- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] ext4: fix use-after-free race in ext4_remount()'s error path" failed to apply to 3.18-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 3.18-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 33458eaba4dfe778a426df6a19b7aad2ff9f7eec Mon Sep 17 00:00:00 2001 From: Theodore Ts'o <tytso(a)mit.edu> Date: Fri, 12 Oct 2018 09:28:09 -0400 Subject: [PATCH] ext4: fix use-after-free race in ext4_remount()'s error path It's possible for ext4_show_quota_options() to try reading s_qf_names[i] while it is being modified by ext4_remount() --- most notably, in ext4_remount's error path when the original values of the quota file name gets restored. Reported-by: syzbot+a2872d6feea6918008a9(a)syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org # 3.2+ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 86e1bacac757..12f90d48ba61 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1405,7 +1405,8 @@ struct ext4_sb_info { u32 s_min_batch_time; struct block_device *journal_bdev; #ifdef CONFIG_QUOTA - char *s_qf_names[EXT4_MAXQUOTAS]; /* Names of quota files with journalled quota */ + /* Names of quota files with journalled quota */ + char __rcu *s_qf_names[EXT4_MAXQUOTAS]; int s_jquota_fmt; /* Format of quota to use */ #endif unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index faf293ed8060..a221f1cdf704 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -914,6 +914,18 @@ static inline void ext4_quota_off_umount(struct super_block *sb) for (type = 0; type < EXT4_MAXQUOTAS; type++) ext4_quota_off(sb, type); } + +/* + * This is a helper function which is used in the mount/remount + * codepaths (which holds s_umount) to fetch the quota file name. + */ +static inline char *get_qf_name(struct super_block *sb, + struct ext4_sb_info *sbi, + int type) +{ + return rcu_dereference_protected(sbi->s_qf_names[type], + lockdep_is_held(&sb->s_umount)); +} #else static inline void ext4_quota_off_umount(struct super_block *sb) { @@ -965,7 +977,7 @@ static void ext4_put_super(struct super_block *sb) percpu_free_rwsem(&sbi->s_journal_flag_rwsem); #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) - kfree(sbi->s_qf_names[i]); + kfree(get_qf_name(sb, sbi, i)); #endif /* Debugging code just in case the in-memory inode orphan list @@ -1531,11 +1543,10 @@ static const char deprecated_msg[] = static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char *qname; + char *qname, *old_qname = get_qf_name(sb, sbi, qtype); int ret = -1; - if (sb_any_quota_loaded(sb) && - !sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && !old_qname) { ext4_msg(sb, KERN_ERR, "Cannot change journaled " "quota options when quota turned on"); @@ -1552,8 +1563,8 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) "Not enough memory for storing quotafile name"); return -1; } - if (sbi->s_qf_names[qtype]) { - if (strcmp(sbi->s_qf_names[qtype], qname) == 0) + if (old_qname) { + if (strcmp(old_qname, qname) == 0) ret = 1; else ext4_msg(sb, KERN_ERR, @@ -1566,7 +1577,7 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) "quotafile must be on filesystem root"); goto errout; } - sbi->s_qf_names[qtype] = qname; + rcu_assign_pointer(sbi->s_qf_names[qtype], qname); set_opt(sb, QUOTA); return 1; errout: @@ -1578,15 +1589,16 @@ static int clear_qf_name(struct super_block *sb, int qtype) { struct ext4_sb_info *sbi = EXT4_SB(sb); + char *old_qname = get_qf_name(sb, sbi, qtype); - if (sb_any_quota_loaded(sb) && - sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && old_qname) { ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options" " when quota turned on"); return -1; } - kfree(sbi->s_qf_names[qtype]); - sbi->s_qf_names[qtype] = NULL; + rcu_assign_pointer(sbi->s_qf_names[qtype], NULL); + synchronize_rcu(); + kfree(old_qname); return 1; } #endif @@ -1961,7 +1973,7 @@ static int parse_options(char *options, struct super_block *sb, int is_remount) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char *p; + char *p, __maybe_unused *usr_qf_name, __maybe_unused *grp_qf_name; substring_t args[MAX_OPT_ARGS]; int token; @@ -1992,11 +2004,13 @@ static int parse_options(char *options, struct super_block *sb, "Cannot enable project quota enforcement."); return 0; } - if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { - if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA]) + usr_qf_name = get_qf_name(sb, sbi, USRQUOTA); + grp_qf_name = get_qf_name(sb, sbi, GRPQUOTA); + if (usr_qf_name || grp_qf_name) { + if (test_opt(sb, USRQUOTA) && usr_qf_name) clear_opt(sb, USRQUOTA); - if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA]) + if (test_opt(sb, GRPQUOTA) && grp_qf_name) clear_opt(sb, GRPQUOTA); if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) { @@ -2030,6 +2044,7 @@ static inline void ext4_show_quota_options(struct seq_file *seq, { #if defined(CONFIG_QUOTA) struct ext4_sb_info *sbi = EXT4_SB(sb); + char *usr_qf_name, *grp_qf_name; if (sbi->s_jquota_fmt) { char *fmtname = ""; @@ -2048,11 +2063,14 @@ static inline void ext4_show_quota_options(struct seq_file *seq, seq_printf(seq, ",jqfmt=%s", fmtname); } - if (sbi->s_qf_names[USRQUOTA]) - seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]); - - if (sbi->s_qf_names[GRPQUOTA]) - seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]); + rcu_read_lock(); + usr_qf_name = rcu_dereference(sbi->s_qf_names[USRQUOTA]); + grp_qf_name = rcu_dereference(sbi->s_qf_names[GRPQUOTA]); + if (usr_qf_name) + seq_show_option(seq, "usrjquota", usr_qf_name); + if (grp_qf_name) + seq_show_option(seq, "grpjquota", grp_qf_name); + rcu_read_unlock(); #endif } @@ -5104,6 +5122,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) int err = 0; #ifdef CONFIG_QUOTA int i, j; + char *to_free[EXT4_MAXQUOTAS]; #endif char *orig_data = kstrdup(data, GFP_KERNEL); @@ -5123,8 +5142,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) old_opts.s_jquota_fmt = sbi->s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) if (sbi->s_qf_names[i]) { - old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i], - GFP_KERNEL); + char *qf_name = get_qf_name(sb, sbi, i); + + old_opts.s_qf_names[i] = kstrdup(qf_name, GFP_KERNEL); if (!old_opts.s_qf_names[i]) { for (j = 0; j < i; j++) kfree(old_opts.s_qf_names[j]); @@ -5353,9 +5373,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { - kfree(sbi->s_qf_names[i]); - sbi->s_qf_names[i] = old_opts.s_qf_names[i]; + to_free[i] = get_qf_name(sb, sbi, i); + rcu_assign_pointer(sbi->s_qf_names[i], old_opts.s_qf_names[i]); } + synchronize_rcu(); + for (i = 0; i < EXT4_MAXQUOTAS; i++) + kfree(to_free[i]); #endif kfree(orig_data); return err; @@ -5546,7 +5569,7 @@ static int ext4_write_info(struct super_block *sb, int type) */ static int ext4_quota_on_mount(struct super_block *sb, int type) { - return dquot_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type], + return dquot_quota_on_mount(sb, get_qf_name(sb, EXT4_SB(sb), type), EXT4_SB(sb)->s_jquota_fmt, type); }

