5.4.19-stable review

index f9ebdf2cfc31d..12aec140819a2 100644
@@ -440,7 +440,6 @@ static int sof_probe_continue(struct snd_sof_dev *sdev)
 
 	return 0;
 
-#if !IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE)
 fw_trace_err:
 	snd_sof_free_trace(sdev);
 fw_run_err:

@@ -451,22 +450,10 @@ static int sof_probe_continue(struct snd_sof_dev *sdev)
 	snd_sof_free_debug(sdev);
 dbg_err:
 	snd_sof_remove(sdev);
-#else
-
-	/*
-	 * when the probe_continue is handled in a work queue, the
-	 * probe does not fail so we don't release resources here.
-	 * They will be released with an explicit call to
-	 * snd_sof_device_remove() when the PCI/ACPI device is removed
-	 */
-
-fw_trace_err:
-fw_run_err:
-fw_load_err:
-ipc_err:
-dbg_err:
 
-#endif
+	/* all resources freed, update state to match */
+	sdev->fw_state = SOF_FW_BOOT_NOT_STARTED;
+	sdev->first_boot = true;
 
 	return ret;
 }

@@ -545,10 +532,12 @@ int snd_sof_device_remove(struct device *dev)
 	if (IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE))
 		cancel_work_sync(&sdev->probe_work);
 
-	snd_sof_fw_unload(sdev);
-	snd_sof_ipc_free(sdev);
-	snd_sof_free_debug(sdev);
-	snd_sof_free_trace(sdev);
+	if (sdev->fw_state > SOF_FW_BOOT_NOT_STARTED) {
+		snd_sof_fw_unload(sdev);
+		snd_sof_ipc_free(sdev);
+		snd_sof_free_debug(sdev);
+		snd_sof_free_trace(sdev);
+	}
 
 	/*
 	 * Unregister machine driver. This will unbind the snd_card which

@@ -564,7 +553,8 @@ int snd_sof_device_remove(struct device *dev)
 	 * scheduled on, when they are unloaded. Therefore, the DSP must be
 	 * removed only after the topology has been unloaded.
 	 */
-	snd_sof_remove(sdev);
+	if (sdev->fw_state > SOF_FW_BOOT_NOT_STARTED)
+		snd_sof_remove(sdev);
 
 	/* release firmware */
 	release_firmware(pdata->fw);

index e9fbac38d9238..195af259e78e3 100644
@@ -269,6 +269,10 @@ static int sof_resume(struct device *dev, bool runtime_resume)
 	if (!sof_ops(sdev)->resume || !sof_ops(sdev)->runtime_resume)
 		return 0;
 
+	/* DSP was never successfully started, nothing to resume */
+	if (sdev->first_boot)
+		return 0;
+
 	/*
 	 * if the runtime_resume flag is set, call the runtime_resume routine
 	 * or else call the system resume routine

index 0708a41cfe2de..b38c6af10da5b 100644
@@ -5102,7 +5102,7 @@ static const struct file_operations ftrace_notrace_fops = {
 
 static DEFINE_MUTEX(graph_lock);
 
-struct ftrace_hash *ftrace_graph_hash = EMPTY_HASH;
+struct ftrace_hash __rcu *ftrace_graph_hash = EMPTY_HASH;
 struct ftrace_hash *ftrace_graph_notrace_hash = EMPTY_HASH;
 
 enum graph_filter_type {

index d685c61085c0d..f8fb3786af72a 100644
@@ -932,22 +932,25 @@ extern void __trace_graph_return(struct trace_array *tr,
 				 unsigned long flags, int pc);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-extern struct ftrace_hash *ftrace_graph_hash;
+extern struct ftrace_hash __rcu *ftrace_graph_hash;
 extern struct ftrace_hash *ftrace_graph_notrace_hash;
 
 static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
 {
 	unsigned long addr = trace->func;
 	int ret = 0;
+	struct ftrace_hash *hash;
 
 	preempt_disable_notrace();
 
-	if (ftrace_hash_empty(ftrace_graph_hash)) {
+	hash = rcu_dereference_protected(ftrace_graph_hash, !preemptible());
+
+	if (ftrace_hash_empty(hash)) {
 		ret = 1;
 		goto out;
 	}
 
-	if (ftrace_lookup_ip(ftrace_graph_hash, addr)) {
+	if (ftrace_lookup_ip(hash, addr)) {
 
 		/*
 		 * This needs to be cleared on the return functions

index b38c6af10da5b..d297a8bdc681a 100644
@@ -5103,7 +5103,7 @@ static const struct file_operations ftrace_notrace_fops = {
 static DEFINE_MUTEX(graph_lock);
 
 struct ftrace_hash __rcu *ftrace_graph_hash = EMPTY_HASH;
-struct ftrace_hash *ftrace_graph_notrace_hash = EMPTY_HASH;
+struct ftrace_hash __rcu *ftrace_graph_notrace_hash = EMPTY_HASH;
 
 enum graph_filter_type {
 	GRAPH_FILTER_NOTRACE	= 0,

index f8fb3786af72a..c4fd5731d6b37 100644
@@ -933,7 +933,7 @@ extern void __trace_graph_return(struct trace_array *tr,
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern struct ftrace_hash __rcu *ftrace_graph_hash;
-extern struct ftrace_hash *ftrace_graph_notrace_hash;
+extern struct ftrace_hash __rcu *ftrace_graph_notrace_hash;
 
 static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
 {

@@ -986,10 +986,14 @@ static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace)
 static inline int ftrace_graph_notrace_addr(unsigned long addr)
 {
 	int ret = 0;
+	struct ftrace_hash *notrace_hash;
 
 	preempt_disable_notrace();
 
-	if (ftrace_lookup_ip(ftrace_graph_notrace_hash, addr))
+	notrace_hash = rcu_dereference_protected(ftrace_graph_notrace_hash,
+						 !preemptible());
+
+	if (ftrace_lookup_ip(notrace_hash, addr))
 		ret = 1;
 
 	preempt_enable_notrace();

index c4fd5731d6b37..08647723cfab9 100644
@@ -943,6 +943,11 @@ static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
 
 	preempt_disable_notrace();
 
+	/*
+	 * Have to open code "rcu_dereference_sched()" because the
+	 * function graph tracer can be called when RCU is not
+	 * "watching".
+	 */
 	hash = rcu_dereference_protected(ftrace_graph_hash, !preemptible());
 
 	if (ftrace_hash_empty(hash)) {

@@ -990,6 +995,11 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr)
 
 	preempt_disable_notrace();
 
+	/*
+	 * Have to open code "rcu_dereference_sched()" because the
+	 * function graph tracer can be called when RCU is not
+	 * "watching".
+	 */
 	notrace_hash = rcu_dereference_protected(ftrace_graph_notrace_hash,
 						 !preemptible());
 

index d297a8bdc681a..407d8bf4ed93e 100644
@@ -5378,8 +5378,15 @@ ftrace_graph_release(struct inode *inode, struct file *file)
 
 		mutex_unlock(&graph_lock);
 
-		/* Wait till all users are no longer using the old hash */
-		synchronize_rcu();
+		/*
+		 * We need to do a hard force of sched synchronization.
+		 * This is because we use preempt_disable() to do RCU, but
+		 * the function tracers can be called where RCU is not watching
+		 * (like before user_exit()). We can not rely on the RCU
+		 * infrastructure to do the synchronization, thus we must do it
+		 * ourselves.
+		 */
+		schedule_on_each_cpu(ftrace_sync);
 
 		free_ftrace_hash(old_hash);
 	}

index 08647723cfab9..a3c29d5fcc616 100644
@@ -947,6 +947,7 @@ static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
 	 * Have to open code "rcu_dereference_sched()" because the
 	 * function graph tracer can be called when RCU is not
 	 * "watching".
+	 * Protected with schedule_on_each_cpu(ftrace_sync)
 	 */
 	hash = rcu_dereference_protected(ftrace_graph_hash, !preemptible());
 

@@ -999,6 +1000,7 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr)
 	 * Have to open code "rcu_dereference_sched()" because the
 	 * function graph tracer can be called when RCU is not
 	 * "watching".
+	 * Protected with schedule_on_each_cpu(ftrace_sync)
 	 */
 	notrace_hash = rcu_dereference_protected(ftrace_graph_notrace_hash,
 						 !preemptible());

@@ -24,6 +24,8 @@ static struct kset           *pcrypt_kse
 
 struct pcrypt_instance_ctx {
 	struct crypto_aead_spawn spawn;
+	struct padata_shell *psenc;
+	struct padata_shell *psdec;
 	atomic_t tfm_count;
 };
 

@@ -32,6 +34,12 @@ struct pcrypt_aead_ctx {
 	unsigned int cb_cpu;
 };
 
+static inline struct pcrypt_instance_ctx *pcrypt_tfm_ictx(
+	struct crypto_aead *tfm)
+{
+	return aead_instance_ctx(aead_alg_instance(tfm));
+}
+
 static int pcrypt_aead_setkey(struct crypto_aead *parent,
 			      const u8 *key, unsigned int keylen)
 {

@@ -90,6 +98,9 @@ static int pcrypt_aead_encrypt(struct ae
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(aead);
 	u32 flags = aead_request_flags(req);
+	struct pcrypt_instance_ctx *ictx;
+
+	ictx = pcrypt_tfm_ictx(aead);
 
 	memset(padata, 0, sizeof(struct padata_priv));
 

@@ -103,7 +114,7 @@ static int pcrypt_aead_encrypt(struct ae
 			       req->cryptlen, req->iv);
 	aead_request_set_ad(creq, req->assoclen);
 
-	err = padata_do_parallel(pencrypt, padata, &ctx->cb_cpu);
+	err = padata_do_parallel(ictx->psenc, padata, &ctx->cb_cpu);
 	if (!err)
 		return -EINPROGRESS;
 

@@ -132,6 +143,9 @@ static int pcrypt_aead_decrypt(struct ae
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(aead);
 	u32 flags = aead_request_flags(req);
+	struct pcrypt_instance_ctx *ictx;
+
+	ictx = pcrypt_tfm_ictx(aead);
 
 	memset(padata, 0, sizeof(struct padata_priv));
 

@@ -145,7 +159,7 @@ static int pcrypt_aead_decrypt(struct ae
 			       req->cryptlen, req->iv);
 	aead_request_set_ad(creq, req->assoclen);
 
-	err = padata_do_parallel(pdecrypt, padata, &ctx->cb_cpu);
+	err = padata_do_parallel(ictx->psdec, padata, &ctx->cb_cpu);
 	if (!err)
 		return -EINPROGRESS;
 

