From 52a118d084675f1171c8fbede992f7cac23c9267 Mon Sep 17 00:00:00 2001 From: Vinayak Menon Date: Thu, 17 May 2018 14:34:41 +0530 Subject: [PATCH 0001/1128] selinux: stop flooding the log buffer The avc allocations are marked with GFP_NOWAIT and thus considered to be non-fatal allocations. This also makes these allocations easy to fail thus filling the log buffer with page allocation failure messages. There are no known cases of these messages being of any importance for debugging. Disable them. Change-Id: I3517a134ad0e8deb307f0d140f4b16cb303a9f7f Signed-off-by: Vinayak Menon --- security/selinux/avc.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 2380b8d72cec..491ede7d156e 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -346,26 +346,27 @@ static struct avc_xperms_decision_node struct avc_xperms_decision_node *xpd_node; struct extended_perms_decision *xpd; - xpd_node = kmem_cache_zalloc(avc_xperms_decision_cachep, GFP_NOWAIT); + xpd_node = kmem_cache_zalloc(avc_xperms_decision_cachep, + GFP_NOWAIT | __GFP_NOWARN); if (!xpd_node) return NULL; xpd = &xpd_node->xpd; if (which & XPERMS_ALLOWED) { xpd->allowed = kmem_cache_zalloc(avc_xperms_data_cachep, - GFP_NOWAIT); + GFP_NOWAIT | __GFP_NOWARN); if (!xpd->allowed) goto error; } if (which & XPERMS_AUDITALLOW) { xpd->auditallow = kmem_cache_zalloc(avc_xperms_data_cachep, - GFP_NOWAIT); + GFP_NOWAIT | __GFP_NOWARN); if (!xpd->auditallow) goto error; } if (which & XPERMS_DONTAUDIT) { xpd->dontaudit = kmem_cache_zalloc(avc_xperms_data_cachep, - GFP_NOWAIT); + GFP_NOWAIT | __GFP_NOWARN); if (!xpd->dontaudit) goto error; } @@ -393,7 +394,8 @@ static struct avc_xperms_node *avc_xperms_alloc(void) { struct avc_xperms_node *xp_node; - xp_node = kmem_cache_zalloc(avc_xperms_cachep, GFP_NOWAIT); + xp_node = kmem_cache_zalloc(avc_xperms_cachep, + GFP_NOWAIT | __GFP_NOWARN); if (!xp_node) return xp_node; INIT_LIST_HEAD(&xp_node->xpd_head); @@ -546,7 +548,7 @@ static struct avc_node *avc_alloc_node(void) { struct avc_node *node; - node = kmem_cache_zalloc(avc_node_cachep, GFP_NOWAIT); + node = kmem_cache_zalloc(avc_node_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!node) goto out; -- GitLab From 4621bd773bd109e71736b1a472559f3f19b89a04 Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Tue, 1 Jan 2019 21:33:11 +0800 Subject: [PATCH 0002/1128] f2fs: change error code to -ENOMEM from -EINVAL The error case of failing allocating memory should return -ENOMEM. Signed-off-by: Chengguang Xu Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 76a791f841ff..3c4dcf381c3b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -269,7 +269,7 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype, if (!qname) { f2fs_msg(sb, KERN_ERR, "Not enough memory for storing quotafile name"); - return -EINVAL; + return -ENOMEM; } if (F2FS_OPTION(sbi).s_qf_names[qtype]) { if (strcmp(F2FS_OPTION(sbi).s_qf_names[qtype], qname) == 0) -- GitLab From 52b24f802a8159faa1c284562f0e26d3e1d264c8 Mon Sep 17 00:00:00 2001 From: Zhikang Zhang Date: Thu, 3 Jan 2019 20:06:38 +0800 Subject: [PATCH 0003/1128] f2fs: fix compile warnings: 'struct *' declared inside parameter list We meet these compile warnings below, which caused by missing declare structs: struct f2fs_io_info, struct extent, struct f2fs_sb_info. warning: 'struct f2fs_io_info' declared inside parameter list warning: 'struct extent_info' declared inside parameter list warning: 'struct f2fs_sb_info' declared inside parameter list Signed-off-by: Zhikang Zhang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 06c87f9f720c..c842bc70c68c 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -150,6 +150,9 @@ TRACE_DEFINE_ENUM(CP_TRIMMED); { CP_SPEC_LOG_NUM, "log type is 2" }, \ { CP_RECOVER_DIR, "dir needs recovery" }) +struct f2fs_sb_info; +struct f2fs_io_info; +struct extent_info; struct victim_sel_policy; struct f2fs_map_blocks; -- GitLab From 63385cccb48b597867afe022a1ed29179d65ab58 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 4 Jan 2019 01:38:29 +0000 Subject: [PATCH 0004/1128] f2fs: remove set but not used variable 'err' Fixes gcc '-Wunused-but-set-variable' warning: fs/f2fs/data.c: In function 'f2fs_dio_submit_bio': fs/f2fs/data.c:2585:6: warning: variable 'err' set but not used [-Wunused-but-set-variable] Signed-off-by: YueHaibing Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index f09187c3d962..c0ee1c06e70e 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2581,14 +2581,11 @@ static void f2fs_dio_submit_bio(struct bio *bio, struct inode *inode, { struct f2fs_private_dio *dio; bool write = (bio_op(bio) == REQ_OP_WRITE); - int err; dio = f2fs_kzalloc(F2FS_I_SB(inode), sizeof(struct f2fs_private_dio), GFP_NOFS); - if (!dio) { - err = -ENOMEM; + if (!dio) goto out; - } dio->inode = inode; dio->orig_end_io = bio->bi_end_io; -- GitLab From 43d60e5b8680e8969c7f168c8604870177542280 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 4 Jan 2019 17:39:53 +0800 Subject: [PATCH 0005/1128] f2fs: check inject_rate validity during configuring Type of inject_rate is unsigned int, let's check new value's validity during configuring. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/sysfs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 948c1a211341..b427122cb71a 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -222,6 +222,8 @@ static ssize_t __sbi_store(struct f2fs_attr *a, #ifdef CONFIG_F2FS_FAULT_INJECTION if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX)) return -EINVAL; + if (a->struct_type == FAULT_INFO_RATE && t >= UINT_MAX) + return -EINVAL; #endif if (a->struct_type == RESERVED_BLOCKS) { spin_lock(&sbi->stat_lock); -- GitLab From 9df86e4e8b9bd2392d97a035b9ed8c79e700cf6f Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 3 Jan 2019 17:19:08 -0800 Subject: [PATCH 0006/1128] f2fs: export FS_NOCOW_FL flag to user This exports pin_file status to user. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 3 ++- fs/f2fs/file.c | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index ecaa01aaf20e..8cd739b51436 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2302,11 +2302,12 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) #define F2FS_EXTENTS_FL 0x00080000 /* Inode uses extents */ #define F2FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */ #define F2FS_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ +#define F2FS_NOCOW_FL 0x00800000 /* Do not cow file */ #define F2FS_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ #define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define F2FS_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define F2FS_FL_USER_VISIBLE 0x304BDFFF /* User visible flags */ +#define F2FS_FL_USER_VISIBLE 0x30CBDFFF /* User visible flags */ #define F2FS_FL_USER_MODIFIABLE 0x204BC0FF /* User modifiable flags */ /* Flags we can manipulate with through F2FS_IOC_FSSETXATTR */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index dfd26475c582..2a06e0f19a9a 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1651,6 +1651,8 @@ static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) flags |= F2FS_ENCRYPT_FL; if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) flags |= F2FS_INLINE_DATA_FL; + if (is_inode_flag_set(inode, FI_PIN_FILE)) + flags |= F2FS_NOCOW_FL; flags &= F2FS_FL_USER_VISIBLE; -- GitLab From 537bb5c403d38f8947c6b1e08340994ba446d56a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 4 Jan 2019 14:26:18 +0100 Subject: [PATCH 0007/1128] f2fs: no need to check return value of debugfs_create functions When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Cc: Jaegeuk Kim Cc: Chao Yu Cc: linux-f2fs-devel@lists.sourceforge.net Signed-off-by: Greg Kroah-Hartman Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/debug.c | 20 +++----------------- fs/f2fs/f2fs.h | 4 ++-- fs/f2fs/super.c | 5 +---- 3 files changed, 6 insertions(+), 23 deletions(-) diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index f05b37ef7182..d00ba9b711a4 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -522,30 +522,16 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi) kvfree(si); } -int __init f2fs_create_root_stats(void) +void __init f2fs_create_root_stats(void) { - struct dentry *file; - f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL); - if (!f2fs_debugfs_root) - return -ENOMEM; - file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, - NULL, &stat_fops); - if (!file) { - debugfs_remove(f2fs_debugfs_root); - f2fs_debugfs_root = NULL; - return -ENOMEM; - } - - return 0; + debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, NULL, + &stat_fops); } void f2fs_destroy_root_stats(void) { - if (!f2fs_debugfs_root) - return; - debugfs_remove_recursive(f2fs_debugfs_root); f2fs_debugfs_root = NULL; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 8cd739b51436..fc6438a40a93 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3330,7 +3330,7 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) int f2fs_build_stats(struct f2fs_sb_info *sbi); void f2fs_destroy_stats(struct f2fs_sb_info *sbi); -int __init f2fs_create_root_stats(void); +void __init f2fs_create_root_stats(void); void f2fs_destroy_root_stats(void); #else #define stat_inc_cp_count(si) do { } while (0) @@ -3368,7 +3368,7 @@ void f2fs_destroy_root_stats(void); static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } -static inline int __init f2fs_create_root_stats(void) { return 0; } +static inline void __init f2fs_create_root_stats(void) { } static inline void f2fs_destroy_root_stats(void) { } #endif diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3c4dcf381c3b..141cac14fc67 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3549,9 +3549,7 @@ static int __init init_f2fs_fs(void) err = register_filesystem(&f2fs_fs_type); if (err) goto free_shrinker; - err = f2fs_create_root_stats(); - if (err) - goto free_filesystem; + f2fs_create_root_stats(); err = f2fs_init_post_read_processing(); if (err) goto free_root_stats; @@ -3559,7 +3557,6 @@ static int __init init_f2fs_fs(void) free_root_stats: f2fs_destroy_root_stats(); -free_filesystem: unregister_filesystem(&f2fs_fs_type); free_shrinker: unregister_shrinker(&f2fs_shrinker_info); -- GitLab From 8faba5de867b358d5a9136e732df7803945e418d Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 8 Jan 2019 10:21:24 +0800 Subject: [PATCH 0008/1128] f2fs: fix to trigger fsck if dirent.name_len is zero While traversing dirents in f2fs_fill_dentries(), if bitmap is valid, filename length should not be zero, otherwise, directory structure consistency could be corrupted, in this case, let's print related info and set SBI_NEED_FSCK to trigger fsck for repairing. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/dir.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 7ff9e993008e..8c1457a7e187 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -800,6 +800,10 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, if (de->name_len == 0) { bit_pos++; ctx->pos = start_pos + bit_pos; + printk_ratelimited( + "%s, invalid namelen(0), ino:%u, run fsck to fix.", + KERN_WARNING, le32_to_cpu(de->ino)); + set_sbi_flag(sbi, SBI_NEED_FSCK); continue; } -- GitLab From 4951bf45e057b891d79a6438e5302b2c9f685673 Mon Sep 17 00:00:00 2001 From: Sheng Yong Date: Mon, 7 Jan 2019 15:02:34 +0800 Subject: [PATCH 0009/1128] f2fs: check if file namelen exceeds max value Dentry bitmap is not enough to detect incorrect dentries. So this patch also checks the namelen value of a dentry. Signed-off-by: Gong Chen Signed-off-by: Sheng Yong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/dir.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 8c1457a7e187..0e0e0880c4de 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -814,7 +814,8 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, /* check memory boundary before moving forward */ bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); - if (unlikely(bit_pos > d->max)) { + if (unlikely(bit_pos > d->max || + le16_to_cpu(de->name_len) > F2FS_NAME_LEN)) { f2fs_msg(sbi->sb, KERN_WARNING, "%s: corrupted namelen=%d, run fsck to fix.", __func__, le16_to_cpu(de->name_len)); -- GitLab From ddb9a293f5e4217e373adfc11e98dfe004a6fced Mon Sep 17 00:00:00 2001 From: Sheng Yong Date: Mon, 14 Jan 2019 22:05:14 +0800 Subject: [PATCH 0010/1128] f2fs: add brackets for macros Signed-off-by: Sheng Yong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index fc6438a40a93..c62b905b0626 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -255,7 +255,7 @@ struct discard_entry { /* max discard pend list number */ #define MAX_PLIST_NUM 512 #define plist_idx(blk_num) ((blk_num) >= MAX_PLIST_NUM ? \ - (MAX_PLIST_NUM - 1) : (blk_num - 1)) + (MAX_PLIST_NUM - 1) : ((blk_num) - 1)) enum { D_PREP, /* initial */ @@ -2764,9 +2764,9 @@ static inline int get_inline_xattr_addrs(struct inode *inode) #define F2FS_OLD_ATTRIBUTE_SIZE (offsetof(struct f2fs_inode, i_addr)) #define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field) \ - ((offsetof(typeof(*f2fs_inode), field) + \ + ((offsetof(typeof(*(f2fs_inode)), field) + \ sizeof((f2fs_inode)->field)) \ - <= (F2FS_OLD_ATTRIBUTE_SIZE + extra_isize)) \ + <= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize))) \ static inline void f2fs_reset_iostat(struct f2fs_sb_info *sbi) { @@ -2795,8 +2795,8 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, #define __is_large_section(sbi) ((sbi)->segs_per_sec > 1) -#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO(fio->type) == META && \ - (!is_read_io(fio->op) || fio->is_meta)) +#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META && \ + (!is_read_io((fio)->op) || (fio)->is_meta)) bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); -- GitLab From a6d7095630e77f6e7485589a20ade0b59b39aed2 Mon Sep 17 00:00:00 2001 From: Sheng Yong Date: Tue, 15 Jan 2019 20:02:15 +0000 Subject: [PATCH 0011/1128] f2fs: UBSAN: set boolean value iostat_enable correctly When setting /sys/fs/f2fs//iostat_enable with non-bool value, UBSAN reports the following warning. [ 7562.295484] ================================================================================ [ 7562.296531] UBSAN: Undefined behaviour in fs/f2fs/f2fs.h:2776:10 [ 7562.297651] load of value 64 is not a valid value for type '_Bool' [ 7562.298642] CPU: 1 PID: 7487 Comm: dd Not tainted 4.20.0-rc4+ #79 [ 7562.298653] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 7562.298662] Call Trace: [ 7562.298760] dump_stack+0x46/0x5b [ 7562.298811] ubsan_epilogue+0x9/0x40 [ 7562.298830] __ubsan_handle_load_invalid_value+0x72/0x90 [ 7562.298863] f2fs_file_write_iter+0x29f/0x3f0 [ 7562.298905] __vfs_write+0x115/0x160 [ 7562.298922] vfs_write+0xa7/0x190 [ 7562.298934] ksys_write+0x50/0xc0 [ 7562.298973] do_syscall_64+0x4a/0xe0 [ 7562.298992] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 7562.299001] RIP: 0033:0x7fa45ec19c00 [ 7562.299004] Code: 73 01 c3 48 8b 0d 88 92 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d dd eb 2c 00 00 75 10 b8 01 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ce 8f 01 00 48 89 04 24 [ 7562.299044] RSP: 002b:00007ffca52b49e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 7562.299052] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fa45ec19c00 [ 7562.299059] RDX: 0000000000000400 RSI: 000000000093f000 RDI: 0000000000000001 [ 7562.299065] RBP: 000000000093f000 R08: 0000000000000004 R09: 0000000000000000 [ 7562.299071] R10: 00007ffca52b47b0 R11: 0000000000000246 R12: 0000000000000400 [ 7562.299077] R13: 000000000093f000 R14: 000000000093f400 R15: 0000000000000000 [ 7562.299091] ================================================================================ So, if iostat_enable is enabled, set its value as true. Signed-off-by: Sheng Yong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/sysfs.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index b427122cb71a..a609c0abbdd0 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -280,10 +280,16 @@ static ssize_t __sbi_store(struct f2fs_attr *a, return count; } - *ui = t; - if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0) - f2fs_reset_iostat(sbi); + if (!strcmp(a->attr.name, "iostat_enable")) { + sbi->iostat_enable = !!t; + if (!sbi->iostat_enable) + f2fs_reset_iostat(sbi); + return count; + } + + *ui = (unsigned int)t; + return count; } -- GitLab From 1c3c592eaa5344727787b76322fc9500d696fdaf Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 16 Jan 2019 09:51:28 +0800 Subject: [PATCH 0012/1128] f2fs: fix to initialize variable to avoid UBSAN/smatch warning As Dan Carpenter as below: The patch df634f444ee9: "f2fs: use rb_*_cached friends" from Oct 4, 2018, leads to the following static checker warning: fs/f2fs/extent_cache.c:606 f2fs_update_extent_tree_range() error: uninitialized symbol 'leftmost'. And also Eric Biggers, and Kyungtae Kim reported, there is an UBSAN warning described as below: We report a bug in linux-4.20.2: "UBSAN: Undefined behaviour in fs/f2fs/extent_cache.c" kernel config: https://kt0755.github.io/etc/config_v4.20_stable repro: https://kt0755.github.io/etc/repro.4a3e7.c (f2fs is mounted on /mnt/f2fs/) This arose in f2fs_update_extent_tree_range (fs/f2fs/extent_cache.c:605). It seems that, for some reason, its last argument became "24" although that was supposed to be bool type. ========================================= UBSAN: Undefined behaviour in fs/f2fs/extent_cache.c:605:4 load of value 24 is not a valid value for type '_Bool' CPU: 0 PID: 6774 Comm: syz-executor5 Not tainted 4.20.2 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xb1/0x118 lib/dump_stack.c:113 ubsan_epilogue+0x12/0x94 lib/ubsan.c:159 __ubsan_handle_load_invalid_value+0x17a/0x1be lib/ubsan.c:457 f2fs_update_extent_tree_range+0x1d4a/0x1d50 fs/f2fs/extent_cache.c:605 f2fs_update_extent_cache+0x2b6/0x350 fs/f2fs/extent_cache.c:804 f2fs_update_data_blkaddr+0x61/0x70 fs/f2fs/data.c:656 f2fs_outplace_write_data+0x1d6/0x4b0 fs/f2fs/segment.c:3140 f2fs_convert_inline_page+0x86d/0x2060 fs/f2fs/inline.c:163 f2fs_convert_inline_inode+0x6b5/0xad0 fs/f2fs/inline.c:208 f2fs_preallocate_blocks+0x78b/0xb00 fs/f2fs/data.c:982 f2fs_file_write_iter+0x31b/0xf40 fs/f2fs/file.c:3062 call_write_iter include/linux/fs.h:1857 [inline] new_sync_write fs/read_write.c:474 [inline] __vfs_write+0x538/0x6e0 fs/read_write.c:487 vfs_write+0x1b3/0x520 fs/read_write.c:549 ksys_write+0xde/0x1c0 fs/read_write.c:598 __do_sys_write fs/read_write.c:610 [inline] __se_sys_write fs/read_write.c:607 [inline] __x64_sys_write+0x7e/0xc0 fs/read_write.c:607 do_syscall_64+0xbe/0x4f0 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4497b9 Code: e8 8c 9f 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 9b 6b fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f1ea15edc68 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007f1ea15ee6cc RCX: 00000000004497b9 RDX: 0000000000001000 RSI: 0000000020000140 RDI: 0000000000000013 RBP: 000000000071bea0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 000000000000bb50 R14: 00000000006f4bf0 R15: 00007f1ea15ee700 ========================================= As I checked, this uninitialized variable won't cause extent cache corruption, but in order to avoid such kind of warning of both UBSAN and smatch, fix to initialize related variable. Reported-by: Dan Carpenter Reported-by: Eric Biggers Reported-by: Kyungtae Kim Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/extent_cache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 1cb0fcc67d2d..caf77fe8ac07 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -506,7 +506,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode, unsigned int end = fofs + len; unsigned int pos = (unsigned int)fofs; bool updated = false; - bool leftmost; + bool leftmost = false; if (!et) return; -- GitLab From d09408e2f47cad1970e3e6d61808209719dc67a8 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 10 Jan 2019 16:40:12 +0800 Subject: [PATCH 0013/1128] f2fs: fix to set sbi dirty correctly In order to record direct IO count, we add two additional type in enum count_type: F2FS_DIO_{WRITE,READ}, but those IO won't dirty filesystem metadata, so we don't need to set filesystem dirty in inc_page_count(), fix it. Fixes: 02b16d0a34a1 ("f2fs: add to account direct IO") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index c62b905b0626..b822ac3cb265 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1800,13 +1800,12 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) { atomic_inc(&sbi->nr_pages[count_type]); - if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES || - count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA || - count_type == F2FS_RD_DATA || count_type == F2FS_RD_NODE || - count_type == F2FS_RD_META) - return; - - set_sbi_flag(sbi, SBI_IS_DIRTY); + if (count_type == F2FS_DIRTY_DENTS || + count_type == F2FS_DIRTY_NODES || + count_type == F2FS_DIRTY_META || + count_type == F2FS_DIRTY_QDATA || + count_type == F2FS_DIRTY_IMETA) + set_sbi_flag(sbi, SBI_IS_DIRTY); } static inline void inode_inc_dirty_pages(struct inode *inode) -- GitLab From a0172a986cb1ebcf496cae7cbf9a25ed3c5eb439 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 14 Jan 2019 10:42:11 -0800 Subject: [PATCH 0014/1128] f2fs: run discard jobs when put_super When we umount f2fs, we need to avoid long delay due to discard commands, which is actually taking tens of seconds, if storage is very slow on UNMAP. So, this patch introduces timeout-based work on it. By default, let me give 5 seconds for discard. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- Documentation/ABI/testing/sysfs-fs-f2fs | 7 +++++++ fs/f2fs/f2fs.h | 5 ++++- fs/f2fs/segment.c | 11 ++++++++++- fs/f2fs/super.c | 4 +++- fs/f2fs/sysfs.c | 3 +++ 5 files changed, 27 insertions(+), 3 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index 381ab9fed3e6..a6fe7368b26c 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -86,6 +86,13 @@ Description: The unit size is one block, now only support configuring in range of [1, 512]. +What: /sys/fs/f2fs//umount_discard_timeout +Date: January 2019 +Contact: "Jaegeuk Kim" +Description: + Set timeout to issue discard commands during umount. + Default: 5 secs + What: /sys/fs/f2fs//max_victim_search Date: January 2014 Contact: "Jaegeuk Kim" diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index b822ac3cb265..417585b0a494 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -192,6 +192,7 @@ enum { #define DEF_CP_INTERVAL 60 /* 60 secs */ #define DEF_IDLE_INTERVAL 5 /* 5 secs */ #define DEF_DISABLE_INTERVAL 5 /* 5 secs */ +#define DEF_UMOUNT_DISCARD_TIMEOUT 5 /* 5 secs */ struct cp_control { int reason; @@ -311,6 +312,7 @@ struct discard_policy { bool sync; /* submit discard with REQ_SYNC flag */ bool ordered; /* issue discard by lba order */ unsigned int granularity; /* discard granularity */ + int timeout; /* discard timeout for put_super */ }; struct discard_cmd_control { @@ -1111,6 +1113,7 @@ enum { DISCARD_TIME, GC_TIME, DISABLE_TIME, + UMOUNT_DISCARD_TIMEOUT, MAX_TIME, }; @@ -3007,7 +3010,7 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi); void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi); -bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi); +bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi); void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 9b79056d705d..5b2b9be6f28d 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1037,6 +1037,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST; dpolicy->io_aware_gran = MAX_PLIST_NUM; + dpolicy->timeout = 0; if (discard_type == DPOLICY_BG) { dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; @@ -1424,7 +1425,14 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, int i, issued = 0; bool io_interrupted = false; + if (dpolicy->timeout != 0) + f2fs_update_time(sbi, dpolicy->timeout); + for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { + if (dpolicy->timeout != 0 && + f2fs_time_over(sbi, dpolicy->timeout)) + break; + if (i + 1 < dpolicy->granularity) break; @@ -1611,7 +1619,7 @@ void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi) } /* This comes from f2fs_put_super */ -bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi) +bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_policy dpolicy; @@ -1619,6 +1627,7 @@ bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi) __init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT, dcc->discard_granularity); + dpolicy.timeout = UMOUNT_DISCARD_TIMEOUT; __issue_discard_cmd(sbi, &dpolicy); dropped = __drop_discard_cmd(sbi); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 141cac14fc67..95a3445f97ca 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1048,7 +1048,7 @@ static void f2fs_put_super(struct super_block *sb) } /* be sure to wait for any on-going discard commands */ - dropped = f2fs_wait_discard_bios(sbi); + dropped = f2fs_issue_discard_timeout(sbi); if ((f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) && !sbi->discard_blks && !dropped) { @@ -2706,6 +2706,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->interval_time[DISCARD_TIME] = DEF_IDLE_INTERVAL; sbi->interval_time[GC_TIME] = DEF_IDLE_INTERVAL; sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_INTERVAL; + sbi->interval_time[UMOUNT_DISCARD_TIMEOUT] = + DEF_UMOUNT_DISCARD_TIMEOUT; clear_sbi_flag(sbi, SBI_NEED_FSCK); for (i = 0; i < NR_COUNT_TYPE; i++) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index a609c0abbdd0..d7b47662a0aa 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -426,6 +426,8 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, discard_idle_interval, interval_time[DISCARD_TIME]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle_interval, interval_time[GC_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, + umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold); @@ -483,6 +485,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(idle_interval), ATTR_LIST(discard_idle_interval), ATTR_LIST(gc_idle_interval), + ATTR_LIST(umount_discard_timeout), ATTR_LIST(iostat_enable), ATTR_LIST(readdir_ra), ATTR_LIST(gc_pin_file_thresh), -- GitLab From 26fe3e8cc3a23131a5165ac571166d6336b42f78 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 24 Jan 2019 17:48:38 -0800 Subject: [PATCH 0015/1128] f2fs: add quick mode of checkpoint=disable for QA This mode returns mount() quickly with EAGAIN. We can trigger this by shutdown(F2FS_GOING_DOWN_NEED_FSCK). Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 5 +++++ fs/f2fs/f2fs.h | 2 ++ fs/f2fs/file.c | 6 +++--- fs/f2fs/segment.c | 3 +++ fs/f2fs/super.c | 5 +++++ include/linux/f2fs_fs.h | 1 + 6 files changed, 19 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index d27d3c4458e4..228d0e685b8d 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1259,6 +1259,11 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) else __clear_ckpt_flags(ckpt, CP_DISABLED_FLAG); + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK)) + __set_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG); + else + __clear_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG); + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); else diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 417585b0a494..f2bfe067aef7 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -192,6 +192,7 @@ enum { #define DEF_CP_INTERVAL 60 /* 60 secs */ #define DEF_IDLE_INTERVAL 5 /* 5 secs */ #define DEF_DISABLE_INTERVAL 5 /* 5 secs */ +#define DEF_DISABLE_QUICK_INTERVAL 1 /* 1 secs */ #define DEF_UMOUNT_DISCARD_TIMEOUT 5 /* 5 secs */ struct cp_control { @@ -1102,6 +1103,7 @@ enum { SBI_IS_SHUTDOWN, /* shutdown by ioctl */ SBI_IS_RECOVERED, /* recovered orphan/data */ SBI_CP_DISABLED, /* CP was disabled last mount */ + SBI_CP_DISABLED_QUICK, /* CP was disabled quickly */ SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */ SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */ SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 2a06e0f19a9a..149710854a3a 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1972,11 +1972,11 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) break; case F2FS_GOING_DOWN_NEED_FSCK: set_sbi_flag(sbi, SBI_NEED_FSCK); + set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); + set_sbi_flag(sbi, SBI_IS_DIRTY); /* do checkpoint only */ ret = f2fs_sync_fs(sb, 1); - if (ret) - goto out; - break; + goto out; default: ret = -EINVAL; goto out; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 5b2b9be6f28d..342b720fb4db 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -868,6 +868,9 @@ int f2fs_disable_cp_again(struct f2fs_sb_info *sbi) if (holes[DATA] > ovp || holes[NODE] > ovp) return -EAGAIN; + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) && + dirty_segments(sbi) > overprovision_segments(sbi)) + return -EAGAIN; return 0; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 95a3445f97ca..f28baa17e98c 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3205,6 +3205,10 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_QUOTA_NEED_FSCK_FLAG)) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_DISABLED_QUICK_FLAG)) { + set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); + sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_QUICK_INTERVAL; + } /* Initialize device list */ err = f2fs_scan_devices(sbi); @@ -3391,6 +3395,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) cur_cp_version(F2FS_CKPT(sbi))); f2fs_update_time(sbi, CP_TIME); f2fs_update_time(sbi, REQ_TIME); + clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); return 0; free_meta: diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index d7711048ef93..d6befe1f9dc7 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -116,6 +116,7 @@ struct f2fs_super_block { /* * For checkpoint */ +#define CP_DISABLED_QUICK_FLAG 0x00002000 #define CP_DISABLED_FLAG 0x00001000 #define CP_QUOTA_NEED_FSCK_FLAG 0x00000800 #define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 -- GitLab From 78a402a25b050119fe0363bff075c3adb0e8a037 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 25 Jan 2019 09:12:13 -0800 Subject: [PATCH 0016/1128] f2fs: try to keep CP_TRIMMED_FLAG after successful umount If every discard were issued successfully, we can avoid further discard. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/segment.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 342b720fb4db..fdd8cd21522f 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1063,6 +1063,8 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, } else if (discard_type == DPOLICY_UMOUNT) { dpolicy->max_requests = UINT_MAX; dpolicy->io_aware = false; + /* we need to issue all to keep CP_TRIMMED_FLAG */ + dpolicy->granularity = 1; } } -- GitLab From 4b7eff5879635a0a52e4bf9f8f916d76fe9b20f0 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 25 Jan 2019 10:26:39 -0800 Subject: [PATCH 0017/1128] f2fs: don't wake up too frequently, if there is lots of IOs Otherwise, it wakes up discard thread which will sleep again by busy IOs in a loop. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/segment.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index a77f76f528b6..5c7ed0442d6e 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -865,7 +865,7 @@ static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force) } } mutex_unlock(&dcc->cmd_lock); - if (!wakeup) + if (!wakeup || !is_idle(sbi, DISCARD_TIME)) return; wake_up: dcc->discard_wake = 1; -- GitLab From d37a8cdf6b7bd626830f8fdc0562e4c12eaef11e Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 25 Jan 2019 12:05:25 -0800 Subject: [PATCH 0018/1128] f2fs: avoid null pointer exception in dcc_info If dcc_info is not set yet, we can get null pointer panic. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index f2bfe067aef7..1fa0013b8669 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2162,10 +2162,17 @@ static inline bool is_idle(struct f2fs_sb_info *sbi, int type) get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) || get_pages(sbi, F2FS_WB_CP_DATA) || get_pages(sbi, F2FS_DIO_READ) || - get_pages(sbi, F2FS_DIO_WRITE) || - atomic_read(&SM_I(sbi)->dcc_info->queued_discard) || - atomic_read(&SM_I(sbi)->fcc_info->queued_flush)) + get_pages(sbi, F2FS_DIO_WRITE)) return false; + + if (SM_I(sbi) && SM_I(sbi)->dcc_info && + atomic_read(&SM_I(sbi)->dcc_info->queued_discard)) + return false; + + if (SM_I(sbi) && SM_I(sbi)->fcc_info && + atomic_read(&SM_I(sbi)->fcc_info->queued_flush)) + return false; + return f2fs_time_over(sbi, type); } -- GitLab From b78c5986c2d91da1313362861e84adcb8eb31bc8 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Sun, 27 Jan 2019 17:59:53 -0800 Subject: [PATCH 0019/1128] f2fs: flush quota blocks after turnning it off After quota_off, we'll get some dirty blocks. If put_super don't have a chance to flush them by checkpoint, it causes NULL pointer exception in end_io after iput(node_inode). (e.g., by checkpoint=disable) Signed-off-by: Jaegeuk Kim --- fs/f2fs/super.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index f28baa17e98c..f18fab590116 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2026,6 +2026,12 @@ void f2fs_quota_off_umount(struct super_block *sb) set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); } } + /* + * In case of checkpoint=disable, we must flush quota blocks. + * This can cause NULL exception for node_inode in end_io, since + * put_super already dropped it. + */ + sync_filesystem(sb); } static void f2fs_truncate_quota_inode_pages(struct super_block *sb) -- GitLab From 90ba3ec9641d50a85ea8567af371ddd84e5c610a Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 22 Jan 2019 14:04:33 -0800 Subject: [PATCH 0020/1128] f2fs: sync filesystem after roll-forward recovery Some works after roll-forward recovery can get an error which will release all the data structures. Let's flush them in order to make it clean. One possible corruption came from: [ 90.400500] list_del corruption. prev->next should be ffffffed1f566208, but was (null) [ 90.675349] Call trace: [ 90.677869] __list_del_entry_valid+0x94/0xb4 [ 90.682351] remove_dirty_inode+0xac/0x114 [ 90.686563] __f2fs_write_data_pages+0x6a8/0x6c8 [ 90.691302] f2fs_write_data_pages+0x40/0x4c [ 90.695695] do_writepages+0x80/0xf0 [ 90.699372] __writeback_single_inode+0xdc/0x4ac [ 90.704113] writeback_sb_inodes+0x280/0x440 [ 90.708501] wb_writeback+0x1b8/0x3d0 [ 90.712267] wb_workfn+0x1a8/0x4d4 [ 90.715765] process_one_work+0x1c0/0x3d4 [ 90.719883] worker_thread+0x224/0x344 [ 90.723739] kthread+0x120/0x130 [ 90.727055] ret_from_fork+0x10/0x18 Reported-by: Sahitya Tummala Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 5 +++-- fs/f2fs/node.c | 4 +++- fs/f2fs/super.c | 44 +++++++++++++++++++++++++++++++++----------- 3 files changed, 39 insertions(+), 14 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 228d0e685b8d..47d720562b3a 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -306,8 +306,9 @@ static int f2fs_write_meta_pages(struct address_space *mapping, goto skip_write; /* collect a number of dirty meta pages and write together */ - if (wbc->for_kupdate || - get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META)) + if (wbc->sync_mode != WB_SYNC_ALL && + get_pages(sbi, F2FS_DIRTY_META) < + nr_pages_to_skip(sbi, META)) goto skip_write; /* if locked failed, cp will flush dirty pages instead */ diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 46fdaebd6185..e39ca804df6f 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1922,7 +1922,9 @@ static int f2fs_write_node_pages(struct address_space *mapping, f2fs_balance_fs_bg(sbi); /* collect a number of dirty node pages and write together */ - if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE)) + if (wbc->sync_mode != WB_SYNC_ALL && + get_pages(sbi, F2FS_DIRTY_NODES) < + nr_pages_to_skip(sbi, NODE)) goto skip_write; if (wbc->sync_mode == WB_SYNC_ALL) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index f18fab590116..445b0c8a56c0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1458,9 +1458,16 @@ static int f2fs_enable_quotas(struct super_block *sb); static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) { + unsigned int s_flags = sbi->sb->s_flags; struct cp_control cpc; - int err; + int err = 0; + int ret; + if (s_flags & SB_RDONLY) { + f2fs_msg(sbi->sb, KERN_ERR, + "checkpoint=disable on readonly fs"); + return -EINVAL; + } sbi->sb->s_flags |= SB_ACTIVE; f2fs_update_time(sbi, DISABLE_TIME); @@ -1468,18 +1475,24 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) while (!f2fs_time_over(sbi, DISABLE_TIME)) { mutex_lock(&sbi->gc_mutex); err = f2fs_gc(sbi, true, false, NULL_SEGNO); - if (err == -ENODATA) + if (err == -ENODATA) { + err = 0; break; + } if (err && err != -EAGAIN) - return err; + break; } - err = sync_filesystem(sbi->sb); - if (err) - return err; + ret = sync_filesystem(sbi->sb); + if (ret || err) { + err = ret ? ret: err; + goto restore_flag; + } - if (f2fs_disable_cp_again(sbi)) - return -EAGAIN; + if (f2fs_disable_cp_again(sbi)) { + err = -EAGAIN; + goto restore_flag; + } mutex_lock(&sbi->gc_mutex); cpc.reason = CP_PAUSE; @@ -1488,7 +1501,9 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) sbi->unusable_block_count = 0; mutex_unlock(&sbi->gc_mutex); - return 0; +restore_flag: + sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + return err; } static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) @@ -3368,7 +3383,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) if (test_opt(sbi, DISABLE_CHECKPOINT)) { err = f2fs_disable_checkpoint(sbi); if (err) - goto free_meta; + goto sync_free_meta; } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) { f2fs_enable_checkpoint(sbi); } @@ -3381,7 +3396,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) /* After POR, we can run background GC thread.*/ err = f2fs_start_gc_thread(sbi); if (err) - goto free_meta; + goto sync_free_meta; } kvfree(options); @@ -3404,6 +3419,11 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); return 0; +sync_free_meta: + /* safe to flush all the data */ + sync_filesystem(sbi->sb); + retry = false; + free_meta: #ifdef CONFIG_QUOTA f2fs_truncate_quota_inode_pages(sb); @@ -3417,6 +3437,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) * falls into an infinite loop in f2fs_sync_meta_pages(). */ truncate_inode_pages_final(META_MAPPING(sbi)); + /* evict some inodes being cached by GC */ + evict_inodes(sb); f2fs_unregister_sysfs(sbi); free_root_inode: dput(sb->s_root); -- GitLab From c34ed1e18ecb74b62e2b57c96ec4a99a4cb71ae8 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Fri, 25 Jan 2019 20:11:39 +0800 Subject: [PATCH 0021/1128] f2fs: use xattr_prefix to wrap up Let's use xattr_prefix instead of open code. No logic changes. Signed-off-by: Gao Xiang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/xattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 18d5ffbc5e8c..fa620d31ea5f 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -538,7 +538,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) if (!handler || (handler->list && !handler->list(dentry))) continue; - prefix = handler->prefix ?: handler->name; + prefix = xattr_prefix(handler); prefix_len = strlen(prefix); size = prefix_len + entry->e_name_len + 1; if (buffer) { -- GitLab From f606c8b390684154bbb19df052b9236a1ba65a76 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 25 Jan 2019 15:35:01 +0800 Subject: [PATCH 0022/1128] f2fs: fix typos in code comments lengh -> length Signed-off-by: Geliang Tang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index d6befe1f9dc7..8d57aaee8166 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -187,7 +187,7 @@ struct f2fs_orphan_block { struct f2fs_extent { __le32 fofs; /* start file offset of the extent */ __le32 blk; /* start block address of the extent */ - __le32 len; /* lengh of the extent */ + __le32 len; /* length of the extent */ } __packed; #define F2FS_NAME_LEN 255 @@ -512,7 +512,7 @@ typedef __le32 f2fs_hash_t; struct f2fs_dir_entry { __le32 hash_code; /* hash code of file name */ __le32 ino; /* inode number */ - __le16 name_len; /* lengh of file name */ + __le16 name_len; /* length of file name */ __u8 file_type; /* file type */ } __packed; -- GitLab From 51f50099a25892f1ed758f137c683c12081f3f4c Mon Sep 17 00:00:00 2001 From: zhengliang Date: Thu, 24 Jan 2019 20:57:03 +0800 Subject: [PATCH 0023/1128] f2fs: fix to data block override node segment by mistake MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The following race could lead to data block override node segment by mistake. Task A | Task B | Task C | Task D ======= | ======== |========== | ========= open file | | | white file | | | submit bio | | | wait io complete | | | | remove file | | ........ | iput_final | | | | sync | | | do checkpoint | | | data segment free | | | | create file1 | | | allocate node segment（if it is the same segment freed by Task C） f2fs_write_end_io | | | So we need to guarantee io complete before truncate inode in f2fs_drop_inode. Signed-off-by: Zheng Liang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/super.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 445b0c8a56c0..b5127a1440d9 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -915,6 +915,10 @@ static int f2fs_drop_inode(struct inode *inode) sb_start_intwrite(inode->i_sb); f2fs_i_size_write(inode, 0); + f2fs_submit_merged_write_cond(F2FS_I_SB(inode), + inode, NULL, 0, DATA); + truncate_inode_pages_final(inode->i_mapping); + if (F2FS_HAS_BLOCKS(inode)) f2fs_truncate(inode); -- GitLab From b62b71523d5e8242078dc10a48c056c2675674af Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 24 Jan 2019 17:18:07 +0800 Subject: [PATCH 0024/1128] f2fs: fix to document inline_xattr_size option We missed to add document for inline_xattr_size mount option in f2fs.txt, add it. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- Documentation/filesystems/f2fs.txt | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index fedbea893ee7..35c777b6e69b 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -126,6 +126,8 @@ disable_ext_identify Disable the extension list configured by mkfs, so f2fs does not aware of cold files such as media files. inline_xattr Enable the inline xattrs feature. noinline_xattr Disable the inline xattrs feature. +inline_xattr_size=%u Support configuring inline xattr size, it depends on + flexible inline xattr feature. inline_data Enable the inline data feature: New created small(<~3.4k) files can be written into inode block. inline_dentry Enable the inline dir feature: data in new created -- GitLab From 73d797ef482b163f327ae1a16d17aaecd77a798f Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Wed, 23 Jan 2019 15:49:44 +0800 Subject: [PATCH 0025/1128] f2fs: jump to label 'free_node_inode' when failing from d_make_root() When sb->s_root is NULL dput() will do nothing, so jump to label 'free_node_inode' instead of lable 'free_root_inode' when failing from d_make_root(). Signed-off-by: Chengguang Xu Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b5127a1440d9..b3b9a74303ba 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3321,7 +3321,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) sb->s_root = d_make_root(root); /* allocate root dentry */ if (!sb->s_root) { err = -ENOMEM; - goto free_root_inode; + goto free_node_inode; } err = f2fs_register_sysfs(sbi); -- GitLab From 0c8c07140e00139e7aa76e2223eebee3a7c24ebd Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 24 Jan 2019 15:18:47 +0800 Subject: [PATCH 0026/1128] f2fs: fix to check inline_xattr_size boundary correctly We use below condition to check inline_xattr_size boundary: if (!F2FS_OPTION(sbi).inline_xattr_size || F2FS_OPTION(sbi).inline_xattr_size >= DEF_ADDRS_PER_INODE - F2FS_TOTAL_EXTRA_ATTR_SIZE - DEF_INLINE_RESERVED_SIZE - DEF_MIN_INLINE_SIZE) There is there problems in that check: - we should allow inline_xattr_size equaling to min size of inline {data,dentry} area. - F2FS_TOTAL_EXTRA_ATTR_SIZE and inline_xattr_size are based on different size unit, previous one is 4 bytes, latter one is 1 bytes. - DEF_MIN_INLINE_SIZE only indicate min size of inline data area, however, we need to consider min size of inline dentry area as well, minimal inline dentry should at least contain two entries: '.' and '..', so that min inline_dentry size is 40 bytes. .bitmap 1 * 1 = 1 .reserved 1 * 1 = 1 .dentry 11 * 2 = 22 .filename 8 * 2 = 16 total 40 Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 1 - fs/f2fs/super.c | 10 +++++----- include/linux/f2fs_fs.h | 13 +++++++------ 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 1fa0013b8669..c696b27d8cc4 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -460,7 +460,6 @@ struct f2fs_flush_device { /* for inline stuff */ #define DEF_INLINE_RESERVED_SIZE 1 -#define DEF_MIN_INLINE_SIZE 1 static inline int get_extra_isize(struct inode *inode); static inline int get_inline_xattr_addrs(struct inode *inode); #define MAX_INLINE_DATA(inode) (sizeof(__le32) * \ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b3b9a74303ba..3166b7266f9e 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -835,11 +835,11 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; } if (!F2FS_OPTION(sbi).inline_xattr_size || - F2FS_OPTION(sbi).inline_xattr_size >= - DEF_ADDRS_PER_INODE - - F2FS_TOTAL_EXTRA_ATTR_SIZE - - DEF_INLINE_RESERVED_SIZE - - DEF_MIN_INLINE_SIZE) { + F2FS_OPTION(sbi).inline_xattr_size > + DEF_ADDRS_PER_INODE - + F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - + DEF_INLINE_RESERVED_SIZE - + MIN_INLINE_DENTRY_SIZE / sizeof(__le32)) { f2fs_msg(sb, KERN_ERR, "inline xattr size is out of range"); return -EINVAL; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 8d57aaee8166..666db8eb71e0 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -490,12 +490,12 @@ typedef __le32 f2fs_hash_t; /* * space utilization of regular dentry and inline dentry (w/o extra reservation) - * regular dentry inline dentry - * bitmap 1 * 27 = 27 1 * 23 = 23 - * reserved 1 * 3 = 3 1 * 7 = 7 - * dentry 11 * 214 = 2354 11 * 182 = 2002 - * filename 8 * 214 = 1712 8 * 182 = 1456 - * total 4096 3488 + * regular dentry inline dentry (def) inline dentry (min) + * bitmap 1 * 27 = 27 1 * 23 = 23 1 * 1 = 1 + * reserved 1 * 3 = 3 1 * 7 = 7 1 * 1 = 1 + * dentry 11 * 214 = 2354 11 * 182 = 2002 11 * 2 = 22 + * filename 8 * 214 = 1712 8 * 182 = 1456 8 * 2 = 16 + * total 4096 3488 40 * * Note: there are more reserved space in inline dentry than in regular * dentry, when converting inline dentry we should handle this carefully. @@ -507,6 +507,7 @@ typedef __le32 f2fs_hash_t; #define SIZE_OF_RESERVED (PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \ F2FS_SLOT_LEN) * \ NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP)) +#define MIN_INLINE_DENTRY_SIZE 40 /* just include '.' and '..' entries */ /* One directory entry slot representing F2FS_SLOT_LEN-sized file name */ struct f2fs_dir_entry { -- GitLab From fb157acbc0ac07452354773bf5c80afe2ef4cad1 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 22 Jan 2019 20:18:06 +0800 Subject: [PATCH 0027/1128] f2fs: fix to avoid deadlock of atomic file operations Thread A Thread B - __fput - f2fs_release_file - drop_inmem_pages - mutex_lock(&fi->inmem_lock) - __revoke_inmem_pages - lock_page(page) - open - f2fs_setattr - truncate_setsize - truncate_inode_pages_range - lock_page(page) - truncate_cleanup_page - f2fs_invalidate_page - drop_inmem_page - mutex_lock(&fi->inmem_lock); We may encounter above ABBA deadlock as reported by Kyungtae Kim: I'm reporting a bug in linux-4.17.19: "INFO: task hung in drop_inmem_page" (no reproducer) I think this might be somehow related to the following: https://groups.google.com/forum/#!searchin/syzkaller-bugs/INFO$3A$20task$20hung$20in$20%7Csort:date/syzkaller-bugs/c6soBTrdaIo/AjAzPeIzCgAJ ========================================= INFO: task syz-executor7:10822 blocked for more than 120 seconds. Not tainted 4.17.19 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. syz-executor7 D27024 10822 6346 0x00000004 Call Trace: context_switch kernel/sched/core.c:2867 [inline] __schedule+0x721/0x1e60 kernel/sched/core.c:3515 schedule+0x88/0x1c0 kernel/sched/core.c:3559 schedule_preempt_disabled+0x18/0x30 kernel/sched/core.c:3617 __mutex_lock_common kernel/locking/mutex.c:833 [inline] __mutex_lock+0x5bd/0x1410 kernel/locking/mutex.c:893 mutex_lock_nested+0x1b/0x20 kernel/locking/mutex.c:908 drop_inmem_page+0xcb/0x810 fs/f2fs/segment.c:327 f2fs_invalidate_page+0x337/0x5e0 fs/f2fs/data.c:2401 do_invalidatepage mm/truncate.c:165 [inline] truncate_cleanup_page+0x261/0x330 mm/truncate.c:187 truncate_inode_pages_range+0x552/0x1610 mm/truncate.c:367 truncate_inode_pages mm/truncate.c:478 [inline] truncate_pagecache+0x6d/0x90 mm/truncate.c:801 truncate_setsize+0x81/0xa0 mm/truncate.c:826 f2fs_setattr+0x44f/0x1270 fs/f2fs/file.c:781 notify_change+0xa62/0xe80 fs/attr.c:313 do_truncate+0x12e/0x1e0 fs/open.c:63 do_last fs/namei.c:2955 [inline] path_openat+0x2042/0x29f0 fs/namei.c:3505 do_filp_open+0x1bd/0x2c0 fs/namei.c:3540 do_sys_open+0x35e/0x4e0 fs/open.c:1101 __do_sys_open fs/open.c:1119 [inline] __se_sys_open fs/open.c:1114 [inline] __x64_sys_open+0x89/0xc0 fs/open.c:1114 do_syscall_64+0xc4/0x4e0 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4497b9 RSP: 002b:00007f734e459c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000002 RAX: ffffffffffffffda RBX: 00007f734e45a6cc RCX: 00000000004497b9 RDX: 0000000000000104 RSI: 00000000000a8280 RDI: 0000000020000080 RBP: 000000000071bea0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 0000000000007230 R14: 00000000006f02d0 R15: 00007f734e45a700 INFO: task syz-executor7:10858 blocked for more than 120 seconds. Not tainted 4.17.19 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. syz-executor7 D28880 10858 6346 0x00000004 Call Trace: context_switch kernel/sched/core.c:2867 [inline] __schedule+0x721/0x1e60 kernel/sched/core.c:3515 schedule+0x88/0x1c0 kernel/sched/core.c:3559 __rwsem_down_write_failed_common kernel/locking/rwsem-xadd.c:565 [inline] rwsem_down_write_failed+0x5e6/0xc90 kernel/locking/rwsem-xadd.c:594 call_rwsem_down_write_failed+0x17/0x30 arch/x86/lib/rwsem.S:117 __down_write arch/x86/include/asm/rwsem.h:142 [inline] down_write+0x58/0xa0 kernel/locking/rwsem.c:72 inode_lock include/linux/fs.h:713 [inline] do_truncate+0x120/0x1e0 fs/open.c:61 do_last fs/namei.c:2955 [inline] path_openat+0x2042/0x29f0 fs/namei.c:3505 do_filp_open+0x1bd/0x2c0 fs/namei.c:3540 do_sys_open+0x35e/0x4e0 fs/open.c:1101 __do_sys_open fs/open.c:1119 [inline] __se_sys_open fs/open.c:1114 [inline] __x64_sys_open+0x89/0xc0 fs/open.c:1114 do_syscall_64+0xc4/0x4e0 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4497b9 RSP: 002b:00007f734e3b4c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000002 RAX: ffffffffffffffda RBX: 00007f734e3b56cc RCX: 00000000004497b9 RDX: 0000000000000104 RSI: 00000000000a8280 RDI: 0000000020000080 RBP: 000000000071c238 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 0000000000007230 R14: 00000000006f02d0 R15: 00007f734e3b5700 INFO: task syz-executor5:10829 blocked for more than 120 seconds. Not tainted 4.17.19 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. syz-executor5 D28760 10829 6308 0x80000002 Call Trace: context_switch kernel/sched/core.c:2867 [inline] __schedule+0x721/0x1e60 kernel/sched/core.c:3515 schedule+0x88/0x1c0 kernel/sched/core.c:3559 io_schedule+0x21/0x80 kernel/sched/core.c:5179 wait_on_page_bit_common mm/filemap.c:1100 [inline] __lock_page+0x2b5/0x390 mm/filemap.c:1273 lock_page include/linux/pagemap.h:483 [inline] __revoke_inmem_pages+0xb35/0x11c0 fs/f2fs/segment.c:231 drop_inmem_pages+0xa3/0x3e0 fs/f2fs/segment.c:306 f2fs_release_file+0x2c7/0x330 fs/f2fs/file.c:1556 __fput+0x2c7/0x780 fs/file_table.c:209 ____fput+0x1a/0x20 fs/file_table.c:243 task_work_run+0x151/0x1d0 kernel/task_work.c:113 exit_task_work include/linux/task_work.h:22 [inline] do_exit+0x8ba/0x30a0 kernel/exit.c:865 do_group_exit+0x13b/0x3a0 kernel/exit.c:968 get_signal+0x6bb/0x1650 kernel/signal.c:2482 do_signal+0x84/0x1b70 arch/x86/kernel/signal.c:810 exit_to_usermode_loop+0x155/0x190 arch/x86/entry/common.c:162 prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline] syscall_return_slowpath arch/x86/entry/common.c:265 [inline] do_syscall_64+0x445/0x4e0 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4497b9 RSP: 002b:00007f1c68e74ce8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: fffffffffffffe00 RBX: 000000000071bf80 RCX: 00000000004497b9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000071bf80 RBP: 000000000071bf80 R08: 0000000000000000 R09: 000000000071bf58 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f1c68e759c0 R15: 00007f1c68e75700 This patch tries to use trylock_page to mitigate such deadlock condition for fix. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/segment.c | 43 +++++++++++++++++++++++++++++++------------ 1 file changed, 31 insertions(+), 12 deletions(-) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index fdd8cd21522f..3602acee4985 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -215,7 +215,8 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page) } static int __revoke_inmem_pages(struct inode *inode, - struct list_head *head, bool drop, bool recover) + struct list_head *head, bool drop, bool recover, + bool trylock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct inmem_pages *cur, *tmp; @@ -227,7 +228,16 @@ static int __revoke_inmem_pages(struct inode *inode, if (drop) trace_f2fs_commit_inmem_page(page, INMEM_DROP); - lock_page(page); + if (trylock) { + /* + * to avoid deadlock in between page lock and + * inmem_lock. + */ + if (!trylock_page(page)) + continue; + } else { + lock_page(page); + } f2fs_wait_on_page_writeback(page, DATA, true, true); @@ -318,13 +328,19 @@ void f2fs_drop_inmem_pages(struct inode *inode) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - mutex_lock(&fi->inmem_lock); - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); - spin_lock(&sbi->inode_lock[ATOMIC_FILE]); - if (!list_empty(&fi->inmem_ilist)) - list_del_init(&fi->inmem_ilist); - spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); - mutex_unlock(&fi->inmem_lock); + while (!list_empty(&fi->inmem_pages)) { + mutex_lock(&fi->inmem_lock); + __revoke_inmem_pages(inode, &fi->inmem_pages, + true, false, true); + + if (list_empty(&fi->inmem_pages)) { + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (!list_empty(&fi->inmem_ilist)) + list_del_init(&fi->inmem_ilist); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + mutex_unlock(&fi->inmem_lock); + } + } clear_inode_flag(inode, FI_ATOMIC_FILE); fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0; @@ -429,12 +445,15 @@ static int __f2fs_commit_inmem_pages(struct inode *inode) * recovery or rewrite & commit last transaction. For other * error number, revoking was done by filesystem itself. */ - err = __revoke_inmem_pages(inode, &revoke_list, false, true); + err = __revoke_inmem_pages(inode, &revoke_list, + false, true, false); /* drop all uncommitted pages */ - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); + __revoke_inmem_pages(inode, &fi->inmem_pages, + true, false, false); } else { - __revoke_inmem_pages(inode, &revoke_list, false, false); + __revoke_inmem_pages(inode, &revoke_list, + false, false, false); } return err; -- GitLab From 72bfaa916781ee355b65f8b1c74439a50f574872 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Sat, 2 Feb 2019 17:33:01 +0800 Subject: [PATCH 0028/1128] f2fs: fix potential data inconsistence of checkpoint Previously, we changed lock from cp_rwsem to node_change, it solved the deadlock issue which was caused by below race condition: Thread A Thread B - f2fs_setattr - f2fs_lock_op -- read_lock - dquot_transfer - __dquot_transfer - dquot_acquire - commit_dqblk - f2fs_quota_write - f2fs_write_begin - f2fs_write_failed - write_checkpoint - block_operations - f2fs_lock_all -- write_lock - f2fs_truncate_blocks - f2fs_lock_op -- read_lock But it breaks the sematics of cp_rwsem, in other callers like: - f2fs_file_write_iter -> f2fs_write_begin -> f2fs_write_failed - f2fs_direct_IO -> f2fs_write_failed We allow to truncate dnode w/o cp_rwsem held, result in incorrect sit bitmap update, which can cause further data corruption. So this patch reverts previous fix implementation, and try to fix deadlock by skipping calling f2fs_truncate_blocks() in f2fs_write_failed() only for quota file, and keep the preallocated data/node in the tail of quota file, we can expecte that the preallocated space can be used to store quota info latter soon. Fixes: af033b2aa8a8 ("f2fs: guarantee journalled quota data by checkpoint") Signed-off-by: Gao Xiang Signed-off-by: Sheng Yong Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 3 ++- fs/f2fs/f2fs.h | 3 +-- fs/f2fs/file.c | 14 ++++++-------- fs/f2fs/inline.c | 4 ++-- 4 files changed, 11 insertions(+), 13 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index c0ee1c06e70e..b94d4eca22f4 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2311,7 +2311,8 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to) down_write(&F2FS_I(inode)->i_mmap_sem); truncate_pagecache(inode, i_size); - f2fs_truncate_blocks(inode, i_size, true, true); + if (!IS_NOQUOTA(inode)) + f2fs_truncate_blocks(inode, i_size, true); up_write(&F2FS_I(inode)->i_mmap_sem); up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index c696b27d8cc4..f5814dc68fa5 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2843,8 +2843,7 @@ static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); void f2fs_truncate_data_blocks(struct dnode_of_data *dn); -int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, - bool buf_write); +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate(struct inode *inode); int f2fs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 149710854a3a..5df1253c2010 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -589,8 +589,7 @@ static int truncate_partial_data_page(struct inode *inode, u64 from, return 0; } -int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, - bool buf_write) +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; @@ -598,7 +597,6 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, int count = 0, err = 0; struct page *ipage; bool truncate_page = false; - int flag = buf_write ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO; trace_f2fs_truncate_blocks_enter(inode, from); @@ -608,7 +606,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, goto free_partial; if (lock) - __do_map_lock(sbi, flag, true); + f2fs_lock_op(sbi); ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { @@ -646,7 +644,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, err = f2fs_truncate_inode_blocks(inode, free_from); out: if (lock) - __do_map_lock(sbi, flag, false); + f2fs_unlock_op(sbi); free_partial: /* lastly zero out the first data page */ if (!err) @@ -681,7 +679,7 @@ int f2fs_truncate(struct inode *inode) return err; } - err = f2fs_truncate_blocks(inode, i_size_read(inode), true, false); + err = f2fs_truncate_blocks(inode, i_size_read(inode), true); if (err) return err; @@ -1262,7 +1260,7 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) new_size = i_size_read(inode) - len; truncate_pagecache(inode, new_size); - ret = f2fs_truncate_blocks(inode, new_size, true, false); + ret = f2fs_truncate_blocks(inode, new_size, true); up_write(&F2FS_I(inode)->i_mmap_sem); if (!ret) f2fs_i_size_write(inode, new_size); @@ -1447,7 +1445,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); down_write(&F2FS_I(inode)->i_mmap_sem); - ret = f2fs_truncate_blocks(inode, i_size_read(inode), true, false); + ret = f2fs_truncate_blocks(inode, i_size_read(inode), true); up_write(&F2FS_I(inode)->i_mmap_sem); if (ret) return ret; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 9804cdcf976e..3ebae34a8b96 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -298,7 +298,7 @@ bool f2fs_recover_inline_data(struct inode *inode, struct page *npage) clear_inode_flag(inode, FI_INLINE_DATA); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - if (f2fs_truncate_blocks(inode, 0, false, false)) + if (f2fs_truncate_blocks(inode, 0, false)) return false; goto process_inline; } @@ -470,7 +470,7 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) return 0; punch_dentry_pages: truncate_inode_pages(&dir->i_data, 0); - f2fs_truncate_blocks(dir, 0, false, false); + f2fs_truncate_blocks(dir, 0, false); f2fs_remove_dirty_inode(dir); return err; } -- GitLab From ad65135dc447f8348ef06552af5a1420a819ee61 Mon Sep 17 00:00:00 2001 From: Sahitya Tummala Date: Mon, 4 Feb 2019 13:36:53 +0530 Subject: [PATCH 0029/1128] f2fs: do not use mutex lock in atomic context Fix below warning coming because of using mutex lock in atomic context. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:98 in_atomic(): 1, irqs_disabled(): 0, pid: 585, name: sh Preemption disabled at: __radix_tree_preload+0x28/0x130 Call trace: dump_backtrace+0x0/0x2b4 show_stack+0x20/0x28 dump_stack+0xa8/0xe0 ___might_sleep+0x144/0x194 __might_sleep+0x58/0x8c mutex_lock+0x2c/0x48 f2fs_trace_pid+0x88/0x14c f2fs_set_node_page_dirty+0xd0/0x184 Do not use f2fs_radix_tree_insert() to avoid doing cond_resched() with spin_lock() acquired. Signed-off-by: Sahitya Tummala Signed-off-by: Jaegeuk Kim --- fs/f2fs/trace.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c index ce2a5eb210b6..d0ab533a9ce8 100644 --- a/fs/f2fs/trace.c +++ b/fs/f2fs/trace.c @@ -14,7 +14,7 @@ #include "trace.h" static RADIX_TREE(pids, GFP_ATOMIC); -static struct mutex pids_lock; +static spinlock_t pids_lock; static struct last_io_info last_io; static inline void __print_last_io(void) @@ -58,23 +58,29 @@ void f2fs_trace_pid(struct page *page) set_page_private(page, (unsigned long)pid); +retry: if (radix_tree_preload(GFP_NOFS)) return; - mutex_lock(&pids_lock); + spin_lock(&pids_lock); p = radix_tree_lookup(&pids, pid); if (p == current) goto out; if (p) radix_tree_delete(&pids, pid); - f2fs_radix_tree_insert(&pids, pid, current); + if (radix_tree_insert(&pids, pid, current)) { + spin_unlock(&pids_lock); + radix_tree_preload_end(); + cond_resched(); + goto retry; + } trace_printk("%3x:%3x %4x %-16s\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), pid, current->comm); out: - mutex_unlock(&pids_lock); + spin_unlock(&pids_lock); radix_tree_preload_end(); } @@ -119,7 +125,7 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush) void f2fs_build_trace_ios(void) { - mutex_init(&pids_lock); + spin_lock_init(&pids_lock); } #define PIDVEC_SIZE 128 @@ -147,7 +153,7 @@ void f2fs_destroy_trace_ios(void) pid_t next_pid = 0; unsigned int found; - mutex_lock(&pids_lock); + spin_lock(&pids_lock); while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) { unsigned idx; @@ -155,5 +161,5 @@ void f2fs_destroy_trace_ios(void) for (idx = 0; idx < found; idx++) radix_tree_delete(&pids, pid[idx]); } - mutex_unlock(&pids_lock); + spin_unlock(&pids_lock); } -- GitLab From 3d41a99972623a65eab446e3fa30ffb9cd949d96 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Fri, 3 Aug 2018 13:05:11 -0700 Subject: [PATCH 0030/1128] PM / devfreq: Make update_devfreq() public Currently update_devfreq() is only visible to devfreq governors outside of devfreq.c. Make it public to allow drivers that adjust devfreq policies to cause a re-evaluation of the frequency after a policy change. Change-Id: I629c39eaa441a4d1cb675f73f0efb679e7a9e702 Signed-off-by: Matthias Kaehlcke Reviewed-by: Brian Norris Reviewed-by: Chanwoo Choi Signed-off-by: MyungJoo Ham Git-commit: b596d895fa2957e136a6b398b97b06bd42b51291 Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git Signed-off-by: Akhil P Oommen --- drivers/devfreq/governor.h | 3 --- include/linux/devfreq.h | 8 ++++++++ 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h index cfc50a61a90d..608e7549465b 100644 --- a/drivers/devfreq/governor.h +++ b/drivers/devfreq/governor.h @@ -54,9 +54,6 @@ struct devfreq_governor { unsigned int event, void *data); }; -/* Caution: devfreq->lock must be locked before calling update_devfreq */ -extern int update_devfreq(struct devfreq *devfreq); - extern void devfreq_monitor_start(struct devfreq *devfreq); extern void devfreq_monitor_stop(struct devfreq *devfreq); extern void devfreq_monitor_suspend(struct devfreq *devfreq); diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 1efff4bfaaf6..f26c0fe68623 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -188,6 +188,14 @@ extern void devm_devfreq_remove_device(struct device *dev, extern int devfreq_suspend_device(struct devfreq *devfreq); extern int devfreq_resume_device(struct devfreq *devfreq); +/** + * update_devfreq() - Reevaluate the device and configure frequency + * @devfreq: the devfreq device + * + * Note: devfreq->lock must be held + */ +extern int update_devfreq(struct devfreq *devfreq); + /* Helper functions for devfreq user device driver with OPP. */ extern struct dev_pm_opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq, u32 flags); -- GitLab From 8cf3847ec3c09f678fabc08c316b98c3bab387aa Mon Sep 17 00:00:00 2001 From: Akhil P Oommen Date: Fri, 22 Feb 2019 19:22:00 +0530 Subject: [PATCH 0031/1128] msm: kgsl: Do GPU bus governor management Currently, bus governor operations like devfreq update, suspend & resume are done by the adreno_tz governor. Instead of that, do these bus governor operations from the driver. Change-Id: I13bf2405f05668346cbe0519a3d143addf75653f Signed-off-by: Akhil P Oommen --- drivers/gpu/msm/kgsl_pwrscale.c | 35 ++++++++++++++++++++------------- drivers/gpu/msm/kgsl_pwrscale.h | 4 +++- 2 files changed, 24 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/msm/kgsl_pwrscale.c b/drivers/gpu/msm/kgsl_pwrscale.c index 244118f31d19..1090b7d30dda 100644 --- a/drivers/gpu/msm/kgsl_pwrscale.c +++ b/drivers/gpu/msm/kgsl_pwrscale.c @@ -1,4 +1,4 @@ -/* Copyright (c) 2010-2018, The Linux Foundation. All rights reserved. +/* Copyright (c) 2010-2019, The Linux Foundation. All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 and @@ -198,7 +198,7 @@ void kgsl_pwrscale_update(struct kgsl_device *device) device->pwrscale.next_governor_call = ktime_add_us(t, KGSL_GOVERNOR_CALL_INTERVAL); - /* to call srcu_notifier_call_chain() from a kernel thread */ + /* to call update_devfreq() from a kernel thread */ if (device->state != KGSL_STATE_SLUMBER) queue_work(device->pwrscale.devfreq_wq, &device->pwrscale.devfreq_notify_ws); @@ -935,7 +935,6 @@ int kgsl_pwrscale_init(struct device *dev, const char *governor) struct kgsl_pwrscale *pwrscale; struct kgsl_pwrctrl *pwr; struct devfreq *devfreq; - struct devfreq *bus_devfreq; struct msm_adreno_extended_profile *gpu_profile; struct devfreq_dev_profile *profile; struct devfreq_msm_adreno_tz_data *data; @@ -1039,17 +1038,16 @@ int kgsl_pwrscale_init(struct device *dev, const char *governor) if (IS_ERR(pwrscale->cooling_dev)) pwrscale->cooling_dev = NULL; - pwrscale->gpu_profile.bus_devfreq = NULL; if (data->bus.num) { pwrscale->bus_profile.profile.max_state = pwr->num_pwrlevels - 1; pwrscale->bus_profile.profile.freq_table = pwrscale->freq_table; - bus_devfreq = devfreq_add_device(device->busmondev, + pwrscale->bus_devfreq = devfreq_add_device(device->busmondev, &pwrscale->bus_profile.profile, "gpubw_mon", NULL); - if (!IS_ERR(bus_devfreq)) - pwrscale->gpu_profile.bus_devfreq = bus_devfreq; + if (IS_ERR(pwrscale->bus_devfreq)) + pwrscale->bus_devfreq = NULL; } ret = sysfs_create_link(&device->dev->kobj, @@ -1109,8 +1107,10 @@ void kgsl_pwrscale_close(struct kgsl_device *device) flush_workqueue(pwrscale->devfreq_wq); destroy_workqueue(pwrscale->devfreq_wq); devfreq_remove_device(device->pwrscale.devfreqptr); + devfreq_remove_device(pwrscale->bus_devfreq); kfree(kgsl_midframe); kgsl_midframe = NULL; + device->pwrscale.bus_devfreq = NULL; device->pwrscale.devfreqptr = NULL; srcu_cleanup_notifier_head(&device->pwrscale.nh); dev_pm_opp_unregister_notifier(&device->pdev->dev, &pwr->nb); @@ -1123,18 +1123,18 @@ static void do_devfreq_suspend(struct work_struct *work) { struct kgsl_pwrscale *pwrscale = container_of(work, struct kgsl_pwrscale, devfreq_suspend_ws); - struct devfreq *devfreq = pwrscale->devfreqptr; - devfreq_suspend_device(devfreq); + devfreq_suspend_device(pwrscale->devfreqptr); + devfreq_suspend_device(pwrscale->bus_devfreq); } static void do_devfreq_resume(struct work_struct *work) { struct kgsl_pwrscale *pwrscale = container_of(work, struct kgsl_pwrscale, devfreq_resume_ws); - struct devfreq *devfreq = pwrscale->devfreqptr; - devfreq_resume_device(devfreq); + devfreq_resume_device(pwrscale->devfreqptr); + devfreq_resume_device(pwrscale->bus_devfreq); } static void do_devfreq_notify(struct work_struct *work) @@ -1142,8 +1142,15 @@ static void do_devfreq_notify(struct work_struct *work) struct kgsl_pwrscale *pwrscale = container_of(work, struct kgsl_pwrscale, devfreq_notify_ws); struct devfreq *devfreq = pwrscale->devfreqptr; + struct devfreq *bus_devfreq = pwrscale->bus_devfreq; - srcu_notifier_call_chain(&pwrscale->nh, - ADRENO_DEVFREQ_NOTIFY_RETIRE, - devfreq); + mutex_lock(&devfreq->lock); + update_devfreq(devfreq); + mutex_unlock(&devfreq->lock); + + if (bus_devfreq) { + mutex_lock(&bus_devfreq->lock); + update_devfreq(bus_devfreq); + mutex_unlock(&bus_devfreq->lock); + } } diff --git a/drivers/gpu/msm/kgsl_pwrscale.h b/drivers/gpu/msm/kgsl_pwrscale.h index 9e28b6594b8d..60415a6c8f2b 100644 --- a/drivers/gpu/msm/kgsl_pwrscale.h +++ b/drivers/gpu/msm/kgsl_pwrscale.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2010-2018, The Linux Foundation. All rights reserved. +/* Copyright (c) 2010-2019, The Linux Foundation. All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 and @@ -71,6 +71,7 @@ struct kgsl_pwr_history { /** * struct kgsl_pwrscale - Power scaling settings for a KGSL device * @devfreqptr - Pointer to the devfreq device + * @bus_devfreq - Pointer to the bus devfreq device * @gpu_profile - GPU profile data for the devfreq device * @bus_profile - Bus specific data for the bus devfreq device * @freq_table - GPU frequencies for the DCVS algorithm @@ -99,6 +100,7 @@ struct kgsl_pwr_history { */ struct kgsl_pwrscale { struct devfreq *devfreqptr; + struct devfreq *bus_devfreq; struct msm_adreno_extended_profile gpu_profile; struct msm_busmon_extended_profile bus_profile; unsigned long freq_table[KGSL_MAX_PWRLEVELS]; -- GitLab From 7603d6f287189afd79a4e2510e59f284c651208a Mon Sep 17 00:00:00 2001 From: Akhil P Oommen Date: Thu, 7 Jun 2018 18:39:27 +0530 Subject: [PATCH 0032/1128] adreno_tz: Remove partner devfreq management Remove partner (bus) devfreq management from the adreno governor. Partner devfreq can be managed directly from the device driver. Change-Id: I745361c2b585e0dd91f208e09ec3001d7ecba717 Signed-off-by: Akhil P Oommen --- drivers/devfreq/governor_msm_adreno_tz.c | 122 +---------------------- include/linux/msm_adreno_devfreq.h | 18 +--- 2 files changed, 3 insertions(+), 137 deletions(-) diff --git a/drivers/devfreq/governor_msm_adreno_tz.c b/drivers/devfreq/governor_msm_adreno_tz.c index 8a93d8d15db8..779c37836ff3 100644 --- a/drivers/devfreq/governor_msm_adreno_tz.c +++ b/drivers/devfreq/governor_msm_adreno_tz.c @@ -1,4 +1,4 @@ -/* Copyright (c) 2010-2018, The Linux Foundation. All rights reserved. +/* Copyright (c) 2010-2019, The Linux Foundation. All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 and @@ -62,14 +62,6 @@ static u64 suspend_time; static u64 suspend_start; static unsigned long acc_total, acc_relative_busy; -static struct msm_adreno_extended_profile *partner_gpu_profile; -static void do_partner_start_event(struct work_struct *work); -static void do_partner_stop_event(struct work_struct *work); -static void do_partner_suspend_event(struct work_struct *work); -static void do_partner_resume_event(struct work_struct *work); - -static struct workqueue_struct *workqueue; - /* * Returns GPU suspend time in millisecond. */ @@ -415,32 +407,6 @@ static int tz_get_target_freq(struct devfreq *devfreq, unsigned long *freq) return 0; } -static int tz_notify(struct notifier_block *nb, unsigned long type, void *devp) -{ - int result = 0; - struct devfreq *devfreq = devp; - - switch (type) { - case ADRENO_DEVFREQ_NOTIFY_IDLE: - case ADRENO_DEVFREQ_NOTIFY_RETIRE: - mutex_lock(&devfreq->lock); - result = update_devfreq(devfreq); - mutex_unlock(&devfreq->lock); - /* Nofifying partner bus governor if any */ - if (partner_gpu_profile && partner_gpu_profile->bus_devfreq) { - mutex_lock(&partner_gpu_profile->bus_devfreq->lock); - update_devfreq(partner_gpu_profile->bus_devfreq); - mutex_unlock(&partner_gpu_profile->bus_devfreq->lock); - } - break; - /* ignored by this governor */ - case ADRENO_DEVFREQ_NOTIFY_SUBMIT: - default: - break; - } - return notifier_from_errno(result); -} - static int tz_start(struct devfreq *devfreq) { struct devfreq_msm_adreno_tz_data *priv; @@ -460,10 +426,8 @@ static int tz_start(struct devfreq *devfreq) * from the container of the device profile */ devfreq->data = gpu_profile->private_data; - partner_gpu_profile = gpu_profile; priv = devfreq->data; - priv->nb.notifier_call = tz_notify; out = 1; if (devfreq->profile->max_state < MSM_ADRENO_MAX_PWRLEVELS) { @@ -475,15 +439,6 @@ static int tz_start(struct devfreq *devfreq) return -EINVAL; } - INIT_WORK(&gpu_profile->partner_start_event_ws, - do_partner_start_event); - INIT_WORK(&gpu_profile->partner_stop_event_ws, - do_partner_stop_event); - INIT_WORK(&gpu_profile->partner_suspend_event_ws, - do_partner_suspend_event); - INIT_WORK(&gpu_profile->partner_resume_event_ws, - do_partner_resume_event); - ret = tz_init(priv, tz_pwrlevels, sizeof(tz_pwrlevels), &version, sizeof(version)); if (ret != 0 || version > MAX_TZ_VERSION) { @@ -494,24 +449,18 @@ static int tz_start(struct devfreq *devfreq) for (i = 0; adreno_tz_attr_list[i] != NULL; i++) device_create_file(&devfreq->dev, adreno_tz_attr_list[i]); - return kgsl_devfreq_add_notifier(devfreq->dev.parent, &priv->nb); + return 0; } static int tz_stop(struct devfreq *devfreq) { int i; - struct devfreq_msm_adreno_tz_data *priv = devfreq->data; - - kgsl_devfreq_del_notifier(devfreq->dev.parent, &priv->nb); for (i = 0; adreno_tz_attr_list[i] != NULL; i++) device_remove_file(&devfreq->dev, adreno_tz_attr_list[i]); - flush_workqueue(workqueue); - /* leaving the governor and cleaning the pointer to private data */ devfreq->data = NULL; - partner_gpu_profile = NULL; return 0; } @@ -531,21 +480,12 @@ static int tz_handler(struct devfreq *devfreq, unsigned int event, void *data) { int result; - struct msm_adreno_extended_profile *gpu_profile = container_of( - (devfreq->profile), - struct msm_adreno_extended_profile, - profile); - switch (event) { case DEVFREQ_GOV_START: result = tz_start(devfreq); break; case DEVFREQ_GOV_STOP: - /* Queue the stop work before the TZ is stopped */ - if (partner_gpu_profile && partner_gpu_profile->bus_devfreq) - queue_work(workqueue, - &gpu_profile->partner_stop_event_ws); spin_lock(&suspend_lock); suspend_start = 0; spin_unlock(&suspend_lock); @@ -576,60 +516,9 @@ static int tz_handler(struct devfreq *devfreq, unsigned int event, void *data) break; } - if (partner_gpu_profile && partner_gpu_profile->bus_devfreq) - switch (event) { - case DEVFREQ_GOV_START: - queue_work(workqueue, - &gpu_profile->partner_start_event_ws); - break; - case DEVFREQ_GOV_SUSPEND: - queue_work(workqueue, - &gpu_profile->partner_suspend_event_ws); - break; - case DEVFREQ_GOV_RESUME: - queue_work(workqueue, - &gpu_profile->partner_resume_event_ws); - break; - } - return result; } -static void _do_partner_event(struct work_struct *work, unsigned int event) -{ - struct devfreq *bus_devfreq; - - if (partner_gpu_profile == NULL) - return; - - bus_devfreq = partner_gpu_profile->bus_devfreq; - - if (bus_devfreq != NULL && - bus_devfreq->governor && - bus_devfreq->governor->event_handler) - bus_devfreq->governor->event_handler(bus_devfreq, event, NULL); -} - -static void do_partner_start_event(struct work_struct *work) -{ - _do_partner_event(work, DEVFREQ_GOV_START); -} - -static void do_partner_stop_event(struct work_struct *work) -{ - _do_partner_event(work, DEVFREQ_GOV_STOP); -} - -static void do_partner_suspend_event(struct work_struct *work) -{ - _do_partner_event(work, DEVFREQ_GOV_SUSPEND); -} - -static void do_partner_resume_event(struct work_struct *work) -{ - _do_partner_event(work, DEVFREQ_GOV_RESUME); -} - static struct devfreq_governor msm_adreno_tz = { .name = "msm-adreno-tz", @@ -639,11 +528,6 @@ static struct devfreq_governor msm_adreno_tz = { static int __init msm_adreno_tz_init(void) { - workqueue = create_freezable_workqueue("governor_msm_adreno_tz_wq"); - - if (workqueue == NULL) - return -ENOMEM; - return devfreq_add_governor(&msm_adreno_tz); } subsys_initcall(msm_adreno_tz_init); @@ -655,8 +539,6 @@ static void __exit msm_adreno_tz_exit(void) if (ret) pr_err(TAG "failed to remove governor %d\n", ret); - if (workqueue != NULL) - destroy_workqueue(workqueue); } module_exit(msm_adreno_tz_exit); diff --git a/include/linux/msm_adreno_devfreq.h b/include/linux/msm_adreno_devfreq.h index 2b94289153f3..c99beecf3cf2 100644 --- a/include/linux/msm_adreno_devfreq.h +++ b/include/linux/msm_adreno_devfreq.