From 321c75b01cc87588a6722c29c2bc46d0405659cd Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Sep 2023 12:43:58 -0400 Subject: [PATCH 01/13] NFS/pNFS: Report EINVAL errors from connect() to the server [ Upstream commit dd7d7ee3ba2a70d12d02defb478790cf57d5b87b ] With IPv6, connect() can occasionally return EINVAL if a route is unavailable. If this happens during I/O to a data server, we want to report it using LAYOUTERROR as an inability to connect. Fixes: dd52128afdde ("NFSv4.1/pnfs Ensure flexfiles reports all connection related errors") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/flexfilelayout/flexfilelayout.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index fa1c920afb49..1b88b78f40be 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1280,6 +1280,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, case -EPFNOSUPPORT: case -EPROTONOSUPPORT: case -EOPNOTSUPP: + case -EINVAL: case -ECONNREFUSED: case -ECONNRESET: case -EHOSTDOWN: From 7d3f6612e90b233b3d855c860b94ba5648ab8161 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Sep 2023 12:50:09 -0400 Subject: [PATCH 02/13] SUNRPC: Mark the cred for revalidation if the server rejects it [ Upstream commit 611fa42dfa9d2f3918ac5f4dd5705dfad81b323d ] If the server rejects the credential as being stale, or bad, then we should mark it for revalidation before retransmitting. Fixes: 7f5667a5f8c4 ("SUNRPC: Clean up rpc_verify_header()") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- net/sunrpc/clnt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 629c05ff1f3e..9071dc6928ac 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2684,6 +2684,7 @@ out_msg_denied: case rpc_autherr_rejectedverf: case rpcsec_gsserr_credproblem: case rpcsec_gsserr_ctxproblem: + rpcauth_invalcred(task); if (!task->tk_cred_retry) break; task->tk_cred_retry--; From e6807c873d8791ae5a5186ad05ec66cab926539a Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 6 Sep 2023 22:47:12 -0400 Subject: [PATCH 03/13] tracing: Increase trace array ref count on enable and filter files [ Upstream commit f5ca233e2e66dc1c249bf07eefa37e34a6c9346a ] When the trace event enable and filter files are opened, increment the trace array ref counter, otherwise they can be accessed when the trace array is being deleted. The ref counter keeps the trace array from being deleted while those files are opened. Link: https://lkml.kernel.org/r/20230907024803.456187066@goodmis.org Link: https://lore.kernel.org/all/1cb3aee2-19af-c472-e265-05176fe9bd84@huawei.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Andrew Morton Fixes: 8530dec63e7b4 ("tracing: Add tracing_check_open_get_tr()") Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Reported-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/trace.c | 27 +++++++++++++++++++++++++++ kernel/trace/trace.h | 2 ++ kernel/trace/trace_events.c | 6 ++++-- 3 files changed, 33 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f9c64329ec15..85ad403006a2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4244,6 +4244,33 @@ int tracing_open_generic_tr(struct inode *inode, struct file *filp) return 0; } +/* + * The private pointer of the inode is the trace_event_file. + * Update the tr ref count associated to it. + */ +int tracing_open_file_tr(struct inode *inode, struct file *filp) +{ + struct trace_event_file *file = inode->i_private; + int ret; + + ret = tracing_check_open_get_tr(file->tr); + if (ret) + return ret; + + filp->private_data = inode->i_private; + + return 0; +} + +int tracing_release_file_tr(struct inode *inode, struct file *filp) +{ + struct trace_event_file *file = inode->i_private; + + trace_array_put(file->tr); + + return 0; +} + static int tracing_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 21f85c0bd66e..f1f54111b856 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -680,6 +680,8 @@ void tracing_reset_all_online_cpus(void); void