[RFC 4/6] mm/swap_state: respect FAULT_FLAG_RETRY_NOWAIT

[Nadav Amit]

From: Nadav Amit <namit@xxxxxxxxxx>

Certain use-cases (e.g., prefetch_page()) may want to avoid polling
while a page is brought from the swap. Yet, swap_cluster_readahead()
and swap_vma_readahead() do not respect FAULT_FLAG_RETRY_NOWAIT.

Add support to respect FAULT_FLAG_RETRY_NOWAIT by not polling in these
cases.

Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Sean Christopherson <seanjc@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: x86@xxxxxxxxxx
Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
---
 mm/memory.c     | 15 +++++++++++++--
 mm/shmem.c      |  1 +
 mm/swap_state.c | 12 +++++++++---
 3 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index feff48e1465a..13b9cf36268f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3326,12 +3326,23 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		}
 
 		if (!page) {
+			/*
+			 * Back out if we failed to bring the page while we
+			 * tried to avoid I/O.
+			 */
+			if (fault_flag_allow_retry_first(vmf->flags) &&
+			    (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+				ret = VM_FAULT_RETRY;
+				delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+				goto out;
+			}
+
 			/*
 			 * Back out if somebody else faulted in this pte
 			 * while we released the pte lock.
 			 */
-			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
-					vmf->address, &vmf->ptl);
+			vmf->pte = pte_offset_map_lock(vma->vm_mm,
+				vmf->pmd, vmf->address, &vmf->ptl);
 			if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
 				ret = VM_FAULT_OOM;
 			delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
diff --git a/mm/shmem.c b/mm/shmem.c
index 7c6b6d8f6c39..b108e9ba9e89 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1525,6 +1525,7 @@ static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
 	shmem_pseudo_vma_init(&pvma, info, index);
 	vmf.vma = &pvma;
 	vmf.address = 0;
+	vmf.flags = 0;
 	page = swap_cluster_readahead(swap, gfp, &vmf);
 	shmem_pseudo_vma_destroy(&pvma);
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 751c1ef2fe0e..1e930f7ff8b3 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -656,10 +656,13 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	unsigned long mask;
 	struct swap_info_struct *si = swp_swap_info(entry);
 	struct blk_plug plug;
-	bool do_poll = true, page_allocated;
+	bool page_allocated, do_poll;
 	struct vm_area_struct *vma = vmf->vma;
 	unsigned long addr = vmf->address;
 
+	do_poll = !fault_flag_allow_retry_first(vmf->flags) ||
+		!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT);
+
 	mask = swapin_nr_pages(offset) - 1;
 	if (!mask)
 		goto skip;
@@ -838,7 +841,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 	pte_t *pte, pentry;
 	swp_entry_t entry;
 	unsigned int i;
-	bool page_allocated;
+	bool page_allocated, do_poll;
 	struct vma_swap_readahead ra_info = {
 		.win = 1,
 	};
@@ -873,9 +876,12 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 	}
 	blk_finish_plug(&plug);
 	lru_add_drain();
+
 skip:
+	do_poll = (!fault_flag_allow_retry_first(vmf->flags) ||
+		!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) && ra_info.win == 1;
 	return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address,
-				     ra_info.win == 1);
+				     do_poll);
 }
 
 /**
-- 
2.25.1