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2016-2017, The Linux Foundation. All rights reserved. +/* Copyright (c) 2016-2019, The Linux Foundation. All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 and @@ -17,22 +17,12 @@ #include #include -#define ADRENO_DEVFREQ_NOTIFY_SUBMIT 1 -#define ADRENO_DEVFREQ_NOTIFY_RETIRE 2 -#define ADRENO_DEVFREQ_NOTIFY_IDLE 3 - #define DEVFREQ_FLAG_WAKEUP_MAXFREQ 0x2 #define DEVFREQ_FLAG_FAST_HINT 0x4 #define DEVFREQ_FLAG_SLOW_HINT 0x8 struct device; -int kgsl_devfreq_add_notifier(struct device *device, - struct notifier_block *block); - -int kgsl_devfreq_del_notifier(struct device *device, - struct notifier_block *block); - /* same as KGSL_MAX_PWRLEVELS */ #define MSM_ADRENO_MAX_PWRLEVELS 10 @@ -73,12 +63,6 @@ struct devfreq_msm_adreno_tz_data { struct msm_adreno_extended_profile { struct devfreq_msm_adreno_tz_data *private_data; - struct devfreq *bus_devfreq; - struct workqueue_struct *partner_wq; - struct work_struct partner_start_event_ws; - struct work_struct partner_stop_event_ws; - struct work_struct partner_suspend_event_ws; - struct work_struct partner_resume_event_ws; struct devfreq_dev_profile profile; }; -- GitLab From cd1d2b21131ce65f3eebb5de0524c5d71c267cf5 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 15 Feb 2019 20:57:53 -0800 Subject: [PATCH 0033/1128] Revert "f2fs: fix to check inline_xattr_size boundary correctly" This reverts commit 802a643228462e0e3f6e84977d912f1871f61467. --- fs/f2fs/f2fs.h | 1 + fs/f2fs/super.c | 10 +++++----- include/linux/f2fs_fs.h | 13 ++++++------- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index f5814dc68fa5..5c0da6c4f187 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -460,6 +460,7 @@ struct f2fs_flush_device { /* for inline stuff */ #define DEF_INLINE_RESERVED_SIZE 1 +#define DEF_MIN_INLINE_SIZE 1 static inline int get_extra_isize(struct inode *inode); static inline int get_inline_xattr_addrs(struct inode *inode); #define MAX_INLINE_DATA(inode) (sizeof(__le32) * \ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3166b7266f9e..b3b9a74303ba 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -835,11 +835,11 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; } if (!F2FS_OPTION(sbi).inline_xattr_size || - F2FS_OPTION(sbi).inline_xattr_size > - DEF_ADDRS_PER_INODE - - F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - - DEF_INLINE_RESERVED_SIZE - - MIN_INLINE_DENTRY_SIZE / sizeof(__le32)) { + F2FS_OPTION(sbi).inline_xattr_size >= + DEF_ADDRS_PER_INODE - + F2FS_TOTAL_EXTRA_ATTR_SIZE - + DEF_INLINE_RESERVED_SIZE - + DEF_MIN_INLINE_SIZE) { f2fs_msg(sb, KERN_ERR, "inline xattr size is out of range"); return -EINVAL; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 666db8eb71e0..8d57aaee8166 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -490,12 +490,12 @@ typedef __le32 f2fs_hash_t; /* * space utilization of regular dentry and inline dentry (w/o extra reservation) - * regular dentry inline dentry (def) inline dentry (min) - * bitmap 1 * 27 = 27 1 * 23 = 23 1 * 1 = 1 - * reserved 1 * 3 = 3 1 * 7 = 7 1 * 1 = 1 - * dentry 11 * 214 = 2354 11 * 182 = 2002 11 * 2 = 22 - * filename 8 * 214 = 1712 8 * 182 = 1456 8 * 2 = 16 - * total 4096 3488 40 + * regular dentry inline dentry + * bitmap 1 * 27 = 27 1 * 23 = 23 + * reserved 1 * 3 = 3 1 * 7 = 7 + * dentry 11 * 214 = 2354 11 * 182 = 2002 + * filename 8 * 214 = 1712 8 * 182 = 1456 + * total 4096 3488 * * Note: there are more reserved space in inline dentry than in regular * dentry, when converting inline dentry we should handle this carefully. @@ -507,7 +507,6 @@ typedef __le32 f2fs_hash_t; #define SIZE_OF_RESERVED (PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \ F2FS_SLOT_LEN) * \ NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP)) -#define MIN_INLINE_DENTRY_SIZE 40 /* just include '.' and '..' entries */ /* One directory entry slot representing F2FS_SLOT_LEN-sized file name */ struct f2fs_dir_entry { -- GitLab From d34a48c54c315f4f33b193c5657b7394867062e4 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 26 Feb 2019 09:47:34 -0800 Subject: [PATCH 0034/1128] Revert "f2fs: fix to avoid deadlock of atomic file operations" This reverts commit f3ac182210162c7e76997a8566a7f9869349f3d8. --- fs/f2fs/segment.c | 43 ++++++++++++------------------------------- 1 file changed, 12 insertions(+), 31 deletions(-) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 3602acee4985..fdd8cd21522f 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -215,8 +215,7 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page) } static int __revoke_inmem_pages(struct inode *inode, - struct list_head *head, bool drop, bool recover, - bool trylock) + struct list_head *head, bool drop, bool recover) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct inmem_pages *cur, *tmp; @@ -228,16 +227,7 @@ static int __revoke_inmem_pages(struct inode *inode, if (drop) trace_f2fs_commit_inmem_page(page, INMEM_DROP); - if (trylock) { - /* - * to avoid deadlock in between page lock and - * inmem_lock. - */ - if (!trylock_page(page)) - continue; - } else { - lock_page(page); - } + lock_page(page); f2fs_wait_on_page_writeback(page, DATA, true, true); @@ -328,19 +318,13 @@ void f2fs_drop_inmem_pages(struct inode *inode) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - while (!list_empty(&fi->inmem_pages)) { - mutex_lock(&fi->inmem_lock); - __revoke_inmem_pages(inode, &fi->inmem_pages, - true, false, true); - - if (list_empty(&fi->inmem_pages)) { - spin_lock(&sbi->inode_lock[ATOMIC_FILE]); - if (!list_empty(&fi->inmem_ilist)) - list_del_init(&fi->inmem_ilist); - spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); - mutex_unlock(&fi->inmem_lock); - } - } + mutex_lock(&fi->inmem_lock); + __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (!list_empty(&fi->inmem_ilist)) + list_del_init(&fi->inmem_ilist); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + mutex_unlock(&fi->inmem_lock); clear_inode_flag(inode, FI_ATOMIC_FILE); fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0; @@ -445,15 +429,12 @@ static int __f2fs_commit_inmem_pages(struct inode *inode) * recovery or rewrite & commit last transaction. For other * error number, revoking was done by filesystem itself. */ - err = __revoke_inmem_pages(inode, &revoke_list, - false, true, false); + err = __revoke_inmem_pages(inode, &revoke_list, false, true); /* drop all uncommitted pages */ - __revoke_inmem_pages(inode, &fi->inmem_pages, - true, false, false); + __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); } else { - __revoke_inmem_pages(inode, &revoke_list, - false, false, false); + __revoke_inmem_pages(inode, &revoke_list, false, false); } return err; -- GitLab From 4df61bb7f2f6e1ec3a70bf114f66a708f6027009 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Wed, 6 Mar 2019 16:57:28 -0800 Subject: [PATCH 0035/1128] ANDROID: cuttlefish: enable CONFIG_USB_RTL8152=y MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is to mirror: https://android-review.googlesource.com/c/kernel/configs/+/920741 Require CONFIG_USB_RTL8152 != n if we have host usb support. Generated via: echo 'CONFIG_USB_RTL8152=y' >> arch/x86/configs/x86_64_cuttlefish_defconfig echo 'CONFIG_USB_RTL8152=y' >> arch/arm64/configs/cuttlefish_defconfig make ARCH=x86_64 x86_64_cuttlefish_defconfig make ARCH=x86_64 savedefconfig cat defconfig > arch/x86/configs/x86_64_cuttlefish_defconfig make ARCH=arm64 cuttlefish_defconfig make ARCH=arm64 savedefconfig cat defconfig > arch/arm64/configs/cuttlefish_defconfig rm defconfig Bug: 110755806 Signed-off-by: Maciej Żenczykowski Change-Id: Iadca2a11b76296532aa42dde999ee73f58e0bd97 --- arch/arm64/configs/cuttlefish_defconfig | 1 + arch/x86/configs/x86_64_cuttlefish_defconfig | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/arm64/configs/cuttlefish_defconfig b/arch/arm64/configs/cuttlefish_defconfig index 126e37bd83a3..6ff030934027 100644 --- a/arch/arm64/configs/cuttlefish_defconfig +++ b/arch/arm64/configs/cuttlefish_defconfig @@ -229,6 +229,7 @@ CONFIG_PPP_DEFLATE=y CONFIG_PPP_MPPE=y CONFIG_PPTP=y CONFIG_PPPOL2TP=y +CONFIG_USB_RTL8152=y CONFIG_USB_USBNET=y # CONFIG_USB_NET_AX8817X is not set # CONFIG_USB_NET_AX88179_178A is not set diff --git a/arch/x86/configs/x86_64_cuttlefish_defconfig b/arch/x86/configs/x86_64_cuttlefish_defconfig index bf11919d50ee..0f5216486809 100644 --- a/arch/x86/configs/x86_64_cuttlefish_defconfig +++ b/arch/x86/configs/x86_64_cuttlefish_defconfig @@ -238,6 +238,7 @@ CONFIG_PPP=y CONFIG_PPP_BSDCOMP=y CONFIG_PPP_DEFLATE=y CONFIG_PPP_MPPE=y +CONFIG_USB_RTL8152=y CONFIG_USB_USBNET=y # CONFIG_USB_NET_AX8817X is not set # CONFIG_USB_NET_AX88179_178A is not set -- GitLab From b11964adfe4c07d6b7cdf64e8c40a3b622a31e17 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Fri, 8 Mar 2019 12:59:15 -0800 Subject: [PATCH 0036/1128] ANDROID: cuttlefish: enable CONFIG_INET_UDP_DIAG=y MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is to mirror: https://android-review.googlesource.com/c/kernel/configs/+/721208 android-base.cfg: enable CONFIG_INET_UDP_DIAG Generated via: echo 'CONFIG_INET_UDP_DIAG=y' >> arch/x86/configs/x86_64_cuttlefish_defconfig echo 'CONFIG_INET_UDP_DIAG=y' >> arch/arm64/configs/cuttlefish_defconfig make ARCH=x86_64 x86_64_cuttlefish_defconfig make ARCH=x86_64 savedefconfig cat defconfig > arch/x86/configs/x86_64_cuttlefish_defconfig make ARCH=arm64 cuttlefish_defconfig make ARCH=arm64 savedefconfig cat defconfig > arch/arm64/configs/cuttlefish_defconfig rm defconfig Bug: 127981801 Signed-off-by: Maciej Żenczykowski Change-Id: I5d4533b7c3b9a11e45e96b0346a70b3f93d4a812 --- arch/x86/configs/x86_64_cuttlefish_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/configs/x86_64_cuttlefish_defconfig b/arch/x86/configs/x86_64_cuttlefish_defconfig index 0f5216486809..d27e3ce9a5c0 100644 --- a/arch/x86/configs/x86_64_cuttlefish_defconfig +++ b/arch/x86/configs/x86_64_cuttlefish_defconfig @@ -95,6 +95,7 @@ CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=y CONFIG_INET_ESP=y # CONFIG_INET_XFRM_MODE_BEET is not set +CONFIG_INET_UDP_DIAG=y CONFIG_INET_DIAG_DESTROY=y CONFIG_TCP_CONG_ADVANCED=y # CONFIG_TCP_CONG_BIC is not set -- GitLab From 85cf5519050d151a77273171f2b2faf0ce5af8eb Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 25 Jan 2019 12:53:07 +0530 Subject: [PATCH 0037/1128] cpufreq: Use struct kobj_attribute instead of struct global_attr commit 625c85a62cb7d3c79f6e16de3cfa972033658250 upstream. The cpufreq_global_kobject is created using kobject_create_and_add() helper, which assigns the kobj_type as dynamic_kobj_ktype and show/store routines are set to kobj_attr_show() and kobj_attr_store(). These routines pass struct kobj_attribute as an argument to the show/store callbacks. But all the cpufreq files created using the cpufreq_global_kobject expect the argument to be of type struct attribute. Things work fine currently as no one accesses the "attr" argument. We may not see issues even if the argument is used, as struct kobj_attribute has struct attribute as its first element and so they will both get same address. But this is logically incorrect and we should rather use struct kobj_attribute instead of struct global_attr in the cpufreq core and drivers and the show/store callbacks should take struct kobj_attribute as argument instead. This bug is caught using CFI CLANG builds in android kernel which catches mismatch in function prototypes for such callbacks. Reported-by: Donghee Han Reported-by: Sangkyu Kim Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/cpufreq/cpufreq.c | 6 +++--- drivers/cpufreq/intel_pstate.c | 18 +++++++++--------- include/linux/cpufreq.h | 12 ++---------- 3 files changed, 14 insertions(+), 22 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 66c2790dcc5f..9f5c51cd67ad 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -554,13 +554,13 @@ EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us); * SYSFS INTERFACE * *********************************************************************/ static ssize_t show_boost(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled); } -static ssize_t store_boost(struct kobject *kobj, struct attribute *attr, - const char *buf, size_t count) +static ssize_t store_boost(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) { int ret, enable; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 114dfe67015b..5ebefa17d195 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -811,7 +811,7 @@ static void intel_pstate_update_policies(void) /************************** sysfs begin ************************/ #define show_one(file_name, object) \ static ssize_t show_##file_name \ - (struct kobject *kobj, struct attribute *attr, char *buf) \ + (struct kobject *kobj, struct kobj_attribute *attr, char *buf) \ { \ return sprintf(buf, "%u\n", global.object); \ } @@ -820,7 +820,7 @@ static ssize_t intel_pstate_show_status(char *buf); static int intel_pstate_update_status(const char *buf, size_t size); static ssize_t show_status(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { ssize_t ret; @@ -831,7 +831,7 @@ static ssize_t show_status(struct kobject *kobj, return ret; } -static ssize_t store_status(struct kobject *a, struct attribute *b, +static ssize_t store_status(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { char *p = memchr(buf, '\n', count); @@ -845,7 +845,7 @@ static ssize_t store_status(struct kobject *a, struct attribute *b, } static ssize_t show_turbo_pct(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { struct cpudata *cpu; int total, no_turbo, turbo_pct; @@ -871,7 +871,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj, } static ssize_t show_num_pstates(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { struct cpudata *cpu; int total; @@ -892,7 +892,7 @@ static ssize_t show_num_pstates(struct kobject *kobj, } static ssize_t show_no_turbo(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { ssize_t ret; @@ -914,7 +914,7 @@ static ssize_t show_no_turbo(struct kobject *kobj, return ret; } -static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, +static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; @@ -961,7 +961,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, return count; } -static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, +static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; @@ -991,7 +991,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, return count; } -static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, +static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index cbf85c4c745f..cad1eb50d668 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -254,20 +254,12 @@ __ATTR(_name, 0644, show_##_name, store_##_name) static struct freq_attr _name = \ __ATTR(_name, 0200, NULL, store_##_name) -struct global_attr { - struct attribute attr; - ssize_t (*show)(struct kobject *kobj, - struct attribute *attr, char *buf); - ssize_t (*store)(struct kobject *a, struct attribute *b, - const char *c, size_t count); -}; - #define define_one_global_ro(_name) \ -static struct global_attr _name = \ +static struct kobj_attribute _name = \ __ATTR(_name, 0444, show_##_name, NULL) #define define_one_global_rw(_name) \ -static struct global_attr _name = \ +static struct kobj_attribute _name = \ __ATTR(_name, 0644, show_##_name, store_##_name) -- GitLab From 910ae4e055528090d7142e89b494e4c2f2478750 Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Wed, 20 Feb 2019 11:43:17 +0100 Subject: [PATCH 0038/1128] USB: serial: option: add Telit ME910 ECM composition commit 6431866b6707d27151be381252d6eef13025cfce upstream. This patch adds Telit ME910 family ECM composition 0x1102. Signed-off-by: Daniele Palmas Cc: stable Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 8cdca3f7acaa..bf72245f1cea 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1151,6 +1151,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), .driver_info = NCTRL(0) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1102, 0xff), /* Telit ME910 (ECM) */ + .driver_info = NCTRL(0) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4), -- GitLab From 4beb72360b435bba31d92dae8fb742b5f14b0b5e Mon Sep 17 00:00:00 2001 From: Ivan Mironov Date: Wed, 6 Feb 2019 21:14:13 +0500 Subject: [PATCH 0039/1128] USB: serial: cp210x: add ID for Ingenico 3070 commit dd9d3d86b08d6a106830364879c42c78db85389c upstream. Here is how this device appears in kernel log: usb 3-1: new full-speed USB device number 18 using xhci_hcd usb 3-1: New USB device found, idVendor=0b00, idProduct=3070 usb 3-1: New USB device strings: Mfr=1, Product=2, SerialNumber=3 usb 3-1: Product: Ingenico 3070 usb 3-1: Manufacturer: Silicon Labs usb 3-1: SerialNumber: 0001 Apparently this is a POS terminal with embedded USB-to-Serial converter. Cc: stable@vger.kernel.org Signed-off-by: Ivan Mironov Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index c931ae689a91..d8e6790ccffe 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -64,6 +64,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */ { USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */ { USB_DEVICE(0x0908, 0x01FF) }, /* Siemens RUGGEDCOM USB Serial Console */ + { USB_DEVICE(0x0B00, 0x3070) }, /* Ingenico 3070 */ { USB_DEVICE(0x0BED, 0x1100) }, /* MEI (TM) Cashflow-SC Bill/Voucher Acceptor */ { USB_DEVICE(0x0BED, 0x1101) }, /* MEI series 2000 Combo Acceptor */ { USB_DEVICE(0x0FCF, 0x1003) }, /* Dynastream ANT development board */ -- GitLab From 888b943801226a5008feb602b44fb597992b2288 Mon Sep 17 00:00:00 2001 From: Mans Rullgard Date: Thu, 14 Feb 2019 19:45:33 +0000 Subject: [PATCH 0040/1128] USB: serial: ftdi_sio: add ID for Hjelmslund Electronics USB485 commit 8d7fa3d4ea3f0ca69554215e87411494e6346fdc upstream. This adds the USB ID of the Hjelmslund Electronics USB485 Iso stick. Signed-off-by: Mans Rullgard Cc: stable Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/ftdi_sio.c | 2 ++ drivers/usb/serial/ftdi_sio_ids.h | 6 ++++++ 2 files changed, 8 insertions(+) diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 385f2ae3be24..d45a2c352c98 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1020,6 +1020,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) }, { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) }, { USB_DEVICE(AIRBUS_DS_VID, AIRBUS_DS_P8GR) }, + /* EZPrototypes devices */ + { USB_DEVICE(EZPROTOTYPES_VID, HJELMSLUND_USB485_ISO_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 975d02666c5a..b863bedb55a1 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1308,6 +1308,12 @@ #define IONICS_VID 0x1c0c #define IONICS_PLUGCOMPUTER_PID 0x0102 +/* + * EZPrototypes (PID reseller) + */ +#define EZPROTOTYPES_VID 0x1c40 +#define HJELMSLUND_USB485_ISO_PID 0x0477 + /* * Dresden Elektronik Sensor Terminal Board */ -- GitLab From 6f06591fc56b0060714956885d120b8958fea33e Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 12 Feb 2019 12:44:50 -0600 Subject: [PATCH 0041/1128] staging: comedi: ni_660x: fix missing break in switch statement commit 479826cc86118e0d87e5cefb3df5b748e0480924 upstream. Add missing break statement in order to prevent the code from falling through to the default case and return -EINVAL every time. This bug was found thanks to the ongoing efforts to enable -Wimplicit-fallthrough. Fixes: aa94f2888825 ("staging: comedi: ni_660x: tidy up ni_660x_set_pfi_routing()") Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Reviewed-by: Ian Abbott Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/ni_660x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/comedi/drivers/ni_660x.c b/drivers/staging/comedi/drivers/ni_660x.c index 6aa755ad3953..b3a83f5e3a19 100644 --- a/drivers/staging/comedi/drivers/ni_660x.c +++ b/drivers/staging/comedi/drivers/ni_660x.c @@ -611,6 +611,7 @@ static int ni_660x_set_pfi_routing(struct comedi_device *dev, case NI_660X_PFI_OUTPUT_DIO: if (chan > 31) return -EINVAL; + break; default: return -EINVAL; } -- GitLab From 313de388865ca397fef61d592cfb364f981329fc Mon Sep 17 00:00:00 2001 From: Ajay Singh Date: Thu, 7 Feb 2019 11:28:58 +0000 Subject: [PATCH 0042/1128] staging: wilc1000: fix to set correct value for 'vif_num' commit dda037057a572f5c82ac2499eb4e6fb17600ba3e upstream. Set correct value in '->vif_num' for the total number of interfaces and set '->idx' value using 'i'. Fixes: 735bb39ca3be ("staging: wilc1000: simplify vif[i]->ndev accesses") Fixes: 0e490657c721 ("staging: wilc1000: Fix problem with wrong vif index") Cc: Suggested-by: Dan Carpenter Reviewed-by: Dan Carpenter Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/staging/wilc1000/linux_wlan.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/wilc1000/linux_wlan.c b/drivers/staging/wilc1000/linux_wlan.c index 119f3459b5bb..2fc6426c3819 100644 --- a/drivers/staging/wilc1000/linux_wlan.c +++ b/drivers/staging/wilc1000/linux_wlan.c @@ -1238,8 +1238,8 @@ int wilc_netdev_init(struct wilc **wilc, struct device *dev, int io_type, vif->wilc = *wilc; vif->ndev = ndev; wl->vif[i] = vif; - wl->vif_num = i; - vif->idx = wl->vif_num; + wl->vif_num = i + 1; + vif->idx = i; ndev->netdev_ops = &wilc_netdev_ops; -- GitLab From acdaa51ac269930ec757065b3f433f6bb943ffb9 Mon Sep 17 00:00:00 2001 From: Qing Xia Date: Fri, 1 Feb 2019 14:59:46 +0800 Subject: [PATCH 0043/1128] staging: android: ion: fix sys heap pool's gfp_flags commit 9bcf065e28122588a6cbee08cf847826dacbb438 upstream. In the first loop, gfp_flags will be modified to high_order_gfp_flags, and there will be no chance to change back to low_order_gfp_flags. Fixes: e7f63771b60e ("ION: Sys_heap: Add cached pool to spead up cached buffer alloc") Signed-off-by: Qing Xia Cc: stable Signed-off-by: Jing Xia Reviewed-by: Yuming Han Reviewed-by: Zhaoyang Huang Reviewed-by: Orson Zhai Signed-off-by: Greg Kroah-Hartman --- drivers/staging/android/ion/ion_system_heap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c index b6ece18e6a88..e64db42aeb1e 100644 --- a/drivers/staging/android/ion/ion_system_heap.c +++ b/drivers/staging/android/ion/ion_system_heap.c @@ -298,10 +298,10 @@ static int ion_system_heap_create_pools(struct ion_page_pool **pools, bool cached) { int i; - gfp_t gfp_flags = low_order_gfp_flags; for (i = 0; i < NUM_ORDERS; i++) { struct ion_page_pool *pool; + gfp_t gfp_flags = low_order_gfp_flags; if (orders[i] > 4) gfp_flags = high_order_gfp_flags; -- GitLab From 412a0e856464b3a063afa721bb928fa0257a9752 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 3 Mar 2019 07:34:57 +0000 Subject: [PATCH 0044/1128] ip6mr: Do not call __IP6_INC_STATS() from preemptible context [ Upstream commit 87c11f1ddbbad38ad8bad47af133a8208985fbdf ] Similar to commit 44f49dd8b5a6 ("ipmr: fix possible race resulting from improper usage of IP_INC_STATS_BH() in preemptible context."), we cannot assume preemption is disabled when incrementing the counter and accessing a per-CPU variable. Preemption can be enabled when we add a route in process context that corresponds to packets stored in the unresolved queue, which are then forwarded using this route [1]. Fix this by using IP6_INC_STATS() which takes care of disabling preemption on architectures where it is needed. [1] [ 157.451447] BUG: using __this_cpu_add() in preemptible [00000000] code: smcrouted/2314 [ 157.460409] caller is ip6mr_forward2+0x73e/0x10e0 [ 157.460434] CPU: 3 PID: 2314 Comm: smcrouted Not tainted 5.0.0-rc7-custom-03635-g22f2712113f1 #1336 [ 157.460449] Hardware name: Mellanox Technologies Ltd. MSN2100-CB2FO/SA001017, BIOS 5.6.5 06/07/2016 [ 157.460461] Call Trace: [ 157.460486] dump_stack+0xf9/0x1be [ 157.460553] check_preemption_disabled+0x1d6/0x200 [ 157.460576] ip6mr_forward2+0x73e/0x10e0 [ 157.460705] ip6_mr_forward+0x9a0/0x1510 [ 157.460771] ip6mr_mfc_add+0x16b3/0x1e00 [ 157.461155] ip6_mroute_setsockopt+0x3cb/0x13c0 [ 157.461384] do_ipv6_setsockopt.isra.8+0x348/0x4060 [ 157.462013] ipv6_setsockopt+0x90/0x110 [ 157.462036] rawv6_setsockopt+0x4a/0x120 [ 157.462058] __sys_setsockopt+0x16b/0x340 [ 157.462198] __x64_sys_setsockopt+0xbf/0x160 [ 157.462220] do_syscall_64+0x14d/0x610 [ 157.462349] entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: 0912ea38de61 ("[IPV6] MROUTE: Add stats in multicast routing module method ip6_mr_forward().") Signed-off-by: Ido Schimmel Reported-by: Amit Cohen Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/ip6mr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index b2fdb3fdd217..459f282d90e1 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2002,10 +2002,10 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTFORWDATAGRAMS); - __IP6_ADD_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTOCTETS, skb->len); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTFORWDATAGRAMS); + IP6_ADD_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTOCTETS, skb->len); return dst_output(net, sk, skb); } -- GitLab From c031a613ff80001c7d02bcbe431509e009d7bde2 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 1 Mar 2019 19:53:57 +0100 Subject: [PATCH 0045/1128] net: dsa: mv88e6xxx: handle unknown duplex modes gracefully in mv88e6xxx_port_set_duplex [ Upstream commit c6195a8bdfc62a7cecf7df685e64847a4b700275 ] When testing another issue I faced the problem that mv88e6xxx_port_setup_mac() failed due to DUPLEX_UNKNOWN being passed as argument to mv88e6xxx_port_set_duplex(). We should handle this case gracefully and return -EOPNOTSUPP, like e.g. mv88e6xxx_port_set_speed() is doing it. Fixes: 7f1ae07b51e8 ("net: dsa: mv88e6xxx: add port duplex setter") Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/dsa/mv88e6xxx/port.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index a7801f6668a5..2cffecfe86e3 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -165,7 +165,7 @@ int mv88e6xxx_port_set_duplex(struct mv88e6xxx_chip *chip, int port, int dup) /* normal duplex detection */ break; default: - return -EINVAL; + return -EOPNOTSUPP; } err = mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_MAC_CTL, reg); -- GitLab From 306bbaeb077068141d472b922ae1adf7ab81fd72 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Sat, 2 Mar 2019 10:34:55 +0800 Subject: [PATCH 0046/1128] net-sysfs: Fix mem leak in netdev_register_kobject [ Upstream commit 895a5e96dbd6386c8e78e5b78e067dcc67b7f0ab ] syzkaller report this: BUG: memory leak unreferenced object 0xffff88837a71a500 (size 256): comm "syz-executor.2", pid 9770, jiffies 4297825125 (age 17.843s) hex dump (first 32 bytes): 00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00 .....N.......... ff ff ff ff ff ff ff ff 20 c0 ef 86 ff ff ff ff ........ ....... backtrace: [<00000000db12624b>] netdev_register_kobject+0x124/0x2e0 net/core/net-sysfs.c:1751 [<00000000dc49a994>] register_netdevice+0xcc1/0x1270 net/core/dev.c:8516 [<00000000e5f3fea0>] tun_set_iff drivers/net/tun.c:2649 [inline] [<00000000e5f3fea0>] __tun_chr_ioctl+0x2218/0x3d20 drivers/net/tun.c:2883 [<000000001b8ac127>] vfs_ioctl fs/ioctl.c:46 [inline] [<000000001b8ac127>] do_vfs_ioctl+0x1a5/0x10e0 fs/ioctl.c:690 [<0000000079b269f8>] ksys_ioctl+0x89/0xa0 fs/ioctl.c:705 [<00000000de649beb>] __do_sys_ioctl fs/ioctl.c:712 [inline] [<00000000de649beb>] __se_sys_ioctl fs/ioctl.c:710 [inline] [<00000000de649beb>] __x64_sys_ioctl+0x74/0xb0 fs/ioctl.c:710 [<000000007ebded1e>] do_syscall_64+0xc8/0x580 arch/x86/entry/common.c:290 [<00000000db315d36>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<00000000115be9bb>] 0xffffffffffffffff It should call kset_unregister to free 'dev->queues_kset' in error path of register_queue_kobjects, otherwise will cause a mem leak. Reported-by: Hulk Robot Fixes: 1d24eb4815d1 ("xps: Transmit Packet Steering") Signed-off-by: YueHaibing Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/net-sysfs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 8f17724a173c..c6a2655cc28a 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1402,6 +1402,9 @@ static int register_queue_kobjects(struct net_device *dev) error: netdev_queue_update_kobjects(dev, txq, 0); net_rx_queue_update_kobjects(dev, rxq, 0); +#ifdef CONFIG_SYSFS + kset_unregister(dev->queues_kset); +#endif return error; } -- GitLab From 094a60b28e8f391100294bcf2e0373e6272d3d8d Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Mon, 4 Mar 2019 15:00:03 +0800 Subject: [PATCH 0047/1128] sky2: Disable MSI on Dell Inspiron 1545 and Gateway P-79 [ Upstream commit b33b7cd6fd86478dd2890a9abeb6f036aa01fdf7 ] Some sky2 chips fire IRQ after S3, before the driver is fully resumed: [ 686.804877] do_IRQ: 1.37 No irq handler for vector This is likely a platform bug that device isn't fully quiesced during S3. Use MSI-X, maskable MSI or INTx can prevent this issue from happening. Since MSI-X and maskable MSI are not supported by this device, fallback to use INTx on affected platforms. BugLink: https://bugs.launchpad.net/bugs/1807259 BugLink: https://bugs.launchpad.net/bugs/1809843 Signed-off-by: Kai-Heng Feng Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/marvell/sky2.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 3954bc1d2333..cf6f58889038 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -46,6 +46,7 @@ #include #include #include +#include #include @@ -93,7 +94,7 @@ static int copybreak __read_mostly = 128; module_param(copybreak, int, 0); MODULE_PARM_DESC(copybreak, "Receive copy threshold"); -static int disable_msi = 0; +static int disable_msi = -1; module_param(disable_msi, int, 0); MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)"); @@ -4931,6 +4932,24 @@ static const char *sky2_name(u8 chipid, char *buf, int sz) return buf; } +static const struct dmi_system_id msi_blacklist[] = { + { + .ident = "Dell Inspiron 1545", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1545"), + }, + }, + { + .ident = "Gateway P-79", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Gateway"), + DMI_MATCH(DMI_PRODUCT_NAME, "P-79"), + }, + }, + {} +}; + static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *dev, *dev1; @@ -5042,6 +5061,9 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_free_pci; } + if (disable_msi == -1) + disable_msi = !!dmi_check_system(msi_blacklist); + if (!disable_msi && pci_enable_msi(pdev) == 0) { err = sky2_test_msi(hw); if (err) { -- GitLab From 1c69361496c97501f205d4ef2bc7b9c8d4c8a699 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 3 Mar 2019 07:35:51 +0000 Subject: [PATCH 0048/1128] team: Free BPF filter when unregistering netdev [ Upstream commit 692c31bd4054212312396b1d303bffab2c5b93a7 ] When team is used in loadbalance mode a BPF filter can be used to provide a hash which will determine the Tx port. When the netdev is later unregistered the filter is not freed which results in memory leaks [1]. Fix by freeing the program and the corresponding filter when unregistering the netdev. [1] unreferenced object 0xffff8881dbc47cc8 (size 16): comm "teamd", pid 3068, jiffies 4294997779 (age 438.247s) hex dump (first 16 bytes): a3 00 6b 6b 6b 6b 6b 6b 88 a5 82 e1 81 88 ff ff ..kkkkkk........ backtrace: [<000000008a3b47e3>] team_nl_cmd_options_set+0x88f/0x11b0 [<00000000c4f4f27e>] genl_family_rcv_msg+0x78f/0x1080 [<00000000610ef838>] genl_rcv_msg+0xca/0x170 [<00000000a281df93>] netlink_rcv_skb+0x132/0x380 [<000000004d9448a2>] genl_rcv+0x29/0x40 [<000000000321b2f4>] netlink_unicast+0x4c0/0x690 [<000000008c25dffb>] netlink_sendmsg+0x929/0xe10 [<00000000068298c5>] sock_sendmsg+0xc8/0x110 [<0000000082a61ff0>] ___sys_sendmsg+0x77a/0x8f0 [<00000000663ae29d>] __sys_sendmsg+0xf7/0x250 [<0000000027c5f11a>] do_syscall_64+0x14d/0x610 [<000000006cfbc8d3>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<00000000e23197e2>] 0xffffffffffffffff unreferenced object 0xffff8881e182a588 (size 2048): comm "teamd", pid 3068, jiffies 4294997780 (age 438.247s) hex dump (first 32 bytes): 20 00 00 00 02 00 00 00 30 00 00 00 28 f0 ff ff .......0...(... 07 00 00 00 00 00 00 00 28 00 00 00 00 00 00 00 ........(....... backtrace: [<000000002daf01fb>] lb_bpf_func_set+0x45c/0x6d0 [<000000008a3b47e3>] team_nl_cmd_options_set+0x88f/0x11b0 [<00000000c4f4f27e>] genl_family_rcv_msg+0x78f/0x1080 [<00000000610ef838>] genl_rcv_msg+0xca/0x170 [<00000000a281df93>] netlink_rcv_skb+0x132/0x380 [<000000004d9448a2>] genl_rcv+0x29/0x40 [<000000000321b2f4>] netlink_unicast+0x4c0/0x690 [<000000008c25dffb>] netlink_sendmsg+0x929/0xe10 [<00000000068298c5>] sock_sendmsg+0xc8/0x110 [<0000000082a61ff0>] ___sys_sendmsg+0x77a/0x8f0 [<00000000663ae29d>] __sys_sendmsg+0xf7/0x250 [<0000000027c5f11a>] do_syscall_64+0x14d/0x610 [<000000006cfbc8d3>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<00000000e23197e2>] 0xffffffffffffffff Fixes: 01d7f30a9f96 ("team: add loadbalance mode") Signed-off-by: Ido Schimmel Reported-by: Amit Cohen Acked-by: Jiri Pirko Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/team/team_mode_loadbalance.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c index 1468ddf424cc..bc0890ee9700 100644 --- a/drivers/net/team/team_mode_loadbalance.c +++ b/drivers/net/team/team_mode_loadbalance.c @@ -319,6 +319,20 @@ static int lb_bpf_func_set(struct team *team, struct team_gsetter_ctx *ctx) return 0; } +static void lb_bpf_func_free(struct team *team) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + struct bpf_prog *fp; + + if (!lb_priv->ex->orig_fprog) + return; + + __fprog_destroy(lb_priv->ex->orig_fprog); + fp = rcu_dereference_protected(lb_priv->fp, + lockdep_is_held(&team->lock)); + bpf_prog_destroy(fp); +} + static int lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx) { struct lb_priv *lb_priv = get_lb_priv(team); @@ -633,6 +647,7 @@ static void lb_exit(struct team *team) team_options_unregister(team, lb_options, ARRAY_SIZE(lb_options)); + lb_bpf_func_free(team); cancel_delayed_work_sync(&lb_priv->ex->stats.refresh_dw); free_percpu(lb_priv->pcpu_stats); kfree(lb_priv->ex); -- GitLab From 71d1e057fe117c23688a8b08bec410265954008a Mon Sep 17 00:00:00 2001 From: Erik Hugne Date: Mon, 4 Mar 2019 23:26:10 +0100 Subject: [PATCH 0049/1128] tipc: fix RDM/DGRAM connect() regression [ Upstream commit 0e63208915a8d7590d0a6218dadb2a6a00ac705a ] Fix regression bug introduced in commit 365ad353c256 ("tipc: reduce risk of user starvation during link congestion") Only signal -EDESTADDRREQ for RDM/DGRAM if we don't have a cached sockaddr. Fixes: 365ad353c256 ("tipc: reduce risk of user starvation during link congestion") Signed-off-by: Erik Hugne Signed-off-by: Jon Maloy Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/tipc/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e5f9f43ff15b..75681845679e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -943,7 +943,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(!dest)) { dest = &tsk->peer; - if (!syn || dest->family != AF_TIPC) + if (!syn && dest->family != AF_TIPC) return -EDESTADDRREQ; } -- GitLab From be11d272e843c47cc7b03f9bd94cf109589db343 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 27 Feb 2019 03:58:53 -0500 Subject: [PATCH 0050/1128] bnxt_en: Drop oversize TX packets to prevent errors. [ Upstream commit 2b3c6885386020b1b9d92d45e8349637e27d1f66 ] There have been reports of oversize UDP packets being sent to the driver to be transmitted, causing error conditions. The issue is likely caused by the dst of the SKB switching between 'lo' with 64K MTU and the hardware device with a smaller MTU. Patches are being proposed by Mahesh Bandewar to fix the issue. In the meantime, add a quick length check in the driver to prevent the error. The driver uses the TX packet size as index to look up an array to setup the TX BD. The array is large enough to support all MTU sizes supported by the driver. The oversize TX packet causes the driver to index beyond the array and put garbage values into the TX BD. Add a simple check to prevent this. Signed-off-by: Michael Chan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index da6c73868fa0..15ad247955f7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -447,6 +447,12 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) } length >>= 9; + if (unlikely(length >= ARRAY_SIZE(bnxt_lhint_arr))) { + dev_warn_ratelimited(&pdev->dev, "Dropped oversize %d bytes TX packet.\n", + skb->len); + i = 0; + goto tx_dma_error; + } flags |= bnxt_lhint_arr[length]; txbd->tx_bd_len_flags_type = cpu_to_le32(flags); -- GitLab From 390ca73e722d77ca776df52b351eb855f4ee5ee3 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 28 Feb 2019 14:56:04 +0100 Subject: [PATCH 0051/1128] geneve: correctly handle ipv6.disable module parameter [ Upstream commit cf1c9ccba7308e48a68fa77f476287d9d614e4c7 ] When IPv6 is compiled but disabled at runtime, geneve_sock_add returns -EAFNOSUPPORT. For metadata based tunnels, this causes failure of the whole operation of bringing up the tunnel. Ignore failure of IPv6 socket creation for metadata based tunnels caused by IPv6 not being available. This is the same fix as what commit d074bf960044 ("vxlan: correctly handle ipv6.disable module parameter") is doing for vxlan. Note there's also commit c0a47e44c098 ("geneve: should not call rt6_lookup() when ipv6 was disabled") which fixes a similar issue but for regular tunnels, while this patch is needed for metadata based tunnels. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/geneve.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index cb51448389a1..55c4b295ed0e 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -632,15 +632,20 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6) static int geneve_open(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); - bool ipv6 = !!(geneve->info.mode & IP_TUNNEL_INFO_IPV6); bool metadata = geneve->collect_md; + bool ipv4, ipv6; int ret = 0; + ipv6 = geneve->info.mode & IP_TUNNEL_INFO_IPV6 || metadata; + ipv4 = !ipv6 || metadata; #if IS_ENABLED(CONFIG_IPV6) - if (ipv6 || metadata) + if (ipv6) { ret = geneve_sock_add(geneve, true); + if (ret < 0 && ret != -EAFNOSUPPORT) + ipv4 = false; + } #endif - if (!ret && (!ipv6 || metadata)) + if (ipv4) ret = geneve_sock_add(geneve, false); if (ret < 0) geneve_sock_release(geneve); -- GitLab From c3a0550e0f1c822f929cb96bd559cb53d00692ce Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 22 Feb 2019 18:25:03 +0000 Subject: [PATCH 0052/1128] hv_netvsc: Fix IP header checksum for coalesced packets [ Upstream commit bf48648d650db1146b75b9bd358502431e86cf4f ] Incoming packets may have IP header checksum verified by the host. They may not have IP header checksum computed after coalescing. This patch re-compute the checksum when necessary, otherwise the packets may be dropped, because Linux network stack always checks it. Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/hyperv/netvsc_drv.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 2d90cffae9ff..74b9e51b2b47 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -741,6 +741,14 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj, schedule_delayed_work(&ndev_ctx->dwork, 0); } +static void netvsc_comp_ipcsum(struct sk_buff *skb) +{ + struct iphdr *iph = (struct iphdr *)skb->data; + + iph->check = 0; + iph->check = ip_fast_csum(iph, iph->ihl); +} + static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, struct napi_struct *napi, const struct ndis_tcp_ip_checksum_info *csum_info, @@ -764,9 +772,17 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, /* skb is already created with CHECKSUM_NONE */ skb_checksum_none_assert(skb); - /* - * In Linux, the IP checksum is always checked. - * Do L4 checksum offload if enabled and present. + /* Incoming packets may have IP header checksum verified by the host. + * They may not have IP header checksum computed after coalescing. + * We compute it here if the flags are set, because on Linux, the IP + * checksum is always checked. + */ + if (csum_info && csum_info->receive.ip_checksum_value_invalid && + csum_info->receive.ip_checksum_succeeded && + skb->protocol == htons(ETH_P_IP)) + netvsc_comp_ipcsum(skb); + + /* Do L4 checksum offload if enabled and present. */ if (csum_info && (net->features & NETIF_F_RXCSUM)) { if (csum_info->receive.tcp_checksum_succeeded || -- GitLab From 0e8ea299ded68ffe0d1bb974ca4a34a56b162a0b Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 28 Feb 2019 18:14:03 +0100 Subject: [PATCH 0053/1128] net: dsa: mv88e6xxx: Fix u64 statistics [ Upstream commit 6e46e2d821bb22b285ae8187959096b65d063b0d ] The switch maintains u64 counters for the number of octets sent and received. These are kept as two u32's which need to be combined. Fix the combing, which wrongly worked on u16's. Fixes: 80c4627b2719 ("dsa: mv88x6xxx: Refactor getting a single statistic") Reported-by: Chris Healy Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index a3543d637736..45ccd98f6265 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -639,7 +639,7 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, default: return UINT64_MAX; } - value = (((u64)high) << 16) | low; + value = (((u64)high) << 32) | low; return value; } -- GitLab From fcfe700acdc1c72eab231300e82b962bac2b2b2c Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Mon, 25 Feb 2019 19:06:06 -0500 Subject: [PATCH 0054/1128] netlabel: fix out-of-bounds memory accesses [ Upstream commit 5578de4834fe0f2a34fedc7374be691443396d1f ] There are two array out-of-bounds memory accesses, one in cipso_v4_map_lvl_valid(), the other in netlbl_bitmap_walk(). Both errors are embarassingly simple, and the fixes are straightforward. As a FYI for anyone backporting this patch to kernels prior to v4.8, you'll want to apply the netlbl_bitmap_walk() patch to cipso_v4_bitmap_walk() as netlbl_bitmap_walk() doesn't exist before Linux v4.8. Reported-by: Jann Horn Fixes: 446fda4f2682 ("[NetLabel]: CIPSOv4 engine") Fixes: 3faa8f982f95 ("netlabel: Move bitmap manipulation functions to the NetLabel core.") Signed-off-by: Paul Moore Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/cipso_ipv4.c | 3 ++- net/netlabel/netlabel_kapi.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 777fa3b7fb13..f4b83de2263e 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -667,7 +667,8 @@ static int cipso_v4_map_lvl_valid(const struct cipso_v4_doi *doi_def, u8 level) case CIPSO_V4_MAP_PASS: return 0; case CIPSO_V4_MAP_TRANS: - if (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL) + if ((level < doi_def->map.std->lvl.cipso_size) && + (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL)) return 0; break; } diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index ea7c67050792..ee3e5b6471a6 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -903,7 +903,8 @@ int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len, (state == 0 && (byte & bitmask) == 0)) return bit_spot; - bit_spot++; + if (++bit_spot >= bitmap_len) + return -1; bitmask >>= 1; if (bitmask == 0) { byte = bitmap[++byte_offset]; -- GitLab From 4de7d30668cb8b06330992e1cd336f91700a2ce7 Mon Sep 17 00:00:00 2001 From: Sheng Lan Date: Thu, 28 Feb 2019 18:47:58 +0800 Subject: [PATCH 0055/1128] net: netem: fix skb length BUG_ON in __skb_to_sgvec [ Upstream commit 5845f706388a4cde0f6b80f9e5d33527e942b7d9 ] It can be reproduced by following steps: 1. virtio_net NIC is configured with gso/tso on 2. configure nginx as http server with an index file bigger than 1M bytes 3. use tc netem to produce duplicate packets and delay: tc qdisc add dev eth0 root netem delay 100ms 10ms 30% duplicate 90% 4. continually curl the nginx http server to get index file on client 5. BUG_ON is seen quickly [10258690.371129] kernel BUG at net/core/skbuff.c:4028! [10258690.371748] invalid opcode: 0000 [#1] SMP PTI [10258690.372094] CPU: 5 PID: 0 Comm: swapper/5 Tainted: G W 5.0.0-rc6 #2 [10258690.372094] RSP: 0018:ffffa05797b43da0 EFLAGS: 00010202 [10258690.372094] RBP: 00000000000005ea R08: 0000000000000000 R09: 00000000000005ea [10258690.372094] R10: ffffa0579334d800 R11: 00000000000002c0 R12: 0000000000000002 [10258690.372094] R13: 0000000000000000 R14: ffffa05793122900 R15: ffffa0578f7cb028 [10258690.372094] FS: 0000000000000000(0000) GS:ffffa05797b40000(0000) knlGS:0000000000000000 [10258690.372094] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [10258690.372094] CR2: 00007f1a6dc00868 CR3: 000000001000e000 CR4: 00000000000006e0 [10258690.372094] Call Trace: [10258690.372094] [10258690.372094] skb_to_sgvec+0x11/0x40 [10258690.372094] start_xmit+0x38c/0x520 [virtio_net] [10258690.372094] dev_hard_start_xmit+0x9b/0x200 [10258690.372094] sch_direct_xmit+0xff/0x260 [10258690.372094] __qdisc_run+0x15e/0x4e0 [10258690.372094] net_tx_action+0x137/0x210 [10258690.372094] __do_softirq+0xd6/0x2a9 [10258690.372094] irq_exit+0xde/0xf0 [10258690.372094] smp_apic_timer_interrupt+0x74/0x140 [10258690.372094] apic_timer_interrupt+0xf/0x20 [10258690.372094] In __skb_to_sgvec(), the skb->len is not equal to the sum of the skb's linear data size and nonlinear data size, thus BUG_ON triggered. Because the skb is cloned and a part of nonlinear data is split off. Duplicate packet is cloned in netem_enqueue() and may be delayed some time in qdisc. When qdisc len reached the limit and returns NET_XMIT_DROP, the skb will be retransmit later in write queue. the skb will be fragmented by tso_fragment(), the limit size that depends on cwnd and mss decrease, the skb's nonlinear data will be split off. The length of the skb cloned by netem will not be updated. When we use virtio_net NIC and invoke skb_to_sgvec(), the BUG_ON trigger. To fix it, netem returns NET_XMIT_SUCCESS to upper stack when it clones a duplicate packet. Fixes: 35d889d1 ("sch_netem: fix skb leak in netem_enqueue()") Signed-off-by: Sheng Lan Reported-by: Qin Ji Suggested-by: Eric Dumazet Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/sched/sch_netem.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 3f4f0b946798..3d5654333d49 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -435,6 +435,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, int nb = 0; int count = 1; int rc = NET_XMIT_SUCCESS; + int rc_drop = NET_XMIT_DROP; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -474,6 +475,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->duplicate = 0; rootq->enqueue(skb2, rootq, to_free); q->duplicate = dupsave; + rc_drop = NET_XMIT_SUCCESS; } /* @@ -486,7 +488,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { segs = netem_segment(skb, sch, to_free); if (!segs) - return NET_XMIT_DROP; + return rc_drop; } else { segs = skb; } @@ -509,8 +511,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, 1<<(prandom_u32() % 8); } - if (unlikely(sch->q.qlen >= sch->limit)) - return qdisc_drop_all(skb, sch, to_free); + if (unlikely(sch->q.qlen >= sch->limit)) { + qdisc_drop_all(skb, sch, to_free); + return rc_drop; + } qdisc_qstats_backlog_inc(sch, skb); -- GitLab From b275f8e6a0096cac11cf697c4e3ad226070264f5 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 22 Feb 2019 15:37:58 +0800 Subject: [PATCH 0056/1128] net: nfc: Fix NULL dereference on nfc_llcp_build_tlv fails [ Upstream commit 58bdd544e2933a21a51eecf17c3f5f94038261b5 ] KASAN report this: BUG: KASAN: null-ptr-deref in nfc_llcp_build_gb+0x37f/0x540 [nfc] Read of size 3 at addr 0000000000000000 by task syz-executor.0/5401 CPU: 0 PID: 5401 Comm: syz-executor.0 Not tainted 5.0.0-rc7+ #45 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xfa/0x1ce lib/dump_stack.c:113 kasan_report+0x171/0x18d mm/kasan/report.c:321 memcpy+0x1f/0x50 mm/kasan/common.c:130 nfc_llcp_build_gb+0x37f/0x540 [nfc] nfc_llcp_register_device+0x6eb/0xb50 [nfc] nfc_register_device+0x50/0x1d0 [nfc] nfcsim_device_new+0x394/0x67d [nfcsim] ? 0xffffffffc1080000 nfcsim_init+0x6b/0x1000 [nfcsim] do_one_initcall+0xfa/0x5ca init/main.c:887 do_init_module+0x204/0x5f6 kernel/module.c:3460 load_module+0x66b2/0x8570 kernel/module.c:3808 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x462e99 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f9cb79dcc58 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462e99 RDX: 0000000000000000 RSI: 0000000020000280 RDI: 0000000000000003 RBP: 00007f9cb79dcc70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f9cb79dd6bc R13: 00000000004bcefb R14: 00000000006f7030 R15: 0000000000000004 nfc_llcp_build_tlv will return NULL on fails, caller should check it, otherwise will trigger a NULL dereference. Reported-by: Hulk Robot Fixes: eda21f16a5ed ("NFC: Set MIU and RW values from CONNECT and CC LLCP frames") Fixes: d646960f7986 ("NFC: Initial LLCP support") Signed-off-by: YueHaibing Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/nfc/llcp_commands.c | 20 ++++++++++++++++++++ net/nfc/llcp_core.c | 24 ++++++++++++++++++++---- 2 files changed, 40 insertions(+), 4 deletions(-) diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 6a196e438b6c..d1fc019e932e 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -419,6 +419,10 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) sock->service_name, sock->service_name_len, &service_name_tlv_length); + if (!service_name_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += service_name_tlv_length; } @@ -429,9 +433,17 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); + if (!miux_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); + if (!rw_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += rw_tlv_length; pr_debug("SKB size %d SN length %zu\n", size, sock->service_name_len); @@ -484,9 +496,17 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); + if (!miux_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); + if (!rw_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += rw_tlv_length; skb = llcp_allocate_pdu(sock, LLCP_PDU_CC, size); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 02eef5cf3cce..7e619ff8a653 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -532,10 +532,10 @@ static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local) static int nfc_llcp_build_gb(struct nfc_llcp_local *local) { - u8 *gb_cur, *version_tlv, version, version_length; - u8 *lto_tlv, lto_length; - u8 *wks_tlv, wks_length; - u8 *miux_tlv, miux_length; + u8 *gb_cur, version, version_length; + u8 lto_length, wks_length, miux_length; + u8 *version_tlv = NULL, *lto_tlv = NULL, + *wks_tlv = NULL, *miux_tlv = NULL; __be16 wks = cpu_to_be16(local->local_wks); u8 gb_len = 0; int ret = 0; @@ -543,17 +543,33 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) version = LLCP_VERSION_11; version_tlv = nfc_llcp_build_tlv(LLCP_TLV_VERSION, &version, 1, &version_length); + if (!version_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += version_length; lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &local->lto, 1, <o_length); + if (!lto_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += lto_length; pr_debug("Local wks 0x%lx\n", local->local_wks); wks_tlv = nfc_llcp_build_tlv(LLCP_TLV_WKS, (u8 *)&wks, 2, &wks_length); + if (!wks_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += wks_length; miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0, &miux_length); + if (!miux_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += miux_length; gb_len += ARRAY_SIZE(llcp_magic); -- GitLab From bf92de28777726d4e95864e5dae7656ab5a4f769 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 26 Feb 2019 19:29:22 +0100 Subject: [PATCH 0057/1128] net: phy: phylink: fix uninitialized variable in phylink_get_mac_state [ Upstream commit d25ed413d5e51644e18f66e34eec049f17a7abcb ] When debugging an issue I found implausible values in state->pause. Reason in that state->pause isn't initialized and later only single bits are changed. Also the struct itself isn't initialized in phylink_resolve(). So better initialize state->pause and other not yet initialized fields. v2: - use right function name in subject v3: - initialize additional fields Fixes: 9525ae83959b ("phylink: add phylink infrastructure") Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/phylink.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index afe335583832..5bfc961e53c9 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -333,6 +333,10 @@ static int phylink_get_mac_state(struct phylink *pl, struct phylink_link_state * linkmode_zero(state->lp_advertising); state->interface = pl->link_config.interface; state->an_enabled = pl->link_config.an_enabled; + state->speed = SPEED_UNKNOWN; + state->duplex = DUPLEX_UNKNOWN; + state->pause = MLO_PAUSE_NONE; + state->an_complete = 0; state->link = 1; return pl->ops->mac_link_state(ndev, state); -- GitLab From 46a5caa79ff73c9403ab37475ef47ed4c027e712 Mon Sep 17 00:00:00 2001 From: Mao Wenan Date: Fri, 1 Mar 2019 23:06:40 +0800 Subject: [PATCH 0058/1128] net: sit: fix memory leak in sit_init_net() [ Upstream commit 07f12b26e21ab359261bf75cfcb424fdc7daeb6d ] If register_netdev() is failed to register sitn->fb_tunnel_dev, it will go to err_reg_dev and forget to free netdev(sitn->fb_tunnel_dev). BUG: memory leak unreferenced object 0xffff888378daad00 (size 512): comm "syz-executor.1", pid 4006, jiffies 4295121142 (age 16.115s) hex dump (first 32 bytes): 00 e6 ed c0 83 88 ff ff 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000d6dcb63e>] kvmalloc include/linux/mm.h:577 [inline] [<00000000d6dcb63e>] kvzalloc include/linux/mm.h:585 [inline] [<00000000d6dcb63e>] netif_alloc_netdev_queues net/core/dev.c:8380 [inline] [<00000000d6dcb63e>] alloc_netdev_mqs+0x600/0xcc0 net/core/dev.c:8970 [<00000000867e172f>] sit_init_net+0x295/0xa40 net/ipv6/sit.c:1848 [<00000000871019fa>] ops_init+0xad/0x3e0 net/core/net_namespace.c:129 [<00000000319507f6>] setup_net+0x2ba/0x690 net/core/net_namespace.c:314 [<0000000087db4f96>] copy_net_ns+0x1dc/0x330 net/core/net_namespace.c:437 [<0000000057efc651>] create_new_namespaces+0x382/0x730 kernel/nsproxy.c:107 [<00000000676f83de>] copy_namespaces+0x2ed/0x3d0 kernel/nsproxy.c:165 [<0000000030b74bac>] copy_process.part.27+0x231e/0x6db0 kernel/fork.c:1919 [<00000000fff78746>] copy_process kernel/fork.c:1713 [inline] [<00000000fff78746>] _do_fork+0x1bc/0xe90 kernel/fork.c:2224 [<000000001c2e0d1c>] do_syscall_64+0xc8/0x580 arch/x86/entry/common.c:290 [<00000000ec48bd44>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<0000000039acff8a>] 0xffffffffffffffff Signed-off-by: Mao Wenan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/sit.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 2e55f9894548..c5b60190b1db 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1856,6 +1856,7 @@ static int __net_init sit_init_net(struct net *net) err_reg_dev: ipip6_dev_free(sitn->fb_tunnel_dev); + free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; } -- GitLab From e5e8350da5b17626d6f73b97157d24c66611d0de Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 21 Feb 2019 14:13:56 -0800 Subject: [PATCH 0059/1128] net: socket: set sock->sk to NULL after calling proto_ops::release() [ Upstream commit ff7b11aa481f682e0e9711abfeb7d03f5cd612bf ] Commit 9060cb719e61 ("net: crypto set sk to NULL when af_alg_release.") fixed a use-after-free in sockfs_setattr() when an AF_ALG socket is closed concurrently with fchownat(). However, it ignored that many other proto_ops::release() methods don't set sock->sk to NULL and therefore allow the same use-after-free: - base_sock_release - bnep_sock_release - cmtp_sock_release - data_sock_release - dn_release - hci_sock_release - hidp_sock_release - iucv_sock_release - l2cap_sock_release - llcp_sock_release - llc_ui_release - rawsock_release - rfcomm_sock_release - sco_sock_release - svc_release - vcc_release - x25_release Rather than fixing all these and relying on every socket type to get this right forever, just make __sock_release() set sock->sk to NULL itself after calling proto_ops::release(). Reproducer that produces the KASAN splat when any of these socket types are configured into the kernel: #include #include #include #include pthread_t t; volatile int fd; void *close_thread(void *arg) { for (;;) { usleep(rand() % 100); close(fd); } } int main() { pthread_create(&t, NULL, close_thread, NULL); for (;;) { fd = socket(rand() % 50, rand() % 11, 0); fchownat(fd, "", 1000, 1000, 0x1000); close(fd); } } Fixes: 86741ec25462 ("net: core: Add a UID field to struct sock.") Signed-off-by: Eric Biggers Acked-by: Cong Wang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/socket.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/socket.c b/net/socket.c index a401578f3f28..6d8f0c248c7e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -600,6 +600,7 @@ static void __sock_release(struct socket *sock, struct inode *inode) if (inode) inode_lock(inode); sock->ops->release(sock); + sock->sk = NULL; if (inode) inode_unlock(inode); sock->ops = NULL; -- GitLab From 03756e820a0213f0d4db77f436878229fce51b2a Mon Sep 17 00:00:00 2001 From: Igor Druzhinin Date: Thu, 28 Feb 2019 14:11:26 +0000 Subject: [PATCH 0060/1128] xen-netback: don't populate the hash cache on XenBus disconnect [ Upstream commit a2288d4e355992d369c50c45d017a85f6061ff71 ] Occasionally, during the disconnection procedure on XenBus which includes hash cache deinitialization there might be some packets still in-flight on other processors. Handling of these packets includes hashing and hash cache population that finally results in hash cache data structure corruption. In order to avoid this we prevent hashing of those packets if there are no queues initialized. In that case RCU protection of queues guards the hash cache as well. Signed-off-by: Igor Druzhinin Reviewed-by: Paul Durrant Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/xen-netback/hash.c | 2 ++ drivers/net/xen-netback/interface.c | 7 +++++++ 2 files changed, 9 insertions(+) diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c index 3b6fb5b3bdb2..6414cc6b9032 100644 --- a/drivers/net/xen-netback/hash.c +++ b/drivers/net/xen-netback/hash.c @@ -435,6 +435,8 @@ void xenvif_init_hash(struct xenvif *vif) if (xenvif_hash_cache_size == 0) return; + BUG_ON(vif->hash.cache.count); + spin_lock_init(&vif->hash.cache.lock); INIT_LIST_HEAD(&vif->hash.cache.list); } diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 4491ca5aee90..d465071656b5 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -153,6 +153,13 @@ static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb, { struct xenvif *vif = netdev_priv(dev); unsigned int size = vif->hash.size; + unsigned int num_queues; + + /* If queues are not set up internally - always return 0 + * as the packet going to be dropped anyway */ + num_queues = READ_ONCE(vif->num_queues); + if (num_queues < 1) + return 0; if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) return fallback(dev, skb) % dev->real_num_tx_queues; -- GitLab From 1902c0cb701cbae2bdc3352ea01bdcf98ada7818 Mon Sep 17 00:00:00 2001 From: Igor Druzhinin Date: Thu, 28 Feb 2019 12:48:03 +0000 Subject: [PATCH 0061/1128] xen-netback: fix occasional leak of grant ref mappings under memory pressure [ Upstream commit 99e87f56b48f490fb16b6e0f74691c1e664dea95 ] Zero-copy callback flag is not yet set on frag list skb at the moment xenvif_handle_frag_list() returns -ENOMEM. This eventually results in leaking grant ref mappings since xenvif_zerocopy_callback() is never called for these fragments. Those eventually build up and cause Xen to kill Dom0 as the slots get reused for new mappings: "d0v0 Attempt to implicitly unmap a granted PTE c010000329fce005" That behavior is observed under certain workloads where sudden spikes of page cache writes coexist with active atomic skb allocations from network traffic. Additionally, rework the logic to deal with frag_list deallocation in a single place. Signed-off-by: Paul Durrant Signed-off-by: Igor Druzhinin Acked-by: Wei Liu Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/xen-netback/netback.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 5042ff8d449a..d09dea77c287 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1074,11 +1074,6 @@ static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *s skb_frag_size_set(&frags[i], len); } - /* Copied all the bits from the frag list -- free it. */ - skb_frag_list_init(skb); - xenvif_skb_zerocopy_prepare(queue, nskb); - kfree_skb(nskb); - /* Release all the original (foreign) frags. */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) skb_frag_unref(skb, f); @@ -1147,6 +1142,8 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) xenvif_fill_frags(queue, skb); if (unlikely(skb_has_frag_list(skb))) { + struct sk_buff *nskb = skb_shinfo(skb)->frag_list; + xenvif_skb_zerocopy_prepare(queue, nskb); if (xenvif_handle_frag_list(queue, skb)) { if (net_ratelimit()) netdev_err(queue->vif->dev, @@ -1155,6 +1152,9 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) kfree_skb(skb); continue; } + /* Copied all the bits from the frag list -- free it. */ + skb_frag_list_init(skb); + kfree_skb(nskb); } skb->dev = queue->vif->dev; -- GitLab From 153100388f39d6dd9f08dc3ba9f00cae00d575e7 Mon Sep 17 00:00:00 2001 From: Nazarov Sergey Date: Mon, 25 Feb 2019 19:24:15 +0300 Subject: [PATCH 0062/1128] net: Add __icmp_send helper. [ Upstream commit 9ef6b42ad6fd7929dd1b6092cb02014e382c6a91 ] Add __icmp_send function having ip_options struct parameter Signed-off-by: Sergey Nazarov Reviewed-by: Paul Moore Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/icmp.h | 9 ++++++++- net/ipv4/icmp.c | 7 ++++--- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/include/net/icmp.h b/include/net/icmp.h index 3ef2743a8eec..8665bf24e3b7 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -22,6 +22,7 @@ #include #include +#include struct icmp_err { int errno; @@ -39,7 +40,13 @@ struct net_proto_family; struct sk_buff; struct net; -void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info); +void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, + const struct ip_options *opt); +static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) +{ + __icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt); +} + int icmp_rcv(struct sk_buff *skb); void icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 3c1570d3e22f..f9d790b058d2 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -573,7 +573,8 @@ static struct rtable *icmp_route_lookup(struct net *net, * MUST reply to only the first fragment. */ -void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) +void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, + const struct ip_options *opt) { struct iphdr *iph; int room; @@ -694,7 +695,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); - if (ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in)) + if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt)) goto out_unlock; @@ -747,7 +748,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) local_bh_enable(); out:; } -EXPORT_SYMBOL(icmp_send); +EXPORT_SYMBOL(__icmp_send); static void icmp_socket_deliver(struct sk_buff *skb, u32 info) -- GitLab From 980a71678eef1f035fa04ba211c98110515bc37a Mon Sep 17 00:00:00 2001 From: Nazarov Sergey Date: Mon, 25 Feb 2019 19:27:15 +0300 Subject: [PATCH 0063/1128] net: avoid use IPCB in cipso_v4_error [ Upstream commit 3da1ed7ac398f34fff1694017a07054d69c5f5c5 ] Extract IP options in cipso_v4_error and use __icmp_send. Signed-off-by: Sergey Nazarov Acked-by: Paul Moore Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/ip.h | 2 ++ net/ipv4/cipso_ipv4.c | 17 +++++++++++++++-- net/ipv4/ip_options.c | 22 +++++++++++++++++----- 3 files changed, 34 insertions(+), 7 deletions(-) diff --git a/include/net/ip.h b/include/net/ip.h index 7c430343176a..80575db4e304 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -593,6 +593,8 @@ static inline int ip_options_echo(struct net *net, struct ip_options *dopt, } void ip_options_fragment(struct sk_buff *skb); +int __ip_options_compile(struct net *net, struct ip_options *opt, + struct sk_buff *skb, __be32 *info); int ip_options_compile(struct net *net, struct ip_options *opt, struct sk_buff *skb); int ip_options_get(struct net *net, struct ip_options_rcu **optp, diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index f4b83de2263e..f0165c5f376b 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1736,13 +1736,26 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) */ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { + unsigned char optbuf[sizeof(struct ip_options) + 40]; + struct ip_options *opt = (struct ip_options *)optbuf; + if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; + /* + * We might be called above the IP layer, + * so we can not use icmp_send and IPCB here. + */ + + memset(opt, 0, sizeof(struct ip_options)); + opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); + if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + return; + if (gateway) - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, opt); else - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, opt); } /** diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ed194d46c00e..32a35043c9f5 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -251,8 +251,9 @@ static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb) * If opt == NULL, then skb->data should point to IP header. */ -int ip_options_compile(struct net *net, - struct ip_options *opt, struct sk_buff *skb) +int __ip_options_compile(struct net *net, + struct ip_options *opt, struct sk_buff *skb, + __be32 *info) { __be32 spec_dst = htonl(INADDR_ANY); unsigned char *pp_ptr = NULL; @@ -468,11 +469,22 @@ int ip_options_compile(struct net *net, return 0; error: - if (skb) { - icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((pp_ptr-iph)<<24)); - } + if (info) + *info = htonl((pp_ptr-iph)<<24); return -EINVAL; } + +int ip_options_compile(struct net *net, + struct ip_options *opt, struct sk_buff *skb) +{ + int ret; + __be32 info; + + ret = __ip_options_compile(net, opt, skb, &info); + if (ret != 0 && skb) + icmp_send(skb, ICMP_PARAMETERPROB, 0, info); + return ret; +} EXPORT_SYMBOL(ip_options_compile); /* -- GitLab From 987e2bfbf8171048db1b133b4294c5ce6deebdfe Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 26 Feb 2019 09:00:02 -0800 Subject: [PATCH 0064/1128] ipv4: Return error for RTA_VIA attribute [ Upstream commit b6e9e5df4ecf100f6a10ab2ade8e46d47a4b9779 ] IPv4 currently does not support nexthops outside of the AF_INET family. Specifically, it does not handle RTA_VIA attribute. If it is passed in a route add request, the actual route added only uses the device which is clearly not what the user intended: $ ip ro add 172.16.1.0/24 via inet6 2001:db8:1::1 dev eth0 $ ip ro ls ... 172.16.1.0/24 dev eth0 Catch this and fail the route add: $ ip ro add 172.16.1.0/24 via inet6 2001:db8:1::1 dev eth0 Error: IPv4 does not support RTA_VIA attribute. Fixes: 03c0566542f4c ("mpls: Netlink commands to add, remove, and dump routes") Signed-off-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/fib_frontend.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b5317b2b191d..ff499000f6cd 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -675,6 +675,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, case RTA_GATEWAY: cfg->fc_gw = nla_get_be32(attr); break; + case RTA_VIA: + NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute"); + err = -EINVAL; + goto errout; case RTA_PRIORITY: cfg->fc_priority = nla_get_u32(attr); break; -- GitLab From 87964ee15964dd576c85abce4ec69530cc25acb3 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 26 Feb 2019 09:00:03 -0800 Subject: [PATCH 0065/1128] ipv6: Return error for RTA_VIA attribute [ Upstream commit e3818541b49fb88650ba339d33cc53e4095da5b3 ] IPv6 currently does not support nexthops outside of the AF_INET6 family. Specifically, it does not handle RTA_VIA attribute. If it is passed in a route add request, the actual route added only uses the device which is clearly not what the user intended: $ ip -6 ro add 2001:db8:2::/64 via inet 172.16.1.1 dev eth0 $ ip ro ls ... 2001:db8:2::/64 dev eth0 metric 1024 pref medium Catch this and fail the route add: $ ip -6 ro add 2001:db8:2::/64 via inet 172.16.1.1 dev eth0 Error: IPv6 does not support RTA_VIA attribute. Fixes: 03c0566542f4c ("mpls: Netlink commands to add, remove, and dump routes") Signed-off-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/route.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 74dd35d6567c..fafecdc06900 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3024,6 +3024,10 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]); cfg->fc_flags |= RTF_GATEWAY; } + if (tb[RTA_VIA]) { + NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute"); + goto errout; + } if (tb[RTA_DST]) { int plen = (rtm->rtm_dst_len + 7) >> 3; -- GitLab From a9494400f8c1ea8d2e760cec1be44dfe225a607b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 26 Feb 2019 09:00:04 -0800 Subject: [PATCH 0066/1128] mpls: Return error for RTA_GATEWAY attribute [ Upstream commit be48220edd48ca0d569782992840488a52373a24 ] MPLS does not support nexthops with an MPLS address family. Specifically, it does not handle RTA_GATEWAY attribute. Make it clear by returning an error. Fixes: 03c0566542f4c ("mpls: Netlink commands to add, remove, and dump routes") Signed-off-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/mpls/af_mpls.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index aee385eb72e7..9a153f64b8d7 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1787,6 +1787,9 @@ static int rtm_to_route_config(struct sk_buff *skb, goto errout; break; } + case RTA_GATEWAY: + NL_SET_ERR_MSG(extack, "MPLS does not support RTA_GATEWAY attribute"); + goto errout; case RTA_VIA: { if (nla_get_via(nla, &cfg->rc_via_alen, -- GitLab From 32869c80859a6fd11b7751e2dc61a04f6feaee9b Mon Sep 17 00:00:00 2001 From: Timur Celik Date: Sat, 23 Feb 2019 12:53:13 +0100 Subject: [PATCH 0067/1128] tun: fix blocking read [ Upstream commit 71828b2240692cec0e68b8d867bc00e1745e7fae ] This patch moves setting of the current state into the loop. Otherwise the task may end up in a busy wait loop if none of the break conditions are met. Signed-off-by: Timur Celik Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/tun.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2956bb6cda72..a87450df3230 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1714,9 +1714,9 @@ static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock, } add_wait_queue(&tfile->wq.wait, &wait); - current->state = TASK_INTERRUPTIBLE; while (1) { + set_current_state(TASK_INTERRUPTIBLE); skb = skb_array_consume(&tfile->tx_array); if (skb) break; @@ -1732,7 +1732,7 @@ static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock, schedule(); } - current->state = TASK_RUNNING; + set_current_state(TASK_RUNNING); remove_wait_queue(&tfile->wq.wait, &wait); out: -- GitLab From a7e2560faea59f89d70123bba4c82cdd162f7c94 Mon Sep 17 00:00:00 2001 From: Timur Celik Date: Mon, 25 Feb 2019 21:13:13 +0100 Subject: [PATCH 0068/1128] tun: remove unnecessary memory barrier [ Upstream commit ecef67cb10db7b83b3b71c61dbb29aa070ab0112 ] Replace set_current_state with __set_current_state since no memory barrier is needed at this point. Signed-off-by: Timur Celik Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/tun.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a87450df3230..4227ee33ef19 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1732,7 +1732,7 @@ static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock, schedule(); } - set_current_state(TASK_RUNNING); + __set_current_state(TASK_RUNNING); remove_wait_queue(&tfile->wq.wait, &wait); out: -- GitLab From b9e298f864a3f066914543213c9c5cff3fd69aa2 Mon Sep 17 00:00:00 2001 From: Rajasingh Thavamani Date: Wed, 27 Feb 2019 17:43:19 +0530 Subject: [PATCH 0069/1128] net: phy: Micrel KSZ8061: link failure after cable connect [ Upstream commit 232ba3a51cc224b339c7114888ed7f0d4d95695e ] With Micrel KSZ8061 PHY, the link may occasionally not come up after Ethernet cable connect. The vendor's (Microchip, former Micrel) errata sheet 80000688A.pdf descripes the problem and possible workarounds in detail, see below. The batch implements workaround 1, which permanently fixes the issue. DESCRIPTION Link-up may not occur properly when the Ethernet cable is initially connected. This issue occurs more commonly when the cable is connected slowly, but it may occur any time a cable is connected. This issue occurs in the auto-negotiation circuit, and will not occur if auto-negotiation is disabled (which requires that the two link partners be set to the same speed and duplex). END USER IMPLICATIONS When this issue occurs, link is not established. Subsequent cable plug/unplaug cycle will not correct the issue. WORk AROUND There are four approaches to work around this issue: 1. This issue can be prevented by setting bit 15 in MMD device address 1, register 2, prior to connecting the cable or prior to setting the Restart Auto-negotiation bit in register 0h. The MMD registers are accessed via the indirect access registers Dh and Eh, or via the Micrel EthUtil utility as shown here: . if using the EthUtil utility (usually with a Micrel KSZ8061 Evaluation Board), type the following commands: > address 1 > mmd 1 > iw 2 b61a . Alternatively, write the following registers to write to the indirect MMD register: Write register Dh, data 0001h Write register Eh, data 0002h Write register Dh, data 4001h Write register Eh, data B61Ah 2. The issue can be avoided by disabling auto-negotiation in the KSZ8061, either by the strapping option, or by clearing bit 12 in register 0h. Care must be taken to ensure that the KSZ8061 and the link partner will link with the same speed and duplex. Note that the KSZ8061 defaults to full-duplex when auto-negotiation is off, but other devices may default to half-duplex in the event of failed auto-negotiation. 3. The issue can be avoided by connecting the cable prior to powering-up or resetting the KSZ8061, and leaving it plugged in thereafter. 4. If the above measures are not taken and the problem occurs, link can be recovered by setting the Restart Auto-Negotiation bit in register 0h, or by resetting or power cycling the device. Reset may be either hardware reset or software reset (register 0h, bit 15). PLAN This errata will not be corrected in the future revision. Fixes: 7ab59dc15e2f ("drivers/net/phy/micrel_phy: Add support for new PHYs") Signed-off-by: Alexander Onnasch Signed-off-by: Rajasingh Thavamani Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/micrel.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 6c45ff650ec7..eb85cf4a381a 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -339,6 +339,17 @@ static int ksz8041_config_aneg(struct phy_device *phydev) return genphy_config_aneg(phydev); } +static int ksz8061_config_init(struct phy_device *phydev) +{ + int ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A); + if (ret) + return ret; + + return kszphy_config_init(phydev); +} + static int ksz9021_load_values_from_of(struct phy_device *phydev, const struct device_node *of_node, u16 reg, @@ -938,7 +949,7 @@ static struct phy_driver ksphy_driver[] = { .phy_id_mask = MICREL_PHY_ID_MASK, .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT, - .config_init = kszphy_config_init, + .config_init = ksz8061_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, -- GitLab From e7c4193e2a1d59afb622a83f605e7c4b58d0fa33 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 1 Mar 2019 23:43:39 +0100 Subject: [PATCH 0070/1128] net: dsa: mv88e6xxx: Fix statistics on mv88e6161 [ Upstream commit a6da21bb0eae459a375d5bd48baed821d14301d0 ] Despite what the datesheet says, the silicon implements the older way of snapshoting the statistics. Change the op. Reported-by: Chris.Healy@zii.aero Tested-by: Chris.Healy@zii.aero Fixes: 0ac64c394900 ("net: dsa: mv88e6xxx: mv88e6161 uses mv88e6320 stats snapshot") Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 45ccd98f6265..4fbc75b73433 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2569,7 +2569,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .port_pause_limit = mv88e6097_port_pause_limit, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, - .stats_snapshot = mv88e6320_g1_stats_snapshot, + .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, .stats_get_stats = mv88e6095_stats_get_stats, -- GitLab From 9e1176f21da05751722d8ee0345697251a739320 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 20 Nov 2018 11:00:18 +0800 Subject: [PATCH 0071/1128] x86/CPU/AMD: Set the CPB bit unconditionally on F17h commit 0237199186e7a4aa5310741f0a6498a20c820fd7 upstream. Some F17h models do not have CPB set in CPUID even though the CPU supports it. Set the feature bit unconditionally on all F17h. [ bp: Rewrite commit message and patch. ] Signed-off-by: Jiaxun Yang Signed-off-by: Borislav Petkov Acked-by: Tom Lendacky Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Sherry Hurwitz Cc: Suravee Suthikulpanit Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/20181120030018.5185-1-jiaxun.yang@flygoat.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/amd.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7e03515662c0..ecf82859f1c0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -791,11 +791,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c) static void init_amd_zn(struct cpuinfo_x86 *c) { set_cpu_cap(c, X86_FEATURE_ZEN); - /* - * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects - * all up to and including B1. - */ - if (c->x86_model <= 1 && c->x86_stepping <= 1) + + /* Fix erratum 1076: CPB feature bit not being set in CPUID. */ + if (!cpu_has(c, X86_FEATURE_CPB)) set_cpu_cap(c, X86_FEATURE_CPB); } -- GitLab From 5838a070d1177dc02d7acb553bc02e6f018e024a Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 9 Jan 2019 16:05:10 -0600 Subject: [PATCH 0072/1128] applicom: Fix potential Spectre v1 vulnerabilities commit d7ac3c6ef5d8ce14b6381d52eb7adafdd6c8bb3c upstream. IndexCard is indirectly controlled by user-space, hence leading to a potential exploitation of the Spectre variant 1 vulnerability. This issue was detected with the help of Smatch: drivers/char/applicom.c:418 ac_write() warn: potential spectre issue 'apbs' [r] drivers/char/applicom.c:728 ac_ioctl() warn: potential spectre issue 'apbs' [r] (local cap) Fix this by sanitizing IndexCard before using it to index apbs. Notice that given that speculation windows are large, the policy is to kill the speculation on the first load and not worry if it can be completed with a dependent load/store [1]. [1] https://lore.kernel.org/lkml/20180423164740.GY17484@dhcp22.suse.cz/ Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Signed-off-by: Greg Kroah-Hartman --- drivers/char/applicom.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c index c0a5b1f3a986..4ccc39e00ced 100644 --- a/drivers/char/applicom.c +++ b/drivers/char/applicom.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -386,7 +387,11 @@ static ssize_t ac_write(struct file *file, const char __user *buf, size_t count, TicCard = st_loc.tic_des_from_pc; /* tic number to send */ IndexCard = NumCard - 1; - if((NumCard < 1) || (NumCard > MAX_BOARD) || !apbs[IndexCard].RamIO) + if (IndexCard >= MAX_BOARD) + return -EINVAL; + IndexCard = array_index_nospec(IndexCard, MAX_BOARD); + + if (!apbs[IndexCard].RamIO) return -EINVAL; #ifdef DEBUG @@ -697,6 +702,7 @@ static long ac_ioctl(struct file *file, unsigned int cmd, unsigned long arg) unsigned char IndexCard; void __iomem *pmem; int ret = 0; + static int warncount = 10; volatile unsigned char byte_reset_it; struct st_ram_io *adgl; void __user *argp = (void __user *)arg; @@ -711,16 +717,12 @@ static long ac_ioctl(struct file *file, unsigned int cmd, unsigned long arg) mutex_lock(&ac_mutex); IndexCard = adgl->num_card-1; - if(cmd != 6 && ((IndexCard >= MAX_BOARD) || !apbs[IndexCard].RamIO)) { - static int warncount = 10; - if (warncount) { - printk( KERN_WARNING "APPLICOM driver IOCTL, bad board number %d\n",(int)IndexCard+1); - warncount--; - } - kfree(adgl); - mutex_unlock(&ac_mutex); - return -EINVAL; - } + if (cmd != 6 && IndexCard >= MAX_BOARD) + goto err; + IndexCard = array_index_nospec(IndexCard, MAX_BOARD); + + if (cmd != 6 && !apbs[IndexCard].RamIO) + goto err; switch (cmd) { @@ -838,5 +840,16 @@ static long ac_ioctl(struct file *file, unsigned int cmd, unsigned long arg) kfree(adgl); mutex_unlock(&ac_mutex); return 0; + +err: + if (warncount) { + pr_warn("APPLICOM driver IOCTL, bad board number %d\n", + (int)IndexCard + 1); + warncount--; + } + kfree(adgl); + mutex_unlock(&ac_mutex); + return -EINVAL; + } -- GitLab From 442d1144f91508471a82e77c01fca193d1e5bc0c Mon Sep 17 00:00:00 2001 From: Liu Xiang Date: Sat, 16 Feb 2019 17:12:24 +0800 Subject: [PATCH 0073/1128] MIPS: irq: Allocate accurate order pages for irq stack commit 72faa7a773ca59336f3c889e878de81445c5a85c upstream. The irq_pages is the number of pages for irq stack, but not the order which is needed by __get_free_pages(). We can use get_order() to calculate the accurate order. Signed-off-by: Liu Xiang Signed-off-by: Paul Burton Fixes: fe8bd18ffea5 ("MIPS: Introduce irq_stack") Cc: linux-mips@vger.kernel.org Cc: stable@vger.kernel.org # v4.11+ Signed-off-by: Greg Kroah-Hartman --- arch/mips/kernel/irq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c index ba150c755fcc..85b6c60f285d 100644 --- a/arch/mips/kernel/irq.c +++ b/arch/mips/kernel/irq.c @@ -52,6 +52,7 @@ asmlinkage void spurious_interrupt(void) void __init init_IRQ(void) { int i; + unsigned int order = get_order(IRQ_STACK_SIZE); for (i = 0; i < NR_IRQS; i++) irq_set_noprobe(i); @@ -62,8 +63,7 @@ void __init init_IRQ(void) arch_init_irq(); for_each_possible_cpu(i) { - int irq_pages = IRQ_STACK_SIZE / PAGE_SIZE; - void *s = (void *)__get_free_pages(GFP_KERNEL, irq_pages); + void *s = (void *)__get_free_pages(GFP_KERNEL, order); irq_stack[i] = s; pr_debug("CPU%d IRQ stack at 0x%p - 0x%p\n", i, -- GitLab From af46f4c0372aea3813afa6f2d9debb39346655c3 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Thu, 28 Feb 2019 16:22:02 -0800 Subject: [PATCH 0074/1128] hugetlbfs: fix races and page leaks during migration commit cb6acd01e2e43fd8bad11155752b7699c3d0fb76 upstream. hugetlb pages should only be migrated if they are 'active'. The routines set/clear_page_huge_active() modify the active state of hugetlb pages. When a new hugetlb page is allocated at fault time, set_page_huge_active is called before the page is locked. Therefore, another thread could race and migrate the page while it is being added to page table by the fault code. This race is somewhat hard to trigger, but can be seen by strategically adding udelay to simulate worst case scheduling behavior. Depending on 'how' the code races, various BUG()s could be triggered. To address this issue, simply delay the set_page_huge_active call until after the page is successfully added to the page table. Hugetlb pages can also be leaked at migration time if the pages are associated with a file in an explicitly mounted hugetlbfs filesystem. For example, consider a two node system with 4GB worth of huge pages available. A program mmaps a 2G file in a hugetlbfs filesystem. It then migrates the pages associated with the file from one node to another. When the program exits, huge page counts are as follows: node0 1024 free_hugepages 1024 nr_hugepages node1 0 free_hugepages 1024 nr_hugepages Filesystem Size Used Avail Use% Mounted on nodev 4.0G 2.0G 2.0G 50% /var/opt/hugepool That is as expected. 