From c39de951282df9a60ef70664e4378d88006b2670 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 11:04:53 +0300 Subject: [PATCH 001/311] fs/ntfs3: Improve alternative boot processing Signed-off-by: Konstantin Komarov --- fs/ntfs3/super.c | 35 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 18 deletions(-) diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 9153dffde950..09d61c6c90aa 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -866,6 +866,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, u16 fn, ao; u8 cluster_bits; u32 boot_off = 0; + sector_t boot_block = 0; const char *hint = "Primary boot"; /* Save original dev_size. Used with alternative boot. */ @@ -873,11 +874,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, sbi->volume.blocks = dev_size >> PAGE_SHIFT; - bh = ntfs_bread(sb, 0); +read_boot: + bh = ntfs_bread(sb, boot_block); if (!bh) - return -EIO; + return boot_block ? -EINVAL : -EIO; -check_boot: err = -EINVAL; /* Corrupted image; do not read OOB */ @@ -1108,26 +1109,24 @@ check_boot: } out: - if (err == -EINVAL && !bh->b_blocknr && dev_size0 > PAGE_SHIFT) { + brelse(bh); + + if (err == -EINVAL && !boot_block && dev_size0 > PAGE_SHIFT) { u32 block_size = min_t(u32, sector_size, PAGE_SIZE); u64 lbo = dev_size0 - sizeof(*boot); - /* - * Try alternative boot (last sector) - */ - brelse(bh); - - sb_set_blocksize(sb, block_size); - bh = ntfs_bread(sb, lbo >> blksize_bits(block_size)); - if (!bh) - return -EINVAL; - + boot_block = lbo >> blksize_bits(block_size); boot_off = lbo & (block_size - 1); - hint = "Alternative boot"; - dev_size = dev_size0; /* restore original size. */ - goto check_boot; + if (boot_block && block_size >= boot_off + sizeof(*boot)) { + /* + * Try alternative boot (last sector) + */ + sb_set_blocksize(sb, block_size); + hint = "Alternative boot"; + dev_size = dev_size0; /* restore original size. */ + goto read_boot; + } } - brelse(bh); return err; } From 22457c047ed971f2f2e33be593ddfabd9639a409 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 11:17:07 +0300 Subject: [PATCH 002/311] fs/ntfs3: Modified fix directory element type detection Unfortunately reparse attribute is used for many purposes (several dozens). It is not possible here to know is this name symlink or not. To get exactly the type of name we should to open inode (read mft). getattr for opened file (fstat) correctly returns symlink. Signed-off-by: Konstantin Komarov --- fs/ntfs3/dir.c | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-) diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index ec0566b322d5..22ede4da0450 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -309,11 +309,31 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, return 0; } - /* NTFS: symlinks are "dir + reparse" or "file + reparse" */ - if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) - dt_type = DT_LNK; - else - dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + /* + * NTFS: symlinks are "dir + reparse" or "file + reparse" + * Unfortunately reparse attribute is used for many purposes (several dozens). + * It is not possible here to know is this name symlink or not. + * To get exactly the type of name we should to open inode (read mft). + * getattr for opened file (fstat) correctly returns symlink. + */ + dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + + /* + * It is not reliable to detect the type of name using duplicated information + * stored in parent directory. + * The only correct way to get the type of name - read MFT record and find ATTR_STD. + * The code below is not good idea. + * It does additional locks/reads just to get the type of name. + * Should we use additional mount option to enable branch below? + */ + if ((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) && + ino != ni->mi.rno) { + struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL); + if (!IS_ERR_OR_NULL(inode)) { + dt_type = fs_umode_to_dtype(inode->i_mode); + iput(inode); + } + } return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); } From 6a799c928b78b14999b7705c4cca0f88e297fe96 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 11:24:33 +0300 Subject: [PATCH 003/311] fs/ntfs3: Improve ntfs_dir_count Signed-off-by: Konstantin Komarov --- fs/ntfs3/dir.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index 22ede4da0450..726122ecd39b 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -515,11 +515,9 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, struct INDEX_HDR *hdr; const struct ATTR_FILE_NAME *fname; u32 e_size, off, end; - u64 vbo = 0; size_t drs = 0, fles = 0, bit = 0; - loff_t i_size = ni->vfs_inode.i_size; struct indx_node *node = NULL; - u8 index_bits = ni->dir.index_bits; + size_t max_indx = ni->vfs_inode.i_size >> ni->dir.index_bits; if (is_empty) *is_empty = true; @@ -563,7 +561,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, fles += 1; } - if (vbo >= i_size) + if (bit >= max_indx) goto out; err = indx_used_bit(&ni->dir, ni, &bit); @@ -573,8 +571,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, if (bit == MINUS_ONE_T) goto out; - vbo = (u64)bit << index_bits; - if (vbo >= i_size) + if (bit >= max_indx) goto out; err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits, @@ -584,7 +581,6 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, hdr = &node->index->ihdr; bit += 1; - vbo = (u64)bit << ni->dir.idx2vbn_bits; } out: From 1918c10e137eae266b8eb0ab1cc14421dcb0e3e2 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 11:26:31 +0300 Subject: [PATCH 004/311] fs/ntfs3: Correct hard links updating when dealing with DOS names Signed-off-by: Konstantin Komarov --- fs/ntfs3/record.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 53629b1f65e9..7b6423584eae 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -535,8 +535,20 @@ bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi, return false; if (ni && is_attr_indexed(attr)) { - le16_add_cpu(&ni->mi.mrec->hard_links, -1); - ni->mi.dirty = true; + u16 links = le16_to_cpu(ni->mi.mrec->hard_links); + struct ATTR_FILE_NAME *fname = + attr->type != ATTR_NAME ? + NULL : + resident_data_ex(attr, + SIZEOF_ATTRIBUTE_FILENAME); + if (fname && fname->type == FILE_NAME_DOS) { + /* Do not decrease links count deleting DOS name. */ + } else if (!links) { + /* minor error. Not critical. */ + } else { + ni->mi.mrec->hard_links = cpu_to_le16(links - 1); + ni->mi.dirty = true; + } } used -= asize; From 85ba2a75faee759809a7e43b4c103ac59bac1026 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 11:34:24 +0300 Subject: [PATCH 005/311] fs/ntfs3: Print warning while fixing hard links count Signed-off-by: Konstantin Komarov --- fs/ntfs3/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 5e3d71374918..fa6c7965473c 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -412,7 +412,6 @@ end_enum: goto out; if (!is_match && name) { - /* Reuse rec as buffer for ascii name. */ err = -ENOENT; goto out; } @@ -427,6 +426,7 @@ end_enum: if (names != le16_to_cpu(rec->hard_links)) { /* Correct minor error on the fly. Do not mark inode as dirty. */ + ntfs_inode_warn(inode, "Correct links count -> %u.", names); rec->hard_links = cpu_to_le16(names); ni->mi.dirty = true; } From 865e7a7700d930d34895a70f8af2eb4e778a5b0e Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 11:42:04 +0300 Subject: [PATCH 006/311] fs/ntfs3: Reduce stack usage Signed-off-by: Konstantin Komarov --- fs/ntfs3/fslog.c | 214 +++++++++++++++++++++-------------------------- 1 file changed, 96 insertions(+), 118 deletions(-) diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 98ccb6650858..7dbb000fc691 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -974,6 +974,16 @@ skip_looking: return e; } +struct restart_info { + u64 last_lsn; + struct RESTART_HDR *r_page; + u32 vbo; + bool chkdsk_was_run; + bool valid_page; + bool initialized; + bool restart; +}; + #define RESTART_SINGLE_PAGE_IO cpu_to_le16(0x0001) #define NTFSLOG_WRAPPED 0x00000001 @@ -987,6 +997,7 @@ struct ntfs_log { struct ntfs_inode *ni; u32 l_size; + u32 orig_file_size; u32 sys_page_size; u32 sys_page_mask; u32 page_size; @@ -1040,6 +1051,8 @@ struct ntfs_log { struct CLIENT_ID client_id; u32 client_undo_commit; + + struct restart_info rst_info, rst_info2; }; static inline u32 lsn_to_vbo(struct ntfs_log *log, const u64 lsn) @@ -1105,16 +1118,6 @@ static inline bool verify_client_lsn(struct ntfs_log *log, lsn <= le64_to_cpu(log->ra->current_lsn) && lsn; } -struct restart_info { - u64 last_lsn; - struct RESTART_HDR *r_page; - u32 vbo; - bool chkdsk_was_run; - bool valid_page; - bool initialized; - bool restart; -}; - static int read_log_page(struct ntfs_log *log, u32 vbo, struct RECORD_PAGE_HDR **buffer, bool *usa_error) { @@ -1176,7 +1179,7 @@ out: * restart page header. It will stop the first time we find a * valid page header. */ -static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first, +static int log_read_rst(struct ntfs_log *log, bool first, struct restart_info *info) { u32 skip, vbo; @@ -1192,7 +1195,7 @@ static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first, } /* Loop continuously until we succeed. */ - for (; vbo < l_size; vbo = 2 * vbo + skip, skip = 0) { + for (; vbo < log->l_size; vbo = 2 * vbo + skip, skip = 0) { bool usa_error; bool brst, bchk; struct RESTART_AREA *ra; @@ -1285,22 +1288,17 @@ check_result: /* * Ilog_init_pg_hdr - Init @log from restart page header. */ -static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size, - u32 page_size, u16 major_ver, u16 minor_ver) +static void log_init_pg_hdr(struct ntfs_log *log, u16 major_ver, u16 minor_ver) { - log->sys_page_size = sys_page_size; - log->sys_page_mask = sys_page_size - 1; - log->page_size = page_size; - log->page_mask = page_size - 1; - log->page_bits = blksize_bits(page_size); + log->sys_page_size = log->page_size; + log->sys_page_mask = log->page_mask; log->clst_per_page = log->page_size >> log->ni->mi.sbi->cluster_bits; if (!log->clst_per_page) log->clst_per_page = 1; - log->first_page = major_ver >= 2 ? - 0x22 * page_size : - ((sys_page_size << 1) + (page_size << 1)); + log->first_page = major_ver >= 2 ? 0x22 * log->page_size : + 4 * log->page_size; log->major_ver = major_ver; log->minor_ver = minor_ver; } @@ -1308,12 +1306,11 @@ static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size, /* * log_create - Init @log in cases when we don't have a restart area to use. */ -static void log_create(struct ntfs_log *log, u32 l_size, const u64 last_lsn, +static void log_create(struct ntfs_log *log, const u64 last_lsn, u32 open_log_count, bool wrapped, bool use_multi_page) { - log->l_size = l_size; /* All file offsets must be quadword aligned. */ - log->file_data_bits = blksize_bits(l_size) - 3; + log->file_data_bits = blksize_bits(log->l_size) - 3; log->seq_num_mask = (8 << log->file_data_bits) - 1; log->seq_num_bits = sizeof(u64) * 8 - log->file_data_bits; log->seq_num = (last_lsn >> log->file_data_bits) + 2; @@ -3720,10 +3717,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) struct ntfs_sb_info *sbi = ni->mi.sbi; struct ntfs_log *log; - struct restart_info rst_info, rst_info2; - u64 rec_lsn, ra_lsn, checkpt_lsn = 0, rlsn = 0; + u64 rec_lsn, checkpt_lsn = 0, rlsn = 0; struct ATTR_NAME_ENTRY *attr_names = NULL; - struct ATTR_NAME_ENTRY *ane; struct RESTART_TABLE *dptbl = NULL; struct RESTART_TABLE *trtbl = NULL; const struct RESTART_TABLE *rt; @@ -3741,9 +3736,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) struct TRANSACTION_ENTRY *tr; struct DIR_PAGE_ENTRY *dp; u32 i, bytes_per_attr_entry; - u32 l_size = ni->vfs_inode.i_size; - u32 orig_file_size = l_size; - u32 page_size, vbo, tail, off, dlen; + u32 vbo, tail, off, dlen; u32 saved_len, rec_len, transact_id; bool use_second_page; struct RESTART_AREA *ra2, *ra = NULL; @@ -3758,52 +3751,50 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) u16 t16; u32 t32; - /* Get the size of page. NOTE: To replay we can use default page. */ -#if PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2 - page_size = norm_file_page(PAGE_SIZE, &l_size, true); -#else - page_size = norm_file_page(PAGE_SIZE, &l_size, false); -#endif - if (!page_size) - return -EINVAL; - log = kzalloc(sizeof(struct ntfs_log), GFP_NOFS); if (!log) return -ENOMEM; log->ni = ni; - log->l_size = l_size; - log->one_page_buf = kmalloc(page_size, GFP_NOFS); + log->l_size = log->orig_file_size = ni->vfs_inode.i_size; + /* Get the size of page. NOTE: To replay we can use default page. */ +#if PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2 + log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, true); +#else + log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, false); +#endif + if (!log->page_size) { + err = -EINVAL; + goto out; + } + + log->one_page_buf = kmalloc(log->page_size, GFP_NOFS); if (!log->one_page_buf) { err = -ENOMEM; goto out; } - log->page_size = page_size; - log->page_mask = page_size - 1; - log->page_bits = blksize_bits(page_size); + log->page_mask = log->page_size - 1; + log->page_bits = blksize_bits(log->page_size); /* Look for a restart area on the disk. */ - memset(&rst_info, 0, sizeof(struct restart_info)); - err = log_read_rst(log, l_size, true, &rst_info); + err = log_read_rst(log, true, &log->rst_info); if (err) goto out; /* remember 'initialized' */ - *initialized = rst_info.initialized; + *initialized = log->rst_info.initialized; - if (!rst_info.restart) { - if (rst_info.initialized) { + if (!log->rst_info.restart) { + if (log->rst_info.initialized) { /* No restart area but the file is not initialized. */ err = -EINVAL; goto out; } - log_init_pg_hdr(log, page_size, page_size, 1, 1); - log_create(log, l_size, 0, get_random_u32(), false, false); - - log->ra = ra; + log_init_pg_hdr(log, 1, 1); + log_create(log, 0, get_random_u32(), false, false); ra = log_create_ra(log); if (!ra) { @@ -3820,25 +3811,26 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) * If the restart offset above wasn't zero then we won't * look for a second restart. */ - if (rst_info.vbo) + if (log->rst_info.vbo) goto check_restart_area; - memset(&rst_info2, 0, sizeof(struct restart_info)); - err = log_read_rst(log, l_size, false, &rst_info2); + err = log_read_rst(log, false, &log->rst_info2); if (err) goto out; /* Determine which restart area to use. */ - if (!rst_info2.restart || rst_info2.last_lsn <= rst_info.last_lsn) + if (!log->rst_info2.restart || + log->rst_info2.last_lsn <= log->rst_info.last_lsn) goto use_first_page; use_second_page = true; - if (rst_info.chkdsk_was_run && page_size != rst_info.vbo) { + if (log->rst_info.chkdsk_was_run && + log->page_size != log->rst_info.vbo) { struct RECORD_PAGE_HDR *sp = NULL; bool usa_error; - if (!read_log_page(log, page_size, &sp, &usa_error) && + if (!read_log_page(log, log->page_size, &sp, &usa_error) && sp->rhdr.sign == NTFS_CHKD_SIGNATURE) { use_second_page = false; } @@ -3846,52 +3838,43 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) } if (use_second_page) { - kfree(rst_info.r_page); - memcpy(&rst_info, &rst_info2, sizeof(struct restart_info)); - rst_info2.r_page = NULL; + kfree(log->rst_info.r_page); + memcpy(&log->rst_info, &log->rst_info2, + sizeof(struct restart_info)); + log->rst_info2.r_page = NULL; } use_first_page: - kfree(rst_info2.r_page); + kfree(log->rst_info2.r_page); check_restart_area: /* * If the restart area is at offset 0, we want * to write the second restart area first. */ - log->init_ra = !!rst_info.vbo; + log->init_ra = !!log->rst_info.vbo; /* If we have a valid page then grab a pointer to the restart area. */ - ra2 = rst_info.valid_page ? - Add2Ptr(rst_info.r_page, - le16_to_cpu(rst_info.r_page->ra_off)) : + ra2 = log->rst_info.valid_page ? + Add2Ptr(log->rst_info.r_page, + le16_to_cpu(log->rst_info.r_page->ra_off)) : NULL; - if (rst_info.chkdsk_was_run || + if (log->rst_info.chkdsk_was_run || (ra2 && ra2->client_idx[1] == LFS_NO_CLIENT_LE)) { bool wrapped = false; bool use_multi_page = false; u32 open_log_count; /* Do some checks based on whether we have a valid log page. */ - if (!rst_info.valid_page) { - open_log_count = get_random_u32(); - goto init_log_instance; - } - open_log_count = le32_to_cpu(ra2->open_log_count); + open_log_count = log->rst_info.valid_page ? + le32_to_cpu(ra2->open_log_count) : + get_random_u32(); - /* - * If the restart page size isn't changing then we want to - * check how much work we need to do. - */ - if (page_size != le32_to_cpu(rst_info.r_page->sys_page_size)) - goto init_log_instance; + log_init_pg_hdr(log, 1, 1); -init_log_instance: - log_init_pg_hdr(log, page_size, page_size, 1, 1); - - log_create(log, l_size, rst_info.last_lsn, open_log_count, - wrapped, use_multi_page); + log_create(log, log->rst_info.last_lsn, open_log_count, wrapped, + use_multi_page); ra = log_create_ra(log); if (!ra) { @@ -3916,28 +3899,27 @@ init_log_instance: * use the log file. We must use the system page size instead of the * default size if there is not a clean shutdown. */ - t32 = le32_to_cpu(rst_info.r_page->sys_page_size); - if (page_size != t32) { - l_size = orig_file_size; - page_size = - norm_file_page(t32, &l_size, t32 == DefaultLogPageSize); + t32 = le32_to_cpu(log->rst_info.r_page->sys_page_size); + if (log->page_size != t32) { + log->l_size = log->orig_file_size; + log->page_size = norm_file_page(t32, &log->l_size, + t32 == DefaultLogPageSize); } - if (page_size != t32 || - page_size != le32_to_cpu(rst_info.r_page->page_size)) { + if (log->page_size != t32 || + log->page_size != le32_to_cpu(log->rst_info.r_page->page_size)) { err = -EINVAL; goto out; } /* If the file size has shrunk then we won't mount it. */ - if (l_size < le64_to_cpu(ra2->l_size)) { + if (log->l_size < le64_to_cpu(ra2->l_size)) { err = -EINVAL; goto out; } - log_init_pg_hdr(log, page_size, page_size, - le16_to_cpu(rst_info.r_page->major_ver), - le16_to_cpu(rst_info.r_page->minor_ver)); + log_init_pg_hdr(log, le16_to_cpu(log->rst_info.r_page->major_ver), + le16_to_cpu(log->rst_info.r_page->minor_ver)); log->l_size = le64_to_cpu(ra2->l_size); log->seq_num_bits = le32_to_cpu(ra2->seq_num_bits); @@ -3945,7 +3927,7 @@ init_log_instance: log->seq_num_mask = (8 << log->file_data_bits) - 1; log->last_lsn = le64_to_cpu(ra2->current_lsn); log->seq_num = log->last_lsn >> log->file_data_bits; - log->ra_off = le16_to_cpu(rst_info.r_page->ra_off); + log->ra_off = le16_to_cpu(log->rst_info.r_page->ra_off); log->restart_size = log->sys_page_size - log->ra_off; log->record_header_len = le16_to_cpu(ra2->rec_hdr_len); log->ra_size = le16_to_cpu(ra2->ra_len); @@ -4045,7 +4027,7 @@ find_oldest: log->current_avail = current_log_avail(log); /* Remember which restart area to write first. */ - log->init_ra = rst_info.vbo; + log->init_ra = log->rst_info.vbo; process_log: /* 1.0, 1.1, 2.0 log->major_ver/minor_ver - short values. */ @@ -4105,7 +4087,7 @@ process_log: log->client_id.seq_num = cr->seq_num; log->client_id.client_idx = client; - err = read_rst_area(log, &rst, &ra_lsn); + err = read_rst_area(log, &rst, &checkpt_lsn); if (err) goto out; @@ -4114,9 +4096,8 @@ process_log: bytes_per_attr_entry = !rst->major_ver ? 0x2C : 0x28; - checkpt_lsn = le64_to_cpu(rst->check_point_start); - if (!checkpt_lsn) - checkpt_lsn = ra_lsn; + if (rst->check_point_start) + checkpt_lsn = le64_to_cpu(rst->check_point_start); /* Allocate and Read the Transaction Table. */ if (!rst->transact_table_len) @@ -4330,23 +4311,20 @@ check_attr_table: lcb = NULL; check_attribute_names2: - if (!rst->attr_names_len) - goto trace_attribute_table; - - ane = attr_names; - if (!oatbl) - goto trace_attribute_table; - while (ane->off) { - /* TODO: Clear table on exit! */ - oe = Add2Ptr(oatbl, le16_to_cpu(ane->off)); - t16 = le16_to_cpu(ane->name_bytes); - oe->name_len = t16 / sizeof(short); - oe->ptr = ane->name; - oe->is_attr_name = 2; - ane = Add2Ptr(ane, sizeof(struct ATTR_NAME_ENTRY) + t16); + if (rst->attr_names_len && oatbl) { + struct ATTR_NAME_ENTRY *ane = attr_names; + while (ane->off) { + /* TODO: Clear table on exit! */ + oe = Add2Ptr(oatbl, le16_to_cpu(ane->off)); + t16 = le16_to_cpu(ane->name_bytes); + oe->name_len = t16 / sizeof(short); + oe->ptr = ane->name; + oe->is_attr_name = 2; + ane = Add2Ptr(ane, + sizeof(struct ATTR_NAME_ENTRY) + t16); + } } -trace_attribute_table: /* * If the checkpt_lsn is zero, then this is a freshly * formatted disk and we have no work to do. @@ -5189,7 +5167,7 @@ out: kfree(oatbl); kfree(dptbl); kfree(attr_names); - kfree(rst_info.r_page); + kfree(log->rst_info.r_page); kfree(ra); kfree(log->one_page_buf); From a8b0c9fc3a2dba07f697ef7825e04363ff12f071 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 11:46:16 +0300 Subject: [PATCH 007/311] fs/ntfs3: Fix multithreaded stress test Signed-off-by: Konstantin Komarov --- fs/ntfs3/attrib.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 63f70259edc0..4b78b669a3bd 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -886,7 +886,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi; u8 cluster_bits; - struct ATTRIB *attr = NULL, *attr_b; + struct ATTRIB *attr, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end, vcn0, alen; @@ -904,12 +904,8 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, *len = 0; up_read(&ni->file.run_lock); - if (*len) { - if (*lcn != SPARSE_LCN || !new) - return 0; /* Fast normal way without allocation. */ - else if (clen > *len) - clen = *len; - } + if (*len && (*lcn != SPARSE_LCN || !new)) + return 0; /* Fast normal way without allocation. */ /* No cluster in cache or we need to allocate cluster in hole. */ sbi = ni->mi.sbi; @@ -918,6 +914,17 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, ni_lock(ni); down_write(&ni->file.run_lock); + /* Repeat the code above (under write lock). */ + if (!run_lookup_entry(run, vcn, lcn, len, NULL)) + *len = 0; + + if (*len) { + if (*lcn != SPARSE_LCN || !new) + goto out; /* normal way without allocation. */ + if (clen > *len) + clen = *len; + } + le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { From d155617006ebc172a80d3eb013c4b867f9a8ada4 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 11:47:30 +0300 Subject: [PATCH 008/311] fs/ntfs3: Fix detected field-spanning write (size 8) of single field "le->name" Signed-off-by: Konstantin Komarov --- fs/ntfs3/ntfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 86aecbb01a92..13e96fc63dae 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -523,7 +523,7 @@ struct ATTR_LIST_ENTRY { __le64 vcn; // 0x08: Starting VCN of this attribute. struct MFT_REF ref; // 0x10: MFT record number with attribute. __le16 id; // 0x18: struct ATTRIB ID. - __le16 name[3]; // 0x1A: Just to align. To get real name can use bNameOffset. + __le16 name[]; // 0x1A: Just to align. To get real name can use name_off. }; // sizeof(0x20) From a40b73f608e7de2120fdb9ddc8970421b3c50bc9 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 12:08:36 +0300 Subject: [PATCH 009/311] fs/ntfs3: Correct use bh_read Signed-off-by: Konstantin Komarov --- fs/ntfs3/file.c | 19 +++++++++---------- fs/ntfs3/inode.c | 7 +++---- 2 files changed, 12 insertions(+), 14 deletions(-) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index a5a30a24ce5d..5691f04e6751 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -188,6 +188,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) u32 bh_next, bh_off, to; sector_t iblock; struct folio *folio; + bool dirty = false; for (; idx < idx_end; idx += 1, from = 0) { page_off = (loff_t)idx << PAGE_SHIFT; @@ -223,29 +224,27 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) /* Ok, it's mapped. Make sure it's up-to-date. */ if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); - - if (!buffer_uptodate(bh)) { - err = bh_read(bh, 0); - if (err < 0) { - folio_unlock(folio); - folio_put(folio); - goto out; - } + else if (bh_read(bh, 0) < 0) { + err = -EIO; + folio_unlock(folio); + folio_put(folio); + goto out; } mark_buffer_dirty(bh); - } while (bh_off = bh_next, iblock += 1, head != (bh = bh->b_this_page)); folio_zero_segment(folio, from, to); + dirty = true; folio_unlock(folio); folio_put(folio); cond_resched(); } out: - mark_inode_dirty(inode); + if (dirty) + mark_inode_dirty(inode); return err; } diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index fa6c7965473c..bba0208c4afd 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -345,9 +345,7 @@ next_attr: inode->i_size = le16_to_cpu(rp.SymbolicLinkReparseBuffer .PrintNameLength) / sizeof(u16); - ni->i_valid = inode->i_size; - /* Clear directory bit. */ if (ni->ni_flags & NI_FLAG_DIR) { indx_clear(&ni->dir); @@ -653,9 +651,10 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, off = vbo & (PAGE_SIZE - 1); folio_set_bh(bh, folio, off); - err = bh_read(bh, 0); - if (err < 0) + if (bh_read(bh, 0) < 0) { + err = -EIO; goto out; + } folio_zero_segment(folio, off + voff, off + block_size); } } From 4dea9cd522424d3002894c20b729c6fbfb6fc22b Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 12:16:49 +0300 Subject: [PATCH 010/311] fs/ntfs3: Add file_modified Signed-off-by: Konstantin Komarov --- fs/ntfs3/file.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 5691f04e6751..bb80ce2eec2f 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -632,11 +632,17 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) &ni->file.run, i_size, &ni->i_valid, true, NULL); ni_unlock(ni); + if (err) + goto out; } else if (new_size > i_size) { inode->i_size = new_size; } } + err = file_modified(file); + if (err) + goto out; + out: if (map_locked) filemap_invalidate_unlock(mapping); @@ -1040,6 +1046,7 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; + int err; struct ntfs_inode *ni = ntfs_i(inode); if (is_encrypted(ni)) { @@ -1067,6 +1074,12 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (ret <= 0) goto out; + err = file_modified(iocb->ki_filp); + if (err) { + ret = err; + goto out; + } + if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) { /* Should never be here, see ntfs_file_open(). */ ret = -EOPNOTSUPP; From e50f9560b8168a625703a3e7fe1fde9fa53f0837 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 12:17:46 +0300 Subject: [PATCH 011/311] fs/ntfs3: Drop suid and sgid bits as a part of fpunch Signed-off-by: Konstantin Komarov --- fs/ntfs3/file.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index bb80ce2eec2f..0ff5d3af2889 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -498,10 +498,14 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) ni_lock(ni); err = attr_punch_hole(ni, vbo, len, &frame_size); ni_unlock(ni); + if (!err) + goto ok; + if (err != E_NTFS_NOTALIGNED) goto out; /* Process not aligned punch. */ + err = 0; mask = frame_size - 1; vbo_a = (vbo + mask) & ~mask; end_a = end & ~mask; @@ -524,6 +528,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) ni_lock(ni); err = attr_punch_hole(ni, vbo_a, end_a - vbo_a, NULL); ni_unlock(ni); + if (err) + goto out; } } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { /* @@ -563,6 +569,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) ni_lock(ni); err = attr_insert_range(ni, vbo, len); ni_unlock(ni); + if (err) + goto out; } else { /* Check new size. */ u8 cluster_bits = sbi->cluster_bits; @@ -639,6 +647,7 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) } } +ok: err = file_modified(file); if (err) goto out; From 6c3684e703837d2116b5cf4beb37aa7145a66b60 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 12:19:37 +0300 Subject: [PATCH 012/311] fs/ntfs3: Implement super_operations::shutdown Signed-off-by: Konstantin Komarov --- fs/ntfs3/file.c | 18 ++++++++++++++++++ fs/ntfs3/frecord.c | 3 +++ fs/ntfs3/inode.c | 21 +++++++++++++++++++-- fs/ntfs3/namei.c | 12 ++++++++++++ fs/ntfs3/ntfs_fs.h | 9 ++++++++- fs/ntfs3/super.c | 12 ++++++++++++ fs/ntfs3/xattr.c | 3 +++ 7 files changed, 75 insertions(+), 3 deletions(-) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 0ff5d3af2889..07ed3d946e7c 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -260,6 +260,9 @@ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma) bool rw = vma->vm_flags & VM_WRITE; int err; + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + if (is_encrypted(ni)) { ntfs_inode_warn(inode, "mmap encrypted not supported"); return -EOPNOTSUPP; @@ -677,6 +680,9 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode = inode->i_mode; int err; + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + err = setattr_prepare(idmap, dentry, attr); if (err) goto out; @@ -732,6 +738,9 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) struct inode *inode = file->f_mapping->host; struct ntfs_inode *ni = ntfs_i(inode); + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + if (is_encrypted(ni)) { ntfs_inode_warn(inode, "encrypted i/o not supported"); return -EOPNOTSUPP; @@ -766,6 +775,9 @@ static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos, struct inode *inode = in->f_mapping->host; struct ntfs_inode *ni = ntfs_i(inode); + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + if (is_encrypted(ni)) { ntfs_inode_warn(inode, "encrypted i/o not supported"); return -EOPNOTSUPP; @@ -1058,6 +1070,9 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) int err; struct ntfs_inode *ni = ntfs_i(inode); + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + if (is_encrypted(ni)) { ntfs_inode_warn(inode, "encrypted i/o not supported"); return -EOPNOTSUPP; @@ -1118,6 +1133,9 @@ int ntfs_file_open(struct inode *inode, struct file *file) { struct ntfs_inode *ni = ntfs_i(inode); + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + if (unlikely((is_compressed(ni) || is_encrypted(ni)) && (file->f_flags & O_DIRECT))) { return -EOPNOTSUPP; diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 3df2d9e34b91..8744ba36d422 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -3259,6 +3259,9 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) if (is_bad_inode(inode) || sb_rdonly(sb)) return 0; + if (unlikely(ntfs3_forced_shutdown(sb))) + return -EIO; + if (!ni_trylock(ni)) { /* 'ni' is under modification, skip for now. */ mark_inode_dirty_sync(inode); diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index bba0208c4afd..85452a6b1d40 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -852,9 +852,13 @@ static int ntfs_resident_writepage(struct folio *folio, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; - struct ntfs_inode *ni = ntfs_i(mapping->host); + struct inode *inode = mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); int ret; + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + ni_lock(ni); ret = attr_data_write_resident(ni, &folio->page); ni_unlock(ni); @@ -868,7 +872,12 @@ static int ntfs_resident_writepage(struct folio *folio, static int ntfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { - if (is_resident(ntfs_i(mapping->host))) + struct inode *inode = mapping->host; + + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + + if (is_resident(ntfs_i(inode))) return write_cache_pages(mapping, wbc, ntfs_resident_writepage, mapping); return mpage_writepages(mapping, wbc, ntfs_get_block); @@ -888,6 +897,9 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + *pagep = NULL; if (is_resident(ni)) { struct page *page = @@ -1305,6 +1317,11 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, goto out1; } + if (unlikely(ntfs3_forced_shutdown(sb))) { + err = -EIO; + goto out2; + } + /* Mark rw ntfs as dirty. it will be cleared at umount. */ ntfs_set_state(sbi, NTFS_DIRTY_DIRTY); diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index ee3093be5170..cae41db0aaa7 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -181,6 +181,9 @@ static int ntfs_unlink(struct inode *dir, struct dentry *dentry) struct ntfs_inode *ni = ntfs_i(dir); int err; + if (unlikely(ntfs3_forced_shutdown(dir->i_sb))) + return -EIO; + ni_lock_dir(ni); err = ntfs_unlink_inode(dir, dentry); @@ -199,6 +202,9 @@ static int ntfs_symlink(struct mnt_idmap *idmap, struct inode *dir, u32 size = strlen(symname); struct inode *inode; + if (unlikely(ntfs3_forced_shutdown(dir->i_sb))) + return -EIO; + inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFLNK | 0777, 0, symname, size, NULL); @@ -227,6 +233,9 @@ static int ntfs_rmdir(struct inode *dir, struct dentry *dentry) struct ntfs_inode *ni = ntfs_i(dir); int err; + if (unlikely(ntfs3_forced_shutdown(dir->i_sb))) + return -EIO; + ni_lock_dir(ni); err = ntfs_unlink_inode(dir, dentry); @@ -264,6 +273,9 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *dir, 1024); static_assert(PATH_MAX >= 4 * 1024); + if (unlikely(ntfs3_forced_shutdown(sb))) + return -EIO; + if (flags & ~RENAME_NOREPLACE) return -EINVAL; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index f6706143d14b..d40bc7669ae5 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -61,6 +61,8 @@ enum utf16_endian; /* sbi->flags */ #define NTFS_FLAGS_NODISCARD 0x00000001 +/* ntfs in shutdown state. */ +#define NTFS_FLAGS_SHUTDOWN 0x00000002 /* Set when LogFile is replaying. */ #define NTFS_FLAGS_LOG_REPLAYING 0x00000008 /* Set when we changed first MFT's which copy must be updated in $MftMirr. */ @@ -226,7 +228,7 @@ struct ntfs_sb_info { u64 maxbytes; // Maximum size for normal files. u64 maxbytes_sparse; // Maximum size for sparse file. - u32 flags; // See NTFS_FLAGS_XXX. + unsigned long flags; // See NTFS_FLAGS_ CLST zone_max; // Maximum MFT zone length in clusters CLST bad_clusters; // The count of marked bad clusters. @@ -999,6 +1001,11 @@ static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb) return sb->s_fs_info; } +static inline bool ntfs3_forced_shutdown(struct super_block *sb) +{ + return test_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags); +} + /* * ntfs_up_cluster - Align up on cluster boundary. */ diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 09d61c6c90aa..af8521a6ed95 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -714,6 +714,14 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root) return 0; } +/* + * ntfs_shutdown - super_operations::shutdown + */ +static void ntfs_shutdown(struct super_block *sb) +{ + set_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags); +} + /* * ntfs_sync_fs - super_operations::sync_fs */ @@ -724,6 +732,9 @@ static int ntfs_sync_fs(struct super_block *sb, int wait) struct ntfs_inode *ni; struct inode *inode; + if (unlikely(ntfs3_forced_shutdown(sb))) + return -EIO; + ni = sbi->security.ni; if (ni) { inode = &ni->vfs_inode; @@ -763,6 +774,7 @@ static const struct super_operations ntfs_sops = { .put_super = ntfs_put_super, .statfs = ntfs_statfs, .show_options = ntfs_show_options, + .shutdown = ntfs_shutdown, .sync_fs = ntfs_sync_fs, .write_inode = ntfs3_write_inode, }; diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 4274b6f31cfa..071356d096d8 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -744,6 +744,9 @@ static int ntfs_getxattr(const struct xattr_handler *handler, struct dentry *de, int err; struct ntfs_inode *ni = ntfs_i(inode); + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + /* Dispatch request. */ if (!strcmp(name, SYSTEM_DOS_ATTRIB)) { /* system.dos_attrib */ From 97ec56d390a3a0077b36cb38627f671c72dddce6 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 24 Nov 2023 12:21:12 +0300 Subject: [PATCH 013/311] fs/ntfs3: ntfs3_forced_shutdown use int instead of bool Signed-off-by: Konstantin Komarov --- fs/ntfs3/fsntfs.c | 3 ++- fs/ntfs3/ntfs_fs.h | 6 +++--- fs/ntfs3/super.c | 2 +- 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index fbfe21dbb425..350461d8cece 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -853,7 +853,8 @@ void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) /* * sb can be NULL here. In this case sbi->flags should be 0 too. */ - if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR)) + if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR) || + unlikely(ntfs3_forced_shutdown(sb))) return; blocksize = sb->s_blocksize; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index d40bc7669ae5..7510875efef6 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -62,7 +62,7 @@ enum utf16_endian; /* sbi->flags */ #define NTFS_FLAGS_NODISCARD 0x00000001 /* ntfs in shutdown state. */ -#define NTFS_FLAGS_SHUTDOWN 0x00000002 +#define NTFS_FLAGS_SHUTDOWN_BIT 0x00000002 /* == 4*/ /* Set when LogFile is replaying. */ #define NTFS_FLAGS_LOG_REPLAYING 0x00000008 /* Set when we changed first MFT's which copy must be updated in $MftMirr. */ @@ -1001,9 +1001,9 @@ static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb) return sb->s_fs_info; } -static inline bool ntfs3_forced_shutdown(struct super_block *sb) +static inline int ntfs3_forced_shutdown(struct super_block *sb) { - return test_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags); + return test_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags); } /* diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index af8521a6ed95..65ef4b57411f 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -719,7 +719,7 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root) */ static void ntfs_shutdown(struct super_block *sb) { - set_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags); + set_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags); } /* From d6ca2d253900b9b0a3a1ad77541d606010f5e5eb Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Tue, 28 Nov 2023 11:08:00 +0300 Subject: [PATCH 014/311] fs/ntfs3: Add and fix comments Signed-off-by: Konstantin Komarov --- fs/ntfs3/dir.c | 4 +++- fs/ntfs3/fsntfs.c | 2 +- fs/ntfs3/ntfs.h | 2 +- fs/ntfs3/ntfs_fs.h | 2 +- 4 files changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index 726122ecd39b..9f6dd445eb04 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -536,8 +536,10 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, e = Add2Ptr(hdr, off); e_size = le16_to_cpu(e->size); if (e_size < sizeof(struct NTFS_DE) || - off + e_size > end) + off + e_size > end) { + /* Looks like corruption. */ break; + } if (de_is_last(e)) break; diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 350461d8cece..321978019407 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -2129,8 +2129,8 @@ int ntfs_insert_security(struct ntfs_sb_info *sbi, if (le32_to_cpu(d_security->size) == new_sec_size && d_security->key.hash == hash_key.hash && !memcmp(d_security + 1, sd, size_sd)) { - *security_id = d_security->key.sec_id; /* Such security already exists. */ + *security_id = d_security->key.sec_id; err = 0; goto out; } diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 13e96fc63dae..c8981429c721 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -523,7 +523,7 @@ struct ATTR_LIST_ENTRY { __le64 vcn; // 0x08: Starting VCN of this attribute. struct MFT_REF ref; // 0x10: MFT record number with attribute. __le16 id; // 0x18: struct ATTRIB ID. - __le16 name[]; // 0x1A: Just to align. To get real name can use name_off. + __le16 name[]; // 0x1A: To get real name use name_off. }; // sizeof(0x20) diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 7510875efef6..abbc7182554a 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -874,7 +874,7 @@ int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode, int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry); ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size); -extern const struct xattr_handler * const ntfs_xattr_handlers[]; +extern const struct xattr_handler *const ntfs_xattr_handlers[]; int ntfs_save_wsl_perm(struct inode *inode, __le16 *ea_size); void ntfs_get_wsl_perm(struct inode *inode); From aaab47f204aaf47838241d57bf8662c8840de60a Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Tue, 28 Nov 2023 11:09:34 +0300 Subject: [PATCH 015/311] fs/ntfs3: Add NULL ptr dereference checking at the end of attr_allocate_frame() It is preferable to exit through the out: label because internal debugging functions are located there. Signed-off-by: Konstantin Komarov --- fs/ntfs3/attrib.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 4b78b669a3bd..646e2dad1b75 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -1743,8 +1743,10 @@ repack: le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); - if (!attr_b) - return -ENOENT; + if (!attr_b) { + err = -ENOENT; + goto out; + } attr = attr_b; le = le_b; @@ -1825,13 +1827,15 @@ ins_ext: ok: run_truncate_around(run, vcn); out: - if (new_valid > data_size) - new_valid = data_size; + if (attr_b) { + if (new_valid > data_size) + new_valid = data_size; - valid_size = le64_to_cpu(attr_b->nres.valid_size); - if (new_valid != valid_size) { - attr_b->nres.valid_size = cpu_to_le64(valid_size); - mi_b->dirty = true; + valid_size = le64_to_cpu(attr_b->nres.valid_size); + if (new_valid != valid_size) { + attr_b->nres.valid_size = cpu_to_le64(valid_size); + mi_b->dirty = true; + } } return err; From 652483bfbc45137e8dce556c9ddbd4458dad4452 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Tue, 28 Nov 2023 11:17:20 +0300 Subject: [PATCH 016/311] fs/ntfs3: Fix c/mtime typo Signed-off-by: Konstantin Komarov --- fs/ntfs3/frecord.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 8744ba36d422..6ff4f70ba077 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -3291,7 +3291,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) modified = true; } - ts = inode_get_mtime(inode); + ts = inode_get_ctime(inode); dup.c_time = kernel2nt(&ts); if (std->c_time != dup.c_time) { std->c_time = dup.c_time; From 4cdfb6e7bc9c80142d33bf1d4653a73fa678ba56 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Thu, 21 Dec 2023 13:59:43 +0300 Subject: [PATCH 017/311] fs/ntfs3: Disable ATTR_LIST_ENTRY size check The use of sizeof(struct ATTR_LIST_ENTRY) has been replaced with le_size(0) due to alignment peculiarities on different platforms. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202312071005.g6YrbaIe-lkp@intel.com/ Signed-off-by: Konstantin Komarov --- fs/ntfs3/attrlist.c | 8 ++++---- fs/ntfs3/ntfs.h | 2 -- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index 7c01735d1219..48e7da47c6b7 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -127,12 +127,13 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, { size_t off; u16 sz; + const unsigned le_min_size = le_size(0); if (!le) { le = ni->attr_list.le; } else { sz = le16_to_cpu(le->size); - if (sz < sizeof(struct ATTR_LIST_ENTRY)) { + if (sz < le_min_size) { /* Impossible 'cause we should not return such le. */ return NULL; } @@ -141,7 +142,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, /* Check boundary. */ off = PtrOffset(ni->attr_list.le, le); - if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) { + if (off + le_min_size > ni->attr_list.size) { /* The regular end of list. */ return NULL; } @@ -149,8 +150,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, sz = le16_to_cpu(le->size); /* Check le for errors. */ - if (sz < sizeof(struct ATTR_LIST_ENTRY) || - off + sz > ni->attr_list.size || + if (sz < le_min_size || off + sz > ni->attr_list.size || sz < le->name_off + le->name_len * sizeof(short)) { return NULL; } diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index c8981429c721..9c7478150a03 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -527,8 +527,6 @@ struct ATTR_LIST_ENTRY { }; // sizeof(0x20) -static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20); - static inline u32 le_size(u8 name_len) { return ALIGN(offsetof(struct ATTR_LIST_ENTRY, name) + From ddb17dc880eeaac37b5a6e984de07b882de7d78d Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Tue, 16 Jan 2024 10:32:20 +0300 Subject: [PATCH 018/311] fs/ntfs3: Use kvfree to free memory allocated by kvmalloc Signed-off-by: Konstantin Komarov --- fs/ntfs3/attrlist.c | 4 ++-- fs/ntfs3/bitmap.c | 4 ++-- fs/ntfs3/frecord.c | 4 ++-- fs/ntfs3/super.c | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index 48e7da47c6b7..9f4bd8d26090 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -29,7 +29,7 @@ static inline bool al_is_valid_le(const struct ntfs_inode *ni, void al_destroy(struct ntfs_inode *ni) { run_close(&ni->attr_list.run); - kfree(ni->attr_list.le); + kvfree(ni->attr_list.le); ni->attr_list.le = NULL; ni->attr_list.size = 0; ni->attr_list.dirty = false; @@ -318,7 +318,7 @@ int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, memcpy(ptr, al->le, off); memcpy(Add2Ptr(ptr, off + sz), le, old_size - off); le = Add2Ptr(ptr, off); - kfree(al->le); + kvfree(al->le); al->le = ptr; } else { memmove(Add2Ptr(le, sz), le, old_size - off); diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index 63f14a0232f6..845f9b22deef 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -124,7 +124,7 @@ void wnd_close(struct wnd_bitmap *wnd) { struct rb_node *node, *next; - kfree(wnd->free_bits); + kvfree(wnd->free_bits); wnd->free_bits = NULL; run_close(&wnd->run); @@ -1360,7 +1360,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short)); memset(new_free + wnd->nwnd, 0, (new_wnd - wnd->nwnd) * sizeof(short)); - kfree(wnd->free_bits); + kvfree(wnd->free_bits); wnd->free_bits = new_free; } diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 6ff4f70ba077..2636ab7640ac 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -778,7 +778,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) run_deallocate(sbi, &ni->attr_list.run, true); run_close(&ni->attr_list.run); ni->attr_list.size = 0; - kfree(ni->attr_list.le); + kvfree(ni->attr_list.le); ni->attr_list.le = NULL; ni->attr_list.dirty = false; @@ -927,7 +927,7 @@ int ni_create_attr_list(struct ntfs_inode *ni) return 0; out: - kfree(ni->attr_list.le); + kvfree(ni->attr_list.le); ni->attr_list.le = NULL; ni->attr_list.size = 0; return err; diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 65ef4b57411f..c55a29793a8d 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -625,7 +625,7 @@ static void ntfs3_free_sbi(struct ntfs_sb_info *sbi) { kfree(sbi->new_rec); kvfree(ntfs_put_shared(sbi->upcase)); - kfree(sbi->def_table); + kvfree(sbi->def_table); kfree(sbi->compress.lznt); #ifdef CONFIG_NTFS3_LZX_XPRESS xpress_free_decompressor(sbi->compress.xpress); From 935024212dafebe065ccb5c4d399f19e4b8dbb82 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Draszik?= Date: Tue, 16 Jan 2024 06:27:31 +0000 Subject: [PATCH 019/311] dt-bindings: don't anchor DT_SCHEMA_FILES to bindings directory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 5e3ef4546819 ("dt-bindings: ignore paths outside kernel for DT_SCHEMA_FILES") anchored all searches to the bindings directory (since bindings only exist below that), but it turns out this is not always desired. Just anchor to the base kernel source directory and while at it, break the overly long line for legibility. Reported-by: Michal Simek Fixes: 5e3ef4546819 ("dt-bindings: ignore paths outside kernel for DT_SCHEMA_FILES") Closes: https://lore.kernel.org/all/827695c3-bb33-4a86-8586-2c7323530398@amd.com/ Cc: Masahiro Yamada Signed-off-by: André Draszik Tested-by: Michal Simek Link: https://lore.kernel.org/r/20240116062731.2810067-1-git@andred.net Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/Makefile | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile index 2323fd5b7cda..129cf698fa8a 100644 --- a/Documentation/devicetree/bindings/Makefile +++ b/Documentation/devicetree/bindings/Makefile @@ -28,7 +28,10 @@ $(obj)/%.example.dts: $(src)/%.yaml check_dtschema_version FORCE find_all_cmd = find $(srctree)/$(src) \( -name '*.yaml' ! \ -name 'processed-schema*' \) -find_cmd = $(find_all_cmd) | sed 's|^$(srctree)/$(src)/||' | grep -F -e "$(subst :," -e ",$(DT_SCHEMA_FILES))" | sed 's|^|$(srctree)/$(src)/|' +find_cmd = $(find_all_cmd) | \ + sed 's|^$(srctree)/||' | \ + grep -F -e "$(subst :," -e ",$(DT_SCHEMA_FILES))" | \ + sed 's|^|$(srctree)/|' CHK_DT_DOCS := $(shell $(find_cmd)) quiet_cmd_yamllint = LINT $(src) From 741ba0134fa7822fcf4e4a0a537a5c4cfd706b20 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 27 Dec 2023 16:21:24 +0100 Subject: [PATCH 020/311] pmdomain: core: Move the unused cleanup to a _sync initcall The unused clock cleanup uses the _sync initcall to give all users at earlier initcalls time to probe. Do the same to avoid leaving some PDs dangling at "on" (which actually happened on qcom!). Fixes: 2fe71dcdfd10 ("PM / domains: Add late_initcall to disable unused PM domains") Signed-off-by: Konrad Dybcio Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20231227-topic-pmdomain_sync_cleanup-v1-1-5f36769d538b@linaro.org Signed-off-by: Ulf Hansson --- drivers/pmdomain/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index a1f6cba3ae6c..18e232b5ed53 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -1109,7 +1109,7 @@ static int __init genpd_power_off_unused(void) return 0; } -late_initcall(genpd_power_off_unused); +late_initcall_sync(genpd_power_off_unused); #ifdef CONFIG_PM_SLEEP From f0e4a1356466ec1858ae8e5c70bea2ce5e55008b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 12 Jan 2024 17:33:55 +0100 Subject: [PATCH 021/311] pmdomain: renesas: r8a77980-sysc: CR7 must be always on MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The power domain containing the Cortex-R7 CPU core on the R-Car V3H SoC must always be in power-on state, unlike on other SoCs in the R-Car Gen3 family. See Table 9.4 "Power domains" in the R-Car Series, 3rd Generation Hardware User’s Manual Rev.1.00 and later. Fix this by marking the domain as a CPU domain without control registers, so the driver will not touch it. Fixes: 41d6d8bd8ae9 ("soc: renesas: rcar-sysc: add R8A77980 support") Signed-off-by: Geert Uytterhoeven Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/fdad9a86132d53ecddf72b734dac406915c4edc0.1705076735.git.geert+renesas@glider.be Signed-off-by: Ulf Hansson --- drivers/pmdomain/renesas/r8a77980-sysc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/pmdomain/renesas/r8a77980-sysc.c b/drivers/pmdomain/renesas/r8a77980-sysc.c index 39ca84a67daa..621e411fc999 100644 --- a/drivers/pmdomain/renesas/r8a77980-sysc.c +++ b/drivers/pmdomain/renesas/r8a77980-sysc.c @@ -25,7 +25,8 @@ static const struct rcar_sysc_area r8a77980_areas[] __initconst = { PD_CPU_NOCR }, { "ca53-cpu3", 0x200, 3, R8A77980_PD_CA53_CPU3, R8A77980_PD_CA53_SCU, PD_CPU_NOCR }, - { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON }, + { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON, + PD_CPU_NOCR }, { "a3ir", 0x180, 0, R8A77980_PD_A3IR, R8A77980_PD_ALWAYS_ON }, { "a2ir0", 0x400, 0, R8A77980_PD_A2IR0, R8A77980_PD_A3IR }, { "a2ir1", 0x400, 1, R8A77980_PD_A2IR1, R8A77980_PD_A3IR }, From 6154fb9c2134f8d9534b2de10491aa3a22f3c9ff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?= Date: Mon, 22 Jan 2024 11:29:18 -0300 Subject: [PATCH 022/311] kselftest: dt: Stop relying on dirname to improve performance MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When walking directory trees, instead of looking for specific files and running dirname to get the parent folder, traverse all folders and ignore the ones not containing the desired files. This avoids the need to call dirname inside the loop, which drastically decreases run time: Running locally on a mt8192-asurada-spherion, which reports 160 test cases, has gone from 5.5s to 2.9s, while running remotely with an nfsroot has gone from 13.5s to 5.5s. This change has a side-effect, which is that the root DT node now also shows in the output, even though it isn't expected to bind to a driver. However there shouldn't be a matching driver for the board compatible, so the end result will be just an extra skipped test: ok 1 / # SKIP Reported-by: Mark Brown Closes: https://lore.kernel.org/all/310391e8-fdf2-4c2f-a680-7744eb685177@sirena.org.uk Fixes: 14571ab1ad21 ("kselftest: Add new test for detecting unprobed Devicetree devices") Tested-by: Mark Brown Signed-off-by: Nícolas F. R. A. Prado Link: https://lore.kernel.org/r/20240122-dt-kselftest-dirname-perf-fix-v2-1-f1630532fd38@collabora.com Signed-off-by: Rob Herring --- tools/testing/selftests/dt/test_unprobed_devices.sh | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/dt/test_unprobed_devices.sh b/tools/testing/selftests/dt/test_unprobed_devices.sh index b07af2a4c4de..7fae90293a9d 100755 --- a/tools/testing/selftests/dt/test_unprobed_devices.sh +++ b/tools/testing/selftests/dt/test_unprobed_devices.sh @@ -33,8 +33,8 @@ if [[ ! -d "${PDT}" ]]; then fi nodes_compatible=$( - for node_compat in $(find ${PDT} -name compatible); do - node=$(dirname "${node_compat}") + for node in $(find ${PDT} -type d); do + [ ! -f "${node}"/compatible ] && continue # Check if node is available if [[ -e "${node}"/status ]]; then status=$(tr -d '\000' < "${node}"/status) @@ -46,10 +46,11 @@ nodes_compatible=$( nodes_dev_bound=$( IFS=$'\n' - for uevent in $(find /sys/devices -name uevent); do - if [[ -d "$(dirname "${uevent}")"/driver ]]; then - grep '^OF_FULLNAME=' "${uevent}" | sed -e 's|OF_FULLNAME=||' - fi + for dev_dir in $(find /sys/devices -type d); do + [ ! -f "${dev_dir}"/uevent ] && continue + [ ! -d "${dev_dir}"/driver ] && continue + + grep '^OF_FULLNAME=' "${dev_dir}"/uevent | sed -e 's|OF_FULLNAME=||' done ) From c41336f4d69057cbf88fed47951379b384540df5 Mon Sep 17 00:00:00 2001 From: Eugen Hristev Date: Mon, 25 Dec 2023 15:36:15 +0200 Subject: [PATCH 023/311] pmdomain: mediatek: fix race conditions with genpd If the power domains are registered first with genpd and *after that* the driver attempts to power them on in the probe sequence, then it is possible that a race condition occurs if genpd tries to power them on in the same time. The same is valid for powering them off before unregistering them from genpd. Attempt to fix race conditions by first removing the domains from genpd and *after that* powering down domains. Also first power up the domains and *after that* register them to genpd. Fixes: 59b644b01cf4 ("soc: mediatek: Add MediaTek SCPSYS power domains") Signed-off-by: Eugen Hristev Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20231225133615.78993-1-eugen.hristev@collabora.com Signed-off-by: Ulf Hansson --- drivers/pmdomain/mediatek/mtk-pm-domains.