7.1.4-rc1 review

@@ -345,8 +345,10 @@ static int scmi_regulator_probe(struct s
 	for_each_child_of_node_scoped(np, child) {
 		ret = process_scmi_regulator_of_node(sdev, ph, child, rinfo);
 		/* abort on any mem issue */
-		if (ret == -ENOMEM)
+		if (ret == -ENOMEM) {
+			of_node_put(np);
 			return ret;
+		}
 	}
 	of_node_put(np);
 	/*

@@ -63,6 +63,7 @@
 static DEFINE_MUTEX(core_lock);
 static DEFINE_IDR(i2c_adapter_idr);
 
+static void i2c_deregister_clients(struct i2c_adapter *adap);
 static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver);
 
 static DEFINE_STATIC_KEY_FALSE(i2c_trace_msg_key);

@@ -1608,6 +1609,7 @@ static int i2c_register_adapter(struct i
 	return 0;
 
 out_reg:
+	i2c_deregister_clients(adap);
 	debugfs_remove_recursive(adap->debugfs);
 	init_completion(&adap->dev_released);
 	device_unregister(&adap->dev);

@@ -1747,29 +1749,10 @@ static int __process_removed_adapter(str
 	return 0;
 }
 
-/**
- * i2c_del_adapter - unregister I2C adapter
- * @adap: the adapter being unregistered
- * Context: can sleep
- *
- * This unregisters an I2C adapter which was previously registered
- * by @i2c_add_adapter or @i2c_add_numbered_adapter.
- */
-void i2c_del_adapter(struct i2c_adapter *adap)
+static void i2c_deregister_clients(struct i2c_adapter *adap)
 {
-	struct i2c_adapter *found;
 	struct i2c_client *client, *next;
 
-	/* First make sure that this adapter was ever added */
-	mutex_lock(&core_lock);
-	found = idr_find(&i2c_adapter_idr, adap->nr);
-	mutex_unlock(&core_lock);
-	if (found != adap) {
-		pr_debug("attempting to delete unregistered adapter [%s]\n", adap->name);
-		return;
-	}
-
-	i2c_acpi_remove_space_handler(adap);
 	/* Tell drivers about this removal */
 	mutex_lock(&core_lock);
 	bus_for_each_drv(&i2c_bus_type, NULL, adap,

@@ -1795,6 +1778,32 @@ void i2c_del_adapter(struct i2c_adapter
 	 * them up properly, so we give them a chance to do that first. */
 	device_for_each_child(&adap->dev, NULL, __unregister_client);
 	device_for_each_child(&adap->dev, NULL, __unregister_dummy);
+}
+
+/**
+ * i2c_del_adapter - unregister I2C adapter
+ * @adap: the adapter being unregistered
+ * Context: can sleep
+ *
+ * This unregisters an I2C adapter which was previously registered
+ * by @i2c_add_adapter or @i2c_add_numbered_adapter.
+ */
+void i2c_del_adapter(struct i2c_adapter *adap)
+{
+	struct i2c_adapter *found;
+
+	/* First make sure that this adapter was ever added */
+	mutex_lock(&core_lock);
+	found = idr_find(&i2c_adapter_idr, adap->nr);
+	mutex_unlock(&core_lock);
+	if (found != adap) {
+		pr_debug("attempting to delete unregistered adapter [%s]\n", adap->name);
+		return;
+	}
+
+	i2c_acpi_remove_space_handler(adap);
+
+	i2c_deregister_clients(adap);
 
 	/* device name is gone after device_unregister */
 	dev_dbg(&adap->dev, "adapter [%s] unregistered\n", adap->name);

@@ -7150,6 +7150,8 @@ static int map_range(struct perf_buffer
 	int err = 0;
 	unsigned long pagenum;
 
+	guard(mutex)(&rb->aux_mutex);
+
 	/*
 	 * We map this as a VM_PFNMAP VMA.
 	 *

@@ -382,9 +382,13 @@ static int luo_session_getfile(struct lu
 
 int luo_session_create(const char *name, struct file **filep)
 {
+	size_t len = strnlen(name, LIVEUPDATE_SESSION_NAME_LENGTH);
 	struct luo_session *session;
 	int err;
 
+	if (len == 0 || len > LIVEUPDATE_SESSION_NAME_LENGTH - 1)
+		return -EINVAL;
+
 	session = luo_session_alloc(name);
 	if (IS_ERR(session))
 		return PTR_ERR(session);

@@ -386,4 +386,46 @@ TEST_F(liveupdate_device, prevent_double
 	ASSERT_EQ(close(session_fd2), 0);
 }
 
+/*
+ * Test Case: Create Session with No Null Termination
+ *
+ * Verifies that filling the entire 64-byte name field with non-null characters
+ * (no '\0' terminator) is rejected by the kernel with EINVAL.
+ */
+TEST_F(liveupdate_device, create_session_no_null_termination)
+{
+	struct liveupdate_ioctl_create_session args = {};
+
+	self->fd1 = open(LIVEUPDATE_DEV, O_RDWR);
+	if (self->fd1 < 0 && errno == ENOENT)
+		SKIP(return, "%s does not exist", LIVEUPDATE_DEV);
+	ASSERT_GE(self->fd1, 0);
+
+	/* Fill entire name field with 'X', no null terminator */
+	args.size = sizeof(args);
+	memset(args.name, 'X', sizeof(args.name));
+
+	EXPECT_LT(ioctl(self->fd1, LIVEUPDATE_IOCTL_CREATE_SESSION, &args), 0);
+	EXPECT_EQ(errno, EINVAL);
+}
+
+/*
+ * Test Case: Create Session with Empty Name
+ *
+ * Verifies that creating a session with an empty string name fails
+ * with EINVAL.
+ */
+TEST_F(liveupdate_device, create_session_empty_name)
+{
+	int session_fd;
+
+	self->fd1 = open(LIVEUPDATE_DEV, O_RDWR);
+	if (self->fd1 < 0 && errno == ENOENT)
+		SKIP(return, "%s does not exist", LIVEUPDATE_DEV);
+	ASSERT_GE(self->fd1, 0);
+
+	session_fd = create_session(self->fd1, "");
+	EXPECT_EQ(session_fd, -EINVAL);
+}
+
 TEST_HARNESS_MAIN

@@ -6,5 +6,6 @@
 #include <linux/compiler.h>	/* For __pure */
 
 bool __pure glob_match(char const *pat, char const *str);
+bool __pure glob_match_len(char const *pat, char const *str, size_t len);
 
 #endif	/* _LINUX_GLOB_H */

@@ -1056,11 +1056,9 @@ static int regex_match_end(char *str, st
 	return 0;
 }
 
-static int regex_match_glob(char *str, struct regex *r, int len __maybe_unused)
+static int regex_match_glob(char *str, struct regex *r, int len)
 {
-	if (glob_match(r->pattern, str))
-		return 1;
-	return 0;
+	return glob_match_len(r->pattern, str, len) ? 1 : 0;
 }
 
 /**

@@ -11,6 +11,9 @@
 MODULE_DESCRIPTION("glob(7) matching");
 MODULE_LICENSE("Dual MIT/GPL");
 
+static bool __pure glob_match_str(char const *pat, char const *str,
+				  char const *str_end);
+
 /**
  * glob_match - Shell-style pattern matching, like !fnmatch(pat, str, 0)
  * @pat: Shell-style pattern to match, e.g. "*.[ch]".