7 years

1
0
0 0

FAILED: patch "[PATCH] ext4: fix use-after-free race in ext4_remount()'s error path" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 33458eaba4dfe778a426df6a19b7aad2ff9f7eec Mon Sep 17 00:00:00 2001 From: Theodore Ts'o <tytso(a)mit.edu> Date: Fri, 12 Oct 2018 09:28:09 -0400 Subject: [PATCH] ext4: fix use-after-free race in ext4_remount()'s error path It's possible for ext4_show_quota_options() to try reading s_qf_names[i] while it is being modified by ext4_remount() --- most notably, in ext4_remount's error path when the original values of the quota file name gets restored. Reported-by: syzbot+a2872d6feea6918008a9(a)syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org # 3.2+ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 86e1bacac757..12f90d48ba61 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1405,7 +1405,8 @@ struct ext4_sb_info { u32 s_min_batch_time; struct block_device *journal_bdev; #ifdef CONFIG_QUOTA - char *s_qf_names[EXT4_MAXQUOTAS]; /* Names of quota files with journalled quota */ + /* Names of quota files with journalled quota */ + char __rcu *s_qf_names[EXT4_MAXQUOTAS]; int s_jquota_fmt; /* Format of quota to use */ #endif unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index faf293ed8060..a221f1cdf704 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -914,6 +914,18 @@ static inline void ext4_quota_off_umount(struct super_block *sb) for (type = 0; type < EXT4_MAXQUOTAS; type++) ext4_quota_off(sb, type); } + +/* + * This is a helper function which is used in the mount/remount + * codepaths (which holds s_umount) to fetch the quota file name. + */ +static inline char *get_qf_name(struct super_block *sb, + struct ext4_sb_info *sbi, + int type) +{ + return rcu_dereference_protected(sbi->s_qf_names[type], + lockdep_is_held(&sb->s_umount)); +} #else static inline void ext4_quota_off_umount(struct super_block *sb) { @@ -965,7 +977,7 @@ static void ext4_put_super(struct super_block *sb) percpu_free_rwsem(&sbi->s_journal_flag_rwsem); #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) - kfree(sbi->s_qf_names[i]); + kfree(get_qf_name(sb, sbi, i)); #endif /* Debugging code just in case the in-memory inode orphan list @@ -1531,11 +1543,10 @@ static const char deprecated_msg[] = static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char *qname; + char *qname, *old_qname = get_qf_name(sb, sbi, qtype); int ret = -1; - if (sb_any_quota_loaded(sb) && - !sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && !old_qname) { ext4_msg(sb, KERN_ERR, "Cannot change journaled " "quota options when quota turned on"); @@ -1552,8 +1563,8 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) "Not enough memory for storing quotafile name"); return -1; } - if (sbi->s_qf_names[qtype]) { - if (strcmp(sbi->s_qf_names[qtype], qname) == 0) + if (old_qname) { + if (strcmp(old_qname, qname) == 0) ret = 1; else ext4_msg(sb, KERN_ERR, @@ -1566,7 +1577,7 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) "quotafile must be on filesystem root"); goto errout; } - sbi->s_qf_names[qtype] = qname; + rcu_assign_pointer(sbi->s_qf_names[qtype], qname); set_opt(sb, QUOTA); return 1; errout: @@ -1578,15 +1589,16 @@ static int clear_qf_name(struct super_block *sb, int qtype) { struct ext4_sb_info *sbi = EXT4_SB(sb); + char *old_qname = get_qf_name(sb, sbi, qtype); - if (sb_any_quota_loaded(sb) && - sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && old_qname) { ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options" " when quota turned on"); return -1; } - kfree(sbi->s_qf_names[qtype]); - sbi->s_qf_names[qtype] = NULL; + rcu_assign_pointer(sbi->s_qf_names[qtype], NULL); + synchronize_rcu(); + kfree(old_qname); return 1; } #endif @@ -1961,7 +1973,7 @@ static int parse_options(char *options, struct super_block *sb, int is_remount) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char *p; + char *p, __maybe_unused *usr_qf_name, __maybe_unused *grp_qf_name; substring_t args[MAX_OPT_ARGS]; int token; @@ -1992,11 +2004,13 @@ static int parse_options(char *options, struct super_block *sb, "Cannot enable project quota enforcement."); return 0; } - if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { - if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA]) + usr_qf_name = get_qf_name(sb, sbi, USRQUOTA); + grp_qf_name = get_qf_name(sb, sbi, GRPQUOTA); + if (usr_qf_name || grp_qf_name) { + if (test_opt(sb, USRQUOTA) && usr_qf_name) clear_opt(sb, USRQUOTA); - if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA]) + if (test_opt(sb, GRPQUOTA) && grp_qf_name) clear_opt(sb, GRPQUOTA); if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) { @@ -2030,6 +2044,7 @@ static inline void ext4_show_quota_options(struct seq_file *seq, { #if defined(CONFIG_QUOTA) struct ext4_sb_info *sbi = EXT4_SB(sb); + char *usr_qf_name, *grp_qf_name; if (sbi->s_jquota_fmt) { char *fmtname = ""; @@ -2048,11 +2063,14 @@ static inline void ext4_show_quota_options(struct seq_file *seq, seq_printf(seq, ",jqfmt=%s", fmtname); } - if (sbi->s_qf_names[USRQUOTA]) - seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]); - - if (sbi->s_qf_names[GRPQUOTA]) - seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]); + rcu_read_lock(); + usr_qf_name = rcu_dereference(sbi->s_qf_names[USRQUOTA]); + grp_qf_name = rcu_dereference(sbi->s_qf_names[GRPQUOTA]); + if (usr_qf_name) + seq_show_option(seq, "usrjquota", usr_qf_name); + if (grp_qf_name) + seq_show_option(seq, "grpjquota", grp_qf_name); + rcu_read_unlock(); #endif } @@ -5104,6 +5122,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) int err = 0; #ifdef CONFIG_QUOTA int i, j; + char *to_free[EXT4_MAXQUOTAS]; #endif char *orig_data = kstrdup(data, GFP_KERNEL); @@ -5123,8 +5142,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) old_opts.s_jquota_fmt = sbi->s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) if (sbi->s_qf_names[i]) { - old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i], - GFP_KERNEL); + char *qf_name = get_qf_name(sb, sbi, i); + + old_opts.s_qf_names[i] = kstrdup(qf_name, GFP_KERNEL); if (!old_opts.s_qf_names[i]) { for (j = 0; j < i; j++) kfree(old_opts.s_qf_names[j]); @@ -5353,9 +5373,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { - kfree(sbi->s_qf_names[i]); - sbi->s_qf_names[i] = old_opts.s_qf_names[i]; + to_free[i] = get_qf_name(sb, sbi, i); + rcu_assign_pointer(sbi->s_qf_names[i], old_opts.s_qf_names[i]); } + synchronize_rcu(); + for (i = 0; i < EXT4_MAXQUOTAS; i++) + kfree(to_free[i]); #endif kfree(orig_data); return err; @@ -5546,7 +5569,7 @@ static int ext4_write_info(struct super_block *sb, int type) */ static int ext4_quota_on_mount(struct super_block *sb, int type) { - return dquot_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type], + return dquot_quota_on_mount(sb, get_qf_name(sb, EXT4_SB(sb), type), EXT4_SB(sb)->s_jquota_fmt, type); }

