From: "Matthew Wilcox (Oracle)" <willy@infradead.org> stable inclusion from stable-v6.6.70 commit c46547b4686e9099dbad1f6f8e29f65a0b2c461c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBJ835 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit d0ed46b60396cfa7e0056f55e1ce0b43c7db57b6 ] To make seq_buf more lightweight as a string buf, move the readpos member from seq_buf to its container, trace_seq. That puts the responsibility of maintaining the readpos entirely in the tracing code. If some future users want to package up the readpos with a seq_buf, we can define a new struct then. Link: https://lore.kernel.org/linux-trace-kernel/20231020033545.2587554-2-willy@in... Cc: Kees Cook <keescook@chromium.org> Cc: Justin Stitt <justinstitt@google.com> Cc: Kent Overstreet <kent.overstreet@linux.dev> Cc: Petr Mladek <pmladek@suse.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> Stable-dep-of: afd2627f727b ("tracing: Check "%s" dereference via the field and not the TP_printk format") Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Li Huafei <lihuafei1@huawei.com> --- include/linux/seq_buf.h | 5 +---- include/linux/trace_seq.h | 2 ++ kernel/trace/trace.c | 10 +++++----- kernel/trace/trace_seq.c | 6 +++++- lib/seq_buf.c | 22 ++++++++++------------ 5 files changed, 23 insertions(+), 22 deletions(-) diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index 515d7fcb9634..a0fb013cebdf 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -14,19 +14,16 @@ * @buffer: pointer to the buffer * @size: size of the buffer * @len: the amount of data inside the buffer - * @readpos: The next position to read in the buffer. */ struct seq_buf { char *buffer; size_t size; size_t len; - loff_t readpos; }; static inline void seq_buf_clear(struct seq_buf *s) { s->len = 0; - s->readpos = 0; } static inline void @@ -143,7 +140,7 @@ extern __printf(2, 0) int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args); extern int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s); extern int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, - int cnt); + size_t start, int cnt); extern int seq_buf_puts(struct seq_buf *s, const char *str); extern int seq_buf_putc(struct seq_buf *s, unsigned char c); extern int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len); diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 6be92bf559fe..3691e0e76a1a 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -14,6 +14,7 @@ struct trace_seq { char buffer[PAGE_SIZE]; struct seq_buf seq; + size_t readpos; int full; }; @@ -22,6 +23,7 @@ trace_seq_init(struct trace_seq *s) { seq_buf_init(&s->seq, s->buffer, PAGE_SIZE); s->full = 0; + s->readpos = 0; } /** diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 24c995d1dab2..d278b1df6286 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1731,15 +1731,15 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) { int len; - if (trace_seq_used(s) <= s->seq.readpos) + if (trace_seq_used(s) <= s->readpos) return -EBUSY; - len = trace_seq_used(s) - s->seq.readpos; + len = trace_seq_used(s) - s->readpos; if (cnt > len) cnt = len; - memcpy(buf, s->buffer + s->seq.readpos, cnt); + memcpy(buf, s->buffer + s->readpos, cnt); - s->seq.readpos += cnt; + s->readpos += cnt; return cnt; } @@ -7014,7 +7014,7 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, /* Now copy what we have to the user */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); - if (iter->seq.seq.readpos >= trace_seq_used(&iter->seq)) + if (iter->seq.readpos >= trace_seq_used(&iter->seq)) trace_seq_init(&iter->seq); /* diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index bac06ee3b98b..7be97229ddf8 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -370,8 +370,12 @@ EXPORT_SYMBOL_GPL(trace_seq_path); */ int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt) { + int ret; __trace_seq_init(s); - return seq_buf_to_user(&s->seq, ubuf, cnt); + ret = seq_buf_to_user(&s->seq, ubuf, s->readpos, cnt); + if (ret > 0) + s->readpos += ret; + return ret; } EXPORT_SYMBOL_GPL(trace_seq_to_user); diff --git a/lib/seq_buf.c b/lib/seq_buf.c index 45c450f423fa..b7477aefff53 100644 --- a/lib/seq_buf.c +++ b/lib/seq_buf.c @@ -324,23 +324,24 @@ int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc) * seq_buf_to_user - copy the sequence buffer to user space * @s: seq_buf descriptor * @ubuf: The userspace memory location to copy to + * @start: The first byte in the buffer to copy * @cnt: The amount to copy * * Copies the sequence buffer