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/pmdomain/mediatek/mtk-pm-domains.c b/drivers/pmdomain/mediatek/mtk-pm-domains.c index e26dc17d07ad..e274e3315fe7 100644 --- a/drivers/pmdomain/mediatek/mtk-pm-domains.c +++ b/drivers/pmdomain/mediatek/mtk-pm-domains.c @@ -561,6 +561,11 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren goto err_put_node; } + /* recursive call to add all subdomains */ + ret = scpsys_add_subdomain(scpsys, child); + if (ret) + goto err_put_node; + ret = pm_genpd_add_subdomain(parent_pd, child_pd); if (ret) { dev_err(scpsys->dev, "failed to add %s subdomain to parent %s\n", @@ -570,11 +575,6 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren dev_dbg(scpsys->dev, "%s add subdomain: %s\n", parent_pd->name, child_pd->name); } - - /* recursive call to add all subdomains */ - ret = scpsys_add_subdomain(scpsys, child); - if (ret) - goto err_put_node; } return 0; @@ -588,9 +588,6 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd) { int ret; - if (scpsys_domain_is_on(pd)) - scpsys_power_off(&pd->genpd); - /* * We're in the error cleanup already, so we only complain, * but won't emit another error on top of the original one. @@ -600,6 +597,8 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd) dev_err(pd->scpsys->dev, "failed to remove domain '%s' : %d - state may be inconsistent\n", pd->genpd.name, ret); + if (scpsys_domain_is_on(pd)) + scpsys_power_off(&pd->genpd); clk_bulk_put(pd->num_clks, pd->clks); clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks); From afb2a4fb84555ef9e61061f6ea63ed7087b295d5 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Fri, 12 Jan 2024 19:37:29 +0100 Subject: [PATCH 024/311] riscv/efistub: Ensure GP-relative addressing is not used The cflags for the RISC-V efistub were missing -mno-relax, thus were under the risk that the compiler could use GP-relative addressing. That happened for _edata with binutils-2.41 and kernel 6.1, causing the relocation to fail due to an invalid kernel_size in handle_kernel_image. It was not yet observed with newer versions, but that may just be luck. Cc: Signed-off-by: Jan Kiszka Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/libstub/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 06964a3c130f..d561d7de46a9 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -28,7 +28,7 @@ cflags-$(CONFIG_ARM) += -DEFI_HAVE_STRLEN -DEFI_HAVE_STRNLEN \ -DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \ -DEFI_HAVE_STRCMP -fno-builtin -fpic \ $(call cc-option,-mno-single-pic-base) -cflags-$(CONFIG_RISCV) += -fpic -DNO_ALTERNATIVE +cflags-$(CONFIG_RISCV) += -fpic -DNO_ALTERNATIVE -mno-relax cflags-$(CONFIG_LOONGARCH) += -fpie cflags-$(CONFIG_EFI_PARAMS_FROM_FDT) += -I$(srctree)/scripts/dtc/libfdt From d2baf8cc82c17459fca019a12348efcf86bfec29 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 16 Jan 2024 14:52:27 +0100 Subject: [PATCH 025/311] riscv/efistub: Tighten ELF relocation check The EFI stub makefile contains logic to ensure that the objects that make up the stub do not contain relocations that require runtime fixups (typically to account for the runtime load address of the executable) On RISC-V, we also avoid GP based relocations, as they require that GP is assigned the correct base in the startup code, which is not implemented in the EFI stub. So add these relocation types to the grep expression that is used to carry out this check. Link: https://lkml.kernel.org/r/42c63cb9-87d0-49db-9af8-95771b186684%40siemens.com Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/libstub/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index d561d7de46a9..73f4810f6db3 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -143,7 +143,7 @@ STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS # exist. STUBCOPY_FLAGS-$(CONFIG_RISCV) += --prefix-alloc-sections=.init \ --prefix-symbols=__efistub_ -STUBCOPY_RELOC-$(CONFIG_RISCV) := R_RISCV_HI20 +STUBCOPY_RELOC-$(CONFIG_RISCV) := -E R_RISCV_HI20\|R_RISCV_$(BITS)\|R_RISCV_RELAX # For LoongArch, keep all the symbols in .init section and make sure that no # absolute symbols references exist. From 1793ce9f205efe07ca2992ef129b86dab2c329f5 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 30 Dec 2023 22:08:23 -0800 Subject: [PATCH 026/311] drm/msm/dpu: fix kernel-doc warnings Correct all kernel-doc warnings in dpu_encoder.c and dpu_rm.c: dpu_encoder.c:212: warning: Excess struct member 'crtc_kickoff_cb' description in 'dpu_encoder_virt' dpu_encoder.c:212: warning: Excess struct member 'crtc_kickoff_cb_data' description in 'dpu_encoder_virt' dpu_encoder.c:212: warning: Excess struct member 'debugfs_root' description in 'dpu_encoder_virt' dpu_rm.c:35: warning: Excess struct member 'hw_res' description in 'dpu_rm_requirements' dpu_rm.c:208: warning: No description found for return value of '_dpu_rm_get_lm_peer' Signed-off-by: Randy Dunlap Cc: Rob Clark Cc: Abhinav Kumar Cc: Dmitry Baryshkov Cc: Sean Paul Cc: Marijn Suijten Cc: linux-arm-msm@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: freedreno@lists.freedesktop.org Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: Jonathan Corbet Cc: Vegard Nossum Reviewed-by: Paloma Arellano Reviewed-by: Dmitry Baryshkov Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202312170641.5exlvQQx-lkp@intel.com/ Fixes: 62d35629da80 ("drm/msm/dpu: move encoder status to standard encoder debugfs dir") Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Patchwork: https://patchwork.freedesktop.org/patch/572962/ Link: https://lore.kernel.org/r/20231231060823.1934-1-rdunlap@infradead.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 4 ---- drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c | 3 ++- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 83380bc92a00..f2b82ca5efb3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -144,10 +144,6 @@ enum dpu_enc_rc_states { * to track crtc in the disable() hook which is called * _after_ encoder_mask is cleared. * @connector: If a mode is set, cached pointer to the active connector - * @crtc_kickoff_cb: Callback into CRTC that will flush & start - * all CTL paths - * @crtc_kickoff_cb_data: Opaque user data given to crtc_kickoff_cb - * @debugfs_root: Debug file system root file node * @enc_lock: Lock around physical encoder * create/destroy/enable/disable * @frame_busy_mask: Bitmask tracking which phys_enc we are still diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index b58a9c2ae326..724537ab776d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -29,7 +29,6 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx, /** * struct dpu_rm_requirements - Reservation requirements parameter bundle * @topology: selected topology for the display - * @hw_res: Hardware resources required as reported by the encoders */ struct dpu_rm_requirements { struct msm_display_topology topology; @@ -204,6 +203,8 @@ static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top) * _dpu_rm_get_lm_peer - get the id of a mixer which is a peer of the primary * @rm: dpu resource manager handle * @primary_idx: index of primary mixer in rm->mixer_blks[] + * + * Returns: lm peer mixed id on success or %-EINVAL on error */ static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx) { From 77e8aad5519e04f6c1e132aaec1c5f8faf41844f Mon Sep 17 00:00:00 2001 From: Kuogee Hsieh Date: Wed, 10 Jan 2024 12:18:51 -0800 Subject: [PATCH 027/311] drm/msms/dp: fixed link clock divider bits be over written in BPC unknown case Since the value of DP_TEST_BIT_DEPTH_8 is already left shifted, in the BPC unknown case, the additional shift causes spill over to the other bits of the [DP_CONFIGURATION_CTRL] register. Fix this by changing the return value of dp_link_get_test_bits_depth() in the BPC unknown case to (DP_TEST_BIT_DEPTH_8 >> DP_TEST_BIT_DEPTH_SHIFT). Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support") Signed-off-by: Kuogee Hsieh Reviewed-by: Abhinav Kumar Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/573989/ Link: https://lore.kernel.org/r/1704917931-30133-1-git-send-email-quic_khsieh@quicinc.com [quic_abhinavk@quicinc.com: fix minor checkpatch warning to align with opening braces] Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/dp/dp_ctrl.c | 5 ----- drivers/gpu/drm/msm/dp/dp_link.c | 10 +++++++--- 2 files changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 77a8d9366ed7..fb588fde298a 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -135,11 +135,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl) tbd = dp_link_get_test_bits_depth(ctrl->link, ctrl->panel->dp_mode.bpp); - if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) { - pr_debug("BIT_DEPTH not set. Configure default\n"); - tbd = DP_TEST_BIT_DEPTH_8; - } - config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT; /* Num of Lanes */ diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index 98427d45e9a7..a0015b9e79eb 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -1179,6 +1179,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link) u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp) { u32 tbd; + struct dp_link_private *link; + + link = container_of(dp_link, struct dp_link_private, dp_link); /* * Few simplistic rules and assumptions made here: @@ -1196,12 +1199,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp) tbd = DP_TEST_BIT_DEPTH_10; break; default: - tbd = DP_TEST_BIT_DEPTH_UNKNOWN; + drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n", + bpp); + tbd = DP_TEST_BIT_DEPTH_8; break; } - if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN) - tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT); + tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT); return tbd; } From fcccdafd91f8bdde568b86ff70848cf83f029add Mon Sep 17 00:00:00 2001 From: Kuogee Hsieh Date: Wed, 17 Jan 2024 13:13:30 -0800 Subject: [PATCH 028/311] drm/msm/dp: return correct Colorimetry for DP_TEST_DYNAMIC_RANGE_CEA case MSA MISC0 bit 1 to 7 contains Colorimetry Indicator Field. dp_link_get_colorimetry_config() returns wrong colorimetry value in the DP_TEST_DYNAMIC_RANGE_CEA case in the current implementation. Hence fix this problem by having dp_link_get_colorimetry_config() return defined CEA RGB colorimetry value in the case of DP_TEST_DYNAMIC_RANGE_CEA. Changes in V2: -- drop retrieving colorimetry from colorspace -- drop dr = link->dp_link.test_video.test_dyn_range assignment Changes in V3: -- move defined MISCr0a Colorimetry vale to dp_reg.h -- rewording commit title -- rewording commit text to more precise describe this patch Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support") Signed-off-by: Kuogee Hsieh Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/574888/ Link: https://lore.kernel.org/r/1705526010-597-1-git-send-email-quic_khsieh@quicinc.com Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/dp/dp_link.c | 12 +++++++----- drivers/gpu/drm/msm/dp/dp_reg.h | 3 +++ 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index a0015b9e79eb..49dfac1fd1ef 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -7,6 +7,7 @@ #include +#include "dp_reg.h" #include "dp_link.h" #include "dp_panel.h" @@ -1082,7 +1083,7 @@ int dp_link_process_request(struct dp_link *dp_link) int dp_link_get_colorimetry_config(struct dp_link *dp_link) { - u32 cc; + u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB; struct dp_link_private *link; if (!dp_link) { @@ -1096,10 +1097,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link) * Unless a video pattern CTS test is ongoing, use RGB_VESA * Only RGB_VESA and RGB_CEA supported for now */ - if (dp_link_is_video_pattern_requested(link)) - cc = link->dp_link.test_video.test_dyn_range; - else - cc = DP_TEST_DYNAMIC_RANGE_VESA; + if (dp_link_is_video_pattern_requested(link)) { + if (link->dp_link.test_video.test_dyn_range & + DP_TEST_DYNAMIC_RANGE_CEA) + cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB; + } return cc; } diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h index ea85a691e72b..78785ed4b40c 100644 --- a/drivers/gpu/drm/msm/dp/dp_reg.h +++ b/drivers/gpu/drm/msm/dp/dp_reg.h @@ -143,6 +143,9 @@ #define DP_MISC0_COLORIMETRY_CFG_SHIFT (0x00000001) #define DP_MISC0_TEST_BITS_DEPTH_SHIFT (0x00000005) +#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB (0) +#define DP_MISC0_COLORIMERY_CFG_CEA_RGB (0x04) + #define REG_DP_VALID_BOUNDARY (0x00000030) #define REG_DP_VALID_BOUNDARY_2 (0x00000034) From 7f3d03c48b1eb6bc45ab20ca98b8b11be25f9f52 Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Wed, 17 Jan 2024 11:41:09 -0800 Subject: [PATCH 029/311] drm/msm/dpu: check for valid hw_pp in dpu_encoder_helper_phys_cleanup The commit 8b45a26f2ba9 ("drm/msm/dpu: reserve cdm blocks for writeback in case of YUV output") introduced a smatch warning about another conditional block in dpu_encoder_helper_phys_cleanup() which had assumed hw_pp will always be valid which may not necessarily be true. Lets fix the other conditional block by making sure hw_pp is valid before dereferencing it. Reported-by: Dan Carpenter Fixes: ae4d721ce100 ("drm/msm/dpu: add an API to reset the encoder related hw blocks") Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/574878/ Link: https://lore.kernel.org/r/20240117194109.21609-1-quic_abhinavk@quicinc.com Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index f2b82ca5efb3..6a4b489d44e5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -2068,7 +2068,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) } /* reset the merge 3D HW block */ - if (phys_enc->hw_pp->merge_3d) { + if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) { phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d, BLEND_3D_NONE); if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d) @@ -2099,7 +2099,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) if (phys_enc->hw_wb) intf_cfg.wb = phys_enc->hw_wb->idx; - if (phys_enc->hw_pp->merge_3d) + if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx; if (ctl->ops.reset_intf_cfg) From 116099ed345c932a8ae4a0d884a8f6cc54fd5fed Mon Sep 17 00:00:00 2001 From: Hu Yadi Date: Tue, 23 Jan 2024 14:26:21 +0800 Subject: [PATCH 030/311] selftests/landlock: Fix net_test build with old libc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit One issue comes up while building selftest/landlock/net_test on my side (gcc 7.3/glibc-2.28/kernel-4.19). net_test.c: In function ‘set_service’: net_test.c:91:45: warning: implicit declaration of function ‘gettid’; [-Wimplicit-function-declaration] "_selftests-landlock-net-tid%d-index%d", gettid(), ^~~~~~ getgid net_test.c:(.text+0x4e0): undefined reference to `gettid' Signed-off-by: Hu Yadi Suggested-by: Jiao Reviewed-by: Berlin Fixes: a549d055a22e ("selftests/landlock: Add network tests") Link: https://lore.kernel.org/r/20240123062621.25082-1-hu.yadi@h3c.com [mic: Cosmetic fixes] Signed-off-by: Mickaël Salaün --- tools/testing/selftests/landlock/net_test.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index ea5f727dd257..efcde123af1f 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include "common.h" @@ -54,6 +55,11 @@ struct service_fixture { }; }; +static pid_t sys_gettid(void) +{ + return syscall(__NR_gettid); +} + static int set_service(struct service_fixture *const srv, const struct protocol_variant prot, const unsigned short index) @@ -88,7 +94,7 @@ static int set_service(struct service_fixture *const srv, case AF_UNIX: srv->unix_addr.sun_family = prot.domain; sprintf(srv->unix_addr.sun_path, - "_selftests-landlock-net-tid%d-index%d", gettid(), + "_selftests-landlock-net-tid%d-index%d", sys_gettid(), index); srv->unix_addr_len = SUN_LEN(&srv->unix_addr); srv->unix_addr.sun_path[0] = '\0'; From 40b7835e74e0383be308d528c5e0e41b3bf72ade Mon Sep 17 00:00:00 2001 From: Hu Yadi Date: Wed, 24 Jan 2024 10:29:08 +0800 Subject: [PATCH 031/311] selftests/landlock: Fix fs_test build with old libc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit One issue comes up while building selftest/landlock/fs_test on my side (gcc 7.3/glibc-2.28/kernel-4.19). gcc -Wall -O2 -isystem fs_test.c -lcap -o selftests/landlock/fs_test fs_test.c:4575:9: error: initializer element is not constant .mnt = mnt_tmp, ^~~~~~~ Signed-off-by: Hu Yadi Suggested-by: Jiao Reviewed-by: Berlin Link: https://lore.kernel.org/r/20240124022908.42100-1-hu.yadi@h3c.com Fixes: 04f9070e99a4 ("selftests/landlock: Add tests for pseudo filesystems") [mic: Factor out mount's data string and make mnt_tmp static] Signed-off-by: Mickaël Salaün --- tools/testing/selftests/landlock/fs_test.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 50818904397c..2d6d9b43d958 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -241,9 +241,11 @@ struct mnt_opt { const char *const data; }; -const struct mnt_opt mnt_tmp = { +#define MNT_TMP_DATA "size=4m,mode=700" + +static const struct mnt_opt mnt_tmp = { .type = "tmpfs", - .data = "size=4m,mode=700", + .data = MNT_TMP_DATA, }; static int mount_opt(const struct mnt_opt *const mnt, const char *const target) @@ -4632,7 +4634,10 @@ FIXTURE_VARIANT(layout3_fs) /* clang-format off */ FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) { /* clang-format on */ - .mnt = mnt_tmp, + .mnt = { + .type = "tmpfs", + .data = MNT_TMP_DATA, + }, .file_path = file1_s1d1, }; From 8d35217149daa33358c284aca6a56d5ab92cfc6c Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 15 Dec 2023 03:32:22 +0200 Subject: [PATCH 032/311] drm/msm/mdss: specify cfg bandwidth for SDM670 Lower the requested CFG bus bandwidth for the SDM670 platform. The default value is 153600 kBps, which is twice as big as required by the platform according to the vendor kernel. Fixes: a55c8ff252d3 ("drm/msm/mdss: Handle the reg bus ICC path") Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Tested-by: Richard Acayan Patchwork: https://patchwork.freedesktop.org/patch/572182/ Link: https://lore.kernel.org/r/20231215013222.827975-1-dmitry.baryshkov@linaro.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/msm_mdss.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 455b2e3a0cdd..35423d10aafa 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -562,6 +562,7 @@ static const struct msm_mdss_data sdm670_data = { .ubwc_enc_version = UBWC_2_0, .ubwc_dec_version = UBWC_2_0, .highest_bank_bit = 1, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data sdm845_data = { From a7a6a01f88e87dec4bf2365571dd2dc7403d52d0 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 26 Jan 2024 12:14:30 +0100 Subject: [PATCH 033/311] x86/efistub: Give up if memory attribute protocol returns an error The recently introduced EFI memory attributes protocol should be used if it exists to ensure that the memory allocation created for the kernel permits execution. This is needed for compatibility with tightened requirements related to Windows logo certification for x86 PCs. Currently, we simply strip the execute protect (XP) attribute from the entire range, but this might be rejected under some firmware security policies, and so in a subsequent patch, this will be changed to only strip XP from the executable region that runs early, and make it read-only (RO) as well. In order to catch any issues early, ensure that the memory attribute protocol works as intended, and give up if it produces spurious errors. Note that the DXE services based fallback was always based on best effort, so don't propagate any errors returned by that API. Fixes: a1b87d54f4e4 ("x86/efistub: Avoid legacy decompressor when doing EFI boot") Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/libstub/x86-stub.c | 24 ++++++++++++++---------- drivers/firmware/efi/libstub/x86-stub.h | 4 ++-- 2 files changed, 16 insertions(+), 12 deletions(-) diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 0d510c9a06a4..cb0be88c8131 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -223,8 +223,8 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) } } -void efi_adjust_memory_range_protection(unsigned long start, - unsigned long size) +efi_status_t efi_adjust_memory_range_protection(unsigned long start, + unsigned long size) { efi_status_t status; efi_gcd_memory_space_desc_t desc; @@ -236,13 +236,17 @@ void efi_adjust_memory_range_protection(unsigned long start, rounded_end = roundup(start + size, EFI_PAGE_SIZE); if (memattr != NULL) { - efi_call_proto(memattr, clear_memory_attributes, rounded_start, - rounded_end - rounded_start, EFI_MEMORY_XP); - return; + status = efi_call_proto(memattr, clear_memory_attributes, + rounded_start, + rounded_end - rounded_start, + EFI_MEMORY_XP); + if (status != EFI_SUCCESS) + efi_warn("Failed to clear EFI_MEMORY_XP attribute\n"); + return status; } if (efi_dxe_table == NULL) - return; + return EFI_SUCCESS; /* * Don't modify memory region attributes, they are @@ -255,7 +259,7 @@ void efi_adjust_memory_range_protection(unsigned long start, status = efi_dxe_call(get_memory_space_descriptor, start, &desc); if (status != EFI_SUCCESS) - return; + break; next = desc.base_address + desc.length; @@ -280,8 +284,10 @@ void efi_adjust_memory_range_protection(unsigned long start, unprotect_start, unprotect_start + unprotect_size, status); + break; } } + return EFI_SUCCESS; } static void setup_unaccepted_memory(void) @@ -805,9 +811,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) *kernel_entry = addr + entry; - efi_adjust_memory_range_protection(addr, kernel_total_size); - - return EFI_SUCCESS; + return efi_adjust_memory_range_protection(addr, kernel_total_size); } static void __noreturn enter_kernel(unsigned long kernel_addr, diff --git a/drivers/firmware/efi/libstub/x86-stub.h b/drivers/firmware/efi/libstub/x86-stub.h index 37c5a36b9d8c..1c20e99a6494 100644 --- a/drivers/firmware/efi/libstub/x86-stub.h +++ b/drivers/firmware/efi/libstub/x86-stub.h @@ -5,8 +5,8 @@ extern void trampoline_32bit_src(void *, bool); extern const u16 trampoline_ljmp_imm_offset; -void efi_adjust_memory_range_protection(unsigned long start, - unsigned long size); +efi_status_t efi_adjust_memory_range_protection(unsigned long start, + unsigned long size); #ifdef CONFIG_X86_64 efi_status_t efi_setup_5level_paging(void); From d6d33f03baa43d763fe094ca926eeae7d3421d07 Mon Sep 17 00:00:00 2001 From: Ism Hong Date: Tue, 26 Dec 2023 16:51:41 +0800 Subject: [PATCH 034/311] fs/ntfs3: use non-movable memory for ntfs3 MFT buffer cache Since the buffer cache for ntfs3 metadata is not released until the file system is unmounted, allocating from the movable zone may result in cma allocation failures. This is due to the page still being used by ntfs3, leading to migration failures. To address this, this commit use sb_bread_umovable() instead of sb_bread(). This change prevents allocation from the movable zone, ensuring compatibility with scenarios where the buffer head is not released until unmount. This patch is inspired by commit a8ac900b8163("ext4: use non-movable memory for the ext4 superblock"). The issue is found when playing video files stored in NTFS on the Android TV platform. During this process, the media parser reads the video file, causing ntfs3 to allocate buffer cache from the CMA area. Subsequently, the hardware decoder attempts to allocate memory from the same CMA area. However, the page is still in use by ntfs3, resulting in a migrate failure in alloc_contig_range(). The pinned page and allocating stacktrace reported by page owner shows below: page:ffffffff00b68880 refcount:3 mapcount:0 mapping:ffffff80046aa828 index:0xc0040 pfn:0x20fa4 aops:def_blk_aops ino:0 flags: 0x2020(active|private) page dumped because: migration failure page last allocated via order 0, migratetype Movable, gfp_mask 0x108c48 (GFP_NOFS|__GFP_NOFAIL|__GFP_HARDWALL|__GFP_MOVABLE), page_owner tracks the page as allocated prep_new_page get_page_from_freelist __alloc_pages_nodemask pagecache_get_page __getblk_gfp __bread_gfp ntfs_read_run_nb ntfs_read_bh mi_read ntfs_iget5 dir_search_u ntfs_lookup __lookup_slow lookup_slow walk_component path_lookupat Signed-off-by: Ism Hong Signed-off-by: Konstantin Komarov --- fs/ntfs3/ntfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index abbc7182554a..2b54ae94440f 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -1035,7 +1035,7 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size) static inline struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block) { - struct buffer_head *bh = sb_bread(sb, block); + struct buffer_head *bh = sb_bread_unmovable(sb, block); if (bh) return bh; From 5ca87d01eba7bdfe9536a157ca33c1455bb8d16c Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 26 Jan 2024 11:03:21 +0300 Subject: [PATCH 035/311] fs/ntfs3: Prevent generic message "attempt to access beyond end of device" It used in test environment. Signed-off-by: Konstantin Komarov --- fs/ntfs3/fsntfs.c | 24 ++++++++++++++++++++++++ fs/ntfs3/ntfs_fs.h | 14 +------------- 2 files changed, 25 insertions(+), 13 deletions(-) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 321978019407..ae2ef5c11868 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -1007,6 +1007,30 @@ static inline __le32 security_hash(const void *sd, size_t bytes) return cpu_to_le32(hash); } +/* + * simple wrapper for sb_bread_unmovable. + */ +struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block) +{ + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct buffer_head *bh; + + if (unlikely(block >= sbi->volume.blocks)) { + /* prevent generic message "attempt to access beyond end of device" */ + ntfs_err(sb, "try to read out of volume at offset 0x%llx", + (u64)block << sb->s_blocksize_bits); + return NULL; + } + + bh = sb_bread_unmovable(sb, block); + if (bh) + return bh; + + ntfs_err(sb, "failed to read volume at offset 0x%llx", + (u64)block << sb->s_blocksize_bits); + return NULL; +} + int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer) { struct block_device *bdev = sb->s_bdev; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 2b54ae94440f..81f7563428ee 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -586,6 +586,7 @@ bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes); int log_replay(struct ntfs_inode *ni, bool *initialized); /* Globals from fsntfs.c */ +struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block); bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes); int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, bool simple); @@ -1032,19 +1033,6 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size) return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; } -static inline struct buffer_head *ntfs_bread(struct super_block *sb, - sector_t block) -{ - struct buffer_head *bh = sb_bread_unmovable(sb, block); - - if (bh) - return bh; - - ntfs_err(sb, "failed to read volume at offset 0x%llx", - (u64)block << sb->s_blocksize_bits); - return NULL; -} - static inline struct ntfs_inode *ntfs_i(struct inode *inode) { return container_of(inode, struct ntfs_inode, vfs_inode); From 4fd6c08a16d7f1ba10212c9ef7bc73218144b463 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 26 Jan 2024 11:12:38 +0300 Subject: [PATCH 036/311] fs/ntfs3: Use i_size_read and i_size_write Signed-off-by: Konstantin Komarov --- fs/ntfs3/attrib.c | 4 ++-- fs/ntfs3/dir.c | 2 +- fs/ntfs3/file.c | 11 ++++++----- fs/ntfs3/frecord.c | 10 +++++----- fs/ntfs3/index.c | 8 ++++---- fs/ntfs3/inode.c | 2 +- 6 files changed, 19 insertions(+), 18 deletions(-) diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 646e2dad1b75..7aadf5010999 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -2084,7 +2084,7 @@ next_attr: /* Update inode size. */ ni->i_valid = valid_size; - ni->vfs_inode.i_size = data_size; + i_size_write(&ni->vfs_inode, data_size); inode_set_bytes(&ni->vfs_inode, total_size); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mark_inode_dirty(&ni->vfs_inode); @@ -2499,7 +2499,7 @@ int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) mi_b->dirty = true; done: - ni->vfs_inode.i_size += bytes; + i_size_write(&ni->vfs_inode, ni->vfs_inode.i_size + bytes); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mark_inode_dirty(&ni->vfs_inode); diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index 9f6dd445eb04..effa6accf8a8 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -517,7 +517,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, u32 e_size, off, end; size_t drs = 0, fles = 0, bit = 0; struct indx_node *node = NULL; - size_t max_indx = ni->vfs_inode.i_size >> ni->dir.index_bits; + size_t max_indx = i_size_read(&ni->vfs_inode) >> ni->dir.index_bits; if (is_empty) *is_empty = true; diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 07ed3d946e7c..b702543a8795 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -646,7 +646,7 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) if (err) goto out; } else if (new_size > i_size) { - inode->i_size = new_size; + i_size_write(inode, new_size); } } @@ -696,7 +696,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, goto out; } inode_dio_wait(inode); - oldsize = inode->i_size; + oldsize = i_size_read(inode); newsize = attr->ia_size; if (newsize <= oldsize) @@ -708,7 +708,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, goto out; ni->ni_flags |= NI_FLAG_UPDATE_PARENT; - inode->i_size = newsize; + i_size_write(inode, newsize); } setattr_copy(idmap, inode, attr); @@ -847,7 +847,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from) size_t count = iov_iter_count(from); loff_t pos = iocb->ki_pos; struct inode *inode = file_inode(file); - loff_t i_size = inode->i_size; + loff_t i_size = i_size_read(inode); struct address_space *mapping = inode->i_mapping; struct ntfs_inode *ni = ntfs_i(inode); u64 valid = ni->i_valid; @@ -1177,7 +1177,8 @@ static int ntfs_file_release(struct inode *inode, struct file *file) down_write(&ni->file.run_lock); err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, - inode->i_size, &ni->i_valid, false, NULL); + i_size_read(inode), &ni->i_valid, false, + NULL); up_write(&ni->file.run_lock); ni_unlock(ni); diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 2636ab7640ac..3b42938a9d3b 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -2099,7 +2099,7 @@ int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page) gfp_t gfp_mask; struct page *pg; - if (vbo >= ni->vfs_inode.i_size) { + if (vbo >= i_size_read(&ni->vfs_inode)) { SetPageUptodate(page); err = 0; goto out; @@ -2173,7 +2173,7 @@ int ni_decompress_file(struct ntfs_inode *ni) { struct ntfs_sb_info *sbi = ni->mi.sbi; struct inode *inode = &ni->vfs_inode; - loff_t i_size = inode->i_size; + loff_t i_size = i_size_read(inode); struct address_space *mapping = inode->i_mapping; gfp_t gfp_mask = mapping_gfp_mask(mapping); struct page **pages = NULL; @@ -2457,6 +2457,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages, struct ATTR_LIST_ENTRY *le = NULL; struct runs_tree *run = &ni->file.run; u64 valid_size = ni->i_valid; + loff_t i_size = i_size_read(&ni->vfs_inode); u64 vbo_disk; size_t unc_size; u32 frame_size, i, npages_disk, ondisk_size; @@ -2548,7 +2549,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages, } } - frames = (ni->vfs_inode.i_size - 1) >> frame_bits; + frames = (i_size - 1) >> frame_bits; err = attr_wof_frame_info(ni, attr, run, frame64, frames, frame_bits, &ondisk_size, &vbo_data); @@ -2556,8 +2557,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages, goto out2; if (frame64 == frames) { - unc_size = 1 + ((ni->vfs_inode.i_size - 1) & - (frame_size - 1)); + unc_size = 1 + ((i_size - 1) & (frame_size - 1)); ondisk_size = attr_size(attr) - vbo_data; } else { unc_size = frame_size; diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index cf92b2433f7a..daabaad63aaf 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1462,7 +1462,7 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, goto out2; if (in->name == I30_NAME) { - ni->vfs_inode.i_size = data_size; + i_size_write(&ni->vfs_inode, data_size); inode_set_bytes(&ni->vfs_inode, alloc_size); } @@ -1544,7 +1544,7 @@ static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, } if (in->name == I30_NAME) - ni->vfs_inode.i_size = data_size; + i_size_write(&ni->vfs_inode, data_size); *vbn = bit << indx->idx2vbn_bits; @@ -2090,7 +2090,7 @@ static int indx_shrink(struct ntfs_index *indx, struct ntfs_inode *ni, return err; if (in->name == I30_NAME) - ni->vfs_inode.i_size = new_data; + i_size_write(&ni->vfs_inode, new_data); bpb = bitmap_size(bit); if (bpb * 8 == nbits) @@ -2576,7 +2576,7 @@ int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni, err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len, &indx->alloc_run, 0, NULL, false, NULL); if (in->name == I30_NAME) - ni->vfs_inode.i_size = 0; + i_size_write(&ni->vfs_inode, 0); err = ni_remove_attr(ni, ATTR_ALLOC, in->name, in->name_len, false, NULL); diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 85452a6b1d40..eb7a8c9fba01 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -985,7 +985,7 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, } if (pos + err > inode->i_size) { - inode->i_size = pos + err; + i_size_write(inode, pos + err); dirty = true; } From 1b7dd28e14c4728ae1a815605ca33ffb4ce1b309 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 26 Jan 2024 11:13:59 +0300 Subject: [PATCH 037/311] fs/ntfs3: Correct function is_rst_area_valid Reported-by: Robert Morris Signed-off-by: Konstantin Komarov --- fs/ntfs3/fslog.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 7dbb000fc691..855519713bf7 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -465,7 +465,7 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr) { const struct RESTART_AREA *ra; u16 cl, fl, ul; - u32 off, l_size, file_dat_bits, file_size_round; + u32 off, l_size, seq_bits; u16 ro = le16_to_cpu(rhdr->ra_off); u32 sys_page = le32_to_cpu(rhdr->sys_page_size); @@ -511,13 +511,15 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr) /* Make sure the sequence number bits match the log file size. */ l_size = le64_to_cpu(ra->l_size); - file_dat_bits = sizeof(u64) * 8 - le32_to_cpu(ra->seq_num_bits); - file_size_round = 1u << (file_dat_bits + 3); - if (file_size_round != l_size && - (file_size_round < l_size || (file_size_round / 2) > l_size)) { - return false; + seq_bits = sizeof(u64) * 8 + 3; + while (l_size) { + l_size >>= 1; + seq_bits -= 1; } + if (seq_bits != ra->seq_num_bits) + return false; + /* The log page data offset and record header length must be quad-aligned. */ if (!IS_ALIGNED(le16_to_cpu(ra->data_off), 8) || !IS_ALIGNED(le16_to_cpu(ra->rec_hdr_len), 8)) From 652cfeb43d6b9aba5c7c4902bed7a7340df131fb Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 26 Jan 2024 11:14:31 +0300 Subject: [PATCH 038/311] fs/ntfs3: Fixed overflow check in mi_enum_attr() Reported-by: Robert Morris Signed-off-by: Konstantin Komarov --- fs/ntfs3/record.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 7b6423584eae..6aa3a9d44df1 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -279,7 +279,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) if (t16 > asize) return NULL; - if (t16 + le32_to_cpu(attr->res.data_size) > asize) + if (le32_to_cpu(attr->res.data_size) > asize - t16) return NULL; t32 = sizeof(short) * attr->name_len; From d68968440b1a75dee05cfac7f368f1aa139e1911 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Mon, 29 Jan 2024 10:30:09 +0300 Subject: [PATCH 039/311] fs/ntfs3: Update inode->i_size after success write into compressed file Reported-by: Giovanni Santini Signed-off-by: Konstantin Komarov --- fs/ntfs3/file.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index b702543a8795..691b0c9b95ae 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -1054,6 +1054,8 @@ out: iocb->ki_pos += written; if (iocb->ki_pos > ni->i_valid) ni->i_valid = iocb->ki_pos; + if (iocb->ki_pos > i_size) + i_size_write(inode, iocb->ki_pos); return written; } From b2dd7b953c25ffd5912dda17e980e7168bebcf6c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 17 Oct 2023 17:04:39 +0300 Subject: [PATCH 040/311] fs/ntfs3: Fix an NULL dereference bug The issue here is when this is called from ntfs_load_attr_list(). The "size" comes from le32_to_cpu(attr->res.data_size) so it can't overflow on a 64bit systems but on 32bit systems the "+ 1023" can overflow and the result is zero. This means that the kmalloc will succeed by returning the ZERO_SIZE_PTR and then the memcpy() will crash with an Oops on the next line. Fixes: be71b5cba2e6 ("fs/ntfs3: Add attrib operations") Signed-off-by: Dan Carpenter Signed-off-by: Konstantin Komarov --- fs/ntfs3/ntfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 81f7563428ee..627419bd6f77 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -475,7 +475,7 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn, int al_update(struct ntfs_inode *ni, int sync); static inline size_t al_aligned(size_t size) { - return (size + 1023) & ~(size_t)1023; + return size_add(size, 1023) & ~(size_t)1023; } /* Globals from bitfunc.c */ From 731ab1f9828800df871c5a7ab9ffe965317d3f15 Mon Sep 17 00:00:00 2001 From: Edward Adam Davis Date: Sat, 30 Dec 2023 17:00:03 +0800 Subject: [PATCH 041/311] fs/ntfs3: Fix oob in ntfs_listxattr The length of name cannot exceed the space occupied by ea. Reported-and-tested-by: syzbot+65e940cfb8f99a97aca7@syzkaller.appspotmail.com Signed-off-by: Edward Adam Davis Signed-off-by: Konstantin Komarov --- fs/ntfs3/xattr.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 071356d096d8..53e7d1fa036a 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -219,6 +219,9 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, if (!ea->name_len) break; + if (ea->name_len > ea_size) + break; + if (buffer) { /* Check if we can use field ea->name */ if (off + ea_size > size) From 1f5fa4b3b85ceb43f1053290f0ade037b50e6297 Mon Sep 17 00:00:00 2001 From: Nekun Date: Mon, 30 Oct 2023 08:33:54 +0000 Subject: [PATCH 042/311] fs/ntfs3: Add ioctl operation for directories (FITRIM) While ntfs3 supports discards, FITRIM ioctl() command has defined only for regular files. This may confuse users trying to invoke `fstrim` utility with the directory argument (for example, call `fstrim ` which is the common practice). In this case, ioctl() returns -ENOTTY without any error messages in kernel ring buffer, this may be easily interpreted as no support for discards in ntfs3 driver. Currently only FITRIM command implemented in ntfs_ioctl() and passed inode used only for dereferencing NTFS superblock, so no need for separate ioctl() handler for directories, just add existing ntfs_ioctl() handler to ntfs_dir_operations. Signed-off-by: Nekun Signed-off-by: Konstantin Komarov --- fs/ntfs3/dir.c | 4 ++++ fs/ntfs3/file.c | 4 ++-- fs/ntfs3/ntfs_fs.h | 2 ++ 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index effa6accf8a8..5cf3d9decf64 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -611,5 +611,9 @@ const struct file_operations ntfs_dir_operations = { .iterate_shared = ntfs_readdir, .fsync = generic_file_fsync, .open = ntfs_file_open, + .unlocked_ioctl = ntfs_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ntfs_compat_ioctl, +#endif }; // clang-format on diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 691b0c9b95ae..5418662c80d8 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -48,7 +48,7 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg) return 0; } -static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg) +long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; @@ -61,7 +61,7 @@ static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg) } #ifdef CONFIG_COMPAT -static long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg) +long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg) { return ntfs_ioctl(filp, cmd, (unsigned long)compat_ptr(arg)); diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 627419bd6f77..79356fd29a14 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -502,6 +502,8 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ntfs_file_open(struct inode *inode, struct file *file); int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); +long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg); +long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg); extern const struct inode_operations ntfs_special_inode_operations; extern const struct inode_operations ntfs_file_inode_operations; extern const struct file_operations ntfs_file_operations; From 622cd3daa8eae37359a6fd3c07c36d19f66606b5 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 10 Nov 2023 20:59:22 +0100 Subject: [PATCH 043/311] fs/ntfs3: Slightly simplify ntfs_inode_printk() The size passed to snprintf() includes the space for the trailing space. So there is no reason here not to use all the available space. So remove the -1 when computing 'name_len'. While at it, use the size of the array directly instead of the intermediate 'name_len' variable. snprintf() also guaranties that the buffer if NULL terminated, so there is no need to write an additional trailing NULL "To be sure". Signed-off-by: Christophe JAILLET Signed-off-by: Konstantin Komarov --- fs/ntfs3/super.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index c55a29793a8d..cef5467fd928 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -122,13 +122,12 @@ void ntfs_inode_printk(struct inode *inode, const char *fmt, ...) if (name) { struct dentry *de = d_find_alias(inode); - const u32 name_len = ARRAY_SIZE(s_name_buf) - 1; if (de) { spin_lock(&de->d_lock); - snprintf(name, name_len, " \"%s\"", de->d_name.name); + snprintf(name, sizeof(s_name_buf), " \"%s\"", + de->d_name.name); spin_unlock(&de->d_lock); - name[name_len] = 0; /* To be sure. */ } else { name[0] = 0; } From 8eed4e00a370b37b4e5985ed983dccedd555ea9d Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Mon, 29 Jan 2024 14:38:42 +0800 Subject: [PATCH 044/311] x86/lib: Revert to _ASM_EXTABLE_UA() for {get,put}_user() fixups During memory error injection test on kernels >= v6.4, the kernel panics like below. However, this issue couldn't be reproduced on kernels <= v6.3. mce: [Hardware Error]: CPU 296: Machine Check Exception: f Bank 1: bd80000000100134 mce: [Hardware Error]: RIP 10: {__get_user_nocheck_4+0x6/0x20} mce: [Hardware Error]: TSC 411a93533ed ADDR 346a8730040 MISC 86 mce: [Hardware Error]: PROCESSOR 0:a06d0 TIME 1706000767 SOCKET 1 APIC 211 microcode 80001490 mce: [Hardware Error]: Run the above through 'mcelog --ascii' mce: [Hardware Error]: Machine check: Data load in unrecoverable area of kernel Kernel panic - not syncing: Fatal local machine check The MCA code can recover from an in-kernel #MC if the fixup type is EX_TYPE_UACCESS, explicitly indicating that the kernel is attempting to access userspace memory. However, if the fixup type is EX_TYPE_DEFAULT the only thing that is raised for an in-kernel #MC is a panic. ex_handler_uaccess() would warn if users gave a non-canonical addresses (with bit 63 clear) to {get, put}_user(), which was unexpected. Therefore, commit b19b74bc99b1 ("x86/mm: Rework address range check in get_user() and put_user()") replaced _ASM_EXTABLE_UA() with _ASM_EXTABLE() for {get, put}_user() fixups. However, the new fixup type EX_TYPE_DEFAULT results in a panic. Commit 6014bc27561f ("x86-64: make access_ok() independent of LAM") added the check gp_fault_address_ok() right before the WARN_ONCE() in ex_handler_uaccess() to not warn about non-canonical user addresses due to LAM. With that in place, revert back to _ASM_EXTABLE_UA() for {get,put}_user() exception fixups in order to be able to handle in-kernel MCEs correctly again. [ bp: Massage commit message. ] Fixes: b19b74bc99b1 ("x86/mm: Rework address range check in get_user() and put_user()") Signed-off-by: Qiuxu Zhuo Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Kirill A. Shutemov Cc: Link: https://lore.kernel.org/r/20240129063842.61584-1-qiuxu.zhuo@intel.com --- arch/x86/lib/getuser.S | 24 ++++++++++++------------ arch/x86/lib/putuser.S | 20 ++++++++++---------- 2 files changed, 22 insertions(+), 22 deletions(-) diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 20ef350a60fb..10d5ed8b5990 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -163,23 +163,23 @@ SYM_CODE_END(__get_user_8_handle_exception) #endif /* get_user */ - _ASM_EXTABLE(1b, __get_user_handle_exception) - _ASM_EXTABLE(2b, __get_user_handle_exception) - _ASM_EXTABLE(3b, __get_user_handle_exception) + _ASM_EXTABLE_UA(1b, __get_user_handle_exception) + _ASM_EXTABLE_UA(2b, __get_user_handle_exception) + _ASM_EXTABLE_UA(3b, __get_user_handle_exception) #ifdef CONFIG_X86_64 - _ASM_EXTABLE(4b, __get_user_handle_exception) + _ASM_EXTABLE_UA(4b, __get_user_handle_exception) #else - _ASM_EXTABLE(4b, __get_user_8_handle_exception) - _ASM_EXTABLE(5b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(4b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(5b, __get_user_8_handle_exception) #endif /* __get_user */ - _ASM_EXTABLE(6b, __get_user_handle_exception) - _ASM_EXTABLE(7b, __get_user_handle_exception) - _ASM_EXTABLE(8b, __get_user_handle_exception) + _ASM_EXTABLE_UA(6b, __get_user_handle_exception) + _ASM_EXTABLE_UA(7b, __get_user_handle_exception) + _ASM_EXTABLE_UA(8b, __get_user_handle_exception) #ifdef CONFIG_X86_64 - _ASM_EXTABLE(9b, __get_user_handle_exception) + _ASM_EXTABLE_UA(9b, __get_user_handle_exception) #else - _ASM_EXTABLE(9b, __get_user_8_handle_exception) - _ASM_EXTABLE(10b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(9b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(10b, __get_user_8_handle_exception) #endif diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 2877f5934177..975c9c18263d 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -133,15 +133,15 @@ SYM_CODE_START_LOCAL(__put_user_handle_exception) RET SYM_CODE_END(__put_user_handle_exception) - _ASM_EXTABLE(1b, __put_user_handle_exception) - _ASM_EXTABLE(2b, __put_user_handle_exception) - _ASM_EXTABLE(3b, __put_user_handle_exception) - _ASM_EXTABLE(4b, __put_user_handle_exception) - _ASM_EXTABLE(5b, __put_user_handle_exception) - _ASM_EXTABLE(6b, __put_user_handle_exception) - _ASM_EXTABLE(7b, __put_user_handle_exception) - _ASM_EXTABLE(9b, __put_user_handle_exception) + _ASM_EXTABLE_UA(1b, __put_user_handle_exception) + _ASM_EXTABLE_UA(2b, __put_user_handle_exception) + _ASM_EXTABLE_UA(3b, __put_user_handle_exception) + _ASM_EXTABLE_UA(4b, __put_user_handle_exception) + _ASM_EXTABLE_UA(5b, __put_user_handle_exception) + _ASM_EXTABLE_UA(6b, __put_user_handle_exception) + _ASM_EXTABLE_UA(7b, __put_user_handle_exception) + _ASM_EXTABLE_UA(9b, __put_user_handle_exception) #ifdef CONFIG_X86_32 - _ASM_EXTABLE(8b, __put_user_handle_exception) - _ASM_EXTABLE(10b, __put_user_handle_exception) + _ASM_EXTABLE_UA(8b, __put_user_handle_exception) + _ASM_EXTABLE_UA(10b, __put_user_handle_exception) #endif From d877550eaf2dc9090d782864c96939397a3c6835 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Mon, 29 Jan 2024 22:36:03 -0800 Subject: [PATCH 045/311] x86/fpu: Stop relying on userspace for info to fault in xsave buffer Before this change, the expected size of the user space buffer was taken from fx_sw->xstate_size. fx_sw->xstate_size can be changed from user-space, so it is possible construct a sigreturn frame where: * fx_sw->xstate_size is smaller than the size required by valid bits in fx_sw->xfeatures. * user-space unmaps parts of the sigrame fpu buffer so that not all of the buffer required by xrstor is accessible. In this case, xrstor tries to restore and accesses the unmapped area which results in a fault. But fault_in_readable succeeds because buf + fx_sw->xstate_size is within the still mapped area, so it goes back and tries xrstor again. It will spin in this loop forever. Instead, fault in the maximum size which can be touched by XRSTOR (taken from fpstate->user_size). [ dhansen: tweak subject / changelog ] Fixes: fcb3635f5018 ("x86/fpu/signal: Handle #PF in the direct restore path") Reported-by: Konstantin Bogomolov Suggested-by: Thomas Gleixner Signed-off-by: Andrei Vagin Signed-off-by: Dave Hansen Cc:stable@vger.kernel.org Link: https://lore.kernel.org/all/20240130063603.3392627-1-avagin%40google.com --- arch/x86/kernel/fpu/signal.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 558076dbde5b..247f2225aa9f 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures, * Attempt to restore the FPU registers directly from user memory. * Pagefaults are handled and any errors returned are fatal. */ -static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, - bool fx_only, unsigned int size) +static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) { struct fpu *fpu = ¤t->thread.fpu; int ret; + /* Restore enabled features only. */ + xrestore &= fpu->fpstate->user_xfeatures; retry: fpregs_lock(); /* Ensure that XFD is up to date */ @@ -309,7 +310,7 @@ retry: if (ret != X86_TRAP_PF) return false; - if (!fault_in_readable(buf, size)) + if (!fault_in_readable(buf, fpu->fpstate->user_size)) goto retry; return false; } @@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, struct user_i387_ia32_struct env; bool success, fx_only = false; union fpregs_state *fpregs; - unsigned int state_size; u64 user_xfeatures = 0; if (use_xsave()) { @@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, return false; fx_only = !fx_sw_user.magic1; - state_size = fx_sw_user.xstate_size; user_xfeatures = fx_sw_user.xfeatures; } else { user_xfeatures = XFEATURE_MASK_FPSSE; - state_size = fpu->fpstate->user_size; } if (likely(!ia32_fxstate)) { /* Restore the FPU registers directly from user memory. */ - return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only, - state_size); + return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); } /* From 2f77465b05b1270c832b5e2ee27037672ad2a10a Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 30 Jan 2024 19:01:35 +0100 Subject: [PATCH 046/311] x86/efistub: Avoid placing the kernel below LOAD_PHYSICAL_ADDR The EFI stub's kernel placement logic randomizes the physical placement of the kernel by taking all available memory into account, and picking a region at random, based on a random seed. When KASLR is disabled, this seed is set to 0x0, and this results in the lowest available region of memory to be selected for loading the kernel, even if this is below LOAD_PHYSICAL_ADDR. Some of this memory is typically reserved for the GFP_DMA region, to accommodate masters that can only access the first 16 MiB of system memory. Even if such devices are rare these days, we may still end up with a warning in the kernel log, as reported by Tom: swapper/0: page allocation failure: order:10, mode:0xcc1(GFP_KERNEL|GFP_DMA), nodemask=(null),cpuset=/,mems_allowed=0 Fix this by tweaking the random allocation logic to accept a low bound on the placement, and set it to LOAD_PHYSICAL_ADDR. Fixes: a1b87d54f4e4 ("x86/efistub: Avoid legacy decompressor when doing EFI boot") Reported-by: Tom Englund Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218404 Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/libstub/efistub.h | 3 ++- drivers/firmware/efi/libstub/kaslr.c | 2 +- drivers/firmware/efi/libstub/randomalloc.c | 12 +++++++----- drivers/firmware/efi/libstub/x86-stub.c | 1 + drivers/firmware/efi/libstub/zboot.c | 2 +- 5 files changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 212687c30d79..c04b82ea40f2 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -956,7 +956,8 @@ efi_status_t efi_get_random_bytes(unsigned long size, u8 *out); efi_status_t efi_random_alloc(unsigned long size, unsigned long align, unsigned long *addr, unsigned long random_seed, - int memory_type, unsigned long alloc_limit); + int memory_type, unsigned long alloc_min, + unsigned long alloc_max); efi_status_t efi_random_get_seed(void); diff --git a/drivers/firmware/efi/libstub/kaslr.c b/drivers/firmware/efi/libstub/kaslr.c index 62d63f7a2645..1a9808012abd 100644 --- a/drivers/firmware/efi/libstub/kaslr.c +++ b/drivers/firmware/efi/libstub/kaslr.c @@ -119,7 +119,7 @@ efi_status_t efi_kaslr_relocate_kernel(unsigned long *image_addr, */ status = efi_random_alloc(*reserve_size, min_kimg_align, reserve_addr, phys_seed, - EFI_LOADER_CODE, EFI_ALLOC_LIMIT); + EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT); if (status != EFI_SUCCESS) efi_warn("efi_random_alloc() failed: 0x%lx\n", status); } else { diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index 674a064b8f7a..4e96a855fdf4 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -17,7 +17,7 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, unsigned long size, unsigned long align_shift, - u64 alloc_limit) + u64 alloc_min, u64 alloc_max) { unsigned long align = 1UL << align_shift; u64 first_slot, last_slot, region_end; @@ -30,11 +30,11 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, return 0; region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1, - alloc_limit); + alloc_max); if (region_end < size) return 0; - first_slot = round_up(md->phys_addr, align); + first_slot = round_up(max(md->phys_addr, alloc_min), align); last_slot = round_down(region_end - size + 1, align); if (first_slot > last_slot) @@ -56,7 +56,8 @@ efi_status_t efi_random_alloc(unsigned long size, unsigned long *addr, unsigned long random_seed, int memory_type, - unsigned long alloc_limit) + unsigned long alloc_min, + unsigned long alloc_max) { unsigned long total_slots = 0, target_slot; unsigned long total_mirrored_slots = 0; @@ -78,7 +79,8 @@ efi_status_t efi_random_alloc(unsigned long size, efi_memory_desc_t *md = (void *)map->map + map_offset; unsigned long slots; - slots = get_entry_num_slots(md, size, ilog2(align), alloc_limit); + slots = get_entry_num_slots(md, size, ilog2(align), alloc_min, + alloc_max); MD_NUM_SLOTS(md) = slots; total_slots += slots; if (md->attribute & EFI_MEMORY_MORE_RELIABLE) diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index cb0be88c8131..99429bc4b0c7 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -799,6 +799,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr, seed[0], EFI_LOADER_CODE, + LOAD_PHYSICAL_ADDR, EFI_X86_KERNEL_ALLOC_LIMIT); if (status != EFI_SUCCESS) return status; diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c index bdb17eac0cb4..1ceace956758 100644 --- a/drivers/firmware/efi/libstub/zboot.c +++ b/drivers/firmware/efi/libstub/zboot.c @@ -119,7 +119,7 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab) } status = efi_random_alloc(alloc_size, min_kimg_align, &image_base, - seed, EFI_LOADER_CODE, EFI_ALLOC_LIMIT); + seed, EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT); if (status != EFI_SUCCESS) { efi_err("Failed to allocate memory\n"); goto free_cmdline; From aa0e784dea7c1a026aabff9db1cb5d2bd92b3e92 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 19 Jan 2024 18:06:35 +0800 Subject: [PATCH 047/311] efi/libstub: Add one kernel-doc comment Add the description of @memory_type to silence the warning: drivers/firmware/efi/libstub/alignedmem.c:27: warning: Function parameter or struct member 'memory_type' not described in 'efi_allocate_pages_aligned' Signed-off-by: Yang Li [ardb: tweak comment] Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/libstub/alignedmem.