7 years

1
0
0 0

FAILED: patch "[PATCH] ext4: fix use-after-free race in ext4_remount()'s error path" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 33458eaba4dfe778a426df6a19b7aad2ff9f7eec Mon Sep 17 00:00:00 2001 From: Theodore Ts'o <tytso(a)mit.edu> Date: Fri, 12 Oct 2018 09:28:09 -0400 Subject: [PATCH] ext4: fix use-after-free race in ext4_remount()'s error path It's possible for ext4_show_quota_options() to try reading s_qf_names[i] while it is being modified by ext4_remount() --- most notably, in ext4_remount's error path when the original values of the quota file name gets restored. Reported-by: syzbot+a2872d6feea6918008a9(a)syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org # 3.2+ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 86e1bacac757..12f90d48ba61 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1405,7 +1405,8 @@ struct ext4_sb_info { u32 s_min_batch_time; struct block_device *journal_bdev; #ifdef CONFIG_QUOTA - char *s_qf_names[EXT4_MAXQUOTAS]; /* Names of quota files with journalled quota */ + /* Names of quota files with journalled quota */ + char __rcu *s_qf_names[EXT4_MAXQUOTAS]; int s_jquota_fmt; /* Format of quota to use */ #endif unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index faf293ed8060..a221f1cdf704 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -914,6 +914,18 @@ static inline void ext4_quota_off_umount(struct super_block *sb) for (type = 0; type < EXT4_MAXQUOTAS; type++) ext4_quota_off(sb, type); } + +/* + * This is a helper function which is used in the mount/remount + * codepaths (which holds s_umount) to fetch the quota file name. + */ +static inline char *get_qf_name(struct super_block *sb, + struct ext4_sb_info *sbi, + int type) +{ + return rcu_dereference_protected(sbi->s_qf_names[type], + lockdep_is_held(&sb->s_umount)); +} #else static inline void ext4_quota_off_umount(struct super_block *sb) { @@ -965,7 +977,7 @@ static void ext4_put_super(struct super_block *sb) percpu_free_rwsem(&sbi->s_journal_flag_rwsem); #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) - kfree(sbi->s_qf_names[i]); + kfree(get_qf_name(sb, sbi, i)); #endif /* Debugging code just in case the in-memory inode orphan list @@ -1531,11 +1543,10 @@ static const char deprecated_msg[] = static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char *qname; + char *qname, *old_qname = get_qf_name(sb, sbi, qtype); int ret = -1; - if (sb_any_quota_loaded(sb) && - !sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && !old_qname) { ext4_msg(sb, KERN_ERR, "Cannot change journaled " "quota options when quota turned on"); @@ -1552,8 +1563,8 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) "Not enough memory for storing quotafile name"); return -1; } - if (sbi->s_qf_names[qtype]) { - if (strcmp(sbi->s_qf_names[qtype], qname) == 0) + if (old_qname) { + if (strcmp(old_qname, qname) == 0) ret = 1; else ext4_msg(sb, KERN_ERR, @@ -1566,7 +1577,7 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) "quotafile must be on filesystem root"); goto errout; } - sbi->s_qf_names[qtype] = qname; + rcu_assign_pointer(sbi->s_qf_names[qtype], qname); set_opt(sb, QUOTA); return 1; errout: @@ -1578,15 +1589,16 @@ static int clear_qf_name(struct super_block *sb, int qtype) { struct ext4_sb_info *sbi = EXT4_SB(sb); + char *old_qname = get_qf_name(sb, sbi, qtype); - if (sb_any_quota_loaded(sb) && - sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && old_qname) { ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options" " when quota turned on"); return -1; } - kfree(sbi->s_qf_names[qtype]); - sbi->s_qf_names[qtype] = NULL; + rcu_assign_pointer(sbi->s_qf_names[qtype], NULL); + synchronize_rcu(); + kfree(old_qname); return 1; } #endif @@ -1961,7 +1973,7 @@ static int parse_options(char *options, struct super_block *sb, int is_remount) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char *p; + char *p, __maybe_unused *usr_qf_name, __maybe_unused *grp_qf_name; substring_t args[MAX_OPT_ARGS]; int token; @@ -1992,11 +2004,13 @@ static int parse_options(char *options, struct super_block *sb, "Cannot enable project quota enforcement."); return 0; } - if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { - if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA]) + usr_qf_name = get_qf_name(sb, sbi, USRQUOTA); + grp_qf_name = get_qf_name(sb, sbi, GRPQUOTA); + if (usr_qf_name || grp_qf_name) { + if (test_opt(sb, USRQUOTA) && usr_qf_name) clear_opt(sb, USRQUOTA); - if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA]) + if (test_opt(sb, GRPQUOTA) && grp_qf_name) clear_opt(sb, GRPQUOTA); if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) { @@ -2030,6 +2044,7 @@ static inline void ext4_show_quota_options(struct seq_file *seq, { #if defined(CONFIG_QUOTA) struct ext4_sb_info *sbi = EXT4_SB(sb); + char *usr_qf_name, *grp_qf_name; if (sbi->s_jquota_fmt) { char *fmtname = ""; @@ -2048,11 +2063,14 @@ static inline void ext4_show_quota_options(struct seq_file *seq, seq_printf(seq, ",jqfmt=%s", fmtname); } - if (sbi->s_qf_names[USRQUOTA]) - seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]); - - if (sbi->s_qf_names[GRPQUOTA]) - seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]); + rcu_read_lock(); + usr_qf_name = rcu_dereference(sbi->s_qf_names[USRQUOTA]); + grp_qf_name = rcu_dereference(sbi->s_qf_names[GRPQUOTA]); + if (usr_qf_name) + seq_show_option(seq, "usrjquota", usr_qf_name); + if (grp_qf_name) + seq_show_option(seq, "grpjquota", grp_qf_name); + rcu_read_unlock(); #endif } @@ -5104,6 +5122,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) int err = 0; #ifdef CONFIG_QUOTA int i, j; + char *to_free[EXT4_MAXQUOTAS]; #endif char *orig_data = kstrdup(data, GFP_KERNEL); @@ -5123,8 +5142,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) old_opts.s_jquota_fmt = sbi->s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) if (sbi->s_qf_names[i]) { - old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i], - GFP_KERNEL); + char *qf_name = get_qf_name(sb, sbi, i); + + old_opts.s_qf_names[i] = kstrdup(qf_name, GFP_KERNEL); if (!old_opts.s_qf_names[i]) { for (j = 0; j < i; j++) kfree(old_opts.s_qf_names[j]); @@ -5353,9 +5373,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { - kfree(sbi->s_qf_names[i]); - sbi->s_qf_names[i] = old_opts.s_qf_names[i]; + to_free[i] = get_qf_name(sb, sbi, i); + rcu_assign_pointer(sbi->s_qf_names[i], old_opts.s_qf_names[i]); } + synchronize_rcu(); + for (i = 0; i < EXT4_MAXQUOTAS; i++) + kfree(to_free[i]); #endif kfree(orig_data); return err; @@ -5546,7 +5569,7 @@ static int ext4_write_info(struct super_block *sb, int type) */ static int ext4_quota_on_mount(struct super_block *sb, int type) { - return dquot_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type], + return dquot_quota_on_mount(sb, get_qf_name(sb, EXT4_SB(sb), type), EXT4_SB(sb)->s_jquota_fmt, type); }

