mm/khugepaged: fix GUP-fast interaction by sending IPI

commit 2ba99c5e08 upstream.

Since commit 70cbc3cc78 ("mm: gup: fix the fast GUP race against THP
collapse"), the lockless_pages_from_mm() fastpath rechecks the pmd_t to
ensure that the page table was not removed by khugepaged in between.

However, lockless_pages_from_mm() still requires that the page table is
not concurrently freed.  Fix it by sending IPIs (if the architecture uses
semi-RCU-style page table freeing) before freeing/reusing page tables.

Link: https://lkml.kernel.org/r/20221129154730.2274278-2-jannh@google.com
Link: https://lkml.kernel.org/r/20221128180252.1684965-2-jannh@google.com
Link: https://lkml.kernel.org/r/20221125213714.4115729-2-jannh@google.com
Fixes: ba76149f47 ("thp: khugepaged")
Signed-off-by: Jann Horn <jannh@google.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
[manual backport: two of the three places in khugepaged that can free
ptes were refactored into a common helper between 5.15 and 6.0]
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

include/asm-generic/tlb.h

@@ -207,12 +207,16 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 #define tlb_needs_table_invalidate() (true)
 #endif
 
+void tlb_remove_table_sync_one(void);
+
 #else
 
 #ifdef tlb_needs_table_invalidate
 #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
 #endif
 
+static inline void tlb_remove_table_sync_one(void) { }
+
 #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
 

mm/khugepaged.c

@@ -1156,6 +1156,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	_pmd = pmdp_collapse_flush(vma, address, pmd);
 	spin_unlock(pmd_ptl);
 	mmu_notifier_invalidate_range_end(&range);
+	tlb_remove_table_sync_one();
 
 	spin_lock(pte_ptl);
 	isolated = __collapse_huge_page_isolate(vma, address, pte,
@@ -1537,6 +1538,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 	/* step 4: collapse pmd */
 	_pmd = pmdp_collapse_flush(vma, haddr, pmd);
 	mm_dec_nr_ptes(mm);
+	tlb_remove_table_sync_one();
 	pte_free(mm, pmd_pgtable(_pmd));
 
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
@@ -1623,6 +1625,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 				/* assume page table is clear */
 				_pmd = pmdp_collapse_flush(vma, addr, pmd);
 				mm_dec_nr_ptes(mm);
+				tlb_remove_table_sync_one();
 				pte_free(mm, pmd_pgtable(_pmd));
 			}
 			mmap_write_unlock(mm);

mm/mmu_gather.c

@@ -139,7 +139,7 @@ static void tlb_remove_table_smp_sync(void *arg)
 	/* Simply deliver the interrupt */
 }
 
-static void tlb_remove_table_sync_one(void)
+void tlb_remove_table_sync_one(void)
 {
 	/*
 	 * This isn't an RCU grace period and hence the page-tables cannot be
@@ -163,8 +163,6 @@ static void tlb_remove_table_free(struct mmu_table_batch *batch)
 
 #else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
-static void tlb_remove_table_sync_one(void) { }
-
 static void tlb_remove_table_free(struct mmu_table_batch *batch)
 {
 	__tlb_remove_table_free(batch);