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.

21 files changed, 645 insertions, 253 deletions

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index bacad18357b3..d927ae32e7d0 100644
--- a/fs/btrfs/compression.c
+++ b/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;
 
diff --git a/fs/btrfs/verity.c b/fs/btrfs/verity.c
index 46bd8ca58670..d4523d5debcd 100644
--- a/fs/btrfs/verity.c
+++ b/fs/btrfs/verity.c
@@ -742,7 +742,7 @@ again:
 	}
 
 	folio = filemap_alloc_folio(mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS),
-				    0);
+				    0, NULL);
 	if (!folio)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index bc80cfe482f7..b7369fb4fbe9 100644
--- a/fs/erofs/zdata.c
+++ b/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;
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 6ad8d3bc6df7..a65e8cd388bc 100644
--- a/fs/f2fs/compress.c
+++ b/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;
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 09b581c1d878..a17fabbc0269 100644
--- a/include/linux/pagemap.h
+++ b/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).
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index bb575f3ab45e..638ca21b7a90 100644
--- a/include/uapi/linux/magic.h
+++ b/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__ */
diff --git a/mm/filemap.c b/mm/filemap.c
index 2f1e7e283a51..270485b19a5b 100644
--- a/mm/filemap.c
+++ b/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 @@ out:
 }
 
 /**
- * __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 @@ out:
  *
  * 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 @@ no_page:
 			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 @@ no_page:
 		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);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index eb83cff7db8c..3d797d47a040 100644
--- a/mm/mempolicy.c
+++ b/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 @@ put_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;
diff --git a/mm/readahead.c b/mm/readahead.c
index 3a4b5d58eeb6..b415c9969176 100644
--- a/mm/readahead.c
+++ b/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);
 
diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index 6338f5bbdb70..8d7758f12280 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_irq.c
+++ b/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 */
diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index e7d9aeb418d3..618c937f3c90 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -19,6 +19,7 @@
 #include <sys/stat.h>
 
 #include "kvm_util.h"
+#include "numaif.h"
 #include "test_util.h"
 #include "ucall_common.h"
 
@@ -75,6 +76,101 @@ static void test_mmap_supported(int fd, size_t total_size)
 	kvm_munmap(mem, total_size);
 }
 
+static void test_mbind(int fd, size_t total_size)
+{
+	const unsigned long nodemask_0 = 1; /* nid: 0 */
+	unsigned long nodemask = 0;
+	unsigned long maxnode = 8;
+	int policy;
+	char *mem;
+	int ret;
+
+	if (!is_multi_numa_node_system())
+		return;
+
+	mem = kvm_mmap(total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd);
+
+	/* Test MPOL_INTERLEAVE policy */
+	kvm_mbind(mem, page_size * 2, MPOL_INTERLEAVE, &nodemask_0, maxnode, 0);
+	kvm_get_mempolicy(&policy, &nodemask, maxnode, mem, MPOL_F_ADDR);
+	TEST_ASSERT(policy == MPOL_INTERLEAVE && nodemask == nodemask_0,
+		    "Wanted MPOL_INTERLEAVE (%u) and nodemask 0x%lx, got %u and 0x%lx",
+		    MPOL_INTERLEAVE, nodemask_0, policy, nodemask);
+
+	/* Test basic MPOL_BIND policy */
+	kvm_mbind(mem + page_size * 2, page_size * 2, MPOL_BIND, &nodemask_0, maxnode, 0);
+	kvm_get_mempolicy(&policy, &nodemask, maxnode, mem + page_size * 2, MPOL_F_ADDR);
+	TEST_ASSERT(policy == MPOL_BIND && nodemask == nodemask_0,
+		    "Wanted MPOL_BIND (%u) and nodemask 0x%lx, got %u and 0x%lx",
+		    MPOL_BIND, nodemask_0, policy, nodemask);
+
+	/* Test MPOL_DEFAULT policy */
+	kvm_mbind(mem, total_size, MPOL_DEFAULT, NULL, 0, 0);
+	kvm_get_mempolicy(&policy, &nodemask, maxnode, mem, MPOL_F_ADDR);
+	TEST_ASSERT(policy == MPOL_DEFAULT && !nodemask,
+		    "Wanted MPOL_DEFAULT (%u) and nodemask 0x0, got %u and 0x%lx",
+		    MPOL_DEFAULT, policy, nodemask);
+
+	/* Test with invalid policy */
+	ret = mbind(mem, page_size, 999, &nodemask_0, maxnode, 0);
+	TEST_ASSERT(ret == -1 && errno == EINVAL,
+		    "mbind with invalid policy should fail with EINVAL");
+
+	kvm_munmap(mem, total_size);
+}
+
+static void test_numa_allocation(int fd, size_t total_size)
+{
+	unsigned long node0_mask = 1;  /* Node 0 */
+	unsigned long node1_mask = 2;  /* Node 1 */
+	unsigned long maxnode = 8;
+	void *pages[4];
+	int status[4];
+	char *mem;
+	int i;
+
+	if (!is_multi_numa_node_system())
+		return;
+
+	mem = kvm_mmap(total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd);
+
+	for (i = 0; i < 4; i++)
+		pages[i] = (char *)mem + page_size * i;
+
+	/* Set NUMA policy after allocation */
+	memset(mem, 0xaa, page_size);
+	kvm_mbind(pages[0], page_size, MPOL_BIND, &node0_mask, maxnode, 0);
+	kvm_fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, page_size);
+
+	/* Set NUMA policy before allocation */
+	kvm_mbind(pages[0], page_size * 2, MPOL_BIND, &node1_mask, maxnode, 0);
+	kvm_mbind(pages[2], page_size * 2, MPOL_BIND, &node0_mask, maxnode, 0);
+	memset(mem, 0xaa, total_size);
+
+	/* Validate if pages are allocated on specified NUMA nodes */
+	kvm_move_pages(0, 4, pages, NULL, status, 0);
+	TEST_ASSERT(status[0] == 1, "Expected page 0 on node 1, got it on node %d", status[0]);
+	TEST_ASSERT(status[1] == 1, "Expected page 1 on node 1, got it on node %d", status[1]);
+	TEST_ASSERT(status[2] == 0, "Expected page 2 on node 0, got it on node %d", status[2]);
+	TEST_ASSERT(status[3] == 0, "Expected page 3 on node 0, got it on node %d", status[3]);
+
+	/* Punch hole for all pages */
+	kvm_fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, total_size);
+
+	/* Change NUMA policy nodes and reallocate */
+	kvm_mbind(pages[0], page_size * 2, MPOL_BIND, &node0_mask, maxnode, 0);
+	kvm_mbind(pages[2], page_size * 2, MPOL_BIND, &node1_mask, maxnode, 0);
+	memset(mem, 0xaa, total_size);
+
+	kvm_move_pages(0, 4, pages, NULL, status, 0);
+	TEST_ASSERT(status[0] == 0, "Expected page 0 on node 0, got it on node %d", status[0]);
+	TEST_ASSERT(status[1] == 0, "Expected page 1 on node 0, got it on node %d", status[1]);
+	TEST_ASSERT(status[2] == 1, "Expected page 2 on node 1, got it on node %d", status[2]);
+	TEST_ASSERT(status[3] == 1, "Expected page 3 on node 1, got it on node %d", status[3]);
+
+	kvm_munmap(mem, total_size);
+}
+
 static void test_fault_sigbus(int fd, size_t accessible_size, size_t map_size)
 {
 	const char val = 0xaa;
@@ -273,11 +369,13 @@ static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags)
 		if (flags & GUEST_MEMFD_FLAG_INIT_SHARED) {
 			gmem_test(mmap_supported, vm, flags);
 			gmem_test(fault_overflow, vm, flags);
+			gmem_test(numa_allocation, vm, flags);
 		} else {
 			gmem_test(fault_private, vm, flags);
 		}
 