tracing_reset_all_online_cpus_unlocked(void); int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); +int tracing_open_file_tr(struct inode *inode, struct file *filp); +int tracing_release_file_tr(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); bool tracer_tracing_is_on(struct trace_array *tr); void tracer_tracing_on(struct trace_array *tr); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 0c21da12b650..51adf0817ef3 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1699,9 +1699,10 @@ static const struct file_operations ftrace_set_event_pid_fops = { }; static const struct file_operations ftrace_enable_fops = { - .open = tracing_open_generic, + .open = tracing_open_file_tr, .read = event_enable_read, .write = event_enable_write, + .release = tracing_release_file_tr, .llseek = default_llseek, }; @@ -1718,9 +1719,10 @@ static const struct file_operations ftrace_event_id_fops = { }; static const struct file_operations ftrace_event_filter_fops = { - .open = tracing_open_generic, + .open = tracing_open_file_tr, .read = event_filter_read, .write = event_filter_write, + .release = tracing_release_file_tr, .llseek = default_llseek, }; From bf0660756510e0e68eeaca941280f2bee0192422 Mon Sep 17 00:00:00 2001 From: Szuying Chen Date: Thu, 7 Sep 2023 16:17:10 +0800 Subject: [PATCH 04/13] ata: libahci: clear pending interrupt status [ Upstream commit 737dd811a3dbfd7edd4ad2ba5152e93d99074f83 ] When a CRC error occurs, the HBA asserts an interrupt to indicate an interface fatal error (PxIS.IFS). The ISR clears PxIE and PxIS, then does error recovery. If the adapter receives another SDB FIS with an error (PxIS.TFES) from the device before the start of the EH recovery process, the interrupt signaling the new SDB cannot be serviced as PxIE was cleared already. This in turn results in the HBA inability to issue any command during the error recovery process after setting PxCMD.ST to 1 because PxIS.TFES is still set. According to AHCI 1.3.1 specifications section 6.2.2, fatal errors notified by setting PxIS.HBFS, PxIS.HBDS, PxIS.IFS or PxIS.TFES will cause the HBA to enter the ERR:Fatal state. In this state, the HBA shall not issue any new commands. To avoid this situation, introduce the function ahci_port_clear_pending_irq() to clear pending interrupts before executing a COMRESET. This follows the AHCI 1.3.1 - section 6.2.2.2 specification. Signed-off-by: Szuying Chen Fixes: e0bfd149973d ("[PATCH] ahci: stop engine during hard reset") Cc: stable@vger.kernel.org Reviewed-by: Niklas Cassel Signed-off-by: Damien Le Moal Signed-off-by: Sasha Levin --- drivers/ata/libahci.c | 35 +++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 12 deletions(-) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index fec2e9754aed..61b5ba8dc1d2 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1199,6 +1199,26 @@ static ssize_t ahci_activity_show(struct ata_device *dev, char *buf) return sprintf(buf, "%d\n", emp->blink_policy); } +static void ahci_port_clear_pending_irq(struct ata_port *ap) +{ + struct ahci_host_priv *hpriv = ap->host->private_data; + void __iomem *port_mmio = ahci_port_base(ap); + u32 tmp; + + /* clear SError */ + tmp = readl(port_mmio + PORT_SCR_ERR); + dev_dbg(ap->host->dev, "PORT_SCR_ERR 0x%x\n", tmp); + writel(tmp, port_mmio + PORT_SCR_ERR); + + /* clear port IRQ */ + tmp = readl(port_mmio + PORT_IRQ_STAT); + dev_dbg(ap->host->dev, "PORT_IRQ_STAT 0x%x\n", tmp); + if (tmp) + writel(tmp, port_mmio + PORT_IRQ_STAT); + + writel(1 << ap->port_no, hpriv->mmio + HOST_IRQ_STAT); +} + static void ahci_port_init(struct device *dev, struct ata_port *ap, int port_no, void __iomem *mmio, void __iomem *port_mmio) @@ -1213,18 +1233,7 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap, if (rc) dev_warn(dev, "%s (%d)\n", emsg, rc); - /* clear SError */ - tmp = readl(port_mmio + PORT_SCR_ERR); - VPRINTK("PORT_SCR_ERR 0x%x\n", tmp); - writel(tmp, port_mmio + PORT_SCR_ERR); - - /* clear port IRQ */ - tmp = readl(port_mmio + PORT_IRQ_STAT); - VPRINTK("PORT_IRQ_STAT 0x%x\n", tmp); - if (tmp) - writel(tmp, port_mmio + PORT_IRQ_STAT); - - writel(1 << port_no, mmio + HOST_IRQ_STAT); + ahci_port_clear_pending_irq(ap); /* mark esata ports */ tmp = readl(port_mmio + PORT_CMD); @@ -1554,6 +1563,8 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class, tf.command = ATA_BUSY; ata_tf_to_fis(&tf, 0, 0, d2h_fis); + ahci_port_clear_pending_irq(ap); + rc = sata_link_hardreset(link, timing, deadline, online, ahci_check_ready); From b0dcbd4bb95783e64e30d3f5a020f7e030b08f24 Mon Sep 17 00:00:00 2001 From: Wang Jianchao Date: Sat, 24 Jul 2021 15:41:20 +0800 Subject: [PATCH 05/13] ext4: remove the 'group' parameter of ext4_trim_extent [ Upstream commit bd2eea8d0a6b6a9aca22f20bf74f73b71d8808af ] Get rid of the 'group' parameter of ext4_trim_extent as we can get it from the 'e4b'. Reviewed-by: Andreas Dilger Signed-off-by: Wang Jianchao Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20210724074124.25731-2-jianchao.wan9@gmail.com Signed-off-by: Theodore Ts'o Stable-dep-of: 45e4ab320c9b ("ext4: move setting of trimmed bit into ext4_try_to_trim_range()") Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index be5c2e53b636..9b4af51c99da 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5159,19 +5159,19 @@ error_return: * @sb: super block for the file system * @start: starting block of the free extent in the alloc. group * @count: number of blocks to TRIM - * @group: alloc. group we are working with * @e4b: ext4 buddy for the group * * Trim "count" blocks starting at "start" in the "group". To assure that no * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ -static int ext4_trim_extent(struct super_block *sb, int start, int count, - ext4_group_t group, struct ext4_buddy *e4b) +static int ext4_trim_extent(struct super_block *sb, + int start, int count, struct ext4_buddy *e4b) __releases(bitlock) __acquires(bitlock) { struct ext4_free_extent ex; + ext4_group_t group = e4b->bd_group; int ret = 0; trace_ext4_trim_extent(sb, group, start, count); @@ -5247,8 +5247,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, next = mb_find_next_bit(bitmap, max + 1, start); if ((next - start) >= minblocks) { - ret = ext4_trim_extent(sb, start, - next - start, group, &e4b); + ret = ext4_trim_extent(sb, start, next - start, &e4b); if (ret && ret != -EOPNOTSUPP) break; ret = 0; From c71cb46affe915b48faff0e604a9cd34df0bbf76 Mon Sep 17 00:00:00 2001 From: Wang Jianchao Date: Sat, 24 Jul 2021 15:41:21 +0800 Subject: [PATCH 06/13] ext4: add new helper interface ext4_try_to_trim_range() [ Upstream commit 6920b3913235f517728bb69abe9b39047a987113 ] There is no functional change in this patch but just split the codes, which serachs free block and does trim, into a new function ext4_try_to_trim_range. This is preparing for the following async backgroup discard. Reviewed-by: Andreas Dilger Signed-off-by: Wang Jianchao Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20210724074124.25731-3-jianchao.wan9@gmail.com Signed-off-by: Theodore Ts'o Stable-dep-of: 45e4ab320c9b ("ext4: move setting of trimmed bit into ext4_try_to_trim_range()") Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 102 ++++++++++++++++++++++++++-------------------- 1 file changed, 57 insertions(+), 45 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 9b4af51c99da..5a7fe5aa0fc3 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5194,6 +5194,54 @@ __acquires(bitlock) return ret; } +static int ext4_try_to_trim_range(struct super_block *sb, + struct ext4_buddy *e4b, ext4_grpblk_t start, + ext4_grpblk_t max, ext4_grpblk_t minblocks) +{ + ext4_grpblk_t next, count, free_count; + void *bitmap; + int ret = 0; + + bitmap = e4b->bd_bitmap; + start = (e4b->bd_info->bb_first_free > start) ? + e4b->bd_info->bb_first_free : start; + count = 0; + free_count = 0; + + while (start <= max) { + start = mb_find_next_zero_bit(bitmap, max + 1, start); + if (start > max) + break; + next = mb_find_next_bit(bitmap, max + 1, start); + + if ((next - start) >= minblocks) { + ret = ext4_trim_extent(sb, start, next - start, e4b); + if (ret && ret != -EOPNOTSUPP) + break; + ret = 0; + count += next - start; + } + free_count += next - start; + start = next + 1; + + if (fatal_signal_pending(current)) { + count = -ERESTARTSYS; + break; + } + + if (need_resched()) { + ext4_unlock_group(sb, e4b->bd_group); + cond_resched(); + ext4_lock_group(sb, e4b->bd_group); + } + + if ((e4b->bd_info->bb_free - free_count) < minblocks) + break; + } + + return count; +} + /** * ext4_trim_all_free -- function to trim all free space in alloc. group * @sb: super block for file system @@ -5217,10 +5265,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { - void *bitmap; - ext4_grpblk_t next, count = 0, free_count = 0; struct ext4_buddy e4b; - int ret = 0; + int ret; trace_ext4_trim_all_free(sb, group, start, max); @@ -5230,57 +5276,23 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ret, group); return ret; } - bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); - if (EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) && - minblocks >= atomic_read(&EXT4_SB(sb)->s_last_trim_minblks)) - goto out; - start = (e4b.bd_info->bb_first_free > start) ? - e4b.bd_info->bb_first_free : start; - - while (start <= max) { - start = mb_find_next_zero_bit(bitmap, max + 1, start); - if (start > max) - break; - next = mb_find_next_bit(bitmap, max + 1, start); - - if ((next - start) >= minblocks) { - ret = ext4_trim_extent(sb, start, next - start, &e4b); - if (ret && ret != -EOPNOTSUPP) - break; - ret = 0; - count += next - start; - } - free_count += next - start; - start = next + 1; - - if (fatal_signal_pending(current)) { - count = -ERESTARTSYS; - break; - } - - if (need_resched()) { - ext4_unlock_group(sb, group); - cond_resched(); - ext4_lock_group(sb, group); - } - - if ((e4b.bd_info->bb_free - free_count) < minblocks) - break; + if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || + minblocks < atomic_read(&EXT4_SB(sb)->s_last_trim_minblks)) { + ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); + if (ret >= 0) + EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); + } else { + ret = 0; } - if (!ret) { - ret = count; - EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); - } -out: ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); ext4_debug("trimmed %d blocks in the group %d\n", - count, group); + ret, group); return ret; } From 2d874151584d4728a34072549c405ce0fa23992b Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 20 Aug 2021 14:08:53 +0200 Subject: [PATCH 07/13] ext4: scope ret locally in ext4_try_to_trim_range() [ Upstream commit afcc4e32f606dbfb47aa7309172c89174b86e74c ] As commit 6920b3913235 ("ext4: add new helper interface ext4_try_to_trim_range()") moves some code into the separate function ext4_try_to_trim_range(), the use of the variable ret within that function is more limited and can be adjusted as well. Scope the use of the variable ret locally and drop dead assignments. No functional change. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20210820120853.23134-1-lukas.bulwahn@gmail.com Signed-off-by: Theodore Ts'o Stable-dep-of: 45e4ab320c9b ("ext4: move setting of trimmed bit into ext4_try_to_trim_range()") Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 5a7fe5aa0fc3..e1b487acb843 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5200,7 +5200,6 @@ static int ext4_try_to_trim_range(struct super_block *sb, { ext4_grpblk_t next, count, free_count; void *bitmap; - int ret = 0; bitmap = e4b->bd_bitmap; start = (e4b->bd_info->bb_first_free > start) ? @@ -5215,10 +5214,10 @@ static int ext4_try_to_trim_range(struct super_block *sb, next = mb_find_next_bit(bitmap, max + 1, start); if ((next - start) >= minblocks) { - ret = ext4_trim_extent(sb, start, next - start, e4b); + int ret = ext4_trim_extent(sb, start, next - start, e4b); + if (ret && ret != -EOPNOTSUPP) break; - ret = 0; count += next - start; } free_count += next - start; From 635901bdbd7ec601b04ea25fc606c070848f0bbb Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Wed, 3 Nov 2021 15:51:21 +0100 Subject: [PATCH 08/13] ext4: change s_last_trim_minblks type to unsigned long [ Upstream commit 2327fb2e23416cfb2795ccca2f77d4d65925be99 ] There is no good reason for the s_last_trim_minblks to be atomic. There is no data integrity needed and there is no real danger in setting and reading it in a racy manner. Change it to be unsigned long, the same type as s_clusters_per_group which is the maximum that's allowed. Signed-off-by: Lukas Czerner Suggested-by: Andreas Dilger Reviewed-by: Andreas Dilger Link: https://lore.kernel.org/r/20211103145122.17338-1-lczerner@redhat.com Signed-off-by: Theodore Ts'o Stable-dep-of: 45e4ab320c9b ("ext4: move setting of trimmed bit into ext4_try_to_trim_range()") Signed-off-by: Sasha Levin --- fs/ext4/ext4.h | 2 +- fs/ext4/mballoc.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 604fef3b2ddf..4d02116193de 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1529,7 +1529,7 @@ struct ext4_sb_info { struct task_struct *s_mmp_tsk; /* record the last minlen when FITRIM is called. */ - atomic_t s_last_trim_minblks; + unsigned long s_last_trim_minblks; /* Reference to checksum algorithm driver via cryptoapi */ struct crypto_shash *s_chksum_driver; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index e1b487acb843..db6bc2493647 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5279,7 +5279,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_lock_group(sb, group); if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || - minblocks < atomic_read(&EXT4_SB(sb)->s_last_trim_minblks)) { + minblocks < EXT4_SB(sb)->s_last_trim_minblks) { ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); if (ret >= 0) EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); @@ -5388,7 +5388,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) } if (!ret) - atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen); + EXT4_SB(sb)->s_last_trim_minblks = minlen; out: range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; From 2fd502f53bf4fc3412e5b3a888405ba461107c89 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Sun, 17 Apr 2022 20:03:15 +0300 Subject: [PATCH 09/13] ext4: mark group as trimmed only if it was fully scanned [ Upstream commit d63c00ea435a5352f486c259665a4ced60399421 ] Otherwise nonaligned fstrim calls will works inconveniently for iterative scanners, for example: // trim [0,16MB] for group-1, but mark full group as trimmed fstrim -o $((1024*1024*128)) -l $((1024*1024*16)) ./m // handle [16MB,16MB] for group-1, do nothing because group already has the flag. fstrim -o $((1024*1024*144)) -l $((1024*1024*16)) ./m [ Update function documentation for ext4_trim_all_free -- TYT ] Signed-off-by: Dmitry Monakhov Link: https://lore.kernel.org/r/1650214995-860245-1-git-send-email-dmtrmonakhov@yandex-team.ru Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Stable-dep-of: 45e4ab320c9b ("ext4: move setting of trimmed bit into ext4_try_to_trim_range()") Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index db6bc2493647..7cd2f2c07858 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5248,6 +5248,7 @@ static int ext4_try_to_trim_range(struct super_block *sb, * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count + * @set_trimmed: set the trimmed flag if at least one block is trimmed * * ext4_trim_all_free walks through group's buddy bitmap searching for free * extents. When the free block is found, ext4_trim_extent is called to TRIM @@ -5262,7 +5263,7 @@ static int ext4_try_to_trim_range(struct super_block *sb, static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, - ext4_grpblk_t minblocks) + ext4_grpblk_t minblocks, bool set_trimmed) { struct ext4_buddy e4b; int ret; @@ -5281,7 +5282,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || minblocks < EXT4_SB(sb)->s_last_trim_minblks) { ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); - if (ret >= 0) + if (ret >= 0 && set_trimmed) EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); } else { ret = 0; @@ -5318,6 +5319,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); + bool whole_group, eof = false; int ret = 0; start = range->start >> sb->s_blocksize_bits; @@ -5336,8 +5338,10 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } - if (end >= max_blks) + if (end >= max_blks - 1) { end = max_blks - 1; + eof = true; + } if (end <= first_data_blk) goto out; if (start < first_data_blk) @@ -5351,6 +5355,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; + whole_group = true; for (group = first_group; group <= last_group; group++) { grp = ext4_get_group_info(sb, group); @@ -5367,12 +5372,13 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ - if (group == last_group) + if (group == last_group) { end = last_cluster; - + whole_group = eof ? true : end == EXT4_CLUSTERS_PER_GROUP(sb) - 1; + } if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, - end, minlen); + end, minlen, whole_group); if (cnt < 0) { ret = cnt; break; From 767a50bef2aa916a7d1293deddc4d520e0c7b8e4 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Tue, 1 Aug 2023 22:32:00 +0800 Subject: [PATCH 10/13] ext4: replace the traditional ternary conditional operator with with max()/min() [ Upstream commit de8bf0e5ee7482585450357c6d4eddec8efc5cb7 ] Replace the traditional ternary conditional operator with with max()/min() Signed-off-by: Kemeng Shi Reviewed-by: Ritesh Harjani (IBM) Link: https://lore.kernel.org/r/20230801143204.2284343-7-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Stable-dep-of: 45e4ab320c9b ("ext4: move setting of trimmed bit into ext4_try_to_trim_range()") Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 7cd2f2c07858..412d2f6a0b91 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5202,8 +5202,7 @@ static int ext4_try_to_trim_range(struct super_block *sb, void *bitmap; bitmap = e4b->bd_bitmap; - start = (e4b->bd_info->bb_first_free > start) ? - e4b->bd_info->bb_first_free : start; + start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; @@ -5423,8 +5422,7 @@ ext4_mballoc_query_range( ext4_lock_group(sb, group); - start = (e4b.bd_info->bb_first_free > start) ? - e4b.bd_info->bb_first_free : start; + start = max(e4b.bd_info->bb_first_free, start); if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; From 4db34feaf29779860f840cf5b072661a83646331 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 13 Sep 2023 17:04:54 +0200 Subject: [PATCH 11/13] ext4: move setting of trimmed bit into ext4_try_to_trim_range() [ Upstream commit 45e4ab320c9b5fa67b1fc3b6a9b381cfcc0c8488 ] Currently we set the group's trimmed bit in ext4_trim_all_free() based on return value of ext4_try_to_trim_range(). However when we will want to abort trimming because of suspend attempt, we want to return success from ext4_try_to_trim_range() but not set the trimmed bit. Instead implementing awkward propagation of this information, just move setting of trimmed bit into ext4_try_to_trim_range() when the whole group is trimmed. Cc: stable@kernel.org Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20230913150504.9054-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 46 +++++++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 21 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 412d2f6a0b91..3632c7258e61 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5194,14 +5194,27 @@ __acquires(bitlock) return ret; } +static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, + ext4_group_t grp) +{ + if (grp < ext4_get_groups_count(sb)) + return