@@ -192,6 +206,8 @@ static void pcrypt_free(struct aead_inst
 	struct pcrypt_instance_ctx *ctx = aead_instance_ctx(inst);
 
 	crypto_drop_aead(&ctx->spawn);
+	padata_free_shell(ctx->psdec);
+	padata_free_shell(ctx->psenc);
 	kfree(inst);
 }
 

@@ -233,12 +249,22 @@ static int pcrypt_create_aead(struct cry
 	if (!inst)
 		return -ENOMEM;
 
+	err = -ENOMEM;
+
 	ctx = aead_instance_ctx(inst);
+	ctx->psenc = padata_alloc_shell(pencrypt);
+	if (!ctx->psenc)
+		goto out_free_inst;
+
+	ctx->psdec = padata_alloc_shell(pdecrypt);
+	if (!ctx->psdec)
+		goto out_free_psenc;
+
 	crypto_set_aead_spawn(&ctx->spawn, aead_crypto_instance(inst));
 
 	err = crypto_grab_aead(&ctx->spawn, name, 0, 0);
 	if (err)
-		goto out_free_inst;
+		goto out_free_psdec;
 
 	alg = crypto_spawn_aead_alg(&ctx->spawn);
 	err = pcrypt_init_instance(aead_crypto_instance(inst), &alg->base);

@@ -271,6 +297,10 @@ out:
 
 out_drop_aead:
 	crypto_drop_aead(&ctx->spawn);
+out_free_psdec:
+	padata_free_shell(ctx->psdec);
+out_free_psenc:
+	padata_free_shell(ctx->psenc);
 out_free_inst:
 	kfree(inst);
 	goto out;

@@ -9,6 +9,7 @@
 #ifndef PADATA_H
 #define PADATA_H
 
+#include <linux/compiler_types.h>
 #include <linux/workqueue.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>

@@ -98,7 +99,7 @@ struct padata_cpumask {
  * struct parallel_data - Internal control structure, covers everything
  * that depends on the cpumask in use.
  *
- * @pinst: padata instance.
+ * @sh: padata_shell object.
  * @pqueue: percpu padata queues used for parallelization.
  * @squeue: percpu padata queues used for serialuzation.
  * @reorder_objects: Number of objects waiting in the reorder queues.

@@ -111,7 +112,7 @@ struct padata_cpumask {
  * @lock: Reorder lock.
  */
 struct parallel_data {
-	struct padata_instance		*pinst;
+	struct padata_shell		*ps;
 	struct padata_parallel_queue	__percpu *pqueue;
 	struct padata_serial_queue	__percpu *squeue;
 	atomic_t			reorder_objects;

@@ -125,13 +126,32 @@ struct parallel_data {
 };
 
 /**
+ * struct padata_shell - Wrapper around struct parallel_data, its
+ * purpose is to allow the underlying control structure to be replaced
+ * on the fly using RCU.
+ *
+ * @pinst: padat instance.
+ * @pd: Actual parallel_data structure which may be substituted on the fly.
+ * @opd: Pointer to old pd to be freed by padata_replace.
+ * @list: List entry in padata_instance list.
+ */
+struct padata_shell {
+	struct padata_instance		*pinst;
+	struct parallel_data __rcu	*pd;
+	struct parallel_data		*opd;
+	struct list_head		list;
+};
+
+/**
  * struct padata_instance - The overall control structure.
  *
  * @cpu_notifier: cpu hotplug notifier.
  * @parallel_wq: The workqueue used for parallel work.
  * @serial_wq: The workqueue used for serial work.
- * @pd: The internal control structure.
+ * @pslist: List of padata_shell objects attached to this instance.
  * @cpumask: User supplied cpumasks for parallel and serial works.
+ * @rcpumask: Actual cpumasks based on user cpumask and cpu_online_mask.
+ * @omask: Temporary storage used to compute the notification mask.
  * @cpumask_change_notifier: Notifiers chain for user-defined notify
  *            callbacks that will be called when either @pcpu or @cbcpu
  *            or both cpumasks change.

@@ -143,8 +163,10 @@ struct padata_instance {
 	struct hlist_node		 node;
 	struct workqueue_struct		*parallel_wq;
 	struct workqueue_struct		*serial_wq;
-	struct parallel_data		*pd;
+	struct list_head		pslist;
 	struct padata_cpumask		cpumask;
+	struct padata_cpumask		rcpumask;
+	cpumask_var_t			omask;
 	struct blocking_notifier_head	 cpumask_change_notifier;
 	struct kobject                   kobj;
 	struct mutex			 lock;

@@ -156,7 +178,9 @@ struct padata_instance {
 
 extern struct padata_instance *padata_alloc_possible(const char *name);
 extern void padata_free(struct padata_instance *pinst);
-extern int padata_do_parallel(struct padata_instance *pinst,
+extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst);
+extern void padata_free_shell(struct padata_shell *ps);
+extern int padata_do_parallel(struct padata_shell *ps,
 			      struct padata_priv *padata, int *cb_cpu);
 extern void padata_do_serial(struct padata_priv *padata);
 extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,

399 lines not on this page · raw message

@@ -3938,6 +3938,11 @@ int btree_write_cache_pages(struct addre
 	if (wbc->range_cyclic) {
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
+		/*
+		 * Start from the beginning does not need to cycle over the
+		 * range, mark it as scanned.
+		 */
+		scanned = (index == 0);
 	} else {
 		index = wbc->range_start >> PAGE_SHIFT;
 		end = wbc->range_end >> PAGE_SHIFT;

@@ -3955,7 +3960,6 @@ retry:
 			tag))) {
 		unsigned i;
 
-		scanned = 1;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 

@@ -4084,6 +4088,11 @@ static int extent_write_cache_pages(stru
 	if (wbc->range_cyclic) {
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
+		/*
+		 * Start from the beginning does not need to cycle over the
+		 * range, mark it as scanned.
+		 */
+		scanned = (index == 0);
 	} else {
 		index = wbc->range_start >> PAGE_SHIFT;
 		end = wbc->range_end >> PAGE_SHIFT;

@@ -4117,7 +4126,6 @@ retry:
 						&index, end, tag))) {
 		unsigned i;
 
-		scanned = 1;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 

@@ -881,17 +881,28 @@ static struct btrfs_fs_devices *find_fsi
 	/*
 	 * Handles the case where scanned device is part of an fs that had
 	 * multiple successful changes of FSID but curently device didn't
-	 * observe it. Meaning our fsid will be different than theirs.
+	 * observe it. Meaning our fsid will be different than theirs. We need
+	 * to handle two subcases :
+	 *  1 - The fs still continues to have different METADATA/FSID uuids.
+	 *  2 - The fs is switched back to its original FSID (METADATA/FSID
+	 *  are equal).
 	 */
 	list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+		/* Changed UUIDs */
 		if (memcmp(fs_devices->metadata_uuid, fs_devices->fsid,
 			   BTRFS_FSID_SIZE) != 0 &&
 		    memcmp(fs_devices->metadata_uuid, disk_super->metadata_uuid,
 			   BTRFS_FSID_SIZE) == 0 &&
 		    memcmp(fs_devices->fsid, disk_super->fsid,
-			   BTRFS_FSID_SIZE) != 0) {
+			   BTRFS_FSID_SIZE) != 0)
+			return fs_devices;
+
+		/* Unchanged UUIDs */
+		if (memcmp(fs_devices->metadata_uuid, fs_devices->fsid,
+			   BTRFS_FSID_SIZE) == 0 &&
+		    memcmp(fs_devices->fsid, disk_super->metadata_uuid,
+			   BTRFS_FSID_SIZE) == 0)
 			return fs_devices;
-		}
 	}
 
 	return NULL;

@@ -120,6 +120,11 @@ static bool seen_reg(int reg, struct rv_
 	return false;
 }
 
+static void mark_fp(struct rv_jit_context *ctx)
+{
+	__set_bit(RV_CTX_F_SEEN_S5, &ctx->flags);
+}
+
 static void mark_call(struct rv_jit_context *ctx)
 {
 	__set_bit(RV_CTX_F_SEEN_CALL, &ctx->flags);

@@ -596,7 +601,8 @@ static void __build_epilogue(u8 reg, str
 
 	emit(rv_addi(RV_REG_SP, RV_REG_SP, stack_adjust), ctx);
 	/* Set return value. */
-	emit(rv_addi(RV_REG_A0, RV_REG_A5, 0), ctx);
+	if (reg == RV_REG_RA)
+		emit(rv_addi(RV_REG_A0, RV_REG_A5, 0), ctx);
 	emit(rv_jalr(RV_REG_ZERO, reg, 0), ctx);
 }
 

@@ -1426,6 +1432,10 @@ static void build_prologue(struct rv_jit
 {
 	int stack_adjust = 0, store_offset, bpf_stack_adjust;
 
+	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
+	if (bpf_stack_adjust)
+		mark_fp(ctx);
+
 	if (seen_reg(RV_REG_RA, ctx))
 		stack_adjust += 8;
 	stack_adjust += 8; /* RV_REG_FP */

@@ -1443,7 +1453,6 @@ static void build_prologue(struct rv_jit
 		stack_adjust += 8;
 
 	stack_adjust = round_up(stack_adjust, 16);
-	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
 	stack_adjust += bpf_stack_adjust;
 
 	store_offset = stack_adjust - 8;

@@ -4,6 +4,7 @@
 #include <sched.h>
 #include <sys/socket.h>
 #include <test_progs.h>
+#include "libbpf_internal.h"
 
 static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 {

@@ -19,7 +20,7 @@ static void on_sample(void *ctx, int cpu
 
 void test_perf_buffer(void)
 {
-	int err, prog_fd, nr_cpus, i, duration = 0;
+	int err, prog_fd, on_len, nr_on_cpus = 0,  nr_cpus, i, duration = 0;
 	const char *prog_name = "kprobe/sys_nanosleep";
 	const char *file = "./test_perf_buffer.o";
 	struct perf_buffer_opts pb_opts = {};

@@ -29,15 +30,27 @@ void test_perf_buffer(void)
 	struct bpf_object *obj;
 	struct perf_buffer *pb;
 	struct bpf_link *link;
+	bool *online;
 
 	nr_cpus = libbpf_num_possible_cpus();
 	if (CHECK(nr_cpus < 0, "nr_cpus", "err %d\n", nr_cpus))
 		return;
 
+	err = parse_cpu_mask_file("/sys/devices/system/cpu/online",
+				  &online, &on_len);
+	if (CHECK(err, "nr_on_cpus", "err %d\n", err))
+		return;
+
+	for (i = 0; i < on_len; i++)
+		if (online[i])
+			nr_on_cpus++;
+
 	/* load program */
 	err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd);
-	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
-		return;
+	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) {
+		obj = NULL;
+		goto out_close;
+	}
 
 	prog = bpf_object__find_program_by_title(obj, prog_name);
 	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name))