 		gmem_test(mmap_cow, vm, flags);
+		gmem_test(mbind, vm, flags);
 	} else {
 		gmem_test(mmap_not_supported, vm, flags);
 	}
diff --git a/tools/testing/selftests/kvm/include/kvm_syscalls.h b/tools/testing/selftests/kvm/include/kvm_syscalls.h
new file mode 100644
index 000000000000..d4e613162bba
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/kvm_syscalls.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_SYSCALLS_H
+#define SELFTEST_KVM_SYSCALLS_H
+
+#include <sys/syscall.h>
+
+#define MAP_ARGS0(m,...)
+#define MAP_ARGS1(m,t,a,...) m(t,a)
+#define MAP_ARGS2(m,t,a,...) m(t,a), MAP_ARGS1(m,__VA_ARGS__)
+#define MAP_ARGS3(m,t,a,...) m(t,a), MAP_ARGS2(m,__VA_ARGS__)
+#define MAP_ARGS4(m,t,a,...) m(t,a), MAP_ARGS3(m,__VA_ARGS__)
+#define MAP_ARGS5(m,t,a,...) m(t,a), MAP_ARGS4(m,__VA_ARGS__)
+#define MAP_ARGS6(m,t,a,...) m(t,a), MAP_ARGS5(m,__VA_ARGS__)
+#define MAP_ARGS(n,...) MAP_ARGS##n(__VA_ARGS__)
+
+#define __DECLARE_ARGS(t, a)	t a
+#define __UNPACK_ARGS(t, a)	a
+
+#define DECLARE_ARGS(nr_args, args...) MAP_ARGS(nr_args, __DECLARE_ARGS, args)
+#define UNPACK_ARGS(nr_args, args...) MAP_ARGS(nr_args, __UNPACK_ARGS, args)
+
+#define __KVM_SYSCALL_ERROR(_name, _ret) \
+	"%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno)
+
+/* Define a kvm_<syscall>() API to assert success. */
+#define __KVM_SYSCALL_DEFINE(name, nr_args, args...)			\
+static inline void kvm_##name(DECLARE_ARGS(nr_args, args))		\
+{									\
+	int r;								\
+									\
+	r = name(UNPACK_ARGS(nr_args, args));				\
+	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR(#name, r));			\
+}
+
+/*
+ * Macro to define syscall APIs, either because KVM selftests doesn't link to
+ * the standard library, e.g. libnuma, or because there is no library that yet
+ * provides the syscall.  These
+ */
+#define KVM_SYSCALL_DEFINE(name, nr_args, args...)			\
+static inline long name(DECLARE_ARGS(nr_args, args))			\
+{									\
+	return syscall(__NR_##name, UNPACK_ARGS(nr_args, args));	\
+}									\
+__KVM_SYSCALL_DEFINE(name, nr_args, args)
+
+/*
+ * Special case mmap(), as KVM selftest rarely/never specific an address,
+ * rarely specify an offset, and because the unique return code requires
+ * special handling anyways.
+ */
+static inline void *__kvm_mmap(size_t size, int prot, int flags, int fd,
+			       off_t offset)
+{
+	void *mem;
+
+	mem = mmap(NULL, size, prot, flags, fd, offset);
+	TEST_ASSERT(mem != MAP_FAILED, __KVM_SYSCALL_ERROR("mmap()",
+		    (int)(unsigned long)MAP_FAILED));
+	return mem;
+}
+
+static inline void *kvm_mmap(size_t size, int prot, int flags, int fd)
+{
+	return __kvm_mmap(size, prot, flags, fd, 0);
+}
+
+static inline int kvm_dup(int fd)
+{
+	int new_fd = dup(fd);
+
+	TEST_ASSERT(new_fd >= 0, __KVM_SYSCALL_ERROR("dup()", new_fd));
+	return new_fd;
+}
+
+__KVM_SYSCALL_DEFINE(munmap, 2, void *, mem, size_t, size);
+__KVM_SYSCALL_DEFINE(close, 1, int, fd);
+__KVM_SYSCALL_DEFINE(fallocate, 4, int, fd, int, mode, loff_t, offset, loff_t, len);
+__KVM_SYSCALL_DEFINE(ftruncate, 2, unsigned int, fd, off_t, length);
+
+#endif /* SELFTEST_KVM_SYSCALLS_H */
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index d3f3e455c031..c2481be61434 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -23,6 +23,7 @@
 
 #include <pthread.h>
 
+#include "kvm_syscalls.h"
 #include "kvm_util_arch.h"
 #include "kvm_util_types.h"
 #include "sparsebit.h"
@@ -283,34 +284,6 @@ static inline bool kvm_has_cap(long cap)
 	return kvm_check_cap(cap);
 }
 
-#define __KVM_SYSCALL_ERROR(_name, _ret) \
-	"%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno)
-
-static inline void *__kvm_mmap(size_t size, int prot, int flags, int fd,
-			       off_t offset)
-{
-	void *mem;
-
-	mem = mmap(NULL, size, prot, flags, fd, offset);
-	TEST_ASSERT(mem != MAP_FAILED, __KVM_SYSCALL_ERROR("mmap()",
-		    (int)(unsigned long)MAP_FAILED));
-
-	return mem;
-}
-
-static inline void *kvm_mmap(size_t size, int prot, int flags, int fd)
-{
-	return __kvm_mmap(size, prot, flags, fd, 0);
-}
-
-static inline void kvm_munmap(void *mem, size_t size)
-{
-	int ret;
-
-	ret = munmap(mem, size);
-	TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
-}
-
 /*
  * Use the "inner", double-underscore macro when reporting errors from within
  * other macros so that the name of ioctl() and not its literal numeric value
@@ -700,12 +673,12 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flag
 				 uint32_t guest_memfd, uint64_t guest_memfd_offset);
 
 void vm_userspace_mem_region_add(struct kvm_vm *vm,
-	enum vm_mem_backing_src_type src_type,
-	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
-	uint32_t flags);
+				 enum vm_mem_backing_src_type src_type,
+				 uint64_t gpa, uint32_t slot, uint64_t npages,
+				 uint32_t flags);
 void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
-		uint64_t guest_paddr, uint32_t slot, uint64_t npages,
-		uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset);
+		uint64_t gpa, uint32_t slot, uint64_t npages, uint32_t flags,
+		int guest_memfd_fd, uint64_t guest_memfd_offset);
 