2G of huge pages are taken from the free_hugepages counts, and 2G is the size of the file in the explicitly mounted filesystem. If the file is then removed, the counts become: node0 1024 free_hugepages 1024 nr_hugepages node1 1024 free_hugepages 1024 nr_hugepages Filesystem Size Used Avail Use% Mounted on nodev 4.0G 2.0G 2.0G 50% /var/opt/hugepool Note that the filesystem still shows 2G of pages used, while there actually are no huge pages in use. The only way to 'fix' the filesystem accounting is to unmount the filesystem If a hugetlb page is associated with an explicitly mounted filesystem, this information in contained in the page_private field. At migration time, this information is not preserved. To fix, simply transfer page_private from old to new page at migration time if necessary. There is a related race with removing a huge page from a file and migration. When a huge page is removed from the pagecache, the page_mapping() field is cleared, yet page_private remains set until the page is actually freed by free_huge_page(). A page could be migrated while in this state. However, since page_mapping() is not set the hugetlbfs specific routine to transfer page_private is not called and we leak the page count in the filesystem. To fix that, check for this condition before migrating a huge page. If the condition is detected, return EBUSY for the page. Link: http://lkml.kernel.org/r/74510272-7319-7372-9ea6-ec914734c179@oracle.com Link: http://lkml.kernel.org/r/20190212221400.3512-1-mike.kravetz@oracle.com Fixes: bcc54222309c ("mm: hugetlb: introduce page_huge_active") Signed-off-by: Mike Kravetz Reviewed-by: Naoya Horiguchi Cc: Michal Hocko Cc: Andrea Arcangeli Cc: "Kirill A . Shutemov" Cc: Mel Gorman Cc: Davidlohr Bueso Cc: [mike.kravetz@oracle.com: v2] Link: http://lkml.kernel.org/r/7534d322-d782-8ac6-1c8d-a8dc380eb3ab@oracle.com [mike.kravetz@oracle.com: update comment and changelog] Link: http://lkml.kernel.org/r/420bcfd6-158b-38e4-98da-26d0cd85bd01@oracle.com Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/hugetlbfs/inode.c | 12 ++++++++++++ mm/hugetlb.c | 16 +++++++++++++--- mm/migrate.c | 11 +++++++++++ 3 files changed, 36 insertions(+), 3 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 2a6ed036d207..eb6f3de29f69 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -845,6 +845,18 @@ static int hugetlbfs_migrate_page(struct address_space *mapping, rc = migrate_huge_page_move_mapping(mapping, newpage, page); if (rc != MIGRATEPAGE_SUCCESS) return rc; + + /* + * page_private is subpool pointer in hugetlb pages. Transfer to + * new page. PagePrivate is not associated with page_private for + * hugetlb pages and can not be set here as only page_huge_active + * pages can be migrated. + */ + if (page_private(page)) { + set_page_private(newpage, page_private(page)); + set_page_private(page, 0); + } + if (mode != MIGRATE_SYNC_NO_COPY) migrate_page_copy(newpage, page); else diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 224cdd953a79..7f75bd2fb8a7 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3577,7 +3577,6 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, copy_user_huge_page(new_page, old_page, address, vma, pages_per_huge_page(h)); __SetPageUptodate(new_page); - set_page_huge_active(new_page); mmun_start = address & huge_page_mask(h); mmun_end = mmun_start + huge_page_size(h); @@ -3600,6 +3599,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, make_huge_pte(vma, new_page, 1)); page_remove_rmap(old_page, true); hugepage_add_new_anon_rmap(new_page, vma, address); + set_page_huge_active(new_page); /* Make the old page be freed below */ new_page = old_page; } @@ -3682,6 +3682,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page; pte_t new_pte; spinlock_t *ptl; + bool new_page = false; /* * Currently, we are forced to kill the process in the event the @@ -3747,7 +3748,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, } clear_huge_page(page, address, pages_per_huge_page(h)); __SetPageUptodate(page); - set_page_huge_active(page); + new_page = true; if (vma->vm_flags & VM_MAYSHARE) { int err = huge_add_to_page_cache(page, mapping, idx); @@ -3818,6 +3819,15 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, } spin_unlock(ptl); + + /* + * Only make newly allocated pages active. Existing pages found + * in the pagecache could be !page_huge_active() if they have been + * isolated for migration. + */ + if (new_page) + set_page_huge_active(page); + unlock_page(page); out: return ret; @@ -4053,7 +4063,6 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, * the set_pte_at() write. */ __SetPageUptodate(page); - set_page_huge_active(page); mapping = dst_vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, dst_vma, dst_addr); @@ -4121,6 +4130,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); + set_page_huge_active(page); if (vm_shared) unlock_page(page); ret = 0; diff --git a/mm/migrate.c b/mm/migrate.c index 8c57cdd77ba5..877269339fa7 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1303,6 +1303,16 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, lock_page(hpage); } + /* + * Check for pages which are in the process of being freed. Without + * page_mapping() set, hugetlbfs specific move page routine will not + * be called and we could leak usage counts for subpools. + */ + if (page_private(hpage) && !page_mapping(hpage)) { + rc = -EBUSY; + goto out_unlock; + } + if (PageAnon(hpage)) anon_vma = page_get_anon_vma(hpage); @@ -1334,6 +1344,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, set_page_owner_migrate_reason(new_hpage, reason); } +out_unlock: unlock_page(hpage); out: if (rc != -EAGAIN) -- GitLab From 1b0322ebab523163f6b1ca189191c125bf58ebbc Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 2 Jan 2019 01:08:32 -0800 Subject: [PATCH 0075/1128] xtensa: fix get_wchan commit d90b88fd3653f1fb66ecc6571b860d5a5749fa56 upstream. Stack unwinding is implemented incorrectly in xtensa get_wchan: instead of extracting a0 and a1 registers from the spill location under the stack pointer it extracts a word pointed to by the stack pointer and subtracts 4 or 3 from it. Cc: stable@vger.kernel.org Signed-off-by: Max Filippov Signed-off-by: Greg Kroah-Hartman --- arch/xtensa/kernel/process.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index f1c46bc5d465..e48a2137e87a 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -314,8 +314,8 @@ unsigned long get_wchan(struct task_struct *p) /* Stack layout: sp-4: ra, sp-3: sp' */ - pc = MAKE_PC_FROM_RA(*(unsigned long*)sp - 4, sp); - sp = *(unsigned long *)sp - 3; + pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), sp); + sp = SPILL_SLOT(sp, 1); } while (count++ < 16); return 0; } -- GitLab From 82c73d482c746a95f5e76246bda842fc00d2469f Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Wed, 2 Jan 2019 16:11:20 -0800 Subject: [PATCH 0076/1128] Bluetooth: Fix locking in bt_accept_enqueue() for BH context commit c4f5627f7eeecde1bb6b646d8c0907b96dc2b2a6 upstream. With commit e16337622016 ("Bluetooth: Handle bt_accept_enqueue() socket atomically") lock_sock[_nested]() is used to acquire the socket lock before manipulating the socket. lock_sock[_nested]() may block, which is problematic since bt_accept_enqueue() can be called in bottom half context (e.g. from rfcomm_connect_ind()): [] __might_sleep+0x4c/0x80 [] lock_sock_nested+0x24/0x58 [] bt_accept_enqueue+0x48/0xd4 [bluetooth] [] rfcomm_connect_ind+0x190/0x218 [rfcomm] Add a parameter to bt_accept_enqueue() to indicate whether the function is called from BH context, and acquire the socket lock with bh_lock_sock_nested() if that's the case. Also adapt all callers of bt_accept_enqueue() to pass the new parameter: - l2cap_sock_new_connection_cb() - uses lock_sock() to lock the parent socket => process context - rfcomm_connect_ind() - acquires the parent socket lock with bh_lock_sock() => BH context - __sco_chan_add() - called from sco_chan_add(), which is called from sco_connect(). parent is NULL, hence bt_accept_enqueue() isn't called in this code path and we can ignore it - also called from sco_conn_ready(). uses bh_lock_sock() to acquire the parent lock => BH context Fixes: e16337622016 ("Bluetooth: Handle bt_accept_enqueue() socket atomically") Signed-off-by: Matthias Kaehlcke Reviewed-by: Douglas Anderson Signed-off-by: Marcel Holtmann Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- include/net/bluetooth/bluetooth.h | 2 +- net/bluetooth/af_bluetooth.c | 16 +++++++++++++--- net/bluetooth/l2cap_sock.c | 2 +- net/bluetooth/rfcomm/sock.c | 2 +- net/bluetooth/sco.c | 2 +- 5 files changed, 17 insertions(+), 7 deletions(-) diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 020142bb9735..2e1d36b33db7 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -273,7 +273,7 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo); int bt_sock_wait_ready(struct sock *sk, unsigned long flags); -void bt_accept_enqueue(struct sock *parent, struct sock *sk); +void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh); void bt_accept_unlink(struct sock *sk); struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock); diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 583951e82cee..b216e697deac 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -154,15 +154,25 @@ void bt_sock_unlink(struct bt_sock_list *l, struct sock *sk) } EXPORT_SYMBOL(bt_sock_unlink); -void bt_accept_enqueue(struct sock *parent, struct sock *sk) +void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) { BT_DBG("parent %p, sk %p", parent, sk); sock_hold(sk); - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); + + if (bh) + bh_lock_sock_nested(sk); + else + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); + list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q); bt_sk(sk)->parent = parent; - release_sock(sk); + + if (bh) + bh_unlock_sock(sk); + else + release_sock(sk); + parent->sk_ack_backlog++; } EXPORT_SYMBOL(bt_accept_enqueue); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 67a8642f57ea..8c329c549ea6 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1253,7 +1253,7 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) l2cap_sock_init(sk, parent); - bt_accept_enqueue(parent, sk); + bt_accept_enqueue(parent, sk, false); release_sock(parent); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 1aaccf637479..8fcd9130439d 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -988,7 +988,7 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * rfcomm_pi(sk)->channel = channel; sk->sk_state = BT_CONFIG; - bt_accept_enqueue(parent, sk); + bt_accept_enqueue(parent, sk, true); /* Accept connection and return socket DLC */ *d = rfcomm_pi(sk)->dlc; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 81fe3949c158..2d23b29ce00d 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -193,7 +193,7 @@ static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, conn->sk = sk; if (parent) - bt_accept_enqueue(parent, sk); + bt_accept_enqueue(parent, sk, true); } static int sco_chan_add(struct sco_conn *conn, struct sock *sk, -- GitLab From 069fb92ea221c72bd75f4863b3540420082f32ba Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 19 Feb 2019 10:10:38 +0800 Subject: [PATCH 0077/1128] exec: Fix mem leak in kernel_read_file commit f612acfae86af7ecad754ae6a46019be9da05b8e upstream. syzkaller report this: BUG: memory leak unreferenced object 0xffffc9000488d000 (size 9195520): comm "syz-executor.0", pid 2752, jiffies 4294787496 (age 18.757s) hex dump (first 32 bytes): ff ff ff ff ff ff ff ff a8 00 00 00 01 00 00 00 ................ 02 00 00 00 00 00 00 00 80 a1 7a c1 ff ff ff ff ..........z..... backtrace: [<000000000863775c>] __vmalloc_node mm/vmalloc.c:1795 [inline] [<000000000863775c>] __vmalloc_node_flags mm/vmalloc.c:1809 [inline] [<000000000863775c>] vmalloc+0x8c/0xb0 mm/vmalloc.c:1831 [<000000003f668111>] kernel_read_file+0x58f/0x7d0 fs/exec.c:924 [<000000002385813f>] kernel_read_file_from_fd+0x49/0x80 fs/exec.c:993 [<0000000011953ff1>] __do_sys_finit_module+0x13b/0x2a0 kernel/module.c:3895 [<000000006f58491f>] do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 [<00000000ee78baf4>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<00000000241f889b>] 0xffffffffffffffff It should goto 'out_free' lable to free allocated buf while kernel_read fails. Fixes: 39d637af5aa7 ("vfs: forbid write access when reading a file into memory") Signed-off-by: YueHaibing Signed-off-by: Al Viro Cc: Thibaut Sautereau Signed-off-by: Greg Kroah-Hartman --- fs/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/exec.c b/fs/exec.c index 0da4d748b4e6..0936b5a8199a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -925,7 +925,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size, bytes = kernel_read(file, *buf + pos, i_size - pos, &pos); if (bytes < 0) { ret = bytes; - goto out; + goto out_free; } if (bytes == 0) -- GitLab From 4d00335342d0d3bd2f02137595845b7438af43b4 Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Thu, 14 Feb 2019 22:57:41 +0100 Subject: [PATCH 0078/1128] scsi: core: reset host byte in DID_NEXUS_FAILURE case commit 4a067cf823d9d8e50d41cfb618011c0d4a969c72 upstream. Up to 4.12, __scsi_error_from_host_byte() would reset the host byte to DID_OK for various cases including DID_NEXUS_FAILURE. Commit 2a842acab109 ("block: introduce new block status code type") replaced this function with scsi_result_to_blk_status() and removed the host-byte resetting code for the DID_NEXUS_FAILURE case. As the line set_host_byte(cmd, DID_OK) was preserved for the other cases, I suppose this was an editing mistake. The fact that the host byte remains set after 4.13 is causing problems with the sg_persist tool, which now returns success rather then exit status 24 when a RESERVATION CONFLICT error is encountered. Fixes: 2a842acab109 "block: introduce new block status code type" Signed-off-by: Martin Wilck Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/scsi_lib.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 7f505c027ce7..37d366696d21 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -734,6 +734,7 @@ static blk_status_t __scsi_error_from_host_byte(struct scsi_cmnd *cmd, set_host_byte(cmd, DID_OK); return BLK_STS_TARGET; case DID_NEXUS_FAILURE: + set_host_byte(cmd, DID_OK); return BLK_STS_NEXUS; case DID_ALLOC_FAILURE: set_host_byte(cmd, DID_OK); -- GitLab From aa4ba765e0903926de64b359e8653bfd29a3c353 Mon Sep 17 00:00:00 2001 From: Alistair Strachan Date: Tue, 18 Dec 2018 20:32:48 -0500 Subject: [PATCH 0079/1128] media: uvcvideo: Fix 'type' check leading to overflow commit 47bb117911b051bbc90764a8bff96543cbd2005f upstream. When initially testing the Camera Terminal Descriptor wTerminalType field (buffer[4]), no mask is used. Later in the function, the MSB is overloaded to store the descriptor subtype, and so a mask of 0x7fff is used to check the type. If a descriptor is specially crafted to set this overloaded bit in the original wTerminalType field, the initial type check will fail (falling through, without adjusting the buffer size), but the later type checks will pass, assuming the buffer has been made suitably large, causing an overflow. Avoid this problem by checking for the MSB in the wTerminalType field. If the bit is set, assume the descriptor is bad, and abort parsing it. Originally reported here: https://groups.google.com/forum/#!topic/syzkaller/Ot1fOE6v1d8 A similar (non-compiling) patch was provided at that time. Reported-by: syzbot Signed-off-by: Alistair Strachan Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/uvc/uvc_driver.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 064d88299adc..c0176f5d8200 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -1054,11 +1054,19 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return -EINVAL; } - /* Make sure the terminal type MSB is not null, otherwise it - * could be confused with a unit. + /* + * Reject invalid terminal types that would cause issues: + * + * - The high byte must be non-zero, otherwise it would be + * confused with a unit. + * + * - Bit 15 must be 0, as we use it internally as a terminal + * direction flag. + * + * Other unknown types are accepted. */ type = get_unaligned_le16(&buffer[4]); - if ((type & 0xff00) == 0) { + if ((type & 0x7f00) == 0 || (type & 0x8000) != 0) { uvc_trace(UVC_TRACE_DESCR, "device %d videocontrol " "interface %d INPUT_TERMINAL %d has invalid " "type 0x%04x, skipping\n", udev->devnum, -- GitLab From 61a2e1118c8a629c463e86a64ddb8d5bf5252b07 Mon Sep 17 00:00:00 2001 From: Su Yanjun Date: Sun, 6 Jan 2019 21:31:20 -0500 Subject: [PATCH 0080/1128] vti4: Fix a ipip packet processing bug in 'IPCOMP' virtual tunnel [ Upstream commit dd9ee3444014e8f28c0eefc9fffc9ac9c5248c12 ] Recently we run a network test over ipcomp virtual tunnel.We find that if a ipv4 packet needs fragment, then the peer can't receive it. We deep into the code and find that when packet need fragment the smaller fragment will be encapsulated by ipip not ipcomp. So when the ipip packet goes into xfrm, it's skb->dev is not properly set. The ipv4 reassembly code always set skb'dev to the last fragment's dev. After ipv4 defrag processing, when the kernel rp_filter parameter is set, the skb will be drop by -EXDEV error. This patch adds compatible support for the ipip process in ipcomp virtual tunnel. Signed-off-by: Su Yanjun Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/ipv4/ip_vti.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 00d4371d4573..306603a7f351 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -74,6 +74,33 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, return 0; } +static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) +{ + struct ip_tunnel *tunnel; + const struct iphdr *iph = ip_hdr(skb); + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); + if (tunnel) { + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; + + skb->dev = tunnel->dev; + + return xfrm_input(skb, nexthdr, spi, encap_type); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; +} + static int vti_rcv(struct sk_buff *skb) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; @@ -82,6 +109,14 @@ static int vti_rcv(struct sk_buff *skb) return vti_input(skb, ip_hdr(skb)->protocol, 0, 0); } +static int vti_rcv_ipip(struct sk_buff *skb) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0); +} + static int vti_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; @@ -439,6 +474,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { .priority = 100, }; +static struct xfrm_tunnel ipip_handler __read_mostly = { + .handler = vti_rcv_ipip, + .err_handler = vti4_err, + .priority = 0, +}; + static int __net_init vti_init_net(struct net *net) { int err; @@ -607,6 +648,13 @@ static int __init vti_init(void) if (err < 0) goto xfrm_proto_comp_failed; + msg = "ipip tunnel"; + err = xfrm4_tunnel_register(&ipip_handler, AF_INET); + if (err < 0) { + pr_info("%s: cant't register tunnel\n",__func__); + goto xfrm_tunnel_failed; + } + msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); if (err < 0) @@ -616,6 +664,8 @@ static int __init vti_init(void) rtnl_link_failed: xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); +xfrm_tunnel_failed: + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: -- GitLab From 482caab70b654d312012cdc5c910147ac3ffa433 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 10 Jan 2019 17:17:16 -0800 Subject: [PATCH 0081/1128] perf core: Fix perf_proc_update_handler() bug [ Upstream commit 1a51c5da5acc6c188c917ba572eebac5f8793432 ] The perf_proc_update_handler() handles /proc/sys/kernel/perf_event_max_sample_rate syctl variable. When the PMU IRQ handler timing monitoring is disabled, i.e, when /proc/sys/kernel/perf_cpu_time_max_percent is equal to 0 or 100, then no modification to sysctl_perf_event_sample_rate is allowed to prevent possible hang from wrong values. The problem is that the test to prevent modification is made after the sysctl variable is modified in perf_proc_update_handler(). You get an error: $ echo 10001 >/proc/sys/kernel/perf_event_max_sample_rate echo: write error: invalid argument But the value is still modified causing all sorts of inconsistencies: $ cat /proc/sys/kernel/perf_event_max_sample_rate 10001 This patch fixes the problem by moving the parsing of the value after the test. Committer testing: # echo 100 > /proc/sys/kernel/perf_cpu_time_max_percent # echo 10001 > /proc/sys/kernel/perf_event_max_sample_rate -bash: echo: write error: Invalid argument # cat /proc/sys/kernel/perf_event_max_sample_rate 10001 # Signed-off-by: Stephane Eranian Reviewed-by: Andi Kleen Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1547169436-6266-1-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- kernel/events/core.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 17d5d41464c6..92939b5397df 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -436,18 +436,18 @@ int perf_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - - if (ret || !write) - return ret; - + int ret; + int perf_cpu = sysctl_perf_cpu_time_max_percent; /* * If throttling is disabled don't allow the write: */ - if (sysctl_perf_cpu_time_max_percent == 100 || - sysctl_perf_cpu_time_max_percent == 0) + if (write && (perf_cpu == 100 || perf_cpu == 0)) return -EINVAL; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret || !write) + return ret; + max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ); perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate; update_perf_cpu_limits(); -- GitLab From 01b094e3c2c5e00a74abd9a978e0ce6c3b5e68a4 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Sat, 19 Jan 2019 00:12:39 -0800 Subject: [PATCH 0082/1128] perf tools: Handle TOPOLOGY headers with no CPU [ Upstream commit 1497e804d1a6e2bd9107ddf64b0310449f4673eb ] This patch fixes an issue in cpumap.c when used with the TOPOLOGY header. In some configurations, some NUMA nodes may have no CPU (empty cpulist). Yet a cpumap map must be created otherwise perf abort with an error. This patch handles this case by creating a dummy map. Before: $ perf record -o - -e cycles noploop 2 | perf script -i - 0x6e8 [0x6c]: failed to process type: 80 After: $ perf record -o - -e cycles noploop 2 | perf script -i - noploop for 2 seconds Signed-off-by: Stephane Eranian Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1547885559-1657-1-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/cpumap.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 1ccbd3342069..383674f448fc 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -134,7 +134,12 @@ struct cpu_map *cpu_map__new(const char *cpu_list) if (!cpu_list) return cpu_map__read_all_cpu_map(); - if (!isdigit(*cpu_list)) + /* + * must handle the case of empty cpumap to cover + * TOPOLOGY header for NUMA nodes with no CPU + * ( e.g., because of CPU hotplug) + */ + if (!isdigit(*cpu_list) && *cpu_list != '\0') goto out; while (isdigit(*cpu_list)) { @@ -181,8 +186,10 @@ struct cpu_map *cpu_map__new(const char *cpu_list) if (nr_cpus > 0) cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else + else if (*cpu_list != '\0') cpus = cpu_map__default_new(); + else + cpus = cpu_map__dummy_new(); invalid: free(tmp_cpus); out: -- GitLab From 3162d8af3f5d89141843a4f6bfd6a749ddbbe08d Mon Sep 17 00:00:00 2001 From: Brian Welty Date: Thu, 17 Jan 2019 12:41:32 -0800 Subject: [PATCH 0083/1128] IB/{hfi1, qib}: Fix WC.byte_len calculation for UD_SEND_WITH_IMM [ Upstream commit 904bba211acc2112fdf866e5a2bc6cd9ecd0de1b ] The work completion length for a receiving a UD send with immediate is short by 4 bytes causing application using this opcode to fail. The UD receive logic incorrectly subtracts 4 bytes for immediate value. These bytes are already included in header length and are used to calculate header/payload split, so the result is these 4 bytes are subtracted twice, once when the header length subtracted from the overall length and once again in the UD opcode specific path. Remove the extra subtraction when handling the opcode. Fixes: 7724105686e7 ("IB/hfi1: add driver files") Reviewed-by: Michael J. Ruhl Signed-off-by: Brian Welty Signed-off-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/ud.c | 1 - drivers/infiniband/hw/qib/qib_ud.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 37abd150fad3..74aff88c593d 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -954,7 +954,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) { wc.ex.imm_data = ohdr->u.ud.imm_data; wc.wc_flags = IB_WC_WITH_IMM; - tlen -= sizeof(u32); } else if (opcode == IB_OPCODE_UD_SEND_ONLY) { wc.ex.imm_data = 0; wc.wc_flags = 0; diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c index be4907453ac4..5ef144e4a4cb 100644 --- a/drivers/infiniband/hw/qib/qib_ud.c +++ b/drivers/infiniband/hw/qib/qib_ud.c @@ -515,7 +515,6 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr, opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) { wc.ex.imm_data = ohdr->u.ud.imm_data; wc.wc_flags = IB_WC_WITH_IMM; - tlen -= sizeof(u32); } else if (opcode == IB_OPCODE_UD_SEND_ONLY) { wc.ex.imm_data = 0; wc.wc_flags = 0; -- GitLab From 1508187f922aa965c4365216aa81d44359fcb1a6 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Thu, 17 Jan 2019 12:29:02 -0700 Subject: [PATCH 0084/1128] iommu/amd: Call free_iova_fast with pfn in map_sg [ Upstream commit 51d8838d66d3249508940d8f59b07701f2129723 ] In the error path of map_sg, free_iova_fast is being called with address instead of the pfn. This results in a bad value getting into the rcache, and can result in hitting a BUG_ON when iova_magazine_free_pfns is called. Cc: Joerg Roedel Cc: Suravee Suthikulpanit Signed-off-by: Jerry Snitselaar Fixes: 80187fd39dcb ("iommu/amd: Optimize map_sg and unmap_sg") Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/amd_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 766103ea237e..ded13a6afa66 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2566,7 +2566,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, } out_free_iova: - free_iova_fast(&dma_dom->iovad, address, npages); + free_iova_fast(&dma_dom->iovad, address >> PAGE_SHIFT, npages); out_err: return 0; -- GitLab From 878a9d34e4e815518c0deea3e0e53ae5b4356373 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Sat, 19 Jan 2019 10:38:05 -0700 Subject: [PATCH 0085/1128] iommu/amd: Unmap all mapped pages in error path of map_sg [ Upstream commit f1724c0883bb0ce93b8dcb94b53dcca3b75ac9a7 ] In the error path of map_sg there is an incorrect if condition for breaking out of the loop that searches the scatterlist for mapped pages to unmap. Instead of breaking out of the loop once all the pages that were mapped have been unmapped, it will break out of the loop after it has unmapped 1 page. Fix the condition, so it breaks out of the loop only after all the mapped pages have been unmapped. Fixes: 80187fd39dcb ("iommu/amd: Optimize map_sg and unmap_sg") Cc: Joerg Roedel Signed-off-by: Jerry Snitselaar Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/amd_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index ded13a6afa66..0c0acf6fda87 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2560,7 +2560,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, bus_addr = address + s->dma_address + (j << PAGE_SHIFT); iommu_unmap_page(domain, bus_addr, PAGE_SIZE); - if (--mapped_pages) + if (--mapped_pages == 0) goto out_free_iova; } } -- GitLab From 34f02c1dd2919dca9e1c90fb497ff0e61e0fc248 Mon Sep 17 00:00:00 2001 From: ZhangXiaoxu Date: Thu, 10 Jan 2019 16:39:06 +0800 Subject: [PATCH 0086/1128] ipvs: Fix signed integer overflow when setsockopt timeout [ Upstream commit 53ab60baa1ac4f20b080a22c13b77b6373922fd7 ] There is a UBSAN bug report as below: UBSAN: Undefined behaviour in net/netfilter/ipvs/ip_vs_ctl.c:2227:21 signed integer overflow: -2147483647 * 1000 cannot be represented in type 'int' Reproduce program: #include #include #include #define IPPROTO_IP 0 #define IPPROTO_RAW 255 #define IP_VS_BASE_CTL (64+1024+64) #define IP_VS_SO_SET_TIMEOUT (IP_VS_BASE_CTL+10) /* The argument to IP_VS_SO_GET_TIMEOUT */ struct ipvs_timeout_t { int tcp_timeout; int tcp_fin_timeout; int udp_timeout; }; int main() { int ret = -1; int sockfd = -1; struct ipvs_timeout_t to; sockfd = socket(AF_INET, SOCK_RAW, IPPROTO_RAW); if (sockfd == -1) { printf("socket init error\n"); return -1; } to.tcp_timeout = -2147483647; to.tcp_fin_timeout = -2147483647; to.udp_timeout = -2147483647; ret = setsockopt(sockfd, IPPROTO_IP, IP_VS_SO_SET_TIMEOUT, (char *)(&to), sizeof(to)); printf("setsockopt return %d\n", ret); return ret; } Return -EINVAL if the timeout value is negative or max than 'INT_MAX / HZ'. Signed-off-by: ZhangXiaoxu Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 2f45c3ce77ef..dff4ead3d117 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2252,6 +2252,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user u->tcp_fin_timeout, u->udp_timeout); +#ifdef CONFIG_IP_VS_PROTO_TCP + if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) || + u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) { + return -EINVAL; + } +#endif + +#ifdef CONFIG_IP_VS_PROTO_UDP + if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ)) + return -EINVAL; +#endif + #ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout) { pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); -- GitLab From ef41aa7ee085d6cedb14fde1c8c0e533150198d3 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 24 Jan 2019 04:16:45 +0000 Subject: [PATCH 0087/1128] iommu/amd: Fix IOMMU page flush when detach device from a domain [ Upstream commit 9825bd94e3a2baae1f4874767ae3a7d4c049720e ] When a VM is terminated, the VFIO driver detaches all pass-through devices from VFIO domain by clearing domain id and page table root pointer from each device table entry (DTE), and then invalidates the DTE. Then, the VFIO driver unmap pages and invalidate IOMMU pages. Currently, the IOMMU driver keeps track of which IOMMU and how many devices are attached to the domain. When invalidate IOMMU pages, the driver checks if the IOMMU is still attached to the domain before issuing the invalidate page command. However, since VFIO has already detached all devices from the domain, the subsequent INVALIDATE_IOMMU_PAGES commands are being skipped as there is no IOMMU attached to the domain. This results in data corruption and could cause the PCI device to end up in indeterministic state. Fix this by invalidate IOMMU pages when detach a device, and before decrementing the per-domain device reference counts. Cc: Boris Ostrovsky Suggested-by: Joerg Roedel Co-developed-by: Brijesh Singh Signed-off-by: Brijesh Singh Signed-off-by: Suravee Suthikulpanit Fixes: 6de8ad9b9ee0 ('x86/amd-iommu: Make iommu_flush_pages aware of multiple IOMMUs') Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/amd_iommu.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 0c0acf6fda87..78b97f31a1f2 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1919,6 +1919,7 @@ static void do_attach(struct iommu_dev_data *dev_data, static void do_detach(struct iommu_dev_data *dev_data) { + struct protection_domain *domain = dev_data->domain; struct amd_iommu *iommu; u16 alias; @@ -1934,10 +1935,6 @@ static void do_detach(struct iommu_dev_data *dev_data) iommu = amd_iommu_rlookup_table[dev_data->devid]; alias = dev_data->alias; - /* decrease reference counters */ - dev_data->domain->dev_iommu[iommu->index] -= 1; - dev_data->domain->dev_cnt -= 1; - /* Update data structures */ dev_data->domain = NULL; list_del(&dev_data->list); @@ -1947,6 +1944,16 @@ static void do_detach(struct iommu_dev_data *dev_data) /* Flush the DTE entry */ device_flush_dte(dev_data); + + /* Flush IOTLB */ + domain_flush_tlb_pde(domain); + + /* Wait for the flushes to finish */ + domain_flush_complete(domain); + + /* decrease reference counters - needs to happen after the flushes */ + domain->dev_iommu[iommu->index] -= 1; + domain->dev_cnt -= 1; } /* -- GitLab From 51cbb781d215eed7ee9146eef96fdce7cbe98132 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Mon, 29 Jan 2018 09:09:41 -0800 Subject: [PATCH 0088/1128] xtensa: SMP: fix ccount_timer_shutdown [ Upstream commit 4fe8713b873fc881284722ce4ac47995de7cf62c ] ccount_timer_shutdown is called from the atomic context in the secondary_start_kernel, resulting in the following BUG: BUG: sleeping function called from invalid context in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 Preemption disabled at: secondary_start_kernel+0xa1/0x130 Call Trace: ___might_sleep+0xe7/0xfc __might_sleep+0x41/0x44 synchronize_irq+0x24/0x64 disable_irq+0x11/0x14 ccount_timer_shutdown+0x12/0x20 clockevents_switch_state+0x82/0xb4 clockevents_exchange_device+0x54/0x60 tick_check_new_device+0x46/0x70 clockevents_register_device+0x8c/0xc8 clockevents_config_and_register+0x1d/0x2c local_timer_setup+0x75/0x7c secondary_start_kernel+0xb4/0x130 should_never_return+0x32/0x35 Use disable_irq_nosync instead of disable_irq to avoid it. This is safe because the ccount timer IRQ is per-CPU, and once IRQ is masked the ISR will not be called. Signed-off-by: Max Filippov Signed-off-by: Sasha Levin --- arch/xtensa/kernel/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index fd524a54d2ab..378186b5eb40 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -89,7 +89,7 @@ static int ccount_timer_shutdown(struct clock_event_device *evt) container_of(evt, struct ccount_timer, evt); if (timer->irq_enabled) { - disable_irq(evt->irq); + disable_irq_nosync(evt->irq); timer->irq_enabled = 0; } return 0; -- GitLab From 33c6313f1e173a739db170addc2049fcf36de307 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 10 Jan 2019 12:38:02 +0000 Subject: [PATCH 0089/1128] selftests: cpu-hotplug: fix case where CPUs offline > CPUs present [ Upstream commit 2b531b6137834a55857a337ac17510d6436b6fbb ] The cpu-hotplug test assumes that we can offline the maximum CPU as described by /sys/devices/system/cpu/offline. However, in the case where the number of CPUs exceeds like kernel configuration then the offline count can be greater than the present count and we end up trying to test the offlining of a CPU that is not available to offline. Fix this by testing the maximum present CPU instead. Also, the test currently offlines the CPU and does not online it, so fix this by onlining the CPU after the test. Fixes: d89dffa976bc ("fault-injection: add selftests for cpu and memory hotplug") Signed-off-by: Colin Ian King Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- .../selftests/cpu-hotplug/cpu-on-off-test.sh | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh index f3a8933c1275..49ccd2293343 100755 --- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh +++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh @@ -35,6 +35,10 @@ prerequisite() exit 0 fi + present_cpus=`cat $SYSFS/devices/system/cpu/present` + present_max=${present_cpus##*-} + echo "present_cpus = $present_cpus present_max = $present_max" + echo -e "\t Cpus in online state: $online_cpus" offline_cpus=`cat $SYSFS/devices/system/cpu/offline` @@ -149,6 +153,8 @@ online_cpus=0 online_max=0 offline_cpus=0 offline_max=0 +present_cpus=0 +present_max=0 while getopts e:ahp: opt; do case $opt in @@ -188,9 +194,10 @@ if [ $allcpus -eq 0 ]; then online_cpu_expect_success $online_max if [[ $offline_cpus -gt 0 ]]; then - echo -e "\t offline to online to offline: cpu $offline_max" - online_cpu_expect_success $offline_max - offline_cpu_expect_success $offline_max + echo -e "\t offline to online to offline: cpu $present_max" + online_cpu_expect_success $present_max + offline_cpu_expect_success $present_max + online_cpu $present_max fi exit 0 else -- GitLab From 19b7005bfaf93740710424694c65ad396d321577 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Fri, 21 Dec 2018 08:26:20 -0800 Subject: [PATCH 0090/1128] xtensa: SMP: fix secondary CPU initialization [ Upstream commit 32a7726c4f4aadfabdb82440d84f88a5a2c8fe13 ] - add missing memory barriers to the secondary CPU synchronization spin loops; add comment to the matching memory barrier in the boot_secondary and __cpu_die functions; - use READ_ONCE/WRITE_ONCE to access cpu_start_id/cpu_start_ccount instead of reading/writing them directly; - re-initialize cpu_running every time before starting secondary CPU to flush possible previous CPU startup results. Signed-off-by: Max Filippov Signed-off-by: Sasha Levin --- arch/xtensa/kernel/head.S | 5 ++++- arch/xtensa/kernel/smp.c | 34 +++++++++++++++++++++------------- 2 files changed, 25 insertions(+), 14 deletions(-) diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index 27c8e07ace43..29f445b410b3 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -281,12 +281,13 @@ should_never_return: movi a2, cpu_start_ccount 1: + memw l32i a3, a2, 0 beqi a3, 0, 1b movi a3, 0 s32i a3, a2, 0 - memw 1: + memw l32i a3, a2, 0 beqi a3, 0, 1b wsr a3, ccount @@ -323,11 +324,13 @@ ENTRY(cpu_restart) rsr a0, prid neg a2, a0 movi a3, cpu_start_id + memw s32i a2, a3, 0 #if XCHAL_DCACHE_IS_WRITEBACK dhwbi a3, 0 #endif 1: + memw l32i a2, a3, 0 dhi a3, 0 bne a2, a0, 1b diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 932d64689bac..c9fc2c4f71b3 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -195,9 +195,11 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts) int i; #ifdef CONFIG_HOTPLUG_CPU - cpu_start_id = cpu; - system_flush_invalidate_dcache_range( - (unsigned long)&cpu_start_id, sizeof(cpu_start_id)); + WRITE_ONCE(cpu_start_id, cpu); + /* Pairs with the third memw in the cpu_restart */ + mb(); + system_flush_invalidate_dcache_range((unsigned long)&cpu_start_id, + sizeof(cpu_start_id)); #endif smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1); @@ -206,18 +208,21 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts) ccount = get_ccount(); while (!ccount); - cpu_start_ccount = ccount; + WRITE_ONCE(cpu_start_ccount, ccount); - while (time_before(jiffies, timeout)) { + do { + /* + * Pairs with the first two memws in the + * .Lboot_secondary. + */ mb(); - if (!cpu_start_ccount) - break; - } + ccount = READ_ONCE(cpu_start_ccount); + } while (ccount && time_before(jiffies, timeout)); - if (cpu_start_ccount) { + if (ccount) { smp_call_function_single(0, mx_cpu_stop, - (void *)cpu, 1); - cpu_start_ccount = 0; + (void *)cpu, 1); + WRITE_ONCE(cpu_start_ccount, 0); return -EIO; } } @@ -237,6 +242,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n", __func__, cpu, idle, start_info.stack); + init_completion(&cpu_running); ret = boot_secondary(cpu, idle); if (ret == 0) { wait_for_completion_timeout(&cpu_running, @@ -298,8 +304,10 @@ void __cpu_die(unsigned int cpu) unsigned long timeout = jiffies + msecs_to_jiffies(1000); while (time_before(jiffies, timeout)) { system_invalidate_dcache_range((unsigned long)&cpu_start_id, - sizeof(cpu_start_id)); - if (cpu_start_id == -cpu) { + sizeof(cpu_start_id)); + /* Pairs with the second memw in the cpu_restart */ + mb(); + if (READ_ONCE(cpu_start_id) == -cpu) { platform_cpu_kill(cpu); return; } -- GitLab From 7b72724baf4639445f25f63a2447bafc64fa0035 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Thu, 24 Jan 2019 17:16:11 -0800 Subject: [PATCH 0091/1128] xtensa: smp_lx200_defconfig: fix vectors clash [ Upstream commit 306b38305c0f86de7f17c5b091a95451dcc93d7d ] Secondary CPU reset vector overlaps part of the double exception handler code, resulting in weird crashes and hangups when running user code. Move exception vectors one page up so that they don't clash with the secondary CPU reset vector. Signed-off-by: Max Filippov Signed-off-by: Sasha Levin --- arch/xtensa/configs/smp_lx200_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig index 14e3ca353ac8..5035b86a2e49 100644 --- a/arch/xtensa/configs/smp_lx200_defconfig +++ b/arch/xtensa/configs/smp_lx200_defconfig @@ -34,6 +34,7 @@ CONFIG_SMP=y CONFIG_HOTPLUG_CPU=y # CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX is not set # CONFIG_PCI is not set +CONFIG_VECTORS_OFFSET=0x00002000 CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0" -- GitLab From c754598b5d09b2e938da24f19981a2700fb08a61 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Sat, 19 Jan 2019 00:26:48 -0800 Subject: [PATCH 0092/1128] xtensa: SMP: mark each possible CPU as present [ Upstream commit 8b1c42cdd7181200dc1fff39dcb6ac1a3fac2c25 ] Otherwise it is impossible to enable CPUs after booting with 'maxcpus' parameter. Signed-off-by: Max Filippov Signed-off-by: Sasha Levin --- arch/xtensa/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index c9fc2c4f71b3..80be6449c497 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -83,7 +83,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { unsigned i; - for (i = 0; i < max_cpus; ++i) + for_each_possible_cpu(i) set_cpu_present(i, true); } -- GitLab From 4c2ceb151db6dc2255581c6c5d4b2f280af94e03 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Sat, 26 Jan 2019 20:35:18 -0800 Subject: [PATCH 0093/1128] xtensa: SMP: limit number of possible CPUs by NR_CPUS [ Upstream commit 25384ce5f9530def39421597b1457d9462df6455 ] This fixes the following warning at boot when the kernel is booted on a board with more CPU cores than was configured in NR_CPUS: smp_init_cpus: Core Count = 8 smp_init_cpus: Core Id = 0 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at include/linux/cpumask.h:121 smp_init_cpus+0x54/0x74 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 5.0.0-rc3-00015-g1459333f88a0 #124 Call Trace: __warn$part$3+0x6a/0x7c warn_slowpath_null+0x35/0x3c smp_init_cpus+0x54/0x74 setup_arch+0x1c0/0x1d0 start_kernel+0x44/0x310 _startup+0x107/0x107 Signed-off-by: Max Filippov Signed-off-by: Sasha Levin --- arch/xtensa/kernel/smp.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 80be6449c497..be1f280c322c 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -96,6 +96,11 @@ void __init smp_init_cpus(void) pr_info("%s: Core Count = %d\n", __func__, ncpus); pr_info("%s: Core Id = %d\n", __func__, core_id); + if (ncpus > NR_CPUS) { + ncpus = NR_CPUS; + pr_info("%s: limiting core count by %d\n", __func__, ncpus); + } + for (i = 0; i < ncpus; ++i) set_cpu_possible(i, true); } -- GitLab From 140e51241934f5da66a590f00dd147a72094e236 Mon Sep 17 00:00:00 2001 From: Tomonori Sakita Date: Fri, 25 Jan 2019 11:02:22 +0900 Subject: [PATCH 0094/1128] net: altera_tse: fix msgdma_tx_completion on non-zero fill_level case [ Upstream commit 6571ebce112a21ec9be68ef2f53b96fcd41fd81b ] If fill_level was not zero and status was not BUSY, result of "tx_prod - tx_cons - inuse" might be zero. Subtracting 1 unconditionally results invalid negative return value on this case. Make sure not to return an negative value. Signed-off-by: Tomonori Sakita Signed-off-by: Atsushi Nemoto Reviewed-by: Dalon L Westergreen Acked-by: Thor Thayer Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/altera/altera_msgdma.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c index 0fb986ba3290..0ae723f75341 100644 --- a/drivers/net/ethernet/altera/altera_msgdma.c +++ b/drivers/net/ethernet/altera/altera_msgdma.c @@ -145,7 +145,8 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv) & 0xffff; if (inuse) { /* Tx FIFO is not empty */ - ready = priv->tx_prod - priv->tx_cons - inuse - 1; + ready = max_t(int, + priv->tx_prod - priv->tx_cons - inuse - 1, 0); } else { /* Check for buffered last packet */ status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status)); -- GitLab From d70329476999adf562b40af15aacec10b496a6ea Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 26 Jan 2019 17:18:25 +0800 Subject: [PATCH 0095/1128] net: hns: Fix for missing of_node_put() after of_parse_phandle() [ Upstream commit 263c6d75f9a544a3c2f8f6a26de4f4808d8f59cf ] In hns enet driver, we use of_parse_handle() to get hold of the device node related to "ae-handle" but we have missed to put the node reference using of_node_put() after we are done using the node. This patch fixes it. Note: This problem is stated in Link: https://lkml.org/lkml/2018/12/22/217 Fixes: 48189d6aaf1e ("net: hns: enet specifies a reference to dsaf") Reported-by: Alexey Khoroshilov Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 86662a14208e..d30c28fba249 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2532,6 +2532,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev) out_notify_fail: (void)cancel_work_sync(&priv->service_task); out_read_prop_fail: + /* safe for ACPI FW */ + of_node_put(to_of_node(priv->fwnode)); free_netdev(ndev); return ret; } @@ -2561,6 +2563,9 @@ static int hns_nic_dev_remove(struct platform_device *pdev) set_bit(NIC_STATE_REMOVING, &priv->state); (void)cancel_work_sync(&priv->service_task); + /* safe for ACPI FW */ + of_node_put(to_of_node(priv->fwnode)); + free_netdev(ndev); return 0; } -- GitLab From a60323e6b9661e007b094a9d8327e7917b79b8af Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 26 Jan 2019 17:18:26 +0800 Subject: [PATCH 0096/1128] net: hns: Restart autoneg need return failed when autoneg off [ Upstream commit ed29ca8b9592562559c64d027fb5eb126e463e2c ] The hns driver of earlier devices, when autoneg off, restart autoneg will return -EINVAL, so make the hns driver for the latest devices do the same. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns/hns_ethtool.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index c1e947bb852f..14df03f60e05 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -1154,16 +1154,18 @@ static int hns_get_regs_len(struct net_device *net_dev) */ static int hns_nic_nway_reset(struct net_device *netdev) { - int ret = 0; struct phy_device *phy = netdev->phydev; - if (netif_running(netdev)) { - /* if autoneg is disabled, don't restart auto-negotiation */ - if (phy && phy->autoneg == AUTONEG_ENABLE) - ret = genphy_restart_aneg(phy); - } + if (!netif_running(netdev)) + return 0; - return ret; + if (!phy) + return -EOPNOTSUPP; + + if (phy->autoneg != AUTONEG_ENABLE) + return -EINVAL; + + return genphy_restart_aneg(phy); } static u32 -- GitLab From 04731b3c702b6008786542707259f1bbe21caae5 Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 26 Jan 2019 17:18:27 +0800 Subject: [PATCH 0097/1128] net: hns: Fix wrong read accesses via Clause 45 MDIO protocol [ Upstream commit cec8abba13e6a26729dfed41019720068eeeff2b ] When reading phy registers via Clause 45 MDIO protocol, after write address operation, the driver use another write address operation, so can not read the right value of any phy registers. This patch fixes it. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns_mdio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index 017e08452d8c..baf5cc251f32 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -321,7 +321,7 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum) } hns_mdio_cmd_write(mdio_dev, is_c45, - MDIO_C45_WRITE_ADDR, phy_id, devad); + MDIO_C45_READ, phy_id, devad); } /* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/ -- GitLab From 366abec996a44f273c5556f2d132ad45afe4f39f Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Sat, 26 Jan 2019 22:48:57 +0300 Subject: [PATCH 0098/1128] net: stmmac: dwmac-rk: fix error handling in rk_gmac_powerup() [ Upstream commit c69c29a1a0a8f68cd87e98ba4a5a79fb8ef2a58c ] If phy_power_on() fails in rk_gmac_powerup(), clocks are left enabled. Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Alexey Khoroshilov Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 13133b30b575..01787344f6e5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1284,8 +1284,10 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv) } ret = phy_power_on(bsp_priv, true); - if (ret) + if (ret) { + gmac_clk_enable(bsp_priv, false); return ret; + } pm_runtime_enable(dev); pm_runtime_get_sync(dev); -- GitLab From f3731c960cbd9e0a13c26266397cd0568524f4fb Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 21 Jan 2019 21:54:36 +0100 Subject: [PATCH 0099/1128] netfilter: ebtables: compat: un-break 32bit setsockopt when no rules are present [ Upstream commit 2035f3ff8eaa29cfb5c8e2160b0f6e85eeb21a95 ] Unlike ip(6)tables ebtables only counts user-defined chains. The effect is that a 32bit ebtables binary on a 64bit kernel can do 'ebtables -N FOO' only after adding at least one rule, else the request fails with -EINVAL. This is a similar fix as done in 3f1e53abff84 ("netfilter: ebtables: don't attempt to allocate 0-sized compat array"). Fixes: 7d7d7e02111e9 ("netfilter: compat: reject huge allocation requests") Reported-by: Francesco Ruggeri Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/bridge/netfilter/ebtables.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 22e4c15a1fc3..53392ac58b38 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2292,9 +2292,12 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); - if (ret < 0) - goto out_unlock; + if (tmp.nentries) { + ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); + if (ret < 0) + goto out_unlock; + } + ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) goto out_unlock; -- GitLab From 50d8083d733e2e656d15973eb28630f983b33784 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 27 Jan 2019 22:58:00 +0100 Subject: [PATCH 0100/1128] gpio: vf610: Mask all GPIO interrupts [ Upstream commit 7ae710f9f8b2cf95297e7bbfe1c09789a7dc43d4 ] On SoC reset all GPIO interrupts are disable. However, if kexec is used to boot into a new kernel, the SoC does not experience a reset. Hence GPIO interrupts can be left enabled from the previous kernel. It is then possible for the interrupt to fire before an interrupt handler is registered, resulting in the kernel complaining of an "unexpected IRQ trap", the interrupt is never cleared, and so fires again, resulting in an interrupt storm. Disable all GPIO interrupts before registering the GPIO IRQ chip. Fixes: 7f2691a19627 ("gpio: vf610: add gpiolib/IRQ chip driver for Vybrid") Signed-off-by: Andrew Lunn Acked-by: Stefan Agner Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/gpio/gpio-vf610.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index cbe9e06861de..1309b444720e 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -261,6 +261,7 @@ static int vf610_gpio_probe(struct platform_device *pdev) struct vf610_gpio_port *port; struct resource *iores; struct gpio_chip *gc; + int i; int ret; port = devm_kzalloc(&pdev->dev, sizeof(*port), GFP_KERNEL); @@ -300,6 +301,10 @@ static int vf610_gpio_probe(struct platform_device *pdev) if (ret < 0) return ret; + /* Mask all GPIO interrupts */ + for (i = 0; i < gc->ngpio; i++) + vf610_gpio_writel(0, port->base + PORT_PCR(i)); + /* Clear the interrupt status register for all GPIO's */ vf610_gpio_writel(~0, port->base + PORT_ISFR); -- GitLab From d2a1e0c3858470f5d9d9347a9358b2f123459f50 Mon Sep 17 00:00:00 2001 From: Fathi Boudra Date: Wed, 16 Jan 2019 11:43:20 -0600 Subject: [PATCH 0101/1128] selftests: timers: use LDLIBS instead of LDFLAGS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7d4e591bc051d3382c45caaa2530969fb42ed23d ] posix_timers fails to build due to undefined reference errors: aarch64-linaro-linux-gcc --sysroot=/build/tmp-rpb-glibc/sysroots/hikey -O2 -pipe -g -feliminate-unused-debug-types -O3 -Wl,-no-as-needed -Wall -DKTEST -Wl,-O1 -Wl,--hash-style=gnu -Wl,--as-needed -lrt -lpthread posix_timers.c -o /build/tmp-rpb-glibc/work/hikey-linaro-linux/kselftests/4.12-r0/linux-4.12-rc7/tools/testing/selftests/timers/posix_timers /tmp/cc1FTZzT.o: In function `check_timer_create': /usr/src/debug/kselftests/4.12-r0/linux-4.12-rc7/tools/testing/selftests/timers/posix_timers.c:157: undefined reference to `timer_create' /usr/src/debug/kselftests/4.12-r0/linux-4.12-rc7/tools/testing/selftests/timers/posix_timers.c:170: undefined reference to `timer_settime' collect2: error: ld returned 1 exit status It's GNU Make and linker specific. The default Makefile rule looks like: $(CC) $(CFLAGS) $(LDFLAGS) $@ $^ $(LDLIBS) When linking is done by gcc itself, no issue, but when it needs to be passed to proper ld, only LDLIBS follows and then ld cannot know what libs to link with. More detail: https://www.gnu.org/software/make/manual/html_node/Implicit-Variables.html LDFLAGS Extra flags to give to compilers when they are supposed to invoke the linker, ‘ld’, such as -L. Libraries (-lfoo) should be added to the LDLIBS variable instead. LDLIBS Library flags or names given to compilers when they are supposed to invoke the linker, ‘ld’. LOADLIBES is a deprecated (but still supported) alternative to LDLIBS. Non-library linker flags, such as -L, should go in the LDFLAGS variable. https://lkml.org/lkml/2010/2/10/362 tools/perf: libraries must come after objects Link order matters, use LDLIBS instead of LDFLAGS to properly link against libpthread. Signed-off-by: Denys Dmytriyenko Signed-off-by: Fathi Boudra Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/timers/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index 3496680981f2..d937e45532d8 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -O3 -Wl,-no-as-needed -Wall -LDFLAGS += -lrt -lpthread -lm +LDLIBS += -lrt -lpthread -lm # these are all "safe" tests that don't modify # system time or require escalated privileges -- GitLab From e5f77942d9533aef9f5cb1c962eb712134da6938 Mon Sep 17 00:00:00 2001 From: Yao Liu Date: Mon, 28 Jan 2019 19:44:14 +0800 Subject: [PATCH 0102/1128] nfs: Fix NULL pointer dereference of dev_name [ Upstream commit 80ff00172407e0aad4b10b94ef0816fc3e7813cb ] There is a NULL pointer dereference of dev_name in nfs_parse_devname() The oops looks something like: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 ... RIP: 0010:nfs_fs_mount+0x3b6/0xc20 [nfs] ... Call Trace: ? ida_alloc_range+0x34b/0x3d0 ? nfs_clone_super+0x80/0x80 [nfs] ? nfs_free_parsed_mount_data+0x60/0x60 [nfs] mount_fs+0x52/0x170 ? __init_waitqueue_head+0x3b/0x50 vfs_kern_mount+0x6b/0x170 do_mount+0x216/0xdc0 ksys_mount+0x83/0xd0 __x64_sys_mount+0x25/0x30 do_syscall_64+0x65/0x220 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fix this by adding a NULL check on dev_name Signed-off-by: Yao Liu Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/super.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 3c4aeb83e1c4..77d8d03344c8 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1901,6 +1901,11 @@ static int nfs_parse_devname(const char *dev_name, size_t len; char *end; + if (unlikely(!dev_name || !*dev_name)) { + dfprintk(MOUNT, "NFS: device name not specified\n"); + return -EINVAL; + } + /* Is the host name protected with square brakcets? */ if (*dev_name == '[') { end = strchr(++dev_name, ']'); -- GitLab From 88b5593c24dde42946e5c245ba88201fd77f9a33 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:04 -0800 Subject: [PATCH 0103/1128] qed: Fix bug in tx promiscuous mode settings [ Upstream commit 9e71a15d8b5bbce25c637f7f8833cd3f45b65646 ] When running tx switched traffic between VNICs created via a bridge(to which VFs are added), adapter drops the unicast packets in tx flow due to VNIC's ucast mac being unknown to it. But VF interfaces being in promiscuous mode should have caused adapter to accept all the unknown ucast packets. Later, it was found that driver doesn't really configure tx promiscuous mode settings to accept all unknown unicast macs. This patch fixes tx promiscuous mode settings to accept all unknown/unmatched unicast macs and works out the scenario. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 83c1c4fa102b..5191b575d57b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -607,6 +607,10 @@ qed_sp_update_accept_mode(struct qed_hwfn *p_hwfn, (!!(accept_filter & QED_ACCEPT_MCAST_MATCHED) && !!(accept_filter & QED_ACCEPT_MCAST_UNMATCHED))); + SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_ACCEPT_ALL, + (!!(accept_filter & QED_ACCEPT_UCAST_MATCHED) && + !!(accept_filter & QED_ACCEPT_UCAST_UNMATCHED))); + SET_FIELD(state, ETH_VPORT_TX_MODE_BCAST_ACCEPT_ALL, !!(accept_filter & QED_ACCEPT_BCAST)); @@ -2640,7 +2644,8 @@ static int qed_configure_filter_rx_mode(struct qed_dev *cdev, if (type == QED_FILTER_RX_MODE_TYPE_PROMISC) { accept_flags.rx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED | QED_ACCEPT_MCAST_UNMATCHED; - accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; + accept_flags.tx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED | + QED_ACCEPT_MCAST_UNMATCHED; } else if (type == QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC) { accept_flags.rx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; -- GitLab From e66622771e8379e69693e041b6f088a39673ecf5 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:05 -0800 Subject: [PATCH 0104/1128] qed: Fix LACP pdu drops for VFs [ Upstream commit ff9296966e5e00b0d0d00477b2365a178f0f06a3 ] VF is always configured to drop control frames (with reserved mac addresses) but to work LACP on the VFs, it would require LACP control frames to be forwarded or transmitted successfully. This patch fixes this in such a way that trusted VFs (marked through ndo_set_vf_trust) would be allowed to pass the control frames such as LACP pdus. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 5 +++++ drivers/net/ethernet/qlogic/qed/qed_l2.h | 3 +++ drivers/net/ethernet/qlogic/qed/qed_sriov.c | 10 ++++++++-- 3 files changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 5191b575d57b..4ffdde755db7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -747,6 +747,11 @@ int qed_sp_vport_update(struct qed_hwfn *p_hwfn, return rc; } + if (p_params->update_ctl_frame_check) { + p_cmn->ctl_frame_mac_check_en = p_params->mac_chk_en; + p_cmn->ctl_frame_ethtype_check_en = p_params->ethtype_chk_en; + } + /* Update mcast bins for VFs, PF doesn't use this functionality */ qed_sp_update_mcast_bin(p_hwfn, p_ramrod, p_params); diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index 91d383f3a661..7c41142452a3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -218,6 +218,9 @@ struct qed_sp_vport_update_params { struct qed_rss_params *rss_params; struct qed_filter_accept_flags accept_flags; struct qed_sge_tpa_params *sge_tpa_params; + u8 update_ctl_frame_check; + u8 mac_chk_en; + u8 ethtype_chk_en; }; int qed_sp_vport_update(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index c6411158afd7..65a53d409e77 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -1963,7 +1963,9 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn, params.vport_id = vf->vport_id; params.max_buffers_per_cqe = start->max_buffers_per_cqe; params.mtu = vf->mtu; - params.check_mac = true; + + /* Non trusted VFs should enable control frame filtering */ + params.check_mac = !vf->p_vf_info.is_trusted_configured; rc = qed_sp_eth_vport_start(p_hwfn, ¶ms); if (rc) { @@ -4910,6 +4912,9 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) params.opaque_fid = vf->opaque_fid; params.vport_id = vf->vport_id; + params.update_ctl_frame_check = 1; + params.mac_chk_en = !vf_info->is_trusted_configured; + if (vf_info->rx_accept_mode & mask) { flags->update_rx_mode_config = 1; flags->rx_accept_filter = vf_info->rx_accept_mode; @@ -4927,7 +4932,8 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) } if (flags->update_rx_mode_config || - flags->update_tx_mode_config) + flags->update_tx_mode_config || + params.update_ctl_frame_check) qed_sp_vport_update(hwfn, ¶ms, QED_SPQ_MODE_EBLOCK, NULL); } -- GitLab From dd155c87ca08b17ffebce151efda853080d67f96 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:06 -0800 Subject: [PATCH 0105/1128] qed: Fix VF probe failure while FLR [ Upstream commit 327852ec64205bb651be391a069784872098a3b2 ] VFs may hit VF-PF channel timeout while probing, as in some cases it was observed that VF FLR and VF "acquire" message transaction (i.e first message from VF to PF in VF's probe flow) could occur simultaneously which could lead VF to fail sending "acquire" message to PF as VF is marked disabled from HW perspective due to FLR, which will result into channel timeout and VF probe failure. In such cases, try retrying VF "acquire" message so that in later attempts it could be successful to pass message to PF after the VF FLR is completed and can be probed successfully. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_vf.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index dd8ebf6d380f..3220086f99de 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -261,6 +261,7 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) struct pfvf_acquire_resp_tlv *resp = &p_iov->pf2vf_reply->acquire_resp; struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info; struct vf_pf_resc_request *p_resc; + u8 retry_cnt = VF_ACQUIRE_THRESH; bool resources_acquired = false; struct vfpf_acquire_tlv *req; int rc = 0, attempts = 0; @@ -314,6 +315,15 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) /* send acquire request */ rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + + /* Re-try acquire in case of vf-pf hw channel timeout */ + if (retry_cnt && rc == -EBUSY) { + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "VF retrying to acquire due to VPC timeout\n"); + retry_cnt--; + continue; + } + if (rc) goto exit; -- GitLab From b757bcc92f8bfd24b239e2dc09b19cc6a1245f79 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:07 -0800 Subject: [PATCH 0106/1128] qed: Fix system crash in ll2 xmit [ Upstream commit 7c81626a3c37e4ac320b8ad785694ba498f24794 ] Cache number of fragments in the skb locally as in case of linear skb (with zero fragments), tx completion (or freeing of skb) may happen before driver tries to get number of frgaments from the skb which could lead to stale access to an already freed skb. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index cef619f0ce10..e82adea55ce9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -2299,19 +2299,24 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb) { struct qed_ll2_tx_pkt_info pkt; const skb_frag_t *frag; + u8 flags = 0, nr_frags; int rc = -EINVAL, i; dma_addr_t mapping; u16 vlan = 0; - u8 flags = 0; if (unlikely(skb->ip_summed != CHECKSUM_NONE)) { DP_INFO(cdev, "Cannot transmit a checksumed packet\n"); return -EINVAL; } - if (1 + skb_shinfo(skb)->nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) { + /* Cache number of fragments from SKB since SKB may be freed by + * the completion routine after calling qed_ll2_prepare_tx_packet() + */ + nr_frags = skb_shinfo(skb)->nr_frags; + + if (1 + nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) { DP_ERR(cdev, "Cannot transmit a packet with %d fragments\n", - 1 + skb_shinfo(skb)->nr_frags); + 1 + nr_frags); return -EINVAL; } @@ -2333,7 +2338,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb) } memset(&pkt, 0, sizeof(pkt)); - pkt.num_of_bds = 1 + skb_shinfo(skb)->nr_frags; + pkt.num_of_bds = 1 + nr_frags; pkt.vlan = vlan; pkt.bd_flags = flags; pkt.tx_dest = QED_LL2_TX_DEST_NW; @@ -2341,12 +2346,17 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb) pkt.first_frag_len = skb->len; pkt.cookie = skb; + /* qed_ll2_prepare_tx_packet() may actually send the packet if + * there are no fragments in the skb and subsequently the completion + * routine may run and free the SKB, so no dereferencing the SKB + * beyond this point unless skb has any fragments. + */ rc = qed_ll2_prepare_tx_packet(&cdev->hwfns[0], cdev->ll2->handle, &pkt, 1); if (rc) goto err; - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + for (i = 0; i < nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; mapping = skb_frag_dma_map(&cdev->pdev->dev, frag, 0, -- GitLab From fa46a54c8c8d3103886354e2433e445196499bf3 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:08 -0800 Subject: [PATCH 0107/1128] qed: Fix stack out of bounds bug [ Upstream commit ffb057f98928aa099b08e419bbe5afc26ec9f448 ] KASAN reported following bug in qed_init_qm_get_idx_from_flags due to inappropriate casting of "pq_flags". Fix the type of "pq_flags". [ 196.624707] BUG: KASAN: stack-out-of-bounds in qed_init_qm_get_idx_from_flags+0x1a4/0x1b8 [qed] [ 196.624712] Read of size 8 at addr ffff809b00bc7360 by task kworker/0:9/1712 [ 196.624714] [ 196.624720] CPU: 0 PID: 1712 Comm: kworker/0:9 Not tainted 4.18.0-60.el8.aarch64+debug #1 [ 196.624723] Hardware name: To be filled by O.E.M. Saber/Saber, BIOS 0ACKL024 09/26/2018 [ 196.624733] Workqueue: events work_for_cpu_fn [ 196.624738] Call trace: [ 196.624742] dump_backtrace+0x0/0x2f8 [ 196.624745] show_stack+0x24/0x30 [ 196.624749] dump_stack+0xe0/0x11c [ 196.624755] print_address_description+0x68/0x260 [ 196.624759] kasan_report+0x178/0x340 [ 196.624762] __asan_report_load_n_noabort+0x38/0x48 [ 196.624786] qed_init_qm_get_idx_from_flags+0x1a4/0x1b8 [qed] [ 196.624808] qed_init_qm_info+0xec0/0x2200 [qed] [ 196.624830] qed_resc_alloc+0x284/0x7e8 [qed] [ 196.624853] qed_slowpath_start+0x6cc/0x1ae8 [qed] [ 196.624864] __qede_probe.isra.10+0x1cc/0x12c0 [qede] [ 196.624874] qede_probe+0x78/0xf0 [qede] [ 196.624879] local_pci_probe+0xc4/0x180 [ 196.624882] work_for_cpu_fn+0x54/0x98 [ 196.624885] process_one_work+0x758/0x1900 [ 196.624888] worker_thread+0x4e0/0xd18 [ 196.624892] kthread+0x2c8/0x350 [ 196.624897] ret_from_fork+0x10/0x18 [ 196.624899] [ 196.624902] Allocated by task 2: [ 196.624906] kasan_kmalloc.part.1+0x40/0x108 [ 196.624909] kasan_kmalloc+0xb4/0xc8 [ 196.624913] kasan_slab_alloc+0x14/0x20 [ 196.624916] kmem_cache_alloc_node+0x1dc/0x480 [ 196.624921] copy_process.isra.1.part.2+0x1d8/0x4a98 [ 196.624924] _do_fork+0x150/0xfa0 [ 196.624926] kernel_thread+0x48/0x58 [ 196.624930] kthreadd+0x3a4/0x5a0 [ 196.624932] ret_from_fork+0x10/0x18 [ 196.624934] [ 196.624937] Freed by task 0: [ 196.624938] (stack is not available) [ 196.624940] [ 196.624943] The buggy address belongs to the object at ffff809b00bc0000 [ 196.624943] which belongs to the cache thread_stack of size 32768 [ 196.624946] The buggy address is located 29536 bytes inside of [ 196.624946] 32768-byte region [ffff809b00bc0000, ffff809b00bc8000) [ 196.624948] The buggy address belongs to the page: [ 196.624952] page:ffff7fe026c02e00 count:1 mapcount:0 mapping:ffff809b4001c000 index:0x0 compound_mapcount: 0 [ 196.624960] flags: 0xfffff8000008100(slab|head) [ 196.624967] raw: 0fffff8000008100 dead000000000100 dead000000000200 ffff809b4001c000 [ 196.624970] raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000 [ 196.624973] page dumped because: kasan: bad access detected [ 196.624974] [ 196.624976] Memory state around the buggy address: [ 196.624980] ffff809b00bc7200: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624983] ffff809b00bc7280: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624985] >ffff809b00bc7300: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 04 f2 f2 f2 [ 196.624988] ^ [ 196.624990] ffff809b00bc7380: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624993] ffff809b00bc7400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624995] ================================================================== Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_dev.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 16953c4ebd71..410528e7d927 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -435,19 +435,19 @@ static void qed_init_qm_pq(struct qed_hwfn *p_hwfn, /* get pq index according to PQ_FLAGS */ static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn, - u32 pq_flags) + unsigned long pq_flags) { struct qed_qm_info *qm_info = &p_hwfn->qm_info; /* Can't have multiple flags set here */ - if (bitmap_weight((unsigned long *)&pq_flags, + if (bitmap_weight(&pq_flags, sizeof(pq_flags) * BITS_PER_BYTE) > 1) { - DP_ERR(p_hwfn, "requested multiple pq flags 0x%x\n", pq_flags); + DP_ERR(p_hwfn, "requested multiple pq flags 0x%lx\n", pq_flags); goto err; } if (!(qed_get_pq_flags(p_hwfn) & pq_flags)) { - DP_ERR(p_hwfn, "pq flag 0x%x is not set\n", pq_flags); + DP_ERR(p_hwfn, "pq flag 0x%lx is not set\n", pq_flags); goto err; } -- GitLab From 6487e6b6d494175e1c729d13dc27e23276d8bd2c Mon Sep 17 00:00:00 2001 From: Ming Lu Date: Thu, 24 Jan 2019 13:25:42 +0800 Subject: [PATCH 0108/1128] scsi: libfc: free skb when receiving invalid flogi resp [ Upstream commit 5d8fc4a9f0eec20b6c07895022a6bea3fb6dfb38 ] The issue to be fixed in this commit is when libfc found it received a invalid FLOGI response from FC switch, it would return without freeing the fc frame, which is just the skb data. This would cause memory leak if FC switch keeps sending invalid FLOGI responses. This fix is just to make it execute `fc_frame_free(fp)` before returning from function `fc_lport_flogi_resp`. Signed-off-by: Ming Lu Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/libfc/fc_lport.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index 2fd0ec651170..ca7967e390f1 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -1739,14 +1739,14 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp, fc_frame_payload_op(fp) != ELS_LS_ACC) { FC_LPORT_DBG(lport, "FLOGI not accepted or bad response\n"); fc_lport_error(lport, fp); - goto err; + goto out; } flp = fc_frame_payload_get(fp, sizeof(*flp)); if (!flp) { FC_LPORT_DBG(lport, "FLOGI bad response\n"); fc_lport_error(lport, fp); - goto err; + goto out; } mfs = ntohs(flp->fl_csp.sp_bb_data) & @@ -1756,7 +1756,7 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp, FC_LPORT_DBG(lport, "FLOGI bad mfs:%hu response, " "lport->mfs:%hu\n", mfs, lport->mfs); fc_lport_error(lport, fp); - goto err; + goto out; } if (mfs <= lport->mfs) { -- GitLab From 84a78676bba9472d3e81fad5d74127c7ebb0c2ed Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 24 Jan 2019 13:33:27 +0300 Subject: [PATCH 0109/1128] scsi: 53c700: pass correct "dev" to dma_alloc_attrs() [ Upstream commit 8437fcf14deed67e5ad90b5e8abf62fb20f30881 ] The "hostdata->dev" pointer is NULL here. We set "hostdata->dev = dev;" later in the function and we also use "hostdata->dev" when we call dma_free_attrs() in NCR_700_release(). This bug predates git version control. Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/53c700.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index 6be77b3aa8a5..ac79f2088b31 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -295,7 +295,7 @@ NCR_700_detect(struct scsi_host_template *tpnt, if(tpnt->sdev_attrs == NULL) tpnt->sdev_attrs = NCR_700_dev_attrs; - memory = dma_alloc_attrs(hostdata->dev, TOTAL_MEM_SIZE, &pScript, + memory = dma_alloc_attrs(dev, TOTAL_MEM_SIZE, &pScript, GFP_KERNEL, DMA_ATTR_NON_CONSISTENT); if(memory == NULL) { printk(KERN_ERR "53c700: Failed to allocate memory for driver, detaching\n"); -- GitLab From b9f6c4ea3b097078c2e285fb69c67eca9061e43e Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 24 Jan 2019 19:31:01 +0000 Subject: [PATCH 0110/1128] platform/x86: Fix unmet dependency warning for SAMSUNG_Q10 [ Upstream commit 0ee4b5f801b73b83a9fb3921d725f2162fd4a2e5 ] Add BACKLIGHT_LCD_SUPPORT for SAMSUNG_Q10 to fix the warning: unmet direct dependencies detected for BACKLIGHT_CLASS_DEVICE. SAMSUNG_Q10 selects BACKLIGHT_CLASS_DEVICE but BACKLIGHT_CLASS_DEVICE depends on BACKLIGHT_LCD_SUPPORT. Copy BACKLIGHT_LCD_SUPPORT dependency into SAMSUNG_Q10 to fix: WARNING: unmet direct dependencies detected for BACKLIGHT_CLASS_DEVICE Depends on [n]: HAS_IOMEM [=y] && BACKLIGHT_LCD_SUPPORT [=n] Selected by [y]: - SAMSUNG_Q10 [=y] && X86 [=y] && X86_PLATFORM_DEVICES [=y] && ACPI [=y] Signed-off-by: Sinan Kaya Acked-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/platform/x86/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 80b87954f6dd..09035705d0a0 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -999,6 +999,7 @@ config INTEL_OAKTRAIL config SAMSUNG_Q10 tristate "Samsung Q10 Extras" depends on ACPI + depends on BACKLIGHT_LCD_SUPPORT select BACKLIGHT_CLASS_DEVICE ---help--- This driver provides support for backlight control on Samsung Q10 -- GitLab From 3c7de41bd199883c3cc04e532827fc272e99c0b0 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Tue, 29 Jan 2019 12:46:16 +1000 Subject: [PATCH 0111/1128] cifs: fix computation for MAX_SMB2_HDR_SIZE [ Upstream commit 58d15ed1203f4d858c339ea4d7dafa94bd2a56d3 ] The size of the fixed part of the create response is 88 bytes not 56. Signed-off-by: Ronnie Sahlberg Signed-off-by: Steve French Reviewed-by: Pavel Shilovsky Signed-off-by: Sasha Levin --- fs/cifs/smb2pdu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index e52454059725..bad458a2b579 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -84,8 +84,8 @@ #define NUMBER_OF_SMB2_COMMANDS 0x0013 -/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */ -#define MAX_SMB2_HDR_SIZE 0x00b0 +/* 52 transform hdr + 64 hdr + 88 create rsp */ +#define MAX_SMB2_HDR_SIZE 204 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) #define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) -- GitLab From 2f3317ddcb55b59e66c1629f39063473949ebf99 Mon Sep 17 00:00:00 2001 From: Thomas Lendacky Date: Thu, 31 Jan 2019 14:33:06 +0000 Subject: [PATCH 0112/1128] x86/microcode/amd: Don't falsely trick the late loading mechanism [ Upstream commit 912139cfbfa6a2bc1da052314d2c29338dae1f6a ] The load_microcode_amd() function searches for microcode patches and attempts to apply a microcode patch if it is of different level than the currently installed level. While the processor won't actually load a level that is less than what is already installed, the logic wrongly returns UCODE_NEW thus signaling to its caller reload_store() that a late loading should be attempted. If the file-system contains an older microcode revision than what is currently running, such a late microcode reload can result in these misleading messages: x86/CPU: CPU features have changed after loading microcode, but might not take effect. x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update. These messages were issued on a system where SME/SEV are not enabled by the BIOS (MSR C001_0010[23] = 0b) because during boot, early_detect_mem_encrypt() is called and cleared the SME and SEV features in this case. However, after the wrong late load attempt, get_cpu_cap() is called and reloads the SME and SEV feature bits, resulting in the messages. Update the microcode level check to not attempt microcode loading if the current level is greater than(!) and not only equal to the current patch level. [ bp: massage commit message. ] Fixes: 2613f36ed965 ("x86/microcode: Attempt late loading only when new microcode is present") Signed-off-by: Tom Lendacky Signed-off-by: Borislav Petkov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/154894518427.9406.8246222496874202773.stgit@tlendack-t1.amdoffice.net Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/microcode/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 9d33dbf2489e..d0a61d3e2fb9 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -707,7 +707,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) if (!p) { return ret; } else { - if (boot_cpu_data.microcode == p->patch_id) + if (boot_cpu_data.microcode >= p->patch_id) return ret; ret = UCODE_NEW; -- GitLab From c72b4dcd26795d6941db0cedd2c2212bb9b32d2f Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 24 Jan 2019 16:32:55 +0000 Subject: [PATCH 0113/1128] arm64: kprobe: Always blacklist the KVM world-switch code [ Upstream commit f2b3d8566d81deaca31f4e3163def0bea7746e11 ] On systems with VHE the kernel and KVM's world-switch code run at the same exception level. Code that is only used on a VHE system does not need to be annotated as __hyp_text as it can reside anywhere in the kernel text. __hyp_text was also used to prevent kprobes from patching breakpoint instructions into this region, as this code runs at a different exception level. While this is no longer true with VHE, KVM still switches VBAR_EL1, meaning a kprobe's breakpoint executed in the world-switch code will cause a hyp-panic. Move the __hyp_text check in the kprobes blacklist so it applies on VHE systems too, to cover the common code and guest enter/exit assembly. Fixes: 888b3c8720e0 ("arm64: Treat all entry code as non-kprobe-able") Reviewed-by: Christoffer Dall Signed-off-by: James Morse Acked-by: Masami Hiramatsu Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/kernel/probes/kprobes.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 0417c929d21a..7d8c33279e9f 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -554,13 +554,13 @@ bool arch_within_kprobe_blacklist(unsigned long addr) addr < (unsigned long)__entry_text_end) || (addr >= (unsigned long)__idmap_text_start && addr < (unsigned long)__idmap_text_end) || + (addr >= (unsigned long)__hyp_text_start && + addr < (unsigned long)__hyp_text_end) || !!search_exception_tables(addr)) return true; if (!is_kernel_in_hyp_mode()) { - if ((addr >= (unsigned long)__hyp_text_start && - addr < (unsigned long)__hyp_text_end) || - (addr >= (unsigned long)__hyp_idmap_text_start && + if ((addr >= (unsigned long)__hyp_idmap_text_start && addr < (unsigned long)__hyp_idmap_text_end)) return true; } -- GitLab From 865c798a37bfacafd35e6c0f2d5d5e5bb572a07d Mon Sep 17 00:00:00 2001 From: John Johansen Date: Thu, 24 Jan 2019 13:53:05 -0800 Subject: [PATCH 0114/1128] apparmor: Fix aa_label_build() error handling for failed merges [ Upstream commit d6d478aee003e19ef90321176552a8ad2929a47f ] aa_label_merge() can return NULL for memory allocations failures make sure to handle and set the correct error in this case. Reported-by: Peng Hao Signed-off-by: John Johansen Signed-off-by: Sasha Levin --- security/apparmor/domain.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index dd754b7850a8..67bf8b7ee8a2 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -1260,7 +1260,10 @@ int aa_change_profile(const char *fqname, int flags) aa_get_label(&profile->label)); if (IS_ERR_OR_NULL(new)) { info = "failed to build target label"; - error = PTR_ERR(new); + if (!new) + error = -ENOMEM; + else + error = PTR_ERR(new); new = NULL; perms.allow = 0; goto audit; -- GitLab From 21b202b7ca599edb5fb39afcfcffae6e6dbb6ec3 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Fri, 18 Jan 2019 19:13:08 +0800 Subject: [PATCH 0115/1128] x86/kexec: Don't setup EFI info if EFI runtime is not enabled [ Upstream commit 2aa958c99c7fd3162b089a1a56a34a0cdb778de1 ] Kexec-ing a kernel with "efi=noruntime" on the first kernel's command line causes the following null pointer dereference: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] Call Trace: efi_runtime_map_copy+0x28/0x30 bzImage64_load+0x688/0x872 arch_kexec_kernel_image_load+0x6d/0x70 kimage_file_alloc_init+0x13e/0x220 __x64_sys_kexec_file_load+0x144/0x290 do_syscall_64+0x55/0x1a0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Just skip the EFI info setup if EFI runtime services are not enabled. [ bp: Massage commit message. ] Suggested-by: Dave Young Signed-off-by: Kairui Song Signed-off-by: Borislav Petkov Acked-by: Dave Young Cc: AKASHI Takahiro Cc: Andrew Morton Cc: Ard Biesheuvel Cc: bhe@redhat.com Cc: David Howells Cc: erik.schmauss@intel.com Cc: fanc.fnst@cn.fujitsu.com Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: kexec@lists.infradead.org Cc: lenb@kernel.org Cc: linux-acpi@vger.kernel.org Cc: Philipp Rudo Cc: rafael.j.wysocki@intel.com Cc: robert.moore@intel.com Cc: Thomas Gleixner Cc: x86-ml Cc: Yannik Sembritzki Link: https://lkml.kernel.org/r/20190118111310.29589-2-kasong@redhat.com Signed-off-by: Sasha Levin --- arch/x86/kernel/kexec-bzimage64.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 928b0c6083c9..4d948d87f01c 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -167,6 +167,9 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr, struct efi_info *current_ei = &boot_params.efi_info; struct efi_info *ei = ¶ms->efi_info; + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return 0; + if (!current_ei->efi_memmap_size) return 0; -- GitLab From 6b6cd12509424e4e6c25569f55482a83e6cf0b5b Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 1 Feb 2019 14:20:20 -0800 Subject: [PATCH 0116/1128] x86_64: increase stack size for KASAN_EXTRA [ Upstream commit a8e911d13540487942d53137c156bd7707f66e5d ] If the kernel is configured with KASAN_EXTRA, the stack size is increasted significantly because this option sets "-fstack-reuse" to "none" in GCC [1]. As a result, it triggers stack overrun quite often with 32k stack size compiled using GCC 8. For example, this reproducer https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/syscalls/madvise/madvise06.c triggers a "corrupted stack end detected inside scheduler" very reliably with CONFIG_SCHED_STACK_END_CHECK enabled. There are just too many functions that could have a large stack with KASAN_EXTRA due to large local variables that have been called over and over again without being able to reuse the stacks. Some noticiable ones are size 7648 shrink_page_list 3584 xfs_rmap_convert 3312 migrate_page_move_mapping 3312 dev_ethtool 3200 migrate_misplaced_transhuge_page 3168 copy_process There are other 49 functions are over 2k in size while compiling kernel with "-Wframe-larger-than=" even with a related minimal config on this machine. Hence, it is too much work to change Makefiles for each object to compile without "-fsanitize-address-use-after-scope" individually. [1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715#c23 Although there is a patch in GCC 9 to help the situation, GCC 9 probably won't be released in a few months and then it probably take another 6-month to 1-year for all major distros to include it as a default. Hence, the stack usage with KASAN_EXTRA can be revisited again in 2020 when GCC 9 is everywhere. Until then, this patch will help users avoid stack overrun. This has already been fixed for arm64 for the same reason via 6e8830674ea ("arm64: kasan: Increase stack size for KASAN_EXTRA"). Link: http://lkml.kernel.org/r/20190109215209.2903-1-cai@lca.pw Signed-off-by: Qian Cai Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- arch/x86/include/asm/page_64_types.