6.5.5-rc1 review

index 591c11888200d..88770561c4350 100644
@@ -3120,14 +3120,24 @@ void console_unblank(void)
  */
 void console_flush_on_panic(enum con_flush_mode mode)
 {
+	bool handover;
+	u64 next_seq;
+
 	/*
-	 * If someone else is holding the console lock, trylock will fail
-	 * and may_schedule may be set.  Ignore and proceed to unlock so
-	 * that messages are flushed out.  As this can be called from any
-	 * context and we don't want to get preempted while flushing,
-	 * ensure may_schedule is cleared.
+	 * Ignore the console lock and flush out the messages. Attempting a
+	 * trylock would not be useful because:
+	 *
+	 *   - if it is contended, it must be ignored anyway
+	 *   - console_lock() and console_trylock() block and fail
+	 *     respectively in panic for non-panic CPUs
+	 *   - semaphores are not NMI-safe
+	 */
+
+	/*
+	 * If another context is holding the console lock,
+	 * @console_may_schedule might be set. Clear it so that
+	 * this context does not call cond_resched() while flushing.
 	 */
-	console_trylock();
 	console_may_schedule = 0;
 
 	if (mode == CONSOLE_REPLAY_ALL) {

@@ -3140,15 +3150,15 @@ void console_flush_on_panic(enum con_flush_mode mode)
 		cookie = console_srcu_read_lock();
 		for_each_console_srcu(c) {
 			/*
-			 * If the above console_trylock() failed, this is an
-			 * unsynchronized assignment. But in that case, the
+			 * This is an unsynchronized assignment, but the
 			 * kernel is in "hope and pray" mode anyway.
 			 */
 			c->seq = seq;
 		}
 		console_srcu_read_unlock(cookie);
 	}
-	console_unlock();
+
+	console_flush_all(false, &next_seq, &handover);
 }
 
 /*

index 88770561c4350..d5e29fad84234 100644
@@ -2308,7 +2308,11 @@ asmlinkage int vprintk_emit(int facility, int level,
 		preempt_enable();
 	}
 
-	wake_up_klogd();
+	if (in_sched)
+		defer_console_output();
+	else
+		wake_up_klogd();
+
 	return printed_len;
 }
 EXPORT_SYMBOL(vprintk_emit);

@@ -3843,11 +3847,33 @@ static void __wake_up_klogd(int val)
 	preempt_enable();
 }
 
+/**
+ * wake_up_klogd - Wake kernel logging daemon
+ *
+ * Use this function when new records have been added to the ringbuffer
+ * and the console printing of those records has already occurred or is
+ * known to be handled by some other context. This function will only
+ * wake the logging daemon.
+ *
+ * Context: Any context.
+ */
 void wake_up_klogd(void)
 {
 	__wake_up_klogd(PRINTK_PENDING_WAKEUP);
 }
 
+/**
+ * defer_console_output - Wake kernel logging daemon and trigger
+ *	console printing in a deferred context
+ *
+ * Use this function when new records have been added to the ringbuffer,
+ * this context is responsible for console printing those records, but
+ * the current context is not allowed to perform the console printing.
+ * Trigger an irq_work context to perform the console printing. This
+ * function also wakes the logging daemon.
+ *
+ * Context: Any context.
+ */
 void defer_console_output(void)
 {
 	/*

@@ -3864,12 +3890,7 @@ void printk_trigger_flush(void)
 
 int vprintk_deferred(const char *fmt, va_list args)
 {
-	int r;
-
-	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
-	defer_console_output();
-
-	return r;
+	return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
 }
 
 int _printk_deferred(const char *fmt, ...)

index ef0f9a2044da1..6d10927a07d83 100644
@@ -38,13 +38,8 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	 * Use the main logbuf even in NMI. But avoid calling console
 	 * drivers that might have their own locks.
 	 */
-	if (this_cpu_read(printk_context) || in_nmi()) {
-		int len;
-
-		len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
-		defer_console_output();
-		return len;
-	}
+	if (this_cpu_read(printk_context) || in_nmi())
+		return vprintk_deferred(fmt, args);
 
 	/* No obstacles. */
 	return vprintk_default(fmt, args);

index 2a17704136f1d..7d4979d5c3ce6 100644
@@ -103,3 +103,5 @@ struct printk_message {
 	u64			seq;
 	unsigned long		dropped;
 };
+
+bool other_cpu_in_panic(void);

index d5e29fad84234..08a9419046b65 100644
@@ -2590,11 +2590,12 @@ static int console_cpu_notify(unsigned int cpu)
 }
 
 /*
- * Return true when this CPU should unlock console_sem without pushing all
- * messages to the console. This reduces the chance that the console is
- * locked when the panic CPU tries to use it.
+ * Return true if a panic is in progress on a remote CPU.
+ *
+ * On true, the local CPU should immediately release any printing resources
+ * that may be needed by the panic CPU.
  */
-static bool abandon_console_lock_in_panic(void)
+bool other_cpu_in_panic(void)
 {
 	if (!panic_in_progress())
 		return false;

@@ -2621,7 +2622,7 @@ void console_lock(void)
 	might_sleep();
 
 	/* On panic, the console_lock must be left to the panic cpu. */
-	while (abandon_console_lock_in_panic())
+	while (other_cpu_in_panic())
 		msleep(1000);
 
 	down_console_sem();

@@ -2643,7 +2644,7 @@ EXPORT_SYMBOL(console_lock);
 int console_trylock(void)
 {
 	/* On panic, the console_lock must be left to the panic cpu. */
-	if (abandon_console_lock_in_panic())
+	if (other_cpu_in_panic())
 		return 0;
 	if (down_trylock_console_sem())
 		return 0;

@@ -2959,7 +2960,7 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove
 			any_progress = true;
 
 			/* Allow panic_cpu to take over the consoles safely. */
-			if (abandon_console_lock_in_panic())
+			if (other_cpu_in_panic())
 				goto abandon;
 
 			if (do_cond_resched)

index 5c3055a32e57a..bd7557d8dec41 100644
@@ -5177,8 +5177,11 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 	pa = ac->ac_pa;
 
 	if (ac->ac_b_ex.fe_len < ac->ac_orig_goal_len) {
-		int new_bex_start;
-		int new_bex_end;
+		struct ext4_free_extent ex = {
+			.fe_logical = ac->ac_g_ex.fe_logical,
+			.fe_len = ac->ac_orig_goal_len,
+		};
+		loff_t orig_goal_end = extent_logical_end(sbi, &ex);
 
 		/* we can't allocate as much as normalizer wants.
 		 * so, found space must get proper lstart

@@ -5197,29 +5200,23 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 		 *    still cover original start
 		 * 3. Else, keep the best ex at start of original request.
 		 */
-		new_bex_end = ac->ac_g_ex.fe_logical +
-			EXT4_C2B(sbi, ac->ac_orig_goal_len);
-		new_bex_start = new_bex_end - EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
-		if (ac->ac_o_ex.fe_logical >= new_bex_start)
-			goto adjust_bex;
+		ex.fe_len = ac->ac_b_ex.fe_len;
 
-		new_bex_start = ac->ac_g_ex.fe_logical;
-		new_bex_end =
-			new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
-		if (ac->ac_o_ex.fe_logical < new_bex_end)
+		ex.fe_logical = orig_goal_end - EXT4_C2B(sbi, ex.fe_len);
+		if (ac->ac_o_ex.fe_logical >= ex.fe_logical)
 			goto adjust_bex;
 
-		new_bex_start = ac->ac_o_ex.fe_logical;
-		new_bex_end =
-			new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
+		ex.fe_logical = ac->ac_g_ex.fe_logical;
+		if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex))
+			goto adjust_bex;
 
+		ex.fe_logical = ac->ac_o_ex.fe_logical;
 adjust_bex:
-		ac->ac_b_ex.fe_logical = new_bex_start;
+		ac->ac_b_ex.fe_logical = ex.fe_logical;
 
 		BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
 		BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
-		BUG_ON(new_bex_end > (ac->ac_g_ex.fe_logical +
-				      EXT4_C2B(sbi, ac->ac_orig_goal_len)));
+		BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end);
 	}
 
 	pa->pa_lstart = ac->ac_b_ex.fe_logical;

index 90ad3006ef3a7..b3bf2e2704888 100644
@@ -1877,9 +1877,9 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc)
  * previous call.
  * Return <0 for fatal error.
  */
-static int submit_eb_page(struct page *page, struct writeback_control *wbc,
-			  struct extent_buffer **eb_context)
+static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 {
+	struct writeback_control *wbc = ctx->wbc;
 	struct address_space *mapping = page->mapping;
 	struct btrfs_block_group *cache = NULL;
 	struct extent_buffer *eb;

@@ -1908,7 +1908,7 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 		return 0;
 	}
 
-	if (eb == *eb_context) {
+	if (eb == ctx->eb) {
 		spin_unlock(&mapping->private_lock);
 		return 0;
 	}

@@ -1917,6 +1917,8 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 	if (!ret)
 		return 0;
 
+	ctx->eb = eb;
+
 	if (!btrfs_check_meta_write_pointer(eb->fs_info, eb, &cache)) {
 		/*
 		 * If for_sync, this hole will be filled with

@@ -1930,8 +1932,6 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 		return ret;
 	}
 
-	*eb_context = eb;
-
 	if (!lock_extent_buffer_for_io(eb, wbc)) {
 		btrfs_revert_meta_write_pointer(cache, eb);
 		if (cache)

@@ -1954,7 +1954,7 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 int btree_write_cache_pages(struct address_space *mapping,
 				   struct writeback_control *wbc)
 {
-	struct extent_buffer *eb_context = NULL;
+	struct btrfs_eb_write_context ctx = { .wbc = wbc };
 	struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info;
 	int ret = 0;
 	int done = 0;

@@ -1996,7 +1996,7 @@ int btree_write_cache_pages(struct address_space *mapping,
 		for (i = 0; i < nr_folios; i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			ret = submit_eb_page(&folio->page, wbc, &eb_context);
+			ret = submit_eb_page(&folio->page, &ctx);
 			if (ret == 0)
 				continue;
 			if (ret < 0) {

index c5fae3a7d911b..ecc1660007c11 100644
@@ -94,6 +94,11 @@ struct extent_buffer {
 #endif
 };
 
+struct btrfs_eb_write_context {
+	struct writeback_control *wbc;
+	struct extent_buffer *eb;
+};
+
 /*
  * Get the correct offset inside the page of extent buffer.
  *

index b3bf2e2704888..c2be1561a52cb 100644
@@ -1881,7 +1881,6 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 {
 	struct writeback_control *wbc = ctx->wbc;
 	struct address_space *mapping = page->mapping;
-	struct btrfs_block_group *cache = NULL;
 	struct extent_buffer *eb;
 	int ret;
 

@@ -1919,7 +1918,7 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 
 	ctx->eb = eb;
 
-	if (!btrfs_check_meta_write_pointer(eb->fs_info, eb, &cache)) {
+	if (!btrfs_check_meta_write_pointer(eb->fs_info, ctx)) {
 		/*
 		 * If for_sync, this hole will be filled with
 		 * trasnsaction commit.