 #ifndef vm_arch_has_protected_memory
 static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm)
diff --git a/tools/testing/selftests/kvm/include/numaif.h b/tools/testing/selftests/kvm/include/numaif.h
index b020547403fd..29572a6d789c 100644
--- a/tools/testing/selftests/kvm/include/numaif.h
+++ b/tools/testing/selftests/kvm/include/numaif.h
@@ -1,55 +1,83 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * tools/testing/selftests/kvm/include/numaif.h
- *
- * Copyright (C) 2020, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * Header file that provides access to NUMA API functions not explicitly
- * exported to user space.
- */
+/* Copyright (C) 2020, Google LLC. */
 
 #ifndef SELFTEST_KVM_NUMAIF_H
 #define SELFTEST_KVM_NUMAIF_H
 
-#define __NR_get_mempolicy 239
-#define __NR_migrate_pages 256
+#include <dirent.h>
 
-/* System calls */
-long get_mempolicy(int *policy, const unsigned long *nmask,
-		   unsigned long maxnode, void *addr, int flags)
+#include <linux/mempolicy.h>
+
+#include "kvm_syscalls.h"
+
+KVM_SYSCALL_DEFINE(get_mempolicy, 5, int *, policy, const unsigned long *, nmask,
+		   unsigned long, maxnode, void *, addr, int, flags);
+
+KVM_SYSCALL_DEFINE(set_mempolicy, 3, int, mode, const unsigned long *, nmask,
+		   unsigned long, maxnode);
+
+KVM_SYSCALL_DEFINE(set_mempolicy_home_node, 4, unsigned long, start,
+		   unsigned long, len, unsigned long, home_node,
+		   unsigned long, flags);
+
+KVM_SYSCALL_DEFINE(migrate_pages, 4, int, pid, unsigned long, maxnode,
+		   const unsigned long *, frommask, const unsigned long *, tomask);
+
+KVM_SYSCALL_DEFINE(move_pages, 6, int, pid, unsigned long, count, void *, pages,
+		   const int *, nodes, int *, status, int, flags);
+
+KVM_SYSCALL_DEFINE(mbind, 6, void *, addr, unsigned long, size, int, mode,
+		   const unsigned long *, nodemask, unsigned long, maxnode,
+		   unsigned int, flags);
+
+static inline int get_max_numa_node(void)
 {
-	return syscall(__NR_get_mempolicy, policy, nmask,
-		       maxnode, addr, flags);
+	struct dirent *de;
+	int max_node = 0;
+	DIR *d;
+
+	/*
+	 * Assume there's a single node if the kernel doesn't support NUMA,
+	 * or if no nodes are found.
+	 */
+	d = opendir("/sys/devices/system/node");
+	if (!d)
+		return 0;
+
+	while ((de = readdir(d)) != NULL) {
+		int node_id;
+		char *endptr;
+
+		if (strncmp(de->d_name, "node", 4) != 0)
+			continue;
+
+		node_id = strtol(de->d_name + 4, &endptr, 10);
+		if (*endptr != '\0')
+			continue;
+
+		if (node_id > max_node)
+			max_node = node_id;
+	}
+	closedir(d);
+
+	return max_node;
 }
 
-long migrate_pages(int pid, unsigned long maxnode,
-		   const unsigned long *frommask,
-		   const unsigned long *tomask)
+static bool is_numa_available(void)
 {
-	return syscall(__NR_migrate_pages, pid, maxnode, frommask, tomask);
+	/*
+	 * Probe for NUMA by doing a dummy get_mempolicy().  If the syscall
+	 * fails with ENOSYS, then the kernel was built without NUMA support.
+	 * if the syscall fails with EPERM, then the process/user lacks the
+	 * necessary capabilities (CAP_SYS_NICE).
+	 */
+	return !get_mempolicy(NULL, NULL, 0, NULL, 0) ||
+		(errno != ENOSYS && errno != EPERM);
 }
 
-/* Policies */
-#define MPOL_DEFAULT	 0
-#define MPOL_PREFERRED	 1
-#define MPOL_BIND	 2
-#define MPOL_INTERLEAVE	 3
-
-#define MPOL_MAX MPOL_INTERLEAVE
-
-/* Flags for get_mem_policy */
-#define MPOL_F_NODE	    (1<<0)  /* return next il node or node of address */
-				    /* Warning: MPOL_F_NODE is unsupported and
-				     * subject to change. Don't use.
-				     */
-#define MPOL_F_ADDR	    (1<<1)  /* look up vma using address */
-#define MPOL_F_MEMS_ALLOWED (1<<2)  /* query nodes allowed in cpuset */
-
-/* Flags for mbind */
-#define MPOL_MF_STRICT	     (1<<0) /* Verify existing pages in the mapping */
-#define MPOL_MF_MOVE	     (1<<1) /* Move pages owned by this process to conform to mapping */
-#define MPOL_MF_MOVE_ALL     (1<<2) /* Move every page to conform to mapping */
+static inline bool is_multi_numa_node_system(void)
+{
+	return is_numa_available() && get_max_numa_node() >= 1;
+}
 
 #endif /* SELFTEST_KVM_NUMAIF_H */
diff --git a/tools/testing/selftests/kvm/kvm_binary_stats_test.c b/tools/testing/selftests/kvm/kvm_binary_stats_test.c
index f02355c3c4c2..b7dbde9c0843 100644
--- a/tools/testing/selftests/kvm/kvm_binary_stats_test.c
+++ b/tools/testing/selftests/kvm/kvm_binary_stats_test.c
@@ -239,14 +239,14 @@ int main(int argc, char *argv[])
 		 * single stats file works and doesn't cause explosions.
 		 */
 		vm_stats_fds = vm_get_stats_fd(vms[i]);
-		stats_test(dup(vm_stats_fds));
+		stats_test(kvm_dup(vm_stats_fds));
 
 		/* Verify userspace can instantiate multiple stats files. */
 		stats_test(vm_get_stats_fd(vms[i]));
 
 		for (j = 0; j < max_vcpu; ++j) {
 			vcpu_stats_fds[j] = vcpu_get_stats_fd(vcpus[i * max_vcpu + j]);
-			stats_test(dup(vcpu_stats_fds[j]));
+			stats_test(kvm_dup(vcpu_stats_fds[j]));
 			stats_test(vcpu_get_stats_fd(vcpus[i * max_vcpu + j]));
 		}
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1a93d6361671..a334f6ed50d6 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -704,8 +704,6 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
 
 static void kvm_stats_release(struct kvm_binary_stats *stats)
 {
-	int ret;
-
 	if (stats->fd < 0)
 		return;
 
@@ -714,8 +712,7 @@ static void kvm_stats_release(struct kvm_binary_stats *stats)
 		stats->desc = NULL;
 	}
 
-	ret = close(stats->fd);
-	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
+	kvm_close(stats->fd);
 	stats->fd = -1;
 }
 
@@ -738,8 +735,6 @@ __weak void vcpu_arch_free(struct kvm_vcpu *vcpu)
  */
 static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 {
-	int ret;
-
 	if (vcpu->dirty_gfns) {
 		kvm_munmap(vcpu->dirty_gfns, vm->dirty_ring_size);
 		vcpu->dirty_gfns = NULL;
@@ -747,9 +742,7 @@ static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 
 	kvm_munmap(vcpu->run, vcpu_mmap_sz());
 