@@ -41,6 +44,29 @@ MODULE_LICENSE("Dual MIT/GPL");
  */
 bool __pure glob_match(char const *pat, char const *str)
 {
+	return glob_match_str(pat, str, NULL);
+}
+EXPORT_SYMBOL(glob_match);
+
+/**
+ * glob_match_len - glob match against a length-bounded string
+ * @pat: Shell-style pattern to match.
+ * @str: String to match.  Need not be NUL-terminated.
+ * @len: Number of bytes of @str that may be read.
+ *
+ * Like glob_match(), but @str is only read up to @len bytes, so it can be
+ * used on buffers that are not NUL-terminated (e.g. trace event fields).
+ * A NUL byte within @len still terminates the string.
+ */
+bool __pure glob_match_len(char const *pat, char const *str, size_t len)
+{
+	return glob_match_str(pat, str, str + len);
+}
+EXPORT_SYMBOL(glob_match_len);
+
+static bool __pure glob_match_str(char const *pat, char const *str,
+				  char const *str_end)
+{
 	/*
 	 * Backtrack to previous * on mismatch and retry starting one
 	 * character later in the string.  Because * matches all characters

@@ -55,9 +81,11 @@ bool __pure glob_match(char const *pat,
 	 * on mismatch, or true after matching the trailing nul bytes.
 	 */
 	for (;;) {
-		unsigned char c = *str++;
+		unsigned char c = (str_end && str >= str_end) ? '\0' : *str;
 		unsigned char d = *pat++;
 
+		str++;
+
 		switch (d) {
 		case '?':	/* Wildcard: anything but nul */
 			if (c == '\0')

@@ -125,4 +153,3 @@ backtrack:
 		}
 	}
 }
-EXPORT_SYMBOL(glob_match);

@@ -62,6 +62,7 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <linux/sctp.h>
+#include <linux/overflow.h>
 
 #include "audit.h"
 

@@ -2080,7 +2081,8 @@ void audit_log_format(struct audit_buffe
 void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf,
 		size_t len)
 {
-	int i, avail, new_len;
+	int avail;
+	size_t i, new_len;
 	unsigned char *ptr;
 	struct sk_buff *skb;
 

@@ -2090,7 +2092,12 @@ void audit_log_n_hex(struct audit_buffer
 	BUG_ON(!ab->skb);
 	skb = ab->skb;
 	avail = skb_tailroom(skb);
-	new_len = len<<1;
+
+	if (check_shl_overflow(len, 1, &new_len)) {
+		audit_log_format(ab, "?");
+		return;
+	}
+
 	if (new_len >= avail) {
 		/* Round the buffer request up to the next multiple */
 		new_len = AUDIT_BUFSIZ*(((new_len-avail)/AUDIT_BUFSIZ) + 1);

@@ -3344,6 +3344,8 @@ static int nfs_open_permission_mask(int
 			mask |= MAY_READ;
 		if ((openflags & O_ACCMODE) != O_RDONLY)
 			mask |= MAY_WRITE;
+		if (openflags & O_TRUNC)
+			mask |= MAY_WRITE;
 	}
 
 	return mask;

@@ -243,12 +243,20 @@ static __always_inline void res_spin_unl
 	({                                        \
 		int __ret;                        \
 		local_irq_save(flags);            \
-		__ret = raw_res_spin_lock(lock);  \
-		if (__ret)                        \
+		preempt_disable();                \
+		__ret = res_spin_lock(lock);      \
+		if (__ret) {                      \
 			local_irq_restore(flags); \
+			preempt_enable();         \
+		}                                 \
 		__ret;                            \
 	})
 
-#define raw_res_spin_unlock_irqrestore(lock, flags) ({ raw_res_spin_unlock(lock); local_irq_restore(flags); })
+#define raw_res_spin_unlock_irqrestore(lock, flags) \
+	({                                          \
+		res_spin_unlock(lock);              \
+		local_irq_restore(flags);           \
+		preempt_enable();                   \
+	})
 
 #endif /* __ASM_GENERIC_RQSPINLOCK_H */

@@ -307,6 +307,8 @@ int module_decompress(struct load_info *
 	 */
 	n_pages = DIV_ROUND_UP(size, PAGE_SIZE) * 2;
 	error = module_extend_max_pages(info, n_pages);
+	if (error)
+		return error;
 
 	data_size = MODULE_DECOMPRESS_FN(info, buf, size);
 	if (data_size < 0) {

index dfdea0842149..763a3f1b7be0 100644
@@ -765,16 +765,22 @@ static void k_fn(struct vc_data *vc, unsigned char value, char up_flag)
 /*
  * Compute xterm-style modifier parameter for CSI sequences.
  * Returns 1 + (shift ? 1 : 0) + (alt ? 2 : 0) + (ctrl ? 4 : 0)
+ *
+ * Only the canonical modifier weights are counted. The left/right variants
+ * (KG_SHIFTL, KG_SHIFTR, KG_CTRLL, KG_CTRLR) and KG_ALTGR are commonly
+ * repurposed as keymap layout-group or level selectors rather than as plain
+ * modifiers (for instance XKB-derived keymaps select the layout group with
+ * KG_SHIFTL/KG_SHIFTR), so counting them would encode a spurious modifier.
  */
 static int csi_modifier_param(void)
 {
 	int mod = 1;
 
-	if (shift_state & (BIT(KG_SHIFT) | BIT(KG_SHIFTL) | BIT(KG_SHIFTR)))
+	if (shift_state & BIT(KG_SHIFT))
 		mod += 1;
-	if (shift_state & (BIT(KG_ALT) | BIT(KG_ALTGR)))
+	if (shift_state & BIT(KG_ALT))
 		mod += 2;
-	if (shift_state & (BIT(KG_CTRL) | BIT(KG_CTRLL) | BIT(KG_CTRLR)))
+	if (shift_state & BIT(KG_CTRL))
 		mod += 4;
 	return mod;
 }

@@ -470,32 +470,70 @@ static void exfat_free_benign_secondary_
 	exfat_free_cluster(inode, &dir);
 }
 
+/*
+ * exfat_init_ext_entry - initialize extension entries in a directory entry set
+ * @es:          target entry set
+ * @num_entries: number of entries excluding benign secondary entries
+ * @p_uniname:   filename to store
+ * @old_es:      optional source entry set with benign secondary entries, or NULL
+ * @num_extra:   number of benign secondary entries to copy from @old_es
+ *
+ * Set up the file, stream extension, and filename entries in @es, optionally
+ * preserving @num_extra benign secondary entries from @old_es.  @es and @old_es
+ * may refer to the same entry set; excess entries are marked as deleted.
+ */
 void exfat_init_ext_entry(struct exfat_entry_set_cache *es, int num_entries,
-		struct exfat_uni_name *p_uniname)
+		struct exfat_uni_name *p_uniname,
+		struct exfat_entry_set_cache *old_es, int num_extra)
 {
-	int i;
+	int i, src_start = 0, old_num;
 	unsigned short *uniname = p_uniname->name;
 	struct exfat_dentry *ep;
 
-	es->num_entries = num_entries;
+	if (WARN_ON(num_extra < 0 || (num_extra && (!old_es ||
+		    old_es->num_entries < ES_IDX_FIRST_FILENAME + num_extra))))
+		num_extra = 0;
+
+	/*
+	 * Save old entry count and source position before modifying
+	 * es->num_entries, since old_es and es may point to the same
+	 * entry set.
+	 */
+	old_num = es->num_entries;
+	if (old_es && num_extra > 0)
+		src_start = old_es->num_entries - num_extra;
+
+	es->num_entries = num_entries + num_extra;
 	ep = exfat_get_dentry_cached(es, ES_IDX_FILE);
-	ep->dentry.file.num_ext = (unsigned char)(num_entries - 1);
+	ep->dentry.file.num_ext = (unsigned char)(num_entries - 1 + num_extra);
 
 	ep = exfat_get_dentry_cached(es, ES_IDX_STREAM);
 	ep->dentry.stream.name_len = p_uniname->name_len;
 	ep->dentry.stream.name_hash = cpu_to_le16(p_uniname->name_hash);
 
+	if (old_es && num_extra > 0) {
+		for (i = 0; i < num_extra; i++)
+			*exfat_get_dentry_cached(es, num_entries + i) =
+				*exfat_get_dentry_cached(old_es, src_start + i);
+	}
+
 	for (i = ES_IDX_FIRST_FILENAME; i < num_entries; i++) {
 		ep = exfat_get_dentry_cached(es, i);
 		exfat_init_name_entry(ep, uniname);
 		uniname += EXFAT_FILE_NAME_LEN;
 	}
 
+	/* Mark excess old entries as deleted (in-place shrink) */
+	for (i = num_entries + num_extra; i < old_num; i++) {
+		ep = exfat_get_dentry_cached(es, i);
+		exfat_set_entry_type(ep, TYPE_DELETED);
+	}
+
 	exfat_update_dir_chksum(es);
 }
 
 void exfat_remove_entries(struct inode *inode, struct exfat_entry_set_cache *es,
-		int order)
+		int order, bool free_benign)
 {
 	int i;
 	struct exfat_dentry *ep;

