[PATCH 5/5] KVM: selftests: use allowed NUMA nodes in guest_memfd_test

[Shivank Garg]

guest_memfd_test assumes that nodes 0 and 1 exist and have memory.
is_multi_numa_node_system() only checks that the maximum node ID is
nonzero, which is not enough for sparse or memoryless nodes.

Select the required nodes from MPOL_F_MEMS_ALLOWED instead. Use the full
nodemask width plus one to mbind(), and let test_mbind() run when only
one memory node is available.

The sysfs helpers for finding maxnode are no longer needed.

Signed-off-by: Shivank Garg <shivankg@xxxxxxx>
---
 tools/testing/selftests/kvm/guest_memfd_test.c | 86 +++++++++++++++++---------
 tools/testing/selftests/kvm/include/numaif.h   | 52 ----------------
 2 files changed, 58 insertions(+), 80 deletions(-)

diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index 2233d871a38f..aee80dda6229 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -76,33 +76,53 @@ static void test_mmap_supported(int fd, size_t total_size)
 	kvm_munmap(mem, total_size);
 }
 
+/*
+ * Fill @nids with the first @nr_nids nodes in the allowed mask.
+ * Return false if the mask contains fewer than @nr_nids nodes.
+ */
+static bool get_numa_node_ids(int *nids, int nr_nids)
+{
+	unsigned long nodemask = get_numa_mem_nodes();
+	unsigned long nid;
+	int nr_found = 0;
+
+	for_each_set_bit(nid, &nodemask, BITS_PER_TYPE(nodemask)) {
+		nids[nr_found++] = nid;
+		if (nr_found == nr_nids)
+			return true;
+	}
+
+	return false;
+}
+
 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 = BITS_PER_TYPE(nodemask);
+	unsigned long nodemask, bind_nodemask;
+	unsigned long maxnode = BITS_PER_TYPE(nodemask) + 1;
 	int policy;
 	char *mem;
+	int nid;
 	int ret;
 
-	if (!is_multi_numa_node_system())
+	if (!get_numa_node_ids(&nid, 1))
 		return;
 
+	bind_nodemask = 1UL << nid;
 	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_mbind(mem, page_size * 2, MPOL_INTERLEAVE, &bind_nodemask, maxnode, 0);
 	kvm_get_mempolicy(&policy, &nodemask, maxnode, mem, MPOL_F_ADDR);
-	TEST_ASSERT(policy == MPOL_INTERLEAVE && nodemask == nodemask_0,
+	TEST_ASSERT(policy == MPOL_INTERLEAVE && nodemask == bind_nodemask,
 		    "Wanted MPOL_INTERLEAVE (%u) and nodemask 0x%lx, got %u and 0x%lx",
-		    MPOL_INTERLEAVE, nodemask_0, policy, nodemask);
+		    MPOL_INTERLEAVE, bind_nodemask, policy, nodemask);
 
 	/* Test basic MPOL_BIND policy */
-	kvm_mbind(mem + page_size * 2, page_size * 2, MPOL_BIND, &nodemask_0, maxnode, 0);
+	kvm_mbind(mem + page_size * 2, page_size * 2, MPOL_BIND, &bind_nodemask, maxnode, 0);
 	kvm_get_mempolicy(&policy, &nodemask, maxnode, mem + page_size * 2, MPOL_F_ADDR);
-	TEST_ASSERT(policy == MPOL_BIND && nodemask == nodemask_0,
+	TEST_ASSERT(policy == MPOL_BIND && nodemask == bind_nodemask,
 		    "Wanted MPOL_BIND (%u) and nodemask 0x%lx, got %u and 0x%lx",
-		    MPOL_BIND, nodemask_0, policy, nodemask);
+		    MPOL_BIND, bind_nodemask, policy, nodemask);
 
 	/* Test MPOL_DEFAULT policy */
 	kvm_mbind(mem, total_size, MPOL_DEFAULT, NULL, 0, 0);
@@ -112,7 +132,7 @@ static void test_mbind(int fd, size_t total_size)
 		    MPOL_DEFAULT, policy, nodemask);
 
 	/* Test with invalid policy */
-	ret = mbind(mem, page_size, 999, &nodemask_0, maxnode, 0);
+	ret = mbind(mem, page_size, 999, &bind_nodemask, maxnode, 0);
 	TEST_ASSERT(ret == -1 && errno == EINVAL,
 		    "mbind with invalid policy should fail with EINVAL");
 