-	ret = close(vcpu->fd);
-	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
-
+	kvm_close(vcpu->fd);
 	kvm_stats_release(&vcpu->stats);
 
 	list_del(&vcpu->list);
@@ -761,16 +754,12 @@ static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 void kvm_vm_release(struct kvm_vm *vmp)
 {
 	struct kvm_vcpu *vcpu, *tmp;
-	int ret;
 
 	list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list)
 		vm_vcpu_rm(vmp, vcpu);
 
-	ret = close(vmp->fd);
-	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
-
-	ret = close(vmp->kvm_fd);
-	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
+	kvm_close(vmp->fd);
+	kvm_close(vmp->kvm_fd);
 
 	/* Free cached stats metadata and close FD */
 	kvm_stats_release(&vmp->stats);
@@ -828,7 +817,7 @@ void kvm_vm_free(struct kvm_vm *vmp)
 int kvm_memfd_alloc(size_t size, bool hugepages)
 {
 	int memfd_flags = MFD_CLOEXEC;
-	int fd, r;
+	int fd;
 
 	if (hugepages)
 		memfd_flags |= MFD_HUGETLB;
@@ -836,11 +825,8 @@ int kvm_memfd_alloc(size_t size, bool hugepages)
 	fd = memfd_create("kvm_selftest", memfd_flags);
 	TEST_ASSERT(fd != -1, __KVM_SYSCALL_ERROR("memfd_create()", fd));
 
-	r = ftruncate(fd, size);
-	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("ftruncate()", r));
-
-	r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size);
-	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+	kvm_ftruncate(fd, size);
+	kvm_fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size);
 
 	return fd;
 }
@@ -957,8 +943,8 @@ void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags
 
 /* FIXME: This thing needs to be ripped apart and rewritten. */
 void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
-		uint64_t guest_paddr, uint32_t slot, uint64_t npages,
-		uint32_t flags, int guest_memfd, uint64_t guest_memfd_offset)
+		uint64_t gpa, uint32_t slot, uint64_t npages, uint32_t flags,
+		int guest_memfd, uint64_t guest_memfd_offset)
 {
 	int ret;
 	struct userspace_mem_region *region;
@@ -972,30 +958,29 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 		"Number of guest pages is not compatible with the host. "
 		"Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages));
 
-	TEST_ASSERT((guest_paddr % vm->page_size) == 0, "Guest physical "
+	TEST_ASSERT((gpa % vm->page_size) == 0, "Guest physical "
 		"address not on a page boundary.\n"
-		"  guest_paddr: 0x%lx vm->page_size: 0x%x",
-		guest_paddr, vm->page_size);
-	TEST_ASSERT((((guest_paddr >> vm->page_shift) + npages) - 1)
+		"  gpa: 0x%lx vm->page_size: 0x%x",
+		gpa, vm->page_size);
+	TEST_ASSERT((((gpa >> vm->page_shift) + npages) - 1)
 		<= vm->max_gfn, "Physical range beyond maximum "
 		"supported physical address,\n"
-		"  guest_paddr: 0x%lx npages: 0x%lx\n"
+		"  gpa: 0x%lx npages: 0x%lx\n"
 		"  vm->max_gfn: 0x%lx vm->page_size: 0x%x",
-		guest_paddr, npages, vm->max_gfn, vm->page_size);
+		gpa, npages, vm->max_gfn, vm->page_size);
 
 	/*
 	 * Confirm a mem region with an overlapping address doesn't
 	 * already exist.
 	 */
 	region = (struct userspace_mem_region *) userspace_mem_region_find(
-		vm, guest_paddr, (guest_paddr + npages * vm->page_size) - 1);
+		vm, gpa, (gpa + npages * vm->page_size) - 1);
 	if (region != NULL)
 		TEST_FAIL("overlapping userspace_mem_region already "
 			"exists\n"
-			"  requested guest_paddr: 0x%lx npages: 0x%lx "
-			"page_size: 0x%x\n"
-			"  existing guest_paddr: 0x%lx size: 0x%lx",
-			guest_paddr, npages, vm->page_size,
+			"  requested gpa: 0x%lx npages: 0x%lx page_size: 0x%x\n"
+			"  existing gpa: 0x%lx size: 0x%lx",
+			gpa, npages, vm->page_size,
 			(uint64_t) region->region.guest_phys_addr,
 			(uint64_t) region->region.memory_size);
 
@@ -1009,8 +994,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 			"already exists.\n"
 			"  requested slot: %u paddr: 0x%lx npages: 0x%lx\n"
 			"  existing slot: %u paddr: 0x%lx size: 0x%lx",
-			slot, guest_paddr, npages,
-			region->region.slot,
+			slot, gpa, npages, region->region.slot,
 			(uint64_t) region->region.guest_phys_addr,
 			(uint64_t) region->region.memory_size);
 	}
@@ -1036,7 +1020,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
-	TEST_ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));
+	TEST_ASSERT_EQ(gpa, align_up(gpa, backing_src_pagesz));
 
 	/* Add enough memory to align up if necessary */
 	if (alignment > 1)
@@ -1084,8 +1068,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 			 * needing to track if the fd is owned by the framework
 			 * or by the caller.
 			 */
-			guest_memfd = dup(guest_memfd);
-			TEST_ASSERT(guest_memfd >= 0, __KVM_SYSCALL_ERROR("dup()", guest_memfd));
+			guest_memfd = kvm_dup(guest_memfd);
 		}
 
 		region->region.guest_memfd = guest_memfd;
@@ -1097,20 +1080,18 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	region->unused_phy_pages = sparsebit_alloc();
 	if (vm_arch_has_protected_memory(vm))
 		region->protected_phy_pages = sparsebit_alloc();
-	sparsebit_set_num(region->unused_phy_pages,
-		guest_paddr >> vm->page_shift, npages);
+	sparsebit_set_num(region->unused_phy_pages, gpa >> vm->page_shift, npages);
 	region->region.slot = slot;
 	region->region.flags = flags;
-	region->region.guest_phys_addr = guest_paddr;
+	region->region.guest_phys_addr = gpa;
 	region->region.memory_size = npages * vm->page_size;
 	region->region.userspace_addr = (uintptr_t) region->host_mem;
 	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
 	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
 		"  rc: %i errno: %i\n"
 		"  slot: %u flags: 0x%x\n"
-		"  guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d",
-		ret, errno, slot, flags,
-		guest_paddr, (uint64_t) region->region.memory_size,
+		"  guest_phys_addr: 0x%lx size: 0x%llx guest_memfd: %d",
+		ret, errno, slot, flags, gpa, region->region.memory_size,
 		region->region.guest_memfd);
 
 	/* Add to quick lookup data structures */
@@ -1132,10 +1113,10 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 
 void vm_userspace_mem_region_add(struct kvm_vm *vm,
 				 enum vm_mem_backing_src_type src_type,
-				 uint64_t guest_paddr, uint32_t slot,
-				 uint64_t npages, uint32_t flags)
+				 uint64_t gpa, uint32_t slot, uint64_t npages,
+				 uint32_t flags)
 {
-	vm_mem_add(vm, src_type, guest_paddr, slot, npages, flags, -1, 0);
+	vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0);
 }
 