EXT4_CLUSTERS_PER_GROUP(sb) - 1; + return (ext4_blocks_count(EXT4_SB(sb)->s_es) - + ext4_group_first_block_no(sb, grp) - 1) >> + EXT4_CLUSTER_BITS(sb); +} + static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { ext4_grpblk_t next, count, free_count; + bool set_trimmed = false; void *bitmap; bitmap = e4b->bd_bitmap; + if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group)) + set_trimmed = true; start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; @@ -5216,16 +5229,14 @@ static int ext4_try_to_trim_range(struct super_block *sb, int ret = ext4_trim_extent(sb, start, next - start, e4b); if (ret && ret != -EOPNOTSUPP) - break; + return count; count += next - start; } free_count += next - start; start = next + 1; - if (fatal_signal_pending(current)) { - count = -ERESTARTSYS; - break; - } + if (fatal_signal_pending(current)) + return -ERESTARTSYS; if (need_resched()) { ext4_unlock_group(sb, e4b->bd_group); @@ -5237,6 +5248,9 @@ static int ext4_try_to_trim_range(struct super_block *sb, break; } + if (set_trimmed) + EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info); + return count; } @@ -5247,7 +5261,6 @@ static int ext4_try_to_trim_range(struct super_block *sb, * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count - * @set_trimmed: set the trimmed flag if at least one block is trimmed * * ext4_trim_all_free walks through group's buddy bitmap searching for free * extents. When the free block is found, ext4_trim_extent is called to TRIM @@ -5262,7 +5275,7 @@ static int ext4_try_to_trim_range(struct super_block *sb, static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, - ext4_grpblk_t minblocks, bool set_trimmed) + ext4_grpblk_t minblocks) { struct ext4_buddy e4b; int ret; @@ -5279,13 +5292,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_lock_group(sb, group); if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || - minblocks < EXT4_SB(sb)->s_last_trim_minblks) { + minblocks < EXT4_SB(sb)->s_last_trim_minblks) ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); - if (ret >= 0 && set_trimmed) - EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); - } else { + else ret = 0; - } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); @@ -5318,7 +5328,6 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); - bool whole_group, eof = false; int ret = 0; start = range->start >> sb->s_blocksize_bits; @@ -5337,10 +5346,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } - if (end >= max_blks - 1) { + if (end >= max_blks - 1) end = max_blks - 1; - eof = true; - } if (end <= first_data_blk) goto out; if (start < first_data_blk) @@ -5354,7 +5361,6 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; - whole_group = true; for (group = first_group; group <= last_group; group++) { grp = ext4_get_group_info(sb, group); @@ -5371,13 +5377,11 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ - if (group == last_group) { + if (group == last_group) end = last_cluster; - whole_group = eof ? true : end == EXT4_CLUSTERS_PER_GROUP(sb) - 1; - } if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, - end, minlen, whole_group); + end, minlen); if (cnt < 0) { ret = cnt; break; From 0c908e1595888d3aa000b31989cd3686e75c1c1d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 13 Sep 2023 17:04:55 +0200 Subject: [PATCH 12/13] ext4: do not let fstrim block system suspend [ Upstream commit 5229a658f6453362fbb9da6bf96872ef25a7097e ] Len Brown has reported that system suspend sometimes fail due to inability to freeze a task working in ext4_trim_fs() for one minute. Trimming a large filesystem on a disk that slowly processes discard requests can indeed take a long time. Since discard is just an advisory call, it is perfectly fine to interrupt it at any time and the return number of discarded blocks until that moment. Do that when we detect the task is being frozen. Cc: stable@kernel.org Reported-by: Len