mm: remove zap_page_range and create zap_vma_pages

zap_page_range was originally designed to unmap pages within an address
range that could span multiple vmas.  While working on [1], it was
discovered that all callers of zap_page_range pass a range entirely within
a single vma.  In addition, the mmu notification call within zap_page
range does not correctly handle ranges that span multiple vmas.  When
crossing a vma boundary, a new mmu_notifier_range_init/end call pair with
the new vma should be made.

Instead of fixing zap_page_range, do the following:
- Create a new routine zap_vma_pages() that will remove all pages within
  the passed vma.  Most users of zap_page_range pass the entire vma and
  can use this new routine.
- For callers of zap_page_range not passing the entire vma, instead call
  zap_page_range_single().
- Remove zap_page_range.

[1] https://lore.kernel.org/linux-mm/20221114235507.294320-2-mike.kravetz@oracle.com/
Link: https://lkml.kernel.org/r/20230104002732.232573-1-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Suggested-by: Peter Xu <peterx@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>	[s390]
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/arm64/kernel/vdso.c

@@ -138,13 +138,11 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 	mmap_read_lock(mm);
 
 	for_each_vma(vmi, vma) {
-		unsigned long size = vma->vm_end - vma->vm_start;
-
 		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm))
-			zap_page_range(vma, vma->vm_start, size);
+			zap_vma_pages(vma);
 #ifdef CONFIG_COMPAT_VDSO
 		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm))
-			zap_page_range(vma, vma->vm_start, size);
+			zap_vma_pages(vma);
 #endif
 	}
 

arch/powerpc/kernel/vdso.c

@@ -120,10 +120,8 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 
 	mmap_read_lock(mm);
 	for_each_vma(vmi, vma) {
-		unsigned long size = vma->vm_end - vma->vm_start;
-
 		if (vma_is_special_mapping(vma, &vvar_spec))
-			zap_page_range(vma, vma->vm_start, size);
+			zap_vma_pages(vma);
 	}
 	mmap_read_unlock(mm);
 

arch/powerpc/platforms/book3s/vas-api.c

@@ -414,7 +414,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
 	/*
 	 * When the LPAR lost credits due to core removal or during
 	 * migration, invalidate the existing mapping for the current
-	 * paste addresses and set windows in-active (zap_page_range in
+	 * paste addresses and set windows in-active (zap_vma_pages in
 	 * reconfig_close_windows()).
 	 * New mapping will be done later after migration or new credits
 	 * available. So continue to receive faults if the user space

arch/powerpc/platforms/pseries/vas.c

@@ -760,8 +760,7 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds,
 		 * is done before the original mmap() and after the ioctl.
 		 */
 		if (vma)
-			zap_page_range(vma, vma->vm_start,
-					vma->vm_end - vma->vm_start);
+			zap_vma_pages(vma);
 
 		mmap_write_unlock(task_ref->mm);
 		mutex_unlock(&task_ref->mmap_mutex);

arch/riscv/kernel/vdso.c

@@ -124,13 +124,11 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 	mmap_read_lock(mm);
 
 	for_each_vma(vmi, vma) {
-		unsigned long size = vma->vm_end - vma->vm_start;
-
 		if (vma_is_special_mapping(vma, vdso_info.dm))
-			zap_page_range(vma, vma->vm_start, size);
+			zap_vma_pages(vma);
 #ifdef CONFIG_COMPAT
 		if (vma_is_special_mapping(vma, compat_vdso_info.dm))
-			zap_page_range(vma, vma->vm_start, size);
+			zap_vma_pages(vma);
 #endif
 	}
 

arch/s390/kernel/vdso.c

@@ -59,11 +59,9 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 
 	mmap_read_lock(mm);
 	for_each_vma(vmi, vma) {
-		unsigned long size = vma->vm_end - vma->vm_start;
-
 		if (!vma_is_special_mapping(vma, &vvar_mapping))
 			continue;
-		zap_page_range(vma, vma->vm_start, size);
+		zap_vma_pages(vma);
 		break;
 	}
 	mmap_read_unlock(mm);

arch/s390/mm/gmap.c

@@ -722,7 +722,7 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
 		if (is_vm_hugetlb_page(vma))
 			continue;
 		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
-		zap_page_range(vma, vmaddr, size);
+		zap_page_range_single(vma, vmaddr, size, NULL);
 	}
 	mmap_read_unlock(gmap->mm);
 }

arch/x86/entry/vdso/vma.c

@@ -113,10 +113,8 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 
 	mmap_read_lock(mm);
 	for_each_vma(vmi, vma) {
-		unsigned long size = vma->vm_end - vma->vm_start;
-
 		if (vma_is_special_mapping(vma, &vvar_mapping))
-			zap_page_range(vma, vma->vm_start, size);
+			zap_vma_pages(vma);
 	}
 	mmap_read_unlock(mm);
 

drivers/android/binder_alloc.c

@@ -1019,7 +1019,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 	if (vma) {
 		trace_binder_unmap_user_start(alloc, index);
 