@@ -503,7 +541,7 @@ void exfat_remove_entries(struct inode *
 	for (i = order; i < es->num_entries; i++) {
 		ep = exfat_get_dentry_cached(es, i);
 
-		if (exfat_get_entry_type(ep) & TYPE_BENIGN_SEC)
+		if (free_benign && (exfat_get_entry_type(ep) & TYPE_BENIGN_SEC))
 			exfat_free_benign_secondary_clusters(inode, ep);
 
 		exfat_set_entry_type(ep, TYPE_DELETED);

@@ -524,9 +524,10 @@ void exfat_init_dir_entry(struct exfat_e
 		unsigned int type, unsigned int start_clu,
 		unsigned long long size, struct timespec64 *ts);
 void exfat_init_ext_entry(struct exfat_entry_set_cache *es, int num_entries,
-		struct exfat_uni_name *p_uniname);
+		struct exfat_uni_name *p_uniname,
+		struct exfat_entry_set_cache *old_es, int num_extra);
 void exfat_remove_entries(struct inode *inode, struct exfat_entry_set_cache *es,
-		int order);
+		int order, bool free_benign);
 void exfat_update_dir_chksum(struct exfat_entry_set_cache *es);
 int exfat_calc_num_entries(struct exfat_uni_name *p_uniname);
 int exfat_find_dir_entry(struct super_block *sb, struct exfat_inode_info *ei,

184 lines not on this page · raw message

@@ -1067,6 +1067,7 @@ rewind:
 
 			if (entry_type == TYPE_EXTEND) {
 				unsigned short entry_uniname[16], unichar;
+				unsigned int offset;
 
 				if (step != DIRENT_STEP_NAME ||
 				    name_len >= MAX_NAME_LENGTH) {

@@ -1075,13 +1076,15 @@ rewind:
 					continue;
 				}
 
-				if (++order == 2)
-					uniname = p_uniname->name;
-				else
-					uniname += EXFAT_FILE_NAME_LEN;
-
+				offset = (++order - 2) * EXFAT_FILE_NAME_LEN;
 				len = exfat_extract_uni_name(ep, entry_uniname);
 				brelse(bh);
+				if (offset > MAX_NAME_LENGTH ||
+				    len > MAX_NAME_LENGTH - offset) {
+					step = DIRENT_STEP_FILE;
+					continue;
+				}
+				uniname = p_uniname->name + offset;
 				name_len += len;
 
 				unichar = *(uniname+len);

@@ -357,7 +357,7 @@ static int ntb_epf_init_isr(struct ntb_e
 				  0, "ntb_epf", ndev);
 		if (ret) {
 			dev_err(dev, "Failed to request irq\n");
-			goto err_request_irq;
+			goto err_free_irq;
 		}
 	}
 

@@ -367,16 +367,14 @@ static int ntb_epf_init_isr(struct ntb_e
 				   argument | irq);
 	if (ret) {
 		dev_err(dev, "Failed to configure doorbell\n");
-		goto err_configure_db;
+		goto err_free_irq;
 	}
 
 	return 0;
 
-err_configure_db:
-	for (i = 0; i < ndev->db_count + 1; i++)
+err_free_irq:
+	while (i--)
 		free_irq(pci_irq_vector(pdev, i), ndev);
-
-err_request_irq:
 	pci_free_irq_vectors(pdev);
 
 	return ret;

@@ -93,6 +93,16 @@
  */
 #define vmemmap		((struct page *)VMEMMAP_START - vmemmap_start_pfn)
 
+/* Needed to limit get_free_mem_region() */
+#if defined(CONFIG_FLATMEM)
+#define DIRECT_MAP_PHYSMEM_END (phys_ram_base + KERN_VIRT_SIZE - 1)
+#elif defined(CONFIG_SPARSEMEM_VMEMMAP)
+#define DIRECT_MAP_PHYSMEM_END \
+	((vmemmap_start_pfn + VMEMMAP_SIZE / sizeof(struct page)) * PAGE_SIZE - 1)
+#elif defined(CONFIG_SPARSEMEM)
+/* DIRECT_MAP_PHYSMEM_END is not limited by VA space assignment in this case */
+#endif
+
 #define PCI_IO_SIZE      SZ_16M
 #define PCI_IO_END       VMEMMAP_START
 #define PCI_IO_START     (PCI_IO_END - PCI_IO_SIZE)

index 213504915737..38996c4baa40 100644
@@ -1253,8 +1253,8 @@ static int dmirror_migrate_to_device(struct dmirror *dmirror,
 	mmap_read_unlock(mm);
 	mmput(mm);
 free_mem:
-	kfree(src_pfns);
-	kfree(dst_pfns);
+	kvfree(src_pfns);
+	kvfree(dst_pfns);
 	return ret;
 }
 

@@ -504,7 +504,7 @@ unsigned long do_mmap(struct file *file,
 			break;
 		case MAP_DROPPABLE:
 			if (VM_DROPPABLE == VM_NONE)
-				return -ENOTSUPP;
+				return -EOPNOTSUPP;
 			/*
 			 * A locked or stack area makes no sense to be droppable.
 			 *

@@ -17,10 +17,10 @@
 
 int main(int argc, char *argv[])
 {
-	size_t alloc_size = 134217728;
-	size_t page_size = getpagesize();
+	const size_t alloc_size = 2 * 1024 * 1024;
+	int retry_count = 10;
+	bool dropped;
 	void *alloc;
-	pid_t child;
 
 	ksft_print_header();
 	ksft_set_plan(1);

@@ -28,26 +28,32 @@ int main(int argc, char *argv[])
 	alloc = mmap(0, alloc_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_DROPPABLE, -1, 0);
 	assert(alloc != MAP_FAILED);
 	memset(alloc, 'A', alloc_size);
-	for (size_t i = 0; i < alloc_size; i += page_size)
-		assert(*(uint8_t *)(alloc + i));
 
-	child = fork();
-	assert(child >= 0);
-	if (!child) {
-		for (;;)
-			*(char *)malloc(page_size) = 'B';
-	}
-
-	for (bool done = false; !done;) {
-		for (size_t i = 0; i < alloc_size; i += page_size) {
-			if (!*(uint8_t *)(alloc + i)) {
-				done = true;
-				break;
+	while (retry_count--) {
+		if (madvise(alloc, alloc_size, MADV_PAGEOUT)) {
+			if (errno == EINVAL) {
+				ksft_test_result_skip("madvise(MADV_PAGEOUT) not supported\n");
+				exit(KSFT_SKIP);
 			}
+			ksft_test_result_fail("madvise(MADV_PAGEOUT) error: %s\n", strerror(errno));
+			exit(KSFT_FAIL);
 		}
+
+		dropped = memchr(alloc, 'A', alloc_size) == NULL;
+
+		/*
+		 * Speculative reference can temporarily prevent some
+		 * pages from getting dropped. So sleep and retry.
+		 *
+		 * If a page is not droppable for 10s, something
+		 * is seriously messed up and we want to fail.
+		 */
+		if (dropped)
+			break;
+		sleep(1);
 	}
-	kill(child, SIGTERM);
 
-	ksft_test_result_pass("MAP_DROPPABLE: PASS\n");
-	exit(KSFT_PASS);
+	ksft_test_result(dropped, "madvise(MADV_PAGEOUT) behavior\n");
+
+	ksft_finished();
 }

@@ -120,14 +120,18 @@ struct page_ext_iter {
  * page_ext_iter_begin() - Prepare for iterating through page extensions.
  * @iter: page extension iterator.
  * @pfn: PFN of the page we're interested in.
+ * @count: maximum number of page extensions to return.
  *
  * Must be called with RCU read lock taken.
  *
  * Return: NULL if no page_ext exists for this page.
  */
 static inline struct page_ext *page_ext_iter_begin(struct page_ext_iter *iter,
-						unsigned long pfn)
+		unsigned long pfn, unsigned long count)
 {
+	if (!count)
+		return NULL;
+
 	iter->index = 0;
 	iter->start_pfn = pfn;
 	iter->page_ext = page_ext_lookup(pfn);