@@ -64,6 +77,11 @@ void test_perf_buffer(void)
 	/* trigger kprobe on every CPU */
 	CPU_ZERO(&cpu_seen);
 	for (i = 0; i < nr_cpus; i++) {
+		if (i >= on_len || !online[i]) {
+			printf("skipping offline CPU #%d\n", i);
+			continue;
+		}
+
 		CPU_ZERO(&cpu_set);
 		CPU_SET(i, &cpu_set);
 

@@ -81,8 +99,8 @@ void test_perf_buffer(void)
 	if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err))
 		goto out_free_pb;
 
-	if (CHECK(CPU_COUNT(&cpu_seen) != nr_cpus, "seen_cpu_cnt",
-		  "expect %d, seen %d\n", nr_cpus, CPU_COUNT(&cpu_seen)))
+	if (CHECK(CPU_COUNT(&cpu_seen) != nr_on_cpus, "seen_cpu_cnt",
+		  "expect %d, seen %d\n", nr_on_cpus, CPU_COUNT(&cpu_seen)))
 		goto out_free_pb;
 
 out_free_pb:

@@ -91,4 +109,5 @@ out_detach:
 	bpf_link__destroy(link);
 out_close:
 	bpf_object__close(obj);
+	free(online);
 }

@@ -293,7 +293,8 @@ struct bpf_dtab_netdev *__dev_map_hash_l
 	struct hlist_head *head = dev_map_index_hash(dtab, key);
 	struct bpf_dtab_netdev *dev;
 
-	hlist_for_each_entry_rcu(dev, head, index_hlist)
+	hlist_for_each_entry_rcu(dev, head, index_hlist,
+				 lockdep_is_held(&dtab->index_lock))
 		if (dev->idx == key)
 			return dev;
 

@@ -2541,7 +2541,9 @@ static struct ids_vec *bpf_core_find_can
 		if (strncmp(local_name, targ_name, local_essent_len) == 0) {
 			pr_debug("[%d] %s: found candidate [%d] %s\n",
 				 local_type_id, local_name, i, targ_name);
-			new_ids = realloc(cand_ids->data, cand_ids->len + 1);
+			new_ids = reallocarray(cand_ids->data,
+					       cand_ids->len + 1,
+					       sizeof(*cand_ids->data));
 			if (!new_ids) {
 				err = -ENOMEM;
 				goto err_out;

@@ -16,6 +16,10 @@ static const char *__doc__ =
 #include <getopt.h>
 #include <net/if.h>
 #include <time.h>
+#include <linux/limits.h>
+
+#define __must_check
+#include <linux/err.h>
 
 #include <arpa/inet.h>
 #include <linux/if_link.h>

@@ -46,6 +50,10 @@ static int cpus_count_map_fd;
 static int cpus_iterator_map_fd;
 static int exception_cnt_map_fd;
 
+#define NUM_TP 5
+struct bpf_link *tp_links[NUM_TP] = { 0 };
+static int tp_cnt = 0;
+
 /* Exit return codes */
 #define EXIT_OK		0
 #define EXIT_FAIL		1

@@ -88,6 +96,10 @@ static void int_exit(int sig)
 			printf("program on interface changed, not removing\n");
 		}
 	}
+	/* Detach tracepoints */
+	while (tp_cnt)
+		bpf_link__destroy(tp_links[--tp_cnt]);
+
 	exit(EXIT_OK);
 }
 

@@ -588,23 +600,61 @@ static void stats_poll(int interval, boo
 	free_stats_record(prev);
 }
 
+static struct bpf_link * attach_tp(struct bpf_object *obj,
+				   const char *tp_category,
+				   const char* tp_name)
+{
+	struct bpf_program *prog;
+	struct bpf_link *link;
+	char sec_name[PATH_MAX];
+	int len;
+
+	len = snprintf(sec_name, PATH_MAX, "tracepoint/%s/%s",
+		       tp_category, tp_name);
+	if (len < 0)
+		exit(EXIT_FAIL);
+
+	prog = bpf_object__find_program_by_title(obj, sec_name);
+	if (!prog) {
+		fprintf(stderr, "ERR: finding progsec: %s\n", sec_name);
+		exit(EXIT_FAIL_BPF);
+	}
+
+	link = bpf_program__attach_tracepoint(prog, tp_category, tp_name);
+	if (IS_ERR(link))
+		exit(EXIT_FAIL_BPF);
+
+	return link;
+}
+
+static void init_tracepoints(struct bpf_object *obj) {
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_err");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_map_err");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_exception");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_enqueue");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_kthread");
+}
+
 static int init_map_fds(struct bpf_object *obj)
 {
-	cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map");
-	rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt");
+	/* Maps updated by tracepoints */
 	redirect_err_cnt_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "redirect_err_cnt");
+	exception_cnt_map_fd =
+		bpf_object__find_map_fd_by_name(obj, "exception_cnt");
 	cpumap_enqueue_cnt_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpumap_enqueue_cnt");
 	cpumap_kthread_cnt_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpumap_kthread_cnt");
+
+	/* Maps used by XDP */
+	rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt");
+	cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map");
 	cpus_available_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpus_available");
 	cpus_count_map_fd = bpf_object__find_map_fd_by_name(obj, "cpus_count");
 	cpus_iterator_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpus_iterator");
-	exception_cnt_map_fd =
-		bpf_object__find_map_fd_by_name(obj, "exception_cnt");
 
 	if (cpu_map_fd < 0 || rx_cnt_map_fd < 0 ||
 	    redirect_err_cnt_map_fd < 0 || cpumap_enqueue_cnt_map_fd < 0 ||

@@ -662,6 +712,7 @@ int main(int argc, char **argv)
 			strerror(errno));
 		return EXIT_FAIL;
 	}
+	init_tracepoints(obj);
 	if (init_map_fds(obj) < 0) {
 		fprintf(stderr, "bpf_object__find_map_fd_by_name failed\n");
 		return EXIT_FAIL;

@@ -2,7 +2,7 @@
 #include <test_progs.h>
 
 ssize_t get_base_addr() {
-	size_t start;
+	size_t start, offset;
 	char buf[256];
 	FILE *f;
 

@@ -10,10 +10,11 @@ ssize_t get_base_addr() {
 	if (!f)
 		return -errno;
 
-	while (fscanf(f, "%zx-%*x %s %*s\n", &start, buf) == 2) {
+	while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n",
+		      &start, buf, &offset) == 3) {
 		if (strcmp(buf, "r-xp") == 0) {
 			fclose(f);
-			return start;
+			return start - offset;
 		}
 	}
 

@@ -49,8 +49,12 @@ retry:
 	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
 			 0 /* cpu 0 */, -1 /* group id */,
 			 0 /* flags */);
-	if (CHECK(pmu_fd < 0, "perf_event_open",
-		  "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n",
+	if (pmu_fd < 0 && errno == ENOENT) {
+		printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__);
+		test__skip();
+		goto cleanup;
+	}
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
 		  pmu_fd, errno))
 		goto close_prog;
 

@@ -331,7 +331,7 @@ static int msg_loop_sendpage(int fd, int
 	FILE *file;
 	int i, fp;
 
-	file = fopen(".sendpage_tst.tmp", "w+");
+	file = tmpfile();
 	if (!file) {
 		perror("create file for sendpage");
 		return 1;

@@ -340,13 +340,8 @@ static int msg_loop_sendpage(int fd, int
 		fwrite(&k, sizeof(char), 1, file);
 	fflush(file);
 	fseek(file, 0, SEEK_SET);
-	fclose(file);
 
-	fp = open(".sendpage_tst.tmp", O_RDONLY);
-	if (fp < 0) {
-		perror("reopen file for sendpage");
-		return 1;
-	}
+	fp = fileno(file);
 
 	clock_gettime(CLOCK_MONOTONIC, &s->start);
 	for (i = 0; i < cnt; i++) {

@@ -354,11 +349,11 @@ static int msg_loop_sendpage(int fd, int
 
 		if (!drop && sent < 0) {
 			perror("send loop error");
-			close(fp);
+			fclose(file);
 			return sent;
 		} else if (drop && sent >= 0) {
 			printf("sendpage loop error expected: %i\n", sent);
-			close(fp);
+			fclose(file);
 			return -EIO;
 		}
 

@@ -366,7 +361,7 @@ static int msg_loop_sendpage(int fd, int
 			s->bytes_sent += sent;
 	}
 	clock_gettime(CLOCK_MONOTONIC, &s->end);
-	close(fp);
+	fclose(file);
 	return 0;
 }
 

@@ -113,6 +113,12 @@ int _select_by_skb_data(struct sk_reusep
 		data_check.skb_ports[0] = th->source;
 		data_check.skb_ports[1] = th->dest;
 
+		if (th->fin)
+			/* The connection is being torn down at the end of a
+			 * test. It can't contain a cmd, so return early.
+			 */
+			return SK_PASS;
+
 		if ((th->doff << 2) + sizeof(*cmd) > data_check.len)
 			GOTO_DONE(DROP_ERR_SKB_DATA);
 		if (bpf_skb_load_bytes(reuse_md, th->doff << 2, &cmd_copy,

@@ -257,6 +257,7 @@ void crypto_alg_tested(const char *name,
 	struct crypto_alg *alg;
 	struct crypto_alg *q;
 	LIST_HEAD(list);
+	bool best;
 
 	down_write(&crypto_alg_sem);
 	list_for_each_entry(q, &crypto_alg_list, cra_list) {

@@ -280,6 +281,21 @@ found:
 
 	alg->cra_flags |= CRYPTO_ALG_TESTED;
 
+	/* Only satisfy larval waiters if we are the best. */
+	best = true;
+	list_for_each_entry(q, &crypto_alg_list, cra_list) {
+		if (crypto_is_moribund(q) || !crypto_is_larval(q))
+			continue;
+
+		if (strcmp(alg->cra_name, q->cra_name))
+			continue;
+
+		if (q->cra_priority > alg->cra_priority) {
+			best = false;
+			break;
+		}
+	}
+
 	list_for_each_entry(q, &crypto_alg_list, cra_list) {
 		if (q == alg)
 			continue;

@@ -303,10 +319,12 @@ found:
 				continue;
 			if ((q->cra_flags ^ alg->cra_flags) & larval->mask)
 				continue;
-			if (!crypto_mod_get(alg))
-				continue;
 
-			larval->adult = alg;
+			if (best && crypto_mod_get(alg))
+				larval->adult = alg;
+			else
+				larval->adult = ERR_PTR(-EAGAIN);
+
 			continue;
 		}
 

@@ -97,7 +97,7 @@ static void crypto_larval_destroy(struct
 	struct crypto_larval *larval = (void *)alg;
 