@@ -1933,18 +1932,15 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 	}
 
 	if (!lock_extent_buffer_for_io(eb, wbc)) {
-		btrfs_revert_meta_write_pointer(cache, eb);
-		if (cache)
-			btrfs_put_block_group(cache);
+		btrfs_revert_meta_write_pointer(ctx->zoned_bg, eb);
 		free_extent_buffer(eb);
 		return 0;
 	}
-	if (cache) {
+	if (ctx->zoned_bg) {
 		/*
 		 * Implies write in zoned mode. Mark the last eb in a block group.
 		 */
-		btrfs_schedule_zone_finish_bg(cache, eb);
-		btrfs_put_block_group(cache);
+		btrfs_schedule_zone_finish_bg(ctx->zoned_bg, eb);
 	}
 	write_one_eb(eb, wbc);
 	free_extent_buffer(eb);

@@ -2057,6 +2053,9 @@ int btree_write_cache_pages(struct address_space *mapping,
 		ret = 0;
 	if (!ret && BTRFS_FS_ERROR(fs_info))
 		ret = -EROFS;
+
+	if (ctx.zoned_bg)
+		btrfs_put_block_group(ctx.zoned_bg);
 	btrfs_zoned_meta_io_unlock(fs_info);
 	return ret;
 }

index ecc1660007c11..f61b7896320a1 100644
@@ -97,6 +97,8 @@ struct extent_buffer {
 struct btrfs_eb_write_context {
 	struct writeback_control *wbc;
 	struct extent_buffer *eb;
+	/* Block group @eb resides in. Only used for zoned mode. */
+	struct btrfs_block_group *zoned_bg;
 };
 
 /*

index d9e6df2da272c..92f11176216b5 100644
@@ -1759,30 +1759,35 @@ void btrfs_finish_ordered_zoned(struct btrfs_ordered_extent *ordered)
 }
 
 bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
-				    struct extent_buffer *eb,
-				    struct btrfs_block_group **cache_ret)
+				    struct btrfs_eb_write_context *ctx)
 {
-	struct btrfs_block_group *cache;
-	bool ret = true;
+	const struct extent_buffer *eb = ctx->eb;
+	struct btrfs_block_group *block_group = ctx->zoned_bg;
 
 	if (!btrfs_is_zoned(fs_info))
 		return true;
 
-	cache = btrfs_lookup_block_group(fs_info, eb->start);
-	if (!cache)
-		return true;
+	if (block_group) {
+		if (block_group->start > eb->start ||
+		    block_group->start + block_group->length <= eb->start) {
+			btrfs_put_block_group(block_group);
+			block_group = NULL;
+			ctx->zoned_bg = NULL;
+		}
+	}
 
-	if (cache->meta_write_pointer != eb->start) {
-		btrfs_put_block_group(cache);
-		cache = NULL;
-		ret = false;
-	} else {
-		cache->meta_write_pointer = eb->start + eb->len;
+	if (!block_group) {
+		block_group = btrfs_lookup_block_group(fs_info, eb->start);
+		if (!block_group)
+			return true;
+		ctx->zoned_bg = block_group;
 	}
 
-	*cache_ret = cache;
+	if (block_group->meta_write_pointer != eb->start)
+		return false;
+	block_group->meta_write_pointer = eb->start + eb->len;
 
-	return ret;
+	return true;
 }
 
 void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache,

index 27322b926038c..49d5bd87245c5 100644
@@ -59,8 +59,7 @@ void btrfs_redirty_list_add(struct btrfs_transaction *trans,
 bool btrfs_use_zone_append(struct btrfs_bio *bbio);
 void btrfs_record_physical_zoned(struct btrfs_bio *bbio);
 bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
-				    struct extent_buffer *eb,
-				    struct btrfs_block_group **cache_ret);
+				    struct btrfs_eb_write_context *ctx);
 void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache,
 				     struct extent_buffer *eb);
 int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length);

@@ -190,8 +189,7 @@ static inline void btrfs_record_physical_zoned(struct btrfs_bio *bbio)
 }
 
 static inline bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
-			       struct extent_buffer *eb,
-			       struct btrfs_block_group **cache_ret)
+						  struct btrfs_eb_write_context *ctx)
 {
 	return true;
 }

index c2be1561a52cb..d4bac66cee533 100644
@@ -1918,14 +1918,9 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 
 	ctx->eb = eb;
 
-	if (!btrfs_check_meta_write_pointer(eb->fs_info, ctx)) {
-		/*
-		 * If for_sync, this hole will be filled with
-		 * trasnsaction commit.
-		 */
-		if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
-			ret = -EAGAIN;
-		else
+	ret = btrfs_check_meta_write_pointer(eb->fs_info, ctx);
+	if (ret) {
+		if (ret == -EBUSY)
 			ret = 0;
 		free_extent_buffer(eb);
 		return ret;

index 92f11176216b5..6e406f1b0d21e 100644
@@ -1758,14 +1758,23 @@ void btrfs_finish_ordered_zoned(struct btrfs_ordered_extent *ordered)
 	}
 }
 
-bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
-				    struct btrfs_eb_write_context *ctx)
+/*
+ * Check if @ctx->eb is aligned to the write pointer.
+ *
+ * Return:
+ *   0:        @ctx->eb is at the write pointer. You can write it.
+ *   -EAGAIN:  There is a hole. The caller should handle the case.
+ *   -EBUSY:   There is a hole, but the caller can just bail out.
+ */
+int btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
+				   struct btrfs_eb_write_context *ctx)
 {
+	const struct writeback_control *wbc = ctx->wbc;
 	const struct extent_buffer *eb = ctx->eb;
 	struct btrfs_block_group *block_group = ctx->zoned_bg;
 
 	if (!btrfs_is_zoned(fs_info))
-		return true;
+		return 0;
 
 	if (block_group) {
 		if (block_group->start > eb->start ||

@@ -1779,15 +1788,20 @@ bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
 	if (!block_group) {
 		block_group = btrfs_lookup_block_group(fs_info, eb->start);
 		if (!block_group)
-			return true;
+			return 0;
 		ctx->zoned_bg = block_group;
 	}
 
-	if (block_group->meta_write_pointer != eb->start)
-		return false;
-	block_group->meta_write_pointer = eb->start + eb->len;
+	if (block_group->meta_write_pointer == eb->start) {
+		block_group->meta_write_pointer = eb->start + eb->len;
 
-	return true;
+		return 0;
+	}
+
+	/* If for_sync, this hole will be filled with trasnsaction commit. */
+	if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
+		return -EAGAIN;
+	return -EBUSY;
 }
 
 void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache,

index 49d5bd87245c5..c0859d8be1520 100644
@@ -58,8 +58,8 @@ void btrfs_redirty_list_add(struct btrfs_transaction *trans,
 			    struct extent_buffer *eb);
 bool btrfs_use_zone_append(struct btrfs_bio *bbio);
 void btrfs_record_physical_zoned(struct btrfs_bio *bbio);
-bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
-				    struct btrfs_eb_write_context *ctx);
+int btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
+				   struct btrfs_eb_write_context *ctx);
 void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache,
 				     struct extent_buffer *eb);
 int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length);

@@ -188,10 +188,10 @@ static inline void btrfs_record_physical_zoned(struct btrfs_bio *bbio)
 {
 }
 
-static inline bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
-						  struct btrfs_eb_write_context *ctx)
+static inline int btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
+						 struct btrfs_eb_write_context *ctx)
 {
-	return true;
+	return 0;
 }
 
 static inline void btrfs_revert_meta_write_pointer(

index d4bac66cee533..2ebc982e8eccb 100644
@@ -1927,15 +1927,14 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 	}
 
 	if (!lock_extent_buffer_for_io(eb, wbc)) {
-		btrfs_revert_meta_write_pointer(ctx->zoned_bg, eb);
 		free_extent_buffer(eb);
 		return 0;
 	}
+	/* Implies write in zoned mode. */
 	if (ctx->zoned_bg) {
-		/*
-		 * Implies write in zoned mode. Mark the last eb in a block group.
-		 */
+		/* Mark the last eb in the block group. */
 		btrfs_schedule_zone_finish_bg(ctx->zoned_bg, eb);
+		ctx->zoned_bg->meta_write_pointer += eb->len;
 	}
 	write_one_eb(eb, wbc);
 	free_extent_buffer(eb);

index 6e406f1b0d21e..cc117283d0c88 100644
@@ -1792,11 +1792,8 @@ int btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
 		ctx->zoned_bg = block_group;
 	}
 