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/firmware/efi/libstub/alignedmem.c b/drivers/firmware/efi/libstub/alignedmem.c index 6b83c492c3b8..31928bd87e0f 100644 --- a/drivers/firmware/efi/libstub/alignedmem.c +++ b/drivers/firmware/efi/libstub/alignedmem.c @@ -14,6 +14,7 @@ * @max: the address that the last allocated memory page shall not * exceed * @align: minimum alignment of the base of the allocation + * @memory_type: the type of memory to allocate * * Allocate pages as EFI_LOADER_DATA. The allocated pages are aligned according * to @align, which should be >= EFI_ALLOC_ALIGN. The last allocated page will From 2d3b3ab8d0d54e6c20260c8c1a73901a7a58a9cd Mon Sep 17 00:00:00 2001 From: Radhey Shyam Pandey Date: Fri, 19 Jan 2024 17:06:21 +0530 Subject: [PATCH 048/311] dt-bindings: xilinx: replace Piyush Mehta maintainership As Piyush is leaving AMD, he handed over ahci-ceva, ZynqMP Mode Pin GPIO controller, Zynq UltraScale+ MPSoC and Versal reset, Xilinx SuperSpeed DWC3 USB SoC controller, Microchip USB5744 4-port Hub Controller and Xilinx udc controller maintainership duties to Mubin and Radhey. Signed-off-by: Radhey Shyam Pandey Acked-by: Mubin Sayyed Acked-by: Michal Simek Acked-by: Krzysztof Kozlowski Acked-by: Piyush Mehta Acked-by: Bartosz Golaszewski Acked-by: Niklas Cassel Link: https://lore.kernel.org/r/1705664181-722937-1-git-send-email-radhey.shyam.pandey@amd.com Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml | 3 ++- .../devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml | 3 ++- Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml | 3 ++- Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml | 3 ++- Documentation/devicetree/bindings/usb/microchip,usb5744.yaml | 3 ++- Documentation/devicetree/bindings/usb/xlnx,usb2.yaml | 3 ++- 6 files changed, 12 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml index b29ce598f9aa..9952e0ef7767 100644 --- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml +++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml @@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Ceva AHCI SATA Controller maintainers: - - Piyush Mehta + - Mubin Sayyed + - Radhey Shyam Pandey description: | The Ceva SATA controller mostly conforms to the AHCI interface with some diff --git a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml index 56143f1fe84a..501771c672a6 100644 --- a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml +++ b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml @@ -12,7 +12,8 @@ description: PS_MODE). Every pin can be configured as input/output. maintainers: - - Piyush Mehta + - Mubin Sayyed + - Radhey Shyam Pandey properties: compatible: diff --git a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml index 49db66801429..1f1b42dde94d 100644 --- a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml +++ b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml @@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Zynq UltraScale+ MPSoC and Versal reset maintainers: - - Piyush Mehta + - Mubin Sayyed + - Radhey Shyam Pandey description: | The Zynq UltraScale+ MPSoC and Versal has several different resets. diff --git a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml index bb373eb025a5..00f87a558c7d 100644 --- a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml +++ b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml @@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Xilinx SuperSpeed DWC3 USB SoC controller maintainers: - - Piyush Mehta + - Mubin Sayyed + - Radhey Shyam Pandey properties: compatible: diff --git a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml index ff3a1707ef57..dfaf3ddde105 100644 --- a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml +++ b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml @@ -16,8 +16,9 @@ description: USB 2.0 traffic. maintainers: - - Piyush Mehta - Michal Simek + - Mubin Sayyed + - Radhey Shyam Pandey properties: compatible: diff --git a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml index 868dffe314bc..a7f75fe36665 100644 --- a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml +++ b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml @@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Xilinx udc controller maintainers: - - Piyush Mehta + - Mubin Sayyed + - Radhey Shyam Pandey properties: compatible: From 4c654ec0ba0f9a04905ebad538689524a8779154 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 22 Jan 2024 14:49:58 -0600 Subject: [PATCH 049/311] dt-bindings: display: nxp,tda998x: Fix 'audio-ports' constraints The constraints for 'audio-ports' don't match the description. There can be 1 or 2 DAI entries and each entry is exactly 2 values. Also, the values' sizes are 32-bits, not 8-bits. Move the size constraints to the outer dimension (number of DAIs) and add constraints on inner array values. Link: https://lore.kernel.org/r/20240122204959.1665970-1-robh@kernel.org Signed-off-by: Rob Herring --- .../devicetree/bindings/display/bridge/nxp,tda998x.yaml | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml b/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml index 21d995f29a1e..b8e9cf6ce4e6 100644 --- a/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml +++ b/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml @@ -29,19 +29,22 @@ properties: audio-ports: description: - Array of 8-bit values, 2 values per DAI (Documentation/sound/soc/dai.rst). + Array of 2 values per DAI (Documentation/sound/soc/dai.rst). The implementation allows one or two DAIs. If two DAIs are defined, they must be of different type. $ref: /schemas/types.yaml#/definitions/uint32-matrix + minItems: 1 + maxItems: 2 items: - minItems: 1 items: - description: | The first value defines the DAI type: TDA998x_SPDIF or TDA998x_I2S (see include/dt-bindings/display/tda998x.h). + enum: [ 1, 2 ] - description: The second value defines the tda998x AP_ENA reg content when the DAI in question is used. + maximum: 0xff '#sound-dai-cells': enum: [ 0, 1 ] From adf0c363ad2c7ceccb2831a295cd8fc50378269e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 24 Jan 2024 13:07:14 -0600 Subject: [PATCH 050/311] dt-bindings: tpm: Drop type from "resets" "resets" is a standard property which already has a type. Users only need to define how many clocks and what each clock is if more than 1 clock. Reviewed-by: Lukas Wunner Link: https://lore.kernel.org/r/20240124190714.1553772-1-robh@kernel.org Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/tpm/tpm-common.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/tpm/tpm-common.yaml b/Documentation/devicetree/bindings/tpm/tpm-common.yaml index 90390624a8be..3c1241b2a43f 100644 --- a/Documentation/devicetree/bindings/tpm/tpm-common.yaml +++ b/Documentation/devicetree/bindings/tpm/tpm-common.yaml @@ -42,7 +42,7 @@ properties: resets: description: Reset controller to reset the TPM - $ref: /schemas/types.yaml#/definitions/phandle + maxItems: 1 reset-gpios: description: Output GPIO pin to reset the TPM From 8f7e917907385e112a845d668ae2832f41e64bf5 Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Tue, 23 Jan 2024 16:14:22 +0100 Subject: [PATCH 051/311] of: property: fix typo in io-channels The property is io-channels and not io-channel. This was effectively preventing the devlink creation. Fixes: 8e12257dead7 ("of: property: Add device link support for iommus, mboxes and io-channels") Cc: stable@vger.kernel.org Signed-off-by: Nuno Sa Reviewed-by: Saravana Kannan Acked-by: Jonathan Cameron Link: https://lore.kernel.org/r/20240123-iio-backend-v7-1-1bff236b8693@analog.com Signed-off-by: Rob Herring --- drivers/of/property.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/of/property.c b/drivers/of/property.c index 641a40cf5cf3..bbf0dee2fb9c 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1244,7 +1244,7 @@ DEFINE_SIMPLE_PROP(clocks, "clocks", "#clock-cells") DEFINE_SIMPLE_PROP(interconnects, "interconnects", "#interconnect-cells") DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells") DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells") -DEFINE_SIMPLE_PROP(io_channels, "io-channel", "#io-channel-cells") +DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells") DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL) DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") From d9807d60c145836043ffa602328ea1d66dc458b1 Mon Sep 17 00:00:00 2001 From: Vincent Chen Date: Wed, 17 Jan 2024 22:03:33 +0800 Subject: [PATCH 052/311] riscv: mm: execute local TLB flush after populating vmemmap The spare_init() calls memmap_populate() many times to create VA to PA mapping for the VMEMMAP area, where all "struct page" are located once CONFIG_SPARSEMEM_VMEMMAP is defined. These "struct page" are later initialized in the zone_sizes_init() function. However, during this process, no sfence.vma instruction is executed for this VMEMMAP area. This omission may cause the hart to fail to perform page table walk because some data related to the address translation is invisible to the hart. To solve this issue, the local_flush_tlb_kernel_range() is called right after the sparse_init() to execute a sfence.vma instruction for this VMEMMAP area, ensuring that all data related to the address translation is visible to the hart. Fixes: d95f1a542c3d ("RISC-V: Implement sparsemem") Signed-off-by: Vincent Chen Reviewed-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20240117140333.2479667-1-vincent.chen@sifive.com Fixes: 7a92fc8b4d20 ("mm: Introduce flush_cache_vmap_early()") Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/tlbflush.h | 1 + arch/riscv/mm/init.c | 4 ++++ arch/riscv/mm/tlbflush.c | 3 ++- 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 928f096dca21..4112cc8d1d69 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -75,6 +75,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, #define flush_tlb_mm(mm) flush_tlb_all() #define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all() +#define local_flush_tlb_kernel_range(start, end) flush_tlb_all() #endif /* !CONFIG_SMP || !CONFIG_MMU */ #endif /* _ASM_RISCV_TLBFLUSH_H */ diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 32cad6a65ccd..fa34cf55037b 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1385,6 +1385,10 @@ void __init misc_mem_init(void) early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); arch_numa_init(); sparse_init(); +#ifdef CONFIG_SPARSEMEM_VMEMMAP + /* The entire VMEMMAP region has been populated. Flush TLB for this region */ + local_flush_tlb_kernel_range(VMEMMAP_START, VMEMMAP_END); +#endif zone_sizes_init(); arch_reserve_crashkernel(); memblock_dump_all(); diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index 8d12b26f5ac3..dffb0e5bd942 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -66,9 +66,10 @@ static inline void local_flush_tlb_range_asid(unsigned long start, local_flush_tlb_range_threshold_asid(start, size, stride, asid); } +/* Flush a range of kernel pages without broadcasting */ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) { - local_flush_tlb_range_asid(start, end, PAGE_SIZE, FLUSH_TLB_NO_ASID); + local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID); } static void __ipi_flush_tlb_all(void *info) From 607aad1e4356c210dbef9022955a3089377909b2 Mon Sep 17 00:00:00 2001 From: "Christian A. Ehrhardt" Date: Mon, 29 Jan 2024 20:25:56 +0100 Subject: [PATCH 053/311] of: unittest: Fix compile in the non-dynamic case If CONFIG_OF_KOBJ is not set, a device_node does not contain a kobj and attempts to access the embedded kobj via kref_read break the compile. Replace affected kref_read calls with a macro that reads the refcount if it exists and returns 1 if there is no embedded kobj. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202401291740.VP219WIz-lkp@intel.com/ Fixes: 4dde83569832 ("of: Fix double free in of_parse_phandle_with_args_map") Signed-off-by: Christian A. Ehrhardt Link: https://lore.kernel.org/r/20240129192556.403271-1-lk@c--e.de Signed-off-by: Rob Herring --- drivers/of/unittest.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index cfd60e35a899..d7593bde2d02 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -50,6 +50,12 @@ static struct unittest_results { failed; \ }) +#ifdef CONFIG_OF_KOBJ +#define OF_KREF_READ(NODE) kref_read(&(NODE)->kobj.kref) +#else +#define OF_KREF_READ(NODE) 1 +#endif + /* * Expected message may have a message level other than KERN_INFO. * Print the expected message only if the current loglevel will allow @@ -570,7 +576,7 @@ static void __init of_unittest_parse_phandle_with_args_map(void) pr_err("missing testcase data\n"); return; } - prefs[i] = kref_read(&p[i]->kobj.kref); + prefs[i] = OF_KREF_READ(p[i]); } rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells"); @@ -693,9 +699,9 @@ static void __init of_unittest_parse_phandle_with_args_map(void) unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); for (i = 0; i < ARRAY_SIZE(p); ++i) { - unittest(prefs[i] == kref_read(&p[i]->kobj.kref), + unittest(prefs[i] == OF_KREF_READ(p[i]), "provider%d: expected:%d got:%d\n", - i, prefs[i], kref_read(&p[i]->kobj.kref)); + i, prefs[i], OF_KREF_READ(p[i])); of_node_put(p[i]); } } From f0377ff97509f5a4921993d5d61da000361bd884 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Thu, 18 Jan 2024 12:48:54 +0100 Subject: [PATCH 054/311] nvme-host: fix the updating of the firmware version The original code didn't update the firmware version if the "next slot" of the AFI register isn't zero or if the "current slot" field is zero; in those cases it assumed that a reset was needed. However, the NVMe specification doesn't exclude the possibility that the "next slot" value is equal to the "current slot" value, meaning that the same firmware slot will be activated after performing a controller level reset; in this case a reset is clearly not necessary and we can safely update the firmware version. Modify the code so the kernel will report that a Controller Level Reset is needed only in the following cases: 1) If the "current slot" field is zero. This is invalid and means that something is wrong, a reset is needed. or 2) if the "next slot" field isn't zero AND it's not equal to the "current slot" value. This means that at the next reset a different firmware slot will be activated. Fixes: 983a338b96c8 ("nvme: update firmware version after commit") Signed-off-by: Maurizio Lombardi Reviewed-by: Daniel Wagner Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0d124a8ca9c3..975245527c1f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4191,6 +4191,7 @@ static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl) static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl) { struct nvme_fw_slot_info_log *log; + u8 next_fw_slot, cur_fw_slot; log = kmalloc(sizeof(*log), GFP_KERNEL); if (!log) @@ -4202,13 +4203,15 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl) goto out_free_log; } - if (log->afi & 0x70 || !(log->afi & 0x7)) { + cur_fw_slot = log->afi & 0x7; + next_fw_slot = (log->afi & 0x70) >> 4; + if (!cur_fw_slot || (next_fw_slot && (cur_fw_slot != next_fw_slot))) { dev_info(ctrl->device, "Firmware is activated after next Controller Level Reset\n"); goto out_free_log; } - memcpy(ctrl->subsys->firmware_rev, &log->frs[(log->afi & 0x7) - 1], + memcpy(ctrl->subsys->firmware_rev, &log->frs[cur_fw_slot - 1], sizeof(ctrl->subsys->firmware_rev)); out_free_log: From 1458eb2c9d88ad4b35eb6d6a4aa1d43d8fbf7f62 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 17 Jan 2024 20:57:40 +0100 Subject: [PATCH 055/311] riscv: Fix set_huge_pte_at() for NAPOT mapping As stated by the privileged specification, we must clear a NAPOT mapping and emit a sfence.vma before setting a new translation. Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page") Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20240117195741.1926459-2-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/hugetlbpage.c | 42 +++++++++++++++++++++++++++++++++++-- 1 file changed, 40 insertions(+), 2 deletions(-) diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 431596c0e20e..865ac5c7d159 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -177,13 +177,36 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) return entry; } +static void clear_flush(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long pgsize, + unsigned long ncontig) +{ + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); + unsigned long i, saddr = addr; + + for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) + ptep_get_and_clear(mm, addr, ptep); + + flush_tlb_range(&vma, saddr, addr); +} + +/* + * When dealing with NAPOT mappings, the privileged specification indicates that + * "if an update needs to be made, the OS generally should first mark all of the + * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions + * within the range, [...] then update the PTE(s), as described in Section + * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by + * arm64. + */ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { - unsigned long hugepage_shift; + unsigned long hugepage_shift, pgsize; int i, pte_num; if (sz >= PGDIR_SIZE) @@ -198,7 +221,22 @@ void set_huge_pte_at(struct mm_struct *mm, hugepage_shift = PAGE_SHIFT; pte_num = sz >> hugepage_shift; - for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift)) + pgsize = 1 << hugepage_shift; + + if (!pte_present(pte)) { + for (i = 0; i < pte_num; i++, ptep++, addr += pgsize) + set_ptes(mm, addr, ptep, pte, 1); + return; + } + + if (!pte_napot(pte)) { + set_ptes(mm, addr, ptep, pte, 1); + return; + } + + clear_flush(mm, addr, ptep, pgsize, pte_num); + + for (i = 0; i < pte_num; i++, ptep++, addr += pgsize) set_pte_at(mm, addr, ptep, pte); } From a179a4bfb694f80f2709a1d0398469e787acb974 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 17 Jan 2024 20:57:41 +0100 Subject: [PATCH 056/311] riscv: Fix hugetlb_mask_last_page() when NAPOT is enabled When NAPOT is enabled, a new hugepage size is available and then we need to make hugetlb_mask_last_page() aware of that. Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page") Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20240117195741.1926459-3-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/hugetlbpage.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 865ac5c7d159..87406b26c3da 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -125,6 +125,26 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return pte; } +unsigned long hugetlb_mask_last_page(struct hstate *h) +{ + unsigned long hp_size = huge_page_size(h); + + switch (hp_size) { +#ifndef __PAGETABLE_PMD_FOLDED + case PUD_SIZE: + return P4D_SIZE - PUD_SIZE; +#endif + case PMD_SIZE: + return PUD_SIZE - PMD_SIZE; + case napot_cont_size(NAPOT_CONT64KB_ORDER): + return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER); + default: + break; + } + + return 0UL; +} + static pte_t get_clear_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, From bb6f4dbe2639d5b8a9fde4bfb6fefecfd3f18df3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Thu, 25 Jan 2024 16:32:29 +0100 Subject: [PATCH 057/311] selftests/landlock: Fix capability for net_test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CAP_NET_ADMIN allows to configure network interfaces, not CAP_SYS_ADMIN which only allows to call unshare(2). Without this change, running network tests as a non-root user but with all capabilities would fail at the setup_loopback() step with "RTNETLINK answers: Operation not permitted". The issue is only visible when running tests with non-root users (i.e. only relying on ambient capabilities). Indeed, when configuring the network interface, the "ip" command is called, which may lead to the special handling of capabilities for the root user by execve(2). If root is the caller, then the inherited, permitted and effective capabilities are all reset, which then includes CAP_NET_ADMIN. However, if a non-root user is the caller, then ambient capabilities are masked by the inherited ones, which were explicitly dropped. To make execution deterministic whatever users are running the tests, set the noroot secure bit for each test, and set the inheritable and ambient capabilities to CAP_NET_ADMIN, the only capability that may be required after an execve(2). Factor out _effective_cap() into _change_cap(), and use it to manage ambient capabilities with the new set_ambient_cap() and clear_ambient_cap() helpers. This makes it possible to run all Landlock tests with check-linux.sh from https://github.com/landlock-lsm/landlock-test-tools Cc: Konstantin Meskhidze Fixes: a549d055a22e ("selftests/landlock: Add network tests") Link: https://lore.kernel.org/r/20240125153230.3817165-2-mic@digikod.net [mic: Make sure SECBIT_NOROOT_LOCKED is set] Signed-off-by: Mickaël Salaün --- tools/testing/selftests/landlock/common.h | 48 +++++++++++++++++---- tools/testing/selftests/landlock/net_test.c | 5 ++- 2 files changed, 44 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 5b79758cae62..e64bbdf0e86e 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -115,11 +116,16 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all) /* clang-format off */ CAP_DAC_OVERRIDE, CAP_MKNOD, + CAP_NET_ADMIN, + CAP_NET_BIND_SERVICE, CAP_SYS_ADMIN, CAP_SYS_CHROOT, - CAP_NET_BIND_SERVICE, /* clang-format on */ }; + const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED; + + if ((cap_get_secbits() & noroot) != noroot) + EXPECT_EQ(0, cap_set_secbits(noroot)); cap_p = cap_get_proc(); EXPECT_NE(NULL, cap_p) @@ -137,6 +143,8 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all) TH_LOG("Failed to cap_set_flag: %s", strerror(errno)); } } + + /* Automatically resets ambient capabilities. */ EXPECT_NE(-1, cap_set_proc(cap_p)) { TH_LOG("Failed to cap_set_proc: %s", strerror(errno)); @@ -145,6 +153,9 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all) { TH_LOG("Failed to cap_free: %s", strerror(errno)); } + + /* Quickly checks that ambient capabilities are cleared. */ + EXPECT_NE(-1, cap_get_ambient(caps[0])); } /* We cannot put such helpers in a library because of kselftest_harness.h . */ @@ -158,8 +169,9 @@ static void __maybe_unused drop_caps(struct __test_metadata *const _metadata) _init_caps(_metadata, true); } -static void _effective_cap(struct __test_metadata *const _metadata, - const cap_value_t caps, const cap_flag_value_t value) +static void _change_cap(struct __test_metadata *const _metadata, + const cap_flag_t flag, const cap_value_t cap, + const cap_flag_value_t value) { cap_t cap_p; @@ -168,7 +180,7 @@ static void _effective_cap(struct __test_metadata *const _metadata, { TH_LOG("Failed to cap_get_proc: %s", strerror(errno)); } - EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value)) + EXPECT_NE(-1, cap_set_flag(cap_p, flag, 1, &cap, value)) { TH_LOG("Failed to cap_set_flag: %s", strerror(errno)); } @@ -183,15 +195,35 @@ static void _effective_cap(struct __test_metadata *const _metadata, } static void __maybe_unused set_cap(struct __test_metadata *const _metadata, - const cap_value_t caps) + const cap_value_t cap) { - _effective_cap(_metadata, caps, CAP_SET); + _change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_SET); } static void __maybe_unused clear_cap(struct __test_metadata *const _metadata, - const cap_value_t caps) + const cap_value_t cap) { - _effective_cap(_metadata, caps, CAP_CLEAR); + _change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_CLEAR); +} + +static void __maybe_unused +set_ambient_cap(struct __test_metadata *const _metadata, const cap_value_t cap) +{ + _change_cap(_metadata, CAP_INHERITABLE, cap, CAP_SET); + + EXPECT_NE(-1, cap_set_ambient(cap, CAP_SET)) + { + TH_LOG("Failed to set ambient capability %d: %s", cap, + strerror(errno)); + } +} + +static void __maybe_unused clear_ambient_cap( + struct __test_metadata *const _metadata, const cap_value_t cap) +{ + EXPECT_EQ(1, cap_get_ambient(cap)); + _change_cap(_metadata, CAP_INHERITABLE, cap, CAP_CLEAR); + EXPECT_EQ(0, cap_get_ambient(cap)); } /* Receives an FD from a UNIX socket. Returns the received FD, or -errno. */ diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index efcde123af1f..936cfc879f1d 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -107,8 +107,11 @@ static void setup_loopback(struct __test_metadata *const _metadata) { set_cap(_metadata, CAP_SYS_ADMIN); ASSERT_EQ(0, unshare(CLONE_NEWNET)); - ASSERT_EQ(0, system("ip link set dev lo up")); clear_cap(_metadata, CAP_SYS_ADMIN); + + set_ambient_cap(_metadata, CAP_NET_ADMIN); + ASSERT_EQ(0, system("ip link set dev lo up")); + clear_ambient_cap(_metadata, CAP_NET_ADMIN); } static bool is_restricted(const struct protocol_variant *const prot, From de1034b38a346ef6be25fe8792f5d1e0684d5ff4 Mon Sep 17 00:00:00 2001 From: Andrew Bresticker Date: Fri, 2 Feb 2024 10:07:03 -0800 Subject: [PATCH 058/311] efi: runtime: Fix potential overflow of soft-reserved region size md_size will have been narrowed if we have >= 4GB worth of pages in a soft-reserved region. Signed-off-by: Andrew Bresticker Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/arm-runtime.c | 2 +- drivers/firmware/efi/riscv-runtime.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 83f5bb57fa4c..83092d93f36a 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -107,7 +107,7 @@ static int __init arm_enable_runtime_services(void) efi_memory_desc_t *md; for_each_efi_memory_desc(md) { - int md_size = md->num_pages << EFI_PAGE_SHIFT; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; struct resource *res; if (!(md->attribute & EFI_MEMORY_SP)) diff --git a/drivers/firmware/efi/riscv-runtime.c b/drivers/firmware/efi/riscv-runtime.c index 09525fb5c240..01f0f90ea418 100644 --- a/drivers/firmware/efi/riscv-runtime.c +++ b/drivers/firmware/efi/riscv-runtime.c @@ -85,7 +85,7 @@ static int __init riscv_enable_runtime_services(void) efi_memory_desc_t *md; for_each_efi_memory_desc(md) { - int md_size = md->num_pages << EFI_PAGE_SHIFT; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; struct resource *res; if (!(md->attribute & EFI_MEMORY_SP)) From 0bcff59ef7a652fcdc6d535554b63278c2406c8f Mon Sep 17 00:00:00 2001 From: Andrew Bresticker Date: Fri, 2 Feb 2024 10:07:04 -0800 Subject: [PATCH 059/311] efi: Don't add memblocks for soft-reserved memory Adding memblocks for soft-reserved regions prevents them from later being hotplugged in by dax_kmem. Signed-off-by: Andrew Bresticker Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/efi-init.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index d4987d013080..a00e07b853f2 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -143,15 +143,6 @@ static __init int is_usable_memory(efi_memory_desc_t *md) case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: case EFI_PERSISTENT_MEMORY: - /* - * Special purpose memory is 'soft reserved', which means it - * is set aside initially, but can be hotplugged back in or - * be assigned to the dax driver after boot. - */ - if (efi_soft_reserve_enabled() && - (md->attribute & EFI_MEMORY_SP)) - return false; - /* * According to the spec, these regions are no longer reserved * after calling ExitBootServices(). However, we can only use @@ -196,6 +187,16 @@ static __init void reserve_regions(void) size = npages << PAGE_SHIFT; if (is_memory(md)) { + /* + * Special purpose memory is 'soft reserved', which + * means it is set aside initially. Don't add a memblock + * for it now so that it can be hotplugged back in or + * be assigned to the dax driver after boot. + */ + if (efi_soft_reserve_enabled() && + (md->attribute & EFI_MEMORY_SP)) + continue; + early_init_dt_add_memory_arch(paddr, size); if (!is_usable_memory(md)) From 54ce1927eb787f7bbb7ee664841c8f5932703f39 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 31 Jan 2024 15:55:38 -0800 Subject: [PATCH 060/311] cxl/cper: Fix errant CPER prints for CXL events Jonathan reports that CXL CPER events dump an extra generic error message. {1}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 1 {1}[Hardware Error]: event severity: recoverable {1}[Hardware Error]: Error 0, type: recoverable {1}[Hardware Error]: section type: unknown, fbcd0a77-c260-417f-85a9-088b1621eba6 {1}[Hardware Error]: section length: 0x90 {1}[Hardware Error]: 00000000: 00000090 00000007 00000000 0d938086 ................ {1}[Hardware Error]: 00000010: 00100000 00000000 00040000 00000000 ................ ... CXL events were rerouted though the CXL subsystem for additional processing. However, when that work was done it was missed that cper_estatus_print_section() continued with a generic error message which is confusing. Teach CPER print code to ignore printing details of some section types. Assign the CXL event GUIDs to this set to prevent confusing unknown prints. Reported-by: Jonathan Cameron Suggested-by: Jonathan Cameron Signed-off-by: Ira Weiny Reviewed-by: Dave Jiang Reviewed-by: Jonathan Cameron Reviewed-by: Alison Schofield Signed-off-by: Ard Biesheuvel --- drivers/acpi/apei/ghes.c | 26 -------------------------- drivers/firmware/efi/cper.c | 19 +++++++++++++++++++ include/linux/cper.h | 23 +++++++++++++++++++++++ 3 files changed, 42 insertions(+), 26 deletions(-) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 7b7c605166e0..fe825a432c5b 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -680,32 +680,6 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata, static DECLARE_RWSEM(cxl_cper_rw_sem); static cxl_cper_callback cper_callback; -/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */ - -/* - * General Media Event Record - * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 - */ -#define CPER_SEC_CXL_GEN_MEDIA_GUID \ - GUID_INIT(0xfbcd0a77, 0xc260, 0x417f, \ - 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6) - -/* - * DRAM Event Record - * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 - */ -#define CPER_SEC_CXL_DRAM_GUID \ - GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, \ - 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24) - -/* - * Memory Module Event Record - * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 - */ -#define CPER_SEC_CXL_MEM_MODULE_GUID \ - GUID_INIT(0xfe927475, 0xdd59, 0x4339, \ - 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74) - static void cxl_cper_post_event(enum cxl_event_type event_type, struct cxl_cper_event_rec *rec) { diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 35c37f667781..9b3884ff81e6 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -523,6 +523,17 @@ static void cper_print_tstamp(const char *pfx, } } +struct ignore_section { + guid_t guid; + const char *name; +}; + +static const struct ignore_section ignore_sections[] = { + { .guid = CPER_SEC_CXL_GEN_MEDIA_GUID, .name = "CXL General Media Event" }, + { .guid = CPER_SEC_CXL_DRAM_GUID, .name = "CXL DRAM Event" }, + { .guid = CPER_SEC_CXL_MEM_MODULE_GUID, .name = "CXL Memory Module Event" }, +}; + static void cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata, int sec_no) @@ -543,6 +554,14 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text); snprintf(newpfx, sizeof(newpfx), "%s ", pfx); + + for (int i = 0; i < ARRAY_SIZE(ignore_sections); i++) { + if (guid_equal(sec_type, &ignore_sections[i].guid)) { + printk("%ssection_type: %s\n", newpfx, ignore_sections[i].name); + return; + } + } + if (guid_equal(sec_type, &CPER_SEC_PROC_GENERIC)) { struct cper_sec_proc_generic *proc_err = acpi_hest_get_payload(gdata); diff --git a/include/linux/cper.h b/include/linux/cper.h index c1a7dc325121..265b0f8fc0b3 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -90,6 +90,29 @@ enum { GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E, \ 0x72, 0x2D, 0xEB, 0x41) +/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */ +/* + * General Media Event Record + * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + */ +#define CPER_SEC_CXL_GEN_MEDIA_GUID \ + GUID_INIT(0xfbcd0a77, 0xc260, 0x417f, \ + 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6) +/* + * DRAM Event Record + * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 + */ +#define CPER_SEC_CXL_DRAM_GUID \ + GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, \ + 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24) +/* + * Memory Module Event Record + * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 + */ +#define CPER_SEC_CXL_MEM_MODULE_GUID \ + GUID_INIT(0xfe927475, 0xdd59, 0x4339, \ + 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74) + /* * Flags bits definitions for flags in struct cper_record_header * If set, the error has been recovered From dbea519d6878c298dd0f48e6ec2dbacebe4bbb2a Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 31 Jan 2024 15:55:39 -0800 Subject: [PATCH 061/311] cxl/trace: Remove unnecessary memcpy's CPER events don't have UUIDs. Therefore UUIDs were removed from the records passed to trace events and replaced with hard coded values. As pointed out by Jonathan, the new defines for the UUIDs present a more efficient way to assign UUID in trace records.[1] Replace memcpy's with the use of static data. [1] https://lore.kernel.org/all/20240108132325.00000e9c@Huawei.com/ Suggested-by: Jonathan Cameron Signed-off-by: Ira Weiny Reviewed-by: Dave Jiang Reviewed-by: Alison Schofield Reviewed-by: Jonathan Cameron Signed-off-by: Ard Biesheuvel --- drivers/cxl/core/trace.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index 89445435303a..bdf117a33744 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -338,7 +338,7 @@ TRACE_EVENT(cxl_general_media, TP_fast_assign( CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); - memcpy(&__entry->hdr_uuid, &CXL_EVENT_GEN_MEDIA_UUID, sizeof(uuid_t)); + __entry->hdr_uuid = CXL_EVENT_GEN_MEDIA_UUID; /* General Media */ __entry->dpa = le64_to_cpu(rec->phys_addr); @@ -425,7 +425,7 @@ TRACE_EVENT(cxl_dram, TP_fast_assign( CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); - memcpy(&__entry->hdr_uuid, &CXL_EVENT_DRAM_UUID, sizeof(uuid_t)); + __entry->hdr_uuid = CXL_EVENT_DRAM_UUID; /* DRAM */ __entry->dpa = le64_to_cpu(rec->phys_addr); @@ -573,7 +573,7 @@ TRACE_EVENT(cxl_memory_module, TP_fast_assign( CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr); - memcpy(&__entry->hdr_uuid, &CXL_EVENT_MEM_MODULE_UUID, sizeof(uuid_t)); + __entry->hdr_uuid = CXL_EVENT_MEM_MODULE_UUID; /* Memory Module Event */ __entry->event_type = rec->event_type; From 1168491e7f53581ba7b6014a39a49cfbbb722feb Mon Sep 17 00:00:00 2001 From: Loic Prylli Date: Fri, 3 Nov 2023 11:30:55 +0100 Subject: [PATCH 062/311] hwmon: (aspeed-pwm-tacho) mutex for tach reading the ASPEED_PTCR_RESULT Register can only hold the result for a single fan input. Adding a mutex to protect the register until the reading is done. Signed-off-by: Loic Prylli Signed-off-by: Alexander Hansen Fixes: 2d7a548a3eff ("drivers: hwmon: Support for ASPEED PWM/Fan tach") Link: https://lore.kernel.org/r/121d888762a1232ef403cf35230ccf7b3887083a.1699007401.git.alexander.hansen@9elements.com Signed-off-by: Guenter Roeck --- drivers/hwmon/aspeed-pwm-tacho.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c index f6e1e55e8292..4acc1858d8ac 100644 --- a/drivers/hwmon/aspeed-pwm-tacho.c +++ b/drivers/hwmon/aspeed-pwm-tacho.c @@ -195,6 +195,8 @@ struct aspeed_pwm_tacho_data { u8 fan_tach_ch_source[MAX_ASPEED_FAN_TACH_CHANNELS]; struct aspeed_cooling_device *cdev[8]; const struct attribute_group *groups[3]; + /* protects access to shared ASPEED_PTCR_RESULT */ + struct mutex tach_lock; }; enum type { TYPEM, TYPEN, TYPEO }; @@ -529,6 +531,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv, u8 fan_tach_ch_source, type, mode, both; int ret; + mutex_lock(&priv->tach_lock); + regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0); regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0x1 << fan_tach_ch); @@ -546,6 +550,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv, ASPEED_RPM_STATUS_SLEEP_USEC, usec); + mutex_unlock(&priv->tach_lock); + /* return -ETIMEDOUT if we didn't get an answer. */ if (ret) return ret; @@ -915,6 +921,7 @@ static int aspeed_pwm_tacho_probe(struct platform_device *pdev) priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + mutex_init(&priv->tach_lock); priv->regmap = devm_regmap_init(dev, NULL, (__force void *)regs, &aspeed_pwm_tacho_regmap_config); if (IS_ERR(priv->regmap)) From 4e440abc894585a34c2904a32cd54af1742311b3 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Fri, 2 Feb 2024 17:21:34 +0800 Subject: [PATCH 063/311] hwmon: (coretemp) Fix out-of-bounds memory access Fix a bug that pdata->cpu_map[] is set before out-of-bounds check. The problem might be triggered on systems with more than 128 cores per package. Fixes: 7108b80a542b ("hwmon/coretemp: Handle large core ID value") Signed-off-by: Zhang Rui Cc: Link: https://lore.kernel.org/r/20240202092144.71180-2-rui.zhang@intel.com Signed-off-by: Guenter Roeck --- drivers/hwmon/coretemp.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index ba82d1e79c13..e78c76919111 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -509,18 +509,14 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, if (pkg_flag) { attr_no = PKG_SYSFS_ATTR_NO; } else { - index = ida_alloc(&pdata->ida, GFP_KERNEL); + index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL); if (index < 0) return index; + pdata->cpu_map[index] = topology_core_id(cpu); attr_no = index + BASE_SYSFS_ATTR_NO; } - if (attr_no > MAX_CORE_DATA - 1) { - err = -ERANGE; - goto ida_free; - } - tdata = init_temp_data(cpu, pkg_flag); if (!tdata) { err = -ENOMEM; From fdaf0c8629d4524a168cb9e4ad4231875749b28c Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Fri, 2 Feb 2024 17:21:35 +0800 Subject: [PATCH 064/311] hwmon: (coretemp) Fix bogus core_id to attr name mapping Before commit 7108b80a542b ("hwmon/coretemp: Handle large core ID value"), there is a fixed mapping between 1. cpu_core_id 2. the index in pdata->core_data[] array 3. the sysfs attr name, aka "tempX_" The later two always equal cpu_core_id + 2. After the commit, pdata->core_data[] index is got from ida so that it can handle sparse core ids and support more cores within a package. However, the commit erroneously maps the sysfs attr name to pdata->core_data[] index instead of cpu_core_id + 2. As a result, the code is not aligned with the comments, and brings user visible changes in hwmon sysfs on systems with sparse core id. For example, before commit 7108b80a542b ("hwmon/coretemp: Handle large core ID value"), /sys/class/hwmon/hwmon2/temp2_label:Core 0 /sys/class/hwmon/hwmon2/temp3_label:Core 1 /sys/class/hwmon/hwmon2/temp4_label:Core 2 /sys/class/hwmon/hwmon2/temp5_label:Core 3 /sys/class/hwmon/hwmon2/temp6_label:Core 4 /sys/class/hwmon/hwmon3/temp10_label:Core 8 /sys/class/hwmon/hwmon3/temp11_label:Core 9 after commit, /sys/class/hwmon/hwmon2/temp2_label:Core 0 /sys/class/hwmon/hwmon2/temp3_label:Core 1 /sys/class/hwmon/hwmon2/temp4_label:Core 2 /sys/class/hwmon/hwmon2/temp5_label:Core 3 /sys/class/hwmon/hwmon2/temp6_label:Core 4 /sys/class/hwmon/hwmon2/temp7_label:Core 8 /sys/class/hwmon/hwmon2/temp8_label:Core 9 Restore the previous behavior and rework the code, comments and variable names to avoid future confusions. Fixes: 7108b80a542b ("hwmon/coretemp: Handle large core ID value") Signed-off-by: Zhang Rui Link: https://lore.kernel.org/r/20240202092144.71180-3-rui.zhang@intel.com Signed-off-by: Guenter Roeck --- drivers/hwmon/coretemp.c | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index e78c76919111..95f4c0b00b2d 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -419,7 +419,7 @@ static ssize_t show_temp(struct device *dev, } static int create_core_attrs(struct temp_data *tdata, struct device *dev, - int attr_no) + int index) { int i; static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev, @@ -431,13 +431,20 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev, }; for (i = 0; i < tdata->attr_size; i++) { + /* + * We map the attr number to core id of the CPU + * The attr number is always core id + 2 + * The Pkgtemp will always show up as temp1_*, if available + */ + int attr_no = tdata->is_pkg_data ? 1 : tdata->cpu_core_id + 2; + snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH, "temp%d_%s", attr_no, suffixes[i]); sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr); tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i]; tdata->sd_attrs[i].dev_attr.attr.mode = 0444; tdata->sd_attrs[i].dev_attr.show = rd_ptr[i]; - tdata->sd_attrs[i].index = attr_no; + tdata->sd_attrs[i].index = index; tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr; } tdata->attr_group.attrs = tdata->attrs; @@ -495,26 +502,25 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, struct platform_data *pdata = platform_get_drvdata(pdev); struct cpuinfo_x86 *c = &cpu_data(cpu); u32 eax, edx; - int err, index, attr_no; + int err, index; if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) return 0; /* - * Find attr number for sysfs: - * We map the attr number to core id of the CPU - * The attr number is always core id + 2 - * The Pkgtemp will always show up as temp1_*, if available + * Get the index of tdata in pdata->core_data[] + * tdata for package: pdata->core_data[1] + * tdata for core: pdata->core_data[2] .. pdata->core_data[NUM_REAL_CORES + 1] */ if (pkg_flag) { - attr_no = PKG_SYSFS_ATTR_NO; + index = PKG_SYSFS_ATTR_NO; } else { index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL); if (index < 0) return index; pdata->cpu_map[index] = topology_core_id(cpu); - attr_no = index + BASE_SYSFS_ATTR_NO; + index += BASE_SYSFS_ATTR_NO; } tdata = init_temp_data(cpu, pkg_flag); @@ -540,20 +546,20 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, if (get_ttarget(tdata, &pdev->dev) >= 0) tdata->attr_size++; - pdata->core_data[attr_no] = tdata; + pdata->core_data[index] = tdata; /* Create sysfs interfaces */ - err = create_core_attrs(tdata, pdata->hwmon_dev, attr_no); + err = create_core_attrs(tdata, pdata->hwmon_dev, index); if (err) goto exit_free; return 0; exit_free: - pdata->core_data[attr_no] = NULL; + pdata->core_data[index] = NULL; kfree(tdata); ida_free: if (!pkg_flag) - ida_free(&pdata->ida, index); + ida_free(&pdata->ida, index - BASE_SYSFS_ATTR_NO); return err; } From 34cf8c657cf0365791cdc658ddbca9cc907726ce Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Fri, 2 Feb 2024 17:21:36 +0800 Subject: [PATCH 065/311] hwmon: (coretemp) Enlarge per package core count limit Currently, coretemp driver supports only 128 cores per package. This loses some core temperature information on systems that have more than 128 cores per package. [ 58.685033] coretemp coretemp.0: Adding Core 128 failed [ 58.692009] coretemp coretemp.0: Adding Core 129 failed ... Enlarge the limitation to 512 because there are platforms with more than 256 cores per package. Signed-off-by: Zhang Rui Link: https://lore.kernel.org/r/20240202092144.71180-4-rui.zhang@intel.com Signed-off-by: Guenter Roeck --- drivers/hwmon/coretemp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 95f4c0b00b2d..b8fc8d1ef20d 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -41,7 +41,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius"); #define PKG_SYSFS_ATTR_NO 1 /* Sysfs attribute for package temp */ #define BASE_SYSFS_ATTR_NO 2 /* Sysfs Base attr no for coretemp */ -#define NUM_REAL_CORES 128 /* Number of Real cores per cpu */ +#define NUM_REAL_CORES 512 /* Number of Real cores per cpu */ #define CORETEMP_NAME_LENGTH 28 /* String Length of attrs */ #define MAX_CORE_ATTRS 4 /* Maximum no of basic attrs */ #define TOTAL_ATTRS (MAX_CORE_ATTRS + 1) From 1a00897e5e96c29b21580dfcfec168dc16c67469 Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Fri, 4 Aug 2023 12:05:44 +0800 Subject: [PATCH 066/311] drm/i915: Replace dead 01.org link 01.org is dead so replace old gvt link with current wiki page. Acked-by: Jani Nikula Reviewed-by: Zhi Wang Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20230804040544.1972958-1-zhenyuw@linux.intel.com --- MAINTAINERS | 2 +- drivers/gpu/drm/i915/Kconfig | 2 +- drivers/gpu/drm/i915/intel_gvt.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 8d1052fa6a69..03fbe24bf40d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10804,7 +10804,7 @@ M: Zhi Wang L: intel-gvt-dev@lists.freedesktop.org L: intel-gfx@lists.freedesktop.org S: Supported -W: https://01.org/igvt-g +W: https://github.com/intel/gvt-linux/wiki T: git https://github.com/intel/gvt-linux.git F: drivers/gpu/drm/i915/gvt/ diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index b5d6e3352071..3089029abba4 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -140,7 +140,7 @@ config DRM_I915_GVT_KVMGT Note that this driver only supports newer device from Broadwell on. For further information and setup guide, you can visit: - http://01.org/igvt-g. + https://github.com/intel/gvt-linux/wiki. If in doubt, say "N". diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c index e98b6d69a91a..9b6d87c8b583 100644 --- a/drivers/gpu/drm/i915/intel_gvt.c +++ b/drivers/gpu/drm/i915/intel_gvt.c @@ -41,7 +41,7 @@ * To virtualize GPU resources GVT-g driver depends on hypervisor technology * e.g KVM/VFIO/mdev, Xen, etc. to provide resource access trapping capability * and be virtualized within GVT-g device module. More architectural design - * doc is available on https://01.org/group/2230/documentation-list. + * doc is available on https://github.com/intel/gvt-linux/wiki. */ static LIST_HEAD(intel_gvt_devices); From 47caa96478b99d6d1199b89467cc3e5a6cc754ee Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 26 Jan 2024 11:41:47 +0300 Subject: [PATCH 067/311] drm/i915/gvt: Fix uninitialized variable in handle_mmio() This code prints the wrong variable in the warning message. It should print "i" instead of "info->offset". On the first iteration "info" is uninitialized leading to a crash and on subsequent iterations it prints the previous offset instead of the current one. Fixes: e0f74ed4634d ("i915/gvt: Separate the MMIO tracking table from GVT-g") Signed-off-by: Dan Carpenter Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/11957c20-b178-4027-9b0a-e32e9591dd7c@moroto.mountain Reviewed-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/handlers.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 90f6c1ece57d..efcb00472be2 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -2849,8 +2849,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset, for (i = start; i < end; i += 4) { p = intel_gvt_find_mmio_info(gvt, i); if (p) { - WARN(1, "dup mmio definition offset %x\n", - info->offset); + WARN(1, "dup mmio definition offset %x\n", i); /* We return -EEXIST here to make GVT-g load fail. * So duplicated MMIO can be found as soon as From 44e4192f88978e32e4ac08b27141f3767366f79b Mon Sep 17 00:00:00 2001 From: Zhi Wang Date: Tue, 30 Jan 2024 21:27:43 +0000 Subject: [PATCH 068/311] MAINTAINERS: Update Zhi Wang's email address Update my email address to zhi.wang.linux@gmail.com. CC: Zhenyu Wang Acked-by: Zhenyu Wang Signed-off-by: Zhi Wang Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20240130212743.7727-1-zhi.wang.linux@gmail.com --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 03fbe24bf40d..052149d304ba 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10800,7 +10800,7 @@ F: drivers/gpio/gpio-tangier.h INTEL GVT-g DRIVERS (Intel GPU Virtualization) M: Zhenyu Wang -M: Zhi Wang +M: Zhi Wang L: intel-gvt-dev@lists.freedesktop.org L: intel-gfx@lists.freedesktop.org S: Supported From 1ad55cecf22f05f1c884adf63cc09d3c3e609ebf Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 5 Feb 2024 09:11:07 +0100 Subject: [PATCH 069/311] x86/efistub: Use 1:1 file:memory mapping for PE/COFF .compat section The .compat section is a dummy PE section that contains the address of the 32-bit entrypoint of the 64-bit kernel image if it is bootable from 32-bit firmware (i.e., CONFIG_EFI_MIXED=y) This section is only 8 bytes in size and is only referenced from the loader, and so it is placed at the end of the memory view of the image, to avoid the need for padding it to 4k, which is required for sections appearing in the middle of the image. Unfortunately, this violates the PE/COFF spec, and even if most EFI loaders will work correctly (including the Tianocore reference implementation), PE loaders do exist that reject such images, on the basis that both the file and memory views of the file contents should be described by the section headers in a monotonically increasing manner without leaving any gaps. So reorganize the sections to avoid this issue. This results in a slight padding overhead (< 4k) which can be avoided if desired by disabling CONFIG_EFI_MIXED (which is only needed in rare cases these days) Fixes: 3e3eabe26dc8 ("x86/boot: Increase section and file alignment to 4k/512") Reported-by: Mike Beaton Link: https://lkml.kernel.org/r/CAHzAAWQ6srV6LVNdmfbJhOwhBw5ZzxxZZ07aHt9oKkfYAdvuQQ%40mail.gmail.com Signed-off-by: Ard Biesheuvel --- arch/x86/boot/header.S | 14 ++++++-------- arch/x86/boot/setup.ld | 6 +++--- 2 files changed, 9 insertions(+), 11 deletions(-) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index b2771710ed98..a1bbedd989e4 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -106,8 +106,7 @@ extra_header_fields: .word 0 # MinorSubsystemVersion .long 0 # Win32VersionValue - .long setup_size + ZO__end + pecompat_vsize - # SizeOfImage + .long setup_size + ZO__end # SizeOfImage .long salign # SizeOfHeaders .long 0 # CheckSum @@ -143,7 +142,7 @@ section_table: .ascii ".setup" .byte 0 .byte 0 - .long setup_size - salign # VirtualSize + .long pecompat_fstart - salign # VirtualSize .long salign # VirtualAddress .long pecompat_fstart - salign # SizeOfRawData .long salign # PointerToRawData @@ -156,8 +155,8 @@ section_table: #ifdef CONFIG_EFI_MIXED .asciz ".compat" - .long 8 # VirtualSize - .long setup_size + ZO__end # VirtualAddress + .long pecompat_fsize # VirtualSize + .long pecompat_fstart # VirtualAddress .long pecompat_fsize # SizeOfRawData .long pecompat_fstart # PointerToRawData @@ -172,17 +171,16 @@ section_table: * modes this image supports. */ .pushsection ".pecompat", "a", @progbits - .balign falign - .set pecompat_vsize, salign + .balign salign .globl pecompat_fstart pecompat_fstart: .byte 0x1 # Version .byte 8 # Size .word IMAGE_FILE_MACHINE_I386 # PE machine type .long setup_size + ZO_efi32_pe_entry # Entrypoint + .byte 0x0 # Sentinel .popsection #else - .set pecompat_vsize, 0 .set pecompat_fstart, setup_size #endif .ascii ".text" diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 83bb7efad8ae..3a2d1360abb0 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -24,6 +24,9 @@ SECTIONS .text : { *(.text .text.*) } .text32 : { *(.text32) } + .pecompat : { *(.pecompat) } + PROVIDE(pecompat_fsize = setup_size - pecompat_fstart); + . = ALIGN(16); .rodata : { *(.rodata*) } @@ -36,9 +39,6 @@ SECTIONS . = ALIGN(16); .data : { *(.data*) } - .pecompat : { *(.pecompat) } - PROVIDE(pecompat_fsize = setup_size - pecompat_fstart); - .signature : { setup_sig = .; LONG(0x5a5aaa55) From c712c05e46c8ce550842951e9e2606e24dbf0475 Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Sun, 4 Feb 2024 17:19:12 +0800 Subject: [PATCH 070/311] spi: imx: fix the burst length at DMA mode and CPU mode For DMA mode, the bus width of the DMA is equal to the size of data word, so burst length should be configured as bits per word. For CPU mode, because of the spi transfer len is in byte, so calculate the total number of words according to spi transfer len and bits per word, burst length should be configured as total data bits. Signed-off-by: Carlos Song Reviewed-by: Clark Wang Fixes: e9b220aeacf1 ("spi: spi-imx: correctly configure burst length when using dma") Fixes: 5f66db08cbd3 ("spi: imx: Take in account bits per word instead of assuming 8-bits") Link: https://lore.kernel.org/r/20240204091912.36488-1-carlos.song@nxp.com Signed-off-by: Mark Brown --- drivers/spi/spi-imx.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 546cdce525fc..833a1bb7a914 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -2,6 +2,7 @@ // Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved. // Copyright (C) 2008 Juergen Beisert +#include #include #include #include @@ -660,15 +661,15 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, << MX51_ECSPI_CTRL_BL_OFFSET; else { if (spi_imx->usedma) { - ctrl |= (spi_imx->bits_per_word * - spi_imx_bytes_per_word(spi_imx->bits_per_word) - 1) + ctrl |= (spi_imx->bits_per_word - 1) << MX51_ECSPI_CTRL_BL_OFFSET; } else { if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST) - ctrl |= (MX51_ECSPI_CTRL_MAX_BURST - 1) + ctrl |= (MX51_ECSPI_CTRL_MAX_BURST * BITS_PER_BYTE - 1) << MX51_ECSPI_CTRL_BL_OFFSET; else - ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1) + ctrl |= spi_imx->count / DIV_ROUND_UP(spi_imx->bits_per_word, + BITS_PER_BYTE) * spi_imx->bits_per_word << MX51_ECSPI_CTRL_BL_OFFSET; } } From 17adc3f329e922bd1dd5aee45f43d9dab351c1e9 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 22 Jan 2024 11:35:14 -0600 Subject: [PATCH 071/311] net: marvell,prestera: Fix example PCI bus addressing The example for PCI devices has some addressing errors. 'reg' is written as if the parent bus is PCI, but the default bus for examples is 1 address and size cell. 'ranges' is defining config space with a size of 0. Generally, config space should not be defined in 'ranges', only PCI memory and I/O spaces. Fix these issues by updating the values with made-up, but valid values. This was uncovered with recent dtschema changes. Link: https://lore.kernel.org/r/20240122173514.935742-1-robh@kernel.org Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/net/marvell,prestera.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/net/marvell,prestera.yaml b/Documentation/devicetree/bindings/net/marvell,prestera.yaml index 5ea8b73663a5..16ff892f7bbd 100644 --- a/Documentation/devicetree/bindings/net/marvell,prestera.yaml +++ b/Documentation/devicetree/bindings/net/marvell,prestera.yaml @@ -78,8 +78,8 @@ examples: pcie@0 { #address-cells = <3>; #size-cells = <2>; - ranges = <0x0 0x0 0x0 0x0 0x0 0x0>; - reg = <0x0 0x0 0x0 0x0 0x0 0x0>; + ranges = <0x02000000 0x0 0x100000 0x10000000 0x0 0x0>; + reg = <0x0 0x1000>; device_type = "pci"; switch@0,0 { From 61712c94782ce105253ee1939cda0c5c025b2c0c Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 30 Jan 2024 13:26:43 +1000 Subject: [PATCH 072/311] nouveau/gsp: use correct size for registry rpc. Timur pointed this out before, and it just slipped my mind, but this might help some things work better, around pcie power management. Cc: # v6.7 Fixes: 8d55b0a940bb ("nouveau/gsp: add some basic registry entries.") Signed-off-by: Dave Airlie Signed-off-by: Danilo Krummrich Link: https://patchwork.freedesktop.org/patch/msgid/20240130032643.2498315-1-airlied@gmail.com --- drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index 9ee58e2a0eb2..5e1fa176aac4 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -1078,7 +1078,6 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp) if (IS_ERR(rpc)) return PTR_ERR(rpc); - rpc->size = sizeof(*rpc); rpc->numEntries = NV_GSP_REG_NUM_ENTRIES; str_offset = offsetof(typeof(*rpc), entries[NV_GSP_REG_NUM_ENTRIES]); @@ -1094,6 +1093,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp) strings += name_len; str_offset += name_len; } + rpc->size = str_offset; return nvkm_gsp_rpc_wr(gsp, rpc, false); } From 042b5f83841fbf7ce39474412db3b5e4765a7ea7 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Fri, 2 Feb 2024 17:06:07 -0600 Subject: [PATCH 073/311] drm/nouveau: fix several DMA buffer leaks Nouveau manages GSP-RM DMA buffers with nvkm_gsp_mem objects. Several of these buffers are never dealloced. Some of them can be deallocated right after GSP-RM is initialized, but the rest need to stay until the driver unloads. Also futher bullet-proof these objects by poisoning the buffer and clearing the nvkm_gsp_mem object when it is deallocated. Poisoning the buffer should trigger an error (or crash) from GSP-RM if it tries to access the buffer after we've deallocated it, because we were wrong about when it is safe to deallocate. Finally, change the mem->size field to a size_t because that's the same type that dma_alloc_coherent expects. Cc: # v6.7 Fixes: 176fdcbddfd2 ("drm/nouveau/gsp/r535: add support for booting GSP-RM") Signed-off-by: Timur Tabi Signed-off-by: Danilo Krummrich Link: https://patchwork.freedesktop.org/patch/msgid/20240202230608.1981026-1-ttabi@nvidia.com --- .../gpu/drm/nouveau/include/nvkm/subdev/gsp.h | 2 +- .../gpu/drm/nouveau/nvkm/subdev/gsp/r535.c | 59 ++++++++++++------- 2 files changed, 39 insertions(+), 22 deletions(-) diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h index d1437c08645f..6f5d376d8fcc 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h @@ -9,7 +9,7 @@ #define GSP_PAGE_SIZE BIT(GSP_PAGE_SHIFT) struct nvkm_gsp_mem { - u32 size; + size_t size; void *data; dma_addr_t addr; }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index 5e1fa176aac4..6208ddd92964 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -997,6 +997,32 @@ r535_gsp_rpc_get_gsp_static_info(struct nvkm_gsp *gsp) return 0; } +static void +nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem) +{ + if (mem->data) { + /* + * Poison the buffer to catch any unexpected access from + * GSP-RM if the buffer was prematurely freed. + */ + memset(mem->data, 0xFF, mem->size); + + dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr); + memset(mem, 0, sizeof(*mem)); + } +} + +static int +nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, size_t size, struct nvkm_gsp_mem *mem) +{ + mem->size = size; + mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL); + if (WARN_ON(!mem->data)) + return -ENOMEM; + + return 0; +} + static int r535_gsp_postinit(struct nvkm_gsp *gsp) { @@ -1024,6 +1050,13 @@ r535_gsp_postinit(struct nvkm_gsp *gsp) nvkm_inth_allow(&gsp->subdev.inth); nvkm_wr32(device, 0x110004, 0x00000040); + + /* Release the DMA buffers that were needed only for boot and init */ + nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw); + nvkm_gsp_mem_dtor(gsp, &gsp->libos); + nvkm_gsp_mem_dtor(gsp, &gsp->rmargs); + nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta); + return ret; } @@ -1532,27 +1565,6 @@ r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc) return 0; } -static void -nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem) -{ - if (mem->data) { - dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr); - mem->data = NULL; - } -} - -static int -nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, u32 size, struct nvkm_gsp_mem *mem) -{ - mem->size = size; - mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL); - if (WARN_ON(!mem->data)) - return -ENOMEM; - - return 0; -} - - static int r535_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1) { @@ -2150,6 +2162,11 @@ r535_gsp_dtor(struct nvkm_gsp *gsp) mutex_destroy(&gsp->cmdq.mutex); r535_gsp_dtor_fws(gsp); + + nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem); + nvkm_gsp_mem_dtor(gsp, &gsp->loginit); + nvkm_gsp_mem_dtor(gsp, &gsp->logintr); + nvkm_gsp_mem_dtor(gsp, &gsp->logrm); } int From 34e659f34a7559ecfd9c1f5b24d4c291f3f54711 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Fri, 2 Feb 2024 17:06:08 -0600 Subject: [PATCH 074/311] drm/nouveau: nvkm_gsp_radix3_sg() should use nvkm_gsp_mem_ctor() Function nvkm_gsp_radix3_sg() uses nvkm_gsp_mem objects to allocate the radix3 tables, but it unnecessarily creates those objects manually instead of using the standard nvkm_gsp_mem_ctor() function like the rest of the code does. Signed-off-by: Timur Tabi Signed-off-by: Danilo Krummrich Link: https://patchwork.freedesktop.org/patch/msgid/20240202230608.1981026-2-ttabi@nvidia.com --- drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index 6208ddd92964..a41735ab6068 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -1950,20 +1950,20 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3) * See kgspCreateRadix3_IMPL */ static int -nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size, +nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size, struct nvkm_gsp_radix3 *rx3) { u64 addr; for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) { u64 *ptes; - int idx; + size_t bufsize; + int ret, idx; - rx3->mem[i].size = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE); - rx3->mem[i].data = dma_alloc_coherent(device->dev, rx3->mem[i].size, - &rx3->mem[i].addr, GFP_KERNEL); - if (WARN_ON(!rx3->mem[i].data)) - return -ENOMEM; + bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE); + ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]); + if (ret) + return ret; ptes = rx3->mem[i].data; if (i == 2) { @@ -2003,7 +2003,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend) if (ret) return ret; - ret = nvkm_gsp_radix3_sg(gsp->subdev.device, &gsp->sr.sgt, len, &gsp->sr.radix3); + ret = nvkm_gsp_radix3_sg(gsp, &gsp->sr.sgt, len, &gsp->sr.radix3); if (ret) return ret; @@ -2211,7 +2211,7 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp) memcpy(gsp->sig.data, data, size); /* Build radix3 page table for ELF image. */ - ret = nvkm_gsp_radix3_sg(device, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3); + ret = nvkm_gsp_radix3_sg(gsp, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3); if (ret) return ret; From 4e6c9011990726f4d175e2cdfebe5b0b8cce4839 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sat, 3 Feb 2024 10:45:21 +0800 Subject: [PATCH 075/311] scsi: core: Move scsi_host_busy() out of host lock if it is for per-command Commit 4373534a9850 ("scsi: core: Move scsi_host_busy() out of host lock for waking up EH handler") intended to fix a hard lockup issue triggered by EH. The core idea was to move scsi_host_busy() out of the host lock when processing individual commands for EH. However, a suggested style change inadvertently caused scsi_host_busy() to remain under the host lock. Fix this by calling scsi_host_busy() outside the lock. Fixes: 4373534a9850 ("scsi: core: Move scsi_host_busy() out of host lock for waking up EH handler") Cc: Sathya Prakash Veerichetty Cc: Bart Van Assche Cc: Ewan D. Milne Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20240203024521.2006455-1-ming.lei@redhat.com Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_error.c | 3 ++- drivers/scsi/scsi_lib.c | 4 +++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 4f455884fdc4..612489afe8d2 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -282,11 +282,12 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head) { struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); struct Scsi_Host *shost = scmd->device->host; + unsigned int busy = scsi_host_busy(shost); unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; - scsi_eh_wakeup(shost, scsi_host_busy(shost)); + scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 1fb80eae9a63..df5ac03d5d6c 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -278,9 +278,11 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd) rcu_read_lock(); __clear_bit(SCMD_STATE_INFLIGHT, &cmd->state); if (unlikely(scsi_host_in_recovery(shost))) { + unsigned int busy = scsi_host_busy(shost); + spin_lock_irqsave(shost->host_lock, flags); if (shost->host_failed || shost->host_eh_scheduled) - scsi_eh_wakeup(shost, scsi_host_busy(shost)); + scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } rcu_read_unlock(); From d6c1b19153f92e95e5e1801d540e98771053afae Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 20 Dec 2023 17:26:58 +0100 Subject: [PATCH 076/311] scsi: lpfc: Use unsigned type for num_sge LUNs going into "failed ready running" state observed on >1T and on even numbers of size (2T, 4T, 6T, 8T and 10T). The issue occurs when DIF is enabled at the host. The kernel logs: Cannot setup S/G List for HBAIO segs 1/1 SGL 512 SCSI 256: 3 0 The host lpfc driver is failing to setup scatter/gather list (protection data) for the I/Os. The return type lpfc_bg_setup_sgl()/lpfc_bg_setup_sgl_prot() causes the compiler to remove the most significant bit. Use an unsigned type instead. Signed-off-by: Hannes Reinecke [dwagner: added commit message] Signed-off-by: Daniel Wagner Link: https://lore.kernel.org/r/20231220162658.12392-1-dwagner@suse.de Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_scsi.