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>

8 files changed, 10 insertions, 21 deletions

diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index e59a32aa0c49..0119dc91abb5 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/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
 	}
 
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 507f8228f983..7a2ff9010f17 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/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);
 
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index eb5bed333750..9580e8e12165 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/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
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index 4ad6e510d405..559112312810 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/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);
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index e410275918ac..5c30212d8d1c 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/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
 	}
 
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index ff7bf4432229..bbaefd84f15e 100644
--- a/arch/s390/kernel/vdso.c
+++ b/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);
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 74e1d873dce0..69af6cdf1a2a 100644
--- a/arch/s390/mm/gmap.c
+++ b/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);
 }
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index b8f3f9b9e53c..ec5e4d2048cb 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/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);