-	if (block_group->meta_write_pointer == eb->start) {
-		block_group->meta_write_pointer = eb->start + eb->len;
-
+	if (block_group->meta_write_pointer == eb->start)
 		return 0;
-	}
 
 	/* If for_sync, this hole will be filled with trasnsaction commit. */
 	if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)

@@ -1804,16 +1801,6 @@ int btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
 	return -EBUSY;
 }
 
-void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache,
-				     struct extent_buffer *eb)
-{
-	if (!btrfs_is_zoned(eb->fs_info) || !cache)
-		return;
-
-	ASSERT(cache->meta_write_pointer == eb->start + eb->len);
-	cache->meta_write_pointer = eb->start;
-}
-
 int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length)
 {
 	if (!btrfs_dev_is_sequential(device, physical))

index c0859d8be1520..74ec37a25808a 100644
@@ -60,8 +60,6 @@ bool btrfs_use_zone_append(struct btrfs_bio *bbio);
 void btrfs_record_physical_zoned(struct btrfs_bio *bbio);
 int btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
 				   struct btrfs_eb_write_context *ctx);
-void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache,
-				     struct extent_buffer *eb);
 int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length);
 int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
 				  u64 physical_start, u64 physical_pos);

@@ -194,12 +192,6 @@ static inline int btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-static inline void btrfs_revert_meta_write_pointer(
-						struct btrfs_block_group *cache,
-						struct extent_buffer *eb)
-{
-}
-
 static inline int btrfs_zoned_issue_zeroout(struct btrfs_device *device,
 					    u64 physical, u64 length)
 {

index 82324c327a502..75385503a35b6 100644
@@ -4273,6 +4273,17 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 	struct btrfs_caching_control *caching_ctl;
 	struct rb_node *n;
 
+	if (btrfs_is_zoned(info)) {
+		if (info->active_meta_bg) {
+			btrfs_put_block_group(info->active_meta_bg);
+			info->active_meta_bg = NULL;
+		}
+		if (info->active_system_bg) {
+			btrfs_put_block_group(info->active_system_bg);
+			info->active_system_bg = NULL;
+		}
+	}
+
 	write_lock(&info->block_group_cache_lock);
 	while (!list_empty(&info->caching_block_groups)) {
 		caching_ctl = list_entry(info->caching_block_groups.next,

index 203d2a2678287..1f2d331121064 100644
@@ -766,6 +766,9 @@ struct btrfs_fs_info {
 	u64 data_reloc_bg;
 	struct mutex zoned_data_reloc_io_lock;
 
+	struct btrfs_block_group *active_meta_bg;
+	struct btrfs_block_group *active_system_bg;
+
 	u64 nr_global_roots;
 
 	spinlock_t zone_active_bgs_lock;

99 lines not on this page · raw message

index 656dd80a0be79..58968c1e7d2f8 100644
@@ -48,9 +48,11 @@ static const struct spi_nor_locking_ops at25fs_nor_locking_ops = {
 	.is_locked = at25fs_nor_is_locked,
 };
 
-static void at25fs_nor_late_init(struct spi_nor *nor)
+static int at25fs_nor_late_init(struct spi_nor *nor)
 {
 	nor->params->locking_ops = &at25fs_nor_locking_ops;
+
+	return 0;
 }
 
 static const struct spi_nor_fixups at25fs_nor_fixups = {

@@ -149,9 +151,11 @@ static const struct spi_nor_locking_ops atmel_nor_global_protection_ops = {
 	.is_locked = atmel_nor_is_global_protected,
 };
 
-static void atmel_nor_global_protection_late_init(struct spi_nor *nor)
+static int atmel_nor_global_protection_late_init(struct spi_nor *nor)
 {
 	nor->params->locking_ops = &atmel_nor_global_protection_ops;
+
+	return 0;
 }
 
 static const struct spi_nor_fixups atmel_nor_global_protection_fixups = {

index 55f4a902b8be9..72973cfb1d201 100644
@@ -2898,16 +2898,23 @@ static void spi_nor_init_fixup_flags(struct spi_nor *nor)
  * SFDP standard, or where SFDP tables are not defined at all.
  * Will replace the spi_nor_manufacturer_init_params() method.
  */
-static void spi_nor_late_init_params(struct spi_nor *nor)
+static int spi_nor_late_init_params(struct spi_nor *nor)
 {
 	struct spi_nor_flash_parameter *params = nor->params;
+	int ret;
 
 	if (nor->manufacturer && nor->manufacturer->fixups &&
-	    nor->manufacturer->fixups->late_init)
-		nor->manufacturer->fixups->late_init(nor);
+	    nor->manufacturer->fixups->late_init) {
+		ret = nor->manufacturer->fixups->late_init(nor);
+		if (ret)
+			return ret;
+	}
 
-	if (nor->info->fixups && nor->info->fixups->late_init)
-		nor->info->fixups->late_init(nor);
+	if (nor->info->fixups && nor->info->fixups->late_init) {
+		ret = nor->info->fixups->late_init(nor);
+		if (ret)
+			return ret;
+	}
 
 	/* Default method kept for backward compatibility. */
 	if (!params->set_4byte_addr_mode)

@@ -2925,6 +2932,8 @@ static void spi_nor_late_init_params(struct spi_nor *nor)
 
 	if (nor->info->n_banks > 1)
 		params->bank_size = div64_u64(params->size, nor->info->n_banks);
+
+	return 0;
 }
 
 /**

@@ -3083,9 +3092,7 @@ static int spi_nor_init_params(struct spi_nor *nor)
 		spi_nor_init_params_deprecated(nor);
 	}
 
-	spi_nor_late_init_params(nor);
-
-	return 0;
+	return spi_nor_late_init_params(nor);
 }
 
 /** spi_nor_octal_dtr_enable() - enable Octal DTR I/O if needed

index 4fb5ff09c63a9..2453bd5743ac9 100644
@@ -377,6 +377,7 @@ struct spi_nor_otp {
  *			than reading the status register to indicate they
  *			are ready for a new command
  * @locking_ops:	SPI NOR locking methods.
+ * @priv:		flash's private data.
  */
 struct spi_nor_flash_parameter {
 	u64				bank_size;

@@ -405,6 +406,7 @@ struct spi_nor_flash_parameter {
 	int (*ready)(struct spi_nor *nor);
 
 	const struct spi_nor_locking_ops *locking_ops;
+	void *priv;
 };
 
 /**

@@ -431,7 +433,7 @@ struct spi_nor_fixups {
 			 const struct sfdp_parameter_header *bfpt_header,
 			 const struct sfdp_bfpt *bfpt);
 	int (*post_sfdp)(struct spi_nor *nor);
-	void (*late_init)(struct spi_nor *nor);
+	int (*late_init)(struct spi_nor *nor);
 };
 
 /**

index 400e2b42f45af..accdf7aa2bfde 100644
@@ -29,7 +29,7 @@ static const struct spi_nor_fixups is25lp256_fixups = {
 	.post_bfpt = is25lp256_post_bfpt_fixups,
 };
 
-static void pm25lv_nor_late_init(struct spi_nor *nor)
+static int pm25lv_nor_late_init(struct spi_nor *nor)
 {
 	struct spi_nor_erase_map *map = &nor->params->erase_map;
 	int i;

@@ -38,6 +38,8 @@ static void pm25lv_nor_late_init(struct spi_nor *nor)
 	for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++)
 		if (map->erase_type[i].size == 4096)
 			map->erase_type[i].opcode = SPINOR_OP_BE_4K_PMC;
+
+	return 0;
 }
 
 static const struct spi_nor_fixups pm25lv_nor_fixups = {

index 04888258e8914..eb149e517c1fe 100644
@@ -110,10 +110,12 @@ static void macronix_nor_default_init(struct spi_nor *nor)
 	nor->params->quad_enable = spi_nor_sr1_bit6_quad_enable;
 }
 
-static void macronix_nor_late_init(struct spi_nor *nor)
+static int macronix_nor_late_init(struct spi_nor *nor)
 {
 	if (!nor->params->set_4byte_addr_mode)
 		nor->params->set_4byte_addr_mode = spi_nor_set_4byte_addr_mode_en4b_ex4b;
+
+	return 0;
 }
 
 static const struct spi_nor_fixups macronix_nor_fixups = {

index 4b919756a2055..28c9c14a4b293 100644
@@ -429,7 +429,7 @@ static void micron_st_nor_default_init(struct spi_nor *nor)
 	nor->params->quad_enable = NULL;
 }
 
-static void micron_st_nor_late_init(struct spi_nor *nor)
+static int micron_st_nor_late_init(struct spi_nor *nor)
 {
 	struct spi_nor_flash_parameter *params = nor->params;
 

@@ -438,6 +438,8 @@ static void micron_st_nor_late_init(struct spi_nor *nor)
 
 	if (!params->set_4byte_addr_mode)
 		params->set_4byte_addr_mode = spi_nor_set_4byte_addr_mode_wren_en4b_ex4b;
+
+	return 0;
 }
 
 static const struct spi_nor_fixups micron_st_nor_fixups = {

190 lines not on this page · raw message

index 688eb20c763e9..09fdc7023e09a 100644
@@ -49,9 +49,11 @@ static const struct spi_nor_locking_ops sst26vf_nor_locking_ops = {
 	.is_locked = sst26vf_nor_is_locked,
 };
 
