5.19.17-rc1 review

@@ -5425,7 +5425,7 @@ int ext4_setattr(struct user_namespace *
 			return -EINVAL;
 		}
 
-		if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
+		if (attr->ia_size != inode->i_size)
 			inode_inc_iversion(inode);
 
 		if (shrink) {

@@ -5735,8 +5735,7 @@ int ext4_mark_iloc_dirty(handle_t *handl
 	 * ea_inodes are using i_version for storing reference count, don't
 	 * mess with it
 	 */
-	if (IS_I_VERSION(inode) &&
-	    !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
+	if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
 		inode_inc_iversion(inode);
 
 	/* the do_update_inode consumes one bh->b_count */

@@ -1585,7 +1585,7 @@ enum {
 	Opt_inlinecrypt,
 	Opt_usrjquota, Opt_grpjquota, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
-	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version,
+	Opt_usrquota, Opt_grpquota, Opt_prjquota,
 	Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
 	Opt_nowarn_on_error, Opt_mblk_io_submit, Opt_debug_want_extra_isize,

@@ -1694,7 +1694,7 @@ static const struct fs_parameter_spec ex
 	fsparam_flag	("barrier",		Opt_barrier),
 	fsparam_u32	("barrier",		Opt_barrier),
 	fsparam_flag	("nobarrier",		Opt_nobarrier),
-	fsparam_flag	("i_version",		Opt_i_version),
+	fsparam_flag	("i_version",		Opt_removed),
 	fsparam_flag	("dax",			Opt_dax),
 	fsparam_enum	("dax",			Opt_dax_type, ext4_param_dax),
 	fsparam_u32	("stripe",		Opt_stripe),

@@ -2140,11 +2140,6 @@ static int ext4_parse_param(struct fs_co
 	case Opt_abort:
 		ctx_set_mount_flag(ctx, EXT4_MF_FS_ABORTED);
 		return 0;
-	case Opt_i_version:
-		ext4_msg(NULL, KERN_WARNING, deprecated_msg, param->key, "5.20");
-		ext4_msg(NULL, KERN_WARNING, "Use iversion instead\n");
-		ctx_set_flags(ctx, SB_I_VERSION);
-		return 0;
 	case Opt_inlinecrypt:
 #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
 		ctx_set_flags(ctx, SB_INLINECRYPT);

@@ -2814,14 +2809,6 @@ static void ext4_apply_options(struct fs
 	sb->s_flags &= ~ctx->mask_s_flags;
 	sb->s_flags |= ctx->vals_s_flags;
 
-	/*
-	 * i_version differs from common mount option iversion so we have
-	 * to let vfs know that it was set, otherwise it would get cleared
-	 * on remount
-	 */
-	if (ctx->mask_s_flags & SB_I_VERSION)
-		fc->sb_flags |= SB_I_VERSION;
-
 #define APPLY(X) ({ if (ctx->spec & EXT4_SPEC_##X) sbi->X = ctx->X; })
 	APPLY(s_commit_interval);
 	APPLY(s_stripe);

@@ -2970,8 +2957,6 @@ static int _ext4_show_options(struct seq
 		SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
 	if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
 		SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
-	if (sb->s_flags & SB_I_VERSION)
-		SEQ_OPTS_PUTS("i_version");
 	if (nodefs || sbi->s_stripe)
 		SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
 	if (nodefs || EXT4_MOUNT_DATA_FLAGS &

@@ -4631,6 +4616,9 @@ static int __ext4_fill_super(struct fs_c
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
 		(test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
 
+	/* i_version is always enabled now */
+	sb->s_flags |= SB_I_VERSION;
+
 	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
 	    (ext4_has_compat_features(sb) ||
 	     ext4_has_ro_compat_features(sb) ||

@@ -205,19 +205,12 @@ int ext4_read_bh(struct buffer_head *bh,
 
 int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait)
 {
-	if (trylock_buffer(bh)) {
-		if (wait)
-			return ext4_read_bh(bh, op_flags, NULL);
+	lock_buffer(bh);
+	if (!wait) {
 		ext4_read_bh_nowait(bh, op_flags, NULL);
 		return 0;
 	}
-	if (wait) {
-		wait_on_buffer(bh);
-		if (buffer_uptodate(bh))
-			return 0;
-		return -EIO;
-	}
-	return 0;
+	return ext4_read_bh(bh, op_flags, NULL);
 }
 
 /*

@@ -264,7 +257,8 @@ void ext4_sb_breadahead_unmovable(struct
 	struct buffer_head *bh = sb_getblk_gfp(sb, block, 0);
 
 	if (likely(bh)) {
-		ext4_read_bh_lock(bh, REQ_RAHEAD, false);
+		if (trylock_buffer(bh))
+			ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL);
 		brelse(bh);
 	}
 }

@@ -1188,6 +1188,13 @@ retry_grab:
 	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
+	/*
+	 * The same as page allocation, we prealloc buffer heads before
+	 * starting the handle.
+	 */
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, inode->i_sb->s_blocksize, 0);
+
 	unlock_page(page);
 
 retry_journal:

@@ -5347,6 +5347,7 @@ int ext4_setattr(struct user_namespace *
 	int error, rc = 0;
 	int orphan = 0;
 	const unsigned int ia_valid = attr->ia_valid;
+	bool inc_ivers = true;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;

@@ -5432,8 +5433,8 @@ int ext4_setattr(struct user_namespace *
 			return -EINVAL;
 		}
 
-		if (attr->ia_size != inode->i_size)
-			inode_inc_iversion(inode);
+		if (attr->ia_size == inode->i_size)
+			inc_ivers = false;
 
 		if (shrink) {
 			if (ext4_should_order_data(inode)) {

@@ -5535,6 +5536,8 @@ out_mmap_sem:
 	}
 
 	if (!error) {
+		if (inc_ivers)
+			inode_inc_iversion(inode);
 		setattr_copy(mnt_userns, inode, attr);
 		mark_inode_dirty(inode);
 	}

@@ -5738,13 +5741,6 @@ int ext4_mark_iloc_dirty(handle_t *handl
 	}
 	ext4_fc_track_inode(handle, inode);
 
-	/*
-	 * ea_inodes are using i_version for storing reference count, don't
-	 * mess with it
-	 */
-	if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
-		inode_inc_iversion(inode);
-
 	/* the do_update_inode consumes one bh->b_count */
 	get_bh(iloc->bh);
 

@@ -442,6 +442,7 @@ static long swap_inode_boot_loader(struc
 	swap_inode_data(inode, inode_bl);
 
 	inode->i_ctime = inode_bl->i_ctime = current_time(inode);
+	inode_inc_iversion(inode);
 
 	inode->i_generation = prandom_u32();
 	inode_bl->i_generation = prandom_u32();

@@ -655,6 +656,7 @@ static int ext4_ioctl_setflags(struct in
 	ext4_set_inode_flags(inode, false);
 
 	inode->i_ctime = current_time(inode);
+	inode_inc_iversion(inode);
 
 	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 flags_err:

@@ -765,6 +767,7 @@ static int ext4_ioctl_setproject(struct
 
 	EXT4_I(inode)->i_projid = kprojid;
 	inode->i_ctime = current_time(inode);
+	inode_inc_iversion(inode);
 out_dirty:
 	rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
 	if (!err)

@@ -1178,6 +1181,7 @@ static long __ext4_ioctl(struct file *fi
 		err = ext4_reserve_inode_write(handle, inode, &iloc);
 		if (err == 0) {
 			inode->i_ctime = current_time(inode);
+			inode_inc_iversion(inode);
 			inode->i_generation = generation;
 			err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 		}

@@ -2412,6 +2412,7 @@ retry_inode:
 	if (!error) {
 		ext4_xattr_update_super_block(handle, inode->i_sb);
 		inode->i_ctime = current_time(inode);
+		inode_inc_iversion(inode);
 		if (!value)
 			no_expand = 0;
 		error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);

@@ -85,15 +85,20 @@ static struct buffer_head *ext4_append(h
 		return bh;
 	inode->i_size += inode->i_sb->s_blocksize;
 	EXT4_I(inode)->i_disksize = inode->i_size;
+	err = ext4_mark_inode_dirty(handle, inode);
+	if (err)
+		goto out;
 	BUFFER_TRACE(bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, inode->i_sb, bh,
 					    EXT4_JTR_NONE);
-	if (err) {
-		brelse(bh);
-		ext4_std_error(inode->i_sb, err);
-		return ERR_PTR(err);
-	}
+	if (err)
+		goto out;
 	return bh;
+
+out:
+	brelse(bh);
+	ext4_std_error(inode->i_sb, err);
+	return ERR_PTR(err);
 }
 
 static int ext4_dx_csum_verify(struct inode *inode,

@@ -874,22 +874,25 @@ static int ext4_fc_write_inode(struct in
 	tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_INODE);
 	tl.fc_len = cpu_to_le16(inode_len + sizeof(fc_inode.fc_ino));
 