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index d26941b131fd..bf879d81846b 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -1918,7 +1918,7 @@ out: * * Returns the number of SGEs added to the SGL. **/ -static int +static uint32_t lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct sli4_sge *sgl, int datasegcnt, struct lpfc_io_buf *lpfc_cmd) @@ -1926,8 +1926,8 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct scatterlist *sgde = NULL; /* s/g data entry */ struct sli4_sge_diseed *diseed = NULL; dma_addr_t physaddr; - int i = 0, num_sge = 0, status; - uint32_t reftag; + int i = 0, status; + uint32_t reftag, num_sge = 0; uint8_t txop, rxop; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS uint32_t rc; @@ -2099,7 +2099,7 @@ out: * * Returns the number of SGEs added to the SGL. **/ -static int +static uint32_t lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct sli4_sge *sgl, int datacnt, int protcnt, struct lpfc_io_buf *lpfc_cmd) @@ -2123,8 +2123,8 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, uint32_t rc; #endif uint32_t checking = 1; - uint32_t dma_offset = 0; - int num_sge = 0, j = 2; + uint32_t dma_offset = 0, num_sge = 0; + int j = 2; struct sli4_hybrid_sgl *sgl_xtra = NULL; sgpe = scsi_prot_sglist(sc); From b513d30d59bb383a6a5d6b533afcab2cee99a8f8 Mon Sep 17 00:00:00 2001 From: Alice Chao Date: Mon, 5 Feb 2024 18:49:04 +0800 Subject: [PATCH 077/311] scsi: ufs: core: Fix shift issue in ufshcd_clear_cmd() When task_tag >= 32 (in MCQ mode) and sizeof(unsigned int) == 4, 1U << task_tag will out of bounds for a u32 mask. Fix this up to prevent SHIFT_ISSUE (bitwise shifts that are out of bounds for their data type). [name:debug_monitors&]Unexpected kernel BRK exception at EL1 [name:traps&]Internal error: BRK handler: 00000000f2005514 [#1] PREEMPT SMP [name:mediatek_cpufreq_hw&]cpufreq stop DVFS log done [name:mrdump&]Kernel Offset: 0x1ba5800000 from 0xffffffc008000000 [name:mrdump&]PHYS_OFFSET: 0x80000000 [name:mrdump&]pstate: 22400005 (nzCv daif +PAN -UAO) [name:mrdump&]pc : [0xffffffdbaf52bb2c] ufshcd_clear_cmd+0x280/0x288 [name:mrdump&]lr : [0xffffffdbaf52a774] ufshcd_wait_for_dev_cmd+0x3e4/0x82c [name:mrdump&]sp : ffffffc0081471b0 Workqueue: ufs_eh_wq_0 ufshcd_err_handler Call trace: dump_backtrace+0xf8/0x144 show_stack+0x18/0x24 dump_stack_lvl+0x78/0x9c dump_stack+0x18/0x44 mrdump_common_die+0x254/0x480 [mrdump] ipanic_die+0x20/0x30 [mrdump] notify_die+0x15c/0x204 die+0x10c/0x5f8 arm64_notify_die+0x74/0x13c do_debug_exception+0x164/0x26c el1_dbg+0x64/0x80 el1h_64_sync_handler+0x3c/0x90 el1h_64_sync+0x68/0x6c ufshcd_clear_cmd+0x280/0x288 ufshcd_wait_for_dev_cmd+0x3e4/0x82c ufshcd_exec_dev_cmd+0x5bc/0x9ac ufshcd_verify_dev_init+0x84/0x1c8 ufshcd_probe_hba+0x724/0x1ce0 ufshcd_host_reset_and_restore+0x260/0x574 ufshcd_reset_and_restore+0x138/0xbd0 ufshcd_err_handler+0x1218/0x2f28 process_one_work+0x5fc/0x1140 worker_thread+0x7d8/0xe20 kthread+0x25c/0x468 ret_from_fork+0x10/0x20 Signed-off-by: Alice Chao Link: https://lore.kernel.org/r/20240205104905.24929-1-alice.chao@mediatek.com Reviewed-by: Stanley Jhu Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 029d017fc1b6..c6cff4aa440a 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -3057,7 +3057,7 @@ bool ufshcd_cmd_inflight(struct scsi_cmnd *cmd) */ static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag) { - u32 mask = 1U << task_tag; + u32 mask; unsigned long flags; int err; @@ -3075,6 +3075,8 @@ static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag) return 0; } + mask = 1U << task_tag; + /* clear outstanding transaction before retry */ spin_lock_irqsave(hba->host->host_lock, flags); ufshcd_utrl_clear(hba, mask); From 17e94b2585417e04dabc2f13bc03b4665ae687f3 Mon Sep 17 00:00:00 2001 From: SEO HOYOUNG Date: Mon, 22 Jan 2024 17:33:24 +0900 Subject: [PATCH 078/311] scsi: ufs: core: Remove the ufshcd_release() in ufshcd_err_handling_prepare() If ufshcd_err_handler() is called in a suspend/resume situation, ufs_release() can be called twice and active_reqs end up going negative. This is because ufshcd_err_handling_prepare() and ufshcd_err_handling_unprepare() both call ufshcd_release(). Remove superfluous call to ufshcd_release(). Signed-off-by: SEO HOYOUNG Link: https://lore.kernel.org/r/20240122083324.11797-1-hy50.seo@samsung.com Reviewed-by: Bart Van Assche Reviewed-by: Can Guo Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index c6cff4aa440a..d77b25b79ae3 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -6354,7 +6354,6 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba) ufshcd_hold(hba); if (!ufshcd_is_clkgating_allowed(hba)) ufshcd_setup_clocks(hba, true); - ufshcd_release(hba); pm_op = hba->is_sys_suspended ? UFS_SYSTEM_PM : UFS_RUNTIME_PM; ufshcd_vops_resume(hba, pm_op); } else { From d0399da9fb5f8e3d897b9776bffee2d3bfe20210 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Mon, 29 Jan 2024 19:04:13 -0800 Subject: [PATCH 079/311] drm/sched: Re-queue run job worker when drm_sched_entity_pop_job() returns NULL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rather then loop over entities until one with a ready job is found, re-queue the run job worker when drm_sched_entity_pop_job() returns NULL. Signed-off-by: Matthew Brost Reviewed-by: Christian König Fixes: 66dbd9004a55 ("drm/sched: Drain all entities in DRM sched run job worker") Reviewed-by: Luben Tuikov Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20240130030413.2031009-1-matthew.brost@intel.com --- drivers/gpu/drm/scheduler/sched_main.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 85f082396d42..d442b893275b 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1178,21 +1178,24 @@ static void drm_sched_run_job_work(struct work_struct *w) struct drm_sched_entity *entity; struct dma_fence *fence; struct drm_sched_fence *s_fence; - struct drm_sched_job *sched_job = NULL; + struct drm_sched_job *sched_job; int r; if (READ_ONCE(sched->pause_submit)) return; /* Find entity with a ready job */ - while (!sched_job && (entity = drm_sched_select_entity(sched))) { - sched_job = drm_sched_entity_pop_job(entity); - if (!sched_job) - complete_all(&entity->entity_idle); - } + entity = drm_sched_select_entity(sched); if (!entity) return; /* No more work */ + sched_job = drm_sched_entity_pop_job(entity); + if (!sched_job) { + complete_all(&entity->entity_idle); + drm_sched_run_job_queue(sched); + return; + } + s_fence = sched_job->s_fence; atomic_add(sched_job->credits, &sched->credit_count); From dad6a09f3148257ac1773cd90934d721d68ab595 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 29 Jan 2024 15:56:36 -0800 Subject: [PATCH 080/311] hrtimer: Report offline hrtimer enqueue The hrtimers migration on CPU-down hotplug process has been moved earlier, before the CPU actually goes to die. This leaves a small window of opportunity to queue an hrtimer in a blind spot, leaving it ignored. For example a practical case has been reported with RCU waking up a SCHED_FIFO task right before the CPUHP_AP_IDLE_DEAD stage, queuing that way a sched/rt timer to the local offline CPU. Make sure such situations never go unnoticed and warn when that happens. Fixes: 5c0930ccaad5 ("hrtimers: Push pending hrtimers away from outgoing CPU earlier") Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240129235646.3171983-4-boqun.feng@gmail.com --- include/linux/hrtimer.h | 4 +++- kernel/time/hrtimer.c | 3 +++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 87e3bedf8eb0..641c4567cfa7 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -157,6 +157,7 @@ enum hrtimer_base_type { * @max_hang_time: Maximum time spent in hrtimer_interrupt * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are * expired + * @online: CPU is online from an hrtimers point of view * @timer_waiters: A hrtimer_cancel() invocation waits for the timer * callback to finish. * @expires_next: absolute time of the next event, is required for remote @@ -179,7 +180,8 @@ struct hrtimer_cpu_base { unsigned int hres_active : 1, in_hrtirq : 1, hang_detected : 1, - softirq_activated : 1; + softirq_activated : 1, + online : 1; #ifdef CONFIG_HIGH_RES_TIMERS unsigned int nr_events; unsigned short nr_retries; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 760793998cdd..edb0f821dcea 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1085,6 +1085,7 @@ static int enqueue_hrtimer(struct hrtimer *timer, enum hrtimer_mode mode) { debug_activate(timer, mode); + WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; @@ -2183,6 +2184,7 @@ int hrtimers_prepare_cpu(unsigned int cpu) cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; + cpu_base->online = 1; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } @@ -2250,6 +2252,7 @@ int hrtimers_cpu_dying(unsigned int dying_cpu) smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); + old_base->online = 0; raw_spin_unlock(&old_base->lock); return 0; From 58aeb5623c2ebdadefe6352b14f8076a7073fea0 Mon Sep 17 00:00:00 2001 From: Fred Ai Date: Sat, 3 Feb 2024 02:29:08 -0800 Subject: [PATCH 081/311] mmc: sdhci-pci-o2micro: Fix a warm reboot issue that disk can't be detected by BIOS Driver shall switch clock source from DLL clock to OPE clock when power off card to ensure that card can be identified with OPE clock by BIOS. Signed-off-by: Fred Ai Fixes:4be33cf18703 ("mmc: sdhci-pci-o2micro: Improve card input timing at SDR104/HS200 mode") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240203102908.4683-1-fredaibayhubtech@126.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-pci-o2micro.c | 30 ++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c index 7bfee28116af..d4a02184784a 100644 --- a/drivers/mmc/host/sdhci-pci-o2micro.c +++ b/drivers/mmc/host/sdhci-pci-o2micro.c @@ -693,6 +693,35 @@ static int sdhci_pci_o2_init_sd_express(struct mmc_host *mmc, struct mmc_ios *io return 0; } +static void sdhci_pci_o2_set_power(struct sdhci_host *host, unsigned char mode, unsigned short vdd) +{ + struct sdhci_pci_chip *chip; + struct sdhci_pci_slot *slot = sdhci_priv(host); + u32 scratch_32 = 0; + u8 scratch_8 = 0; + + chip = slot->chip; + + if (mode == MMC_POWER_OFF) { + /* UnLock WP */ + pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8); + scratch_8 &= 0x7f; + pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8); + + /* Set PCR 0x354[16] to switch Clock Source back to OPE Clock */ + pci_read_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, &scratch_32); + scratch_32 &= ~(O2_SD_SEL_DLL); + pci_write_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, scratch_32); + + /* Lock WP */ + pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8); + scratch_8 |= 0x80; + pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8); + } + + sdhci_set_power(host, mode, vdd); +} + static int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot) { struct sdhci_pci_chip *chip; @@ -1051,6 +1080,7 @@ static const struct sdhci_ops sdhci_pci_o2_ops = { .set_bus_width = sdhci_set_bus_width, .reset = sdhci_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, + .set_power = sdhci_pci_o2_set_power, }; const struct sdhci_pci_fixes sdhci_o2 = { From cc9432c4fb159a3913e0ce3173b8218cd5bad2e0 Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Tue, 6 Feb 2024 09:39:12 +0100 Subject: [PATCH 082/311] mmc: slot-gpio: Allow non-sleeping GPIO ro This change uses the appropriate _cansleep or non-sleeping API for reading GPIO read-only state. This allows users with GPIOs that never sleepbeing called in atomic context. Implement the same mechanism as in commit 52af318c93e97 ("mmc: Allow non-sleeping GPIO cd"). Signed-off-by: Alexander Stein Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240206083912.2543142-1-alexander.stein@ew.tq-group.com Signed-off-by: Ulf Hansson --- drivers/mmc/core/slot-gpio.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index 2a2d949a9344..39f45c2b6de8 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -75,11 +75,15 @@ EXPORT_SYMBOL(mmc_gpio_set_cd_irq); int mmc_gpio_get_ro(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; + int cansleep; if (!ctx || !ctx->ro_gpio) return -ENOSYS; - return gpiod_get_value_cansleep(ctx->ro_gpio); + cansleep = gpiod_cansleep(ctx->ro_gpio); + return cansleep ? + gpiod_get_value_cansleep(ctx->ro_gpio) : + gpiod_get_value(ctx->ro_gpio); } EXPORT_SYMBOL(mmc_gpio_get_ro); From c9da9a1f17bf4fa96b115950fd389c917b583c1c Mon Sep 17 00:00:00 2001 From: "Wachowski, Karol" Date: Fri, 26 Jan 2024 13:27:58 +0100 Subject: [PATCH 083/311] accel/ivpu: Force snooping for MMU writes Set AW_SNOOP_OVERRIDE bit in VPU_37/40XX_HOST_IF_TCU_PTW_OVERRIDES to force snooping for MMU write accesses (setting event queue events). MMU event queue buffer is the only buffer written by MMU and mapped as write-back which break cache coherency. Force write transactions to be snooped solving the problem. Signed-off-by: Wachowski, Karol Signed-off-by: Jacek Lawrynowicz Reviewed-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-2-jacek.lawrynowicz@linux.intel.com --- drivers/accel/ivpu/ivpu_hw_37xx.c | 2 +- drivers/accel/ivpu/ivpu_hw_40xx.c | 2 +- drivers/accel/ivpu/ivpu_mmu.c | 3 --- 3 files changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c index f15a93d83057..77accd029c4a 100644 --- a/drivers/accel/ivpu/ivpu_hw_37xx.c +++ b/drivers/accel/ivpu/ivpu_hw_37xx.c @@ -525,7 +525,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev) u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES); val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val); - val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val); + val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val); val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val); REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val); diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c index 704288084f37..86b89b94f9f3 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx.c +++ b/drivers/accel/ivpu/ivpu_hw_40xx.c @@ -530,7 +530,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev) u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES); val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val); - val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val); + val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val); val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val); REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val); diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c index 9a3122ffce03..8df78adeee33 100644 --- a/drivers/accel/ivpu/ivpu_mmu.c +++ b/drivers/accel/ivpu/ivpu_mmu.c @@ -560,7 +560,6 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev) mmu->cmdq.cons = 0; memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE); - clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE); mmu->evtq.prod = 0; mmu->evtq.cons = 0; @@ -877,8 +876,6 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev) if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT)) return NULL; - clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE); - evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK; REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons); From b039f1c4d3727c3e44a7e89ff79e7e8533e1beec Mon Sep 17 00:00:00 2001 From: "Wachowski, Karol" Date: Fri, 26 Jan 2024 13:27:59 +0100 Subject: [PATCH 084/311] accel/ivpu: Correct MMU queue size checking functions Do not use kernel CIRC_SPACE and CIRC_CNT that incorrectly return space of a queue when wrap bit was set. Use correct implementation that compares producer, consumer and wrap bit values. Without this fix it was possible to lose events in case when event queue was full. Signed-off-by: Wachowski, Karol Signed-off-by: Jacek Lawrynowicz Reviewed-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-3-jacek.lawrynowicz@linux.intel.com --- drivers/accel/ivpu/ivpu_mmu.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c index 8df78adeee33..91bd640655ab 100644 --- a/drivers/accel/ivpu/ivpu_mmu.c +++ b/drivers/accel/ivpu/ivpu_mmu.c @@ -72,10 +72,10 @@ #define IVPU_MMU_Q_COUNT_LOG2 4 /* 16 entries */ #define IVPU_MMU_Q_COUNT ((u32)1 << IVPU_MMU_Q_COUNT_LOG2) -#define IVPU_MMU_Q_WRAP_BIT (IVPU_MMU_Q_COUNT << 1) -#define IVPU_MMU_Q_WRAP_MASK (IVPU_MMU_Q_WRAP_BIT - 1) -#define IVPU_MMU_Q_IDX_MASK (IVPU_MMU_Q_COUNT - 1) +#define IVPU_MMU_Q_WRAP_MASK GENMASK(IVPU_MMU_Q_COUNT_LOG2, 0) +#define IVPU_MMU_Q_IDX_MASK (IVPU_MMU_Q_COUNT - 1) #define IVPU_MMU_Q_IDX(val) ((val) & IVPU_MMU_Q_IDX_MASK) +#define IVPU_MMU_Q_WRP(val) ((val) & IVPU_MMU_Q_COUNT) #define IVPU_MMU_CMDQ_CMD_SIZE 16 #define IVPU_MMU_CMDQ_SIZE (IVPU_MMU_Q_COUNT * IVPU_MMU_CMDQ_CMD_SIZE) @@ -475,20 +475,32 @@ static int ivpu_mmu_cmdq_wait_for_cons(struct ivpu_device *vdev) return 0; } +static bool ivpu_mmu_queue_is_full(struct ivpu_mmu_queue *q) +{ + return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) && + (IVPU_MMU_Q_WRP(q->prod) != IVPU_MMU_Q_WRP(q->cons))); +} + +static bool ivpu_mmu_queue_is_empty(struct ivpu_mmu_queue *q) +{ + return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) && + (IVPU_MMU_Q_WRP(q->prod) == IVPU_MMU_Q_WRP(q->cons))); +} + static int ivpu_mmu_cmdq_cmd_write(struct ivpu_device *vdev, const char *name, u64 data0, u64 data1) { - struct ivpu_mmu_queue *q = &vdev->mmu->cmdq; - u64 *queue_buffer = q->base; - int idx = IVPU_MMU_Q_IDX(q->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer)); + struct ivpu_mmu_queue *cmdq = &vdev->mmu->cmdq; + u64 *queue_buffer = cmdq->base; + int idx = IVPU_MMU_Q_IDX(cmdq->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer)); - if (!CIRC_SPACE(IVPU_MMU_Q_IDX(q->prod), IVPU_MMU_Q_IDX(q->cons), IVPU_MMU_Q_COUNT)) { + if (ivpu_mmu_queue_is_full(cmdq)) { ivpu_err(vdev, "Failed to write MMU CMD %s\n", name); return -EBUSY; } queue_buffer[idx] = data0; queue_buffer[idx + 1] = data1; - q->prod = (q->prod + 1) & IVPU_MMU_Q_WRAP_MASK; + cmdq->prod = (cmdq->prod + 1) & IVPU_MMU_Q_WRAP_MASK; ivpu_dbg(vdev, MMU, "CMD write: %s data: 0x%llx 0x%llx\n", name, data0, data1); @@ -873,12 +885,10 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev) u32 *evt = evtq->base + (idx * IVPU_MMU_EVTQ_CMD_SIZE); evtq->prod = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC); - if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT)) + if (ivpu_mmu_queue_is_empty(evtq)) return NULL; evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK; - REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons); - return evt; } @@ -899,6 +909,7 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev) } ivpu_mmu_user_context_mark_invalid(vdev, ssid); + REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons); } } From a7f31091ddf457352e3dd7ac183fdbd26b4dcd04 Mon Sep 17 00:00:00 2001 From: Jacek Lawrynowicz Date: Fri, 26 Jan 2024 13:28:00 +0100 Subject: [PATCH 085/311] accel/ivpu: Disable d3hot_delay on all NPU generations NPU does not require this delay regardless of the generation. All generations are integrated into the SOC. Signed-off-by: Jacek Lawrynowicz Reviewed-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-4-jacek.lawrynowicz@linux.intel.com --- drivers/accel/ivpu/ivpu_drv.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 9418c73ee8ef..4b0640226986 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -480,9 +480,8 @@ static int ivpu_pci_init(struct ivpu_device *vdev) /* Clear any pending errors */ pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f); - /* VPU 37XX does not require 10m D3hot delay */ - if (ivpu_hw_gen(vdev) == IVPU_HW_37XX) - pdev->d3hot_delay = 0; + /* NPU does not require 10m D3hot delay */ + pdev->d3hot_delay = 0; ret = pcim_enable_device(pdev); if (ret) { From a939c03d37788e4a9a645c88d5e5b6a475ba0fd5 Mon Sep 17 00:00:00 2001 From: Krystian Pradzynski Date: Fri, 26 Jan 2024 13:28:02 +0100 Subject: [PATCH 086/311] accel/ivpu/40xx: Enable D0i3 message All recent 40xx firmware already supports D0i3 entry message and this WA is no longer needed. Signed-off-by: Krystian Pradzynski Signed-off-by: Jacek Lawrynowicz Reviewed-by: Jacek Lawrynowicz Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-6-jacek.lawrynowicz@linux.intel.com --- drivers/accel/ivpu/ivpu_fw.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c index 6576232f3e67..5fa8bd4603d5 100644 --- a/drivers/accel/ivpu/ivpu_fw.c +++ b/drivers/accel/ivpu/ivpu_fw.c @@ -222,7 +222,6 @@ ivpu_fw_init_wa(struct ivpu_device *vdev) const struct vpu_firmware_header *fw_hdr = (const void *)vdev->fw->file->data; if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, BOOT, 3, 17) || - (ivpu_hw_gen(vdev) > IVPU_HW_37XX) || (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_DISABLE)) vdev->wa.disable_d0i3_msg = true; From 553099da45397914a995dce6307d6c26523c2567 Mon Sep 17 00:00:00 2001 From: Krystian Pradzynski Date: Fri, 26 Jan 2024 13:28:03 +0100 Subject: [PATCH 087/311] accel/ivpu/40xx: Stop passing SKU boot parameters to FW This parameter was never used by the 40xx FW. Signed-off-by: Krystian Pradzynski Signed-off-by: Jacek Lawrynowicz Reviewed-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-7-jacek.lawrynowicz@linux.intel.com --- drivers/accel/ivpu/ivpu_hw_40xx.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c index 86b89b94f9f3..1c995307c113 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx.c +++ b/drivers/accel/ivpu/ivpu_hw_40xx.c @@ -704,7 +704,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev) { struct ivpu_hw_info *hw = vdev->hw; u32 tile_disable; - u32 tile_enable; u32 fuse; fuse = REGB_RD32(VPU_40XX_BUTTRESS_TILE_FUSE); @@ -725,10 +724,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev) else ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", TILE_MAX_NUM); - tile_enable = (~tile_disable) & TILE_MAX_MASK; - - hw->sku = REG_SET_FLD_NUM(SKU, HW_ID, LNL_HW_ID, hw->sku); - hw->sku = REG_SET_FLD_NUM(SKU, TILE, tile_enable, hw->sku); hw->tile_fuse = tile_disable; hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT; From 5f8408aca66772d3aa9b4831577b2ac5ec41bcd9 Mon Sep 17 00:00:00 2001 From: Grzegorz Trzebiatowski Date: Fri, 26 Jan 2024 13:28:04 +0100 Subject: [PATCH 088/311] accel/ivpu: Add job status for jobs aborted by the driver Add DRM_IVPU_JOB_STATUS_ABORTED to indicate that the job was aborted by the driver due to e.g. TDR or user context MMU faults. This will help UMD and tests distinguish if job was aborted by the FW or the driver. Signed-off-by: Grzegorz Trzebiatowski Signed-off-by: Jacek Lawrynowicz Reviewed-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-8-jacek.lawrynowicz@linux.intel.com --- drivers/accel/ivpu/ivpu_job.c | 4 ++-- include/uapi/drm/ivpu_accel.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 0440bee3ecaf..e70cfb859339 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -294,7 +294,7 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32 return -ENOENT; if (job->file_priv->has_mmu_faults) - job_status = VPU_JSM_STATUS_ABORTED; + job_status = DRM_IVPU_JOB_STATUS_ABORTED; job->bos[CMD_BUF_IDX]->job_status = job_status; dma_fence_signal(job->done_fence); @@ -315,7 +315,7 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev) unsigned long id; xa_for_each(&vdev->submitted_jobs_xa, id, job) - ivpu_job_signal_and_destroy(vdev, id, VPU_JSM_STATUS_ABORTED); + ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED); } static int ivpu_job_submit(struct ivpu_job *job) diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h index 63c49318a863..19a13468eca5 100644 --- a/include/uapi/drm/ivpu_accel.h +++ b/include/uapi/drm/ivpu_accel.h @@ -305,6 +305,7 @@ struct drm_ivpu_submit { /* drm_ivpu_bo_wait job status codes */ #define DRM_IVPU_JOB_STATUS_SUCCESS 0 +#define DRM_IVPU_JOB_STATUS_ABORTED 256 /** * struct drm_ivpu_bo_wait - Wait for BO to become inactive From 411a20db905b44e18cc9129b745f1d5deba4eae5 Mon Sep 17 00:00:00 2001 From: Oleksandr Natalenko Date: Mon, 29 Jan 2024 17:49:31 +0100 Subject: [PATCH 089/311] HID: logitech-hidpp: Do not flood kernel log Since commit 680ee411a98e ("HID: logitech-hidpp: Fix connect event race") the following messages appear in the kernel log from time to time: logitech-hidpp-device 0003:046D:408A.0005: HID++ 4.5 device connected. logitech-hidpp-device 0003:046D:408A.0005: HID++ 4.5 device connected. logitech-hidpp-device 0003:046D:4051.0006: Disconnected logitech-hidpp-device 0003:046D:408A.0005: Disconnected As discussed, print the first per-device "device connected" message at info level, demoting subsequent messages to debug level. Also, demote the "Disconnected message" to debug level unconditionally. Link: https://lore.kernel.org/lkml/3277085.44csPzL39Z@natalenko.name/ Signed-off-by: Oleksandr Natalenko Reviewed-by: Hans de Goede Signed-off-by: Jiri Kosina --- drivers/hid/hid-logitech-hidpp.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 6ef0c88e3e60..d2f3f234f29d 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -203,6 +203,8 @@ struct hidpp_device { struct hidpp_scroll_counter vertical_wheel_counter; u8 wireless_feature_index; + + bool connected_once; }; /* HID++ 1.0 error codes */ @@ -988,8 +990,13 @@ static int hidpp_root_get_protocol_version(struct hidpp_device *hidpp) hidpp->protocol_minor = response.rap.params[1]; print_version: - hid_info(hidpp->hid_dev, "HID++ %u.%u device connected.\n", - hidpp->protocol_major, hidpp->protocol_minor); + if (!hidpp->connected_once) { + hid_info(hidpp->hid_dev, "HID++ %u.%u device connected.\n", + hidpp->protocol_major, hidpp->protocol_minor); + hidpp->connected_once = true; + } else + hid_dbg(hidpp->hid_dev, "HID++ %u.%u device connected.\n", + hidpp->protocol_major, hidpp->protocol_minor); return 0; } @@ -4184,7 +4191,7 @@ static void hidpp_connect_event(struct work_struct *work) /* Get device version to check if it is connected */ ret = hidpp_root_get_protocol_version(hidpp); if (ret) { - hid_info(hidpp->hid_dev, "Disconnected\n"); + hid_dbg(hidpp->hid_dev, "Disconnected\n"); if (hidpp->battery.ps) { hidpp->battery.online = false; hidpp->battery.status = POWER_SUPPLY_STATUS_UNKNOWN; From c1d6708bf0d3dd976460d435373cf5abf21ce258 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Mon, 29 Jan 2024 14:35:45 -0800 Subject: [PATCH 090/311] HID: wacom: Do not register input devices until after hid_hw_start If a input device is opened before hid_hw_start is called, events may not be received from the hardware. In the case of USB-backed devices, for example, the hid_hw_start function is responsible for filling in the URB which is submitted when the input device is opened. If a device is opened prematurely, polling will never start because the device will not have been in the correct state to send the URB. Because the wacom driver registers its input devices before calling hid_hw_start, there is a window of time where a device can be opened and end up in an inoperable state. Some ARM-based Chromebooks in particular reliably trigger this bug. This commit splits the wacom_register_inputs function into two pieces. One which is responsible for setting up the allocated inputs (and runs prior to hid_hw_start so that devices are ready for any input events they may end up receiving) and another which only registers the devices (and runs after hid_hw_start to ensure devices can be immediately opened without issue). Note that the functions to initialize the LEDs and remotes are also moved after hid_hw_start to maintain their own dependency chains. Fixes: 7704ac937345 ("HID: wacom: implement generic HID handling for pen generic devices") Cc: stable@vger.kernel.org # v3.18+ Suggested-by: Dmitry Torokhov Signed-off-by: Jason Gerecke Tested-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- drivers/hid/wacom_sys.c | 63 ++++++++++++++++++++++++++++------------- 1 file changed, 43 insertions(+), 20 deletions(-) diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index b613f11ed949..2bc45b24075c 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2087,7 +2087,7 @@ static int wacom_allocate_inputs(struct wacom *wacom) return 0; } -static int wacom_register_inputs(struct wacom *wacom) +static int wacom_setup_inputs(struct wacom *wacom) { struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev; struct wacom_wac *wacom_wac = &(wacom->wacom_wac); @@ -2106,10 +2106,6 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(pen_input_dev); wacom_wac->pen_input = NULL; pen_input_dev = NULL; - } else { - error = input_register_device(pen_input_dev); - if (error) - goto fail; } error = wacom_setup_touch_input_capabilities(touch_input_dev, wacom_wac); @@ -2118,10 +2114,6 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(touch_input_dev); wacom_wac->touch_input = NULL; touch_input_dev = NULL; - } else { - error = input_register_device(touch_input_dev); - if (error) - goto fail; } error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac); @@ -2130,7 +2122,34 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(pad_input_dev); wacom_wac->pad_input = NULL; pad_input_dev = NULL; - } else { + } + + return 0; +} + +static int wacom_register_inputs(struct wacom *wacom) +{ + struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev; + struct wacom_wac *wacom_wac = &(wacom->wacom_wac); + int error = 0; + + pen_input_dev = wacom_wac->pen_input; + touch_input_dev = wacom_wac->touch_input; + pad_input_dev = wacom_wac->pad_input; + + if (pen_input_dev) { + error = input_register_device(pen_input_dev); + if (error) + goto fail; + } + + if (touch_input_dev) { + error = input_register_device(touch_input_dev); + if (error) + goto fail; + } + + if (pad_input_dev) { error = input_register_device(pad_input_dev); if (error) goto fail; @@ -2383,6 +2402,20 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) if (error) goto fail; + error = wacom_setup_inputs(wacom); + if (error) + goto fail; + + if (features->type == HID_GENERIC) + connect_mask |= HID_CONNECT_DRIVER; + + /* Regular HID work starts now */ + error = hid_hw_start(hdev, connect_mask); + if (error) { + hid_err(hdev, "hw start failed\n"); + goto fail; + } + error = wacom_register_inputs(wacom); if (error) goto fail; @@ -2397,16 +2430,6 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail; } - if (features->type == HID_GENERIC) - connect_mask |= HID_CONNECT_DRIVER; - - /* Regular HID work starts now */ - error = hid_hw_start(hdev, connect_mask); - if (error) { - hid_err(hdev, "hw start failed\n"); - goto fail; - } - if (!wireless) { /* Note that if query fails it is not a hard failure */ wacom_query_tablet_data(wacom); From 853b8d7597eea4ccaaefbcf0942cd42fc86d542a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 2 Feb 2024 12:22:58 +0200 Subject: [PATCH 091/311] remap_range: merge do_clone_file_range() into vfs_clone_file_range() commit dfad37051ade ("remap_range: move permission hooks out of do_clone_file_range()") moved the permission hooks from do_clone_file_range() out to its caller vfs_clone_file_range(), but left all the fast sanity checks in do_clone_file_range(). This makes the expensive security hooks be called in situations that they would not have been called before (e.g. fs does not support clone). The only reason for the do_clone_file_range() helper was that overlayfs did not use to be able to call vfs_clone_file_range() from copy up context with sb_writers lock held. However, since commit c63e56a4a652 ("ovl: do not open/llseek lower file with upper sb_writers held"), overlayfs just uses an open coded version of vfs_clone_file_range(). Merge_clone_file_range() into vfs_clone_file_range(), restoring the original order of checks as it was before the regressing commit and adapt the overlayfs code to call vfs_clone_file_range() before the permission hooks that were added by commit ca7ab482401c ("ovl: add permission hooks outside of do_splice_direct()"). Note that in the merge of do_clone_file_range(), the file_start_write() context was reduced to cover ->remap_file_range() without holding it over the permission hooks, which was the reason for doing the regressing commit in the first place. Reported-and-tested-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202401312229.eddeb9a6-oliver.sang@intel.com Fixes: dfad37051ade ("remap_range: move permission hooks out of do_clone_file_range()") Signed-off-by: Amir Goldstein Link: https://lore.kernel.org/r/20240202102258.1582671-1-amir73il@gmail.com Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- fs/overlayfs/copy_up.c | 14 ++++++-------- fs/remap_range.c | 31 +++++++++---------------------- include/linux/fs.h | 3 --- 3 files changed, 15 insertions(+), 33 deletions(-) diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index b8e25ca51016..8586e2f5d243 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -265,20 +265,18 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, if (IS_ERR(old_file)) return PTR_ERR(old_file); + /* Try to use clone_file_range to clone up within the same fs */ + cloned = vfs_clone_file_range(old_file, 0, new_file, 0, len, 0); + if (cloned == len) + goto out_fput; + + /* Couldn't clone, so now we try to copy the data */ error = rw_verify_area(READ, old_file, &old_pos, len); if (!error) error = rw_verify_area(WRITE, new_file, &new_pos, len); if (error) goto out_fput; - /* Try to use clone_file_range to clone up within the same fs */ - ovl_start_write(dentry); - cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0); - ovl_end_write(dentry); - if (cloned == len) - goto out_fput; - /* Couldn't clone, so now we try to copy the data */ - /* Check if lower fs supports seek operation */ if (old_file->f_mode & FMODE_LSEEK) skip_hole = true; diff --git a/fs/remap_range.c b/fs/remap_range.c index f8c1120b8311..de07f978ce3e 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -373,9 +373,9 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, } EXPORT_SYMBOL(generic_remap_file_range_prep); -loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t len, unsigned int remap_flags) +loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { loff_t ret; @@ -391,23 +391,6 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, if (!file_in->f_op->remap_file_range) return -EOPNOTSUPP; - ret = file_in->f_op->remap_file_range(file_in, pos_in, - file_out, pos_out, len, remap_flags); - if (ret < 0) - return ret; - - fsnotify_access(file_in); - fsnotify_modify(file_out); - return ret; -} -EXPORT_SYMBOL(do_clone_file_range); - -loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t len, unsigned int remap_flags) -{ - loff_t ret; - ret = remap_verify_area(file_in, pos_in, len, false); if (ret) return ret; @@ -417,10 +400,14 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, return ret; file_start_write(file_out); - ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len, - remap_flags); + ret = file_in->f_op->remap_file_range(file_in, pos_in, + file_out, pos_out, len, remap_flags); file_end_write(file_out); + if (ret < 0) + return ret; + fsnotify_access(file_in); + fsnotify_modify(file_out); return ret; } EXPORT_SYMBOL(vfs_clone_file_range); diff --git a/include/linux/fs.h b/include/linux/fs.h index ed5966a70495..023f37c60709 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2101,9 +2101,6 @@ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); -extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t len, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); From f814bdda774c183b0cc15ec8f3b6e7c6f4527ba5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 23 Jan 2024 18:58:26 +0100 Subject: [PATCH 092/311] blk-wbt: Fix detection of dirty-throttled tasks The detection of dirty-throttled tasks in blk-wbt has been subtly broken since its beginning in 2016. Namely if we are doing cgroup writeback and the throttled task is not in the root cgroup, balance_dirty_pages() will set dirty_sleep for the non-root bdi_writeback structure. However blk-wbt checks dirty_sleep only in the root cgroup bdi_writeback structure. Thus detection of recently throttled tasks is not working in this case (we noticed this when we switched to cgroup v2 and suddently writeback was slow). Since blk-wbt has no easy way to get to proper bdi_writeback and furthermore its intention has always been to work on the whole device rather than on individual cgroups, just move the dirty_sleep timestamp from bdi_writeback to backing_dev_info. That fixes the checking for recently throttled task and saves memory for everybody as a bonus. CC: stable@vger.kernel.org Fixes: b57d74aff9ab ("writeback: track if we're sleeping on progress in balance_dirty_pages()") Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20240123175826.21452-1-jack@suse.cz [axboe: fixup indentation errors] Signed-off-by: Jens Axboe --- block/blk-wbt.c | 4 ++-- include/linux/backing-dev-defs.h | 7 +++++-- mm/backing-dev.c | 2 +- mm/page-writeback.c | 2 +- 4 files changed, 9 insertions(+), 6 deletions(-) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 5ba3cd574eac..0c0e270a8265 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -163,9 +163,9 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) */ static bool wb_recent_wait(struct rq_wb *rwb) { - struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb; + struct backing_dev_info *bdi = rwb->rqos.disk->bdi; - return time_before(jiffies, wb->dirty_sleep + HZ); + return time_before(jiffies, bdi->last_bdp_sleep + HZ); } static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index ae12696ec492..2ad261082bba 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -141,8 +141,6 @@ struct bdi_writeback { struct delayed_work dwork; /* work item used for writeback */ struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ - unsigned long dirty_sleep; /* last wait */ - struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK @@ -179,6 +177,11 @@ struct backing_dev_info { * any dirty wbs, which is depended upon by bdi_has_dirty(). */ atomic_long_t tot_write_bandwidth; + /* + * Jiffies when last process was dirty throttled on this bdi. Used by + * blk-wbt. + */ + unsigned long last_bdp_sleep; struct bdi_writeback wb; /* the root writeback info for this bdi */ struct list_head wb_list; /* list of all wbs */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 1e3447bccdb1..e039d05304dd 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -436,7 +436,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); - wb->dirty_sleep = jiffies; err = fprop_local_init_percpu(&wb->completions, gfp); if (err) @@ -921,6 +920,7 @@ int bdi_init(struct backing_dev_info *bdi) INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); + bdi->last_bdp_sleep = jiffies; return cgwb_bdi_init(bdi); } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index cd4e4ae77c40..cc37fa7f3364 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1921,7 +1921,7 @@ pause: break; } __set_current_state(TASK_KILLABLE); - wb->dirty_sleep = now; + bdi->last_bdp_sleep = jiffies; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; From 7ed4380009e96d9e9c605e12822e987b35b05648 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 7 Feb 2024 08:01:17 +0900 Subject: [PATCH 093/311] firewire: core: send bus reset promptly on gap count error If we are bus manager and the bus has inconsistent gap counts, send a bus reset immediately instead of trying to read the root node's config ROM first. Otherwise, we could spend a lot of time trying to read the config ROM but never succeeding. This eliminates a 50+ second delay before the FireWire bus is usable after a newly connected device is powered on in certain circumstances. The delay occurs if a gap count inconsistency occurs, we are not the root node, and we become bus manager. One scenario that causes this is with a TI XIO2213B OHCI, the first time a Sony DSR-25 is powered on after being connected to the FireWire cable. In this configuration, the Linux box will not receive the initial PHY configuration packet sent by the DSR-25 as IRM, resulting in the DSR-25 having a gap count of 44 while the Linux box has a gap count of 63. FireWire devices have a gap count parameter, which is set to 63 on power-up and can be changed with a PHY configuration packet. This determines the duration of the subaction and arbitration gaps. For reliable communication, all nodes on a FireWire bus must have the same gap count. A node may have zero or more of the following roles: root node, bus manager (BM), isochronous resource manager (IRM), and cycle master. Unless a root node was forced with a PHY configuration packet, any node might become root node after a bus reset. Only the root node can become cycle master. If the root node is not cycle master capable, the BM or IRM should force a change of root node. After a bus reset, each node sends a self-ID packet, which contains its current gap count. A single bus reset does not change the gap count, but two bus resets in a row will set the gap count to 63. Because a consistent gap count is required for reliable communication, IEEE 1394a-2000 requires that the bus manager generate a bus reset if it detects that the gap count is inconsistent. When the gap count is inconsistent, build_tree() will notice this after the self identification process. It will set card->gap_count to the invalid value 0. If we become bus master, this will force bm_work() to send a bus reset when it performs gap count optimization. After a bus reset, there is no bus manager. We will almost always try to become bus manager. Once we become bus manager, we will first determine whether the root node is cycle master capable. Then, we will determine if the gap count should be changed. If either the root node or the gap count should be changed, we will generate a bus reset. To determine if the root node is cycle master capable, we read its configuration ROM. bm_work() will wait until we have finished trying to read the configuration ROM. However, an inconsistent gap count can make this take a long time. read_config_rom() will read the first few quadlets from the config ROM. Due to the gap count inconsistency, eventually one of the reads will time out. When read_config_rom() fails, fw_device_init() calls it again until MAX_RETRIES is reached. This takes 50+ seconds. Once we give up trying to read the configuration ROM, bm_work() will wake up, assume that the root node is not cycle master capable, and do a bus reset. Hopefully, this will resolve the gap count inconsistency. This change makes bm_work() check for an inconsistent gap count before waiting for the root node's configuration ROM. If the gap count is inconsistent, bm_work() will immediately do a bus reset. This eliminates the 50+ second delay and rapidly brings the bus to a working state. I considered that if the gap count is inconsistent, a PHY configuration packet might not be successful, so it could be desirable to skip the PHY configuration packet before the bus reset in this case. However, IEEE 1394a-2000 and IEEE 1394-2008 say that the bus manager may transmit a PHY configuration packet before a bus reset when correcting a gap count error. Since the standard endorses this, I decided it's safe to retain the PHY configuration packet transmission. Normally, after a topology change, we will reset the bus a maximum of 5 times to change the root node and perform gap count optimization. However, if there is a gap count inconsistency, we must always generate a bus reset. Otherwise the gap count inconsistency will persist and communication will be unreliable. For that reason, if there is a gap count inconstency, we generate a bus reset even if we already reached the 5 reset limit. Signed-off-by: Adam Goldman Reference: https://sourceforge.net/p/linux1394/mailman/message/58727806/ Signed-off-by: Takashi Sakamoto --- drivers/firewire/core-card.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 6ac5ff20a2fe..8aaa7fcb2630 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -429,7 +429,23 @@ static void bm_work(struct work_struct *work) */ card->bm_generation = generation; - if (root_device == NULL) { + if (card->gap_count == 0) { + /* + * If self IDs have inconsistent gap counts, do a + * bus reset ASAP. The config rom read might never + * complete, so don't wait for it. However, still + * send a PHY configuration packet prior to the + * bus reset. The PHY configuration packet might + * fail, but 1394-2008 8.4.5.2 explicitly permits + * it in this case, so it should be safe to try. + */ + new_root_id = local_id; + /* + * We must always send a bus reset if the gap count + * is inconsistent, so bypass the 5-reset limit. + */ + card->bm_retries = 0; + } else if (root_device == NULL) { /* * Either link_on is false, or we failed to read the * config rom. In either case, pick another root. From 829388b725f8d266ccec32a2f446717d8693eaba Mon Sep 17 00:00:00 2001 From: David Gow Date: Thu, 1 Feb 2024 14:04:36 +0800 Subject: [PATCH 094/311] kunit: device: Unregister the kunit_bus on shutdown If KUnit is built as a module, and it's unloaded, the kunit_bus is not unregistered. This causes an error if it's then re-loaded later, as we try to re-register the bus. Unregister the bus and root_device on shutdown, if it looks valid. In addition, be more specific about the value of kunit_bus_device. It is: - a valid struct device* if the kunit_bus initialised correctly. - an ERR_PTR if it failed to initialise. - NULL before initialisation and after shutdown. Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Signed-off-by: David Gow Reviewed-by: Rae Moar Signed-off-by: Shuah Khan --- lib/kunit/device-impl.h | 2 ++ lib/kunit/device.c | 14 ++++++++++++++ lib/kunit/test.c | 3 +++ 3 files changed, 19 insertions(+) diff --git a/lib/kunit/device-impl.h b/lib/kunit/device-impl.h index 54bd55836405..5fcd48ff0f36 100644 --- a/lib/kunit/device-impl.h +++ b/lib/kunit/device-impl.h @@ -13,5 +13,7 @@ // For internal use only -- registers the kunit_bus. int kunit_bus_init(void); +// For internal use only -- unregisters the kunit_bus. +void kunit_bus_shutdown(void); #endif //_KUNIT_DEVICE_IMPL_H diff --git a/lib/kunit/device.c b/lib/kunit/device.c index 074c6dd2e36a..644a38a1f5b1 100644 --- a/lib/kunit/device.c +++ b/lib/kunit/device.c @@ -54,6 +54,20 @@ int kunit_bus_init(void) return error; } +/* Unregister the 'kunit_bus' in case the KUnit module is unloaded. */ +void kunit_bus_shutdown(void) +{ + /* Make sure the bus exists before we unregister it. */ + if (IS_ERR_OR_NULL(kunit_bus_device)) + return; + + bus_unregister(&kunit_bus_type); + + root_device_unregister(kunit_bus_device); + + kunit_bus_device = NULL; +} + /* Release a 'fake' KUnit device. */ static void kunit_device_release(struct device *d) { diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 31a5a992e646..1d1475578515 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -928,6 +928,9 @@ static void __exit kunit_exit(void) #ifdef CONFIG_MODULES unregister_module_notifier(&kunit_mod_nb); #endif + + kunit_bus_shutdown(); + kunit_debugfs_cleanup(); } module_exit(kunit_exit); From 97cf301fa42e8ea6e0a24de97bc0abcdc87d9504 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Sun, 28 Jan 2024 13:04:05 +0100 Subject: [PATCH 095/311] riscv: Flush the tlb when a page directory is freed The riscv privileged specification mandates to flush the TLB whenever a page directory is modified, so add that to tlb_flush(). Fixes: c5e9b2c2ae82 ("riscv: Improve tlb_flush()") Signed-off-by: Alexandre Ghiti Reviewed-by: Charlie Jenkins Link: https://lore.kernel.org/r/20240128120405.25876-1-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/tlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h index 1eb5682b2af6..50b63b5c15bd 100644 --- a/arch/riscv/include/asm/tlb.h +++ b/arch/riscv/include/asm/tlb.h @@ -16,7 +16,7 @@ static void tlb_flush(struct mmu_gather *tlb); static inline void tlb_flush(struct mmu_gather *tlb) { #ifdef CONFIG_MMU - if (tlb->fullmm || tlb->need_flush_all) + if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables) flush_tlb_mm(tlb->mm); else flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, From 7011b51f13b391ee06708bb1f82653a2953f8cfc Mon Sep 17 00:00:00 2001 From: Ben Wolsieffer Date: Tue, 6 Feb 2024 10:10:05 -0500 Subject: [PATCH 096/311] regmap: kunit: fix raw noinc write test wrapping The raw noinc write test places a known value in the register following the noinc register to verify that it is not disturbed by the noinc write. This test ensures this value is distinct by adding 100 to the second element of the noinc write data. The regmap registers are 16-bit, while the test value is stored in an unsigned int. Therefore, adding 100 may cause the register to wrap while the test value does not, causing the test to fail. This patch fixes this by changing val_test and val_last from unsigned int to u16. Signed-off-by: Ben Wolsieffer Reported-by: Guenter Roeck Closes: https://lore.kernel.org/linux-kernel/745d3a11-15bc-48b6-84c8-c8761c943bed@roeck-us.net/T/ Tested-by: Guenter Roeck Link: https://lore.kernel.org/r/20240206151004.1636761-2-ben.wolsieffer@hefring.com Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-kunit.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/base/regmap/regmap-kunit.c b/drivers/base/regmap/regmap-kunit.c index 026bdcb45127..4eb18f5d3265 100644 --- a/drivers/base/regmap/regmap-kunit.c +++ b/drivers/base/regmap/regmap-kunit.c @@ -1202,7 +1202,8 @@ static void raw_noinc_write(struct kunit *test) struct regmap *map; struct regmap_config config; struct regmap_ram_data *data; - unsigned int val, val_test, val_last; + unsigned int val; + u16 val_test, val_last; u16 val_array[BLOCK_TEST_SIZE]; config = raw_regmap_config; From cd7d469c25704d414d71bf3644f163fb74e7996b Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Fri, 13 Oct 2023 13:55:44 +0800 Subject: [PATCH 097/311] libceph: fail sparse-read if the data length doesn't match Once this happens that means there have bugs. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 3 ++- net/ceph/osd_client.c | 18 +++++++++++++++--- 2 files changed, 17 insertions(+), 4 deletions(-) diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index fa018d5864e7..f66f6aac74f6 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -45,6 +45,7 @@ enum ceph_sparse_read_state { CEPH_SPARSE_READ_HDR = 0, CEPH_SPARSE_READ_EXTENTS, CEPH_SPARSE_READ_DATA_LEN, + CEPH_SPARSE_READ_DATA_PRE, CEPH_SPARSE_READ_DATA, }; @@ -64,7 +65,7 @@ struct ceph_sparse_read { u64 sr_req_len; /* orig request length */ u64 sr_pos; /* current pos in buffer */ int sr_index; /* current extent index */ - __le32 sr_datalen; /* length of actual data */ + u32 sr_datalen; /* length of actual data */ u32 sr_count; /* extent count in reply */ int sr_ext_len; /* length of extent array */ struct ceph_sparse_extent *sr_extent; /* extent array */ diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 625622016f57..2cea35e4ff8e 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -5857,8 +5857,8 @@ static int osd_sparse_read(struct ceph_connection *con, struct ceph_osd *o = con->private; struct ceph_sparse_read *sr = &o->o_sparse_read; u32 count = sr->sr_count; - u64 eoff, elen; - int ret; + u64 eoff, elen, len = 0; + int i, ret; switch (sr->sr_state) { case CEPH_SPARSE_READ_HDR: @@ -5903,8 +5903,20 @@ next_op: convert_extent_map(sr); ret = sizeof(sr->sr_datalen); *pbuf = (char *)&sr->sr_datalen; - sr->sr_state = CEPH_SPARSE_READ_DATA; + sr->sr_state = CEPH_SPARSE_READ_DATA_PRE; break; + case CEPH_SPARSE_READ_DATA_PRE: + /* Convert sr_datalen to host-endian */ + sr->sr_datalen = le32_to_cpu((__force __le32)sr->sr_datalen); + for (i = 0; i < count; i++) + len += sr->sr_extent[i].len; + if (sr->sr_datalen != len) { + pr_warn_ratelimited("data len %u != extent len %llu\n", + sr->sr_datalen, len); + return -EREMOTEIO; + } + sr->sr_state = CEPH_SPARSE_READ_DATA; + fallthrough; case CEPH_SPARSE_READ_DATA: if (sr->sr_index >= count) { sr->sr_state = CEPH_SPARSE_READ_HDR; From ee97302fbc0c98a25732d736fc73aaf4d62c4128 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 14 Dec 2023 09:21:15 +0800 Subject: [PATCH 098/311] libceph: rename read_sparse_msg_*() to read_partial_sparse_msg_*() These functions are supposed to behave like other read_partial_*() handlers: the contract with messenger v1 is that the handler bails if the area of the message it's responsible for is already processed. This comes up when handling short reads from the socket. [ idryomov: changelog ] Signed-off-by: Xiubo Li Acked-by: Jeff Layton Signed-off-by: Ilya Dryomov --- net/ceph/messenger_v1.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c index f9a50d7f0d20..4cb60bacf5f5 100644 --- a/net/ceph/messenger_v1.c +++ b/net/ceph/messenger_v1.c @@ -991,7 +991,7 @@ static inline int read_partial_message_section(struct ceph_connection *con, return read_partial_message_chunk(con, section, sec_len, crc); } -static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc) +static int read_partial_sparse_msg_extent(struct ceph_connection *con, u32 *crc) { struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor; bool do_bounce = ceph_test_opt(from_msgr(con->msgr), RXBOUNCE); @@ -1026,7 +1026,7 @@ static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc) return 1; } -static int read_sparse_msg_data(struct ceph_connection *con) +static int read_partial_sparse_msg_data(struct ceph_connection *con) { struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor; bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC); @@ -1043,7 +1043,7 @@ static int read_sparse_msg_data(struct ceph_connection *con) con->v1.in_sr_len, &crc); else if (cursor->sr_resid > 0) - ret = read_sparse_msg_extent(con, &crc); + ret = read_partial_sparse_msg_extent(con, &crc); if (ret <= 0) { if (do_datacrc) @@ -1254,7 +1254,7 @@ static int read_partial_message(struct ceph_connection *con) return -EIO; if (m->sparse_read) - ret = read_sparse_msg_data(con); + ret = read_partial_sparse_msg_data(con); else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) ret = read_partial_msg_data_bounce(con); else From 8e46a2d068c92a905d01cbb018b00d66991585ab Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 14 Dec 2023 16:01:03 +0800 Subject: [PATCH 099/311] libceph: just wait for more data to be available on the socket A short read may occur while reading the message footer from the socket. Later, when the socket is ready for another read, the messenger invokes all read_partial_*() handlers, including read_partial_sparse_msg_data(). The expectation is that read_partial_sparse_msg_data() would bail, allowing the messenger to invoke read_partial() for the footer and pick up where it left off. However read_partial_sparse_msg_data() violates that and ends up calling into the state machine in the OSD client. The sparse-read state machine assumes that it's a new op and interprets some piece of the footer as the sparse-read header and returns bogus extents/data length, etc. To determine whether read_partial_sparse_msg_data() should bail, let's reuse cursor->total_resid. Because once it reaches to zero that means all the extents and data have been successfully received in last read, else it could break out when partially reading any of the extents and data. And then osd_sparse_read() could continue where it left off. [ idryomov: changelog ] Link: https://tracker.ceph.com/issues/63586 Fixes: d396f89db39a ("libceph: add sparse read support to msgr1") Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/messenger.h | 2 +- net/ceph/messenger_v1.c | 25 +++++++++++++------------ net/ceph/messenger_v2.c | 4 ++-- net/ceph/osd_client.c | 9 +++------ 4 files changed, 19 insertions(+), 21 deletions(-) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 2eaaabbe98cb..1717cc57cdac 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -283,7 +283,7 @@ struct ceph_msg { struct kref kref; bool more_to_follow; bool needs_out_seq; - bool sparse_read; + u64 sparse_read_total; int front_alloc_len; struct ceph_msgpool *pool; diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c index 4cb60bacf5f5..0cb61c76b9b8 100644 --- a/net/ceph/messenger_v1.c +++ b/net/ceph/messenger_v1.c @@ -160,8 +160,9 @@ static size_t sizeof_footer(struct ceph_connection *con) static void prepare_message_data(struct ceph_msg *msg, u32 data_len) { /* Initialize data cursor if it's not a sparse read */ - if (!msg->sparse_read) - ceph_msg_data_cursor_init(&msg->cursor, msg, data_len); + u64 len = msg->sparse_read_total ? : data_len; + + ceph_msg_data_cursor_init(&msg->cursor, msg, len); } /* @@ -1036,7 +1037,7 @@ static int read_partial_sparse_msg_data(struct ceph_connection *con) if (do_datacrc) crc = con->in_data_crc; - do { + while (cursor->total_resid) { if (con->v1.in_sr_kvec.iov_base) ret = read_partial_message_chunk(con, &con->v1.in_sr_kvec, @@ -1044,23 +1045,23 @@ static int read_partial_sparse_msg_data(struct ceph_connection *con) &crc); else if (cursor->sr_resid > 0) ret = read_partial_sparse_msg_extent(con, &crc); - - if (ret <= 0) { - if (do_datacrc) - con->in_data_crc = crc; - return ret; - } + if (ret <= 0) + break; memset(&con->v1.in_sr_kvec, 0, sizeof(con->v1.in_sr_kvec)); ret = con->ops->sparse_read(con, cursor, (char **)&con->v1.in_sr_kvec.iov_base); + if (ret <= 0) { + ret = ret ? ret : 1; /* must return > 0 to indicate success */ + break; + } con->v1.in_sr_len = ret; - } while (ret > 0); + } if (do_datacrc) con->in_data_crc = crc; - return ret < 0 ? ret : 1; /* must return > 0 to indicate success */ + return ret; } static int read_partial_msg_data(struct ceph_connection *con) @@ -1253,7 +1254,7 @@ static int read_partial_message(struct ceph_connection *con) if (!m->num_data_items) return -EIO; - if (m->sparse_read) + if (m->sparse_read_total) ret = read_partial_sparse_msg_data(con); else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) ret = read_partial_msg_data_bounce(con); diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index f8ec60e1aba3..a0ca5414b333 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -1128,7 +1128,7 @@ static int decrypt_tail(struct ceph_connection *con) struct sg_table enc_sgt = {}; struct sg_table sgt = {}; struct page **pages = NULL; - bool sparse = con->in_msg->sparse_read; + bool sparse = !!con->in_msg->sparse_read_total; int dpos = 0; int tail_len; int ret; @@ -2060,7 +2060,7 @@ static int prepare_read_tail_plain(struct ceph_connection *con) } if (data_len(msg)) { - if (msg->sparse_read) + if (msg->sparse_read_total) con->v2.in_state = IN_S_PREPARE_SPARSE_DATA; else con->v2.in_state = IN_S_PREPARE_READ_DATA; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 2cea35e4ff8e..9d078b37fe0b 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -5510,7 +5510,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, } m = ceph_msg_get(req->r_reply); - m->sparse_read = (bool)srlen; + m->sparse_read_total = srlen; dout("get_reply tid %lld %p\n", tid, m); @@ -5777,11 +5777,8 @@ static int prep_next_sparse_read(struct ceph_connection *con, } if (o->o_sparse_op_idx < 0) { - u64 srlen = sparse_data_requested(req); - - dout("%s: [%d] starting new sparse read req. srlen=0x%llx\n", - __func__, o->o_osd, srlen); - ceph_msg_data_cursor_init(cursor, con->in_msg, srlen); + dout("%s: [%d] starting new sparse read req\n", + __func__, o->o_osd); } else { u64 end; From bbb20ea993f46743f7429092ddc52f1a5c5428ef Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 18 Jan 2024 14:24:41 +0800 Subject: [PATCH 100/311] ceph: always set initial i_blkbits to CEPH_FSCRYPT_BLOCK_SHIFT The fscrypt code will use i_blkbits to setup ci_data_unit_bits when allocating the new inode, but ceph will initiate i_blkbits ater when filling the inode, which is too late. Since ci_data_unit_bits will only be used by the fscrypt framework so initiating i_blkbits with CEPH_FSCRYPT_BLOCK_SHIFT is safe. Link: https://tracker.ceph.com/issues/64035 Fixes: 5b1188847180 ("fscrypt: support crypto data unit size less than filesystem block size") Signed-off-by: Xiubo Li Reviewed-by: Eric Biggers Signed-off-by: Ilya Dryomov --- fs/ceph/inode.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 0c25d326afc4..7b2e77517f23 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -78,6 +78,8 @@ struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry, if (!inode) return ERR_PTR(-ENOMEM); + inode->i_blkbits = CEPH_FSCRYPT_BLOCK_SHIFT; + if (!S_ISLNK(*mode)) { err = ceph_pre_init_acls(dir, mode, as_ctx); if (err < 0) From cda4672da1c26835dcbd7aec2bfed954eda9b5ef Mon Sep 17 00:00:00 2001 From: Rishabh Dave Date: Thu, 1 Feb 2024 17:07:16 +0530 Subject: [PATCH 101/311] ceph: prevent use-after-free in encode_cap_msg() In fs/ceph/caps.c, in encode_cap_msg(), "use after free" error was caught by KASAN at this line - 'ceph_buffer_get(arg->xattr_buf);'. This implies before the refcount could be increment here, it was freed. In same file, in "handle_cap_grant()" refcount is decremented by this line - 'ceph_buffer_put(ci->i_xattrs.blob);'. It appears that a race occurred and resource was freed by the latter line before the former line could increment it. encode_cap_msg() is called by __send_cap() and __send_cap() is called by ceph_check_caps() after calling __prep_cap(). __prep_cap() is where arg->xattr_buf is assigned to ci->i_xattrs.blob. This is the spot where the refcount must be increased to prevent "use after free" error. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/59259 Signed-off-by: Rishabh Dave Reviewed-by: Jeff Layton Reviewed-by: Xiubo Li Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 9c02f328c966..e8bf082105d8 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1452,7 +1452,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, if (flushing & CEPH_CAP_XATTR_EXCL) { arg->old_xattr_buf = __ceph_build_xattrs_blob(ci); arg->xattr_version = ci->i_xattrs.version; - arg->xattr_buf = ci->i_xattrs.blob; + arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob); } else { arg->xattr_buf = NULL; arg->old_xattr_buf = NULL; @@ -1553,6 +1553,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci) encode_cap_msg(msg, arg); ceph_con_send(&arg->session->s_con, msg); ceph_buffer_put(arg->old_xattr_buf); + ceph_buffer_put(arg->xattr_buf); if (arg->wake) wake_up_all(&ci->i_cap_wq); } From 07045648c07c5632e0dfd5ce084d3cd0cec0258a Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 4 Jan 2024 09:21:30 +0800 Subject: [PATCH 102/311] ceph: always check dir caps asynchronously The MDS will issue the 'Fr' caps for async dirop, while there is buggy in kclient and it could miss releasing the async dirop caps, which is 'Fsxr'. And then the MDS will complain with: "[WRN] client.xxx isn't responding to mclientcaps(revoke) ..." So when releasing the dirop async requests or when they fail we should always make sure that being revoked caps could be released. Link: https://tracker.ceph.com/issues/50223 Signed-off-by: Xiubo Li Reviewed-by: Milind Changire Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 6 ------ fs/ceph/mds_client.c | 9 ++++----- fs/ceph/mds_client.h | 2 +- fs/ceph/super.h | 2 -- 4 files changed, 5 insertions(+), 14 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index e8bf082105d8..ad1f46c66fbf 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -3216,7 +3216,6 @@ static int ceph_try_drop_cap_snap(struct ceph_inode_info *ci, enum put_cap_refs_mode { PUT_CAP_REFS_SYNC = 0, - PUT_CAP_REFS_NO_CHECK, PUT_CAP_REFS_ASYNC, }; @@ -3332,11 +3331,6 @@ void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had) __ceph_put_cap_refs(ci, had, PUT_CAP_REFS_ASYNC); } -void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci, int had) -{ - __ceph_put_cap_refs(ci, had, PUT_CAP_REFS_NO_CHECK); -} - /* * Release @nr WRBUFFER refs on dirty pages for the given @snapc snap * context. Adjust per-snap dirty page accounting as appropriate. diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 548d1de379f3..f71bb9c9569f 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1089,7 +1089,7 @@ void ceph_mdsc_release_request(struct kref *kref) struct ceph_mds_request *req = container_of(kref, struct ceph_mds_request, r_kref); - ceph_mdsc_release_dir_caps_no_check(req); + ceph_mdsc_release_dir_caps_async(req); destroy_reply_info(&req->r_reply_info); if (req->r_request) ceph_msg_put(req->r_request); @@ -4261,7 +4261,7 @@ void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req) } } -void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req) +void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req) { struct ceph_client *cl = req->r_mdsc->fsc->client; int dcaps; @@ -4269,8 +4269,7 @@ void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req) dcaps = xchg(&req->r_dir_caps, 0); if (dcaps) { doutc(cl, "releasing r_dir_caps=%s\n", ceph_cap_string(dcaps)); - ceph_put_cap_refs_no_check_caps(ceph_inode(req->r_parent), - dcaps); + ceph_put_cap_refs_async(ceph_inode(req->r_parent), dcaps); } } @@ -4306,7 +4305,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc, if (req->r_session->s_mds != session->s_mds) continue; - ceph_mdsc_release_dir_caps_no_check(req); + ceph_mdsc_release_dir_caps_async(req); __send_request(session, req, true); } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 2e6ddaa13d72..40560af38827 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -552,7 +552,7 @@ extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, struct inode *dir, struct ceph_mds_request *req); extern void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req); -extern void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req); +extern void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req); static inline void ceph_mdsc_get_request(struct ceph_mds_request *req) { kref_get(&req->r_kref); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index b06e2bc86221..b63b4cd9b5b6 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1255,8 +1255,6 @@ extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps, extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps); extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had); extern void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had); -extern void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci, - int had); extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, struct ceph_snap_context *snapc); extern void __ceph_remove_capsnap(struct inode *inode, From ce68c035457bdd025a9961e0ba2157323090c581 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Tue, 30 Jan 2024 13:01:14 +0100 Subject: [PATCH 103/311] riscv: Fix arch_hugetlb_migration_supported() for NAPOT arch_hugetlb_migration_supported() must be reimplemented to add support for NAPOT hugepages, which is done here. Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page") Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20240130120114.106003-1-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/hugetlb.h | 3 +++ arch/riscv/mm/hugetlbpage.c | 16 +++++++++++++--- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 4c5b0e929890..20f9c3ba2341 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -11,6 +11,9 @@ static inline void arch_clear_hugepage_flags(struct page *page) } #define arch_clear_hugepage_flags arch_clear_hugepage_flags +bool arch_hugetlb_migration_supported(struct hstate *h); +#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported + #ifdef CONFIG_RISCV_ISA_SVNAPOT #define __HAVE_ARCH_HUGE_PTE_CLEAR void huge_pte_clear(struct mm_struct *mm, unsigned long addr, diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 87406b26c3da..29c7606414d2 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -364,7 +364,7 @@ void huge_pte_clear(struct mm_struct *mm, pte_clear(mm, addr, ptep); } -static __init bool is_napot_size(unsigned long size) +static bool is_napot_size(unsigned long size) { unsigned long order; @@ -392,7 +392,7 @@ arch_initcall(napot_hugetlbpages_init); #else -static __init bool is_napot_size(unsigned long size) +static bool is_napot_size(unsigned long size) { return false; } @@ -409,7 +409,7 @@ int pmd_huge(pmd_t pmd) return pmd_leaf(pmd); } -bool __init arch_hugetlb_valid_size(unsigned long size) +static bool __hugetlb_valid_size(unsigned long size) { if (size == HPAGE_SIZE) return true; @@ -421,6 +421,16 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return false; } +bool __init arch_hugetlb_valid_size(unsigned long size) +{ + return __hugetlb_valid_size(size); +} + +bool arch_hugetlb_migration_supported(struct hstate *h) +{ + return __hugetlb_valid_size(huge_page_size(h)); +} + #ifdef CONFIG_CONTIG_ALLOC static __init int gigantic_pages_init(void) { From 2cf963787529f615f7c93bdcf13a5e82029e7f38 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Thu, 23 Nov 2023 13:42:14 +0000 Subject: [PATCH 104/311] riscv: declare overflow_stack as exported from traps.c The percpu area overflow_stacks is exported from arch/riscv/kernel/traps.c for use in the entry code, but is not declared anywhere. Add the relevant declaration to arch/riscv/include/asm/stacktrace.h to silence the following sparse warning: arch/riscv/kernel/traps.c:395:1: warning: symbol '__pcpu_scope_overflow_stack' was not declared. Should it be static? We don't add the stackinfo_get_overflow() call as for some of the other architectures as this doesn't seem to be used yet, so just silence the warning. Signed-off-by: Ben Dooks Reviewed-by: Conor Dooley Fixes: be97d0db5f44 ("riscv: VMAP_STACK overflow detection thread-safe") Link: https://lore.kernel.org/r/20231123134214.81481-1-ben.dooks@codethink.co.uk Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/stacktrace.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h index f7e8ef2418b9..b1495a7e06ce 100644 --- a/arch/riscv/include/asm/stacktrace.h +++ b/arch/riscv/include/asm/stacktrace.h @@ -21,4 +21,9 @@ static inline bool on_thread_stack(void) return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); } + +#ifdef CONFIG_VMAP_STACK +DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack); +#endif /* CONFIG_VMAP_STACK */ + #endif /* _ASM_RISCV_STACKTRACE_H */ From 3951f6add519a8e954bf78691a412f65b24f4715 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Tue, 30 Jan 2024 12:55:08 +0100 Subject: [PATCH 105/311] riscv: Fix arch_tlbbatch_flush() by clearing the batch cpumask We must clear the cpumask once we have flushed the batch, otherwise cpus get accumulated and we end sending IPIs to more cpus than needed. Fixes: 54d7431af73e ("riscv: Add support for BATCHED_UNMAP_TLB_FLUSH") Signed-off-by: Alexandre Ghiti Reviewed-by: Charlie Jenkins Reviewed-by: Jisheng Zhang Link: https://lore.kernel.org/r/20240130115508.105386-1-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/tlbflush.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index dffb0e5bd942..893566e004b7 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -234,4 +234,5 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) { __flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE); + cpumask_clear(&batch->cpumask); } From 1f4137e882c621f8ed4bd4da9b10cf91d059e52a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 6 Feb 2024 09:47:21 -0800 Subject: [PATCH 106/311] nvme: move passthrough logging attribute to head The namespace does not have attributes, but the head does. Move the new logging attribute to that structure instead of dereferencing the wrong type. And while we're here, fix the reverse-tree coding style. Fixes: 9f079dda14339e ("nvme: allow passthru cmd error logging") Reported-by: Tasmiya Nalatwad Tested-by: Tasmiya Nalatwad Reviewed-by: Chaitanya Kulkarni Reviewed-by: Alan Adamson Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 3 +-- drivers/nvme/host/nvme.h | 2 +- drivers/nvme/host/sysfs.c | 30 +++++++++++++++--------------- 3 files changed, 17 insertions(+), 18 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 975245527c1f..246e92c05aac 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -713,7 +713,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd) if (req->q->queuedata) { struct nvme_ns *ns = req->q->disk->private_data; - logging_enabled = ns->passthru_err_log_enabled; + logging_enabled = ns->head->passthru_err_log_enabled; req->timeout = NVME_IO_TIMEOUT; } else { /* no queuedata implies admin queue */ logging_enabled = nr->ctrl->passthru_err_log_enabled; @@ -3696,7 +3696,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) ns->disk = disk; ns->queue = disk->queue; - ns->passthru_err_log_enabled = false; if (ctrl->opts && ctrl->opts->data_digest) blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 3897334e3950..7b87763e2f8a 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -455,6 +455,7 @@ struct nvme_ns_head { struct list_head entry; struct kref ref; bool shared; + bool passthru_err_log_enabled; int instance; struct nvme_effects_log *effects; u64 nuse; @@ -523,7 +524,6 @@ struct nvme_ns { struct device cdev_device; struct nvme_fault_inject fault_inject; - bool passthru_err_log_enabled; }; /* NVMe ns supports metadata actions by the controller (generate/strip) */ diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index d099218e494a..f2832f70e7e0 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -48,8 +48,8 @@ static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - int err; bool passthru_err_log_enabled; + int err; err = kstrtobool(buf, &passthru_err_log_enabled); if (err) @@ -60,25 +60,34 @@ static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev, return count; } +static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (nvme_disk_is_ns_head(disk)) + return disk->private_data; + return nvme_get_ns_from_dev(dev)->head; +} + static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nvme_ns *n = dev_get_drvdata(dev); + struct nvme_ns_head *head = dev_to_ns_head(dev); - return sysfs_emit(buf, n->passthru_err_log_enabled ? "on\n" : "off\n"); + return sysfs_emit(buf, head->passthru_err_log_enabled ? "on\n" : "off\n"); } static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct nvme_ns *ns = dev_get_drvdata(dev); - int err; + struct nvme_ns_head *head = dev_to_ns_head(dev); bool passthru_err_log_enabled; + int err; err = kstrtobool(buf, &passthru_err_log_enabled); if (err) return -EINVAL; - ns->passthru_err_log_enabled = passthru_err_log_enabled; + head->passthru_err_log_enabled = passthru_err_log_enabled; return count; } @@ -91,15 +100,6 @@ static struct device_attribute dev_attr_io_passthru_err_log_enabled = \ __ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \ nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store); -static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev) -{ - struct gendisk *disk = dev_to_disk(dev); - - if (nvme_disk_is_ns_head(disk)) - return disk->private_data; - return nvme_get_ns_from_dev(dev)->head; -} - static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, char *buf) { From e8c263ed6de8183e670fbd127c2512292a2ad8eb Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Mon, 5 Feb 2024 16:30:21 -0800 Subject: [PATCH 107/311] nvme-core: fix comment to reflect right functions The functions and the attribute listed in the comment doesn't exists in the code, (ns->logging_enabled, nvme_passthru_err_log_enabled_store() and nvme_passthru_err_log_enabled_show()) Update the comment with right function names and a comment ns->head->passthru_err_log_enabled, nvme_io_passthru_err_log_enabled_store() and nvme_io_passthru_err_log_enabled_show(). Signed-off-by: Chaitanya Kulkarni Reviewed-by: Alan Adamson Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 246e92c05aac..60537c9224bf 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3761,8 +3761,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) /* * Set ns->disk->device->driver_data to ns so we can access - * ns->logging_enabled in nvme_passthru_err_log_enabled_store() and - * nvme_passthru_err_log_enabled_show(). + * ns->head->passthru_err_log_enabled in + * nvme_io_passthru_err_log_enabled_[store | show](). */ dev_set_drvdata(disk_to_dev(ns->disk), ns); From b5d1b4b46f856da1473c7ba9a5cdfcb55c9b2478 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 26 Jan 2024 11:40:37 +0300 Subject: [PATCH 108/311] PCI: dwc: Fix a 64bit bug in dw_pcie_ep_raise_msix_irq() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The "msg_addr" variable is u64. However, the "aligned_offset" is an unsigned int. This means that when the code does: msg_addr &= ~aligned_offset; it will unintentionally zero out the high 32 bits. Use ALIGN_DOWN() to do the alignment instead. Fixes: 2217fffcd63f ("PCI: dwc: endpoint: Fix dw_pcie_ep_raise_msix_irq() alignment support") Link: https://lore.kernel.org/r/af59c7ad-ab93-40f7-ad4a-7ac0b14d37f5@moroto.mountain Signed-off-by: Dan Carpenter Signed-off-by: Bjorn Helgaas Reviewed-by: Niklas Cassel Reviewed-by: Ilpo Järvinen Reviewed-by: Manivannan Sadhasivam Cc: --- drivers/pci/controller/dwc/pcie-designware-ep.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 5befed2dc02b..d6b66597101e 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -6,6 +6,7 @@ * Author: Kishon Vijay Abraham I */ +#include #include #include #include @@ -551,7 +552,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, } aligned_offset = msg_addr & (epc->mem->window.page_size - 1); - msg_addr &= ~aligned_offset; + msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size); ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, epc->mem->window.page_size); if (ret) From 67057f48df79a3d73683385f521215146861684b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 26 Jan 2024 11:41:01 +0300 Subject: [PATCH 109/311] PCI: dwc: Clean up dw_pcie_ep_raise_msi_irq() alignment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I recently changed the alignment code in dw_pcie_ep_raise_msix_irq(). The code in dw_pcie_ep_raise_msi_irq() is similar, so update it to match, just for consistency. (No effect on runtime, just a cleanup). Link: https://lore.kernel.org/r/184097e0-c728-42c7-9e8a-556bd33fb612@moroto.mountain Signed-off-by: Dan Carpenter Signed-off-by: Bjorn Helgaas Reviewed-by: Niklas Cassel Reviewed-by: Ilpo Järvinen Reviewed-by: Manivannan Sadhasivam --- drivers/pci/controller/dwc/pcie-designware-ep.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index d6b66597101e..9a437cfce073 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -483,9 +483,10 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, reg = ep_func->msi_cap + PCI_MSI_DATA_32; msg_data = dw_pcie_ep_readw_dbi(ep, func_no, reg); } - aligned_offset = msg_addr_lower & (epc->mem->window.page_size - 1); - msg_addr = ((u64)msg_addr_upper) << 32 | - (msg_addr_lower & ~aligned_offset); + msg_addr = ((u64)msg_addr_upper) << 32 | msg_addr_lower; + + aligned_offset = msg_addr & (epc->mem->window.page_size - 1); + msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size); ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, epc->mem->window.page_size); if (ret) From 46f5ab762d048dad224436978315cbc2fa79c630 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 6 Feb 2024 11:22:09 +0100 Subject: [PATCH 110/311] fs: relax mount_setattr() permission checks When we added mount_setattr() I added additional checks compared to the legacy do_reconfigure_mnt() and do_change_type() helpers used by regular mount(2). If that mount had a parent then verify that the caller and the mount namespace the mount is attached to match and if not make sure that it's an anonymous mount. The real rootfs falls into neither category. It is neither an anoymous mount because it is obviously attached to the initial mount namespace but it also obviously doesn't have a parent mount. So that means legacy mount(2) allows changing mount properties on the real rootfs but mount_setattr(2) blocks this. I never thought much about this but of course someone on this planet of earth changes properties on the real rootfs as can be seen in [1]. Since util-linux finally switched to the new mount api in 2.39 not so long ago it also relies on mount_setattr() and that surfaced this issue when Fedora 39 finally switched to it. Fix this. Link: https://bugzilla.redhat.com/show_bug.cgi?id=2256843 Link: https://lore.kernel.org/r/20240206-vfs-mount-rootfs-v1-1-19b335eee133@kernel.org Reviewed-by: Jan Kara Reported-by: Karel Zak Cc: stable@vger.kernel.org # v5.12+ Signed-off-by: Christian Brauner --- fs/namespace.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index 437f60e96d40..5a51315c6678 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4472,10 +4472,15 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) /* * If this is an attached mount make sure it's located in the callers * mount namespace. If it's not don't let the caller interact with it. - * If this is a detached mount make sure it has an anonymous mount - * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE. + * + * If this mount doesn't have a parent it's most often simply a + * detached mount with an anonymous mount namespace. IOW, something + * that's simply not attached yet. But there are apparently also users + * that do change mount properties on the rootfs itself. That obviously + * neither has a parent nor is it a detached mount so we cannot + * unconditionally check for detached mounts. */ - if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns))) + if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt)) goto out; /* From e96fddb32931d007db12b1fce9b5e8e4c080401b Mon Sep 17 00:00:00 2001 From: Srinivasan Shanmugam Date: Sat, 27 Jan 2024 18:34:01 +0530 Subject: [PATCH 111/311] drm/amd/display: Fix 'panel_cntl' could be null in 'dcn21_set_backlight_level()' 'panel_cntl' structure used to control the display panel could be null, dereferencing it could lead to a null pointer access. Fixes the below: drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn21/dcn21_hwseq.c:269 dcn21_set_backlight_level() error: we previously assumed 'panel_cntl' could be null (see line 250) Fixes: 474ac4a875ca ("drm/amd/display: Implement some asic specific abm call backs.") Cc: Yongqiang Sun Cc: Anthony Koo Cc: Rodrigo Siqueira Cc: Aurabindo Pillai Signed-off-by: Srinivasan Shanmugam Reviewed-by: Anthony Koo Signed-off-by: Alex Deucher --- .../amd/display/dc/hwss/dcn21/dcn21_hwseq.c | 39 ++++++++++--------- 1 file changed, 20 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c index 8e88dcaf88f5..a9cd39f77360 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c @@ -237,34 +237,35 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx, { struct dc_context *dc = pipe_ctx->stream->ctx; struct abm *abm = pipe_ctx->stream_res.abm; + struct timing_generator *tg = pipe_ctx->stream_res.tg; struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl; + uint32_t otg_inst; + + if (!abm && !tg && !panel_cntl) + return false; + + otg_inst = tg->inst; if (dc->dc->res_pool->dmcu) { dce110_set_backlight_level(pipe_ctx, backlight_pwm_u16_16, frame_ramp); return true; } - if (abm != NULL) { - uint32_t otg_inst = pipe_ctx->stream_res.tg->inst; - - if (abm && panel_cntl) { - if (abm->funcs && abm->funcs->set_pipe_ex) { - abm->funcs->set_pipe_ex(abm, - otg_inst, - SET_ABM_PIPE_NORMAL, - panel_cntl->inst, - panel_cntl->pwrseq_inst); - } else { - dmub_abm_set_pipe(abm, - otg_inst, - SET_ABM_PIPE_NORMAL, - panel_cntl->inst, - panel_cntl->pwrseq_inst); - } - } + if (abm->funcs && abm->funcs->set_pipe_ex) { + abm->funcs->set_pipe_ex(abm, + otg_inst, + SET_ABM_PIPE_NORMAL, + panel_cntl->inst, + panel_cntl->pwrseq_inst); + } else { + dmub_abm_set_pipe(abm, + otg_inst, + SET_ABM_PIPE_NORMAL, + panel_cntl->inst, + panel_cntl->pwrseq_inst); } - if (abm && abm->funcs && abm->funcs->set_backlight_level_pwm) + if (abm->funcs && abm->funcs->set_backlight_level_pwm) abm->funcs->set_backlight_level_pwm(abm, backlight_pwm_u16_16, frame_ramp, 0, panel_cntl->inst); else From 66951d98d9bf45ba25acf37fe0747253fafdf298 Mon Sep 17 00:00:00 2001 From: Srinivasan Shanmugam Date: Wed, 31 Jan 2024 08:49:41 +0530 Subject: [PATCH 112/311] drm/amd/display: Add NULL test for 'timing generator' in 'dcn21_set_pipe()' In "u32 otg_inst = pipe_ctx->stream_res.tg->inst;" pipe_ctx->stream_res.tg could be NULL, it is relying on the caller to ensure the tg is not NULL. Fixes: 474ac4a875ca ("drm/amd/display: Implement some asic specific abm call backs.") Cc: Yongqiang Sun Cc: Anthony Koo Cc: Rodrigo Siqueira Cc: Aurabindo Pillai Signed-off-by: Srinivasan Shanmugam Reviewed-by: Anthony Koo Signed-off-by: Alex Deucher --- .../amd/display/dc/hwss/dcn21/dcn21_hwseq.c | 24 +++++++++++-------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c index a9cd39f77360..5c7f380a84f9 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c @@ -206,28 +206,32 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx) void dcn21_set_pipe(struct pipe_ctx *pipe_ctx) { struct abm *abm = pipe_ctx->stream_res.abm; - uint32_t otg_inst = pipe_ctx->stream_res.tg->inst; + struct timing_generator *tg = pipe_ctx->stream_res.tg; struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl; struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu; + uint32_t otg_inst; + + if (!abm && !tg && !panel_cntl) + return; + + otg_inst = tg->inst; if (dmcu) { dce110_set_pipe(pipe_ctx); return; } - if (abm && panel_cntl) { - if (abm->funcs && abm->funcs->set_pipe_ex) { - abm->funcs->set_pipe_ex(abm, + if (abm->funcs && abm->funcs->set_pipe_ex) { + abm->funcs->set_pipe_ex(abm, otg_inst, SET_ABM_PIPE_NORMAL, panel_cntl->inst, panel_cntl->pwrseq_inst); - } else { - dmub_abm_set_pipe(abm, otg_inst, - SET_ABM_PIPE_NORMAL, - panel_cntl->inst, - panel_cntl->pwrseq_inst); - } + } else { + dmub_abm_set_pipe(abm, otg_inst, + SET_ABM_PIPE_NORMAL, + panel_cntl->inst, + panel_cntl->pwrseq_inst); } } From 2103370afba74dda39ff5d2d69163c86644ce528 Mon Sep 17 00:00:00 2001 From: Wenjing Liu Date: Thu, 18 Jan 2024 18:12:15 -0500 Subject: [PATCH 113/311] drm/amd/display: set odm_combine_policy based on context in dcn32 resource [why] When populating dml pipes, odm combine policy should be assigned based on the pipe topology of the context passed in. DML pipes could be repopulated multiple times during single validate bandwidth attempt. We need to make sure that whenever we repopulate the dml pipes it is always aligned with the updated context. There is a case where DML pipes get repopulated during FPO optimization after ODM combine policy is changed. Since in the current code we reinitlaize ODM combine policy, even though the current context has ODM combine enabled, we overwrite it despite the pipes are already split. This causes DML to think that MPC combine is used so we mistakenly enable MPC combine because we apply pipe split with ODM combine policy reset. This issue doesn't impact non windowed MPO with ODM case because the legacy policy has restricted use cases. We don't encounter the case where both ODM and FPO optimizations are enabled together. So we decide to leave it as is because it is about to be replaced anyway. Cc: stable@vger.kernel.org # 6.6+ Reviewed-by: Chaitanya Dhere Reviewed-by: Alvin Lee Acked-by: Hamza Mahfooz Signed-off-by: Wenjing Liu Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 15 ++++++++++---- drivers/gpu/drm/amd/display/dc/inc/resource.h | 20 ++++++++----------- .../dc/resource/dcn32/dcn32_resource.c | 16 ++++++++++++++- 3 files changed, 34 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index dd781a20692e..ba76dd4a2ce2 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -1288,7 +1288,7 @@ static bool update_pipes_with_split_flags(struct dc *dc, struct dc_state *contex return updated; } -static bool should_allow_odm_power_optimization(struct dc *dc, +static bool should_apply_odm_power_optimization(struct dc *dc, struct dc_state *context, struct vba_vars_st *v, int *split, bool *merge) { @@ -1392,9 +1392,12 @@ static void try_odm_power_optimization_and_revalidate( { int i; unsigned int new_vlevel; + unsigned int cur_policy[MAX_PIPES]; - for (i = 0; i < pipe_cnt; i++) + for (i = 0; i < pipe_cnt; i++) { + cur_policy[i] = pipes[i].pipe.dest.odm_combine_policy; pipes[i].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1; + } new_vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt); @@ -1403,6 +1406,9 @@ static void try_odm_power_optimization_and_revalidate( memset(merge, 0, MAX_PIPES * sizeof(bool)); *vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, new_vlevel, split, merge); context->bw_ctx.dml.vba.VoltageLevel = *vlevel; + } else { + for (i = 0; i < pipe_cnt; i++) + pipes[i].pipe.dest.odm_combine_policy = cur_policy[i]; } } @@ -1580,7 +1586,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc, } } - if (should_allow_odm_power_optimization(dc, context, vba, split, merge)) + if (should_apply_odm_power_optimization(dc, context, vba, split, merge)) try_odm_power_optimization_and_revalidate( dc, context, pipes, split, merge, vlevel, *pipe_cnt); @@ -2209,7 +2215,8 @@ bool dcn32_internal_validate_bw(struct dc *dc, int i; pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); - dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes); + if (!dc->config.enable_windowed_mpo_odm) + dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes); /* repopulate_pipes = 1 means the pipes were either split or merged. In this case * we have to re-calculate the DET allocation and run through DML once more to diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index c958ef37b78a..77a60aa9f27b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -427,22 +427,18 @@ struct pipe_ctx *resource_get_primary_dpp_pipe(const struct pipe_ctx *dpp_pipe); int resource_get_mpc_slice_index(const struct pipe_ctx *dpp_pipe); /* - * Get number of MPC "cuts" of the plane associated with the pipe. MPC slice - * count is equal to MPC splits + 1. For example if a plane is cut 3 times, it - * will have 4 pieces of slice. - * return - 0 if pipe is not used for a plane with MPCC combine. otherwise - * the number of MPC "cuts" for the plane. + * Get the number of MPC slices associated with the pipe. + * The function returns 0 if the pipe is not associated with an MPC combine + * pipe topology. */ -int resource_get_mpc_slice_count(const struct pipe_ctx *opp_head); +int resource_get_mpc_slice_count(const struct pipe_ctx *pipe); /* - * Get number of ODM "cuts" of the timing associated with the pipe. ODM slice - * count is equal to ODM splits + 1. For example if a timing is cut 3 times, it - * will have 4 pieces of slice. - * return - 0 if pipe is not used for ODM combine. otherwise - * the number of ODM "cuts" for the timing. + * Get the number of ODM slices associated with the pipe. + * The function returns 0 if the pipe is not associated with an ODM combine + * pipe topology. */ -int resource_get_odm_slice_count(const struct pipe_ctx *otg_master); +int resource_get_odm_slice_count(const struct pipe_ctx *pipe); /* Get the ODM slice index counting from 0 from left most slice */ int resource_get_odm_slice_index(const struct pipe_ctx *opp_head); diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c index c4d71e7f18af..6f10052caeef 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c @@ -1829,7 +1829,21 @@ int dcn32_populate_dml_pipes_from_context( dcn32_zero_pipe_dcc_fraction(pipes, pipe_cnt); DC_FP_END(); pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch; - pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal; + if (dc->config.enable_windowed_mpo_odm && + dc->debug.enable_single_display_2to1_odm_policy) { + switch (resource_get_odm_slice_count(pipe)) { + case 2: + pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1; + break; + case 4: + pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_4to1; + break; + default: + pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal; + } + } else { + pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal; + } pipes[pipe_cnt].pipe.src.gpuvm_min_page_size_kbytes = 256; // according to spreadsheet pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_19; From 93bafa32a6918154aa0caf9f66679a32c2431357 Mon Sep 17 00:00:00 2001 From: Prike Liang Date: Tue, 16 Jan 2024 19:10:45 +0800 Subject: [PATCH 114/311] drm/amdgpu: skip to program GFXDEC registers for suspend abort In the suspend abort cases, the gfx power rail doesn't turn off so some GFXDEC registers/CSB can't reset to default value and at this moment reinitialize GFXDEC/CSB will result in an unexpected error. So let skip those program sequence for the suspend abort case. Signed-off-by: Prike Liang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 ++ drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 8 ++++++++ 3 files changed, 12 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 3d8a48f46b01..6dce81a061ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1078,6 +1078,8 @@ struct amdgpu_device { bool in_s3; bool in_s4; bool in_s0ix; + /* indicate amdgpu suspension status */ + bool suspend_complete; enum pp_mp1_state mp1_state; struct amdgpu_doorbell_index doorbell_index; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 971acf01bea6..211501ea9169 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2476,6 +2476,7 @@ static int amdgpu_pmops_suspend(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); + adev->suspend_complete = false; if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; else if (amdgpu_acpi_is_s3_active(adev)) @@ -2490,6 +2491,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); + adev->suspend_complete = true; if (amdgpu_acpi_should_gpu_reset(adev)) return amdgpu_asic_reset(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 69c500910746..3bc6943365a4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3034,6 +3034,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev) gfx_v9_0_cp_gfx_enable(adev, true); + /* Now only limit the quirk on the APU gfx9 series and already + * confirmed that the APU gfx10/gfx11 needn't such update. + */ + if (adev->flags & AMD_IS_APU && + adev->in_s3 && !adev->suspend_complete) { + DRM_INFO(" Will skip the CSB packet resubmit\n"); + return 0; + } r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3); if (r) { DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r); From 6ef82ac664bb9568ca3956e0d9c9c478e25077ff Mon Sep 17 00:00:00 2001 From: Prike Liang Date: Wed, 17 Jan 2024 13:39:37 +0800 Subject: [PATCH 115/311] drm/amdgpu: reset gpu for s3 suspend abort case In the s3 suspend abort case some type of gfx9 power rail not turn off from FCH side and this will put the GPU in an unknown power status, so let's reset the gpu to a known good power state before reinitialize gpu device. Signed-off-by: Prike Liang Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/soc15.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 15033efec2ba..c64c01e2944a 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1298,10 +1298,32 @@ static int soc15_common_suspend(void *handle) return soc15_common_hw_fini(adev); } +static bool soc15_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg; + + sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); + + /* Will reset for the following suspend abort cases. + * 1) Only reset limit on APU side, dGPU hasn't checked yet. + * 2) S3 suspend abort and TOS already launched. + */ + if (adev->flags & AMD_IS_APU && adev->in_s3 && + !adev->suspend_complete && + sol_reg) + return true; + + return false; +} + static int soc15_common_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (soc15_need_reset_on_resume(adev)) { + dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n"); + soc15_asic_reset(adev); + } return soc15_common_hw_init(adev); } From 897925dcc5dfff5b3b23ba991a89fe3ebaca6ef8 Mon Sep 17 00:00:00 2001 From: Li Ma Date: Thu, 1 Feb 2024 19:31:06 +0800 Subject: [PATCH 116/311] drm/amdgpu: remove asymmetrical irq disabling in jpeg 4.0.5 suspend A supplement to commit: 615dd56ac5379f4239940be69139a33e79e59c67 There is an irq warning of jpeg during resume in s2idle process. No irq enabled in jpeg 4.0.5 resume. Fixes: 615dd56ac537 ("drm/amdgpu: remove asymmetrical irq disabling in vcn 4.0.5 suspend") Signed-off-by: Li Ma Acked-By: Saleemkhan Jamadar Reviewed-by: Yifan Zhang Reviewed-by: Veerabadhran Gopalakrishnan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c | 9 --------- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c | 10 ---------- 2 files changed, 19 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index bc38b90f8cf8..88ea58d5c4ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -674,14 +674,6 @@ static int jpeg_v4_0_set_powergating_state(void *handle, return ret; } -static int jpeg_v4_0_set_interrupt_state(struct amdgpu_device *adev, - struct amdgpu_irq_src *source, - unsigned type, - enum amdgpu_interrupt_state state) -{ - return 0; -} - static int jpeg_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source, unsigned int type, @@ -765,7 +757,6 @@ static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev) } static const struct amdgpu_irq_src_funcs jpeg_v4_0_irq_funcs = { - .set = jpeg_v4_0_set_interrupt_state, .process = jpeg_v4_0_process_interrupt, }; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c index 6ede85b28cc8..78b74daf4eeb 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c @@ -181,7 +181,6 @@ static int jpeg_v4_0_5_hw_fini(void *handle) RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS)) jpeg_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE); } - amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0); return 0; } @@ -516,14 +515,6 @@ static int jpeg_v4_0_5_set_powergating_state(void *handle, return ret; } -static int jpeg_v4_0_5_set_interrupt_state(struct amdgpu_device *adev, - struct amdgpu_irq_src *source, - unsigned type, - enum amdgpu_interrupt_state state) -{ - return 0; -} - static int jpeg_v4_0_5_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) @@ -603,7 +594,6 @@ static void jpeg_v4_0_5_set_dec_ring_funcs(struct amdgpu_device *adev) } static const struct amdgpu_irq_src_funcs jpeg_v4_0_5_irq_funcs = { - .set = jpeg_v4_0_5_set_interrupt_state, .process = jpeg_v4_0_5_process_interrupt, }; From 280df4996c2bfc0e340ae758ab6da35748853a7e Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Tue, 23 Jan 2024 12:20:06 -0500 Subject: [PATCH 117/311] drm/amd/display: Increase eval/entry delay for DCN35 [Why] To match firmware measurements and avoid hanging when accessing HW that's in idle. [How] Increase the delays to what we've measured. Reviewed-by: Ovidiu Bunea Acked-by: Hamza Mahfooz Signed-off-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index 761ec9891875..2142cee6cac2 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -780,8 +780,8 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_z10 = false, .ignore_pg = true, .psp_disabled_wa = true, - .ips2_eval_delay_us = 200, - .ips2_entry_delay_us = 400, + .ips2_eval_delay_us = 1650, + .ips2_entry_delay_us = 800, .static_screen_wait_frames = 2, }; From 2dcf82a8e8dc930655787797ef8a3692b527c7a9 Mon Sep 17 00:00:00 2001 From: "Stanley.Yang" Date: Mon, 5 Feb 2024 15:55:48 +0800 Subject: [PATCH 118/311] drm/amdgpu: Fix shared buff copy to user ta if invoke node buffer |-------- ta type ----------| |-------- ta id ----------| |-------- cmd id ----------| |------ shared buf len -----| |------ shared buffer ------| ta if invoke node buffer is as above, copy shared buffer data to correct location Signed-off-by: Stanley.Yang Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c index 468a67b302d4..ca5c86e5f7cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c @@ -362,7 +362,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size } } - if (copy_to_user((char *)buf, context->mem_context.shared_buf, shared_buf_len)) + if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len)) ret = -EFAULT; err_free_shared_buf: From e6a7df96facdcf5b1f71eb3ec26f2f9f6ad61e57 Mon Sep 17 00:00:00 2001 From: Fangzhi Zuo Date: Mon, 22 Jan 2024 13:43:46 -0500 Subject: [PATCH 119/311] drm/amd/display: Fix MST Null Ptr for RV The change try to fix below error specific to RV platform: BUG: kernel NULL pointer dereference, address: 0000000000000008 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 4 PID: 917 Comm: sway Not tainted 6.3.9-arch1-1 #1 124dc55df4f5272ccb409f39ef4872fc2b3376a2 Hardware name: LENOVO 20NKS01Y00/20NKS01Y00, BIOS R12ET61W(1.31 ) 07/28/2022 RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper] Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8> RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224 RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280 RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850 R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000 R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224 FS: 00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000010ddc6000 CR4: 00000000003506e0 Call Trace: ? __die+0x23/0x70 ? page_fault_oops+0x171/0x4e0 ? plist_add+0xbe/0x100 ? exc_page_fault+0x7c/0x180 ? asm_exc_page_fault+0x26/0x30 ? drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026] ? drm_dp_atomic_find_time_slots+0x28/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026] compute_mst_dsc_configs_for_link+0x2ff/0xa40 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] ? fill_plane_buffer_attributes+0x419/0x510 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] compute_mst_dsc_configs_for_state+0x1e1/0x250 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] amdgpu_dm_atomic_check+0xecd/0x1190 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] drm_atomic_check_only+0x5c5/0xa40 drm_mode_atomic_ioctl+0x76e/0xbc0 ? _copy_to_user+0x25/0x30 ? drm_ioctl+0x296/0x4b0 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10 drm_ioctl_kernel+0xcd/0x170 drm_ioctl+0x26d/0x4b0 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10 amdgpu_drm_ioctl+0x4e/0x90 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] __x64_sys_ioctl+0x94/0xd0 do_syscall_64+0x60/0x90 ? do_syscall_64+0x6c/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f4dad17f76f Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <89> c> RSP: 002b:00007ffd9ae859f0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 000055e255a55900 RCX: 00007f4dad17f76f RDX: 00007ffd9ae85a90 RSI: 00000000c03864bc RDI: 000000000000000b RBP: 00007ffd9ae85a90 R08: 0000000000000003 R09: 0000000000000003 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000c03864bc R13: 000000000000000b R14: 000055e255a7fc60 R15: 000055e255a01eb0 Modules linked in: rfcomm snd_seq_dummy snd_hrtimer snd_seq snd_seq_device ccm cmac algif_hash algif_skcipher af_alg joydev mousedev bnep > typec libphy k10temp ipmi_msghandler roles i2c_scmi acpi_cpufreq mac_hid nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_mas> CR2: 0000000000000008 ---[ end trace 0000000000000000 ]--- RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper] Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8> RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224 RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280 RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850 R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000 R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224 FS: 00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000010ddc6000 CR4: 00000000003506e0 With a second DP monitor connected, drm_atomic_state in dm atomic check sequence does not include the connector state for the old/existing/first DP monitor. In such case, dsc determination policy would hit a null ptr when it tries to iterate the old/existing stream that does not have a valid connector state attached to it. When that happens, dm atomic check should call drm_atomic_get_connector_state for a new connector state. Existing dm has already done that, except for RV due to it does not have official support of dsc where .num_dsc is not defined in dcn10 resource cap, that prevent from getting drm_atomic_get_connector_state called. So, skip dsc determination policy for ASICs that don't have DSC support. Cc: stable@vger.kernel.org # 6.1+ Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2314 Reviewed-by: Wayne Lin Acked-by: Hamza Mahfooz Signed-off-by: Fangzhi Zuo Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index d292f290cd6e..59d2eee72a32 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -10731,11 +10731,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; } - ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); - if (ret) { - DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); - ret = -EINVAL; - goto fail; + if (dc_resource_is_dsc_encoding_supported(dc)) { + ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); + if (ret) { + DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); + ret = -EINVAL; + goto fail; + } } ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars); From ca8179ba11f211cdcb6c12ddd83814eaec999738 Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Fri, 26 Jan 2024 16:47:20 -0500 Subject: [PATCH 120/311] drm/amd/display: Update phantom pipe enable / disable sequence Previously we would call apply_ctx_to_hw to enable and disable phantom pipes. However, apply_ctx_to_hw can potentially update non-phantom pipes as well which is undesired. Instead of calling apply_ctx_to_hw as a whole, call the relevant helpers for each phantom pipe when enabling / disabling which will avoid us modifying hardware state for non-phantom pipes unknowingly. The use case is for an FRL display where FRL_Update is requested by the display. In this case link_state_valid flag is cleared in a passive callback thread and should be handled in the next stream / link update. However, due to the call to apply_ctx_to_hw for the phantom pipes during a flip, the main pipes were modified outside of the desired sequence (driver does not handle link_state_valid = 0 on flips). Cc: stable@vger.kernel.org # 6.6+ Reviewed-by: Samson Tam Acked-by: Hamza Mahfooz Signed-off-by: Alvin Lee Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 4 +- .../amd/display/dc/hwss/dce110/dce110_hwseq.c | 4 +- .../amd/display/dc/hwss/dce110/dce110_hwseq.h | 4 + .../amd/display/dc/hwss/dcn20/dcn20_hwseq.c | 2 +- .../amd/display/dc/hwss/dcn20/dcn20_hwseq.h | 4 + .../amd/display/dc/hwss/dcn32/dcn32_hwseq.c | 74 +++++++++++++++++-- .../amd/display/dc/hwss/dcn32/dcn32_hwseq.h | 2 + .../amd/display/dc/hwss/dcn32/dcn32_init.c | 3 + .../drm/amd/display/dc/hwss/hw_sequencer.h | 1 + .../display/dc/hwss/hw_sequencer_private.h | 7 ++ 10 files changed, 93 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index aa7c02ba948e..2c424e435962 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3817,7 +3817,9 @@ static void commit_planes_for_stream(struct dc *dc, * programming has completed (we turn on phantom OTG in order * to complete the plane disable for phantom pipes). */ - dc->hwss.apply_ctx_to_hw(dc, context); + + if (dc->hwss.disable_phantom_streams) + dc->hwss.disable_phantom_streams(dc, context); } if (update_type != UPDATE_TYPE_FAST) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 2352428bcea3..01493c49bd7a 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1476,7 +1476,7 @@ static enum dc_status dce110_enable_stream_timing( return DC_OK; } -static enum dc_status apply_single_controller_ctx_to_hw( +enum dc_status dce110_apply_single_controller_ctx_to_hw( struct pipe_ctx *pipe_ctx, struct dc_state *context, struct dc *dc) @@ -2302,7 +2302,7 @@ enum dc_status dce110_apply_ctx_to_hw( if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe) continue; - status = apply_single_controller_ctx_to_hw( + status = dce110_apply_single_controller_ctx_to_hw( pipe_ctx, context, dc); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h index 08028a1779ae..ed3cc3648e8e 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h @@ -39,6 +39,10 @@ enum dc_status dce110_apply_ctx_to_hw( struct dc *dc, struct dc_state *context); +enum dc_status dce110_apply_single_controller_ctx_to_hw( + struct pipe_ctx *pipe_ctx, + struct dc_state *context, + struct dc *dc); void dce110_enable_stream(struct pipe_ctx *pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index 4853ecac53f9..931ac8ed7069 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -2561,7 +2561,7 @@ void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx) tg->funcs->setup_vertical_interrupt2(tg, start_line); } -static void dcn20_reset_back_end_for_pipe( +void dcn20_reset_back_end_for_pipe( struct dc *dc, struct pipe_ctx *pipe_ctx, struct dc_state *context) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h index b94c85340abf..d950b3e54ec2 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h @@ -84,6 +84,10 @@ enum dc_status dcn20_enable_stream_timing( void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx); void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx); void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx); +void dcn20_reset_back_end_for_pipe( + struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct dc_state *context); void dcn20_init_blank( struct dc *dc, struct timing_generator *tg); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c index 6c9299c7683d..aa36d7a56ca8 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c @@ -1474,9 +1474,44 @@ void dcn32_update_dsc_pg(struct dc *dc, } } +void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context) +{ + struct dce_hwseq *hws = dc->hwseq; + int i; + + for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) { + struct pipe_ctx *pipe_ctx_old = + &dc->current_state->res_ctx.pipe_ctx[i]; + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (!pipe_ctx_old->stream) + continue; + + if (dc_state_get_pipe_subvp_type(dc->current_state, pipe_ctx_old) != SUBVP_PHANTOM) + continue; + + if (pipe_ctx_old->top_pipe || pipe_ctx_old->prev_odm_pipe) + continue; + + if (!pipe_ctx->stream || pipe_need_reprogram(pipe_ctx_old, pipe_ctx) || + (pipe_ctx->stream && dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)) { + struct clock_source *old_clk = pipe_ctx_old->clock_source; + + if (hws->funcs.reset_back_end_for_pipe) + hws->funcs.reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state); + if (hws->funcs.enable_stream_gating) + hws->funcs.enable_stream_gating(dc, pipe_ctx_old); + if (old_clk) + old_clk->funcs->cs_power_down(old_clk); + } + } +} + void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context) { unsigned int i; + enum dc_status status = DC_OK; + struct dce_hwseq *hws = dc->hwseq; for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; @@ -1497,16 +1532,39 @@ void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context) } } for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *pipe_ctx_old = + &dc->current_state->res_ctx.pipe_ctx[i]; + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; - if (new_pipe->stream && dc_state_get_pipe_subvp_type(context, new_pipe) == SUBVP_PHANTOM) { - // If old context or new context has phantom pipes, apply - // the phantom timings now. We can't change the phantom - // pipe configuration safely without driver acquiring - // the DMCUB lock first. - dc->hwss.apply_ctx_to_hw(dc, context); - break; + if (pipe_ctx->stream == NULL) + continue; + + if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM) + continue; + + if (pipe_ctx->stream == pipe_ctx_old->stream && + pipe_ctx->stream->link->link_state_valid) { + continue; } + + if (pipe_ctx_old->stream && !pipe_need_reprogram(pipe_ctx_old, pipe_ctx)) + continue; + + if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe) + continue; + + if (hws->funcs.apply_single_controller_ctx_to_hw) + status = hws->funcs.apply_single_controller_ctx_to_hw( + pipe_ctx, + context, + dc); + + ASSERT(status == DC_OK); + +#ifdef CONFIG_DRM_AMD_DC_FP + if (hws->funcs.resync_fifo_dccg_dio) + hws->funcs.resync_fifo_dccg_dio(hws, dc, context); +#endif } } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h index cecf7f0f5671..069e20bc87c0 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h @@ -111,6 +111,8 @@ void dcn32_update_dsc_pg(struct dc *dc, void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context); +void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context); + void dcn32_init_blank( struct dc *dc, struct timing_generator *tg); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c index 427cfc8c24a4..e8ac94a005b8 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c @@ -109,6 +109,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .get_dcc_en_bits = dcn10_get_dcc_en_bits, .commit_subvp_config = dcn32_commit_subvp_config, .enable_phantom_streams = dcn32_enable_phantom_streams, + .disable_phantom_streams = dcn32_disable_phantom_streams, .subvp_pipe_control_lock = dcn32_subvp_pipe_control_lock, .update_visual_confirm_color = dcn10_update_visual_confirm_color, .subvp_pipe_control_lock_fast = dcn32_subvp_pipe_control_lock_fast, @@ -159,6 +160,8 @@ static const struct hwseq_private_funcs dcn32_private_funcs = { .set_pixels_per_cycle = dcn32_set_pixels_per_cycle, .resync_fifo_dccg_dio = dcn32_resync_fifo_dccg_dio, .is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy, + .apply_single_controller_ctx_to_hw = dce110_apply_single_controller_ctx_to_hw, + .reset_back_end_for_pipe = dcn20_reset_back_end_for_pipe, }; void dcn32_hw_sequencer_init_functions(struct dc *dc) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h index a54399383318..64ca7c66509b 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h @@ -379,6 +379,7 @@ struct hw_sequencer_funcs { struct dc_cursor_attributes *cursor_attr); void (*commit_subvp_config)(struct dc *dc, struct dc_state *context); void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context); + void (*disable_phantom_streams)(struct dc *dc, struct dc_state *context); void (*subvp_pipe_control_lock)(struct dc *dc, struct dc_state *context, bool lock, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h index 6137cf09aa54..b3c62a82cb1c 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h @@ -165,8 +165,15 @@ struct hwseq_private_funcs { void (*set_pixels_per_cycle)(struct pipe_ctx *pipe_ctx); void (*resync_fifo_dccg_dio)(struct dce_hwseq *hws, struct dc *dc, struct dc_state *context); + enum dc_status (*apply_single_controller_ctx_to_hw)( + struct pipe_ctx *pipe_ctx, + struct dc_state *context, + struct dc *dc); bool (*is_dp_dig_pixel_rate_div_policy)(struct pipe_ctx *pipe_ctx); #endif + void (*reset_back_end_for_pipe)(struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct dc_state *context); }; struct dce_hwseq { From 29c5da1a124671caa87c4a936c625432c16ad8ca Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Thu, 11 Jan 2024 14:25:27 -0700 Subject: [PATCH 121/311] drm/amd/display: Disable ODM by default for DCN35 Just ensure that ODM optimization is disabled by default. Acked-by: Hamza Mahfooz Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index 2142cee6cac2..1c3d89264ef7 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -2130,6 +2130,7 @@ static bool dcn35_resource_construct( dc->dml2_options.dcn_pipe_count = pool->base.pipe_count; dc->dml2_options.use_native_pstate_optimization = true; dc->dml2_options.use_native_soc_bb_construction = true; + dc->dml2_options.minimize_dispclk_using_odm = false; if (dc->config.EnableMinDispClkODM) dc->dml2_options.minimize_dispclk_using_odm = true; dc->dml2_options.enable_windowed_mpo_odm = dc->config.enable_windowed_mpo_odm; From 55173942a63668bdc1d61812c7c9e0406aefb5bf Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Wed, 31 Jan 2024 16:34:32 +0530 Subject: [PATCH 122/311] drm/amdgpu: Avoid fetching VRAM vendor info The present way to fetch VRAM vendor information turns out to be not reliable on GFX 9.4.3 dGPUs as well. Avoid using the data. Signed-off-by: Lijo Lazar Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 40a00ea0009f..e67a62db9e12 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1947,14 +1947,6 @@ static int gmc_v9_0_init_mem_ranges(struct amdgpu_device *adev) static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev) { - static const u32 regBIF_BIOS_SCRATCH_4 = 0x50; - u32 vram_info; - - /* Only for dGPU, vendor informaton is reliable */ - if (!amdgpu_sriov_vf(adev) && !(adev->flags & AMD_IS_APU)) { - vram_info = RREG32(regBIF_BIOS_SCRATCH_4); - adev->gmc.vram_vendor = vram_info & 0xF; - } adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM; adev->gmc.vram_width = 128 * 64; } From da48914e1fcdbf57f6b95d4552fcc088e6547ce4 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 2 Feb 2024 18:30:59 -0600 Subject: [PATCH 123/311] drm/amd/display: Clear phantom stream count and plane count When dc_state_destruct() was refactored the new phantom_stream_count and phantom_plane_count members weren't cleared. Fixes: 012a04b1d6af ("drm/amd/display: Refactor phantom resource allocation") Acked-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_state.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c index 88c6436b28b6..180ac47868c2 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c @@ -291,11 +291,14 @@ void dc_state_destruct(struct dc_state *state) dc_stream_release(state->phantom_streams[i]); state->phantom_streams[i] = NULL; } + state->phantom_stream_count = 0; for (i = 0; i < state->phantom_plane_count; i++) { dc_plane_state_release(state->phantom_planes[i]); state->phantom_planes[i] = NULL; } + state->phantom_plane_count = 0; + state->stream_mask = 0; memset(&state->res_ctx, 0, sizeof(state->res_ctx)); memset(&state->pp_display_cfg, 0, sizeof(state->pp_display_cfg)); From e63e35f0164c43fbc1adb481d6604f253b9f9667 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 5 Feb 2024 14:54:05 -0700 Subject: [PATCH 124/311] drm/amd/display: Increase frame-larger-than for all display_mode_vba files After a recent change in LLVM, allmodconfig (which has CONFIG_KCSAN=y and CONFIG_WERROR=y enabled) has a few new instances of -Wframe-larger-than for the mode support and system configuration functions: drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn20/display_mode_vba_20v2.c:3393:6: error: stack frame size (2144) exceeds limit (2048) in 'dml20v2_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than] 3393 | void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib) | ^ 1 error generated. drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn21/display_mode_vba_21.c:3520:6: error: stack frame size (2192) exceeds limit (2048) in 'dml21_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than] 3520 | void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib) | ^ 1 error generated. drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn20/display_mode_vba_20.c:3286:6: error: stack frame size (2128) exceeds limit (2048) in 'dml20_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than] 3286 | void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib) | ^ 1 error generated. Without the sanitizers enabled, there are no warnings. This was the catalyst for commit 6740ec97bcdb ("drm/amd/display: Increase frame warning limit with KASAN or KCSAN in dml2") and that same change was made to dml in commit 5b750b22530f ("drm/amd/display: Increase frame warning limit with KASAN or KCSAN in dml") but the frame_warn_flag variable was not applied to all files. Do so now to clear up the warnings and make all these files consistent. Cc: stable@vger.kernel.org Closes: https://github.com/ClangBuiltLinux/linux/issue/1990 Signed-off-by: Nathan Chancellor Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/Makefile | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 6042a5a6a44f..59ade76ffb18 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -72,11 +72,11 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags) From 58fca355ad37dcb5f785d9095db5f748b79c5dc2 Mon Sep 17 00:00:00 2001 From: Srinivasan Shanmugam Date: Wed, 7 Feb 2024 10:20:57 +0530 Subject: [PATCH 125/311] drm/amd/display: Implement bounds check for stream encoder creation in DCN301 'stream_enc_regs' array is an array of dcn10_stream_enc_registers structures. The array is initialized with four elements, corresponding to the four calls to stream_enc_regs() in the array initializer. This means that valid indices for this array are 0, 1, 2, and 3. The error message 'stream_enc_regs' 4 <= 5 below, is indicating that there is an attempt to access this array with an index of 5, which is out of bounds. This could lead to undefined behavior Here, eng_id is used as an index to access the stream_enc_regs array. If eng_id is 5, this would result in an out-of-bounds access on the stream_enc_regs array. Thus fixing Buffer overflow error in dcn301_stream_encoder_create reported by Smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/resource/dcn301/dcn301_resource.c:1011 dcn301_stream_encoder_create() error: buffer overflow 'stream_enc_regs' 4 <= 5 Fixes: 3a83e4e64bb1 ("drm/amd/display: Add dcn3.01 support to DC (v2)") Cc: Roman Li Cc: Rodrigo Siqueira Cc: Aurabindo Pillai Signed-off-by: Srinivasan Shanmugam Reviewed-by: Roman Li Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c index 511ff6b5b985..7538b548c572 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c @@ -999,7 +999,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id vpg = dcn301_vpg_create(ctx, vpg_inst); afmt = dcn301_afmt_create(ctx, afmt_inst); - if (!enc1 || !vpg || !afmt) { + if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) { kfree(enc1); kfree(vpg); kfree(afmt); From 534c8a5b9d5d41d30cdcac93cfa1bca5e17be009 Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Fri, 8 Dec 2023 13:48:22 +0530 Subject: [PATCH 126/311] drm/amdgpu: Fix HDP flush for VFs on nbio v7.9 HDP flush remapping is not done for VFs. Keep the original offsets in VF environment. Signed-off-by: Lijo Lazar Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c index e90f33780803..b4723d68eab0 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c @@ -431,6 +431,12 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev) u32 inst_mask; int i; + if (amdgpu_sriov_vf(adev)) + adev->rmmio_remap.reg_offset = + SOC15_REG_OFFSET( + NBIO, 0, + regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) + << 2; WREG32_SOC15(NBIO, 0, regXCC_DOORBELL_FENCE, 0xff & ~(adev->gfx.xcc_mask)); From 4054705215ad7e6dd8e4e6ff27c39abd7667f700 Mon Sep 17 00:00:00 2001 From: Francis Pravin Date: Wed, 7 Feb 2024 05:04:17 +0530 Subject: [PATCH 127/311] nvme: use ns->head->pi_size instead of t10_pi_tuple structure size Currently kernel supports 8 byte and 16 byte protection information. So, use ns->head->pi_size instead of sizeof(struct t10_pi_tuple). Signed-off-by: Francis Pravin Signed-off-by: Sathyavathi M Signed-off-by: Keith Busch --- drivers/nvme/host/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 18f5c1be5d67..3dfd5ae99ae0 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -228,7 +228,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) length = (io.nblocks + 1) << ns->head->lba_shift; if ((io.control & NVME_RW_PRINFO_PRACT) && - ns->head->ms == sizeof(struct t10_pi_tuple)) { + (ns->head->ms == ns->head->pi_size)) { /* * Protection information is stripped/inserted by the * controller. From a12bc36032a2f7917068f9ce9eb26d869e54b31a Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 2 Feb 2024 16:13:17 +0800 Subject: [PATCH 128/311] ksmbd: Add kernel-doc for ksmbd_extract_sharename() function The ksmbd_extract_sharename() function lacked a complete kernel-doc comment. This patch adds parameter descriptions and detailed function behavior to improve code readability and maintainability. Signed-off-by: Yang Li Acked-by: Randy Dunlap Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/misc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/smb/server/misc.c b/fs/smb/server/misc.c index 9e8afaa686e3..1a5faa6f6e7b 100644 --- a/fs/smb/server/misc.c +++ b/fs/smb/server/misc.c @@ -261,6 +261,7 @@ out_ascii: /** * ksmbd_extract_sharename() - get share name from tree connect request + * @um: pointer to a unicode_map structure for character encoding handling * @treename: buffer containing tree name and share name * * Return: share name on success, otherwise error From 108a020c64434fed4b69762879d78cd24088b4c7 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Mon, 5 Feb 2024 14:19:16 +0300 Subject: [PATCH 129/311] ksmbd: free aux buffer if ksmbd_iov_pin_rsp_read fails ksmbd_iov_pin_rsp_read() doesn't free the provided aux buffer if it fails. Seems to be the caller's responsibility to clear the buffer in error case. Found by Linux Verification Center (linuxtesting.org). Fixes: e2b76ab8b5c9 ("ksmbd: add support for read compound") Cc: stable@vger.kernel.org Signed-off-by: Fedor Pchelkin Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index ba7a72a6a4f4..0c97d3c86072 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -6173,8 +6173,10 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); - if (err) + if (err) { + kvfree(aux_payload_buf); goto out; + } kvfree(rpc_resp); } else { err = ksmbd_iov_pin_rsp(work, (void *)rsp, @@ -6384,8 +6386,10 @@ int smb2_read(struct ksmbd_work *work) err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); - if (err) + if (err) { + kvfree(aux_payload_buf); goto out; + } ksmbd_fd_put(work, fp); return 0; From e656c7a9e59607d1672d85ffa9a89031876ffe67 Mon Sep 17 00:00:00 2001 From: Prakash Sangappa Date: Tue, 23 Jan 2024 12:04:42 -0800 Subject: [PATCH 130/311] mm: hugetlb pages should not be reserved by shmat() if SHM_NORESERVE For shared memory of type SHM_HUGETLB, hugetlb pages are reserved in shmget() call. If SHM_NORESERVE flags is specified then the hugetlb pages are not reserved. However when the shared memory is attached with the shmat() call the hugetlb pages are getting reserved incorrectly for SHM_HUGETLB shared memory created with SHM_NORESERVE which is a bug. ------------------------------- Following test shows the issue. $cat shmhtb.c int main() { int shmflags = 0660 | IPC_CREAT | SHM_HUGETLB | SHM_NORESERVE; int shmid; shmid = shmget(SKEY, SHMSZ, shmflags); if (shmid < 0) { printf("shmat: shmget() failed, %d\n", errno); return 1; } printf("After shmget()\n"); system("cat /proc/meminfo | grep -i hugepages_"); shmat(shmid, NULL, 0); printf("\nAfter shmat()\n"); system("cat /proc/meminfo | grep -i hugepages_"); shmctl(shmid, IPC_RMID, NULL); return 0; } #sysctl -w vm.nr_hugepages=20 #./shmhtb After shmget() HugePages_Total: 20 HugePages_Free: 20 HugePages_Rsvd: 0 HugePages_Surp: 0 After shmat() HugePages_Total: 20 HugePages_Free: 20 HugePages_Rsvd: 5 <-- HugePages_Surp: 0 -------------------------------- Fix is to ensure that hugetlb pages are not reserved for SHM_HUGETLB shared memory in the shmat() call. Link: https://lkml.kernel.org/r/1706040282-12388-1-git-send-email-prakash.sangappa@oracle.com Signed-off-by: Prakash Sangappa Acked-by: Muchun Song Cc: Signed-off-by: Andrew Morton --- fs/hugetlbfs/inode.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 671664fed307..ee13c2ca8ad2 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -100,6 +100,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); + vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has @@ -141,10 +142,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); ret = -ENOMEM; + + vm_flags = vma->vm_flags; + /* + * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip + * reserving here. Note: only for SHM hugetlbfs file, the inode + * flag S_PRIVATE is set. + */ + if (inode->i_flags & S_PRIVATE) + vm_flags |= VM_NORESERVE; + if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, - vma->vm_flags)) + vm_flags)) goto out; ret = 0; From daa694e4137571b4ebec330f9a9b4d54aa8b8089 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Jan 2024 16:50:50 +0100 Subject: [PATCH 131/311] getrusage: move thread_group_cputime_adjusted() outside of lock_task_sighand() Patch series "getrusage: use sig->stats_lock", v2. This patch (of 2): thread_group_cputime() does its own locking, we can safely shift thread_group_cputime_adjusted() which does another for_each_thread loop outside of ->siglock protected section. This is also preparation for the next patch which changes getrusage() to use stats_lock instead of siglock, thread_group_cputime() takes the same lock. With the current implementation recursive read_seqbegin_or_lock() is fine, thread_group_cputime() can't enter the slow mode if the caller holds stats_lock, yet this looks more safe and better performance-wise. Link: https://lkml.kernel.org/r/20240122155023.GA26169@redhat.com Link: https://lkml.kernel.org/r/20240122155050.GA26205@redhat.com Signed-off-by: Oleg Nesterov Reported-by: Dylan Hatch Tested-by: Dylan Hatch Cc: Eric W. Biederman Cc: Signed-off-by: Andrew Morton --- kernel/sys.c | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/kernel/sys.c b/kernel/sys.c index e219fcfa112d..70ad06ad852e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1785,17 +1785,19 @@ void getrusage(struct task_struct *p, int who, struct rusage *r) struct task_struct *t; unsigned long flags; u64 tgutime, tgstime, utime, stime; - unsigned long maxrss = 0; + unsigned long maxrss; + struct mm_struct *mm; struct signal_struct *sig = p->signal; - memset((char *)r, 0, sizeof (*r)); + memset(r, 0, sizeof(*r)); utime = stime = 0; + maxrss = 0; if (who == RUSAGE_THREAD) { task_cputime_adjusted(current, &utime, &stime); accumulate_thread_rusage(p, r); maxrss = sig->maxrss; - goto out; + goto out_thread; } if (!lock_task_sighand(p, &flags)) @@ -1819,9 +1821,6 @@ void getrusage(struct task_struct *p, int who, struct rusage *r) fallthrough; case RUSAGE_SELF: - thread_group_cputime_adjusted(p, &tgutime, &tgstime); - utime += tgutime; - stime += tgstime; r->ru_nvcsw += sig->nvcsw; r->ru_nivcsw += sig->nivcsw; r->ru_minflt += sig->min_flt; @@ -1839,19 +1838,24 @@ void getrusage(struct task_struct *p, int who, struct rusage *r) } unlock_task_sighand(p, &flags); -out: + if (who == RUSAGE_CHILDREN) + goto out_children; + + thread_group_cputime_adjusted(p, &tgutime, &tgstime); + utime += tgutime; + stime += tgstime; + +out_thread: + mm = get_task_mm(p); + if (mm) { + setmax_mm_hiwater_rss(&maxrss, mm); + mmput(mm); + } + +out_children: + r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ r->ru_utime = ns_to_kernel_old_timeval(utime); r->ru_stime = ns_to_kernel_old_timeval(stime); - - if (who != RUSAGE_CHILDREN) { - struct mm_struct *mm = get_task_mm(p); - - if (mm) { - setmax_mm_hiwater_rss(&maxrss, mm); - mmput(mm); - } - } - r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ } SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) From f7ec1cd5cc7ef3ad964b677ba82b8b77f1c93009 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Jan 2024 16:50:53 +0100 Subject: [PATCH 132/311] getrusage: use sig->stats_lock rather than lock_task_sighand() lock_task_sighand() can trigger a hard lockup. If NR_CPUS threads call getrusage() at the same time and the process has NR_THREADS, spin_lock_irq will spin with irqs disabled O(NR_CPUS * NR_THREADS) time. Change getrusage() to use sig->stats_lock, it was specifically designed for this type of use. This way it runs lockless in the likely case. TODO: - Change do_task_stat() to use sig->stats_lock too, then we can remove spin_lock_irq(siglock) in wait_task_zombie(). - Turn sig->stats_lock into seqcount_rwlock_t, this way the readers in the slow mode won't exclude each other. See https://lore.kernel.org/all/20230913154907.GA26210@redhat.com/ - stats_lock has to disable irqs because ->siglock can be taken in irq context, it would be very nice to change __exit_signal() to avoid the siglock->stats_lock dependency. Link: https://lkml.kernel.org/r/20240122155053.GA26214@redhat.com Signed-off-by: Oleg Nesterov Reported-by: Dylan Hatch Tested-by: Dylan Hatch Cc: Eric W. Biederman Cc: Signed-off-by: Andrew Morton --- kernel/sys.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/kernel/sys.c b/kernel/sys.c index 70ad06ad852e..f8e543f1e38a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1788,7 +1788,9 @@ void getrusage(struct task_struct *p, int who, struct rusage *r) unsigned long maxrss; struct mm_struct *mm; struct signal_struct *sig = p->signal; + unsigned int seq = 0; +retry: memset(r, 0, sizeof(*r)); utime = stime = 0; maxrss = 0; @@ -1800,8 +1802,7 @@ void getrusage(struct task_struct *p, int who, struct rusage *r) goto out_thread; } - if (!lock_task_sighand(p, &flags)) - return; + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); switch (who) { case RUSAGE_BOTH: @@ -1829,14 +1830,23 @@ void getrusage(struct task_struct *p, int who, struct rusage *r) r->ru_oublock += sig->oublock; if (maxrss < sig->maxrss) maxrss = sig->maxrss; + + rcu_read_lock(); __for_each_thread(sig, t) accumulate_thread_rusage(t, r); + rcu_read_unlock(); + break; default: BUG(); } - unlock_task_sighand(p, &flags); + + if (need_seqretry(&sig->stats_lock, seq)) { + seq = 1; + goto retry; + } + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); if (who == RUSAGE_CHILDREN) goto out_children; From 60f92acb60a989b14e4b744501a0df0f82ef30a3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 23 Jan 2024 16:33:55 +0100 Subject: [PATCH 133/311] fs/proc: do_task_stat: move thread_group_cputime_adjusted() outside of lock_task_sighand() Patch series "fs/proc: do_task_stat: use sig->stats_". do_task_stat() has the same problem as getrusage() had before "getrusage: use sig->stats_lock rather than lock_task_sighand()": a hard lockup. If NR_CPUS threads call lock_task_sighand() at the same time and the process has NR_THREADS, spin_lock_irq will spin with irqs disabled O(NR_CPUS * NR_THREADS) time. This patch (of 3): thread_group_cputime() does its own locking, we can safely shift thread_group_cputime_adjusted() which does another for_each_thread loop outside of ->siglock protected section. Not only this removes for_each_thread() from the critical section with irqs disabled, this removes another case when stats_lock is taken with siglock held. We want to remove this dependency, then we can change the users of stats_lock to not disable irqs. Link: https://lkml.kernel.org/r/20240123153313.GA21832@redhat.com Link: https://lkml.kernel.org/r/20240123153355.GA21854@redhat.com Signed-off-by: Oleg Nesterov Signed-off-by: Dylan Hatch Cc: Eric W. Biederman Cc: Signed-off-by: Andrew Morton --- fs/proc/array.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/proc/array.c b/fs/proc/array.c index ff08a8957552..45ba91863808 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -511,7 +511,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = utime = stime = 0; + cutime = cstime = 0; cgtime = gtime = 0; if (lock_task_sighand(task, &flags)) { @@ -546,7 +546,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, min_flt += sig->min_flt; maj_flt += sig->maj_flt; - thread_group_cputime_adjusted(task, &utime, &stime); gtime += sig->gtime; if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) @@ -562,10 +561,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, if (permitted && (!whole || num_threads < 2)) wchan = !task_is_running(task); - if (!whole) { + + if (whole) { + thread_group_cputime_adjusted(task, &utime, &stime); + } else { + task_cputime_adjusted(task, &utime, &stime); min_flt = task->min_flt; maj_flt = task->maj_flt; - task_cputime_adjusted(task, &utime, &stime); gtime = task_gtime(task); } From 7601df8031fd67310af891897ef6cc0df4209305 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 23 Jan 2024 16:33:57 +0100 Subject: [PATCH 134/311] fs/proc: do_task_stat: use sig->stats_lock to gather the threads/children stats lock_task_sighand() can trigger a hard lockup. If NR_CPUS threads call do_task_stat() at the same time and the process has NR_THREADS, it will spin with irqs disabled O(NR_CPUS * NR_THREADS) time. Change do_task_stat() to use sig->stats_lock to gather the statistics outside of ->siglock protected section, in the likely case this code will run lockless. Link: https://lkml.kernel.org/r/20240123153357.GA21857@redhat.com Signed-off-by: Oleg Nesterov Signed-off-by: Dylan Hatch Cc: Eric W. Biederman Cc: Signed-off-by: Andrew Morton --- fs/proc/array.c | 58 +++++++++++++++++++++++++++---------------------- 1 file changed, 32 insertions(+), 26 deletions(-) diff --git a/fs/proc/array.c b/fs/proc/array.c index 45ba91863808..34a47fb0c57f 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -477,13 +477,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, int permitted; struct mm_struct *mm; unsigned long long start_time; - unsigned long cmin_flt = 0, cmaj_flt = 0; - unsigned long min_flt = 0, maj_flt = 0; - u64 cutime, cstime, utime, stime; - u64 cgtime, gtime; + unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt; + u64 cutime, cstime, cgtime, utime, stime, gtime; unsigned long rsslim = 0; unsigned long flags; int exit_code = task->exit_code; + struct signal_struct *sig = task->signal; + unsigned int seq = 1; state = *get_task_state(task); vsize = eip = esp = 0; @@ -511,12 +511,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = 0; - cgtime = gtime = 0; if (lock_task_sighand(task, &flags)) { - struct signal_struct *sig = task->signal; - if (sig->tty) { struct pid *pgrp = tty_get_pgrp(sig->tty); tty_pgrp = pid_nr_ns(pgrp, ns); @@ -527,27 +523,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, num_threads = get_nr_threads(task); collect_sigign_sigcatch(task, &sigign, &sigcatch); - cmin_flt = sig->cmin_flt; - cmaj_flt = sig->cmaj_flt; - cutime = sig->cutime; - cstime = sig->cstime; - cgtime = sig->cgtime; rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); - /* add up live thread stats at the group level */ if (whole) { - struct task_struct *t; - - __for_each_thread(sig, t) { - min_flt += t->min_flt; - maj_flt += t->maj_flt; - gtime += task_gtime(t); - } - - min_flt += sig->min_flt; - maj_flt += sig->maj_flt; - gtime += sig->gtime; - if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) exit_code = sig->group_exit_code; } @@ -562,6 +540,34 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, if (permitted && (!whole || num_threads < 2)) wchan = !task_is_running(task); + do { + seq++; /* 2 on the 1st/lockless path, otherwise odd */ + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); + + cmin_flt = sig->cmin_flt; + cmaj_flt = sig->cmaj_flt; + cutime = sig->cutime; + cstime = sig->cstime; + cgtime = sig->cgtime; + + if (whole) { + struct task_struct *t; + + min_flt = sig->min_flt; + maj_flt = sig->maj_flt; + gtime = sig->gtime; + + rcu_read_lock(); + __for_each_thread(sig, t) { + min_flt += t->min_flt; + maj_flt += t->maj_flt; + gtime += task_gtime(t); + } + rcu_read_unlock(); + } + } while (need_seqretry(&sig->stats_lock, seq)); + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); + if (whole) { thread_group_cputime_adjusted(task, &utime, &stime); } else { From c1be35a16b2f1fe21f4f26f9de030ad6eaaf6a25 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 23 Jan 2024 16:34:00 +0100 Subject: [PATCH 135/311] exit: wait_task_zombie: kill the no longer necessary spin_lock_irq(siglock) After the recent changes nobody use siglock to read the values protected by stats_lock, we can kill spin_lock_irq(¤t->sighand->siglock) and update the comment. With this patch only __exit_signal() and thread_group_start_cputime() take stats_lock under siglock. Link: https://lkml.kernel.org/r/20240123153359.GA21866@redhat.com Signed-off-by: Oleg Nesterov Signed-off-by: Dylan Hatch Cc: Eric W. Biederman Cc: Signed-off-by: Andrew Morton --- kernel/exit.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 3988a02efaef..dfb963d2f862 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1127,17 +1127,14 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) * and nobody can change them. * * psig->stats_lock also protects us from our sub-threads - * which can reap other children at the same time. Until - * we change k_getrusage()-like users to rely on this lock - * we have to take ->siglock as well. + * which can reap other children at the same time. * * We use thread_group_cputime_adjusted() to get times for * the thread group, which consolidates times for all threads * in the group including the group leader. */ thread_group_cputime_adjusted(p, &tgutime, &tgstime); - spin_lock_irq(¤t->sighand->siglock); - write_seqlock(&psig->stats_lock); + write_seqlock_irq(&psig->stats_lock); psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; @@ -1160,8 +1157,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) psig->cmaxrss = maxrss; task_io_accounting_add(&psig->ioac, &p->ioac); task_io_accounting_add(&psig->ioac, &sig->ioac); - write_sequnlock(&psig->stats_lock); - spin_unlock_irq(¤t->sighand->siglock); + write_sequnlock_irq(&psig->stats_lock); } if (wo->wo_rusage) From 56ae10cf628b02279980d17439c6241a643959c2 Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Tue, 23 Jan 2024 14:17:55 +0000 Subject: [PATCH 136/311] mm/userfaultfd: UFFDIO_MOVE implementation should use ptep_get() Commit c33c794828f2 ("mm: ptep_get() conversion") converted all (non-arch) call sites to use ptep_get() instead of doing a direct dereference of the pte. Full rationale can be found in that commit's log. Since then, UFFDIO_MOVE has been implemented which does 7 direct pte dereferences. Let's fix those up to use ptep_get(). I've asserted in the past that there is no reliable automated mechanism to catch these; I'm relying on a combination of Coccinelle (which throws up a lot of false positives) and some compiler magic to force a compiler error on dereference. But given the frequency with which new issues are coming up, I'll add it to my todo list to try to find an automated solution. Link: https://lkml.kernel.org/r/20240123141755.3836179-1-ryan.roberts@arm.com Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI") Signed-off-by: Ryan Roberts Reviewed-by: Suren Baghdasaryan Cc: Andrea Arcangeli Cc: David Hildenbrand Signed-off-by: Andrew Morton --- mm/userfaultfd.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 75fcf1f783bc..7cf7d4384259 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -902,8 +902,8 @@ static int move_present_pte(struct mm_struct *mm, double_pt_lock(dst_ptl, src_ptl); - if (!pte_same(*src_pte, orig_src_pte) || - !pte_same(*dst_pte, orig_dst_pte)) { + if (!pte_same(ptep_get(src_pte), orig_src_pte) || + !pte_same(ptep_get(dst_pte), orig_dst_pte)) { err = -EAGAIN; goto out; } @@ -946,8 +946,8 @@ static int move_swap_pte(struct mm_struct *mm, double_pt_lock(dst_ptl, src_ptl); - if (!pte_same(*src_pte, orig_src_pte) || - !pte_same(*dst_pte, orig_dst_pte)) { + if (!pte_same(ptep_get(src_pte), orig_src_pte) || + !pte_same(ptep_get(dst_pte), orig_dst_pte)) { double_pt_unlock(dst_ptl, src_ptl); return -EAGAIN; } @@ -1016,7 +1016,7 @@ retry: } spin_lock(dst_ptl); - orig_dst_pte = *dst_pte; + orig_dst_pte = ptep_get(dst_pte); spin_unlock(dst_ptl); if (!pte_none(orig_dst_pte)) { err = -EEXIST; @@ -1024,7 +1024,7 @@ retry: } spin_lock(src_ptl); - orig_src_pte = *src_pte; + orig_src_pte = ptep_get(src_pte); spin_unlock(src_ptl); if (pte_none(orig_src_pte)) { if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) @@ -1054,7 +1054,7 @@ retry: * page isn't freed under us */ spin_lock(src_ptl); - if (!pte_same(orig_src_pte, *src_pte)) { + if (!pte_same(orig_src_pte, ptep_get(src_pte))) { spin_unlock(src_ptl); err = -EAGAIN; goto out; From 67b8bcbaed4777871bb0dcc888fb02a614a98ab1 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Wed, 24 Jan 2024 21:19:36 +0900 Subject: [PATCH 137/311] nilfs2: fix data corruption in dsync block recovery for small block sizes The helper function nilfs_recovery_copy_block() of nilfs_recovery_dsync_blocks(), which recovers data from logs created by data sync writes during a mount after an unclean shutdown, incorrectly calculates the on-page offset when copying repair data to the file's page cache. In environments where the block size is smaller than the page size, this flaw can cause data corruption and leak uninitialized memory bytes during the recovery process. Fix these issues by correcting this byte offset calculation on the page. Link: https://lkml.kernel.org/r/20240124121936.10575-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/recovery.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 0955b657938f..a9b8d77c8c1d 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs, static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, struct nilfs_recovery_block *rb, - struct page *page) + loff_t pos, struct page *page) { struct buffer_head *bh_org; + size_t from = pos & ~PAGE_MASK; void *kaddr; bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize); @@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, return -EIO; kaddr = kmap_atomic(page); - memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size); + memcpy(kaddr + from, bh_org->b_data, bh_org->b_size); kunmap_atomic(kaddr); brelse(bh_org); return 0; @@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_inode; } - err = nilfs_recovery_copy_block(nilfs, rb, page); + err = nilfs_recovery_copy_block(nilfs, rb, pos, page); if (unlikely(err)) goto failed_page; From 9cee7e8ef3e31ca25b40ca52b8585dc6935deff2 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Wed, 24 Jan 2024 10:00:22 +0000 Subject: [PATCH 138/311] mm: memcg: optimize parent iteration in memcg_rstat_updated() In memcg_rstat_updated(), we iterate the memcg being updated and its parents to update memcg->vmstats_percpu->stats_updates in the fast path (i.e. no atomic updates). According to my math, this is 3 memory loads (and potentially 3 cache misses) per memcg: - Load the address of memcg->vmstats_percpu. - Load vmstats_percpu->stats_updates (based on some percpu calculation). - Load the address of the parent memcg. Avoid most of the cache misses by caching a pointer from each struct memcg_vmstats_percpu to its parent on the corresponding CPU. In this case, for the first memcg we have 2 memory loads (same as above): - Load the address of memcg->vmstats_percpu. - Load vmstats_percpu->stats_updates (based on some percpu calculation). Then for each additional memcg, we need a single load to get the parent's stats_updates directly. This reduces the number of loads from O(3N) to O(2+N) -- where N is the number of memcgs we need to iterate. Additionally, stash a pointer to memcg->vmstats in each struct memcg_vmstats_percpu such that we can access the atomic counter that all CPUs fold into, memcg->vmstats->stats_updates. memcg_should_flush_stats() is changed to memcg_vmstats_needs_flush() to accept a struct memcg_vmstats pointer accordingly. In struct memcg_vmstats_percpu, make sure both pointers together with stats_updates live on the same cacheline. Finally, update mem_cgroup_alloc() to take in a parent pointer and initialize the new cache pointers on each CPU. The percpu loop in mem_cgroup_alloc() may look concerning, but there are multiple similar loops in the cgroup creation path (e.g. cgroup_rstat_init()), most of which are hidden within alloc_percpu(). According to Oliver's testing [1], this fixes multiple 30-38% regressions in vm-scalability, will-it-scale-tlb_flush2, and will-it-scale-fallocate1. This comes at a cost of 2 more pointers per CPU (<2KB on a machine with 128 CPUs). [1] https://lore.kernel.org/lkml/ZbDJsfsZt2ITyo61@xsang-OptiPlex-9020/ [yosryahmed@google.com: fix struct memcg_vmstats_percpu size and alignment] Link: https://lkml.kernel.org/r/20240203044612.1234216-1-yosryahmed@google.com Link: https://lkml.kernel.org/r/20240124100023.660032-1-yosryahmed@google.com Signed-off-by: Yosry Ahmed Fixes: 8d59d2214c23 ("mm: memcg: make stats flushing threshold per-memcg") Tested-by: kernel test robot Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202401221624.cb53a8ca-oliver.sang@intel.com Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Roman Gushchin Cc: Greg Thelen Signed-off-by: Andrew Morton --- mm/memcontrol.c | 56 ++++++++++++++++++++++++++++++------------------- 1 file changed, 35 insertions(+), 21 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 46d8d02114cf..1ed40f9d3a27 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -621,6 +621,15 @@ static inline int memcg_events_index(enum vm_event_item idx) } struct memcg_vmstats_percpu { + /* Stats updates since the last flush */ + unsigned int stats_updates; + + /* Cached pointers for fast iteration in memcg_rstat_updated() */ + struct memcg_vmstats_percpu *parent; + struct memcg_vmstats *vmstats; + + /* The above should fit a single cacheline for memcg_rstat_updated() */ + /* Local (CPU and cgroup) page state & events */ long state[MEMCG_NR_STAT]; unsigned long events[NR_MEMCG_EVENTS]; @@ -632,10 +641,7 @@ struct memcg_vmstats_percpu { /* Cgroup1: threshold notifications & softlimit tree updates */ unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; - - /* Stats updates since the last flush */ - unsigned int stats_updates; -}; +} ____cacheline_aligned; struct memcg_vmstats { /* Aggregated (CPU and subtree) page state & events */ @@ -698,36 +704,35 @@ static void memcg_stats_unlock(void) } -static bool memcg_should_flush_stats(struct mem_cgroup *memcg) +static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats) { - return atomic64_read(&memcg->vmstats->stats_updates) > + return atomic64_read(&vmstats->stats_updates) > MEMCG_CHARGE_BATCH * num_online_cpus(); } static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) { + struct memcg_vmstats_percpu *statc; int cpu = smp_processor_id(); - unsigned int x; if (!val) return; cgroup_rstat_updated(memcg->css.cgroup, cpu); - - for (; memcg; memcg = parent_mem_cgroup(memcg)) { - x = __this_cpu_add_return(memcg->vmstats_percpu->stats_updates, - abs(val)); - - if (x < MEMCG_CHARGE_BATCH) + statc = this_cpu_ptr(memcg->vmstats_percpu); + for (; statc; statc = statc->parent) { + statc->stats_updates += abs(val); + if (statc->stats_updates < MEMCG_CHARGE_BATCH) continue; /* * If @memcg is already flush-able, increasing stats_updates is * redundant. Avoid the overhead of the atomic update. */ - if (!memcg_should_flush_stats(memcg)) - atomic64_add(x, &memcg->vmstats->stats_updates); - __this_cpu_write(memcg->vmstats_percpu->stats_updates, 0); + if (!memcg_vmstats_needs_flush(statc->vmstats)) + atomic64_add(statc->stats_updates, + &statc->vmstats->stats_updates); + statc->stats_updates = 0; } } @@ -756,7 +761,7 @@ void mem_cgroup_flush_stats(struct mem_cgroup *memcg) if (!memcg) memcg = root_mem_cgroup; - if (memcg_should_flush_stats(memcg)) + if (memcg_vmstats_needs_flush(memcg->vmstats)) do_flush_stats(memcg); } @@ -770,7 +775,7 @@ void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) static void flush_memcg_stats_dwork(struct work_struct *w) { /* - * Deliberately ignore memcg_should_flush_stats() here so that flushing + * Deliberately ignore memcg_vmstats_needs_flush() here so that flushing * in latency-sensitive paths is as cheap as possible. */ do_flush_stats(root_mem_cgroup); @@ -5477,10 +5482,11 @@ static void mem_cgroup_free(struct mem_cgroup *memcg) __mem_cgroup_free(memcg); } -static struct mem_cgroup *mem_cgroup_alloc(void) +static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent) { + struct memcg_vmstats_percpu *statc, *pstatc; struct mem_cgroup *memcg; - int node; + int node, cpu; int __maybe_unused i; long error = -ENOMEM; @@ -5504,6 +5510,14 @@ static struct mem_cgroup *mem_cgroup_alloc(void) if (!memcg->vmstats_percpu) goto fail; + for_each_possible_cpu(cpu) { + if (parent) + pstatc = per_cpu_ptr(parent->vmstats_percpu, cpu); + statc = per_cpu_ptr(memcg->vmstats_percpu, cpu); + statc->parent = parent ? pstatc : NULL; + statc->vmstats = memcg->vmstats; + } + for_each_node(node) if (alloc_mem_cgroup_per_node_info(memcg, node)) goto fail; @@ -5549,7 +5563,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) struct mem_cgroup *memcg, *old_memcg; old_memcg = set_active_memcg(parent); - memcg = mem_cgroup_alloc(); + memcg = mem_cgroup_alloc(parent); set_active_memcg(old_memcg); if (IS_ERR(memcg)) return ERR_CAST(memcg); From 2fde9e7f9e6dc38e1d7091b9705c22be945c8697 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Wed, 24 Jan 2024 16:40:14 +0800 Subject: [PATCH 139/311] mm/memory-failure: fix crash in split_huge_page_to_list from soft_offline_page When I did soft offline stress test, a machine was observed to crash with the following message: kernel BUG at include/linux/memcontrol.h:554! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 5 PID: 3837 Comm: hwpoison.sh Not tainted 6.7.0-next-20240112-00001-g8ecf3e7fb7c8-dirty #97 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 RIP: 0010:folio_memcg+0xaf/0xd0 Code: 10 5b 5d c3 cc cc cc cc 48 c7 c6 08 b1 f2 b2 48 89 ef e8 b4 c5 f8 ff 90 0f 0b 48 c7 c6 d0 b0 f2 b2 48 89 ef e8 a2 c5 f8 ff 90 <0f> 0b 48 c7 c6 08 b1 f2 b2 48 89 ef e8 90 c5 f8 ff 90 0f 0b 66 66 RSP: 0018:ffffb6c043657c98 EFLAGS: 00000296 RAX: 000000000000004b RBX: ffff932bc1d1e401 RCX: ffff933abfb5c908 RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff933abfb5c900 RBP: ffffea6f04019080 R08: ffffffffb3338ce8 R09: 0000000000009ffb R10: 00000000000004dd R11: ffffffffb3308d00 R12: ffffea6f04019080 R13: ffffea6f04019080 R14: 0000000000000001 R15: ffffb6c043657da0 FS: 00007f6c60f6b740(0000) GS:ffff933abfb40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000559c3bc8b980 CR3: 0000000107f1c000 CR4: 00000000000006f0 Call Trace: split_huge_page_to_list+0x4d/0x1380 try_to_split_thp_page+0x3a/0xf0 soft_offline_page+0x1ea/0x8a0 soft_offline_page_store+0x52/0x90 kernfs_fop_write_iter+0x118/0x1b0 vfs_write+0x30b/0x430 ksys_write+0x5e/0xe0 do_syscall_64+0xb0/0x1b0 entry_SYSCALL_64_after_hwframe+0x6d/0x75 RIP: 0033:0x7f6c60d14697 Code: 10 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 RSP: 002b:00007ffe9b72b8d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007f6c60d14697 RDX: 000000000000000c RSI: 0000559c3bc8b980 RDI: 0000000000000001 RBP: 0000559c3bc8b980 R08: 00007f6c60dd1460 R09: 000000007fffffff R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000c R13: 00007f6c60e1a780 R14: 00007f6c60e16600 R15: 00007f6c60e15a00 The problem is that page->mapping is overloaded with slab->slab_list or slabs fields now, so slab pages could be taken as non-LRU movable pages if field slabs contains PAGE_MAPPING_MOVABLE or slab_list->prev is set to LIST_POISON2. These slab pages will be treated as thp later leading to crash in split_huge_page_to_list(). Link: https://lkml.kernel.org/r/20240126065837.2100184-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20240124084014.1772906-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Fixes: 130d4df57390 ("mm/sl[au]b: rearrange struct slab fields to allow larger rcu_head") Reviewed-by: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/memory-failure.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 636280d04008..9349948f1abf 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1377,6 +1377,9 @@ void ClearPageHWPoisonTakenOff(struct page *page) */ static inline bool HWPoisonHandlable(struct page *page, unsigned long flags) { + if (PageSlab(page)) + return false; + /* Soft offline could migrate non-LRU movable pages */ if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page)) return true; From 01c1484ac04790fe27a37f89dd3a350f99646815 Mon Sep 17 00:00:00 2001 From: Muhammad Usama Anjum Date: Tue, 24 Oct 2023 20:51:25 +0500 Subject: [PATCH 140/311] selftests: core: include linux/close_range.h for CLOSE_RANGE_* macros Correct header file is needed for getting CLOSE_RANGE_* macros. Previously it was tested with newer glibc which didn't show the need to include the header which was a mistake. Link: https://lkml.kernel.org/r/20231024155137.219700-1-usama.anjum@collabora.com Fixes: ec54424923cf ("selftests: core: remove duplicate defines") Reported-by: Aishwarya TCV Link: https://lore.kernel.org/all/7161219e-0223-d699-d6f3-81abd9abf13b@arm.com Signed-off-by: Muhammad Usama Anjum Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/core/close_range_test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index 534576f06df1..c59e4adb905d 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "../kselftest_harness.h" #include "../clone3/clone3_selftests.h" From e870920bbe68e52335a4c31a059e6af6a9a59dbb Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 22 Jan 2024 22:43:05 -0800 Subject: [PATCH 141/311] arch/arm/mm: fix major fault accounting when retrying under per-VMA lock The change [1] missed ARM architecture when fixing major fault accounting for page fault retry under per-VMA lock. The user-visible effects is that it restores correct major fault accounting that was broken after [2] was merged in 6.7 kernel. The more detailed description is in [3] and this patch simply adds the same fix to ARM architecture which I missed in [3]. Add missing code to fix ARM architecture fault accounting. [1] 46e714c729c8 ("arch/mm/fault: fix major fault accounting when retrying under per-VMA lock") [2] https://lore.kernel.org/all/20231006195318.4087158-6-willy@infradead.org/ [3] https://lore.kernel.org/all/20231226214610.109282-1-surenb@google.com/ Link: https://lkml.kernel.org/r/20240123064305.2829244-1-surenb@google.com Fixes: 12214eba1992 ("mm: handle read faults under the VMA lock") Reported-by: Russell King (Oracle) Signed-off-by: Suren Baghdasaryan Cc: Alexander Gordeev Cc: Andy Lutomirski Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Gerald Schaefer Cc: Matthew Wilcox (Oracle) Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Peter Zijlstra Cc: Will Deacon Cc: Signed-off-by: Andrew Morton --- arch/arm/mm/fault.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index e96fb40b9cc3..07565b593ed6 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -298,6 +298,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { From 4c2da3188b848d33c26d7f0f8b14f3150331c923 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Fri, 26 Jan 2024 12:25:48 +0900 Subject: [PATCH 142/311] mm/madvise: don't forget to leave lazy MMU mode in madvise_cold_or_pageout_pte_range() We need to leave lazy MMU mode before unlocking. Link: https://lkml.kernel.org/r/20240126032608.355899-1-senozhatsky@chromium.org Fixes: b2f557a21bc8 ("mm/madvise: add cond_resched() in madvise_cold_or_pageout_pte_range()") Signed-off-by: Sergey Senozhatsky Cc: Jiexun Wang Signed-off-by: Andrew Morton --- mm/madvise.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/madvise.c b/mm/madvise.c index 912155a94ed5..cfa5e7288261 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -429,6 +429,7 @@ restart: if (++batch_count == SWAP_CLUSTER_MAX) { batch_count = 0; if (need_resched()) { + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); cond_resched(); goto restart; From 2e601e1e8e4b330020a346c55ba111d49e0b188e Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 29 Jan 2024 20:34:38 -0500 Subject: [PATCH 143/311] mm: zswap: fix objcg use-after-free in entry destruction In the per-memcg LRU universe, LRU removal uses entry->objcg to determine which list count needs to be decreased. Drop the objcg reference after updating the LRU, to fix a possible use-after-free. Link: https://lkml.kernel.org/r/20240130013438.565167-1-hannes@cmpxchg.org Fixes: a65b0e7607cc ("zswap: make shrinking memcg-aware") Signed-off-by: Johannes Weiner Acked-by: Yosry Ahmed Reviewed-by: Nhat Pham Reviewed-by: Chengming Zhou Signed-off-by: Andrew Morton --- mm/zswap.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index ca25b676048e..0a94b197ed32 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -536,10 +536,6 @@ static struct zpool *zswap_find_zpool(struct zswap_entry *entry) */ static void zswap_free_entry(struct zswap_entry *entry) { - if (entry->objcg) { - obj_cgroup_uncharge_zswap(entry->objcg, entry->length); - obj_cgroup_put(entry->objcg); - } if (!entry->length) atomic_dec(&zswap_same_filled_pages); else { @@ -548,6 +544,10 @@ static void zswap_free_entry(struct zswap_entry *entry) atomic_dec(&entry->pool->nr_stored); zswap_pool_put(entry->pool); } + if (entry->objcg) { + obj_cgroup_uncharge_zswap(entry->objcg, entry->length); + obj_cgroup_put(entry->objcg); + } zswap_entry_cache_free(entry); atomic_dec(&zswap_stored_pages); zswap_update_total_size(); From f2076032096775d1bb1af16b6eddbc6534575328 Mon Sep 17 00:00:00 2001 From: John Moon Date: Wed, 31 Jan 2024 03:43:18 +0000 Subject: [PATCH 144/311] mailmap: switch email address for John Moon Add current email address as QUIC email is no longer active. Link: https://lkml.kernel.org/r/20240131034311.46706-1-john@jmoon.dev Signed-off-by: John Moon Acked-by: Trilok Soni Cc: Elliot Berman Signed-off-by: Andrew Morton --- .mailmap | 1 + 1 file changed, 1 insertion(+) diff --git a/.mailmap b/.mailmap index 04998f7bda81..8ae00bd3708a 100644 --- a/.mailmap +++ b/.mailmap @@ -289,6 +289,7 @@ Johan Hovold John Crispin John Fastabend John Keeping +John Moon John Paul Adrian Glaubitz John Stultz From 79d72c68c58784a3e1cd2378669d51bfd0cb7498 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Tue, 30 Jan 2024 22:04:18 +0100 Subject: [PATCH 145/311] fs,hugetlb: fix NULL pointer dereference in hugetlbs_fill_super When configuring a hugetlb filesystem via the fsconfig() syscall, there is a possible NULL dereference in hugetlbfs_fill_super() caused by assigning NULL to ctx->hstate in hugetlbfs_parse_param() when the requested pagesize is non valid. E.g: Taking the following steps: fd = fsopen("hugetlbfs", FSOPEN_CLOEXEC); fsconfig(fd, FSCONFIG_SET_STRING, "pagesize", "1024", 0); fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); Given that the requested "pagesize" is invalid, ctxt->hstate will be replaced with NULL, losing its previous value, and we will print an error: ... ... case Opt_pagesize: ps = memparse(param->string, &rest); ctx->hstate = h; if (!ctx->hstate) { pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } return 0; ... ... This is a problem because later on, we will dereference ctxt->hstate in hugetlbfs_fill_super() ... ... sb->s_blocksize = huge_page_size(ctx->hstate); ... ... Causing below Oops. Fix this by replacing cxt->hstate value only when then pagesize is known to be valid. kernel: hugetlbfs: Unsupported page size 0 MB kernel: BUG: kernel NULL pointer dereference, address: 0000000000000028 kernel: #PF: supervisor read access in kernel mode kernel: #PF: error_code(0x0000) - not-present page kernel: PGD 800000010f66c067 P4D 800000010f66c067 PUD 1b22f8067 PMD 0 kernel: Oops: 0000 [#1] PREEMPT SMP PTI kernel: CPU: 4 PID: 5659 Comm: syscall Tainted: G E 6.8.0-rc2-default+ #22 5a47c3fef76212addcc6eb71344aabc35190ae8f kernel: Hardware name: Intel Corp. GROVEPORT/GROVEPORT, BIOS GVPRCRB1.86B.0016.D04.1705030402 05/03/2017 kernel: RIP: 0010:hugetlbfs_fill_super+0xb4/0x1a0 kernel: Code: 48 8b 3b e8 3e c6 ed ff 48 85 c0 48 89 45 20 0f 84 d6 00 00 00 48 b8 ff ff ff ff ff ff ff 7f 4c 89 e7 49 89 44 24 20 48 8b 03 <8b> 48 28 b8 00 10 00 00 48 d3 e0 49 89 44 24 18 48 8b 03 8b 40 28 kernel: RSP: 0018:ffffbe9960fcbd48 EFLAGS: 00010246 kernel: RAX: 0000000000000000 RBX: ffff9af5272ae780 RCX: 0000000000372004 kernel: RDX: ffffffffffffffff RSI: ffffffffffffffff RDI: ffff9af555e9b000 kernel: RBP: ffff9af52ee66b00 R08: 0000000000000040 R09: 0000000000370004 kernel: R10: ffffbe9960fcbd48 R11: 0000000000000040 R12: ffff9af555e9b000 kernel: R13: ffffffffa66b86c0 R14: ffff9af507d2f400 R15: ffff9af507d2f400 kernel: FS: 00007ffbc0ba4740(0000) GS:ffff9b0bd7000000(0000) knlGS:0000000000000000 kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 kernel: CR2: 0000000000000028 CR3: 00000001b1ee0000 CR4: 00000000001506f0 kernel: Call Trace: kernel: kernel: ? __die_body+0x1a/0x60 kernel: ? page_fault_oops+0x16f/0x4a0 kernel: ? search_bpf_extables+0x65/0x70 kernel: ? fixup_exception+0x22/0x310 kernel: ? exc_page_fault+0x69/0x150 kernel: ? asm_exc_page_fault+0x22/0x30 kernel: ? __pfx_hugetlbfs_fill_super+0x10/0x10 kernel: ? hugetlbfs_fill_super+0xb4/0x1a0 kernel: ? hugetlbfs_fill_super+0x28/0x1a0 kernel: ? __pfx_hugetlbfs_fill_super+0x10/0x10 kernel: vfs_get_super+0x40/0xa0 kernel: ? __pfx_bpf_lsm_capable+0x10/0x10 kernel: vfs_get_tree+0x25/0xd0 kernel: vfs_cmd_create+0x64/0xe0 kernel: __x64_sys_fsconfig+0x395/0x410 kernel: do_syscall_64+0x80/0x160 kernel: ? syscall_exit_to_user_mode+0x82/0x240 kernel: ? do_syscall_64+0x8d/0x160 kernel: ? syscall_exit_to_user_mode+0x82/0x240 kernel: ? do_syscall_64+0x8d/0x160 kernel: ? exc_page_fault+0x69/0x150 kernel: entry_SYSCALL_64_after_hwframe+0x6e/0x76 kernel: RIP: 0033:0x7ffbc0cb87c9 kernel: Code: 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 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 73 01 c3 48 8b 0d 97 96 0d 00 f7 d8 64 89 01 48 kernel: RSP: 002b:00007ffc29d2f388 EFLAGS: 00000206 ORIG_RAX: 00000000000001af kernel: RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007ffbc0cb87c9 kernel: RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000003 kernel: RBP: 00007ffc29d2f3b0 R08: 0000000000000000 R09: 0000000000000000 kernel: R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000 kernel: R13: 00007ffc29d2f4c0 R14: 0000000000000000 R15: 0000000000000000 kernel: kernel: Modules linked in: rpcsec_gss_krb5(E) auth_rpcgss(E) nfsv4(E) dns_resolver(E) nfs(E) lockd(E) grace(E) sunrpc(E) netfs(E) af_packet(E) bridge(E) stp(E) llc(E) iscsi_ibft(E) iscsi_boot_sysfs(E) intel_rapl_msr(E) intel_rapl_common(E) iTCO_wdt(E) intel_pmc_bxt(E) sb_edac(E) iTCO_vendor_support(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) kvm_intel(E) rfkill(E) ipmi_ssif(E) kvm(E) acpi_ipmi(E) irqbypass(E) pcspkr(E) igb(E) ipmi_si(E) mei_me(E) i2c_i801(E) joydev(E) intel_pch_thermal(E) i2c_smbus(E) dca(E) lpc_ich(E) mei(E) ipmi_devintf(E) ipmi_msghandler(E) acpi_pad(E) tiny_power_button(E) button(E) fuse(E) efi_pstore(E) configfs(E) ip_tables(E) x_tables(E) ext4(E) mbcache(E) jbd2(E) hid_generic(E) usbhid(E) sd_mod(E) t10_pi(E) crct10dif_pclmul(E) crc32_pclmul(E) crc32c_intel(E) polyval_clmulni(E) ahci(E) xhci_pci(E) polyval_generic(E) gf128mul(E) ghash_clmulni_intel(E) sha512_ssse3(E) sha256_ssse3(E) xhci_pci_renesas(E) libahci(E) ehci_pci(E) sha1_ssse3(E) xhci_hcd(E) ehci_hcd(E) libata(E) kernel: mgag200(E) i2c_algo_bit(E) usbcore(E) wmi(E) sg(E) dm_multipath(E) dm_mod(E) scsi_dh_rdac(E) scsi_dh_emc(E) scsi_dh_alua(E) scsi_mod(E) scsi_common(E) aesni_intel(E) crypto_simd(E) cryptd(E) kernel: Unloaded tainted modules: acpi_cpufreq(E):1 fjes(E):1 kernel: CR2: 0000000000000028 kernel: ---[ end trace 0000000000000000 ]--- kernel: RIP: 0010:hugetlbfs_fill_super+0xb4/0x1a0 kernel: Code: 48 8b 3b e8 3e c6 ed ff 48 85 c0 48 89 45 20 0f 84 d6 00 00 00 48 b8 ff ff ff ff ff ff ff 7f 4c 89 e7 49 89 44 24 20 48 8b 03 <8b> 48 28 b8 00 10 00 00 48 d3 e0 49 89 44 24 18 48 8b 03 8b 40 28 kernel: RSP: 0018:ffffbe9960fcbd48 EFLAGS: 00010246 kernel: RAX: 0000000000000000 RBX: ffff9af5272ae780 RCX: 0000000000372004 kernel: RDX: ffffffffffffffff RSI: ffffffffffffffff RDI: ffff9af555e9b000 kernel: RBP: ffff9af52ee66b00 R08: 0000000000000040 R09: 0000000000370004 kernel: R10: ffffbe9960fcbd48 R11: 0000000000000040 R12: ffff9af555e9b000 kernel: R13: ffffffffa66b86c0 R14: ffff9af507d2f400 R15: ffff9af507d2f400 kernel: FS: 00007ffbc0ba4740(0000) GS:ffff9b0bd7000000(0000) knlGS:0000000000000000 kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 kernel: CR2: 0000000000000028 CR3: 00000001b1ee0000 CR4: 00000000001506f0 Link: https://lkml.kernel.org/r/20240130210418.3771-1-osalvador@suse.de Fixes: 32021982a324 ("hugetlbfs: Convert to fs_context") Signed-off-by: Michal Hocko Signed-off-by: Oscar Salvador Acked-by: Muchun Song Cc: Signed-off-by: Andrew Morton --- fs/hugetlbfs/inode.