 /*
@@ -2305,11 +2286,35 @@ __weak void kvm_selftest_arch_init(void)
 {
 }
 
+static void report_unexpected_signal(int signum)
+{
+#define KVM_CASE_SIGNUM(sig)					\
+	case sig: TEST_FAIL("Unexpected " #sig " (%d)\n", signum)
+
+	switch (signum) {
+	KVM_CASE_SIGNUM(SIGBUS);
+	KVM_CASE_SIGNUM(SIGSEGV);
+	KVM_CASE_SIGNUM(SIGILL);
+	KVM_CASE_SIGNUM(SIGFPE);
+	default:
+		TEST_FAIL("Unexpected signal %d\n", signum);
+	}
+}
+
 void __attribute((constructor)) kvm_selftest_init(void)
 {
+	struct sigaction sig_sa = {
+		.sa_handler = report_unexpected_signal,
+	};
+
 	/* Tell stdout not to buffer its content. */
 	setbuf(stdout, NULL);
 
+	sigaction(SIGBUS, &sig_sa, NULL);
+	sigaction(SIGSEGV, &sig_sa, NULL);
+	sigaction(SIGILL, &sig_sa, NULL);
+	sigaction(SIGFPE, &sig_sa, NULL);
+
 	guest_random_seed = last_guest_seed = random();
 	pr_info("Random seed: 0x%x\n", guest_random_seed);
 
diff --git a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
index 82a8d88b5338..1969f4ab9b28 100644
--- a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
+++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
@@ -380,7 +380,7 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 	pthread_t threads[KVM_MAX_VCPUS];
 	struct kvm_vm *vm;
-	int memfd, i, r;
+	int memfd, i;
 
 	const struct vm_shape shape = {
 		.mode = VM_MODE_DEFAULT,
@@ -428,11 +428,8 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t
 	 * should prevent the VM from being fully destroyed until the last
 	 * reference to the guest_memfd is also put.
 	 */
-	r = fallocate(memfd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, memfd_size);
-	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
-
-	r = fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size);
-	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+	kvm_fallocate(memfd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, memfd_size);
+	kvm_fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size);
 
 	close(memfd);
 }
diff --git a/tools/testing/selftests/kvm/x86/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c
index 35cb9de54a82..ae4a4b6c05ca 100644
--- a/tools/testing/selftests/kvm/x86/xapic_ipi_test.c
+++ b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c
@@ -256,7 +256,7 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs,
 	int nodes = 0;
 	time_t start_time, last_update, now;
 	time_t interval_secs = 1;
-	int i, r;
+	int i;
 	int from, to;
 	unsigned long bit;
 	uint64_t hlt_count;
@@ -267,9 +267,8 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs,
 		delay_usecs);
 
 	/* Get set of first 64 numa nodes available */
-	r = get_mempolicy(NULL, &nodemask, sizeof(nodemask) * 8,
+	kvm_get_mempolicy(NULL, &nodemask, sizeof(nodemask) * 8,
 			  0, MPOL_F_MEMS_ALLOWED);
-	TEST_ASSERT(r == 0, "get_mempolicy failed errno=%d", errno);
 
 	fprintf(stderr, "Numa nodes found amongst first %lu possible nodes "
 		"(each 1-bit indicates node is present): %#lx\n",
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index ffadc5ee8e04..fdaea3422c30 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -1,18 +1,47 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/anon_inodes.h>
 #include <linux/backing-dev.h>
 #include <linux/falloc.h>
+#include <linux/fs.h>
 #include <linux/kvm_host.h>
+#include <linux/mempolicy.h>
+#include <linux/pseudo_fs.h>
 #include <linux/pagemap.h>
-#include <linux/anon_inodes.h>
 
 #include "kvm_mm.h"
 
-struct kvm_gmem {
+static struct vfsmount *kvm_gmem_mnt;
+
+/*
+ * A guest_memfd instance can be associated multiple VMs, each with its own
+ * "view" of the underlying physical memory.
+ *
+ * The gmem's inode is effectively the raw underlying physical storage, and is
+ * used to track properties of the physical memory, while each gmem file is
+ * effectively a single VM's view of that storage, and is used to track assets
+ * specific to its associated VM, e.g. memslots=>gmem bindings.
+ */
+struct gmem_file {
 	struct kvm *kvm;
 	struct xarray bindings;
 	struct list_head entry;
 };
 
+struct gmem_inode {
+	struct shared_policy policy;
+	struct inode vfs_inode;
+
+	u64 flags;
+};
+
+static __always_inline struct gmem_inode *GMEM_I(struct inode *inode)
+{
+	return container_of(inode, struct gmem_inode, vfs_inode);
+}
+
+#define kvm_gmem_for_each_file(f, mapping) \
+	list_for_each_entry(f, &(mapping)->i_private_list, entry)
+
 /**
  * folio_file_pfn - like folio_file_page, but return a pfn.
  * @folio: The folio which contains this index.
@@ -25,6 +54,11 @@ static inline kvm_pfn_t folio_file_pfn(struct folio *folio, pgoff_t index)
 	return folio_pfn(folio) + (index & (folio_nr_pages(folio) - 1));
 }
 
+static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return gfn - slot->base_gfn + slot->gmem.pgoff;
+}
+
 static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot,
 				    pgoff_t index, struct folio *folio)
 {
@@ -77,9 +111,9 @@ static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot,
 	 * The order will be passed when creating the guest_memfd, and
 	 * checked when creating memslots.
 	 */
-	WARN_ON(!IS_ALIGNED(slot->gmem.pgoff, 1 << folio_order(folio)));
-	index = gfn - slot->base_gfn + slot->gmem.pgoff;
-	index = ALIGN_DOWN(index, 1 << folio_order(folio));
+	WARN_ON(!IS_ALIGNED(slot->gmem.pgoff, folio_nr_pages(folio)));
+	index = kvm_gmem_get_index(slot, gfn);
+	index = ALIGN_DOWN(index, folio_nr_pages(folio));
 	r = __kvm_gmem_prepare_folio(kvm, slot, index, folio);
 	if (!r)
 		kvm_gmem_mark_prepared(folio);
@@ -99,27 +133,45 @@ static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot,
 static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
 {
 	/* TODO: Support huge pages. */
-	return filemap_grab_folio(inode->i_mapping, index);
+	struct mempolicy *policy;
+	struct folio *folio;
+
+	/*
+	 * Fast-path: See if folio is already present in mapping to avoid
+	 * policy_lookup.
+	 */
+	folio = __filemap_get_folio(inode->i_mapping, index,
+				    FGP_LOCK | FGP_ACCESSED, 0);
+	if (!IS_ERR(folio))
+		return folio;
+
+	policy = mpol_shared_policy_lookup(&GMEM_I(inode)->policy, index);
+	folio = __filemap_get_folio_mpol(inode->i_mapping, index,
+					 FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
+					 mapping_gfp_mask(inode->i_mapping), policy);
+	mpol_cond_put(policy);
+
+	return folio;
 }
 
 static enum kvm_gfn_range_filter kvm_gmem_get_invalidate_filter(struct inode *inode)
 {
-	if ((u64)inode->i_private & GUEST_MEMFD_FLAG_INIT_SHARED)
+	if (GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED)
 		return KVM_FILTER_SHARED;
 
 	return KVM_FILTER_PRIVATE;
 }
 
-static void __kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start,
+static void __kvm_gmem_invalidate_begin(struct gmem_file *f, pgoff_t start,
 					pgoff_t end,
 					enum kvm_gfn_range_filter attr_filter)
 {
 	bool flush = false, found_memslot = false;
 	struct kvm_memory_slot *slot;
-	struct kvm *kvm = gmem->kvm;
+	struct kvm *kvm = f->kvm;
 	unsigned long index;
 
-	xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) {
+	xa_for_each_range(&f->bindings, index, slot, start, end - 1) {
 		pgoff_t pgoff = slot->gmem.pgoff;
 
 		struct kvm_gfn_range gfn_range = {
@@ -150,22 +202,21 @@ static void __kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start,
 static void kvm_gmem_invalidate_begin(struct inode *inode, pgoff_t start,
 				      pgoff_t end)
 {
-	struct list_head *gmem_list = &inode->i_mapping->i_private_list;
 	enum kvm_gfn_range_filter attr_filter;
-	struct kvm_gmem *gmem;
+	struct gmem_file *f;
 
 	attr_filter = kvm_gmem_get_invalidate_filter(inode);
 
-	list_for_each_entry(gmem, gmem_list, entry)
-		__kvm_gmem_invalidate_begin(gmem, start, end, attr_filter);
+	kvm_gmem_for_each_file(f, inode->i_mapping)
+		__kvm_gmem_invalidate_begin(f, start, end, attr_filter);
 }
 
-static void __kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start,
+static void __kvm_gmem_invalidate_end(struct gmem_file *f, pgoff_t start,
 				      pgoff_t end)
 {
-	struct kvm *kvm = gmem->kvm;
+	struct kvm *kvm = f->kvm;
 
-	if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+	if (xa_find(&f->bindings, &start, end - 1, XA_PRESENT)) {
 		KVM_MMU_LOCK(kvm);
 		kvm_mmu_invalidate_end(kvm);
 		KVM_MMU_UNLOCK(kvm);
@@ -175,11 +226,10 @@ static void __kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start,
 static void kvm_gmem_invalidate_end(struct inode *inode, pgoff_t start,
 				    pgoff_t end)
 {
-	struct list_head *gmem_list = &inode->i_mapping->i_private_list;
-	struct kvm_gmem *gmem;
+	struct gmem_file *f;
 
-	list_for_each_entry(gmem, gmem_list, entry)
-		__kvm_gmem_invalidate_end(gmem, start, end);
+	kvm_gmem_for_each_file(f, inode->i_mapping)
+		__kvm_gmem_invalidate_end(f, start, end);
 }
 
 static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
@@ -277,9 +327,9 @@ static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset,
 
 static int kvm_gmem_release(struct inode *inode, struct file *file)
 {
-	struct kvm_gmem *gmem = file->private_data;
+	struct gmem_file *f = file->private_data;
 	struct kvm_memory_slot *slot;
-	struct kvm *kvm = gmem->kvm;
+	struct kvm *kvm = f->kvm;
 	unsigned long index;
 
 	/*
@@ -299,7 +349,7 @@ static int kvm_gmem_release(struct inode *inode, struct file *file)
 
 	filemap_invalidate_lock(inode->i_mapping);
 
-	xa_for_each(&gmem->bindings, index, slot)
+	xa_for_each(&f->bindings, index, slot)
 		WRITE_ONCE(slot->gmem.file, NULL);
 
 	/*
@@ -307,18 +357,18 @@ static int kvm_gmem_release(struct inode *inode, struct file *file)
 	 * Zap all SPTEs pointed at by this file.  Do not free the backing
 	 * memory, as its lifetime is associated with the inode, not the file.
 	 */
-	__kvm_gmem_invalidate_begin(gmem, 0, -1ul,
+	__kvm_gmem_invalidate_begin(f, 0, -1ul,
 				    kvm_gmem_get_invalidate_filter(inode));
-	__kvm_gmem_invalidate_end(gmem, 0, -1ul);
+	__kvm_gmem_invalidate_end(f, 0, -1ul);
 
-	list_del(&gmem->entry);
+	list_del(&f->entry);
 
 	filemap_invalidate_unlock(inode->i_mapping);
 
 	mutex_unlock(&kvm->slots_lock);
 
-	xa_destroy(&gmem->bindings);
-	kfree(gmem);
+	xa_destroy(&f->bindings);
+	kfree(f);
 
 	kvm_put_kvm(kvm);
 
@@ -335,16 +385,12 @@ static inline struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot)
 	return get_file_active(&slot->gmem.file);
 }
 
-static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
-{
-	return gfn - slot->base_gfn + slot->gmem.pgoff;
-}
+DEFINE_CLASS(gmem_get_file, struct file *, if (_T) fput(_T),
+	     kvm_gmem_get_file(slot), struct kvm_memory_slot *slot);
 
 static bool kvm_gmem_supports_mmap(struct inode *inode)
 {
-	const u64 flags = (u64)inode->i_private;
-
-	return flags & GUEST_MEMFD_FLAG_MMAP;
+	return GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_MMAP;
 }
 
 static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf)
@@ -356,17 +402,15 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf)
 	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
 		return VM_FAULT_SIGBUS;
 
-	if (!((u64)inode->i_private & GUEST_MEMFD_FLAG_INIT_SHARED))
+	if (!(GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED))
 		return VM_FAULT_SIGBUS;
 
 	folio = kvm_gmem_get_folio(inode, vmf->pgoff);
 	if (IS_ERR(folio)) {
-		int err = PTR_ERR(folio);
-
-		if (err == -EAGAIN)
+		if (PTR_ERR(folio) == -EAGAIN)
 			return VM_FAULT_RETRY;
 
-		return vmf_error(err);
+		return vmf_error(PTR_ERR(folio));
 	}
 
 	if (WARN_ON_ONCE(folio_test_large(folio))) {
@@ -390,8 +434,40 @@ out_folio:
 	return ret;
 }
 
+#ifdef CONFIG_NUMA
+static int kvm_gmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
+{
+	struct inode *inode = file_inode(vma->vm_file);
+
+	return mpol_set_shared_policy(&GMEM_I(inode)->policy, vma, mpol);
+}
+
+static struct mempolicy *kvm_gmem_get_policy(struct vm_area_struct *vma,
+					     unsigned long addr, pgoff_t *pgoff)
+{
+	struct inode *inode = file_inode(vma->vm_file);
+
+	*pgoff = vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT);
+
+	/*
+	 * Return the memory policy for this index, or NULL if none is set.
+	 *
+	 * Returning NULL, e.g. instead of the current task's memory policy, is
+	 * important for the .get_policy kernel ABI: it indicates that no
+	 * explicit policy has been set via mbind() for this memory. The caller
+	 * can then replace NULL with the default memory policy instead of the
+	 * current task's memory policy.
+	 */
+	return mpol_shared_policy_lookup(&GMEM_I(inode)->policy, *pgoff);
+}
+#endif /* CONFIG_NUMA */
+
 static const struct vm_operations_struct kvm_gmem_vm_ops = {
-	.fault = kvm_gmem_fault_user_mapping,
+	.fault		= kvm_gmem_fault_user_mapping,
+#ifdef CONFIG_NUMA
+	.get_policy	= kvm_gmem_get_policy,
+	.set_policy	= kvm_gmem_set_policy,
+#endif
 };
 
 static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
@@ -416,11 +492,6 @@ static struct file_operations kvm_gmem_fops = {
 	.fallocate	= kvm_gmem_fallocate,
 };
 