+	ret = -ECANCELED;
 	dst = ext4_fc_reserve_space(inode->i_sb,
 			sizeof(tl) + inode_len + sizeof(fc_inode.fc_ino), crc);
 	if (!dst)
-		return -ECANCELED;
+		goto err;
 
 	if (!ext4_fc_memcpy(inode->i_sb, dst, &tl, sizeof(tl), crc))
-		return -ECANCELED;
+		goto err;
 	dst += sizeof(tl);
 	if (!ext4_fc_memcpy(inode->i_sb, dst, &fc_inode, sizeof(fc_inode), crc))
-		return -ECANCELED;
+		goto err;
 	dst += sizeof(fc_inode);
 	if (!ext4_fc_memcpy(inode->i_sb, dst, (u8 *)ext4_raw_inode(&iloc),
 					inode_len, crc))
-		return -ECANCELED;
-
-	return 0;
+		goto err;
+	ret = 0;
+err:
+	brelse(iloc.bh);
+	return ret;
 }
 
 /*

@@ -1494,13 +1494,15 @@ static int ext4_fc_record_modified_inode
 		if (state->fc_modified_inodes[i] == ino)
 			return 0;
 	if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) {
-		state->fc_modified_inodes = krealloc(
-				state->fc_modified_inodes,
+		int *fc_modified_inodes;
+
+		fc_modified_inodes = krealloc(state->fc_modified_inodes,
 				sizeof(int) * (state->fc_modified_inodes_size +
 				EXT4_FC_REPLAY_REALLOC_INCREMENT),
 				GFP_KERNEL);
-		if (!state->fc_modified_inodes)
+		if (!fc_modified_inodes)
 			return -ENOMEM;
+		state->fc_modified_inodes = fc_modified_inodes;
 		state->fc_modified_inodes_size +=
 			EXT4_FC_REPLAY_REALLOC_INCREMENT;
 	}

@@ -1687,15 +1687,17 @@ int ext4_fc_record_regions(struct super_
 	if (replay && state->fc_regions_used != state->fc_regions_valid)
 		state->fc_regions_used = state->fc_regions_valid;
 	if (state->fc_regions_used == state->fc_regions_size) {
+		struct ext4_fc_alloc_region *fc_regions;
+
 		state->fc_regions_size +=
 			EXT4_FC_REPLAY_REALLOC_INCREMENT;
-		state->fc_regions = krealloc(
-					state->fc_regions,
-					state->fc_regions_size *
-					sizeof(struct ext4_fc_alloc_region),
-					GFP_KERNEL);
-		if (!state->fc_regions)
+		fc_regions = krealloc(state->fc_regions,
+				      state->fc_regions_size *
+				      sizeof(struct ext4_fc_alloc_region),
+				      GFP_KERNEL);
+		if (!fc_regions)
 			return -ENOMEM;
+		state->fc_regions = fc_regions;
 	}
 	region = &state->fc_regions[state->fc_regions_used++];
 	region->ino = ino;

@@ -1689,14 +1689,15 @@ int ext4_fc_record_regions(struct super_
 	if (state->fc_regions_used == state->fc_regions_size) {
 		struct ext4_fc_alloc_region *fc_regions;
 
-		state->fc_regions_size +=
-			EXT4_FC_REPLAY_REALLOC_INCREMENT;
 		fc_regions = krealloc(state->fc_regions,
-				      state->fc_regions_size *
-				      sizeof(struct ext4_fc_alloc_region),
+				      sizeof(struct ext4_fc_alloc_region) *
+				      (state->fc_regions_size +
+				       EXT4_FC_REPLAY_REALLOC_INCREMENT),
 				      GFP_KERNEL);
 		if (!fc_regions)
 			return -ENOMEM;
+		state->fc_regions_size +=
+			EXT4_FC_REPLAY_REALLOC_INCREMENT;
 		state->fc_regions = fc_regions;
 	}
 	region = &state->fc_regions[state->fc_regions_used++];

@@ -610,9 +610,23 @@ void klp_reverse_transition(void)
 /* Called from copy_process() during fork */
 void klp_copy_process(struct task_struct *child)
 {
-	child->patch_state = current->patch_state;
 
-	/* TIF_PATCH_PENDING gets copied in setup_thread_stack() */
+	/*
+	 * The parent process may have gone through a KLP transition since
+	 * the thread flag was copied in setup_thread_stack earlier. Bring
+	 * the task flag up to date with the parent here.
+	 *
+	 * The operation is serialized against all klp_*_transition()
+	 * operations by the tasklist_lock. The only exception is
+	 * klp_update_patch_state(current), but we cannot race with
+	 * that because we are current.
+	 */
+	if (test_tsk_thread_flag(current, TIF_PATCH_PENDING))
+		set_tsk_thread_flag(child, TIF_PATCH_PENDING);
+	else
+		clear_tsk_thread_flag(child, TIF_PATCH_PENDING);
+
+	child->patch_state = current->patch_state;
 }
 
 /*

@@ -6037,8 +6037,12 @@ int ftrace_regex_release(struct inode *i
 
 		if (filter_hash) {
 			orig_hash = &iter->ops->func_hash->filter_hash;
-			if (iter->tr && !list_empty(&iter->tr->mod_trace))
-				iter->hash->flags |= FTRACE_HASH_FL_MOD;
+			if (iter->tr) {
+				if (list_empty(&iter->tr->mod_trace))
+					iter->hash->flags &= ~FTRACE_HASH_FL_MOD;
+				else
+					iter->hash->flags |= FTRACE_HASH_FL_MOD;
+			}
 		} else
 			orig_hash = &iter->ops->func_hash->notrace_hash;
 

@@ -1644,6 +1644,18 @@ ftrace_find_tramp_ops_any_other(struct d
 static struct ftrace_ops *
 ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops);
 
+static bool skip_record(struct dyn_ftrace *rec)
+{
+	/*
+	 * At boot up, weak functions are set to disable. Function tracing
+	 * can be enabled before they are, and they still need to be disabled now.
+	 * If the record is disabled, still continue if it is marked as already
+	 * enabled (this is needed to keep the accounting working).
+	 */
+	return rec->flags & FTRACE_FL_DISABLED &&
+		!(rec->flags & FTRACE_FL_ENABLED);
+}
+
 static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				     int filter_hash,
 				     bool inc)

@@ -1693,7 +1705,7 @@ static bool __ftrace_hash_rec_update(str
 		int in_hash = 0;
 		int match = 0;
 
-		if (rec->flags & FTRACE_FL_DISABLED)
+		if (skip_record(rec))
 			continue;
 
 		if (all) {

@@ -2090,7 +2102,7 @@ static int ftrace_check_record(struct dy
 
 	ftrace_bug_type = FTRACE_BUG_UNKNOWN;
 
-	if (rec->flags & FTRACE_FL_DISABLED)
+	if (skip_record(rec))
 		return FTRACE_UPDATE_IGNORE;
 
 	/*

@@ -2205,7 +2217,7 @@ static int ftrace_check_record(struct dy
 	if (update) {
 		/* If there's no more users, clear all flags */
 		if (!ftrace_rec_count(rec))
-			rec->flags = 0;
+			rec->flags &= FTRACE_FL_DISABLED;
 		else
 			/*
 			 * Just disable the record, but keep the ops TRAMP

@@ -2599,7 +2611,7 @@ void __weak ftrace_replace_code(int mod_
 
 	do_for_each_ftrace_rec(pg, rec) {
 
-		if (rec->flags & FTRACE_FL_DISABLED)
+		if (skip_record(rec))
 			continue;
 
 		failed = __ftrace_replace_code(rec, enable);

@@ -5616,7 +5616,15 @@ int ring_buffer_read_page(struct trace_b
 		unsigned int pos = 0;
 		unsigned int size;
 
-		if (full)
+		/*
+		 * If a full page is expected, this can still be returned
+		 * if there's been a previous partial read and the
+		 * rest of the page can be read and the commit page is off
+		 * the reader page.
+		 */
+		if (full &&
+		    (!read || (len < (commit - read)) ||
+		     cpu_buffer->reader_page == cpu_buffer->commit_page))
 			goto out_unlock;
 
 		if (len > (commit - read))

