From 079c24d5690262e83ee476e2a548e416f3237511 Mon Sep 17 00:00:00 2001 From: Kalesh Singh Date: Thu, 19 Feb 2026 15:36:56 -0800 Subject: mm/tracing: rss_stat: ensure curr is false from kthread context The rss_stat trace event allows userspace tools, like Perfetto [1], to inspect per-process RSS metric changes over time. The curr field was introduced to rss_stat in commit e4dcad204d3a ("rss_stat: add support to detect RSS updates of external mm"). Its intent is to indicate whether the RSS update is for the mm_struct of the current execution context; and is set to false when operating on a remote mm_struct (e.g., via kswapd or a direct reclaimer). However, an issue arises when a kernel thread temporarily adopts a user process's mm_struct. Kernel threads do not have their own mm_struct and normally have current->mm set to NULL. To operate on user memory, they can "borrow" a memory context using kthread_use_mm(), which sets current->mm to the user process's mm. This can be observed, for example, in the USB Function Filesystem (FFS) driver. The ffs_user_copy_worker() handles AIO completions and uses kthread_use_mm() to copy data to a user-space buffer. If a page fault occurs during this copy, the fault handler executes in the kthread's context. At this point, current is the kthread, but current->mm points to the user process's mm. Since the rss_stat event (from the page fault) is for that same mm, the condition current->mm == mm becomes true, causing curr to be incorrectly set to true when the trace event is emitted. This is misleading because it suggests the mm belongs to the kthread, confusing userspace tools that track per-process RSS changes and corrupting their mm_id-to-process association. Fix this by ensuring curr is always false when the trace event is emitted from a kthread context by checking for the PF_KTHREAD flag. Link: https://lkml.kernel.org/r/20260219233708.1971199-1-kaleshsingh@google.com Link: https://perfetto.dev/ [1] Fixes: e4dcad204d3a ("rss_stat: add support to detect RSS updates of external mm") Signed-off-by: Kalesh Singh Acked-by: Zi Yan Acked-by: SeongJae Park Reviewed-by: Pedro Falcato Cc: "David Hildenbrand (Arm)" Cc: Joel Fernandes Cc: Lorenzo Stoakes Cc: Minchan Kim Cc: Steven Rostedt Cc: Suren Baghdasaryan Cc: [5.10+] Signed-off-by: Andrew Morton --- include/trace/events/kmem.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 7f93e754da5c..cd7920c81f85 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -440,7 +440,13 @@ TRACE_EVENT(rss_stat, TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); - __entry->curr = !!(current->mm == mm); + /* + * curr is true if the mm matches the current task's mm_struct. + * Since kthreads (PF_KTHREAD) have no mm_struct of their own + * but can borrow one via kthread_use_mm(), we must filter them + * out to avoid incorrectly attributing the RSS update to them. + */ + __entry->curr = current->mm == mm && !(current->flags & PF_KTHREAD); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); -- cgit v1.2.3 From a0b4c7a49137ed21279f354eb59f49ddae8dffc2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 26 Feb 2026 13:32:33 +0000 Subject: netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict sequence Fix netfslib such that when it's making an unbuffered or DIO write, to make sure that it sends each subrequest strictly sequentially, waiting till the previous one is 'committed' before sending the next so that we don't have pieces landing out of order and potentially leaving a hole if an error occurs (ENOSPC for example). This is done by copying in just those bits of issuing, collecting and retrying subrequests that are necessary to do one subrequest at a time. Retrying, in particular, is simpler because if the current subrequest needs retrying, the source iterator can just be copied again and the subrequest prepped and issued again without needing to be concerned about whether it needs merging with the previous or next in the sequence. Note that the issuing loop waits for a subrequest to complete right after issuing it, but this wait could be moved elsewhere allowing preparatory steps to be performed whilst the subrequest is in progress. In particular, once content encryption is available in netfslib, that could be done whilst waiting, as could cleanup of buffers that have been completed. Fixes: 153a9961b551 ("netfs: Implement unbuffered/DIO write support") Signed-off-by: David Howells Link: https://patch.msgid.link/58526.1772112753@warthog.procyon.org.uk Tested-by: Steve French Reviewed-by: Paulo Alcantara (Red Hat) cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- include/trace/events/netfs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 64a382fbc31a..2d366be46a1c 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -57,6 +57,7 @@ EM(netfs_rreq_trace_done, "DONE ") \ EM(netfs_rreq_trace_end_copy_to_cache, "END-C2C") \ EM(netfs_rreq_trace_free, "FREE ") \ + EM(netfs_rreq_trace_intr, "INTR ") \ EM(netfs_rreq_trace_ki_complete, "KI-CMPL") \ EM(netfs_rreq_trace_recollect, "RECLLCT") \ EM(netfs_rreq_trace_redirty, "REDIRTY") \ @@ -169,7 +170,8 @@ EM(netfs_sreq_trace_put_oom, "PUT OOM ") \ EM(netfs_sreq_trace_put_wip, "PUT WIP ") \ EM(netfs_sreq_trace_put_work, "PUT WORK ") \ - E_(netfs_sreq_trace_put_terminated, "PUT TERM ") + EM(netfs_sreq_trace_put_terminated, "PUT TERM ") \ + E_(netfs_sreq_trace_see_failed, "SEE FAILED ") #define netfs_folio_traces \ EM(netfs_folio_is_uptodate, "mod-uptodate") \ -- cgit v1.2.3