Merge tag 'fix-scrub-reap-calculations_2025-09-05' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-6.18-merge

xfs: improve online repair reap calculations [6.18 v2 1/2]

A few months ago, the multi-fsblock untorn writes patchset added a bunch
of log intent item helper functions to estimate the number of intent
items that could be added to a particular transaction.  Those helpers
enabled us to compute a safe upper bound on the number of blocks that
could be written in an untorn fashion with filesystem-provided out of
place writes.

Currently, the online fsck code employs static limits on the number of
intent items that it's willing to accrue to a single transaction when
it's trying to reap what it thinks are the old blocks from a corrupt
structure.  There have been no problems reported with this approach
after years of testing, but static limits are scary and gross because
overestimating the intent item limit could result in transaction
overflows and dead filesystems; and underestimating causes unnecessary
overhead.

This series uses the new log intent item size helpers to estimate the
limits dynamically based on worst-case per-block repair work vs. the
size of the scrub transaction.  After several months of testing this,
there don't seem to be any problems here either.

v2: rearrange patches, add review tags

This has been running on the djcloud for months with no problems.  Enjoy!

Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>

19 files changed, 66 insertions, 79 deletions

diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 45f2f278b50a..70807c679f1a 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -185,6 +185,7 @@ struct atmdev_ops { /* only send is required */
 	int (*compat_ioctl)(struct atm_dev *dev,unsigned int cmd,
 			    void __user *arg);
 #endif
+	int (*pre_send)(struct atm_vcc *vcc, struct sk_buff *skb);
 	int (*send)(struct atm_vcc *vcc,struct sk_buff *skb);
 	int (*send_bh)(struct atm_vcc *vcc, struct sk_buff *skb);
 	int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 95886b404b16..fe1797bbec42 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -656,6 +656,7 @@ enum {
 	QUEUE_FLAG_SQ_SCHED,		/* single queue style io dispatch */
 	QUEUE_FLAG_DISABLE_WBT_DEF,	/* for sched to disable/enable wbt */
 	QUEUE_FLAG_NO_ELV_SWITCH,	/* can't switch elevator any more */
+	QUEUE_FLAG_QOS_ENABLED,		/* qos is enabled */
 	QUEUE_FLAG_MAX
 };
 
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 6f04a1d8c720..64ff73c533e5 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -288,14 +288,6 @@ static inline void *offset_to_ptr(const int *off)
 #define __ADDRESSABLE(sym) \
 	___ADDRESSABLE(sym, __section(".discard.addressable"))
 
-#define __ADDRESSABLE_ASM(sym)						\
-	.pushsection .discard.addressable,"aw";				\
-	.align ARCH_SEL(8,4);						\
-	ARCH_SEL(.quad, .long) __stringify(sym);			\
-	.popsection;
-
-#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym))
-
 /*
  * This returns a constant expression while determining if an argument is
  * a constant expression, most importantly without evaluating the argument.
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index edfa61d80702..62cd7b35a29c 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -168,6 +168,7 @@ enum cpuhp_state {
 	CPUHP_AP_QCOM_TIMER_STARTING,
 	CPUHP_AP_TEGRA_TIMER_STARTING,
 	CPUHP_AP_ARMADA_TIMER_STARTING,
+	CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING,
 	CPUHP_AP_MIPS_GIC_TIMER_STARTING,
 	CPUHP_AP_ARC_TIMER_STARTING,
 	CPUHP_AP_REALTEK_TIMER_STARTING,
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index f48e5fb88bd5..332b80c42b6f 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -153,6 +153,9 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page,
 {
 	__free_pages(page, get_order(size));
 }
+static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+}
 #endif /* CONFIG_DMA_CMA*/
 
 #ifdef CONFIG_DMA_DECLARE_COHERENT
diff --git a/include/linux/export.h b/include/linux/export.h
index f35d03b4113b..a686fd0ba406 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -91,6 +91,6 @@
 #define EXPORT_SYMBOL_NS(sym, ns)	__EXPORT_SYMBOL(sym, "", ns)
 #define EXPORT_SYMBOL_NS_GPL(sym, ns)	__EXPORT_SYMBOL(sym, "GPL", ns)
 