@@ -138,19 +142,22 @@ static inline struct page_ext *page_ext_
 /**
  * page_ext_iter_next() - Get next page extension
  * @iter: page extension iterator.
+ * @count: maximum number of page extensions to return.
  *
  * Must be called with RCU read lock taken.
  *
  * Return: NULL if no next page_ext exists.
  */
-static inline struct page_ext *page_ext_iter_next(struct page_ext_iter *iter)
+static inline struct page_ext *page_ext_iter_next(struct page_ext_iter *iter,
+		unsigned long count)
 {
 	unsigned long pfn;
 
 	if (WARN_ON_ONCE(!iter->page_ext))
 		return NULL;
 
-	iter->index++;
+	if (++iter->index >= count)
+		return NULL;
 	pfn = iter->start_pfn + iter->index;
 
 	if (page_ext_iter_next_fast_possible(pfn))

@@ -183,9 +190,9 @@ static inline struct page_ext *page_ext_
  * IMPORTANT: must be called with RCU read lock taken.
  */
 #define for_each_page_ext(__page, __pgcount, __page_ext, __iter) \
-	for (__page_ext = page_ext_iter_begin(&__iter, page_to_pfn(__page));\
-		__page_ext && __iter.index < __pgcount;          \
-		__page_ext = page_ext_iter_next(&__iter))
+	for (__page_ext = page_ext_iter_begin(&__iter, page_to_pfn(__page), __pgcount); \
+		__page_ext; \
+		__page_ext = page_ext_iter_next(&__iter, __pgcount))
 
 #else /* !CONFIG_PAGE_EXTENSION */
 struct page_ext;

@@ -2438,6 +2438,11 @@ static inline struct mnt_idmap *file_mnt
 	return mnt_idmap(file->f_path.mnt);
 }
 
+static inline bool file_owner_or_capable(const struct file *file)
+{
+	return inode_owner_or_capable(file_mnt_idmap(file), file_inode(file));
+}
+
 /**
  * is_idmapped_mnt - check whether a mount is mapped
  * @mnt: the mount to check

@@ -4671,7 +4671,7 @@ static inline bool can_do_cachestat(stru
 {
 	if (f->f_mode & FMODE_WRITE)
 		return true;
-	if (inode_owner_or_capable(file_mnt_idmap(f), file_inode(f)))
+	if (file_owner_or_capable(f))
 		return true;
 	return file_permission(f, MAY_WRITE) == 0;
 }

@@ -336,8 +336,7 @@ static inline bool can_do_file_pageout(s
 	 * otherwise we'd be including shared non-exclusive mappings, which
 	 * opens a side channel.
 	 */
-	return inode_owner_or_capable(&nop_mnt_idmap,
-				      file_inode(vma->vm_file)) ||
+	return file_owner_or_capable(vma->vm_file) ||
 	       file_permission(vma->vm_file, MAY_WRITE) == 0;
 }
 

@@ -227,8 +227,7 @@ static inline bool can_do_mincore(struct
 	 * for writing; otherwise we'd be including shared non-exclusive
 	 * mappings, which opens a side channel.
 	 */
-	return inode_owner_or_capable(&nop_mnt_idmap,
-				      file_inode(vma->vm_file)) ||
+	return file_owner_or_capable(vma->vm_file) ||
 	       file_permission(vma->vm_file, MAY_WRITE) == 0;
 }
 

@@ -1366,7 +1366,7 @@ void *thread_proc(void *mem)
 			ksft_exit_fail_msg("pthread_barrier_wait\n");
 
 		for (i = 0; i < access_per_thread; ++i)
-			__atomic_add_fetch(m + i * (0x1000 / sizeof(*m)), 1, __ATOMIC_SEQ_CST);
+			__atomic_add_fetch(m + i * (page_size / sizeof(*m)), 1, __ATOMIC_SEQ_CST);
 
 		ret = pthread_barrier_wait(&end_barrier);
 		if (ret && ret != PTHREAD_BARRIER_SERIAL_THREAD)

@@ -1401,15 +1401,15 @@ static void transact_test(int page_size)
 	if (pthread_barrier_init(&end_barrier, NULL, nthreads + 1))
 		ksft_exit_fail_msg("pthread_barrier_init\n");
 
-	mem = mmap(NULL, 0x1000 * nthreads * pages_per_thread, PROT_READ | PROT_WRITE,
+	mem = mmap(NULL, page_size * nthreads * pages_per_thread, PROT_READ | PROT_WRITE,
 		   MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
 	if (mem == MAP_FAILED)
 		ksft_exit_fail_msg("Error mmap %s.\n", strerror(errno));
 
-	wp_init(mem, 0x1000 * nthreads * pages_per_thread);
-	wp_addr_range(mem, 0x1000 * nthreads * pages_per_thread);
+	wp_init(mem, page_size * nthreads * pages_per_thread);
+	wp_addr_range(mem, page_size * nthreads * pages_per_thread);
 
-	memset(mem, 0, 0x1000 * nthreads * pages_per_thread);
+	memset(mem, 0, page_size * nthreads * pages_per_thread);
 
 	count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size);
 	ksft_test_result(count > 0, "%s count %u\n", __func__, count);

@@ -1418,7 +1418,7 @@ static void transact_test(int page_size)
 
 	finish = 0;
 	for (i = 0; i < nthreads; ++i)
-		pthread_create(&th, NULL, thread_proc, mem + 0x1000 * i * pages_per_thread);
+		pthread_create(&th, NULL, thread_proc, mem + page_size * i * pages_per_thread);
 
 	extra_pages = 0;
 	for (i = 0; i < iter_count; ++i) {

@@ -230,29 +230,26 @@ nvkm_vmm_unref_sptes(struct nvkm_vmm_ite
 		 * covered by a number of LPTEs, the LPTEs once again take
 		 * control over their address range.
 		 *
-		 * Determine how many LPTEs need to transition state.
+		 * Transition each LPTE individually as each may have a
+		 * different target state (sparse, invalid, or valid).
 		 */
-		pgt->pte[ptei].s.spte_valid = false;
-		for (ptes = 1, ptei++; ptei < lpti; ptes++, ptei++) {
+		for (ptei++; ptei < lpti; ptei++) {
 			if (pgt->pte[ptei].s.sptes)
 				break;
-			pgt->pte[ptei].s.spte_valid = false;
 		}
 
-		if (pgt->pte[pteb].s.sparse) {
-			TRA(it, "LPTE %05x: U -> S %d PTEs", pteb, ptes);
-			pair->func->sparse(vmm, pgt->pt[0], pteb, ptes);
-		} else if (!pgt->pte[pteb].s.lpte_valid) {
-			if (pair->func->invalid) {
-				/* If the MMU supports it, restore the LPTE to the
-				 * INVALID state to tell the MMU there is no point
-				 * trying to fetch the corresponding SPTEs.
-				 */
-				TRA(it, "LPTE %05x: U -> I %d PTEs", pteb, ptes);
-				pair->func->invalid(vmm, pgt->pt[0], pteb, ptes);
+		while (pteb < ptei) {
+			pgt->pte[pteb].s.spte_valid = false;
+			if (pgt->pte[pteb].s.sparse) {
+				TRA(it, "LPTE %05x: U -> S", pteb);
+				pair->func->sparse(vmm, pgt->pt[0], pteb, 1);
+			} else if (!pgt->pte[pteb].s.lpte_valid) {
+				if (pair->func->invalid) {
+					TRA(it, "LPTE %05x: U -> I", pteb);
+					pair->func->invalid(vmm, pgt->pt[0], pteb, 1);
+				}
 			}
-		} else {
-			TRA(it, "LPTE %05x: V %d PTEs", pteb, ptes);
+			pteb++;
 		}
 	}
 }

@@ -14,6 +14,8 @@
 
 #ifdef CONFIG_BPF_LSM
 
+extern bool bpf_lsm_initialized __ro_after_init;
+
 #define LSM_HOOK(RET, DEFAULT, NAME, ...) \
 	RET bpf_lsm_##NAME(__VA_ARGS__);
 #include <linux/lsm_hook_defs.h>

@@ -55,6 +57,8 @@ bool bpf_lsm_has_d_inode_locked(const st
 
 #else /* !CONFIG_BPF_LSM */
 
+#define bpf_lsm_initialized false
+
 static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id)
 {
 	return false;