7 years

1
0
0 0

FAILED: patch "[PATCH] IB/rxe: Revise the ib_wr_opcode enum" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 9a59739bd01f77db6fbe2955a4fce165f0f43568 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe <jgg(a)mellanox.com> Date: Tue, 14 Aug 2018 15:33:02 -0700 Subject: [PATCH] IB/rxe: Revise the ib_wr_opcode enum This enum has become part of the uABI, as both RXE and the ib_uverbs_post_send() command expect userspace to supply values from this enum. So it should be properly placed in include/uapi/rdma. In userspace this enum is called 'enum ibv_wr_opcode' as part of libibverbs.h. That enum defines different values for IB_WR_LOCAL_INV, IB_WR_SEND_WITH_INV, and IB_WR_LSO. These were introduced (incorrectly, it turns out) into libiberbs in 2015. The kernel has changed its mind on the numbering for several of the IB_WC values over the years, but has remained stable on IB_WR_LOCAL_INV and below. Based on this we can conclude that there is no real user space user of the values beyond IB_WR_ATOMIC_FETCH_AND_ADD, as they have never worked via rdma-core. This is confirmed by inspection, only rxe uses the kernel enum and implements the latter operations. rxe has clearly never worked with these attributes from userspace. Other drivers that support these opcodes implement the functionality without calling out to the kernel. To make IB_WR_SEND_WITH_INV and related work for RXE in userspace we choose to renumber the IB_WR enum in the kernel to match the uABI that userspace has bee using since before Soft RoCE was merged. This is an overall simpler configuration for the whole software stack, and obviously can't break anything existing. Reported-by: Seth Howell <seth.howell(a)intel.com> Tested-by: Seth Howell <seth.howell(a)intel.com> Fixes: 8700e3e7c485 ("Soft RoCE driver") Cc: <stable(a)vger.kernel.org> Signed-off-by: Jason Gunthorpe <jgg(a)mellanox.com> diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 6076c9b72ab9..e463d3007a35 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1281,21 +1281,27 @@ struct ib_qp_attr { }; enum ib_wr_opcode { - IB_WR_RDMA_WRITE, - IB_WR_RDMA_WRITE_WITH_IMM, - IB_WR_SEND, - IB_WR_SEND_WITH_IMM, - IB_WR_RDMA_READ, - IB_WR_ATOMIC_CMP_AND_SWP, - IB_WR_ATOMIC_FETCH_AND_ADD, - IB_WR_LSO, - IB_WR_SEND_WITH_INV, - IB_WR_RDMA_READ_WITH_INV, - IB_WR_LOCAL_INV, - IB_WR_REG_MR, - IB_WR_MASKED_ATOMIC_CMP_AND_SWP, - IB_WR_MASKED_ATOMIC_FETCH_AND_ADD, + /* These are shared with userspace */ + IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE, + IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM, + IB_WR_SEND = IB_UVERBS_WR_SEND, + IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM, + IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ, + IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP, + IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD, + IB_WR_LSO = IB_UVERBS_WR_TSO, + IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV, + IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV, + IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV, + IB_WR_MASKED_ATOMIC_CMP_AND_SWP = + IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP, + IB_WR_MASKED_ATOMIC_FETCH_AND_ADD = + IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD, + + /* These are kernel only and can not be issued by userspace */ + IB_WR_REG_MR = 0x20, IB_WR_REG_SIG_MR, + /* reserve values for low level drivers' internal use. * These values will not be used at all in the ib core layer. */ diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 25a16760de2a..1254b51a551a 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -763,10 +763,28 @@ struct ib_uverbs_sge { __u32 lkey; }; +enum ib_uverbs_wr_opcode { + IB_UVERBS_WR_RDMA_WRITE = 0, + IB_UVERBS_WR_RDMA_WRITE_WITH_IMM = 1, + IB_UVERBS_WR_SEND = 2, + IB_UVERBS_WR_SEND_WITH_IMM = 3, + IB_UVERBS_WR_RDMA_READ = 4, + IB_UVERBS_WR_ATOMIC_CMP_AND_SWP = 5, + IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD = 6, + IB_UVERBS_WR_LOCAL_INV = 7, + IB_UVERBS_WR_BIND_MW = 8, + IB_UVERBS_WR_SEND_WITH_INV = 9, + IB_UVERBS_WR_TSO = 10, + IB_UVERBS_WR_RDMA_READ_WITH_INV = 11, + IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP = 12, + IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD = 13, + /* Review enum ib_wr_opcode before modifying this */ +}; + struct ib_uverbs_send_wr { __aligned_u64 wr_id; __u32 num_sge; - __u32 opcode; + __u32 opcode; /* see enum ib_uverbs_wr_opcode */ __u32 send_flags; union { __be32 imm_data;

