From b3fcb70064065bd1aa2083d98a5ec711d099a1ee Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 14 Dec 2016 10:12:56 -0800 Subject: f2fs: support IO alignment for DATA and NODE writes commit 0a595ebaaa6b53a2226d3fee2a2fd616ea5ba378 upstream. This patch implements IO alignment by filling dummy blocks in DATA and NODE write bios. If we can guarantee, for example, 32KB or 64KB for such the IOs, we can eliminate underlying dummy page problem which FTL conducts in order to close MLC or TLC partial written pages. Note that, - it requires "-o mode=lfs". - IO size should be power of 2, not exceed BIO_MAX_PAGES, 256. - read IO is still 4KB. - do checkpoint at fsync, if dummy NODE page was written. Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 3e5972ef5019..cf54a312993f 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -36,6 +36,12 @@ #define F2FS_NODE_INO(sbi) (sbi->node_ino_num) #define F2FS_META_INO(sbi) (sbi->meta_ino_num) +#define F2FS_IO_SIZE(sbi) (1 << (sbi)->write_io_size_bits) /* Blocks */ +#define F2FS_IO_SIZE_KB(sbi) (1 << ((sbi)->write_io_size_bits + 2)) /* KB */ +#define F2FS_IO_SIZE_BYTES(sbi) (1 << ((sbi)->write_io_size_bits + 12)) /* B */ +#define F2FS_IO_SIZE_BITS(sbi) ((sbi)->write_io_size_bits) /* power of 2 */ +#define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1) + /* This flag is used by node and meta inodes, and by recovery */ #define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO) #define GFP_F2FS_HIGH_ZERO (GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM) -- cgit v1.2.3 From 13f002354db13a029aef84aa1a8bfa51bd6b8d56 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 9 Jan 2017 18:16:29 -0800 Subject: f2fs: catch up to v4.14-rc1 This is cherry-picked from upstrea-f2fs-stable-linux-4.4.y. Changes include: commit c7fd9e2b4a6876 ("f2fs: hurry up to issue discard after io interruption") commit 603dde39653d6d ("f2fs: fix to show correct discard_granularity in sysfs") ... commit 565f0225f95f15 ("f2fs: factor out discard command info into discard_cmd_control") commit c4cc29d19eaf01 ("f2fs: remove batched discard in f2fs_trim_fs") Change-Id: Icd8a85ac0c19a8aa25cd2591a12b4e9b85bdf1c5 Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 43 +++++----- include/linux/fscrypt_common.h | 138 +++++++++++++++++++++++++++++++ include/linux/fscrypt_notsupp.h | 177 ++++++++++++++++++++++++++++++++++++++++ include/linux/fscrypt_supp.h | 145 ++++++++++++++++++++++++++++++++ include/linux/fscrypto.h | 12 +-- 5 files changed, 485 insertions(+), 30 deletions(-) create mode 100644 include/linux/fscrypt_common.h create mode 100644 include/linux/fscrypt_notsupp.h create mode 100644 include/linux/fscrypt_supp.h (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index cf54a312993f..c2a975e4a711 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -114,6 +114,8 @@ struct f2fs_super_block { /* * For checkpoint */ +#define CP_TRIMMED_FLAG 0x00000100 +#define CP_NAT_BITS_FLAG 0x00000080 #define CP_CRC_RECOVERY_FLAG 0x00000040 #define CP_FASTBOOT_FLAG 0x00000020 #define CP_FSCK_FLAG 0x00000010 @@ -184,6 +186,8 @@ struct f2fs_extent { #define F2FS_NAME_LEN 255 #define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */ #define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ +#define CUR_ADDRS_PER_INODE(inode) (DEF_ADDRS_PER_INODE - \ + get_extra_isize(inode)) #define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */ #define ADDRS_PER_INODE(inode) addrs_per_inode(inode) #define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ @@ -203,9 +207,7 @@ struct f2fs_extent { #define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */ #define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */ #define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */ - -#define MAX_INLINE_DATA (sizeof(__le32) * (DEF_ADDRS_PER_INODE - \ - F2FS_INLINE_XATTR_ADDRS - 1)) +#define F2FS_EXTRA_ATTR 0x20 /* file having extra