@@ -1011,7 +1011,7 @@ int ring_buffer_wait(struct trace_buffer
 			nr_pages = cpu_buffer->nr_pages;
 			dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
 			if (!cpu_buffer->shortest_full ||
-			    cpu_buffer->shortest_full < full)
+			    cpu_buffer->shortest_full > full)
 				cpu_buffer->shortest_full = full;
 			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 			if (!pagebusy &&

@@ -917,8 +917,9 @@ static void rb_wake_up_waiters(struct ir
 	struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
 
 	wake_up_all(&rbwork->waiters);
-	if (rbwork->wakeup_full) {
+	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
 		rbwork->wakeup_full = false;
+		rbwork->full_waiters_pending = false;
 		wake_up_all(&rbwork->full_waiters);
 	}
 }

@@ -101,7 +101,7 @@ __ring_buffer_alloc(unsigned long size,
 int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full);
 __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table);
-
+void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu);
 
 #define RING_BUFFER_ALL_CPUS -1
 

@@ -413,6 +413,7 @@ struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
 	wait_queue_head_t		full_waiters;
+	long				wait_index;
 	bool				waiters_pending;
 	bool				full_waiters_pending;
 	bool				wakeup_full;

@@ -925,6 +926,37 @@ static void rb_wake_up_waiters(struct ir
 }
 
 /**
+ * ring_buffer_wake_waiters - wake up any waiters on this ring buffer
+ * @buffer: The ring buffer to wake waiters on
+ *
+ * In the case of a file that represents a ring buffer is closing,
+ * it is prudent to wake up any waiters that are on this.
+ */
+void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct rb_irq_work *rbwork;
+
+	if (cpu == RING_BUFFER_ALL_CPUS) {
+
+		/* Wake up individual ones too. One level recursion */
+		for_each_buffer_cpu(buffer, cpu)
+			ring_buffer_wake_waiters(buffer, cpu);
+
+		rbwork = &buffer->irq_work;
+	} else {
+		cpu_buffer = buffer->buffers[cpu];
+		rbwork = &cpu_buffer->irq_work;
+	}
+
+	rbwork->wait_index++;
+	/* make sure the waiters see the new index */
+	smp_wmb();
+
+	rb_wake_up_waiters(&rbwork->work);
+}
+
+/**
  * ring_buffer_wait - wait for input to the ring buffer
  * @buffer: buffer to wait on
  * @cpu: the cpu buffer to wait on

@@ -939,6 +971,7 @@ int ring_buffer_wait(struct trace_buffer
 	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
 	struct rb_irq_work *work;
+	long wait_index;
 	int ret = 0;
 
 	/*

@@ -957,6 +990,7 @@ int ring_buffer_wait(struct trace_buffer
 		work = &cpu_buffer->irq_work;
 	}
 
+	wait_index = READ_ONCE(work->wait_index);
 
 	while (true) {
 		if (full)

@@ -1021,6 +1055,11 @@ int ring_buffer_wait(struct trace_buffer
 		}
 
 		schedule();
+
+		/* Make sure to see the new wait index */
+		smp_rmb();
+		if (wait_index != work->wait_index)
+			break;
 	}
 
 	if (full)

@@ -2648,6 +2648,9 @@ rb_reset_tail(struct ring_buffer_per_cpu
 		/* Mark the rest of the page with padding */
 		rb_event_set_padding(event);
 
+		/* Make sure the padding is visible before the write update */
+		smp_wmb();
+
 		/* Set the write back to the previous setting */
 		local_sub(length, &tail_page->write);
 		return;

@@ -2659,6 +2662,9 @@ rb_reset_tail(struct ring_buffer_per_cpu
 	/* time delta must be non zero */
 	event->time_delta = 1;
 
+	/* Make sure the padding is visible before the tail_page->write update */
+	smp_wmb();
+
 	/* Set write to end of buffer */
 	length = (tail + length) - BUF_PAGE_SIZE;
 	local_sub(length, &tail_page->write);

@@ -4627,6 +4633,33 @@ rb_get_reader_page(struct ring_buffer_pe
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
+	/*
+	 * The writer has preempt disable, wait for it. But not forever
+	 * Although, 1 second is pretty much "forever"
+	 */
+#define USECS_WAIT	1000000
+        for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) {
+		/* If the write is past the end of page, a writer is still updating it */
+		if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE))
+			break;
+
+		udelay(1);
+
+		/* Get the latest version of the reader write value */
+		smp_rmb();
+	}
+
+	/* The writer is not moving forward? Something is wrong */
+	if (RB_WARN_ON(cpu_buffer, nr_loops == USECS_WAIT))
+		reader = NULL;
+
+	/*
+	 * Make sure we see any padding after the write update
+	 * (see rb_reset_tail())
+	 */
+	smp_rmb();
+
+
 	return reader;
 }
 

@@ -1193,12 +1193,14 @@ void *tracing_cond_snapshot_data(struct
 {
 	void *cond_data = NULL;
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 
 	if (tr->cond_snapshot)
 		cond_data = tr->cond_snapshot->cond_data;
 
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 
 	return cond_data;
 }

@@ -1334,9 +1336,11 @@ int tracing_snapshot_cond_enable(struct
 		goto fail_unlock;
 	}
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 	tr->cond_snapshot = cond_snapshot;
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 
 	mutex_unlock(&trace_types_lock);
 

@@ -1363,6 +1367,7 @@ int tracing_snapshot_cond_disable(struct
 {
 	int ret = 0;
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 
 	if (!tr->cond_snapshot)

@@ -1373,6 +1378,7 @@ int tracing_snapshot_cond_disable(struct
 	}
 
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 
 	return ret;
 }

@@ -2200,6 +2206,11 @@ static size_t tgid_map_max;
 
 #define SAVED_CMDLINES_DEFAULT 128
 #define NO_CMDLINE_MAP UINT_MAX
+/*
+ * Preemption must be disabled before acquiring trace_cmdline_lock.
+ * The various trace_arrays' max_lock must be acquired in a context
+ * where interrupt is disabled.
+ */
 static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 struct saved_cmdlines_buffer {
 	unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];

@@ -2412,7 +2423,11 @@ static int trace_save_cmdline(struct tas
 	 * the lock, but we also don't want to spin
 	 * nor do we want to disable interrupts,
 	 * so if we miss here, then better luck next time.
+	 *
+	 * This is called within the scheduler and wake up, so interrupts
+	 * had better been disabled and run queue lock been held.
 	 */
+	lockdep_assert_preemption_disabled();
 	if (!arch_spin_trylock(&trace_cmdline_lock))
 		return 0;
 

@@ -5890,9 +5905,11 @@ tracing_saved_cmdlines_size_read(struct
 	char buf[64];
 	int r;
 
+	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 	r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
 	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }

@@ -5917,10 +5934,12 @@ static int tracing_resize_saved_cmdlines
 		return -ENOMEM;
 	}
 
+	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 	savedcmd_temp = savedcmd;
 	savedcmd = s;
 	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
 	free_saved_cmdlines_buffer(savedcmd_temp);
 
 	return 0;

@@ -6373,10 +6392,12 @@ int tracing_set_tracer(struct trace_arra
 
 #ifdef CONFIG_TRACER_SNAPSHOT
 	if (t->use_max_tr) {
+		local_irq_disable();
 		arch_spin_lock(&tr->max_lock);
 		if (tr->cond_snapshot)
 			ret = -EBUSY;
 		arch_spin_unlock(&tr->max_lock);
+		local_irq_enable();
 		if (ret)
 			goto out;
 	}

@@ -7436,10 +7457,12 @@ tracing_snapshot_write(struct file *filp
 		goto out;
 	}
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 	if (tr->cond_snapshot)
 		ret = -EBUSY;
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 	if (ret)
 		goto out;
 

@@ -92,6 +92,7 @@ struct trace_iterator {
 	unsigned int		temp_size;
 	char			*fmt;	/* modified format holder */
 	unsigned int		fmt_size;
+	long			wait_index;
 
 	/* trace_seq for __print_flags() and __print_symbolic() etc. */
 	struct trace_seq	tmp_seq;

@@ -8160,6 +8160,12 @@ static int tracing_buffers_release(struc
 
 	__trace_array_put(iter->tr);
 
+	iter->wait_index++;
+	/* Make sure the waiters see the new wait_index */
+	smp_wmb();
+
+	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
 	if (info->spare)
 		ring_buffer_free_read_page(iter->array_buffer->buffer,
 					   info->spare_cpu, info->spare);

