From dcbd1ac2668b5fa02069ea96d581ca3f70a7543c Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Fri, 19 May 2023 16:07:40 -0700 Subject: tracing/user_events: Rename link fields for clarity Currently most list_head fields of various structs within user_events are simply named link. This causes folks to keep additional context in their head when working with the code, which can be confusing. Instead of using link, describe what the actual link is, for example: list_del_rcu(&mm->link); Changes into: list_del_rcu(&mm->mms_link); The reader now is given a hint the link is to the mms global list instead of having to remember or spot check within the code. Link: https://lkml.kernel.org/r/20230519230741.669-4-beaub@linux.microsoft.com Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wicngggxVpbnrYHjRTwGE0WYscPRM+L2HO2BF8ia1EXgQ@mail.gmail.com/ Suggested-by: Linus Torvalds Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 2847f5a18a86..17d452b389de 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -17,7 +17,7 @@ #ifdef CONFIG_USER_EVENTS struct user_event_mm { - struct list_head link; + struct list_head mms_link; struct list_head enablers; struct mm_struct *mm; struct user_event_mm *next; -- cgit v1.2.3 From ff9e1632d69e596d8ca256deb07433a8f3565038 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Fri, 19 May 2023 16:07:41 -0700 Subject: tracing/user_events: Document user_event_mm one-shot list usage During 6.4 development it became clear that the one-shot list used by the user_event_mm's next field was confusing to others. It is not clear how this list is protected or what the next field usage is for unless you are familiar with the code. Add comments into the user_event_mm struct indicating lock requirement and usage. Also document how and why this approach was used via comments in both user_event_enabler_update() and user_event_mm_get_all() and the rules to properly use it. Link: https://lkml.kernel.org/r/20230519230741.669-5-beaub@linux.microsoft.com Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wicngggxVpbnrYHjRTwGE0WYscPRM+L2HO2BF8ia1EXgQ@mail.gmail.com/ Suggested-by: Linus Torvalds Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 1 + kernel/trace/trace_events_user.c | 23 ++++++++++++++++++++++- 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 17d452b389de..8afa8c3a0973 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -20,6 +20,7 @@ struct user_event_mm { struct list_head mms_link; struct list_head enablers; struct mm_struct *mm; + /* Used for one-shot lists, protected by event_mutex */ struct user_event_mm *next; refcount_t refcnt; refcount_t tasks; diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 238c7a0615fa..dbb14705d0d3 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -451,12 +451,25 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, static void user_event_enabler_update(struct user_event *user) { struct user_event_enabler *enabler; - struct user_event_mm *mm = user_event_mm_get_all(user); struct user_event_mm *next; + struct user_event_mm *mm; int attempt; lockdep_assert_held(&event_mutex); + /* + * We need to build a one-shot list of all the mms that have an + * enabler for the user_event passed in. This list is only valid + * while holding the event_mutex. The only reason for this is due + * to the global mm list being RCU protected and we use methods + * which can wait (mmap_read_lock and pin_user_pages_remote). + * + * NOTE: user_event_mm_get_all() increments the ref count of each + * mm that is added to the list to prevent removal timing windows. + * We must always put each mm after they are used, which may wait. + */ + mm = user_event_mm_get_all(user); + while (mm) { next = mm->next; mmap_read_lock(mm->mm); @@ -515,6 +528,14 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) struct user_event_enabler *enabler; struct user_event_mm *mm; + /* + * We use the mm->next field to build a one-shot list from the global + * RCU protected list. To build this list the event_mutex must be held. + * This lets us build a list without requiring allocs that could fail + * when user based events are most wanted for diagnostics. + */ + lockdep_assert_held(&event_mutex); + /* * We do not want to block fork/exec while enablements are being * updated, so we use RCU to walk the current tasks that have used -- cgit v1.2.3 From 4b512860bdbdddcf41467ebd394f27cb8dfb528c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 23 May 2023 23:09:13 -0400 Subject: tracing: Rename stacktrace field to common_stacktrace The histogram and synthetic events can use a pseudo event called "stacktrace" that will create a stacktrace at the time of the event and use it just like it was a normal field. We have other pseudo events such as "common_cpu" and "common_timestamp". To stay consistent with that, convert "stacktrace" to "common_stacktrace". As this was used in older kernels, to keep backward compatibility, this will act just like "common_cpu" did with "cpu". That is, "cpu" will be the same as "common_cpu" unless the event has a "cpu" field. In which case, the event's field is used. The same is true with "stacktrace". Also update the documentation to reflect this change. Link: https://lore.kernel.org/linux-trace-kernel/20230523230913.6860e28d@rorschach.local.home Cc: Masami Hiramatsu Cc: Tom Zanussi Cc: Mark Rutland Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/histogram.rst | 64 +++++++++++++++++++-------------------- include/linux/trace_events.h | 1 + kernel/trace/trace.c | 2 +- kernel/trace/trace_events.c | 2 ++ kernel/trace/trace_events_hist.c | 16 ++++++---- 5 files changed, 46 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 479c9eac6335..3c9b263de9c2 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -35,7 +35,7 @@ Documentation written by Tom Zanussi in place of an explicit value field - this is simply a count of event hits. If 'values' isn't specified, an implicit 'hitcount' value will be automatically created and used as the only value. - Keys can be any field, or the special string 'stacktrace', which + Keys can be any field, or the special string 'common_stacktrace', which will use the event's kernel stacktrace as the key. The keywords 'keys' or 'key' can be used to specify keys, and the keywords 'values', 'vals', or 'val' can be used to specify values. Compound @@ -54,7 +54,7 @@ Documentation written by Tom Zanussi 'compatible' if the fields named in the trigger share the same number and type of fields and those fields also have the same names. Note that any two events always share the compatible 'hitcount' and - 'stacktrace' fields and can therefore be combined using those + 'common_stacktrace' fields and can therefore be combined using those fields, however pointless that may be. 'hist' triggers add a 'hist' file to each event's subdirectory. @@ -547,9 +547,9 @@ Extended error information the hist trigger display symbolic call_sites, we can have the hist trigger additionally display the complete set of kernel stack traces that led to each call_site. To do that, we simply use the special - value 'stacktrace' for the key parameter:: + value 'common_stacktrace' for the key parameter:: - # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ + # echo 'hist:keys=common_stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ /sys/kernel/tracing/events/kmem/kmalloc/trigger The above trigger will use the kernel stack trace in effect when an @@ -561,9 +561,9 @@ Extended error information every callpath to a kmalloc for a kernel compile):: # cat /sys/kernel/tracing/events/kmem/kmalloc/hist - # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] + # trigger info: hist:keys=common_stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -581,7 +581,7 @@ Extended error information cpu_startup_entry+0x315/0x3e0 rest_init+0x7c/0x80 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -596,7 +596,7 @@ Extended error information do_IRQ+0x5a/0xf0 ret_from_intr+0x0/0x30 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 aa_alloc_task_context+0x27/0x40 apparmor_cred_prepare+0x1f/0x50 @@ -608,7 +608,7 @@ Extended error information . . . - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 i915_gem_execbuffer2+0x6c/0x2c0 [i915] drm_ioctl+0x349/0x670 [drm] @@ -616,7 +616,7 @@ Extended error information SyS_ioctl+0x81/0xa0 system_call_fastpath+0x12/0x6a } hitcount: 17726 bytes_req: 13944120 bytes_alloc: 19593808 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 load_elf_phdrs+0x76/0xa0 load_elf_binary+0x102/0x1650 @@ -625,7 +625,7 @@ Extended error information SyS_execve+0x3a/0x50 return_from_execve+0x0/0x23 } hitcount: 33348 bytes_req: 17152128 bytes_alloc: 20226048 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 apparmor_file_alloc_security+0x27/0x40 security_file_alloc+0x16/0x20 @@ -636,7 +636,7 @@ Extended error information SyS_open+0x1e/0x20 system_call_fastpath+0x12/0x6a } hitcount: 4766422 bytes_req: 9532844 bytes_alloc: 38131376 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 seq_buf_alloc+0x1b/0x50 seq_read+0x2cc/0x370 @@ -1026,7 +1026,7 @@ Extended error information First we set up an initially paused stacktrace trigger on the netif_receive_skb event:: - # echo 'hist:key=stacktrace:vals=len:pause' > \ + # echo 'hist:key=common_stacktrace:vals=len:pause' > \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Next, we set up an 'enable_hist' trigger on the sched_process_exec @@ -1060,9 +1060,9 @@ Extended error information $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1079,7 +1079,7 @@ Extended error information kthread+0xd2/0xf0 ret_from_fork+0x42/0x70 } hitcount: 85 len: 28884 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1097,7 +1097,7 @@ Extended error information irq_thread+0x11f/0x150 kthread+0xd2/0xf0 } hitcount: 98 len: 664329 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 process_backlog+0xa8/0x150 @@ -1115,7 +1115,7 @@ Extended error information inet_sendmsg+0x64/0xa0 sock_sendmsg+0x3d/0x50 } hitcount: 115 len: 13030 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1142,14 +1142,14 @@ Extended error information into the histogram. In order to avoid having to set everything up again, we can just clear the histogram first:: - # echo 'hist:key=stacktrace:vals=len:clear' >> \ + # echo 'hist:key=common_stacktrace:vals=len:clear' >> \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Just to verify that it is in fact cleared, here's what we now see in the hist file:: # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] Totals: Hits: 0 @@ -1485,12 +1485,12 @@ Extended error information And here's an example that shows how to combine histogram data from any two events even if they don't share any 'compatible' fields - other than 'hitcount' and 'stacktrace'. These commands create a + other than 'hitcount' and 'common_stacktrace'. These commands create a couple of triggers named 'bar' using those fields:: - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/sched/sched_process_fork/trigger - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/net/netif_rx/trigger And displaying the output of either shows some interesting if @@ -1501,16 +1501,16 @@ Extended error information # event histogram # - # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] + # trigger info: hist:name=bar:keys=common_stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] # - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 kernel_thread+0x29/0x30 kthreadd+0x154/0x1b0 ret_from_fork+0x3f/0x70 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1528,7 +1528,7 @@ Extended error information call_cpuidle+0x3b/0x60 cpu_startup_entry+0x22d/0x310 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1543,7 +1543,7 @@ Extended error information SyS_sendto+0xe/0x10 entry_SYSCALL_64_fastpath+0x12/0x6a } hitcount: 2 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1561,7 +1561,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x14e/0x270 } hitcount: 76 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1579,7 +1579,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x269/0x270 } hitcount: 77 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1597,7 +1597,7 @@ Extended error information sock_sendmsg+0x38/0x50 SYSC_sendto+0xef/0x170 } hitcount: 88 - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 SyS_clone+0x19/0x20 entry_SYSCALL_64_fastpath+0x12/0x6a @@ -1949,7 +1949,7 @@ uninterruptible state:: # cd /sys/kernel/tracing # echo 's:block_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events - # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger + # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger # echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(block_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger # echo 1 > events/synthetic/block_lat/enable # cat trace diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 0e373222a6df..7c4a0b72334e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -806,6 +806,7 @@ enum { FILTER_TRACE_FN, FILTER_COMM, FILTER_CPU, + FILTER_STACKTRACE, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ebc59781456a..81801dc31784 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5752,7 +5752,7 @@ static const char readme_msg[] = "\t table using the key(s) and value(s) named, and the value of a\n" "\t sum called 'hitcount' is incremented. Keys and values\n" "\t correspond to fields in the event's format description. Keys\n" - "\t can be any field, or the special string 'stacktrace'.\n" + "\t can be any field, or the special string 'common_stacktrace'.\n" "\t Compound keys consisting of up to two fields can be specified\n" "\t by the 'keys' keyword. Values must correspond to numeric\n" "\t fields. Sort keys consisting of up to two fields can be\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 654ffa40457a..57e539d47989 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -194,6 +194,8 @@ static int trace_define_generic_fields(void) __generic_field(int, common_cpu, FILTER_CPU); __generic_field(char *, COMM, FILTER_COMM); __generic_field(char *, comm, FILTER_COMM); + __generic_field(char *, stacktrace, FILTER_STACKTRACE); + __generic_field(char *, STACKTRACE, FILTER_STACKTRACE); return ret; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 543cb7dc84ad..b97d3ad832f1 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1364,7 +1364,7 @@ static const char *hist_field_name(struct hist_field *field, if (field->field) field_name = field->field->name; else - field_name = "stacktrace"; + field_name = "common_stacktrace"; } else if (field->flags & HIST_FIELD_FL_HITCOUNT) field_name = "hitcount"; @@ -2367,7 +2367,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, hist_data->enable_timestamps = true; if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS) hist_data->attrs->ts_in_usecs = true; - } else if (strcmp(field_name, "stacktrace") == 0) { + } else if (strcmp(field_name, "common_stacktrace") == 0) { *flags |= HIST_FIELD_FL_STACKTRACE; } else if (strcmp(field_name, "common_cpu") == 0) *flags |= HIST_FIELD_FL_CPU; @@ -2378,11 +2378,15 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, if (!field || !field->size) { /* * For backward compatibility, if field_name - * was "cpu", then we treat this the same as - * common_cpu. This also works for "CPU". + * was "cpu" or "stacktrace", then we treat this + * the same as common_cpu and common_stacktrace + * respectively. This also works for "CPU", and + * "STACKTRACE". */ if (field && field->filter_type == FILTER_CPU) { *flags |= HIST_FIELD_FL_CPU; + } else if (field && field->filter_type == FILTER_STACKTRACE) { + *flags |= HIST_FIELD_FL_STACKTRACE; } else { hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, errpos(field_name)); @@ -5394,7 +5398,7 @@ static void hist_trigger_print_key(struct seq_file *m, if (key_field->field) seq_printf(m, "%s.stacktrace", key_field->field->name); else - seq_puts(m, "stacktrace:\n"); + seq_puts(m, "common_stacktrace:\n"); hist_trigger_stacktrace_print(m, key + key_field->offset, HIST_STACKTRACE_DEPTH); @@ -5977,7 +5981,7 @@ static int event_hist_trigger_print(struct seq_file *m, if (field->field) seq_printf(m, "%s.stacktrace", field->field->name); else - seq_puts(m, "stacktrace"); + seq_puts(m, "common_stacktrace"); } else hist_field_print(m, field); } -- cgit v1.2.3 From ac2263b588dffd3a1efd7ed0b156ea6c5aea200d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 29 May 2023 06:40:33 -0400 Subject: Revert "module: error out early on concurrent load of the same module file" This reverts commit 9828ed3f695a138f7add89fa2a186ababceb8006. Sadly, it does seem to cause failures to load modules. Johan Hovold reports: "This change breaks module loading during boot on the Lenovo Thinkpad X13s (aarch64). Specifically it results in indefinite probe deferral of the display and USB (ethernet) which makes it a pain to debug. Typing in the dark to acquire some logs reveals that other modules are missing as well" Since this was applied late as a "let's try this", I'm reverting it asap, and we can try to figure out what goes wrong later. The excessive parallel module loading problem is annoying, but not noticeable in normal situations, and this was only meant as an optimistic workaround for a user-space bug. One possible solution may be to do the optimistic exclusive open first, and then use a lock to serialize loading if that fails. Reported-by: Johan Hovold Link: https://lore.kernel.org/lkml/ZHRpH-JXAxA6DnzR@hovoldconsulting.com/ Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ------ kernel/module/main.c | 58 ++++++++++++++-------------------------------------- 2 files changed, 15 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 86b50271b4f7..133f0640fb24 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2566,12 +2566,6 @@ static inline int deny_write_access(struct file *file) struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } -static inline int exclusive_deny_write_access(struct file *file) -{ - int old = 0; - struct inode *inode = file_inode(file); - return atomic_try_cmpxchg(&inode->i_writecount, &old, -1) ? 0 : -ETXTBSY; -} static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); diff --git a/kernel/module/main.c b/kernel/module/main.c index b4c7e925fdb0..044aa2c9e3cb 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -3057,13 +3057,25 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, return load_module(&info, uargs, 0); } -static int file_init_module(struct file *file, const char __user * uargs, int flags) +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) { struct load_info info = { }; void *buf = NULL; int len; + int err; + + err = may_init_module(); + if (err) + return err; + + pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - len = kernel_read_file(file, 0, &buf, INT_MAX, NULL, + if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS + |MODULE_INIT_IGNORE_VERMAGIC + |MODULE_INIT_COMPRESSED_FILE)) + return -EINVAL; + + len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, READING_MODULE); if (len < 0) { mod_stat_inc(&failed_kreads); @@ -3072,7 +3084,7 @@ static int file_init_module(struct file *file, const char __user * uargs, int fl } if (flags & MODULE_INIT_COMPRESSED_FILE) { - int err = module_decompress(&info, buf, len); + err = module_decompress(&info, buf, len); vfree(buf); /* compressed data is no longer needed */ if (err) { mod_stat_inc(&failed_decompress); @@ -3087,46 +3099,6 @@ static int file_init_module(struct file *file, const char __user * uargs, int fl return load_module(&info, uargs, flags); } -/* - * kernel_read_file() will already deny write access, but module - * loading wants _exclusive_ access to the file, so we do that - * here, along with basic sanity checks. - */ -static int prepare_file_for_module_load(struct file *file) -{ - if (!file || !