On Fri, Aug 09, 2024 at 12:34:34PM +0200, Amir Goldstein wrote:
> On Thu, Aug 8, 2024 at 9:28 PM Josef Bacik <josef@xxxxxxxxxxxxxx> wrote:
> >
> > FS_PRE_ACCESS or FS_PRE_MODIFY will be generated on page fault depending
> > on the faulting method.
> >
> > This pre-content event is meant to be used by hierarchical storage
> > managers that want to fill in the file content on first read access.
> >
> > Signed-off-by: Josef Bacik <josef@xxxxxxxxxxxxxx>
> > ---
> > include/linux/mm.h | 2 +
> > mm/filemap.c | 97 ++++++++++++++++++++++++++++++++++++++++++----
> > 2 files changed, 92 insertions(+), 7 deletions(-)
> >
> > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > index ab3d78116043..c33f3b7f7261 100644
> > --- a/include/linux/mm.h
> > +++ b/include/linux/mm.h
> > @@ -3503,6 +3503,8 @@ extern vm_fault_t filemap_fault(struct vm_fault *vmf);
> > extern vm_fault_t filemap_map_pages(struct vm_fault *vmf,
> > pgoff_t start_pgoff, pgoff_t end_pgoff);
> > extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
> > +extern vm_fault_t filemap_maybe_emit_fsnotify_event(struct vm_fault *vmf,
> > + struct file **fpin);
> >
> > extern unsigned long stack_guard_gap;
> > /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
> > diff --git a/mm/filemap.c b/mm/filemap.c
> > index 8b1684b62177..3d232166b051 100644
> > --- a/mm/filemap.c
> > +++ b/mm/filemap.c
> > @@ -46,6 +46,7 @@
> > #include <linux/pipe_fs_i.h>
> > #include <linux/splice.h>
> > #include <linux/rcupdate_wait.h>
> > +#include <linux/fsnotify.h>
> > #include <asm/pgalloc.h>
> > #include <asm/tlbflush.h>
> > #include "internal.h"
> > @@ -3112,13 +3113,13 @@ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio,
> > * that. If we didn't pin a file then we return NULL. The file that is
> > * returned needs to be fput()'ed when we're done with it.
> > */
> > -static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
> > +static struct file *do_sync_mmap_readahead(struct vm_fault *vmf,
> > + struct file *fpin)
> > {
> > struct file *file = vmf->vma->vm_file;
> > struct file_ra_state *ra = &file->f_ra;
> > struct address_space *mapping = file->f_mapping;
> > DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff);
> > - struct file *fpin = NULL;
> > unsigned long vm_flags = vmf->vma->vm_flags;
> > unsigned int mmap_miss;
> >
> > @@ -3190,12 +3191,12 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
> > * was pinned if we have to drop the mmap_lock in order to do IO.
> > */
> > static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
> > - struct folio *folio)
> > + struct folio *folio,
> > + struct file *fpin)
> > {
> > struct file *file = vmf->vma->vm_file;
> > struct file_ra_state *ra = &file->f_ra;
> > DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff);
> > - struct file *fpin = NULL;
> > unsigned int mmap_miss;
> >
> > /* See comment in do_sync_mmap_readahead. */
> > @@ -3260,6 +3261,72 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf)
> > return ret;
> > }
> >
> > +/**
> > + * filemap_maybe_emit_fsnotify_event - maybe emit a pre-content event.
> > + * @vmf: struct vm_fault containing details of the fault.
> > + * @fpin: pointer to the struct file pointer that may be pinned.
> > + *
> > + * If we have pre-content watches on this file we will need to emit an event for
> > + * this range. We will handle dropping the lock and emitting the event.
> > + *
> > + * If FAULT_FLAG_RETRY_NOWAIT is set then we'll return VM_FAULT_RETRY.
> > + *
> > + * If no event was emitted then *fpin will be NULL and we will return 0.
> > + *
> > + * If any error occurred we will return VM_FAULT_SIGBUS, *fpin could still be
> > + * set and will need to have fput() called on it.
> > + *
> > + * If we emitted the event then we will return 0 and *fpin will be set, this
> > + * must have fput() called on it, and the caller must call VM_FAULT_RETRY after
> > + * any other operations it does in order to re-fault the page and make sure the
> > + * appropriate locking is maintained.
> > + *
> > + * Return: the appropriate vm_fault_t return code, 0 on success.
> > + */
> > +vm_fault_t filemap_maybe_emit_fsnotify_event(struct vm_fault *vmf,
> > + struct file **fpin)
> > +{
> > + struct file *file = vmf->vma->vm_file;
> > + loff_t pos = vmf->pgoff << PAGE_SHIFT;
> > + int mask = (vmf->flags & FAULT_FLAG_WRITE) ? MAY_WRITE : MAY_READ;
>
> You missed my comment about using MAY_ACCESS here
> and alter fsnotify hook, so legacy FAN_ACCESS_PERM event
> won't be generated from page fault.
I did miss that, I'll fix it up in v3, thanks!
Josef