@@ -8313,6 +8319,8 @@ tracing_buffers_splice_read(struct file
 
 	/* did we read anything? */
 	if (!spd.nr_pages) {
+		long wait_index;
+
 		if (ret)
 			goto out;
 

@@ -8320,10 +8328,17 @@ tracing_buffers_splice_read(struct file
 		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
 			goto out;
 
+		wait_index = READ_ONCE(iter->wait_index);
+
 		ret = wait_on_pipe(iter, iter->tr->buffer_percent);
 		if (ret)
 			goto out;
 
+		/* Make sure we see the new wait_index */
+		smp_rmb();
+		if (wait_index != iter->wait_index)
+			goto out;
+
 		goto again;
 	}
 

@@ -8334,6 +8334,10 @@ tracing_buffers_splice_read(struct file
 		if (ret)
 			goto out;
 
+		/* No need to wait after waking up when tracing is off */
+		if (!tracer_tracing_is_on(iter->tr))
+			goto out;
+
 		/* Make sure we see the new wait_index */
 		smp_rmb();
 		if (wait_index != iter->wait_index)

@@ -9043,6 +9047,8 @@ rb_simple_write(struct file *filp, const
 			tracer_tracing_off(tr);
 			if (tr->current_trace->stop)
 				tr->current_trace->stop(tr);
+			/* Wake up any waiters */
+			ring_buffer_wake_waiters(buffer, RING_BUFFER_ALL_CPUS);
 		}
 		mutex_unlock(&trace_types_lock);
 	}

@@ -8353,12 +8353,34 @@ out:
 	return ret;
 }
 
+/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */
+static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct ftrace_buffer_info *info = file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	if (cmd)
+		return -ENOIOCTLCMD;
+
+	mutex_lock(&trace_types_lock);
+
+	iter->wait_index++;
+	/* Make sure the waiters see the new wait_index */
+	smp_wmb();
+
+	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
+	mutex_unlock(&trace_types_lock);
+	return 0;
+}
+
 static const struct file_operations tracing_buffers_fops = {
 	.open		= tracing_buffers_open,
 	.read		= tracing_buffers_read,
 	.poll		= tracing_buffers_poll,
 	.release	= tracing_buffers_release,
 	.splice_read	= tracing_buffers_splice_read,
+	.unlocked_ioctl = tracing_buffers_ioctl,
 	.llseek		= no_llseek,
 };
 

@@ -6428,12 +6428,12 @@ int tracing_set_tracer(struct trace_arra
 	if (tr->current_trace->reset)
 		tr->current_trace->reset(tr);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+	had_max_tr = tr->current_trace->use_max_tr;
+
 	/* Current trace needs to be nop_trace before synchronize_rcu */
 	tr->current_trace = &nop_trace;
 
-#ifdef CONFIG_TRACER_MAX_TRACE
-	had_max_tr = tr->allocated_snapshot;
-
 	if (had_max_tr && !t->use_max_tr) {
 		/*
 		 * We need to make sure that the update_max_tr sees that

@@ -6446,11 +6446,13 @@ int tracing_set_tracer(struct trace_arra
 		free_snapshot(tr);
 	}
 
-	if (t->use_max_tr && !had_max_tr) {
+	if (t->use_max_tr && !tr->allocated_snapshot) {
 		ret = tracing_alloc_snapshot_instance(tr);
 		if (ret < 0)
 			goto out;
 	}
+#else
+	tr->current_trace = &nop_trace;
 #endif
 
 	if (t->init) {

@@ -16,6 +16,7 @@
 #include "trace_dynevent.h"
 #include "trace_probe.h"
 #include "trace_probe_tmpl.h"
+#include "trace_probe_kernel.h"
 
 #define EPROBE_EVENT_SYSTEM "eprobes"
 

@@ -452,29 +453,14 @@ NOKPROBE_SYMBOL(process_fetch_insn)
 static nokprobe_inline int
 fetch_store_strlen_user(unsigned long addr)
 {
-	const void __user *uaddr =  (__force const void __user *)addr;
-
-	return strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
+	return kern_fetch_store_strlen_user(addr);
 }
 
 /* Return the length of string -- including null terminal byte */
 static nokprobe_inline int
 fetch_store_strlen(unsigned long addr)
 {
-	int ret, len = 0;
-	u8 c;
-
-#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
-	if (addr < TASK_SIZE)
-		return fetch_store_strlen_user(addr);
-#endif
-
-	do {
-		ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
-		len++;
-	} while (c && ret == 0 && len < MAX_STRING_SIZE);
-
-	return (ret < 0) ? ret : len;
+	return kern_fetch_store_strlen(addr);
 }
 
 /*

@@ -484,21 +470,7 @@ fetch_store_strlen(unsigned long addr)
 static nokprobe_inline int
 fetch_store_string_user(unsigned long addr, void *dest, void *base)
 {
-	const void __user *uaddr =  (__force const void __user *)addr;
-	int maxlen = get_loc_len(*(u32 *)dest);
-	void *__dest;
-	long ret;
-
-	if (unlikely(!maxlen))
-		return -ENOMEM;
-
-	__dest = get_loc_data(dest, base);
-
-	ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
-	if (ret >= 0)
-		*(u32 *)dest = make_data_loc(ret, __dest - base);
-
-	return ret;
+	return kern_fetch_store_string_user(addr, dest, base);
 }
 
 /*

@@ -508,29 +480,7 @@ fetch_store_string_user(unsigned long ad
 static nokprobe_inline int
 fetch_store_string(unsigned long addr, void *dest, void *base)
 {
-	int maxlen = get_loc_len(*(u32 *)dest);
-	void *__dest;
-	long ret;
-
-#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
-	if ((unsigned long)addr < TASK_SIZE)
-		return fetch_store_string_user(addr, dest, base);
-#endif
-
-	if (unlikely(!maxlen))
-		return -ENOMEM;
-
-	__dest = get_loc_data(dest, base);
-
-	/*
-	 * Try to get string again, since the string can be changed while
-	 * probing.
-	 */
-	ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
-	if (ret >= 0)
-		*(u32 *)dest = make_data_loc(ret, __dest - base);
-
-	return ret;
+	return kern_fetch_store_string(addr, dest, base);
 }
 
 static nokprobe_inline int

90 lines not on this page · raw message

96 lines not on this page · raw message

@@ -2,6 +2,8 @@
 #ifndef __TRACE_PROBE_KERNEL_H_
 #define __TRACE_PROBE_KERNEL_H_
 
+#define FAULT_STRING "(fault)"
+
 /*
  * This depends on trace_probe.h, but can not include it due to
  * the way trace_probe_tmpl.h is used by trace_kprobe.c and trace_eprobe.c.

@@ -13,8 +15,16 @@ static nokprobe_inline int
 kern_fetch_store_strlen_user(unsigned long addr)
 {
 	const void __user *uaddr =  (__force const void __user *)addr;
+	int ret;
 
-	return strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
+	ret = strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
+	/*
+	 * strnlen_user_nofault returns zero on fault, insert the
+	 * FAULT_STRING when that occurs.
+	 */
+	if (ret <= 0)
+		return strlen(FAULT_STRING) + 1;
+	return ret;
 }
 
 /* Return the length of string -- including null terminal byte */

@@ -34,7 +44,18 @@ kern_fetch_store_strlen(unsigned long ad
 		len++;
 	} while (c && ret == 0 && len < MAX_STRING_SIZE);
 
-	return (ret < 0) ? ret : len;
+	/* For faults, return enough to hold the FAULT_STRING */
+	return (ret < 0) ? strlen(FAULT_STRING) + 1 : len;
+}
+
+static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void *base, int len)
+{
+	if (ret >= 0) {
+		*(u32 *)dest = make_data_loc(ret, __dest - base);
+	} else {
+		strscpy(__dest, FAULT_STRING, len);
+		ret = strlen(__dest) + 1;
+	}
 }
 
 /*

@@ -55,8 +76,7 @@ kern_fetch_store_string_user(unsigned lo
 	__dest = get_loc_data(dest, base);
 