(file->f_mode & FMODE_READ)) - return -EBADF; - if (!S_ISREG(file_inode(file)->i_mode)) - return -EINVAL; - return exclusive_deny_write_access(file); -} - -SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) -{ - struct fd f; - int err; - - err = may_init_module(); - if (err) - return err; - - pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - - if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS - |MODULE_INIT_IGNORE_VERMAGIC - |MODULE_INIT_COMPRESSED_FILE)) - return -EINVAL; - - f = fdget(fd); - err = prepare_file_for_module_load(f.file); - if (!err) { - err = file_init_module(f.file, uargs, flags); - allow_write_access(f.file); - } - fdput(f); - return err; -} - /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ char *module_flags(struct module *mod, char *buf, bool show_state) { -- cgit v1.2.3 From 54abe19e00cfcc5a72773d15cd00ed19ab763439 Mon Sep 17 00:00:00 2001 From: Rafael Aquini Date: Tue, 6 Jun 2023 19:36:13 -0400 Subject: writeback: fix dereferencing NULL mapping->host on writeback_page_template When commit 19343b5bdd16 ("mm/page-writeback: introduce tracepoint for wait_on_page_writeback()") repurposed the writeback_dirty_page trace event as a template to create its new wait_on_page_writeback trace event, it ended up opening a window to NULL pointer dereference crashes due to the (infrequent) occurrence of a race where an access to a page in the swap-cache happens concurrently with the moment this page is being written to disk and the tracepoint is enabled: BUG: kernel NULL pointer dereference, address: 0000000000000040 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 800000010ec0a067 P4D 800000010ec0a067 PUD 102353067 PMD 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 1320 Comm: shmem-worker Kdump: loaded Not tainted 6.4.0-rc5+ #13 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20230301gitf80f052277c8-1.fc37 03/01/2023 RIP: 0010:trace_event_raw_event_writeback_folio_template+0x76/0xf0 Code: 4d 85 e4 74 5c 49 8b 3c 24 e8 06 98 ee ff 48 89 c7 e8 9e 8b ee ff ba 20 00 00 00 48 89 ef 48 89 c6 e8 fe d4 1a 00 49 8b 04 24 <48> 8b 40 40 48 89 43 28 49 8b 45 20 48 89 e7 48 89 43 30 e8 a2 4d RSP: 0000:ffffaad580b6fb60 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff90e38035c01c RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff90e38035c044 RBP: ffff90e38035c024 R08: 0000000000000002 R09: 0000000000000006 R10: ffff90e38035c02e R11: 0000000000000020 R12: ffff90e380bac000 R13: ffffe3a7456d9200 R14: 0000000000001b81 R15: ffffe3a7456d9200 FS: 00007f2e4e8a15c0(0000) GS:ffff90e3fbc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000040 CR3: 00000001150c6003 CR4: 0000000000170ee0 Call Trace: ? __die+0x20/0x70 ? page_fault_oops+0x76/0x170 ? kernelmode_fixup_or_oops+0x84/0x110 ? exc_page_fault+0x65/0x150 ? asm_exc_page_fault+0x22/0x30 ? trace_event_raw_event_writeback_folio_template+0x76/0xf0 folio_wait_writeback+0x6b/0x80 shmem_swapin_folio+0x24a/0x500 ? filemap_get_entry+0xe3/0x140 shmem_get_folio_gfp+0x36e/0x7c0 ? find_busiest_group+0x43/0x1a0 shmem_fault+0x76/0x2a0 ? __update_load_avg_cfs_rq+0x281/0x2f0 __do_fault+0x33/0x130 do_read_fault+0x118/0x160 do_pte_missing+0x1ed/0x2a0 __handle_mm_fault+0x566/0x630 handle_mm_fault+0x91/0x210 do_user_addr_fault+0x22c/0x740 exc_page_fault+0x65/0x150 asm_exc_page_fault+0x22/0x30 This problem arises from the fact that the repurposed writeback_dirty_page trace event code was written assuming that every pointer to mapping (struct address_space) would come from a file-mapped page-cache object, thus mapping->host would always be populated, and that was a valid case before commit 19343b5bdd16. The swap-cache address space (swapper_spaces), however, doesn't populate its ->host (struct inode) pointer, thus leading to the crashes in the corner-case aforementioned. commit 19343b5bdd16 ended up breaking the assignment of __entry->name and __entry->ino for the wait_on_page_writeback tracepoint -- both dependent on mapping->host carrying a pointer to a valid inode. The assignment of __entry->name was fixed by commit 68f23b89067f ("memcg: fix a crash in wb_workfn when a device disappears"), and this commit fixes the remaining case, for __entry->ino. Link: https://lkml.kernel.org/r/20230606233613.1290819-1-aquini@redhat.com Fixes: 19343b5bdd16 ("mm/page-writeback: introduce tracepoint for wait_on_page_writeback()") Signed-off-by: Rafael Aquini Reviewed-by: Yafang Shao Cc: Aristeu Rozanski Cc: Signed-off-by: Andrew Morton --- include/trace/events/writeback.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 86b2a82da546..54e353c9f919 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -68,7 +68,7 @@ DECLARE_EVENT_CLASS(writeback_folio_template, strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); - __entry->ino = mapping ? mapping->host->i_ino : 0; + __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = folio->index; ), -- cgit v1.2.3