-#define EXPORT_SYMBOL_GPL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods)
+#define EXPORT_SYMBOL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods)
 
 #endif /* _LINUX_EXPORT_H */
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index cceb70415ed2..d38c6e538e5c 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -341,7 +341,11 @@ struct fw_address_handler {
 	u64 length;
 	fw_address_callback_t address_callback;
 	void *callback_data;
+
+	// Only for core functions.
 	struct list_head link;
+	struct kref kref;
+	struct completion done;
 };
 
 struct fw_address_region {
diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h
index 4696abfd311c..3e85afe794c0 100644
--- a/include/linux/iosys-map.h
+++ b/include/linux/iosys-map.h
@@ -264,12 +264,7 @@ static inline bool iosys_map_is_set(const struct iosys_map *map)
  */
 static inline void iosys_map_clear(struct iosys_map *map)
 {
-	if (map->is_iomem) {
-		map->vaddr_iomem = NULL;
-		map->is_iomem = false;
-	} else {
-		map->vaddr = NULL;
-	}
+	memset(map, 0, sizeof(*map));
 }
 
 /**
diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h
index c4aa58032faf..f9a17fbbd398 100644
--- a/include/linux/iov_iter.h
+++ b/include/linux/iov_iter.h
@@ -160,7 +160,7 @@ size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2
 
 	do {
 		struct folio *folio = folioq_folio(folioq, slot);
-		size_t part, remain, consumed;
+		size_t part, remain = 0, consumed;
 		size_t fsize;
 		void *base;
 
@@ -168,14 +168,16 @@ size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2
 			break;
 
 		fsize = folioq_folio_size(folioq, slot);
-		base = kmap_local_folio(folio, skip);
-		part = umin(len, PAGE_SIZE - skip % PAGE_SIZE);
-		remain = step(base, progress, part, priv, priv2);
-		kunmap_local(base);
-		consumed = part - remain;
-		len -= consumed;
-		progress += consumed;
-		skip += consumed;
+		if (skip < fsize) {
+			base = kmap_local_folio(folio, skip);
+			part = umin(len, PAGE_SIZE - skip % PAGE_SIZE);
+			remain = step(base, progress, part, priv, priv2);
+			kunmap_local(base);
+			consumed = part - remain;
+			len -= consumed;
+			progress += consumed;
+			skip += consumed;
+		}
 		if (skip >= fsize) {
 			skip = 0;
 			slot++;
diff --git a/include/linux/kcov.h b/include/linux/kcov.h
index 75a2fb8b16c3..0143358874b0 100644
--- a/include/linux/kcov.h
+++ b/include/linux/kcov.h
@@ -57,47 +57,21 @@ static inline void kcov_remote_start_usb(u64 id)
 
 /*
  * The softirq flavor of kcov_remote_*() functions is introduced as a temporary
- * workaround for KCOV's lack of nested remote coverage sections support.
- *
- * Adding support is tracked in https://bugzilla.kernel.org/show_bug.cgi?id=210337.
- *
- * kcov_remote_start_usb_softirq():
- *
- * 1. Only collects coverage when called in the softirq context. This allows
- *    avoiding nested remote coverage collection sections in the task context.
- *    For example, USB/IP calls usb_hcd_giveback_urb() in the task context
- *    within an existing remote coverage collection section. Thus, KCOV should
- *    not attempt to start collecting coverage within the coverage collection
- *    section in __usb_hcd_giveback_urb() in this case.
- *
- * 2. Disables interrupts for the duration of the coverage collection section.
- *    This allows avoiding nested remote coverage collection sections in the
- *    softirq context (a softirq might occur during the execution of a work in
- *    the BH workqueue, which runs with in_serving_softirq() > 0).
- *    For example, usb_giveback_urb_bh() runs in the BH workqueue with
- *    interrupts enabled, so __usb_hcd_giveback_urb() might be interrupted in
- *    the middle of its remote coverage collection section, and the interrupt
- *    handler might invoke __usb_hcd_giveback_urb() again.
+ * work around for kcov's lack of nested remote coverage sections support in
+ * task context. Adding support for nested sections is tracked in:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=210337
  */
 