 	ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
-	if (ret >= 0)
-		*(u32 *)dest = make_data_loc(ret, __dest - base);
+	set_data_loc(ret, dest, __dest, base, maxlen);
 
 	return ret;
 }

@@ -87,8 +107,7 @@ kern_fetch_store_string(unsigned long ad
 	 * probing.
 	 */
 	ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
-	if (ret >= 0)
-		*(u32 *)dest = make_data_loc(ret, __dest - base);
+	set_data_loc(ret, dest, __dest, base, maxlen);
 
 	return ret;
 }

@@ -17,6 +17,8 @@
 /* for gfp flag names */
 #include <linux/trace_events.h>
 #include <trace/events/mmflags.h>
+#include "trace_probe.h"
+#include "trace_probe_kernel.h"
 
 #include "trace_synth.h"
 

@@ -409,6 +411,7 @@ static unsigned int trace_string(struct
 {
 	unsigned int len = 0;
 	char *str_field;
+	int ret;
 
 	if (is_dynamic) {
 		u32 data_offset;

@@ -417,19 +420,27 @@ static unsigned int trace_string(struct
 		data_offset += event->n_u64 * sizeof(u64);
 		data_offset += data_size;
 
-		str_field = (char *)entry + data_offset;
-
-		len = strlen(str_val) + 1;
-		strscpy(str_field, str_val, len);
+		len = kern_fetch_store_strlen((unsigned long)str_val);
 
 		data_offset |= len << 16;
 		*(u32 *)&entry->fields[*n_u64] = data_offset;
 
+		ret = kern_fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry);
+
 		(*n_u64)++;
 	} else {
 		str_field = (char *)&entry->fields[*n_u64];
 
-		strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+		if ((unsigned long)str_val < TASK_SIZE)
+			ret = strncpy_from_user_nofault(str_field, str_val, STR_VAR_LEN_MAX);
+		else
+#endif
+			ret = strncpy_from_kernel_nofault(str_field, str_val, STR_VAR_LEN_MAX);
+
+		if (ret < 0)
+			strcpy(str_field, FAULT_STRING);
+
 		(*n_u64) += STR_VAR_LEN_MAX / sizeof(u64);
 	}
 

@@ -462,7 +473,7 @@ static notrace void trace_event_raw_even
 		val_idx = var_ref_idx[field_pos];
 		str_val = (char *)(long)var_ref_vals[val_idx];
 
-		len = strlen(str_val) + 1;
+		len = kern_fetch_store_strlen((unsigned long)str_val);
 
 		fields_size += len;
 	}

@@ -76,7 +76,9 @@ int rpmsg_chrdev_eptdev_destroy(struct d
 
 	mutex_lock(&eptdev->ept_lock);
 	if (eptdev->ept) {
-		rpmsg_destroy_ept(eptdev->ept);
+		/* The default endpoint is released by the rpmsg core */
+		if (!eptdev->default_ept)
+			rpmsg_destroy_ept(eptdev->ept);
 		eptdev->ept = NULL;
 	}
 	mutex_unlock(&eptdev->ept_lock);

@@ -2822,6 +2822,26 @@ static void tb_switch_credits_init(struc
 		tb_sw_info(sw, "failed to determine preferred buffer allocation, using defaults\n");
 }
 
+static int tb_switch_port_hotplug_enable(struct tb_switch *sw)
+{
+	struct tb_port *port;
+
+	if (tb_switch_is_icm(sw))
+		return 0;
+
+	tb_switch_for_each_port(sw, port) {
+		int res;
+
+		if (!port->cap_usb4)
+			continue;
+
+		res = usb4_port_hotplug_enable(port);
+		if (res)
+			return res;
+	}
+	return 0;
+}
+
 /**
  * tb_switch_add() - Add a switch to the domain
  * @sw: Switch to add

@@ -2891,6 +2911,10 @@ int tb_switch_add(struct tb_switch *sw)
 			return ret;
 	}
 
+	ret = tb_switch_port_hotplug_enable(sw);
+	if (ret)
+		return ret;
+
 	ret = device_add(&sw->dev);
 	if (ret) {
 		dev_err(&sw->dev, "failed to add device: %d\n", ret);

@@ -1170,6 +1170,7 @@ int usb4_switch_add_ports(struct tb_swit
 void usb4_switch_remove_ports(struct tb_switch *sw);
 
 int usb4_port_unlock(struct tb_port *port);
+int usb4_port_hotplug_enable(struct tb_port *port);
 int usb4_port_configure(struct tb_port *port);
 void usb4_port_unconfigure(struct tb_port *port);
 int usb4_port_configure_xdomain(struct tb_port *port);

@@ -302,6 +302,7 @@ struct tb_regs_port_header {
 #define ADP_CS_5				0x05
 #define ADP_CS_5_LCA_MASK			GENMASK(28, 22)
 #define ADP_CS_5_LCA_SHIFT			22
+#define ADP_CS_5_DHP				BIT(31)
 
 /* TMU adapter registers */
 #define TMU_ADP_CS_3				0x03

@@ -1046,6 +1046,26 @@ int usb4_port_unlock(struct tb_port *por
 	return tb_port_write(port, &val, TB_CFG_PORT, ADP_CS_4, 1);
 }
 
+/**
+ * usb4_port_hotplug_enable() - Enables hotplug for a port
+ * @port: USB4 port to operate on
+ *
+ * Enables hot plug events on a given port. This is only intended
+ * to be used on lane, DP-IN, and DP-OUT adapters.
+ */
+int usb4_port_hotplug_enable(struct tb_port *port)
+{
+	int ret;
+	u32 val;
+
+	ret = tb_port_read(port, &val, TB_CFG_PORT, ADP_CS_5, 1);
+	if (ret)
+		return ret;
+
+	val &= ~ADP_CS_5_DHP;
+	return tb_port_write(port, &val, TB_CFG_PORT, ADP_CS_5, 1);
+}
+
 static int usb4_port_set_configured(struct tb_port *port, bool configured)
 {
 	int ret;

@@ -280,14 +280,6 @@ efi_status_t allocate_new_fdt_and_exit_b
 		goto fail;
 	}
 
-	/*
-	 * Now that we have done our final memory allocation (and free)
-	 * we can get the memory map key needed for exit_boot_services().
-	 */
-	status = efi_get_memory_map(&map);
-	if (status != EFI_SUCCESS)
-		goto fail_free_new_fdt;
-
 	status = update_fdt((void *)fdt_addr, fdt_size,
 			    (void *)*new_fdt_addr, MAX_FDT_SIZE, cmdline_ptr,
 			    initrd_addr, initrd_size);

@@ -422,6 +422,8 @@ static int cedrus_probe(struct platform_
 	if (!dev)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, dev);
+
 	dev->vfd = cedrus_video_device;
 	dev->dev = &pdev->dev;
 	dev->pdev = pdev;

@@ -495,8 +497,6 @@ static int cedrus_probe(struct platform_
 		goto err_m2m_mc;
 	}
 
-	platform_set_drvdata(pdev, dev);
-
 	return 0;
 
 err_m2m_mc:

@@ -234,8 +234,9 @@ static void cedrus_h265_skip_bits(struct
 		cedrus_write(dev, VE_DEC_H265_TRIGGER,
 			     VE_DEC_H265_TRIGGER_FLUSH_BITS |
 			     VE_DEC_H265_TRIGGER_TYPE_N_BITS(tmp));
-		while (cedrus_read(dev, VE_DEC_H265_STATUS) & VE_DEC_H265_STATUS_VLD_BUSY)
-			udelay(1);
+
+		if (cedrus_wait_for(dev, VE_DEC_H265_STATUS, VE_DEC_H265_STATUS_VLD_BUSY))
+			dev_err_ratelimited(dev->dev, "timed out waiting to skip bits\n");
 
 		count += tmp;
 	}

@@ -760,8 +760,6 @@ EXPORT_SYMBOL(bio_put);
 static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp)
 {
 	bio_set_flag(bio, BIO_CLONED);
-	if (bio_flagged(bio_src, BIO_THROTTLED))
-		bio_set_flag(bio, BIO_THROTTLED);
 	bio->bi_ioprio = bio_src->bi_ioprio;
 	bio->bi_iter = bio_src->bi_iter;
 

@@ -811,7 +811,7 @@ static bool tg_with_in_bps_limit(struct
 	unsigned int bio_size = throtl_bio_data_size(bio);
 
 	/* no need to throttle if this bio's bytes have been accounted */
-	if (bps_limit == U64_MAX || bio_flagged(bio, BIO_THROTTLED)) {
+	if (bps_limit == U64_MAX || bio_flagged(bio, BIO_BPS_THROTTLED)) {
 		if (wait)
 			*wait = 0;
 		return true;