into the userspace memory pointed to - * by @ubuf. It starts from the last read position (@s->readpos) - * and writes up to @cnt characters or till it reaches the end of - * the content in the buffer (@s->len), which ever comes first. + * by @ubuf. It starts from @start and writes up to @cnt characters + * or until it reaches the end of the content in the buffer (@s->len), + * whichever comes first. * * On success, it returns a positive number of the number of bytes * it copied. * * On failure it returns -EBUSY if all of the content in the * sequence has been already read, which includes nothing in the - * sequence (@s->len == @s->readpos). + * sequence (@s->len == @start). * * Returns -EFAULT if the copy to userspace fails. */ -int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, int cnt) +int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, size_t start, int cnt) { int len; int ret; @@ -350,20 +351,17 @@ int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, int cnt) len = seq_buf_used(s); - if (len <= s->readpos) + if (len <= start) return -EBUSY; - len -= s->readpos; + len -= start; if (cnt > len) cnt = len; - ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt); + ret = copy_to_user(ubuf, s->buffer + start, cnt); if (ret == cnt) return -EFAULT; - cnt -= ret; - - s->readpos += cnt; - return cnt; + return cnt - ret; } /** -- 2.25.1

From: Kees Cook <keescook@chromium.org> stable inclusion from stable-v6.6.70 commit 6920e362bc080d045dd1eca431c7819f22014a81 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBJ835 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit dcc4e5728eeaeda84878ca0018758cff1abfca21 ] Solve two ergonomic issues with struct seq_buf; 1) Too much boilerplate is required to initialize: struct seq_buf s; char buf[32]; seq_buf_init(s, buf, sizeof(buf)); Instead, we can build this directly on the stack. Provide DECLARE_SEQ_BUF() macro to do this: DECLARE_SEQ_BUF(s, 32); 2) %NUL termination is fragile and requires 2 steps to get a valid C String (and is a layering violation exposing the "internals" of seq_buf): seq_buf_terminate(s); do_something(s->buffer); Instead, we can just return s->buffer directly after terminating it in the refactored seq_buf_terminate(), now known as seq_buf_str(): do_something(seq_buf_str(s)); Link: https://lore.kernel.org/linux-trace-kernel/20231027155634.make.260-kees@kern... Link: https://lore.kernel.org/linux-trace-kernel/20231026194033.it.702-kees@kernel... Cc: Yosry Ahmed <yosryahmed@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Justin Stitt <justinstitt@google.com> Cc: Kent Overstreet <kent.overstreet@linux.dev> Cc: Petr Mladek <pmladek@suse.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Yun Zhou <yun.zhou@windriver.com> Cc: Jacob Keller <jacob.e.keller@intel.com> Cc: Zhen Lei <thunder.leizhen@huawei.com> Signed-off-by: Kees Cook <keescook@chromium.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> Stable-dep-of: afd2627f727b ("tracing: Check "%s" dereference via the field and not the TP_printk format") Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Li Huafei <lihuafei1@huawei.com> --- include/linux/seq_buf.h | 21 +++++++++++++++++---- kernel/trace/trace.c | 11 +---------- lib/seq_buf.c | 4 +--- 3 files changed, 19 insertions(+), 17 deletions(-) diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index a0fb013cebdf..d9db59f420a4 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -21,9 +21,18 @@ struct seq_buf { size_t len; }; +#define DECLARE_SEQ_BUF(NAME, SIZE) \ + char __ ## NAME ## _buffer[SIZE] = ""; \ + struct seq_buf NAME = { \ + .buffer = &__ ## NAME ## _buffer, \ + .size = SIZE, \ + } + static inline void seq_buf_clear(struct seq_buf *s) { s->len = 0; + if (s->size) + s->buffer[0] = '\0'; } static inline void @@ -69,8 +78,8 @@ static inline unsigned int seq_buf_used(struct seq_buf *s) } /** - * seq_buf_terminate - Make sure buffer is nul terminated - * @s: the seq_buf descriptor to terminate. + * seq_buf_str - get %NUL-terminated C string from seq_buf + * @s: the seq_buf handle * * This makes sure that the buffer in @s is nul terminated and * safe to read as a string. @@ -81,16 +90,20 @@ static inline unsigned int seq_buf_used(struct seq_buf *s) * * After this function is called, s->buffer is safe to use * in string operations. + * + * Returns @s->buf after making sure it is terminated. */ -static inline void seq_buf_terminate(struct seq_buf *s) +static inline const char *seq_buf_str(struct seq_buf *s) { if (WARN_ON(s->size == 0)) - return; + return ""; if (seq_buf_buffer_left(s)) s->buffer[s->len] = 0; else s->buffer[s->size - 1] = 0; + + return s->buffer; } /** diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d278b1df6286..88027b3b8158 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3810,15 +3810,6 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str, return false; } -static const char *show_buffer(struct trace_seq *s) -{ - struct seq_buf *seq = &s->seq; - - seq_buf_terminate(seq); - - return seq->buffer; -} - static DEFINE_STATIC_KEY_FALSE(trace_no_verify); static int test_can_verify_check(const char *fmt, ...) @@ -3958,7 +3949,7 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, */ if (WARN_ONCE(!trace_safe_str(iter, str, star, len), "fmt: '%s' current_buffer: '%s'", - fmt, show_buffer(&iter->seq))) { + fmt, seq_buf_str(&iter->seq.seq))) { int ret; /* Try to safely read the string */ diff --git a/lib/seq_buf.c b/lib/seq_buf.c index b7477aefff53..23518f77ea9c 100644 --- a/lib/seq_buf.c +++ b/lib/seq_buf.c @@ -109,9 +109,7 @@ void seq_buf_do_printk(struct seq_buf *s, const char *lvl) if (s->size == 0 || s->len == 0) return; - seq_buf_terminate(s); - - start = s->buffer; + start = seq_buf_str(s); while ((lf = strchr(start, '\n'))) { int len = lf - start + 1; -- 2.25.1

From: Steven Rostedt <rostedt@goodmis.org> stable inclusion from stable-v6.6.68 commit cc2c77b3518619acb26e15d9828abac547cef144 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBJ835 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- commit 917110481f6bc1c96b1e54b62bb114137fbc6d17 upstream. The process_pointer() helper function looks to see if various trace event macros are used. These macros are for storing data in the event. This makes it safe to dereference as the dereference will then point into the event on the ring buffer where the content of the data stays with the event itself. A few helper functions were missing. Those were: __get_rel_dynamic_array() __get_dynamic_array_len() __get_rel_dynamic_array_len() __get_rel_sockaddr() Also add a helper function find_print_string() to not need to use a middle man variable to test if the string exists. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: https://lore.kernel.org/20241217024720.521836792@goodmis.org Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers") Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Li Huafei <lihuafei1@huawei.com> --- kernel/trace/trace_events.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index aab8143fb720..6b48d8a0fba7 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -274,6 +274,15 @@ static bool test_field(const char *fmt, struct trace_event_call *call) return false; } +/* Look for a string within an argument */ +static bool find_print_string(const char *arg, const char *str, const char *end) +{ + const char *r; + + r = strstr(arg, str); + return r && r < end; +} + /* Return true if the argument pointer is safe */ static bool process_pointer(const char *fmt, int len, struct trace_event_call *call) { @@ -292,9 +301,17 @@ static bool process_pointer(const char *fmt, int len, struct trace_event_call *c a = strchr(fmt, '&'); if ((a && (a < r)) || test_field(r, call)) return true; - } else if ((r = strstr(fmt, "__get_dynamic_array(")) && r < e) { + } else if (find_print_string(fmt, "__get_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_sockaddr(", e)) { return true; - } else if ((r = strstr(fmt, "__get_sockaddr(")) && r < e) { + } else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) { return true; } return false; -- 2.25.1

From: Steven Rostedt <rostedt@goodmis.org> stable inclusion from stable-v6.6.70 commit f452f397f9a6a605989e4151078ab76b41d490cc category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBJ835 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit afd2627f727b89496d79a6b934a025fc916d4ded ] The TP_printk() portion of a trace event is executed at the time a event is read from the trace. This can happen seconds, minutes, hours, days, months, years possibly later since the event was recorded. If the print format contains a dereference to a string via "%s", and that string was allocated, there's a chance that string could be freed before it is read by the trace file. To protect against such bugs, there are two functions that verify the event. The first one is test_event_printk(), which is called when the event is created. It reads the TP_printk() format as well as its arguments to make sure nothing may