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index ee13c2ca8ad2..d746866ae3b6 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1365,6 +1365,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct fs_parse_result result; + struct hstate *h; char *rest; unsigned long ps; int opt; @@ -1409,11 +1410,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par case Opt_pagesize: ps = memparse(param->string, &rest); - ctx->hstate = size_to_hstate(ps); - if (!ctx->hstate) { + h = size_to_hstate(ps); + if (!h) { pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } + ctx->hstate = h; return 0; case Opt_min_size: From 27d3969b47cc38810b3fd65d72231940e8671e6c Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Sun, 28 Jan 2024 13:28:49 +0000 Subject: [PATCH 146/311] mm/zswap: don't return LRU_SKIP if we have dropped lru lock LRU_SKIP can only be returned if we don't ever dropped lru lock, or we need to return LRU_RETRY to restart from the head of lru list. Otherwise, the iteration might continue from a cursor position that was freed while the locks were dropped. Actually we may need to introduce another LRU_STOP to really terminate the ongoing shrinking scan process, when we encounter a warm page already in the swap cache. The current list_lru implementation doesn't have this function to early break from __list_lru_walk_one. Link: https://lkml.kernel.org/r/20240126-zswap-writeback-race-v2-1-b10479847099@bytedance.com Fixes: b5ba474f3f51 ("zswap: shrink zswap pool based on memory pressure") Signed-off-by: Chengming Zhou Acked-by: Johannes Weiner Reviewed-by: Nhat Pham Cc: Chris Li Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/zswap.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index 0a94b197ed32..350dd2fc8159 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -895,10 +895,8 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o * into the warmer region. We should terminate shrinking (if we're in the dynamic * shrinker context). */ - if (writeback_result == -EEXIST && encountered_page_in_swapcache) { - ret = LRU_SKIP; + if (writeback_result == -EEXIST && encountered_page_in_swapcache) *encountered_page_in_swapcache = true; - } goto put_unlock; } From 6f1f15a5e492082c8082bea56d87852b65588b5c Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Thu, 1 Feb 2024 10:10:08 +0800 Subject: [PATCH 147/311] MAINTAINERS: Leo Yan has moved I will lose access to my @linaro.org email address next week, update the MAINTAINERS file and map it in .mailmap with the new email address. Link: https://lkml.kernel.org/r/20240201021022.886-1-leo.yan@linux.dev Signed-off-by: Leo Yan Cc: Arnaldo Carvalho de Melo Cc: Ian Rogers Cc: James Clark Cc: Mike Leach Cc: Namhyung Kim Signed-off-by: Andrew Morton --- .mailmap | 1 + MAINTAINERS | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 8ae00bd3708a..ee8f03cc7f72 100644 --- a/.mailmap +++ b/.mailmap @@ -345,6 +345,7 @@ Leonid I Ananiev Leon Romanovsky Leon Romanovsky Leon Romanovsky +Leo Yan Liam Mark Linas Vepstas Linus Lüssing diff --git a/MAINTAINERS b/MAINTAINERS index 960512bec428..95b47e3cee0a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17183,7 +17183,7 @@ R: John Garry R: Will Deacon R: James Clark R: Mike Leach -R: Leo Yan +R: Leo Yan L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: tools/build/feature/test-libopencsd.c From 38296afe3c6ee07319e01bb249aa4bb47c07b534 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Wed, 31 Jan 2024 23:56:57 +0900 Subject: [PATCH 148/311] nilfs2: fix hang in nilfs_lookup_dirty_data_buffers() Syzbot reported a hang issue in migrate_pages_batch() called by mbind() and nilfs_lookup_dirty_data_buffers() called in the log writer of nilfs2. While migrate_pages_batch() locks a folio and waits for the writeback to complete, the log writer thread that should bring the writeback to completion picks up the folio being written back in nilfs_lookup_dirty_data_buffers() that it calls for subsequent log creation and was trying to lock the folio. Thus causing a deadlock. In the first place, it is unexpected that folios/pages in the middle of writeback will be updated and become dirty. Nilfs2 adds a checksum to verify the validity of the log being written and uses it for recovery at mount, so data changes during writeback are suppressed. Since this is broken, an unclean shutdown could potentially cause recovery to fail. Investigation revealed that the root cause is that the wait for writeback completion in nilfs_page_mkwrite() is conditional, and if the backing device does not require stable writes, data may be modified without waiting. Fix these issues by making nilfs_page_mkwrite() wait for writeback to finish regardless of the stable write requirement of the backing device. Link: https://lkml.kernel.org/r/20240131145657.4209-1-konishi.ryusuke@gmail.com Fixes: 1d1d1a767206 ("mm: only enforce stable page writes if the backing device requires it") Signed-off-by: Ryusuke Konishi Reported-by: syzbot+ee2ae68da3b22d04cd8d@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/00000000000047d819061004ad6c@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/file.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index bec33b89a075..0e3fc5ba33c7 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -107,7 +107,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf) nilfs_transaction_commit(inode->i_sb); mapped: - folio_wait_stable(folio); + /* + * Since checksumming including data blocks is performed to determine + * the validity of the log to be written and used for recovery, it is + * necessary to wait for writeback to finish here, regardless of the + * stable write requirement of the backing device. + */ + folio_wait_writeback(folio); out: sb_end_pagefault(inode->i_sb); return vmf_fs_error(ret); From b9e4bc1046d20e0623a80660ef8627448056f817 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 2 Feb 2024 11:19:56 -0800 Subject: [PATCH 149/311] mm/damon/sysfs-schemes: fix wrong DAMOS tried regions update timeout setup DAMON sysfs interface's update_schemes_tried_regions command has a timeout of two apply intervals of the DAMOS scheme. Having zero value DAMOS scheme apply interval means it will use the aggregation interval as the value. However, the timeout setup logic is mistakenly using the sampling interval insted of the aggregartion interval for the case. This could cause earlier-than-expected timeout of the command. Fix it. Link: https://lkml.kernel.org/r/20240202191956.88791-1-sj@kernel.org Fixes: 7d6fa31a2fd7 ("mm/damon/sysfs-schemes: add timeout for update_schemes_tried_regions") Signed-off-by: SeongJae Park Cc: # 6.7.x Signed-off-by: Andrew Morton --- mm/damon/sysfs-schemes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 8dbaac6e5c2d..dd2fb5127009 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -2194,7 +2194,7 @@ static void damos_tried_regions_init_upd_status( sysfs_regions->upd_timeout_jiffies = jiffies + 2 * usecs_to_jiffies(scheme->apply_interval_us ? scheme->apply_interval_us : - ctx->attrs.sample_interval); + ctx->attrs.aggr_interval); } } From 5bc09b397cbf1221f8a8aacb1152650c9195b02b Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Sun, 4 Feb 2024 01:16:45 +0900 Subject: [PATCH 150/311] nilfs2: fix potential bug in end_buffer_async_write According to a syzbot report, end_buffer_async_write(), which handles the completion of block device writes, may detect abnormal condition of the buffer async_write flag and cause a BUG_ON failure when using nilfs2. Nilfs2 itself does not use end_buffer_async_write(). But, the async_write flag is now used as a marker by commit 7f42ec394156 ("nilfs2: fix issue with race condition of competition between segments for dirty blocks") as a means of resolving double list insertion of dirty blocks in nilfs_lookup_dirty_data_buffers() and nilfs_lookup_node_buffers() and the resulting crash. This modification is safe as long as it is used for file data and b-tree node blocks where the page caches are independent. However, it was irrelevant and redundant to also introduce async_write for segment summary and super root blocks that share buffers with the backing device. This led to the possibility that the BUG_ON check in end_buffer_async_write would fail as described above, if independent writebacks of the backing device occurred in parallel. The use of async_write for segment summary buffers has already been removed in a previous change. Fix this issue by removing the manipulation of the async_write flag for the remaining super root block buffer. Link: https://lkml.kernel.org/r/20240203161645.4992-1-konishi.ryusuke@gmail.com Fixes: 7f42ec394156 ("nilfs2: fix issue with race condition of competition between segments for dirty blocks") Signed-off-by: Ryusuke Konishi Reported-by: syzbot+5c04210f7c7f897c1e7f@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/00000000000019a97c05fd42f8c8@google.com Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/segment.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 2590a0860eab..2bfb08052d39 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1703,7 +1703,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - set_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_folio != bd_folio) { folio_lock(bd_folio); @@ -1714,6 +1713,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) } break; } + set_buffer_async_write(bh); if (bh->b_folio != fs_folio) { nilfs_begin_folio_io(fs_folio); fs_folio = bh->b_folio; @@ -1800,7 +1800,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { clear_buffer_uptodate(bh); if (bh->b_folio != bd_folio) { @@ -1809,6 +1808,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) } break; } + clear_buffer_async_write(bh); if (bh->b_folio != fs_folio) { nilfs_end_folio_io(fs_folio, err); fs_folio = bh->b_folio; @@ -1896,8 +1896,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) BIT(BH_Delay) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Redirected)); - set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh == segbuf->sb_super_root) { + set_buffer_uptodate(bh); + clear_buffer_dirty(bh); if (bh->b_folio != bd_folio) { folio_end_writeback(bd_folio); bd_folio = bh->b_folio; @@ -1905,6 +1906,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) update_sr = true; break; } + set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh->b_folio != fs_folio) { nilfs_end_folio_io(fs_folio, 0); fs_folio = bh->b_folio; From ddc7d4c584704666fe7088bbd9ec2d72d0f63e65 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Thu, 1 Feb 2024 09:55:32 -0800 Subject: [PATCH 151/311] drm/xe: Fix loop in vm_bind_ioctl_ops_unwind MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The logic for the unwind loop is incorrect resulting in an infinite loop. Fix to unwind to go from the last operations list to he first. Fixes: 617eebb9c480 ("drm/xe: Fix array of binds") Signed-off-by: Matthew Brost Reviewed-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20240201175532.2303168-1-matthew.brost@intel.com (cherry picked from commit 3acc1ff1a72fce00cdbd3ef1c27108a967fd5616) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_vm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 30db264d34a3..d45cbf75d203 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -2669,7 +2669,7 @@ static void vm_bind_ioctl_ops_unwind(struct xe_vm *vm, { int i; - for (i = num_ops_list - 1; i; ++i) { + for (i = num_ops_list - 1; i >= 0; --i) { struct drm_gpuva_ops *__ops = ops[i]; struct drm_gpuva_op *__op; From fc29b6d5ab5395dcb9f35de71e0347f3a6bca542 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Wed, 31 Jan 2024 16:48:48 -0800 Subject: [PATCH 152/311] drm/xe: Take a reference in xe_exec_queue_last_fence_get() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Take a reference in xe_exec_queue_last_fence_get(). Also fix a reference counting underflow bug VM bind and unbind. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Brost Reviewed-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20240201004849.2219558-2-matthew.brost@intel.com (cherry picked from commit a856b67a84169e065ebbeee50258936b1eacc9eb) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_exec_queue.c | 8 ++++++-- drivers/gpu/drm/xe/xe_migrate.c | 5 ++++- drivers/gpu/drm/xe/xe_sched_job.c | 1 - drivers/gpu/drm/xe/xe_sync.c | 2 -- drivers/gpu/drm/xe/xe_vm.c | 1 + 5 files changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index bcfc4127c7c5..254b1d3af4cb 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -926,20 +926,24 @@ void xe_exec_queue_last_fence_put_unlocked(struct xe_exec_queue *q) * @q: The exec queue * @vm: The VM the engine does a bind or exec for * - * Get last fence, does not take a ref + * Get last fence, takes a ref * * Returns: last fence if not signaled, dma fence stub if signaled */ struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *q, struct xe_vm *vm) { + struct dma_fence *fence; + xe_exec_queue_last_fence_lockdep_assert(q, vm); if (q->last_fence && test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &q->last_fence->flags)) xe_exec_queue_last_fence_put(q, vm); - return q->last_fence ? q->last_fence : dma_fence_get_stub(); + fence = q->last_fence ? q->last_fence : dma_fence_get_stub(); + dma_fence_get(fence); + return fence; } /** diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 5c6c54624252..0cc31837ef26 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -1204,8 +1204,11 @@ static bool no_in_syncs(struct xe_vm *vm, struct xe_exec_queue *q, } if (q) { fence = xe_exec_queue_last_fence_get(q, vm); - if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + dma_fence_put(fence); return false; + } + dma_fence_put(fence); } return true; diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c index 01106a1156ad..4e2ccad0e52f 100644 --- a/drivers/gpu/drm/xe/xe_sched_job.c +++ b/drivers/gpu/drm/xe/xe_sched_job.c @@ -274,7 +274,6 @@ int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm) struct dma_fence *fence; fence = xe_exec_queue_last_fence_get(job->q, vm); - dma_fence_get(fence); return drm_sched_job_add_dependency(&job->drm, fence); } diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c index e4c220cf9115..aab92bee1d7c 100644 --- a/drivers/gpu/drm/xe/xe_sync.c +++ b/drivers/gpu/drm/xe/xe_sync.c @@ -307,7 +307,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync, /* Easy case... */ if (!num_in_fence) { fence = xe_exec_queue_last_fence_get(q, vm); - dma_fence_get(fence); return fence; } @@ -322,7 +321,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync, } } fences[current_fence++] = xe_exec_queue_last_fence_get(q, vm); - dma_fence_get(fences[current_fence - 1]); cf = dma_fence_array_create(num_in_fence, fences, vm->composite_fence_ctx, vm->composite_fence_seqno++, diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index d45cbf75d203..96b1833c0e8c 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1984,6 +1984,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma, xe_exec_queue_last_fence_get(wait_exec_queue, vm); xe_sync_entry_signal(&syncs[i], NULL, fence); + dma_fence_put(fence); } } From 21abf108a062fa0323077b5ba3d26e2c0bba9232 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Wed, 31 Jan 2024 16:48:49 -0800 Subject: [PATCH 153/311] drm/xe: Pick correct userptr VMA to repin on REMAP op failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A REMAP op is composed of 3 VMA's - unmap, prev map, and next map. When op_execute fails with -EAGAIN we need to update the local VMA pointer to the current op state and then repin the VMA if it is a userptr. Fixes a failure seen in xe_vm.munmap-style-unbind-userptr-one-partial. Fixes: b06d47be7c83 ("drm/xe: Port Xe to GPUVA") Signed-off-by: Matthew Brost Reviewed-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20240201004849.2219558-3-matthew.brost@intel.com (cherry picked from commit 447f74d223b4f6cbab74963bf1099050c15374ce) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_vm.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 96b1833c0e8c..ca11f8381115 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -2531,13 +2531,25 @@ retry_userptr: } drm_exec_fini(&exec); - if (err == -EAGAIN && xe_vma_is_userptr(vma)) { + if (err == -EAGAIN) { lockdep_assert_held_write(&vm->lock); - err = xe_vma_userptr_pin_pages(to_userptr_vma(vma)); - if (!err) - goto retry_userptr; - trace_xe_vma_fail(vma); + if (op->base.op == DRM_GPUVA_OP_REMAP) { + if (!op->remap.unmap_done) + vma = gpuva_to_vma(op->base.remap.unmap->va); + else if (op->remap.prev) + vma = op->remap.prev; + else + vma = op->remap.next; + } + + if (xe_vma_is_userptr(vma)) { + err = xe_vma_userptr_pin_pages(to_userptr_vma(vma)); + if (!err) + goto retry_userptr; + + trace_xe_vma_fail(vma); + } } return err; From 90773aaf9129ea6f47915bd3c47da261abe6a447 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 3 Jan 2024 12:48:02 +0100 Subject: [PATCH 154/311] drm/xe: circumvent bogus stringop-overflow warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc-13 warns about an array overflow that it sees but that is prevented by the "asid % NUM_PF_QUEUE" calculation: drivers/gpu/drm/xe/xe_gt_pagefault.c: In function 'xe_guc_pagefault_handler': include/linux/fortify-string.h:57:33: error: writing 16 bytes into a region of size 0 [-Werror=stringop-overflow=] include/linux/fortify-string.h:689:26: note: in expansion of macro '__fortify_memcpy_chk' 689 | #define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \ | ^~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/xe/xe_gt_pagefault.c:341:17: note: in expansion of macro 'memcpy' 341 | memcpy(pf_queue->data + pf_queue->tail, msg, len * sizeof(u32)); | ^~~~~~ drivers/gpu/drm/xe/xe_gt_types.h:102:25: note: at offset [1144, 265324] into destination object 'tile' of size 8 I found that rewriting the assignment using pointer addition rather than the equivalent array index calculation prevents the warning, so use that instead. I sent a bug report against gcc for the false positive warning. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113214 Signed-off-by: Arnd Bergmann Signed-off-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240103114819.2913937-1-arnd@kernel.org (cherry picked from commit 774ef5dfc95578a9079426d5106076dcd59c4dfa) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_gt_pagefault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 9c2fe1697d6e..73f08f1924df 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -335,7 +335,7 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len) return -EPROTO; asid = FIELD_GET(PFD_ASID, msg[1]); - pf_queue = >->usm.pf_queue[asid % NUM_PF_QUEUE]; + pf_queue = gt->usm.pf_queue + (asid % NUM_PF_QUEUE); spin_lock_irqsave(&pf_queue->lock, flags); full = pf_queue_full(pf_queue); From 3aa3c5c249086ffc920e8f6d6a15bdd441153d45 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Thu, 1 Feb 2024 19:34:40 -0800 Subject: [PATCH 155/311] drm/xe: Map both mem.kernel_bb_pool and usm.bb_pool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For integrated devices we need to map both mem.kernel_bb_pool and usm.bb_pool to be able to run batches from both pools. Fixes: a682b6a42d4d ("drm/xe: Support device page faults on integrated platforms") Tested-by: Brian Welty Signed-off-by: Matthew Brost Reviewed-by: Brian Welty Link: https://patchwork.freedesktop.org/patch/msgid/20240202033440.2351862-1-matthew.brost@intel.com (cherry picked from commit 72f86ed3c88933d6fa09b036de93621ea71097a7) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_gt.c | 5 ++++- drivers/gpu/drm/xe/xe_migrate.c | 23 ++++++++++++++++++----- 2 files changed, 22 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 3af2adec1295..35474ddbaf97 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -437,7 +437,10 @@ static int all_fw_domain_init(struct xe_gt *gt) * USM has its only SA pool to non-block behind user operations */ if (gt_to_xe(gt)->info.has_usm) { - gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt), SZ_1M, 16); + struct xe_device *xe = gt_to_xe(gt); + + gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt), + IS_DGFX(xe) ? SZ_1M : SZ_512K, 16); if (IS_ERR(gt->usm.bb_pool)) { err = PTR_ERR(gt->usm.bb_pool); goto err_force_wake; diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 0cc31837ef26..70480c305602 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -170,11 +170,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, if (!IS_DGFX(xe)) { /* Write out batch too */ m->batch_base_ofs = NUM_PT_SLOTS * XE_PAGE_SIZE; - if (xe->info.has_usm) { - batch = tile->primary_gt->usm.bb_pool->bo; - m->usm_batch_base_ofs = m->batch_base_ofs; - } - for (i = 0; i < batch->size; i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE : XE_PAGE_SIZE) { @@ -185,6 +180,24 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, entry); level++; } + if (xe->info.has_usm) { + xe_tile_assert(tile, batch->size == SZ_1M); + + batch = tile->primary_gt->usm.bb_pool->bo; + m->usm_batch_base_ofs = m->batch_base_ofs + SZ_1M; + xe_tile_assert(tile, batch->size == SZ_512K); + + for (i = 0; i < batch->size; + i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE : + XE_PAGE_SIZE) { + entry = vm->pt_ops->pte_encode_bo(batch, i, + pat_index, 0); + + xe_map_wr(xe, &bo->vmap, map_ofs + level * 8, u64, + entry); + level++; + } + } } else { u64 batch_addr = xe_bo_addr(batch, 0, XE_PAGE_SIZE); From 11572b3f68d9933fef5c1afef4c20041701d8025 Mon Sep 17 00:00:00 2001 From: Xiaoming Wang Date: Fri, 2 Feb 2024 13:56:58 -0800 Subject: [PATCH 156/311] drm/xe/display: Fix memleak in display initialization MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit intel_power_domains_init is called twice in xe_device_probe: 1) intel_power_domains_init() xe_display_init_nommio() xe_device_probe() 2) intel_power_domains_init() intel_display_driver_probe_noirq() xe_display_init_noirq() xe_device_probe() It needs remove one to avoid power_domains->power_wells double malloc. unreferenced object 0xffff88811150ee00 (size 512): comm "systemd-udevd", pid 506, jiffies 4294674198 (age 3605.560s) hex dump (first 32 bytes): 10 b4 9d a0 ff ff ff ff ff ff ff ff ff ff ff ff ................ ff ff ff ff ff ff ff ff 00 00 00 00 00 00 00 00 ................ backtrace: [] __kmem_cache_alloc_node+0x1c1/0x2b0 [] __kmalloc+0x52/0x150 [] __set_power_wells+0xc3/0x360 [xe] [] xe_display_init_nommio+0x4c/0x70 [xe] [] xe_device_probe+0x3c/0x5a0 [xe] [] xe_pci_probe+0x33f/0x5a0 [xe] [] local_pci_probe+0x47/0xa0 [] pci_device_probe+0xc3/0x1f0 [] really_probe+0x1a2/0x410 [] __driver_probe_device+0x78/0x160 [] driver_probe_device+0x1e/0x90 [] __driver_attach+0xda/0x1d0 [] bus_for_each_dev+0x7c/0xd0 [] bus_add_driver+0x119/0x220 [] driver_register+0x60/0x120 [] 0xffffffffa05e50a0 The call to intel_power_domains_cleanup() needs to stay where it is for now. The main issue is that while the init is called by the display side, shared by i915 and xe, the cleanup is called by a non-shared code path. Fixing that will be done as a separate commit. Fixes: 44e694958b95 ("drm/xe/display: Implement display support") Signed-off-by: Xiaoming Wang [ reword commit message and explain why the fini needs to stay where it is ] Reviewed-by: Lucas De Marchi Signed-off-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240202215658.561298-1-lucas.demarchi@intel.com (cherry picked from commit 86c99abb5f1b6fcd69fb268eeb2e34cb7c4f355c) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_display.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_display.c b/drivers/gpu/drm/xe/xe_display.c index 74391d9b11ae..e4db069f0db3 100644 --- a/drivers/gpu/drm/xe/xe_display.c +++ b/drivers/gpu/drm/xe/xe_display.c @@ -134,8 +134,6 @@ static void xe_display_fini_nommio(struct drm_device *dev, void *dummy) int xe_display_init_nommio(struct xe_device *xe) { - int err; - if (!xe->info.enable_display) return 0; @@ -145,10 +143,6 @@ int xe_display_init_nommio(struct xe_device *xe) /* This must be called before any calls to HAS_PCH_* */ intel_detect_pch(xe); - err = intel_power_domains_init(xe); - if (err) - return err; - return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe); } From 95c058c8ef1d5d9e39ab2039a5eea4d5b93f4117 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Mon, 5 Feb 2024 15:17:14 -0800 Subject: [PATCH 157/311] drm/xe: Assume large page size if VMA not yet bound MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The calculation to determine max page size of a VMA during a REMAP operations assumes the VMA has been bound. This assumption is not true if the VMA is from an eariler operation in an array of binds. If a VMA has not been bound use the maximum page size which will ensure the previous / next REMAP operations are not incorrectly skipped. Fixes: 8f33b4f054fc ("drm/xe: Avoid doing rebinds") Signed-off-by: Matthew Brost Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20240205231714.2956225-1-matthew.brost@intel.com (cherry picked from commit 5ad6af5c91e9b942c44b657122270d935db3a813) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_vm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index ca11f8381115..99f151d73154 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -2200,8 +2200,10 @@ static u64 xe_vma_max_pte_size(struct xe_vma *vma) return SZ_1G; else if (vma->gpuva.flags & XE_VMA_PTE_2M) return SZ_2M; + else if (vma->gpuva.flags & XE_VMA_PTE_4K) + return SZ_4K; - return SZ_4K; + return SZ_1G; /* Uninitialized, used max size */ } static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size) From 9e3fc1d65d4e8cf302e289847ab165ad9358fdb2 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Fri, 2 Feb 2024 17:14:36 +0000 Subject: [PATCH 158/311] drm/xe/vm: don't ignore error when in_kthread MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If GUP fails and we are in_kthread, we can have pinned = 0 and ret = 0. If that happens we call sg_alloc_append_table_from_pages() with n_pages = 0, which is not well behaved and can trigger: kernel BUG at include/linux/scatterlist.h:115! depending on if the pages array happens to be zeroed or not. Even if we don't hit that it crashes later when trying to dma_map the returned table. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Matthew Brost Reviewed-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20240202171435.427630-2-matthew.auld@intel.com (cherry picked from commit 8087199cd5951c1eba26003b3e4296dbb2110adf) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_vm.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 99f151d73154..a9df89413155 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -114,11 +114,8 @@ retry: num_pages - pinned, read_only ? 0 : FOLL_WRITE, &pages[pinned]); - if (ret < 0) { - if (in_kthread) - ret = 0; + if (ret < 0) break; - } pinned += ret; ret = 0; From bf4c27b8267d7848bb81fd41e6aa07aa662f07fb Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Mon, 5 Feb 2024 20:50:10 -0800 Subject: [PATCH 159/311] drm/xe: Remove TEST_VM_ASYNC_OPS_ERROR MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit TEST_VM_ASYNC_OPS_ERROR is broken and unused. Remove for now and will pull back in a later time when it is used, fixed, and properly hidden behind a Kconfig option. Also fixup the supported flags value. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Brost Reviewed-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20240206045010.2981051-1-matthew.brost@intel.com (cherry picked from commit d9890c028d66a9e1ee3cccaa081ab5aedcbfe431) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_vm.c | 28 +--------------------------- drivers/gpu/drm/xe/xe_vm_types.h | 8 -------- 2 files changed, 1 insertion(+), 35 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index a9df89413155..865e10d0a06a 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -37,8 +37,6 @@ #include "generated/xe_wa_oob.h" #include "xe_wa.h" -#define TEST_VM_ASYNC_OPS_ERROR - static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm) { return vm->gpuvm.r_obj; @@ -2062,7 +2060,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo, struct drm_gem_object *obj = bo ? &bo->ttm.base : NULL; struct drm_gpuva_ops *ops; struct drm_gpuva_op *__op; - struct xe_vma_op *op; struct drm_gpuvm_bo *vm_bo; int err; @@ -2109,15 +2106,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo, if (IS_ERR(ops)) return ops; -#ifdef TEST_VM_ASYNC_OPS_ERROR - if (operation & FORCE_ASYNC_OP_ERROR) { - op = list_first_entry_or_null(&ops->list, struct xe_vma_op, - base.entry); - if (op) - op->inject_error = true; - } -#endif - drm_gpuva_for_each_op(__op, ops) { struct xe_vma_op *op = gpuva_op_to_vma_op(__op); @@ -2560,13 +2548,6 @@ static int xe_vma_op_execute(struct xe_vm *vm, struct xe_vma_op *op) lockdep_assert_held_write(&vm->lock); -#ifdef TEST_VM_ASYNC_OPS_ERROR - if (op->inject_error) { - op->inject_error = false; - return -ENOMEM; - } -#endif - switch (op->base.op) { case DRM_GPUVA_OP_MAP: ret = __xe_vma_op_execute(vm, op->map.vma, op); @@ -2726,16 +2707,9 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm, return 0; } -#ifdef TEST_VM_ASYNC_OPS_ERROR -#define SUPPORTED_FLAGS \ - (FORCE_ASYNC_OP_ERROR | DRM_XE_VM_BIND_FLAG_READONLY | \ - DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | 0xffff) -#else #define SUPPORTED_FLAGS \ (DRM_XE_VM_BIND_FLAG_READONLY | \ - DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \ - 0xffff) -#endif + DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL) #define XE_64K_PAGE_MASK 0xffffull #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP) diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index 1fec66ae2eb2..5ac9c5bebabc 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -21,9 +21,6 @@ struct xe_bo; struct xe_sync_entry; struct xe_vm; -#define TEST_VM_ASYNC_OPS_ERROR -#define FORCE_ASYNC_OP_ERROR BIT(31) - #define XE_VMA_READ_ONLY DRM_GPUVA_USERBITS #define XE_VMA_DESTROYED (DRM_GPUVA_USERBITS << 1) #define XE_VMA_ATOMIC_PTE_BIT (DRM_GPUVA_USERBITS << 2) @@ -360,11 +357,6 @@ struct xe_vma_op { /** @flags: operation flags */ enum xe_vma_op_flags flags; -#ifdef TEST_VM_ASYNC_OPS_ERROR - /** @inject_error: inject error to test async op error handling */ - bool inject_error; -#endif - union { /** @map: VMA map operation specific data */ struct xe_vma_op_map map; From 2526dffc6d65cffa32b88556bd68e4e72e889a55 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 5 Feb 2024 11:22:29 +0100 Subject: [PATCH 160/311] gpio: remove GPIO device from the list unconditionally in error path Since commit 48e1b4d369cf ("gpiolib: remove the GPIO device from the list when it's unregistered") we remove the GPIO device entry from the global list (used to order devices by their GPIO ranges) when unregistering the chip, not when releasing the device. It will not happen when the last reference is put anymore. This means, we need to remove it in error path in gpiochip_add_data_with_key() unconditionally, without checking if the device's .release() callback is set. Fixes: 48e1b4d369cf ("gpiolib: remove the GPIO device from the list when it's unregistered") Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 44c8f5743a24..8b3a0f45b574 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1005,15 +1005,15 @@ err_remove_of_chip: err_free_gpiochip_mask: gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); +err_remove_from_list: + spin_lock_irqsave(&gpio_lock, flags); + list_del(&gdev->list); + spin_unlock_irqrestore(&gpio_lock, flags); if (gdev->dev.release) { /* release() has been registered by gpiochip_setup_dev() */ gpio_device_put(gdev); goto err_print_message; } -err_remove_from_list: - spin_lock_irqsave(&gpio_lock, flags); - list_del(&gdev->list); - spin_unlock_irqrestore(&gpio_lock, flags); err_free_label: kfree_const(gdev->label); err_free_descs: From c98d8836b817d11fdff4ca7749cbbe04ff7f0c64 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 31 Jan 2024 16:49:10 +0100 Subject: [PATCH 161/311] wifi: mac80211: reload info pointer in ieee80211_tx_dequeue() This pointer can change here since the SKB can change, so we actually later open-coded IEEE80211_SKB_CB() again. Reload the pointer where needed, so the monitor-mode case using it gets fixed, and then use info-> later as well. Cc: stable@vger.kernel.org Fixes: 531682159092 ("mac80211: fix VLAN handling with TXQs") Link: https://msgid.link/20240131164910.b54c28d583bc.I29450cec84ea6773cff5d9c16ff92b836c331471@changeid Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e448ab338448..6fbb15b65902 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation * * Transmit and frame generation functions. */ @@ -3927,6 +3927,7 @@ begin: goto begin; skb = __skb_dequeue(&tx.skbs); + info = IEEE80211_SKB_CB(skb); if (!skb_queue_empty(&tx.skbs)) { spin_lock_bh(&fq->lock); @@ -3971,7 +3972,7 @@ begin: } encap_out: - IEEE80211_SKB_CB(skb)->control.vif = vif; + info->control.vif = vif; if (tx.sta && wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { From 2e57b77583ca34fdb6e14f253172636c52f81cf2 Mon Sep 17 00:00:00 2001 From: Daniel Gabay Date: Mon, 5 Feb 2024 00:06:03 +0200 Subject: [PATCH 162/311] wifi: iwlwifi: mvm: use correct address 3 in A-MSDU As described in IEEE sta 802.11-2020, table 9-30 (Address field contents), A-MSDU address 3 should contain the BSSID address. In TX_CMD we copy the MAC header from skb, and skb address 3 holds the destination address, but it may not be identical to the BSSID. Using the wrong destination address appears to work with (most) receivers without MLO, but in MLO some devices are checking for it carefully, perhaps as a consequence of link to MLD address translation. Replace address 3 in the TX_CMD MAC header with the correct address while retaining the skb address 3 unchanged. This ensures that skb address 3 will be utilized later for constructing the A-MSDU subframes. Note that we fill in the MLD address, but the firmware will do the necessary translation to link address after encryption. Signed-off-by: Daniel Gabay Signed-off-by: Miri Korenblit Link: https://msgid.link/20240204235836.4583a1bf9188.I3f8e7892bdf8f86b4daa28453771a8c9817b2416@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 73 +++++++++++++++++---- 1 file changed, 61 insertions(+), 12 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index db986bfc4dc3..461f26d9214e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -520,13 +520,24 @@ static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm, } } +static void iwl_mvm_copy_hdr(void *cmd, const void *hdr, int hdrlen, + const u8 *addr3_override) +{ + struct ieee80211_hdr *out_hdr = cmd; + + memcpy(cmd, hdr, hdrlen); + if (addr3_override) + memcpy(out_hdr->addr3, addr3_override, ETH_ALEN); +} + /* * Allocates and sets the Tx cmd the driver data pointers in the skb */ static struct iwl_device_tx_cmd * iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, struct ieee80211_tx_info *info, int hdrlen, - struct ieee80211_sta *sta, u8 sta_id) + struct ieee80211_sta *sta, u8 sta_id, + const u8 *addr3_override) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct iwl_device_tx_cmd *dev_cmd; @@ -584,7 +595,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, cmd->len = cpu_to_le16((u16)skb->len); /* Copy MAC header from skb into command buffer */ - memcpy(cmd->hdr, hdr, hdrlen); + iwl_mvm_copy_hdr(cmd->hdr, hdr, hdrlen, addr3_override); cmd->flags = cpu_to_le16(flags); cmd->rate_n_flags = cpu_to_le32(rate_n_flags); @@ -599,7 +610,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, cmd->len = cpu_to_le16((u16)skb->len); /* Copy MAC header from skb into command buffer */ - memcpy(cmd->hdr, hdr, hdrlen); + iwl_mvm_copy_hdr(cmd->hdr, hdr, hdrlen, addr3_override); cmd->flags = cpu_to_le32(flags); cmd->rate_n_flags = cpu_to_le32(rate_n_flags); @@ -617,7 +628,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, iwl_mvm_set_tx_cmd_rate(mvm, tx_cmd, info, sta, hdr->frame_control); /* Copy MAC header from skb into command buffer */ - memcpy(tx_cmd->hdr, hdr, hdrlen); + iwl_mvm_copy_hdr(tx_cmd->hdr, hdr, hdrlen, addr3_override); out: return dev_cmd; @@ -820,7 +831,8 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) IWL_DEBUG_TX(mvm, "station Id %d, queue=%d\n", sta_id, queue); - dev_cmd = iwl_mvm_set_tx_params(mvm, skb, &info, hdrlen, NULL, sta_id); + dev_cmd = iwl_mvm_set_tx_params(mvm, skb, &info, hdrlen, NULL, sta_id, + NULL); if (!dev_cmd) return -1; @@ -1140,7 +1152,8 @@ static int iwl_mvm_tx_pkt_queued(struct iwl_mvm *mvm, */ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, struct ieee80211_tx_info *info, - struct ieee80211_sta *sta) + struct ieee80211_sta *sta, + const u8 *addr3_override) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct iwl_mvm_sta *mvmsta; @@ -1172,7 +1185,8 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, iwl_mvm_probe_resp_set_noa(mvm, skb); dev_cmd = iwl_mvm_set_tx_params(mvm, skb, info, hdrlen, - sta, mvmsta->deflink.sta_id); + sta, mvmsta->deflink.sta_id, + addr3_override); if (!dev_cmd) goto drop; @@ -1294,9 +1308,11 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb, struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); struct ieee80211_tx_info info; struct sk_buff_head mpdus_skbs; + struct ieee80211_vif *vif; unsigned int payload_len; int ret; struct sk_buff *orig_skb = skb; + const u8 *addr3; if (WARN_ON_ONCE(!mvmsta)) return -1; @@ -1307,26 +1323,59 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb, memcpy(&info, skb->cb, sizeof(info)); if (!skb_is_gso(skb)) - return iwl_mvm_tx_mpdu(mvm, skb, &info, sta); + return iwl_mvm_tx_mpdu(mvm, skb, &info, sta, NULL); payload_len = skb_tail_pointer(skb) - skb_transport_header(skb) - tcp_hdrlen(skb) + skb->data_len; if (payload_len <= skb_shinfo(skb)->gso_size) - return iwl_mvm_tx_mpdu(mvm, skb, &info, sta); + return iwl_mvm_tx_mpdu(mvm, skb, &info, sta, NULL); __skb_queue_head_init(&mpdus_skbs); + vif = info.control.vif; + if (!vif) + return -1; + ret = iwl_mvm_tx_tso(mvm, skb, &info, sta, &mpdus_skbs); if (ret) return ret; WARN_ON(skb_queue_empty(&mpdus_skbs)); - while (!skb_queue_empty(&mpdus_skbs)) { - skb = __skb_dequeue(&mpdus_skbs); + /* + * As described in IEEE sta 802.11-2020, table 9-30 (Address + * field contents), A-MSDU address 3 should contain the BSSID + * address. + * Pass address 3 down to iwl_mvm_tx_mpdu() and further to set it + * in the command header. We need to preserve the original + * address 3 in the skb header to correctly create all the + * A-MSDU subframe headers from it. + */ + switch (vif->type) { + case NL80211_IFTYPE_STATION: + addr3 = vif->cfg.ap_addr; + break; + case NL80211_IFTYPE_AP: + addr3 = vif->addr; + break; + default: + addr3 = NULL; + break; + } - ret = iwl_mvm_tx_mpdu(mvm, skb, &info, sta); + while (!skb_queue_empty(&mpdus_skbs)) { + struct ieee80211_hdr *hdr; + bool amsdu; + + skb = __skb_dequeue(&mpdus_skbs); + hdr = (void *)skb->data; + amsdu = ieee80211_is_data_qos(hdr->frame_control) && + (*ieee80211_get_qos_ctl(hdr) & + IEEE80211_QOS_CTL_A_MSDU_PRESENT); + + ret = iwl_mvm_tx_mpdu(mvm, skb, &info, sta, + amsdu ? addr3 : NULL); if (ret) { /* Free skbs created as part of TSO logic that have not yet been dequeued */ __skb_queue_purge(&mpdus_skbs); From 3012477cd510044d346c5e0465ead4732aef8349 Mon Sep 17 00:00:00 2001 From: Miri Korenblit Date: Mon, 5 Feb 2024 00:06:16 +0200 Subject: [PATCH 163/311] wifi: iwlwifi: clear link_id in time_event Before sending a SESSION PROTECTION cmd the driver checks if the link_id indicated in the time event (and for which the cmd will be sent) is valid and exists. Clear the te_data::link_id when FW notifies that a session protection ended, so the check will actually fail when it should. Fixes: 135065837310 ("wifi: iwlwifi: support link_id in SESSION_PROTECTION cmd") Signed-off-by: Miri Korenblit Link: https://msgid.link/20240204235836.c64a6b3606c2.I35cdc08e8a3be282563163690f8ca3edb51a3854@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/time-event.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 218fdf1ed530..2e653a417d62 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2023 Intel Corporation + * Copyright (C) 2012-2014, 2018-2024 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2017 Intel Deutschland GmbH */ @@ -972,6 +972,7 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, if (!le32_to_cpu(notif->status) || !le32_to_cpu(notif->start)) { /* End TE, notify mac80211 */ mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID; + mvmvif->time_event_data.link_id = -1; iwl_mvm_p2p_roc_finished(mvm); ieee80211_remain_on_channel_expired(mvm->hw); } else if (le32_to_cpu(notif->start)) { From c6ebb5b67641994de8bc486b33457fe0b681d6fe Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 8 Feb 2024 13:17:06 +0300 Subject: [PATCH 164/311] wifi: iwlwifi: Fix some error codes This saves the error as PTR_ERR(wifi_pkg). The problem is that "wifi_pkg" is a valid pointer, not an error pointer. Set the error code to -EINVAL instead. Fixes: 2a8084147bff ("iwlwifi: acpi: support reading and storing WRDS revision 1 and 2") Signed-off-by: Dan Carpenter Link: https://msgid.link/9620bb77-2d7c-4d76-b255-ad824ebf8e35@moroto.mountain Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index b96f30d11644..d73d561709d3 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -618,7 +618,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 2) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -634,7 +634,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 1) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -650,7 +650,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 0) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -707,7 +707,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 2) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -723,7 +723,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 1) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -739,7 +739,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 0) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } From 65c6ee90455053cfd3067c17aaa4a42b0c766543 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 8 Feb 2024 13:17:31 +0300 Subject: [PATCH 165/311] wifi: iwlwifi: uninitialized variable in iwl_acpi_get_ppag_table() This is an error path and Smatch complains that "tbl_rev" is uninitialized on this path. All the other functions follow this same patter where they set the error code and goto out_free so that's probably what was intended here as well. Fixes: e8e10a37c51c ("iwlwifi: acpi: move ppag code from mvm to fw/acpi") Signed-off-by: Dan Carpenter Link: https://msgid.link/09900c01-6540-4a32-9451-563da0029cb6@moroto.mountain Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index d73d561709d3..dcc4810cb324 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -1116,6 +1116,9 @@ int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt) goto read_table; } + ret = PTR_ERR(wifi_pkg); + goto out_free; + read_table: fwrt->ppag_ver = tbl_rev; flags = &wifi_pkg->package.elements[1]; From b7198383ef2debe748118996f627452281cf27d7 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Tue, 6 Feb 2024 18:02:04 +0200 Subject: [PATCH 166/311] wifi: iwlwifi: mvm: fix a crash when we run out of stations A DoS tool that injects loads of authentication frames made our AP crash. The iwl_mvm_is_dup() function couldn't find the per-queue dup_data which was not allocated. The root cause for that is that we ran out of stations in the firmware and we didn't really add the station to the firmware, yet we didn't return an error to mac80211. Mac80211 was thinking that we have the station and because of that, sta_info::uploaded was set to 1. This allowed ieee80211_find_sta_by_ifaddr() to return a valid station object, but that ieee80211_sta didn't have any iwl_mvm_sta object initialized and that caused the crash mentioned earlier when we got Rx on that station. Cc: stable@vger.kernel.org Fixes: 57974a55d995 ("wifi: iwlwifi: mvm: refactor iwl_mvm_mac_sta_state_common()") Signed-off-by: Emmanuel Grumbach Signed-off-by: Miri Korenblit Link: https://msgid.link/20240206175739.1f76c44b2486.I6a00955e2842f15f0a089db2f834adb9d10fbe35@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 3 +++ drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 4 ++++ 2 files changed, 7 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 3447d67a8b31..53e26c3c3a9a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3687,6 +3687,9 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm, NL80211_TDLS_SETUP); } + if (ret) + return ret; + for_each_sta_active_link(vif, sta, link_sta, i) link_sta->agg.max_rc_amsdu_len = 1; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 886d00098528..af15d470c69b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -505,6 +505,10 @@ static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue, return false; mvm_sta = iwl_mvm_sta_from_mac80211(sta); + + if (WARN_ON_ONCE(!mvm_sta->dup_data)) + return false; + dup_data = &mvm_sta->dup_data[queue]; /* From 8c427cc2fa73684ea140999e121b7b6c1c717632 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Wed, 24 Jan 2024 00:02:34 +0900 Subject: [PATCH 167/311] tracing/probes: Fix to show a parse error for bad type for $comm Fix to show a parse error for bad type (non-string) for $comm/$COMM and immediate-string. With this fix, error_log file shows appropriate error message as below. /sys/kernel/tracing # echo 'p vfs_read $comm:u32' >> kprobe_events sh: write error: Invalid argument /sys/kernel/tracing # echo 'p vfs_read \"hoge":u32' >> kprobe_events sh: write error: Invalid argument /sys/kernel/tracing # cat error_log [ 30.144183] trace_kprobe: error: $comm and immediate-string only accepts string type Command: p vfs_read $comm:u32 ^ [ 62.618500] trace_kprobe: error: $comm and immediate-string only accepts string type Command: p vfs_read \"hoge":u32 ^ Link: https://lore.kernel.org/all/170602215411.215583.2238016352271091852.stgit@devnote2/ Fixes: 3dd1f7f24f8c ("tracing: probeevent: Fix to make the type of $comm string") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_probe.c | 7 +++++-- kernel/trace/trace_probe.h | 3 ++- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 4dc74d73fc1d..c6da5923e5b9 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1159,9 +1159,12 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, if (!(ctx->flags & TPARG_FL_TEVENT) && (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 || strncmp(arg, "\\\"", 2) == 0)) { - /* The type of $comm must be "string", and not an array. */ - if (parg->count || (t && strcmp(t, "string"))) + /* The type of $comm must be "string", and not an array type. */ + if (parg->count || (t && strcmp(t, "string"))) { + trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), + NEED_STRING_TYPE); goto out; + } parg->type = find_fetch_type("string", ctx->flags); } else parg->type = find_fetch_type(t, ctx->flags); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 850d9ecb6765..c1877d018269 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -515,7 +515,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(BAD_HYPHEN, "Failed to parse single hyphen. Forgot '>'?"), \ C(NO_BTF_FIELD, "This field is not found."), \ C(BAD_BTF_TID, "Failed to get BTF type info."),\ - C(BAD_TYPE4STR, "This type does not fit for string."), + C(BAD_TYPE4STR, "This type does not fit for string."),\ + C(NEED_STRING_TYPE, "$comm and immediate-string only accepts string type"), #undef C #define C(a, b) TP_ERR_##a From 9a571c1e275cedacd48c66a6bddd0c23f1dffdbf Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Wed, 24 Jan 2024 00:03:02 +0900 Subject: [PATCH 168/311] tracing/probes: Fix to set arg size and fmt after setting type from BTF Since the BTF type setting updates probe_arg::type, the type size calculation and setting print-fmt should be done after that. Without this fix, the argument size and print-fmt can be wrong. Link: https://lore.kernel.org/all/170602218196.215583.6417859469540955777.stgit@devnote2/ Fixes: b576e09701c7 ("tracing/probes: Support function parameters if BTF is available") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_probe.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index c6da5923e5b9..34289f9c6707 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1172,18 +1172,6 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), BAD_TYPE); goto out; } - parg->offset = *size; - *size += parg->type->size * (parg->count ?: 1); - - ret = -ENOMEM; - if (parg->count) { - len = strlen(parg->type->fmttype) + 6; - parg->fmt = kmalloc(len, GFP_KERNEL); - if (!parg->fmt) - goto out; - snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype, - parg->count); - } code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL); if (!code) @@ -1207,6 +1195,19 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, goto fail; } } + parg->offset = *size; + *size += parg->type->size * (parg->count ?: 1); + + if (parg->count) { + len = strlen(parg->type->fmttype) + 6; + parg->fmt = kmalloc(len, GFP_KERNEL); + if (!parg->fmt) { + ret = -ENOMEM; + goto out; + } + snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype, + parg->count); + } ret = -EINVAL; /* Store operation */ From 9efd24ec5599ed485b7c4d9aeb731141f6285167 Mon Sep 17 00:00:00 2001 From: Li zeming Date: Tue, 19 Sep 2023 09:28:23 +0800 Subject: [PATCH 169/311] kprobes: Remove unnecessary initial values of variables ri and sym is assigned first, so it does not need to initialize the assignment. Link: https://lore.kernel.org/all/20230919012823.7815-1-zeming@nfschina.com/ Signed-off-by: Li zeming Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) --- kernel/kprobes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index d5a0ee40bf66..9d9095e81792 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1993,7 +1993,7 @@ NOKPROBE_SYMBOL(__kretprobe_find_ret_addr); unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, struct llist_node **cur) { - struct kretprobe_instance *ri = NULL; + struct kretprobe_instance *ri; kprobe_opcode_t *ret; if (WARN_ON_ONCE(!cur)) @@ -2802,7 +2802,7 @@ static int show_kprobe_addr(struct seq_file *pi, void *v) { struct hlist_head *head; struct kprobe *p, *kp; - const char *sym = NULL; + const char *sym; unsigned int i = *(loff_t *) v; unsigned long offset = 0; char *modname, namebuf[KSYM_NAME_LEN]; From 45be0882c5f91e1b92e645001dd1a53b3bd58c97 Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 5 Feb 2024 14:43:17 -0600 Subject: [PATCH 170/311] smb3: add missing null server pointer check Address static checker warning in cifs_ses_get_chan_index(): warn: variable dereferenced before check 'server' To be consistent, and reduce risk, we should add another check for null server pointer. Fixes: 88675b22d34e ("cifs: do not search for channel if server is terminating") Reported-by: Dan Carpenter Reviewed-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/sess.