-void kvm_gmem_init(struct module *module)
-{
-	kvm_gmem_fops.owner = module;
-}
-
 static int kvm_gmem_migrate_folio(struct address_space *mapping,
 				  struct folio *dst, struct folio *src,
 				  enum migrate_mode mode)
@@ -492,8 +563,8 @@ bool __weak kvm_arch_supports_gmem_init_shared(struct kvm *kvm)
 
 static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 {
-	const char *anon_name = "[kvm-gmem]";
-	struct kvm_gmem *gmem;
+	static const char *name = "[kvm-gmem]";
+	struct gmem_file *f;
 	struct inode *inode;
 	struct file *file;
 	int fd, err;
@@ -502,25 +573,24 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 	if (fd < 0)
 		return fd;
 
-	gmem = kzalloc(sizeof(*gmem), GFP_KERNEL);
-	if (!gmem) {
+	f = kzalloc(sizeof(*f), GFP_KERNEL);
+	if (!f) {
 		err = -ENOMEM;
 		goto err_fd;
 	}
 
-	file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem,
-					 O_RDWR, NULL);
-	if (IS_ERR(file)) {
-		err = PTR_ERR(file);
+	/* __fput() will take care of fops_put(). */
+	if (!fops_get(&kvm_gmem_fops)) {
+		err = -ENOENT;
 		goto err_gmem;
 	}
 
-	file->f_flags |= O_LARGEFILE;
-
-	inode = file->f_inode;
-	WARN_ON(file->f_mapping != inode->i_mapping);
+	inode = anon_inode_make_secure_inode(kvm_gmem_mnt->mnt_sb, name, NULL);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		goto err_fops;
+	}
 
-	inode->i_private = (void *)(unsigned long)flags;
 	inode->i_op = &kvm_gmem_iops;
 	inode->i_mapping->a_ops = &kvm_gmem_aops;
 	inode->i_mode |= S_IFREG;
@@ -530,16 +600,31 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 	/* Unmovable mappings are supposed to be marked unevictable as well. */
 	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
 
+	GMEM_I(inode)->flags = flags;
+
+	file = alloc_file_pseudo(inode, kvm_gmem_mnt, name, O_RDWR, &kvm_gmem_fops);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto err_inode;
+	}
+
+	file->f_flags |= O_LARGEFILE;
+	file->private_data = f;
+
 	kvm_get_kvm(kvm);
-	gmem->kvm = kvm;
-	xa_init(&gmem->bindings);
-	list_add(&gmem->entry, &inode->i_mapping->i_private_list);
+	f->kvm = kvm;
+	xa_init(&f->bindings);
+	list_add(&f->entry, &inode->i_mapping->i_private_list);
 
 	fd_install(fd, file);
 	return fd;
 
+err_inode:
+	iput(inode);
+err_fops:
+	fops_put(&kvm_gmem_fops);
 err_gmem:
-	kfree(gmem);
+	kfree(f);
 err_fd:
 	put_unused_fd(fd);
 	return err;
@@ -564,7 +649,7 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
 {
 	loff_t size = slot->npages << PAGE_SHIFT;
 	unsigned long start, end;
-	struct kvm_gmem *gmem;
+	struct gmem_file *f;
 	struct inode *inode;
 	struct file *file;
 	int r = -EINVAL;
@@ -578,8 +663,8 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
 	if (file->f_op != &kvm_gmem_fops)
 		goto err;
 
-	gmem = file->private_data;
-	if (gmem->kvm != kvm)
+	f = file->private_data;
+	if (f->kvm != kvm)
 		goto err;
 
 	inode = file_inode(file);
@@ -593,8 +678,8 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
 	start = offset >> PAGE_SHIFT;
 	end = start + slot->npages;
 
-	if (!xa_empty(&gmem->bindings) &&
-	    xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+	if (!xa_empty(&f->bindings) &&
+	    xa_find(&f->bindings, &start, end - 1, XA_PRESENT)) {
 		filemap_invalidate_unlock(inode->i_mapping);
 		goto err;
 	}
@@ -609,7 +694,7 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
 	if (kvm_gmem_supports_mmap(inode))
 		slot->flags |= KVM_MEMSLOT_GMEM_ONLY;
 
-	xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL);
+	xa_store_range(&f->bindings, start, end - 1, slot, GFP_KERNEL);
 	filemap_invalidate_unlock(inode->i_mapping);
 
 	/*
@@ -623,12 +708,12 @@ err:
 	return r;
 }
 
-static void __kvm_gmem_unbind(struct kvm_memory_slot *slot, struct kvm_gmem *gmem)
+static void __kvm_gmem_unbind(struct kvm_memory_slot *slot, struct gmem_file *f)
 {
 	unsigned long start = slot->gmem.pgoff;
 	unsigned long end = start + slot->npages;
 
-	xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL);
+	xa_store_range(&f->bindings, start, end - 1, NULL, GFP_KERNEL);
 
 	/*
 	 * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn()
@@ -639,8 +724,6 @@ static void __kvm_gmem_unbind(struct kvm_memory_slot *slot, struct kvm_gmem *gme
 
 void kvm_gmem_unbind(struct kvm_memory_slot *slot)
 {
-	struct file *file;
-
 	/*
 	 * Nothing to do if the underlying file was _already_ closed, as
 	 * kvm_gmem_release() invalidates and nullifies all bindings.
@@ -648,7 +731,7 @@ void kvm_gmem_unbind(struct kvm_memory_slot *slot)
 	if (!slot->gmem.file)
 		return;
 
-	file = kvm_gmem_get_file(slot);
+	CLASS(gmem_get_file, file)(slot);
 
 	/*
 	 * However, if the file is _being_ closed, then the bindings need to be
@@ -668,8 +751,6 @@ void kvm_gmem_unbind(struct kvm_memory_slot *slot)
 	filemap_invalidate_lock(file->f_mapping);
 	__kvm_gmem_unbind(slot, file->private_data);
 	filemap_invalidate_unlock(file->f_mapping);
-
-	fput(file);
 }
 
 /* Returns a locked folio on success.  */
@@ -678,18 +759,17 @@ static struct folio *__kvm_gmem_get_pfn(struct file *file,
 					pgoff_t index, kvm_pfn_t *pfn,
 					bool *is_prepared, int *max_order)
 {
-	struct file *gmem_file = READ_ONCE(slot->gmem.file);
-	struct kvm_gmem *gmem = file->private_data;
+	struct file *slot_file = READ_ONCE(slot->gmem.file);
+	struct gmem_file *f = file->private_data;
 	struct folio *folio;
 
-	if (file != gmem_file) {
-		WARN_ON_ONCE(gmem_file);
+	if (file != slot_file) {
+		WARN_ON_ONCE(slot_file);
 		return ERR_PTR(-EFAULT);
 	}
 
-	gmem = file->private_data;
-	if (xa_load(&gmem->bindings, index) != slot) {
-		WARN_ON_ONCE(xa_load(&gmem->bindings, index));
+	if (xa_load(&f->bindings, index) != slot) {
+		WARN_ON_ONCE(xa_load(&f->bindings, index));
 		return ERR_PTR(-EIO);
 	}
 