-static void sst26vf_nor_late_init(struct spi_nor *nor)
+static int sst26vf_nor_late_init(struct spi_nor *nor)
 {
 	nor->params->locking_ops = &sst26vf_nor_locking_ops;
+
+	return 0;
 }
 
 static const struct spi_nor_fixups sst26vf_nor_fixups = {

@@ -203,10 +205,12 @@ static int sst_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 	return ret;
 }
 
-static void sst_nor_late_init(struct spi_nor *nor)
+static int sst_nor_late_init(struct spi_nor *nor)
 {
 	if (nor->info->mfr_flags & SST_WRITE)
 		nor->mtd._write = sst_nor_write;
+
+	return 0;
 }
 
 static const struct spi_nor_fixups sst_nor_fixups = {

index 63ba8e3a96f51..cd99c9a1c5688 100644
@@ -217,7 +217,7 @@ static const struct spi_nor_otp_ops winbond_nor_otp_ops = {
 	.is_locked = spi_nor_otp_is_locked_sr2,
 };
 
-static void winbond_nor_late_init(struct spi_nor *nor)
+static int winbond_nor_late_init(struct spi_nor *nor)
 {
 	struct spi_nor_flash_parameter *params = nor->params;
 

@@ -233,6 +233,8 @@ static void winbond_nor_late_init(struct spi_nor *nor)
 	 * from BFPT, if any.
 	 */
 	params->set_4byte_addr_mode = winbond_nor_set_4byte_addr_mode;
+
+	return 0;
 }
 
 static const struct spi_nor_fixups winbond_nor_fixups = {

index 7175de8aa336a..00d53eae5ee83 100644
@@ -155,10 +155,12 @@ static int xilinx_nor_setup(struct spi_nor *nor,
 	return 0;
 }
 
-static void xilinx_nor_late_init(struct spi_nor *nor)
+static int xilinx_nor_late_init(struct spi_nor *nor)
 {
 	nor->params->setup = xilinx_nor_setup;
 	nor->params->ready = xilinx_nor_sr_ready;
+
+	return 0;
 }
 
 static const struct spi_nor_fixups xilinx_nor_fixups = {

index 9edc1b7ac091a..4fbaa6fba45a6 100644
@@ -4,6 +4,7 @@
  * Copyright (C) 2014, Freescale Semiconductor, Inc.
  */
 
+#include <linux/bitfield.h>
 #include <linux/device.h>
 #include <linux/mtd/spi-nor.h>
 

@@ -28,6 +29,7 @@
 #define SPINOR_REG_CYPRESS_CFR2			0x3
 #define SPINOR_REG_CYPRESS_CFR2V					\
 	(SPINOR_REG_CYPRESS_VREG + SPINOR_REG_CYPRESS_CFR2)
+#define SPINOR_REG_CYPRESS_CFR2_MEMLAT_MASK	GENMASK(3, 0)
 #define SPINOR_REG_CYPRESS_CFR2_MEMLAT_11_24	0xb
 #define SPINOR_REG_CYPRESS_CFR2_ADRBYT		BIT(7)
 #define SPINOR_REG_CYPRESS_CFR3			0x4

@@ -161,8 +163,18 @@ static int cypress_nor_octal_dtr_en(struct spi_nor *nor)
 	int ret;
 	u8 addr_mode_nbytes = nor->params->addr_mode_nbytes;
 
+	op = (struct spi_mem_op)
+		CYPRESS_NOR_RD_ANY_REG_OP(addr_mode_nbytes,
+					  SPINOR_REG_CYPRESS_CFR2V, 0, buf);
+
+	ret = spi_nor_read_any_reg(nor, &op, nor->reg_proto);
+	if (ret)
+		return ret;
+
 	/* Use 24 dummy cycles for memory array reads. */
-	*buf = SPINOR_REG_CYPRESS_CFR2_MEMLAT_11_24;
+	*buf &= ~SPINOR_REG_CYPRESS_CFR2_MEMLAT_MASK;
+	*buf |= FIELD_PREP(SPINOR_REG_CYPRESS_CFR2_MEMLAT_MASK,
+			   SPINOR_REG_CYPRESS_CFR2_MEMLAT_11_24);
 	op = (struct spi_mem_op)
 		CYPRESS_NOR_WR_ANY_REG_OP(addr_mode_nbytes,
 					  SPINOR_REG_CYPRESS_CFR2V, 1, buf);

index 6aa9bf3661ac8..51070c0d4141e 100644
@@ -681,6 +681,14 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 	return -EINVAL;
 }
 
+u8 *btrfs_sb_fsid_ptr(struct btrfs_super_block *sb)
+{
+	bool has_metadata_uuid = (btrfs_super_incompat_flags(sb) &
+				  BTRFS_FEATURE_INCOMPAT_METADATA_UUID);
+
+	return has_metadata_uuid ? sb->metadata_uuid : sb->fsid;
+}
+
 /*
  * Handle scanned device having its CHANGING_FSID_V2 flag set and the fs_devices
  * being created with a disk that has already completed its fsid change. Such

index b8c51f16ba867..0f87057bb575f 100644
@@ -749,5 +749,6 @@ int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info);
 bool btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical);
 
 bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr);
+u8 *btrfs_sb_fsid_ptr(struct btrfs_super_block *sb);
 
 #endif

index 4494883a19abc..0593f8f458a6e 100644
@@ -2391,13 +2391,11 @@ int btrfs_validate_super(struct btrfs_fs_info *fs_info,
 		ret = -EINVAL;
 	}
 
-	if (btrfs_fs_incompat(fs_info, METADATA_UUID) &&
-	    memcmp(fs_info->fs_devices->metadata_uuid,
-		   fs_info->super_copy->metadata_uuid, BTRFS_FSID_SIZE)) {
+	if (memcmp(fs_info->fs_devices->metadata_uuid, btrfs_sb_fsid_ptr(sb),
+		   BTRFS_FSID_SIZE) != 0) {
 		btrfs_err(fs_info,
 "superblock metadata_uuid doesn't match metadata uuid of fs_devices: %pU != %pU",
-			fs_info->super_copy->metadata_uuid,
-			fs_info->fs_devices->metadata_uuid);
+			  btrfs_sb_fsid_ptr(sb), fs_info->fs_devices->metadata_uuid);
 		ret = -EINVAL;
 	}
 

index 868aa4de2e4c4..cd92d7ddf5ed1 100644
@@ -348,7 +348,7 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd)
 	while (length) {
 		u32 iov_len = min_t(u32, length, sg->length - sg_offset);
 
-		bvec_set_page(iov, sg_page(sg), sg->length,
+		bvec_set_page(iov, sg_page(sg), iov_len,
 				sg->offset + sg_offset);
 
 		length -= iov_len;

index c5bb683e440c5..0187539ff5eaa 100644
@@ -70,10 +70,10 @@ MODULE_PARM_DESC(eco_mode, "Turn on Eco mode (less bright, more silent)");
 #define READ_STATUS_SIZE		13
 #define MISC_VALUE_SIZE			4
 
-#define CMD_TIMEOUT			msecs_to_jiffies(200)
-#define DATA_TIMEOUT			msecs_to_jiffies(1000)
-#define IDLE_TIMEOUT			msecs_to_jiffies(2000)
-#define FIRST_FRAME_TIMEOUT		msecs_to_jiffies(2000)
+#define CMD_TIMEOUT			200
+#define DATA_TIMEOUT			1000
+#define IDLE_TIMEOUT			2000
+#define FIRST_FRAME_TIMEOUT		2000
 
 #define MISC_REQ_GET_SET_ECO_A		0xff
 #define MISC_REQ_GET_SET_ECO_B		0x35

@@ -389,7 +389,7 @@ static void gm12u320_fb_update_work(struct work_struct *work)
 	 * switches back to showing its logo.
 	 */
 	queue_delayed_work(system_long_wq, &gm12u320->fb_update.work,
-			   IDLE_TIMEOUT);
+			   msecs_to_jiffies(IDLE_TIMEOUT));
 
 	return;
 err:

index f060e593685de..a7a364760b800 100644
@@ -116,7 +116,7 @@ qla2x00_dfs_create_rport(scsi_qla_host_t *vha, struct fc_port *fp)
 
 	sprintf(wwn, "pn-%016llx", wwn_to_u64(fp->port_name));
 	fp->dfs_rport_dir = debugfs_create_dir(wwn, vha->dfs_rport_root);
-	if (!fp->dfs_rport_dir)
+	if (IS_ERR(fp->dfs_rport_dir))
 		return;
 	if (NVME_TARGET(vha->hw, fp))
 		debugfs_create_file("dev_loss_tmo", 0600, fp->dfs_rport_dir,

@@ -708,14 +708,14 @@ qla2x00_dfs_setup(scsi_qla_host_t *vha)
 	if (IS_QLA27XX(ha) || IS_QLA83XX(ha) || IS_QLA28XX(ha)) {
 		ha->tgt.dfs_naqp = debugfs_create_file("naqp",
 		    0400, ha->dfs_dir, vha, &dfs_naqp_ops);
-		if (!ha->tgt.dfs_naqp) {
+		if (IS_ERR(ha->tgt.dfs_naqp)) {
 			ql_log(ql_log_warn, vha, 0xd011,
 			       "Unable to create debugFS naqp node.\n");
 			goto out;
 		}
 	}
 	vha->dfs_rport_root = debugfs_create_dir("rports", ha->dfs_dir);
-	if (!vha->dfs_rport_root) {
+	if (IS_ERR(vha->dfs_rport_root)) {
 		ql_log(ql_log_warn, vha, 0xd012,
 		       "Unable to create debugFS rports node.\n");
 		goto out;

index 2a4a3d3039fae..fba2809cd384a 100644
@@ -798,14 +798,14 @@ void mddev_unlock(struct mddev *mddev)
 	} else
 		mutex_unlock(&mddev->reconfig_mutex);
 