-static inline unsigned long kcov_remote_start_usb_softirq(u64 id)
+static inline void kcov_remote_start_usb_softirq(u64 id)
 {
-	unsigned long flags = 0;
-
-	if (in_serving_softirq()) {
-		local_irq_save(flags);
+	if (in_serving_softirq() && !in_hardirq())
 		kcov_remote_start_usb(id);
-	}
-
-	return flags;
 }
 
-static inline void kcov_remote_stop_softirq(unsigned long flags)
+static inline void kcov_remote_stop_softirq(void)
 {
-	if (in_serving_softirq()) {
+	if (in_serving_softirq() && !in_hardirq())
 		kcov_remote_stop();
-		local_irq_restore(flags);
-	}
 }
 
 #ifdef CONFIG_64BIT
@@ -131,11 +105,8 @@ static inline u64 kcov_common_handle(void)
 }
 static inline void kcov_remote_start_common(u64 id) {}
 static inline void kcov_remote_start_usb(u64 id) {}
-static inline unsigned long kcov_remote_start_usb_softirq(u64 id)
-{
-	return 0;
-}
-static inline void kcov_remote_stop_softirq(unsigned long flags) {}
+static inline void kcov_remote_start_usb_softirq(u64 id) {}
+static inline void kcov_remote_stop_softirq(void) {}
 
 #endif /* CONFIG_KCOV */
 #endif /* _LINUX_KCOV_H */
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b96746376e17..fcda8481de9a 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -40,8 +40,9 @@ extern unsigned long long max_possible_pfn;
  * via a driver, and never indicated in the firmware-provided memory map as
  * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the
  * kernel resource tree.
- * @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are
- * not initialized (only for reserved regions).
+ * @MEMBLOCK_RSRV_NOINIT: reserved memory region for which struct pages are not
+ * fully initialized. Users of this flag are responsible to properly initialize
+ * struct pages of this region
  * @MEMBLOCK_RSRV_KERN: memory region that is reserved for kernel use,
  * either explictitly with memblock_reserve_kern() or via memblock
  * allocation APIs. All memblock allocations set this flag.
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index acadd41e0b5c..9009e27b5f44 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -79,6 +79,7 @@ void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl)
 void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
 int folio_migrate_mapping(struct address_space *mapping,
 		struct folio *newfolio, struct folio *folio, int extra_count);
+int set_movable_ops(const struct movable_operations *ops, enum pagetype type);
 
 #else
 
@@ -100,6 +101,10 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 {
 	return -ENOSYS;
 }
+static inline int set_movable_ops(const struct movable_operations *ops, enum pagetype type)
+{
+	return -ENOSYS;
+}
 
 #endif /* CONFIG_MIGRATION */
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5e5de4b0a433..f3a3b761abfb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2071,6 +2071,8 @@ enum netdev_reg_state {
  *	@max_pacing_offload_horizon: max EDT offload horizon in nsec.
  *	@napi_config: An array of napi_config structures containing per-NAPI
  *		      settings.
+ *	@num_napi_configs:	number of allocated NAPI config structs,
+ *		always >= max(num_rx_queues, num_tx_queues).
  *	@gro_flush_timeout:	timeout for GRO layer in NAPI
  *	@napi_defer_hard_irqs:	If not zero, provides a counter that would
  *				allow to avoid NIC hard IRQ, on busy queues.
@@ -2482,8 +2484,9 @@ struct net_device {
 
 	u64			max_pacing_offload_horizon;
 	struct napi_config	*napi_config;
-	unsigned long		gro_flush_timeout;
+	u32			num_napi_configs;
 	u32			napi_defer_hard_irqs;
+	unsigned long		gro_flush_timeout;
 
