fanotify: disable readahead if we have pre-content watches

With page faults we can trigger readahead on the file, and then
subsequent faults can find these pages and insert them into the file
without emitting an fanotify event.  To avoid this case, disable
readahead if we have pre-content watches on the file.  This way we are
guaranteed to get an event for every range we attempt to access on a
pre-content watched file.

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/70a54e859f555e54bc7a47b32fe5aca92b085615.1731684329.git.josef@toxicpanda.com

diff --git a/mm/filemap.c b/mm/filemap.c
index 7c76a123ba18b362a94e5952f3b89f7061c6fb4d..e9a0f330d33ee0df58df428fbc03497d6466484a 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3150,6 +3150,14 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
        unsigned long vm_flags = vmf->vma->vm_flags;
        unsigned int mmap_miss;
 
+       /*
+        * If we have pre-content watches we need to disable readahead to make
+        * sure that we don't populate our mapping with 0 filled pages that we
+        * never emitted an event for.
+        */
+       if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode)))
+               return fpin;
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
        /* Use the readahead code, even if readahead is disabled */
        if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) {
@@ -3218,6 +3226,10 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
        struct file *fpin = NULL;
        unsigned int mmap_miss;
 
+       /* See comment in do_sync_mmap_readahead. */
+       if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode)))
+               return fpin;
+
        /* If we don't want any read-ahead, don't bother */
        if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages)
                return fpin;

diff --git a/mm/readahead.c b/mm/readahead.c
index 8f1cf599b5722513de1c162ce0fbb6f879c64e1a..1fa4710bdf89bc4ac130284ee3d406e89af32cd4 100644 (file)
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -128,6 +128,7 @@
 #include <linux/blk-cgroup.h>
 #include <linux/fadvise.h>
 #include <linux/sched/mm.h>
+#include <linux/fsnotify.h>
 
 #include "internal.h"
 
@@ -549,6 +550,15 @@ void page_cache_sync_ra(struct readahead_control *ractl,
        unsigned long max_pages, contig_count;
        pgoff_t prev_index, miss;
 
+       /*
+        * If we have pre-content watches we need to disable readahead to make
+        * sure that we don't find 0 filled pages in cache that we never emitted
+        * events for. Filesystems supporting HSM must make sure to not call
+        * this function with ractl->file unset for files handled by HSM.
+        */
+       if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode)))
+               return;
+
        /*
         * Even if readahead is disabled, issue this request as readahead
         * as we'll need it to satisfy the requested range. The forced
@@ -627,6 +637,10 @@ void page_cache_async_ra(struct readahead_control *ractl,
        if (!ra->ra_pages)
                return;
 
+       /* See the comment in page_cache_sync_ra. */
+       if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode)))
+               return;
+
        /*
         * Same bit is used for PG_readahead and PG_reclaim.
         */