+	md_wakeup_thread(mddev->thread);
+	wake_up(&mddev->sb_wait);
+
 	list_for_each_entry_safe(rdev, tmp, &delete, same_set) {
 		list_del_init(&rdev->same_set);
 		kobject_del(&rdev->kobj);
 		export_rdev(rdev, mddev);
 	}
-
-	md_wakeup_thread(mddev->thread);
-	wake_up(&mddev->sb_wait);
 }
 EXPORT_SYMBOL_GPL(mddev_unlock);
 

index fba2809cd384a..06a8ccdb5135d 100644
@@ -2452,7 +2452,8 @@ static void export_rdev(struct md_rdev *rdev, struct mddev *mddev)
 	if (test_bit(AutoDetected, &rdev->flags))
 		md_autodetect_dev(rdev->bdev->bd_dev);
 #endif
-	blkdev_put(rdev->bdev, mddev->external ? &claim_rdev : rdev);
+	blkdev_put(rdev->bdev,
+		   test_bit(Holder, &rdev->flags) ? rdev : &claim_rdev);
 	rdev->bdev = NULL;
 	kobject_put(&rdev->kobj);
 }

@@ -3632,6 +3633,7 @@ EXPORT_SYMBOL_GPL(md_rdev_init);
 static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor)
 {
 	struct md_rdev *rdev;
+	struct md_rdev *holder;
 	sector_t size;
 	int err;
 

@@ -3646,8 +3648,15 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 	if (err)
 		goto out_clear_rdev;
 
+	if (super_format == -2) {
+		holder = &claim_rdev;
+	} else {
+		holder = rdev;
+		set_bit(Holder, &rdev->flags);
+	}
+
 	rdev->bdev = blkdev_get_by_dev(newdev, BLK_OPEN_READ | BLK_OPEN_WRITE,
-			super_format == -2 ? &claim_rdev : rdev, NULL);
+				       holder, NULL);
 	if (IS_ERR(rdev->bdev)) {
 		pr_warn("md: could not open device unknown-block(%u,%u).\n",
 			MAJOR(newdev), MINOR(newdev));

@@ -3684,7 +3693,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 	return rdev;
 
 out_blkdev_put:
-	blkdev_put(rdev->bdev, super_format == -2 ? &claim_rdev : rdev);
+	blkdev_put(rdev->bdev, holder);
 out_clear_rdev:
 	md_rdev_clear(rdev);
 out_free_rdev:

index 1aef86bf3fc31..b0a0f5a5c7836 100644
@@ -211,6 +211,9 @@ enum flag_bits {
 				 * check if there is collision between raid1
 				 * serial bios.
 				 */
+	Holder,			/* rdev is used as holder while opening
+				 * underlying disk exclusively.
+				 */
 };
 
 static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,

index e028fafa04f38..996271473609a 100644
@@ -32,10 +32,16 @@ static int efivarfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	u64 storage_space, remaining_space, max_variable_size;
 	efi_status_t status;
 
-	status = efivar_query_variable_info(attr, &storage_space, &remaining_space,
-					    &max_variable_size);
-	if (status != EFI_SUCCESS)
-		return efi_status_to_err(status);
+	/* Some UEFI firmware does not implement QueryVariableInfo() */
+	storage_space = remaining_space = 0;
+	if (efi_rt_services_supported(EFI_RT_SUPPORTED_QUERY_VARIABLE_INFO)) {
+		status = efivar_query_variable_info(attr, &storage_space,
+						    &remaining_space,
+						    &max_variable_size);
+		if (status != EFI_SUCCESS && status != EFI_UNSUPPORTED)
+			pr_warn_ratelimited("query_variable_info() failed: 0x%lx\n",
+					    status);
+	}
 
 	/*
 	 * This is not a normal filesystem, so no point in pretending it has a block

index 2b4a946a6ff5c..8d35b9f9aaa3f 100644
@@ -786,9 +786,9 @@ int hibernate(void)
 	unlock_device_hotplug();
 	if (snapshot_test) {
 		pm_pr_dbg("Checking hibernation image\n");
-		error = swsusp_check(snapshot_test);
+		error = swsusp_check(false);
 		if (!error)
-			error = load_image_and_restore(snapshot_test);
+			error = load_image_and_restore(false);
 	}
 	thaw_processes();
 

@@ -945,14 +945,14 @@ static int software_resume(void)
 	pm_pr_dbg("Looking for hibernation image.\n");
 
 	mutex_lock(&system_transition_mutex);
-	error = swsusp_check(false);
+	error = swsusp_check(true);
 	if (error)
 		goto Unlock;
 
 	/* The snapshot device should not be opened while we're running */
 	if (!hibernate_acquire()) {
 		error = -EBUSY;
-		swsusp_close(false);
+		swsusp_close(true);
 		goto Unlock;
 	}
 

@@ -973,7 +973,7 @@ static int software_resume(void)
 		goto Close_Finish;
 	}
 
-	error = load_image_and_restore(false);
+	error = load_image_and_restore(true);
 	thaw_processes();
  Finish:
 	pm_notifier_call_chain(PM_POST_RESTORE);

@@ -987,7 +987,7 @@ static int software_resume(void)
 	pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
 	return error;
  Close_Finish:
-	swsusp_close(false);
+	swsusp_close(true);
 	goto Finish;
 }
 

index 97a3de7892d3f..5ff49fd67732e 100644
@@ -8,6 +8,14 @@
 #undef notrace
 #define notrace __attribute__((no_instrument_function))
 
+#ifdef CONFIG_64BIT
+/*
+ * The generic version tends to create spurious ENDBR instructions under
+ * certain conditions.
+ */
+#define _THIS_IP_ ({ unsigned long __here; asm ("lea 0(%%rip), %0" : "=r" (__here)); __here; })
+#endif
+
 #ifdef CONFIG_X86_32
 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
 #endif /* CONFIG_X86_32 */

index cda1f706eaeb1..aa0b3ffea9353 100644
@@ -2,7 +2,12 @@
 #ifndef _LINUX_INSTRUCTION_POINTER_H
 #define _LINUX_INSTRUCTION_POINTER_H
 
+#include <asm/linkage.h>
+
 #define _RET_IP_		(unsigned long)__builtin_return_address(0)
+
+#ifndef _THIS_IP_
 #define _THIS_IP_  ({ __label__ __here; __here: (unsigned long)&&__here; })
+#endif
 
 #endif /* _LINUX_INSTRUCTION_POINTER_H */

index c08bb5c3b3857..b3b96ff46d193 100644
@@ -98,7 +98,13 @@ static int elf_find_pbase(struct kimage *image, unsigned long kernel_len,
 	kbuf.image = image;
 	kbuf.buf_min = lowest_paddr;
 	kbuf.buf_max = ULONG_MAX;
-	kbuf.buf_align = PAGE_SIZE;
+
+	/*
+	 * Current riscv boot protocol requires 2MB alignment for
+	 * RV64 and 4MB alignment for RV32
+	 *
+	 */
+	kbuf.buf_align = PMD_SIZE;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE);
 	kbuf.top_down = false;

index 7d82f0bd449c7..747b83a373a2d 100644
@@ -587,7 +587,6 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 }
 
 
-#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_CLUSTER) || defined(CONFIG_SCHED_MC)
 static inline int x86_sched_itmt_flags(void)
 {
 	return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;

@@ -611,7 +610,14 @@ static int x86_cluster_flags(void)
 	return cpu_cluster_flags() | x86_sched_itmt_flags();
 }
 #endif
-#endif
+
+static int x86_die_flags(void)
+{
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+	       return x86_sched_itmt_flags();
+
+	return 0;
+}
 
 /*
  * Set if a package/die has multiple NUMA nodes inside.

@@ -653,7 +659,7 @@ static void __init build_sched_topology(void)
 	 */
 	if (!x86_has_numa_in_package) {
 		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, SD_INIT_NAME(DIE)
+			cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(DIE)
 		};
 	}
 

index 687adc9e086ca..0686882bcbda3 100644
@@ -264,6 +264,7 @@ void target_free_cmd_counter(struct target_cmd_counter *cmd_cnt)
 		percpu_ref_put(&cmd_cnt->refcnt);
 
 	percpu_ref_exit(&cmd_cnt->refcnt);
+	kfree(cmd_cnt);
 }
 EXPORT_SYMBOL_GPL(target_free_cmd_counter);
 

index 7f9b221e7c34a..ea9b42225e629 100644
@@ -6073,7 +6073,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 					    phba->hba_debugfs_root,
 					    phba,
 					    &lpfc_debugfs_op_multixripools);
-		if (!phba->debug_multixri_pools) {
+		if (IS_ERR(phba->debug_multixri_pools)) {
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
 					 "0527 Cannot create debugfs multixripools\n");
 			goto debug_failed;

@@ -6085,7 +6085,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 			debugfs_create_file(name, S_IFREG | 0644,
 					    phba->hba_debugfs_root,
 					    phba, &lpfc_cgn_buffer_op);
-		if (!phba->debug_cgn_buffer) {
+		if (IS_ERR(phba->debug_cgn_buffer)) {
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
 					 "6527 Cannot create debugfs "
 					 "cgn_buffer\n");

@@ -6098,7 +6098,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 			debugfs_create_file(name, S_IFREG | 0644,
 					    phba->hba_debugfs_root,
 					    phba, &lpfc_rx_monitor_op);
-		if (!phba->debug_rx_monitor) {
+		if (IS_ERR(phba->debug_rx_monitor)) {
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
 					 "6528 Cannot create debugfs "
 					 "rx_monitor\n");

@@ -6111,7 +6111,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 			debugfs_create_file(name, 0644,
 					    phba->hba_debugfs_root,
 					    phba, &lpfc_debugfs_ras_log);
-		if (!phba->debug_ras_log) {
+		if (IS_ERR(phba->debug_ras_log)) {
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
 					 "6148 Cannot create debugfs"
 					 " ras_log\n");