 	BUG_ON(!crypto_is_larval(alg));
-	if (larval->adult)
+	if (!IS_ERR_OR_NULL(larval->adult))
 		crypto_mod_put(larval->adult);
 	kfree(larval);
 }

@@ -178,6 +178,8 @@ static struct crypto_alg *crypto_larval_
 		alg = ERR_PTR(-ETIMEDOUT);
 	else if (!alg)
 		alg = ERR_PTR(-ENOENT);
+	else if (IS_ERR(alg))
+		;
 	else if (crypto_is_test_larval(larval) &&
 		 !(alg->cra_flags & CRYPTO_ALG_TESTED))
 		alg = ERR_PTR(-EAGAIN);

@@ -12,6 +12,10 @@
 
 /* hisi_zip_sqe dw3 */
 #define HZIP_BD_STATUS_M			GENMASK(7, 0)
+/* hisi_zip_sqe dw7 */
+#define HZIP_IN_SGE_DATA_OFFSET_M		GENMASK(23, 0)
+/* hisi_zip_sqe dw8 */
+#define HZIP_OUT_SGE_DATA_OFFSET_M		GENMASK(23, 0)
 /* hisi_zip_sqe dw9 */
 #define HZIP_REQ_TYPE_M				GENMASK(7, 0)
 #define HZIP_ALG_TYPE_ZLIB			0x02

178 lines not on this page · raw message

@@ -586,6 +586,7 @@ const struct ccp_vdata ccpv3_platform =
 	.setup = NULL,
 	.perform = &ccp3_actions,
 	.offset = 0,
+	.rsamax = CCP_RSA_MAX_WIDTH,
 };
 
 const struct ccp_vdata ccpv3 = {

@@ -261,7 +261,7 @@ static int ghash_setkey(struct crypto_sh
 static struct shash_alg ghash_alg[] = {{
 	.base.cra_name		= "ghash",
 	.base.cra_driver_name	= "ghash-neon",
-	.base.cra_priority	= 100,
+	.base.cra_priority	= 150,
 	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct ghash_key),
 	.base.cra_module	= THIS_MODULE,

@@ -71,7 +71,6 @@ static void pcrypt_aead_done(struct cryp
 	struct padata_priv *padata = pcrypt_request_padata(preq);
 
 	padata->info = err;
-	req->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	padata_do_serial(padata);
 }

@@ -88,7 +88,6 @@
 struct atmel_aes_caps {
 	bool			has_dualbuff;
 	bool			has_cfb64;
-	bool			has_ctr32;
 	bool			has_gcm;
 	bool			has_xts;
 	bool			has_authenc;

@@ -1013,8 +1012,9 @@ static int atmel_aes_ctr_transfer(struct
 	struct atmel_aes_ctr_ctx *ctx = atmel_aes_ctr_ctx_cast(dd->ctx);
 	struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq);
 	struct scatterlist *src, *dst;
-	u32 ctr, blocks;
 	size_t datalen;
+	u32 ctr;
+	u16 blocks, start, end;
 	bool use_dma, fragmented = false;
 
 	/* Check for transfer completion. */

@@ -1026,27 +1026,17 @@ static int atmel_aes_ctr_transfer(struct
 	datalen = req->nbytes - ctx->offset;
 	blocks = DIV_ROUND_UP(datalen, AES_BLOCK_SIZE);
 	ctr = be32_to_cpu(ctx->iv[3]);
-	if (dd->caps.has_ctr32) {
-		/* Check 32bit counter overflow. */
-		u32 start = ctr;
-		u32 end = start + blocks - 1;
-
-		if (end < start) {
-			ctr |= 0xffffffff;
-			datalen = AES_BLOCK_SIZE * -start;
-			fragmented = true;
-		}
-	} else {
-		/* Check 16bit counter overflow. */
-		u16 start = ctr & 0xffff;
-		u16 end = start + (u16)blocks - 1;
-
-		if (blocks >> 16 || end < start) {
-			ctr |= 0xffff;
-			datalen = AES_BLOCK_SIZE * (0x10000-start);
-			fragmented = true;
-		}
+
+	/* Check 16bit counter overflow. */
+	start = ctr & 0xffff;
+	end = start + blocks - 1;
+
+	if (blocks >> 16 || end < start) {
+		ctr |= 0xffff;
+		datalen = AES_BLOCK_SIZE * (0x10000 - start);
+		fragmented = true;
 	}
+
 	use_dma = (datalen >= ATMEL_AES_DMA_THRESHOLD);
 
 	/* Jump to offset. */

@@ -2550,7 +2540,6 @@ static void atmel_aes_get_cap(struct atm
 {
 	dd->caps.has_dualbuff = 0;
 	dd->caps.has_cfb64 = 0;
-	dd->caps.has_ctr32 = 0;
 	dd->caps.has_gcm = 0;
 	dd->caps.has_xts = 0;
 	dd->caps.has_authenc = 0;

@@ -2561,7 +2550,6 @@ static void atmel_aes_get_cap(struct atm
 	case 0x500:
 		dd->caps.has_dualbuff = 1;
 		dd->caps.has_cfb64 = 1;
-		dd->caps.has_ctr32 = 1;
 		dd->caps.has_gcm = 1;
 		dd->caps.has_xts = 1;
 		dd->caps.has_authenc = 1;

@@ -2570,7 +2558,6 @@ static void atmel_aes_get_cap(struct atm
 	case 0x200:
 		dd->caps.has_dualbuff = 1;
 		dd->caps.has_cfb64 = 1;
-		dd->caps.has_ctr32 = 1;
 		dd->caps.has_gcm = 1;
 		dd->caps.max_burst_size = 4;
 		break;

@@ -697,22 +697,16 @@ EXPORT_SYMBOL_GPL(crypto_drop_spawn);
 static struct crypto_alg *crypto_spawn_alg(struct crypto_spawn *spawn)
 {
 	struct crypto_alg *alg;
-	struct crypto_alg *alg2;
 
 	down_read(&crypto_alg_sem);
 	alg = spawn->alg;
-	alg2 = alg;
-	if (alg2)
-		alg2 = crypto_mod_get(alg2);
-	up_read(&crypto_alg_sem);
-
-	if (!alg2) {
-		if (alg)
-			crypto_shoot_alg(alg);
-		return ERR_PTR(-EAGAIN);
+	if (alg && !crypto_mod_get(alg)) {
+		alg->cra_flags |= CRYPTO_ALG_DYING;
+		alg = NULL;
 	}
+	up_read(&crypto_alg_sem);
 
-	return alg;
+	return alg ?: ERR_PTR(-EAGAIN);
 }
 
 struct crypto_tfm *crypto_spawn_tfm(struct crypto_spawn *spawn, u32 type,

@@ -346,13 +346,12 @@ static unsigned int crypto_ctxsize(struc
 	return len;
 }
 
-void crypto_shoot_alg(struct crypto_alg *alg)
+static void crypto_shoot_alg(struct crypto_alg *alg)
 {
 	down_write(&crypto_alg_sem);
 	alg->cra_flags |= CRYPTO_ALG_DYING;
 	up_write(&crypto_alg_sem);
 }
-EXPORT_SYMBOL_GPL(crypto_shoot_alg);
 
 struct crypto_tfm *__crypto_alloc_tfm(struct crypto_alg *alg, u32 type,
 				      u32 mask)

@@ -68,7 +68,6 @@ void crypto_alg_tested(const char *name,
 void crypto_remove_spawns(struct crypto_alg *alg, struct list_head *list,
 			  struct crypto_alg *nalg);
 void crypto_remove_final(struct list_head *list);
-void crypto_shoot_alg(struct crypto_alg *alg);
 struct crypto_tfm *__crypto_alloc_tfm(struct crypto_alg *alg, u32 type,
 				      u32 mask);
 void *crypto_create_tfm(struct crypto_alg *alg,

@@ -1613,6 +1613,11 @@ static const struct of_device_id spacc_o
 MODULE_DEVICE_TABLE(of, spacc_of_id_table);
 #endif /* CONFIG_OF */
 
+static void spacc_tasklet_kill(void *data)
+{
+	tasklet_kill(data);
+}
+
 static int spacc_probe(struct platform_device *pdev)
 {
 	int i, err, ret;

@@ -1655,6 +1660,14 @@ static int spacc_probe(struct platform_d
 		return -ENXIO;
 	}
 
+	tasklet_init(&engine->complete, spacc_spacc_complete,
+		     (unsigned long)engine);
+
+	ret = devm_add_action(&pdev->dev, spacc_tasklet_kill,
+			      &engine->complete);
+	if (ret)
+		return ret;
+
 	if (devm_request_irq(&pdev->dev, irq->start, spacc_spacc_irq, 0,
 			     engine->name, engine)) {
 		dev_err(engine->dev, "failed to request IRQ\n");

@@ -1712,8 +1725,6 @@ static int spacc_probe(struct platform_d
 	INIT_LIST_HEAD(&engine->completed);
 	INIT_LIST_HEAD(&engine->in_progress);
 	engine->in_flight = 0;
-	tasklet_init(&engine->complete, spacc_spacc_complete,
-		     (unsigned long)engine);
 
 	platform_set_drvdata(pdev, engine);
 

@@ -35,7 +35,7 @@ static inline int arch_futex_atomic_op_i
 {
 	int oldval = 0, ret;
 
-	allow_write_to_user(uaddr, sizeof(*uaddr));
+	allow_read_write_user(uaddr, uaddr, sizeof(*uaddr));
 	pagefault_disable();
 
 	switch (op) {

@@ -62,7 +62,7 @@ static inline int arch_futex_atomic_op_i
 
 	*oval = oldval;
 
-	prevent_write_to_user(uaddr, sizeof(*uaddr));
+	prevent_read_write_user(uaddr, uaddr, sizeof(*uaddr));
 	return ret;
 }
 

@@ -76,7 +76,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval,
 	if (!access_ok(uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	allow_write_to_user(uaddr, sizeof(*uaddr));
+	allow_read_write_user(uaddr, uaddr, sizeof(*uaddr));
+
         __asm__ __volatile__ (
         PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %1,0,%3         # futex_atomic_cmpxchg_inatomic\n\

@@ -97,7 +98,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval,
         : "cc", "memory");
 
 	*uval = prev;
-	prevent_write_to_user(uaddr, sizeof(*uaddr));
+	prevent_read_write_user(uaddr, uaddr, sizeof(*uaddr));
+
         return ret;
 }
 

@@ -2519,12 +2519,6 @@ qla83xx_fw_dump_failed:
 /*                         Driver Debug Functions.                          */
 /****************************************************************************/
 
-static inline int
-ql_mask_match(uint level)
-{
-	return (level & ql2xextended_error_logging) == level;
-}
-
 /*
  * This function is for formatting and logging debug information.
  * It is to be used when vha is available. It formats the message

