DYNAMIC = BIT(1), FTRACE_OPS_FL_SAVE_REGS = BIT(2), FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = BIT(3), - FTRACE_OPS_FL_RECURSION_SAFE = BIT(4), + FTRACE_OPS_FL_RECURSION = BIT(4), FTRACE_OPS_FL_STUB = BIT(5), FTRACE_OPS_FL_INITIALIZED = BIT(6), FTRACE_OPS_FL_DELETED = BIT(7), -- cgit v1.2.3 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') 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 v1.2.3 From 60602cb549f1965a7edbc96026760dfb93911fab Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 28 Oct 2020 08:19:24 -0400 Subject: fgraph: Make overruns 4 bytes in graph stack structure Inspecting the data structures of the function graph tracer, I found that the overrun value is unsigned long, which is 8 bytes on a 64 bit machine, and not only that, the depth is an int (4 bytes). The overrun can be simply an unsigned int (4 bytes) and pack the ftrace_graph_ret structure better. The depth is moved up next to the func, as it is used more often with func, and improves cache locality. Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 806196345c3f..8dde9c17aaa5 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -864,11 +864,11 @@ struct ftrace_graph_ent { */ struct ftrace_graph_ret { unsigned long func; /* Current function */ + int depth; /* Number of functions that overran the depth limit for current task */ - unsigned long overrun; + unsigned int overrun; unsigned long long calltime; unsigned long long rettime; - int depth; } __packed; /* Type of the callback handlers for tracing function graph*/ -- cgit v1.2.3 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') 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 v1.2.3 From d19ad0775dcd64b49eecf4fa79c17959ebfbd26b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 28 Oct 2020 17:42:17 -0400 Subject: ftrace: Have the callbacks receive a struct ftrace_regs instead of pt_regs In preparation to have arguments of a function passed to callbacks attached to functions as default, change the default callback prototype to receive a struct ftrace_regs as the forth parameter instead of a pt_regs. For callbacks that set the FL_SAVE_REGS flag in their ftrace_ops flags, they will now need to get the pt_regs via a ftrace_get_regs() helper call. If this is called by a callback that their ftrace_ops did not have a FL_SAVE_REGS flag set, it that helper function will return NULL. This will allow the ftrace_regs to hold enough just to get the parameters and stack pointer, but without the worry that callbacks may have a pt_regs that is not completely filled. Acked-by: Peter Zijlstra (Intel) Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 16 ++++++++++++++-- include/linux/kprobes.h | 2 +- 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 8dde9c17aaa5..24e1fa52337d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -90,8 +90,20 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, struct ftrace_ops; +struct ftrace_regs { + struct pt_regs regs; +}; + +static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs) +{ + if (!fregs) + return NULL; + + return &fregs->regs; +} + typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *regs); + struct ftrace_ops *op, struct ftrace_regs *fregs); ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); @@ -259,7 +271,7 @@ int register_ftrace_function(struct ftrace_ops *ops); int unregister_ftrace_function(struct ftrace_ops *ops); extern void ftrace_stub(unsigned long a0, unsigned long a1, - struct ftrace_ops *op, struct pt_regs *regs); + struct ftrace_ops *op, struct ftrace_regs *fregs); #else /* !CONFIG_FUNCTION_TRACER */ /* diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 629abaf25681..be73350955e4 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -345,7 +345,7 @@ static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct pt_regs *regs); + struct ftrace_ops *ops, struct ftrace_regs *fregs); extern int arch_prepare_kprobe_ftrace(struct kprobe *p); #endif -- cgit v1.2.3 From 02a474ca266a47ea8f4d5a11f4ffa120f83730ad Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 27 Oct 2020 10:55:55 -0400 Subject: ftrace/x86: Allow for arguments to be passed in to ftrace_regs by default Currently, the only way to get access to the registers of a function via a ftrace callback is to set the "FL_SAVE_REGS" bit in the ftrace_ops. But as this saves all regs as if a breakpoint were to trigger (for use with kprobes), it is expensive. The regs are already saved on the stack for the default ftrace callbacks, as that is required otherwise a function being traced will get the wrong arguments and possibly crash. And on