@@ -6132,7 +6132,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 			debugfs_create_file(name, S_IFREG | 0644,
 					    phba->hba_debugfs_root,
 					    phba, &lpfc_debugfs_op_lockstat);
-		if (!phba->debug_lockstat) {
+		if (IS_ERR(phba->debug_lockstat)) {
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
 					 "4610 Can't create debugfs lockstat\n");
 			goto debug_failed;

@@ -6358,7 +6358,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 		debugfs_create_file(name, 0644,
 				    vport->vport_debugfs_root,
 				    vport, &lpfc_debugfs_op_scsistat);
-	if (!vport->debug_scsistat) {
+	if (IS_ERR(vport->debug_scsistat)) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
 				 "4611 Cannot create debugfs scsistat\n");
 		goto debug_failed;

@@ -6369,7 +6369,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 		debugfs_create_file(name, 0644,
 				    vport->vport_debugfs_root,
 				    vport, &lpfc_debugfs_op_ioktime);
-	if (!vport->debug_ioktime) {
+	if (IS_ERR(vport->debug_ioktime)) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
 				 "0815 Cannot create debugfs ioktime\n");
 		goto debug_failed;

index 10effe40a3fa6..ea1c5fcb2d191 100644
@@ -697,6 +697,7 @@ void warn_slowpath_fmt(const char *file, int line, unsigned taint,
 	if (!fmt) {
 		__warn(file, line, __builtin_return_address(0), taint,
 		       NULL, NULL);
+		warn_rcu_exit(rcu);
 		return;
 	}
 

index 04db0f2c683a7..c7a29c3ac6701 100644
@@ -1586,13 +1586,11 @@ static unsigned ata_exec_internal_sg(struct ata_device *dev,
 		}
 	}
 
-	if (ap->ops->error_handler)
-		ata_eh_release(ap);
+	ata_eh_release(ap);
 
 	rc = wait_for_completion_timeout(&wait, msecs_to_jiffies(timeout));
 
-	if (ap->ops->error_handler)
-		ata_eh_acquire(ap);
+	ata_eh_acquire(ap);
 
 	ata_sff_flush_pio_task(ap);
 

@@ -1607,10 +1605,7 @@ static unsigned ata_exec_internal_sg(struct ata_device *dev,
 		if (qc->flags & ATA_QCFLAG_ACTIVE) {
 			qc->err_mask |= AC_ERR_TIMEOUT;
 
-			if (ap->ops->error_handler)
-				ata_port_freeze(ap);
-			else
-				ata_qc_complete(qc);
+			ata_port_freeze(ap);
 
 			ata_dev_warn(dev, "qc timeout after %u msecs (cmd 0x%x)\n",
 				     timeout, command);

@@ -4874,126 +4869,103 @@ static void ata_verify_xfer(struct ata_queued_cmd *qc)
 void ata_qc_complete(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
+	struct ata_device *dev = qc->dev;
+	struct ata_eh_info *ehi = &dev->link->eh_info;
 
 	/* Trigger the LED (if available) */
 	ledtrig_disk_activity(!!(qc->tf.flags & ATA_TFLAG_WRITE));
 
-	/* XXX: New EH and old EH use different mechanisms to
-	 * synchronize EH with regular execution path.
-	 *
-	 * In new EH, a qc owned by EH is marked with ATA_QCFLAG_EH.
-	 * Normal execution path is responsible for not accessing a
-	 * qc owned by EH.  libata core enforces the rule by returning NULL
-	 * from ata_qc_from_tag() for qcs owned by EH.
+	/*
+	 * In order to synchronize EH with the regular execution path, a qc that
+	 * is owned by EH is marked with ATA_QCFLAG_EH.
 	 *
-	 * Old EH depends on ata_qc_complete() nullifying completion
-	 * requests if ATA_QCFLAG_EH_SCHEDULED is set.  Old EH does
-	 * not synchronize with interrupt handler.  Only PIO task is
-	 * taken care of.
+	 * The normal execution path is responsible for not accessing a qc owned
+	 * by EH.  libata core enforces the rule by returning NULL from
+	 * ata_qc_from_tag() for qcs owned by EH.
 	 */
-	if (ap->ops->error_handler) {
-		struct ata_device *dev = qc->dev;
-		struct ata_eh_info *ehi = &dev->link->eh_info;
-
-		if (unlikely(qc->err_mask))
-			qc->flags |= ATA_QCFLAG_EH;
+	if (unlikely(qc->err_mask))
+		qc->flags |= ATA_QCFLAG_EH;
 
-		/*
-		 * Finish internal commands without any further processing
-		 * and always with the result TF filled.
-		 */
-		if (unlikely(ata_tag_internal(qc->tag))) {
-			fill_result_tf(qc);
-			trace_ata_qc_complete_internal(qc);
-			__ata_qc_complete(qc);
-			return;
-		}
+	/*
+	 * Finish internal commands without any further processing and always
+	 * with the result TF filled.
+	 */
+	if (unlikely(ata_tag_internal(qc->tag))) {
+		fill_result_tf(qc);
+		trace_ata_qc_complete_internal(qc);
+		__ata_qc_complete(qc);
+		return;
+	}
 
-		/*
-		 * Non-internal qc has failed.  Fill the result TF and
-		 * summon EH.
-		 */
-		if (unlikely(qc->flags & ATA_QCFLAG_EH)) {
-			fill_result_tf(qc);
-			trace_ata_qc_complete_failed(qc);
-			ata_qc_schedule_eh(qc);
-			return;
-		}
+	/* Non-internal qc has failed.  Fill the result TF and summon EH. */
+	if (unlikely(qc->flags & ATA_QCFLAG_EH)) {
+		fill_result_tf(qc);
+		trace_ata_qc_complete_failed(qc);
+		ata_qc_schedule_eh(qc);
+		return;
+	}
 
-		WARN_ON_ONCE(ata_port_is_frozen(ap));
+	WARN_ON_ONCE(ata_port_is_frozen(ap));
 
-		/* read result TF if requested */
-		if (qc->flags & ATA_QCFLAG_RESULT_TF)
-			fill_result_tf(qc);
+	/* read result TF if requested */
+	if (qc->flags & ATA_QCFLAG_RESULT_TF)
+		fill_result_tf(qc);
 
-		trace_ata_qc_complete_done(qc);
+	trace_ata_qc_complete_done(qc);
 
+	/*
+	 * For CDL commands that completed without an error, check if we have
+	 * sense data (ATA_SENSE is set). If we do, then the command may have
+	 * been aborted by the device due to a limit timeout using the policy
+	 * 0xD. For these commands, invoke EH to get the command sense data.
+	 */
+	if (qc->result_tf.status & ATA_SENSE &&
+	    ((ata_is_ncq(qc->tf.protocol) &&
+	      dev->flags & ATA_DFLAG_CDL_ENABLED) ||
+	     (!ata_is_ncq(qc->tf.protocol) &&
+	      ata_id_sense_reporting_enabled(dev->id)))) {
 		/*
-		 * For CDL commands that completed without an error, check if
-		 * we have sense data (ATA_SENSE is set). If we do, then the
-		 * command may have been aborted by the device due to a limit
-		 * timeout using the policy 0xD. For these commands, invoke EH
-		 * to get the command sense data.
+		 * Tell SCSI EH to not overwrite scmd->result even if this
+		 * command is finished with result SAM_STAT_GOOD.
 		 */
-		if (qc->result_tf.status & ATA_SENSE &&
-		    ((ata_is_ncq(qc->tf.protocol) &&
-		      dev->flags & ATA_DFLAG_CDL_ENABLED) ||
-		     (!ata_is_ncq(qc->tf.protocol) &&
-		      ata_id_sense_reporting_enabled(dev->id)))) {
-			/*
-			 * Tell SCSI EH to not overwrite scmd->result even if
-			 * this command is finished with result SAM_STAT_GOOD.
-			 */
-			qc->scsicmd->flags |= SCMD_FORCE_EH_SUCCESS;
-			qc->flags |= ATA_QCFLAG_EH_SUCCESS_CMD;
-			ehi->dev_action[dev->devno] |= ATA_EH_GET_SUCCESS_SENSE;
-
-			/*
-			 * set pending so that ata_qc_schedule_eh() does not
-			 * trigger fast drain, and freeze the port.
-			 */
-			ap->pflags |= ATA_PFLAG_EH_PENDING;
-			ata_qc_schedule_eh(qc);
-			return;
-		}
+		qc->scsicmd->flags |= SCMD_FORCE_EH_SUCCESS;
+		qc->flags |= ATA_QCFLAG_EH_SUCCESS_CMD;
+		ehi->dev_action[dev->devno] |= ATA_EH_GET_SUCCESS_SENSE;
 
-		/* Some commands need post-processing after successful
-		 * completion.
+		/*
+		 * set pending so that ata_qc_schedule_eh() does not trigger
+		 * fast drain, and freeze the port.
 		 */
-		switch (qc->tf.command) {
-		case ATA_CMD_SET_FEATURES:
-			if (qc->tf.feature != SETFEATURES_WC_ON &&
-			    qc->tf.feature != SETFEATURES_WC_OFF &&
-			    qc->tf.feature != SETFEATURES_RA_ON &&
-			    qc->tf.feature != SETFEATURES_RA_OFF)
-				break;
-			fallthrough;
-		case ATA_CMD_INIT_DEV_PARAMS: /* CHS translation changed */
-		case ATA_CMD_SET_MULTI: /* multi_count changed */
-			/* revalidate device */
-			ehi->dev_action[dev->devno] |= ATA_EH_REVALIDATE;
-			ata_port_schedule_eh(ap);
-			break;
+		ap->pflags |= ATA_PFLAG_EH_PENDING;
+		ata_qc_schedule_eh(qc);
+		return;
+	}
 