@@ -921,22 +921,13 @@ static void throtl_charge_bio(struct thr
 	unsigned int bio_size = throtl_bio_data_size(bio);
 
 	/* Charge the bio to the group */
-	if (!bio_flagged(bio, BIO_THROTTLED)) {
+	if (!bio_flagged(bio, BIO_BPS_THROTTLED)) {
 		tg->bytes_disp[rw] += bio_size;
 		tg->last_bytes_disp[rw] += bio_size;
 	}
 
 	tg->io_disp[rw]++;
 	tg->last_io_disp[rw]++;
-
-	/*
-	 * BIO_THROTTLED is used to prevent the same bio to be throttled
-	 * more than once as a throttled bio will go through blk-throtl the
-	 * second time when it eventually gets issued.  Set it when a bio
-	 * is being charged to a tg.
-	 */
-	if (!bio_flagged(bio, BIO_THROTTLED))
-		bio_set_flag(bio, BIO_THROTTLED);
 }
 
 /**

@@ -1026,6 +1017,7 @@ static void tg_dispatch_one_bio(struct t
 	sq->nr_queued[rw]--;
 
 	throtl_charge_bio(tg, bio);
+	bio_set_flag(bio, BIO_BPS_THROTTLED);
 
 	/*
 	 * If our parent is another tg, we just need to transfer @bio to

@@ -2159,8 +2151,10 @@ again:
 		qn = &tg->qnode_on_parent[rw];
 		sq = sq->parent_sq;
 		tg = sq_to_tg(sq);
-		if (!tg)
+		if (!tg) {
+			bio_set_flag(bio, BIO_BPS_THROTTLED);
 			goto out_unlock;
+		}
 	}
 
 	/* out-of-limit, queue to @tg */

@@ -2189,8 +2183,6 @@ again:
 	}
 
 out_unlock:
-	bio_set_flag(bio, BIO_THROTTLED);
-
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	if (throttled || !td->track_bio_latency)
 		bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY;

@@ -175,7 +175,7 @@ static inline bool blk_throtl_bio(struct
 	struct throtl_grp *tg = blkg_to_tg(bio->bi_blkg);
 
 	/* no need to throttle bps any more if the bio has been throttled */
-	if (bio_flagged(bio, BIO_THROTTLED) &&
+	if (bio_flagged(bio, BIO_BPS_THROTTLED) &&
 	    !(tg->flags & THROTL_TG_HAS_IOPS_LIMIT))
 		return false;
 

@@ -509,7 +509,7 @@ static inline void bio_set_dev(struct bi
 {
 	bio_clear_flag(bio, BIO_REMAPPED);
 	if (bio->bi_bdev != bdev)
-		bio_clear_flag(bio, BIO_THROTTLED);
+		bio_clear_flag(bio, BIO_BPS_THROTTLED);
 	bio->bi_bdev = bdev;
 	bio_associate_blkg(bio);
 }

@@ -323,7 +323,7 @@ enum {
 	BIO_QUIET,		/* Make BIO Quiet */
 	BIO_CHAIN,		/* chained bio, ->bi_remaining in effect */
 	BIO_REFFED,		/* bio has elevated ->bi_cnt */
-	BIO_THROTTLED,		/* This bio has already been subjected to
+	BIO_BPS_THROTTLED,	/* This bio has already been subjected to
 				 * throttling rules. Don't do it again. */
 	BIO_TRACE_COMPLETION,	/* bio_endio() should trace the final completion
 				 * of this bio. */

@@ -843,6 +843,10 @@ int wbt_init(struct request_queue *q)
 	rwb->enable_state = WBT_STATE_ON_DEFAULT;
 	rwb->wc = 1;
 	rwb->rq_depth.default_depth = RWB_DEF_DEPTH;
+	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
+
+	wbt_queue_depth_changed(&rwb->rqos);
+	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 
 	/*
 	 * Assign rwb and add the stats callback.

@@ -853,11 +857,6 @@ int wbt_init(struct request_queue *q)
 
 	blk_stat_add_callback(q, rwb->cb);
 
-	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
-
-	wbt_queue_depth_changed(&rwb->rqos);
-	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
-
 	return 0;
 
 err_free:

@@ -1955,7 +1955,7 @@ static int em_pop_sreg(struct x86_emulat
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	if (ctxt->modrm_reg == VCPU_SREG_SS)
+	if (seg == VCPU_SREG_SS)
 		ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS;
 	if (ctxt->op_bytes > 2)
 		rsp_increment(ctxt, ctxt->op_bytes - 2);

@@ -4264,14 +4264,6 @@ static void prepare_vmcs12(struct kvm_vc
 			nested_vmx_abort(vcpu,
 					 VMX_ABORT_SAVE_GUEST_MSR_FAIL);
 	}
-
-	/*
-	 * Drop what we picked up for L2 via vmx_complete_interrupts. It is
-	 * preserved above and would only end up incorrectly in L1.
-	 */
-	vcpu->arch.nmi_injected = false;
-	kvm_clear_exception_queue(vcpu);
-	kvm_clear_interrupt_queue(vcpu);
 }
 
 /*

@@ -4611,6 +4603,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *
 		WARN_ON_ONCE(nested_early_check);
 	}
 
+	/*
+	 * Drop events/exceptions that were queued for re-injection to L2
+	 * (picked up via vmx_complete_interrupts()), as well as exceptions
+	 * that were pending for L2.  Note, this must NOT be hoisted above
+	 * prepare_vmcs12(), events/exceptions queued for re-injection need to
+	 * be captured in vmcs12 (see vmcs12_save_pending_event()).
+	 */
+	vcpu->arch.nmi_injected = false;
+	kvm_clear_exception_queue(vcpu);
+	kvm_clear_interrupt_queue(vcpu);
+
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
 	/* Update any VMCS fields that might have changed while L2 ran */

@@ -2322,9 +2322,14 @@ static void prepare_vmcs02_early(struct
 	 * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate
 	 * on the related bits (if supported by the CPU) in the hope that
 	 * we can avoid VMWrites during vmx_set_efer().
+	 *
+	 * Similarly, take vmcs01's PERF_GLOBAL_CTRL in the hope that if KVM is
+	 * loading PERF_GLOBAL_CTRL via the VMCS for L1, then KVM will want to
+	 * do the same for L2.
 	 */
 	exec_control = __vm_entry_controls_get(vmcs01);
-	exec_control |= vmcs12->vm_entry_controls;
+	exec_control |= (vmcs12->vm_entry_controls &
+			 ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL);
 	exec_control &= ~(VM_ENTRY_IA32E_MODE | VM_ENTRY_LOAD_IA32_EFER);
 	if (cpu_has_load_ia32_efer()) {
 		if (guest_efer & EFER_LMA)

@@ -3839,7 +3839,16 @@ static void nested_vmx_inject_exception_
 	u32 intr_info = nr | INTR_INFO_VALID_MASK;
 
 	if (vcpu->arch.exception.has_error_code) {
-		vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code;
+		/*
+		 * Intel CPUs do not generate error codes with bits 31:16 set,
+		 * and more importantly VMX disallows setting bits 31:16 in the
+		 * injected error code for VM-Entry.  Drop the bits to mimic
+		 * hardware and avoid inducing failure on nested VM-Entry if L1
+		 * chooses to inject the exception back to L2.  AMD CPUs _do_
+		 * generate "full" 32-bit error codes, so KVM allows userspace
+		 * to inject exception error codes with bits 31:16 set.
+		 */
+		vmcs12->vm_exit_intr_error_code = (u16)vcpu->arch.exception.error_code;
 		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
 	}
 

@@ -1687,7 +1687,17 @@ static void vmx_queue_exception(struct k
 	kvm_deliver_exception_payload(vcpu);
 
 	if (has_error_code) {
-		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
+		/*
+		 * Despite the error code being architecturally defined as 32
+		 * bits, and the VMCS field being 32 bits, Intel CPUs and thus
+		 * VMX don't actually supporting setting bits 31:16.  Hardware
+		 * will (should) never provide a bogus error code, but AMD CPUs
+		 * do generate error codes with bits 31:16 set, and so KVM's
+		 * ABI lets userspace shove in arbitrary 32-bit values.  Drop
+		 * the upper bits to avoid VM-Fail, losing information that
+		 * does't really exist is preferable to killing the VM.
+		 */
+		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)error_code);
 		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
 	}
 