7 years

1
0
0 0

FAILED: patch "[PATCH] IB/rxe: Revise the ib_wr_opcode enum" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 9a59739bd01f77db6fbe2955a4fce165f0f43568 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe <jgg(a)mellanox.com> Date: Tue, 14 Aug 2018 15:33:02 -0700 Subject: [PATCH] IB/rxe: Revise the ib_wr_opcode enum This enum has become part of the uABI, as both RXE and the ib_uverbs_post_send() command expect userspace to supply values from this enum. So it should be properly placed in include/uapi/rdma. In userspace this enum is called 'enum ibv_wr_opcode' as part of libibverbs.h. That enum defines different values for IB_WR_LOCAL_INV, IB_WR_SEND_WITH_INV, and IB_WR_LSO. These were introduced (incorrectly, it turns out) into libiberbs in 2015. The kernel has changed its mind on the numbering for several of the IB_WC values over the years, but has remained stable on IB_WR_LOCAL_INV and below. Based on this we can conclude that there is no real user space user of the values beyond IB_WR_ATOMIC_FETCH_AND_ADD, as they have never worked via rdma-core. This is confirmed by inspection, only rxe uses the kernel enum and implements the latter operations. rxe has clearly never worked with these attributes from userspace. Other drivers that support these opcodes implement the functionality without calling out to the kernel. To make IB_WR_SEND_WITH_INV and related work for RXE in userspace we choose to renumber the IB_WR enum in the kernel to match the uABI that userspace has bee using since before Soft RoCE was merged. This is an overall simpler configuration for the whole software stack, and obviously can't break anything existing. Reported-by: Seth Howell <seth.howell(a)intel.com> Tested-by: Seth Howell <seth.howell(a)intel.com> Fixes: 8700e3e7c485 ("Soft RoCE driver") Cc: <stable(a)vger.kernel.org> Signed-off-by: Jason Gunthorpe <jgg(a)mellanox.com> diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 6076c9b72ab9..e463d3007a35 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1281,21 +1281,27 @@ struct ib_qp_attr { }; enum ib_wr_opcode { - IB_WR_RDMA_WRITE, - IB_WR_RDMA_WRITE_WITH_IMM, - IB_WR_SEND, - IB_WR_SEND_WITH_IMM, - IB_WR_RDMA_READ, - IB_WR_ATOMIC_CMP_AND_SWP, - IB_WR_ATOMIC_FETCH_AND_ADD, - IB_WR_LSO, - IB_WR_SEND_WITH_INV, - IB_WR_RDMA_READ_WITH_INV, - IB_WR_LOCAL_INV, - IB_WR_REG_MR, - IB_WR_MASKED_ATOMIC_CMP_AND_SWP, - IB_WR_MASKED_ATOMIC_FETCH_AND_ADD, + /* These are shared with userspace */ + IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE, + IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM, + IB_WR_SEND = IB_UVERBS_WR_SEND, + IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM, + IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ, + IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP, + IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD, + IB_WR_LSO = IB_UVERBS_WR_TSO, + IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV, + IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV, + IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV, + IB_WR_MASKED_ATOMIC_CMP_AND_SWP = + IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP, + IB_WR_MASKED_ATOMIC_FETCH_AND_ADD = + IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD, + + /* These are kernel only and can not be issued by userspace */ + IB_WR_REG_MR = 0x20, IB_WR_REG_SIG_MR, + /* reserve values for low level drivers' internal use. * These values will not be used at all in the ib core layer. */ diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 25a16760de2a..1254b51a551a 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -763,10 +763,28 @@ struct ib_uverbs_sge { __u32 lkey; }; +enum ib_uverbs_wr_opcode { + IB_UVERBS_WR_RDMA_WRITE = 0, + IB_UVERBS_WR_RDMA_WRITE_WITH_IMM = 1, + IB_UVERBS_WR_SEND = 2, + IB_UVERBS_WR_SEND_WITH_IMM = 3, + IB_UVERBS_WR_RDMA_READ = 4, + IB_UVERBS_WR_ATOMIC_CMP_AND_SWP = 5, + IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD = 6, + IB_UVERBS_WR_LOCAL_INV = 7, + IB_UVERBS_WR_BIND_MW = 8, + IB_UVERBS_WR_SEND_WITH_INV = 9, + IB_UVERBS_WR_TSO = 10, + IB_UVERBS_WR_RDMA_READ_WITH_INV = 11, + IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP = 12, + IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD = 13, + /* Review enum ib_wr_opcode before modifying this */ +}; + struct ib_uverbs_send_wr { __aligned_u64 wr_id; __u32 num_sge; - __u32 opcode; + __u32 opcode; /* see enum ib_uverbs_wr_opcode */ __u32 send_flags; union { __be32 imm_data;

7 years

1
0
0 0

[PATCH for-stable] dmaengine: stm32-dma: fix incomplete configuration in cyclic mode

by Joel Fernandes (Google)

From: Pierre Yves MORDRET <pierre-yves.mordret(a)st.com> commit e57cb3b3f10d005410f09d4598cc6d62b833f2b0 upstream. When in cyclic mode, the configuration is updated after having started the DMA hardware (STM32_DMA_SCR_EN) leading to incomplete configuration of SMxAR registers. Signed-off-by: Pierre-Yves MORDRET <pierre-yves.mordret(a)st.com> Signed-off-by: Hugues Fruchet <hugues.fruchet(a)st.com> Signed-off-by: Vinod Koul <vinod.koul(a)intel.com> --- drivers/dma/stm32-dma.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index 4099948b6914..fae7de54f00a 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -441,6 +441,8 @@ static void stm32_dma_dump_reg(struct stm32_dma_chan *chan) dev_dbg(chan2dev(chan), "SFCR: 0x%08x\n", sfcr); } +static void stm32_dma_configure_next_sg(struct stm32_dma_chan *chan); + static void stm32_dma_start_transfer(struct stm32_dma_chan *chan) { struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan); @@ -483,6 +485,9 @@ static void stm32_dma_start_transfer(struct stm32_dma_chan *chan) if (status) stm32_dma_irq_clear(chan, status); + if (chan->desc->cyclic) + stm32_dma_configure_next_sg(chan); + stm32_dma_dump_reg(chan); /* Start DMA */ @@ -576,8 +581,7 @@ static void stm32_dma_issue_pending(struct dma_chan *c) if (vchan_issue_pending(&chan->vchan) && !chan->desc && !chan->busy) { dev_dbg(chan2dev(chan), "vchan %p: issued\n", &chan->vchan); stm32_dma_start_transfer(chan); - if (chan->desc->cyclic) - stm32_dma_configure_next_sg(chan); + } spin_unlock_irqrestore(&chan->vchan.lock, flags); } -- 2.19.0.605.g01d371f741-goog