-		case ATA_CMD_SLEEP:
-			dev->flags |= ATA_DFLAG_SLEEPING;
+	/* Some commands need post-processing after successful completion. */
+	switch (qc->tf.command) {
+	case ATA_CMD_SET_FEATURES:
+		if (qc->tf.feature != SETFEATURES_WC_ON &&
+		    qc->tf.feature != SETFEATURES_WC_OFF &&
+		    qc->tf.feature != SETFEATURES_RA_ON &&
+		    qc->tf.feature != SETFEATURES_RA_OFF)
 			break;
-		}
-
-		if (unlikely(dev->flags & ATA_DFLAG_DUBIOUS_XFER))
-			ata_verify_xfer(qc);
+		fallthrough;
+	case ATA_CMD_INIT_DEV_PARAMS: /* CHS translation changed */
+	case ATA_CMD_SET_MULTI: /* multi_count changed */
+		/* revalidate device */
+		ehi->dev_action[dev->devno] |= ATA_EH_REVALIDATE;
+		ata_port_schedule_eh(ap);
+		break;
 
-		__ata_qc_complete(qc);
-	} else {
-		if (qc->flags & ATA_QCFLAG_EH_SCHEDULED)
-			return;
+	case ATA_CMD_SLEEP:
+		dev->flags |= ATA_DFLAG_SLEEPING;
+		break;
+	}
 
-		/* read result TF if failed or requested */
-		if (qc->err_mask || qc->flags & ATA_QCFLAG_RESULT_TF)
-			fill_result_tf(qc);
+	if (unlikely(dev->flags & ATA_DFLAG_DUBIOUS_XFER))
+		ata_verify_xfer(qc);
 
-		__ata_qc_complete(qc);
-	}
+	__ata_qc_complete(qc);
 }
 EXPORT_SYMBOL_GPL(ata_qc_complete);
 

@@ -5039,11 +5011,8 @@ void ata_qc_issue(struct ata_queued_cmd *qc)
 	struct ata_link *link = qc->dev->link;
 	u8 prot = qc->tf.protocol;
 
-	/* Make sure only one non-NCQ command is outstanding.  The
-	 * check is skipped for old EH because it reuses active qc to
-	 * request ATAPI sense.
-	 */
-	WARN_ON_ONCE(ap->ops->error_handler && ata_tag_valid(link->active_tag));
+	/* Make sure only one non-NCQ command is outstanding. */
+	WARN_ON_ONCE(ata_tag_valid(link->active_tag));
 
 	if (ata_is_ncq(prot)) {
 		WARN_ON_ONCE(link->sactive & (1 << qc->hw_tag));

@@ -5917,15 +5886,9 @@ void __ata_port_probe(struct ata_port *ap)
 
 int ata_port_probe(struct ata_port *ap)
 {
-	int rc = 0;
-
-	if (ap->ops->error_handler) {
-		__ata_port_probe(ap);
-		ata_port_wait_eh(ap);
-	} else {
-		rc = ata_bus_probe(ap);
-	}
-	return rc;
+	__ata_port_probe(ap);
+	ata_port_wait_eh(ap);
+	return 0;
 }
 
 

@@ -6130,9 +6093,6 @@ static void ata_port_detach(struct ata_port *ap)
 	struct ata_link *link;
 	struct ata_device *dev;
 
-	if (!ap->ops->error_handler)
-		goto skip_eh;
-
 	/* tell EH we're leaving & flush EH */
 	spin_lock_irqsave(ap->lock, flags);
 	ap->pflags |= ATA_PFLAG_UNLOADING;

@@ -6148,7 +6108,6 @@ static void ata_port_detach(struct ata_port *ap)
 	cancel_delayed_work_sync(&ap->hotplug_task);
 	cancel_delayed_work_sync(&ap->scsi_rescan_task);
 
- skip_eh:
 	/* clean up zpodd on port removal */
 	ata_for_each_link(link, ap, HOST_FIRST) {
 		ata_for_each_dev(dev, link, ALL) {

228 lines not on this page · raw message

index 85e279a12f62c..99d4ab04bcce6 100644
@@ -1158,12 +1158,7 @@ EXPORT_SYMBOL_GPL(ata_sas_port_alloc);
  */
 int ata_sas_port_start(struct ata_port *ap)
 {
-	/*
-	 * the port is marked as frozen at allocation time, but if we don't
-	 * have new eh, we won't thaw it
-	 */
-	if (!ap->ops->error_handler)
-		ap->pflags &= ~ATA_PFLAG_FROZEN;
+	/* the port is marked as frozen at allocation time */
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ata_sas_port_start);

263 lines not on this page · raw message

index 9d28badfe41d6..84471d92cd1b9 100644
@@ -883,31 +883,21 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 {
 	struct ata_port *ap = qc->ap;
 
-	if (ap->ops->error_handler) {
-		if (in_wq) {
-			/* EH might have kicked in while host lock is
-			 * released.
-			 */
-			qc = ata_qc_from_tag(ap, qc->tag);
-			if (qc) {
-				if (likely(!(qc->err_mask & AC_ERR_HSM))) {
-					ata_sff_irq_on(ap);
-					ata_qc_complete(qc);
-				} else
-					ata_port_freeze(ap);
-			}
-		} else {
-			if (likely(!(qc->err_mask & AC_ERR_HSM)))
+	if (in_wq) {
+		/* EH might have kicked in while host lock is released. */
+		qc = ata_qc_from_tag(ap, qc->tag);
+		if (qc) {
+			if (likely(!(qc->err_mask & AC_ERR_HSM))) {
+				ata_sff_irq_on(ap);
 				ata_qc_complete(qc);
-			else
+			} else
 				ata_port_freeze(ap);
 		}
 	} else {
-		if (in_wq) {
-			ata_sff_irq_on(ap);
-			ata_qc_complete(qc);
-		} else
+		if (likely(!(qc->err_mask & AC_ERR_HSM)))
 			ata_qc_complete(qc);
+		else
+			ata_port_freeze(ap);
 	}
 }
 

index 820f7a3a2749b..3eeea76c30de4 100644
@@ -1785,7 +1785,7 @@ static inline struct ata_queued_cmd *ata_qc_from_tag(struct ata_port *ap,
 {
 	struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
 
-	if (unlikely(!qc) || !ap->ops->error_handler)
+	if (unlikely(!qc))
 		return qc;
 
 	if ((qc->flags & (ATA_QCFLAG_ACTIVE |

index 04db0f2c683a..79d02eb4e479 100644
@@ -4935,11 +4935,8 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
 		 * timeout using the policy 0xD. For these commands, invoke EH
 		 * to get the command sense data.
 		 */
-		if (qc->result_tf.status & ATA_SENSE &&
-		    ((ata_is_ncq(qc->tf.protocol) &&
-		      dev->flags & ATA_DFLAG_CDL_ENABLED) ||
-		     (!ata_is_ncq(qc->tf.protocol) &&
-		      ata_id_sense_reporting_enabled(dev->id)))) {
+		if (qc->flags & ATA_QCFLAG_HAS_CDL &&
+		    qc->result_tf.status & ATA_SENSE) {
 			/*
 			 * Tell SCSI EH to not overwrite scmd->result even if
 			 * this command is finished with result SAM_STAT_GOOD.

index c7a29c3ac6701..291e128f4d2b4 100644
@@ -4919,11 +4919,8 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
 	 * been aborted by the device due to a limit timeout using the policy
 	 * 0xD. For these commands, invoke EH to get the command sense data.
 	 */
-	if (qc->result_tf.status & ATA_SENSE &&
-	    ((ata_is_ncq(qc->tf.protocol) &&
-	      dev->flags & ATA_DFLAG_CDL_ENABLED) ||
-	     (!ata_is_ncq(qc->tf.protocol) &&
-	      ata_id_sense_reporting_enabled(dev->id)))) {
+	if (qc->flags & ATA_QCFLAG_HAS_CDL &&
+	    qc->result_tf.status & ATA_SENSE) {
 		/*
 		 * Tell SCSI EH to not overwrite scmd->result even if this
 		 * command is finished with result SAM_STAT_GOOD.

index bcc956c17872b..08f93b0401bbd 100644
@@ -59,6 +59,14 @@ static void *alloc_pgt_page(void *context)
 		return NULL;
 	}
 
+	/* Consumed more tables than expected? */
+	if (pages->pgt_buf_offset == BOOT_PGT_SIZE_WARN) {
+		debug_putstr("pgt_buf running low in " __FILE__ "\n");
+		debug_putstr("Need to raise BOOT_PGT_SIZE?\n");
+		debug_putaddr(pages->pgt_buf_offset);
+		debug_putaddr(pages->pgt_buf_size);
+	}
+
 	entry = pages->pgt_buf + pages->pgt_buf_offset;
 	pages->pgt_buf_offset += PAGE_SIZE;
 

54 lines not on this page · raw message

index 9debd128b2ab8..b99322f188e59 100644
@@ -70,7 +70,9 @@ static int __init hw_break_module_init(void)
 static void __exit hw_break_module_exit(void)
 {
 	unregister_wide_hw_breakpoint(sample_hbp);
+#ifdef CONFIG_MODULE_UNLOAD
 	__symbol_put(ksym_name);
+#endif
 	printk(KERN_INFO "HW Breakpoint for %s write uninstalled\n", ksym_name);
 }
 