@@ -374,3 +374,9 @@ extern int qla24xx_dump_ram(struct qla_h
 extern void qla24xx_pause_risc(struct device_reg_24xx __iomem *,
 	struct qla_hw_data *);
 extern int qla24xx_soft_reset(struct qla_hw_data *);
+
+static inline int
+ql_mask_match(uint level)
+{
+	return (level & ql2xextended_error_logging) == level;
+}

@@ -1897,6 +1897,18 @@ static void qla24xx_nvme_iocb_entry(scsi
 		inbuf = (uint32_t *)&sts->nvme_ersp_data;
 		outbuf = (uint32_t *)fd->rspaddr;
 		iocb->u.nvme.rsp_pyld_len = le16_to_cpu(sts->nvme_rsp_pyld_len);
+		if (unlikely(iocb->u.nvme.rsp_pyld_len >
+		    sizeof(struct nvme_fc_ersp_iu))) {
+			if (ql_mask_match(ql_dbg_io)) {
+				WARN_ONCE(1, "Unexpected response payload length %u.\n",
+				    iocb->u.nvme.rsp_pyld_len);
+				ql_log(ql_log_warn, fcport->vha, 0x5100,
+				    "Unexpected response payload length %u.\n",
+				    iocb->u.nvme.rsp_pyld_len);
+			}
+			iocb->u.nvme.rsp_pyld_len =
+			    sizeof(struct nvme_fc_ersp_iu);
+		}
 		iter = iocb->u.nvme.rsp_pyld_len >> 2;
 		for (; iter; iter--)
 			*outbuf++ = swab32(*inbuf++);

@@ -162,6 +162,17 @@ typedef struct {
 	bool eof;
 } nfs_readdir_descriptor_t;
 
+static
+void nfs_readdir_init_array(struct page *page)
+{
+	struct nfs_cache_array *array;
+
+	array = kmap_atomic(page);
+	memset(array, 0, sizeof(struct nfs_cache_array));
+	array->eof_index = -1;
+	kunmap_atomic(array);
+}
+
 /*
  * we are freeing strings created by nfs_add_to_readdir_array()
  */

@@ -174,6 +185,7 @@ void nfs_readdir_clear_array(struct page
 	array = kmap_atomic(page);
 	for (i = 0; i < array->size; i++)
 		kfree(array->array[i].string.name);
+	array->size = 0;
 	kunmap_atomic(array);
 }
 

@@ -610,6 +622,8 @@ int nfs_readdir_xdr_to_array(nfs_readdir
 	int status = -ENOMEM;
 	unsigned int array_size = ARRAY_SIZE(pages);
 
+	nfs_readdir_init_array(page);
+
 	entry.prev_cookie = 0;
 	entry.cookie = desc->last_cookie;
 	entry.eof = 0;

@@ -626,8 +640,6 @@ int nfs_readdir_xdr_to_array(nfs_readdir
 	}
 
 	array = kmap(page);
-	memset(array, 0, sizeof(struct nfs_cache_array));
-	array->eof_index = -1;
 
 	status = nfs_readdir_alloc_pages(pages, array_size);
 	if (status < 0)

@@ -682,6 +694,7 @@ int nfs_readdir_filler(void *data, struc
 	unlock_page(page);
 	return 0;
  error:
+	nfs_readdir_clear_array(page);
 	unlock_page(page);
 	return ret;
 }

@@ -702,8 +702,6 @@ int nfs_readdir_filler(void *data, struc
 static
 void cache_page_release(nfs_readdir_descriptor_t *desc)
 {
-	if (!desc->page->mapping)
-		nfs_readdir_clear_array(desc->page);
 	put_page(desc->page);
 	desc->page = NULL;
 }

@@ -717,19 +715,28 @@ struct page *get_cache_page(nfs_readdir_
 
 /*
  * Returns 0 if desc->dir_cookie was found on page desc->page_index
+ * and locks the page to prevent removal from the page cache.
  */
 static
-int find_cache_page(nfs_readdir_descriptor_t *desc)
+int find_and_lock_cache_page(nfs_readdir_descriptor_t *desc)
 {
 	int res;
 
 	desc->page = get_cache_page(desc);
 	if (IS_ERR(desc->page))
 		return PTR_ERR(desc->page);
-
-	res = nfs_readdir_search_array(desc);
+	res = lock_page_killable(desc->page);
 	if (res != 0)
-		cache_page_release(desc);
+		goto error;
+	res = -EAGAIN;
+	if (desc->page->mapping != NULL) {
+		res = nfs_readdir_search_array(desc);
+		if (res == 0)
+			return 0;
+	}
+	unlock_page(desc->page);
+error:
+	cache_page_release(desc);
 	return res;
 }
 

@@ -744,7 +751,7 @@ int readdir_search_pagecache(nfs_readdir
 		desc->last_cookie = 0;
 	}
 	do {
-		res = find_cache_page(desc);
+		res = find_and_lock_cache_page(desc);
 	} while (res == -EAGAIN);
 	return res;
 }

@@ -783,7 +790,6 @@ int nfs_do_filldir(nfs_readdir_descripto
 		desc->eof = true;
 
 	kunmap(desc->page);
-	cache_page_release(desc);
 	dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n",
 			(unsigned long long)*desc->dir_cookie, res);
 	return res;

@@ -829,13 +835,13 @@ int uncached_readdir(nfs_readdir_descrip
 
 	status = nfs_do_filldir(desc);
 
+ out_release:
+	nfs_readdir_clear_array(desc->page);
+	cache_page_release(desc);
  out:
 	dfprintk(DIRCACHE, "NFS: %s: returns %d\n",
 			__func__, status);
 	return status;
- out_release:
-	cache_page_release(desc);
-	goto out;
 }
 
 /* The file offset position represents the dirent entry number.  A

@@ -900,6 +906,8 @@ static int nfs_readdir(struct file *file
 			break;
 
 		res = nfs_do_filldir(desc);
+		unlock_page(desc->page);
+		cache_page_release(desc);
 		if (res < 0)
 			break;
 	} while (!desc->eof);

@@ -791,6 +791,7 @@ nfsd_file_acquire(struct svc_rqst *rqstp
 	struct nfsd_file *nf, *new;
 	struct inode *inode;
 	unsigned int hashval;
+	bool retry = true;
 
 	/* FIXME: skip this if fh_dentry is already set? */
 	status = fh_verify(rqstp, fhp, S_IFREG,

@@ -826,6 +827,11 @@ wait_for_construction:
 
 	/* Did construction of this file fail? */
 	if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
+		if (!retry) {
+			status = nfserr_jukebox;
+			goto out;
+		}
+		retry = false;
 		nfsd_file_put_noref(nf);
 		goto retry;
 	}

@@ -981,6 +981,7 @@ static void *jbd2_seq_info_start(struct
 
 static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos)
 {
+	(*pos)++;
 	return NULL;
 }
 

@@ -478,17 +478,26 @@ int ext4_bio_write_page(struct ext4_io_s
 		gfp_t gfp_flags = GFP_NOFS;
 		unsigned int enc_bytes = round_up(len, i_blocksize(inode));
 
+		/*
+		 * Since bounce page allocation uses a mempool, we can only use
+		 * a waiting mask (i.e. request guaranteed allocation) on the
+		 * first page of the bio.  Otherwise it can deadlock.
+		 */
+		if (io->io_bio)
+			gfp_flags = GFP_NOWAIT | __GFP_NOWARN;
 	retry_encrypt:
 		bounce_page = fscrypt_encrypt_pagecache_blocks(page, enc_bytes,
 							       0, gfp_flags);
 		if (IS_ERR(bounce_page)) {
 			ret = PTR_ERR(bounce_page);
-			if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) {
-				if (io->io_bio) {
+			if (ret == -ENOMEM &&
+			    (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) {
+				gfp_flags = GFP_NOFS;
+				if (io->io_bio)
 					ext4_io_submit(io);
-					congestion_wait(BLK_RW_ASYNC, HZ/50);
-				}
-				gfp_flags |= __GFP_NOFAIL;
+				else
+					gfp_flags |= __GFP_NOFAIL;
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
 				goto retry_encrypt;
 			}
 			bounce_page = NULL;

@@ -673,9 +673,11 @@ static int ext4_d_compare(const struct d
 			  const char *str, const struct qstr *name)
 {
 	struct qstr qstr = {.name = str, .len = len };
-	struct inode *inode = dentry->d_parent->d_inode;
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *inode = READ_ONCE(parent->d_inode);
 
-	if (!IS_CASEFOLDED(inode) || !EXT4_SB(inode->i_sb)->s_encoding) {
+	if (!inode || !IS_CASEFOLDED(inode) ||
+	    !EXT4_SB(inode->i_sb)->s_encoding) {
 		if (len != name->len)
 			return -1;
 		return memcmp(str, name->name, len);

@@ -688,10 +690,11 @@ static int ext4_d_hash(const struct dent
 {
 	const struct ext4_sb_info *sbi = EXT4_SB(dentry->d_sb);
 	const struct unicode_map *um = sbi->s_encoding;
+	const struct inode *inode = READ_ONCE(dentry->d_inode);
 	unsigned char *norm;
 	int len, ret = 0;
 
-	if (!IS_CASEFOLDED(dentry->d_inode) || !um)
+	if (!inode || !IS_CASEFOLDED(inode) || !um)
 		return 0;
 
 	norm = kmalloc(PATH_MAX, GFP_ATOMIC);

@@ -3953,7 +3953,7 @@ static int log_csums(struct btrfs_trans_
 static noinline int copy_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_inode *inode,
 			       struct btrfs_path *dst_path,
-			       struct btrfs_path *src_path, u64 *last_extent,
+			       struct btrfs_path *src_path,
 			       int start_slot, int nr, int inode_only,
 			       u64 logged_isize)
 {

@@ -3964,7 +3964,6 @@ static noinline int copy_items(struct bt
 	struct btrfs_file_extent_item *extent;
 	struct btrfs_inode_item *inode_item;
 	struct extent_buffer *src = src_path->nodes[0];
-	struct btrfs_key first_key, last_key, key;
 	int ret;
 	struct btrfs_key *ins_keys;
 	u32 *ins_sizes;

@@ -3972,9 +3971,6 @@ static noinline int copy_items(struct bt
 	int i;
 	struct list_head ordered_sums;
 	int skip_csum = inode->flags & BTRFS_INODE_NODATASUM;
-	bool has_extents = false;
-	bool need_find_last_extent = true;
-	bool done = false;
 
 	INIT_LIST_HEAD(&ordered_sums);
 

@@ -3983,8 +3979,6 @@ static noinline int copy_items(struct bt
 	if (!ins_data)
 		return -ENOMEM;
 