attribute */ struct f2fs_inode { __le16 i_mode; /* file mode */ @@ -233,8 +235,16 @@ struct f2fs_inode { struct f2fs_extent i_ext; /* caching a largest extent */ - __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ - + union { + struct { + __le16 i_extra_isize; /* extra inode attribute size */ + __le16 i_padding; /* padding */ + __le32 i_projid; /* project id */ + __le32 i_inode_checksum;/* inode meta checksum */ + __le32 i_extra_end[0]; /* for attribute size calculation */ + }; + __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ + }; __le32 i_nid[DEF_NIDS_PER_INODE]; /* direct(2), indirect(2), double_indirect(1) node id */ } __packed; @@ -278,6 +288,7 @@ struct f2fs_node { * For NAT entries */ #define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry)) +#define NAT_ENTRY_BITMAP_SIZE ((NAT_ENTRY_PER_BLOCK + 7) / 8) struct f2fs_nat_entry { __u8 version; /* latest version of cached nat entry */ @@ -462,7 +473,7 @@ typedef __le32 f2fs_hash_t; #define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1)) /* - * space utilization of regular dentry and inline dentry + * 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 @@ -498,24 +509,6 @@ struct f2fs_dentry_block { __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN]; } __packed; -/* for inline dir */ -#define NR_INLINE_DENTRY (MAX_INLINE_DATA * BITS_PER_BYTE / \ - ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ - BITS_PER_BYTE + 1)) -#define INLINE_DENTRY_BITMAP_SIZE ((NR_INLINE_DENTRY + \ - BITS_PER_BYTE - 1) / BITS_PER_BYTE) -#define INLINE_RESERVED_SIZE (MAX_INLINE_DATA - \ - ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ - NR_INLINE_DENTRY + INLINE_DENTRY_BITMAP_SIZE)) - -/* inline directory entry structure */ -struct f2fs_inline_dentry { - __u8 dentry_bitmap[INLINE_DENTRY_BITMAP_SIZE]; - __u8 reserved[INLINE_RESERVED_SIZE]; - struct f2fs_dir_entry dentry[NR_INLINE_DENTRY]; - __u8 filename[NR_INLINE_DENTRY][F2FS_SLOT_LEN]; -} __packed; - /* file types used in inode_info->flags */ enum { F2FS_FT_UNKNOWN, @@ -531,4 +524,6 @@ enum { #define S_SHIFT 12 +#define F2FS_DEF_PROJID 0 /* default project ID */ + #endif /* _LINUX_F2FS_FS_H */ diff --git a/include/linux/fscrypt_common.h b/include/linux/fscrypt_common.h new file mode 100644 index 000000000000..4022c61f7e9b --- /dev/null +++ b/include/linux/fscrypt_common.h @@ -0,0 +1,138 @@ +/* + * fscrypt_common.h: common declarations for per-file encryption + * + * Copyright (C) 2015, Google, Inc. + * + * Written by Michael Halcrow, 2015. + * Modified by Jaegeuk Kim, 2015. + */ + +#ifndef _LINUX_FSCRYPT_COMMON_H +#define _LINUX_FSCRYPT_COMMON_H + +#include +#include +#include +#include +#include +#include +#include + +#define FS_CRYPTO_BLOCK_SIZE 16 + +struct fscrypt_info; + +struct fscrypt_ctx { + union { + struct { + struct page *bounce_page; /* Ciphertext page */ + struct page *control_page; /* Original page */ + } w; + struct { + struct bio *bio; + struct work_struct work; + } r; + struct list_head free_list; /* Free list */ + }; + u8 flags; /* Flags */ +}; + +/** + * For encrypted symlinks, the ciphertext length is stored at the beginning + * of the string in little-endian format. + */ +struct fscrypt_symlink_data { + __le16 len; + char encrypted_path[1]; +} __packed; + +struct fscrypt_str { + unsigned char *name; + u32 len; +}; + +struct fscrypt_name { + const struct qstr *usr_fname; + struct fscrypt_str disk_name; + u32 hash; + u32 minor_hash; + struct fscrypt_str crypto_buf; +}; + +#define FSTR_INIT(n, l) { .name = n, .len = l } +#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) +#define fname_name(p) ((p)->disk_name.name) +#define fname_len(p) ((p)->disk_name.len) + +/* + * fscrypt superblock flags + */ +#define FS_CFLG_OWN_PAGES (1U << 1) + +/* + * crypto opertions for filesystems + */ +struct fscrypt_operations { + unsigned int flags; + const char *key_prefix; + int (*get_context)(struct inode *, void *, size_t); + int (*set_context)(struct inode *, const void *, size_t, void *); + int (*dummy_context)(struct inode *); + bool (*is_encrypted)(struct inode *); + bool (*empty_dir)(struct inode *); + unsigned (*max_namelen)(struct inode *); +}; + +static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +{ + if (inode->i_sb->s_cop->dummy_context && + inode->i_sb->s_cop->dummy_context(inode)) + return true; + return false; +} + +static inline bool fscrypt_valid_enc_modes(u32 contents_mode, + u32 filenames_mode) +{ + if (contents_mode == FS_ENCRYPTION_MODE_AES_128_CBC && + filenames_mode == FS_ENCRYPTION_MODE_AES_128_CTS) + return true; + + if (contents_mode == FS_ENCRYPTION_MODE_AES_256_XTS && + filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS) + return true; + + return false; +} + +static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) +{ + if (str->len == 1 && str->name[0] == '.') + return true; + + if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') + return true; + + return false; +} + +static inline struct page *fscrypt_control_page(struct page *page) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + return ((struct fscrypt_ctx *)page_private(page))->w.control_page; +#else + WARN_ON_ONCE(1); + return ERR_PTR(-EINVAL); +#endif +} + +static inline int fscrypt_has_encryption_key(const struct inode *inode) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + return (inode->i_crypt_info != NULL); +#else + return 0; +#endif +} + +#endif /* _LINUX_FSCRYPT_COMMON_H */ diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h new file mode 100644 index 000000000000..ec406aed2f2f --- /dev/null +++ b/include/linux/fscrypt_notsupp.h @@ -0,0 +1,177 @@ +/* + * fscrypt_notsupp.h + * + * This stubs out the fscrypt functions for filesystems configured without + * encryption support. + */ + +#ifndef _LINUX_FSCRYPT_NOTSUPP_H +#define _LINUX_FSCRYPT_NOTSUPP_H + +#include + +/* crypto.c */ +static inline struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, + gfp_t gfp_flags) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx) +{ + return; +} + +static inline struct page *fscrypt_encrypt_page(const struct inode *inode, + struct page *page, + unsigned int len, + unsigned int offs, + u64 lblk_num, gfp_t gfp_flags) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline int fscrypt_decrypt_page(const struct inode *inode, + struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num) +{ + return -EOPNOTSUPP; +} + + +static inline void fscrypt_restore_control_page(struct page *page) +{ + return; +} + +static inline void fscrypt_set_d_op(struct dentry *dentry) +{ + return; +} + +static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) +{ + return; +} + +/* policy.c */ +static inline int fscrypt_ioctl_set_policy(struct file *filp, + const void __user *arg) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_has_permitted_context(struct inode *parent, + struct inode *child) +{ + return 0; +} + +static inline int fscrypt_inherit_context(struct inode *parent, + struct inode *child, + void *fs_data, bool preload) +{ + return -EOPNOTSUPP; +} + +/* keyinfo.c */ +static inline int fscrypt_get_encryption_info(struct inode *inode) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_put_encryption_info(struct inode *inode, + struct fscrypt_info *ci) +{ + return; +} + + /* fname.c */ +static inline int fscrypt_setup_filename(struct inode *dir, + const struct qstr *iname, + int lookup, struct fscrypt_name *fname) +{ + if (dir->i_sb->s_cop->is_encrypted(dir)) + return -EOPNOTSUPP; + + memset(fname, 0, sizeof(struct fscrypt_name)); + fname->usr_fname = iname; + fname->disk_name.name = (unsigned char *)iname->name; + fname->disk_name.len = iname->len; + return 0; +} + +static inline void fscrypt_free_filename(struct fscrypt_name *fname) +{ + return; +} + +static inline u32 fscrypt_fname_encrypted_size(const struct inode *inode, + u32 