@@ -4420,6 +4420,16 @@ static int blk_mq_realloc_tag_set_tags(s
 		       sizeof(*set->tags));
 	kfree(set->tags);
 	set->tags = new_tags;
+
+	for (i = set->nr_hw_queues; i < new_nr_hw_queues; i++) {
+		if (!__blk_mq_alloc_map_and_rqs(set, i)) {
+			while (--i >= set->nr_hw_queues)
+				__blk_mq_free_map_and_rqs(set, i);
+			return -ENOMEM;
+		}
+		cond_resched();
+	}
+
 done:
 	set->nr_hw_queues = new_nr_hw_queues;
 	return 0;

@@ -4404,11 +4404,8 @@ static int blk_mq_realloc_tag_set_tags(s
 	struct blk_mq_tags **new_tags;
 	int i;
 
-	if (set->nr_hw_queues >= new_nr_hw_queues) {
-		for (i = new_nr_hw_queues; i < set->nr_hw_queues; i++)
-			__blk_mq_free_map_and_rqs(set, i);
+	if (set->nr_hw_queues >= new_nr_hw_queues)
 		goto done;
-	}
 
 	new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
 				GFP_KERNEL, set->numa_node);

@@ -4718,7 +4715,8 @@ static void __blk_mq_update_nr_hw_queues
 {
 	struct request_queue *q;
 	LIST_HEAD(head);
-	int prev_nr_hw_queues;
+	int prev_nr_hw_queues = set->nr_hw_queues;
+	int i;
 
 	lockdep_assert_held(&set->tag_list_lock);
 

@@ -4745,7 +4743,6 @@ static void __blk_mq_update_nr_hw_queues
 		blk_mq_sysfs_unregister_hctxs(q);
 	}
 
-	prev_nr_hw_queues = set->nr_hw_queues;
 	if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0)
 		goto reregister;
 

@@ -4781,6 +4778,10 @@ switch_back:
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_unfreeze_queue(q);
+
+	/* Free the excess tags when nr_hw_queues shrink. */
+	for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++)
+		__blk_mq_free_map_and_rqs(set, i);
 }
 
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)

index 80aeee63dfb78..a60acd72210aa 100644
@@ -1829,12 +1829,11 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	struct r1conf *conf = mddev->private;
 	int err = 0;
 	int number = rdev->raid_disk;
+	struct raid1_info *p = conf->mirrors + number;
 
 	if (unlikely(number >= conf->raid_disks))
 		goto abort;
 
-	struct raid1_info *p = conf->mirrors + number;
-
 	if (rdev != p->rdev)
 		p = conf->mirrors + conf->raid_disks + number;
 

@@ -2722,7 +2722,7 @@ out_unparsable:
 
 out_verifier:
 	trace_rpc_bad_verifier(task);
-	goto out_err;
+	goto out_garbage;
 
 out_msg_denied:
 	error = -EACCES;

@@ -394,9 +394,25 @@ int notify_change(struct mnt_idmap *idma
 		return error;
 
 	if ((ia_valid & ATTR_MODE)) {
-		umode_t amode = attr->ia_mode;
+		/*
+		 * Don't allow changing the mode of symlinks:
+		 *
+		 * (1) The vfs doesn't take the mode of symlinks into account
+		 *     during permission checking.
+		 * (2) This has never worked correctly. Most major filesystems
+		 *     did return EOPNOTSUPP due to interactions with POSIX ACLs
+		 *     but did still updated the mode of the symlink.
+		 *     This inconsistency led system call wrapper providers such
+		 *     as libc to block changing the mode of symlinks with
+		 *     EOPNOTSUPP already.
+		 * (3) To even do this in the first place one would have to use
+		 *     specific file descriptors and quite some effort.
+		 */
+		if (S_ISLNK(inode->i_mode))
+			return -EOPNOTSUPP;
+
 		/* Flag setting protected by i_mutex */
-		if (is_sxid(amode))
+		if (is_sxid(attr->ia_mode))
 			inode->i_flags &= ~S_NOSEC;
 	}
 

@@ -617,7 +617,8 @@ static int ovl_copy_up_metadata(struct o
 	if (err)
 		return err;
 
-	if (inode->i_flags & OVL_COPY_I_FLAGS_MASK) {
+	if (inode->i_flags & OVL_COPY_I_FLAGS_MASK &&
+	    (S_ISREG(c->stat.mode) || S_ISDIR(c->stat.mode))) {
 		/*
 		 * Copy the fileattr inode flags that are the source of already
 		 * copied i_flags

@@ -19,7 +19,6 @@ struct ovl_aio_req {
 	struct kiocb iocb;
 	refcount_t ref;
 	struct kiocb *orig_iocb;
-	struct fd fd;
 };
 
 static struct kmem_cache *ovl_aio_request_cachep;

@@ -277,7 +276,7 @@ static rwf_t ovl_iocb_to_rwf(int ifl)
 static inline void ovl_aio_put(struct ovl_aio_req *aio_req)
 {
 	if (refcount_dec_and_test(&aio_req->ref)) {
-		fdput(aio_req->fd);
+		fput(aio_req->iocb.ki_filp);
 		kmem_cache_free(ovl_aio_request_cachep, aio_req);
 	}
 }

@@ -342,10 +341,9 @@ static ssize_t ovl_read_iter(struct kioc
 		if (!aio_req)
 			goto out;
 
-		aio_req->fd = real;
 		real.flags = 0;
 		aio_req->orig_iocb = iocb;
-		kiocb_clone(&aio_req->iocb, iocb, real.file);
+		kiocb_clone(&aio_req->iocb, iocb, get_file(real.file));
 		aio_req->iocb.ki_complete = ovl_aio_rw_complete;
 		refcount_set(&aio_req->ref, 2);
 		ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter);

@@ -413,10 +411,9 @@ static ssize_t ovl_write_iter(struct kio
 		/* Pacify lockdep, same trick as done in aio_write() */
 		__sb_writers_release(file_inode(real.file)->i_sb,
 				     SB_FREEZE_WRITE);
-		aio_req->fd = real;
 		real.flags = 0;
 		aio_req->orig_iocb = iocb;
-		kiocb_clone(&aio_req->iocb, iocb, real.file);
+		kiocb_clone(&aio_req->iocb, iocb, get_file(real.file));
 		aio_req->iocb.ki_flags = ifl;
 		aio_req->iocb.ki_complete = ovl_aio_rw_complete;
 		refcount_set(&aio_req->ref, 2);

@@ -183,6 +183,10 @@ static int io_setup_async_msg(struct io_
 	memcpy(async_msg, kmsg, sizeof(*kmsg));
 	if (async_msg->msg.msg_name)
 		async_msg->msg.msg_name = &async_msg->addr;
+
+	if ((req->flags & REQ_F_BUFFER_SELECT) && !async_msg->msg.msg_iter.nr_segs)
+		return -EAGAIN;
+
 	/* if were using fast_iov, set it to the new one */
 	if (iter_is_iovec(&kmsg->msg.msg_iter) && !kmsg->free_iov) {
 		size_t fast_idx = iter_iov(&kmsg->msg.msg_iter) - kmsg->fast_iov;

@@ -542,6 +546,7 @@ static int io_recvmsg_copy_hdr(struct io
 			       struct io_async_msghdr *iomsg)
 {
 	iomsg->msg.msg_name = &iomsg->addr;
+	iomsg->msg.msg_iter.nr_segs = 0;
 
 #ifdef CONFIG_COMPAT
 	if (req->ctx->compat)

@@ -2245,25 +2245,8 @@ int nvme_enable_ctrl(struct nvme_ctrl *c
 	else
 		ctrl->ctrl_config = NVME_CC_CSS_NVM;
 
-	if (ctrl->cap & NVME_CAP_CRMS_CRWMS) {
-		u32 crto;
-
-		ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto);
-		if (ret) {
-			dev_err(ctrl->device, "Reading CRTO failed (%d)\n",
-				ret);
-			return ret;
-		}
-
-		if (ctrl->cap & NVME_CAP_CRMS_CRIMS) {
-			ctrl->ctrl_config |= NVME_CC_CRIME;
-			timeout = NVME_CRTO_CRIMT(crto);
-		} else {
-			timeout = NVME_CRTO_CRWMT(crto);
-		}
-	} else {
-		timeout = NVME_CAP_TIMEOUT(ctrl->cap);
-	}
+	if (ctrl->cap & NVME_CAP_CRMS_CRWMS && ctrl->cap & NVME_CAP_CRMS_CRIMS)
+		ctrl->ctrl_config |= NVME_CC_CRIME;
 
 	ctrl->ctrl_config |= (NVME_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT;
 	ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;

@@ -2277,6 +2260,39 @@ int nvme_enable_ctrl(struct nvme_ctrl *c
 	if (ret)
 		return ret;
 
+	/* CAP value may change after initial CC write */
+	ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap);
+	if (ret)
+		return ret;
+
+	timeout = NVME_CAP_TIMEOUT(ctrl->cap);
+	if (ctrl->cap & NVME_CAP_CRMS_CRWMS) {
+		u32 crto, ready_timeout;
+
+		ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto);
+		if (ret) {
+			dev_err(ctrl->device, "Reading CRTO failed (%d)\n",
+				ret);
+			return ret;
+		}
+
+		/*
+		 * CRTO should always be greater or equal to CAP.TO, but some
+		 * devices are known to get this wrong. Use the larger of the
+		 * two values.
+		 */
+		if (ctrl->ctrl_config & NVME_CC_CRIME)
+			ready_timeout = NVME_CRTO_CRIMT(crto);
+		else
+			ready_timeout = NVME_CRTO_CRWMT(crto);
+
+		if (ready_timeout < timeout)
+			dev_warn_once(ctrl->device, "bad crto:%x cap:%llx\n",
+				      crto, ctrl->cap);
+		else
+			timeout = ready_timeout;
+	}
+
 	ctrl->ctrl_config |= NVME_CC_ENABLE;
 	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
 	if (ret)