From 7aba71dbc41641e43a79fb9f6fac91719094b4fb Mon Sep 17 00:00:00 2001 From: Thomas Hellström Date: Thu, 5 Mar 2026 10:39:06 +0100 Subject: mm/mmu_notifier: Allow two-pass struct mmu_interval_notifiers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit GPU use-cases for mmu_interval_notifiers with hmm often involve starting a gpu operation and then waiting for it to complete. These operations are typically context preemption or TLB flushing. With single-pass notifiers per GPU this doesn't scale in multi-gpu scenarios. In those scenarios we'd want to first start preemption- or TLB flushing on all GPUs and as a second pass wait for them to complete. One can do this on per-driver basis multiplexing per-driver notifiers but that would mean sharing the notifier "user" lock across all GPUs and that doesn't scale well either, so adding support for multi-pass in the core appears to be the right choice. Implement two-pass capability in the mmu_interval_notifier. Use a linked list for the final passes to minimize the impact for use-cases that don't need the multi-pass functionality by avoiding a second interval tree walk, and to be able to easily pass data between the two passes. v1: - Restrict to two passes (Jason Gunthorpe) - Improve on documentation (Jason Gunthorpe) - Improve on function naming (Alistair Popple) v2: - Include the invalidate_finish() callback in the struct mmu_interval_notifier_ops. - Update documentation (GitHub Copilot:claude-sonnet-4.6) - Use lockless list for list management. v3: - Update kerneldoc for the struct mmu_interval_notifier_finish::list member (Matthew Brost) - Add a WARN_ON_ONCE() checking for NULL invalidate_finish() op if if invalidate_start() is non-NULL. (Matthew Brost) v4: - Addressed documentation review comments by David Hildenbrand. Cc: Matthew Brost Cc: Christian König Cc: David Hildenbrand Cc: Lorenzo Stoakes Cc: Liam R. Howlett Cc: Vlastimil Babka Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Michal Hocko Cc: Jason Gunthorpe Cc: Andrew Morton Cc: Simona Vetter Cc: Dave Airlie Cc: Alistair Popple Cc: Cc: Cc: Assisted-by: GitHub Copilot:claude-sonnet-4.6 # Documentation only. Signed-off-by: Thomas Hellström Acked-by: David Hildenbrand (Arm) Reviewed-by: Maarten Lankhorst Link: https://patch.msgid.link/20260305093909.43623-2-thomas.hellstrom@linux.intel.com --- include/linux/mmu_notifier.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'include') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index d1094c2d5fb6..b60673a8e0bb 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -233,16 +233,58 @@ struct mmu_notifier { unsigned int users; }; +/** + * struct mmu_interval_notifier_finish - mmu_interval_notifier two-pass abstraction + * @link: Lockless list link for the notifiers pending pass list + * @notifier: The mmu_interval_notifier for which the finish pass is called. + * + * Allocate, typically using GFP_NOWAIT in the interval notifier's start pass. + * Note that with a large number of notifiers implementing two passes, + * allocation with GFP_NOWAIT will become increasingly likely to fail, so consider + * implementing a small pool instead of using kmalloc() allocations. + * + * If the implementation needs to pass data between the start and the finish passes, + * the recommended way is to embed struct mmu_interval_notifier_finish into a larger + * structure that also contains the data needed to be shared. Keep in mind that + * a notifier callback can be invoked in parallel, and each invocation needs its + * own struct mmu_interval_notifier_finish. + * + * If allocation fails, then the &mmu_interval_notifier_ops->invalidate_start op + * needs to implements the full notifier functionality. Please refer to its + * documentation. + */ +struct mmu_interval_notifier_finish { + struct llist_node link; + struct mmu_interval_notifier *notifier; +}; + /** * struct mmu_interval_notifier_ops * @invalidate: Upon return the caller must stop using any SPTEs within this * range. This function can sleep. Return false only if sleeping * was required but mmu_notifier_range_blockable(range) is false. + * @invalidate_start: Similar to @invalidate, but intended for two-pass notifier + * callbacks where the call to @invalidate_start is the first + * pass and any struct mmu_interval_notifier_finish pointer + * returned in the @finish parameter describes the finish pass. + * If *@finish is %NULL on return, then no final pass will be + * called, and @invalidate_start needs to implement the full + * notifier, behaving like @invalidate. The value of *@finish + * is guaranteed to be %NULL at function entry. + * @invalidate_finish: Called as the second pass for any notifier that returned + * a non-NULL *@finish from @invalidate_start. The @finish + * pointer passed here is the same one returned by + * @invalidate_start. */ struct mmu_interval_notifier_ops { bool (*invalidate)(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range, unsigned long cur_seq); + bool (*invalidate_start)(struct mmu_interval_notifier *interval_sub, + const struct mmu_notifier_range *range, + unsigned long cur_seq, + struct mmu_interval_notifier_finish **finish); + void (*invalidate_finish)(struct mmu_interval_notifier_finish *finish); }; struct mmu_interval_notifier { -- cgit v1.2.3