@@ -3,7 +3,6 @@
  * Greybus Audio Sound SoC helper APIs
  */
 
-#include <linux/debugfs.h>
 #include <sound/core.h>
 #include <sound/soc.h>
 #include <sound/soc-dapm.h>

@@ -116,10 +115,6 @@ int gbaudio_dapm_free_controls(struct sn
 {
 	int i;
 	struct snd_soc_dapm_widget *w, *next_w;
-#ifdef CONFIG_DEBUG_FS
-	struct dentry *parent = dapm->debugfs_dapm;
-	struct dentry *debugfs_w = NULL;
-#endif
 
 	mutex_lock(&dapm->card->dapm_mutex);
 	for (i = 0; i < num; i++) {

@@ -139,12 +134,6 @@ int gbaudio_dapm_free_controls(struct sn
 			continue;
 		}
 		widget++;
-#ifdef CONFIG_DEBUG_FS
-		if (!parent)
-			debugfs_w = debugfs_lookup(w->name, parent);
-		debugfs_remove(debugfs_w);
-		debugfs_w = NULL;
-#endif
 		gbaudio_dapm_free_widget(w);
 	}
 	mutex_unlock(&dapm->card->dapm_mutex);

@@ -503,7 +503,8 @@ nouveau_connector_set_encoder(struct drm
 			connector->interlace_allowed =
 				nv_encoder->caps.dp_interlace;
 		else
-			connector->interlace_allowed = true;
+			connector->interlace_allowed =
+				drm->client.device.info.family < NV_DEVICE_INFO_V0_VOLTA;
 		connector->doublescan_allowed = true;
 	} else
 	if (nv_encoder->dcb->type == DCB_OUTPUT_LVDS ||

@@ -71,7 +71,6 @@ struct drm_gem_object *nouveau_gem_prime
 	ret = nouveau_bo_init(nvbo, size, align, NOUVEAU_GEM_DOMAIN_GART,
 			      sg, robj);
 	if (ret) {
-		nouveau_bo_ref(NULL, &nvbo);
 		obj = ERR_PTR(ret);
 		goto unlock;
 	}

@@ -247,6 +247,7 @@ err_scratch1:
 	i915_gem_object_put(vm->scratch[1]);
 err_scratch0:
 	i915_gem_object_put(vm->scratch[0]);
+	vm->scratch[0] = NULL;
 	return ret;
 }
 

@@ -268,9 +269,10 @@ static void gen6_ppgtt_cleanup(struct i9
 	gen6_ppgtt_free_pd(ppgtt);
 	free_scratch(vm);
 
-	mutex_destroy(&ppgtt->flush);
+	if (ppgtt->base.pd)
+		free_pd(&ppgtt->base.vm, ppgtt->base.pd);
 
-	free_pd(&ppgtt->base.vm, ppgtt->base.pd);
+	mutex_destroy(&ppgtt->flush);
 }
 
 static void pd_vma_bind(struct i915_address_space *vm,

@@ -449,19 +451,17 @@ struct i915_ppgtt *gen6_ppgtt_create(str
 
 	err = gen6_ppgtt_init_scratch(ppgtt);
 	if (err)
-		goto err_free;
+		goto err_put;
 
 	ppgtt->base.pd = gen6_alloc_top_pd(ppgtt);
 	if (IS_ERR(ppgtt->base.pd)) {
 		err = PTR_ERR(ppgtt->base.pd);
-		goto err_scratch;
+		goto err_put;
 	}
 
 	return &ppgtt->base;
 
-err_scratch:
-	free_scratch(&ppgtt->base.vm);
-err_free:
-	kfree(ppgtt);
+err_put:
+	i915_vm_put(&ppgtt->base.vm);
 	return ERR_PTR(err);
 }

101 lines not on this page · raw message

@@ -405,6 +405,9 @@ void free_scratch(struct i915_address_sp
 {
 	int i;
 
+	if (!vm->scratch[0])
+		return;
+
 	for (i = 0; i <= vm->top; i++)
 		i915_gem_object_put(vm->scratch[i]);
 }

@@ -5307,10 +5307,12 @@ skl_compute_wm_params(const struct intel
 		      modifier == I915_FORMAT_MOD_4_TILED ||
 		      modifier == I915_FORMAT_MOD_Yf_TILED ||
 		      modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
-		      modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
+		      modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
+		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS;
 	wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED;
 	wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
-			 modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
+			 modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
+			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS;
 	wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);
 
 	wp->width = width;

@@ -5308,11 +5308,13 @@ skl_compute_wm_params(const struct intel
 		      modifier == I915_FORMAT_MOD_Yf_TILED ||
 		      modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 		      modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
-		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS;
+		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS;
 	wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED;
 	wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 			 modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
-			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS;
+			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS;
 	wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);
 
 	wp->width = width;

@@ -5309,12 +5309,14 @@ skl_compute_wm_params(const struct intel
 		      modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 		      modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
 		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
-		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS;
+		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS ||
+		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC;
 	wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED;
 	wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 			 modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
 			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
-			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS;
+			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS ||
+			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC;
 	wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);
 
 	wp->width = width;

@@ -5310,13 +5310,17 @@ skl_compute_wm_params(const struct intel
 		      modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
 		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
 		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS ||
-		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC;
+		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC ||
+		      modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS ||
+		      modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS;
 	wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED;
 	wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 			 modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
 			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
 			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS ||
-			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC;
+			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC ||
+			 modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS ||
+			 modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS;
 	wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);
 
 	wp->width = width;

@@ -5312,7 +5312,8 @@ skl_compute_wm_params(const struct intel
 		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS ||
 		      modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC ||
 		      modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS ||
-		      modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS;
+		      modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS ||
+		      modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC;
 	wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED;
 	wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 			 modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||

@@ -5320,7 +5321,8 @@ skl_compute_wm_params(const struct intel
 			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS ||
 			 modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC ||
 			 modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS ||
-			 modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS;
+			 modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS ||
+			 modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC;
 	wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);
 
 	wp->width = width;

@@ -9157,15 +9157,15 @@ static void amdgpu_dm_handle_vrr_transit
 		 * We also need vupdate irq for the actual core vblank handling
 		 * at end of vblank.
 		 */
-		dm_set_vupdate_irq(new_state->base.crtc, true);
-		drm_crtc_vblank_get(new_state->base.crtc);
+		WARN_ON(dm_set_vupdate_irq(new_state->base.crtc, true) != 0);
+		WARN_ON(drm_crtc_vblank_get(new_state->base.crtc) != 0);
 		DRM_DEBUG_DRIVER("%s: crtc=%u VRR off->on: Get vblank ref\n",
 				 __func__, new_state->base.crtc->base.id);
 	} else if (old_vrr_active && !new_vrr_active) {
 		/* Transition VRR active -> inactive:
 		 * Allow vblank irq disable again for fixed refresh rate.
 		 */
-		dm_set_vupdate_irq(new_state->base.crtc, false);
+		WARN_ON(dm_set_vupdate_irq(new_state->base.crtc, false) != 0);
 		drm_crtc_vblank_put(new_state->base.crtc);
 		DRM_DEBUG_DRIVER("%s: crtc=%u VRR on->off: Drop vblank ref\n",
 				 __func__, new_state->base.crtc->base.id);

@@ -9916,23 +9916,6 @@ static void amdgpu_dm_atomic_commit_tail
 		mutex_unlock(&dm->dc_lock);
 	}
 
-	/* Count number of newly disabled CRTCs for dropping PM refs later. */
-	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
-				      new_crtc_state, i) {
-		if (old_crtc_state->active && !new_crtc_state->active)
-			crtc_disable_count++;
-
-		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
-		dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
-
-		/* For freesync config update on crtc state and params for irq */
-		update_stream_irq_parameters(dm, dm_new_crtc_state);
-
-		/* Handle vrr on->off / off->on transitions */
-		amdgpu_dm_handle_vrr_transition(dm_old_crtc_state,
-						dm_new_crtc_state);
-	}
-
 	/**
 	 * Enable interrupts for CRTCs that are newly enabled or went through
 	 * a modeset. It was intentionally deferred until after the front end