-	first_key.objectid = (u64)-1;
-
 	ins_sizes = (u32 *)ins_data;
 	ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32));
 

@@ -4005,9 +3999,6 @@ static noinline int copy_items(struct bt
 
 		src_offset = btrfs_item_ptr_offset(src, start_slot + i);
 
-		if (i == nr - 1)
-			last_key = ins_keys[i];
-
 		if (ins_keys[i].type == BTRFS_INODE_ITEM_KEY) {
 			inode_item = btrfs_item_ptr(dst_path->nodes[0],
 						    dst_path->slots[0],

@@ -4021,20 +4012,6 @@ static noinline int copy_items(struct bt
 					   src_offset, ins_sizes[i]);
 		}
 
-		/*
-		 * We set need_find_last_extent here in case we know we were
-		 * processing other items and then walk into the first extent in
-		 * the inode.  If we don't hit an extent then nothing changes,
-		 * we'll do the last search the next time around.
-		 */
-		if (ins_keys[i].type == BTRFS_EXTENT_DATA_KEY) {
-			has_extents = true;
-			if (first_key.objectid == (u64)-1)
-				first_key = ins_keys[i];
-		} else {
-			need_find_last_extent = false;
-		}
-
 		/* take a reference on file data extents so that truncates
 		 * or deletes of this inode don't have to relog the inode
 		 * again

@@ -4100,167 +4077,6 @@ static noinline int copy_items(struct bt
 		kfree(sums);
 	}
 
-	if (!has_extents)
-		return ret;
-
-	if (need_find_last_extent && *last_extent == first_key.offset) {
-		/*
-		 * We don't have any leafs between our current one and the one
-		 * we processed before that can have file extent items for our
-		 * inode (and have a generation number smaller than our current
-		 * transaction id).
-		 */
-		need_find_last_extent = false;
-	}
-
-	/*
-	 * Because we use btrfs_search_forward we could skip leaves that were
-	 * not modified and then assume *last_extent is valid when it really
-	 * isn't.  So back up to the previous leaf and read the end of the last
-	 * extent before we go and fill in holes.
-	 */
-	if (need_find_last_extent) {
-		u64 len;
-
-		ret = btrfs_prev_leaf(inode->root, src_path);
-		if (ret < 0)
-			return ret;
-		if (ret)
-			goto fill_holes;
-		if (src_path->slots[0])
-			src_path->slots[0]--;
-		src = src_path->nodes[0];
-		btrfs_item_key_to_cpu(src, &key, src_path->slots[0]);
-		if (key.objectid != btrfs_ino(inode) ||
-		    key.type != BTRFS_EXTENT_DATA_KEY)
-			goto fill_holes;
-		extent = btrfs_item_ptr(src, src_path->slots[0],
-					struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(src, extent) ==
-		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_ram_bytes(src, extent);
-			*last_extent = ALIGN(key.offset + len,
-					     fs_info->sectorsize);
-		} else {
-			len = btrfs_file_extent_num_bytes(src, extent);
-			*last_extent = key.offset + len;
-		}
-	}
-fill_holes:
-	/* So we did prev_leaf, now we need to move to the next leaf, but a few
-	 * things could have happened
-	 *
-	 * 1) A merge could have happened, so we could currently be on a leaf
-	 * that holds what we were copying in the first place.
-	 * 2) A split could have happened, and now not all of the items we want
-	 * are on the same leaf.
-	 *
-	 * So we need to adjust how we search for holes, we need to drop the
-	 * path and re-search for the first extent key we found, and then walk
-	 * forward until we hit the last one we copied.
-	 */
-	if (need_find_last_extent) {
-		/* btrfs_prev_leaf could return 1 without releasing the path */
-		btrfs_release_path(src_path);
-		ret = btrfs_search_slot(NULL, inode->root, &first_key,
-				src_path, 0, 0);
-		if (ret < 0)
-			return ret;
-		ASSERT(ret == 0);
-		src = src_path->nodes[0];
-		i = src_path->slots[0];
-	} else {
-		i = start_slot;
-	}
-
-	/*
-	 * Ok so here we need to go through and fill in any holes we may have
-	 * to make sure that holes are punched for those areas in case they had
-	 * extents previously.
-	 */
-	while (!done) {
-		u64 offset, len;
-		u64 extent_end;
-
-		if (i >= btrfs_header_nritems(src_path->nodes[0])) {
-			ret = btrfs_next_leaf(inode->root, src_path);
-			if (ret < 0)
-				return ret;
-			ASSERT(ret == 0);
-			src = src_path->nodes[0];
-			i = 0;
-			need_find_last_extent = true;
-		}
-
-		btrfs_item_key_to_cpu(src, &key, i);
-		if (!btrfs_comp_cpu_keys(&key, &last_key))
-			done = true;
-		if (key.objectid != btrfs_ino(inode) ||
-		    key.type != BTRFS_EXTENT_DATA_KEY) {
-			i++;
-			continue;
-		}
-		extent = btrfs_item_ptr(src, i, struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(src, extent) ==
-		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_ram_bytes(src, extent);
-			extent_end = ALIGN(key.offset + len,
-					   fs_info->sectorsize);
-		} else {
-			len = btrfs_file_extent_num_bytes(src, extent);
-			extent_end = key.offset + len;
-		}
-		i++;
-
-		if (*last_extent == key.offset) {
-			*last_extent = extent_end;
-			continue;
-		}
-		offset = *last_extent;
-		len = key.offset - *last_extent;
-		ret = btrfs_insert_file_extent(trans, log, btrfs_ino(inode),
-				offset, 0, 0, len, 0, len, 0, 0, 0);
-		if (ret)
-			break;
-		*last_extent = extent_end;
-	}
-
-	/*
-	 * Check if there is a hole between the last extent found in our leaf
-	 * and the first extent in the next leaf. If there is one, we need to
-	 * log an explicit hole so that at replay time we can punch the hole.
-	 */
-	if (ret == 0 &&
-	    key.objectid == btrfs_ino(inode) &&
-	    key.type == BTRFS_EXTENT_DATA_KEY &&
-	    i == btrfs_header_nritems(src_path->nodes[0])) {
-		ret = btrfs_next_leaf(inode->root, src_path);
-		need_find_last_extent = true;
-		if (ret > 0) {
-			ret = 0;
-		} else if (ret == 0) {
-			btrfs_item_key_to_cpu(src_path->nodes[0], &key,
-					      src_path->slots[0]);
-			if (key.objectid == btrfs_ino(inode) &&
-			    key.type == BTRFS_EXTENT_DATA_KEY &&
-			    *last_extent < key.offset) {
-				const u64 len = key.offset - *last_extent;
-
-				ret = btrfs_insert_file_extent(trans, log,
-							       btrfs_ino(inode),
-							       *last_extent, 0,
-							       0, len, 0, len,
-							       0, 0, 0);
-				*last_extent += len;
-			}
-		}
-	}
-	/*
-	 * Need to let the callers know we dropped the path so they should
-	 * re-search.
-	 */
-	if (!ret && need_find_last_extent)
-		ret = 1;
 	return ret;
 }
 

@@ -4425,7 +4241,7 @@ static int btrfs_log_prealloc_extents(st
 	const u64 i_size = i_size_read(&inode->vfs_inode);
 	const u64 ino = btrfs_ino(inode);
 	struct btrfs_path *dst_path = NULL;
-	u64 last_extent = (u64)-1;
+	bool dropped_extents = false;
 	int ins_nr = 0;
 	int start_slot;
 	int ret;

@@ -4447,8 +4263,7 @@ static int btrfs_log_prealloc_extents(st
 		if (slot >= btrfs_header_nritems(leaf)) {
 			if (ins_nr > 0) {
 				ret = copy_items(trans, inode, dst_path, path,
-						 &last_extent, start_slot,
-						 ins_nr, 1, 0);
+						 start_slot, ins_nr, 1, 0);
 				if (ret < 0)
 					goto out;
 				ins_nr = 0;

@@ -4472,8 +4287,7 @@ static int btrfs_log_prealloc_extents(st
 			path->slots[0]++;
 			continue;
 		}
-		if (last_extent == (u64)-1) {
-			last_extent = key.offset;
+		if (!dropped_extents) {
 			/*
 			 * Avoid logging extent items logged in past fsync calls
 			 * and leading to duplicate keys in the log tree.

@@ -4487,6 +4301,7 @@ static int btrfs_log_prealloc_extents(st
 			} while (ret == -EAGAIN);
 			if (ret)
 				goto out;
+			dropped_extents = true;
 		}
 		if (ins_nr == 0)
 			start_slot = slot;

@@ -4501,7 +4316,7 @@ static int btrfs_log_prealloc_extents(st
 		}
 	}
 	if (ins_nr > 0) {
-		ret = copy_items(trans, inode, dst_path, path, &last_extent,
+		ret = copy_items(trans, inode, dst_path, path,
 				 start_slot, ins_nr, 1, 0);
 		if (ret > 0)
 			ret = 0;

@@ -4688,13 +4503,8 @@ static int btrfs_log_all_xattrs(struct b
 
 		if (slot >= nritems) {
 			if (ins_nr > 0) {
-				u64 last_extent = 0;
-
 				ret = copy_items(trans, inode, dst_path, path,
-						 &last_extent, start_slot,
-						 ins_nr, 1, 0);
-				/* can't be 1, extent items aren't processed */
-				ASSERT(ret <= 0);
+						 start_slot, ins_nr, 1, 0);
 				if (ret < 0)
 					return ret;
 				ins_nr = 0;

@@ -4718,13 +4528,8 @@ static int btrfs_log_all_xattrs(struct b
 		cond_resched();
 	}
 	if (ins_nr > 0) {
-		u64 last_extent = 0;
-
 		ret = copy_items(trans, inode, dst_path, path,
-				 &last_extent, start_slot,
-				 ins_nr, 1, 0);
-		/* can't be 1, extent items aren't processed */
-		ASSERT(ret <= 0);
+				 start_slot, ins_nr, 1, 0);
 		if (ret < 0)
 			return ret;
 	}