Brown Suggested-by: Dave Chinner References: https://bugzilla.kernel.org/show_bug.cgi?id=216322 Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20230913150504.9054-2-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 3632c7258e61..9099e112fda5 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #ifdef CONFIG_EXT4_DEBUG @@ -5204,6 +5205,11 @@ static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, EXT4_CLUSTER_BITS(sb); } +static bool ext4_trim_interrupted(void) +{ + return fatal_signal_pending(current) || freezing(current); +} + static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) @@ -5235,8 +5241,8 @@ static int ext4_try_to_trim_range(struct super_block *sb, free_count += next - start; start = next + 1; - if (fatal_signal_pending(current)) - return -ERESTARTSYS; + if (ext4_trim_interrupted()) + return count; if (need_resched()) { ext4_unlock_group(sb, e4b->bd_group); @@ -5363,6 +5369,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; for (group = first_group; group <= last_group; group++) { + if (ext4_trim_interrupted()) + break; grp = ext4_get_group_info(sb, group); /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { From d2a6844be5bd367444b3ec35ff8c565f7473e54f Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 7 Sep 2023 11:05:04 +0200 Subject: [PATCH 13/13] ASoC: meson: spdifin: start hw on dai probe [ Upstream commit aedf323b66b2b875137422ecb7d2525179759076 ] For spdif input to report the locked rate correctly, even when no capture is running, the HW and reference clock must be started as soon as the dai is probed. Fixes: 5ce5658375e6 ("ASoC: meson: add axg spdif input") Signed-off-by: Jerome Brunet Link: https://lore.kernel.org/r/20230907090504.12700-1-jbrunet@baylibre.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/meson/axg-spdifin.c | 49 ++++++++++++----------------------- 1 file changed, 17 insertions(+), 32 deletions(-) diff --git a/sound/soc/meson/axg-spdifin.c b/sound/soc/meson/axg-spdifin.c index d0d09f945b48..7aaded1fc376 100644 --- a/sound/soc/meson/axg-spdifin.c +++ b/sound/soc/meson/axg-spdifin.c @@ -112,34 +112,6 @@ static int axg_spdifin_prepare(struct snd_pcm_substream *substream, return 0; } -static int axg_spdifin_startup(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); - int ret; - - ret = clk_prepare_enable(priv->refclk); - if (ret) { - dev_err(dai->dev, - "failed to enable spdifin reference clock\n"); - return ret; - } - - regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, - SPDIFIN_CTRL0_EN); - - return 0; -} - -static void axg_spdifin_shutdown(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); - - regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, 0); - clk_disable_unprepare(priv->refclk); -} - static void axg_spdifin_write_mode_param(struct regmap *map, int mode, unsigned int val, unsigned int num_per_reg, @@ -251,25 +223,38 @@ static int axg_spdifin_dai_probe(struct snd_soc_dai *dai) ret = axg_spdifin_sample_mode_config(dai, priv); if (ret) { dev_err(dai->dev, "mode configuration failed\n"); - clk_disable_unprepare(priv->pclk); - return ret; + goto pclk_err; } + ret = clk_prepare_enable(priv->refclk); + if (ret) { + dev_err(dai->dev, + "failed to enable spdifin reference clock\n"); + goto pclk_err; + } + + regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, + SPDIFIN_CTRL0_EN); + return 0; + +pclk_err: + clk_disable_unprepare(priv->pclk); + return ret; } static int axg_spdifin_dai_remove(struct snd_soc_dai *dai) { struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); + regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, 0); + clk_disable_unprepare(priv->refclk); clk_disable_unprepare(priv->pclk); return 0; } static const struct snd_soc_dai_ops axg_spdifin_ops = { .prepare = axg_spdifin_prepare, - .startup = axg_spdifin_startup, - .shutdown = axg_spdifin_shutdown, }; static int axg_spdifin_iec958_info(struct snd_kcontrol *kcontrol,