be dereferencing a pointer that was not copied into the ring buffer along with the event. If it is, it will trigger a WARN_ON(). For strings that use "%s", it is not so easy. The string may not reside in the ring buffer but may still be valid. Strings that are static and part of the kernel proper which will not be freed for the life of the running system, are safe to dereference. But to know if it is a pointer to a static string or to something on the heap can not be determined until the event is triggered. This brings us to the second function that tests for the bad dereferencing of strings, trace_check_vprintf(). It would walk through the printf format looking for "%s", and when it finds it, it would validate that the pointer is safe to read. If not, it would produces a WARN_ON() as well and write into the ring buffer "[UNSAFE-MEMORY]". The problem with this is how it used va_list to have vsnprintf() handle all the cases that it didn't need to check. Instead of re-implementing vsnprintf(), it would make a copy of the format up to the %s part, and call vsnprintf() with the current va_list ap variable, where the ap would then be ready to point at the string in question. For architectures that passed va_list by reference this was possible. For architectures that passed it by copy it was not. A test_can_verify() function was used to differentiate between the two, and if it wasn't possible, it would disable it. Even for architectures where this was feasible, it was a stretch to rely on such a method that is undocumented, and could cause issues later on with new optimizations of the compiler. Instead, the first function test_event_printk() was updated to look at "%s" as well. If the "%s" argument is a pointer outside the event in the ring buffer, it would find the field type of the event that is the problem and mark the structure with a new flag called "needs_test". The event itself will be marked by TRACE_EVENT_FL_TEST_STR to let it be known that this event has a field that needs to be verified before the event can be printed using the printf format. When the event fields are created from the field type structure, the fields would copy the field type's "needs_test" value. Finally, before being printed, a new function ignore_event() is called which will check if the event has the TEST_STR flag set (if not, it returns false). If the flag is set, it then iterates through the events fields looking for the ones that have the "needs_test" flag set. Then it uses the offset field from the field structure to find the pointer in the ring buffer event. It runs the tests to make sure that pointer is safe to print and if not, it triggers the WARN_ON() and also adds to the trace output that the event in question has an unsafe memory access. The ignore_event() makes the trace_check_vprintf() obsolete so it is removed. Link: https://lore.kernel.org/all/CAHk-=wh3uOnqnZPpR0PeLZZtyWbZLboZ7cHLCKRWsocvs9Y... Cc: stable@vger.kernel.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: https://lore.kernel.org/20241217024720.848621576@goodmis.org Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers") Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> Signed-off-by: Sasha Levin <sashal@kernel.org> Conflicts: include/linux/trace_events.h kernel/trace/trace.c [ 1. Conflicts caused by KABI reservation of the ftrace_event_field structure. 2. On LTS-6.6, the modifications of the following dependency patches will be reverted by the current patch: - 680c07fabc2b ("tracing: Handle old buffer mappings for event strings and functions") - 55841e8820b9 ("tracing: Fix trace_check_vprintf() when tp_printk is used") And merging these two patches would cause an individual commit to fail compilation. Therefore, we decided not to backport these patches and resolved the conflicts manually. ] Signed-off-by: Li Huafei <lihuafei1@huawei.com> --- include/linux/trace_events.h | 6 +- kernel/trace/trace.c | 214 +++++++++-------------------------- kernel/trace/trace.h | 6 +- kernel/trace/trace_events.c | 32 ++++-- kernel/trace/trace_output.c | 6 +- 5 files changed, 91 insertions(+), 173 deletions(-) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 54ade3cea56e..e6cb294f03b4 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -280,7 +280,8 @@ struct trace_event_fields { const char *name; const int size; const int align; - const int is_signed; + const unsigned int is_signed:1; + unsigned int needs_test:1; const int filter_type; const int len; }; @@ -332,6 +333,7 @@ enum { TRACE_EVENT_FL_EPROBE_BIT, TRACE_EVENT_FL_FPROBE_BIT, TRACE_EVENT_FL_CUSTOM_BIT, + TRACE_EVENT_FL_TEST_STR_BIT, }; /* @@ -349,6 +351,7 @@ enum { * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) * This is set when the custom event has not been attached * to a tracepoint yet, then it is cleared when it is. + * TEST_STR - The event has a "%s" that points to a string outside the event */ enum { TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), @@ -362,6 +365,7 @@ enum { TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT), TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), + TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 88027b3b8158..10aace4d26e7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3760,17 +3760,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter) } /* Returns true if the string is safe to dereference from an event */ -static bool trace_safe_str(struct trace_iterator *iter, const char *str, - bool star, int len) +static bool trace_safe_str(struct trace_iterator *iter, const char *str) { unsigned long addr = (unsigned long)str; struct trace_event *trace_event; struct trace_event_call *event; - /* Ignore strings with no length */ - if (star && !len) - return true; - /* OK if part of the event data */ if ((addr >= (unsigned long)iter->ent) && (addr < (unsigned long)iter->ent + iter->ent_size)) @@ -3810,133 +3805,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str, return false; } -static DEFINE_STATIC_KEY_FALSE(trace_no_verify); - -static int test_can_verify_check(const char *fmt, ...) -{ - char buf[16]; - va_list ap; - int ret; - - /* - * The verifier is dependent on vsnprintf() modifies the va_list - * passed to it, where it is sent as a reference. Some architectures - * (like x86_32) passes it by value, which means that vsnprintf() - * does not modify the va_list passed to it, and the verifier - * would then need to be able to understand all the values that - * vsnprintf can use. If it is passed by value, then the verifier - * is disabled. - */ - va_start(ap, fmt); - vsnprintf(buf, 16, "%d", ap); - ret = va_arg(ap, int); - va_end(ap); - - return ret; -} - -static void test_can_verify(void) -{ - if (!test_can_verify_check("%d %d", 0, 1)) { - pr_info("trace event string verifier disabled\n"); - static_branch_inc(&trace_no_verify); - } -} - /** - * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer + * ignore_event - Check dereferenced fields while writing to the seq buffer * @iter: The iterator that holds the seq buffer and the event being printed - * @fmt: The format used to print the event - * @ap: The va_list holding the data to print from @fmt. * - * This writes the data into the @iter->seq buffer using the data from - * @fmt and @ap. If the format has a %s, then the source of the string - * is examined to make sure it is safe to print, otherwise it will - * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string - * pointer. + * At boot up, test_event_printk() will flag any event that dereferences + * a string with "%s" that does exist in the ring buffer. It may still + * be valid, as the string may point to a static string in the kernel + * rodata that never gets freed. But if the string pointer is pointing + * to something that was allocated, there's a chance that it can be freed + * by the time the user reads the trace. This would cause a bad memory + * access by the kernel and possibly crash the system. + * + * This function will check if the event has any fields flagged as needing + * to be checked at runtime and perform those checks. + * + * If it is found that a field is unsafe, it will write into the @iter->seq + * a message stating what was found to be unsafe. + * + * @return: true if the event is unsafe and should be ignored, + * false otherwise. */ -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) +bool ignore_event(struct trace_iterator *iter) { - const char *p = fmt; - const char *str; - int i, j; + struct ftrace_event_field *field; + struct trace_event *trace_event; + struct trace_event_call *event; + struct list_head *head; + struct trace_seq *seq; + const void *ptr; - if (WARN_ON_ONCE(!fmt)) - return; + trace_event = ftrace_find_event(iter->ent->type); - if (static_branch_unlikely(&trace_no_verify)) - goto print; + seq = &iter->seq; - /* Don't bother checking when doing a ftrace_dump() */ - if (iter->fmt == static_fmt_buf) - goto print; + if (!trace_event) { + trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type); + return true; + } - while (*p) { - bool star = false; - int len = 0; - - j = 0; - - /* We only care about %s and variants */ - for (i = 0; p[i]; i++) { - if (i + 1 >= iter->fmt_size) { - /* - * If we can't expand the copy buffer, - * just print it. - */ - if (!trace_iter_expand_format(iter)) - goto print; - } + event = container_of(trace_event, struct trace_event_call, event); + if (!