[PATCH] mm/gup: update pin_user_pages.rst for "case 3" (mmu notifiers)

From: John Hubbard
Date: Wed May 27 2020 - 15:49:57 EST

Update case 3 so that it covers the use of mmu notifiers, for
hardware that does, or does not have replayable page faults.

Also, elaborate case 4 slightly, as it was quite cryptic.

Cc: Daniel Vetter <daniel@xxxxxxxx>
Cc: JÃrÃme Glisse <jglisse@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: linux-doc@xxxxxxxxxxxxxxx
Cc: linux-fsdevel@xxxxxxxxxxxxxxx
Signed-off-by: John Hubbard <jhubbard@xxxxxxxxxx>
Documentation/core-api/pin_user_pages.rst | 33 +++++++++++++----------
1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst
index 2e939ff10b86..4675b04e8829 100644
--- a/Documentation/core-api/pin_user_pages.rst
+++ b/Documentation/core-api/pin_user_pages.rst
@@ -148,23 +148,28 @@ NOTE: Some pages, such as DAX pages, cannot be pinned with longterm pins. That's
because DAX pages do not have a separate page cache, and so "pinning" implies
locking down file system blocks, which is not (yet) supported in that way.

-CASE 3: Hardware with page faulting support
-Here, a well-written driver doesn't normally need to pin pages at all. However,
-if the driver does choose to do so, it can register MMU notifiers for the range,
-and will be called back upon invalidation. Either way (avoiding page pinning, or
-using MMU notifiers to unpin upon request), there is proper synchronization with
-both filesystem and mm (page_mkclean(), munmap(), etc).
-Therefore, neither flag needs to be set.
-In this case, ideally, neither get_user_pages() nor pin_user_pages() should be
-called. Instead, the software should be written so that it does not pin pages.
-This allows mm and filesystems to operate more efficiently and reliably.
+CASE 3: MMU notifier registration, with or without page faulting hardware
+Device drivers can pin pages via get_user_pages*(), and register for mmu
+notifier callbacks for the memory range. Then, upon receiving a notifier
+"invalidate range" callback , stop the device from using the range, and unpin
+the pages. There may be other possible schemes, such as for example explicitly
+synchronizing against pending IO, that accomplish approximately the same thing.
+Or, if the hardware supports replayable page faults, then the device driver can
+avoid pinning entirely (this is ideal), as follows: register for mmu notifier
+callbacks as above, but instead of stopping the device and unpinning in the
+callback, simply remove the range from the device's page tables.
+Either way, as long as the driver unpins the pages upon mmu notifier callback,
+then there is proper synchronization with both filesystem and mm
+(page_mkclean(), munmap(), etc). Therefore, neither flag needs to be set.

CASE 4: Pinning for struct page manipulation only
-Here, normal GUP calls are sufficient, so neither flag needs to be set.
+If only struct page data (as opposed to the actual memory contents that a page
+is tracking) is affected, then normal GUP calls are sufficient, and neither flag
+needs to be set.

page_maybe_dma_pinned(): the whole point of pinning