@@ -9942,16 +9925,29 @@ static void amdgpu_dm_atomic_commit_tail
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
 #ifdef CONFIG_DEBUG_FS
-		bool configure_crc = false;
 		enum amdgpu_dm_pipe_crc_source cur_crc_src;
 #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY)
-		struct crc_rd_work *crc_rd_wrk = dm->crc_rd_wrk;
+		struct crc_rd_work *crc_rd_wrk;
+#endif
+#endif
+		/* Count number of newly disabled CRTCs for dropping PM refs later. */
+		if (old_crtc_state->active && !new_crtc_state->active)
+			crtc_disable_count++;
+
+		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
+		dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
+
+		/* For freesync config update on crtc state and params for irq */
+		update_stream_irq_parameters(dm, dm_new_crtc_state);
+
+#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY)
+		crc_rd_wrk = dm->crc_rd_wrk;
 #endif
 		spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 		cur_crc_src = acrtc->dm_irq_params.crc_src;
 		spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 #endif
-		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
 
 		if (new_crtc_state->active &&
 		    (!old_crtc_state->active ||

@@ -9959,16 +9955,19 @@ static void amdgpu_dm_atomic_commit_tail
 			dc_stream_retain(dm_new_crtc_state->stream);
 			acrtc->dm_irq_params.stream = dm_new_crtc_state->stream;
 			manage_dm_interrupts(adev, acrtc, true);
+		}
+		/* Handle vrr on->off / off->on transitions */
+		amdgpu_dm_handle_vrr_transition(dm_old_crtc_state, dm_new_crtc_state);
 
 #ifdef CONFIG_DEBUG_FS
+		if (new_crtc_state->active &&
+		    (!old_crtc_state->active ||
+		     drm_atomic_crtc_needs_modeset(new_crtc_state))) {
 			/**
 			 * Frontend may have changed so reapply the CRC capture
 			 * settings for the stream.
 			 */
-			dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
-
 			if (amdgpu_dm_is_valid_crc_source(cur_crc_src)) {
-				configure_crc = true;
 #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY)
 				if (amdgpu_dm_crc_window_is_activated(crtc)) {
 					spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);

@@ -9980,12 +9979,10 @@ static void amdgpu_dm_atomic_commit_tail
 					spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 				}
 #endif
-			}
-
-			if (configure_crc)
 				if (amdgpu_dm_crtc_configure_crc_source(
 					crtc, dm_new_crtc_state, cur_crc_src))
 					DRM_DEBUG_DRIVER("Failed to configure crc source");
+			}
 #endif
 		}
 	}

@@ -60,11 +60,15 @@ static bool link_supports_psrsu(struct d
  */
 void amdgpu_dm_set_psr_caps(struct dc_link *link)
 {
-	if (!(link->connector_signal & SIGNAL_TYPE_EDP))
+	if (!(link->connector_signal & SIGNAL_TYPE_EDP)) {
+		link->psr_settings.psr_feature_enabled = false;
 		return;
+	}
 
-	if (link->type == dc_connection_none)
+	if (link->type == dc_connection_none) {
+		link->psr_settings.psr_feature_enabled = false;
 		return;
+	}
 
 	if (link->dpcd_caps.psr_info.psr_version == 0) {
 		link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED;

@@ -2410,7 +2410,7 @@ create_sd_buf(umode_t mode, bool set_own
 	unsigned int acelen, acl_size, ace_count;
 	unsigned int owner_offset = 0;
 	unsigned int group_offset = 0;
-	struct smb3_acl acl;
+	struct smb3_acl acl = {};
 
 	*len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8);
 

@@ -2483,6 +2483,7 @@ create_sd_buf(umode_t mode, bool set_own
 	acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */
 	acl.AclSize = cpu_to_le16(acl_size);
 	acl.AceCount = cpu_to_le16(ace_count);
+	/* acl.Sbz1 and Sbz2 MBZ so are not set here, but initialized above */
 	memcpy(aclptr, &acl, sizeof(struct smb3_acl));
 
 	buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd);

index bde74fcecee3..3e0fbbd99534 100644
@@ -750,22 +750,26 @@ int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name,
 	const struct evm_ima_xattr_data *xvalue = xattr_value;
 	int digsig = 0;
 	int result;
+	int err;
 
 	result = ima_protect_xattr(dentry, xattr_name, xattr_value,
 				   xattr_value_len);
 	if (result == 1) {
 		if (!xattr_value_len || (xvalue->type >= IMA_XATTR_LAST))
 			return -EINVAL;
+
+		err = validate_hash_algo(dentry, xvalue, xattr_value_len);
+		if (err)
+			return err;
+
 		digsig = (xvalue->type == EVM_IMA_XATTR_DIGSIG);
 	} else if (!strcmp(xattr_name, XATTR_NAME_EVM) && xattr_value_len > 0) {
 		digsig = (xvalue->type == EVM_XATTR_PORTABLE_DIGSIG);
 	}
 	if (result == 1 || evm_revalidate_status(xattr_name)) {
-		result = validate_hash_algo(dentry, xvalue, xattr_value_len);
-		if (result)
-			return result;
-
 		ima_reset_appraise_flags(d_backing_inode(dentry), digsig);
+		if (result == 1)
+			result = 0;
 	}
 	return result;
 }

index ab0576d372d6..fa0a2fa5debb 100644
@@ -991,7 +991,7 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *new,
 	int fd;
 
 	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new,
-			O_RDWR | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
+			O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
 	if (fd < 0)
 		return fd;
 

@@ -2096,7 +2096,7 @@ SYSCALL_DEFINE1(userfaultfd, int, flags)
 	mmgrab(ctx->mm);
 
 	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx,
-			O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
+			O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
 	if (fd < 0) {
 		mmdrop(ctx->mm);
 		kmem_cache_free(userfaultfd_ctx_cachep, ctx);

index 803ff4c63c31..3b94ad22d9c0 100644
@@ -1941,8 +1941,6 @@ const struct inode_operations ntfs_link_inode_operations = {
 	.setattr	= ntfs3_setattr,
 	.listxattr	= ntfs_listxattr,
 	.permission	= ntfs_permission,
-	.get_acl	= ntfs_get_acl,
-	.set_acl	= ntfs_set_acl,
 };
 
 const struct address_space_operations ntfs_aops = {

132 lines not on this page · raw message

index dc19e7c80751..ca5746f53d9e 100644
@@ -530,17 +530,17 @@ __cpufreq_cooling_register(struct device_node *np,
 	struct thermal_cooling_device_ops *cooling_ops;
 	char *name;
 
+	if (IS_ERR_OR_NULL(policy)) {
+		pr_err("%s: cpufreq policy isn't valid: %p\n", __func__, policy);
+		return ERR_PTR(-EINVAL);
+	}
+
 	dev = get_cpu_device(policy->cpu);
 	if (unlikely(!dev)) {
 		pr_warn("No cpu device for cpu %d\n", policy->cpu);
 		return ERR_PTR(-ENODEV);
 	}
 
-	if (IS_ERR_OR_NULL(policy)) {
-		pr_err("%s: cpufreq policy isn't valid: %p\n", __func__, policy);
-		return ERR_PTR(-EINVAL);
-	}
-
 	i = cpufreq_table_count_valid_entries(policy);
 	if (!i) {
 		pr_debug("%s: CPUFreq table not found or has no valid entries\n",

index 9ac75c1cde9c..365f3ad166a7 100644
@@ -152,6 +152,7 @@ static inline int amd_pstate_enable(bool enable)
 static int pstate_init_perf(struct amd_cpudata *cpudata)
 {
 	u64 cap1;
+	u32 highest_perf;
 
 	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
 				     &cap1);

@@ -163,7 +164,11 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	 *
 	 * CPPC entry doesn't indicate the highest performance in some ASICs.
 	 */
-	WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf());
+	highest_perf = amd_get_highest_perf();
+	if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1))
+		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
+
+	WRITE_ONCE(cpudata->highest_perf, highest_perf);
 
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));

@@ -175,12 +180,17 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 static int cppc_init_perf(struct amd_cpudata *cpudata)
 {
 	struct cppc_perf_caps cppc_perf;
+	u32 highest_perf;
 
 	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
 	if (ret)
 		return ret;
 
-	WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf());
+	highest_perf = amd_get_highest_perf();
+	if (highest_perf > cppc_perf.highest_perf)
+		highest_perf = cppc_perf.highest_perf;
+
+	WRITE_ONCE(cpudata->highest_perf, highest_perf);
 
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,

index 8edb824049b9..0cb0ca149ac3 100644
@@ -4,7 +4,7 @@
 
 #include <asm-generic/sections.h>
 
-extern long __machvec_start, __machvec_end;
+extern char __machvec_start[], __machvec_end[];
 extern char __uncached_start, __uncached_end;
 extern char __start_eh_frame[], __stop_eh_frame[];