@@ -121,17 +141,19 @@ static void test_mbind(int fd, size_t 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;
+	unsigned long bind_nodemasks[2];
+	unsigned long maxnode = BITS_PER_TYPE(bind_nodemasks[0]) + 1;
 	void *pages[4];
+	int nids[2];
 	int status[4];
 	char *mem;
 	int i;
 
-	if (!is_multi_numa_node_system())
+	if (!get_numa_node_ids(nids, ARRAY_SIZE(nids)))
 		return;
 
+	bind_nodemasks[0] = 1UL << nids[0];
+	bind_nodemasks[1] = 1UL << nids[1];
 	mem = kvm_mmap(total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd);
 
 	for (i = 0; i < 4; i++)
@@ -139,34 +161,42 @@ static void test_numa_allocation(int fd, size_t total_size)
 
 	/* Set NUMA policy after allocation */
 	memset(mem, 0xaa, page_size);
-	kvm_mbind(pages[0], page_size, MPOL_BIND, &node0_mask, maxnode, 0);
+	kvm_mbind(pages[0], page_size, MPOL_BIND, &bind_nodemasks[0], 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);
+	kvm_mbind(pages[0], page_size * 2, MPOL_BIND, &bind_nodemasks[1], maxnode, 0);
+	kvm_mbind(pages[2], page_size * 2, MPOL_BIND, &bind_nodemasks[0], 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]);
+	TEST_ASSERT(status[0] == nids[1],
+		    "Expected page 0 on node %d, got it on node %d", nids[1], status[0]);
+	TEST_ASSERT(status[1] == nids[1],
+		    "Expected page 1 on node %d, got it on node %d", nids[1], status[1]);
+	TEST_ASSERT(status[2] == nids[0],
+		    "Expected page 2 on node %d, got it on node %d", nids[0], status[2]);
+	TEST_ASSERT(status[3] == nids[0],
+		    "Expected page 3 on node %d, got it on node %d", nids[0], 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);
+	kvm_mbind(pages[0], page_size * 2, MPOL_BIND, &bind_nodemasks[0], maxnode, 0);
+	kvm_mbind(pages[2], page_size * 2, MPOL_BIND, &bind_nodemasks[1], 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]);
+	TEST_ASSERT(status[0] == nids[0],
+		    "Expected page 0 on node %d, got it on node %d", nids[0], status[0]);
+	TEST_ASSERT(status[1] == nids[0],
+		    "Expected page 1 on node %d, got it on node %d", nids[0], status[1]);
+	TEST_ASSERT(status[2] == nids[1],
+		    "Expected page 2 on node %d, got it on node %d", nids[1], status[2]);
+	TEST_ASSERT(status[3] == nids[1],
+		    "Expected page 3 on node %d, got it on node %d", nids[1], status[3]);
 
 	kvm_munmap(mem, total_size);
 }
diff --git a/tools/testing/selftests/kvm/include/numaif.h b/tools/testing/selftests/kvm/include/numaif.h
index 55124e2330ab..4bbbf314e9d7 100644
--- a/tools/testing/selftests/kvm/include/numaif.h
+++ b/tools/testing/selftests/kvm/include/numaif.h
@@ -4,8 +4,6 @@
 #ifndef SELFTEST_KVM_NUMAIF_H
 #define SELFTEST_KVM_NUMAIF_H
 
-#include <dirent.h>
-
 #include <linux/mempolicy.h>
 
 #include "kvm_syscalls.h"
@@ -30,51 +28,6 @@ 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)
-{
-	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;
-}
-
-static bool is_numa_available(void)
-{
-	/*
-	 * 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);
-}
-
 static inline unsigned long get_numa_mem_nodes(void)
 {
 	unsigned long nodemask = 0;
@@ -87,9 +40,4 @@ static inline unsigned long get_numa_mem_nodes(void)
 	return nodemask;
 }
 
-static inline bool is_multi_numa_node_system(void)
-{
-	return is_numa_available() && get_max_numa_node() >= 1;
-}
-
 #endif /* SELFTEST_KVM_NUMAIF_H */

-- 
2.43.0