7 years

2
1
0 0

stable/linux-3.18.y boot: 31 boots: 0 failed, 25 passed with 6 offline (v3.18.125)

by kernelci.org bot

stable/linux-3.18.y boot: 31 boots: 0 failed, 25 passed with 6 offline (v3.18.125) Full Boot Summary: https://kernelci.org/boot/all/job/stable/branch/linux-3.18.y/kernel/v3.18.1… Full Build Summary: https://kernelci.org/build/stable/branch/linux-3.18.y/kernel/v3.18.125/ Tree: stable Branch: linux-3.18.y Git Describe: v3.18.125 Git Commit: 78e0897dd8b321ba1b4a2137778ab7ae7d400af5 Git URL: http://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git Tested: 18 unique boards, 10 SoC families, 10 builds out of 183 Offline Platforms: arm: tegra_defconfig: tegra124-jetson-tk1: 1 offline lab bcm2835_defconfig: bcm2835-rpi-b: 1 offline lab omap2plus_defconfig: am335x-boneblack: 1 offline lab multi_v7_defconfig: am335x-boneblack: 1 offline lab tegra124-jetson-tk1: 1 offline lab sama5_defconfig: at91-sama5d4ek: 1 offline lab --- For more info write to <info(a)kernelci.org>

7 years

1
0
0 0

stable/linux-4.9.y boot: 62 boots: 0 failed, 48 passed with 14 offline (v4.9.136)

by kernelci.org bot

stable/linux-4.9.y boot: 62 boots: 0 failed, 48 passed with 14 offline (v4.9.136) Full Boot Summary: https://kernelci.org/boot/all/job/stable/branch/linux-4.9.y/kernel/v4.9.136/ Full Build Summary: https://kernelci.org/build/stable/branch/linux-4.9.y/kernel/v4.9.136/ Tree: stable Branch: linux-4.9.y Git Describe: v4.9.136 Git Commit: 0bb1a5e5aa1728a2c501cdd916923ef44fc07e2f Git URL: http://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git Tested: 38 unique boards, 17 SoC families, 13 builds out of 182 Offline Platforms: arm: omap2plus_defconfig: am335x-boneblack: 1 offline lab sunxi_defconfig: sun5i-r8-chip: 1 offline lab tegra_defconfig: tegra124-jetson-tk1: 1 offline lab bcm2835_defconfig: bcm2835-rpi-b: 1 offline lab sama5_defconfig: at91-sama5d4_xplained: 1 offline lab multi_v7_defconfig: alpine-db: 1 offline lab am335x-boneblack: 1 offline lab at91-sama5d4_xplained: 1 offline lab socfpga_cyclone5_de0_sockit: 1 offline lab sun5i-r8-chip: 1 offline lab tegra124-jetson-tk1: 1 offline lab socfpga_defconfig: socfpga_cyclone5_de0_sockit: 1 offline lab arm64: defconfig: apq8016-sbc: 1 offline lab juno-r2: 1 offline lab --- For more info write to <info(a)kernelci.org>

7 years

1
0
0 0

[PATCH 3.16, 4.4, 4.9] dm bufio: drop the lock when doing GFP_NOIO allocation

by Mikulas Patocka

This is backport of the upstream patch 41c73a49df31151f4ff868f28fe4f129f113fa2c. It should be backported to stable kernels because this performance problem was seen on the android 4.4 kernel. commit 41c73a49df31151f4ff868f28fe4f129f113fa2c Author: Mikulas Patocka <mpatocka(a)redhat.com> Date: Wed Nov 23 17:04:00 2016 -0500 dm bufio: drop the lock when doing GFP_NOIO allocation If the first allocation attempt using GFP_NOWAIT fails, drop the lock and retry using GFP_NOIO allocation (lock is dropped because the allocation can take some time). Note that we won't do GFP_NOIO allocation when we loop for the second time, because the lock shouldn't be dropped between __wait_for_free_buffer and __get_unclaimed_buffer. Signed-off-by: Mikulas Patocka <mpatocka(a)redhat.com> Signed-off-by: Mike Snitzer <snitzer(a)redhat.com> diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 9ef88f0e2382..1c2e1dd7ca16 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -822,6 +822,7 @@ enum new_flag { static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client *c, enum new_flag nf) { struct dm_buffer *b; + bool tried_noio_alloc = false; /* * dm-bufio is resistant to allocation failures (it just keeps @@ -846,6 +847,15 @@ static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client if (nf == NF_PREFETCH) return NULL; + if (dm_bufio_cache_size_latch != 1 && !tried_noio_alloc) { + dm_bufio_unlock(c); + b = alloc_buffer(c, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + dm_bufio_lock(c); + if (b) + return b; + tried_noio_alloc = true; + } + if (!list_empty(&c->reserved_buffers)) { b = list_entry(c->reserved_buffers.next, struct dm_buffer, lru_list);

