Merge tag 'kvm-x86-gmem-6.19' of https://github.com/kvm-x86/linux into HEAD

KVM guest_memfd changes for 6.19:

 - Add NUMA mempolicy support for guest_memfd, and clean up a variety of
   rough edges in guest_memfd along the way.

 - Define a CLASS to automatically handle get+put when grabbing a guest_memfd
   from a memslot to make it harder to leak references.

 - Enhance KVM selftests to make it easer to develop and debug selftests like
   those added for guest_memfd NUMA support, e.g. where test and/or KVM bugs
   often result in hard-to-debug SIGBUS errors.

 - Misc cleanups.

Author: bonzini

fs/btrfs/compression.c

@@ -491,8 +491,8 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			continue;
 		}
 
-		folio = filemap_alloc_folio(mapping_gfp_constraint(mapping,
-								   ~__GFP_FS), 0);
+		folio = filemap_alloc_folio(mapping_gfp_constraint(mapping, ~__GFP_FS),
+					    0, NULL);
 		if (!folio)
 			break;
 

fs/btrfs/verity.c

@@ -742,7 +742,7 @@ static struct page *btrfs_read_merkle_tree_page(struct inode *inode,
 	}
 
 	folio = filemap_alloc_folio(mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS),
-				    0);
+				    0, NULL);
 	if (!folio)
 		return ERR_PTR(-ENOMEM);
 

fs/erofs/zdata.c

@@ -562,7 +562,7 @@ static void z_erofs_bind_cache(struct z_erofs_frontend *fe)
 			 * Allocate a managed folio for cached I/O, or it may be
 			 * then filled with a file-backed folio for in-place I/O
 			 */
-			newfolio = filemap_alloc_folio(gfp, 0);
+			newfolio = filemap_alloc_folio(gfp, 0, NULL);
 			if (!newfolio)
 				continue;
 			newfolio->private = Z_EROFS_PREALLOCATED_FOLIO;

fs/f2fs/compress.c

@@ -1947,7 +1947,7 @@ static void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi,
 		return;
 	}
 
-	cfolio = filemap_alloc_folio(__GFP_NOWARN | __GFP_IO, 0);
+	cfolio = filemap_alloc_folio(__GFP_NOWARN | __GFP_IO, 0, NULL);
 	if (!cfolio)
 		return;
 

include/linux/pagemap.h

@@ -654,9 +654,11 @@ static inline void *detach_page_private(struct page *page)
 }
 
 #ifdef CONFIG_NUMA
-struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order);
+struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *policy);
 #else
-static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
+static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *policy)
 {
 	return folio_alloc_noprof(gfp, order);
 }
@@ -667,7 +669,7 @@ static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int o
 
 static inline struct page *__page_cache_alloc(gfp_t gfp)
 {
-	return &filemap_alloc_folio(gfp, 0)->page;
+	return &filemap_alloc_folio(gfp, 0, NULL)->page;
 }
 
 static inline gfp_t readahead_gfp_mask(struct address_space *x)
@@ -753,11 +755,17 @@ static inline fgf_t fgf_set_order(size_t size)
 }
 
 void *filemap_get_entry(struct address_space *mapping, pgoff_t index);
-struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
-		fgf_t fgp_flags, gfp_t gfp);
+struct folio *__filemap_get_folio_mpol(struct address_space *mapping,
+		pgoff_t index, fgf_t fgf_flags, gfp_t gfp, struct mempolicy *policy);
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 		fgf_t fgp_flags, gfp_t gfp);
 
+static inline struct folio *__filemap_get_folio(struct address_space *mapping,
+		pgoff_t index, fgf_t fgf_flags, gfp_t gfp)
+{
+	return __filemap_get_folio_mpol(mapping, index, fgf_flags, gfp, NULL);
+}
+
 /**
  * write_begin_get_folio - Get folio for write_begin with flags.
  * @iocb: The kiocb passed from write_begin (may be NULL).

include/uapi/linux/magic.h

@@ -103,5 +103,6 @@
 #define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
 #define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
 #define PID_FS_MAGIC		0x50494446	/* "PIDF" */
+#define GUEST_MEMFD_MAGIC	0x474d454d	/* "GMEM" */
 
 #endif /* __LINUX_MAGIC_H__ */

mm/filemap.c

@@ -1002,11 +1002,16 @@ int filemap_add_folio(struct address_space *mapping, struct folio *folio,
 EXPORT_SYMBOL_GPL(filemap_add_folio);
 
 #ifdef CONFIG_NUMA
-struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
+struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *policy)
 {
 	int n;
 	struct folio *folio;
 
+	if (policy)
+		return folio_alloc_mpol_noprof(gfp, order, policy,
+				NO_INTERLEAVE_INDEX, numa_node_id());
+
 	if (cpuset_do_page_mem_spread()) {
 		unsigned int cpuset_mems_cookie;
 		do {
@@ -1923,11 +1928,12 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index)
 }
 