ilen) +{ + /* never happens */ + WARN_ON(1); + return 0; +} + +static inline int fscrypt_fname_alloc_buffer(const struct inode *inode, + u32 ilen, + struct fscrypt_str *crypto_str) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) +{ + return; +} + +static inline int fscrypt_fname_disk_to_usr(struct inode *inode, + u32 hash, u32 minor_hash, + const struct fscrypt_str *iname, + struct fscrypt_str *oname) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_fname_usr_to_disk(struct inode *inode, + const struct qstr *iname, + struct fscrypt_str *oname) +{ + return -EOPNOTSUPP; +} + +static inline bool fscrypt_match_name(const struct fscrypt_name *fname, + const u8 *de_name, u32 de_name_len) +{ + /* Encryption support disabled; use standard comparison */ + if (de_name_len != fname->disk_name.len) + return false; + return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); +} + +/* bio.c */ +static inline void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, + struct bio *bio) +{ + return; +} + +static inline void fscrypt_pullback_bio_page(struct page **page, bool restore) +{ + return; +} + +static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, + sector_t pblk, unsigned int len) +{ + return -EOPNOTSUPP; +} + +#endif /* _LINUX_FSCRYPT_NOTSUPP_H */ diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h new file mode 100644 index 000000000000..32e2fcf13b01 --- /dev/null +++ b/include/linux/fscrypt_supp.h @@ -0,0 +1,145 @@ +/* + * fscrypt_supp.h + * + * This is included by filesystems configured with encryption support. + */ + +#ifndef _LINUX_FSCRYPT_SUPP_H +#define _LINUX_FSCRYPT_SUPP_H + +#include + +/* crypto.c */ +extern struct kmem_cache *fscrypt_info_cachep; +extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); +extern void fscrypt_release_ctx(struct fscrypt_ctx *); +extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, + unsigned int, unsigned int, + u64, gfp_t); +extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int, + unsigned int, u64); +extern void fscrypt_restore_control_page(struct page *); + +extern const struct dentry_operations fscrypt_d_ops; + +static inline void fscrypt_set_d_op(struct dentry *dentry) +{ + d_set_d_op(dentry, &fscrypt_d_ops); +} + +static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY; + spin_unlock(&dentry->d_lock); +} + +/* policy.c */ +extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); +extern int fscrypt_ioctl_get_policy(struct file *, void __user *); +extern int fscrypt_has_permitted_context(struct inode *, struct inode *); +extern int fscrypt_inherit_context(struct inode *, struct inode *, + void *, bool); +/* keyinfo.c */ +extern int fscrypt_get_encryption_info(struct inode *); +extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *); + +/* fname.c */ +extern int fscrypt_setup_filename(struct inode *, const struct qstr *, + int lookup, struct fscrypt_name *); + +static inline void fscrypt_free_filename(struct fscrypt_name *fname) +{ + kfree(fname->crypto_buf.name); +} + +extern u32 fscrypt_fname_encrypted_size(const struct inode *, u32); +extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, + struct fscrypt_str *); +extern void fscrypt_fname_free_buffer(struct fscrypt_str *); +extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32, + const struct fscrypt_str *, struct fscrypt_str *); +extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *, + struct fscrypt_str *); + +#define FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE 32 + +/* Extracts the second-to-last ciphertext block; see explanation below */ +#define FSCRYPT_FNAME_DIGEST(name, len) \ + ((name) + round_down((len) - FS_CRYPTO_BLOCK_SIZE - 1, \ + FS_CRYPTO_BLOCK_SIZE)) + +#define FSCRYPT_FNAME_DIGEST_SIZE FS_CRYPTO_BLOCK_SIZE + +/** + * fscrypt_digested_name - alternate identifier for an on-disk filename + * + * When userspace lists an encrypted directory without access to the