[PATCH v2 stable 4.9,4.14 1/2] mm/khugepaged: fix GUP-fast interaction by sending IPI

[Jann Horn <jannh@google.com>]

Since commit 70cbc3cc78a99 ("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: ba76149f47d8 ("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;
TLB flushing was refactored between 5.4 and 5.10;
TLB flushing was refactored between 4.19 and 5.4;
pmd collapse for PTE-mapped THP was only added in 5.4;
ugly hack for s390 in <=4.19]
Signed-off-by: Jann Horn <jannh@google.com>
---
added an incredibly ugly hack to work around the s390 issue reported in
https://lore.kernel.org/all/Y5aaQqNH71IMVks0@sashalap/

 include/asm-generic/tlb.h |  6 ++++++
 mm/khugepaged.c           | 15 +++++++++++++++
 mm/memory.c               |  5 +++++
 3 files changed, 26 insertions(+)

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 5e7e4aaf36c5..43409a047480 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -60,6 +60,12 @@ struct mmu_table_batch {
 extern void tlb_table_flush(struct mmu_gather *tlb);
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
+void tlb_remove_table_sync_one(void);
+
+#else
+
+static inline void tlb_remove_table_sync_one(void) { }
+
 #endif
 
 /*
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index f426d42d629d..7825f3af5c6d 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -23,6 +23,19 @@
 #include <asm/pgalloc.h>
 #include "internal.h"
 
+/* gross hack for <=4.19 stable */
+#ifdef CONFIG_S390
+static void tlb_remove_table_smp_sync(void *arg)
+{
+        /* Simply deliver the interrupt */
+}
+
+static void tlb_remove_table_sync_one(void)
+{
+        smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+}
+#endif
+
 enum scan_result {
 	SCAN_FAIL,
 	SCAN_SUCCEED,
@@ -1046,6 +1059,7 @@ 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(mm, mmun_start, mmun_end);
+	tlb_remove_table_sync_one();
 
 	spin_lock(pte_ptl);
 	isolated = __collapse_huge_page_isolate(vma, address, pte);
@@ -1295,6 +1309,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 				_pmd = pmdp_collapse_flush(vma, addr, pmd);
 				spin_unlock(ptl);
 				atomic_long_dec(&mm->nr_ptes);
+				tlb_remove_table_sync_one();
 				pte_free(mm, pmd_pgtable(_pmd));
 			}
 			up_write(&mm->mmap_sem);
diff --git a/mm/memory.c b/mm/memory.c
index 615cb3fe763d..0136af15ba18 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -373,6 +373,11 @@ static void tlb_remove_table_smp_sync(void *arg)
 	/* Simply deliver the interrupt */
 }
 
+void tlb_remove_table_sync_one(void)
+{
+	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+}
+
 static void tlb_remove_table_one(void *table)
 {
 	/*

base-commit: 179ef7fe86775fe32bd1bfe791887d1994ddcfb0
-- 
2.39.0.rc1.256.g54fd8350bd-goog