 /**
- * __filemap_get_folio - Find and get a reference to a folio.
+ * __filemap_get_folio_mpol - Find and get a reference to a folio.
  * @mapping: The address_space to search.
  * @index: The page index.
  * @fgp_flags: %FGP flags modify how the folio is returned.
  * @gfp: Memory allocation flags to use if %FGP_CREAT is specified.
+ * @policy: NUMA memory allocation policy to follow.
  *
  * Looks up the page cache entry at @mapping & @index.
  *
@@ -1938,8 +1944,8 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index)
  *
  * Return: The found folio or an ERR_PTR() otherwise.
  */
-struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
-		fgf_t fgp_flags, gfp_t gfp)
+struct folio *__filemap_get_folio_mpol(struct address_space *mapping,
+		pgoff_t index, fgf_t fgp_flags, gfp_t gfp, struct mempolicy *policy)
 {
 	struct folio *folio;
 
@@ -2009,7 +2015,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 			err = -ENOMEM;
 			if (order > min_order)
 				alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
-			folio = filemap_alloc_folio(alloc_gfp, order);
+			folio = filemap_alloc_folio(alloc_gfp, order, policy);
 			if (!folio)
 				continue;
 
@@ -2056,7 +2062,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		folio_clear_dropbehind(folio);
 	return folio;
 }
-EXPORT_SYMBOL(__filemap_get_folio);
+EXPORT_SYMBOL(__filemap_get_folio_mpol);
 
 static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max,
 		xa_mark_t mark)
@@ -2551,7 +2557,7 @@ static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch)
 	if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
 		return -EAGAIN;
 
-	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order);
+	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order, NULL);
 	if (!folio)
 		return -ENOMEM;
 	if (iocb->ki_flags & IOCB_DONTCACHE)
@@ -3995,8 +4001,7 @@ static struct folio *do_read_cache_folio(struct address_space *mapping,
 repeat:
 	folio = filemap_get_folio(mapping, index);
 	if (IS_ERR(folio)) {
-		folio = filemap_alloc_folio(gfp,
-					    mapping_min_folio_order(mapping));
+		folio = filemap_alloc_folio(gfp, mapping_min_folio_order(mapping), NULL);
 		if (!folio)
 			return ERR_PTR(-ENOMEM);
 		index = mapping_align_index(mapping, index);

mm/mempolicy.c

@@ -354,6 +354,7 @@ struct mempolicy *get_task_policy(struct task_struct *p)
 
 	return &default_policy;
 }
+EXPORT_SYMBOL_FOR_MODULES(get_task_policy, "kvm");
 
 static const struct mempolicy_operations {
 	int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
@@ -487,6 +488,7 @@ void __mpol_put(struct mempolicy *pol)
 		return;
 	kmem_cache_free(policy_cache, pol);
 }
+EXPORT_SYMBOL_FOR_MODULES(__mpol_put, "kvm");
 
 static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes)
 {
@@ -2885,6 +2887,7 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 	read_unlock(&sp->lock);
 	return pol;
 }
+EXPORT_SYMBOL_FOR_MODULES(mpol_shared_policy_lookup, "kvm");
 
 static void sp_free(struct sp_node *n)
 {
@@ -3170,6 +3173,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 		mpol_put(mpol);	/* drop our incoming ref on sb mpol */
 	}
 }
+EXPORT_SYMBOL_FOR_MODULES(mpol_shared_policy_init, "kvm");
 
 int mpol_set_shared_policy(struct shared_policy *sp,
 			struct vm_area_struct *vma, struct mempolicy *pol)
@@ -3188,6 +3192,7 @@ int mpol_set_shared_policy(struct shared_policy *sp,
 		sp_free(new);
 	return err;
 }
+EXPORT_SYMBOL_FOR_MODULES(mpol_set_shared_policy, "kvm");
 
 /* Free a backing policy store on inode delete. */
 void mpol_free_shared_policy(struct shared_policy *sp)
@@ -3206,6 +3211,7 @@ void mpol_free_shared_policy(struct shared_policy *sp)
 	}
 	write_unlock(&sp->lock);
 }
+EXPORT_SYMBOL_FOR_MODULES(mpol_free_shared_policy, "kvm");
 
 #ifdef CONFIG_NUMA_BALANCING
 static int __initdata numabalancing_override;

mm/readahead.c

@@ -186,7 +186,7 @@ static struct folio *ractl_alloc_folio(struct readahead_control *ractl,
 {
 	struct folio *folio;
 
-	folio = filemap_alloc_folio(gfp_mask, order);
+	folio = filemap_alloc_folio(gfp_mask, order, NULL);
 	if (folio && ractl->dropbehind)
 		__folio_set_dropbehind(folio);
 

tools/testing/selftests/kvm/arm64/vgic_irq.c

@@ -636,7 +636,7 @@ static void kvm_routing_and_irqfd_check(struct kvm_vm *vm,
 	}
 
 	for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++)
-		close(fd[f]);
+		kvm_close(fd[f]);
 }
 
 /* handles the valid case: intid=0xffffffff num=1 */