key, + * filenames whose ciphertext is longer than FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE + * bytes are shown in this abbreviated form (base64-encoded) rather than as the + * full ciphertext (base64-encoded). This is necessary to allow supporting + * filenames up to NAME_MAX bytes, since base64 encoding expands the length. + * + * To make it possible for filesystems to still find the correct directory entry + * despite not knowing the full on-disk name, we encode any filesystem-specific + * 'hash' and/or 'minor_hash' which the filesystem may need for its lookups, + * followed by the second-to-last ciphertext block of the filename. Due to the + * use of the CBC-CTS encryption mode, the second-to-last ciphertext block + * depends on the full plaintext. (Note that ciphertext stealing causes the + * last two blocks to appear "flipped".) This makes accidental collisions very + * unlikely: just a 1 in 2^128 chance for two filenames to collide even if they + * share the same filesystem-specific hashes. + * + * However, this scheme isn't immune to intentional collisions, which can be + * created by anyone able to create arbitrary plaintext filenames and view them + * without the key. Making the "digest" be a real cryptographic hash like + * SHA-256 over the full ciphertext would prevent this, although it would be + * less efficient and harder to implement, especially since the filesystem would + * need to calculate it for each directory entry examined during a search. + */ +struct fscrypt_digested_name { + u32 hash; + u32 minor_hash; + u8 digest[FSCRYPT_FNAME_DIGEST_SIZE]; +}; + +/** + * fscrypt_match_name() - test whether the given name matches a directory entry + * @fname: the name being searched for + * @de_name: the name from the directory entry + * @de_name_len: the length of @de_name in bytes + * + * Normally @fname->disk_name will be set, and in that case we simply compare + * that to the name stored in the directory entry. The only exception is that + * if we don't have the key for an encrypted directory and a filename in it is + * very long, then we won't have the full disk_name and we'll instead need to + * match against the fscrypt_digested_name. + * + * Return: %true if the name matches, otherwise %false. + */ +static inline bool fscrypt_match_name(const struct fscrypt_name *fname, + const u8 *de_name, u32 de_name_len) +{ + if (unlikely(!fname->disk_name.name)) { + const struct fscrypt_digested_name *n = + (const void *)fname->crypto_buf.name; + if (WARN_ON_ONCE(fname->usr_fname->name[0] != '_')) + return false; + if (de_name_len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) + return false; + return !memcmp(FSCRYPT_FNAME_DIGEST(de_name, de_name_len), + n->digest, FSCRYPT_FNAME_DIGEST_SIZE); + } + + if (de_name_len != fname->disk_name.len) + return false; + return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); +} + +/* bio.c */ +extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); +extern void fscrypt_pullback_bio_page(struct page **, bool); +extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, + unsigned int); + +#endif /* _LINUX_FSCRYPT_SUPP_H */ diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index ff8b11b26f31..e6e53a36104b 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -250,8 +250,8 @@ extern void fscrypt_restore_control_page(struct page *); extern int fscrypt_zeroout_range(struct inode *, pgoff_t, sector_t, unsigned int); /* policy.c */ -extern int fscrypt_process_policy(struct file *, const struct fscrypt_policy *); -extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *); +extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); +extern int fscrypt_ioctl_get_policy(struct file *, void __user *); extern int fscrypt_has_permitted_context(struct inode *, struct inode *); extern int fscrypt_inherit_context(struct inode *, struct inode *, void *, bool); @@ -320,14 +320,14 @@ static