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 74d531f6d518..50c8baaca4b0 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -7,7 +7,11 @@ #endif #ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_EXTRA +#define KASAN_STACK_ORDER 2 +#else #define KASAN_STACK_ORDER 1 +#endif #else #define KASAN_STACK_ORDER 0 #endif -- GitLab From 659052d1f16e0c3af60a371fa0147c007eba5a97 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 1 Feb 2019 14:20:34 -0800 Subject: [PATCH 0117/1128] mm, memory_hotplug: is_mem_section_removable do not pass the end of a zone [ Upstream commit efad4e475c312456edb3c789d0996d12ed744c13 ] Patch series "mm, memory_hotplug: fix uninitialized pages fallouts", v2. Mikhail Zaslonko has posted fixes for the two bugs quite some time ago [1]. I have pushed back on those fixes because I believed that it is much better to plug the problem at the initialization time rather than play whack-a-mole all over the hotplug code and find all the places which expect the full memory section to be initialized. We have ended up with commit 2830bf6f05fb ("mm, memory_hotplug: initialize struct pages for the full memory section") merged and cause a regression [2][3]. The reason is that there might be memory layouts when two NUMA nodes share the same memory section so the merged fix is simply incorrect. In order to plug this hole we really have to be zone range aware in those handlers. I have split up the original patch into two. One is unchanged (patch 2) and I took a different approach for `removable' crash. [1] http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com [2] https://bugzilla.redhat.com/show_bug.cgi?id=1666948 [3] http://lkml.kernel.org/r/20190125163938.GA20411@dhcp22.suse.cz This patch (of 2): Mikhail has reported the following VM_BUG_ON triggered when reading sysfs removable state of a memory block: page:000003d08300c000 is uninitialized and poisoned page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) Call Trace: is_mem_section_removable+0xb4/0x190 show_mem_removable+0x9a/0xd8 dev_attr_show+0x34/0x70 sysfs_kf_seq_show+0xc8/0x148 seq_read+0x204/0x480 __vfs_read+0x32/0x178 vfs_read+0x82/0x138 ksys_read+0x5a/0xb0 system_call+0xdc/0x2d8 Last Breaking-Event-Address: is_mem_section_removable+0xb4/0x190 Kernel panic - not syncing: Fatal exception: panic_on_oops The reason is that the memory block spans the zone boundary and we are stumbling over an unitialized struct page. Fix this by enforcing zone range in is_mem_section_removable so that we never run away from a zone. Link: http://lkml.kernel.org/r/20190128144506.15603-2-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Mikhail Zaslonko Debugged-by: Mikhail Zaslonko Tested-by: Gerald Schaefer Tested-by: Mikhail Gavrilov Reviewed-by: Oscar Salvador Cc: Pavel Tatashin Cc: Heiko Carstens Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- mm/memory_hotplug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c7c74a927d6f..39db89f3df65 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1256,7 +1256,8 @@ static struct page *next_active_pageblock(struct page *page) bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { struct page *page = pfn_to_page(start_pfn); - struct page *end_page = page + nr_pages; + unsigned long end_pfn = min(start_pfn + nr_pages, zone_end_pfn(page_zone(page))); + struct page *end_page = pfn_to_page(end_pfn); /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { -- GitLab From d83382c6c3c751867dbbadd0d4a2740ba028dd85 Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Fri, 1 Feb 2019 14:20:38 -0800 Subject: [PATCH 0118/1128] mm, memory_hotplug: test_pages_in_a_zone do not pass the end of zone [ Upstream commit 24feb47c5fa5b825efb0151f28906dfdad027e61 ] If memory end is not aligned with the sparse memory section boundary, the mapping of such a section is only partly initialized. This may lead to VM_BUG_ON due to uninitialized struct pages access from test_pages_in_a_zone() function triggered by memory_hotplug sysfs handlers. Here are the the panic examples: CONFIG_DEBUG_VM_PGFLAGS=y kernel parameter mem=2050M -------------------------- page:000003d082008000 is uninitialized and poisoned page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) Call Trace: test_pages_in_a_zone+0xde/0x160 show_valid_zones+0x5c/0x190 dev_attr_show+0x34/0x70 sysfs_kf_seq_show+0xc8/0x148 seq_read+0x204/0x480 __vfs_read+0x32/0x178 vfs_read+0x82/0x138 ksys_read+0x5a/0xb0 system_call+0xdc/0x2d8 Last Breaking-Event-Address: test_pages_in_a_zone+0xde/0x160 Kernel panic - not syncing: Fatal exception: panic_on_oops Fix this by checking whether the pfn to check is within the zone. [mhocko@suse.com: separated this change from http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com] Link: http://lkml.kernel.org/r/20190128144506.15603-3-mhocko@kernel.org [mhocko@suse.com: separated this change from http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com] Signed-off-by: Michal Hocko Signed-off-by: Mikhail Zaslonko Tested-by: Mikhail Gavrilov Reviewed-by: Oscar Salvador Tested-by: Gerald Schaefer Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Mikhail Gavrilov Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- mm/memory_hotplug.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 39db89f3df65..c9d3a49bd4e2 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1297,6 +1297,9 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, i++; if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) continue; + /* Check if we got outside of the zone */ + if (zone && !zone_spans_pfn(zone, pfn + i)) + return 0; page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) return 0; -- GitLab From 8d5b25551442ea58b129fb9a0a1c439894ceec0f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 1 Feb 2019 14:20:58 -0800 Subject: [PATCH 0119/1128] lib/test_kmod.c: potential double free in error handling [ Upstream commit db7ddeab3ce5d64c9696e70d61f45ea9909cd196 ] There is a copy and paste bug so we set "config->test_driver" to NULL twice instead of setting "config->test_fs". Smatch complains that it leads to a double free: lib/test_kmod.c:840 __kmod_config_init() warn: 'config->test_fs' double freed Link: http://lkml.kernel.org/r/20190121140011.GA14283@kadam Fixes: d9c6a72d6fa2 ("kmod: add test driver to stress test the module loader") Signed-off-by: Dan Carpenter Acked-by: Luis Chamberlain Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- lib/test_kmod.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/test_kmod.c b/lib/test_kmod.c index 7abb59ce6613..cf619795a182 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -632,7 +632,7 @@ static void __kmod_config_free(struct test_config *config) config->test_driver = NULL; kfree_const(config->test_fs); - config->test_driver = NULL; + config->test_fs = NULL; } static void kmod_config_free(struct kmod_test_device *test_dev) -- GitLab From 9c72acbe4940e1a542336daf9be2ca6493788e67 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 1 Feb 2019 14:21:23 -0800 Subject: [PATCH 0120/1128] fs/drop_caches.c: avoid softlockups in drop_pagecache_sb() [ Upstream commit c27d82f52f75fc9d8d9d40d120d2a96fdeeada5e ] When superblock has lots of inodes without any pagecache (like is the case for /proc), drop_pagecache_sb() will iterate through all of them without dropping sb->s_inode_list_lock which can lead to softlockups (one of our customers hit this). Fix the problem by going to the slow path and doing cond_resched() in case the process needs rescheduling. Link: http://lkml.kernel.org/r/20190114085343.15011-1-jack@suse.cz Signed-off-by: Jan Kara Acked-by: Michal Hocko Reviewed-by: Andrew Morton Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/drop_caches.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 82377017130f..d31b6c72b476 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -21,8 +21,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); + /* + * We must skip inodes in unusual state. We may also skip + * inodes without pages but we deliberately won't in case + * we need to reschedule to avoid softlockups. + */ if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || - (inode->i_mapping->nrpages == 0)) { + (inode->i_mapping->nrpages == 0 && !need_resched())) { spin_unlock(&inode->i_lock); continue; } @@ -30,6 +35,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); + cond_resched(); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; -- GitLab From 327e34dfa9945f61db8f340e5a67907df1770c0d Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Fri, 1 Feb 2019 14:21:26 -0800 Subject: [PATCH 0121/1128] autofs: drop dentry reference only when it is never used [ Upstream commit 63ce5f552beb9bdb41546b3a26c4374758b21815 ] autofs_expire_run() calls dput(dentry) to drop the reference count of dentry. However, dentry is read via autofs_dentry_ino(dentry) after that. This may result in a use-free-bug. The patch drops the reference count of dentry only when it is never used. Link: http://lkml.kernel.org/r/154725122396.11260.16053424107144453867.stgit@pluto-themaw-net Signed-off-by: Pan Bian Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/autofs4/expire.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 57725d4a8c59..141f9bc213a3 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -567,7 +567,6 @@ int autofs4_expire_run(struct super_block *sb, pkt.len = dentry->d_name.len; memcpy(pkt.name, dentry->d_name.name, pkt.len); pkt.name[pkt.len] = '\0'; - dput(dentry); if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire))) ret = -EFAULT; @@ -580,6 +579,8 @@ int autofs4_expire_run(struct super_block *sb, complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); + dput(dentry); + return ret; } -- GitLab From 70e6e8e8ee2ac2846af14676d3cffaa78e40631a Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Fri, 1 Feb 2019 14:21:29 -0800 Subject: [PATCH 0122/1128] autofs: fix error return in autofs_fill_super() [ Upstream commit f585b283e3f025754c45bbe7533fc6e5c4643700 ] In autofs_fill_super() on error of get inode/make root dentry the return should be ENOMEM as this is the only failure case of the called functions. Link: http://lkml.kernel.org/r/154725123240.11260.796773942606871359.stgit@pluto-themaw-net Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/autofs4/inode.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 3c7e727612fa..e455388a939c 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -259,8 +259,10 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) } root_inode = autofs4_get_inode(s, S_IFDIR | 0755); root = d_make_root(root_inode); - if (!root) + if (!root) { + ret = -ENOMEM; goto fail_ino; + } pipe = NULL; root->d_fsdata = ino; -- GitLab From 9cb9f1d9d9f76860e8d570f5e8527ccc6920fa7d Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 7 Jan 2019 09:52:43 -0800 Subject: [PATCH 0123/1128] ARM: dts: omap4-droid4: Fix typo in cpcap IRQ flags [ Upstream commit ef4a55b9197a8f844ea0663138e902dcce3e2f36 ] We're now getting the following error: genirq: Setting trigger mode 1 for irq 230 failed (regmap_irq_set_type+0x0/0x15c) cpcap-usb-phy cpcap-usb-phy.0: could not get irq dp: -524 Cc: Sebastian Reichel Reported-by: Pavel Machek Tested-by: Pavel Machek Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi index 4d61e5b1334a..bcced922b280 100644 --- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi +++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi @@ -92,7 +92,7 @@ interrupts-extended = < &cpcap 15 0 &cpcap 14 0 &cpcap 28 0 &cpcap 19 0 &cpcap 18 0 &cpcap 17 0 &cpcap 16 0 &cpcap 49 0 - &cpcap 48 1 + &cpcap 48 0 >; interrupt-names = "id_ground", "id_float", "se0conn", "vbusvld", -- GitLab From 703db5d1b1759fd2aec0ce3c3b6f6c4262a1433d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 10 Jan 2019 14:39:15 +0100 Subject: [PATCH 0124/1128] arm64: dts: renesas: r8a7796: Enable DMA for SCIF2 [ Upstream commit 97f26702bc95b5c3a72671d5c6675e4d6ee0a2f4 ] SCIF2 on R-Car M3-W can be used with both DMAC1 and DMAC2. Fixes: dbcae5ea4bd27409 ("arm64: dts: r8a7796: Enable SCIF DMA") Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/renesas/r8a7796.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/renesas/r8a7796.dtsi b/arch/arm64/boot/dts/renesas/r8a7796.dtsi index 369092e17e34..016b84552a62 100644 --- a/arch/arm64/boot/dts/renesas/r8a7796.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7796.dtsi @@ -937,6 +937,9 @@ <&cpg CPG_CORE R8A7796_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; -- GitLab From 27a0e499a313796fbc56b0ba7d2d2171cc3d4ac3 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Fri, 21 Dec 2018 16:41:42 +0200 Subject: [PATCH 0125/1128] soc: fsl: qbman: avoid race in clearing QMan interrupt [ Upstream commit 89857a8a5c89a406b967ab2be7bd2ccdbe75e73d ] By clearing all interrupt sources, not only those that already occurred, the existing code may acknowledge by mistake interrupts that occurred after the code checks for them. Signed-off-by: Madalin Bucur Signed-off-by: Roy Pledge Signed-off-by: Li Yang Signed-off-by: Sasha Levin --- drivers/soc/fsl/qbman/qman.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 4f27e95efcdd..90892a360c61 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -1048,18 +1048,19 @@ static void qm_mr_process_task(struct work_struct *work); static irqreturn_t portal_isr(int irq, void *ptr) { struct qman_portal *p = ptr; - - u32 clear = QM_DQAVAIL_MASK | p->irq_sources; u32 is = qm_in(&p->p, QM_REG_ISR) & p->irq_sources; + u32 clear = 0; if (unlikely(!is)) return IRQ_NONE; /* DQRR-handling if it's interrupt-driven */ - if (is & QM_PIRQ_DQRI) + if (is & QM_PIRQ_DQRI) { __poll_portal_fast(p, QMAN_POLL_LIMIT); + clear = QM_DQAVAIL_MASK | QM_PIRQ_DQRI; + } /* Handling of anything else that's interrupt-driven */ - clear |= __poll_portal_slow(p, is); + clear |= __poll_portal_slow(p, is) & QM_PIRQ_SLOW; qm_out(&p->p, QM_REG_ISR, clear); return IRQ_HANDLED; } -- GitLab From d74f30ef8972099e2bcc1c8a212f9418c6eebd7c Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Wed, 23 Jan 2019 12:37:19 +0800 Subject: [PATCH 0126/1128] bpf: sock recvbuff must be limited by rmem_max in bpf_setsockopt() [ Upstream commit c9e4576743eeda8d24dedc164d65b78877f9a98c ] When sock recvbuff is set by bpf_setsockopt(), the value must by limited by rmem_max. It is the same with sendbuff. Fixes: 8c4b4c7e9ff0 ("bpf: Add setsockopt helper function to bpf") Signed-off-by: Yafang Shao Acked-by: Martin KaFai Lau Acked-by: Lawrence Brakmo Signed-off-by: Daniel Borkmann Signed-off-by: Sasha Levin --- net/core/filter.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/filter.c b/net/core/filter.c index 41ede90fc28f..61396648381e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3081,10 +3081,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, /* Only some socketops are supported */ switch (optname) { case SO_RCVBUF: + val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_SNDBUF: + val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); break; -- GitLab From 7031b8ca7fde45b8d7d53d12b9454c8dd2d795ed Mon Sep 17 00:00:00 2001 From: Peng Hao Date: Sat, 29 Dec 2018 13:10:06 +0800 Subject: [PATCH 0127/1128] ARM: pxa: ssp: unneeded to free devm_ allocated data [ Upstream commit ba16adeb346387eb2d1ada69003588be96f098fa ] devm_ allocated data will be automatically freed. The free of devm_ allocated data is invalid. Fixes: 1c459de1e645 ("ARM: pxa: ssp: use devm_ functions") Signed-off-by: Peng Hao [title's prefix changed] Signed-off-by: Robert Jarzmik Signed-off-by: Sasha Levin --- arch/arm/plat-pxa/ssp.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c index ba13f793fbce..b92673efffff 100644 --- a/arch/arm/plat-pxa/ssp.c +++ b/arch/arm/plat-pxa/ssp.c @@ -237,8 +237,6 @@ static int pxa_ssp_remove(struct platform_device *pdev) if (ssp == NULL) return -ENODEV; - iounmap(ssp->mmio_base); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); release_mem_region(res->start, resource_size(res)); @@ -248,7 +246,6 @@ static int pxa_ssp_remove(struct platform_device *pdev) list_del(&ssp->node); mutex_unlock(&ssp_lock); - kfree(ssp); return 0; } -- GitLab From 5a6e25e1e9b84b790ec013c13c56e8de0d1e0843 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Mon, 10 Dec 2018 13:56:33 +0000 Subject: [PATCH 0128/1128] arm64: dts: add msm8996 compatible to gicv3 [ Upstream commit 2a81efb0de0e33f2d2c83154af0bd3ce389b3269 ] Add compatible to gicv3 node to enable quirk required to restrict writing to GICR_WAKER register which is restricted on msm8996 SoC in Hypervisor. With this quirk MSM8996 can at least boot out of mainline, which can help community to work with boards based on MSM8996. Without this patch Qualcomm DB820c board reboots on mainline. Signed-off-by: Srinivas Kandagatla Signed-off-by: Andy Gross Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8996.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index ab00be277c6f..6f372ec055dd 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -359,7 +359,7 @@ }; intc: interrupt-controller@9bc0000 { - compatible = "arm,gic-v3"; + compatible = "qcom,msm8996-gic-v3", "arm,gic-v3"; #interrupt-cells = <3>; interrupt-controller; #redistributor-regions = <1>; -- GitLab From f01ebdb120b292335ffdd51be04e630fae5dfdfb Mon Sep 17 00:00:00 2001 From: Zhou Yanjie Date: Fri, 25 Jan 2019 02:22:15 +0800 Subject: [PATCH 0129/1128] DTS: CI20: Fix bugs in ci20's device tree. [ Upstream commit 1ca1c87f91d9dc50d6a38e2177b2032996e7901c ] According to the Schematic, the hardware of ci20 leads to uart3, but not to uart2. Uart2 is miswritten in the original code. Signed-off-by: Zhou Yanjie Signed-off-by: Paul Burton Cc: linux-mips Cc: linux-kernel Cc: devicetree@vger.kernel.org Cc: robh+dt@kernel.org Cc: ralf@linux-mips.org Cc: jhogan@kernel.org Cc: mark.rutland@arm.com Cc: malat@debian.org Cc: ezequiel@collabora.co.uk Cc: ulf.hansson@linaro.org Cc: syq Cc: jiaxun.yang Signed-off-by: Sasha Levin --- arch/mips/boot/dts/ingenic/ci20.dts | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index a4cc52214dbd..dad4aa0ebdd8 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -54,7 +54,7 @@ status = "okay"; pinctrl-names = "default"; - pinctrl-0 = <&pins_uart2>; + pinctrl-0 = <&pins_uart3>; }; &uart4 { @@ -174,9 +174,9 @@ bias-disable; }; - pins_uart2: uart2 { - function = "uart2"; - groups = "uart2-data", "uart2-hwflow"; + pins_uart3: uart3 { + function = "uart3"; + groups = "uart3-data", "uart3-hwflow"; bias-disable; }; -- GitLab From ecfcdee1e9d57fd0d3e38e9491510307358dc9d3 Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Tue, 22 Jan 2019 11:36:02 +0100 Subject: [PATCH 0130/1128] usb: phy: fix link errors [ Upstream commit f2105d42597f4d10e431b195d69e96dccaf9b012 ] Fix link errors when CONFIG_FSL_USB2_OTG is enabled and USB_OTG_FSM is set to module then the following link error occurs. aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `fsl_otg_ioctl': drivers/usb/phy/phy-fsl-usb.c:1083: undefined reference to `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.c:1083:(.text+0x574): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `fsl_otg_start_srp': drivers/usb/phy/phy-fsl-usb.c:674: undefined reference to `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.c:674:(.text+0x61c): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `fsl_otg_set_host': drivers/usb/phy/phy-fsl-usb.c:593: undefined reference to `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.c:593:(.text+0x7a4): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `fsl_otg_start_hnp': drivers/usb/phy/phy-fsl-usb.c:695: undefined reference to `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.c:695:(.text+0x858): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `a_wait_enum': drivers/usb/phy/phy-fsl-usb.c:274: undefined reference to `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.c:274:(.text+0x16f0): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o:drivers/usb/phy/phy-fsl-usb.c:619: more undefined references to `otg_statemachine' follow aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `fsl_otg_set_peripheral': drivers/usb/phy/phy-fsl-usb.c:619:(.text+0x1fa0): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' make[1]: *** [Makefile:1020: vmlinux] Error 1 make[1]: Target 'Image' not remade because of errors. make: *** [Makefile:152: sub-make] Error 2 make: Target 'Image' not remade because of errors. Rework so that FSL_USB2_OTG depends on that the USB_OTG_FSM is builtin. Signed-off-by: Anders Roxell Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/phy/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig index aff702c0eb9f..85a92d0813dd 100644 --- a/drivers/usb/phy/Kconfig +++ b/drivers/usb/phy/Kconfig @@ -21,7 +21,7 @@ config AB8500_USB config FSL_USB2_OTG bool "Freescale USB OTG Transceiver Driver" - depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM && PM + depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM=y && PM depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' select USB_PHY help -- GitLab From 18579f6965137f4c134e22b8dd906eba8a712dfc Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Mon, 28 Jan 2019 16:59:35 +0100 Subject: [PATCH 0131/1128] irqchip/mmp: Only touch the PJ4 IRQ & FIQ bits on enable/disable [ Upstream commit 2380a22b60ce6f995eac806e69c66e397b59d045 ] Resetting bit 4 disables the interrupt delivery to the "secure processor" core. This breaks the keyboard on a OLPC XO 1.75 laptop, where the firmware running on the "secure processor" bit-bangs the PS/2 protocol over the GPIO lines. It is not clear what the rest of the bits are and Marvell was unhelpful when asked for documentation. Aside from the SP bit, there are probably priority bits. Leaving the unknown bits as the firmware set them up seems to be a wiser course of action compared to just turning them off. Signed-off-by: Lubomir Rintel Acked-by: Pavel Machek [maz: fixed-up subject and commit message] Signed-off-by: Marc Zyngier Signed-off-by: Sasha Levin --- drivers/irqchip/irq-mmp.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c index 25f32e1d7764..3496b61a312a 100644 --- a/drivers/irqchip/irq-mmp.c +++ b/drivers/irqchip/irq-mmp.c @@ -34,6 +34,9 @@ #define SEL_INT_PENDING (1 << 6) #define SEL_INT_NUM_MASK 0x3f +#define MMP2_ICU_INT_ROUTE_PJ4_IRQ (1 << 5) +#define MMP2_ICU_INT_ROUTE_PJ4_FIQ (1 << 6) + struct icu_chip_data { int nr_irqs; unsigned int virq_base; @@ -190,7 +193,8 @@ static const struct mmp_intc_conf mmp_conf = { static const struct mmp_intc_conf mmp2_conf = { .conf_enable = 0x20, .conf_disable = 0x0, - .conf_mask = 0x7f, + .conf_mask = MMP2_ICU_INT_ROUTE_PJ4_IRQ | + MMP2_ICU_INT_ROUTE_PJ4_FIQ, }; static void __exception_irq_entry mmp_handle_irq(struct pt_regs *regs) -- GitLab From 13e429213f160a92780d9144bfdfe286e9ff6a84 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 30 Jan 2019 15:54:19 +0100 Subject: [PATCH 0132/1128] net: stmmac: Fallback to Platform Data clock in Watchdog conversion [ Upstream commit 4ec5302fa906ec9d86597b236f62315bacdb9622 ] If we don't have DT then stmmac_clk will not be available. Let's add a new Platform Data field so that we can specify the refclk by this mean. This way we can still use the coalesce command in PCI based setups. Signed-off-by: Jose Abreu Cc: Joao Pinto Cc: David S. Miller Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 14 ++++++++++---- include/linux/stmmac.h | 1 + 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index c3c6335cbe9a..ecddd9948788 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -702,8 +702,11 @@ static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (usec * (clk / 1000000)) / 256; } @@ -712,8 +715,11 @@ static u32 stmmac_riwt2usec(u32 riwt, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (riwt * 256) / (clk / 1000000); } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 32feac5bbd75..5844105a482b 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -183,6 +183,7 @@ struct plat_stmmacenet_data { struct clk *pclk; struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; + unsigned int clk_ref_rate; struct reset_control *stmmac_rst; struct stmmac_axi *axi; int has_gmac4; -- GitLab From 405bff8e8799005ac56c901c78f222e3c7e0375c Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 30 Jan 2019 15:54:20 +0100 Subject: [PATCH 0133/1128] net: stmmac: Send TSO packets always from Queue 0 [ Upstream commit c5acdbee22a1b200dde07effd26fd1f649e9ab8a ] The number of TSO enabled channels in HW can be different than the number of total channels. There is no way to determined, at runtime, the number of TSO capable channels and its safe to assume that if TSO is enabled then at least channel 0 will be TSO capable. Lets always send TSO packets from Queue 0. Signed-off-by: Jose Abreu Cc: Joao Pinto Cc: David S. Miller Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 0e66a5082140..b1454c63e675 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3019,8 +3019,17 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { - if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) + if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { + /* + * There is no way to determine the number of TSO + * capable Queues. Let's use always the Queue 0 + * because if TSO is supported then at least this + * one will be capable. + */ + skb_set_queue_mapping(skb, 0); + return stmmac_tso_xmit(skb, dev); + } } if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) { -- GitLab From a63215cb5311d48bf7c5d9c26b6f4e08f33ac74e Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 30 Jan 2019 15:54:21 +0100 Subject: [PATCH 0134/1128] net: stmmac: Disable EEE mode earlier in XMIT callback [ Upstream commit e2cd682deb231ba6f80524bb84e57e7138261149 ] In stmmac xmit callback we use a different flow for TSO packets but TSO xmit callback is not disabling the EEE mode. Fix this by disabling earlier the EEE mode, i.e. before calling the TSO xmit callback. Signed-off-by: Jose Abreu Cc: Joao Pinto Cc: David S. Miller Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b1454c63e675..0cc83e8417ef 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3017,6 +3017,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) tx_q = &priv->tx_queue[queue]; + if (priv->tx_path_in_lpi_mode) + stmmac_disable_eee_mode(priv); + /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { @@ -3044,9 +3047,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } - if (priv->tx_path_in_lpi_mode) - stmmac_disable_eee_mode(priv); - entry = tx_q->cur_tx; first_entry = entry; -- GitLab From 8939e8cdd004ba5d7dd3bbf9c105990f9ebe96f8 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Thu, 31 Jan 2019 11:19:43 +0000 Subject: [PATCH 0135/1128] irqchip/gic-v3-its: Fix ITT_entry_size accessor [ Upstream commit 56841070ccc87b463ac037d2d1f2beb8e5e35f0c ] According to ARM IHI 0069C (ID070116), we should use GITS_TYPER's bits [7:4] as ITT_entry_size instead of [8:4]. Although this is pretty annoying, it only results in a potential over-allocation of memory, and nothing bad happens. Fixes: 3dfa576bfb45 ("irqchip/gic-v3-its: Add probing for VLPI properties") Signed-off-by: Zenghui Yu [maz: massaged subject and commit message] Signed-off-by: Marc Zyngier Signed-off-by: Sasha Levin --- include/linux/irqchip/arm-gic-v3.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index bacb499c512c..845ff8c51564 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -306,7 +306,7 @@ #define GITS_TYPER_PLPIS (1UL << 0) #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 -#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1) +#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) -- GitLab From 167a0989ec15a0b738dc8fd25922b1fae00c0dba Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 31 Jan 2019 13:57:58 +0100 Subject: [PATCH 0136/1128] relay: check return of create_buf_file() properly [ Upstream commit 2c1cf00eeacb784781cf1c9896b8af001246d339 ] If create_buf_file() returns an error, don't try to reference it later as a valid dentry pointer. This problem was exposed when debugfs started to return errors instead of just NULL for some calls when they do not succeed properly. Also, the check for WARN_ON(dentry) was just wrong :) Reported-by: Kees Cook Reported-and-tested-by: syzbot+16c3a70e1e9b29346c43@syzkaller.appspotmail.com Reported-by: Tetsuo Handa Cc: Andrew Morton Cc: David Rientjes Fixes: ff9fb72bc077 ("debugfs: return error values, not NULL") Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- kernel/relay.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/relay.c b/kernel/relay.c index 1537158c67b3..61d37e6da22d 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -427,6 +427,8 @@ static struct dentry *relay_create_buf_file(struct rchan *chan, dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR, buf, &chan->is_global); + if (IS_ERR(dentry)) + dentry = NULL; kfree(tmpname); @@ -460,7 +462,7 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu) dentry = chan->cb->create_buf_file(NULL, NULL, S_IRUSR, buf, &chan->is_global); - if (WARN_ON(dentry)) + if (IS_ERR_OR_NULL(dentry)) goto free_buf; } -- GitLab From 3084058a72e297e7dbce277b8161fc323d087d1d Mon Sep 17 00:00:00 2001 From: Martynas Pumputis Date: Thu, 31 Jan 2019 10:19:33 +0100 Subject: [PATCH 0137/1128] bpf, selftests: fix handling of sparse CPU allocations [ Upstream commit 1bb54c4071f585ebef56ce8fdfe6026fa2cbcddd ] Previously, bpf_num_possible_cpus() had a bug when calculating a number of possible CPUs in the case of sparse CPU allocations, as it was considering only the first range or element of /sys/devices/system/cpu/possible. E.g. in the case of "0,2-3" (CPU 1 is not available), the function returned 1 instead of 3. This patch fixes the function by making it parse all CPU ranges and elements. Signed-off-by: Martynas Pumputis Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/bpf_util.h | 30 +++++++++++++++++--------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index d0811b3d6a6f..4bf720364934 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -13,7 +13,7 @@ static inline unsigned int bpf_num_possible_cpus(void) unsigned int start, end, possible_cpus = 0; char buff[128]; FILE *fp; - int n; + int len, n, i, j = 0; fp = fopen(fcpu, "r"); if (!fp) { @@ -21,17 +21,27 @@ static inline unsigned int bpf_num_possible_cpus(void) exit(1); } - while (fgets(buff, sizeof(buff), fp)) { - n = sscanf(buff, "%u-%u", &start, &end); - if (n == 0) { - printf("Failed to retrieve # possible CPUs!\n"); - exit(1); - } else if (n == 1) { - end = start; + if (!fgets(buff, sizeof(buff), fp)) { + printf("Failed to read %s!\n", fcpu); + exit(1); + } + + len = strlen(buff); + for (i = 0; i <= len; i++) { + if (buff[i] == ',' || buff[i] == '\0') { + buff[i] = '\0'; + n = sscanf(&buff[j], "%u-%u", &start, &end); + if (n <= 0) { + printf("Failed to retrieve # possible CPUs!\n"); + exit(1); + } else if (n == 1) { + end = start; + } + possible_cpus += end - start + 1; + j = i + 1; } - possible_cpus = start == 0 ? end + 1 : 0; - break; } + fclose(fp); return possible_cpus; -- GitLab From dcab2483a1a3eff37411377202837d8a473d885f Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 30 Jan 2019 18:12:43 -0800 Subject: [PATCH 0138/1128] bpf: fix lockdep false positive in percpu_freelist [ Upstream commit a89fac57b5d080771efd4d71feaae19877cf68f0 ] Lockdep warns about false positive: [ 12.492084] 00000000e6b28347 (&head->lock){+...}, at: pcpu_freelist_push+0x2a/0x40 [ 12.492696] but this lock was taken by another, HARDIRQ-safe lock in the past: [ 12.493275] (&rq->lock){-.-.} [ 12.493276] [ 12.493276] [ 12.493276] and interrupts could create inverse lock ordering between them. [ 12.493276] [ 12.494435] [ 12.494435] other info that might help us debug this: [ 12.494979] Possible interrupt unsafe locking scenario: [ 12.494979] [ 12.495518] CPU0 CPU1 [ 12.495879] ---- ---- [ 12.496243] lock(&head->lock); [ 12.496502] local_irq_disable(); [ 12.496969] lock(&rq->lock); [ 12.497431] lock(&head->lock); [ 12.497890] [ 12.498104] lock(&rq->lock); [ 12.498368] [ 12.498368] *** DEADLOCK *** [ 12.498368] [ 12.498837] 1 lock held by dd/276: [ 12.499110] #0: 00000000c58cb2ee (rcu_read_lock){....}, at: trace_call_bpf+0x5e/0x240 [ 12.499747] [ 12.499747] the shortest dependencies between 2nd lock and 1st lock: [ 12.500389] -> (&rq->lock){-.-.} { [ 12.500669] IN-HARDIRQ-W at: [ 12.500934] _raw_spin_lock+0x2f/0x40 [ 12.501373] scheduler_tick+0x4c/0xf0 [ 12.501812] update_process_times+0x40/0x50 [ 12.502294] tick_periodic+0x27/0xb0 [ 12.502723] tick_handle_periodic+0x1f/0x60 [ 12.503203] timer_interrupt+0x11/0x20 [ 12.503651] __handle_irq_event_percpu+0x43/0x2c0 [ 12.504167] handle_irq_event_percpu+0x20/0x50 [ 12.504674] handle_irq_event+0x37/0x60 [ 12.505139] handle_level_irq+0xa7/0x120 [ 12.505601] handle_irq+0xa1/0x150 [ 12.506018] do_IRQ+0x77/0x140 [ 12.506411] ret_from_intr+0x0/0x1d [ 12.506834] _raw_spin_unlock_irqrestore+0x53/0x60 [ 12.507362] __setup_irq+0x481/0x730 [ 12.507789] setup_irq+0x49/0x80 [ 12.508195] hpet_time_init+0x21/0x32 [ 12.508644] x86_late_time_init+0xb/0x16 [ 12.509106] start_kernel+0x390/0x42a [ 12.509554] secondary_startup_64+0xa4/0xb0 [ 12.510034] IN-SOFTIRQ-W at: [ 12.510305] _raw_spin_lock+0x2f/0x40 [ 12.510772] try_to_wake_up+0x1c7/0x4e0 [ 12.511220] swake_up_locked+0x20/0x40 [ 12.511657] swake_up_one+0x1a/0x30 [ 12.512070] rcu_process_callbacks+0xc5/0x650 [ 12.512553] __do_softirq+0xe6/0x47b [ 12.512978] irq_exit+0xc3/0xd0 [ 12.513372] smp_apic_timer_interrupt+0xa9/0x250 [ 12.513876] apic_timer_interrupt+0xf/0x20 [ 12.514343] default_idle+0x1c/0x170 [ 12.514765] do_idle+0x199/0x240 [ 12.515159] cpu_startup_entry+0x19/0x20 [ 12.515614] start_kernel+0x422/0x42a [ 12.516045] secondary_startup_64+0xa4/0xb0 [ 12.516521] INITIAL USE at: [ 12.516774] _raw_spin_lock_irqsave+0x38/0x50 [ 12.517258] rq_attach_root+0x16/0xd0 [ 12.517685] sched_init+0x2f2/0x3eb [ 12.518096] start_kernel+0x1fb/0x42a [ 12.518525] secondary_startup_64+0xa4/0xb0 [ 12.518986] } [ 12.519132] ... key at: [] __key.71384+0x0/0x8 [ 12.519649] ... acquired at: [ 12.519892] pcpu_freelist_pop+0x7b/0xd0 [ 12.520221] bpf_get_stackid+0x1d2/0x4d0 [ 12.520563] ___bpf_prog_run+0x8b4/0x11a0 [ 12.520887] [ 12.521008] -> (&head->lock){+...} { [ 12.521292] HARDIRQ-ON-W at: [ 12.521539] _raw_spin_lock+0x2f/0x40 [ 12.521950] pcpu_freelist_push+0x2a/0x40 [ 12.522396] bpf_get_stackid+0x494/0x4d0 [ 12.522828] ___bpf_prog_run+0x8b4/0x11a0 [ 12.523296] INITIAL USE at: [ 12.523537] _raw_spin_lock+0x2f/0x40 [ 12.523944] pcpu_freelist_populate+0xc0/0x120 [ 12.524417] htab_map_alloc+0x405/0x500 [ 12.524835] __do_sys_bpf+0x1a3/0x1a90 [ 12.525253] do_syscall_64+0x4a/0x180 [ 12.525659] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 12.526167] } [ 12.526311] ... key at: [] __key.13130+0x0/0x8 [ 12.526812] ... acquired at: [ 12.527047] __lock_acquire+0x521/0x1350 [ 12.527371] lock_acquire+0x98/0x190 [ 12.527680] _raw_spin_lock+0x2f/0x40 [ 12.527994] pcpu_freelist_push+0x2a/0x40 [ 12.528325] bpf_get_stackid+0x494/0x4d0 [ 12.528645] ___bpf_prog_run+0x8b4/0x11a0 [ 12.528970] [ 12.529092] [ 12.529092] stack backtrace: [ 12.529444] CPU: 0 PID: 276 Comm: dd Not tainted 5.0.0-rc3-00018-g2fa53f892422 #475 [ 12.530043] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 [ 12.530750] Call Trace: [ 12.530948] dump_stack+0x5f/0x8b [ 12.531248] check_usage_backwards+0x10c/0x120 [ 12.531598] ? ___bpf_prog_run+0x8b4/0x11a0 [ 12.531935] ? mark_lock+0x382/0x560 [ 12.532229] mark_lock+0x382/0x560 [ 12.532496] ? print_shortest_lock_dependencies+0x180/0x180 [ 12.532928] __lock_acquire+0x521/0x1350 [ 12.533271] ? find_get_entry+0x17f/0x2e0 [ 12.533586] ? find_get_entry+0x19c/0x2e0 [ 12.533902] ? lock_acquire+0x98/0x190 [ 12.534196] lock_acquire+0x98/0x190 [ 12.534482] ? pcpu_freelist_push+0x2a/0x40 [ 12.534810] _raw_spin_lock+0x2f/0x40 [ 12.535099] ? pcpu_freelist_push+0x2a/0x40 [ 12.535432] pcpu_freelist_push+0x2a/0x40 [ 12.535750] bpf_get_stackid+0x494/0x4d0 [ 12.536062] ___bpf_prog_run+0x8b4/0x11a0 It has been explained that is a false positive here: https://lkml.org/lkml/2018/7/25/756 Recap: - stackmap uses pcpu_freelist - The lock in pcpu_freelist is a percpu lock - stackmap is only used by tracing bpf_prog - A tracing bpf_prog cannot be run if another bpf_prog has already been running (ensured by the percpu bpf_prog_active counter). Eric pointed out that this lockdep splats stops other legit lockdep splats in selftests/bpf/test_progs.c. Fix this by calling local_irq_save/restore for stackmap. Another false positive had also been worked around by calling local_irq_save in commit 89ad2fa3f043 ("bpf: fix lockdep splat"). That commit added unnecessary irq_save/restore to fast path of bpf hash map. irqs are already disabled at that point, since htab is holding per bucket spin_lock with irqsave. Let's reduce overhead for htab by introducing __pcpu_freelist_push/pop function w/o irqsave and convert pcpu_freelist_push/pop to irqsave to be used elsewhere (right now only in stackmap). It stops lockdep false positive in stackmap with a bit of acceptable overhead. Fixes: 557c0c6e7df8 ("bpf: convert stackmap to pre-allocation") Reported-by: Naresh Kamboju Reported-by: Eric Dumazet Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Signed-off-by: Sasha Levin --- kernel/bpf/hashtab.c | 4 ++-- kernel/bpf/percpu_freelist.c | 41 +++++++++++++++++++++++++----------- kernel/bpf/percpu_freelist.h | 4 ++++ 3 files changed, 35 insertions(+), 14 deletions(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3d0ecc273cc6..84237f640789 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -655,7 +655,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) } if (htab_is_prealloc(htab)) { - pcpu_freelist_push(&htab->freelist, &l->fnode); + __pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); l->htab = htab; @@ -717,7 +717,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, } else { struct pcpu_freelist_node *l; - l = pcpu_freelist_pop(&htab->freelist); + l = __pcpu_freelist_pop(&htab->freelist); if (!l) return ERR_PTR(-E2BIG); l_new = container_of(l, struct htab_elem, fnode); diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index 673fa6fe2d73..0c1b4ba9e90e 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -28,8 +28,8 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s) free_percpu(s->freelist); } -static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, - struct pcpu_freelist_node *node) +static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, + struct pcpu_freelist_node *node) { raw_spin_lock(&head->lock); node->next = head->first; @@ -37,12 +37,22 @@ static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, raw_spin_unlock(&head->lock); } -void pcpu_freelist_push(struct pcpu_freelist *s, +void __pcpu_freelist_push(struct pcpu_freelist *s, struct pcpu_freelist_node *node) { struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist); - __pcpu_freelist_push(head, node); + ___pcpu_freelist_push(head, node); +} + +void pcpu_freelist_push(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + unsigned long flags; + + local_irq_save(flags); + __pcpu_freelist_push(s, node); + local_irq_restore(flags); } void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, @@ -63,7 +73,7 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, for_each_possible_cpu(cpu) { again: head = per_cpu_ptr(s->freelist, cpu); - __pcpu_freelist_push(head, buf); + ___pcpu_freelist_push(head, buf); i++; buf += elem_size; if (i == nr_elems) @@ -74,14 +84,12 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, local_irq_restore(flags); } -struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) { struct pcpu_freelist_head *head; struct pcpu_freelist_node *node; - unsigned long flags; int orig_cpu, cpu; - local_irq_save(flags); orig_cpu = cpu = raw_smp_processor_id(); while (1) { head = per_cpu_ptr(s->freelist, cpu); @@ -89,16 +97,25 @@ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) node = head->first; if (node) { head->first = node->next; - raw_spin_unlock_irqrestore(&head->lock, flags); + raw_spin_unlock(&head->lock); return node; } raw_spin_unlock(&head->lock); cpu = cpumask_next(cpu, cpu_possible_mask); if (cpu >= nr_cpu_ids) cpu = 0; - if (cpu == orig_cpu) { - local_irq_restore(flags); + if (cpu == orig_cpu) return NULL; - } } } + +struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +{ + struct pcpu_freelist_node *ret; + unsigned long flags; + + local_irq_save(flags); + ret = __pcpu_freelist_pop(s); + local_irq_restore(flags); + return ret; +} diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h index 3049aae8ea1e..c3960118e617 100644 --- a/kernel/bpf/percpu_freelist.h +++ b/kernel/bpf/percpu_freelist.h @@ -22,8 +22,12 @@ struct pcpu_freelist_node { struct pcpu_freelist_node *next; }; +/* pcpu_freelist_* do spin_lock_irqsave. */ void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *); +/* __pcpu_freelist_* do spin_lock only. caller must disable irqs. */ +void __pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *); void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, u32 nr_elems); int pcpu_freelist_init(struct pcpu_freelist *); -- GitLab From 2b34bef88a2ee48936997c77bc0b04149cac39ca Mon Sep 17 00:00:00 2001 From: Paul Kocialkowski Date: Thu, 31 Jan 2019 14:25:50 +0100 Subject: [PATCH 0139/1128] drm/sun4i: tcon: Prepare and enable TCON channel 0 clock at init [ Upstream commit b14e945bda8ae227d1bf2b1837c0c4a61721cd1a ] When initializing clocks, a reference to the TCON channel 0 clock is obtained. However, the clock is never prepared and enabled later. Switching from simplefb to DRM actually disables the clock (that was usually configured by U-Boot) because of that. On the V3s, this results in a hang when writing to some mixer registers when switching over to DRM from simplefb. Fix this by preparing and enabling the clock when initializing other clocks. Waiting for sun4i_tcon_channel_enable to enable the clock is apparently too late and results in the same mixer register access hang. Signed-off-by: Paul Kocialkowski Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20190131132550.26355-1-paul.kocialkowski@bootlin.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/sun4i/sun4i_tcon.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 7b909d814d38..095bd6b4ae80 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -371,6 +371,7 @@ static int sun4i_tcon_init_clocks(struct device *dev, dev_err(dev, "Couldn't get the TCON channel 0 clock\n"); return PTR_ERR(tcon->sclk0); } + clk_prepare_enable(tcon->sclk0); if (tcon->quirks->has_channel_1) { tcon->sclk1 = devm_clk_get(dev, "tcon-ch1"); @@ -385,6 +386,7 @@ static int sun4i_tcon_init_clocks(struct device *dev, static void sun4i_tcon_free_clocks(struct sun4i_tcon *tcon) { + clk_disable_unprepare(tcon->sclk0); clk_disable_unprepare(tcon->clk); } -- GitLab From 253543f745286b00d637a12034657444d2db02c5 Mon Sep 17 00:00:00 2001 From: Codrin Ciubotariu Date: Wed, 23 Jan 2019 16:33:47 +0000 Subject: [PATCH 0140/1128] dmaengine: at_xdmac: Fix wrongfull report of a channel as in use [ Upstream commit dc3f595b6617ebc0307e0ce151e8f2f2b2489b95 ] atchan->status variable is used to store two different information: - pass channel interrupts status from interrupt handler to tasklet; - channel information like whether it is cyclic or paused; This causes a bug when device_terminate_all() is called, (AT_XDMAC_CHAN_IS_CYCLIC cleared on atchan->status) and then a late End of Block interrupt arrives (AT_XDMAC_CIS_BIS), which sets bit 0 of atchan->status. Bit 0 is also used for AT_XDMAC_CHAN_IS_CYCLIC, so when a new descriptor for a cyclic transfer is created, the driver reports the channel as in use: if (test_and_set_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status)) { dev_err(chan2dev(chan), "channel currently used\n"); return NULL; } This patch fixes the bug by adding a different struct member to keep the interrupts status separated from the channel status bits. Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller driver") Signed-off-by: Codrin Ciubotariu Acked-by: Ludovic Desroches Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/at_xdmac.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 94236ec9d410..4db2cd1c611d 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -203,6 +203,7 @@ struct at_xdmac_chan { u32 save_cim; u32 save_cnda; u32 save_cndc; + u32 irq_status; unsigned long status; struct tasklet_struct tasklet; struct dma_slave_config sconfig; @@ -1580,8 +1581,8 @@ static void at_xdmac_tasklet(unsigned long data) struct at_xdmac_desc *desc; u32 error_mask; - dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08lx\n", - __func__, atchan->status); + dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n", + __func__, atchan->irq_status); error_mask = AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS @@ -1589,15 +1590,15 @@ static void at_xdmac_tasklet(unsigned long data) if (at_xdmac_chan_is_cyclic(atchan)) { at_xdmac_handle_cyclic(atchan); - } else if ((atchan->status & AT_XDMAC_CIS_LIS) - || (atchan->status & error_mask)) { + } else if ((atchan->irq_status & AT_XDMAC_CIS_LIS) + || (atchan->irq_status & error_mask)) { struct dma_async_tx_descriptor *txd; - if (atchan->status & AT_XDMAC_CIS_RBEIS) + if (atchan->irq_status & AT_XDMAC_CIS_RBEIS) dev_err(chan2dev(&atchan->chan), "read bus error!!!"); - if (atchan->status & AT_XDMAC_CIS_WBEIS) + if (atchan->irq_status & AT_XDMAC_CIS_WBEIS) dev_err(chan2dev(&atchan->chan), "write bus error!!!"); - if (atchan->status & AT_XDMAC_CIS_ROIS) + if (atchan->irq_status & AT_XDMAC_CIS_ROIS) dev_err(chan2dev(&atchan->chan), "request overflow error!!!"); spin_lock_bh(&atchan->lock); @@ -1652,7 +1653,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) atchan = &atxdmac->chan[i]; chan_imr = at_xdmac_chan_read(atchan, AT_XDMAC_CIM); chan_status = at_xdmac_chan_read(atchan, AT_XDMAC_CIS); - atchan->status = chan_status & chan_imr; + atchan->irq_status = chan_status & chan_imr; dev_vdbg(atxdmac->dma.dev, "%s: chan%d: imr=0x%x, status=0x%x\n", __func__, i, chan_imr, chan_status); @@ -1666,7 +1667,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) at_xdmac_chan_read(atchan, AT_XDMAC_CDA), at_xdmac_chan_read(atchan, AT_XDMAC_CUBC)); - if (atchan->status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS)) + if (atchan->irq_status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS)) at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask); tasklet_schedule(&atchan->tasklet); -- GitLab From 6a78f5dccfff5c0b64b6956e6f6beadd669e0108 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 1 Feb 2019 12:42:06 +0100 Subject: [PATCH 0141/1128] vsock/virtio: fix kernel panic after device hot-unplug [ Upstream commit 22b5c0b63f32568e130fa2df4ba23efce3eb495b ] virtio_vsock_remove() invokes the vsock_core_exit() also if there are opened sockets for the AF_VSOCK protocol family. In this way the vsock "transport" pointer is set to NULL, triggering the kernel panic at the first socket activity. This patch move the vsock_core_init()/vsock_core_exit() in the virtio_vsock respectively in module_init and module_exit functions, that cannot be invoked until there are open sockets. Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1609699 Reported-by: Yan Fu Signed-off-by: Stefano Garzarella Acked-by: Stefan Hajnoczi Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/vmw_vsock/virtio_transport.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index fdb294441682..8cdf6ddec9b7 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -75,6 +75,9 @@ static u32 virtio_transport_get_local_cid(void) { struct virtio_vsock *vsock = virtio_vsock_get(); + if (!vsock) + return VMADDR_CID_ANY; + return vsock->guest_cid; } @@ -584,10 +587,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) virtio_vsock_update_guest_cid(vsock); - ret = vsock_core_init(&virtio_transport.transport); - if (ret < 0) - goto out_vqs; - vsock->rx_buf_nr = 0; vsock->rx_buf_max_nr = 0; atomic_set(&vsock->queued_replies, 0); @@ -618,8 +617,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) mutex_unlock(&the_virtio_vsock_mutex); return 0; -out_vqs: - vsock->vdev->config->del_vqs(vsock->vdev); out: kfree(vsock); mutex_unlock(&the_virtio_vsock_mutex); @@ -669,7 +666,6 @@ static void virtio_vsock_remove(struct virtio_device *vdev) mutex_lock(&the_virtio_vsock_mutex); the_virtio_vsock = NULL; - vsock_core_exit(); mutex_unlock(&the_virtio_vsock_mutex); vdev->config->del_vqs(vdev); @@ -702,14 +698,28 @@ static int __init virtio_vsock_init(void) virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0); if (!virtio_vsock_workqueue) return -ENOMEM; + ret = register_virtio_driver(&virtio_vsock_driver); if (ret) - destroy_workqueue(virtio_vsock_workqueue); + goto out_wq; + + ret = vsock_core_init(&virtio_transport.transport); + if (ret) + goto out_vdr; + + return 0; + +out_vdr: + unregister_virtio_driver(&virtio_vsock_driver); +out_wq: + destroy_workqueue(virtio_vsock_workqueue); return ret; + } static void __exit virtio_vsock_exit(void) { + vsock_core_exit(); unregister_virtio_driver(&virtio_vsock_driver); destroy_workqueue(virtio_vsock_workqueue); } -- GitLab From 46a96f8729b4ef232d70ed893d50da1c7cb434a4 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 1 Feb 2019 12:42:07 +0100 Subject: [PATCH 0142/1128] vsock/virtio: reset connected sockets on device removal [ Upstream commit 85965487abc540368393a15491e6e7fcd230039d ] When the virtio transport device disappear, we should reset all connected sockets in order to inform the users. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/vmw_vsock/virtio_transport.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 8cdf6ddec9b7..2ff751eba037 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -634,6 +634,9 @@ static void virtio_vsock_remove(struct virtio_device *vdev) flush_work(&vsock->event_work); flush_work(&vsock->send_pkt_work); + /* Reset all connected sockets when the device disappear */ + vsock_for_each_connected_socket(virtio_vsock_reset_sock); + vdev->config->reset(vdev); mutex_lock(&vsock->rx_lock); -- GitLab From f2dbb2b5d97143761de075856596ec8e704fe02d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jan 2019 21:48:44 +0200 Subject: [PATCH 0143/1128] dmaengine: dmatest: Abort test in case of mapping error [ Upstream commit 6454368a804c4955ccd116236037536f81e5b1f1 ] In case of mapping error the DMA addresses are invalid and continuing will screw system memory or potentially something else. [ 222.480310] dmatest: dma0chan7-copy0: summary 1 tests, 3 failures 6 iops 349 KB/s (0) ... [ 240.912725] check: Corrupted low memory at 00000000c7c75ac9 (2940 phys) = 5656000000000000 [ 240.921998] check: Corrupted low memory at 000000005715a1cd (2948 phys) = 279f2aca5595ab2b [ 240.931280] check: Corrupted low memory at 000000002f4024c0 (2950 phys) = 5e5624f349e793cf ... Abort any test if mapping failed. Fixes: 4076e755dbec ("dmatest: convert to dmaengine_unmap_data") Cc: Dan Williams Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/dmatest.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 80cc2be6483c..e39336127741 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -626,11 +626,9 @@ static int dmatest_func(void *data) srcs[i] = um->addr[i] + src_off; ret = dma_mapping_error(dev->dev, um->addr[i]); if (ret) { - dmaengine_unmap_put(um); result("src mapping error", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } um->to_cnt++; } @@ -645,11 +643,9 @@ static int dmatest_func(void *data) DMA_BIDIRECTIONAL); ret = dma_mapping_error(dev->dev, dsts[i]); if (ret) { - dmaengine_unmap_put(um); result("dst mapping error", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } um->bidi_cnt++; } @@ -679,12 +675,10 @@ static int dmatest_func(void *data) } if (!tx) { - dmaengine_unmap_put(um); result("prep error", total_tests, src_off, dst_off, len, ret); msleep(100); - failed_tests++; - continue; + goto error_unmap_continue; } done->done = false; @@ -693,12 +687,10 @@ static int dmatest_func(void *data) cookie = tx->tx_submit(tx); if (dma_submit_error(cookie)) { - dmaengine_unmap_put(um); result("submit error", total_tests, src_off, dst_off, len, ret); msleep(100); - failed_tests++; - continue; + goto error_unmap_continue; } dma_async_issue_pending(chan); @@ -711,16 +703,14 @@ static int dmatest_func(void *data) dmaengine_unmap_put(um); result("test timed out", total_tests, src_off, dst_off, len, 0); - failed_tests++; - continue; + goto error_unmap_continue; } else if (status != DMA_COMPLETE) { dmaengine_unmap_put(um); result(status == DMA_ERROR ? "completion error status" : "completion busy status", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } dmaengine_unmap_put(um); @@ -765,6 +755,12 @@ static int dmatest_func(void *data) verbose_result("test passed", total_tests, src_off, dst_off, len, 0); } + + continue; + +error_unmap_continue: + dmaengine_unmap_put(um); + failed_tests++; } ktime = ktime_sub(ktime_get(), ktime); ktime = ktime_sub(ktime, comparetime); -- GitLab From 25825f52ba4138e09dfbeaaa104f363b8256e5cf Mon Sep 17 00:00:00 2001 From: Naresh Kamboju Date: Tue, 29 Jan 2019 06:28:35 +0000 Subject: [PATCH 0144/1128] selftests: netfilter: fix config fragment CONFIG_NF_TABLES_INET [ Upstream commit 952b72f89ae23b316da8c1021b18d0c388ad6cc4 ] In selftests the config fragment for netfilter was added as NF_TABLES_INET=y and this patch correct it as CONFIG_NF_TABLES_INET=y Signed-off-by: Naresh Kamboju Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- tools/testing/selftests/netfilter/config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config index 1017313e41a8..59caa8f71cd8 100644 --- a/tools/testing/selftests/netfilter/config +++ b/tools/testing/selftests/netfilter/config @@ -1,2 +1,2 @@ CONFIG_NET_NS=y -NF_TABLES_INET=y +CONFIG_NF_TABLES_INET=y -- GitLab From 0ea42d0813665ec60682eeac3ab83adbfef556c0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 29 Jan 2019 15:16:23 +0100 Subject: [PATCH 0145/1128] selftests: netfilter: add simple masq/redirect test cases [ Upstream commit 98bfc3414bda335dbd7fec58bde6266f991801d7 ] Check basic nat/redirect/masquerade for ipv4 and ipv6. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- tools/testing/selftests/netfilter/Makefile | 2 +- tools/testing/selftests/netfilter/nft_nat.sh | 762 +++++++++++++++++++ 2 files changed, 763 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/nft_nat.sh diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 47ed6cef93fb..c9ff2b47bd1c 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh new file mode 100755 index 000000000000..8ec76681605c --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -0,0 +1,762 @@ +#!/bin/bash +# +# This test is for basic NAT functionality: snat, dnat, redirect, masquerade. +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add ns0 +ip netns add ns1 +ip netns add ns2 + +ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 +ip link add veth1 netns ns0 type veth peer name eth0 netns ns2 + +ip -net ns0 link set lo up +ip -net ns0 link set veth0 up +ip -net ns0 addr add 10.0.1.1/24 dev veth0 +ip -net ns0 addr add dead:1::1/64 dev veth0 + +ip -net ns0 link set veth1 up +ip -net ns0 addr add 10.0.2.1/24 dev veth1 +ip -net ns0 addr add dead:2::1/64 dev veth1 + +for i in 1 2; do + ip -net ns$i link set lo up + ip -net ns$i link set eth0 up + ip -net ns$i addr add 10.0.$i.99/24 dev eth0 + ip -net ns$i route add default via 10.0.$i.1 + ip -net ns$i addr add dead:$i::99/64 dev eth0 + ip -net ns$i route add default via dead:$i::1 +done + +bad_counter() +{ + local ns=$1 + local counter=$2 + local expect=$3 + + echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter $counter 1>&2 +} + +check_counters() +{ + ns=$1 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84") + if [ $? -ne 0 ]; then + bad_counter $ns ns0in "packets 1 bytes 84" + lret=1 + fi + cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84") + if [ $? -ne 0 ]; then + bad_counter $ns ns0out "packets 1 bytes 84" + lret=1 + fi + + expect="packets 1 bytes 104" + cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter $ns ns0in6 "$expect" + lret=1 + fi + cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter $ns ns0out6 "$expect" + lret=1 + fi + + return $lret +} + +check_ns0_counters() +{ + local ns=$1 + local lret=0 + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0in "packets 0 bytes 0" + lret=1 + fi + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0in6 "packets 0 bytes 0" + lret=1 + fi + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0out "packets 0 bytes 0" + lret=1 + fi + cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0out6 "packets 0 bytes 0" + lret=1 + fi + + for dir in "in" "out" ; do + expect="packets 1 bytes 84" + cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 $ns$dir "$expect" + lret=1 + fi + + expect="packets 1 bytes 104" + cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 $ns$dir6 "$expect" + lret=1 + fi + done + + return $lret +} + +reset_counters() +{ + for i in 0 1 2;do + ip netns exec ns$i nft reset counters inet > /dev/null + done +} + +test_local_dnat6() +{ + local lret=0 +ip netns exec ns0 nft -f - < /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping6 failed" + return $lret + fi + + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns1$dir "$expect" + lret=1 + fi + done + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 0 count in ns1 + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # expect 1 packet in ns2 + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns0$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was NATted to ns2" + ip netns exec ns0 nft flush chain ip6 nat output + + return $lret +} + +test_local_dnat() +{ + local lret=0 +ip netns exec ns0 nft -f - < /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping failed" + return $lret + fi + + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns1$dir "$expect" + lret=1 + fi + done + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 0 count in ns1 + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # expect 1 packet in ns2 + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns0$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ping to ns1 was NATted to ns2" + + ip netns exec ns0 nft flush chain ip nat output + + reset_counters + ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping failed" + return $lret + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns1$dir "$expect" + lret=1 + fi + done + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 1 count in ns1 + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0$dir "$expect" + lret=1 + fi + done + + # expect 0 packet in ns2 + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns2$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ping to ns1 OK after nat output chain flush" + + return $lret +} + + +test_masquerade6() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 via ipv6" + return 1 + lret=1 + fi + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add masquerading rule +ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading" + lret=1 + fi + + # ns1 should have seen packets from ns0, due to masquerade + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft flush chain ip6 nat postrouting + if [ $? -ne 0 ]; then + echo "ERROR: Could not flush ip6 nat postrouting" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2" + + return $lret +} + +test_masquerade() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: canot ping ns1 from ns2" + lret=1 + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add masquerading rule +ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading" + lret=1 + fi + + # ns1 should have seen packets from ns0, due to masquerade + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft flush chain ip nat postrouting + if [ $? -ne 0 ]; then + echo "ERROR: Could not flush nat postrouting" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP masquerade for ns2" + + return $lret +} + +test_redirect6() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannnot ping ns1 from ns2 via ipv6" + lret=1 + fi + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add redirect rule +ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip6 redirect" + lret=1 + fi + + # ns1 should have seen no packets from ns2, due to redirection + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # ns0 should have seen packets from ns2, due to masquerade + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft delete table ip6 nat + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete ip6 nat table" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IPv6 redirection for ns2" + + return $lret +} + +test_redirect() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2" + lret=1 + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add redirect rule +ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip redirect" + lret=1 + fi + + # ns1 should have seen no packets from ns2, due to redirection + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # ns0 should have seen packets from ns2, due to masquerade + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft delete table ip nat + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete nat table" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP redirection for ns2" + + return $lret +} + + +# ip netns exec ns0 ping -c 1 -q 10.0.$i.99 +for i in 0 1 2; do +ip netns exec ns$i nft -f - < /dev/null + if [ $? -ne 0 ];then + echo "ERROR: Could not reach other namespace(s)" 1>&2 + ret=1 + fi + + ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null + if [ $? -ne 0 ];then + echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2 + ret=1 + fi + check_counters ns$i + if [ $? -ne 0 ]; then + ret=1 + fi + + check_ns0_counters ns$i + if [ $? -ne 0 ]; then + ret=1 + fi + reset_counters +done + +if [ $ret -eq 0 ];then + echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2" +fi + +reset_counters +test_local_dnat +test_local_dnat6 + +reset_counters +test_masquerade +test_masquerade6 + +reset_counters +test_redirect +test_redirect6 + +for i in 0 1 2; do ip netns del ns$i;done + +exit $ret -- GitLab From c1c60bac48457bc88392a0953799606c5f5d57d9 Mon Sep 17 00:00:00 2001 From: Martynas Pumputis Date: Tue, 29 Jan 2019 15:51:42 +0100 Subject: [PATCH 0146/1128] netfilter: nf_nat: skip nat clash resolution for same-origin entries [ Upstream commit 4e35c1cb9460240e983a01745b5f29fe3a4d8e39 ] It is possible that two concurrent packets originating from the same socket of a connection-less protocol (e.g. UDP) can end up having different IP_CT_DIR_REPLY tuples which results in one of the packets being dropped. To illustrate this, consider the following simplified scenario: 1. Packet A and B are sent at the same time from two different threads by same UDP socket. No matching conntrack entry exists yet. Both packets cause allocation of a new conntrack entry. 2. get_unique_tuple gets called for A. No clashing entry found. conntrack entry for A is added to main conntrack table. 3. get_unique_tuple is called for B and will find that the reply tuple of B is already taken by A. It will allocate a new UDP source port for B to resolve the clash. 4. conntrack entry for B cannot be added to main conntrack table because its ORIGINAL direction is clashing with A and the REPLY directions of A and B are not the same anymore due to UDP source port reallocation done in step 3. This patch modifies nf_conntrack_tuple_taken so it doesn't consider colliding reply tuples if the IP_CT_DIR_ORIGINAL tuples are equal. [ Florian: simplify patch to not use .allow_clash setting and always ignore identical flows ] Signed-off-by: Martynas Pumputis Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_core.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index b793b55d1488..f07357ba9629 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -869,6 +869,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, } if (nf_ct_key_equal(h, tuple, zone, net)) { + /* Tuple is taken already, so caller will need to find + * a new source port to use. + * + * Only exception: + * If the *original tuples* are identical, then both + * conntracks refer to the same flow. + * This is a rare situation, it can occur e.g. when + * more than one UDP packet is sent from same socket + * in different threads. + * + * Let nf_ct_resolve_clash() deal with this later. + */ + if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) + continue; + NF_CT_STAT_INC_ATOMIC(net, found); rcu_read_unlock(); return 1; -- GitLab From d4802260ed30ac142da8739402bb03e28d22f9de Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Mon, 4 Feb 2019 17:40:07 +0100 Subject: [PATCH 0147/1128] s390/qeth: fix use-after-free in error path [ Upstream commit afa0c5904ba16d59b0454f7ee4c807dae350f432 ] The error path in qeth_alloc_qdio_buffers() that takes care of cleaning up the Output Queues is buggy. It first frees the queue, but then calls qeth_clear_outq_buffers() with that very queue struct. Make the call to qeth_clear_outq_buffers() part of the free action (in the correct order), and while at it fix the naming of the helper. Fixes: 0da9581ddb0f ("qeth: exploit asynchronous delivery of storage blocks") Signed-off-by: Julian Wiedmann Reviewed-by: Alexandra Winter Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/s390/net/qeth_core_main.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 69ef5f4060ed..6566fceef38d 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2472,11 +2472,12 @@ static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx) return rc; } -static void qeth_free_qdio_out_buf(struct qeth_qdio_out_q *q) +static void qeth_free_output_queue(struct qeth_qdio_out_q *q) { if (!q) return; + qeth_clear_outq_buffers(q, 1); qdio_free_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); kfree(q); } @@ -2549,10 +2550,8 @@ static int qeth_alloc_qdio_buffers(struct qeth_card *card) card->qdio.out_qs[i]->bufs[j] = NULL; } out_freeoutq: - while (i > 0) { - qeth_free_qdio_out_buf(card->qdio.out_qs[--i]); - qeth_clear_outq_buffers(card->qdio.out_qs[i], 1); - } + while (i > 0) + qeth_free_output_queue(card->qdio.out_qs[--i]); kfree(card->qdio.out_qs); card->qdio.out_qs = NULL; out_freepool: @@ -2585,10 +2584,8 @@ static void qeth_free_qdio_buffers(struct qeth_card *card) qeth_free_buffer_pool(card); /* free outbound qdio_qs */ if (card->qdio.out_qs) { - for (i = 0; i < card->qdio.no_out_queues; ++i) { - qeth_clear_outq_buffers(card->qdio.out_qs[i], 1); - qeth_free_qdio_out_buf(card->qdio.out_qs[i]); - } + for (i = 0; i < card->qdio.no_out_queues; i++) + qeth_free_output_queue(card->qdio.out_qs[i]); kfree(card->qdio.out_qs); card->qdio.out_qs = NULL; } -- GitLab From bb4bf9df6d439c2c33cd452533c5f182faadc9da Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 28 Jan 2019 14:35:26 +0100 Subject: [PATCH 0148/1128] perf symbols: Filter out hidden symbols from labels [ Upstream commit 59a17706915fe5ea6f711e1f92d4fb706bce07fe ] When perf is built with the annobin plugin (RHEL8 build) extra symbols are added to its binary: # nm perf | grep annobin | head -10 0000000000241100 t .annobin_annotate.c 0000000000326490 t .annobin_annotate.c 0000000000249255 t .annobin_annotate.c_end 00000000003283a8 t .annobin_annotate.c_end 00000000001bce18 t .annobin_annotate.c_end.hot 00000000001bce18 t .annobin_annotate.c_end.hot 00000000001bc3e2 t .annobin_annotate.c_end.unlikely 00000000001bc400 t .annobin_annotate.c_end.unlikely 00000000001bce18 t .annobin_annotate.c.hot 00000000001bce18 t .annobin_annotate.c.hot ... Those symbols have no use for report or annotation and should be skipped. Moreover they interfere with the DWARF unwind test on the PPC arch, where they are mixed with checked symbols and then the test fails: # perf test dwarf -v 59: Test dwarf unwind : --- start --- test child forked, pid 8515 unwind: .annobin_dwarf_unwind.c:ip = 0x10dba40dc (0x2740dc) ... got: .annobin_dwarf_unwind.c 0x10dba40dc, expecting test__arch_unwind_sample unwind: failed with 'no error' The annobin symbols are defined as NOTYPE/LOCAL/HIDDEN: # readelf -s ./perf | grep annobin | head -1 40: 00000000001bce4f 0 NOTYPE LOCAL HIDDEN 13 .annobin_init.c They can still pass the check for the label symbol. Adding check for HIDDEN and INTERNAL (as suggested by Nick below) visibility and filter out such symbols. > Just to be awkward, if you are going to ignore STV_HIDDEN > symbols then you should probably also ignore STV_INTERNAL ones > as well... Annobin does not generate them, but you never know, > one day some other tool might create some. Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Masami Hiramatsu Cc: Michael Petlan Cc: Namhyung Kim Cc: Nick Clifton Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20190128133526.GD15461@krava Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/symbol-elf.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 8ad4296de98b..3d39332b3a06 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -87,6 +87,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) return GELF_ST_TYPE(sym->st_info); } +static inline uint8_t elf_sym__visibility(const GElf_Sym *sym) +{ + return GELF_ST_VISIBILITY(sym->st_other); +} + #ifndef STT_GNU_IFUNC #define STT_GNU_IFUNC 10 #endif @@ -111,7 +116,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym) return elf_sym__type(sym) == STT_NOTYPE && sym->st_name != 0 && sym->st_shndx != SHN_UNDEF && - sym->st_shndx != SHN_ABS; + sym->st_shndx != SHN_ABS && + elf_sym__visibility(sym) != STV_HIDDEN && + elf_sym__visibility(sym) != STV_INTERNAL; } static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type) -- GitLab From a4fc33cf212a244e138720c5237da6ad2cfebc2f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 29 Jan 2019 15:12:34 +0100 Subject: [PATCH 0149/1128] perf trace: Support multiple "vfs_getname" probes [ Upstream commit 6ab3bc240ade47a0f52bc16d97edd9accbe0024e ] With a suitably defined "probe:vfs_getname" probe, 'perf trace' can "beautify" its output, so syscalls like open() or openat() can print the "filename" argument instead of just its hex address, like: $ perf trace -e open -- touch /dev/null [...] 0.590 ( 0.014 ms): touch/18063 open(filename: /dev/null, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3 [...] The output without such beautifier looks like: 0.529 ( 0.011 ms): touch/18075 open(filename: 0xc78cf288, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3 However, when the vfs_getname probe expands to multiple probes and it is not the first one that is hit, the beautifier fails, as following: 0.326 ( 0.010 ms): touch/18072 open(filename: , flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3 Fix it by hooking into all the expanded probes (inlines), now, for instance: [root@quaco ~]# perf probe -l probe:vfs_getname (on getname_flags:73@fs/namei.c with pathname) probe:vfs_getname_1 (on getname_flags:73@fs/namei.c with pathname) [root@quaco ~]# perf trace -e open* sleep 1 0.010 ( 0.005 ms): sleep/5588 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: RDONLY|CLOEXEC) = 3 0.029 ( 0.006 ms): sleep/5588 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: RDONLY|CLOEXEC) = 3 0.194 ( 0.008 ms): sleep/5588 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: RDONLY|CLOEXEC) = 3 [root@quaco ~]# Works, further verified with: [root@quaco ~]# perf test vfs 65: Use vfs_getname probe to get syscall args filenames : Ok 66: Add vfs_getname probe to get syscall args filenames : Ok 67: Check open filename arg using perf trace + vfs_getname: Ok [root@quaco ~]# Reported-by: Michael Petlan Tested-by: Michael Petlan Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-mv8kolk17xla1smvmp3qabv1@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/builtin-trace.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 8e3c4ec00017..b224bf3f2b99 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2109,19 +2109,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist) { - struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname"); + bool found = false; + struct perf_evsel *evsel, *tmp; + struct parse_events_error err = { .idx = 0, }; + int ret = parse_events(evlist, "probe:vfs_getname*", &err); - if (IS_ERR(evsel)) + if (ret) return false; - if (perf_evsel__field(evsel, "pathname") == NULL) { + evlist__for_each_entry_safe(evlist, evsel, tmp) { + if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname")) + continue; + + if (perf_evsel__field(evsel, "pathname")) { + evsel->handler = trace__vfs_getname; + found = true; + continue; + } + + list_del_init(&evsel->node); + evsel->evlist = NULL; perf_evsel__delete(evsel); - return false; } - evsel->handler = trace__vfs_getname; - perf_evlist__add(evlist, evsel); - return true; + return found; } static struct perf_evsel *perf_evsel__new_pgfault(u64 config) -- GitLab From a09faaf5d2de312ec77029933fc80f5a79aadb90 Mon Sep 17 00:00:00 2001 From: Jun-Ru Chang Date: Tue, 29 Jan 2019 11:56:07 +0800 Subject: [PATCH 0150/1128] MIPS: Remove function size check in get_frame_info() [ Upstream commit 2b424cfc69728224fcb5fad138ea7260728e0901 ] Patch (b6c7a324df37b "MIPS: Fix get_frame_info() handling of microMIPS function size.") introduces additional function size check for microMIPS by only checking insn between ip and ip + func_size. However, func_size in get_frame_info() is always 0 if KALLSYMS is not enabled. This causes get_frame_info() to return immediately without calculating correct frame_size, which in turn causes "Can't analyze schedule() prologue" warning messages at boot time. This patch removes func_size check, and let the frame_size check run up to 128 insns for both MIPS and microMIPS. Signed-off-by: Jun-Ru Chang Signed-off-by: Tony Wu Signed-off-by: Paul Burton Fixes: b6c7a324df37b ("MIPS: Fix get_frame_info() handling of microMIPS function size.") Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Signed-off-by: Sasha Levin --- arch/mips/kernel/process.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index e8b166e9146a..ea563bfea0e1 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -370,7 +370,7 @@ static inline int is_sp_move_ins(union mips_instruction *ip, int *frame_size) static int get_frame_info(struct mips_frame_info *info) { bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS); - union mips_instruction insn, *ip, *ip_end; + union mips_instruction insn, *ip; const unsigned int max_insns = 128; unsigned int last_insn_size = 0; unsigned int i; @@ -383,10 +383,9 @@ static int get_frame_info(struct mips_frame_info *info) if (!ip) goto err; - ip_end = (void *)ip + info->func_size; - - for (i = 0; i < max_insns && ip < ip_end; i++) { + for (i = 0; i < max_insns; i++) { ip = (void *)ip + last_insn_size; + if (is_mmips && mm_insn_16bit(ip->halfword[0])) { insn.word = ip->halfword[0] << 16; last_insn_size = 2; -- GitLab From e18d0dad0c43b8879434f7f92d39b40b3f563289 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 10 Jan 2019 07:59:16 -0800 Subject: [PATCH 0151/1128] i2c: omap: Use noirq system sleep pm ops to idle device for suspend [ Upstream commit c6e2bd956936d925748581e4d0294f10f1d92f2c ] We currently get the following error with pixcir_ts driver during a suspend resume cycle: omap_i2c 4802a000.i2c: controller timed out pixcir_ts 1-005c: pixcir_int_enable: can't read reg 0x34 : -110 pixcir_ts 1-005c: Failed to disable interrupt generation: -110 pixcir_ts 1-005c: Failed to stop dpm_run_callback(): pixcir_i2c_ts_resume+0x0/0x98 [pixcir_i2c_ts] returns -110 PM: Device 1-005c failed to resume: error -110 And at least am437x based devices with pixcir_ts will fail to resume to a touchscreen that is configured as the wakeup-source in device tree for these devices. This is because pixcir_ts tries to reconfigure it's registers for noirq suspend which fails. This also leaves i2c-omap in enabled state for suspend. Let's fix the pixcir_ts issue and make sure i2c-omap is suspended by adding SET_NOIRQ_SYSTEM_SLEEP_PM_OPS. Let's also get rid of some ifdefs while at it and replace them with __maybe_unused as SET_RUNTIME_PM_OPS and SET_NOIRQ_SYSTEM_SLEEP_PM_OPS already deal with the various PM Kconfig options. Reported-by: Keerthy Signed-off-by: Tony Lindgren Acked-by: Vignesh R Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-omap.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 23c2ea2baedc..12ba183693d6 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1477,8 +1477,7 @@ static int omap_i2c_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM -static int omap_i2c_runtime_suspend(struct device *dev) +static int __maybe_unused omap_i2c_runtime_suspend(struct device *dev) { struct omap_i2c_dev *omap = dev_get_drvdata(dev); @@ -1504,7 +1503,7 @@ static int omap_i2c_runtime_suspend(struct device *dev) return 0; } -static int omap_i2c_runtime_resume(struct device *dev) +static int __maybe_unused omap_i2c_runtime_resume(struct device *dev) { struct omap_i2c_dev *omap = dev_get_drvdata(dev); @@ -1519,20 +1518,18 @@ static int omap_i2c_runtime_resume(struct device *dev) } static const struct dev_pm_ops omap_i2c_pm_ops = { + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) SET_RUNTIME_PM_OPS(omap_i2c_runtime_suspend, omap_i2c_runtime_resume, NULL) }; -#define OMAP_I2C_PM_OPS (&omap_i2c_pm_ops) -#else -#define OMAP_I2C_PM_OPS NULL -#endif /* CONFIG_PM */ static struct platform_driver omap_i2c_driver = { .probe = omap_i2c_probe, .remove = omap_i2c_remove, .driver = { .name = "omap_i2c", - .pm = OMAP_I2C_PM_OPS, + .pm = &omap_i2c_pm_ops, .of_match_table = of_match_ptr(omap_i2c_of_match), }, }; -- GitLab From ef1c919ec66b5cd8c8f19dd3683f90064813f1f5 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 21 Jan 2019 22:49:37 +0900 Subject: [PATCH 0152/1128] fs: ratelimit __find_get_block_slow() failure message. [ Upstream commit 43636c804df0126da669c261fc820fb22f62bfc2 ] When something let __find_get_block_slow() hit all_mapped path, it calls printk() for 100+ times per a second. But there is no need to print same message with such high frequency; it is just asking for stall warning, or at least bloating log files. [ 399.866302][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8 [ 399.873324][T15342] b_state=0x00000029, b_size=512 [ 399.878403][T15342] device loop0 blocksize: 4096 [ 399.883296][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8 [ 399.890400][T15342] b_state=0x00000029, b_size=512 [ 399.895595][T15342] device loop0 blocksize: 4096 [ 399.900556][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8 [ 399.907471][T15342] b_state=0x00000029, b_size=512 [ 399.912506][T15342] device loop0 blocksize: 4096 This patch reduces frequency to up to once per a second, in addition to concatenating three lines into one. [ 399.866302][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8, b_state=0x00000029, b_size=512, device loop0 blocksize: 4096 Signed-off-by: Tetsuo Handa Reviewed-by: Jan Kara Cc: Dmitry Vyukov Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- fs/buffer.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index b96f3b98a6ef..8086cc8ff0bc 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -208,6 +208,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) struct buffer_head *head; struct page *page; int all_mapped = 1; + static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); @@ -235,15 +236,15 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ - if (all_mapped) { - printk("__find_get_block_slow() failed. " - "block=%llu, b_blocknr=%llu\n", - (unsigned long long)block, - (unsigned long long)bh->b_blocknr); - printk("b_state=0x%08lx, b_size=%zu\n", - bh->b_state, bh->b_size); - printk("device %pg blocksize: %d\n", bdev, - 1 << bd_inode->i_blkbits); + ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); + if (all_mapped && __ratelimit(&last_warned)) { + printk("__find_get_block_slow() failed. block=%llu, " + "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " + "device %pg blocksize: %d\n", + (unsigned long long)block, + (unsigned long long)bh->b_blocknr, + bh->b_state, bh->b_size, bdev, + 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); -- GitLab From 14b718fd0bdb2a8f1afd9dedfce8c9b46bdf6d00 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Wed, 6 Feb 2019 14:43:42 -0800 Subject: [PATCH 0153/1128] qed: Fix EQ full firmware assert. [ Upstream commit 660492bcf4a7561b5fdc13be0ae0b0c0a8c120be ] When slowpath messages are sent with high rate, the resulting events can lead to a FW assert in case they are not handled fast enough (Event Queue Full assert). Attempt to send queued slowpath messages only after the newly evacuated entries in the EQ ring are indicated to FW. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_sp.h | 1 + drivers/net/ethernet/qlogic/qed/qed_spq.c | 15 +++++++-------- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 01a213d4ee9c..e7192f3babc2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -380,6 +380,7 @@ void qed_consq_setup(struct qed_hwfn *p_hwfn); * @param p_hwfn */ void qed_consq_free(struct qed_hwfn *p_hwfn); +int qed_spq_pend_post(struct qed_hwfn *p_hwfn); /** * @file diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 467755b6dd0b..01f8e2b5cb6c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -404,6 +404,11 @@ int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie) qed_eq_prod_update(p_hwfn, qed_chain_get_prod_idx(p_chain)); + /* Attempt to post pending requests */ + spin_lock_bh(&p_hwfn->p_spq->lock); + rc = qed_spq_pend_post(p_hwfn); + spin_unlock_bh(&p_hwfn->p_spq->lock); + return rc; } @@ -747,7 +752,7 @@ static int qed_spq_post_list(struct qed_hwfn *p_hwfn, return 0; } -static int qed_spq_pend_post(struct qed_hwfn *p_hwfn) +int qed_spq_pend_post(struct qed_hwfn *p_hwfn) { struct qed_spq *p_spq = p_hwfn->p_spq; struct qed_spq_entry *p_ent = NULL; @@ -879,7 +884,6 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent = NULL; struct qed_spq_entry *tmp; struct qed_spq_entry *found = NULL; - int rc; if (!p_hwfn) return -EINVAL; @@ -937,12 +941,7 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, */ qed_spq_return_entry(p_hwfn, found); - /* Attempt to post pending requests */ - spin_lock_bh(&p_spq->lock); - rc = qed_spq_pend_post(p_hwfn); - spin_unlock_bh(&p_spq->lock); - - return rc; + return 0; } int qed_consq_alloc(struct qed_hwfn *p_hwfn) -- GitLab From 6fbdc61620d47ae14d17d37953a3e43e74d6b75d Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 6 Feb 2019 14:43:44 -0800 Subject: [PATCH 0154/1128] qed: Consider TX tcs while deriving the max num_queues for PF. [ Upstream commit fb1faab74ddef9ec2d841d54e5d0912a097b3abe ] Max supported queues is derived incorrectly in the case of multi-CoS. Need to consider TCs while calculating num_queues for PF. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 4ffdde755db7..62cde3854a5c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2170,7 +2170,7 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, u16 num_queues = 0; /* Since the feature controls only queue-zones, - * make sure we have the contexts [rx, tx, xdp] to + * make sure we have the contexts [rx, xdp, tcs] to * match. */ for_each_hwfn(cdev, i) { @@ -2180,7 +2180,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, u16 cids; cids = hwfn->pf_params.eth_pf_params.num_cons; - num_queues += min_t(u16, l2_queues, cids / 3); + cids /= (2 + info->num_tc); + num_queues += min_t(u16, l2_queues, cids); } /* queues might theoretically be >256, but interrupts' -- GitLab From e2f4d4675420401218e1ebdaa3258d81cbf17716 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Sat, 9 Mar 2019 15:32:13 -0800 Subject: [PATCH 0155/1128] Input: wacom_serial4 - add support for Wacom ArtPad II tablet commit 44fc95e218a09d7966a9d448941fdb003f6bb69f upstream. Tablet initially begins communicating at 9600 baud, so this command should be used to connect to the device: $ inputattach --daemon --baud 9600 --wacom_iv /dev/ttyS0 https://github.com/linuxwacom/xf86-input-wacom/issues/40 Signed-off-by: Jason Gerecke Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/tablet/wacom_serial4.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/input/tablet/wacom_serial4.c b/drivers/input/tablet/wacom_serial4.c index 38bfaca48eab..150f9eecaca7 100644 --- a/drivers/input/tablet/wacom_serial4.c +++ b/drivers/input/tablet/wacom_serial4.c @@ -187,6 +187,7 @@ enum { MODEL_DIGITIZER_II = 0x5544, /* UD */ MODEL_GRAPHIRE = 0x4554, /* ET */ MODEL_PENPARTNER = 0x4354, /* CT */ + MODEL_ARTPAD_II = 0x4B54, /* KT */ }; static void wacom_handle_model_response(struct wacom *wacom) @@ -245,6 +246,7 @@ static void wacom_handle_model_response(struct wacom *wacom) wacom->flags = F_HAS_STYLUS2 | F_HAS_SCROLLWHEEL; break; + case MODEL_ARTPAD_II: case MODEL_DIGITIZER_II: wacom->dev->name = "Wacom Digitizer II"; wacom->dev->id.version = MODEL_DIGITIZER_II; -- GitLab From d89a25ffd66fbbc8bcfaa881257bab5ac485a176 Mon Sep 17 00:00:00 2001 From: Vincent Batts Date: Sat, 9 Mar 2019 15:48:04 -0800 Subject: [PATCH 0156/1128] Input: elan_i2c - add id for touchpad found in Lenovo s21e-20 commit e154ab69321ce2c54f19863d75c77b4e2dc9d365 upstream. Lenovo s21e-20 uses ELAN0601 in its ACPI tables for the Elan touchpad. Signed-off-by: Vincent Batts Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/mouse/elan_i2c_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index fce70f4ef004..2ce805d31ed1 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1252,6 +1252,7 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0000", 0 }, { "ELAN0100", 0 }, { "ELAN0600", 0 }, + { "ELAN0601", 0 }, { "ELAN0602", 0 }, { "ELAN0605", 0 }, { "ELAN0608", 0 }, -- GitLab From 81f470ebe37ecb7822f99cc16e7a68477f8071f0 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 11 Feb 2019 12:43:23 -0600 Subject: [PATCH 0157/1128] iscsi_ibft: Fix missing break in switch statement commit df997abeebadaa4824271009e2d2b526a70a11cb upstream. Add missing break statement in order to prevent the code from falling through to case ISCSI_BOOT_TGT_NAME, which is unnecessary. This bug was found thanks to the ongoing efforts to enable -Wimplicit-fallthrough. Fixes: b33a84a38477 ("ibft: convert iscsi_ibft module to iscsi boot lib") Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/iscsi_ibft.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c index 14042a64bdd5..132b9bae4b6a 100644 --- a/drivers/firmware/iscsi_ibft.c +++ b/drivers/firmware/iscsi_ibft.c @@ -542,6 +542,7 @@ static umode_t __init ibft_check_tgt_for(void *data, int type) case ISCSI_BOOT_TGT_NIC_ASSOC: case ISCSI_BOOT_TGT_CHAP_TYPE: rc = S_IRUGO; + break; case ISCSI_BOOT_TGT_NAME: if (tgt->tgt_name_len) rc = S_IRUGO; -- GitLab From 0472ddf81d02c85d480b470d749599094aaa1bde Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 15 Feb 2019 15:42:42 -0600 Subject: [PATCH 0158/1128] scsi: aacraid: Fix missing break in switch statement commit 5e420fe635813e5746b296cfc8fff4853ae205a2 upstream. Add missing break statement and fix identation issue. This bug was found thanks to the ongoing efforts to enable -Wimplicit-fallthrough. Fixes: 9cb62fa24e0d ("aacraid: Log firmware AIF messages") Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/aacraid/commsup.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index 3e38bae6ecde..a284527999c5 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -1332,8 +1332,9 @@ static void aac_handle_aif(struct aac_dev * dev, struct fib * fibptr) ADD : DELETE; break; } - case AifBuManagerEvent: - aac_handle_aif_bu(dev, aifcmd); + break; + case AifBuManagerEvent: + aac_handle_aif_bu(dev, aifcmd); break; } -- GitLab From c238ab2fb928b40d8af691b24628ca512e1c62e4 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Thu, 24 Jan 2019 08:52:33 +0100 Subject: [PATCH 0159/1128] arm64: dts: hikey: Give wifi some time after power-on commit 83b944174ad79825ae84a47af1a0354485b24602 upstream. Somewhere along recent changes to power control of the wl1835, power-on became very unreliable on the hikey, failing like this: wl1271_sdio: probe of mmc2:0001:1 failed with error -16 wl1271_sdio: probe of mmc2:0001:2 failed with error -16 After playing with some dt parameters and comparing to other users of this chip, it turned out we need some power-on delay to make things stable again. In contrast to those other users which define 200 ms, the hikey would already be happy with 1 ms. Still, we use the safer 10 ms, like on the Ultra96. Fixes: ea452678734e ("arm64: dts: hikey: Fix WiFi support") Cc: #4.12+ Signed-off-by: Jan Kiszka Acked-by: Ulf Hansson Signed-off-by: Wei Xu Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts index 3aee6123d161..6887cc1a743d 100644 --- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts +++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts @@ -118,6 +118,7 @@ reset-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>; clocks = <&pmic>; clock-names = "ext_clock"; + post-power-on-delay-ms = <10>; power-off-delay-us = <10>; }; -- GitLab From 9e4ce0485a832489da333e735324d3300f4b6cde Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 24 Jan 2019 13:22:57 +0100 Subject: [PATCH 0160/1128] ARM: dts: exynos: Fix pinctrl definition for eMMC RTSN line on Odroid X2/U3 commit ec33745bccc8f336957c751f4153421cc9ef5a54 upstream. Commit 225da7e65a03 ("ARM: dts: add eMMC reset line for exynos4412-odroid-common") added MMC power sequence for eMMC card of Odroid X2/U3. It reused generic sd1_cd pin control configuration node and only disabled pull-up. However that time the pinctrl configuration was not applied during MMC power sequence driver initialization. This has been changed later by commit d97a1e5d7cd2 ("mmc: pwrseq: convert to proper platform device"). It turned out then, that the provided pinctrl configuration is not correct, because the eMMC_RTSN line is being re-configured as 'special function/card detect function for mmc1 controller' not the simple 'output', thus the power sequence driver doesn't really set the pin value. This in effect broke the reboot of Odroid X2/U3 boards. Fix this by providing separate node with eMMC_RTSN pin configuration. Cc: Reported-by: Markus Reichl Suggested-by: Ulf Hansson Fixes: 225da7e65a03 ("ARM: dts: add eMMC reset line for exynos4412-odroid-common") Signed-off-by: Marek Szyprowski Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/exynos4412-odroid-common.dtsi | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi index 102acd78be15..0d516529bf54 100644 --- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi +++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi @@ -60,7 +60,7 @@ }; emmc_pwrseq: pwrseq { - pinctrl-0 = <&sd1_cd>; + pinctrl-0 = <&emmc_rstn>; pinctrl-names = "default"; compatible = "mmc-pwrseq-emmc"; reset-gpios = <&gpk1 2 GPIO_ACTIVE_LOW>; @@ -161,12 +161,6 @@ cpu0-supply = <&buck2_reg>; }; -/* RSTN signal for eMMC */ -&sd1_cd { - samsung,pin-pud = ; - samsung,pin-drv = ; -}; - &pinctrl_1 { gpio_power_key: power_key { samsung,pins = "gpx1-3"; @@ -184,6 +178,11 @@ samsung,pins = "gpx3-7"; samsung,pin-pud = ; }; + + emmc_rstn: emmc-rstn { + samsung,pins = "gpk1-2"; + samsung,pin-pud = ; + }; }; &ehci { -- GitLab From 1b3cd7be3e8bd093cdb165ee3013dcb43ab7eff3 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 15 Feb 2019 11:36:50 +0100 Subject: [PATCH 0161/1128] ARM: dts: exynos: Add minimal clkout parameters to Exynos3250 PMU commit a66352e005488ecb4b534ba1af58a9f671eba9b8 upstream. Add minimal parameters needed by the Exynos CLKOUT driver to Exynos3250 PMU node. This fixes the following warning on boot: exynos_clkout_init: failed to register clkout clock Fixes: d19bb397e19e ("ARM: dts: exynos: Update PMU node with CLKOUT related data") Cc: Signed-off-by: Marek Szyprowski Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/exynos3250.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi index 3ed3d1a0fd40..aa06a02c3ff5 100644 --- a/arch/arm/boot/dts/exynos3250.dtsi +++ b/arch/arm/boot/dts/exynos3250.dtsi @@ -172,6 +172,9 @@ interrupt-controller; #interrupt-cells = <3>; interrupt-parent = <&gic>; + clock-names = "clkout8"; + clocks = <&cmu CLK_FIN_PLL>; + #clock-cells = <1>; }; mipi_phy: video-phy { -- GitLab From 0bcbfa51a77def77d079c6cd8acbd8ebd6a69c66 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 24 Jan 2019 13:06:58 +0100 Subject: [PATCH 0162/1128] drm: disable uncached DMA optimization for ARM and arm64 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e02f5c1bb2283cfcee68f2f0feddcc06150f13aa ] The DRM driver stack is designed to work with cache coherent devices only, but permits an optimization to be enabled in some cases, where for some buffers, both the CPU and the GPU use uncached mappings, removing the need for DMA snooping and allocation in the CPU caches. The use of uncached GPU mappings relies on the correct implementation of the PCIe NoSnoop TLP attribute by the platform, otherwise the GPU will use cached mappings nonetheless. On x86 platforms, this does not seem to matter, as uncached CPU mappings will snoop the caches in any case. However, on ARM and arm64, enabling this optimization on a platform where NoSnoop is ignored results in loss of coherency, which breaks correct operation of the device. Since we have no way of detecting whether NoSnoop works or not, just disable this optimization entirely for ARM and arm64. Cc: Christian Koenig Cc: Alex Deucher Cc: David Zhou Cc: Huang Rui Cc: Junwei Zhang Cc: Michel Daenzer Cc: David Airlie Cc: Daniel Vetter Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Sean Paul Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Will Deacon Cc: Christoph Hellwig Cc: Robin Murphy Cc: amd-gfx list Cc: dri-devel Reported-by: Carsten Haitzler Signed-off-by: Ard Biesheuvel Reviewed-by: Christian König Reviewed-by: Alex Deucher Link: https://patchwork.kernel.org/patch/10778815/ Signed-off-by: Christian König Signed-off-by: Sasha Levin --- include/drm/drm_cache.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h index beab0f0d0cfb..250e2d13c61b 100644 --- a/include/drm/drm_cache.h +++ b/include/drm/drm_cache.h @@ -45,6 +45,24 @@ static inline bool drm_arch_can_wc_memory(void) return false; #elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON3) return false; +#elif defined(CONFIG_ARM) || defined(CONFIG_ARM64) + /* + * The DRM driver stack is designed to work with cache coherent devices + * only, but permits an optimization to be enabled in some cases, where + * for some buffers, both the CPU and the GPU use uncached mappings, + * removing the need for DMA snooping and allocation in the CPU caches. + * + * The use of uncached GPU mappings relies on the correct implementation + * of the PCIe NoSnoop TLP attribute by the platform, otherwise the GPU + * will use cached mappings nonetheless. On x86 platforms, this does not + * seem to matter, as uncached CPU mappings will snoop the caches in any + * case. However, on ARM and arm64, enabling this optimization on a + * platform where NoSnoop is ignored results in loss of coherency, which + * breaks correct operation of the device. Since we have no way of + * detecting whether NoSnoop works or not, just disable this + * optimization entirely for ARM and arm64. + */ + return false; #else return true; #endif -- GitLab From 8256eef5a6a5a288f89f4a4160cf19375a2f6603 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Fri, 13 Jul 2018 11:12:22 +0100 Subject: [PATCH 0163/1128] ARM: 8781/1: Fix Thumb-2 syscall return for binutils 2.29+ [ Upstream commit afc9f65e01cd114cb2cedf544d22239116ce0cc6 ] When building the kernel as Thumb-2 with binutils 2.29 or newer, if the assembler has seen the .type directive (via ENDPROC()) for a symbol, it automatically handles the setting of the lowest bit when the symbol is used with ADR. The badr macro on the other hand handles this lowest bit manually. This leads to a jump to a wrong address in the wrong state in the syscall return path: Internal error: Oops - undefined instruction: 0 [#2] SMP THUMB2 Modules linked in: CPU: 0 PID: 652 Comm: modprobe Tainted: G D 4.18.0-rc3+ #8 PC is at ret_fast_syscall+0x4/0x62 LR is at sys_brk+0x109/0x128 pc : [<80101004>] lr : [<801c8a35>] psr: 60000013 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 50c5387d Table: 9e82006a DAC: 00000051 Process modprobe (pid: 652, stack limit = 0x(ptrval)) 80101000 : 80101000: b672 cpsid i 80101002: f8d9 2008 ldr.w r2, [r9, #8] 80101006: f1b2 4ffe cmp.w r2, #2130706432 ; 0x7f000000 80101184 : 80101184: f8d9 a000 ldr.w sl, [r9] 80101188: e92d 0030 stmdb sp!, {r4, r5} 8010118c: f01a 0ff0 tst.w sl, #240 ; 0xf0 80101190: d117 bne.n 801011c2 <__sys_trace> 80101192: 46ba mov sl, r7 80101194: f5ba 7fc8 cmp.w sl, #400 ; 0x190 80101198: bf28 it cs 8010119a: f04f 0a00 movcs.w sl, #0 8010119e: f3af 8014 nop.w {20} 801011a2: f2af 1ea2 subw lr, pc, #418 ; 0x1a2 To fix this, add a new symbol name which doesn't have ENDPROC used on it and use that with badr. We can't remove the badr usage since that would would cause breakage with older binutils. Signed-off-by: Vincent Whitchurch Signed-off-by: Russell King Signed-off-by: Sasha Levin --- arch/arm/kernel/entry-common.S | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 54c10503d71f..d7dc808a3d15 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -46,6 +46,7 @@ saved_pc .req lr * features make this path too inefficient. */ ret_fast_syscall: +__ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts @@ -75,6 +76,7 @@ fast_work_pending: * r0 first to avoid needing to save registers around each C function call. */ ret_fast_syscall: +__ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 @@ -241,7 +243,7 @@ local_restart: tst r10, #_TIF_SYSCALL_WORK @ are we tracing syscalls? bne __sys_trace - invoke_syscall tbl, scno, r10, ret_fast_syscall + invoke_syscall tbl, scno, r10, __ret_fast_syscall add r1, sp, #S_OFF 2: cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE) -- GitLab From 5a507c217779a6ef65e22bd7d337fed949f61c2b Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 6 Mar 2019 15:41:57 +0100 Subject: [PATCH 0164/1128] gfs2: Fix missed wakeups in find_insert_glock commit 605b0487f0bc1ae9963bf52ece0f5c8055186f81 upstream. Mark Syms has reported seeing tasks that are stuck waiting in find_insert_glock. It turns out that struct lm_lockname contains four padding bytes on 64-bit architectures that function glock_waitqueue doesn't skip when hashing the glock name. As a result, we can end up waking up the wrong waitqueue, and the waiting tasks may be stuck forever. Fix that by using ht_parms.key_len instead of sizeof(struct lm_lockname) for the key length. Reported-by: Mark Syms Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson Signed-off-by: Greg Kroah-Hartman --- fs/gfs2/glock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 11066d8647d2..d5284d0dbdb5 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -107,7 +107,7 @@ static int glock_wake_function(wait_queue_entry_t *wait, unsigned int mode, static wait_queue_head_t *glock_waitqueue(struct lm_lockname *name) { - u32 hash = jhash2((u32 *)name, sizeof(*name) / 4, 0); + u32 hash = jhash2((u32 *)name, ht_parms.key_len / 4, 0); return glock_wait_table + hash_32(hash, GLOCK_WAIT_TABLE_BITS); } -- GitLab From 3944df7bae9dd13c3bfefd25fe2915e8b04220b3 Mon Sep 17 00:00:00 2001 From: "Daniel F. Dickinson" Date: Sat, 22 Dec 2018 01:09:13 -0500 Subject: [PATCH 0165/1128] ath9k: Avoid OF no-EEPROM quirks without qca,no-eeprom commit ce938231bd3b1d7af3cbd8836f084801090470e1 upstream. ath9k_of_init() function[0] was initially written on the assumption that if someone had an explicit ath9k OF node that "there must be something wrong, why would someone add an OF node if everything is fine"[1] (Quoting Martin Blumenstingl ) "it turns out it's not that simple. with your requirements I'm now aware of two use-cases where the current code in ath9k_of_init() doesn't work without modifications"[1] The "your requirements" Martin speaks of is the result of the fact that I have a device (PowerCloud Systems CR5000) has some kind of default - not unique mac address - set and requires to set the correct MAC address via mac-address devicetree property, however: "some cards come with a physical EEPROM chip [or OTP] so "qca,no-eeprom" should not be set (your use-case). in this case AH_USE_EEPROM should be set (which is the default when there is no OF node)"[1] The other use case is: the firmware on some PowerMac G5 seems to add a OF node for the ath9k card automatically. depending on the EEPROM on the card AH_NO_EEP_SWAP should be unset (which is the default when there is no OF node). see [3] After this patch to ath9k_of_init() the new behavior will be: if there's no OF node then everything is the same as before if there's an empty OF node then ath9k will use the hardware EEPROM (before ath9k would fail to initialize because no EEPROM data was provided by userspace) if there's an OF node with only a MAC address then ath9k will use the MAC address and the hardware EEPROM (see the case above) with "qca,no-eeprom" EEPROM data from userspace will be requested. the behavior here will not change [1] Martin provides additional background on EEPROM swapping[1]. Thanks to Christian Lamparter for all his help on troubleshooting this issue and the basis for this patch. [0]https://elixir.bootlin.com/linux/v4.20-rc7/source/drivers/net/wireless/ath/ath9k/init.c#L615 [1]https://github.com/openwrt/openwrt/pull/1645#issuecomment-448027058 [2]https://github.com/openwrt/openwrt/pull/1613 [3]https://patchwork.kernel.org/patch/10241731/ Fixes: 138b41253d9c ("ath9k: parse the device configuration from an OF node") Reviewed-by: Martin Blumenstingl Tested-by: Martin Blumenstingl Signed-off-by: Daniel F. Dickinson Signed-off-by: Kalle Valo Cc: Christian Lamparter Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/ath/ath9k/init.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c index bb7936090b91..b8e520fc2870 100644 --- a/drivers/net/wireless/ath/ath9k/init.c +++ b/drivers/net/wireless/ath/ath9k/init.c @@ -580,15 +580,15 @@ static int ath9k_of_init(struct ath_softc *sc) ret = ath9k_eeprom_request(sc, eeprom_name); if (ret) return ret; + + ah->ah_flags &= ~AH_USE_EEPROM; + ah->ah_flags |= AH_NO_EEP_SWAP; } mac = of_get_mac_address(np); if (mac) ether_addr_copy(common->macaddr, mac); - ah->ah_flags &= ~AH_USE_EEPROM; - ah->ah_flags |= AH_NO_EEP_SWAP; - return 0; } -- GitLab From 6f166975a72c85094ca5364f85efd46b36f0f86a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 7 Feb 2019 20:36:53 +0100 Subject: [PATCH 0166/1128] driver core: Postpone DMA tear-down until after devres release MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 376991db4b6464e906d699ef07681e2ffa8ab08c upstream. When unbinding the (IOMMU-enabled) R-Car SATA device on Salvator-XS (R-Car H3 ES2.0), in preparation of rebinding against vfio-platform for device pass-through for virtualization:     echo ee300000.sata > /sys/bus/platform/drivers/sata_rcar/unbind the kernel crashes with:     Unable to handle kernel paging request at virtual address ffffffbf029ffffc     Mem abort info:       ESR = 0x96000006       Exception class = DABT (current EL), IL = 32 bits       SET = 0, FnV = 0       EA = 0, S1PTW = 0     Data abort info:       ISV = 0, ISS = 0x00000006       CM = 0, WnR = 0     swapper pgtable: 4k pages, 39-bit VAs, pgdp = 000000007e8c586c     [ffffffbf029ffffc] pgd=000000073bfc6003, pud=000000073bfc6003, pmd=0000000000000000     Internal error: Oops: 96000006 [#1] SMP     Modules linked in:     CPU: 0 PID: 1098 Comm: bash Not tainted 5.0.0-rc5-salvator-x-00452-g37596f884f4318ef #287     Hardware name: Renesas Salvator-X 2nd version board based on r8a7795 ES2.0+ (DT)     pstate: 60400005 (nZCv daif +PAN -UAO)     pc : __free_pages+0x8/0x58     lr : __dma_direct_free_pages+0x50/0x5c     sp : ffffff801268baa0     x29: ffffff801268baa0 x28: 0000000000000000     x27: ffffffc6f9c60bf0 x26: ffffffc6f9c60bf0     x25: ffffffc6f9c60810 x24: 0000000000000000     x23: 00000000fffff000 x22: ffffff8012145000     x21: 0000000000000800 x20: ffffffbf029fffc8     x19: 0000000000000000 x18: ffffffc6f86c42c8     x17: 0000000000000000 x16: 0000000000000070     x15: 0000000000000003 x14: 0000000000000000     x13: ffffff801103d7f8 x12: 0000000000000028     x11: ffffff8011117604 x10: 0000000000009ad8     x9 : ffffff80110126d0 x8 : ffffffc6f7563000     x7 : 6b6b6b6b6b6b6b6b x6 : 0000000000000018     x5 : ffffff8011cf3cc8 x4 : 0000000000004000     x3 : 0000000000080000 x2 : 0000000000000001     x1 : 0000000000000000 x0 : ffffffbf029fffc8     Process bash (pid: 1098, stack limit = 0x00000000c38e3e32)     Call trace:      __free_pages+0x8/0x58      __dma_direct_free_pages+0x50/0x5c      arch_dma_free+0x1c/0x98      dma_direct_free+0x14/0x24      dma_free_attrs+0x9c/0xdc      dmam_release+0x18/0x20      release_nodes+0x25c/0x28c      devres_release_all+0x48/0x4c      device_release_driver_internal+0x184/0x1f0      device_release_driver+0x14/0x1c      unbind_store+0x70/0xb8      drv_attr_store+0x24/0x34      sysfs_kf_write+0x4c/0x64      kernfs_fop_write+0x154/0x1c4      __vfs_write+0x34/0x164      vfs_write+0xb4/0x16c      ksys_write+0x5c/0xbc      __arm64_sys_write+0x14/0x1c      el0_svc_common+0x98/0x114      el0_svc_handler+0x1c/0x24      el0_svc+0x8/0xc     Code: d51b4234 17fffffa a9bf7bfd 910003fd (b9403404)     ---[ end trace 8c564cdd3a1a840f ]--- While I've bisected this to commit e8e683ae9a736407 ("iommu/of: Fix probe-deferral"), and reverting that commit on post-v5.0-rc4 kernels does fix the problem, this turned out to be a red herring. On arm64, arch_teardown_dma_ops() resets dev->dma_ops to NULL. Hence if a driver has used a managed DMA allocation API, the allocated DMA memory will be freed using the direct DMA ops, while it may have been allocated using a custom DMA ops (iommu_dma_ops in this case). Fix this by reversing the order of the calls to devres_release_all() and arch_teardown_dma_ops(). Signed-off-by: Geert Uytterhoeven Acked-by: Christoph Hellwig Reviewed-by: Rafael J. Wysocki Cc: stable Reviewed-by: Robin Murphy [rm: backport for 4.12-4.19 - kernels before 5.0 will not see the crash above, but may get silent memory corruption instead] Signed-off-by: Robin Murphy Signed-off-by: Greg Kroah-Hartman --- drivers/base/dd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index d928cc6d0638..cb3672cfdaaa 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -850,9 +850,9 @@ static void __device_release_driver(struct device *dev, struct device *parent) drv->remove(dev); device_links_driver_cleanup(dev); - dma_deconfigure(dev); devres_release_all(dev); + dma_deconfigure(dev); dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) -- GitLab From 3abe75e37347254f6d5401b4da267c20e220b8f5 Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" Date: Tue, 5 Mar 2019 22:23:15 +0100 Subject: [PATCH 0167/1128] perf/x86/intel: Make cpuc allocations consistent commit d01b1f96a82e5dd7841a1d39db3abfdaf95f70ab upstream The cpuc data structure allocation is different between fake and real cpuc's; use the same code to init/free both. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/core.c | 13 +++++-------- arch/x86/events/intel/core.c | 29 ++++++++++++++++++----------- arch/x86/events/perf_event.h | 11 ++++++++--- 3 files changed, 31 insertions(+), 22 deletions(-) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index e14a39598e8a..65e44f0588e2 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1968,7 +1968,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu) */ static void free_fake_cpuc(struct cpu_hw_events *cpuc) { - kfree(cpuc->shared_regs); + intel_cpuc_finish(cpuc); kfree(cpuc); } @@ -1980,14 +1980,11 @@ static struct cpu_hw_events *allocate_fake_cpuc(void) cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL); if (!cpuc) return ERR_PTR(-ENOMEM); - - /* only needed, if we have extra_regs */ - if (x86_pmu.extra_regs) { - cpuc->shared_regs = allocate_shared_regs(cpu); - if (!cpuc->shared_regs) - goto error; - } cpuc->is_fake = 1; + + if (intel_cpuc_prepare(cpuc, cpu)) + goto error; + return cpuc; error: free_fake_cpuc(cpuc); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 9f556c94a0b8..b1bec46698cc 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3262,7 +3262,7 @@ ssize_t intel_event_sysfs_show(char *page, u64 config) return x86_event_sysfs_show(page, config, event); } -struct intel_shared_regs *allocate_shared_regs(int cpu) +static struct intel_shared_regs *allocate_shared_regs(int cpu) { struct intel_shared_regs *regs; int i; @@ -3294,10 +3294,9 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) return c; } -static int intel_pmu_cpu_prepare(int cpu) -{ - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); +int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) +{ if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) @@ -3307,7 +3306,7 @@ static int intel_pmu_cpu_prepare(int cpu) if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint); - cpuc->constraint_list = kzalloc(sz, GFP_KERNEL); + cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu)); if (!cpuc->constraint_list) goto err_shared_regs; @@ -3332,6 +3331,11 @@ static int intel_pmu_cpu_prepare(int cpu) return -ENOMEM; } +static int intel_pmu_cpu_prepare(int cpu) +{ + return intel_cpuc_prepare(&per_cpu(cpu_hw_events, cpu), cpu); +} + static void flip_smm_bit(void *data) { unsigned long set = *(unsigned long *)data; @@ -3403,9 +3407,8 @@ static void intel_pmu_cpu_starting(int cpu) } } -static void free_excl_cntrs(int cpu) +static void free_excl_cntrs(struct cpu_hw_events *cpuc) { - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); struct intel_excl_cntrs *c; c = cpuc->excl_cntrs; @@ -3423,9 +3426,8 @@ static void intel_pmu_cpu_dying(int cpu) fini_debug_store_on_cpu(cpu); } -static void intel_pmu_cpu_dead(int cpu) +void intel_cpuc_finish(struct cpu_hw_events *cpuc) { - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); struct intel_shared_regs *pc; pc = cpuc->shared_regs; @@ -3435,7 +3437,12 @@ static void intel_pmu_cpu_dead(int cpu) cpuc->shared_regs = NULL; } - free_excl_cntrs(cpu); + free_excl_cntrs(cpuc); +} + +static void intel_pmu_cpu_dead(int cpu) +{ + intel_cpuc_finish(&per_cpu(cpu_hw_events, cpu)); } static void intel_pmu_sched_task(struct perf_event_context *ctx, @@ -4494,7 +4501,7 @@ static __init int fixup_ht_bug(void) hardlockup_detector_perf_restart(); for_each_online_cpu(c) - free_excl_cntrs(c); + free_excl_cntrs(&per_cpu(cpu_hw_events, c)); cpus_read_unlock(); pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n"); diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index fbbc10338987..ee96c4883188 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -880,7 +880,8 @@ struct event_constraint * x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event); -struct intel_shared_regs *allocate_shared_regs(int cpu); +extern int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu); +extern void intel_cpuc_finish(struct cpu_hw_events *cpuc); int intel_pmu_init(void); @@ -1014,9 +1015,13 @@ static inline int intel_pmu_init(void) return 0; } -static inline struct intel_shared_regs *allocate_shared_regs(int cpu) +static inline int intel_cpuc_prepare(struct cpu_hw_event *cpuc, int cpu) +{ + return 0; +} + +static inline void intel_cpuc_finish(struct cpu_hw_event *cpuc) { - return NULL; } static inline int is_ht_workaround_enabled(void) -- GitLab From 2a78ea141f9088dd4e6745c07dd3971162a73930 Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" Date: Tue, 5 Mar 2019 22:23:16 +0100 Subject: [PATCH 0168/1128] perf/x86/intel: Generalize dynamic constraint creation commit 11f8b2d65ca9029591c8df26bb6bd063c312b7fe upstream Such that we can re-use it. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/intel/core.c | 51 +++++++++++++++++++++--------------- 1 file changed, 30 insertions(+), 21 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index b1bec46698cc..3c29e7fe53f1 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2639,6 +2639,35 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc) raw_spin_unlock(&excl_cntrs->lock); } +static struct event_constraint * +dyn_constraint(struct cpu_hw_events *cpuc, struct event_constraint *c, int idx) +{ + WARN_ON_ONCE(!cpuc->constraint_list); + + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { + struct event_constraint *cx; + + /* + * grab pre-allocated constraint entry + */ + cx = &cpuc->constraint_list[idx]; + + /* + * initialize dynamic constraint + * with static constraint + */ + *cx = *c; + + /* + * mark constraint as dynamic + */ + cx->flags |= PERF_X86_EVENT_DYNAMIC; + c = cx; + } + + return c; +} + static struct event_constraint * intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, int idx, struct event_constraint *c) @@ -2669,27 +2698,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * only needed when constraint has not yet * been cloned (marked dynamic) */ - if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { - struct event_constraint *cx; - - /* - * grab pre-allocated constraint entry - */ - cx = &cpuc->constraint_list[idx]; - - /* - * initialize dynamic constraint - * with static constraint - */ - *cx = *c; - - /* - * mark constraint as dynamic, so we - * can free it later on - */ - cx->flags |= PERF_X86_EVENT_DYNAMIC; - c = cx; - } + c = dyn_constraint(cpuc, c, idx); /* * From here on, the constraint is dynamic. -- GitLab From 0e6487a0c7a8099231e0c14312a31efcf5f38e4e Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" Date: Tue, 5 Mar 2019 22:23:17 +0100 Subject: [PATCH 0169/1128] x86: Add TSX Force Abort CPUID/MSR commit 52f64909409c17adf54fcf5f9751e0544ca3a6b4 upstream Skylake systems will receive a microcode update to address a TSX errata. This microcode will (by default) clobber PMC3 when TSX instructions are (speculatively or not) executed. It also provides an MSR to cause all TSX transaction to abort and preserve PMC3. Add the CPUID enumeration and MSR definition. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/msr-index.h | 6 ++++++ 2 files changed, 7 insertions(+) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 7d910827126b..e90940ecb436 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -339,6 +339,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index fed3636dce9a..b0df002c60df 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -610,6 +610,12 @@ #define MSR_IA32_TSC_DEADLINE 0x000006E0 + +#define MSR_TSX_FORCE_ABORT 0x0000010F + +#define MSR_TFA_RTM_FORCE_ABORT_BIT 0 +#define MSR_TFA_RTM_FORCE_ABORT BIT_ULL(MSR_TFA_RTM_FORCE_ABORT_BIT) + /* P4/Xeon+ specific */ #define MSR_IA32_MCG_EAX 0x00000180 #define MSR_IA32_MCG_EBX 0x00000181 -- GitLab From d7ec8d8cc95f2899e7047fb5eda53d7f48553ffe Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" Date: Tue, 5 Mar 2019 22:23:18 +0100 Subject: [PATCH 0170/1128] perf/x86/intel: Implement support for TSX Force Abort commit 400816f60c543153656ac74eaf7f36f6b7202378 upstream Skylake (and later) will receive a microcode update to address a TSX errata. This microcode will, on execution of a TSX instruction (speculative or not) use (clobber) PMC3. This update will also provide a new MSR to change this behaviour along with a CPUID bit to enumerate the presence of this new MSR. When the MSR gets set; the microcode will no longer use PMC3 but will Force Abort every TSX transaction (upon executing COMMIT). When TSX Force Abort (TFA) is allowed (default); the MSR gets set when PMC3 gets scheduled and cleared when, after scheduling, PMC3 is unused. When TFA is not allowed; clear PMC3 from all constraints such that it will not get used. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/intel/core.c | 74 ++++++++++++++++++++++++++++++++++-- arch/x86/events/perf_event.h | 6 +++ 2 files changed, 77 insertions(+), 3 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 3c29e7fe53f1..65a369a42338 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -1995,6 +1995,39 @@ static void intel_pmu_nhm_enable_all(int added) intel_pmu_enable_all(added); } +static void intel_set_tfa(struct cpu_hw_events *cpuc, bool on) +{ + u64 val = on ? MSR_TFA_RTM_FORCE_ABORT : 0; + + if (cpuc->tfa_shadow != val) { + cpuc->tfa_shadow = val; + wrmsrl(MSR_TSX_FORCE_ABORT, val); + } +} + +static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) +{ + /* + * We're going to use PMC3, make sure TFA is set before we touch it. + */ + if (cntr == 3 && !cpuc->is_fake) + intel_set_tfa(cpuc, true); +} + +static void intel_tfa_pmu_enable_all(int added) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + /* + * If we find PMC3 is no longer used when we enable the PMU, we can + * clear TFA. + */ + if (!test_bit(3, cpuc->active_mask)) + intel_set_tfa(cpuc, false); + + intel_pmu_enable_all(added); +} + static inline u64 intel_pmu_get_status(void) { u64 status; @@ -3218,6 +3251,26 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, return c; } +static bool allow_tsx_force_abort = true; + +static struct event_constraint * +tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c = hsw_get_event_constraints(cpuc, idx, event); + + /* + * Without TFA we must not use PMC3. + */ + if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) { + c = dyn_constraint(cpuc, c, idx); + c->idxmsk64 &= ~(1ULL << 3); + c->weight--; + } + + return c; +} + /* * Broadwell: * @@ -3312,13 +3365,15 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) goto err; } - if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { + if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) { size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint); cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu)); if (!cpuc->constraint_list) goto err_shared_regs; + } + if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { cpuc->excl_cntrs = allocate_excl_cntrs(cpu); if (!cpuc->excl_cntrs) goto err_constraint_list; @@ -3425,9 +3480,10 @@ static void free_excl_cntrs(struct cpu_hw_events *cpuc) if (c->core_id == -1 || --c->refcnt == 0) kfree(c); cpuc->excl_cntrs = NULL; - kfree(cpuc->constraint_list); - cpuc->constraint_list = NULL; } + + kfree(cpuc->constraint_list); + cpuc->constraint_list = NULL; } static void intel_pmu_cpu_dying(int cpu) @@ -3912,8 +3968,11 @@ static struct attribute *intel_pmu_caps_attrs[] = { NULL }; +DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort); + static struct attribute *intel_pmu_attrs[] = { &dev_attr_freeze_on_smi.attr, + NULL, /* &dev_attr_allow_tsx_force_abort.attr.attr */ NULL, }; @@ -4369,6 +4428,15 @@ __init int intel_pmu_init(void) x86_pmu.cpu_events = get_hsw_events_attrs(); intel_pmu_pebs_data_source_skl( boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X); + + if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) { + x86_pmu.flags |= PMU_FL_TFA; + x86_pmu.get_event_constraints = tfa_get_event_constraints; + x86_pmu.enable_all = intel_tfa_pmu_enable_all; + x86_pmu.commit_scheduling = intel_tfa_commit_scheduling; + intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr; + } + pr_cont("Skylake events, "); name = "skylake"; break; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ee96c4883188..9702f4ed4748 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -238,6 +238,11 @@ struct cpu_hw_events { struct intel_excl_cntrs *excl_cntrs; int excl_thread_id; /* 0 or 1 */ + /* + * SKL TSX_FORCE_ABORT shadow + */ + u64 tfa_shadow; + /* * AMD specific bits */ @@ -672,6 +677,7 @@ do { \ #define PMU_FL_HAS_RSP_1 0x2 /* has 2 equivalent offcore_rsp regs */ #define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */ #define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ +#define PMU_FL_TFA 0x20 /* deal with TSX force abort */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr -- GitLab From d9896164529697fade02aafc65a06722f7191d68 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 13 Mar 2019 14:03:24 -0700 Subject: [PATCH 0171/1128] Linux 4.14.106 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index d5375891a7eb..ecc3a2a82a49 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 105 +SUBLEVEL = 106 EXTRAVERSION = NAME = Petit Gorille -- GitLab From 5cf19c008d09b7f4f00bb2658a93e490f1b5856f Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 15 Feb 2019 00:08:25 +0800 Subject: [PATCH 0172/1128] f2fs: fix to check inline_xattr_size boundary correctly We use below condition to check inline_xattr_size boundary: if (!F2FS_OPTION(sbi).inline_xattr_size || F2FS_OPTION(sbi).inline_xattr_size >= DEF_ADDRS_PER_INODE - F2FS_TOTAL_EXTRA_ATTR_SIZE - DEF_INLINE_RESERVED_SIZE - DEF_MIN_INLINE_SIZE) There is there problems in that check: - we should allow inline_xattr_size equaling to min size of inline {data,dentry} area. - F2FS_TOTAL_EXTRA_ATTR_SIZE and inline_xattr_size are based on different size unit, previous one is 4 bytes, latter one is 1 bytes. - DEF_MIN_INLINE_SIZE only indicate min size of inline data area, however, we need to consider min size of inline dentry area as well, minimal inline dentry should at least contain two entries: '.' and '..', so that min inline_dentry size is 40 bytes. .bitmap 1 * 1 = 1 .reserved 1 * 1 = 1 .dentry 11 * 2 = 22 .filename 8 * 2 = 16 total 40 Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 1 - fs/f2fs/super.c | 13 +++++++------ include/linux/f2fs_fs.h | 13 +++++++------ 3 files changed, 14 insertions(+), 13 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 5c0da6c4f187..f5814dc68fa5 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -460,7 +460,6 @@ struct f2fs_flush_device { /* for inline stuff */ #define DEF_INLINE_RESERVED_SIZE 1 -#define DEF_MIN_INLINE_SIZE 1 static inline int get_extra_isize(struct inode *inode); static inline int get_inline_xattr_addrs(struct inode *inode); #define MAX_INLINE_DATA(inode) (sizeof(__le32) * \ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b3b9a74303ba..7432d1a7938a 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -834,12 +834,13 @@ static int parse_options(struct super_block *sb, char *options) "set with inline_xattr option"); return -EINVAL; } - if (!F2FS_OPTION(sbi).inline_xattr_size || - F2FS_OPTION(sbi).inline_xattr_size >= - DEF_ADDRS_PER_INODE - - F2FS_TOTAL_EXTRA_ATTR_SIZE - - DEF_INLINE_RESERVED_SIZE - - DEF_MIN_INLINE_SIZE) { + if (F2FS_OPTION(sbi).inline_xattr_size < + sizeof(struct f2fs_xattr_header) / sizeof(__le32) || + F2FS_OPTION(sbi).inline_xattr_size > + DEF_ADDRS_PER_INODE - + F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - + DEF_INLINE_RESERVED_SIZE - + MIN_INLINE_DENTRY_SIZE / sizeof(__le32)) { f2fs_msg(sb, KERN_ERR, "inline xattr size is out of range"); return -EINVAL; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 8d57aaee8166..666db8eb71e0 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -490,12 +490,12 @@ typedef __le32 f2fs_hash_t; /* * space utilization of regular dentry and inline dentry (w/o extra reservation) - * regular dentry inline dentry - * bitmap 1 * 27 = 27 1 * 23 = 23 - * reserved 1 * 3 = 3 1 * 7 = 7 - * dentry 11 * 214 = 2354 11 * 182 = 2002 - * filename 8 * 214 = 1712 8 * 182 = 1456 - * total 4096 3488 + * regular dentry inline dentry (def) inline dentry (min) + * bitmap 1 * 27 = 27 1 * 23 = 23 1 * 1 = 1 + * reserved 1 * 3 = 3 1 * 7 = 7 1 * 1 = 1 + * dentry 11 * 214 = 2354 11 * 182 = 2002 11 * 2 = 22 + * filename 8 * 214 = 1712 8 * 182 = 1456 8 * 2 = 16 + * total 4096 3488 40 * * Note: there are more reserved space in inline dentry than in regular * dentry, when converting inline dentry we should handle this carefully. @@ -507,6 +507,7 @@ typedef __le32 f2fs_hash_t; #define SIZE_OF_RESERVED (PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \ F2FS_SLOT_LEN) * \ NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP)) +#define MIN_INLINE_DENTRY_SIZE 40 /* just include '.' and '..' entries */ /* One directory entry slot representing F2FS_SLOT_LEN-sized file name */ struct f2fs_dir_entry { -- GitLab From 72e41a1bb0d52dddb7c1ee12fa6ca20fd98cdde5 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 15 Feb 2019 00:16:15 +0800 Subject: [PATCH 0173/1128] f2fs: don't allow negative ->write_io_size_bits As Dan reported: "We put an upper bound on ->write_io_size_bits but we don't have a lower bound." So let's add lower bound check for ->write_io_size_bits in parse_options(). [We don't allow configuring ->write_io_size_bits to zero, since at least we need to fill one dummy page for aligned IO.] Reported-by: Dan Carpenter Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 7432d1a7938a..c415c8135296 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -586,7 +586,7 @@ static int parse_options(struct super_block *sb, char *options) case Opt_io_size_bits: if (args->from && match_int(args, &arg)) return -EINVAL; - if (arg > __ilog2_u32(BIO_MAX_PAGES)) { + if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_PAGES)) { f2fs_msg(sb, KERN_WARNING, "Not support %d, larger than %d", 1 << arg, BIO_MAX_PAGES); -- GitLab From 1b5eba010446b752b0038b8fa900b253bb057f9a Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 5 Feb 2019 07:59:57 -0800 Subject: [PATCH 0174/1128] f2fs: don't clear CP_QUOTA_NEED_FSCK_FLAG If we met this once, let fsck.f2fs clear this only. Note that, this addresses all the subtle fault injection test. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 47d720562b3a..62a8770cb19b 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1267,8 +1267,10 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); - else - __clear_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + /* + * TODO: we count on fsck.f2fs to clear this flag until we figure out + * missing cases which clear it incorrectly. + */ if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); -- GitLab From 85cedd366c63a7672f38354f39329754df759ce1 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 15 Feb 2019 19:04:38 -0800 Subject: [PATCH 0175/1128] f2fs: fix wrong #endif We have to cover whole headerfile with last #endif. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index f5814dc68fa5..26c28a78f38b 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3627,8 +3627,6 @@ extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, #define f2fs_build_fault_attr(sbi, rate, type) do { } while (0) #endif -#endif - static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) { #ifdef CONFIG_QUOTA @@ -3641,3 +3639,5 @@ static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) #endif return false; } + +#endif -- GitLab From 09081958cbe80fae92daded756751442cedc6281 Mon Sep 17 00:00:00 2001 From: Zeng Guangyue Date: Mon, 18 Feb 2019 14:26:41 +0800 Subject: [PATCH 0176/1128] f2fs: correct spelling mistake correct spelling mistake for "nunmber" Signed-off-by: Zeng Guangyue Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 666db8eb71e0..f5740423b002 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -285,7 +285,7 @@ enum { struct node_footer { __le32 nid; /* node id */ - __le32 ino; /* inode nunmber */ + __le32 ino; /* inode number */ __le32 flag; /* include cold/fsync/dentry marks and offset */ __le64 cp_ver; /* checkpoint version */ __le32 next_blkaddr; /* next node page block address */ -- GitLab From 4d1af3c6f4b65d5fc49c5eacbf3dc9d94fb4469a Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Tue, 19 Feb 2019 10:31:52 +0800 Subject: [PATCH 0177/1128] f2fs: silence VM_WARN_ON_ONCE in mempool_alloc Note that __GFP_ZERO is not supported for mempool_alloc, which also documented in the mempool_alloc comments. Signed-off-by: Gao Xiang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index b94d4eca22f4..b9ee3a450d57 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -298,9 +298,10 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, for (; start < F2FS_IO_SIZE(sbi); start++) { struct page *page = mempool_alloc(sbi->write_io_dummy, - GFP_NOIO | __GFP_ZERO | __GFP_NOFAIL); + GFP_NOIO | __GFP_NOFAIL); f2fs_bug_on(sbi, !page); + zero_user_segment(page, 0, PAGE_SIZE); SetPagePrivate(page); set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE); lock_page(page); -- GitLab From 5fc60b5c67b80f5d4e65250358a2eb6665280253 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 19 Feb 2019 16:23:53 +0800 Subject: [PATCH 0178/1128] f2fs: fix to retry fill_super only if recovery failed With current retry mechanism in f2fs_fill_super, first fill_super fails due to no memory, then second fill_super runs w/o recovery, if we succeed, we may lose fsynced data, it doesn't make sense. Let's retry fill_super only if it occurs non-ENOMEM error during recovery. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/super.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index c415c8135296..2dc279daf7f2 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3053,10 +3053,11 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) struct f2fs_super_block *raw_super; struct inode *root; int err; - bool retry = true, need_fsck = false; + bool skip_recovery = false, need_fsck = false; char *options = NULL; int recovery, i, valid_super_block; struct curseg_info *seg_i; + int retry_cnt = 1; try_onemore: err = -EINVAL; @@ -3344,7 +3345,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) goto free_meta; if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG))) - goto skip_recovery; + goto reset_checkpoint; /* recover fsynced data */ if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { @@ -3361,11 +3362,13 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) if (need_fsck) set_sbi_flag(sbi, SBI_NEED_FSCK); - if (!retry) - goto skip_recovery; + if (skip_recovery) + goto reset_checkpoint; err = f2fs_recover_fsync_data(sbi, false); if (err < 0) { + if (err != -ENOMEM) + skip_recovery = true; need_fsck = true; f2fs_msg(sb, KERN_ERR, "Cannot recover all fsync data errno=%d", err); @@ -3381,7 +3384,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) goto free_meta; } } -skip_recovery: +reset_checkpoint: /* f2fs_recover_fsync_data() cleared this already */ clear_sbi_flag(sbi, SBI_POR_DOING); @@ -3427,7 +3430,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) sync_free_meta: /* safe to flush all the data */ sync_filesystem(sbi->sb); - retry = false; + retry_cnt = 0; free_meta: #ifdef CONFIG_QUOTA @@ -3487,8 +3490,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) kvfree(sbi); /* give only one another chance */ - if (retry) { - retry = false; + if (retry_cnt > 0 && skip_recovery) { + retry_cnt--; shrink_dcache_sb(sb); goto try_onemore; } -- GitLab From 95484da8dd2366bf7f680061e62812b138a43c92 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 19 Feb 2019 17:08:18 +0800 Subject: [PATCH 0179/1128] f2fs: make fault injection covering __submit_flush_wait() This patch changes to allow failure of f2fs_bio_alloc() in __submit_flush_wait(), which can simulate flush error in checkpoint() for covering more error paths. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/segment.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index fdd8cd21522f..2537893e9466 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -542,9 +542,13 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) static int __submit_flush_wait(struct f2fs_sb_info *sbi, struct block_device *bdev) { - struct bio *bio = f2fs_bio_alloc(sbi, 0, true); + struct bio *bio; int ret; + bio = f2fs_bio_alloc(sbi, 0, false); + if (!bio) + return -ENOMEM; + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; bio_set_dev(bio, bdev); ret = submit_bio_wait(bio); -- GitLab From 3823b7d1081f438def137ce486a73f6e6d5e2fdc Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 21 Feb 2019 20:37:14 +0800 Subject: [PATCH 0180/1128] f2fs: fix encrypted page memory leak For IPU path of f2fs_do_write_data_page(), in its error path, we need to release encrypted page and fscrypt context, otherwise it will cause memory leak. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index b9ee3a450d57..91dad12942b4 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1860,8 +1860,13 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) if (fio->need_lock == LOCK_REQ) f2fs_unlock_op(fio->sbi); err = f2fs_inplace_write_data(fio); - if (err && PageWriteback(page)) - end_page_writeback(page); + if (err) { + if (f2fs_encrypted_file(inode)) + fscrypt_pullback_bio_page(&fio->encrypted_page, + true); + if (PageWriteback(page)) + end_page_writeback(page); + } trace_f2fs_do_write_data_page(fio->page, IPU); set_inode_flag(inode, FI_UPDATE_WRITE); return err; -- GitLab From 357040ed18b6b7d83cf1734ec4bf1026267de4bc Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 21 Feb 2019 20:40:13 +0800 Subject: [PATCH 0181/1128] f2fs: fix to update iostat correctly in IPU path In error path of IPU, we didn't account iostat correctly, fix it. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/segment.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 2537893e9466..d74359325da6 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -3182,10 +3182,10 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) stat_inc_inplace_blocks(fio->sbi); err = f2fs_submit_page_bio(fio); - if (!err) + if (!err) { update_device_state(fio); - - f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); + f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); + } return err; } -- GitLab From c6fcc42aaf5ff55cbbf12cd45f29c3441bd622a0 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Thu, 21 Feb 2019 12:57:35 +0800 Subject: [PATCH 0182/1128] f2fs: no need to take page lock in readdir VFS will take inode_lock for readdir, therefore no need to take page lock in readdir at all just as the majority of other generic filesystems. This patch improves concurrency since .iterate_shared was introduced to VFS years ago. Signed-off-by: Gao Xiang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/dir.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 0e0e0880c4de..dd06815048f4 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -896,7 +896,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) page_cache_sync_readahead(inode->i_mapping, ra, file, n, min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES)); - dentry_page = f2fs_get_lock_data_page(inode, n, false); + dentry_page = f2fs_find_data_page(inode, n); if (IS_ERR(dentry_page)) { err = PTR_ERR(dentry_page); if (err == -ENOENT) { @@ -914,11 +914,11 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) err = f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr); if (err) { - f2fs_put_page(dentry_page, 1); + f2fs_put_page(dentry_page, 0); break; } - f2fs_put_page(dentry_page, 1); + f2fs_put_page(dentry_page, 0); } out_free: fscrypt_fname_free_buffer(&fstr); -- GitLab From fb28b034f8aa3e92b0ac303ad965397704a1d7e5 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 25 Feb 2019 09:46:45 -0800 Subject: [PATCH 0183/1128] f2fs: give random value to i_generation This follows to give random number to i_generation along with commit 232530680290b ("ext4: improve smp scalability for inode generation") This can be used for DUN for UFS HW encryption. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 2 -- fs/f2fs/namei.c | 3 ++- fs/f2fs/super.c | 1 - 3 files changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 26c28a78f38b..26afa6b31f96 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1243,8 +1243,6 @@ struct f2fs_sb_info { unsigned int nquota_files; /* # of quota sysfile */ - u32 s_next_generation; /* for NFS support */ - /* # of pages, see count_type */ atomic_t nr_pages[NR_COUNT_TYPE]; /* # of allocated blocks */ diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 826e708a0ed0..c97f1665d430 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -50,7 +51,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = F2FS_I(inode)->i_crtime = current_time(inode); - inode->i_generation = sbi->s_next_generation++; + inode->i_generation = prandom_u32(); if (S_ISDIR(inode->i_mode)) F2FS_I(inode)->i_current_depth = 1; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 2dc279daf7f2..f1baa20bb974 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3129,7 +3129,6 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) sb->s_maxbytes = sbi->max_file_blocks << le32_to_cpu(raw_super->log_blocksize); sb->s_max_links = F2FS_LINK_MAX; - get_random_bytes(&sbi->s_next_generation, sizeof(u32)); #ifdef CONFIG_QUOTA sb->dq_op = &f2fs_quota_operations; -- GitLab From 2568f36fa988a796b8786bb7ac16413380dc050e Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Sat, 23 Feb 2019 09:48:27 +0800 Subject: [PATCH 0184/1128] f2fs: fix to dirty inode for i_mode recovery As Seulbae Kim reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202637 We didn't recover permission field correctly after sudden power-cut, the reason is in setattr we didn't add inode into global dirty list once i_mode is changed, so latter checkpoint triggered by fsync will not flush last i_mode into disk, result in this problem, fix it. Reported-by: Seulbae Kim Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 5df1253c2010..c6085c966e6b 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -766,7 +766,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int err; - bool size_changed = false; if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; @@ -841,8 +840,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) down_write(&F2FS_I(inode)->i_sem); F2FS_I(inode)->last_disk_size = i_size_read(inode); up_write(&F2FS_I(inode)->i_sem); - - size_changed = true; } __setattr_copy(inode, attr); @@ -856,7 +853,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) } /* file size may changed here */ - f2fs_mark_inode_dirty_sync(inode, size_changed); + f2fs_mark_inode_dirty_sync(inode, true); /* inode change will produce dirty node pages flushed by checkpoint */ f2fs_balance_fs(F2FS_I_SB(inode), true); -- GitLab From 23feb6194dc9cd1359f79ee369eb7d927ade5672 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 25 Feb 2019 17:11:03 +0800 Subject: [PATCH 0185/1128] f2fs: fix to avoid deadlock of atomic file operations Thread A Thread B - __fput - f2fs_release_file - drop_inmem_pages - mutex_lock(&fi->inmem_lock) - __revoke_inmem_pages - lock_page(page) - open - f2fs_setattr - truncate_setsize - truncate_inode_pages_range - lock_page(page) - truncate_cleanup_page - f2fs_invalidate_page - drop_inmem_page - mutex_lock(&fi->inmem_lock); We may encounter above ABBA deadlock as reported by Kyungtae Kim: I'm reporting a bug in linux-4.17.19: "INFO: task hung in drop_inmem_page" (no reproducer) I think this might be somehow related to the following: https://groups.google.com/forum/#!searchin/syzkaller-bugs/INFO$3A$20task$20hung$20in$20%7Csort:date/syzkaller-bugs/c6soBTrdaIo/AjAzPeIzCgAJ ========================================= INFO: task syz-executor7:10822 blocked for more than 120 seconds. Not tainted 4.17.19 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. syz-executor7 D27024 10822 6346 0x00000004 Call Trace: context_switch kernel/sched/core.c:2867 [inline] __schedule+0x721/0x1e60 kernel/sched/core.c:3515 schedule+0x88/0x1c0 kernel/sched/core.c:3559 schedule_preempt_disabled+0x18/0x30 kernel/sched/core.c:3617 __mutex_lock_common kernel/locking/mutex.c:833 [inline] __mutex_lock+0x5bd/0x1410 kernel/locking/mutex.c:893 mutex_lock_nested+0x1b/0x20 kernel/locking/mutex.c:908 drop_inmem_page+0xcb/0x810 fs/f2fs/segment.c:327 f2fs_invalidate_page+0x337/0x5e0 fs/f2fs/data.c:2401 do_invalidatepage mm/truncate.c:165 [inline] truncate_cleanup_page+0x261/0x330 mm/truncate.c:187 truncate_inode_pages_range+0x552/0x1610 mm/truncate.c:367 truncate_inode_pages mm/truncate.c:478 [inline] truncate_pagecache+0x6d/0x90 mm/truncate.c:801 truncate_setsize+0x81/0xa0 mm/truncate.c:826 f2fs_setattr+0x44f/0x1270 fs/f2fs/file.c:781 notify_change+0xa62/0xe80 fs/attr.c:313 do_truncate+0x12e/0x1e0 fs/open.c:63 do_last fs/namei.c:2955 [inline] path_openat+0x2042/0x29f0 fs/namei.c:3505 do_filp_open+0x1bd/0x2c0 fs/namei.c:3540 do_sys_open+0x35e/0x4e0 fs/open.c:1101 __do_sys_open fs/open.c:1119 [inline] __se_sys_open fs/open.c:1114 [inline] __x64_sys_open+0x89/0xc0 fs/open.c:1114 do_syscall_64+0xc4/0x4e0 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4497b9 RSP: 002b:00007f734e459c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000002 RAX: ffffffffffffffda RBX: 00007f734e45a6cc RCX: 00000000004497b9 RDX: 0000000000000104 RSI: 00000000000a8280 RDI: 0000000020000080 RBP: 000000000071bea0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 0000000000007230 R14: 00000000006f02d0 R15: 00007f734e45a700 INFO: task syz-executor7:10858 blocked for more than 120 seconds. Not tainted 4.17.19 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. syz-executor7 D28880 10858 6346 0x00000004 Call Trace: context_switch kernel/sched/core.c:2867 [inline] __schedule+0x721/0x1e60 kernel/sched/core.c:3515 schedule+0x88/0x1c0 kernel/sched/core.c:3559 __rwsem_down_write_failed_common kernel/locking/rwsem-xadd.c:565 [inline] rwsem_down_write_failed+0x5e6/0xc90 kernel/locking/rwsem-xadd.c:594 call_rwsem_down_write_failed+0x17/0x30 arch/x86/lib/rwsem.S:117 __down_write arch/x86/include/asm/rwsem.h:142 [inline] down_write+0x58/0xa0 kernel/locking/rwsem.c:72 inode_lock include/linux/fs.h:713 [inline] do_truncate+0x120/0x1e0 fs/open.c:61 do_last fs/namei.c:2955 [inline] path_openat+0x2042/0x29f0 fs/namei.c:3505 do_filp_open+0x1bd/0x2c0 fs/namei.c:3540 do_sys_open+0x35e/0x4e0 fs/open.c:1101 __do_sys_open fs/open.c:1119 [inline] __se_sys_open fs/open.c:1114 [inline] __x64_sys_open+0x89/0xc0 fs/open.c:1114 do_syscall_64+0xc4/0x4e0 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4497b9 RSP: 002b:00007f734e3b4c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000002 RAX: ffffffffffffffda RBX: 00007f734e3b56cc RCX: 00000000004497b9 RDX: 0000000000000104 RSI: 00000000000a8280 RDI: 0000000020000080 RBP: 000000000071c238 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 0000000000007230 R14: 00000000006f02d0 R15: 00007f734e3b5700 INFO: task syz-executor5:10829 blocked for more than 120 seconds. Not tainted 4.17.19 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. syz-executor5 D28760 10829 6308 0x80000002 Call Trace: context_switch kernel/sched/core.c:2867 [inline] __schedule+0x721/0x1e60 kernel/sched/core.c:3515 schedule+0x88/0x1c0 kernel/sched/core.c:3559 io_schedule+0x21/0x80 kernel/sched/core.c:5179 wait_on_page_bit_common mm/filemap.c:1100 [inline] __lock_page+0x2b5/0x390 mm/filemap.c:1273 lock_page include/linux/pagemap.h:483 [inline] __revoke_inmem_pages+0xb35/0x11c0 fs/f2fs/segment.c:231 drop_inmem_pages+0xa3/0x3e0 fs/f2fs/segment.c:306 f2fs_release_file+0x2c7/0x330 fs/f2fs/file.c:1556 __fput+0x2c7/0x780 fs/file_table.c:209 ____fput+0x1a/0x20 fs/file_table.c:243 task_work_run+0x151/0x1d0 kernel/task_work.c:113 exit_task_work include/linux/task_work.h:22 [inline] do_exit+0x8ba/0x30a0 kernel/exit.c:865 do_group_exit+0x13b/0x3a0 kernel/exit.c:968 get_signal+0x6bb/0x1650 kernel/signal.c:2482 do_signal+0x84/0x1b70 arch/x86/kernel/signal.c:810 exit_to_usermode_loop+0x155/0x190 arch/x86/entry/common.c:162 prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline] syscall_return_slowpath arch/x86/entry/common.c:265 [inline] do_syscall_64+0x445/0x4e0 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4497b9 RSP: 002b:00007f1c68e74ce8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: fffffffffffffe00 RBX: 000000000071bf80 RCX: 00000000004497b9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000071bf80 RBP: 000000000071bf80 R08: 0000000000000000 R09: 000000000071bf58 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f1c68e759c0 R15: 00007f1c68e75700 This patch tries to use trylock_page to mitigate such deadlock condition for fix. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/segment.c | 43 +++++++++++++++++++++++++++++++------------ 1 file changed, 31 insertions(+), 12 deletions(-) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index d74359325da6..e730c334abba 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -215,7 +215,8 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page) } static int __revoke_inmem_pages(struct inode *inode, - struct list_head *head, bool drop, bool recover) + struct list_head *head, bool drop, bool recover, + bool trylock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct inmem_pages *cur, *tmp; @@ -227,7 +228,16 @@ static int __revoke_inmem_pages(struct inode *inode, if (drop) trace_f2fs_commit_inmem_page(page, INMEM_DROP); - lock_page(page); + if (trylock) { + /* + * to avoid deadlock in between page lock and + * inmem_lock. + */ + if (!trylock_page(page)) + continue; + } else { + lock_page(page); + } f2fs_wait_on_page_writeback(page, DATA, true, true); @@ -318,13 +328,19 @@ void f2fs_drop_inmem_pages(struct inode *inode) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - mutex_lock(&fi->inmem_lock); - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); - spin_lock(&sbi->inode_lock[ATOMIC_FILE]); - if (!list_empty(&fi->inmem_ilist)) - list_del_init(&fi->inmem_ilist); - spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); - mutex_unlock(&fi->inmem_lock); + while (!list_empty(&fi->inmem_pages)) { + mutex_lock(&fi->inmem_lock); + __revoke_inmem_pages(inode, &fi->inmem_pages, + true, false, true); + + if (list_empty(&fi->inmem_pages)) { + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (!list_empty(&fi->inmem_ilist)) + list_del_init(&fi->inmem_ilist); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + } + mutex_unlock(&fi->inmem_lock); + } clear_inode_flag(inode, FI_ATOMIC_FILE); fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0; @@ -429,12 +445,15 @@ static int __f2fs_commit_inmem_pages(struct inode *inode) * recovery or rewrite & commit last transaction. For other * error number, revoking was done by filesystem itself. */ - err = __revoke_inmem_pages(inode, &revoke_list, false, true); + err = __revoke_inmem_pages(inode, &revoke_list, + false, true, false); /* drop all uncommitted pages */ - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); + __revoke_inmem_pages(inode, &fi->inmem_pages, + true, false, false); } else { - __revoke_inmem_pages(inode, &revoke_list, false, false); + __revoke_inmem_pages(inode, &revoke_list, + false, false, false); } return err; -- GitLab From 9bc3cabe1acb4522ac2084533c140c788c9904eb Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 26 Feb 2019 19:01:15 +0800 Subject: [PATCH 0186/1128] f2fs: trace f2fs_ioc_shutdown This patch supports to trace f2fs_ioc_shutdown. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 3 +++ include/trace/events/f2fs.h | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index c6085c966e6b..1b9106523f27 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1987,6 +1987,9 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) out: if (in != F2FS_GOING_DOWN_FULLSYNC) mnt_drop_write_file(filp); + + trace_f2fs_shutdown(sbi, in, ret); + return ret; } diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index c842bc70c68c..4bf5c7d35d52 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -150,6 +150,14 @@ TRACE_DEFINE_ENUM(CP_TRIMMED); { CP_SPEC_LOG_NUM, "log type is 2" }, \ { CP_RECOVER_DIR, "dir needs recovery" }) +#define show_shutdown_mode(type) \ + __print_symbolic(type, \ + { F2FS_GOING_DOWN_FULLSYNC, "full sync" }, \ + { F2FS_GOING_DOWN_METASYNC, "meta sync" }, \ + { F2FS_GOING_DOWN_NOSYNC, "no sync" }, \ + { F2FS_GOING_DOWN_METAFLUSH, "meta flush" }, \ + { F2FS_GOING_DOWN_NEED_FSCK, "need fsck" }) + struct f2fs_sb_info; struct f2fs_io_info; struct extent_info; @@ -1620,6 +1628,30 @@ DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_exit, TP_ARGS(sb, type, count) ); +TRACE_EVENT(f2fs_shutdown, + + TP_PROTO(struct f2fs_sb_info *sbi, unsigned int mode, int ret), + + TP_ARGS(sbi, mode, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, mode) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = sbi->sb->s_dev; + __entry->mode = mode; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), mode: %s, ret:%d", + show_dev(__entry->dev), + show_shutdown_mode(__entry->mode), + __entry->ret) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- GitLab From 2ef9ad7b9b133bac997e3c2e8fea5433c23dc845 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 26 Feb 2019 19:01:16 +0800 Subject: [PATCH 0187/1128] f2fs: print more parameters in trace_f2fs_map_blocks for better map_blocks trace. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 4bf5c7d35d52..2ce6af3235fb 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -545,6 +545,9 @@ TRACE_EVENT(f2fs_map_blocks, __field(block_t, m_lblk) __field(block_t, m_pblk) __field(unsigned int, m_len) + __field(unsigned int, m_flags) + __field(int, m_seg_type) + __field(bool, m_may_create) __field(int, ret) ), @@ -554,15 +557,22 @@ TRACE_EVENT(f2fs_map_blocks, __entry->m_lblk = map->m_lblk; __entry->m_pblk = map->m_pblk; __entry->m_len = map->m_len; + __entry->m_flags = map->m_flags; + __entry->m_seg_type = map->m_seg_type; + __entry->m_may_create = map->m_may_create; __entry->ret = ret; ), TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, " - "start blkaddr = 0x%llx, len = 0x%llx, err = %d", + "start blkaddr = 0x%llx, len = 0x%llx, flags = %u," + "seg_type = %d, may_create = %d, err = %d", show_dev_ino(__entry), (unsigned long long)__entry->m_lblk, (unsigned long long)__entry->m_pblk, (unsigned long long)__entry->m_len, + __entry->m_flags, + __entry->m_seg_type, + __entry->m_may_create, __entry->ret) ); -- GitLab From d8c29f1e8c3162ce9d585c4b4b55d78ed413e1ef Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 5 Mar 2019 17:52:33 +0800 Subject: [PATCH 0188/1128] f2fs: fix to use kvfree instead of kzfree As Jiqun Li reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202747 System can panic due to using wrong allocate/free function pair in xattr interface: - use kvmalloc to allocate memory - use kzfree to free memory Let's fix to use kvfree instead of kzfree, BTW, we are safe to get rid of kzfree, since there is no such confidential data stored as xattr, we don't need to zero it before free memory. Fixes: 5222595d093e ("f2fs: use kvmalloc, if kmalloc is failed") Reported-by: Jiqun Li Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/xattr.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index fa620d31ea5f..ca47224d78ab 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -340,7 +340,7 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, *base_addr = txattr_addr; return 0; out: - kzfree(txattr_addr); + kvfree(txattr_addr); return err; } @@ -383,7 +383,7 @@ static int read_all_xattrs(struct inode *inode, struct page *ipage, *base_addr = txattr_addr; return 0; fail: - kzfree(txattr_addr); + kvfree(txattr_addr); return err; } @@ -510,7 +510,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, } error = size; out: - kzfree(base_addr); + kvfree(base_addr); return error; } @@ -556,7 +556,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) } error = buffer_size - rest; cleanup: - kzfree(base_addr); + kvfree(base_addr); return error; } @@ -687,7 +687,7 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (!error && S_ISDIR(inode->i_mode)) set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP); exit: - kzfree(base_addr); + kvfree(base_addr); return error; } -- GitLab From 3031d67522f4eb9c0b9feaefee1635f896e2413e Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 6 Mar 2019 16:18:33 +0800 Subject: [PATCH 0189/1128] f2fs: remove wrong comment in f2fs_invalidate_page() Since 8c242db9b8c0 ("f2fs: fix stale ATOMIC_WRITTEN_PAGE private pointer"), we've started to not skip clear private flag for atomic_write page truncation, so removing old wrong comment in f2fs_invalidate_page(). Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 91dad12942b4..f16bc212088f 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2710,7 +2710,6 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, clear_cold_data(page); - /* This is atomic written page, keep Private */ if (IS_ATOMIC_WRITTEN_PAGE(page)) return f2fs_drop_inmem_page(inode, page); -- GitLab From ac9805cff1fcac21889af7348aae793664225109 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 6 Mar 2019 17:30:59 +0800 Subject: [PATCH 0190/1128] f2fs: fix to add refcount once page is tagged PG_private As Gao Xiang reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202749 f2fs may skip pageout() due to incorrect page reference count. The problem here is that MM defined the rule [1] very clearly that once page was set with PG_private flag, we should increment the refcount in that page, also main flows like pageout(), migrate_page() will assume there is one additional page reference count if page_has_private() returns true. But currently, f2fs won't add/del refcount when changing PG_private flag. Anyway, f2fs should follow MM's rule to make MM's related flows running as expected. [1] https://lore.kernel.org/lkml/2b19b3c4-2bc4-15fa-15cc-27a13e5c7af1@aol.com/ Reported-by: Gao Xiang Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 4 ++-- fs/f2fs/data.c | 21 ++++++++------------- fs/f2fs/dir.c | 2 +- fs/f2fs/f2fs.h | 21 +++++++++++++++++++++ fs/f2fs/node.c | 2 +- fs/f2fs/segment.c | 9 +++------ 6 files changed, 36 insertions(+), 23 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 62a8770cb19b..5029480e69f7 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -406,7 +406,7 @@ static int f2fs_set_meta_page_dirty(struct page *page) if (!PageDirty(page)) { __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); return 1; } @@ -957,7 +957,7 @@ void f2fs_update_dirty_page(struct inode *inode, struct page *page) inode_inc_dirty_pages(inode); spin_unlock(&sbi->inode_lock[type]); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index f16bc212088f..9107411a6dab 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2713,8 +2713,7 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, if (IS_ATOMIC_WRITTEN_PAGE(page)) return f2fs_drop_inmem_page(inode, page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); } int f2fs_release_page(struct page *page, gfp_t wait) @@ -2728,8 +2727,7 @@ int f2fs_release_page(struct page *page, gfp_t wait) return 0; clear_cold_data(page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); return 1; } @@ -2797,12 +2795,8 @@ int f2fs_migrate_page(struct address_space *mapping, return -EAGAIN; } - /* - * A reference is expected if PagePrivate set when move mapping, - * however F2FS breaks this for maintaining dirty page counts when - * truncating pages. So here adjusting the 'extra_count' make it work. - */ - extra_count = (atomic_written ? 1 : 0) - page_has_private(page); + /* one extra reference was held for atomic_write page */ + extra_count = atomic_written ? 1 : 0; rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, extra_count); if (rc != MIGRATEPAGE_SUCCESS) { @@ -2823,9 +2817,10 @@ int f2fs_migrate_page(struct address_space *mapping, get_page(newpage); } - if (PagePrivate(page)) - SetPagePrivate(newpage); - set_page_private(newpage, page_private(page)); + if (PagePrivate(page)) { + f2fs_set_page_private(newpage, page_private(page)); + f2fs_clear_page_private(page); + } if (mode != MIGRATE_SYNC_NO_COPY) migrate_page_copy(newpage, page); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index dd06815048f4..d3eafe9e2ed2 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -728,7 +728,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, !f2fs_truncate_hole(dir, page->index, page->index + 1)) { f2fs_clear_radix_tree_dirty_tag(page); clear_page_dirty_for_io(page); - ClearPagePrivate(page); + f2fs_clear_page_private(page); ClearPageUptodate(page); clear_cold_data(page); inode_dec_dirty_pages(dir); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 26afa6b31f96..2327059af4a8 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2836,6 +2836,27 @@ static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, return true; } +static inline void f2fs_set_page_private(struct page *page, + unsigned long data) +{ + if (PagePrivate(page)) + return; + + get_page(page); + SetPagePrivate(page); + set_page_private(page, data); +} + +static inline void f2fs_clear_page_private(struct page *page) +{ + if (!PagePrivate(page)) + return; + + set_page_private(page, 0); + ClearPagePrivate(page); + f2fs_put_page(page, 0); +} + /* * file.c */ diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index e39ca804df6f..93e9d422c99a 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1963,7 +1963,7 @@ static int f2fs_set_node_page_dirty(struct page *page) if (!PageDirty(page)) { __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); return 1; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index e730c334abba..aa7fe79b62b2 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -191,8 +191,7 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page) f2fs_trace_pid(page); - set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); - SetPagePrivate(page); + f2fs_set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS); @@ -280,8 +279,7 @@ static int __revoke_inmem_pages(struct inode *inode, ClearPageUptodate(page); clear_cold_data(page); } - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); f2fs_put_page(page, 1); list_del(&cur->list); @@ -370,8 +368,7 @@ void f2fs_drop_inmem_page(struct inode *inode, struct page *page) kmem_cache_free(inmem_entry_slab, cur); ClearPageUptodate(page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); f2fs_put_page(page, 0); trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE); -- GitLab From f36230ae4a730301e67c631a972f4a1f13824f66 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 7 Mar 2019 17:31:30 +0800 Subject: [PATCH 0191/1128] f2fs: don't trigger read IO for beyond EOF page In f2fs_mpage_readpages(), if page is beyond EOF, we should just zero out it, but previously, before checking previous mapping info, we missed to check filesize boundary, fix it. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9107411a6dab..ec503a11e534 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1550,6 +1550,9 @@ static int f2fs_mpage_readpages(struct address_space *mapping, if (last_block > last_block_in_file) last_block = last_block_in_file; + /* just zeroing out page which is beyond EOF */ + if (block_in_file >= last_block) + goto zero_out; /* * Map blocks using the previous result first. */ @@ -1562,16 +1565,11 @@ static int f2fs_mpage_readpages(struct address_space *mapping, * Then do more f2fs_map_blocks() calls until we are * done with this page. */ - map.m_flags = 0; + map.m_lblk = block_in_file; + map.m_len = last_block - block_in_file; - if (block_in_file < last_block) { - map.m_lblk = block_in_file; - map.m_len = last_block - block_in_file; - - if (f2fs_map_blocks(inode, &map, 0, - F2FS_GET_BLOCK_DEFAULT)) - goto set_error_page; - } + if (f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT)) + goto set_error_page; got_it: if ((map.m_flags & F2FS_MAP_MAPPED)) { block_nr = map.m_pblk + block_in_file - map.m_lblk; @@ -1586,6 +1584,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping, DATA_GENERIC)) goto set_error_page; } else { +zero_out: zero_user_segment(page, 0, PAGE_SIZE); if (!PageUptodate(page)) SetPageUptodate(page); -- GitLab From d895b644336cde3f22e885cd3fb0be85bb7aad0b Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 12 Mar 2019 11:49:53 -0700 Subject: [PATCH 0192/1128] f2fs: give some messages for inline_xattr_size This patch adds some kernel messages when user sets wrong inline_xattr_size. Fixes: 500e0b28ecd3 ("f2fs: fix to check inline_xattr_size boundary correctly") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/super.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index f1baa20bb974..bb75398d9f99 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -821,6 +821,8 @@ static int parse_options(struct super_block *sb, char *options) } if (test_opt(sbi, INLINE_XATTR_SIZE)) { + int min_size, max_size; + if (!f2fs_sb_has_extra_attr(sbi) || !f2fs_sb_has_flexible_inline_xattr(sbi)) { f2fs_msg(sb, KERN_ERR, @@ -834,15 +836,18 @@ static int parse_options(struct super_block *sb, char *options) "set with inline_xattr option"); return -EINVAL; } - if (F2FS_OPTION(sbi).inline_xattr_size < - sizeof(struct f2fs_xattr_header) / sizeof(__le32) || - F2FS_OPTION(sbi).inline_xattr_size > - DEF_ADDRS_PER_INODE - + + min_size = sizeof(struct f2fs_xattr_header) / sizeof(__le32); + max_size = DEF_ADDRS_PER_INODE - F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - DEF_INLINE_RESERVED_SIZE - - MIN_INLINE_DENTRY_SIZE / sizeof(__le32)) { + MIN_INLINE_DENTRY_SIZE / sizeof(__le32); + + if (F2FS_OPTION(sbi).inline_xattr_size < min_size || + F2FS_OPTION(sbi).inline_xattr_size > max_size) { f2fs_msg(sb, KERN_ERR, - "inline xattr size is out of range"); + "inline xattr size is out of range: %d ~ %d", + min_size, max_size); return -EINVAL; } } -- GitLab From 4ff98f21c14cde80af119e81c7bacd18ac34db34 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 4 Mar 2019 17:19:04 +0800 Subject: [PATCH 0193/1128] f2fs: fix to do sanity check with inode.i_inline_xattr_size As Paul Bandha reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202709 When I run the poc on the mounted f2fs img I get a buffer overflow in read_inline_xattr due to there being no sanity check on the value of i_inline_xattr_size. I created the img by just modifying the value of i_inline_xattr_size in the inode: i_name [test1.txt] i_ext: fofs:0 blkaddr:0 len:0 i_extra_isize [0x 18 : 24] i_inline_xattr_size [0x ffff : 65535] i_addr[ofs] [0x 0 : 0] mkdir /mnt/f2fs mount ./f2fs1.img /mnt/f2fs gcc poc.c -o poc ./poc int main() { int y = syscall(SYS_listxattr, "/mnt/f2fs/test1.txt", NULL, 0); printf("ret %d", y); printf("errno: %d\n", errno); } BUG: KASAN: slab-out-of-bounds in read_inline_xattr+0x18f/0x260 Read of size 262140 at addr ffff88011035efd8 by task f2fs1poc/3263 CPU: 0 PID: 3263 Comm: f2fs1poc Not tainted 4.18.0-custom #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.1-0-g0551a4be2c-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0x71/0xab print_address_description+0x83/0x250 kasan_report+0x213/0x350 memcpy+0x1f/0x50 read_inline_xattr+0x18f/0x260 read_all_xattrs+0xba/0x190 f2fs_listxattr+0x9d/0x3f0 listxattr+0xb2/0xd0 path_listxattr+0x93/0xe0 do_syscall_64+0x9d/0x220 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Let's add sanity check for inode.i_inline_xattr_size during f2fs_iget() to avoid this issue. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/inode.c | 15 +++++++++++++++ fs/f2fs/super.c | 5 +---- fs/f2fs/xattr.h | 6 ++++++ 3 files changed, 22 insertions(+), 4 deletions(-) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index bec52961630b..d44e6de70cb3 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -14,6 +14,7 @@ #include "f2fs.h" #include "node.h" #include "segment.h" +#include "xattr.h" #include @@ -248,6 +249,20 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } + if (f2fs_has_extra_attr(inode) && + f2fs_sb_has_flexible_inline_xattr(sbi) && + f2fs_has_inline_xattr(inode) && + (!fi->i_inline_xattr_size || + fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: inode (ino=%lx) has corrupted " + "i_inline_xattr_size: %d, max: %zu", + __func__, inode->i_ino, fi->i_inline_xattr_size, + MAX_INLINE_XATTR_SIZE); + return false; + } + if (F2FS_I(inode)->extent_tree) { struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index bb75398d9f99..27d36b08f67b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -838,10 +838,7 @@ static int parse_options(struct super_block *sb, char *options) } min_size = sizeof(struct f2fs_xattr_header) / sizeof(__le32); - max_size = DEF_ADDRS_PER_INODE - - F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - - DEF_INLINE_RESERVED_SIZE - - MIN_INLINE_DENTRY_SIZE / sizeof(__le32); + max_size = MAX_INLINE_XATTR_SIZE; if (F2FS_OPTION(sbi).inline_xattr_size < min_size || F2FS_OPTION(sbi).inline_xattr_size > max_size) { diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 67db134da0f5..9172ee082ca8 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -78,6 +78,12 @@ struct f2fs_xattr_entry { sizeof(struct f2fs_xattr_header) - \ sizeof(struct f2fs_xattr_entry)) +#define MAX_INLINE_XATTR_SIZE \ + (DEF_ADDRS_PER_INODE - \ + F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - \ + DEF_INLINE_RESERVED_SIZE - \ + MIN_INLINE_DENTRY_SIZE / sizeof(__le32)) + /* * On-disk structure of f2fs_xattr * We use inline xattrs space + 1 block for xattr. -- GitLab From a23295a806b9a074faab902adf011801dfed1a27 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 5 Mar 2019 19:32:26 +0800 Subject: [PATCH 0194/1128] f2fs: fix to adapt small inline xattr space in __find_inline_xattr() With below testcase, we will fail to find existed xattr entry: 1. mkfs.f2fs -O extra_attr -O flexible_inline_xattr /dev/zram0 2. mount -t f2fs -o inline_xattr_size=1 /dev/zram0 /mnt/f2fs/ 3. touch /mnt/f2fs/file 4. setfattr -n "user.name" -v 0 /mnt/f2fs/file 5. getfattr -n "user.name" /mnt/f2fs/file /mnt/f2fs/file: user.name: No such attribute The reason is for inode which has very small inline xattr size, __find_inline_xattr() will fail to traverse any entry due to first entry may not be loaded from xattr node yet, later, we may skip to check entire xattr datas in __find_xattr(), result in such wrong condition. This patch adds condition to check such case to avoid this issue. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/xattr.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index ca47224d78ab..848a785abe25 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -224,11 +224,11 @@ static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode, { struct f2fs_xattr_entry *entry; unsigned int inline_size = inline_xattr_size(inode); + void *max_addr = base_addr + inline_size; list_for_each_xattr(entry, base_addr) { - if ((void *)entry + sizeof(__u32) > base_addr + inline_size || - (void *)XATTR_NEXT_ENTRY(entry) + sizeof(__u32) > - base_addr + inline_size) { + if ((void *)entry + sizeof(__u32) > max_addr || + (void *)XATTR_NEXT_ENTRY(entry) > max_addr) { *last_addr = entry; return NULL; } @@ -239,6 +239,13 @@ static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode, if (!memcmp(entry->e_name, name, len)) break; } + + /* inline xattr header or entry across max inline xattr size */ + if (IS_XATTR_LAST_ENTRY(entry) && + (void *)entry + sizeof(__u32) > max_addr) { + *last_addr = entry; + return NULL; + } return entry; } -- GitLab From 5a98485eb30cb971d07ac38d09c85c531d6f40b8 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 12 Mar 2019 15:44:27 +0800 Subject: [PATCH 0195/1128] f2fs: fix to avoid deadlock in f2fs_read_inline_dir() As Jiqun Li reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202883 sometimes, dead lock when make system call SYS_getdents64 with fsync() is called by another process. monkey running on android9.0 1. task 9785 held sbi->cp_rwsem and waiting lock_page() 2. task 10349 held mm_sem and waiting sbi->cp_rwsem 3. task 9709 held lock_page() and waiting mm_sem so this is a dead lock scenario. task stack is show by crash tools as following crash_arm64> bt ffffffc03c354080 PID: 9785 TASK: ffffffc03c354080 CPU: 1 COMMAND: "RxIoScheduler-3" >> #7 [ffffffc01b50fac0] __lock_page at ffffff80081b11e8 crash-arm64> bt 10349 PID: 10349 TASK: ffffffc018b83080 CPU: 1 COMMAND: "BUGLY_ASYNC_UPL" >> #3 [ffffffc01f8cfa40] rwsem_down_read_failed at ffffff8008a93afc PC: 00000033 LR: 00000000 SP: 00000000 PSTATE: ffffffffffffffff crash-arm64> bt 9709 PID: 9709 TASK: ffffffc03e7f3080 CPU: 1 COMMAND: "IntentService[A" >> #3 [ffffffc001e67850] rwsem_down_read_failed at ffffff8008a93afc >> #8 [ffffffc001e67b80] el1_ia at ffffff8008084fc4 PC: ffffff8008274114 [compat_filldir64+120] LR: ffffff80083584d4 [f2fs_fill_dentries+448] SP: ffffffc001e67b80 PSTATE: 80400145 X29: ffffffc001e67b80 X28: 0000000000000000 X27: 000000000000001a X26: 00000000000093d7 X25: ffffffc070d52480 X24: 0000000000000008 X23: 0000000000000028 X22: 00000000d43dfd60 X21: ffffffc001e67e90 X20: 0000000000000011 X19: ffffff80093a4000 X18: 0000000000000000 X17: 0000000000000000 X16: 0000000000000000 X15: 0000000000000000 X14: ffffffffffffffff X13: 0000000000000008 X12: 0101010101010101 X11: 7f7f7f7f7f7f7f7f X10: 6a6a6a6a6a6a6a6a X9: 7f7f7f7f7f7f7f7f X8: 0000000080808000 X7: ffffff800827409c X6: 0000000080808000 X5: 0000000000000008 X4: 00000000000093d7 X3: 000000000000001a X2: 0000000000000011 X1: ffffffc070d52480 X0: 0000000000800238 >> #9 [ffffffc001e67be0] f2fs_fill_dentries at ffffff80083584d0 PC: 0000003c LR: 00000000 SP: 00000000 PSTATE: 000000d9 X12: f48a02ff X11: d4678960 X10: d43dfc00 X9: d4678ae4 X8: 00000058 X7: d4678994 X6: d43de800 X5: 000000d9 X4: d43dfc0c X3: d43dfc10 X2: d46799c8 X1: 00000000 X0: 00001068 Below potential deadlock will happen between three threads: Thread A Thread B Thread C - f2fs_do_sync_file - f2fs_write_checkpoint - down_write(&sbi->node_change) -- 1) - do_page_fault - down_write(&mm->mmap_sem) -- 2) - do_wp_page - f2fs_vm_page_mkwrite - getdents64 - f2fs_read_inline_dir - lock_page -- 3) - f2fs_sync_node_pages - lock_page -- 3) - __do_map_lock - down_read(&sbi->node_change) -- 1) - f2fs_fill_dentries - dir_emit - compat_filldir64 - do_page_fault - down_read(&mm->mmap_sem) -- 2) Since f2fs_readdir is protected by inode.i_rwsem, there should not be any updates in inode page, we're safe to lookup dents in inode page without its lock held, so taking off the lock to improve concurrency of readdir and avoid potential deadlock. Reported-by: Jiqun Li Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/inline.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 3ebae34a8b96..c16bb32f42f0 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -659,6 +659,12 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, if (IS_ERR(ipage)) return PTR_ERR(ipage); + /* + * f2fs_readdir was protected by inode.i_rwsem, it is safe to access + * ipage without page's lock held. + */ + unlock_page(ipage); + inline_dentry = inline_data_addr(inode, ipage); make_dentry_ptr_inline(inode, &d, inline_dentry); @@ -667,7 +673,7 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, if (!err) ctx->pos = d.max; - f2fs_put_page(ipage, 1); + f2fs_put_page(ipage, 0); return err < 0 ? err : 0; } -- GitLab From 4592dca5048f0d6d684d0fa52c8b8c308c46c21f Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 13 Mar 2019 16:15:08 -0700 Subject: [PATCH 0196/1128] f2fs: set pin_file under CAP_SYS_ADMIN Android uses pin_file for uncrypt during OTA, and that should be managed by CAP_SYS_ADMIN only. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 1b9106523f27..69db0d1c34a0 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2873,8 +2873,8 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) __u32 pin; int ret = 0; - if (!inode_owner_or_capable(inode)) - return -EACCES; + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; if (get_user(pin, (__u32 __user *)arg)) return -EFAULT; -- GitLab From ea583d1606216977a8285c1a49f76d08be4e6b3b Mon Sep 17 00:00:00 2001 From: Connor O'Brien Date: Fri, 1 Mar 2019 15:40:30 -0800 Subject: [PATCH 0197/1128] ANDROID: cpufreq: times: don't copy invalid freqs from freq table Invalid frequency checks are a bottleneck in reading /proc/uid_time_in_state, but there's no reason to include invalid frequencies in our local copies of frequency tables. Revise cpufreq_times_create_policy() to only copy valid frequencies, and eliminate all the checks this change makes unnecessary. Bug: 111216804 Test: cat /proc/uid_time_in_state & confirm values & format are sane Test: /proc/uid_time_in_state read times reduced by ~40% Change-Id: I506420a6ac5fe8a6c87d01b16ad267b192d43f1d Signed-off-by: Connor O'Brien --- drivers/cpufreq/cpufreq_times.c | 55 ++++++++++++--------------------- 1 file changed, 19 insertions(+), 36 deletions(-) diff --git a/drivers/cpufreq/cpufreq_times.c b/drivers/cpufreq/cpufreq_times.c index 2883d675b1eb..5b5248a7c87c 100644 --- a/drivers/cpufreq/cpufreq_times.c +++ b/drivers/cpufreq/cpufreq_times.c @@ -137,27 +137,10 @@ static struct uid_entry *find_or_register_uid_locked(uid_t uid) return uid_entry; } -static bool freq_index_invalid(unsigned int index) -{ - unsigned int cpu; - struct cpu_freqs *freqs; - - for_each_possible_cpu(cpu) { - freqs = all_freqs[cpu]; - if (!freqs || index < freqs->offset || - freqs->offset + freqs->max_state <= index) - continue; - return freqs->freq_table[index - freqs->offset] == - CPUFREQ_ENTRY_INVALID; - } - return true; -} - static int single_uid_time_in_state_show(struct seq_file *m, void *ptr) { struct uid_entry *uid_entry; unsigned int i; - u64 time; uid_t uid = from_kuid_munged(current_user_ns(), *(kuid_t *)m->private); if (uid == overflowuid) @@ -172,9 +155,7 @@ static int single_uid_time_in_state_show(struct seq_file *m, void *ptr) } for (i = 0; i < uid_entry->max_state; ++i) { - if (freq_index_invalid(i)) - continue; - time = nsec_to_clock_t(uid_entry->time_in_state[i]); + u64 time = nsec_to_clock_t(uid_entry->time_in_state[i]); seq_write(m, &time, sizeof(time)); } @@ -219,9 +200,6 @@ static int uid_time_in_state_seq_show(struct seq_file *m, void *v) continue; last_freqs = freqs; for (i = 0; i < freqs->max_state; i++) { - if (freqs->freq_table[i] == - CPUFREQ_ENTRY_INVALID) - continue; seq_put_decimal_ull(m, " ", freqs->freq_table[i]); } @@ -237,10 +215,7 @@ static int uid_time_in_state_seq_show(struct seq_file *m, void *v) seq_putc(m, ':'); } for (i = 0; i < uid_entry->max_state; ++i) { - u64 time; - if (freq_index_invalid(i)) - continue; - time = nsec_to_clock_t(uid_entry->time_in_state[i]); + u64 time = nsec_to_clock_t(uid_entry->time_in_state[i]); seq_put_decimal_ull(m, " ", time); } if (uid_entry->max_state) @@ -407,8 +382,6 @@ int proc_time_in_state_show(struct seq_file *m, struct pid_namespace *ns, seq_printf(m, "cpu%u\n", cpu); for (i = 0; i < freqs->max_state; i++) { - if (freqs->freq_table[i] == CPUFREQ_ENTRY_INVALID) - continue; cputime = 0; if (freqs->offset + i < p->max_state && p->time_in_state) @@ -488,9 +461,19 @@ void cpufreq_acct_update_power(struct task_struct *p, u64 cputime) rcu_read_unlock(); } +static int cpufreq_times_get_index(struct cpu_freqs *freqs, unsigned int freq) +{ + int index; + for (index = 0; index < freqs->max_state; ++index) { + if (freqs->freq_table[index] == freq) + return index; + } + return -1; +} + void cpufreq_times_create_policy(struct cpufreq_policy *policy) { - int cpu, index; + int cpu, index = 0; unsigned int count = 0; struct cpufreq_frequency_table *pos, *table; struct cpu_freqs *freqs; @@ -503,7 +486,7 @@ void cpufreq_times_create_policy(struct cpufreq_policy *policy) if (!table) return; - cpufreq_for_each_entry(pos, table) + cpufreq_for_each_valid_entry(pos, table) count++; tmp = kzalloc(sizeof(*freqs) + sizeof(freqs->freq_table[0]) * count, @@ -514,13 +497,13 @@ void cpufreq_times_create_policy(struct cpufreq_policy *policy) freqs = tmp; freqs->max_state = count; - index = cpufreq_frequency_table_get_index(policy, policy->cur); + cpufreq_for_each_valid_entry(pos, table) + freqs->freq_table[index++] = pos->frequency; + + index = cpufreq_times_get_index(freqs, policy->cur); if (index >= 0) WRITE_ONCE(freqs->last_index, index); - cpufreq_for_each_entry(pos, table) - freqs->freq_table[pos - table] = pos->frequency; - freqs->offset = next_offset; WRITE_ONCE(next_offset, freqs->offset + count); for_each_cpu(cpu, policy->related_cpus) @@ -564,7 +547,7 @@ void cpufreq_times_record_transition(struct cpufreq_policy *policy, if (!freqs) return; - index = cpufreq_frequency_table_get_index(policy, new_freq); + index = cpufreq_times_get_index(freqs, new_freq); if (index >= 0) WRITE_ONCE(freqs->last_index, index); } -- GitLab From 785eb09ceb61a9c7d2a6c72e033bef04a89f1778 Mon Sep 17 00:00:00 2001 From: Erik Schmauss Date: Fri, 10 Aug 2018 14:43:02 -0700 Subject: [PATCH 0198/1128] ACPICA: Reference Counts: increase max to 0x4000 for large servers commit 8b23570ab001c1982c8a068cde468ff067255314 upstream. Increase the reference count limit to 0x4000 as the current one is not sufficient for some large server systems. Reviewed-by: Dimitri Sivanich Tested-by: Russ Anderson Reported-by: Mike Travis Signed-off-by: Mike Travis Signed-off-by: Erik Schmauss [ rjw: Changelog ] Signed-off-by: Rafael J. Wysocki Cc: Frank van der Linden Signed-off-by: Greg Kroah-Hartman --- include/acpi/acconfig.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index 6db3b4668b1a..707ce8aca824 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -123,7 +123,7 @@ /* Maximum object reference count (detects object deletion issues) */ -#define ACPI_MAX_REFERENCE_COUNT 0x1000 +#define ACPI_MAX_REFERENCE_COUNT 0x4000 /* Default page size for use in mapping memory for operation regions */ -- GitLab From 1ce1eb5fb1daa64eba1dc1d58b13fb3b327be8ed Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Wed, 6 Dec 2017 01:50:40 +0000 Subject: [PATCH 0199/1128] perf tools: Fix compile error with libunwind x86 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 44df1afdb174fd6038e419f80efd914c0b5f2f85 upstream. Fix a compile error: ... CC util/libunwind/x86_32.o In file included from util/libunwind/x86_32.c:33:0: util/libunwind/../../arch/x86/util/unwind-libunwind.c: In function 'libunwind__x86_reg_id': util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: error: 'EINVAL' undeclared (first use in this function) return -EINVAL; ^ util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: note: each undeclared identifier is reported only once for each function it appears in mv: cannot stat 'util/libunwind/.x86_32.o.tmp': No such file or directory make[4]: *** [util/libunwind/x86_32.o] Error 1 make[3]: *** [util] Error 2 make[2]: *** [libperf-in.o] Error 2 make[1]: *** [sub-make] Error 2 make: *** [all] Error 2 It happens when libunwind-x86 feature is detected. Signed-off-by: Wang Nan Link: http://lkml.kernel.org/r/20171206015040.114574-1-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo Cc: Daniel Díaz Signed-off-by: Greg Kroah-Hartman --- tools/perf/arch/x86/util/unwind-libunwind.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c index 9c917f80c906..05920e3edf7a 100644 --- a/tools/perf/arch/x86/util/unwind-libunwind.c +++ b/tools/perf/arch/x86/util/unwind-libunwind.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 -#ifndef REMOTE_UNWIND_LIBUNWIND #include +#ifndef REMOTE_UNWIND_LIBUNWIND #include #include "perf_regs.h" #include "../../util/unwind.h" -- GitLab From 136e109797f3e9e61076a401eb1353362be592b4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 10 Mar 2019 10:39:37 -0700 Subject: [PATCH 0200/1128] gro_cells: make sure device is up in gro_cells_receive() [ Upstream commit 2a5ff07a0eb945f291e361aa6f6becca8340ba46 ] We keep receiving syzbot reports [1] that show that tunnels do not play the rcu/IFF_UP rules properly. At device dismantle phase, gro_cells_destroy() will be called only after a full rcu grace period is observed after IFF_UP has been cleared. This means that IFF_UP needs to be tested before queueing packets into netif_rx() or gro_cells. This patch implements the test in gro_cells_receive() because too many callers do not seem to bother enough. [1] BUG: unable to handle kernel paging request at fffff4ca0b9ffffe PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 21 Comm: kworker/u4:1 Not tainted 5.0.0+ #97 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: netns cleanup_net RIP: 0010:__skb_unlink include/linux/skbuff.h:1929 [inline] RIP: 0010:__skb_dequeue include/linux/skbuff.h:1945 [inline] RIP: 0010:__skb_queue_purge include/linux/skbuff.h:2656 [inline] RIP: 0010:gro_cells_destroy net/core/gro_cells.c:89 [inline] RIP: 0010:gro_cells_destroy+0x19d/0x360 net/core/gro_cells.c:78 Code: 03 42 80 3c 20 00 0f 85 53 01 00 00 48 8d 7a 08 49 8b 47 08 49 c7 07 00 00 00 00 48 89 f9 49 c7 47 08 00 00 00 00 48 c1 e9 03 <42> 80 3c 21 00 0f 85 10 01 00 00 48 89 c1 48 89 42 08 48 c1 e9 03 RSP: 0018:ffff8880aa3f79a8 EFLAGS: 00010a02 RAX: 00ffffffffffffe8 RBX: ffffe8ffffc64b70 RCX: 1ffff8ca0b9ffffe RDX: ffffc6505cffffe8 RSI: ffffffff858410ca RDI: ffffc6505cfffff0 RBP: ffff8880aa3f7a08 R08: ffff8880aa3e8580 R09: fffffbfff1263645 R10: fffffbfff1263644 R11: ffffffff8931b223 R12: dffffc0000000000 R13: 0000000000000000 R14: ffffe8ffffc64b80 R15: ffffe8ffffc64b75 kobject: 'loop2' (000000004bd7d84a): kobject_uevent_env FS: 0000000000000000(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffff4ca0b9ffffe CR3: 0000000094941000 CR4: 00000000001406f0 Call Trace: kobject: 'loop2' (000000004bd7d84a): fill_kobj_path: path = '/devices/virtual/block/loop2' ip_tunnel_dev_free+0x19/0x60 net/ipv4/ip_tunnel.c:1010 netdev_run_todo+0x51c/0x7d0 net/core/dev.c:8970 rtnl_unlock+0xe/0x10 net/core/rtnetlink.c:116 ip_tunnel_delete_nets+0x423/0x5f0 net/ipv4/ip_tunnel.c:1124 vti_exit_batch_net+0x23/0x30 net/ipv4/ip_vti.c:495 ops_exit_list.isra.0+0x105/0x160 net/core/net_namespace.c:156 cleanup_net+0x3fb/0x960 net/core/net_namespace.c:551 process_one_work+0x98e/0x1790 kernel/workqueue.c:2173 worker_thread+0x98/0xe40 kernel/workqueue.c:2319 kthread+0x357/0x430 kernel/kthread.c:246 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352 Modules linked in: CR2: fffff4ca0b9ffffe [ end trace 513fc9c1338d1cb3 ] RIP: 0010:__skb_unlink include/linux/skbuff.h:1929 [inline] RIP: 0010:__skb_dequeue include/linux/skbuff.h:1945 [inline] RIP: 0010:__skb_queue_purge include/linux/skbuff.h:2656 [inline] RIP: 0010:gro_cells_destroy net/core/gro_cells.c:89 [inline] RIP: 0010:gro_cells_destroy+0x19d/0x360 net/core/gro_cells.c:78 Code: 03 42 80 3c 20 00 0f 85 53 01 00 00 48 8d 7a 08 49 8b 47 08 49 c7 07 00 00 00 00 48 89 f9 49 c7 47 08 00 00 00 00 48 c1 e9 03 <42> 80 3c 21 00 0f 85 10 01 00 00 48 89 c1 48 89 42 08 48 c1 e9 03 RSP: 0018:ffff8880aa3f79a8 EFLAGS: 00010a02 RAX: 00ffffffffffffe8 RBX: ffffe8ffffc64b70 RCX: 1ffff8ca0b9ffffe RDX: ffffc6505cffffe8 RSI: ffffffff858410ca RDI: ffffc6505cfffff0 RBP: ffff8880aa3f7a08 R08: ffff8880aa3e8580 R09: fffffbfff1263645 R10: fffffbfff1263644 R11: ffffffff8931b223 R12: dffffc0000000000 kobject: 'loop3' (00000000e4ee57a6): kobject_uevent_env R13: 0000000000000000 R14: ffffe8ffffc64b80 R15: ffffe8ffffc64b75 FS: 0000000000000000(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffff4ca0b9ffffe CR3: 0000000094941000 CR4: 00000000001406f0 Fixes: c9e6bc644e55 ("net: add gro_cells infrastructure") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/gro_cells.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index acf45ddbe924..e095fb871d91 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -13,22 +13,36 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct gro_cell *cell; + int res; - if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) - return netif_rx(skb); + rcu_read_lock(); + if (unlikely(!(dev->flags & IFF_UP))) + goto drop; + + if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) { + res = netif_rx(skb); + goto unlock; + } cell = this_cpu_ptr(gcells->cells); if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) { +drop: atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); - return NET_RX_DROP; + res = NET_RX_DROP; + goto unlock; } __skb_queue_tail(&cell->napi_skbs, skb); if (skb_queue_len(&cell->napi_skbs) == 1) napi_schedule(&cell->napi); - return NET_RX_SUCCESS; + + res = NET_RX_SUCCESS; + +unlock: + rcu_read_unlock(); + return res; } EXPORT_SYMBOL(gro_cells_receive); -- GitLab From c8c6b846249b8cfe825d86e71df9cbbea0d9c01c Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 6 Mar 2019 10:42:53 +0100 Subject: [PATCH 0201/1128] ipv4/route: fail early when inet dev is missing [ Upstream commit 22c74764aa2943ecdf9f07c900d8a9c8ba6c9265 ] If a non local multicast packet reaches ip_route_input_rcu() while the ingress device IPv4 private data (in_dev) is NULL, we end up doing a NULL pointer dereference in IN_DEV_MFORWARD(). Since the later call to ip_route_input_mc() is going to fail if !in_dev, we can fail early in such scenario and avoid the dangerous code path. v1 -> v2: - clarified the commit message, no code changes Reported-by: Tianhao Zhao Fixes: e58e41596811 ("net: Enable support for VRF with ipv4 multicast") Signed-off-by: Paolo Abeni Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/route.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index cb30f4e4e553..0a35d294abec 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2123,12 +2123,13 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, int our = 0; int err = -EINVAL; - if (in_dev) - our = ip_check_mc_rcu(in_dev, daddr, saddr, - ip_hdr(skb)->protocol); + if (!in_dev) + return err; + our = ip_check_mc_rcu(in_dev, daddr, saddr, + ip_hdr(skb)->protocol); /* check l3 master if no match yet */ - if ((!in_dev || !our) && netif_is_l3_slave(dev)) { + if (!our && netif_is_l3_slave(dev)) { struct in_device *l3_in_dev; l3_in_dev = __in_dev_get_rcu(skb->dev); -- GitLab From af6822a7915acf7eacd84cabf4a1c9013345aed0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Mar 2019 06:50:11 -0700 Subject: [PATCH 0202/1128] l2tp: fix infoleak in l2tp_ip6_recvmsg() [ Upstream commit 163d1c3d6f17556ed3c340d3789ea93be95d6c28 ] Back in 2013 Hannes took care of most of such leaks in commit bceaa90240b6 ("inet: prevent leakage of uninitialized memory to user in recv syscalls") But the bug in l2tp_ip6_recvmsg() has not been fixed. syzbot report : BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 CPU: 1 PID: 10996 Comm: syz-executor362 Not tainted 5.0.0+ #11 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:600 kmsan_internal_check_memory+0x9f4/0xb10 mm/kmsan/kmsan.c:694 kmsan_copy_to_user+0xab/0xc0 mm/kmsan/kmsan_hooks.c:601 _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 copy_to_user include/linux/uaccess.h:174 [inline] move_addr_to_user+0x311/0x570 net/socket.c:227 ___sys_recvmsg+0xb65/0x1310 net/socket.c:2283 do_recvmmsg+0x646/0x10c0 net/socket.c:2390 __sys_recvmmsg net/socket.c:2469 [inline] __do_sys_recvmmsg net/socket.c:2492 [inline] __se_sys_recvmmsg+0x1d1/0x350 net/socket.c:2485 __x64_sys_recvmmsg+0x62/0x80 net/socket.c:2485 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x445819 Code: e8 6c b6 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b 12 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f64453eddb8 EFLAGS: 00000246 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 00000000006dac28 RCX: 0000000000445819 RDX: 0000000000000005 RSI: 0000000020002f80 RDI: 0000000000000003 RBP: 00000000006dac20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dac2c R13: 00007ffeba8f87af R14: 00007f64453ee9c0 R15: 20c49ba5e353f7cf Local variable description: ----addr@___sys_recvmsg Variable was created at: ___sys_recvmsg+0xf6/0x1310 net/socket.c:2244 do_recvmmsg+0x646/0x10c0 net/socket.c:2390 Bytes 0-31 of 32 are uninitialized Memory access of size 32 starts at ffff8880ae62fbb0 Data copied to user address 0000000020000000 Fixes: a32e0eec7042 ("l2tp: introduce L2TPv3 IP encapsulation support for IPv6") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/l2tp/l2tp_ip6.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 3c77507601c7..bec13226ce4f 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -684,9 +684,6 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*lsa); - if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); @@ -716,6 +713,7 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, lsa->l2tp_conn_id = 0; if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) lsa->l2tp_scope_id = inet6_iif(skb); + *addr_len = sizeof(*lsa); } if (np->rxopt.all) -- GitLab From 1aa1e0a3f6dde5c37bb5d6a9121847b95b255c1f Mon Sep 17 00:00:00 2001 From: Mao Wenan Date: Wed, 6 Mar 2019 22:45:01 +0800 Subject: [PATCH 0203/1128] net: hsr: fix memory leak in hsr_dev_finalize() [ Upstream commit 6caabe7f197d3466d238f70915d65301f1716626 ] If hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER) failed to add port, it directly returns res and forgets to free the node that allocated in hsr_create_self_node(), and forgets to delete the node->mac_list linked in hsr->self_node_db. BUG: memory leak unreferenced object 0xffff8881cfa0c780 (size 64): comm "syz-executor.0", pid 2077, jiffies 4294717969 (age 2415.377s) hex dump (first 32 bytes): e0 c7 a0 cf 81 88 ff ff 00 02 00 00 00 00 ad de ................ 00 e6 49 cd 81 88 ff ff c0 9b 87 d0 81 88 ff ff ..I............. backtrace: [<00000000e2ff5070>] hsr_dev_finalize+0x736/0x960 [hsr] [<000000003ed2e597>] hsr_newlink+0x2b2/0x3e0 [hsr] [<000000003fa8c6b6>] __rtnl_newlink+0xf1f/0x1600 net/core/rtnetlink.c:3182 [<000000001247a7ad>] rtnl_newlink+0x66/0x90 net/core/rtnetlink.c:3240 [<00000000e7d1b61d>] rtnetlink_rcv_msg+0x54e/0xb90 net/core/rtnetlink.c:5130 [<000000005556bd3a>] netlink_rcv_skb+0x129/0x340 net/netlink/af_netlink.c:2477 [<00000000741d5ee6>] netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] [<00000000741d5ee6>] netlink_unicast+0x49a/0x650 net/netlink/af_netlink.c:1336 [<000000009d56f9b7>] netlink_sendmsg+0x88b/0xdf0 net/netlink/af_netlink.c:1917 [<0000000046b35c59>] sock_sendmsg_nosec net/socket.c:621 [inline] [<0000000046b35c59>] sock_sendmsg+0xc3/0x100 net/socket.c:631 [<00000000d208adc9>] __sys_sendto+0x33e/0x560 net/socket.c:1786 [<00000000b582837a>] __do_sys_sendto net/socket.c:1798 [inline] [<00000000b582837a>] __se_sys_sendto net/socket.c:1794 [inline] [<00000000b582837a>] __x64_sys_sendto+0xdd/0x1b0 net/socket.c:1794 [<00000000c866801d>] do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 [<00000000fea382d9>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<00000000e01dacb3>] 0xffffffffffffffff Fixes: c5a759117210 ("net/hsr: Use list_head (and rcu) instead of array for slave devices.") Reported-by: Hulk Robot Signed-off-by: Mao Wenan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/hsr/hsr_device.c | 4 +++- net/hsr/hsr_framereg.c | 12 ++++++++++++ net/hsr/hsr_framereg.h | 1 + 3 files changed, 16 insertions(+), 1 deletion(-) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 172d8309f89e..0e0b2a09c453 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -487,7 +487,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER); if (res) - return res; + goto err_add_port; res = register_netdevice(hsr_dev); if (res) @@ -507,6 +507,8 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], fail: hsr_for_each_port(hsr, port) hsr_del_port(port); +err_add_port: + hsr_del_node(&hsr->self_node_db); return res; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 284a9b820df8..6705420b3111 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -124,6 +124,18 @@ int hsr_create_self_node(struct list_head *self_node_db, return 0; } +void hsr_del_node(struct list_head *self_node_db) +{ + struct hsr_node *node; + + rcu_read_lock(); + node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); + rcu_read_unlock(); + if (node) { + list_del_rcu(&node->mac_list); + kfree(node); + } +} /* Allocate an hsr_node and add it to node_db. 'addr' is the node's AddressA; * seq_out is used to initialize filtering of outgoing duplicate frames diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 4e04f0e868e9..43958a338095 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -16,6 +16,7 @@ struct hsr_node; +void hsr_del_node(struct list_head *self_node_db); struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], u16 seq_out); struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, -- GitLab From 60001460c89d2c92fe53e8b1865a1ddec7fb01eb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Mar 2019 09:36:33 -0800 Subject: [PATCH 0204/1128] net/hsr: fix possible crash in add_timer() [ Upstream commit 1e027960edfaa6a43f9ca31081729b716598112b ] syzbot found another add_timer() issue, this time in net/hsr [1] Let's use mod_timer() which is safe. [1] kernel BUG at kernel/time/timer.c:1136! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 15909 Comm: syz-executor.3 Not tainted 5.0.0+ #97 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 kobject: 'loop2' (00000000f5629718): kobject_uevent_env RIP: 0010:add_timer kernel/time/timer.c:1136 [inline] RIP: 0010:add_timer+0x654/0xbe0 kernel/time/timer.c:1134 Code: 0f 94 c5 31 ff 44 89 ee e8 09 61 0f 00 45 84 ed 0f 84 77 fd ff ff e8 bb 5f 0f 00 e8 07 10 a0 ff e9 68 fd ff ff e8 ac 5f 0f 00 <0f> 0b e8 a5 5f 0f 00 0f 0b e8 9e 5f 0f 00 4c 89 b5 58 ff ff ff e9 RSP: 0018:ffff8880656eeca0 EFLAGS: 00010246 kobject: 'loop2' (00000000f5629718): fill_kobj_path: path = '/devices/virtual/block/loop2' RAX: 0000000000040000 RBX: 1ffff1100caddd9a RCX: ffffc9000c436000 RDX: 0000000000040000 RSI: ffffffff816056c4 RDI: ffff88806a2f6cc8 RBP: ffff8880656eed58 R08: ffff888067f4a300 R09: ffff888067f4abc8 R10: 0000000000000000 R11: 0000000000000000 R12: ffff88806a2f6cc0 R13: dffffc0000000000 R14: 0000000000000001 R15: ffff8880656eed30 FS: 00007fc2019bf700(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000738000 CR3: 0000000067e8e000 CR4: 00000000001406f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: hsr_check_announce net/hsr/hsr_device.c:99 [inline] hsr_check_carrier_and_operstate+0x567/0x6f0 net/hsr/hsr_device.c:120 hsr_netdev_notify+0x297/0xa00 net/hsr/hsr_main.c:51 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93 __raw_notifier_call_chain kernel/notifier.c:394 [inline] raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1739 call_netdevice_notifiers_extack net/core/dev.c:1751 [inline] call_netdevice_notifiers net/core/dev.c:1765 [inline] dev_open net/core/dev.c:1436 [inline] dev_open+0x143/0x160 net/core/dev.c:1424 team_port_add drivers/net/team/team.c:1203 [inline] team_add_slave+0xa07/0x15d0 drivers/net/team/team.c:1933 do_set_master net/core/rtnetlink.c:2358 [inline] do_set_master+0x1d4/0x230 net/core/rtnetlink.c:2332 do_setlink+0x966/0x3510 net/core/rtnetlink.c:2493 rtnl_setlink+0x271/0x3b0 net/core/rtnetlink.c:2747 rtnetlink_rcv_msg+0x465/0xb00 net/core/rtnetlink.c:5192 netlink_rcv_skb+0x17a/0x460 net/netlink/af_netlink.c:2485 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5210 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0x536/0x720 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x8ae/0xd70 net/netlink/af_netlink.c:1925 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg+0xdd/0x130 net/socket.c:632 sock_write_iter+0x27c/0x3e0 net/socket.c:923 call_write_iter include/linux/fs.h:1869 [inline] do_iter_readv_writev+0x5e0/0x8e0 fs/read_write.c:680 do_iter_write fs/read_write.c:956 [inline] do_iter_write+0x184/0x610 fs/read_write.c:937 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1001 do_writev+0xf6/0x290 fs/read_write.c:1036 __do_sys_writev fs/read_write.c:1109 [inline] __se_sys_writev fs/read_write.c:1106 [inline] __x64_sys_writev+0x75/0xb0 fs/read_write.c:1106 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457f29 Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fc2019bec78 EFLAGS: 00000246 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457f29 RDX: 0000000000000001 RSI: 00000000200000c0 RDI: 0000000000000003 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fc2019bf6d4 R13: 00000000004c4a60 R14: 00000000004dd218 R15: 00000000ffffffff Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)") Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Arvid Brodin Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/hsr/hsr_device.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 0e0b2a09c453..cfe20f15f618 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -94,9 +94,8 @@ static void hsr_check_announce(struct net_device *hsr_dev, && (old_operstate != IF_OPER_UP)) { /* Went up */ hsr->announce_count = 0; - hsr->announce_timer.expires = jiffies + - msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); - add_timer(&hsr->announce_timer); + mod_timer(&hsr->announce_timer, + jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if ((hsr_dev->operstate != IF_OPER_UP) && (old_operstate == IF_OPER_UP)) @@ -332,6 +331,7 @@ static void hsr_announce(unsigned long data) { struct hsr_priv *hsr; struct hsr_port *master; + unsigned long interval; hsr = (struct hsr_priv *) data; @@ -343,18 +343,16 @@ static void hsr_announce(unsigned long data) hsr->protVersion); hsr->announce_count++; - hsr->announce_timer.expires = jiffies + - msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); + interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); } else { send_hsr_supervision_frame(master, HSR_TLV_LIFE_CHECK, hsr->protVersion); - hsr->announce_timer.expires = jiffies + - msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); + interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); } if (is_admin_up(master->dev)) - add_timer(&hsr->announce_timer); + mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } -- GitLab From a68ac22fc4366b37d9271a5300da59bfeb448cd3 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 11 Mar 2019 16:29:32 +0800 Subject: [PATCH 0205/1128] net: sit: fix UBSAN Undefined behaviour in check_6rd [ Upstream commit a843dc4ebaecd15fca1f4d35a97210f72ea1473b ] In func check_6rd,tunnel->ip6rd.relay_prefixlen may equal to 32,so UBSAN complain about it. UBSAN: Undefined behaviour in net/ipv6/sit.c:781:47 shift exponent 32 is too large for 32-bit type 'unsigned int' CPU: 6 PID: 20036 Comm: syz-executor.0 Not tainted 4.19.27 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xca/0x13e lib/dump_stack.c:113 ubsan_epilogue+0xe/0x81 lib/ubsan.c:159 __ubsan_handle_shift_out_of_bounds+0x293/0x2e8 lib/ubsan.c:425 check_6rd.constprop.9+0x433/0x4e0 net/ipv6/sit.c:781 try_6rd net/ipv6/sit.c:806 [inline] ipip6_tunnel_xmit net/ipv6/sit.c:866 [inline] sit_tunnel_xmit+0x141c/0x2720 net/ipv6/sit.c:1033 __netdev_start_xmit include/linux/netdevice.h:4300 [inline] netdev_start_xmit include/linux/netdevice.h:4309 [inline] xmit_one net/core/dev.c:3243 [inline] dev_hard_start_xmit+0x17c/0x780 net/core/dev.c:3259 __dev_queue_xmit+0x1656/0x2500 net/core/dev.c:3829 neigh_output include/net/neighbour.h:501 [inline] ip6_finish_output2+0xa36/0x2290 net/ipv6/ip6_output.c:120 ip6_finish_output+0x3e7/0xa20 net/ipv6/ip6_output.c:154 NF_HOOK_COND include/linux/netfilter.h:278 [inline] ip6_output+0x1e2/0x720 net/ipv6/ip6_output.c:171 dst_output include/net/dst.h:444 [inline] ip6_local_out+0x99/0x170 net/ipv6/output_core.c:176 ip6_send_skb+0x9d/0x2f0 net/ipv6/ip6_output.c:1697 ip6_push_pending_frames+0xc0/0x100 net/ipv6/ip6_output.c:1717 rawv6_push_pending_frames net/ipv6/raw.c:616 [inline] rawv6_sendmsg+0x2435/0x3530 net/ipv6/raw.c:946 inet_sendmsg+0xf8/0x5c0 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg+0xc8/0x110 net/socket.c:631 ___sys_sendmsg+0x6cf/0x890 net/socket.c:2114 __sys_sendmsg+0xf0/0x1b0 net/socket.c:2152 do_syscall_64+0xc8/0x580 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Signed-off-by: linmiaohe Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/sit.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index c5b60190b1db..e23190725244 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -767,8 +767,9 @@ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, pbw0 = tunnel->ip6rd.prefixlen >> 5; pbi0 = tunnel->ip6rd.prefixlen & 0x1f; - d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> - tunnel->ip6rd.relay_prefixlen; + d = tunnel->ip6rd.relay_prefixlen < 32 ? + (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> + tunnel->ip6rd.relay_prefixlen : 0; pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; if (pbi1 > 0) -- GitLab From ffd4228bdf861b3a206738854f171eef85093c54 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 10 Mar 2019 09:07:14 -0700 Subject: [PATCH 0206/1128] net/x25: fix use-after-free in x25_device_event() [ Upstream commit 95d6ebd53c79522bf9502dbc7e89e0d63f94dae4 ] In case of failure x25_connect() does a x25_neigh_put(x25->neighbour) but forgets to clear x25->neighbour pointer, thus triggering use-after-free. Since the socket is visible in x25_list, we need to hold x25_list_lock to protect the operation. syzbot report : BUG: KASAN: use-after-free in x25_kill_by_device net/x25/af_x25.c:217 [inline] BUG: KASAN: use-after-free in x25_device_event+0x296/0x2b0 net/x25/af_x25.c:252 Read of size 8 at addr ffff8880a030edd0 by task syz-executor003/7854 CPU: 0 PID: 7854 Comm: syz-executor003 Not tainted 5.0.0+ #97 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135 x25_kill_by_device net/x25/af_x25.c:217 [inline] x25_device_event+0x296/0x2b0 net/x25/af_x25.c:252 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93 __raw_notifier_call_chain kernel/notifier.c:394 [inline] raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1739 call_netdevice_notifiers_extack net/core/dev.c:1751 [inline] call_netdevice_notifiers net/core/dev.c:1765 [inline] __dev_notify_flags+0x1e9/0x2c0 net/core/dev.c:7607 dev_change_flags+0x10d/0x170 net/core/dev.c:7643 dev_ifsioc+0x2b0/0x940 net/core/dev_ioctl.c:237 dev_ioctl+0x1b8/0xc70 net/core/dev_ioctl.c:488 sock_do_ioctl+0x1bd/0x300 net/socket.c:995 sock_ioctl+0x32b/0x610 net/socket.c:1096 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:509 [inline] do_vfs_ioctl+0xd6e/0x1390 fs/ioctl.c:696 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713 __do_sys_ioctl fs/ioctl.c:720 [inline] __se_sys_ioctl fs/ioctl.c:718 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4467c9 Code: e8 0c e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 5b 07 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fdbea222d98 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00000000006dbc58 RCX: 00000000004467c9 RDX: 0000000020000340 RSI: 0000000000008914 RDI: 0000000000000003 RBP: 00000000006dbc50 R08: 00007fdbea223700 R09: 0000000000000000 R10: 00007fdbea223700 R11: 0000000000000246 R12: 00000000006dbc5c R13: 6000030030626669 R14: 0000000000000000 R15: 0000000030626669 Allocated by task 7843: save_stack+0x45/0xd0 mm/kasan/common.c:73 set_track mm/kasan/common.c:85 [inline] __kasan_kmalloc mm/kasan/common.c:495 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:468 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:509 kmem_cache_alloc_trace+0x151/0x760 mm/slab.c:3615 kmalloc include/linux/slab.h:545 [inline] x25_link_device_up+0x46/0x3f0 net/x25/x25_link.c:249 x25_device_event+0x116/0x2b0 net/x25/af_x25.c:242 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93 __raw_notifier_call_chain kernel/notifier.c:394 [inline] raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1739 call_netdevice_notifiers_extack net/core/dev.c:1751 [inline] call_netdevice_notifiers net/core/dev.c:1765 [inline] __dev_notify_flags+0x121/0x2c0 net/core/dev.c:7605 dev_change_flags+0x10d/0x170 net/core/dev.c:7643 dev_ifsioc+0x2b0/0x940 net/core/dev_ioctl.c:237 dev_ioctl+0x1b8/0xc70 net/core/dev_ioctl.c:488 sock_do_ioctl+0x1bd/0x300 net/socket.c:995 sock_ioctl+0x32b/0x610 net/socket.c:1096 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:509 [inline] do_vfs_ioctl+0xd6e/0x1390 fs/ioctl.c:696 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713 __do_sys_ioctl fs/ioctl.c:720 [inline] __se_sys_ioctl fs/ioctl.c:718 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 7865: save_stack+0x45/0xd0 mm/kasan/common.c:73 set_track mm/kasan/common.c:85 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:457 kasan_slab_free+0xe/0x10 mm/kasan/common.c:465 __cache_free mm/slab.c:3494 [inline] kfree+0xcf/0x230 mm/slab.c:3811 x25_neigh_put include/net/x25.h:253 [inline] x25_connect+0x8d8/0xde0 net/x25/af_x25.c:824 __sys_connect+0x266/0x330 net/socket.c:1685 __do_sys_connect net/socket.c:1696 [inline] __se_sys_connect net/socket.c:1693 [inline] __x64_sys_connect+0x73/0xb0 net/socket.c:1693 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff8880a030edc0 which belongs to the cache kmalloc-256 of size 256 The buggy address is located 16 bytes inside of 256-byte region [ffff8880a030edc0, ffff8880a030eec0) The buggy address belongs to the page: page:ffffea000280c380 count:1 mapcount:0 mapping:ffff88812c3f07c0 index:0x0 flags: 0x1fffc0000000200(slab) raw: 01fffc0000000200 ffffea0002806788 ffffea00027f0188 ffff88812c3f07c0 raw: 0000000000000000 ffff8880a030e000 000000010000000c 0000000000000000 page dumped because: kasan: bad access detected Signed-off-by: Eric Dumazet Reported-by: syzbot+04babcefcd396fabec37@syzkaller.appspotmail.com Cc: andrew hendry Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/x25/af_x25.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 47f600564f24..716d53b683e0 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -812,8 +812,12 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTED; rc = 0; out_put_neigh: - if (rc) + if (rc) { + read_lock_bh(&x25_list_lock); x25_neigh_put(x25->neighbour); + x25->neighbour = NULL; + read_unlock_bh(&x25_list_lock); + } out_put_route: x25_route_put(rt); out: -- GitLab From 91820c10ea6149c9af32be20d7cfda3375ab6529 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 11 Mar 2019 13:48:44 -0700 Subject: [PATCH 0207/1128] net/x25: reset state in x25_connect() [ Upstream commit ee74d0bd4325efb41e38affe5955f920ed973f23 ] In case x25_connect() fails and frees the socket neighbour, we also need to undo the change done to x25->state. Before my last bug fix, we had use-after-free so this patch fixes a latent bug. syzbot report : kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 16137 Comm: syz-executor.1 Not tainted 5.0.0+ #117 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:x25_write_internal+0x1e8/0xdf0 net/x25/x25_subr.c:173 Code: 00 40 88 b5 e0 fe ff ff 0f 85 01 0b 00 00 48 8b 8b 80 04 00 00 48 ba 00 00 00 00 00 fc ff df 48 8d 79 1c 48 89 fe 48 c1 ee 03 <0f> b6 34 16 48 89 fa 83 e2 07 83 c2 03 40 38 f2 7c 09 40 84 f6 0f RSP: 0018:ffff888076717a08 EFLAGS: 00010207 RAX: ffff88805f2f2292 RBX: ffff8880a0ae6000 RCX: 0000000000000000 kobject: 'loop5' (0000000018d0d0ee): kobject_uevent_env RDX: dffffc0000000000 RSI: 0000000000000003 RDI: 000000000000001c RBP: ffff888076717b40 R08: ffff8880950e0580 R09: ffffed100be5e46d R10: ffffed100be5e46c R11: ffff88805f2f2363 R12: ffff888065579840 kobject: 'loop5' (0000000018d0d0ee): fill_kobj_path: path = '/devices/virtual/block/loop5' R13: 1ffff1100ece2f47 R14: 0000000000000013 R15: 0000000000000013 FS: 00007fb88cf43700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f9a42a41028 CR3: 0000000087a67000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: x25_release+0xd0/0x340 net/x25/af_x25.c:658 __sock_release+0xd3/0x2b0 net/socket.c:579 sock_close+0x1b/0x30 net/socket.c:1162 __fput+0x2df/0x8d0 fs/file_table.c:278 ____fput+0x16/0x20 fs/file_table.c:309 task_work_run+0x14a/0x1c0 kernel/task_work.c:113 get_signal+0x1961/0x1d50 kernel/signal.c:2388 do_signal+0x87/0x1940 arch/x86/kernel/signal.c:816 exit_to_usermode_loop+0x244/0x2c0 arch/x86/entry/common.c:162 prepare_exit_to_usermode arch/x86/entry/common.c:197 [inline] syscall_return_slowpath arch/x86/entry/common.c:268 [inline] do_syscall_64+0x52d/0x610 arch/x86/entry/common.c:293 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457f29 Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fb88cf42c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: fffffffffffffe00 RBX: 0000000000000003 RCX: 0000000000457f29 RDX: 0000000000000012 RSI: 0000000020000080 RDI: 0000000000000004 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fb88cf436d4 R13: 00000000004be462 R14: 00000000004cec98 R15: 00000000ffffffff Modules linked in: Fixes: 95d6ebd53c79 ("net/x25: fix use-after-free in x25_device_event()") Signed-off-by: Eric Dumazet Cc: andrew hendry Reported-by: syzbot Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/x25/af_x25.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 716d53b683e0..8d0b0f2ee697 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -817,6 +817,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, x25_neigh_put(x25->neighbour); x25->neighbour = NULL; read_unlock_bh(&x25_list_lock); + x25->state = X25_STATE_0; } out_put_route: x25_route_put(rt); -- GitLab From eff9b85fe90978a740f053e95441ee937463f25e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 13 Mar 2019 17:00:48 +0800 Subject: [PATCH 0208/1128] pptp: dst_release sk_dst_cache in pptp_sock_destruct [ Upstream commit 9417d81f4f8adfe20a12dd1fadf73a618cbd945d ] sk_setup_caps() is called to set sk->sk_dst_cache in pptp_connect, so we have to dst_release(sk->sk_dst_cache) in pptp_sock_destruct, otherwise, the dst refcnt will leak. It can be reproduced by this syz log: r1 = socket$pptp(0x18, 0x1, 0x2) bind$pptp(r1, &(0x7f0000000100)={0x18, 0x2, {0x0, @local}}, 0x1e) connect$pptp(r1, &(0x7f0000000000)={0x18, 0x2, {0x3, @remote}}, 0x1e) Consecutive dmesg warnings will occur: unregister_netdevice: waiting for lo to become free. Usage count = 1 v1->v2: - use rcu_dereference_protected() instead of rcu_dereference_check(), as suggested by Eric. Fixes: 00959ade36ac ("PPTP: PPP over IPv4 (Point-to-Point Tunneling Protocol)") Reported-by: Xiumei Mu Signed-off-by: Xin Long Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ppp/pptp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 9b70a3af678e..68b274b3e448 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -539,6 +539,7 @@ static void pptp_sock_destruct(struct sock *sk) pppox_unbind_sock(sk); } skb_queue_purge(&sk->sk_receive_queue); + dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); } static int pptp_create(struct net *net, struct socket *sock, int kern) -- GitLab From 1a443e2d40e6e278c8f468b835c7f3e21904aa7a Mon Sep 17 00:00:00 2001 From: Masaru Nagai Date: Thu, 7 Mar 2019 11:24:47 +0100 Subject: [PATCH 0209/1128] ravb: Decrease TxFIFO depth of Q3 and Q2 to one [ Upstream commit ae9819e339b451da7a86ab6fe38ecfcb6814e78a ] Hardware has the CBS (Credit Based Shaper) which affects only Q3 and Q2. When updating the CBS settings, even if the driver does so after waiting for Tx DMA finished, there is a possibility that frame data still remains in TxFIFO. To avoid this, decrease TxFIFO depth of Q3 and Q2 to one. This patch has been exercised this using netperf TCP_MAERTS, TCP_STREAM and UDP_STREAM tests run on an Ebisu board. No performance change was detected, outside of noise in the tests, both in terms of throughput and CPU utilisation. Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper") Signed-off-by: Masaru Nagai Signed-off-by: Kazuya Mizuguchi [simon: updated changelog] Signed-off-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/renesas/ravb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ff3a293ffe36..ce79af4a7f6f 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -458,7 +458,7 @@ static int ravb_dmac_init(struct net_device *ndev) RCR_EFFS | RCR_ENCF | RCR_ETS0 | RCR_ESF | 0x18000000, RCR); /* Set FIFO size */ - ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00222200, TGC); + ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00112200, TGC); /* Timestamp enable */ ravb_write(ndev, TCCR_TFEN, TCCR); -- GitLab From 68588407399ab282872f7d9e85c79a6def785214 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 8 Mar 2019 14:50:54 +0800 Subject: [PATCH 0210/1128] route: set the deleted fnhe fnhe_daddr to 0 in ip_del_fnhe to fix a race [ Upstream commit ee60ad219f5c7c4fb2f047f88037770063ef785f ] The race occurs in __mkroute_output() when 2 threads lookup a dst: CPU A CPU B find_exception() find_exception() [fnhe expires] ip_del_fnhe() [fnhe is deleted] rt_bind_exception() In rt_bind_exception() it will bind a deleted fnhe with the new dst, and this dst will get no chance to be freed. It causes a dev defcnt leak and consecutive dmesg warnings: unregister_netdevice: waiting for ethX to become free. Usage count = 1 Especially thanks Jon to identify the issue. This patch fixes it by setting fnhe_daddr to 0 in ip_del_fnhe() to stop binding the deleted fnhe with a new dst when checking fnhe's fnhe_daddr and daddr in rt_bind_exception(). It works as both ip_del_fnhe() and rt_bind_exception() are protected by fnhe_lock and the fhne is freed by kfree_rcu(). Fixes: deed49df7390 ("route: check and remove route cache when we get route") Signed-off-by: Jon Maxwell Signed-off-by: Xin Long Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/route.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0a35d294abec..a1bf87711bfa 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1315,6 +1315,10 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) if (fnhe->fnhe_daddr == daddr) { rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + /* set fnhe_daddr to 0 to ensure it won't bind with + * new dsts in rt_bind_exception(). + */ + fnhe->fnhe_daddr = 0; fnhe_flush_routes(fnhe); kfree_rcu(fnhe, rcu); break; -- GitLab From a63c7fca080e9bdd3368c9c4ab573c01d03f1332 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 9 Mar 2019 00:29:58 +0000 Subject: [PATCH 0211/1128] rxrpc: Fix client call queueing, waiting for channel [ Upstream commit 69ffaebb90369ce08657b5aea4896777b9d6e8fc ] rxrpc_get_client_conn() adds a new call to the front of the waiting_calls queue if the connection it's going to use already exists. This is bad as it allows calls to get starved out. Fix this by adding to the tail instead. Also change the other enqueue point in the same function to put it on the front (ie. when we have a new connection). This makes the point that in the case of a new connection the new call goes at the front (though it doesn't actually matter since the queue should be unoccupied). Fixes: 45025bceef17 ("rxrpc: Improve management and caching of client connection objects") Signed-off-by: David Howells Reviewed-by: Marc Dionne Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/rxrpc/conn_client.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 78a154173d90..0aa4bf09fb9c 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -351,7 +351,7 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, * normally have to take channel_lock but we do this before anyone else * can see the connection. */ - list_add_tail(&call->chan_wait_link, &candidate->waiting_calls); + list_add(&call->chan_wait_link, &candidate->waiting_calls); if (cp->exclusive) { call->conn = candidate; @@ -430,7 +430,7 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, call->conn = conn; call->security_ix = conn->security_ix; call->service_id = conn->service_id; - list_add(&call->chan_wait_link, &conn->waiting_calls); + list_add_tail(&call->chan_wait_link, &conn->waiting_calls); spin_unlock(&conn->channel_lock); _leave(" = 0 [extant %d]", conn->debug_id); return 0; -- GitLab From d51c4c0c1fbc338d1b756d9d9d1ba438534546cd Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Mon, 11 Mar 2019 11:41:05 -0700 Subject: [PATCH 0212/1128] tcp: Don't access TCP_SKB_CB before initializing it [ Upstream commit f2feaefdabb0a6253aa020f65e7388f07a9ed47c ] Since commit eeea10b83a13 ("tcp: add tcp_v4_fill_cb()/tcp_v4_restore_cb()"), tcp_vX_fill_cb is only called after tcp_filter(). That means, TCP_SKB_CB(skb)->end_seq still points to the IP-part of the cb. We thus should not mock with it, as this can trigger bugs (thanks syzkaller): [ 12.349396] ================================================================== [ 12.350188] BUG: KASAN: slab-out-of-bounds in ip6_datagram_recv_specific_ctl+0x19b3/0x1a20 [ 12.351035] Read of size 1 at addr ffff88006adbc208 by task test_ip6_datagr/1799 Setting end_seq is actually no more necessary in tcp_filter as it gets initialized later on in tcp_vX_fill_cb. Cc: Eric Dumazet Fixes: eeea10b83a13 ("tcp: add tcp_v4_fill_cb()/tcp_v4_restore_cb()") Signed-off-by: Christoph Paasch Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_ipv4.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e593301f442f..97a414dbdaf4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1578,15 +1578,8 @@ EXPORT_SYMBOL(tcp_add_backlog); int tcp_filter(struct sock *sk, struct sk_buff *skb) { struct tcphdr *th = (struct tcphdr *)skb->data; - unsigned int eaten = skb->len; - int err; - err = sk_filter_trim_cap(sk, skb, th->doff * 4); - if (!err) { - eaten -= skb->len; - TCP_SKB_CB(skb)->end_seq -= eaten; - } - return err; + return sk_filter_trim_cap(sk, skb, th->doff * 4); } EXPORT_SYMBOL(tcp_filter); -- GitLab From bb73b637993bd77087c0f3e56e86a040f230e435 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 8 Mar 2019 22:09:47 +0100 Subject: [PATCH 0213/1128] tcp: handle inet_csk_reqsk_queue_add() failures [ Upstream commit 9d3e1368bb45893a75a5dfb7cd21fdebfa6b47af ] Commit 7716682cc58e ("tcp/dccp: fix another race at listener dismantle") let inet_csk_reqsk_queue_add() fail, and adjusted {tcp,dccp}_check_req() accordingly. However, TFO and syncookies weren't modified, thus leaking allocated resources on error. Contrary to tcp_check_req(), in both syncookies and TFO cases, we need to drop the request socket. Also, since the child socket is created with inet_csk_clone_lock(), we have to unlock it and drop an extra reference (->sk_refcount is initially set to 2 and inet_csk_reqsk_queue_add() drops only one ref). For TFO, we also need to revert the work done by tcp_try_fastopen() (with reqsk_fastopen_remove()). Fixes: 7716682cc58e ("tcp/dccp: fix another race at listener dismantle") Signed-off-by: Guillaume Nault Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/syncookies.c | 7 ++++++- net/ipv4/tcp_input.c | 8 +++++++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 77cf32a80952..2f871424925e 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -216,7 +216,12 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, refcount_set(&req->rsk_refcnt, 1); tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); - inet_csk_reqsk_queue_add(sk, req, child); + if (!inet_csk_reqsk_queue_add(sk, req, child)) { + bh_unlock_sock(child); + sock_put(child); + child = NULL; + reqsk_put(req); + } } else { reqsk_free(req); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e24c0d7adf65..c8227e07d574 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6406,7 +6406,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, af_ops->send_synack(fastopen_sk, dst, &fl, req, &foc, TCP_SYNACK_FASTOPEN); /* Add the child socket directly into the accept queue */ - inet_csk_reqsk_queue_add(sk, req, fastopen_sk); + if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) { + reqsk_fastopen_remove(fastopen_sk, req, false); + bh_unlock_sock(fastopen_sk); + sock_put(fastopen_sk); + reqsk_put(req); + goto drop; + } sk->sk_data_ready(sk); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); -- GitLab From 1ed2291ca6e2782d507f316abcbcb279828dcab7 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Fri, 8 Mar 2019 16:40:57 +0100 Subject: [PATCH 0214/1128] vxlan: Fix GRO cells race condition between receive and link delete [ Upstream commit ad6c9986bcb627c7c22b8f9e9a934becc27df87c ] If we receive a packet while deleting a VXLAN device, there's a chance vxlan_rcv() is called at the same time as vxlan_dellink(). This is fine, except that vxlan_dellink() should never ever touch stuff that's still in use, such as the GRO cells list. Otherwise, vxlan_rcv() crashes while queueing packets via gro_cells_receive(). Move the gro_cells_destroy() to vxlan_uninit(), which runs after the RCU grace period is elapsed and nothing needs the gro_cells anymore. This is now done in the same way as commit 8e816df87997 ("geneve: Use GRO cells infrastructure.") originally implemented for GENEVE. Reported-by: Jianlin Shi Fixes: 58ce31cca1ff ("vxlan: GRO support at tunnel layer") Signed-off-by: Stefano Brivio Reviewed-by: Sabrina Dubroca Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/vxlan.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index a1b40b9c4906..eb1c91e86fcd 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2462,6 +2462,8 @@ static void vxlan_uninit(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); + gro_cells_destroy(&vxlan->gro_cells); + vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni); free_percpu(dev->tstats); @@ -3523,7 +3525,6 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head) vxlan_flush(vxlan, true); - gro_cells_destroy(&vxlan->gro_cells); list_del(&vxlan->next); unregister_netdevice_queue(dev, head); } -- GitLab From 06c7cd5b40e1fd95f3f6303aa5a505d9bb68c1bb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 10 Mar 2019 10:36:40 -0700 Subject: [PATCH 0215/1128] vxlan: test dev->flags & IFF_UP before calling gro_cells_receive() [ Upstream commit 59cbf56fcd98ba2a715b6e97c4e43f773f956393 ] Same reasons than the ones explained in commit 4179cb5a4c92 ("vxlan: test dev->flags & IFF_UP before calling netif_rx()") netif_rx() or gro_cells_receive() must be called under a strict contract. At device dismantle phase, core networking clears IFF_UP and flush_all_backlogs() is called after rcu grace period to make sure no incoming packet might be in a cpu backlog and still referencing the device. A similar protocol is used for gro_cells infrastructure, as gro_cells_destroy() will be called only after a full rcu grace period is observed after IFF_UP has been cleared. Most drivers call netif_rx() from their interrupt handler, and since the interrupts are disabled at device dismantle, netif_rx() does not have to check dev->flags & IFF_UP Virtual drivers do not have this guarantee, and must therefore make the check themselves. Otherwise we risk use-after-free and/or crashes. Fixes: d342894c5d2f ("vxlan: virtual extensible lan") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/vxlan.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index eb1c91e86fcd..df48f65c4f90 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1468,6 +1468,14 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) goto drop; } + rcu_read_lock(); + + if (unlikely(!(vxlan->dev->flags & IFF_UP))) { + rcu_read_unlock(); + atomic_long_inc(&vxlan->dev->rx_dropped); + goto drop; + } + stats = this_cpu_ptr(vxlan->dev->tstats); u64_stats_update_begin(&stats->syncp); stats->rx_packets++; @@ -1475,6 +1483,9 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) u64_stats_update_end(&stats->syncp); gro_cells_receive(&vxlan->gro_cells, skb); + + rcu_read_unlock(); + return 0; drop: -- GitLab From 22768ca28f896276db1519bd5cf384dcd3cd0db2 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Tue, 12 Mar 2019 17:05:47 +0200 Subject: [PATCH 0216/1128] net/mlx4_core: Fix reset flow when in command polling mode [ Upstream commit e15ce4b8d11227007577e6dc1364d288b8874fbe ] As part of unloading a device, the driver switches from FW command event mode to FW command polling mode. Part of switching over to polling mode is freeing the command context array memory (unfortunately, currently, without NULLing the command context array pointer). The reset flow calls "complete" to complete all outstanding fw commands (if we are in event mode). The check for event vs. polling mode here is to test if the command context array pointer is NULL. If the reset flow is activated after the switch to polling mode, it will attempt (incorrectly) to complete all the commands in the context array -- because the pointer was not NULLed when the driver switched over to polling mode. As a result, we have a use-after-free situation, which results in a kernel crash. For example: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [] __wake_up_common+0x2e/0x90 PGD 0 Oops: 0000 [#1] SMP Modules linked in: netconsole nfsv3 nfs_acl nfs lockd grace ... CPU: 2 PID: 940 Comm: kworker/2:3 Kdump: loaded Not tainted 3.10.0-862.el7.x86_64 #1 Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006 04/28/2016 Workqueue: events hv_eject_device_work [pci_hyperv] task: ffff8d1734ca0fd0 ti: ffff8d17354bc000 task.ti: ffff8d17354bc000 RIP: 0010:[] [] __wake_up_common+0x2e/0x90 RSP: 0018:ffff8d17354bfa38 EFLAGS: 00010082 RAX: 0000000000000000 RBX: ffff8d17362d42c8 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000003 RDI: ffff8d17362d42c8 RBP: ffff8d17354bfa70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000298 R11: ffff8d173610e000 R12: ffff8d17362d42d0 R13: 0000000000000246 R14: 0000000000000000 R15: 0000000000000003 FS: 0000000000000000(0000) GS:ffff8d1802680000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000f16d8000 CR4: 00000000001406e0 Call Trace: [] complete+0x3c/0x50 [] mlx4_cmd_wake_completions+0x70/0x90 [mlx4_core] [] mlx4_enter_error_state+0xe1/0x380 [mlx4_core] [] mlx4_comm_cmd+0x29b/0x360 [mlx4_core] [] __mlx4_cmd+0x441/0x920 [mlx4_core] [] ? __slab_free+0x81/0x2f0 [] ? __radix_tree_lookup+0x84/0xf0 [] mlx4_free_mtt_range+0x5b/0xb0 [mlx4_core] [] mlx4_mtt_cleanup+0x17/0x20 [mlx4_core] [] mlx4_free_eq+0xa7/0x1c0 [mlx4_core] [] mlx4_cleanup_eq_table+0xde/0x130 [mlx4_core] [] mlx4_unload_one+0x118/0x300 [mlx4_core] [] mlx4_remove_one+0x91/0x1f0 [mlx4_core] The fix is to set the command context array pointer to NULL after freeing the array. Fixes: f5aef5aa3506 ("net/mlx4_core: Activate reset flow upon fatal command cases") Signed-off-by: Jack Morgenstein Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 6a9086dc1e92..5b69d373bcb2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2686,6 +2686,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev) down(&priv->cmd.event_sem); kfree(priv->cmd.context); + priv->cmd.context = NULL; up(&priv->cmd.poll_sem); up_write(&priv->cmd.switch_sem); -- GitLab From 3d31f62c115e55178d7903a202d1f967c0b7531f Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Tue, 12 Mar 2019 17:05:48 +0200 Subject: [PATCH 0217/1128] net/mlx4_core: Fix locking in SRIOV mode when switching between events and polling [ Upstream commit c07d27927f2f2e96fcd27bb9fb330c9ea65612d0 ] In procedures mlx4_cmd_use_events() and mlx4_cmd_use_polling(), we need to guarantee that there are no FW commands in progress on the comm channel (for VFs) or wrapped FW commands (on the PF) when SRIOV is active. We do this by also taking the slave_cmd_mutex when SRIOV is active. This is especially important when switching from event to polling, since we free the command-context array during the switch. If there are FW commands in progress (e.g., waiting for a completion event), the completion event handler will access freed memory. Since the decision to use comm_wait or comm_poll is taken before grabbing the event_sem/poll_sem in mlx4_comm_cmd_wait/poll, we must take the slave_cmd_mutex as well (to guarantee that the decision to use events or polling and the call to the appropriate cmd function are atomic). Fixes: a7e1f04905e5 ("net/mlx4_core: Fix deadlock when switching between polling and event fw commands") Signed-off-by: Jack Morgenstein Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 5b69d373bcb2..4c2ee9fd9e57 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2642,6 +2642,8 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev) if (!priv->cmd.context) return -ENOMEM; + if (mlx4_is_mfunc(dev)) + mutex_lock(&priv->cmd.slave_cmd_mutex); down_write(&priv->cmd.switch_sem); for (i = 0; i < priv->cmd.max_cmds; ++i) { priv->cmd.context[i].token = i; @@ -2667,6 +2669,8 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev) down(&priv->cmd.poll_sem); priv->cmd.use_events = 1; up_write(&priv->cmd.switch_sem); + if (mlx4_is_mfunc(dev)) + mutex_unlock(&priv->cmd.slave_cmd_mutex); return err; } @@ -2679,6 +2683,8 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev) struct mlx4_priv *priv = mlx4_priv(dev); int i; + if (mlx4_is_mfunc(dev)) + mutex_lock(&priv->cmd.slave_cmd_mutex); down_write(&priv->cmd.switch_sem); priv->cmd.use_events = 0; @@ -2690,6 +2696,8 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev) up(&priv->cmd.poll_sem); up_write(&priv->cmd.switch_sem); + if (mlx4_is_mfunc(dev)) + mutex_unlock(&priv->cmd.slave_cmd_mutex); } struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev) -- GitLab From 048d7079926598a0ab94582f86b1ef46954ed8ec Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Tue, 12 Mar 2019 17:05:49 +0200 Subject: [PATCH 0218/1128] net/mlx4_core: Fix qp mtt size calculation [ Upstream commit 8511a653e9250ef36b95803c375a7be0e2edb628 ] Calculation of qp mtt size (in function mlx4_RST2INIT_wrapper) ultimately depends on function roundup_pow_of_two. If the amount of memory required by the QP is less than one page, roundup_pow_of_two is called with argument zero. In this case, the roundup_pow_of_two result is undefined. Calling roundup_pow_of_two with a zero argument resulted in the following stack trace: UBSAN: Undefined behaviour in ./include/linux/log2.h:61:13 shift exponent 64 is too large for 64-bit type 'long unsigned int' CPU: 4 PID: 26939 Comm: rping Tainted: G OE 4.19.0-rc1 Hardware name: Supermicro X9DR3-F/X9DR3-F, BIOS 3.2a 07/09/2015 Call Trace: dump_stack+0x9a/0xeb ubsan_epilogue+0x9/0x7c __ubsan_handle_shift_out_of_bounds+0x254/0x29d ? __ubsan_handle_load_invalid_value+0x180/0x180 ? debug_show_all_locks+0x310/0x310 ? sched_clock+0x5/0x10 ? sched_clock+0x5/0x10 ? sched_clock_cpu+0x18/0x260 ? find_held_lock+0x35/0x1e0 ? mlx4_RST2INIT_QP_wrapper+0xfb1/0x1440 [mlx4_core] mlx4_RST2INIT_QP_wrapper+0xfb1/0x1440 [mlx4_core] Fix this by explicitly testing for zero, and returning one if the argument is zero (assuming that the next higher power of 2 in this case should be one). Fixes: c82e9aa0a8bc ("mlx4_core: resource tracking for HCA resources used by guests") Signed-off-by: Jack Morgenstein Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index a5381b091710..53ca6cf316dc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2717,13 +2717,13 @@ static int qp_get_mtt_size(struct mlx4_qp_context *qpc) int total_pages; int total_mem; int page_offset = (be32_to_cpu(qpc->params2) >> 6) & 0x3f; + int tot; sq_size = 1 << (log_sq_size + log_sq_sride + 4); rq_size = (srq|rss|xrc) ? 0 : (1 << (log_rq_size + log_rq_stride + 4)); total_mem = sq_size + rq_size; - total_pages = - roundup_pow_of_two((total_mem + (page_offset << 6)) >> - page_shift); + tot = (total_mem + (page_offset << 6)) >> page_shift; + total_pages = !tot ? 1 : roundup_pow_of_two(tot); return total_pages; } -- GitLab From 64a6e35ac51036d309fbcc003e4daae672fb5849 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 23 Feb 2019 13:24:59 -0800 Subject: [PATCH 0219/1128] net/x25: fix a race in x25_bind() [ Upstream commit 797a22bd5298c2674d927893f46cadf619dad11d ] syzbot was able to trigger another soft lockup [1] I first thought it was the O(N^2) issue I mentioned in my prior fix (f657d22ee1f "net/x25: do not hold the cpu too long in x25_new_lci()"), but I eventually found that x25_bind() was not checking SOCK_ZAPPED state under socket lock protection. This means that multiple threads can end up calling x25_insert_socket() for the same socket, and corrupt x25_list [1] watchdog: BUG: soft lockup - CPU#0 stuck for 123s! [syz-executor.2:10492] Modules linked in: irq event stamp: 27515 hardirqs last enabled at (27514): [] trace_hardirqs_on_thunk+0x1a/0x1c hardirqs last disabled at (27515): [] trace_hardirqs_off_thunk+0x1a/0x1c softirqs last enabled at (32): [] x25_get_neigh+0xa3/0xd0 net/x25/x25_link.c:336 softirqs last disabled at (34): [] x25_find_socket+0x23/0x140 net/x25/af_x25.c:341 CPU: 0 PID: 10492 Comm: syz-executor.2 Not tainted 5.0.0-rc7+ #88 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__sanitizer_cov_trace_pc+0x4/0x50 kernel/kcov.c:97 Code: f4 ff ff ff e8 11 9f ea ff 48 c7 05 12 fb e5 08 00 00 00 00 e9 c8 e9 ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 55 48 89 e5 <48> 8b 75 08 65 48 8b 04 25 40 ee 01 00 65 8b 15 38 0c 92 7e 81 e2 RSP: 0018:ffff88806e94fc48 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff13 RAX: 1ffff1100d84dac5 RBX: 0000000000000001 RCX: ffffc90006197000 RDX: 0000000000040000 RSI: ffffffff86324bf3 RDI: ffff88806c26d628 RBP: ffff88806e94fc48 R08: ffff88806c1c6500 R09: fffffbfff1282561 R10: fffffbfff1282560 R11: ffffffff89412b03 R12: ffff88806c26d628 R13: ffff888090455200 R14: dffffc0000000000 R15: 0000000000000000 FS: 00007f3a107e4700(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3a107e3db8 CR3: 00000000a5544000 CR4: 00000000001406f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __x25_find_socket net/x25/af_x25.c:327 [inline] x25_find_socket+0x7d/0x140 net/x25/af_x25.c:342 x25_new_lci net/x25/af_x25.c:355 [inline] x25_connect+0x380/0xde0 net/x25/af_x25.c:784 __sys_connect+0x266/0x330 net/socket.c:1662 __do_sys_connect net/socket.c:1673 [inline] __se_sys_connect net/socket.c:1670 [inline] __x64_sys_connect+0x73/0xb0 net/socket.c:1670 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457e29 Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f3a107e3c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457e29 RDX: 0000000000000012 RSI: 0000000020000200 RDI: 0000000000000005 RBP: 000000000073c040 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f3a107e46d4 R13: 00000000004be362 R14: 00000000004ceb98 R15: 00000000ffffffff Sending NMI from CPU 0 to CPUs 1: NMI backtrace for cpu 1 CPU: 1 PID: 10493 Comm: syz-executor.3 Not tainted 5.0.0-rc7+ #88 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__read_once_size include/linux/compiler.h:193 [inline] RIP: 0010:queued_write_lock_slowpath+0x143/0x290 kernel/locking/qrwlock.c:86 Code: 4c 8d 2c 01 41 83 c7 03 41 0f b6 45 00 41 38 c7 7c 08 84 c0 0f 85 0c 01 00 00 8b 03 3d 00 01 00 00 74 1a f3 90 41 0f b6 55 00 <41> 38 d7 7c eb 84 d2 74 e7 48 89 df e8 cc aa 4e 00 eb dd be 04 00 RSP: 0018:ffff888085c47bd8 EFLAGS: 00000206 RAX: 0000000000000300 RBX: ffffffff89412b00 RCX: 1ffffffff1282560 RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffffffff89412b00 RBP: ffff888085c47c70 R08: 1ffffffff1282560 R09: fffffbfff1282561 R10: fffffbfff1282560 R11: ffffffff89412b03 R12: 00000000000000ff R13: fffffbfff1282560 R14: 1ffff11010b88f7d R15: 0000000000000003 FS: 00007fdd04086700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fdd04064db8 CR3: 0000000090be0000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: queued_write_lock include/asm-generic/qrwlock.h:104 [inline] do_raw_write_lock+0x1d6/0x290 kernel/locking/spinlock_debug.c:203 __raw_write_lock_bh include/linux/rwlock_api_smp.h:204 [inline] _raw_write_lock_bh+0x3b/0x50 kernel/locking/spinlock.c:312 x25_insert_socket+0x21/0xe0 net/x25/af_x25.c:267 x25_bind+0x273/0x340 net/x25/af_x25.c:703 __sys_bind+0x23f/0x290 net/socket.c:1481 __do_sys_bind net/socket.c:1492 [inline] __se_sys_bind net/socket.c:1490 [inline] __x64_sys_bind+0x73/0xb0 net/socket.c:1490 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457e29 Fixes: 90c27297a9bf ("X.25 remove bkl in bind") Signed-off-by: Eric Dumazet Cc: andrew hendry Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/x25/af_x25.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 8d0b0f2ee697..1b830a6ee3ff 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -678,8 +678,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr; int len, i, rc = 0; - if (!sock_flag(sk, SOCK_ZAPPED) || - addr_len != sizeof(struct sockaddr_x25) || + if (addr_len != sizeof(struct sockaddr_x25) || addr->sx25_family != AF_X25) { rc = -EINVAL; goto out; @@ -694,9 +693,13 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } lock_sock(sk); - x25_sk(sk)->source_addr = addr->sx25_addr; - x25_insert_socket(sk); - sock_reset_flag(sk, SOCK_ZAPPED); + if (sock_flag(sk, SOCK_ZAPPED)) { + x25_sk(sk)->source_addr = addr->sx25_addr; + x25_insert_socket(sk); + sock_reset_flag(sk, SOCK_ZAPPED); + } else { + rc = -EINVAL; + } release_sock(sk); SOCK_DEBUG(sk, "x25_bind: socket is bound\n"); out: -- GitLab From 07c2216c3783daca34ea0d86affb9dfc5346f183 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 21 Feb 2019 22:42:01 +0800 Subject: [PATCH 0220/1128] mdio_bus: Fix use-after-free on device_register fails [ Upstream commit 6ff7b060535e87c2ae14dd8548512abfdda528fb ] KASAN has found use-after-free in fixed_mdio_bus_init, commit 0c692d07842a ("drivers/net/phy/mdio_bus.c: call put_device on device_register() failure") call put_device() while device_register() fails,give up the last reference to the device and allow mdiobus_release to be executed ,kfreeing the bus. However in most drives, mdiobus_free be called to free the bus while mdiobus_register fails. use-after-free occurs when access bus again, this patch revert it to let mdiobus_free free the bus. KASAN report details as below: BUG: KASAN: use-after-free in mdiobus_free+0x85/0x90 drivers/net/phy/mdio_bus.c:482 Read of size 4 at addr ffff8881dc824d78 by task syz-executor.0/3524 CPU: 1 PID: 3524 Comm: syz-executor.0 Not tainted 5.0.0-rc7+ #45 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xfa/0x1ce lib/dump_stack.c:113 print_address_description+0x65/0x270 mm/kasan/report.c:187 kasan_report+0x149/0x18d mm/kasan/report.c:317 mdiobus_free+0x85/0x90 drivers/net/phy/mdio_bus.c:482 fixed_mdio_bus_init+0x283/0x1000 [fixed_phy] ? 0xffffffffc0e40000 ? 0xffffffffc0e40000 ? 0xffffffffc0e40000 do_one_initcall+0xfa/0x5ca init/main.c:887 do_init_module+0x204/0x5f6 kernel/module.c:3460 load_module+0x66b2/0x8570 kernel/module.c:3808 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x462e99 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f6215c19c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462e99 RDX: 0000000000000000 RSI: 0000000020000080 RDI: 0000000000000003 RBP: 00007f6215c19c70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f6215c1a6bc R13: 00000000004bcefb R14: 00000000006f7030 R15: 0000000000000004 Allocated by task 3524: set_track mm/kasan/common.c:85 [inline] __kasan_kmalloc.constprop.3+0xa0/0xd0 mm/kasan/common.c:496 kmalloc include/linux/slab.h:545 [inline] kzalloc include/linux/slab.h:740 [inline] mdiobus_alloc_size+0x54/0x1b0 drivers/net/phy/mdio_bus.c:143 fixed_mdio_bus_init+0x163/0x1000 [fixed_phy] do_one_initcall+0xfa/0x5ca init/main.c:887 do_init_module+0x204/0x5f6 kernel/module.c:3460 load_module+0x66b2/0x8570 kernel/module.c:3808 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 3524: set_track mm/kasan/common.c:85 [inline] __kasan_slab_free+0x130/0x180 mm/kasan/common.c:458 slab_free_hook mm/slub.c:1409 [inline] slab_free_freelist_hook mm/slub.c:1436 [inline] slab_free mm/slub.c:2986 [inline] kfree+0xe1/0x270 mm/slub.c:3938 device_release+0x78/0x200 drivers/base/core.c:919 kobject_cleanup lib/kobject.c:662 [inline] kobject_release lib/kobject.c:691 [inline] kref_put include/linux/kref.h:67 [inline] kobject_put+0x146/0x240 lib/kobject.c:708 put_device+0x1c/0x30 drivers/base/core.c:2060 __mdiobus_register+0x483/0x560 drivers/net/phy/mdio_bus.c:382 fixed_mdio_bus_init+0x26b/0x1000 [fixed_phy] do_one_initcall+0xfa/0x5ca init/main.c:887 do_init_module+0x204/0x5f6 kernel/module.c:3460 load_module+0x66b2/0x8570 kernel/module.c:3808 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff8881dc824c80 which belongs to the cache kmalloc-2k of size 2048 The buggy address is located 248 bytes inside of 2048-byte region [ffff8881dc824c80, ffff8881dc825480) The buggy address belongs to the page: page:ffffea0007720800 count:1 mapcount:0 mapping:ffff8881f6c02800 index:0x0 compound_mapcount: 0 flags: 0x2fffc0000010200(slab|head) raw: 02fffc0000010200 0000000000000000 0000000500000001 ffff8881f6c02800 raw: 0000000000000000 00000000800f000f 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8881dc824c00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff8881dc824c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8881dc824d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8881dc824d80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8881dc824e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 0c692d07842a ("drivers/net/phy/mdio_bus.c: call put_device on device_register() failure") Signed-off-by: YueHaibing Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/mdio_bus.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 1ece41277993..c545fb1f82bd 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -347,7 +347,6 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) err = device_register(&bus->dev); if (err) { pr_err("mii_bus %s failed to register\n", bus->id); - put_device(&bus->dev); return -EINVAL; } -- GitLab From b3dc5b185072520422e26d8bd1a65203f0713a61 Mon Sep 17 00:00:00 2001 From: Kalash Nainwal Date: Wed, 20 Feb 2019 16:23:04 -0800 Subject: [PATCH 0221/1128] net: Set rtm_table to RT_TABLE_COMPAT for ipv6 for tables > 255 [ Upstream commit 97f0082a0592212fc15d4680f5a4d80f79a1687c ] Set rtm_table to RT_TABLE_COMPAT for ipv6 for tables > 255 to keep legacy software happy. This is similar to what was done for ipv4 in commit 709772e6e065 ("net: Fix routing tables with id > 255 for legacy software"). Signed-off-by: Kalash Nainwal Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fafecdc06900..00f8fe8cebd5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3495,7 +3495,7 @@ static int rt6_fill_node(struct net *net, table = rt->rt6i_table->tb6_id; else table = RT6_TABLE_UNSPEC; - rtm->rtm_table = table; + rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; if (rt->rt6i_flags & RTF_REJECT) { -- GitLab From 6c338fafab643efe92229caf9a4d301d92ff9fd1 Mon Sep 17 00:00:00 2001 From: Michal Soltys Date: Mon, 18 Feb 2019 17:55:28 +0100 Subject: [PATCH 0222/1128] bonding: fix PACKET_ORIGDEV regression MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3c963a3306eada999be5ebf4f293dfa3d3945487 ] This patch fixes a subtle PACKET_ORIGDEV regression which was a side effect of fixes introduced by: 6a9e461f6fe4 bonding: pass link-local packets to bonding master also. ... to: b89f04c61efe bonding: deliver link-local packets with skb->dev set to link that packets arrived on While 6a9e461f6fe4 restored pre-b89f04c61efe presence of link-local packets on bonding masters (which is required e.g. by linux bridges participating in spanning tree or needed for lab-like setups created with group_fwd_mask) it also caused the originating device information to be lost due to cloning. Maciej Żenczykowski proposed another solution that doesn't require packet cloning and retains original device information - instead of returning RX_HANDLER_PASS for all link-local packets it's now limited only to packets from inactive slaves. At the same time, packets passed to bonding masters retain correct information about the originating device and PACKET_ORIGDEV can be used to determine it. This elegantly solves all issues so far: - link-local packets that were removed from bonding masters - LLDP daemons being forced to explicitly bind to slave interfaces - PACKET_ORIGDEV having no effect on bond interfaces Fixes: 6a9e461f6fe4 (bonding: pass link-local packets to bonding master also.) Reported-by: Vincent Bernat Signed-off-by: Michal Soltys Signed-off-by: Maciej Żenczykowski Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/bonding/bond_main.c | 35 +++++++++++++-------------------- 1 file changed, 14 insertions(+), 21 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 65c5a65af0ba..99e60bb5fe07 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1177,29 +1177,22 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) } } - /* Link-local multicast packets should be passed to the - * stack on the link they arrive as well as pass them to the - * bond-master device. These packets are mostly usable when - * stack receives it with the link on which they arrive - * (e.g. LLDP) they also must be available on master. Some of - * the use cases include (but are not limited to): LLDP agents - * that must be able to operate both on enslaved interfaces as - * well as on bonds themselves; linux bridges that must be able - * to process/pass BPDUs from attached bonds when any kind of - * STP version is enabled on the network. + /* + * For packets determined by bond_should_deliver_exact_match() call to + * be suppressed we want to make an exception for link-local packets. + * This is necessary for e.g. LLDP daemons to be able to monitor + * inactive slave links without being forced to bind to them + * explicitly. + * + * At the same time, packets that are passed to the bonding master + * (including link-local ones) can have their originating interface + * determined via PACKET_ORIGDEV socket option. */ - if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) { - struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); - - if (nskb) { - nskb->dev = bond->dev; - nskb->queue_mapping = 0; - netif_rx(nskb); - } - return RX_HANDLER_PASS; - } - if (bond_should_deliver_exact_match(skb, slave, bond)) + if (bond_should_deliver_exact_match(skb, slave, bond)) { + if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) + return RX_HANDLER_PASS; return RX_HANDLER_EXACT; + } skb->dev = bond->dev; -- GitLab From 727a261969faaaa47262329dad10816188c75a6b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 15 Feb 2019 20:09:35 +0000 Subject: [PATCH 0223/1128] missing barriers in some of unix_sock ->addr and ->path accesses [ Upstream commit ae3b564179bfd06f32d051b9e5d72ce4b2a07c37 ] Several u->addr and u->path users are not holding any locks in common with unix_bind(). unix_state_lock() is useless for those purposes. u->addr is assign-once and *(u->addr) is fully set up by the time we set u->addr (all under unix_table_lock). u->path is also set in the same critical area, also before setting u->addr, and any unix_sock with ->path filled will have non-NULL ->addr. So setting ->addr with smp_store_release() is all we need for those "lockless" users - just have them fetch ->addr with smp_load_acquire() and don't even bother looking at ->path if they see NULL ->addr. Users of ->addr and ->path fall into several classes now: 1) ones that do smp_load_acquire(u->addr) and access *(u->addr) and u->path only if smp_load_acquire() has returned non-NULL. 2) places holding unix_table_lock. These are guaranteed that *(u->addr) is seen fully initialized. If unix_sock is in one of the "bound" chains, so's ->path. 3) unix_sock_destructor() using ->addr is safe. All places that set u->addr are guaranteed to have seen all stores *(u->addr) while holding a reference to u and unix_sock_destructor() is called when (atomic) refcount hits zero. 4) unix_release_sock() using ->path is safe. unix_bind() is serialized wrt unix_release() (normally - by struct file refcount), and for the instances that had ->path set by unix_bind() unix_release_sock() comes from unix_release(), so they are fine. Instances that had it set in unix_stream_connect() either end up attached to a socket (in unix_accept()), in which case the call chain to unix_release_sock() and serialization are the same as in the previous case, or they never get accept'ed and unix_release_sock() is called when the listener is shut down and its queue gets purged. In that case the listener's queue lock provides the barriers needed - unix_stream_connect() shoves our unix_sock into listener's queue under that lock right after having set ->path and eventual unix_release_sock() caller picks them from that queue under the same lock right before calling unix_release_sock(). 