7 years

3
2
0 0

[PATCH 3.16, 4.4, 4.9] dm bufio: avoid sleeping while holding the dm_bufio lock

by Mikulas Patocka

This is backport of the upstream patch 9ea61cac0b1ad0c09022f39fd97e9b99a2cfc2dc. It should be backported to stable kernels because this performance problem was seen on the android 4.4 kernel. commit 9ea61cac0b1ad0c09022f39fd97e9b99a2cfc2dc Author: Douglas Anderson <dianders(a)chromium.org> Date: Thu Nov 17 11:24:20 2016 -0800 dm bufio: avoid sleeping while holding the dm_bufio lock We've seen in-field reports showing _lots_ (18 in one case, 41 in another) of tasks all sitting there blocked on: mutex_lock+0x4c/0x68 dm_bufio_shrink_count+0x38/0x78 shrink_slab.part.54.constprop.65+0x100/0x464 shrink_zone+0xa8/0x198 In the two cases analyzed, we see one task that looks like this: Workqueue: kverityd verity_prefetch_io __switch_to+0x9c/0xa8 __schedule+0x440/0x6d8 schedule+0x94/0xb4 schedule_timeout+0x204/0x27c schedule_timeout_uninterruptible+0x44/0x50 wait_iff_congested+0x9c/0x1f0 shrink_inactive_list+0x3a0/0x4cc shrink_lruvec+0x418/0x5cc shrink_zone+0x88/0x198 try_to_free_pages+0x51c/0x588 __alloc_pages_nodemask+0x648/0xa88 __get_free_pages+0x34/0x7c alloc_buffer+0xa4/0x144 __bufio_new+0x84/0x278 dm_bufio_prefetch+0x9c/0x154 verity_prefetch_io+0xe8/0x10c process_one_work+0x240/0x424 worker_thread+0x2fc/0x424 kthread+0x10c/0x114 ...and that looks to be the one holding the mutex. The problem has been reproduced on fairly easily: 0. Be running Chrome OS w/ verity enabled on the root filesystem 1. Pick test patch: http://crosreview.com/412360 2. Install launchBalloons.sh and balloon.arm from http://crbug.com/468342 ...that's just a memory stress test app. 3. On a 4GB rk3399 machine, run nice ./launchBalloons.sh 4 900 100000 ...that tries to eat 4 * 900 MB of memory and keep accessing. 4. Login to the Chrome web browser and restore many tabs With that, I've seen printouts like: DOUG: long bufio 90758 ms ...and stack trace always show's we're in dm_bufio_prefetch(). The problem is that we try to allocate memory with GFP_NOIO while we're holding the dm_bufio lock. Instead we should be using GFP_NOWAIT. Using GFP_NOIO can cause us to sleep while holding the lock and that causes the above problems. The current behavior explained by David Rientjes: It will still try reclaim initially because __GFP_WAIT (or __GFP_KSWAPD_RECLAIM) is set by GFP_NOIO. This is the cause of contention on dm_bufio_lock() that the thread holds. You want to pass GFP_NOWAIT instead of GFP_NOIO to alloc_buffer() when holding a mutex that can be contended by a concurrent slab shrinker (if count_objects didn't use a trylock, this pattern would trivially deadlock). This change significantly increases responsiveness of the system while in this state. It makes a real difference because it unblocks kswapd. In the bug report analyzed, kswapd was hung: kswapd0 D ffffffc000204fd8 0 72 2 0x00000000 Call trace: [<ffffffc000204fd8>] __switch_to+0x9c/0xa8 [<ffffffc00090b794>] __schedule+0x440/0x6d8 [<ffffffc00090bac0>] schedule+0x94/0xb4 [<ffffffc00090be44>] schedule_preempt_disabled+0x28/0x44 [<ffffffc00090d900>] __mutex_lock_slowpath+0x120/0x1ac [<ffffffc00090d9d8>] mutex_lock+0x4c/0x68 [<ffffffc000708e7c>] dm_bufio_shrink_count+0x38/0x78 [<ffffffc00030b268>] shrink_slab.part.54.constprop.65+0x100/0x464 [<ffffffc00030dbd8>] shrink_zone+0xa8/0x198 [<ffffffc00030e578>] balance_pgdat+0x328/0x508 [<ffffffc00030eb7c>] kswapd+0x424/0x51c [<ffffffc00023f06c>] kthread+0x10c/0x114 [<ffffffc000203dd0>] ret_from_fork+0x10/0x40 By unblocking kswapd memory pressure should be reduced. Suggested-by: David Rientjes <rientjes(a)google.com> Reviewed-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Douglas Anderson <dianders(a)chromium.org> Signed-off-by: Mike Snitzer <snitzer(a)redhat.com> diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 125aedc3875f..b5d3428d109e 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -827,7 +827,8 @@ static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client * dm-bufio is resistant to allocation failures (it just keeps * one buffer reserved in cases all the allocations fail). * So set flags to not try too hard: - * GFP_NOIO: don't recurse into the I/O layer + * GFP_NOWAIT: don't wait; if we need to sleep we'll release our + * mutex and wait ourselves. * __GFP_NORETRY: don't retry and rather return failure * __GFP_NOMEMALLOC: don't use emergency reserves * __GFP_NOWARN: don't print a warning in case of failure @@ -837,7 +838,7 @@ static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client */ while (1) { if (dm_bufio_cache_size_latch != 1) { - b = alloc_buffer(c, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + b = alloc_buffer(c, GFP_NOWAIT | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); if (b) return b; }

7 years

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror