Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 344 insertions, 0 deletions

diff --git a/fs/btrfs/fs.c b/fs/btrfs/fs.c
new file mode 100644
index 000000000..de160d29d
--- /dev/null
+++ b/fs/btrfs/fs.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/crc32.h>
+#include "messages.h"
+#include "fs.h"
+#include "accessors.h"
+#include "volumes.h"
+
+static const struct btrfs_csums {
+	u16		size;
+	const char	name[10];
+} btrfs_csums[] = {
+	[BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" },
+	[BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" },
+	[BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" },
+	[BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b" },
+};
+
+/* This exists for btrfs-progs usages. */
+u16 btrfs_csum_type_size(u16 type)
+{
+	return btrfs_csums[type].size;
+}
+
+int btrfs_super_csum_size(const struct btrfs_super_block *s)
+{
+	u16 t = btrfs_super_csum_type(s);
+
+	/* csum type is validated at mount time. */
+	return btrfs_csum_type_size(t);
+}
+
+const char *btrfs_super_csum_name(u16 csum_type)
+{
+	/* csum type is validated at mount time. */
+	return btrfs_csums[csum_type].name;
+}
+
+size_t __attribute_const__ btrfs_get_num_csums(void)
+{
+	return ARRAY_SIZE(btrfs_csums);
+}
+
+void btrfs_csum(u16 csum_type, const u8 *data, size_t len, u8 *out)
+{
+	switch (csum_type) {
+	case BTRFS_CSUM_TYPE_CRC32:
+		put_unaligned_le32(~crc32c(~0, data, len), out);
+		break;
+	case BTRFS_CSUM_TYPE_XXHASH:
+		put_unaligned_le64(xxh64(data, len, 0), out);
+		break;
+	case BTRFS_CSUM_TYPE_SHA256:
+		sha256(data, len, out);
+		break;
+	case BTRFS_CSUM_TYPE_BLAKE2:
+		blake2b(NULL, 0, data, len, out, 32);
+		break;
+	default:
+		/* Checksum type is validated at mount time. */
+		BUG();
+	}
+}
+
+void btrfs_csum_init(struct btrfs_csum_ctx *ctx, u16 csum_type)
+{
+	ctx->csum_type = csum_type;
+	switch (ctx->csum_type) {
+	case BTRFS_CSUM_TYPE_CRC32:
+		ctx->crc32 = ~0;
+		break;
+	case BTRFS_CSUM_TYPE_XXHASH:
+		xxh64_reset(&ctx->xxh64, 0);
+		break;
+	case BTRFS_CSUM_TYPE_SHA256:
+		sha256_init(&ctx->sha256);
+		break;
+	case BTRFS_CSUM_TYPE_BLAKE2:
+		blake2b_init(&ctx->blake2b, 32);
+		break;
+	default:
+		/* Checksume type is validated at mount time. */
+		BUG();
+	}
+}
+
+void btrfs_csum_update(struct btrfs_csum_ctx *ctx, const u8 *data, size_t len)
+{
+	switch (ctx->csum_type) {
+	case BTRFS_CSUM_TYPE_CRC32:
+		ctx->crc32 = crc32c(ctx->crc32, data, len);
+		break;
+	case BTRFS_CSUM_TYPE_XXHASH:
+		xxh64_update(&ctx->xxh64, data, len);
+		break;
+	case BTRFS_CSUM_TYPE_SHA256:
+		sha256_update(&ctx->sha256, data, len);
+		break;
+	case BTRFS_CSUM_TYPE_BLAKE2:
+		blake2b_update(&ctx->blake2b, data, len);
+		break;
+	default:
+		/* Checksum type is validated at mount time. */
+		BUG();
+	}
+}
+
+void btrfs_csum_final(struct btrfs_csum_ctx *ctx, u8 *out)
+{
+	switch (ctx->csum_type) {
+	case BTRFS_CSUM_TYPE_CRC32:
+		put_unaligned_le32(~ctx->crc32, out);
+		break;
+	case BTRFS_CSUM_TYPE_XXHASH:
+		put_unaligned_le64(xxh64_digest(&ctx->xxh64), out);
+		break;
+	case BTRFS_CSUM_TYPE_SHA256:
+		sha256_final(&ctx->sha256, out);
+		break;
+	case BTRFS_CSUM_TYPE_BLAKE2:
+		blake2b_final(&ctx->blake2b, out);
+		break;
+	default:
+		/* Checksum type is validated at mount time. */
+		BUG();
+	}
+}
+
+/*
+ * For regular builds, any block size <= page size is supported.
+ * For experimental builds, any block size between BTRFS_MIN_BLOCKSIZE
+ * and BTRFS_MAX_BLOCKSIZE (inclusive) is supported.
+ */
+bool __attribute_const__ btrfs_supported_blocksize(u32 blocksize)
+{
+	/* @blocksize should be validated first. */
+	ASSERT(is_power_of_2(blocksize) && blocksize >= BTRFS_MIN_BLOCKSIZE &&
+	       blocksize <= BTRFS_MAX_BLOCKSIZE);
+
+	if (blocksize <= PAGE_SIZE)
+		return true;
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+	/*
+	 * For bs > ps support it's done by specifying a minimal folio order
+	 * for filemap, thus implying large data folios.
+	 * For HIGHMEM systems, we can not always access the content of a (large)
+	 * folio in one go, but go through them page by page.
+	 *
+	 * A lot of features don't implement a proper PAGE sized loop for large
+	 * folios, this includes:
+	 *
+	 * - compression
+	 * - verity
+	 * - encoded write
+	 *
+	 * Considering HIGHMEM is such a pain to deal with and it's going
+	 * to be deprecated eventually, just reject HIGHMEM && bs > ps cases.
+	 *
+	 * Finally, for bs > ps cases, we need to set the minimal folio order,
+	 * which requires transparent hugepage.
+	 */
+	if (blocksize > PAGE_SIZE) {
+		if (IS_ENABLED(CONFIG_HIGHMEM))
+			return false;
+
+		if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+			return false;
+	}
+	return true;
+#endif
+	return false;
+}
+
+/*
+ * Start exclusive operation @type, return true on success.
+ */
+bool btrfs_exclop_start(struct btrfs_fs_info *fs_info,
+			enum btrfs_exclusive_operation type)
+{
+	bool ret = false;
+
+	spin_lock(&fs_info->super_lock);
+	if (fs_info->exclusive_operation == BTRFS_EXCLOP_NONE) {
+		fs_info->exclusive_operation = type;
+		ret = true;
+	}
+	spin_unlock(&fs_info->super_lock);
+
+	return ret;
+}
+
+/*
+ * Conditionally allow to enter the exclusive operation in case it's compatible
+ * with the running one.  This must be paired with btrfs_exclop_start_unlock()
+ * and btrfs_exclop_finish().