5) unix_find_other() use of ->path is pointless, but safe - it happens with successful lookup by (abstract) name, so ->path.dentry is guaranteed to be NULL there. earlier-variant-reviewed-by: "Paul E. McKenney" Signed-off-by: Al Viro Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/unix/af_unix.c | 57 +++++++++++++++++++++++++------------------- net/unix/diag.c | 3 ++- security/lsm_audit.c | 10 ++++---- 3 files changed, 41 insertions(+), 29 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 7f46bab4ce5c..2adfcc6dec5a 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -892,7 +892,7 @@ static int unix_autobind(struct socket *sock) addr->hash ^= sk->sk_type; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(&unix_socket_table[addr->hash], sk); spin_unlock(&unix_table_lock); err = 0; @@ -1062,7 +1062,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = 0; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(list, sk); out_unlock: @@ -1333,15 +1333,29 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); - /* copy address information from listening to new sock*/ - if (otheru->addr) { - refcount_inc(&otheru->addr->refcnt); - newu->addr = otheru->addr; - } + /* copy address information from listening to new sock + * + * The contents of *(otheru->addr) and otheru->path + * are seen fully set up here, since we have found + * otheru in hash under unix_table_lock. Insertion + * into the hash chain we'd found it in had been done + * in an earlier critical area protected by unix_table_lock, + * the same one where we'd set *(otheru->addr) contents, + * as well as otheru->path and otheru->addr itself. + * + * Using smp_store_release() here to set newu->addr + * is enough to make those stores, as well as stores + * to newu->path visible to anyone who gets newu->addr + * by smp_load_acquire(). IOW, the same warranties + * as for unix_sock instances bound in unix_bind() or + * in unix_autobind(). + */ if (otheru->path.dentry) { path_get(&otheru->path); newu->path = otheru->path; } + refcount_inc(&otheru->addr->refcnt); + smp_store_release(&newu->addr, otheru->addr); /* Set credentials */ copy_peercred(sk, other); @@ -1455,7 +1469,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer) { struct sock *sk = sock->sk; - struct unix_sock *u; + struct unix_address *addr; DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr); int err = 0; @@ -1470,19 +1484,15 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_ sock_hold(sk); } - u = unix_sk(sk); - unix_state_lock(sk); - if (!u->addr) { + addr = smp_load_acquire(&unix_sk(sk)->addr); + if (!addr) { sunaddr->sun_family = AF_UNIX; sunaddr->sun_path[0] = 0; *uaddr_len = sizeof(short); } else { - struct unix_address *addr = u->addr; - *uaddr_len = addr->len; memcpy(sunaddr, addr->name, *uaddr_len); } - unix_state_unlock(sk); sock_put(sk); out: return err; @@ -2075,11 +2085,11 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { - struct unix_sock *u = unix_sk(sk); + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); - if (u->addr) { - msg->msg_namelen = u->addr->len; - memcpy(msg->msg_name, u->addr->name, u->addr->len); + if (addr) { + msg->msg_namelen = addr->len; + memcpy(msg->msg_name, addr->name, addr->len); } } @@ -2583,15 +2593,14 @@ static int unix_open_file(struct sock *sk) if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; - unix_state_lock(sk); + if (!smp_load_acquire(&unix_sk(sk)->addr)) + return -ENOENT; + path = unix_sk(sk)->path; - if (!path.dentry) { - unix_state_unlock(sk); + if (!path.dentry) return -ENOENT; - } path_get(&path); - unix_state_unlock(sk); fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) @@ -2831,7 +2840,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) (s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING), sock_i_ino(s)); - if (u->addr) { + if (u->addr) { // under unix_table_lock here int i, len; seq_putc(seq, ' '); diff --git a/net/unix/diag.c b/net/unix/diag.c index 384c84e83462..3183d9b8ab33 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -10,7 +10,8 @@ static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb) { - struct unix_address *addr = unix_sk(sk)->addr; + /* might or might not have unix_table_lock */ + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); if (!addr) return 0; diff --git a/security/lsm_audit.c b/security/lsm_audit.c index 67703dbe29ea..3a8916aa73c4 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -321,6 +321,7 @@ static void dump_common_audit_data(struct audit_buffer *ab, if (a->u.net->sk) { struct sock *sk = a->u.net->sk; struct unix_sock *u; + struct unix_address *addr; int len = 0; char *p = NULL; @@ -351,14 +352,15 @@ static void dump_common_audit_data(struct audit_buffer *ab, #endif case AF_UNIX: u = unix_sk(sk); + addr = smp_load_acquire(&u->addr); + if (!addr) + break; if (u->path.dentry) { audit_log_d_path(ab, " path=", &u->path); break; } - if (!u->addr) - break; - len = u->addr->len-sizeof(short); - p = &u->addr->name->sun_path[0]; + len = addr->len-sizeof(short); + p = &addr->name->sun_path[0]; audit_log_format(ab, " path="); if (*p) audit_log_untrustedstring(ab, p); -- GitLab From ddcc3253f8dd3dae3b131e319fe8217a687a2cd2 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 20 Feb 2019 00:15:30 +0100 Subject: [PATCH 0224/1128] ipvlan: disallow userns cap_net_admin to change global mode/flags [ Upstream commit 7cc9f7003a969d359f608ebb701d42cafe75b84a ] When running Docker with userns isolation e.g. --userns-remap="default" and spawning up some containers with CAP_NET_ADMIN under this realm, I noticed that link changes on ipvlan slave device inside that container can affect all devices from this ipvlan group which are in other net namespaces where the container should have no permission to make changes to, such as the init netns, for example. This effectively allows to undo ipvlan private mode and switch globally to bridge mode where slaves can communicate directly without going through hostns, or it allows to switch between global operation mode (l2/l3/l3s) for everyone bound to the given ipvlan master device. libnetwork plugin here is creating an ipvlan master and ipvlan slave in hostns and a slave each that is moved into the container's netns upon creation event. * In hostns: # ip -d a [...] 8: cilium_host@bond0: mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000 link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535 ipvlan mode l3 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535 inet 10.41.0.1/32 scope link cilium_host valid_lft forever preferred_lft forever [...] * Spawn container & change ipvlan mode setting inside of it: # docker run -dt --cap-add=NET_ADMIN --network cilium-net --name client -l app=test cilium/netperf 9fff485d69dcb5ce37c9e33ca20a11ccafc236d690105aadbfb77e4f4170879c # docker exec -ti client ip -d a [...] 10: cilium0@if4: mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000 link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535 ipvlan mode l3 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535 inet 10.41.197.43/32 brd 10.41.197.43 scope global cilium0 valid_lft forever preferred_lft forever # docker exec -ti client ip link change link cilium0 name cilium0 type ipvlan mode l2 # docker exec -ti client ip -d a [...] 10: cilium0@if4: mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000 link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535 ipvlan mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535 inet 10.41.197.43/32 brd 10.41.197.43 scope global cilium0 valid_lft forever preferred_lft forever * In hostns (mode switched to l2): # ip -d a [...] 8: cilium_host@bond0: mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000 link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535 ipvlan mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535 inet 10.41.0.1/32 scope link cilium_host valid_lft forever preferred_lft forever [...] Same l3 -> l2 switch would also happen by creating another slave inside the container's network namespace when specifying the existing cilium0 link to derive the actual (bond0) master: # docker exec -ti client ip link add link cilium0 name cilium1 type ipvlan mode l2 # docker exec -ti client ip -d a [...] 2: cilium1@if4: mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535 ipvlan mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535 10: cilium0@if4: mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000 link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535 ipvlan mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535 inet 10.41.197.43/32 brd 10.41.197.43 scope global cilium0 valid_lft forever preferred_lft forever * In hostns: # ip -d a [...] 8: cilium_host@bond0: mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000 link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535 ipvlan mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535 inet 10.41.0.1/32 scope link cilium_host valid_lft forever preferred_lft forever [...] One way to mitigate it is to check CAP_NET_ADMIN permissions of the ipvlan master device's ns, and only then allow to change mode or flags for all devices bound to it. Above two cases are then disallowed after the patch. Signed-off-by: Daniel Borkmann Acked-by: Mahesh Bandewar Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ipvlan/ipvlan_main.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 2222ed63d055..d629dddb0e89 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -482,7 +482,12 @@ static int ipvlan_nl_changelink(struct net_device *dev, struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int err = 0; - if (data && data[IFLA_IPVLAN_MODE]) { + if (!data) + return 0; + if (!ns_capable(dev_net(ipvlan->phy_dev)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + if (data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, nmode); @@ -551,6 +556,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct ipvl_dev *tmp = netdev_priv(phy_dev); phy_dev = tmp->phy_dev; + if (!ns_capable(dev_net(phy_dev)->user_ns, CAP_NET_ADMIN)) + return -EPERM; } else if (!netif_is_ipvlan_port(phy_dev)) { err = ipvlan_port_create(phy_dev); if (err < 0) -- GitLab From 578aa457dad7831a420592890141cd6de6465006 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 15 Mar 2019 09:14:10 +0100 Subject: [PATCH 0225/1128] perf/x86: Fixup typo in stub functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f764c58b7faa26f5714e6907f892abc2bc0de4f8 upstream. Guenter reported a build warning for CONFIG_CPU_SUP_INTEL=n: > With allmodconfig-CONFIG_CPU_SUP_INTEL, this patch results in: > > In file included from arch/x86/events/amd/core.c:8:0: > arch/x86/events/amd/../perf_event.h:1036:45: warning: ‘struct cpu_hw_event’ declared inside parameter list will not be visible outside of this definition or declaration > static inline int intel_cpuc_prepare(struct cpu_hw_event *cpuc, int cpu) While harmless (an unsed pointer is an unused pointer, no matter the type) it needs fixing. Reported-by: Guenter Roeck Signed-off-by: Peter Zijlstra (Intel) Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@vger.kernel.org Fixes: d01b1f96a82e ("perf/x86/intel: Make cpuc allocations consistent") Link: http://lkml.kernel.org/r/20190315081410.GR5996@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/perf_event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 9702f4ed4748..84b3841c131d 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1021,12 +1021,12 @@ static inline int intel_pmu_init(void) return 0; } -static inline int intel_cpuc_prepare(struct cpu_hw_event *cpuc, int cpu) +static inline int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) { return 0; } -static inline void intel_cpuc_finish(struct cpu_hw_event *cpuc) +static inline void intel_cpuc_finish(struct cpu_hw_events *cpuc) { } -- GitLab From 18d48bd413830eb2df22d06d0573f499185d935c Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Tue, 26 Feb 2019 13:38:16 +0900 Subject: [PATCH 0226/1128] ALSA: bebob: use more identical mod_alias for Saffire Pro 10 I/O against Liquid Saffire 56 commit 7dc661bd8d3261053b69e4e2d0050cd1ee540fc1 upstream. ALSA bebob driver has an entry for Focusrite Saffire Pro 10 I/O. The entry matches vendor_id in root directory and model_id in unit directory of configuration ROM for IEEE 1394 bus. On the other hand, configuration ROM of Focusrite Liquid Saffire 56 has the same vendor_id and model_id. This device is an application of TCAT Dice (TCD2220 a.k.a Dice Jr.) however ALSA bebob driver can be bound to it randomly instead of ALSA dice driver. At present, drivers in ALSA firewire stack can not handle this situation appropriately. This commit uses more identical mod_alias for Focusrite Saffire Pro 10 I/O in ALSA bebob driver. $ python2 crpp < /sys/bus/firewire/devices/fw1/config_rom ROM header and bus information block ----------------------------------------------------------------- 400 042a829d bus_info_length 4, crc_length 42, crc 33437 404 31333934 bus_name "1394" 408 f0649222 irmc 1, cmc 1, isc 1, bmc 1, pmc 0, cyc_clk_acc 100, max_rec 9 (1024), max_rom 2, gen 2, spd 2 (S400) 40c 00130e01 company_id 00130e | 410 000606e0 device_id 01000606e0 | EUI-64 00130e01000606e0 root directory ----------------------------------------------------------------- 414 0009d31c directory_length 9, crc 54044 418 04000014 hardware version 41c 0c0083c0 node capabilities per IEEE 1394 420 0300130e vendor 424 81000012 --> descriptor leaf at 46c 428 17000006 model 42c 81000016 --> descriptor leaf at 484 430 130120c2 version 434 d1000002 --> unit directory at 43c 438 d4000006 --> dependent info directory at 450 unit directory at 43c ----------------------------------------------------------------- 43c 0004707c directory_length 4, crc 28796 440 1200a02d specifier id: 1394 TA 444 13010001 version: AV/C 448 17000006 model 44c 81000013 --> descriptor leaf at 498 dependent info directory at 450 ----------------------------------------------------------------- 450 000637c7 directory_length 6, crc 14279 454 120007f5 specifier id 458 13000001 version 45c 3affffc7 (immediate value) 460 3b100000 (immediate value) 464 3cffffc7 (immediate value) 468 3d600000 (immediate value) descriptor leaf at 46c ----------------------------------------------------------------- 46c 00056f3b leaf_length 5, crc 28475 470 00000000 textual descriptor 474 00000000 minimal ASCII 478 466f6375 "Focu" 47c 73726974 "srit" 480 65000000 "e" descriptor leaf at 484 ----------------------------------------------------------------- 484 0004a165 leaf_length 4, crc 41317 488 00000000 textual descriptor 48c 00000000 minimal ASCII 490 50726f31 "Pro1" 494 30494f00 "0IO" descriptor leaf at 498 ----------------------------------------------------------------- 498 0004a165 leaf_length 4, crc 41317 49c 00000000 textual descriptor 4a0 00000000 minimal ASCII 4a4 50726f31 "Pro1" 4a8 30494f00 "0IO" $ python2 crpp < /sys/bus/firewire/devices/fw1/config_rom ROM header and bus information block ----------------------------------------------------------------- 400 040442e4 bus_info_length 4, crc_length 4, crc 17124 404 31333934 bus_name "1394" 408 e0ff8112 irmc 1, cmc 1, isc 1, bmc 0, pmc 0, cyc_clk_acc 255, max_rec 8 (512), max_rom 1, gen 1, spd 2 (S400) 40c 00130e04 company_id 00130e | 410 018001e9 device_id 04018001e9 | EUI-64 00130e04018001e9 root directory ----------------------------------------------------------------- 414 00065612 directory_length 6, crc 22034 418 0300130e vendor 41c 8100000a --> descriptor leaf at 444 420 17000006 model 424 8100000e --> descriptor leaf at 45c 428 0c0087c0 node capabilities per IEEE 1394 42c d1000001 --> unit directory at 430 unit directory at 430 ----------------------------------------------------------------- 430 000418a0 directory_length 4, crc 6304 434 1200130e specifier id 438 13000001 version 43c 17000006 model 440 8100000f --> descriptor leaf at 47c descriptor leaf at 444 ----------------------------------------------------------------- 444 00056f3b leaf_length 5, crc 28475 448 00000000 textual descriptor 44c 00000000 minimal ASCII 450 466f6375 "Focu" 454 73726974 "srit" 458 65000000 "e" descriptor leaf at 45c ----------------------------------------------------------------- 45c 000762c6 leaf_length 7, crc 25286 460 00000000 textual descriptor 464 00000000 minimal ASCII 468 4c495155 "LIQU" 46c 49445f53 "ID_S" 470 41464649 "AFFI" 474 52455f35 "RE_5" 478 36000000 "6" descriptor leaf at 47c ----------------------------------------------------------------- 47c 000762c6 leaf_length 7, crc 25286 480 00000000 textual descriptor 484 00000000 minimal ASCII 488 4c495155 "LIQU" 48c 49445f53 "ID_S" 490 41464649 "AFFI" 494 52455f35 "RE_5" 498 36000000 "6" Cc: # v3.16+ Fixes: 25784ec2d034 ("ALSA: bebob: Add support for Focusrite Saffire/SaffirePro series") Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/firewire/bebob/bebob.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/sound/firewire/bebob/bebob.c b/sound/firewire/bebob/bebob.c index de4af8a41ff0..5636e89ce5c7 100644 --- a/sound/firewire/bebob/bebob.c +++ b/sound/firewire/bebob/bebob.c @@ -474,7 +474,19 @@ static const struct ieee1394_device_id bebob_id_table[] = { /* Focusrite, SaffirePro 26 I/O */ SND_BEBOB_DEV_ENTRY(VEN_FOCUSRITE, 0x00000003, &saffirepro_26_spec), /* Focusrite, SaffirePro 10 I/O */ - SND_BEBOB_DEV_ENTRY(VEN_FOCUSRITE, 0x00000006, &saffirepro_10_spec), + { + // The combination of vendor_id and model_id is the same as the + // same as the one of Liquid Saffire 56. + .match_flags = IEEE1394_MATCH_VENDOR_ID | + IEEE1394_MATCH_MODEL_ID | + IEEE1394_MATCH_SPECIFIER_ID | + IEEE1394_MATCH_VERSION, + .vendor_id = VEN_FOCUSRITE, + .model_id = 0x000006, + .specifier_id = 0x00a02d, + .version = 0x010001, + .driver_data = (kernel_ulong_t)&saffirepro_10_spec, + }, /* Focusrite, Saffire(no label and LE) */ SND_BEBOB_DEV_ENTRY(VEN_FOCUSRITE, MODEL_FOCUSRITE_SAFFIRE_BOTH, &saffire_spec), -- GitLab From 34cdfe7845089d2762f7439825e582887994ecf5 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Tue, 26 Feb 2019 13:38:37 +0900 Subject: [PATCH 0227/1128] ALSA: firewire-motu: fix construction of PCM frame for capture direction MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f97a0944a72b26a2bece72516294e112a890f98a upstream. In data blocks of common isochronous packet for MOTU devices, PCM frames are multiplexed in a shape of '24 bit * 4 Audio Pack', described in IEC 61883-6. The frames are not aligned to quadlet. For capture PCM substream, ALSA firewire-motu driver constructs PCM frames by reading data blocks byte-by-byte. However this operation includes bug for lower byte of the PCM sample. This brings invalid content of the PCM samples. This commit fixes the bug. Reported-by: Peter Sjöberg Cc: # v4.12+ Fixes: 4641c9394010 ("ALSA: firewire-motu: add MOTU specific protocol layer") Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/firewire/motu/amdtp-motu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/firewire/motu/amdtp-motu.c b/sound/firewire/motu/amdtp-motu.c index 96f0091144bb..2cf18bedb91e 100644 --- a/sound/firewire/motu/amdtp-motu.c +++ b/sound/firewire/motu/amdtp-motu.c @@ -136,7 +136,9 @@ static void read_pcm_s32(struct amdtp_stream *s, byte = (u8 *)buffer + p->pcm_byte_offset; for (c = 0; c < channels; ++c) { - *dst = (byte[0] << 24) | (byte[1] << 16) | byte[2]; + *dst = (byte[0] << 24) | + (byte[1] << 16) | + (byte[2] << 8); byte += 3; dst++; } -- GitLab From 2a003d3333f2cb41ced9183506397ccb6a0571eb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 14 Mar 2019 14:01:14 +0100 Subject: [PATCH 0228/1128] perf/x86/intel: Fix memory corruption commit ede271b059463731cbd6dffe55ffd70d7dbe8392 upstream. Through: validate_event() x86_pmu.get_event_constraints(.idx=-1) tfa_get_event_constraints() dyn_constraint() cpuc->constraint_list[-1] is used, which is an obvious out-of-bound access. In this case, simply skip the TFA constraint code, there is no event constraint with just PMC3, therefore the code will never result in the empty set. Fixes: 400816f60c54 ("perf/x86/intel: Implement support for TSX Force Abort") Reported-by: Tony Jones Reported-by: "DSouza, Nelson" Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Tested-by: Tony Jones Tested-by: "DSouza, Nelson" Cc: eranian@google.com Cc: jolsa@redhat.com Cc: stable@kernel.org Link: https://lkml.kernel.org/r/20190314130705.441549378@infradead.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/intel/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 65a369a42338..ade4773375bc 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3262,7 +3262,7 @@ tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx, /* * Without TFA we must not use PMC3. */ - if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) { + if (!allow_tsx_force_abort && test_bit(3, c->idxmsk) && idx >= 0) { c = dyn_constraint(cpuc, c, idx); c->idxmsk64 &= ~(1ULL << 3); c->weight--; -- GitLab From 94b2a2c534f5a01fb8e93857cf376528c599502c Mon Sep 17 00:00:00 2001 From: kbuild test robot Date: Thu, 14 Mar 2019 02:42:43 +0800 Subject: [PATCH 0229/1128] perf/x86/intel: Make dev_attr_allow_tsx_force_abort static commit c634dc6bdedeb0b2c750fc611612618a85639ab2 upstream. Fixes: 400816f60c54 ("perf/x86/intel: Implement support for TSX Force Abort") Signed-off-by: kbuild test robot Signed-off-by: Thomas Gleixner Cc: "Peter Zijlstra (Intel)" Cc: kbuild-all@01.org Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Kan Liang Cc: Jiri Olsa Cc: Andi Kleen Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190313184243.GA10820@lkp-sb-ep06 Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/intel/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index ade4773375bc..dc8f8b3e6cec 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3968,7 +3968,7 @@ static struct attribute *intel_pmu_caps_attrs[] = { NULL }; -DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort); +static DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort); static struct attribute *intel_pmu_attrs[] = { &dev_attr_freeze_on_smi.attr, -- GitLab From c9794e6820ad92bc0fa47ac6a99f63f6bb477225 Mon Sep 17 00:00:00 2001 From: Xiao Ni Date: Fri, 8 Mar 2019 23:52:05 +0800 Subject: [PATCH 0230/1128] It's wrong to add len to sector_nr in raid10 reshape twice commit b761dcf1217760a42f7897c31dcb649f59b2333e upstream. In reshape_request it already adds len to sector_nr already. It's wrong to add len to sector_nr again after adding pages to bio. If there is bad block it can't copy one chunk at a time, it needs to goto read_more. Now the sector_nr is wrong. It can cause data corruption. Cc: stable@vger.kernel.org # v3.16+ Signed-off-by: Xiao Ni Signed-off-by: Song Liu Signed-off-by: Greg Kroah-Hartman --- drivers/md/raid10.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 2ce079a0b0bd..ed1b7bf1ec0e 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4495,7 +4495,6 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, atomic_inc(&r10_bio->remaining); read_bio->bi_next = NULL; generic_make_request(read_bio); - sector_nr += nr_sectors; sectors_done += nr_sectors; if (sector_nr <= last) goto read_more; -- GitLab From b384efc1fbb944255c096b9372162de4b4c2ceb7 Mon Sep 17 00:00:00 2001 From: Zha Bin Date: Tue, 8 Jan 2019 16:07:03 +0800 Subject: [PATCH 0231/1128] vhost/vsock: fix vhost vsock cid hashing inconsistent commit 7fbe078c37aba3088359c9256c1a1d0c3e39ee81 upstream. The vsock core only supports 32bit CID, but the Virtio-vsock spec define CID (dst_cid and src_cid) as u64 and the upper 32bits is reserved as zero. This inconsistency causes one bug in vhost vsock driver. The scenarios is: 0. A hash table (vhost_vsock_hash) is used to map an CID to a vsock object. And hash_min() is used to compute the hash key. hash_min() is defined as: (sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits)). That means the hash algorithm has dependency on the size of macro argument 'val'. 0. In function vhost_vsock_set_cid(), a 64bit CID is passed to hash_min() to compute the hash key when inserting a vsock object into the hash table. 0. In function vhost_vsock_get(), a 32bit CID is passed to hash_min() to compute the hash key when looking up a vsock for an CID. Because the different size of the CID, hash_min() returns different hash key, thus fails to look up the vsock object for an CID. To fix this bug, we keep CID as u64 in the IOCTLs and virtio message headers, but explicitly convert u64 to u32 when deal with the hash table and vsock core. Fixes: 834e772c8db0 ("vhost/vsock: fix use-after-free in network stack callers") Link: https://github.com/stefanha/virtio/blob/vsock/trunk/content.tex Signed-off-by: Zha Bin Reviewed-by: Liu Jiang Reviewed-by: Stefan Hajnoczi Acked-by: Jason Wang Signed-off-by: David S. Miller Signed-off-by: Shengjing Zhu Signed-off-by: Greg Kroah-Hartman --- drivers/vhost/vsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 831758335e2c..d0cf3d5aa570 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -642,7 +642,7 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid) hash_del_rcu(&vsock->hash); vsock->guest_cid = guest_cid; - hash_add_rcu(vhost_vsock_hash, &vsock->hash, guest_cid); + hash_add_rcu(vhost_vsock_hash, &vsock->hash, vsock->guest_cid); spin_unlock_bh(&vhost_vsock_lock); return 0; -- GitLab From 5726a8d0f1958af80ad8e514bc2c18d213e739b7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 19 Mar 2019 13:13:25 +0100 Subject: [PATCH 0232/1128] Linux 4.14.107 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index ecc3a2a82a49..e3e2121718a8 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 106 +SUBLEVEL = 107 EXTRAVERSION = NAME = Petit Gorille -- GitLab From cfbe30be85c4eb6743fd6eb05dcbf8cb1a3e1d0a Mon Sep 17 00:00:00 2001 From: Samer Xie Date: Mon, 4 Mar 2019 15:30:44 +0800 Subject: [PATCH 0233/1128] sched/fair: fix energy compute when a cluster is only a cpu core in multi-cluster system when a cluster is only a cpu core in multi-cluster system, compute_energy will only compute cpu core power(MC domain),but the power consumed by the DIE domain is not computed. fix the bug,end compute energy in DIE domain. Bug: 120440300 Signed-off-by: Samer Xie --- kernel/sched/fair.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7fb7ec0ef868..91ea9af6c1c4 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6358,7 +6358,8 @@ static int compute_energy(struct energy_env *eenv) cpu_count--; } - if (cpumask_equal(sched_group_span(sg), sched_group_span(eenv->sg_top))) + if (cpumask_equal(sched_group_span(sg), sched_group_span(eenv->sg_top)) && + sd->child) goto next_cpu; } while (sg = sg->next, sg != sd->groups); -- GitLab From 1d54f31271140e2f6c21caed39589bbf6c1d3f7e Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:04 -0700 Subject: [PATCH 0234/1128] UPSTREAM: mm: workingset: tell cache transitions from workingset thrashing Refaults happen during transitions between workingsets as well as in-place thrashing. Knowing the difference between the two has a range of applications, including measuring the impact of memory shortage on the system performance, as well as the ability to smarter balance pressure between the filesystem cache and the swap-backed workingset. During workingset transitions, inactive cache refaults and pushes out established active cache. When that active cache isn't stale, however, and also ends up refaulting, that's bonafide thrashing. Introduce a new page flag that tells on eviction whether the page has been active or not in its lifetime. This bit is then stored in the shadow entry, to classify refaults as transitioning or thrashing. How many page->flags does this leave us with on 32-bit? 20 bits are always page flags 21 if you have an MMU 23 with the zone bits for DMA, Normal, HighMem, Movable 29 with the sparsemem section bits 30 if PAE is enabled 31 with this patch. So on 32-bit PAE, that leaves 1 bit for distinguishing two NUMA nodes. If that's not enough, the system can switch to discontigmem and re-gain the 6 or 7 sparsemem section bits. Link: http://lkml.kernel.org/r/20180828172258.3185-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 8508cf3ffad4defa202b303e5b6379efc4cd9054) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I71df060dce5590a3c654f9a0e8e54deeb74b64c2 Signed-off-by: Suren Baghdasaryan --- include/linux/mmzone.h | 1 + include/linux/page-flags.h | 5 +- include/linux/swap.h | 2 +- include/trace/events/mmflags.h | 1 + mm/filemap.c | 9 ++-- mm/huge_memory.c | 1 + mm/migrate.c | 2 + mm/swap_state.c | 1 + mm/vmscan.c | 1 + mm/vmstat.c | 1 + mm/workingset.c | 95 ++++++++++++++++++++++------------ 11 files changed, 77 insertions(+), 42 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f679f5268467..71b7a8bc82ea 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -163,6 +163,7 @@ enum node_stat_item { NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_RESTORE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 584b14c774c1..6900ad07554b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -74,13 +74,14 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ - PG_error, PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, + PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ + PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, @@ -273,6 +274,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) +PAGEFLAG(Workingset, workingset, PF_HEAD) + TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 4fd1ab9565ba..1db5eca571d3 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -304,7 +304,7 @@ struct vma_swap_readahead { /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); -bool workingset_refault(void *shadow); +void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); void workingset_update_node(struct radix_tree_node *node, void *private); diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 72162f3a03fa..40b9cc3bfaf9 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -89,6 +89,7 @@ {1UL << PG_dirty, "dirty" }, \ {1UL << PG_lru, "lru" }, \ {1UL << PG_active, "active" }, \ + {1UL << PG_workingset, "workingset" }, \ {1UL << PG_slab, "slab" }, \ {1UL << PG_owner_priv_1, "owner_priv_1" }, \ {1UL << PG_arch_1, "arch_1" }, \ diff --git a/mm/filemap.c b/mm/filemap.c index 1578319813e6..c8a0393b8edf 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -815,12 +815,9 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ - if (!(gfp_mask & __GFP_WRITE) && - shadow && workingset_refault(shadow)) { - SetPageActive(page); - workingset_activation(page); - } else - ClearPageActive(page); + WARN_ON_ONCE(PageActive(page)); + if (!(gfp_mask & __GFP_WRITE) && shadow) + workingset_refault(page, shadow); lru_cache_add(page); } return ret; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 930f2aa3bb4d..4ef967ad24ec 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2327,6 +2327,7 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_mlocked) | (1L << PG_uptodate) | (1L << PG_active) | + (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | (1L << PG_dirty))); diff --git a/mm/migrate.c b/mm/migrate.c index 877269339fa7..ee56839be7bf 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -673,6 +673,8 @@ void migrate_page_states(struct page *newpage, struct page *page) SetPageActive(newpage); } else if (TestClearPageUnevictable(page)) SetPageUnevictable(newpage); + if (PageWorkingset(page)) + SetPageWorkingset(newpage); if (PageChecked(page)) SetPageChecked(newpage); if (PageMappedToDisk(page)) diff --git a/mm/swap_state.c b/mm/swap_state.c index 326439428daf..3931379fac4d 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -435,6 +435,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * Initiate read into locked page and return. */ + SetPageWorkingset(new_page); lru_cache_add_anon(new_page); *new_page_allocated = true; return new_page; diff --git a/mm/vmscan.c b/mm/vmscan.c index 9734e62654fa..06a7d1605a5d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2056,6 +2056,7 @@ static void shrink_active_list(unsigned long nr_to_scan, } ClearPageActive(page); /* we are de-activating */ + SetPageWorkingset(page); list_add(&page->lru, &l_inactive); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 6389e876c7a7..efab0fca0bb7 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1074,6 +1074,7 @@ const char * const vmstat_text[] = { "nr_isolated_file", "workingset_refault", "workingset_activate", + "workingset_restore", "workingset_nodereclaim", "nr_anon_pages", "nr_mapped", diff --git a/mm/workingset.c b/mm/workingset.c index b997c9de28f6..808a69a4a9ef 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -121,7 +121,7 @@ * the only thing eating into inactive list space is active pages. * * - * Activating refaulting pages + * Refaulting inactive pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given @@ -134,6 +134,10 @@ * used less frequently than the refaulting page - or even not used at * all anymore. * + * That means if inactive cache is refaulting with a suitable refault + * distance, we assume the cache workingset is transitioning and put + * pressure on the current active list. + * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. @@ -141,6 +145,14 @@ * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * + * Refaulting active pages + * + * If on the other hand the refaulting pages have recently been + * deactivated, it means that the active list is no longer protecting + * actively used cache from reclaim. The cache is NOT transitioning to + * a different workingset; the existing workingset is thrashing in the + * space allocated to the page cache. + * * * Implementation * @@ -156,8 +168,7 @@ */ #define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \ - NODES_SHIFT + \ - MEM_CGROUP_ID_SHIFT) + 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* @@ -170,23 +181,28 @@ */ static unsigned int bucket_order __read_mostly; -static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction) +static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, + bool workingset) { eviction >>= bucket_order; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; + eviction = (eviction << 1) | workingset; eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, - unsigned long *evictionp) + unsigned long *evictionp, bool *workingsetp) { unsigned long entry = (unsigned long)shadow; int memcgid, nid; + bool workingset; entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; + workingset = entry & 1; + entry >>= 1; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); @@ -195,6 +211,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, *memcgidp = memcgid; *pgdat = NODE_DATA(nid); *evictionp = entry << bucket_order; + *workingsetp = workingset; } /** @@ -207,8 +224,8 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, */ void *workingset_eviction(struct address_space *mapping, struct page *page) { - struct mem_cgroup *memcg = page_memcg(page); struct pglist_data *pgdat = page_pgdat(page); + struct mem_cgroup *memcg = page_memcg(page); int memcgid = mem_cgroup_id(memcg); unsigned long eviction; struct lruvec *lruvec; @@ -220,30 +237,30 @@ void *workingset_eviction(struct address_space *mapping, struct page *page) lruvec = mem_cgroup_lruvec(pgdat, memcg); eviction = atomic_long_inc_return(&lruvec->inactive_age); - return pack_shadow(memcgid, pgdat, eviction); + return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } /** * workingset_refault - evaluate the refault of a previously evicted page + * @page: the freshly allocated replacement page * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously * evicted page in the context of the node it was allocated in. - * - * Returns %true if the page should be activated, %false otherwise. */ -bool workingset_refault(void *shadow) +void workingset_refault(struct page *page, void *shadow) { unsigned long refault_distance; + struct pglist_data *pgdat; unsigned long active_file; struct mem_cgroup *memcg; unsigned long eviction; struct lruvec *lruvec; unsigned long refault; - struct pglist_data *pgdat; + bool workingset; int memcgid; - unpack_shadow(shadow, &memcgid, &pgdat, &eviction); + unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); rcu_read_lock(); /* @@ -263,41 +280,51 @@ bool workingset_refault(void *shadow) * configurations instead. */ memcg = mem_cgroup_from_id(memcgid); - if (!mem_cgroup_disabled() && !memcg) { - rcu_read_unlock(); - return false; - } + if (!mem_cgroup_disabled() && !memcg) + goto out; lruvec = mem_cgroup_lruvec(pgdat, memcg); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES); /* - * The unsigned subtraction here gives an accurate distance - * across inactive_age overflows in most cases. + * Calculate the refault distance * - * There is a special case: usually, shadow entries have a - * short lifetime and are either refaulted or reclaimed along - * with the inode before they get too old. But it is not - * impossible for the inactive_age to lap a shadow entry in - * the field, which can then can result in a false small - * refault distance, leading to a false activation should this - * old entry actually refault again. However, earlier kernels - * used to deactivate unconditionally with *every* reclaim - * invocation for the longest time, so the occasional - * inappropriate activation leading to pressure on the active - * list is not a problem. + * The unsigned subtraction here gives an accurate distance + * across inactive_age overflows in most cases. There is a + * special case: usually, shadow entries have a short lifetime + * and are either refaulted or reclaimed along with the inode + * before they get too old. But it is not impossible for the + * inactive_age to lap a shadow entry in the field, which can + * then result in a false small refault distance, leading to a + * false activation should this old entry actually refault + * again. However, earlier kernels used to deactivate + * unconditionally with *every* reclaim invocation for the + * longest time, so the occasional inappropriate activation + * leading to pressure on the active list is not a problem. */ refault_distance = (refault - eviction) & EVICTION_MASK; inc_lruvec_state(lruvec, WORKINGSET_REFAULT); - if (refault_distance <= active_file) { - inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); - rcu_read_unlock(); - return true; + /* + * Compare the distance to the existing workingset size. We + * don't act on pages that couldn't stay resident even if all + * the memory was available to the page cache. + */ + if (refault_distance > active_file) + goto out; + + SetPageActive(page); + atomic_long_inc(&lruvec->inactive_age); + inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); + + /* Page was active prior to eviction */ + if (workingset) { + SetPageWorkingset(page); + inc_lruvec_state(lruvec, WORKINGSET_RESTORE); } +out: rcu_read_unlock(); - return false; } /** -- GitLab From c6c21fac50f5ba738fc05c8f19d0757d4ffa424d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:08 -0700 Subject: [PATCH 0235/1128] UPSTREAM: delayacct: track delays from thrashing cache pages Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit b1d29ba82cf2bc784f4c963ddd6a2cf29e229b33) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I259f693987cf04e6a52ee7e8accf55a17e0de005 Signed-off-by: Suren Baghdasaryan --- include/linux/delayacct.h | 23 +++++++++++++++++++++++ include/uapi/linux/taskstats.h | 6 +++++- kernel/delayacct.c | 15 +++++++++++++++ mm/filemap.c | 11 +++++++++++ tools/accounting/getdelays.c | 8 +++++++- 5 files changed, 61 insertions(+), 2 deletions(-) diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 31c865d1842e..577d1b25fccd 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -57,7 +57,12 @@ struct task_delay_info { u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ + + u64 thrashing_start; + u64 thrashing_delay; /* wait for thrashing page */ + u32 freepages_count; /* total count of memory reclaim */ + u32 thrashing_count; /* total count of thrash waits */ }; #endif @@ -76,6 +81,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); +extern void __delayacct_thrashing_start(void); +extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { @@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } +static inline void delayacct_thrashing_start(void) +{ + if (current->delays) + __delayacct_thrashing_start(); +} + +static inline void delayacct_thrashing_end(void) +{ + if (current->delays) + __delayacct_thrashing_end(); +} + #else static inline void delayacct_set_flag(int flag) {} @@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} +static inline void delayacct_thrashing_start(void) +{} +static inline void delayacct_thrashing_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index b7aa7bb2349f..5e8ca16a9079 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 8 +#define TASKSTATS_VERSION 9 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -164,6 +164,10 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; + + /* Delay waiting for thrashing page */ + __u64 thrashing_count; + __u64 thrashing_delay_total; }; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index ca8ac2824f0b..2a12b988c717 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -135,9 +135,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; tmp = d->freepages_delay_total + tsk->delays->freepages_delay; d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; + tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; + d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; + d->thrashing_count += tsk->delays->thrashing_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -169,3 +172,15 @@ void __delayacct_freepages_end(void) ¤t->delays->freepages_count); } +void __delayacct_thrashing_start(void) +{ + current->delays->thrashing_start = ktime_get_ns(); +} + +void __delayacct_thrashing_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->thrashing_start, + ¤t->delays->thrashing_delay, + ¤t->delays->thrashing_count); +} diff --git a/mm/filemap.c b/mm/filemap.c index c8a0393b8edf..2b0920b8188c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "internal.h" #define CREATE_TRACE_POINTS @@ -973,8 +974,15 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; + bool thrashing = false; int ret = 0; + if (bit_nr == PG_locked && !PageSwapBacked(page) && + !PageUptodate(page) && PageWorkingset(page)) { + delayacct_thrashing_start(); + thrashing = true; + } + init_wait(wait); wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0; wait->func = wake_page_function; @@ -1013,6 +1021,9 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, finish_wait(q, wait); + if (thrashing) + delayacct_thrashing_end(); + /* * A signal could leave PageWaiters set. Clearing it here if * !waitqueue_active would be possible (by open-coding finish_wait), diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 9f420d98b5fb..8cb504d30384 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -203,6 +203,8 @@ static void print_delayacct(struct taskstats *t) "SWAP %15s%15s%15s\n" " %15llu%15llu%15llums\n" "RECLAIM %12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "THRASHING%12s%15s%15s\n" " %15llu%15llu%15llums\n", "count", "real total", "virtual total", "delay total", "delay average", @@ -222,7 +224,11 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->freepages_count, (unsigned long long)t->freepages_delay_total, - average_ms(t->freepages_delay_total, t->freepages_count)); + average_ms(t->freepages_delay_total, t->freepages_count), + "count", "delay total", "delay average", + (unsigned long long)t->thrashing_count, + (unsigned long long)t->thrashing_delay_total, + average_ms(t->thrashing_delay_total, t->thrashing_count)); } static void task_context_switch_counts(struct taskstats *t) -- GitLab From d900bee055bf92861df06e18070173dc972fadc6 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:11 -0700 Subject: [PATCH 0236/1128] BACKPORT: sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD There are several definitions of those functions/macros in places that mess with fixed-point load averages. Provide an official version. [akpm@linux-foundation.org: fix missed conversion in block/blk-iolatency.c] Link: http://lkml.kernel.org/r/20180828172258.3185-5-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 8508cf3ffad4defa202b303e5b6379efc4cd9054) Conflicts: block/blk-iolatency.c (1. skipped changes in block/blk-iolatency.c as file does not exist in 4.14) Bug: 127712811 Test: lmkd in PSI mode Change-Id: Ifb7e12280b2aa4d379df29e24bbeab3e82a0bff8 Signed-off-by: Suren Baghdasaryan --- .../platforms/cell/cpufreq_spudemand.c | 2 +- arch/powerpc/platforms/cell/spufs/sched.c | 9 +++----- arch/s390/appldata/appldata_os.c | 4 ---- drivers/cpuidle/governors/menu.c | 4 ---- fs/proc/loadavg.c | 3 --- include/linux/sched/loadavg.h | 21 +++++++++++++++---- kernel/debug/kdb/kdb_main.c | 7 +------ kernel/sched/loadavg.c | 15 ------------- 8 files changed, 22 insertions(+), 43 deletions(-) diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c index 882944c36ef5..5d8e8b6bb1cc 100644 --- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c +++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c @@ -49,7 +49,7 @@ static int calc_freq(struct spu_gov_info_struct *info) cpu = info->policy->cpu; busy_spus = atomic_read(&cbe_spu_info[cpu_to_node(cpu)].busy_spus); - CALC_LOAD(info->busy_spus, EXP, busy_spus * FIXED_1); + info->busy_spus = calc_load(info->busy_spus, EXP, busy_spus * FIXED_1); pr_debug("cpu %d: busy_spus=%d, info->busy_spus=%ld\n", cpu, busy_spus, info->busy_spus); diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 1fbb5da17dd2..509cf6709131 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -987,9 +987,9 @@ static void spu_calc_load(void) unsigned long active_tasks; /* fixed-point */ active_tasks = count_active_contexts() * FIXED_1; - CALC_LOAD(spu_avenrun[0], EXP_1, active_tasks); - CALC_LOAD(spu_avenrun[1], EXP_5, active_tasks); - CALC_LOAD(spu_avenrun[2], EXP_15, active_tasks); + spu_avenrun[0] = calc_load(spu_avenrun[0], EXP_1, active_tasks); + spu_avenrun[1] = calc_load(spu_avenrun[1], EXP_5, active_tasks); + spu_avenrun[2] = calc_load(spu_avenrun[2], EXP_15, active_tasks); } static void spusched_wake(unsigned long data) @@ -1071,9 +1071,6 @@ void spuctx_switch_state(struct spu_context *ctx, } } -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static int show_spu_loadavg(struct seq_file *s, void *private) { int a, b, c; diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c index 45b3178200ab..a8aac17e1e82 100644 --- a/arch/s390/appldata/appldata_os.c +++ b/arch/s390/appldata/appldata_os.c @@ -24,10 +24,6 @@ #include "appldata.h" - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - /* * OS data * diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 58c103b5892b..55f55aec6ccb 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -133,10 +133,6 @@ struct menu_device { int interval_ptr; }; - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static inline int get_loadavg(unsigned long load) { return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10; diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c index 9bc5c58c00ee..b3c0475f88de 100644 --- a/fs/proc/loadavg.c +++ b/fs/proc/loadavg.c @@ -10,9 +10,6 @@ #include #include -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static int loadavg_proc_show(struct seq_file *m, void *v) { unsigned long avnrun[3]; diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index 80bc84ba5d2a..cc9cc62bb1f8 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -22,10 +22,23 @@ extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); #define EXP_5 2014 /* 1/exp(5sec/5min) */ #define EXP_15 2037 /* 1/exp(5sec/15min) */ -#define CALC_LOAD(load,exp,n) \ - load *= exp; \ - load += n*(FIXED_1-exp); \ - load >>= FSHIFT; +/* + * a1 = a0 * e + a * (1 - e) + */ +static inline unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; +} + +#define LOAD_INT(x) ((x) >> FSHIFT) +#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) extern void calc_global_load(unsigned long ticks); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 993db6b2348e..3083df2a783e 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2586,16 +2586,11 @@ static int kdb_summary(int argc, const char **argv) } kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60); - /* lifted from fs/proc/proc_misc.c::loadavg_read_proc() */ - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) kdb_printf("load avg %ld.%02ld %ld.%02ld %ld.%02ld\n", LOAD_INT(val.loads[0]), LOAD_FRAC(val.loads[0]), LOAD_INT(val.loads[1]), LOAD_FRAC(val.loads[1]), LOAD_INT(val.loads[2]), LOAD_FRAC(val.loads[2])); -#undef LOAD_INT -#undef LOAD_FRAC + /* Display in kilobytes */ #define K(x) ((x) << (PAGE_SHIFT - 10)) kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n" diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 89a989e4d758..d37eb9fe8aa8 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -95,21 +95,6 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) return delta; } -/* - * a1 = a0 * e + a * (1 - e) - */ -static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) -{ - unsigned long newload; - - newload = load * exp + active * (FIXED_1 - exp); - if (active >= load) - newload += FIXED_1-1; - - return newload / FIXED_1; -} - #ifdef CONFIG_NO_HZ_COMMON /* * Handle NO_HZ for the global load-average. -- GitLab From 2015a58b7a348e1225e0ba90a4a89ac24ff651e8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:16 -0700 Subject: [PATCH 0237/1128] UPSTREAM: sched: loadavg: make calc_load_n() public It's going to be used in a later patch. Keep the churn separate. Link: http://lkml.kernel.org/r/20180828172258.3185-6-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 5c54f5b9edb1aa2eabbb1091c458f1b6776a1896) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I50e0cb0dbf20ced329a484493f82ff69ca1ae97a Signed-off-by: Suren Baghdasaryan --- include/linux/sched/loadavg.h | 3 + kernel/sched/loadavg.c | 138 +++++++++++++++++----------------- 2 files changed, 72 insertions(+), 69 deletions(-) diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index cc9cc62bb1f8..4859bea47a7b 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -37,6 +37,9 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) return newload / FIXED_1; } +extern unsigned long calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n); + #define LOAD_INT(x) ((x) >> FSHIFT) #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index d37eb9fe8aa8..73157e882918 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -95,6 +95,75 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) return delta; } +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. + */ +static unsigned long +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) +{ + unsigned long result = 1UL << frac_bits; + + if (n) { + for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + } + + return result; +} + +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); +} + #ifdef CONFIG_NO_HZ_COMMON /* * Handle NO_HZ for the global load-average. @@ -214,75 +283,6 @@ static long calc_load_nohz_fold(void) return delta; } -/** - * fixed_power_int - compute: x^n, in O(log n) time - * - * @x: base of the power - * @frac_bits: fractional bits of @x - * @n: power to raise @x to. - * - * By exploiting the relation between the definition of the natural power - * function: x^n := x*x*...*x (x multiplied by itself for n times), and - * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, - * (where: n_i \elem {0, 1}, the binary vector representing n), - * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is - * of course trivially computable in O(log_2 n), the length of our binary - * vector. - */ -static unsigned long -fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) -{ - unsigned long result = 1UL << frac_bits; - - if (n) { - for (;;) { - if (n & 1) { - result *= x; - result += 1UL << (frac_bits - 1); - result >>= frac_bits; - } - n >>= 1; - if (!n) - break; - x *= x; - x += 1UL << (frac_bits - 1); - x >>= frac_bits; - } - } - - return result; -} - -/* - * a1 = a0 * e + a * (1 - e) - * - * a2 = a1 * e + a * (1 - e) - * = (a0 * e + a * (1 - e)) * e + a * (1 - e) - * = a0 * e^2 + a * (1 - e) * (1 + e) - * - * a3 = a2 * e + a * (1 - e) - * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) - * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) - * - * ... - * - * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] - * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) - * = a0 * e^n + a * (1 - e^n) - * - * [1] application of the geometric series: - * - * n 1 - x^(n+1) - * S_n := \Sum x^i = ------------- - * i=0 1 - x - */ -static unsigned long -calc_load_n(unsigned long load, unsigned long exp, - unsigned long active, unsigned int n) -{ - return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); -} - /* * NO_HZ can leave us missing all per-cpu ticks calling * calc_load_fold_active(), but since a NO_HZ CPU folds its delta into -- GitLab From 3727902dc52312e4837de9800a1f2a99fbc7c3f2 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:19 -0700 Subject: [PATCH 0238/1128] UPSTREAM: sched: sched.h: make rq locking and clock functions available in stats.h kernel/sched/sched.h includes "stats.h" half-way through the file. The next patch introduces users of sched.h's rq locking functions and update_rq_clock() in kernel/sched/stats.h. Move those definitions up in the file so they are available in stats.h. Link: http://lkml.kernel.org/r/20180828172258.3185-7-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 1f351d7f7590857ea281579c26e6045b4c548ef4) Bug: 127712811 Test: lmkd in PSI mode Change-Id: Id342e0ba9a62b49e64f2ce8b87f883ea70230b2f Signed-off-by: Suren Baghdasaryan --- kernel/sched/sched.h | 164 +++++++++++++++++++++---------------------- 1 file changed, 82 insertions(+), 82 deletions(-) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c3ea9a3ad3a6..753e7c560f2e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -888,6 +888,8 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() raw_cpu_ptr(&runqueues) +extern void update_rq_clock(struct rq *rq); + static inline u64 __rq_clock_broken(struct rq *rq) { return READ_ONCE(rq->clock); @@ -999,6 +1001,86 @@ static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf) #endif } +struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(rq->lock); + +struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(p->pi_lock) + __acquires(rq->lock); + +static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); +} + +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) + __releases(rq->lock) + __releases(p->pi_lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); +} + +static inline void +rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock_irqsave(&rq->lock, rf->flags); + rq_pin_lock(rq, rf); +} + +static inline void +rq_lock_irq(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock_irq(&rq->lock); + rq_pin_lock(rq, rf); +} + +static inline void +rq_lock(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock(&rq->lock); + rq_pin_lock(rq, rf); +} + +static inline void +rq_relock(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock(&rq->lock); + rq_repin_lock(rq, rf); +} + +static inline void +rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock_irqrestore(&rq->lock, rf->flags); +} + +static inline void +rq_unlock_irq(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock_irq(&rq->lock); +} + +static inline void +rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); +} + #ifdef CONFIG_NUMA enum numa_topology_type { NUMA_DIRECT, @@ -1689,8 +1771,6 @@ static inline void rq_last_tick_reset(struct rq *rq) #endif } -extern void update_rq_clock(struct rq *rq); - extern void activate_task(struct rq *rq, struct task_struct *p, int flags); extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); @@ -1790,86 +1870,6 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } static inline void sched_avg_update(struct rq *rq) { } #endif -struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) - __acquires(rq->lock); - -struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) - __acquires(p->pi_lock) - __acquires(rq->lock); - -static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); -} - -static inline void -task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) - __releases(rq->lock) - __releases(p->pi_lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); - raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); -} - -static inline void -rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock_irqsave(&rq->lock, rf->flags); - rq_pin_lock(rq, rf); -} - -static inline void -rq_lock_irq(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock_irq(&rq->lock); - rq_pin_lock(rq, rf); -} - -static inline void -rq_lock(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock(&rq->lock); - rq_pin_lock(rq, rf); -} - -static inline void -rq_relock(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock(&rq->lock); - rq_repin_lock(rq, rf); -} - -static inline void -rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock_irqrestore(&rq->lock, rf->flags); -} - -static inline void -rq_unlock_irq(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock_irq(&rq->lock); -} - -static inline void -rq_unlock(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); -} - #ifdef CONFIG_SMP #ifdef CONFIG_PREEMPT -- GitLab From 0a48a70eb393cf96558df2c99d88bdcd5c9a34e6 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:23 -0700 Subject: [PATCH 0239/1128] UPSTREAM: sched: introduce this_rq_lock_irq() do_sched_yield() disables IRQs, looks up this_rq() and locks it. The next patch is adding another site with the same pattern, so provide a convenience function for it. Link: http://lkml.kernel.org/r/20180828172258.3185-8-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 246b3b3342c9b0a2e24cda2178be87bc36e1c874) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I24b42cff1624c80633f116b7cb485564f53a30a7 Signed-off-by: Suren Baghdasaryan --- kernel/sched/core.c | 4 +--- kernel/sched/sched.h | 12 ++++++++++++ 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c52663838539..9483a8046a5c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4882,9 +4882,7 @@ SYSCALL_DEFINE0(sched_yield) struct rq_flags rf; struct rq *rq; - local_irq_disable(); - rq = this_rq(); - rq_lock(rq, &rf); + rq = this_rq_lock_irq(&rf); schedstat_inc(rq->yld_count); current->sched_class->yield_task(rq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 753e7c560f2e..4e6ca7632691 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1081,6 +1081,18 @@ rq_unlock(struct rq *rq, struct rq_flags *rf) raw_spin_unlock(&rq->lock); } +static inline struct rq * +this_rq_lock_irq(struct rq_flags *rf) + __acquires(rq->lock) +{ + struct rq *rq; + + local_irq_disable(); + rq = this_rq(); + rq_lock(rq, rf); + return rq; +} + #ifdef CONFIG_NUMA enum numa_topology_type { NUMA_DIRECT, -- GitLab From 94eab674ff739fe42cf77d4d3e86a564a283e768 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:27 -0700 Subject: [PATCH 0240/1128] UPSTREAM: psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit eb414681d5a07d28d2ff90dc05f69ec6b232ebd2) Bug: 127712811 Test: lmkd in PSI mode Change-Id: Id00d23c977169b0c4636d92016fc1fee0274be05 Signed-off-by: Suren Baghdasaryan --- Documentation/accounting/psi.txt | 64 +++ include/linux/psi.h | 28 ++ include/linux/psi_types.h | 92 +++++ include/linux/sched.h | 10 + init/Kconfig | 15 + kernel/fork.c | 4 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 12 +- kernel/sched/psi.c | 657 +++++++++++++++++++++++++++++++ kernel/sched/sched.h | 2 + kernel/sched/stats.h | 86 ++++ mm/compaction.c | 5 + mm/filemap.c | 15 +- mm/page_alloc.c | 9 + mm/vmscan.c | 9 + 15 files changed, 1003 insertions(+), 6 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt new file mode 100644 index 000000000000..3753a82f1cf5 --- /dev/null +++ b/Documentation/accounting/psi.txt @@ -0,0 +1,64 @@ +================================ +PSI - Pressure Stall Information +================================ + +:Date: April, 2018 +:Author: Johannes Weiner + +When CPU, memory or IO devices are contended, workloads experience +latency spikes, throughput losses, and run the risk of OOM kills. + +Without an accurate measure of such contention, users are forced to +either play it safe and under-utilize their hardware resources, or +roll the dice and frequently suffer the disruptions resulting from +excessive overcommit. + +The psi feature identifies and quantifies the disruptions caused by +such resource crunches and the time impact it has on complex workloads +or even entire systems. + +Having an accurate measure of productivity losses caused by resource +scarcity aids users in sizing workloads to hardware--or provisioning +hardware according to workload demand. + +As psi aggregates this information in realtime, systems can be managed +dynamically using techniques such as load shedding, migrating jobs to +other systems or data centers, or strategically pausing or killing low +priority or restartable batch jobs. + +This allows maximizing hardware utilization without sacrificing +workload health or risking major disruptions such as OOM kills. + +Pressure interface +================== + +Pressure information for each resource is exported through the +respective file in /proc/pressure/ -- cpu, memory, and io. + +The format for CPU is as such: + +some avg10=0.00 avg60=0.00 avg300=0.00 total=0 + +and for memory and IO: + +some avg10=0.00 avg60=0.00 avg300=0.00 total=0 +full avg10=0.00 avg60=0.00 avg300=0.00 total=0 + +The "some" line indicates the share of time in which at least some +tasks are stalled on a given resource. + +The "full" line indicates the share of time in which all non-idle +tasks are stalled on a given resource simultaneously. In this state +actual CPU cycles are going to waste, and a workload that spends +extended time in this state is considered to be thrashing. This has +severe impact on performance, and it's useful to distinguish this +situation from a state where some tasks are stalled but the CPU is +still doing productive work. As such, time spent in this subset of the +stall state is tracked separately and exported in the "full" averages. + +The ratios are tracked as recent trends over ten, sixty, and three +hundred second windows, which gives insight into short term events as +well as medium and long term trends. The total absolute stall time is +tracked and exported as well, to allow detection of latency spikes +which wouldn't necessarily make a dent in the time averages, or to +average trends over custom time frames. diff --git a/include/linux/psi.h b/include/linux/psi.h new file mode 100644 index 000000000000..b0daf050de58 --- /dev/null +++ b/include/linux/psi.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_PSI_H +#define _LINUX_PSI_H + +#include +#include + +#ifdef CONFIG_PSI + +extern bool psi_disabled; + +void psi_init(void); + +void psi_task_change(struct task_struct *task, int clear, int set); + +void psi_memstall_tick(struct task_struct *task, int cpu); +void psi_memstall_enter(unsigned long *flags); +void psi_memstall_leave(unsigned long *flags); + +#else /* CONFIG_PSI */ + +static inline void psi_init(void) {} + +static inline void psi_memstall_enter(unsigned long *flags) {} +static inline void psi_memstall_leave(unsigned long *flags) {} + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_H */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h new file mode 100644 index 000000000000..2cf422db5d18 --- /dev/null +++ b/include/linux/psi_types.h @@ -0,0 +1,92 @@ +#ifndef _LINUX_PSI_TYPES_H +#define _LINUX_PSI_TYPES_H + +#include +#include + +#ifdef CONFIG_PSI + +/* Tracked task states */ +enum psi_task_count { + NR_IOWAIT, + NR_MEMSTALL, + NR_RUNNING, + NR_PSI_TASK_COUNTS, +}; + +/* Task state bitmasks */ +#define TSK_IOWAIT (1 << NR_IOWAIT) +#define TSK_MEMSTALL (1 << NR_MEMSTALL) +#define TSK_RUNNING (1 << NR_RUNNING) + +/* Resources that workloads could be stalled on */ +enum psi_res { + PSI_IO, + PSI_MEM, + PSI_CPU, + NR_PSI_RESOURCES, +}; + +/* + * Pressure states for each resource: + * + * SOME: Stalled tasks & working tasks + * FULL: Stalled tasks & no working tasks + */ +enum psi_states { + PSI_IO_SOME, + PSI_IO_FULL, + PSI_MEM_SOME, + PSI_MEM_FULL, + PSI_CPU_SOME, + /* Only per-CPU, to weigh the CPU in the global average: */ + PSI_NONIDLE, + NR_PSI_STATES, +}; + +struct psi_group_cpu { + /* 1st cacheline updated by the scheduler */ + + /* Aggregator needs to know of concurrent changes */ + seqcount_t seq ____cacheline_aligned_in_smp; + + /* States of the tasks belonging to this group */ + unsigned int tasks[NR_PSI_TASK_COUNTS]; + + /* Period time sampling buckets for each state of interest (ns) */ + u32 times[NR_PSI_STATES]; + + /* Time of last task change in this group (rq_clock) */ + u64 state_start; + + /* 2nd cacheline updated by the aggregator */ + + /* Delta detection against the sampling buckets */ + u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp; +}; + +struct psi_group { + /* Protects data updated during an aggregation */ + struct mutex stat_lock; + + /* Per-cpu task state & time tracking */ + struct psi_group_cpu __percpu *pcpu; + + /* Periodic aggregation state */ + u64 total_prev[NR_PSI_STATES - 1]; + u64 last_update; + u64 next_update; + struct delayed_work clock_work; + + /* Total stall times and sampled pressure averages */ + u64 total[NR_PSI_STATES - 1]; + unsigned long avg[NR_PSI_STATES - 1][3]; +}; + +#else /* CONFIG_PSI */ + +struct psi_group { }; + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 44b54d648838..a5e47b74d6bf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -751,6 +752,10 @@ struct task_struct { unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_remote_wakeup:1; +#ifdef CONFIG_PSI + unsigned sched_psi_wake_requeue:1; +#endif + /* Force alignment to the next boundary: */ unsigned :0; @@ -1013,6 +1018,10 @@ struct task_struct { siginfo_t *last_siginfo; struct task_io_accounting ioac; +#ifdef CONFIG_PSI + /* Pressure stall state */ + unsigned int psi_flags; +#endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; @@ -1442,6 +1451,7 @@ extern struct pid *cad_pid; #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ diff --git a/init/Kconfig b/init/Kconfig index 37ecab2cba99..9c6c93b319ad 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -479,6 +479,21 @@ config TASK_IO_ACCOUNTING Say N if unsure. +config PSI + bool "Pressure stall information tracking" + help + Collect metrics that indicate how overcommitted the CPU, memory, + and IO capacity are in the system. + + If you say Y here, the kernel will create /proc/pressure/ with the + pressure statistics files cpu, memory, and io. These will indicate + the share of walltime in which some or all tasks in the system are + delayed due to contention of the respective resource. + + For more details see Documentation/accounting/psi.txt. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting" source "kernel/rcu/Kconfig" diff --git a/kernel/fork.c b/kernel/fork.c index ecd2c63c5e0a..5a34c13ca34b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1672,6 +1672,10 @@ static __latent_entropy struct task_struct *copy_process( p->default_timer_slack_ns = current->timer_slack_ns; +#ifdef CONFIG_PSI + p->psi_flags = 0; +#endif + task_io_accounting_init(&p->ioac); acct_clear_integrals(p); diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index b9207a9caa86..c4f150b38b52 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -30,3 +30,4 @@ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o +obj-$(CONFIG_PSI) += psi.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9483a8046a5c..f6aa84279757 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -763,8 +763,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & ENQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & ENQUEUE_RESTORE)) + if (!(flags & ENQUEUE_RESTORE)) { sched_info_queued(rq, p); + psi_enqueue(p, flags & ENQUEUE_WAKEUP); + } p->sched_class->enqueue_task(rq, p, flags); } @@ -774,8 +776,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & DEQUEUE_SAVE)) + if (!(flags & DEQUEUE_SAVE)) { sched_info_dequeued(rq, p); + psi_dequeue(p, flags & DEQUEUE_SLEEP); + } p->sched_class->dequeue_task(rq, p, flags); } @@ -2110,6 +2114,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags, sibling_count_hint); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; + psi_ttwu_dequeue(p); set_task_cpu(p, cpu); } @@ -3089,6 +3094,7 @@ void scheduler_tick(void) curr->sched_class->task_tick(rq, curr, 0); cpu_load_update_active(rq); calc_global_load_tick(rq); + psi_task_tick(rq); rq_unlock(rq, &rf); @@ -6036,6 +6042,8 @@ void __init sched_init(void) init_schedstats(); + psi_init(); + scheduler_running = 1; } diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c new file mode 100644 index 000000000000..595414599b98 --- /dev/null +++ b/kernel/sched/psi.c @@ -0,0 +1,657 @@ +/* + * Pressure stall information for CPU, memory and IO + * + * Copyright (c) 2018 Facebook, Inc. + * Author: Johannes Weiner + * + * When CPU, memory and IO are contended, tasks experience delays that + * reduce throughput and introduce latencies into the workload. Memory + * and IO contention, in addition, can cause a full loss of forward + * progress in which the CPU goes idle. + * + * This code aggregates individual task delays into resource pressure + * metrics that indicate problems with both workload health and + * resource utilization. + * + * Model + * + * The time in which a task can execute on a CPU is our baseline for + * productivity. Pressure expresses the amount of time in which this + * potential cannot be realized due to resource contention. + * + * This concept of productivity has two components: the workload and + * the CPU. To measure the impact of pressure on both, we define two + * contention states for a resource: SOME and FULL. + * + * In the SOME state of a given resource, one or more tasks are + * delayed on that resource. This affects the workload's ability to + * perform work, but the CPU may still be executing other tasks. + * + * In the FULL state of a given resource, all non-idle tasks are + * delayed on that resource such that nobody is advancing and the CPU + * goes idle. This leaves both workload and CPU unproductive. + * + * (Naturally, the FULL state doesn't exist for the CPU resource.) + * + * SOME = nr_delayed_tasks != 0 + * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0 + * + * The percentage of wallclock time spent in those compound stall + * states gives pressure numbers between 0 and 100 for each resource, + * where the SOME percentage indicates workload slowdowns and the FULL + * percentage indicates reduced CPU utilization: + * + * %SOME = time(SOME) / period + * %FULL = time(FULL) / period + * + * Multiple CPUs + * + * The more tasks and available CPUs there are, the more work can be + * performed concurrently. This means that the potential that can go + * unrealized due to resource contention *also* scales with non-idle + * tasks and CPUs. + * + * Consider a scenario where 257 number crunching tasks are trying to + * run concurrently on 256 CPUs. If we simply aggregated the task + * states, we would have to conclude a CPU SOME pressure number of + * 100%, since *somebody* is waiting on a runqueue at all + * times. However, that is clearly not the amount of contention the + * workload is experiencing: only one out of 256 possible exceution + * threads will be contended at any given time, or about 0.4%. + * + * Conversely, consider a scenario of 4 tasks and 4 CPUs where at any + * given time *one* of the tasks is delayed due to a lack of memory. + * Again, looking purely at the task state would yield a memory FULL + * pressure number of 0%, since *somebody* is always making forward + * progress. But again this wouldn't capture the amount of execution + * potential lost, which is 1 out of 4 CPUs, or 25%. + * + * To calculate wasted potential (pressure) with multiple processors, + * we have to base our calculation on the number of non-idle tasks in + * conjunction with the number of available CPUs, which is the number + * of potential execution threads. SOME becomes then the proportion of + * delayed tasks to possibe threads, and FULL is the share of possible + * threads that are unproductive due to delays: + * + * threads = min(nr_nonidle_tasks, nr_cpus) + * SOME = min(nr_delayed_tasks / threads, 1) + * FULL = (threads - min(nr_running_tasks, threads)) / threads + * + * For the 257 number crunchers on 256 CPUs, this yields: + * + * threads = min(257, 256) + * SOME = min(1 / 256, 1) = 0.4% + * FULL = (256 - min(257, 256)) / 256 = 0% + * + * For the 1 out of 4 memory-delayed tasks, this yields: + * + * threads = min(4, 4) + * SOME = min(1 / 4, 1) = 25% + * FULL = (4 - min(3, 4)) / 4 = 25% + * + * [ Substitute nr_cpus with 1, and you can see that it's a natural + * extension of the single-CPU model. ] + * + * Implementation + * + * To assess the precise time spent in each such state, we would have + * to freeze the system on task changes and start/stop the state + * clocks accordingly. Obviously that doesn't scale in practice. + * + * Because the scheduler aims to distribute the compute load evenly + * among the available CPUs, we can track task state locally to each + * CPU and, at much lower frequency, extrapolate the global state for + * the cumulative stall times and the running averages. + * + * For each runqueue, we track: + * + * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0) + * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu]) + * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0) + * + * and then periodically aggregate: + * + * tNONIDLE = sum(tNONIDLE[i]) + * + * tSOME = sum(tSOME[i] * tNONIDLE[i]) / tNONIDLE + * tFULL = sum(tFULL[i] * tNONIDLE[i]) / tNONIDLE + * + * %SOME = tSOME / period + * %FULL = tFULL / period + * + * This gives us an approximation of pressure that is practical + * cost-wise, yet way more sensitive and accurate than periodic + * sampling of the aggregate task states would be. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "sched.h" + +static int psi_bug __read_mostly; + +bool psi_disabled __read_mostly; +core_param(psi_disabled, psi_disabled, bool, 0644); + +/* Running averages - we need to be higher-res than loadavg */ +#define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ +#define EXP_10s 1677 /* 1/exp(2s/10s) as fixed-point */ +#define EXP_60s 1981 /* 1/exp(2s/60s) */ +#define EXP_300s 2034 /* 1/exp(2s/300s) */ + +/* Sampling frequency in nanoseconds */ +static u64 psi_period __read_mostly; + +/* System-level pressure and stall tracking */ +static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu); +static struct psi_group psi_system = { + .pcpu = &system_group_pcpu, +}; + +static void psi_update_work(struct work_struct *work); + +static void group_init(struct psi_group *group) +{ + int cpu; + + for_each_possible_cpu(cpu) + seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); + group->next_update = sched_clock() + psi_period; + INIT_DELAYED_WORK(&group->clock_work, psi_update_work); + mutex_init(&group->stat_lock); +} + +void __init psi_init(void) +{ + if (psi_disabled) + return; + + psi_period = jiffies_to_nsecs(PSI_FREQ); + group_init(&psi_system); +} + +static bool test_state(unsigned int *tasks, enum psi_states state) +{ + switch (state) { + case PSI_IO_SOME: + return tasks[NR_IOWAIT]; + case PSI_IO_FULL: + return tasks[NR_IOWAIT] && !tasks[NR_RUNNING]; + case PSI_MEM_SOME: + return tasks[NR_MEMSTALL]; + case PSI_MEM_FULL: + return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]; + case PSI_CPU_SOME: + return tasks[NR_RUNNING] > 1; + case PSI_NONIDLE: + return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] || + tasks[NR_RUNNING]; + default: + return false; + } +} + +static void get_recent_times(struct psi_group *group, int cpu, u32 *times) +{ + struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); + unsigned int tasks[NR_PSI_TASK_COUNTS]; + u64 now, state_start; + unsigned int seq; + int s; + + /* Snapshot a coherent view of the CPU state */ + do { + seq = read_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); + memcpy(times, groupc->times, sizeof(groupc->times)); + memcpy(tasks, groupc->tasks, sizeof(groupc->tasks)); + state_start = groupc->state_start; + } while (read_seqcount_retry(&groupc->seq, seq)); + + /* Calculate state time deltas against the previous snapshot */ + for (s = 0; s < NR_PSI_STATES; s++) { + u32 delta; + /* + * In addition to already concluded states, we also + * incorporate currently active states on the CPU, + * since states may last for many sampling periods. + * + * This way we keep our delta sampling buckets small + * (u32) and our reported pressure close to what's + * actually happening. + */ + if (test_state(tasks, s)) + times[s] += now - state_start; + + delta = times[s] - groupc->times_prev[s]; + groupc->times_prev[s] = times[s]; + + times[s] = delta; + } +} + +static void calc_avgs(unsigned long avg[3], int missed_periods, + u64 time, u64 period) +{ + unsigned long pct; + + /* Fill in zeroes for periods of no activity */ + if (missed_periods) { + avg[0] = calc_load_n(avg[0], EXP_10s, 0, missed_periods); + avg[1] = calc_load_n(avg[1], EXP_60s, 0, missed_periods); + avg[2] = calc_load_n(avg[2], EXP_300s, 0, missed_periods); + } + + /* Sample the most recent active period */ + pct = div_u64(time * 100, period); + pct *= FIXED_1; + avg[0] = calc_load(avg[0], EXP_10s, pct); + avg[1] = calc_load(avg[1], EXP_60s, pct); + avg[2] = calc_load(avg[2], EXP_300s, pct); +} + +static bool update_stats(struct psi_group *group) +{ + u64 deltas[NR_PSI_STATES - 1] = { 0, }; + unsigned long missed_periods = 0; + unsigned long nonidle_total = 0; + u64 now, expires, period; + int cpu; + int s; + + mutex_lock(&group->stat_lock); + + /* + * Collect the per-cpu time buckets and average them into a + * single time sample that is normalized to wallclock time. + * + * For averaging, each CPU is weighted by its non-idle time in + * the sampling period. This eliminates artifacts from uneven + * loading, or even entirely idle CPUs. + */ + for_each_possible_cpu(cpu) { + u32 times[NR_PSI_STATES]; + u32 nonidle; + + get_recent_times(group, cpu, times); + + nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]); + nonidle_total += nonidle; + + for (s = 0; s < PSI_NONIDLE; s++) + deltas[s] += (u64)times[s] * nonidle; + } + + /* + * Integrate the sample into the running statistics that are + * reported to userspace: the cumulative stall times and the + * decaying averages. + * + * Pressure percentages are sampled at PSI_FREQ. We might be + * called more often when the user polls more frequently than + * that; we might be called less often when there is no task + * activity, thus no data, and clock ticks are sporadic. The + * below handles both. + */ + + /* total= */ + for (s = 0; s < NR_PSI_STATES - 1; s++) + group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL)); + + /* avgX= */ + now = sched_clock(); + expires = group->next_update; + if (now < expires) + goto out; + if (now - expires > psi_period) + missed_periods = div_u64(now - expires, psi_period); + + /* + * The periodic clock tick can get delayed for various + * reasons, especially on loaded systems. To avoid clock + * drift, we schedule the clock in fixed psi_period intervals. + * But the deltas we sample out of the per-cpu buckets above + * are based on the actual time elapsing between clock ticks. + */ + group->next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->last_update + (missed_periods * psi_period)); + group->last_update = now; + + for (s = 0; s < NR_PSI_STATES - 1; s++) { + u32 sample; + + sample = group->total[s] - group->total_prev[s]; + /* + * Due to the lockless sampling of the time buckets, + * recorded time deltas can slip into the next period, + * which under full pressure can result in samples in + * excess of the period length. + * + * We don't want to report non-sensical pressures in + * excess of 100%, nor do we want to drop such events + * on the floor. Instead we punt any overage into the + * future until pressure subsides. By doing this we + * don't underreport the occurring pressure curve, we + * just report it delayed by one period length. + * + * The error isn't cumulative. As soon as another + * delta slips from a period P to P+1, by definition + * it frees up its time T in P. + */ + if (sample > period) + sample = period; + group->total_prev[s] += sample; + calc_avgs(group->avg[s], missed_periods, sample, period); + } +out: + mutex_unlock(&group->stat_lock); + return nonidle_total; +} + +static void psi_update_work(struct work_struct *work) +{ + struct delayed_work *dwork; + struct psi_group *group; + bool nonidle; + + dwork = to_delayed_work(work); + group = container_of(dwork, struct psi_group, clock_work); + + /* + * If there is task activity, periodically fold the per-cpu + * times and feed samples into the running averages. If things + * are idle and there is no data to process, stop the clock. + * Once restarted, we'll catch up the running averages in one + * go - see calc_avgs() and missed_periods. + */ + + nonidle = update_stats(group); + + if (nonidle) { + unsigned long delay = 0; + u64 now; + + now = sched_clock(); + if (group->next_update > now) + delay = nsecs_to_jiffies(group->next_update - now) + 1; + schedule_delayed_work(dwork, delay); + } +} + +static void record_times(struct psi_group_cpu *groupc, int cpu, + bool memstall_tick) +{ + u32 delta; + u64 now; + + now = cpu_clock(cpu); + delta = now - groupc->state_start; + groupc->state_start = now; + + if (test_state(groupc->tasks, PSI_IO_SOME)) { + groupc->times[PSI_IO_SOME] += delta; + if (test_state(groupc->tasks, PSI_IO_FULL)) + groupc->times[PSI_IO_FULL] += delta; + } + + if (test_state(groupc->tasks, PSI_MEM_SOME)) { + groupc->times[PSI_MEM_SOME] += delta; + if (test_state(groupc->tasks, PSI_MEM_FULL)) + groupc->times[PSI_MEM_FULL] += delta; + else if (memstall_tick) { + u32 sample; + /* + * Since we care about lost potential, a + * memstall is FULL when there are no other + * working tasks, but also when the CPU is + * actively reclaiming and nothing productive + * could run even if it were runnable. + * + * When the timer tick sees a reclaiming CPU, + * regardless of runnable tasks, sample a FULL + * tick (or less if it hasn't been a full tick + * since the last state change). + */ + sample = min(delta, (u32)jiffies_to_nsecs(1)); + groupc->times[PSI_MEM_FULL] += sample; + } + } + + if (test_state(groupc->tasks, PSI_CPU_SOME)) + groupc->times[PSI_CPU_SOME] += delta; + + if (test_state(groupc->tasks, PSI_NONIDLE)) + groupc->times[PSI_NONIDLE] += delta; +} + +static void psi_group_change(struct psi_group *group, int cpu, + unsigned int clear, unsigned int set) +{ + struct psi_group_cpu *groupc; + unsigned int t, m; + + groupc = per_cpu_ptr(group->pcpu, cpu); + + /* + * First we assess the aggregate resource states this CPU's + * tasks have been in since the last change, and account any + * SOME and FULL time these may have resulted in. + * + * Then we update the task counts according to the state + * change requested through the @clear and @set bits. + */ + write_seqcount_begin(&groupc->seq); + + record_times(groupc, cpu, false); + + for (t = 0, m = clear; m; m &= ~(1 << t), t++) { + if (!