inline int fscrypt_notsupp_zeroout_range(struct inode *i, pgoff_t p, } /* policy.c */ -static inline int fscrypt_notsupp_process_policy(struct file *f, - const struct fscrypt_policy *p) +static inline int fscrypt_notsupp_ioctl_set_policy(struct file *f, + const void __user *arg) { return -EOPNOTSUPP; } -static inline int fscrypt_notsupp_get_policy(struct inode *i, - struct fscrypt_policy *p) +static inline int fscrypt_notsupp_ioctl_get_policy(struct file *f, + void __user *arg) { return -EOPNOTSUPP; } -- cgit v1.2.3 From 539255aea88e47932a98ba7656775cbca4f3d27c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Sep 2017 11:37:03 -0700 Subject: KEYS: prevent creating a different user's keyrings commit 237bbd29f7a049d310d907f4b2716a7feef9abf3 upstream. It was possible for an unprivileged user to create the user and user session keyrings for another user. For example: sudo -u '#3000' sh -c 'keyctl add keyring _uid.4000 "" @u keyctl add keyring _uid_ses.4000 "" @u sleep 15' & sleep 1 sudo -u '#4000' keyctl describe @u sudo -u '#4000' keyctl describe @us This is problematic because these "fake" keyrings won't have the right permissions. In particular, the user who created them first will own them and will have full access to them via the possessor permissions, which can be used to compromise the security of a user's keys: -4: alswrv-----v------------ 3000 0 keyring: _uid.4000 -5: alswrv-----v------------ 3000 0 keyring: _uid_ses.4000 Fix it by marking user and user session keyrings with a flag KEY_FLAG_UID_KEYRING. Then, when searching for a user or user session keyring by name, skip all keyrings that don't have the flag set. Fixes: 69664cf16af4 ("keys: don't generate user and user session keyrings unless they're accessed") Signed-off-by: Eric Biggers Signed-off-by: David Howells Signed-off-by: Greg Kroah-Hartman --- include/linux/key.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index 66f705243985..dcc115e8dd03 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -177,6 +177,7 @@ struct key { #define KEY_FLAG_TRUSTED_ONLY 9 /* set if keyring only accepts links to trusted keys */ #define KEY_FLAG_BUILTIN 10 /* set if key is builtin */ #define KEY_FLAG_ROOT_CAN_INVAL 11 /* set if key can be invalidated by root without permission */ +#define KEY_FLAG_UID_KEYRING 12 /* set if key is a user or user session keyring */ /* the key type and key description string * - the desc is used to match a key against search criteria @@ -218,6 +219,7 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_QUOTA_OVERRUN 0x0001 /* add to quota, permit even if overrun */ #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ #define KEY_ALLOC_TRUSTED 0x0004 /* Key should be flagged as trusted */ +#define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); -- cgit v1.2.3 From a85f176c857e4fe0d2c0b5d2c7090c422982e585 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Mon, 15 Feb 2016 21:57:46 +0100 Subject: dmaengine: mmp-pdma: add number of requestors commit c283e41ef32442f41e7180f9bb1c5aedf9255bfe upstream. The DMA chip has a fixed number of requestor lines used for flow control. This number is platform dependent. The pxa_dma dma driver will use this value to activate or not the flow control. There won't be any impact on mmp_pdma driver. Signed-off-by: Robert Jarzmik Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/mmp_dma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmp_dma.h b/include/linux/platform_data/mmp_dma.h index 2a330ec9e2af..d1397c8ed94e 100644 --- a/include/linux/platform_data/mmp_dma.h +++ b/include/linux/platform_data/mmp_dma.h @@ -14,6 +14,7 @@ struct mmp_dma_platdata { int dma_channels; + int nb_requestors; }; #endif /* MMP_DMA_H */ -- cgit v1.2.3 From e5486e9c8991aa5b55959c96b6b375645b12dad6 Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 5 Oct 2017 17:54:32 -0700 Subject: FROMLIST: tracing: Add support for preempt and irq enable/disable events Preempt and irq trace events can be used for tracing the start and end of an atomic section which can be used by a trace viewer like systrace to graphically view the start and end of an atomic section and correlate them with latencies and scheduling issues. This also serves as a prelude to using synthetic events or probes to rewrite the preempt and irqsoff tracers, along with numerous benefits of using trace events features for these events. Change-Id: I718d40f7c3c48579adf9d7121b21495a669c89bd Cc: Steven Rostedt Cc: Peter Zilstra Cc: kernel-team@android.com Link: https://patchwork.kernel.org/patch/9988157/ Signed-off-by: Joel Fernandes --- include/linux/ftrace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 60048c50404e..ed94cea9eaff 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -702,7 +702,8 @@ static inline void __ftrace_enabled_restore(int enabled) static inline void time_hardirqs_off(unsigned long a0, unsigned long a1) { } #endif -#ifdef CONFIG_PREEMPT_TRACER +#if defined(CONFIG_PREEMPT_TRACER) || \ + (defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS)) extern void trace_preempt_on(unsigned long a0, unsigned long a1); extern void trace_preempt_off(unsigned long a0, unsigned long a1); #else -- cgit v1.2.3 From 093fe104c5bbd99b4934bd80216b6e6d7371c4fc Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 17 Jan 2017 11:07:15 -0500 Subject: audit: log 32-bit socketcalls [ Upstream commit 62bc306e2083436675e33b5bdeb6a77907d35971 ] 32-bit socketcalls were not being logged by audit on x86_64 systems. Log them. This is basically a duplicate of the call from net/socket.c:sys_socketcall(), but it addresses the impedance mismatch between 32-bit userspace process and 64-bit kernel audit. See: https://github.com/linux-audit/audit-kernel/issues/14 Signed-off-by: Richard Guy Briggs Acked-by: David S. Miller Signed-off-by: Paul Moore Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- include/linux/audit.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 20eba1eb0a3c..faac391badac 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -281,6 +281,20 @@ static inline int audit_socketcall(int nargs, unsigned long *args) return __audit_socketcall(nargs, args); return 0; } + +static inline int audit_socketcall_compat(int nargs, u32 *args) +{ + unsigned long a[AUDITSC_ARGS]; + int i; + + if (audit_dummy_context()) + return 0; + + for (i = 0; i < nargs; i++) + a[i] = (unsigned long)args[i]; + return __audit_socketcall(nargs, a); +} + static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) @@ -407,6 +421,12 @@ static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } + +static inline int audit_socketcall_compat(int nargs, u32 *args) +{ + return 0; +} + static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) -- cgit v1.2.3 From 1b760fdad9f0626e7be2c1082c94dca21f72470b Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 29 Mar 2017 20:54:37 +0200 Subject: mmc: sdio: fix alignment issue in struct sdio_func [ Upstream commit 5ef1ecf060f28ecef313b5723f1fd39bf5a35f56 ] Certain 64-bit systems (e.g. Amlogic Meson GX) require buffers to be used for DMA to be 8-byte-aligned. struct sdio_func has an embedded small DMA buffer not meeting this requirement. When testing switching to descriptor chain mode in meson-gx driver SDIO is broken therefore. Fix this by allocating the small DMA buffer separately as kmalloc ensures that the returned memory area is properly aligned for every basic data type. Signed-off-by: Heiner Kallweit Tested-by: Helmut Klein Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- include/linux/mmc/sdio_func.