+ *
+ * Compatibility:
+ * - the same type is already running
+ * - when trying to add a device and balance has been paused
+ * - not BTRFS_EXCLOP_NONE - this is intentionally incompatible and the caller
+ *   must check the condition first that would allow none -> @type
+ */
+bool btrfs_exclop_start_try_lock(struct btrfs_fs_info *fs_info,
+				 enum btrfs_exclusive_operation type)
+{
+	spin_lock(&fs_info->super_lock);
+	if (fs_info->exclusive_operation == type ||
+	    (fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED &&
+	     type == BTRFS_EXCLOP_DEV_ADD))
+		return true;
+
+	spin_unlock(&fs_info->super_lock);
+	return false;
+}
+
+void btrfs_exclop_start_unlock(struct btrfs_fs_info *fs_info)
+{
+	spin_unlock(&fs_info->super_lock);
+}
+
+void btrfs_exclop_finish(struct btrfs_fs_info *fs_info)
+{
+	spin_lock(&fs_info->super_lock);
+	WRITE_ONCE(fs_info->exclusive_operation, BTRFS_EXCLOP_NONE);
+	spin_unlock(&fs_info->super_lock);
+	sysfs_notify(&fs_info->fs_devices->fsid_kobj, NULL, "exclusive_operation");
+}
+
+void btrfs_exclop_balance(struct btrfs_fs_info *fs_info,
+			  enum btrfs_exclusive_operation op)
+{
+	switch (op) {
+	case BTRFS_EXCLOP_BALANCE_PAUSED:
+		spin_lock(&fs_info->super_lock);
+		ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE ||
+		       fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD ||
+		       fs_info->exclusive_operation == BTRFS_EXCLOP_NONE ||
+		       fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED);
+		fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE_PAUSED;
+		spin_unlock(&fs_info->super_lock);
+		break;
+	case BTRFS_EXCLOP_BALANCE:
+		spin_lock(&fs_info->super_lock);
+		ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED);
+		fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE;
+		spin_unlock(&fs_info->super_lock);
+		break;
+	default:
+		btrfs_warn(fs_info,
+			"invalid exclop balance operation %d requested", op);
+	}
+}
+
+void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag,
+			     const char *name)
+{
+	struct btrfs_super_block *disk_super;
+	u64 features;
+
+	disk_super = fs_info->super_copy;
+	features = btrfs_super_incompat_flags(disk_super);
+	if (!(features & flag)) {
+		spin_lock(&fs_info->super_lock);
+		features = btrfs_super_incompat_flags(disk_super);
+		if (!(features & flag)) {
+			features |= flag;
+			btrfs_set_super_incompat_flags(disk_super, features);
+			btrfs_info(fs_info,
+				"setting incompat feature flag for %s (0x%llx)",
+				name, flag);
+		}
+		spin_unlock(&fs_info->super_lock);
+		set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
+	}
+}
+
+void __btrfs_clear_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag,
+			       const char *name)
+{
+	struct btrfs_super_block *disk_super;
+	u64 features;
+
+	disk_super = fs_info->super_copy;
+	features = btrfs_super_incompat_flags(disk_super);
+	if (features & flag) {
+		spin_lock(&fs_info->super_lock);
+		features = btrfs_super_incompat_flags(disk_super);
+		if (features & flag) {
+			features &= ~flag;
+			btrfs_set_super_incompat_flags(disk_super, features);
+			btrfs_info(fs_info,
+				"clearing incompat feature flag for %s (0x%llx)",
+				name, flag);
+		}
+		spin_unlock(&fs_info->super_lock);
+		set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
+	}
+}
+
+void __btrfs_set_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag,
+			      const char *name)
+{
+	struct btrfs_super_block *disk_super;
+	u64 features;
+
+	disk_super = fs_info->super_copy;
+	features = btrfs_super_compat_ro_flags(disk_super);
+	if (!(features & flag)) {
+		spin_lock(&fs_info->super_lock);
+		features = btrfs_super_compat_ro_flags(disk_super);
+		if (!(features & flag)) {
+			features |= flag;
+			btrfs_set_super_compat_ro_flags(disk_super, features);
+			btrfs_info(fs_info,
+				"setting compat-ro feature flag for %s (0x%llx)",
+				name, flag);
+		}
+		spin_unlock(&fs_info->super_lock);
+		set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
+	}
+}
+
+void __btrfs_clear_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag,
+				const char *name)
+{
+	struct btrfs_super_block *disk_super;
+	u64 features;
+
+	disk_super = fs_info->super_copy;
+	features = btrfs_super_compat_ro_flags(disk_super);
+	if (features & flag) {
+		spin_lock(&fs_info->super_lock);
+		features = btrfs_super_compat_ro_flags(disk_super);
+		if (features & flag) {
+			features &= ~flag;
+			btrfs_set_super_compat_ro_flags(disk_super, features);
+			btrfs_info(fs_info,
+				"clearing compat-ro feature flag for %s (0x%llx)",
+				name, flag);
+		}
+		spin_unlock(&fs_info->super_lock);
+		set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
+	}
+}