(m & (1 << t))) + continue; + if (groupc->tasks[t] == 0 && !psi_bug) { + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n", + cpu, t, groupc->tasks[0], + groupc->tasks[1], groupc->tasks[2], + clear, set); + psi_bug = 1; + } + groupc->tasks[t]--; + } + + for (t = 0; set; set &= ~(1 << t), t++) + if (set & (1 << t)) + groupc->tasks[t]++; + + write_seqcount_end(&groupc->seq); + + if (!delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); +} + +void psi_task_change(struct task_struct *task, int clear, int set) +{ + int cpu = task_cpu(task); + + if (!task->pid) + return; + + if (((task->psi_flags & set) || + (task->psi_flags & clear) != clear) && + !psi_bug) { + printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n", + task->pid, task->comm, cpu, + task->psi_flags, clear, set); + psi_bug = 1; + } + + task->psi_flags &= ~clear; + task->psi_flags |= set; + + psi_group_change(&psi_system, cpu, clear, set); +} + +void psi_memstall_tick(struct task_struct *task, int cpu) +{ + struct psi_group_cpu *groupc; + + groupc = per_cpu_ptr(psi_system.pcpu, cpu); + write_seqcount_begin(&groupc->seq); + record_times(groupc, cpu, true); + write_seqcount_end(&groupc->seq); +} + +/** + * psi_memstall_enter - mark the beginning of a memory stall section + * @flags: flags to handle nested sections + * + * Marks the calling task as being stalled due to a lack of memory, + * such as waiting for a refault or performing reclaim. + */ +void psi_memstall_enter(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (psi_disabled) + return; + + *flags = current->flags & PF_MEMSTALL; + if (*flags) + return; + /* + * PF_MEMSTALL setting & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we can + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags |= PF_MEMSTALL; + psi_task_change(current, 0, TSK_MEMSTALL); + + rq_unlock_irq(rq, &rf); +} + +/** + * psi_memstall_leave - mark the end of an memory stall section + * @flags: flags to handle nested memdelay sections + * + * Marks the calling task as no longer stalled due to lack of memory. + */ +void psi_memstall_leave(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (psi_disabled) + return; + + if (*flags) + return; + /* + * PF_MEMSTALL clearing & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we could + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags &= ~PF_MEMSTALL; + psi_task_change(current, TSK_MEMSTALL, 0); + + rq_unlock_irq(rq, &rf); +} + +static int psi_show(struct seq_file *m, struct psi_group *group, + enum psi_res res) +{ + int full; + + if (psi_disabled) + return -EOPNOTSUPP; + + update_stats(group); + + for (full = 0; full < 2 - (res == PSI_CPU); full++) { + unsigned long avg[3]; + u64 total; + int w; + + for (w = 0; w < 3; w++) + avg[w] = group->avg[res * 2 + full][w]; + total = div_u64(group->total[res * 2 + full], NSEC_PER_USEC); + + seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", + full ? "full" : "some", + LOAD_INT(avg[0]), LOAD_FRAC(avg[0]), + LOAD_INT(avg[1]), LOAD_FRAC(avg[1]), + LOAD_INT(avg[2]), LOAD_FRAC(avg[2]), + total); + } + + return 0; +} + +static int psi_io_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IO); +} + +static int psi_memory_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_MEM); +} + +static int psi_cpu_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_CPU); +} + +static int psi_io_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_io_show, NULL); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_memory_show, NULL); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_cpu_show, NULL); +} + +static const struct file_operations psi_io_fops = { + .open = psi_io_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_memory_fops = { + .open = psi_memory_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_cpu_fops = { + .open = psi_cpu_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init psi_proc_init(void) +{ + proc_mkdir("pressure", NULL); + proc_create("pressure/io", 0, NULL, &psi_io_fops); + proc_create("pressure/memory", 0, NULL, &psi_memory_fops); + proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops); + return 0; +} +module_init(psi_proc_init); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4e6ca7632691..67c8144258dd 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -268,6 +269,7 @@ extern bool dl_cpu_busy(unsigned int cpu); #ifdef CONFIG_CGROUP_SCHED #include +#include struct cfs_rq; struct rt_rq; diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index baf500d12b7c..8ee534f7ac42 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -55,6 +55,92 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta) #define schedstat_val_or_zero(var) 0 #endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_PSI +/* + * PSI tracks state that persists across sleeps, such as iowaits and + * memory stalls. As a result, it has to distinguish between sleeps, + * where a task's runnable state changes, and requeues, where a task + * and its state are being moved between CPUs and runqueues. + */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) +{ + int clear = 0, set = TSK_RUNNING; + + if (psi_disabled) + return; + + if (!wakeup || p->sched_psi_wake_requeue) { + if (p->flags & PF_MEMSTALL) + set |= TSK_MEMSTALL; + if (p->sched_psi_wake_requeue) + p->sched_psi_wake_requeue = 0; + } else { + if (p->in_iowait) + clear |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_dequeue(struct task_struct *p, bool sleep) +{ + int clear = TSK_RUNNING, set = 0; + + if (psi_disabled) + return; + + if (!sleep) { + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + } else { + if (p->in_iowait) + set |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_ttwu_dequeue(struct task_struct *p) +{ + if (psi_disabled) + return; + /* + * Is the task being migrated during a wakeup? Make sure to + * deregister its sleep-persistent psi states from the old + * queue, and let psi_enqueue() know it has to requeue. + */ + if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) { + struct rq_flags rf; + struct rq *rq; + int clear = 0; + + if (p->in_iowait) + clear |= TSK_IOWAIT; + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + + rq = __task_rq_lock(p, &rf); + psi_task_change(p, clear, 0); + p->sched_psi_wake_requeue = 1; + __task_rq_unlock(rq, &rf); + } +} + +static inline void psi_task_tick(struct rq *rq) +{ + if (psi_disabled) + return; + + if (unlikely(rq->curr->flags & PF_MEMSTALL)) + psi_memstall_tick(rq->curr, cpu_of(rq)); +} +#else /* CONFIG_PSI */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) {} +static inline void psi_dequeue(struct task_struct *p, bool sleep) {} +static inline void psi_ttwu_dequeue(struct task_struct *p) {} +static inline void psi_task_tick(struct rq *rq) {} +#endif /* CONFIG_PSI */ + #ifdef CONFIG_SCHED_INFO static inline void sched_info_reset_dequeued(struct task_struct *t) { diff --git a/mm/compaction.c b/mm/compaction.c index 85395dc6eb13..c9827c820a92 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "internal.h" #ifdef CONFIG_COMPACTION @@ -2038,11 +2039,15 @@ static int kcompactd(void *p) pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1; while (!kthread_should_stop()) { + unsigned long pflags; + trace_mm_compaction_kcompactd_sleep(pgdat->node_id); wait_event_freezable(pgdat->kcompactd_wait, kcompactd_work_requested(pgdat)); + psi_memstall_enter(&pflags); kcompactd_do_work(pgdat); + psi_memstall_leave(&pflags); } return 0; diff --git a/mm/filemap.c b/mm/filemap.c index 2b0920b8188c..a51b4979374d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "internal.h" #define CREATE_TRACE_POINTS @@ -975,11 +976,14 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; + unsigned long pflags; int ret = 0; - if (bit_nr == PG_locked && !PageSwapBacked(page) && + if (bit_nr == PG_locked && !PageUptodate(page) && PageWorkingset(page)) { - delayacct_thrashing_start(); + if (!PageSwapBacked(page)) + delayacct_thrashing_start(); + psi_memstall_enter(&pflags); thrashing = true; } @@ -1021,8 +1025,11 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, finish_wait(q, wait); - if (thrashing) - delayacct_thrashing_end(); + if (thrashing) { + if (!PageSwapBacked(page)) + delayacct_thrashing_end(); + psi_memstall_leave(&pflags); + } /* * A signal could leave PageWaiters set. Clearing it here if diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b207b5fc243c..770ab6182b57 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -67,6 +67,7 @@ #include #include #include +#include #include #include @@ -3383,15 +3384,20 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, enum compact_priority prio, enum compact_result *compact_result) { struct page *page; + unsigned long pflags; unsigned int noreclaim_flag; if (!order) return NULL; + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); + *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, prio); + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); if (*compact_result <= COMPACT_INACTIVE) return NULL; @@ -3580,11 +3586,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, struct reclaim_state reclaim_state; int progress; unsigned int noreclaim_flag; + unsigned long pflags; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); fs_reclaim_acquire(gfp_mask); reclaim_state.reclaimed_slab = 0; @@ -3596,6 +3604,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, current->reclaim_state = NULL; fs_reclaim_release(gfp_mask); memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); cond_resched(); diff --git a/mm/vmscan.c b/mm/vmscan.c index 06a7d1605a5d..26ce98805714 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -3134,6 +3135,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, { struct zonelist *zonelist; unsigned long nr_reclaimed; + unsigned long pflags; int nid; unsigned int noreclaim_flag; struct scan_control sc = { @@ -3162,9 +3164,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, sc.gfp_mask, sc.reclaim_idx); + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); @@ -3329,6 +3335,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + unsigned long pflags; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, @@ -3338,6 +3345,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) .may_unmap = 1, .may_swap = 1, }; + psi_memstall_enter(&pflags); count_vm_event(PAGEOUTRUN); do { @@ -3432,6 +3440,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) out: snapshot_refaults(NULL, pgdat); + psi_memstall_leave(&pflags); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller -- GitLab From edd6f9faedd2467c4d78ba5b64f82e2adc28a57a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:31 -0700 Subject: [PATCH 0241/1128] BACKPORT: psi: cgroup support On a system that executes multiple cgrouped jobs and independent workloads, we don't just care about the health of the overall system, but also that of individual jobs, so that we can ensure individual job health, fairness between jobs, or prioritize some jobs over others. This patch implements pressure stall tracking for cgroups. In kernels with CONFIG_PSI=y, cgroup2 groups will have cpu.pressure, memory.pressure, and io.pressure files that track aggregate pressure stall times for only the tasks inside the cgroup. Link: http://lkml.kernel.org/r/20180828172258.3185-10-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Tejun Heo Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 2ce7135adc9ad081aa3c49744144376ac74fea60) Conflicts: Documentation/cgroup-v2.txt include/linux/psi.h kernel/cgroup/cgroup.c (1. manual merge from Documentation/admin-guide/cgroup-v2.rst 2. include into include/linux/psi.h 3. manual merge in css_free_work_fn to allow psi support only for cgroup v2 4. manual merge in cgroup_create to allow psi support only for cgroup v2) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I163e6657aaa60aa5aab9372616a3bce2a65e90ec Signed-off-by: Suren Baghdasaryan --- Documentation/accounting/psi.txt | 9 +++ Documentation/cgroup-v2.txt | 18 +++++ include/linux/cgroup-defs.h | 4 ++ include/linux/cgroup.h | 15 ++++ include/linux/psi.h | 26 +++++++ init/Kconfig | 4 ++ kernel/cgroup/cgroup.c | 45 +++++++++++- kernel/sched/psi.c | 118 ++++++++++++++++++++++++++++--- 8 files changed, 230 insertions(+), 9 deletions(-) diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt index 3753a82f1cf5..b8ca28b60215 100644 --- a/Documentation/accounting/psi.txt +++ b/Documentation/accounting/psi.txt @@ -62,3 +62,12 @@ well as medium and long term trends. The total absolute stall time is tracked and exported as well, to allow detection of latency spikes which wouldn't necessarily make a dent in the time averages, or to average trends over custom time frames. + +Cgroup2 interface +================= + +In a system with a CONFIG_CGROUP=y kernel and the cgroup2 filesystem +mounted, pressure stall information is also tracked for tasks grouped +into cgroups. Each subdirectory in the cgroupfs mountpoint contains +cpu.pressure, memory.pressure, and io.pressure files; the format is +the same as the /proc/pressure/ files. diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt index dc44785dc0fa..7e3672812510 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -958,6 +958,12 @@ All time durations are in microseconds. $PERIOD duration. If only one number is written, $MAX is updated. + cpu.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for CPU. See + Documentation/accounting/psi.txt for details. + Memory ------ @@ -1194,6 +1200,12 @@ PAGE_SIZE multiple when read back. Swap usage hard limit. If a cgroup's swap usage reaches this limit, anonymous meomry of the cgroup will not be swapped out. + memory.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for memory. See + Documentation/accounting/psi.txt for details. + Usage Guidelines ~~~~~~~~~~~~~~~~ @@ -1329,6 +1341,12 @@ IO Interface Files 8:16 rbps=2097152 wbps=max riops=max wiops=max + io.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for IO. See + Documentation/accounting/psi.txt for details. + Writeback ~~~~~~~~~ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index e7905d9353e8..f113ebd940e0 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -19,6 +19,7 @@ #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -368,6 +369,9 @@ struct cgroup { /* used to schedule release agent */ struct work_struct release_agent_work; + /* used to track pressure stalls */ + struct psi_group psi; + /* used to store eBPF programs */ struct cgroup_bpf bpf; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index dddbc29e2009..28a1a067da52 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -626,6 +626,11 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return &cgrp->psi; +} + static inline void cgroup_init_kthreadd(void) { /* @@ -679,6 +684,16 @@ static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) return NULL; } +static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) +{ + return NULL; +} + +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return NULL; +} + static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { diff --git a/include/linux/psi.h b/include/linux/psi.h index b0daf050de58..3d759c00df7f 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -3,6 +3,10 @@ #include #include +#include + +struct seq_file; +struct css_set; #ifdef CONFIG_PSI @@ -16,6 +20,14 @@ void psi_memstall_tick(struct task_struct *task, int cpu); void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); +int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); +#endif + #else /* CONFIG_PSI */ static inline void psi_init(void) {} @@ -23,6 +35,20 @@ static inline void psi_init(void) {} static inline void psi_memstall_enter(unsigned long *flags) {} static inline void psi_memstall_leave(unsigned long *flags) {} +#ifdef CONFIG_CGROUPS +static inline int psi_cgroup_alloc(struct cgroup *cgrp) +{ + return 0; +} +static inline void psi_cgroup_free(struct cgroup *cgrp) +{ +} +static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) +{ + rcu_assign_pointer(p->cgroups, to); +} +#endif + #endif /* CONFIG_PSI */ #endif /* _LINUX_PSI_H */ diff --git a/init/Kconfig b/init/Kconfig index 9c6c93b319ad..418af46f5d6a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -490,6 +490,10 @@ config PSI the share of walltime in which some or all tasks in the system are delayed due to contention of the respective resource. + In kernels with cgroup support, cgroups (cgroup2 only) will + have cpu.pressure, memory.pressure, and io.pressure files, + which aggregate pressure stalls for the grouped tasks only. + For more details see Documentation/accounting/psi.txt. Say N if unsure. diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 21bbfc09e395..1742c6e1c1b9 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #define CREATE_TRACE_POINTS @@ -794,7 +795,7 @@ static void css_set_move_task(struct task_struct *task, */ WARN_ON_ONCE(task->flags & PF_EXITING); - rcu_assign_pointer(task->cgroups, to_cset); + cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } @@ -3329,6 +3330,21 @@ static int cgroup_stat_show(struct seq_file *seq, void *v) return 0; } +#ifdef CONFIG_PSI +static int cgroup_io_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_IO); +} +static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_MEM); +} +static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU); +} +#endif + static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of->kn->priv; @@ -4439,6 +4455,23 @@ static struct cftype cgroup_base_files[] = { .name = "cgroup.stat", .seq_show = cgroup_stat_show, }, +#ifdef CONFIG_PSI + { + .name = "io.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_io_pressure_show, + }, + { + .name = "memory.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_memory_pressure_show, + }, + { + .name = "cpu.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_cpu_pressure_show, + }, +#endif { } /* terminate */ }; @@ -4499,6 +4532,8 @@ static void css_free_work_fn(struct work_struct *work) */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); + if (cgroup_on_dfl(cgrp)) + psi_cgroup_free(cgrp); kfree(cgrp); } else { /* @@ -4775,6 +4810,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent) if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); + if (cgroup_on_dfl(cgrp)) { + ret = psi_cgroup_alloc(cgrp); + if (ret) + goto out_idr_free; + } + if (parent) cgroup_bpf_inherit(cgrp, parent); @@ -4782,6 +4823,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent) return cgrp; +out_idr_free: + cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 595414599b98..7cdecfc010af 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -473,9 +473,35 @@ static void psi_group_change(struct psi_group *group, int cpu, schedule_delayed_work(&group->clock_work, PSI_FREQ); } +static struct psi_group *iterate_groups(struct task_struct *task, void **iter) +{ +#ifdef CONFIG_CGROUPS + struct cgroup *cgroup = NULL; + + if (!*iter) + cgroup = task->cgroups->dfl_cgrp; + else if (*iter == &psi_system) + return NULL; + else + cgroup = cgroup_parent(*iter); + + if (cgroup && cgroup_parent(cgroup)) { + *iter = cgroup; + return cgroup_psi(cgroup); + } +#else + if (*iter) + return NULL; +#endif + *iter = &psi_system; + return &psi_system; +} + void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); + struct psi_group *group; + void *iter = NULL; if (!task->pid) return; @@ -492,17 +518,23 @@ void psi_task_change(struct task_struct *task, int clear, int set) task->psi_flags &= ~clear; task->psi_flags |= set; - psi_group_change(&psi_system, cpu, clear, set); + while ((group = iterate_groups(task, &iter))) + psi_group_change(group, cpu, clear, set); } void psi_memstall_tick(struct task_struct *task, int cpu) { - struct psi_group_cpu *groupc; + struct psi_group *group; + void *iter = NULL; - groupc = per_cpu_ptr(psi_system.pcpu, cpu); - write_seqcount_begin(&groupc->seq); - record_times(groupc, cpu, true); - write_seqcount_end(&groupc->seq); + while ((group = iterate_groups(task, &iter))) { + struct psi_group_cpu *groupc; + + groupc = per_cpu_ptr(group->pcpu, cpu); + write_seqcount_begin(&groupc->seq); + record_times(groupc, cpu, true); + write_seqcount_end(&groupc->seq); + } } /** @@ -565,8 +597,78 @@ void psi_memstall_leave(unsigned long *flags) rq_unlock_irq(rq, &rf); } -static int psi_show(struct seq_file *m, struct psi_group *group, - enum psi_res res) +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgroup) +{ + if (psi_disabled) + return 0; + + cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); + if (!cgroup->psi.pcpu) + return -ENOMEM; + group_init(&cgroup->psi); + return 0; +} + +void psi_cgroup_free(struct cgroup *cgroup) +{ + if (psi_disabled) + return; + + cancel_delayed_work_sync(&cgroup->psi.clock_work); + free_percpu(cgroup->psi.pcpu); +} + +/** + * cgroup_move_task - move task to a different cgroup + * @task: the task + * @to: the target css_set + * + * Move task to a new cgroup and safely migrate its associated stall + * state between the different groups. + * + * This function acquires the task's rq lock to lock out concurrent + * changes to the task's scheduling state and - in case the task is + * running - concurrent changes to its stall state. + */ +void cgroup_move_task(struct task_struct *task, struct css_set *to) +{ + bool move_psi = !psi_disabled; + unsigned int task_flags = 0; + struct rq_flags rf; + struct rq *rq; + + if (move_psi) { + rq = task_rq_lock(task, &rf); + + if (task_on_rq_queued(task)) + task_flags = TSK_RUNNING; + else if (task->in_iowait) + task_flags = TSK_IOWAIT; + + if (task->flags & PF_MEMSTALL) + task_flags |= TSK_MEMSTALL; + + if (task_flags) + psi_task_change(task, task_flags, 0); + } + + /* + * Lame to do this here, but the scheduler cannot be locked + * from the outside, so we move cgroups from inside sched/. + */ + rcu_assign_pointer(task->cgroups, to); + + if (move_psi) { + if (task_flags) + psi_task_change(task, 0, task_flags); + + task_rq_unlock(rq, task, &rf); + } +} +#endif /* CONFIG_CGROUPS */ + +int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { int full; -- GitLab From 7b8aa973f7a3d6f9fbfd23b381de49b6cc5dec8d Mon Sep 17 00:00:00 2001 From: Olof Johansson Date: Fri, 16 Nov 2018 15:08:00 -0800 Subject: [PATCH 0242/1128] UPSTREAM: kernel/sched/psi.c: simplify cgroup_move_task() The existing code triggered an invalid warning about 'rq' possibly being used uninitialized. Instead of doing the silly warning suppression by initializa it to NULL, refactor the code to bail out early instead. Warning was: kernel/sched/psi.c: In function `cgroup_move_task': kernel/sched/psi.c:639:13: warning: `rq' may be used uninitialized in this function [-Wmaybe-uninitialized] Link: http://lkml.kernel.org/r/20181103183339.8669-1-olof@lixom.net Fixes: 2ce7135adc9ad ("psi: cgroup support") Signed-off-by: Olof Johansson Reviewed-by: Andrew Morton Acked-by: Johannes Weiner Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 8fcb2312d1e3300e81aa871aad00d4c038cfc184) Bug: 127712811 Test: lmkd in PSI mode Change-Id: Id989da224a726082e0cfa5d5d9460bf63d448a93 Signed-off-by: Suren Baghdasaryan --- kernel/sched/psi.c | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 7cdecfc010af..3d7355d7c3e3 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -633,38 +633,39 @@ void psi_cgroup_free(struct cgroup *cgroup) */ void cgroup_move_task(struct task_struct *task, struct css_set *to) { - bool move_psi = !psi_disabled; unsigned int task_flags = 0; struct rq_flags rf; struct rq *rq; - if (move_psi) { - rq = task_rq_lock(task, &rf); + if (psi_disabled) { + /* + * Lame to do this here, but the scheduler cannot be locked + * from the outside, so we move cgroups from inside sched/. + */ + rcu_assign_pointer(task->cgroups, to); + return; + } - if (task_on_rq_queued(task)) - task_flags = TSK_RUNNING; - else if (task->in_iowait) - task_flags = TSK_IOWAIT; + rq = task_rq_lock(task, &rf); - if (task->flags & PF_MEMSTALL) - task_flags |= TSK_MEMSTALL; + if (task_on_rq_queued(task)) + task_flags = TSK_RUNNING; + else if (task->in_iowait) + task_flags = TSK_IOWAIT; - if (task_flags) - psi_task_change(task, task_flags, 0); - } + if (task->flags & PF_MEMSTALL) + task_flags |= TSK_MEMSTALL; - /* - * Lame to do this here, but the scheduler cannot be locked - * from the outside, so we move cgroups from inside sched/. - */ + if (task_flags) + psi_task_change(task, task_flags, 0); + + /* See comment above */ rcu_assign_pointer(task->cgroups, to); - if (move_psi) { - if (task_flags) - psi_task_change(task, 0, task_flags); + if (task_flags) + psi_task_change(task, 0, task_flags); - task_rq_unlock(rq, task, &rf); - } + task_rq_unlock(rq, task, &rf); } #endif /* CONFIG_CGROUPS */ -- GitLab From 978392049e485f5748a2066433fe29ea6e392e68 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 30 Nov 2018 14:09:58 -0800 Subject: [PATCH 0243/1128] UPSTREAM: psi: make disabling/enabling easier for vendor kernels Mel Gorman reports a hackbench regression with psi that would prohibit shipping the suse kernel with it default-enabled, but he'd still like users to be able to opt in at little to no cost to others. With the current combination of CONFIG_PSI and the psi_disabled bool set from the commandline, this is a challenge. Do the following things to make it easier: 1. Add a config option CONFIG_PSI_DEFAULT_DISABLED that allows distros to enable CONFIG_PSI in their kernel but leave the feature disabled unless a user requests it at boot-time. To avoid double negatives, rename psi_disabled= to psi=. 2. Make psi_disabled a static branch to eliminate any branch costs when the feature is disabled. In terms of numbers before and after this patch, Mel says: : The following is a comparision using CONFIG_PSI=n as a baseline against : your patch and a vanilla kernel : : 4.20.0-rc4 4.20.0-rc4 4.20.0-rc4 : kconfigdisable-v1r1 vanilla psidisable-v1r1 : Amean 1 1.3100 ( 0.00%) 1.3923 ( -6.28%) 1.3427 ( -2.49%) : Amean 3 3.8860 ( 0.00%) 4.1230 * -6.10%* 3.8860 ( -0.00%) : Amean 5 6.8847 ( 0.00%) 8.0390 * -16.77%* 6.7727 ( 1.63%) : Amean 7 9.9310 ( 0.00%) 10.8367 * -9.12%* 9.9910 ( -0.60%) : Amean 12 16.6577 ( 0.00%) 18.2363 * -9.48%* 17.1083 ( -2.71%) : Amean 18 26.5133 ( 0.00%) 27.8833 * -5.17%* 25.7663 ( 2.82%) : Amean 24 34.3003 ( 0.00%) 34.6830 ( -1.12%) 32.0450 ( 6.58%) : Amean 30 40.0063 ( 0.00%) 40.5800 ( -1.43%) 41.5087 ( -3.76%) : Amean 32 40.1407 ( 0.00%) 41.2273 ( -2.71%) 39.9417 ( 0.50%) : : It's showing that the vanilla kernel takes a hit (as the bisection : indicated it would) and that disabling PSI by default is reasonably : close in terms of performance for this particular workload on this : particular machine so; Link: http://lkml.kernel.org/r/20181127165329.GA29728@cmpxchg.org Signed-off-by: Johannes Weiner Tested-by: Mel Gorman Reported-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit e0c274472d5d27f277af722e017525e0b33784cd) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I6cb666fa351e8901df82e4d6931bfec0c5ce230d Signed-off-by: Suren Baghdasaryan --- .../admin-guide/kernel-parameters.txt | 4 +++ include/linux/psi.h | 3 +- init/Kconfig | 9 ++++++ kernel/sched/psi.c | 30 +++++++++++++------ kernel/sched/stats.h | 8 ++--- 5 files changed, 40 insertions(+), 14 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 98c95029ec30..3971554ca0d0 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3325,6 +3325,10 @@ before loading. See Documentation/blockdev/ramdisk.txt. + psi= [KNL] Enable or disable pressure stall information + tracking. + Format: + psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to probe for; one of (bare|imps|exps|lifebook|any). psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports diff --git a/include/linux/psi.h b/include/linux/psi.h index 3d759c00df7f..cf6f56d959e8 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,6 +1,7 @@ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H +#include #include #include #include @@ -10,7 +11,7 @@ struct css_set; #ifdef CONFIG_PSI -extern bool psi_disabled; +extern struct static_key_false psi_disabled; void psi_init(void); diff --git a/init/Kconfig b/init/Kconfig index 418af46f5d6a..26c554bc65d4 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -498,6 +498,15 @@ config PSI Say N if unsure. +config PSI_DEFAULT_DISABLED + bool "Require boot parameter to enable pressure stall information tracking" + default n + depends on PSI + help + If set, pressure stall information tracking will be disabled + per default but can be enabled through passing psi_enable=1 + on the kernel commandline during boot. + endmenu # "CPU/Task time and stats accounting" source "kernel/rcu/Kconfig" diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 3d7355d7c3e3..fe24de3fbc93 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -136,8 +136,18 @@ static int psi_bug __read_mostly; -bool psi_disabled __read_mostly; -core_param(psi_disabled, psi_disabled, bool, 0644); +DEFINE_STATIC_KEY_FALSE(psi_disabled); + +#ifdef CONFIG_PSI_DEFAULT_DISABLED +bool psi_enable; +#else +bool psi_enable = true; +#endif +static int __init setup_psi(char *str) +{ + return kstrtobool(str, &psi_enable) == 0; +} +__setup("psi=", setup_psi); /* Running averages - we need to be higher-res than loadavg */ #define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ @@ -169,8 +179,10 @@ static void group_init(struct psi_group *group) void __init psi_init(void) { - if (psi_disabled) + if (!psi_enable) { + static_branch_enable(&psi_disabled); return; + } psi_period = jiffies_to_nsecs(PSI_FREQ); group_init(&psi_system); @@ -549,7 +561,7 @@ void psi_memstall_enter(unsigned long *flags) struct rq_flags rf; struct rq *rq; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; *flags = current->flags & PF_MEMSTALL; @@ -579,7 +591,7 @@ void psi_memstall_leave(unsigned long *flags) struct rq_flags rf; struct rq *rq; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (*flags) @@ -600,7 +612,7 @@ void psi_memstall_leave(unsigned long *flags) #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return 0; cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); @@ -612,7 +624,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) void psi_cgroup_free(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; cancel_delayed_work_sync(&cgroup->psi.clock_work); @@ -637,7 +649,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) struct rq_flags rf; struct rq *rq; - if (psi_disabled) { + if (static_branch_likely(&psi_disabled)) { /* * Lame to do this here, but the scheduler cannot be locked * from the outside, so we move cgroups from inside sched/. @@ -673,7 +685,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { int full; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; update_stats(group); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 8ee534f7ac42..5d30f4b7d344 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -66,7 +66,7 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup) { int clear = 0, set = TSK_RUNNING; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (!wakeup || p->sched_psi_wake_requeue) { @@ -86,7 +86,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) { int clear = TSK_RUNNING, set = 0; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (!sleep) { @@ -102,7 +102,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) static inline void psi_ttwu_dequeue(struct task_struct *p) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; /* * Is the task being migrated during a wakeup? Make sure to @@ -128,7 +128,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) static inline void psi_task_tick(struct rq *rq) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (unlikely(rq->curr->flags & PF_MEMSTALL)) -- GitLab From 9c915720231bd612ebfc6910c10c160dff64d096 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Fri, 14 Dec 2018 14:17:03 -0800 Subject: [PATCH 0244/1128] UPSTREAM: psi: fix reference to kernel commandline enable The kernel commandline parameter named in CONFIG_PSI_DEFAULT_DISABLED help text contradicts the documentation in kernel-parameters.txt, and the code. Fix that. Link: http://lkml.kernel.org/r/20181203213416.GA12627@cmpxchg.org Fixes: e0c274472d ("psi: make disabling/enabling easier for vendor kernels") Signed-off-by: Baruch Siach Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 428a1cb4baeb9e5c7feda93af7372ba6d2491558) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I592b66d6542f4fa7c2b6eb9f60a5dd43bcfbabf3 Signed-off-by: Suren Baghdasaryan --- init/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index 26c554bc65d4..d58ade72b7df 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -504,8 +504,8 @@ config PSI_DEFAULT_DISABLED depends on PSI help If set, pressure stall information tracking will be disabled - per default but can be enabled through passing psi_enable=1 - on the kernel commandline during boot. + per default but can be enabled through passing psi=1 on the + kernel commandline during boot. endmenu # "CPU/Task time and stats accounting" -- GitLab From 094ac9419e581ee9aefb396a503672f22c665d99 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 1 Feb 2019 14:20:42 -0800 Subject: [PATCH 0245/1128] UPSTREAM: psi: fix aggregation idle shut-off psi has provisions to shut off the periodic aggregation worker when there is a period of no task activity - and thus no data that needs aggregating. However, while developing psi monitoring, Suren noticed that the aggregation clock currently won't stay shut off for good. Debugging this revealed a flaw in the idle design: an aggregation run will see no task activity and decide to go to sleep; shortly thereafter, the kworker thread that executed the aggregation will go idle and cause a scheduling change, during which the psi callback will kick the !pending worker again. This will ping-pong forever, and is equivalent to having no shut-off logic at all (but with more code!) Fix this by exempting aggregation workers from psi's clock waking logic when the state change is them going to sleep. To do this, tag workers with the last work function they executed, and if in psi we see a worker going to sleep after aggregating psi data, we will not reschedule the aggregation work item. What if the worker is also executing other items before or after? Any psi state times that were incurred by work items preceding the aggregation work will have been collected from the per-cpu buckets during the aggregation itself. If there are work items following the aggregation work, the worker's last_func tag will be overwritten and the aggregator will be kept alive to process this genuine new activity. If the aggregation work is the last thing the worker does, and we decide to go idle, the brief period of non-idle time incurred between the aggregation run and the kworker's dequeue will be stranded in the per-cpu buckets until the clock is woken by later activity. But that should not be a problem. The buckets can hold 4s worth of time, and future activity will wake the clock with a 2s delay, giving us 2s worth of data we can leave behind when disabling aggregation. If it takes a worker more than two seconds to go idle after it finishes its last work item, we likely have bigger problems in the system, and won't notice one sample that was averaged with a bogus per-CPU weight. Link: http://lkml.kernel.org/r/20190116193501.1910-1-hannes@cmpxchg.org Fixes: eb414681d5a0 ("psi: pressure stall information for CPU, memory, and IO") Signed-off-by: Johannes Weiner Reported-by: Suren Baghdasaryan Acked-by: Tejun Heo Cc: Peter Zijlstra Cc: Lai Jiangshan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 1b69ac6b40ebd85eed73e4dbccde2a36961ab990) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I2877fec3d381b1006b8bd1261895fdfd68bd21db Signed-off-by: Suren Baghdasaryan --- kernel/sched/psi.c | 21 +++++++++++++++++---- kernel/workqueue.c | 23 +++++++++++++++++++++++ kernel/workqueue_internal.h | 6 +++++- 3 files changed, 45 insertions(+), 5 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index fe24de3fbc93..c3484785b179 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -124,6 +124,7 @@ * sampling of the aggregate task states would be. */ +#include "../workqueue_internal.h" #include #include #include @@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu, groupc->tasks[t]++; write_seqcount_end(&groupc->seq); - - if (!delayed_work_pending(&group->clock_work)) - schedule_delayed_work(&group->clock_work, PSI_FREQ); } static struct psi_group *iterate_groups(struct task_struct *task, void **iter) @@ -513,6 +511,7 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; + bool wake_clock = true; void *iter = NULL; if (!task->pid) @@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set) task->psi_flags &= ~clear; task->psi_flags |= set; - while ((group = iterate_groups(task, &iter))) + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((clear & TSK_RUNNING) && + (task->flags & PF_WQ_WORKER) && + wq_worker_last_func(task) == psi_update_work)) + wake_clock = false; + + while ((group = iterate_groups(task, &iter))) { psi_group_change(group, cpu, clear, set); + if (wake_clock && !delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); + } } void psi_memstall_tick(struct task_struct *task, int cpu) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 08bc551976b2..cd950d62f1bf 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -911,6 +911,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) return to_wakeup ? to_wakeup->task : NULL; } +/** + * wq_worker_last_func - retrieve worker's last work function + * + * Determine the last function a worker executed. This is called from + * the scheduler to get a worker's last known identity. + * + * CONTEXT: + * spin_lock_irq(rq->lock) + * + * Return: + * The last work function %current executed as a worker, NULL if it + * hasn't executed any work yet. + */ +work_func_t wq_worker_last_func(struct task_struct *task) +{ + struct worker *worker = kthread_data(task); + + return worker->last_func; +} + /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self @@ -2145,6 +2165,9 @@ __acquires(&pool->lock) if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); + /* tag the worker for identification in schedule() */ + worker->last_func = worker->current_func; + /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index d390d1be3748..f8f5fd8df88f 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -54,6 +54,9 @@ struct worker { /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ + + /* used by the scheduler to determine a worker's last known identity */ + work_func_t last_func; }; /** @@ -68,9 +71,10 @@ static inline struct worker *current_wq_worker(void) /* * Scheduler hooks for concurrency managed workqueue. Only to be used from - * sched/core.c and workqueue.c. + * sched/ and workqueue.c. */ void wq_worker_waking_up(struct task_struct *task, int cpu); struct task_struct *wq_worker_sleeping(struct task_struct *task); +work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ -- GitLab From 8abcc2a17ecc79052ccb6ec0da427809c2160dcb Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 1 Feb 2019 14:21:15 -0800 Subject: [PATCH 0246/1128] UPSTREAM: psi: clarify the Kconfig text for the default-disable option The current help text caused some confusion in online forums about whether or not to default-enable or default-disable psi in vendor kernels. This is because it doesn't communicate the reason for why we made this setting configurable in the first place: that the overhead is non-zero in an artificial scheduler stress test. Since this isn't representative of real workloads, and the effect was not measurable in scheduler-heavy real world applications such as the webservers and memcache installations at Facebook, it's fair to point out that this is a pretty cautious option to select. Link: http://lkml.kernel.org/r/20190129233617.16767-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Andrew Morton Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 7b2489d37e1e355228f7c55724f77580e1dec22a) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I5d0cb901562fd74c82d9d211544745b802776d8a Signed-off-by: Suren Baghdasaryan --- init/Kconfig | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/init/Kconfig b/init/Kconfig index d58ade72b7df..41053e87d144 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -507,6 +507,17 @@ config PSI_DEFAULT_DISABLED per default but can be enabled through passing psi=1 on the kernel commandline during boot. + This feature adds some code to the task wakeup and sleep + paths of the scheduler. The overhead is too low to affect + common scheduling-intense workloads in practice (such as + webservers, memcache), but it does show up in artificial + scheduler stress tests, such as hackbench. + + If you are paranoid and not sure what the kernel will be + used for, say Y. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting" source "kernel/rcu/Kconfig" -- GitLab From 4556adc0672bb7f4e1e29b45370877534d229dd5 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 20 Feb 2019 22:19:59 -0800 Subject: [PATCH 0247/1128] UPSTREAM: psi: avoid divide-by-zero crash inside virtual machines MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We've been seeing hard-to-trigger psi crashes when running inside VM instances: divide error: 0000 [#1] SMP PTI Modules linked in: [...] CPU: 0 PID: 212 Comm: kworker/0:2 Not tainted 4.16.18-119_fbk9_3817_gfe944c98d695 #119 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.0.0 02/06/2015 Workqueue: events psi_clock RIP: 0010:psi_update_stats+0x270/0x490 RSP: 0018:ffffc90001117e10 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff8800a35a13f8 RDX: 0000000000000000 RSI: ffff8800a35a1340 RDI: 0000000000000000 RBP: 0000000000000658 R08: ffff8800a35a1470 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 00000000000f8502 FS: 0000000000000000(0000) GS:ffff88023fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fbe370fa000 CR3: 00000000b1e3a000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: psi_clock+0x12/0x50 process_one_work+0x1e0/0x390 worker_thread+0x2b/0x3c0 ? rescuer_thread+0x330/0x330 kthread+0x113/0x130 ? kthread_create_worker_on_cpu+0x40/0x40 ? SyS_exit_group+0x10/0x10 ret_from_fork+0x35/0x40 Code: 48 0f 47 c7 48 01 c2 45 85 e4 48 89 16 0f 85 e6 00 00 00 4c 8b 49 10 4c 8b 51 08 49 69 d9 f2 07 00 00 48 6b c0 64 4c 8b 29 31 d2 <48> f7 f7 49 69 d5 8d 06 00 00 48 89 c5 4c 69 f0 00 98 0b 00 48 The Code-line points to `period` being 0 inside update_stats(), and we divide by that when calculating that period's pressure percentage. The elapsed period should never be 0. The reason this can happen is due to an off-by-one in the idle time / missing period calculation combined with a coarse sched_clock() in the virtual machine. The target time for aggregation is advanced into the future on a fixed grid to prevent clock drift. So when an aggregation runs after some idle period, we can not just set it to "now + psi_period", but have to calculate the downtime and advance the target time relative to itself. However, if the aggregator was disabled exactly one psi_period (ns), we drop one idle period in the calculation due to a > when we should do >=. In that case, next_update will be advanced from 'now - psi_period' to 'now' when it should be moved to 'now + psi_period'. The run finishes with last_update == next_update == sched_clock(). With hardware clocks, this exact nanosecond match isn't likely in the first place; but if it does happen, the clock will still have moved on and the period non-zero by the time the worker runs. A pointlessly short period, but besides the extra work, no harm no foul. However, a slow sched_clock() like we have on VMs might not have advanced either by the time the worker runs again. And when we calculate the elapsed period, the result, our pressure divisor, will be 0. Ouch. Fix this by correctly handling the situation when the elapsed time between aggregation runs is precisely two periods, and advance the expiration timestamp correctly to period into the future. Link: http://lkml.kernel.org/r/20190214193157.15788-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reported-by: Łukasz Siudut Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 4e37504d1c49eec6434d0cc97278d2b51c9e8763) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I40917c84354f9f32259c6703f00b6b1d21f45f02 Signed-off-by: Suren Baghdasaryan --- kernel/sched/psi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index c3484785b179..0e97ca9306ef 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -322,7 +322,7 @@ static bool update_stats(struct psi_group *group) expires = group->next_update; if (now < expires) goto out; - if (now - expires > psi_period) + if (now - expires >= psi_period) missed_periods = div_u64(now - expires, psi_period); /* -- GitLab From 29d0475df1d10adc5e01914caa4a9dc010590cfa Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 31 Jan 2019 10:41:54 +1100 Subject: [PATCH 0248/1128] BACKPORT: fs: kernfs: add poll file operation Patch series "psi: pressure stall monitors", v3. Android is adopting psi to detect and remedy memory pressure that results in stuttering and decreased responsiveness on mobile devices. Psi gives us the stall information, but because we're dealing with latencies in the millisecond range, periodically reading the pressure files to detect stalls in a timely fashion is not feasible. Psi also doesn't aggregate its averages at a high enough frequency right now. This patch series extends the psi interface such that users can configure sensitive latency thresholds and use poll() and friends to be notified when these are breached. As high-frequency aggregation is costly, it implements an aggregation method that is optimized for fast, short-interval averaging, and makes the aggregation frequency adaptive, such that high-frequency updates only happen while monitored stall events are actively occurring. With these patches applied, Android can monitor for, and ward off, mounting memory shortages before they cause problems for the user. For example, using memory stall monitors in userspace low memory killer daemon (lmkd) we can detect mounting pressure and kill less important processes before device becomes visibly sluggish. In our memory stress testing psi memory monitors produce roughly 10x less false positives compared to vmpressure signals. Having ability to specify multiple triggers for the same psi metric allows other parts of Android framework to monitor memory state of the device and act accordingly. The new interface is straightforward. The user opens one of the pressure files for writing and writes a trigger description into the file descriptor that defines the stall state - some or full, and the maximum stall time over a given window of time. E.g.: /* Signal when stall time exceeds 100ms of a 1s window */ char trigger[] = "full 100000 1000000"; fd = open("/proc/pressure/memory"); write(fd, trigger, sizeof(trigger)); while (poll() >= 0) { ... } close(fd); When the monitored stall state is entered, psi adapts its aggregation frequency according to what the configured time window requires in order to emit event signals in a timely fashion. Once the stalling subsides, aggregation reverts back to normal. The trigger is associated with the open file descriptor. To stop monitoring, the user only needs to close the file descriptor and the trigger is discarded. Patches 1-4 prepare the psi code for polling support. Patch 5 implements the adaptive polling logic, the pressure growth detection optimized for short intervals, and hooks up write() and poll() on the pressure files. The patches were developed in collaboration with Johannes Weiner. This patch (of 5): Kernfs has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.com Signed-off-by: Johannes Weiner Signed-off-by: Suren Baghdasaryan Cc: Dennis Zhou Cc: Ingo Molnar Cc: Jens Axboe Cc: Li Zefan Cc: Peter Zijlstra Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Stephen Rothwell (cherry picked from commit: 147e1a97c4a0bdd43f55a582a9416bb9092563a9) Conflicts: fs/kernfs/file.c include/linux/kernfs.h 1. replaced __poll_t with unsigned int. 2. replaced EPOLLERR/EPOLLPRI with POLLERR/POLLPRI (values are the same) Bug: 127712811 Test: lmkd in PSI mode Change-Id: Ic2bed334d05aec62f4e695f263893c3057921c55 Signed-off-by: Suren Baghdasaryan --- fs/kernfs/file.c | 31 ++++++++++++++++++++----------- include/linux/kernfs.h | 6 ++++++ 2 files changed, 26 insertions(+), 11 deletions(-) diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index d8f49c412f50..d5b3cd692b29 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -832,26 +832,35 @@ void kernfs_drain_open_files(struct kernfs_node *kn) * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ +unsigned int kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) +{ + struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry); + struct kernfs_open_node *on = kn->attr.open; + + poll_wait(of->file, &on->poll, wait); + + if (of->event != atomic_read(&on->event)) + return DEFAULT_POLLMASK|POLLERR|POLLPRI; + + return DEFAULT_POLLMASK; +} + static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); - struct kernfs_open_node *on = kn->attr.open; + unsigned int ret; if (!kernfs_get_active(kn)) - goto trigger; + return DEFAULT_POLLMASK|POLLERR|POLLPRI; - poll_wait(filp, &on->poll, wait); + if (kn->attr.ops->poll) + ret = kn->attr.ops->poll(of, wait); + else + ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); - - if (of->event != atomic_read(&on->event)) - goto trigger; - - return DEFAULT_POLLMASK; - - trigger: - return DEFAULT_POLLMASK|POLLERR|POLLPRI; + return ret; } static void kernfs_notify_workfn(struct work_struct *work) diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index ab25c8b6d9e3..caf4d07273bb 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -24,6 +24,7 @@ struct seq_file; struct vm_area_struct; struct super_block; struct file_system_type; +struct poll_table_struct; struct kernfs_open_node; struct kernfs_iattrs; @@ -260,6 +261,9 @@ struct kernfs_ops { ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); + unsigned int (*poll)(struct kernfs_open_file *of, + struct poll_table_struct *pt); + int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -347,6 +351,8 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns); int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); +unsigned int kernfs_generic_poll(struct kernfs_open_file *of, + struct poll_table_struct *pt); void kernfs_notify(struct kernfs_node *kn); const void *kernfs_super_ns(struct super_block *sb); -- GitLab From 90ed659d1720ee624885c8f8c67144b38b3d911f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 31 Jan 2019 10:41:54 +1100 Subject: [PATCH 0249/1128] BACKPORT: kernel: cgroup: add poll file operation Cgroup has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-3-surenb@google.com Signed-off-by: Johannes Weiner Signed-off-by: Suren Baghdasaryan Cc: Dennis Zhou Cc: Ingo Molnar Cc: Jens Axboe Cc: Li Zefan Cc: Peter Zijlstra Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Stephen Rothwell (cherry picked from commit: dc50537bdd1a0804fa2cbc990565ee9a944e66fa) Conflicts: include/linux/cgroup-defs.h kernel/cgroup.c (1. replaced __poll_t with unsigned int) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I21aff1d9d31e3d4b45e257aa4d299405a2ce6de3 Signed-off-by: Suren Baghdasaryan --- include/linux/cgroup-defs.h | 4 ++++ kernel/cgroup/cgroup.c | 13 +++++++++++++ 2 files changed, 17 insertions(+) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index f113ebd940e0..11117351b8f2 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -31,6 +31,7 @@ struct kernfs_node; struct kernfs_ops; struct kernfs_open_file; struct seq_file; +struct poll_table_struct; #define MAX_CGROUP_TYPE_NAMELEN 32 #define MAX_CGROUP_ROOT_NAMELEN 64 @@ -502,6 +503,9 @@ struct cftype { ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); + unsigned int (*poll)(struct kernfs_open_file *of, + struct poll_table_struct *pt); + #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; #endif diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 1742c6e1c1b9..d20a96ed6af0 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3412,6 +3412,17 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, return ret ?: nbytes; } +static unsigned int cgroup_file_poll(struct kernfs_open_file *of, + poll_table *pt) +{ + struct cftype *cft = of->kn->priv; + + if (cft->poll) + return cft->poll(of, pt); + + return kernfs_generic_poll(of, pt); +} + static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { return seq_cft(seq)->seq_start(seq, ppos); @@ -3450,6 +3461,7 @@ static struct kernfs_ops cgroup_kf_single_ops = { .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, + .poll = cgroup_file_poll, .seq_show = cgroup_seqfile_show, }; @@ -3458,6 +3470,7 @@ static struct kernfs_ops cgroup_kf_ops = { .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, + .poll = cgroup_file_poll, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, -- GitLab From 740617b2f48fe6097b8bb6f51366b8cbfb5a8236 Mon Sep 17 00:00:00 2001 From: Alistair Strachan Date: Fri, 22 Mar 2019 14:10:59 -0700 Subject: [PATCH 0250/1128] ANDROID: cuttlefish_defconfig: Enable CONFIG_PSI Bug: 120439617 Bug: 127712811 Change-Id: Id3531e3573ccea1720047d502288f60ee151cbff Signed-off-by: Alistair Strachan --- arch/arm64/configs/cuttlefish_defconfig | 1 + arch/x86/configs/x86_64_cuttlefish_defconfig | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/arm64/configs/cuttlefish_defconfig b/arch/arm64/configs/cuttlefish_defconfig index 6ff030934027..e6c3dcad412e 100644 --- a/arch/arm64/configs/cuttlefish_defconfig +++ b/arch/arm64/configs/cuttlefish_defconfig @@ -6,6 +6,7 @@ CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_PSI=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_MEMCG=y diff --git a/arch/x86/configs/x86_64_cuttlefish_defconfig b/arch/x86/configs/x86_64_cuttlefish_defconfig index d27e3ce9a5c0..8afd1a141c78 100644 --- a/arch/x86/configs/x86_64_cuttlefish_defconfig +++ b/arch/x86/configs/x86_64_cuttlefish_defconfig @@ -9,6 +9,7 @@ CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_PSI=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_CGROUPS=y -- GitLab From 74ca8857fffd27621baaf302bc4e68d3d04084e8 Mon Sep 17 00:00:00 2001 From: Alistair Strachan Date: Fri, 22 Mar 2019 16:52:47 -0700 Subject: [PATCH 0251/1128] ANDROID: cuttlefish_defconfig: Enable CONFIG_INPUT_MOUSEDEV Bug: 120439617 Bug: 128633328 Change-Id: I2186d8070f7885937925a25e85ce7b5722a73d57 Signed-off-by: Alistair Strachan --- arch/x86/configs/x86_64_cuttlefish_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/configs/x86_64_cuttlefish_defconfig b/arch/x86/configs/x86_64_cuttlefish_defconfig index 8afd1a141c78..ec2686d8abc2 100644 --- a/arch/x86/configs/x86_64_cuttlefish_defconfig +++ b/arch/x86/configs/x86_64_cuttlefish_defconfig @@ -267,6 +267,7 @@ CONFIG_USB_USBNET=y # CONFIG_WLAN_VENDOR_QUANTENNA is not set CONFIG_MAC80211_HWSIM=y CONFIG_VIRT_WIFI=y +CONFIG_INPUT_MOUSEDEV=y CONFIG_INPUT_EVDEV=y CONFIG_INPUT_KEYRESET=y # CONFIG_INPUT_KEYBOARD is not set -- GitLab From 4161b2837c52acabfbd4e39fb0e688d6b1e2f913 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 31 Jan 2019 10:41:54 +1100 Subject: [PATCH 0252/1128] FROMLIST: psi: introduce state_mask to represent stalled psi states The psi monitoring patches will need to determine the same states as record_times(). To avoid calculating them twice, maintain a state mask that can be consulted cheaply. Do this in a separate patch to keep the churn in the main feature patch at a minimum. This adds 4-byte state_mask member into psi_group_cpu struct which results in its first cacheline-aligned part becoming 52 bytes long. Add explicit values to enumeration element counters that affect psi_group_cpu struct size. Link: http://lkml.kernel.org/r/20190124211518.244221-4-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Johannes Weiner Cc: Dennis Zhou Cc: Ingo Molnar Cc: Jens Axboe Cc: Li Zefan Cc: Peter Zijlstra Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Stephen Rothwell (not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052414/) Bug: 127712811 Bug: 129157727 Test: lmkd in PSI mode Change-Id: I7807b687e2a5d78aed44c5e33be1621aa11451cb Signed-off-by: Suren Baghdasaryan --- include/linux/psi_types.h | 9 ++++++--- kernel/sched/psi.c | 29 +++++++++++++++++++---------- 2 files changed, 25 insertions(+), 13 deletions(-) diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 2cf422db5d18..762c6bb16f3c 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -11,7 +11,7 @@ enum psi_task_count { NR_IOWAIT, NR_MEMSTALL, NR_RUNNING, - NR_PSI_TASK_COUNTS, + NR_PSI_TASK_COUNTS = 3, }; /* Task state bitmasks */ @@ -24,7 +24,7 @@ enum psi_res { PSI_IO, PSI_MEM, PSI_CPU, - NR_PSI_RESOURCES, + NR_PSI_RESOURCES = 3, }; /* @@ -41,7 +41,7 @@ enum psi_states { PSI_CPU_SOME, /* Only per-CPU, to weigh the CPU in the global average: */ PSI_NONIDLE, - NR_PSI_STATES, + NR_PSI_STATES = 6, }; struct psi_group_cpu { @@ -53,6 +53,9 @@ struct psi_group_cpu { /* States of the tasks belonging to this group */ unsigned int tasks[NR_PSI_TASK_COUNTS]; + /* Aggregate pressure state derived from the tasks */ + u32 state_mask; + /* Period time sampling buckets for each state of interest (ns) */ u32 times[NR_PSI_STATES]; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 0e97ca9306ef..22c1505ad290 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -213,17 +213,17 @@ static bool test_state(unsigned int *tasks, enum psi_states state) static void get_recent_times(struct psi_group *group, int cpu, u32 *times) { struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); - unsigned int tasks[NR_PSI_TASK_COUNTS]; u64 now, state_start; + enum psi_states s; unsigned int seq; - int s; + u32 state_mask; /* Snapshot a coherent view of the CPU state */ do { seq = read_seqcount_begin(&groupc->seq); now = cpu_clock(cpu); memcpy(times, groupc->times, sizeof(groupc->times)); - memcpy(tasks, groupc->tasks, sizeof(groupc->tasks)); + state_mask = groupc->state_mask; state_start = groupc->state_start; } while (read_seqcount_retry(&groupc->seq, seq)); @@ -239,7 +239,7 @@ static void get_recent_times(struct psi_group *group, int cpu, u32 *times) * (u32) and our reported pressure close to what's * actually happening. */ - if (test_state(tasks, s)) + if (state_mask & (1 << s)) times[s] += now - state_start; delta = times[s] - groupc->times_prev[s]; @@ -407,15 +407,15 @@ static void record_times(struct psi_group_cpu *groupc, int cpu, delta = now - groupc->state_start; groupc->state_start = now; - if (test_state(groupc->tasks, PSI_IO_SOME)) { + if (groupc->state_mask & (1 << PSI_IO_SOME)) { groupc->times[PSI_IO_SOME] += delta; - if (test_state(groupc->tasks, PSI_IO_FULL)) + if (groupc->state_mask & (1 << PSI_IO_FULL)) groupc->times[PSI_IO_FULL] += delta; } - if (test_state(groupc->tasks, PSI_MEM_SOME)) { + if (groupc->state_mask & (1 << PSI_MEM_SOME)) { groupc->times[PSI_MEM_SOME] += delta; - if (test_state(groupc->tasks, PSI_MEM_FULL)) + if (groupc->state_mask & (1 << PSI_MEM_FULL)) groupc->times[PSI_MEM_FULL] += delta; else if (memstall_tick) { u32 sample; @@ -436,10 +436,10 @@ static void record_times(struct psi_group_cpu *groupc, int cpu, } } - if (test_state(groupc->tasks, PSI_CPU_SOME)) + if (groupc->state_mask & (1 << PSI_CPU_SOME)) groupc->times[PSI_CPU_SOME] += delta; - if (test_state(groupc->tasks, PSI_NONIDLE)) + if (groupc->state_mask & (1 << PSI_NONIDLE)) groupc->times[PSI_NONIDLE] += delta; } @@ -448,6 +448,8 @@ static void psi_group_change(struct psi_group *group, int cpu, { struct psi_group_cpu *groupc; unsigned int t, m; + enum psi_states s; + u32 state_mask = 0; groupc = per_cpu_ptr(group->pcpu, cpu); @@ -480,6 +482,13 @@ static void psi_group_change(struct psi_group *group, int cpu, if (set & (1 << t)) groupc->tasks[t]++; + /* Calculate state mask representing active states */ + for (s = 0; s < NR_PSI_STATES; s++) { + if (test_state(groupc->tasks, s)) + state_mask |= (1 << s); + } + groupc->state_mask = state_mask; + write_seqcount_end(&groupc->seq); } -- GitLab From 76c9304a6e995e2b22d8bb251d8ef7c6c0d3c682 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 31 Jan 2019 10:41:54 +1100 Subject: [PATCH 0253/1128] FROMLIST: psi: make psi_enable static psi_enable is not used outside of psi.c, make it static. Suggested-by: Andrew Morton Signed-off-by: Suren Baghdasaryan (not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052415/) Bug: 127712811 Bug: 129157727 Test: lmkd in PSI mode Change-Id: I3c422d6c0c4299095c6ba05cfe942a2b00705f29 Signed-off-by: Suren Baghdasaryan --- kernel/sched/psi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 22c1505ad290..281702de9772 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -140,9 +140,9 @@ static int psi_bug __read_mostly; DEFINE_STATIC_KEY_FALSE(psi_disabled); #ifdef CONFIG_PSI_DEFAULT_DISABLED -bool psi_enable; +static bool psi_enable; #else -bool psi_enable = true; +static bool psi_enable = true; #endif static int __init setup_psi(char *str) { -- GitLab From 28d1bd44e94d613d33d621db1099bb0a1fdfb119 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 6 Mar 2019 09:21:03 -0800 Subject: [PATCH 0254/1128] FROMLIST: psi: rename psi fields in preparation for psi trigger addition Renaming psi_group structure member fields used for calculating psi totals and averages for clear distinction between them and trigger-related fields that will be added next. Signed-off-by: Suren Baghdasaryan (not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052416/) Bug: 127712811 Bug: 129157727 Test: lmkd in PSI mode Change-Id: I7aaadfc558950b54b02a051d63e508e8fe233b49 Signed-off-by: Suren Baghdasaryan --- include/linux/psi_types.h | 14 ++++++------- kernel/sched/psi.c | 41 ++++++++++++++++++++------------------- 2 files changed, 28 insertions(+), 27 deletions(-) diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 762c6bb16f3c..4d1c1f67be18 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -69,17 +69,17 @@ struct psi_group_cpu { }; struct psi_group { - /* Protects data updated during an aggregation */ - struct mutex stat_lock; + /* Protects data used by the aggregator */ + struct mutex avgs_lock; /* Per-cpu task state & time tracking */ struct psi_group_cpu __percpu *pcpu; - /* Periodic aggregation state */ - u64 total_prev[NR_PSI_STATES - 1]; - u64 last_update; - u64 next_update; - struct delayed_work clock_work; + /* Running pressure averages */ + u64 avg_total[NR_PSI_STATES - 1]; + u64 avg_last_update; + u64 avg_next_update; + struct delayed_work avgs_work; /* Total stall times and sampled pressure averages */ u64 total[NR_PSI_STATES - 1]; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 281702de9772..4fb4d9913bc8 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -165,7 +165,7 @@ static struct psi_group psi_system = { .pcpu = &system_group_pcpu, }; -static void psi_update_work(struct work_struct *work); +static void psi_avgs_work(struct work_struct *work); static void group_init(struct psi_group *group) { @@ -173,9 +173,9 @@ static void group_init(struct psi_group *group) for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); - group->next_update = sched_clock() + psi_period; - INIT_DELAYED_WORK(&group->clock_work, psi_update_work); - mutex_init(&group->stat_lock); + group->avg_next_update = sched_clock() + psi_period; + INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); + mutex_init(&group->avgs_lock); } void __init psi_init(void) @@ -278,7 +278,7 @@ static bool update_stats(struct psi_group *group) int cpu; int s; - mutex_lock(&group->stat_lock); + mutex_lock(&group->avgs_lock); /* * Collect the per-cpu time buckets and average them into a @@ -319,7 +319,7 @@ static bool update_stats(struct psi_group *group) /* avgX= */ now = sched_clock(); - expires = group->next_update; + expires = group->avg_next_update; if (now < expires) goto out; if (now - expires >= psi_period) @@ -332,14 +332,14 @@ static bool update_stats(struct psi_group *group) * But the deltas we sample out of the per-cpu buckets above * are based on the actual time elapsing between clock ticks. */ - group->next_update = expires + ((1 + missed_periods) * psi_period); - period = now - (group->last_update + (missed_periods * psi_period)); - group->last_update = now; + group->avg_next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->avg_last_update + (missed_periods * psi_period)); + group->avg_last_update = now; for (s = 0; s < NR_PSI_STATES - 1; s++) { u32 sample; - sample = group->total[s] - group->total_prev[s]; + sample = group->total[s] - group->avg_total[s]; /* * Due to the lockless sampling of the time buckets, * recorded time deltas can slip into the next period, @@ -359,22 +359,22 @@ static bool update_stats(struct psi_group *group) */ if (sample > period) sample = period; - group->total_prev[s] += sample; + group->avg_total[s] += sample; calc_avgs(group->avg[s], missed_periods, sample, period); } out: - mutex_unlock(&group->stat_lock); + mutex_unlock(&group->avgs_lock); return nonidle_total; } -static void psi_update_work(struct work_struct *work) +static void psi_avgs_work(struct work_struct *work) { struct delayed_work *dwork; struct psi_group *group; bool nonidle; dwork = to_delayed_work(work); - group = container_of(dwork, struct psi_group, clock_work); + group = container_of(dwork, struct psi_group, avgs_work); /* * If there is task activity, periodically fold the per-cpu @@ -391,8 +391,9 @@ static void psi_update_work(struct work_struct *work) u64 now; now = sched_clock(); - if (group->next_update > now) - delay = nsecs_to_jiffies(group->next_update - now) + 1; + if (group->avg_next_update > now) + delay = nsecs_to_jiffies( + group->avg_next_update - now) + 1; schedule_delayed_work(dwork, delay); } } @@ -546,13 +547,13 @@ void psi_task_change(struct task_struct *task, int clear, int set) */ if (unlikely((clear & TSK_RUNNING) && (task->flags & PF_WQ_WORKER) && - wq_worker_last_func(task) == psi_update_work)) + wq_worker_last_func(task) == psi_avgs_work)) wake_clock = false; while ((group = iterate_groups(task, &iter))) { psi_group_change(group, cpu, clear, set); - if (wake_clock && !delayed_work_pending(&group->clock_work)) - schedule_delayed_work(&group->clock_work, PSI_FREQ); + if (wake_clock && !delayed_work_pending(&group->avgs_work)) + schedule_delayed_work(&group->avgs_work, PSI_FREQ); } } @@ -649,7 +650,7 @@ void psi_cgroup_free(struct cgroup *cgroup) if (static_branch_likely(&psi_disabled)) return; - cancel_delayed_work_sync(&cgroup->psi.clock_work); + cancel_delayed_work_sync(&cgroup->psi.avgs_work); free_percpu(cgroup->psi.pcpu); } -- GitLab From 20b2b1b5e28127b7b9a09ae121ee461951b1fce4 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 6 Mar 2019 09:52:23 -0800 Subject: [PATCH 0255/1128] FROMLIST: psi: split update_stats into parts Split update_stats into collect_percpu_times and update_averages for collect_percpu_times to be reused later inside psi monitor. Signed-off-by: Suren Baghdasaryan (not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052419/) Bug: 127712811 Bug: 129157727 Test: lmkd in PSI mode Change-Id: Ic5dca1924a3f8997b49b5d16289f53bcc43b88fa Signed-off-by: Suren Baghdasaryan --- kernel/sched/psi.c | 57 +++++++++++++++++++++++++++------------------- 1 file changed, 34 insertions(+), 23 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 4fb4d9913bc8..ace5ed97b186 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -269,17 +269,13 @@ static void calc_avgs(unsigned long avg[3], int missed_periods, avg[2] = calc_load(avg[2], EXP_300s, pct); } -static bool update_stats(struct psi_group *group) +static bool collect_percpu_times(struct psi_group *group) { u64 deltas[NR_PSI_STATES - 1] = { 0, }; - unsigned long missed_periods = 0; unsigned long nonidle_total = 0; - u64 now, expires, period; int cpu; int s; - mutex_lock(&group->avgs_lock); - /* * Collect the per-cpu time buckets and average them into a * single time sample that is normalized to wallclock time. @@ -317,11 +313,18 @@ static bool update_stats(struct psi_group *group) for (s = 0; s < NR_PSI_STATES - 1; s++) group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL)); + return nonidle_total; +} + +static u64 update_averages(struct psi_group *group, u64 now) +{ + unsigned long missed_periods = 0; + u64 expires, period; + u64 avg_next_update; + int s; + /* avgX= */ - now = sched_clock(); expires = group->avg_next_update; - if (now < expires) - goto out; if (now - expires >= psi_period) missed_periods = div_u64(now - expires, psi_period); @@ -332,7 +335,7 @@ static bool update_stats(struct psi_group *group) * But the deltas we sample out of the per-cpu buckets above * are based on the actual time elapsing between clock ticks. */ - group->avg_next_update = expires + ((1 + missed_periods) * psi_period); + avg_next_update = expires + ((1 + missed_periods) * psi_period); period = now - (group->avg_last_update + (missed_periods * psi_period)); group->avg_last_update = now; @@ -362,9 +365,8 @@ static bool update_stats(struct psi_group *group) group->avg_total[s] += sample; calc_avgs(group->avg[s], missed_periods, sample, period); } -out: - mutex_unlock(&group->avgs_lock); - return nonidle_total; + + return avg_next_update; } static void psi_avgs_work(struct work_struct *work) @@ -372,10 +374,16 @@ static void psi_avgs_work(struct work_struct *work) struct delayed_work *dwork; struct psi_group *group; bool nonidle; + u64 now; dwork = to_delayed_work(work); group = container_of(dwork, struct psi_group, avgs_work); + mutex_lock(&group->avgs_lock); + + now = sched_clock(); + + nonidle = collect_percpu_times(group); /* * If there is task activity, periodically fold the per-cpu * times and feed samples into the running averages. If things @@ -383,19 +391,15 @@ static void psi_avgs_work(struct work_struct *work) * Once restarted, we'll catch up the running averages in one * go - see calc_avgs() and missed_periods. */ - - nonidle = update_stats(group); + if (now >= group->avg_next_update) + group->avg_next_update = update_averages(group, now); if (nonidle) { - unsigned long delay = 0; - u64 now; - - now = sched_clock(); - if (group->avg_next_update > now) - delay = nsecs_to_jiffies( - group->avg_next_update - now) + 1; - schedule_delayed_work(dwork, delay); + schedule_delayed_work(dwork, nsecs_to_jiffies( + group->avg_next_update - now) + 1); } + + mutex_unlock(&group->avgs_lock); } static void record_times(struct psi_group_cpu *groupc, int cpu, @@ -707,11 +711,18 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { int full; + u64 now; if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; - update_stats(group); + /* Update averages before reporting them */ + mutex_lock(&group->avgs_lock); + now = sched_clock(); + collect_percpu_times(group); + if (now >= group->avg_next_update) + group->avg_next_update = update_averages(group, now); + mutex_unlock(&group->avgs_lock); for (full = 0; full < 2 - (res == PSI_CPU); full++) { unsigned long avg[3]; -- GitLab From dd754874d9241cbd4a7457b2419c30f2924b0822 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 6 Mar 2019 10:25:50 -0800 Subject: [PATCH 0256/1128] FROMLIST: psi: track changed states Introduce changed_states parameter into collect_percpu_times to track the states changed since the last update. Signed-off-by: Suren Baghdasaryan (not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052420/) Bug: 127712811 Bug: 129157727 Test: lmkd in PSI mode Change-Id: Idb2f7d73013bff16bb101b62a2609917a5353bf9 Signed-off-by: Suren Baghdasaryan --- kernel/sched/psi.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ace5ed97b186..1b99eeffaa25 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -210,7 +210,8 @@ static bool test_state(unsigned int *tasks, enum psi_states state) } } -static void get_recent_times(struct psi_group *group, int cpu, u32 *times) +static void get_recent_times(struct psi_group *group, int cpu, u32 *times, + u32 *pchanged_states) { struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); u64 now, state_start; @@ -218,6 +219,8 @@ static void get_recent_times(struct psi_group *group, int cpu, u32 *times) unsigned int seq; u32 state_mask; + *pchanged_states = 0; + /* Snapshot a coherent view of the CPU state */ do { seq = read_seqcount_begin(&groupc->seq); @@ -246,6 +249,8 @@ static void get_recent_times(struct psi_group *group, int cpu, u32 *times) groupc->times_prev[s] = times[s]; times[s] = delta; + if (delta) + *pchanged_states |= (1 << s); } } @@ -269,10 +274,11 @@ static void calc_avgs(unsigned long avg[3], int missed_periods, avg[2] = calc_load(avg[2], EXP_300s, pct); } -static bool collect_percpu_times(struct psi_group *group) +static void collect_percpu_times(struct psi_group *group, u32 *pchanged_states) { u64 deltas[NR_PSI_STATES - 1] = { 0, }; unsigned long nonidle_total = 0; + u32 changed_states = 0; int cpu; int s; @@ -287,8 +293,11 @@ static bool collect_percpu_times(struct psi_group *group) for_each_possible_cpu(cpu) { u32 times[NR_PSI_STATES]; u32 nonidle; + u32 cpu_changed_states; - get_recent_times(group, cpu, times); + get_recent_times(group, cpu, times, + &cpu_changed_states); + changed_states |= cpu_changed_states; nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]); nonidle_total += nonidle; @@ -313,7 +322,8 @@ static bool collect_percpu_times(struct psi_group *group) for (s = 0; s < NR_PSI_STATES - 1; s++) group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL)); - return nonidle_total; + if (pchanged_states) + *pchanged_states = changed_states; } static u64 update_averages(struct psi_group *group, u64 now) @@ -373,6 +383,7 @@ static void psi_avgs_work(struct work_struct *work) { struct delayed_work *dwork; struct psi_group *group; + u32 changed_states; bool nonidle; u64 now; @@ -383,7 +394,8 @@ static void psi_avgs_work(struct work_struct *work) now = sched_clock(); - nonidle = collect_percpu_times(group); + collect_percpu_times(group, &changed_states); + nonidle = changed_states & (1 << PSI_NONIDLE); /* * If there is task activity, periodically fold the per-cpu * times and feed samples into the running averages. If things @@ -719,7 +731,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) /* Update averages before reporting them */ mutex_lock(&group->avgs_lock); now = sched_clock(); - collect_percpu_times(group); + collect_percpu_times(group, NULL); if (now >= group->avg_next_update) group->avg_next_update = update_averages(group, now); mutex_unlock(&group->avgs_lock); -- GitLab From 4c08ee4e58d5ded6d4468333890d078cbaf2a28b Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Sun, 17 Feb 2019 15:07:38 -0800 Subject: [PATCH 0257/1128] FROMLIST: refactor header includes to allow kthread.h inclusion in psi_types.h kthread.h can't be included in psi_types.h because it creates a circular inclusion with kthread.h eventually including psi_types.h and complaining on kthread structures not being defined because they are defined further in the kthread.h. Resolve this by removing psi_types.h inclusion from the headers included from kthread.h. Signed-off-by: Suren Baghdasaryan (not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052417/) Conflicts: include/linux/kthread.h kernel/kthread.c (1. include is already missing in kthread.h 2. is already included in kthread.c) Bug: 127712811 Bug: 129157727 Test: lmkd in PSI mode Change-Id: I07c1f4fddf0c43b3095f505e062d9d179d041544 Signed-off-by: Suren Baghdasaryan --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index a5e47b74d6bf..2d86c0eeee49 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,7 +25,6 @@ #include #include #include -#include #include #include -- GitLab From a58d5685c5d9e7d39632cd21a4d339847a63e92c Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 3 Dec 2018 17:36:42 -0800 Subject: [PATCH 0258/1128] FROMLIST: psi: introduce psi monitor Psi monitor aims to provide a low-latency short-term pressure detection mechanism configurable by users. It allows users to monitor psi metrics growth and trigger events whenever a metric raises above user-defined threshold within user-defined time window. Time window and threshold are both expressed in usecs. Multiple psi resources with different thresholds and window sizes can be monitored concurrently. Psi monitors activate when system enters stall state for the monitored psi metric and deactivate upon exit from the stall state. While system is in the stall state psi signal growth is monitored at a rate of 10 times per tracking window. Min window size is 500ms, therefore the min monitoring interval is 50ms. Max window size is 10s with monitoring interval of 1s. When activated psi monitor stays active for at least the duration of one tracking window to avoid repeated activations/deactivations when psi signal is bouncing. Notifications to the users are rate-limited to one per tracking window. Signed-off-by: Suren Baghdasaryan Signed-off-by: Johannes Weiner (not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052418/) Conflicts: include/linux/psi.h kernel/cgroup/cgroup.c kernel/sched/psi.c (1. replaced __poll_t with unsigned int 2. replaced EPOLLERR/EPOLLPRI with POLLERR/POLLPRI (values are the same) 3. include in include/linux/psi.h 4. include in kernel/sched/psi.c) Bug: 127712811 Bug: 129157727 Test: lmkd in PSI mode Change-Id: I1688f047e98e1f109627dad72a33d2f70e575268 Signed-off-by: Suren Baghdasaryan --- Documentation/accounting/psi.txt | 107 +++++++ include/linux/psi.h | 8 + include/linux/psi_types.h | 82 ++++- kernel/cgroup/cgroup.c | 71 ++++- kernel/sched/psi.c | 495 ++++++++++++++++++++++++++++++- 5 files changed, 743 insertions(+), 20 deletions(-) diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt index b8ca28b60215..4fb40fe94828 100644 --- a/Documentation/accounting/psi.txt +++ b/Documentation/accounting/psi.txt @@ -63,6 +63,110 @@ tracked and exported as well, to allow detection of latency spikes which wouldn't necessarily make a dent in the time averages, or to average trends over custom time frames. +Monitoring for pressure thresholds +================================== + +Users can register triggers and use poll() to be woken up when resource +pressure exceeds certain thresholds. + +A trigger describes the maximum cumulative stall time over a specific +time window, e.g. 100ms of total stall time within any 500ms window to +generate a wakeup event. + +To register a trigger user has to open psi interface file under +/proc/pressure/ representing the resource to be monitored and write the +desired threshold and time window. The open file descriptor should be +used to wait for trigger events using select(), poll() or epoll(). +The following format is used: + +