@@ -4733,100 +4538,119 @@ static int btrfs_log_all_xattrs(struct b
 }
 
 /*
- * If the no holes feature is enabled we need to make sure any hole between the
- * last extent and the i_size of our inode is explicitly marked in the log. This
- * is to make sure that doing something like:
- *
- *      1) create file with 128Kb of data
- *      2) truncate file to 64Kb
- *      3) truncate file to 256Kb
- *      4) fsync file
- *      5) <crash/power failure>
- *      6) mount fs and trigger log replay
- *
- * Will give us a file with a size of 256Kb, the first 64Kb of data match what
- * the file had in its first 64Kb of data at step 1 and the last 192Kb of the
- * file correspond to a hole. The presence of explicit holes in a log tree is
- * what guarantees that log replay will remove/adjust file extent items in the
- * fs/subvol tree.
- *
- * Here we do not need to care about holes between extents, that is already done
- * by copy_items(). We also only need to do this in the full sync path, where we
- * lookup for extents from the fs/subvol tree only. In the fast path case, we
- * lookup the list of modified extent maps and if any represents a hole, we
- * insert a corresponding extent representing a hole in the log tree.
+ * When using the NO_HOLES feature if we punched a hole that causes the
+ * deletion of entire leafs or all the extent items of the first leaf (the one
+ * that contains the inode item and references) we may end up not processing
+ * any extents, because there are no leafs with a generation matching the
+ * current transaction that have extent items for our inode. So we need to find
+ * if any holes exist and then log them. We also need to log holes after any
+ * truncate operation that changes the inode's size.
  */
-static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
-				   struct btrfs_root *root,
-				   struct btrfs_inode *inode,
-				   struct btrfs_path *path)
+static int btrfs_log_holes(struct btrfs_trans_handle *trans,
+			   struct btrfs_root *root,
+			   struct btrfs_inode *inode,
+			   struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	int ret;
 	struct btrfs_key key;
-	u64 hole_start;
-	u64 hole_size;
-	struct extent_buffer *leaf;
-	struct btrfs_root *log = root->log_root;
 	const u64 ino = btrfs_ino(inode);
 	const u64 i_size = i_size_read(&inode->vfs_inode);
+	u64 prev_extent_end = 0;
+	int ret;
 
-	if (!btrfs_fs_incompat(fs_info, NO_HOLES))
+	if (!btrfs_fs_incompat(fs_info, NO_HOLES) || i_size == 0)
 		return 0;
 
 	key.objectid = ino;
 	key.type = BTRFS_EXTENT_DATA_KEY;
-	key.offset = (u64)-1;
+	key.offset = 0;
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	ASSERT(ret != 0);
 	if (ret < 0)
 		return ret;
 
-	ASSERT(path->slots[0] > 0);
-	path->slots[0]--;
-	leaf = path->nodes[0];
-	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-
-	if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) {
-		/* inode does not have any extents */
-		hole_start = 0;
-		hole_size = i_size;
-	} else {
+	while (true) {
 		struct btrfs_file_extent_item *extent;
+		struct extent_buffer *leaf = path->nodes[0];
 		u64 len;
 
-		/*
-		 * If there's an extent beyond i_size, an explicit hole was
-		 * already inserted by copy_items().
-		 */
-		if (key.offset >= i_size)
-			return 0;
+		if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				return ret;
+			if (ret > 0) {
+				ret = 0;
+				break;
+			}
+			leaf = path->nodes[0];
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+		if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY)
+			break;
+
+		/* We have a hole, log it. */
+		if (prev_extent_end < key.offset) {
+			const u64 hole_len = key.offset - prev_extent_end;
+
+			/*
+			 * Release the path to avoid deadlocks with other code
+			 * paths that search the root while holding locks on
+			 * leafs from the log root.
+			 */
+			btrfs_release_path(path);
+			ret = btrfs_insert_file_extent(trans, root->log_root,
+						       ino, prev_extent_end, 0,
+						       0, hole_len, 0, hole_len,
+						       0, 0, 0);
+			if (ret < 0)
+				return ret;
+
+			/*
+			 * Search for the same key again in the root. Since it's
+			 * an extent item and we are holding the inode lock, the
+			 * key must still exist. If it doesn't just emit warning
+			 * and return an error to fall back to a transaction
+			 * commit.
+			 */
+			ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+			if (ret < 0)
+				return ret;
+			if (WARN_ON(ret > 0))
+				return -ENOENT;
+			leaf = path->nodes[0];
+		}
 
 		extent = btrfs_item_ptr(leaf, path->slots[0],
 					struct btrfs_file_extent_item);
-
 		if (btrfs_file_extent_type(leaf, extent) ==
-		    BTRFS_FILE_EXTENT_INLINE)
-			return 0;
+		    BTRFS_FILE_EXTENT_INLINE) {
+			len = btrfs_file_extent_ram_bytes(leaf, extent);
+			prev_extent_end = ALIGN(key.offset + len,
+						fs_info->sectorsize);
+		} else {
+			len = btrfs_file_extent_num_bytes(leaf, extent);
+			prev_extent_end = key.offset + len;
+		}
 
-		len = btrfs_file_extent_num_bytes(leaf, extent);
-		/* Last extent goes beyond i_size, no need to log a hole. */
-		if (key.offset + len > i_size)
-			return 0;
-		hole_start = key.offset + len;
-		hole_size = i_size - hole_start;
+		path->slots[0]++;
+		cond_resched();
 	}
-	btrfs_release_path(path);
 
-	/* Last extent ends at i_size. */
-	if (hole_size == 0)
-		return 0;
+	if (prev_extent_end < i_size) {
+		u64 hole_len;
 
-	hole_size = ALIGN(hole_size, fs_info->sectorsize);
-	ret = btrfs_insert_file_extent(trans, log, ino, hole_start, 0, 0,
-				       hole_size, 0, hole_size, 0, 0, 0);
-	return ret;
+		btrfs_release_path(path);
+		hole_len = ALIGN(i_size - prev_extent_end, fs_info->sectorsize);
+		ret = btrfs_insert_file_extent(trans, root->log_root,
+					       ino, prev_extent_end, 0, 0,
+					       hole_len, 0, hole_len,
+					       0, 0, 0);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
 }
 
 /*

@@ -5129,7 +4953,6 @@ static int btrfs_log_inode(struct btrfs_
 	struct btrfs_key min_key;
 	struct btrfs_key max_key;
 	struct btrfs_root *log = root->log_root;
-	u64 last_extent = 0;
 	int err = 0;
 	int ret;
 	int nritems;

@@ -5307,7 +5130,7 @@ again:
 					ins_start_slot = path->slots[0];
 				}
 				ret = copy_items(trans, inode, dst_path, path,
-						 &last_extent, ins_start_slot,
+						 ins_start_slot,
 						 ins_nr, inode_only,
 						 logged_isize);
 				if (ret < 0) {

@@ -5330,17 +5153,13 @@ again:
 			if (ins_nr == 0)
 				goto next_slot;
 			ret = copy_items(trans, inode, dst_path, path,
-					 &last_extent, ins_start_slot,
+					 ins_start_slot,
 					 ins_nr, inode_only, logged_isize);
 			if (ret < 0) {
 				err = ret;
 				goto out_unlock;
 			}
 			ins_nr = 0;
-			if (ret) {
-				btrfs_release_path(path);
-				continue;
-			}
 			goto next_slot;
 		}
 

@@ -5353,18 +5172,13 @@ again:
 			goto next_slot;
 		}
 
-		ret = copy_items(trans, inode, dst_path, path, &last_extent,
+		ret = copy_items(trans, inode, dst_path, path,
 				 ins_start_slot, ins_nr, inode_only,
 				 logged_isize);
 		if (ret < 0) {
 			err = ret;
 			goto out_unlock;
 		}
-		if (ret) {
-			ins_nr = 0;
-			btrfs_release_path(path);
-			continue;
-		}
 		ins_nr = 1;
 		ins_start_slot = path->slots[0];
 next_slot:

@@ -5378,13 +5192,12 @@ next_slot:
 		}
 		if (ins_nr) {
 			ret = copy_items(trans, inode, dst_path, path,
-					 &last_extent, ins_start_slot,
+					 ins_start_slot,
 					 ins_nr, inode_only, logged_isize);
 			if (ret < 0) {
 				err = ret;
 				goto out_unlock;
 			}
-			ret = 0;
 			ins_nr = 0;
 		}
 		btrfs_release_path(path);

@@ -5399,14 +5212,13 @@ next_key:
 		}
 	}
 	if (ins_nr) {
-		ret = copy_items(trans, inode, dst_path, path, &last_extent,
+		ret = copy_items(trans, inode, dst_path, path,
 				 ins_start_slot, ins_nr, inode_only,
 				 logged_isize);
 		if (ret < 0) {
 			err = ret;
 			goto out_unlock;
 		}
-		ret = 0;
 		ins_nr = 0;
 	}
 

@@ -5419,7 +5231,7 @@ next_key:
 	if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
 		btrfs_release_path(path);
 		btrfs_release_path(dst_path);
-		err = btrfs_log_trailing_hole(trans, root, inode, path);
+		err = btrfs_log_holes(trans, root, inode, path);
 		if (err)
 			goto out_unlock;
 	}

@@ -3244,6 +3244,7 @@ static void btrfs_double_extent_lock(str
 static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len,
 				   struct inode *dst, u64 dst_loff)
 {
+	const u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
 	int ret;
 
 	/*

@@ -3251,7 +3252,7 @@ static int btrfs_extent_same_range(struc
 	 * source range to serialize with relocation.
 	 */
 	btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
-	ret = btrfs_clone(src, dst, loff, len, len, dst_loff, 1);
+	ret = btrfs_clone(src, dst, loff, len, ALIGN(len, bs), dst_loff, 1);
 	btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
 
 	return ret;

@@ -4855,6 +4855,50 @@ static int log_conflicting_inodes(struct
 			continue;
 		}
 		/*
+		 * If the inode was already logged skip it - otherwise we can
+		 * hit an infinite loop. Example:
+		 *
+		 * From the commit root (previous transaction) we have the
+		 * following inodes:
+		 *
+		 * inode 257 a directory
+		 * inode 258 with references "zz" and "zz_link" on inode 257
+		 * inode 259 with reference "a" on inode 257
+		 *
+		 * And in the current (uncommitted) transaction we have:
+		 *
+		 * inode 257 a directory, unchanged
+		 * inode 258 with references "a" and "a2" on inode 257
+		 * inode 259 with reference "zz_link" on inode 257
+		 * inode 261 with reference "zz" on inode 257
+		 *
+		 * When logging inode 261 the following infinite loop could
+		 * happen if we don't skip already logged inodes:
+		 *
+		 * - we detect inode 258 as a conflicting inode, with inode 261
+		 *   on reference "zz", and log it;
+		 *
+		 * - we detect inode 259 as a conflicting inode, with inode 258
+		 *   on reference "a", and log it;
+		 *
+		 * - we detect inode 258 as a conflicting inode, with inode 259
+		 *   on reference "zz_link", and log it - again! After this we
+		 *   repeat the above steps forever.
+		 */
+		spin_lock(&BTRFS_I(inode)->lock);
+		/*
+		 * Check the inode's logged_trans only instead of
+		 * btrfs_inode_in_log(). This is because the last_log_commit of
+		 * the inode is not updated when we only log that it exists and
+		 * and it has the full sync bit set (see btrfs_log_inode()).
+		 */
+		if (BTRFS_I(inode)->logged_trans == trans->transid) {
+			spin_unlock(&BTRFS_I(inode)->lock);
+			btrfs_add_delayed_iput(inode);
+			continue;
+		}
+		spin_unlock(&BTRFS_I(inode)->lock);
+		/*
 		 * We are safe logging the other inode without acquiring its
 		 * lock as long as we log with the LOG_INODE_EXISTS mode. We
 		 * are safe against concurrent renames of the other inode as