@@ -178,6 +178,15 @@ static int notsupp_get_next_key(struct b
 
 static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr)
 {
+	/*
+	 * Do not allow allocation of BPF_MAP_TYPE_INODE_STORAGE if the BPF LSM
+	 * was not initialized by the LSM framework at boot. Without proper
+	 * initialization, the BPF inode security blob offset remains unprepared,
+	 * causing bpf_inode() to calculate an invalid memory offset and corrupt
+	 * inode->i_security.
+	 */
+	if (!bpf_lsm_initialized)
+		return ERR_PTR(-EOPNOTSUPP);
 	return bpf_local_storage_map_alloc(attr, &inode_cache);
 }
 

@@ -7,6 +7,8 @@
 #include <linux/bpf_lsm.h>
 #include <uapi/linux/lsm.h>
 
+bool bpf_lsm_initialized __ro_after_init;
+
 static struct security_hook_list bpf_lsm_hooks[] __ro_after_init = {
 	#define LSM_HOOK(RET, DEFAULT, NAME, ...) \
 	LSM_HOOK_INIT(NAME, bpf_lsm_##NAME),

@@ -24,6 +26,7 @@ static int __init bpf_lsm_init(void)
 {
 	security_add_hooks(bpf_lsm_hooks, ARRAY_SIZE(bpf_lsm_hooks),
 			   &bpf_lsmid);
+	bpf_lsm_initialized = true;
 	pr_info("LSM support for eBPF active\n");
 	return 0;
 }

@@ -1254,18 +1254,29 @@ void intel_iommu_disable_iopf(struct dev
 static inline int iopf_for_domain_set(struct iommu_domain *domain,
 				      struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+
 	if (!domain || !domain->iopf_handler)
 		return 0;
 
+	/* SVA with non-IOMMU/PRI IOPF handling is allowed. */
+	if (domain->type == IOMMU_DOMAIN_SVA && !info->pri_supported)
+		return 0;
+
 	return intel_iommu_enable_iopf(dev);
 }
 
 static inline void iopf_for_domain_remove(struct iommu_domain *domain,
 					  struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+
 	if (!domain || !domain->iopf_handler)
 		return;
 
+	if (domain->type == IOMMU_DOMAIN_SVA && !info->pri_supported)
+		return;
+
 	intel_iommu_disable_iopf(dev);
 }
 

@@ -164,12 +164,9 @@ static int intel_svm_set_dev_pasid(struc
 	if (IS_ERR(dev_pasid))
 		return PTR_ERR(dev_pasid);
 
-	/* SVA with non-IOMMU/PRI IOPF handling is allowed. */
-	if (info->pri_supported) {
-		ret = iopf_for_domain_replace(domain, old, dev);
-		if (ret)
-			goto out_remove_dev_pasid;
-	}
+	ret = iopf_for_domain_replace(domain, old, dev);
+	if (ret)
+		goto out_remove_dev_pasid;
 
 	/* Setup the pasid table: */
 	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;

@@ -184,8 +181,7 @@ static int intel_svm_set_dev_pasid(struc
 
 	return 0;
 out_unwind_iopf:
-	if (info->pri_supported)
-		iopf_for_domain_replace(old, domain, dev);
+	iopf_for_domain_replace(old, domain, dev);
 out_remove_dev_pasid:
 	domain_remove_dev_pasid(domain, dev, pasid);
 	return ret;

@@ -1774,7 +1774,8 @@ void amd_iommu_domain_flush_pages(struct
 {
 	lockdep_assert_held(&domain->lock);
 
-	if (likely(!amd_iommu_np_cache)) {
+	if (likely(!amd_iommu_np_cache) ||
+		size >= (1ULL<<52)) {
 		__domain_flush_pages(domain, address, size);
 
 		/* Wait until IOMMU TLB and all device IOTLB flushes are complete */

@@ -321,7 +321,7 @@ static ssize_t iommufd_veventq_fops_read
 
 		/* If being a normal vEVENT, validate against the full size */
 		if (!vevent_for_lost_events_header(cur) &&
-		    sizeof(hdr) + cur->data_len > count - done) {
+		    sizeof(*hdr) + cur->data_len > count - done) {
 			iommufd_veventq_deliver_restore(veventq, cur);
 			break;
 		}

@@ -602,7 +602,7 @@ struct iommufd_vevent {
 	struct iommufd_vevent_header header;
 	struct list_head node; /* for iommufd_eventq::deliver */
 	ssize_t data_len;
-	u64 event_data[] __counted_by(data_len);
+	u8 event_data[] __counted_by(data_len);
 };
 
 #define vevent_for_lost_events_header(vevent) \

@@ -149,15 +149,18 @@ int iommufd_viommu_report_event(struct i
 		goto out_unlock_veventqs;
 	}
 
-	spin_lock(&veventq->common.lock);
-	if (veventq->num_events == veventq->depth) {
+	/* Pre-allocate to avoid GFP_ATOMIC; use GFP_NOWAIT to avoid sleeping */
+	vevent = kzalloc_flex(*vevent, event_data, data_len, GFP_NOWAIT);
+	if (!vevent) {
+		spin_lock(&veventq->common.lock);
 		vevent = &veventq->lost_events_header;
+		rc = -ENOMEM;
 		goto out_set_header;
 	}
 
-	vevent = kzalloc_flex(*vevent, event_data, data_len, GFP_ATOMIC);
-	if (!vevent) {
-		rc = -ENOMEM;
+	spin_lock(&veventq->common.lock);
+	if (veventq->num_events == veventq->depth) {
+		kfree(vevent);
 		vevent = &veventq->lost_events_header;
 		goto out_set_header;
 	}

@@ -473,6 +473,9 @@ int iommufd_fault_iopf_handler(struct io
 static const struct file_operations iommufd_veventq_fops =
 	INIT_EVENTQ_FOPS(iommufd_veventq_fops_read, NULL);
 
+/* An arbitrary upper bound for veventq_depth that fits all existing HWs */
+#define VEVENTQ_MAX_DEPTH (1U << 19)
+
 int iommufd_veventq_alloc(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_veventq_alloc *cmd = ucmd->cmd;

@@ -484,7 +487,7 @@ int iommufd_veventq_alloc(struct iommufd
 	if (cmd->flags || cmd->__reserved ||
 	    cmd->type == IOMMU_VEVENTQ_TYPE_DEFAULT)
 		return -EOPNOTSUPP;
-	if (!cmd->veventq_depth)
+	if (!cmd->veventq_depth || cmd->veventq_depth > VEVENTQ_MAX_DEPTH)
 		return -EINVAL;
 
 	viommu = iommufd_get_viommu(ucmd, cmd->viommu_id);

@@ -336,6 +336,7 @@ static ssize_t iommufd_veventq_fops_read
 		if (cur->data_len &&
 		    copy_to_user(buf + done, cur->event_data, cur->data_len)) {
 			iommufd_veventq_deliver_restore(veventq, cur);
+			done -= sizeof(*hdr);
 			rc = -EFAULT;
 			break;
 		}

@@ -310,6 +310,9 @@ static ssize_t iommufd_veventq_fops_read
 
 	if (*ppos)
 		return -ESPIPE;
+	/* Minimum read count is a vEVENT header */
+	if (count < sizeof(*hdr))
+		return -EINVAL;
 
 	while ((cur = iommufd_veventq_deliver_fetch(veventq))) {
 		/* Validate the remaining bytes against the header size */

@@ -323,6 +326,9 @@ static ssize_t iommufd_veventq_fops_read
 		if (!vevent_for_lost_events_header(cur) &&
 		    sizeof(*hdr) + cur->data_len > count - done) {
 			iommufd_veventq_deliver_restore(veventq, cur);
+			/* Read count doesn't fit a single normal vEVENT */
+			if (done == 0)
+				rc = -EINVAL;
 			break;
 		}
 

@@ -264,8 +264,10 @@ iommufd_veventq_deliver_fetch(struct iom
 		/* Make a copy of the lost_events_header for copy_to_user */
 		if (next == &veventq->lost_events_header) {
 			vevent = kzalloc_obj(*vevent, GFP_ATOMIC);
-			if (!vevent)
+			if (!vevent) {
+				vevent = ERR_PTR(-ENOMEM);
 				goto out_unlock;
+			}
 		}
 		list_del(&next->node);
 		if (vevent)