x86, the arguments are already stored where they would be on a pt_regs structure to use that code for both the regs version of a callback, it makes sense to pass that information always to all functions. If an architecture does this (as x86_64 now does), it is to set HAVE_DYNAMIC_FTRACE_WITH_ARGS, and this will let the generic code that it could have access to arguments without having to set the flags. This also includes having the stack pointer being saved, which could be used for accessing arguments on the stack, as well as having the function graph tracer not require its own trampoline! Acked-by: Peter Zijlstra (Intel) Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 24e1fa52337d..588ea7023a7a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -90,16 +90,21 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, struct ftrace_ops; +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS + struct ftrace_regs { struct pt_regs regs; }; +#define arch_ftrace_get_regs(fregs) (&(fregs)->regs) + +#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs) { if (!fregs) return NULL; - return &fregs->regs; + return arch_ftrace_get_regs(fregs); } typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, -- cgit v1.2.3 From 2860cd8a235375df3c8ec8039d9fe5eb2f658b86 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 28 Oct 2020 17:15:27 -0400 Subject: livepatch: Use the default ftrace_ops instead of REGS when ARGS is available When CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS is available, the ftrace call will be able to set the ip of the calling function. This will improve the performance of live kernel patching where it does not need all the regs to be stored just to change the instruction pointer. If all archs that support live kernel patching also support HAVE_DYNAMIC_FTRACE_WITH_ARGS, then the architecture specific function klp_arch_set_pc() could be made generic. It is possible that an arch can support HAVE_DYNAMIC_FTRACE_WITH_ARGS but not HAVE_DYNAMIC_FTRACE_WITH_REGS and then have access to live patching. Cc: Josh Poimboeuf Cc: Jiri Kosina Cc: live-patching@vger.kernel.org Acked-by: Peter Zijlstra (Intel) Acked-by: Miroslav Benes Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 588ea7023a7a..9a8ce28e4485 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -97,6 +97,13 @@ struct ftrace_regs { }; #define arch_ftrace_get_regs(fregs) (&(fregs)->regs) +/* + * ftrace_instruction_pointer_set() is to be defined by the architecture + * if to allow setting of the instruction pointer from the ftrace_regs + * when HAVE_DYNAMIC_FTRACE_WITH_ARGS is set and it supports + * live kernel patching. + */ +#define ftrace_instruction_pointer_set(fregs, ip) do { } while (0) #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs) -- cgit v1.2.3 From d9a9280a0d0ae51dc1d4142138b99242b7ec8ac6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 26 Oct 2020 17:10:58 +0100 Subject: seq_buf: Avoid type mismatch for seq_buf_init Building with W=2 prints a number of warnings for one function that has a pointer type mismatch: linux/seq_buf.h: In function 'seq_buf_init': linux/seq_buf.h:35:12: warning: pointer targets in assignment from 'unsigned char *' to 'char *' differ in signedness [-Wpointer-sign] Change the type in the function prototype according to the type in the structure. Link: https://lkml.kernel.org/r/20201026161108.3707783-1-arnd@kernel.org Fixes: 9a7777935c34 ("tracing: Convert seq_buf fields to be like seq_file fields") Reviewed-by: Cezary Rojewski Signed-off-by: Arnd Bergmann Signed-off-by: Steven Rostedt (VMware) --- include/linux/seq_buf.h | 2 +- include/linux/trace_seq.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index fb0205d87d3c..9d6c28cc4d8f 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -30,7 +30,7 @@ static inline void seq_buf_clear(struct seq_buf *s) } static inline void -seq_buf_init(struct seq_buf *s, unsigned char *buf, unsigned int size) +seq_buf_init(struct seq_buf *s, char *buf, unsigned int size) { s->buffer = buf; s->size = size; diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 6c30508fca19..5a2c650d9e1c 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -12,7 +12,7 @@ */ struct trace_seq { - unsigned char buffer[PAGE_SIZE]; + char buffer[PAGE_SIZE]; struct seq_buf seq; int full; }; @@ -51,7 +51,7 @@ static inline int trace_seq_used(struct trace_seq *s) * that is about to be written to and then return the result * of that write. */ -static inline unsigned char * +static inline char * trace_seq_buffer_ptr(struct trace_seq *s) { return s->buffer + seq_buf_used(&s->seq); -- cgit v1.2.3