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index aab032a6ae61..97ca105347a6 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -53,7 +53,7 @@ struct sdio_func { unsigned int state; /* function state */ #define SDIO_STATE_PRESENT (1<<0) /* present in sysfs */ - u8 tmpbuf[4]; /* DMA:able scratch buffer */ + u8 *tmpbuf; /* DMA:able scratch buffer */ unsigned num_info; /* number of info strings */ const char **info; /* info strings */ -- cgit v1.2.3 From 4b9c62a00aeae875cecbc9ac67753534e2681e4b Mon Sep 17 00:00:00 2001 From: Dragos Bogdan Date: Tue, 5 Sep 2017 15:14:45 +0300 Subject: iio: ad_sigma_delta: Implement a dedicated reset function commit 7fc10de8d49a748c476532c9d8e8fe19e548dd67 upstream. Since most of the SD ADCs have the option of reseting the serial interface by sending a number of SCLKs with CS = 0 and DIN = 1, a dedicated function that can do this is usefull. Needed for the patch: iio: ad7793: Fix the serial interface reset Signed-off-by: Dragos Bogdan Acked-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- include/linux/iio/adc/ad_sigma_delta.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index e7fdec4db9da..6cc48ac55fd2 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -111,6 +111,9 @@ int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, unsigned int size, unsigned int *val); +int ad_sd_reset(struct ad_sigma_delta *sigma_delta, + unsigned int reset_length); + int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, int *val); int ad_sd_calibrate_all(struct ad_sigma_delta *sigma_delta, -- cgit v1.2.3 From 90fd6738731b6d105fc8f04832ae17a9ac82c05c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Sep 2017 11:13:38 +0200 Subject: sched/cpuset/pm: Fix cpuset vs. suspend-resume bugs commit 50e76632339d4655859523a39249dd95ee5e93e7 upstream. Cpusets vs. suspend-resume is _completely_ broken. And it got noticed because it now resulted in non-cpuset usage breaking too. On suspend cpuset_cpu_inactive() doesn't call into cpuset_update_active_cpus() because it doesn't want to move tasks about, there is no need, all tasks are frozen and won't run again until after we've resumed everything. But this means that when we finally do call into cpuset_update_active_cpus() after resuming the last frozen cpu in cpuset_cpu_active(), the top_cpuset will not have any difference with the cpu_active_mask and this it will not in fact do _anything_. So the cpuset configuration will not be restored. This was largely hidden because we would unconditionally create identity domains and mobile users would not in fact use cpusets much. And servers what do use cpusets tend to not suspend-resume much. An addition problem is that we'd not in fact wait for the cpuset work to finish before resuming the tasks, allowing spurious migrations outside of the specified domains. Fix the rebuild by introducing cpuset_force_rebuild() and fix the ordering with cpuset_wait_for_hotplug(). Reported-by: Andy Lutomirski Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Tejun Heo Cc: Thomas Gleixner Fixes: deb7aa308ea2 ("cpuset: reorganize CPU / memory hotplug handling") Link: http://lkml.kernel.org/r/20170907091338.orwxrqkbfkki3c24@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar Signed-off-by: Mike Galbraith Signed-off-by: Greg Kroah-Hartman --- include/linux/cpuset.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 8397dc235e84..ad98acfbcba8 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -43,7 +43,9 @@ static inline void cpuset_dec(void) extern int cpuset_init(void); extern void cpuset_init_smp(void); +extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(bool cpu_online); +extern void cpuset_wait_for_hotplug(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern void cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -147,11 +149,15 @@ static inline bool cpusets_enabled(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} +static inline void cpuset_force_rebuild(void) { } + static inline void cpuset_update_active_cpus(bool cpu_online) { partition_sched_domains(1, NULL, NULL); } +static inline void cpuset_wait_for_hotplug(void) { } + static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { -- cgit v1.2.3