@@ -315,6 +317,12 @@ static ssize_t iommufd_veventq_fops_read
 		return -EINVAL;
 
 	while ((cur = iommufd_veventq_deliver_fetch(veventq))) {
+		if (IS_ERR(cur)) {
+			if (done == 0)
+				rc = PTR_ERR(cur);
+			break;
+		}
+
 		/* Validate the remaining bytes against the header size */
 		if (done >= count || sizeof(*hdr) > count - done) {
 			iommufd_veventq_deliver_restore(veventq, cur);

@@ -142,6 +142,9 @@ static ssize_t iommufd_fault_fops_read(s
 		if (done >= count ||
 		    group->fault_count * fault_size > count - done) {
 			iommufd_fault_deliver_restore(fault, group);
+			/* Read count doesn't fit the first fault group */
+			if (done == 0)
+				rc = -EINVAL;
 			break;
 		}
 

@@ -168,6 +168,8 @@ static ssize_t iommufd_fault_fops_read(s
 			}
 			done += fault_size;
 		}
+		if (rc)
+			break;
 	}
 	mutex_unlock(&fault->mutex);
 

@@ -139,6 +139,8 @@ static ssize_t iommufd_fault_fops_read(s
 
 	mutex_lock(&fault->mutex);
 	while ((group = iommufd_fault_deliver_fetch(fault))) {
+		size_t group_done = done;
+
 		if (done >= count ||
 		    group->fault_count * fault_size > count - done) {
 			iommufd_fault_deliver_restore(fault, group);

@@ -160,16 +162,17 @@ static ssize_t iommufd_fault_fops_read(s
 			iommufd_compose_fault_message(&iopf->fault,
 						      &data, idev,
 						      group->cookie);
-			if (copy_to_user(buf + done, &data, fault_size)) {
+			if (copy_to_user(buf + group_done, &data, fault_size)) {
 				xa_erase(&fault->response, group->cookie);
 				iommufd_fault_deliver_restore(fault, group);
 				rc = -EFAULT;
 				break;
 			}
-			done += fault_size;
+			group_done += fault_size;
 		}
 		if (rc)
 			break;
+		done = group_done;
 	}
 	mutex_unlock(&fault->mutex);
 

@@ -489,6 +489,9 @@ int iommufd_hwpt_get_dirty_bitmap(struct
 	return rc;
 }
 
+/* An arbitrary entry_num cap, far above any realistic invalidation batch */
+#define IOMMU_HWPT_INVALIDATE_ENTRY_NUM_MAX (1U << 19)
+
 int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_hwpt_invalidate *cmd = ucmd->cmd;

@@ -507,7 +510,13 @@ int iommufd_hwpt_invalidate(struct iommu
 		goto out;
 	}
 
-	if (cmd->entry_num && (!cmd->data_uptr || !cmd->entry_len)) {
+	/*
+	 * Bound entry_num and entry_len so a single call cannot pin the CPU;
+	 * entry_len also caps the copy_struct_from_user() trailing-zero scan.
+	 */
+	if (cmd->entry_num &&
+	    (!cmd->data_uptr || !cmd->entry_len || cmd->entry_len > PAGE_SIZE ||
+	     cmd->entry_num > IOMMU_HWPT_INVALIDATE_ENTRY_NUM_MAX)) {
 		rc = -EINVAL;
 		goto out;
 	}

@@ -84,10 +84,6 @@ struct audit_fsnotify_mark *audit_alloc_
 	dentry = kern_path_parent(pathname, &path);
 	if (IS_ERR(dentry))
 		return ERR_CAST(dentry); /* returning an error */
-	if (d_really_is_negative(dentry)) {
-		audit_mark = ERR_PTR(-ENOENT);
-		goto out;
-	}
 
 	audit_mark = kzalloc_obj(*audit_mark);
 	if (unlikely(!audit_mark)) {

@@ -198,6 +198,7 @@ static int current_check_access_socket(s
 		return 0;
 
 	audit_net.family = address->sa_family;
+	audit_net.sk = sock->sk;
 	landlock_log_denial(subject,
 			    &(struct landlock_request){
 				    .type = LANDLOCK_REQUEST_NET_ACCESS,

66 lines not on this page · raw message

@@ -494,10 +494,9 @@ static int audit_init_filter_exe(struct
 static int audit_cleanup(int audit_fd, struct audit_filter *filter)
 {
 	struct audit_filter new_filter;
+	int err = 0;
 
 	if (audit_fd < 0 || !filter) {
-		int err;
-
 		/*
 		 * Simulates audit_init_with_exe_filter() when called from
 		 * FIXTURE_TEARDOWN_PARENT().

@@ -508,23 +507,19 @@ static int audit_cleanup(int audit_fd, s
 
 		filter = &new_filter;
 		err = audit_init_filter_exe(filter, NULL);
-		if (err) {
-			close(audit_fd);
-			return err;
-		}
+		if (err)
+			goto err_close;
 	}
 
 	/* Filters might not be in place. */
 	audit_filter_exe(audit_fd, filter, AUDIT_DEL_RULE);
 	audit_filter_drop(audit_fd, AUDIT_DEL_RULE);
 
-	/*
-	 * Because audit_cleanup() might not be called by the test auditd
-	 * process, it might not be possible to explicitly set it.  Anyway,
-	 * AUDIT_STATUS_ENABLED will implicitly be set to 0 when the auditd
-	 * process will exit.
-	 */
-	return close(audit_fd);
+	err = audit_set_status(audit_fd, AUDIT_STATUS_ENABLED, 0);
+
+err_close:
+	close(audit_fd);
+	return err;
 }
 
 static int audit_init_with_exe_filter(struct audit_filter *filter)

@@ -849,10 +849,8 @@ FIXTURE_SETUP(audit_exec)
 FIXTURE_TEARDOWN(audit_exec)
 {
 	set_cap(_metadata, CAP_AUDIT_CONTROL);
-	EXPECT_EQ(0, audit_filter_exe(self->audit_fd, &self->audit_filter,
-				      AUDIT_DEL_RULE));
+	EXPECT_EQ(0, audit_cleanup(self->audit_fd, &self->audit_filter));
 	clear_cap(_metadata, CAP_AUDIT_CONTROL);
-	EXPECT_EQ(0, close(self->audit_fd));
 }
 
 TEST_F(audit_exec, signal_and_open)

@@ -90,11 +90,12 @@ static struct landlock_details *get_curr
 		return ERR_CAST(buffer);
 
 	/*
-	 * Create the new details according to the path's length.  Do not
-	 * allocate with GFP_KERNEL_ACCOUNT because it is independent from the
-	 * caller.
+	 * Create the new details according to the path's length.  Account to
+	 * the calling task's memcg, like the other Landlock per-domain
+	 * allocations, even if it may not control the related size.
 	 */
-	details = kzalloc_flex(*details, exe_path, path_size);
+	details =
+		kzalloc_flex(*details, exe_path, path_size, GFP_KERNEL_ACCOUNT);
 	if (!details)
 		return ERR_PTR(-ENOMEM);
 

@@ -33,10 +33,7 @@ enum landlock_log_status {
  * Rarely accessed, mainly when logging the first domain's denial.
  *
  * The contained pointers are initialized at the domain creation time and never
- * changed again.  Contrary to most other Landlock object types, this one is
- * not allocated with GFP_KERNEL_ACCOUNT because its size may not be under the
- * caller's control (e.g. unknown exe_path) and the data is not explicitly
- * requested nor used by tasks.
+ * changed again.
  */
 struct landlock_details {
 	/**

@@ -381,18 +381,24 @@ struct audit_records {
 };
 