(event->flags & TRACE_EVENT_FL_TEST_STR)) + return false; - if (p[i] == '\\' && p[i+1]) { - i++; - continue; - } - if (p[i] == '%') { - /* Need to test cases like %08.*s */ - for (j = 1; p[i+j]; j++) { - if (isdigit(p[i+j]) || - p[i+j] == '.') - continue; - if (p[i+j] == '*') { - star = true; - continue; - } - break; - } - if (p[i+j] == 's') - break; - star = false; - } - j = 0; - } - /* If no %s found then just print normally */ - if (!p[i]) - break; + head = trace_get_fields(event); + if (!head) { + trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n", + trace_event_name(event)); + return true; + } - /* Copy up to the %s, and print that */ - strncpy(iter->fmt, p, i); - iter->fmt[i] = '\0'; - trace_seq_vprintf(&iter->seq, iter->fmt, ap); + /* Offsets are from the iter->ent that points to the raw event */ + ptr = iter->ent; - /* - * If iter->seq is full, the above call no longer guarantees - * that ap is in sync with fmt processing, and further calls - * to va_arg() can return wrong positional arguments. - * - * Ensure that ap is no longer used in this case. - */ - if (iter->seq.full) { - p = ""; - break; - } + list_for_each_entry(field, head, link) { + const char *str; + bool good; + + if (!field->needs_test) + continue; - if (star) - len = va_arg(ap, int); + str = *(const char **)(ptr + field->offset); - /* The ap now points to the string data of the %s */ - str = va_arg(ap, const char *); + good = trace_safe_str(iter, str); /* * If you hit this warning, it is likely that the @@ -3947,45 +3878,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, * instead. See samples/trace_events/trace-events-sample.h * for reference. */ - if (WARN_ONCE(!trace_safe_str(iter, str, star, len), - "fmt: '%s' current_buffer: '%s'", - fmt, seq_buf_str(&iter->seq.seq))) { - int ret; - - /* Try to safely read the string */ - if (star) { - if (len + 1 > iter->fmt_size) - len = iter->fmt_size - 1; - if (len < 0) - len = 0; - ret = copy_from_kernel_nofault(iter->fmt, str, len); - iter->fmt[len] = 0; - star = false; - } else { - ret = strncpy_from_kernel_nofault(iter->fmt, str, - iter->fmt_size); - } - if (ret < 0) - trace_seq_printf(&iter->seq, "(0x%px)", str); - else - trace_seq_printf(&iter->seq, "(0x%px:%s)", - str, iter->fmt); - str = "[UNSAFE-MEMORY]"; - strcpy(iter->fmt, "%s"); - } else { - strncpy(iter->fmt, p + i, j + 1); - iter->fmt[j+1] = '\0'; + if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'", + trace_event_name(event), field->name)) { + trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n", + trace_event_name(event), field->name); + return true; } - if (star) - trace_seq_printf(&iter->seq, iter->fmt, len, str); - else - trace_seq_printf(&iter->seq, iter->fmt, str); - - p += i + j + 1; } - print: - if (*p) - trace_seq_vprintf(&iter->seq, p, ap); + return false; } const char *trace_event_format(struct trace_iterator *iter, const char *fmt) @@ -10533,8 +10433,6 @@ __init static int tracer_alloc_buffers(void) register_snapshot_cmd(); - test_can_verify(); - return 0; out_free_pipe_cpumask: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3ff785aa9444..2af084b67fa0 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -648,9 +648,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, bool trace_is_tracepoint_string(const char *str); const char *trace_event_format(struct trace_iterator *iter, const char *fmt); -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) __printf(2, 0); char *trace_iter_expand_format(struct trace_iterator *iter); +bool ignore_event(struct trace_iterator *iter); int trace_empty(struct trace_iterator *iter); @@ -1329,7 +1328,8 @@ struct ftrace_event_field { int filter_type; int offset; int size; - int is_signed; + unsigned int is_signed:1; + unsigned int needs_test:1; int len; KABI_RESERVE(1) KABI_RESERVE(2) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 64cd856308e7..0b7eb6f230ed 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system) } static struct ftrace_event_field * -__find_event_field(struct list_head *head, char *name) +__find_event_field(struct list_head *head, const char *name) { struct