 	/**
 	 * @up: copy of @state's IFF_UP, but safe to read with just @lock.
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 185bd8196503..98c96d649bf9 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -150,6 +150,7 @@ struct netfs_io_stream {
 	bool			active;		/* T if stream is active */
 	bool			need_retry;	/* T if this stream needs retrying */
 	bool			failed;		/* T if this stream failed */
+	bool			transferred_valid; /* T is ->transferred is valid */
 };
 
 /*
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 169b4ae30ff4..9aed39abc94b 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -160,6 +160,7 @@ extern void nfs_join_page_group(struct nfs_page *head,
 extern int nfs_page_group_lock(struct nfs_page *);
 extern void nfs_page_group_unlock(struct nfs_page *);
 extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int);
+extern bool nfs_page_group_sync_on_bit_locked(struct nfs_page *, unsigned int);
 extern	int nfs_page_set_headlock(struct nfs_page *req);
 extern void nfs_page_clear_headlock(struct nfs_page *req);
 extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *);
diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h
index 78276a11c48d..1571e9157fa5 100644
--- a/include/linux/platform_data/x86/int3472.h
+++ b/include/linux/platform_data/x86/int3472.h
@@ -27,6 +27,7 @@
 #define INT3472_GPIO_TYPE_CLK_ENABLE				0x0c
 #define INT3472_GPIO_TYPE_PRIVACY_LED				0x0d
 #define INT3472_GPIO_TYPE_HANDSHAKE				0x12
+#define INT3472_GPIO_TYPE_HOTPLUG_DETECT			0x13
 
 #define INT3472_PDEV_MAX_NAME_LEN				23
 #define INT3472_MAX_SENSOR_GPIOS				3
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2b272382673d..f8188b833350 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2152,6 +2152,8 @@ static inline struct mutex *__get_task_blocked_on(struct task_struct *p)
 
 static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)
 {
+	struct mutex *blocked_on = READ_ONCE(p->blocked_on);
+
 	WARN_ON_ONCE(!m);
 	/* The task should only be setting itself as blocked */
 	WARN_ON_ONCE(p != current);
@@ -2162,8 +2164,8 @@ static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)
 	 * with a different mutex. Note, setting it to the same
 	 * lock repeatedly is ok.
 	 */
-	WARN_ON_ONCE(p->blocked_on && p->blocked_on != m);
-	p->blocked_on = m;
+	WARN_ON_ONCE(blocked_on && blocked_on != m);
+	WRITE_ONCE(p->blocked_on, m);
 }
 
 static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m)
@@ -2174,16 +2176,19 @@ static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m)
 
 static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m)
 {
-	WARN_ON_ONCE(!m);
-	/* Currently we serialize blocked_on under the mutex::wait_lock */
-	lockdep_assert_held_once(&m->wait_lock);
-	/*
-	 * There may be cases where we re-clear already cleared
-	 * blocked_on relationships, but make sure we are not
-	 * clearing the relationship with a different lock.
-	 */
-	WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m);
-	p->blocked_on = NULL;
+	if (m) {
+		struct mutex *blocked_on = READ_ONCE(p->blocked_on);
+
+		/* Currently we serialize blocked_on under the mutex::wait_lock */
+		lockdep_assert_held_once(&m->wait_lock);
+		/*
+		 * There may be cases where we re-clear already cleared
+		 * blocked_on relationships, but make sure we are not
+		 * clearing the relationship with a different lock.
+		 */
+		WARN_ON_ONCE(blocked_on && blocked_on != m);
+	}
+	WRITE_ONCE(p->blocked_on, NULL);
 }
 
 static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 14b923ddb6df..fa633657e4c0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4172,6 +4172,8 @@ int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset,
 				      struct iov_iter *to, int len, u32 *crcp);
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from, int len);
+int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset,
+				     struct iov_iter *from, int len);
 int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);
 void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags);
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 918cf25cd3c6..8bf156dde554 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -328,8 +328,6 @@ static inline
 bool virtio_get_shm_region(struct virtio_device *vdev,
 			   struct virtio_shm_region *region, u8 id)
 {
-	if (!region->len)
-		return false;
 	if (!vdev->config->get_shm_region)
 		return false;
 	return vdev->config->get_shm_region(vdev, region, id);