 /*
- * WARNING: Do not assert records.domain == 0 without a preceding
- * audit_match_record() call.  Domain deallocation records are emitted
- * asynchronously from kworker threads and can arrive after the drain in
- * audit_init(), corrupting the domain count.  A preceding audit_match_record()
- * call consumes stale records while scanning, making the assertion safe in
- * practice because stale deallocation records arrive before the expected access
- * records.
+ * Counts remaining audit records by type, skipping domain deallocation records.
+ * Deallocation records are emitted asynchronously from kworker threads after a
+ * previous test's child has exited, so they can arrive after the drain in
+ * audit_init() and after the preceding audit_match_record() call.  Allocation
+ * records are emitted synchronously during landlock_log_denial() in the current
+ * test's syscall context, so only those are counted in records->domain.
  */
 static int audit_count_records(int audit_fd, struct audit_records *records)
 {
+	static const char dealloc_pattern[] = REGEX_LANDLOCK_PREFIX
+		" status=deallocated ";
 	struct audit_message msg;
-	int err;
+	regex_t dealloc_re;
+	int ret, err = 0;
+
+	ret = regcomp(&dealloc_re, dealloc_pattern, 0);
+	if (ret)
+		return -ENOMEM;
 
 	records->access = 0;
 	records->domain = 0;

@@ -402,9 +408,8 @@ static int audit_count_records(int audit
 		err = audit_recv(audit_fd, &msg);
 		if (err) {
 			if (err == -EAGAIN)
-				return 0;
-			else
-				return err;
+				err = 0;
+			break;
 		}
 
 		switch (msg.header.nlmsg_type) {

@@ -412,12 +417,20 @@ static int audit_count_records(int audit
 			records->access++;
 			break;
 		case AUDIT_LANDLOCK_DOMAIN:
-			records->domain++;
+			ret = regexec(&dealloc_re, msg.data, 0, NULL, 0);
+			if (ret == REG_NOMATCH) {
+				records->domain++;
+			} else if (ret != 0) {
+				err = -EIO;
+				goto out;
+			}
 			break;
 		}
 	} while (true);
 
-	return 0;
+out:
+	regfree(&dealloc_re);
+	return err;
 }
 
 static int audit_init(void)

@@ -730,6 +730,7 @@ TEST_F(audit_flags, signal)
 		} else {
 			EXPECT_EQ(1, records.access);
 		}
+		EXPECT_EQ(0, records.domain);
 
 		/* Updates filter rules to match the drop record. */
 		set_cap(_metadata, CAP_AUDIT_CONTROL);

@@ -915,6 +916,7 @@ TEST_F(audit_exec, signal_and_open)
 	/* Tests that there was no denial until now. */
 	EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
 	EXPECT_EQ(0, records.access);
+	EXPECT_EQ(0, records.domain);
 
 	/*
 	 * Wait for the child to do a first denied action by layer1 and

@@ -342,6 +342,7 @@ TEST_F(audit, trace)
 	/* Makes sure there is no superfluous logged records. */
 	EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
 	EXPECT_EQ(0, records.access);
+	EXPECT_EQ(0, records.domain);
 
 	yama_ptrace_scope = get_yama_ptrace_scope();
 	ASSERT_LE(0, yama_ptrace_scope);

@@ -312,6 +312,7 @@ TEST_F(scoped_audit, connect_to_child)
 	/* Makes sure there is no superfluous logged records. */
 	EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
 	EXPECT_EQ(0, records.access);
+	EXPECT_EQ(0, records.domain);
 
 	ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC));
 	ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));

@@ -45,17 +45,25 @@ struct audit_message {
 	};
 };
 
-static const struct timeval audit_tv_dom_drop = {
+static const struct timeval audit_tv_default = {
 	/*
-	 * Because domain deallocation is tied to asynchronous credential
-	 * freeing, receiving such event may take some time.  In practice,
-	 * on a small VM, it should not exceed 100k usec, but let's wait up
-	 * to 1 second to be safe.
+	 * Default socket timeout for audit_match_record() callers that expect a
+	 * record to arrive.  Asynchronous kauditd delivery can exceed 1 usec
+	 * under heavy debug configs (KASAN, lockdep), where kauditd_thread
+	 * scheduling between audit_log_end() and netlink_unicast() takes longer
+	 * than the previous 1 usec timeout. 1 second is a generous ceiling: on
+	 * the happy path, kauditd delivers within dozens of usec.
 	 */
 	.tv_sec = 1,
 };
 
-static const struct timeval audit_tv_default = {
+static const struct timeval audit_tv_fast = {
+	/*
+	 * Fast timeout for paths that expect no record (audit_init() drain,
+	 * audit_count_records(), probes).  Causes audit_recv() to return
+	 * -EAGAIN once the socket buffer is empty, naturally terminating the
+	 * read loop.
+	 */
 	.tv_usec = 1,
 };
 

@@ -334,8 +342,13 @@ static int __maybe_unused matches_log_do
  * Matches a domain deallocation record.  When expected_domain_id is non-zero,
  * the pattern includes the specific domain ID so that stale deallocation
  * records from a previous test (with a different domain ID) are skipped by
- * audit_match_record(), and the socket timeout is temporarily increased to
- * audit_tv_dom_drop to wait for the asynchronous kworker deallocation.
+ * audit_match_record(), waiting for the asynchronous kworker deallocation with
+ * the default patient timeout.
+ *
+ * When expected_domain_id is zero, the caller is probing for any dealloc record
+ * that may or may not arrive.  Temporarily lowers the socket timeout to
+ * audit_tv_fast for this probe so it returns promptly when no record is
+ * pending; restores audit_tv_default after.
  */
 static int __maybe_unused
 matches_log_domain_deallocated(int audit_fd, unsigned int num_denials,

@@ -361,16 +374,21 @@ matches_log_domain_deallocated(int audit
 	if (log_match_len >= sizeof(log_match))
 		return -E2BIG;
 
-	if (expected_domain_id)
-		setsockopt(audit_fd, SOL_SOCKET, SO_RCVTIMEO,
-			   &audit_tv_dom_drop, sizeof(audit_tv_dom_drop));
+	if (!expected_domain_id) {
+		if (setsockopt(audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+			       &audit_tv_fast, sizeof(audit_tv_fast)))
+			return -errno;
+	}
 
 	err = audit_match_record(audit_fd, AUDIT_LANDLOCK_DOMAIN, log_match,
 				 domain_id);
 
-	if (expected_domain_id)
-		setsockopt(audit_fd, SOL_SOCKET, SO_RCVTIMEO, &audit_tv_default,
-			   sizeof(audit_tv_default));
+	if (!expected_domain_id) {
+		if (setsockopt(audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+			       &audit_tv_default, sizeof(audit_tv_default)) &&
+		    !err)
+			err = -errno;
+	}
 
 	return err;
 }

@@ -387,6 +405,11 @@ struct audit_records {
  * audit_init() and after the preceding audit_match_record() call.  Allocation
  * records are emitted synchronously during landlock_log_denial() in the current
  * test's syscall context, so only those are counted in records->domain.
+ *
+ * Temporarily lowers SO_RCVTIMEO to audit_tv_fast for the read loop: this is a
+ * "no record expected" path that should terminate on the first -EAGAIN.  The
+ * default patient timeout is restored on exit for subsequent
+ * audit_match_record() callers.
  */
 static int audit_count_records(int audit_fd, struct audit_records *records)
 {

@@ -403,6 +426,12 @@ static int audit_count_records(int audit
 	records->access = 0;
 	records->domain = 0;
 
+	if (setsockopt(audit_fd, SOL_SOCKET, SO_RCVTIMEO, &audit_tv_fast,
+		       sizeof(audit_tv_fast))) {
+		err = -errno;
+		goto out;
+	}
+
 	do {
 		memset(&msg, 0, sizeof(msg));
 		err = audit_recv(audit_fd, &msg);

@@ -429,6 +458,10 @@ static int audit_count_records(int audit
 	} while (true);
 
 out:
+	if (setsockopt(audit_fd, SOL_SOCKET, SO_RCVTIMEO, &audit_tv_default,
+		       sizeof(audit_tv_default)) &&
+	    !err)
+		err = -errno;
 	regfree(&dealloc_re);
 	return err;
 }

@@ -449,9 +482,9 @@ static int audit_init(void)
 	if (err)
 		goto err_close;
 
-	/* Sets a timeout for negative tests. */
-	err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &audit_tv_default,
-			 sizeof(audit_tv_default));
+	/* Uses the fast timeout to drain stale records below. */
+	err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &audit_tv_fast,
+			 sizeof(audit_tv_fast));
 	if (err) {
 		err = -errno;
 		goto err_close;

@@ -467,6 +500,19 @@ static int audit_init(void)
 	while (audit_recv(fd, NULL) == 0)
 		;
 