-		zap_page_range(vma, page_addr, PAGE_SIZE);
+		zap_page_range_single(vma, page_addr, PAGE_SIZE, NULL);
 
 		trace_binder_unmap_user_end(alloc, index);
 	}

include/linux/mm.h

@@ -1977,10 +1977,13 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		  unsigned long size);
-void zap_page_range(struct vm_area_struct *vma, unsigned long address,
-		    unsigned long size);
 void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 			   unsigned long size, struct zap_details *details);
+static inline void zap_vma_pages(struct vm_area_struct *vma)
+{
+	zap_page_range_single(vma, vma->vm_start,
+			      vma->vm_end - vma->vm_start, NULL);
+}
 void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 		struct vm_area_struct *start_vma, unsigned long start,
 		unsigned long end);

mm/memory.c

@@ -1693,36 +1693,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 	mmu_notifier_invalidate_range_end(&range);
 }
 
-/**
- * zap_page_range - remove user pages in a given range
- * @vma: vm_area_struct holding the applicable pages
- * @start: starting address of pages to zap
- * @size: number of bytes to zap
- *
- * Caller must protect the VMA list
- */
-void zap_page_range(struct vm_area_struct *vma, unsigned long start,
-		unsigned long size)
-{
-	struct maple_tree *mt = &vma->vm_mm->mm_mt;
-	unsigned long end = start + size;
-	struct mmu_notifier_range range;
-	struct mmu_gather tlb;
-	MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
-
-	lru_add_drain();
-	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
-				start, start + size);
-	tlb_gather_mmu(&tlb, vma->vm_mm);
-	update_hiwater_rss(vma->vm_mm);
-	mmu_notifier_invalidate_range_start(&range);
-	do {
-		unmap_single_vma(&tlb, vma, start, range.end, NULL);
-	} while ((vma = mas_find(&mas, end - 1)) != NULL);
-	mmu_notifier_invalidate_range_end(&range);
-	tlb_finish_mmu(&tlb);
-}
-
 /**
  * zap_page_range_single - remove user pages in a given range
  * @vma: vm_area_struct holding the applicable pages

mm/page-writeback.c

@@ -2690,7 +2690,7 @@ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb)
  *
  * The caller must hold lock_page_memcg().  Most callers have the folio
  * locked.  A few have the folio blocked from truncation through other
- * means (eg zap_page_range() has it mapped and is holding the page table
+ * means (eg zap_vma_pages() has it mapped and is holding the page table
  * lock).  This can also be called from mark_buffer_dirty(), which I
  * cannot prove is always protected against truncate.
  */

net/ipv4/tcp.c

@@ -2092,7 +2092,7 @@ static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma,
 		maybe_zap_len = total_bytes_to_map -  /* All bytes to map */
 				*length + /* Mapped or pending */
 				(pages_remaining * PAGE_SIZE); /* Failed map. */
-		zap_page_range(vma, *address, maybe_zap_len);
+		zap_page_range_single(vma, *address, maybe_zap_len, NULL);
 		err = 0;
 	}
 
@@ -2100,7 +2100,7 @@ static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma,
 		unsigned long leftover_pages = pages_remaining;
 		int bytes_mapped;
 
-		/* We called zap_page_range, try to reinsert. */
+		/* We called zap_page_range_single, try to reinsert. */
 		err = vm_insert_pages(vma, *address,
 				      pending_pages,
 				      &pages_remaining);
@@ -2234,7 +2234,8 @@ static int tcp_zerocopy_receive(struct sock *sk,
 	total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1);
 	if (total_bytes_to_map) {
 		if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT))
-			zap_page_range(vma, address, total_bytes_to_map);
+			zap_page_range_single(vma, address, total_bytes_to_map,
+					      NULL);
 		zc->length = total_bytes_to_map;
 		zc->recv_skip_hint = 0;
 	} else {