@@ -716,19 +796,17 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 		     int *max_order)
 {
 	pgoff_t index = kvm_gmem_get_index(slot, gfn);
-	struct file *file = kvm_gmem_get_file(slot);
 	struct folio *folio;
 	bool is_prepared = false;
 	int r = 0;
 
+	CLASS(gmem_get_file, file)(slot);
 	if (!file)
 		return -EFAULT;
 
 	folio = __kvm_gmem_get_pfn(file, slot, index, pfn, &is_prepared, max_order);
-	if (IS_ERR(folio)) {
-		r = PTR_ERR(folio);
-		goto out;
-	}
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
 
 	if (!is_prepared)
 		r = kvm_gmem_prepare_folio(kvm, slot, gfn, folio);
@@ -740,8 +818,6 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 	else
 		folio_put(folio);
 
-out:
-	fput(file);
 	return r;
 }
 EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn);
@@ -750,7 +826,6 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn);
 long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages,
 		       kvm_gmem_populate_cb post_populate, void *opaque)
 {
-	struct file *file;
 	struct kvm_memory_slot *slot;
 	void __user *p;
 
@@ -766,7 +841,7 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long
 	if (!kvm_slot_has_gmem(slot))
 		return -EINVAL;
 
-	file = kvm_gmem_get_file(slot);
+	CLASS(gmem_get_file, file)(slot);
 	if (!file)
 		return -EFAULT;
 
@@ -824,8 +899,118 @@ put_folio_and_exit:
 
 	filemap_invalidate_unlock(file->f_mapping);
 
-	fput(file);
 	return ret && !i ? ret : i;
 }
 EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_populate);
 #endif
+
+static struct kmem_cache *kvm_gmem_inode_cachep;
+
+static void kvm_gmem_init_inode_once(void *__gi)
+{
+	struct gmem_inode *gi = __gi;
+
+	/*
+	 * Note!  Don't initialize the inode with anything specific to the
+	 * guest_memfd instance, or that might be specific to how the inode is
+	 * used (from the VFS-layer's perspective).  This hook is called only
+	 * during the initial slab allocation, i.e. only fields/state that are
+	 * idempotent across _all_ use of the inode _object_ can be initialized
+	 * at this time!
+	 */
+	inode_init_once(&gi->vfs_inode);
+}
+
+static struct inode *kvm_gmem_alloc_inode(struct super_block *sb)
+{
+	struct gmem_inode *gi;
+
+	gi = alloc_inode_sb(sb, kvm_gmem_inode_cachep, GFP_KERNEL);
+	if (!gi)
+		return NULL;
+
+	mpol_shared_policy_init(&gi->policy, NULL);
+
+	gi->flags = 0;
+	return &gi->vfs_inode;
+}
+
+static void kvm_gmem_destroy_inode(struct inode *inode)
+{
+	mpol_free_shared_policy(&GMEM_I(inode)->policy);
+}
+
+static void kvm_gmem_free_inode(struct inode *inode)
+{
+	kmem_cache_free(kvm_gmem_inode_cachep, GMEM_I(inode));
+}
+
+static const struct super_operations kvm_gmem_super_operations = {
+	.statfs		= simple_statfs,
+	.alloc_inode	= kvm_gmem_alloc_inode,
+	.destroy_inode	= kvm_gmem_destroy_inode,
+	.free_inode	= kvm_gmem_free_inode,
+};
+
+static int kvm_gmem_init_fs_context(struct fs_context *fc)
+{
+	struct pseudo_fs_context *ctx;
+
+	if (!init_pseudo(fc, GUEST_MEMFD_MAGIC))
+		return -ENOMEM;
+
+	fc->s_iflags |= SB_I_NOEXEC;
+	fc->s_iflags |= SB_I_NODEV;
+	ctx = fc->fs_private;
+	ctx->ops = &kvm_gmem_super_operations;
+
+	return 0;
+}
+
+static struct file_system_type kvm_gmem_fs = {
+	.name		 = "guest_memfd",
+	.init_fs_context = kvm_gmem_init_fs_context,
+	.kill_sb	 = kill_anon_super,
+};
+
+static int kvm_gmem_init_mount(void)
+{
+	kvm_gmem_mnt = kern_mount(&kvm_gmem_fs);
+
+	if (IS_ERR(kvm_gmem_mnt))
+		return PTR_ERR(kvm_gmem_mnt);
+
+	kvm_gmem_mnt->mnt_flags |= MNT_NOEXEC;
+	return 0;
+}
+
+int kvm_gmem_init(struct module *module)
+{
+	struct kmem_cache_args args = {
+		.align = 0,
+		.ctor = kvm_gmem_init_inode_once,
+	};
+	int ret;
+
+	kvm_gmem_fops.owner = module;
+	kvm_gmem_inode_cachep = kmem_cache_create("kvm_gmem_inode_cache",
+						  sizeof(struct gmem_inode),
+						  &args, SLAB_ACCOUNT);
+	if (!kvm_gmem_inode_cachep)
+		return -ENOMEM;
+
+	ret = kvm_gmem_init_mount();
+	if (ret) {
+		kmem_cache_destroy(kvm_gmem_inode_cachep);
+		return ret;
+	}
+	return 0;
+}
+
+void kvm_gmem_exit(void)
+{
+	kern_unmount(kvm_gmem_mnt);
+	kvm_gmem_mnt = NULL;
+	rcu_barrier();
+	kmem_cache_destroy(kvm_gmem_inode_cachep);
+}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index cde1eddbaa91..a5d9a6f221c2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -6517,7 +6517,9 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	if (WARN_ON_ONCE(r))
 		goto err_vfio;
 
-	kvm_gmem_init(module);
+	r = kvm_gmem_init(module);
+	if (r)
+		goto err_gmem;
 
 	r = kvm_init_virtualization();
 	if (r)
@@ -6538,6 +6540,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 err_register:
 	kvm_uninit_virtualization();
 err_virt:
+	kvm_gmem_exit();
+err_gmem:
 	kvm_vfio_ops_exit();
 err_vfio:
 	kvm_async_pf_deinit();
@@ -6569,6 +6573,7 @@ void kvm_exit(void)
 	for_each_possible_cpu(cpu)
 		free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
 	kmem_cache_destroy(kvm_vcpu_cache);
+	kvm_gmem_exit();
 	kvm_vfio_ops_exit();
 	kvm_async_pf_deinit();
 	kvm_irqfd_exit();
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index 31defb08ccba..9fcc5d5b7f8d 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -68,17 +68,18 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 #endif /* HAVE_KVM_PFNCACHE */
 
 #ifdef CONFIG_KVM_GUEST_MEMFD
-void kvm_gmem_init(struct module *module);
+int kvm_gmem_init(struct module *module);
+void kvm_gmem_exit(void);
 int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args);
 int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
 		  unsigned int fd, loff_t offset);
 void kvm_gmem_unbind(struct kvm_memory_slot *slot);
 #else
-static inline void kvm_gmem_init(struct module *module)
+static inline int kvm_gmem_init(struct module *module)
 {
-
+	return 0;
 }
-
+static inline void kvm_gmem_exit(void) {};
 static inline int kvm_gmem_bind(struct kvm *kvm,
 					 struct kvm_memory_slot *slot,
 					 unsigned int fd, loff_t offset)