ftrace_event_field *field; @@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name) static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, - int is_signed, int filter_type, int len) + int is_signed, int filter_type, int len, + int need_test) { struct ftrace_event_field *field; @@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type, field->offset = offset; field->size = size; field->is_signed = is_signed; + field->needs_test = need_test; field->len = len; list_add(&field->link, head); @@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type, head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, 0); + is_signed, filter_type, 0, 0); } EXPORT_SYMBOL_GPL(trace_define_field); static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, - int filter_type, int len) + int filter_type, int len, int need_test) { struct list_head *head; @@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, len); + is_signed, filter_type, len, need_test); } #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ - filter_type, 0); \ + filter_type, 0, 0); \ if (ret) \ return ret; @@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ - is_signed_type(type), FILTER_OTHER, 0); \ + is_signed_type(type), FILTER_OTHER, \ + 0, 0); \ if (ret) \ return ret; @@ -332,6 +335,7 @@ static bool process_pointer(const char *fmt, int len, struct trace_event_call *c /* Return true if the string is safe */ static bool process_string(const char *fmt, int len, struct trace_event_call *call) { + struct trace_event_fields *field; const char *r, *e, *s; e = fmt + len; @@ -372,8 +376,16 @@ static bool process_string(const char *fmt, int len, struct trace_event_call *ca if (process_pointer(fmt, len, call)) return true; - /* Make sure the field is found, and consider it OK for now if it is */ - return find_event_field(fmt, call) != NULL; + /* Make sure the field is found */ + field = find_event_field(fmt, call); + if (!field) + return false; + + /* Test this field's string before printing the event */ + call->flags |= TRACE_EVENT_FL_TEST_STR; + field->needs_test = 1; + + return true; } /* @@ -2552,7 +2564,7 @@ event_define_fields(struct trace_event_call *call) ret = trace_define_field_ext(call, field->type, field->name, offset, field->size, field->is_signed, field->filter_type, - field->len); + field->len, field->needs_test); if (WARN_ON_ONCE(ret)) { pr_err("error code is %d\n", ret); break; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index db575094c498..2b948d35fb59 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -317,10 +317,14 @@ EXPORT_SYMBOL(trace_raw_output_prep); void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...) { + struct trace_seq *s = &iter->seq; va_list ap; + if (ignore_event(iter)) + return; + va_start(ap, fmt); - trace_check_vprintf(iter, trace_event_format(iter, fmt), ap); + trace_seq_vprintf(s, trace_event_format(iter, fmt), ap); va_end(ap); } EXPORT_SYMBOL(trace_event_printf); -- 2.25.1

From: Nathan Lynch <nathanl@linux.ibm.com> stable inclusion from stable-v6.6.70 commit c3b5a7d6a13baa7e5d6deadb929da20809b345e8 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBJ835 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit 7a8e9cdf9405819105ae7405cd91e482bf574b01 ] Using the address operator on the array doesn't work: ./include/linux/seq_buf.h:27:27: error: initialization of ‘char *’ from incompatible pointer type ‘char (*)[128]’ [-Werror=incompatible-pointer-types] 27 | .buffer = &__ ## NAME ## _buffer, \ | ^ Apart from fixing that, we can improve DECLARE_SEQ_BUF() by using a compound literal to define the buffer array without attaching a name to it. This makes the macro a single statement, allowing constructs such as: static DECLARE_SEQ_BUF(my_seq_buf, MYSB_SIZE); to work as intended. Link: https://lkml.kernel.org/r/20240116-declare-seq-buf-fix-v1-1-915db4692f32@lin... Cc: stable@vger.kernel.org Acked-by: Kees Cook <keescook@chromium.org> Fixes: dcc4e5728eea ("seq_buf: Introduce DECLARE_SEQ_BUF and seq_buf_str()") Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Li Huafei <lihuafei1@huawei.com> --- include/linux/seq_buf.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index d9db59f420a4..468d8c5eef4a 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -22,9 +22,8 @@ struct seq_buf { }; #define DECLARE_SEQ_BUF(NAME, SIZE) \ - char __ ## NAME ## _buffer[SIZE] = ""; \ struct seq_buf NAME = { \ - .buffer = &__ ## NAME ## _buffer, \ + .buffer = (char[SIZE]) { 0 }, \ .size = SIZE, \ } -- 2.25.1