@@ -1949,6 +1949,14 @@ int btrfs_commit_transaction(struct btrf
 	struct btrfs_transaction *prev_trans = NULL;
 	int ret;
 
+	/*
+	 * Some places just start a transaction to commit it.  We need to make
+	 * sure that if this commit fails that the abort code actually marks the
+	 * transaction as failed, so set trans->dirty to make the abort code do
+	 * the right thing.
+	 */
+	trans->dirty = true;
+
 	/* Stop the commit early if ->aborted is set */
 	if (unlikely(READ_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;

@@ -77,13 +77,14 @@ void btrfs_put_transaction(struct btrfs_
 	}
 }
 
-static noinline void switch_commit_roots(struct btrfs_transaction *trans)
+static noinline void switch_commit_roots(struct btrfs_trans_handle *trans)
 {
+	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root, *tmp;
 
 	down_write(&fs_info->commit_root_sem);
-	list_for_each_entry_safe(root, tmp, &trans->switch_commits,
+	list_for_each_entry_safe(root, tmp, &cur_trans->switch_commits,
 				 dirty_list) {
 		list_del_init(&root->dirty_list);
 		free_extent_buffer(root->commit_root);

@@ -95,16 +96,17 @@ static noinline void switch_commit_roots
 	}
 
 	/* We can free old roots now. */
-	spin_lock(&trans->dropped_roots_lock);
-	while (!list_empty(&trans->dropped_roots)) {
-		root = list_first_entry(&trans->dropped_roots,
+	spin_lock(&cur_trans->dropped_roots_lock);
+	while (!list_empty(&cur_trans->dropped_roots)) {
+		root = list_first_entry(&cur_trans->dropped_roots,
 					struct btrfs_root, root_list);
 		list_del_init(&root->root_list);
-		spin_unlock(&trans->dropped_roots_lock);
+		spin_unlock(&cur_trans->dropped_roots_lock);
+		btrfs_free_log(trans, root);
 		btrfs_drop_and_free_fs_root(fs_info, root);
-		spin_lock(&trans->dropped_roots_lock);
+		spin_lock(&cur_trans->dropped_roots_lock);
 	}
-	spin_unlock(&trans->dropped_roots_lock);
+	spin_unlock(&cur_trans->dropped_roots_lock);
 	up_write(&fs_info->commit_root_sem);
 }
 

@@ -1359,7 +1361,7 @@ static int qgroup_account_snapshot(struc
 	ret = commit_cowonly_roots(trans);
 	if (ret)
 		goto out;
-	switch_commit_roots(trans->transaction);
+	switch_commit_roots(trans);
 	ret = btrfs_write_and_wait_transaction(trans);
 	if (ret)
 		btrfs_handle_fs_error(fs_info, ret,

@@ -2245,7 +2247,7 @@ int btrfs_commit_transaction(struct btrf
 	list_add_tail(&fs_info->chunk_root->dirty_list,
 		      &cur_trans->switch_commits);
 
-	switch_commit_roots(cur_trans);
+	switch_commit_roots(trans);
 
 	ASSERT(list_empty(&cur_trans->dirty_bgs));
 	ASSERT(list_empty(&cur_trans->io_bgs));

@@ -330,12 +330,10 @@ u64 btrfs_get_tree_mod_seq(struct btrfs_
 			   struct seq_list *elem)
 {
 	write_lock(&fs_info->tree_mod_log_lock);
-	spin_lock(&fs_info->tree_mod_seq_lock);
 	if (!elem->seq) {
 		elem->seq = btrfs_inc_tree_mod_seq(fs_info);
 		list_add_tail(&elem->list, &fs_info->tree_mod_seq_list);
 	}
-	spin_unlock(&fs_info->tree_mod_seq_lock);
 	write_unlock(&fs_info->tree_mod_log_lock);
 
 	return elem->seq;

@@ -355,7 +353,7 @@ void btrfs_put_tree_mod_seq(struct btrfs
 	if (!seq_putting)
 		return;
 
-	spin_lock(&fs_info->tree_mod_seq_lock);
+	write_lock(&fs_info->tree_mod_log_lock);
 	list_del(&elem->list);
 	elem->seq = 0;
 

@@ -366,19 +364,17 @@ void btrfs_put_tree_mod_seq(struct btrfs
 				 * blocker with lower sequence number exists, we
 				 * cannot remove anything from the log
 				 */
-				spin_unlock(&fs_info->tree_mod_seq_lock);
+				write_unlock(&fs_info->tree_mod_log_lock);
 				return;
 			}
 			min_seq = cur_elem->seq;
 		}
 	}
-	spin_unlock(&fs_info->tree_mod_seq_lock);
 
 	/*
 	 * anything that's lower than the lowest existing (read: blocked)
 	 * sequence number can be removed from the tree.
 	 */
-	write_lock(&fs_info->tree_mod_log_lock);
 	tm_root = &fs_info->tree_mod_log;
 	for (node = rb_first(tm_root); node; node = next) {
 		next = rb_next(node);

@@ -671,14 +671,12 @@ struct btrfs_fs_info {
 	atomic_t nr_delayed_iputs;
 	wait_queue_head_t delayed_iputs_wait;
 
-	/* this protects tree_mod_seq_list */
-	spinlock_t tree_mod_seq_lock;
 	atomic64_t tree_mod_seq;
-	struct list_head tree_mod_seq_list;
 
-	/* this protects tree_mod_log */
+	/* this protects tree_mod_log and tree_mod_seq_list */
 	rwlock_t tree_mod_log_lock;
 	struct rb_root tree_mod_log;
+	struct list_head tree_mod_seq_list;
 
 	atomic_t async_delalloc_pages;
 

@@ -492,7 +492,7 @@ void btrfs_merge_delayed_refs(struct btr
 	if (head->is_data)
 		return;
 
-	spin_lock(&fs_info->tree_mod_seq_lock);
+	read_lock(&fs_info->tree_mod_log_lock);
 	if (!list_empty(&fs_info->tree_mod_seq_list)) {
 		struct seq_list *elem;
 

@@ -500,7 +500,7 @@ void btrfs_merge_delayed_refs(struct btr
 					struct seq_list, list);
 		seq = elem->seq;
 	}
-	spin_unlock(&fs_info->tree_mod_seq_lock);
+	read_unlock(&fs_info->tree_mod_log_lock);
 
 again:
 	for (node = rb_first_cached(&head->ref_tree); node;

@@ -518,7 +518,7 @@ int btrfs_check_delayed_seq(struct btrfs
 	struct seq_list *elem;
 	int ret = 0;
 
-	spin_lock(&fs_info->tree_mod_seq_lock);
+	read_lock(&fs_info->tree_mod_log_lock);
 	if (!list_empty(&fs_info->tree_mod_seq_list)) {
 		elem = list_first_entry(&fs_info->tree_mod_seq_list,
 					struct seq_list, list);

@@ -531,7 +531,7 @@ int btrfs_check_delayed_seq(struct btrfs
 		}
 	}
 
-	spin_unlock(&fs_info->tree_mod_seq_lock);
+	read_unlock(&fs_info->tree_mod_log_lock);
 	return ret;
 }
 

@@ -2652,7 +2652,6 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
 	spin_lock_init(&fs_info->defrag_inodes_lock);
-	spin_lock_init(&fs_info->tree_mod_seq_lock);
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->buffer_lock);
 	spin_lock_init(&fs_info->unused_bgs_lock);

@@ -121,7 +121,6 @@ struct btrfs_fs_info *btrfs_alloc_dummy_
 	spin_lock_init(&fs_info->qgroup_lock);
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
-	spin_lock_init(&fs_info->tree_mod_seq_lock);
 	mutex_init(&fs_info->qgroup_ioctl_lock);
 	mutex_init(&fs_info->qgroup_rescan_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);

@@ -4185,7 +4185,16 @@ retry:
 		 */
 		scanned = 1;
 		index = 0;
-		goto retry;
+
+		/*
+		 * If we're looping we could run into a page that is locked by a
+		 * writer and that writer could be waiting on writeback for a
+		 * page in our current bio, and thus deadlock, so flush the
+		 * write bio here.
+		 */
+		ret = flush_write_bio(epd);
+		if (!ret)
+			goto retry;
 	}
 
 	if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))

@@ -1583,21 +1583,25 @@ void find_first_clear_extent_bit(struct
 	/* Find first extent with bits cleared */
 	while (1) {
 		node = __etree_search(tree, start, &next, &prev, NULL, NULL);
-		if (!node) {
+		if (!node && !next && !prev) {
+			/*
+			 * Tree is completely empty, send full range and let
+			 * caller deal with it
+			 */
+			*start_ret = 0;
+			*end_ret = -1;
+			goto out;
+		} else if (!node && !next) {
+			/*
+			 * We are past the last allocated chunk, set start at
+			 * the end of the last extent.
+			 */
+			state = rb_entry(prev, struct extent_state, rb_node);
+			*start_ret = state->end + 1;
+			*end_ret = -1;
+			goto out;
+		} else if (!node) {
 			node = next;
-			if (!node) {
-				/*
-				 * We are past the last allocated chunk,
-				 * set start at the end of the last extent. The
-				 * device alloc tree should never be empty so
-				 * prev is always set.
-				 */
-				ASSERT(prev);
-				state = rb_entry(prev, struct extent_state, rb_node);
-				*start_ret = state->end + 1;
-				*end_ret = -1;
-				goto out;
-			}
 		}
 		/*
 		 * At this point 'node' either contains 'start' or start is

@@ -441,8 +441,17 @@ static int test_find_first_clear_extent_
 	int ret = -EINVAL;
 
 	test_msg("running find_first_clear_extent_bit test");
+
 	extent_io_tree_init(NULL, &tree, IO_TREE_SELFTEST, NULL);
 
+	/* Test correct handling of empty tree */
+	find_first_clear_extent_bit(&tree, 0, &start, &end, CHUNK_TRIMMED);
+	if (start != 0 || end != -1) {
+		test_err(
+	"error getting a range from completely empty tree: start %llu end %llu",
+			 start, end);
+		goto out;
+	}
 	/*
 	 * Set 1M-4M alloc/discard and 32M-64M thus leaving a hole between
 	 * 4M-32M