+	/*
+	 * Restores the default timeout for audit_match_record() callers that
+	 * expect a record to arrive.  Paths that expect no record restore the
+	 * fast timeout locally (audit_count_records(), the expected_domain_id
+	 * == 0 probe in matches_log_domain_deallocated()).
+	 */
+	err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &audit_tv_default,
+			 sizeof(audit_tv_default));
+	if (err) {
+		err = -errno;
+		goto err_close;
+	}
+
 	return fd;
 
 err_close:

@@ -904,9 +904,21 @@ static void invalidate_vncr(struct vncr_
 		clear_fixmap(vncr_fixmap(vt->cpu));
 }
 
+/*
+ * VNCR TLB invalidation occurs from MMU notifiers or TLBI instructions, and
+ * either can race against a vcpu not being onlined yet (no pseudo-TLB
+ * allocated). Similarly, the TLB might be invalid.  Skip those, as they
+ * obviously don't participate in the invalidation at this stage.
+ */
+#define kvm_for_each_vncr_tlb(idx, vcpup, tlbp, kvm)	\
+	kvm_for_each_vcpu(idx, vcpup, kvm)		\
+		if (((tlbp) = vcpup->arch.vncr_tlb) &&	\
+		    (tlbp)->valid)
+
 static void kvm_invalidate_vncr_ipa(struct kvm *kvm, u64 start, u64 end)
 {
 	struct kvm_vcpu *vcpu;
+	struct vncr_tlb *vt;
 	unsigned long i;
 
 	lockdep_assert_held_write(&kvm->mmu_lock);

@@ -914,24 +926,9 @@ static void kvm_invalidate_vncr_ipa(stru
 	if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY))
 		return;
 
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
+	kvm_for_each_vncr_tlb(i, vcpu, vt, kvm) {
 		u64 ipa_start, ipa_end, ipa_size;
 
-		/*
-		 * Careful here: We end-up here from an MMU notifier,
-		 * and this can race against a vcpu not being onlined
-		 * yet, without the pseudo-TLB being allocated.
-		 *
-		 * Skip those, as they obviously don't participate in
-		 * the invalidation at this stage.
-		 */
-		if (!vt)
-			continue;
-
-		if (!vt->valid)
-			continue;
-
 		ipa_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift,
 							    vt->wr.level));
 		ipa_start = vt->wr.pa & ~(ipa_size - 1);

@@ -961,17 +958,14 @@ static void invalidate_vncr_va(struct kv
 			       struct s1e2_tlbi_scope *scope)
 {
 	struct kvm_vcpu *vcpu;
+	struct vncr_tlb *vt;
 	unsigned long i;
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
+	kvm_for_each_vncr_tlb(i, vcpu, vt, kvm) {
 		u64 va_start, va_end, va_size;
 
-		if (!vt->valid)
-			continue;
-
 		va_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift,
 							   vt->wr.level));
 		va_start = vt->gva & ~(va_size - 1);

@@ -645,10 +645,14 @@ static int kvm_eiointc_create(struct kvm
 
 	device = &s->device_vext;
 	kvm_iodevice_init(device, &kvm_eiointc_virt_ops);
+	mutex_lock(&kvm->slots_lock);
 	ret = kvm_io_bus_register_dev(kvm, KVM_IOCSR_BUS,
 			EIOINTC_VIRT_BASE, EIOINTC_VIRT_SIZE, device);
+	mutex_unlock(&kvm->slots_lock);
 	if (ret < 0) {
+		mutex_lock(&kvm->slots_lock);
 		kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &s->device);
+		mutex_unlock(&kvm->slots_lock);
 		kfree(s);
 		return ret;
 	}

@@ -667,8 +671,10 @@ static void kvm_eiointc_destroy(struct k
 
 	kvm = dev->kvm;
 	eiointc = kvm->arch.eiointc;
+	mutex_lock(&kvm->slots_lock);
 	kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device);
 	kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device_vext);
+	mutex_unlock(&kvm->slots_lock);
 	kfree(eiointc);
 	kfree(dev);
 }

@@ -447,7 +447,9 @@ static void kvm_ipi_destroy(struct kvm_d
 
 	kvm = dev->kvm;
 	ipi = kvm->arch.ipi;
+	mutex_lock(&kvm->slots_lock);
 	kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &ipi->device);
+	mutex_unlock(&kvm->slots_lock);
 	kfree(ipi);
 	kfree(dev);
 }

@@ -481,7 +481,9 @@ static void kvm_pch_pic_destroy(struct k
 	kvm = dev->kvm;
 	s = kvm->arch.pch_pic;
 	/* unregister pch pic device and free it's memory */
+	mutex_lock(&kvm->slots_lock);
 	kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &s->device);
+	mutex_unlock(&kvm->slots_lock);
 	kfree(s);
 	kfree(dev);
 }

@@ -157,5 +157,6 @@ extern unsigned long kvm_nvhe_sym(__icac
 extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits);
 extern unsigned int kvm_nvhe_sym(kvm_host_sve_max_vl);
 extern unsigned long kvm_nvhe_sym(hyp_nr_cpus);
+extern unsigned int kvm_nvhe_sym(hyp_gicv3_nr_lr);
 
 #endif /* __ARM64_KVM_HYP_H__ */

@@ -2426,6 +2426,8 @@ static int __init init_subsystems(void)
 	switch (err) {
 	case 0:
 		vgic_present = true;
+		if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
+			kvm_nvhe_sym(hyp_gicv3_nr_lr) = kvm_vgic_global_state.nr_lr;
 		break;
 	case -ENODEV:
 	case -ENXIO:

@@ -24,6 +24,9 @@
 
 DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
+/* Number of implemented GICv3 LRs. Used by flush_hyp_vcpu(). */
+unsigned int hyp_gicv3_nr_lr;
+
 void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);
 
 static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)

@@ -139,6 +142,12 @@ static void flush_hyp_vcpu(struct pkvm_h
 
 	hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3 = host_vcpu->arch.vgic_cpu.vgic_v3;
 
+	/* Bound used_lrs by the number of implemented list registers. */
+	hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3.used_lrs =
+		min_t(unsigned int,
+		      hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3.used_lrs,
+		      hyp_gicv3_nr_lr);
+
 	hyp_vcpu->vcpu.arch.pid = host_vcpu->arch.pid;
 }
 

@@ -131,6 +131,9 @@ static void flush_hyp_vcpu(struct pkvm_h
 
 	hyp_vcpu->vcpu.arch.ctxt	= host_vcpu->arch.ctxt;
 
+	/* __hyp_running_vcpu must be NULL in a guest context. */
+	hyp_vcpu->vcpu.arch.ctxt.__hyp_running_vcpu = NULL;
+
 	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
 	hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE);
 	hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) &

@@ -2470,6 +2470,7 @@ static int snp_launch_update(struct kvm
 	sev_populate_args.type = params.type;
 
 	count = kvm_gmem_populate(kvm, params.gfn_start, src, npages,
+				  params.type == KVM_SEV_SNP_PAGE_TYPE_CPUID,
 				  sev_gmem_post_populate, &sev_populate_args);
 	if (count < 0) {
 		argp->error = sev_populate_args.fw_error;

@@ -3185,7 +3185,7 @@ static int tdx_vcpu_init_mem_region(stru
 		};
 		gmem_ret = kvm_gmem_populate(kvm, gpa_to_gfn(region.gpa),
 					     u64_to_user_ptr(region.source_addr),
-					     1, tdx_gmem_post_populate, &arg);
+					     1, false, tdx_gmem_post_populate, &arg);
 		if (gmem_ret < 0) {
 			ret = gmem_ret;
 			break;

@@ -2601,7 +2601,8 @@ int kvm_arch_gmem_prepare(struct kvm *kv
 typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
 				    struct page *page, void *opaque);
 
-long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages,
+long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src,
+		       long npages, bool may_writeback_src,
 		       kvm_gmem_populate_cb post_populate, void *opaque);
 #endif
 

@@ -858,7 +858,8 @@ out_unlock:
 	return ret;
 }
 
-long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages,
+long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src,
+		       long npages, bool may_writeback_src,
 		       kvm_gmem_populate_cb post_populate, void *opaque)
 {
 	struct kvm_memory_slot *slot;