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index ed4bd88dd528..476d54fceb50 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -76,7 +76,7 @@ cifs_ses_get_chan_index(struct cifs_ses *ses, unsigned int i; /* if the channel is waiting for termination */ - if (server->terminate) + if (server && server->terminate) return CIFS_INVAL_CHAN_INDEX; for (i = 0; i < ses->chan_count; i++) { From 55c7788c37242702868bfac7861cdf0c358d6c3d Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Fri, 2 Feb 2024 12:38:24 -0300 Subject: [PATCH 171/311] smb: client: set correct d_type for reparse points under DFS mounts Send query dir requests with an info level of SMB_FIND_FILE_FULL_DIRECTORY_INFO rather than SMB_FIND_FILE_DIRECTORY_INFO when the client is generating its own inode numbers (e.g. noserverino) so that reparse tags still can be parsed directly from the responses, but server won't send UniqueId (server inode number) Signed-off-by: Paulo Alcantara Signed-off-by: Steve French --- fs/smb/client/readdir.c | 15 ++++++++------- fs/smb/client/smb2pdu.c | 6 ++++++ 2 files changed, 14 insertions(+), 7 deletions(-) diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 3b1b01d10f7d..b520eea7bfce 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -307,14 +307,16 @@ cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info, } static void cifs_fulldir_info_to_fattr(struct cifs_fattr *fattr, - SEARCH_ID_FULL_DIR_INFO *info, + const void *info, struct cifs_sb_info *cifs_sb) { + const FILE_FULL_DIRECTORY_INFO *di = info; + __dir_info_to_fattr(fattr, info); - /* See MS-FSCC 2.4.19 FileIdFullDirectoryInformation */ + /* See MS-FSCC 2.4.14, 2.4.19 */ if (fattr->cf_cifsattrs & ATTR_REPARSE) - fattr->cf_cifstag = le32_to_cpu(info->EaSize); + fattr->cf_cifstag = le32_to_cpu(di->EaSize); cifs_fill_common_info(fattr, cifs_sb); } @@ -396,7 +398,7 @@ ffirst_retry: } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) { cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO; } else /* not srvinos - BB fixme add check for backlevel? */ { - cifsFile->srch_inf.info_level = SMB_FIND_FILE_DIRECTORY_INFO; + cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO; } search_flags = CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME; @@ -987,10 +989,9 @@ static int cifs_filldir(char *find_entry, struct file *file, (FIND_FILE_STANDARD_INFO *)find_entry, cifs_sb); break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: case SMB_FIND_FILE_ID_FULL_DIR_INFO: - cifs_fulldir_info_to_fattr(&fattr, - (SEARCH_ID_FULL_DIR_INFO *)find_entry, - cifs_sb); + cifs_fulldir_info_to_fattr(&fattr, find_entry, cifs_sb); break; default: cifs_dir_info_to_fattr(&fattr, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index c58fa44dd6b0..4085ce27fd38 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -5206,6 +5206,9 @@ int SMB2_query_directory_init(const unsigned int xid, case SMB_FIND_FILE_POSIX_INFO: req->FileInformationClass = SMB_FIND_FILE_POSIX_INFO; break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: + req->FileInformationClass = FILE_FULL_DIRECTORY_INFORMATION; + break; default: cifs_tcon_dbg(VFS, "info level %u isn't supported\n", info_level); @@ -5275,6 +5278,9 @@ smb2_parse_query_directory(struct cifs_tcon *tcon, /* note that posix payload are variable size */ info_buf_size = sizeof(struct smb2_posix_info); break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: + info_buf_size = sizeof(FILE_FULL_DIRECTORY_INFO); + break; default: cifs_tcon_dbg(VFS, "info level %u isn't supported\n", srch_inf->info_level); From 2a427b49d02995ea4a6ff93a1432c40fa4d36821 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 20 Nov 2023 12:25:56 -1000 Subject: [PATCH 172/311] blk-iocost: Fix an UBSAN shift-out-of-bounds warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When iocg_kick_delay() is called from a CPU different than the one which set the delay, @now may be in the past of @iocg->delay_at leading to the following warning: UBSAN: shift-out-of-bounds in block/blk-iocost.c:1359:23 shift exponent 18446744073709 is too large for 64-bit type 'u64' (aka 'unsigned long long') ... Call Trace: dump_stack_lvl+0x79/0xc0 __ubsan_handle_shift_out_of_bounds+0x2ab/0x300 iocg_kick_delay+0x222/0x230 ioc_rqos_merge+0x1d7/0x2c0 __rq_qos_merge+0x2c/0x80 bio_attempt_back_merge+0x83/0x190 blk_attempt_plug_merge+0x101/0x150 blk_mq_submit_bio+0x2b1/0x720 submit_bio_noacct_nocheck+0x320/0x3e0 __swap_writepage+0x2ab/0x9d0 The underflow itself doesn't really affect the behavior in any meaningful way; however, the past timestamp may exaggerate the delay amount calculated later in the code, which shouldn't be a material problem given the nature of the delay mechanism. If @now is in the past, this CPU is racing another CPU which recently set up the delay and there's nothing this CPU can contribute w.r.t. the delay. Let's bail early from iocg_kick_delay() in such cases. Reported-by: Breno Leitão Signed-off-by: Tejun Heo Fixes: 5160a5a53c0c ("blk-iocost: implement delay adjustment hysteresis") Link: https://lore.kernel.org/r/ZVvc9L_CYk5LO1fT@slm.duckdns.org Signed-off-by: Jens Axboe --- block/blk-iocost.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index c8beec6d7df0..04d44f0bcbc8 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1353,6 +1353,13 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) lockdep_assert_held(&iocg->waitq.lock); + /* + * If the delay is set by another CPU, we may be in the past. No need to + * change anything if so. This avoids decay calculation underflow. + */ + if (time_before64(now->now, iocg->delay_at)) + return false; + /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; if (iocg->delay) From c23de7ceae59e4ca5894c3ecf4f785c50c0fa428 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Mon, 5 Feb 2024 18:51:26 +0100 Subject: [PATCH 173/311] docs: kernel_feat.py: fix build error for missing files If the directory passed to the '.. kernel-feat::' directive does not exist or the get_feat.pl script does not find any files to extract features from, Sphinx will report the following error: Sphinx parallel build error: UnboundLocalError: local variable 'fname' referenced before assignment make[2]: *** [Documentation/Makefile:102: htmldocs] Error 2 This is due to how I changed the script in c48a7c44a1d0 ("docs: kernel_feat.py: fix potential command injection"). Before that, the filename passed along to self.nestedParse() in this case was weirdly just the whole get_feat.pl invocation. We can fix it by doing what kernel_abi.py does -- just pass self.arguments[0] as 'fname'. Fixes: c48a7c44a1d0 ("docs: kernel_feat.py: fix potential command injection") Cc: Justin Forbes Cc: Salvatore Bonaccorso Cc: Jani Nikula Cc: Mauro Carvalho Chehab Cc: stable@vger.kernel.org Signed-off-by: Vegard Nossum Link: https://lore.kernel.org/r/20240205175133.774271-2-vegard.nossum@oracle.com Signed-off-by: Jonathan Corbet --- Documentation/sphinx/kernel_feat.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/sphinx/kernel_feat.py b/Documentation/sphinx/kernel_feat.py index b9df61eb4501..03ace5f01b5c 100644 --- a/Documentation/sphinx/kernel_feat.py +++ b/Documentation/sphinx/kernel_feat.py @@ -109,7 +109,7 @@ class KernelFeat(Directive): else: out_lines += line + "\n" - nodeList = self.nestedParse(out_lines, fname) + nodeList = self.nestedParse(out_lines, self.arguments[0]) return nodeList def nestedParse(self, lines, fname): From 4ce6e2db00de8103a0687fb0f65fd17124a51aaa Mon Sep 17 00:00:00 2001 From: Yi Sun Date: Mon, 29 Jan 2024 16:52:50 +0800 Subject: [PATCH 174/311] virtio-blk: Ensure no requests in virtqueues before deleting vqs. Ensure no remaining requests in virtqueues before resetting vdev and deleting virtqueues. Otherwise these requests will never be completed. It may cause the system to become unresponsive. Function blk_mq_quiesce_queue() can ensure that requests have become in_flight status, but it cannot guarantee that requests have been processed by the device. Virtqueues should never be deleted before all requests become complete status. Function blk_mq_freeze_queue() ensure that all requests in virtqueues become complete status. And no requests can enter in virtqueues. Signed-off-by: Yi Sun Reviewed-by: Stefan Hajnoczi Link: https://lore.kernel.org/r/20240129085250.1550594-1-yi.sun@unisoc.com Signed-off-by: Jens Axboe --- drivers/block/virtio_blk.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 5bf98fd6a651..2bf14a0e2815 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -1593,14 +1593,15 @@ static int virtblk_freeze(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; + /* Ensure no requests in virtqueues before deleting vqs. */ + blk_mq_freeze_queue(vblk->disk->queue); + /* Ensure we don't receive any more interrupts */ virtio_reset_device(vdev); /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); - blk_mq_quiesce_queue(vblk->disk->queue); - vdev->config->del_vqs(vdev); kfree(vblk->vqs); @@ -1618,7 +1619,7 @@ static int virtblk_restore(struct virtio_device *vdev) virtio_device_ready(vdev); - blk_mq_unquiesce_queue(vblk->disk->queue); + blk_mq_unfreeze_queue(vblk->disk->queue); return 0; } #endif From 53c0441dd2c44ee93fddb5473885fd41e4bc2361 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 7 Feb 2024 12:59:02 +0100 Subject: [PATCH 175/311] dpll: fix possible deadlock during netlink dump operation Recently, I've been hitting following deadlock warning during dpll pin dump: [52804.637962] ====================================================== [52804.638536] WARNING: possible circular locking dependency detected [52804.639111] 6.8.0-rc2jiri+ #1 Not tainted [52804.639529] ------------------------------------------------------ [52804.640104] python3/2984 is trying to acquire lock: [52804.640581] ffff88810e642678 (nlk_cb_mutex-GENERIC){+.+.}-{3:3}, at: netlink_dump+0xb3/0x780 [52804.641417] but task is already holding lock: [52804.642010] ffffffff83bde4c8 (dpll_lock){+.+.}-{3:3}, at: dpll_lock_dumpit+0x13/0x20 [52804.642747] which lock already depends on the new lock. [52804.643551] the existing dependency chain (in reverse order) is: [52804.644259] -> #1 (dpll_lock){+.+.}-{3:3}: [52804.644836] lock_acquire+0x174/0x3e0 [52804.645271] __mutex_lock+0x119/0x1150 [52804.645723] dpll_lock_dumpit+0x13/0x20 [52804.646169] genl_start+0x266/0x320 [52804.646578] __netlink_dump_start+0x321/0x450 [52804.647056] genl_family_rcv_msg_dumpit+0x155/0x1e0 [52804.647575] genl_rcv_msg+0x1ed/0x3b0 [52804.648001] netlink_rcv_skb+0xdc/0x210 [52804.648440] genl_rcv+0x24/0x40 [52804.648831] netlink_unicast+0x2f1/0x490 [52804.649290] netlink_sendmsg+0x36d/0x660 [52804.649742] __sock_sendmsg+0x73/0xc0 [52804.650165] __sys_sendto+0x184/0x210 [52804.650597] __x64_sys_sendto+0x72/0x80 [52804.651045] do_syscall_64+0x6f/0x140 [52804.651474] entry_SYSCALL_64_after_hwframe+0x46/0x4e [52804.652001] -> #0 (nlk_cb_mutex-GENERIC){+.+.}-{3:3}: [52804.652650] check_prev_add+0x1ae/0x1280 [52804.653107] __lock_acquire+0x1ed3/0x29a0 [52804.653559] lock_acquire+0x174/0x3e0 [52804.653984] __mutex_lock+0x119/0x1150 [52804.654423] netlink_dump+0xb3/0x780 [52804.654845] __netlink_dump_start+0x389/0x450 [52804.655321] genl_family_rcv_msg_dumpit+0x155/0x1e0 [52804.655842] genl_rcv_msg+0x1ed/0x3b0 [52804.656272] netlink_rcv_skb+0xdc/0x210 [52804.656721] genl_rcv+0x24/0x40 [52804.657119] netlink_unicast+0x2f1/0x490 [52804.657570] netlink_sendmsg+0x36d/0x660 [52804.658022] __sock_sendmsg+0x73/0xc0 [52804.658450] __sys_sendto+0x184/0x210 [52804.658877] __x64_sys_sendto+0x72/0x80 [52804.659322] do_syscall_64+0x6f/0x140 [52804.659752] entry_SYSCALL_64_after_hwframe+0x46/0x4e [52804.660281] other info that might help us debug this: [52804.661077] Possible unsafe locking scenario: [52804.661671] CPU0 CPU1 [52804.662129] ---- ---- [52804.662577] lock(dpll_lock); [52804.662924] lock(nlk_cb_mutex-GENERIC); [52804.663538] lock(dpll_lock); [52804.664073] lock(nlk_cb_mutex-GENERIC); [52804.664490] The issue as follows: __netlink_dump_start() calls control->start(cb) with nlk->cb_mutex held. In control->start(cb) the dpll_lock is taken. Then nlk->cb_mutex is released and taken again in netlink_dump(), while dpll_lock still being held. That leads to ABBA deadlock when another CPU races with the same operation. Fix this by moving dpll_lock taking into dumpit() callback which ensures correct lock taking order. Fixes: 9d71b54b65b1 ("dpll: netlink: Add DPLL framework base functions") Signed-off-by: Jiri Pirko Reviewed-by: Arkadiusz Kubalewski Link: https://lore.kernel.org/r/20240207115902.371649-1-jiri@resnulli.us Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/dpll.yaml | 4 ---- drivers/dpll/dpll_netlink.c | 20 ++++++-------------- drivers/dpll/dpll_nl.c | 4 ---- drivers/dpll/dpll_nl.h | 2 -- 4 files changed, 6 insertions(+), 24 deletions(-) diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index b14aed18065f..3dcc9ece272a 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -384,8 +384,6 @@ operations: - type dump: - pre: dpll-lock-dumpit - post: dpll-unlock-dumpit reply: *dev-attrs - @@ -473,8 +471,6 @@ operations: - fractional-frequency-offset dump: - pre: dpll-lock-dumpit - post: dpll-unlock-dumpit request: attributes: - id diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 314bb3775465..4ca9ad16cd95 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -1199,6 +1199,7 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) unsigned long i; int ret = 0; + mutex_lock(&dpll_lock); xa_for_each_marked_start(&dpll_pin_xa, i, pin, DPLL_REGISTERED, ctx->idx) { if (!dpll_pin_available(pin)) @@ -1218,6 +1219,8 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } genlmsg_end(skb, hdr); } + mutex_unlock(&dpll_lock); + if (ret == -EMSGSIZE) { ctx->idx = i; return skb->len; @@ -1373,6 +1376,7 @@ int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) unsigned long i; int ret = 0; + mutex_lock(&dpll_lock); xa_for_each_marked_start(&dpll_device_xa, i, dpll, DPLL_REGISTERED, ctx->idx) { hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, @@ -1389,6 +1393,8 @@ int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } genlmsg_end(skb, hdr); } + mutex_unlock(&dpll_lock); + if (ret == -EMSGSIZE) { ctx->idx = i; return skb->len; @@ -1439,20 +1445,6 @@ dpll_unlock_doit(const struct genl_split_ops *ops, struct sk_buff *skb, mutex_unlock(&dpll_lock); } -int dpll_lock_dumpit(struct netlink_callback *cb) -{ - mutex_lock(&dpll_lock); - - return 0; -} - -int dpll_unlock_dumpit(struct netlink_callback *cb) -{ - mutex_unlock(&dpll_lock); - - return 0; -} - int dpll_pin_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c index eaee5be7aa64..1e95f5397cfc 100644 --- a/drivers/dpll/dpll_nl.c +++ b/drivers/dpll/dpll_nl.c @@ -95,9 +95,7 @@ static const struct genl_split_ops dpll_nl_ops[] = { }, { .cmd = DPLL_CMD_DEVICE_GET, - .start = dpll_lock_dumpit, .dumpit = dpll_nl_device_get_dumpit, - .done = dpll_unlock_dumpit, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, }, { @@ -129,9 +127,7 @@ static const struct genl_split_ops dpll_nl_ops[] = { }, { .cmd = DPLL_CMD_PIN_GET, - .start = dpll_lock_dumpit, .dumpit = dpll_nl_pin_get_dumpit, - .done = dpll_unlock_dumpit, .policy = dpll_pin_get_dump_nl_policy, .maxattr = DPLL_A_PIN_ID, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, diff --git a/drivers/dpll/dpll_nl.h b/drivers/dpll/dpll_nl.h index 92d4c9c4f788..f491262bee4f 100644 --- a/drivers/dpll/dpll_nl.h +++ b/drivers/dpll/dpll_nl.h @@ -30,8 +30,6 @@ dpll_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, void dpll_pin_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); -int dpll_lock_dumpit(struct netlink_callback *cb); -int dpll_unlock_dumpit(struct netlink_callback *cb); int dpll_nl_device_id_get_doit(struct sk_buff *skb, struct genl_info *info); int dpll_nl_device_get_doit(struct sk_buff *skb, struct genl_info *info); From aa1eec2f546f2afa8c98ec41e5d8ee488165d685 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 6 Feb 2024 17:43:28 +0100 Subject: [PATCH 176/311] net/mlx5: DPLL, Fix possible use after free after delayed work timer triggers I managed to hit following use after free warning recently: [ 2169.711665] ================================================================== [ 2169.714009] BUG: KASAN: slab-use-after-free in __run_timers.part.0+0x179/0x4c0 [ 2169.716293] Write of size 8 at addr ffff88812b326a70 by task swapper/4/0 [ 2169.719022] CPU: 4 PID: 0 Comm: swapper/4 Not tainted 6.8.0-rc2jiri+ #2 [ 2169.720974] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 2169.722457] Call Trace: [ 2169.722756] [ 2169.723024] dump_stack_lvl+0x58/0xb0 [ 2169.723417] print_report+0xc5/0x630 [ 2169.723807] ? __virt_addr_valid+0x126/0x2b0 [ 2169.724268] kasan_report+0xbe/0xf0 [ 2169.724667] ? __run_timers.part.0+0x179/0x4c0 [ 2169.725116] ? __run_timers.part.0+0x179/0x4c0 [ 2169.725570] __run_timers.part.0+0x179/0x4c0 [ 2169.726003] ? call_timer_fn+0x320/0x320 [ 2169.726404] ? lock_downgrade+0x3a0/0x3a0 [ 2169.726820] ? kvm_clock_get_cycles+0x14/0x20 [ 2169.727257] ? ktime_get+0x92/0x150 [ 2169.727630] ? lapic_next_deadline+0x35/0x60 [ 2169.728069] run_timer_softirq+0x40/0x80 [ 2169.728475] __do_softirq+0x1a1/0x509 [ 2169.728866] irq_exit_rcu+0x95/0xc0 [ 2169.729241] sysvec_apic_timer_interrupt+0x6b/0x80 [ 2169.729718] [ 2169.729993] [ 2169.730259] asm_sysvec_apic_timer_interrupt+0x16/0x20 [ 2169.730755] RIP: 0010:default_idle+0x13/0x20 [ 2169.731190] Code: c0 08 00 00 00 4d 29 c8 4c 01 c7 4c 29 c2 e9 72 ff ff ff cc cc cc cc 8b 05 9a 7f 1f 02 85 c0 7e 07 0f 00 2d cf 69 43 00 fb f4 c3 66 66 2e 0f 1f 84 00 00 00 00 00 65 48 8b 04 25 c0 93 04 00 [ 2169.732759] RSP: 0018:ffff888100dbfe10 EFLAGS: 00000242 [ 2169.733264] RAX: 0000000000000001 RBX: ffff888100d9c200 RCX: ffffffff8241bd62 [ 2169.733925] RDX: ffffed109a848b15 RSI: 0000000000000004 RDI: ffffffff8127ac55 [ 2169.734566] RBP: 0000000000000004 R08: 0000000000000000 R09: ffffed109a848b14 [ 2169.735200] R10: ffff8884d42458a3 R11: 000000000000ba7e R12: ffffffff83d7d3a0 [ 2169.735835] R13: 1ffff110201b7fc6 R14: 0000000000000000 R15: ffff888100d9c200 [ 2169.736478] ? ct_kernel_exit.constprop.0+0xa2/0xc0 [ 2169.736954] ? do_idle+0x285/0x290 [ 2169.737323] default_idle_call+0x63/0x90 [ 2169.737730] do_idle+0x285/0x290 [ 2169.738089] ? arch_cpu_idle_exit+0x30/0x30 [ 2169.738511] ? mark_held_locks+0x1a/0x80 [ 2169.738917] ? lockdep_hardirqs_on_prepare+0x12e/0x200 [ 2169.739417] cpu_startup_entry+0x30/0x40 [ 2169.739825] start_secondary+0x19a/0x1c0 [ 2169.740229] ? set_cpu_sibling_map+0xbd0/0xbd0 [ 2169.740673] secondary_startup_64_no_verify+0x15d/0x16b [ 2169.741179] [ 2169.741686] Allocated by task 1098: [ 2169.742058] kasan_save_stack+0x1c/0x40 [ 2169.742456] kasan_save_track+0x10/0x30 [ 2169.742852] __kasan_kmalloc+0x83/0x90 [ 2169.743246] mlx5_dpll_probe+0xf5/0x3c0 [mlx5_dpll] [ 2169.743730] auxiliary_bus_probe+0x62/0xb0 [ 2169.744148] really_probe+0x127/0x590 [ 2169.744534] __driver_probe_device+0xd2/0x200 [ 2169.744973] device_driver_attach+0x6b/0xf0 [ 2169.745402] bind_store+0x90/0xe0 [ 2169.745761] kernfs_fop_write_iter+0x1df/0x2a0 [ 2169.746210] vfs_write+0x41f/0x790 [ 2169.746579] ksys_write+0xc7/0x160 [ 2169.746947] do_syscall_64+0x6f/0x140 [ 2169.747333] entry_SYSCALL_64_after_hwframe+0x46/0x4e [ 2169.748049] Freed by task 1220: [ 2169.748393] kasan_save_stack+0x1c/0x40 [ 2169.748789] kasan_save_track+0x10/0x30 [ 2169.749188] kasan_save_free_info+0x3b/0x50 [ 2169.749621] poison_slab_object+0x106/0x180 [ 2169.750044] __kasan_slab_free+0x14/0x50 [ 2169.750451] kfree+0x118/0x330 [ 2169.750792] mlx5_dpll_remove+0xf5/0x110 [mlx5_dpll] [ 2169.751271] auxiliary_bus_remove+0x2e/0x40 [ 2169.751694] device_release_driver_internal+0x24b/0x2e0 [ 2169.752191] unbind_store+0xa6/0xb0 [ 2169.752563] kernfs_fop_write_iter+0x1df/0x2a0 [ 2169.753004] vfs_write+0x41f/0x790 [ 2169.753381] ksys_write+0xc7/0x160 [ 2169.753750] do_syscall_64+0x6f/0x140 [ 2169.754132] entry_SYSCALL_64_after_hwframe+0x46/0x4e [ 2169.754847] Last potentially related work creation: [ 2169.755315] kasan_save_stack+0x1c/0x40 [ 2169.755709] __kasan_record_aux_stack+0x9b/0xf0 [ 2169.756165] __queue_work+0x382/0x8f0 [ 2169.756552] call_timer_fn+0x126/0x320 [ 2169.756941] __run_timers.part.0+0x2ea/0x4c0 [ 2169.757376] run_timer_softirq+0x40/0x80 [ 2169.757782] __do_softirq+0x1a1/0x509 [ 2169.758387] Second to last potentially related work creation: [ 2169.758924] kasan_save_stack+0x1c/0x40 [ 2169.759322] __kasan_record_aux_stack+0x9b/0xf0 [ 2169.759773] __queue_work+0x382/0x8f0 [ 2169.760156] call_timer_fn+0x126/0x320 [ 2169.760550] __run_timers.part.0+0x2ea/0x4c0 [ 2169.760978] run_timer_softirq+0x40/0x80 [ 2169.761381] __do_softirq+0x1a1/0x509 [ 2169.761998] The buggy address belongs to the object at ffff88812b326a00 which belongs to the cache kmalloc-256 of size 256 [ 2169.763061] The buggy address is located 112 bytes inside of freed 256-byte region [ffff88812b326a00, ffff88812b326b00) [ 2169.764346] The buggy address belongs to the physical page: [ 2169.764866] page:000000000f2b1e89 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x12b324 [ 2169.765731] head:000000000f2b1e89 order:2 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 2169.766484] anon flags: 0x200000000000840(slab|head|node=0|zone=2) [ 2169.767048] page_type: 0xffffffff() [ 2169.767422] raw: 0200000000000840 ffff888100042b40 0000000000000000 dead000000000001 [ 2169.768183] raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000 [ 2169.768899] page dumped because: kasan: bad access detected [ 2169.769649] Memory state around the buggy address: [ 2169.770116] ffff88812b326900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 2169.770805] ffff88812b326980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 2169.771485] >ffff88812b326a00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 2169.772173] ^ [ 2169.772787] ffff88812b326a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 2169.773477] ffff88812b326b00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 2169.774160] ================================================================== [ 2169.774845] ================================================================== I didn't manage to reproduce it. Though the issue seems to be obvious. There is a chance that the mlx5_dpll_remove() calls cancel_delayed_work() when the work runs and manages to re-arm itself. In that case, after delay timer triggers next attempt to queue it, it works with freed memory. Fix this by using cancel_delayed_work_sync() instead which makes sure that work is done when it returns. Fixes: 496fd0a26bbf ("mlx5: Implement SyncE support using DPLL infrastructure") Signed-off-by: Jiri Pirko Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240206164328.360313-1-jiri@resnulli.us Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/dpll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c index 18fed2b34fb1..928bf24d4b12 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c @@ -389,7 +389,7 @@ static void mlx5_dpll_remove(struct auxiliary_device *adev) struct mlx5_dpll *mdpll = auxiliary_get_drvdata(adev); struct mlx5_core_dev *mdev = mdpll->mdev; - cancel_delayed_work(&mdpll->work); + cancel_delayed_work_sync(&mdpll->work); mlx5_dpll_mdev_netdev_untrack(mdpll, mdev); destroy_workqueue(mdpll->wq); dpll_pin_unregister(mdpll->dpll, mdpll->dpll_pin, From 4e1d71cabb19ec2586827adfc60d68689c68c194 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 6 Feb 2024 14:16:31 -0500 Subject: [PATCH 177/311] net/handshake: Fix handshake_req_destroy_test1 Recently, handshake_req_destroy_test1 started failing: Expected handshake_req_destroy_test == req, but handshake_req_destroy_test == 0000000000000000 req == 0000000060f99b40 not ok 11 req_destroy works This is because "sock_release(sock)" was replaced with "fput(filp)" to address a memory leak. Note that sock_release() is synchronous but fput() usually delays the final close and clean-up. The delay is not consequential in the other cases that were changed but handshake_req_destroy_test1 is testing that handshake_req_cancel() followed by closing the file actually does call the ->hp_destroy method. Thus the PTR_EQ test at the end has to be sure that the final close is complete before it checks the pointer. We cannot use a completion here because if ->hp_destroy is never called (ie, there is an API bug) then the test will hang. Reported by: Guenter Roeck Closes: https://lore.kernel.org/netdev/ZcKDd1to4MPANCrn@tissot.1015granger.net/T/#mac5c6299f86799f1c71776f3a07f9c566c7c3c40 Fixes: 4a0f07d71b04 ("net/handshake: Fix memory leak in __sock_create() and sock_alloc_file()") Signed-off-by: Chuck Lever Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/170724699027.91401.7839730697326806733.stgit@oracle-102.nfsv4bat.org Signed-off-by: Jakub Kicinski --- net/handshake/handshake-test.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c index 16ed7bfd29e4..34fd1d9b2db8 100644 --- a/net/handshake/handshake-test.c +++ b/net/handshake/handshake-test.c @@ -471,7 +471,10 @@ static void handshake_req_destroy_test1(struct kunit *test) handshake_req_cancel(sock->sk); /* Act */ - fput(filp); + /* Ensure the close/release/put process has run to + * completion before checking the result. + */ + __fput_sync(filp); /* Assert */ KUNIT_EXPECT_PTR_EQ(test, handshake_req_destroy_test, req); From 9b0ed890ac2ae233efd8b27d11aee28a19437bb8 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 7 Feb 2024 09:47:36 +0100 Subject: [PATCH 178/311] bonding: do not report NETDEV_XDP_ACT_XSK_ZEROCOPY MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Do not report the XDP capability NETDEV_XDP_ACT_XSK_ZEROCOPY as the bonding driver does not support XDP and AF_XDP in zero-copy mode even if the real NIC drivers do. Note that the driver used to report everything as supported before a device was bonded. Instead of just masking out the zero-copy support from this, have the driver report that no XDP feature is supported until a real device is bonded. This seems to be more truthful as it is the real drivers that decide what XDP features are supported. Fixes: cb9e6e584d58 ("bonding: add xdp_features support") Reported-by: Prashant Batra Link: https://lore.kernel.org/all/CAJ8uoz2ieZCopgqTvQ9ZY6xQgTbujmC6XkMTamhp68O-h_-rLg@mail.gmail.com/T/ Signed-off-by: Magnus Karlsson Reviewed-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20240207084737.20890-1-magnus.karlsson@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 4e0600c7b050..a11748b8d69b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1819,6 +1819,8 @@ void bond_xdp_set_features(struct net_device *bond_dev) bond_for_each_slave(bond, slave, iter) val &= slave->dev->xdp_features; + val &= ~NETDEV_XDP_ACT_XSK_ZEROCOPY; + xdp_set_features_flag(bond_dev, val); } @@ -5909,9 +5911,6 @@ void bond_setup(struct net_device *bond_dev) if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) bond_dev->features |= BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ - - if (bond_xdp_check(bond)) - bond_dev->xdp_features = NETDEV_XDP_ACT_MASK; } /* Destroy a bonding device. From 4ab18af47a2c2a80ac11674122935700caf80cc6 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 6 Feb 2024 18:17:17 +0200 Subject: [PATCH 179/311] devlink: Fix command annotation documentation Command example string is not read as command. Fix command annotation. Fixes: a8ce7b26a51e ("devlink: Expose port function commands to control migratable") Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240206161717.466653-1-parav@nvidia.com Signed-off-by: Jakub Kicinski --- Documentation/networking/devlink/devlink-port.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index e33ad2401ad7..562f46b41274 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -126,7 +126,7 @@ Users may also set the RoCE capability of the function using `devlink port function set roce` command. Users may also set the function as migratable using -'devlink port function set migratable' command. +`devlink port function set migratable` command. Users may also set the IPsec crypto capability of the function using `devlink port function set ipsec_crypto` command. From 02d9009f4e8c27dcf10c3e39bc0666436686a219 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 7 Feb 2024 18:31:10 +0100 Subject: [PATCH 180/311] selftests: net: add more missing kernel config The reuseport_addr_any.sh is currently skipping DCCP tests and pmtu.sh is skipping all the FOU/GUE related cases: add the missing options. Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/38d3ca7f909736c1aef56e6244d67c82a9bba6ff.1707326987.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/config | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 3b749addd364..5e4390cac17e 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -24,10 +24,14 @@ CONFIG_IFB=y CONFIG_INET_DIAG=y CONFIG_INET_ESP=y CONFIG_INET_ESP_OFFLOAD=y +CONFIG_NET_FOU=y +CONFIG_NET_FOU_IP_TUNNELS=y CONFIG_IP_GRE=m CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=m +CONFIG_IPV6_SIT=y +CONFIG_IP_DCCP=m CONFIG_NF_NAT=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP_NF_IPTABLES=m @@ -62,6 +66,7 @@ CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_CLS_U32=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m +CONFIG_NET_IPIP=y CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_HTB=m CONFIG_NET_SCH_FQ=m @@ -78,7 +83,6 @@ CONFIG_TLS=m CONFIG_TRACEPOINTS=y CONFIG_NET_DROP_MONITOR=m CONFIG_NETDEVSIM=m -CONFIG_NET_FOU=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m CONFIG_NET_SCH_INGRESS=m From a8b9cf62ade1bf17261a979fc97e40c2d7842353 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Wed, 10 Jan 2024 09:13:06 +0900 Subject: [PATCH 181/311] ftrace: Fix DIRECT_CALLS to use SAVE_REGS by default The commit 60c8971899f3 ("ftrace: Make DIRECT_CALLS work WITH_ARGS and !WITH_REGS") changed DIRECT_CALLS to use SAVE_ARGS when there are multiple ftrace_ops at the same function, but since the x86 only support to jump to direct_call from ftrace_regs_caller, when we set the function tracer on the same target function on x86, ftrace-direct does not work as below (this actually works on arm64.) At first, insmod ftrace-direct.ko to put a direct_call on 'wake_up_process()'. # insmod kernel/samples/ftrace/ftrace-direct.ko # less trace ... -0 [006] ..s1. 564.686958: my_direct_func: waking up rcu_preempt-17 -0 [007] ..s1. 564.687836: my_direct_func: waking up kcompactd0-63 -0 [006] ..s1. 564.690926: my_direct_func: waking up rcu_preempt-17 -0 [006] ..s1. 564.696872: my_direct_func: waking up rcu_preempt-17 -0 [007] ..s1. 565.191982: my_direct_func: waking up kcompactd0-63 Setup a function filter to the 'wake_up_process' too, and enable it. # cd /sys/kernel/tracing/ # echo wake_up_process > set_ftrace_filter # echo function > current_tracer # less trace ... -0 [006] ..s3. 686.180972: wake_up_process <-call_timer_fn -0 [006] ..s3. 686.186919: wake_up_process <-call_timer_fn -0 [002] ..s3. 686.264049: wake_up_process <-call_timer_fn -0 [002] d.h6. 686.515216: wake_up_process <-kick_pool -0 [002] d.h6. 686.691386: wake_up_process <-kick_pool Then, only function tracer is shown on x86. But if you enable 'kprobe on ftrace' event (which uses SAVE_REGS flag) on the same function, it is shown again. # echo 'p wake_up_process' >> dynamic_events # echo 1 > events/kprobes/p_wake_up_process_0/enable # echo > trace # less trace ... -0 [006] ..s2. 2710.345919: p_wake_up_process_0: (wake_up_process+0x4/0x20) -0 [006] ..s3. 2710.345923: wake_up_process <-call_timer_fn -0 [006] ..s1. 2710.345928: my_direct_func: waking up rcu_preempt-17 -0 [006] ..s2. 2710.349931: p_wake_up_process_0: (wake_up_process+0x4/0x20) -0 [006] ..s3. 2710.349934: wake_up_process <-call_timer_fn -0 [006] ..s1. 2710.349937: my_direct_func: waking up rcu_preempt-17 To fix this issue, use SAVE_REGS flag for multiple ftrace_ops flag of direct_call by default. Link: https://lore.kernel.org/linux-trace-kernel/170484558617.178953.1590516949390270842.stgit@devnote2 Fixes: 60c8971899f3 ("ftrace: Make DIRECT_CALLS work WITH_ARGS and !WITH_REGS") Cc: stable@vger.kernel.org Cc: Florent Revest Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Mark Rutland Tested-by: Mark Rutland [arm64] Acked-by: Jiri Olsa Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b01ae7d36021..c060d5b47910 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5325,7 +5325,17 @@ static LIST_HEAD(ftrace_direct_funcs); static int register_ftrace_function_nolock(struct ftrace_ops *ops); +/* + * If there are multiple ftrace_ops, use SAVE_REGS by default, so that direct + * call will be jumped from ftrace_regs_caller. Only if the architecture does + * not support ftrace_regs_caller but direct_call, use SAVE_ARGS so that it + * jumps from ftrace_caller for multiple ftrace_ops. + */ +#ifndef HAVE_DYNAMIC_FTRACE_WITH_REGS #define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_ARGS) +#else +#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS) +#endif static int check_direct_multi(struct ftrace_ops *ops) { From f4653ec9861cd96a1a6a3258c4a807898ee8cf3c Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Tue, 6 Feb 2024 17:18:00 -0800 Subject: [PATCH 182/311] of: property: Improve finding the consumer of a remote-endpoint property We have a more accurate function to find the right consumer of a remote-endpoint property instead of searching for a parent with compatible string property. So, use that instead. While at it, make the code to find the consumer a bit more flexible and based on the property being parsed. Fixes: f7514a663016 ("of: property: fw_devlink: Add support for remote-endpoint") Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20240207011803.2637531-2-saravanak@google.com Signed-off-by: Rob Herring --- drivers/of/property.c | 47 +++++++++---------------------------------- 1 file changed, 10 insertions(+), 37 deletions(-) diff --git a/drivers/of/property.c b/drivers/of/property.c index bbf0dee2fb9c..773304be5ca6 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1063,36 +1063,6 @@ of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, return of_device_get_match_data(dev); } -static struct device_node *of_get_compat_node(struct device_node *np) -{ - of_node_get(np); - - while (np) { - if (!of_device_is_available(np)) { - of_node_put(np); - np = NULL; - } - - if (of_property_present(np, "compatible")) - break; - - np = of_get_next_parent(np); - } - - return np; -} - -static struct device_node *of_get_compat_node_parent(struct device_node *np) -{ - struct device_node *parent, *node; - - parent = of_get_parent(np); - node = of_get_compat_node(parent); - of_node_put(parent); - - return node; -} - static void of_link_to_phandle(struct device_node *con_np, struct device_node *sup_np) { @@ -1222,10 +1192,10 @@ static struct device_node *parse_##fname(struct device_node *np, \ * parse_prop.prop_name: Name of property holding a phandle value * parse_prop.index: For properties holding a list of phandles, this is the * index into the list + * @get_con_dev: If the consumer node containing the property is never converted + * to a struct device, implement this ops so fw_devlink can use it + * to find the true consumer. * @optional: Describes whether a supplier is mandatory or not - * @node_not_dev: The consumer node containing the property is never converted - * to a struct device. Instead, parse ancestor nodes for the - * compatible property to find a node corresponding to a device. * * Returns: * parse_prop() return values are @@ -1236,8 +1206,8 @@ static struct device_node *parse_##fname(struct device_node *np, \ struct supplier_bindings { struct device_node *(*parse_prop)(struct device_node *np, const char *prop_name, int index); + struct device_node *(*get_con_dev)(struct device_node *np); bool optional; - bool node_not_dev; }; DEFINE_SIMPLE_PROP(clocks, "clocks", "#clock-cells") @@ -1352,7 +1322,10 @@ static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_pinctrl6, }, { .parse_prop = parse_pinctrl7, }, { .parse_prop = parse_pinctrl8, }, - { .parse_prop = parse_remote_endpoint, .node_not_dev = true, }, + { + .parse_prop = parse_remote_endpoint, + .get_con_dev = of_graph_get_port_parent, + }, { .parse_prop = parse_pwms, }, { .parse_prop = parse_resets, }, { .parse_prop = parse_leds, }, @@ -1403,8 +1376,8 @@ static int of_link_property(struct device_node *con_np, const char *prop_name) while ((phandle = s->parse_prop(con_np, prop_name, i))) { struct device_node *con_dev_np; - con_dev_np = s->node_not_dev - ? of_get_compat_node_parent(con_np) + con_dev_np = s->get_con_dev + ? s->get_con_dev(con_np) : of_node_get(con_np); matched = true; i++; From 782bfd03c3ae2c0e6e01b661b8e18f1de50357be Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Tue, 6 Feb 2024 17:18:01 -0800 Subject: [PATCH 183/311] of: property: Improve finding the supplier of a remote-endpoint property After commit 4a032827daa8 ("of: property: Simplify of_link_to_phandle()"), remote-endpoint properties created a fwnode link from the consumer device to the supplier endpoint. This is a tiny bit inefficient (not buggy) when trying to create device links or detecting cycles. So, improve this the same way we improved finding the consumer of a remote-endpoint property. Fixes: 4a032827daa8 ("of: property: Simplify of_link_to_phandle()") Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20240207011803.2637531-3-saravanak@google.com Signed-off-by: Rob Herring --- drivers/of/property.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/of/property.c b/drivers/of/property.c index 773304be5ca6..a5f562a5e146 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1232,7 +1232,6 @@ DEFINE_SIMPLE_PROP(pinctrl5, "pinctrl-5", NULL) DEFINE_SIMPLE_PROP(pinctrl6, "pinctrl-6", NULL) DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL) DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL) -DEFINE_SIMPLE_PROP(remote_endpoint, "remote-endpoint", NULL) DEFINE_SIMPLE_PROP(pwms, "pwms", "#pwm-cells") DEFINE_SIMPLE_PROP(resets, "resets", "#reset-cells") DEFINE_SIMPLE_PROP(leds, "leds", NULL) @@ -1298,6 +1297,17 @@ static struct device_node *parse_interrupts(struct device_node *np, return of_irq_parse_one(np, index, &sup_args) ? NULL : sup_args.np; } +static struct device_node *parse_remote_endpoint(struct device_node *np, + const char *prop_name, + int index) +{ + /* Return NULL for index > 0 to signify end of remote-endpoints. */ + if (!index || strcmp(prop_name, "remote-endpoint")) + return NULL; + + return of_graph_get_remote_port_parent(np); +} + static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_clocks, }, { .parse_prop = parse_interconnects, }, From 8f1e0d791b5281f3a38620bc7c57763dc551be15 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Tue, 6 Feb 2024 17:18:02 -0800 Subject: [PATCH 184/311] of: property: Add in-ports/out-ports support to of_graph_get_port_parent() Similar to the existing "ports" node name, coresight device tree bindings have added "in-ports" and "out-ports" as standard node names for a collection of ports. Add support for these name to of_graph_get_port_parent() so that remote-endpoint parsing can find the correct parent node for these coresight ports too. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20240207011803.2637531-4-saravanak@google.com Signed-off-by: Rob Herring --- drivers/of/property.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/of/property.c b/drivers/of/property.c index a5f562a5e146..b71267c6667c 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -763,7 +763,9 @@ struct device_node *of_graph_get_port_parent(struct device_node *node) /* Walk 3 levels up only if there is 'ports' node. */ for (depth = 3; depth && node; depth--) { node = of_get_next_parent(node); - if (depth == 2 && !of_node_name_eq(node, "ports")) + if (depth == 2 && !of_node_name_eq(node, "ports") && + !of_node_name_eq(node, "in-ports") && + !of_node_name_eq(node, "out-ports")) break; } return node; From 44dc5c41b5b1267d4dd037d26afc0c4d3a568acb Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 9 Feb 2024 06:36:22 -0500 Subject: [PATCH 185/311] tracing: Fix wasted memory in saved_cmdlines logic While looking at improving the saved_cmdlines cache I found a huge amount of wasted memory that should be used for the cmdlines. The tracing data saves pids during the trace. At sched switch, if a trace occurred, it will save the comm of the task that did the trace. This is saved in a "cache" that maps pids to comms and exposed to user space via the /sys/kernel/tracing/saved_cmdlines file. Currently it only caches by default 128 comms. The structure that uses this creates an array to store the pids using PID_MAX_DEFAULT (which is usually set to 32768). This causes the structure to be of the size of 131104 bytes on 64 bit machines. In hex: 131104 = 0x20020, and since the kernel allocates generic memory in powers of two, the kernel would allocate 0x40000 or 262144 bytes to store this structure. That leaves 131040 bytes of wasted space. Worse, the structure points to an allocated array to store the comm names, which is 16 bytes times the amount of names to save (currently 128), which is 2048 bytes. Instead of allocating a separate array, make the structure end with a variable length string and use the extra space for that. This is similar to a recommendation that Linus had made about eventfs_inode names: https://lore.kernel.org/all/20240130190355.11486-5-torvalds@linux-foundation.org/ Instead of allocating a separate string array to hold the saved comms, have the structure end with: char saved_cmdlines[]; and round up to the next power of two over sizeof(struct saved_cmdline_buffers) + num_cmdlines * TASK_COMM_LEN It will use this extra space for the saved_cmdline portion. Now, instead of saving only 128 comms by default, by using this wasted space at the end of the structure it can save over 8000 comms and even saves space by removing the need for allocating the other array. Link: https://lore.kernel.org/linux-trace-kernel/20240209063622.1f7b6d5f@rorschach.local.home Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Vincent Donnefort Cc: Sven Schnelle Cc: Mete Durlu Fixes: 939c7a4f04fcd ("tracing: Introduce saved_cmdlines_size file") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 75 ++++++++++++++++++++++---------------------- 1 file changed, 37 insertions(+), 38 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2a7c6fd934e9..9ff8a439d674 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2320,7 +2320,7 @@ struct saved_cmdlines_buffer { unsigned *map_cmdline_to_pid; unsigned cmdline_num; int cmdline_idx; - char *saved_cmdlines; + char saved_cmdlines[]; }; static struct saved_cmdlines_buffer *savedcmd; @@ -2334,47 +2334,58 @@ static inline void set_cmdline(int idx, const char *cmdline) strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN); } -static int allocate_cmdlines_buffer(unsigned int val, - struct saved_cmdlines_buffer *s) +static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) { + int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN); + + kfree(s->map_cmdline_to_pid); + free_pages((unsigned long)s, order); +} + +static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) +{ + struct saved_cmdlines_buffer *s; + struct page *page; + int orig_size, size; + int order; + + /* Figure out how much is needed to hold the given number of cmdlines */ + orig_size = sizeof(*s) + val * TASK_COMM_LEN; + order = get_order(orig_size); + size = 1 << (order + PAGE_SHIFT); + page = alloc_pages(GFP_KERNEL, order); + if (!page) + return NULL; + + s = page_address(page); + memset(s, 0, sizeof(*s)); + + /* Round up to actual allocation */ + val = (size - sizeof(*s)) / TASK_COMM_LEN; + s->cmdline_num = val; + s->map_cmdline_to_pid = kmalloc_array(val, sizeof(*s->map_cmdline_to_pid), GFP_KERNEL); - if (!s->map_cmdline_to_pid) - return -ENOMEM; - - s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL); - if (!s->saved_cmdlines) { - kfree(s->map_cmdline_to_pid); - return -ENOMEM; + if (!s->map_cmdline_to_pid) { + free_saved_cmdlines_buffer(s); + return NULL; } s->cmdline_idx = 0; - s->cmdline_num = val; memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(s->map_pid_to_cmdline)); memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP, val * sizeof(*s->map_cmdline_to_pid)); - return 0; + return s; } static int trace_create_savedcmd(void) { - int ret; + savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT); - savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL); - if (!savedcmd) - return -ENOMEM; - - ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd); - if (ret < 0) { - kfree(savedcmd); - savedcmd = NULL; - return -ENOMEM; - } - - return 0; + return savedcmd ? 0 : -ENOMEM; } int is_tracing_stopped(void) @@ -6056,26 +6067,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } -static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) -{ - kfree(s->saved_cmdlines); - kfree(s->map_cmdline_to_pid); - kfree(s); -} - static int tracing_resize_saved_cmdlines(unsigned int val) { struct saved_cmdlines_buffer *s, *savedcmd_temp; - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = allocate_cmdlines_buffer(val); if (!s) return -ENOMEM; - if (allocate_cmdlines_buffer(val, s) < 0) { - kfree(s); - return -ENOMEM; - } - preempt_disable(); arch_spin_lock(&trace_cmdline_lock); savedcmd_temp = savedcmd; From 9f208e097801f9c2088eb339a1162fff81c08b4e Mon Sep 17 00:00:00 2001 From: Christian Lamparter Date: Fri, 9 Feb 2024 15:59:07 +0100 Subject: [PATCH 186/311] spi: spi-ppc4xx: include missing platform_device.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit the driver currently fails to compile on 6.8-rc3 due to: | spi-ppc4xx.c: In function ‘spi_ppc4xx_of_probe’: | @346:36: error: invalid use of undefined type ‘struct platform_device’ | 346 | struct device_node *np = op->dev.of_node; | | ^~ | ... (more similar errors) it was working with 6.7. Looks like it only needed the include and its compiling fine! Signed-off-by: Christian Lamparter Link: https://lore.kernel.org/r/3eb3f9c4407ba99d1cd275662081e46b9e839173.1707490664.git.chunkeey@gmail.com Signed-off-by: Mark Brown --- drivers/spi/spi-ppc4xx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c index 03aab661be9d..412d6e678224 100644 --- a/drivers/spi/spi-ppc4xx.c +++ b/drivers/spi/spi-ppc4xx.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include From f6a1892585cd19e63c4ef2334e26cd536d5b678d Mon Sep 17 00:00:00 2001 From: Aleksander Mazur Date: Tue, 23 Jan 2024 14:43:00 +0100 Subject: [PATCH 187/311] x86/Kconfig: Transmeta Crusoe is CPU family 5, not 6 The kernel built with MCRUSOE is unbootable on Transmeta Crusoe. It shows the following error message: This kernel requires an i686 CPU, but only detected an i586 CPU. Unable to boot - please use a kernel appropriate for your CPU. Remove MCRUSOE from the condition introduced in commit in Fixes, effectively changing X86_MINIMUM_CPU_FAMILY back to 5 on that machine, which matches the CPU family given by CPUID. [ bp: Massage commit message. ] Fixes: 25d76ac88821 ("x86/Kconfig: Explicitly enumerate i686-class CPUs in Kconfig") Signed-off-by: Aleksander Mazur Signed-off-by: Borislav Petkov (AMD) Acked-by: H. Peter Anvin Cc: Link: https://lore.kernel.org/r/20240123134309.1117782-1-deweloper@wp.pl --- arch/x86/Kconfig.cpu | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index b9224cf2ee4d..2a7279d80460 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -379,7 +379,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" From 5571e41ec6e56e35f34ae9f5b3a335ef510e0ade Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 31 Jan 2024 14:27:25 -0500 Subject: [PATCH 188/311] btrfs: don't drop extent_map for free space inode on write error While running the CI for an unrelated change I hit the following panic with generic/648 on btrfs_holes_spacecache. assertion failed: block_start != EXTENT_MAP_HOLE, in fs/btrfs/extent_io.c:1385 ------------[ cut here ]------------ kernel BUG at fs/btrfs/extent_io.c:1385! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 1 PID: 2695096 Comm: fsstress Kdump: loaded Tainted: G W 6.8.0-rc2+ #1 RIP: 0010:__extent_writepage_io.constprop.0+0x4c1/0x5c0 Call Trace: extent_write_cache_pages+0x2ac/0x8f0 extent_writepages+0x87/0x110 do_writepages+0xd5/0x1f0 filemap_fdatawrite_wbc+0x63/0x90 __filemap_fdatawrite_range+0x5c/0x80 btrfs_fdatawrite_range+0x1f/0x50 btrfs_write_out_cache+0x507/0x560 btrfs_write_dirty_block_groups+0x32a/0x420 commit_cowonly_roots+0x21b/0x290 btrfs_commit_transaction+0x813/0x1360 btrfs_sync_file+0x51a/0x640 __x64_sys_fdatasync+0x52/0x90 do_syscall_64+0x9c/0x190 entry_SYSCALL_64_after_hwframe+0x6e/0x76 This happens because we fail to write out the free space cache in one instance, come back around and attempt to write it again. However on the second pass through we go to call btrfs_get_extent() on the inode to get the extent mapping. Because this is a new block group, and with the free space inode we always search the commit root to avoid deadlocking with the tree, we find nothing and return a EXTENT_MAP_HOLE for the requested range. This happens because the first time we try to write the space cache out we hit an error, and on an error we drop the extent mapping. This is normal for normal files, but the free space cache inode is special. We always expect the extent map to be correct. Thus the second time through we end up with a bogus extent map. Since we're deprecating this feature, the most straightforward way to fix this is to simply skip dropping the extent map range for this failed range. I shortened the test by using error injection to stress the area to make it easier to reproduce. With this patch in place we no longer panic with my error injection test. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/inode.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7bcc1c03437a..d232eca1bbee 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3184,8 +3184,23 @@ out: unwritten_start += logical_len; clear_extent_uptodate(io_tree, unwritten_start, end, NULL); - /* Drop extent maps for the part of the extent we didn't write. */ - btrfs_drop_extent_map_range(inode, unwritten_start, end, false); + /* + * Drop extent maps for the part of the extent we didn't write. + * + * We have an exception here for the free_space_inode, this is + * because when we do btrfs_get_extent() on the free space inode + * we will search the commit root. If this is a new block group + * we won't find anything, and we will trip over the assert in + * writepage where we do ASSERT(em->block_start != + * EXTENT_MAP_HOLE). + * + * Theoretically we could also skip this for any NOCOW extent as + * we don't mess with the extent map tree in the NOCOW case, but + * for now simply skip this if we are the free space inode. + */ + if (!btrfs_is_free_space_inode(inode)) + btrfs_drop_extent_map_range(inode, unwritten_start, + end, false); /* * If the ordered extent had an IOERR or something else went From 1693d5442c458ae8d5b0d58463b873cd879569ed Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 25 Jan 2024 09:53:06 +0000 Subject: [PATCH 189/311] btrfs: add and use helper to check if block group is used Add a helper function to determine if a block group is being used and make use of it at btrfs_delete_unused_bgs(). This helper will also be used in future code changes. Reviewed-by: Johannes Thumshirn Reviewed-by: Josef Bacik Reviewed-by: Boris Burkov Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 3 +-- fs/btrfs/block-group.h | 7 +++++++ 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index a9be9ac99222..9daef18bcbbc 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1512,8 +1512,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) } spin_lock(&block_group->lock); - if (block_group->reserved || block_group->pinned || - block_group->used || block_group->ro || + if (btrfs_is_block_group_used(block_group) || block_group->ro || list_is_singular(&block_group->list)) { /* * We want to bail if we made new allocations or have diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index c4a1f01cc1c2..962b11983901 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -257,6 +257,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) return (block_group->start + block_group->length); } +static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg) +{ + lockdep_assert_held(&bg->lock); + + return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0); +} + static inline bool btrfs_is_block_group_data_only( struct btrfs_block_group *block_group) { From f4a9f219411f318ae60d6ff7f129082a75686c6c Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 25 Jan 2024 09:53:14 +0000 Subject: [PATCH 190/311] btrfs: do not delete unused block group if it may be used soon Before deleting a block group that is in the list of unused block groups (fs_info->unused_bgs), we check if the block group became used before deleting it, as extents from it may have been allocated after it was added to the list. However even if the block group was not yet used, there may be tasks that have only reserved space and have not yet allocated extents, and they might be relying on the availability of the unused block group in order to allocate extents. The reservation works first by increasing the "bytes_may_use" field of the corresponding space_info object (which may first require flushing delayed items, allocating a new block group, etc), and only later a task does the actual allocation of extents. For metadata we usually don't end up using all reserved space, as we are pessimistic and typically account for the worst cases (need to COW every single node in a path of a tree at maximum possible height, etc). For data we usually reserve the exact amount of space we're going to allocate later, except when using compression where we always reserve space based on the uncompressed size, as compression is only triggered when writeback starts so we don't know in advance how much space we'll actually need, or if the data is compressible. So don't delete an unused block group if the total size of its space_info object minus the block group's size is less then the sum of used space and space that may be used (space_info->bytes_may_use), as that means we have tasks that reserved space and may need to allocate extents from the block group. In this case, besides skipping the deletion, re-add the block group to the list of unused block groups so that it may be reconsidered later, in case the tasks that reserved space end up not needing to allocate extents from it. Allowing the deletion of the block group while we have reserved space, can result in tasks failing to allocate metadata extents (-ENOSPC) while under a transaction handle, resulting in a transaction abort, or failure during writeback for the case of data extents. CC: stable@vger.kernel.org # 6.0+ Reviewed-by: Johannes Thumshirn Reviewed-by: Josef Bacik Reviewed-by: Boris Burkov Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 46 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 9daef18bcbbc..5fe37bc82f11 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1455,6 +1455,7 @@ out: */ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) { + LIST_HEAD(retry_list); struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; struct btrfs_trans_handle *trans; @@ -1476,6 +1477,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->unused_bgs)) { + u64 used; int trimming; block_group = list_first_entry(&fs_info->unused_bgs, @@ -1511,6 +1513,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) goto next; } + spin_lock(&space_info->lock); spin_lock(&block_group->lock); if (btrfs_is_block_group_used(block_group) || block_group->ro || list_is_singular(&block_group->list)) { @@ -1522,10 +1525,49 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) */ trace_btrfs_skip_unused_block_group(block_group); spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); up_write(&space_info->groups_sem); goto next; } + + /* + * The block group may be unused but there may be space reserved + * accounting with the existence of that block group, that is, + * space_info->bytes_may_use was incremented by a task but no + * space was yet allocated from the block group by the task. + * That space may or may not be allocated, as we are generally + * pessimistic about space reservation for metadata as well as + * for data when using compression (as we reserve space based on + * the worst case, when data can't be compressed, and before + * actually attempting compression, before starting writeback). + * + * So check if the total space of the space_info minus the size + * of this block group is less than the used space of the + * space_info - if that's the case, then it means we have tasks + * that might be relying on the block group in order to allocate + * extents, and add back the block group to the unused list when + * we finish, so that we retry later in case no tasks ended up + * needing to allocate extents from the block group. + */ + used = btrfs_space_info_used(space_info, true); + if (space_info->total_bytes - block_group->length < used) { + /* + * Add a reference for the list, compensate for the ref + * drop under the "next" label for the + * fs_info->unused_bgs list. + */ + btrfs_get_block_group(block_group); + list_add_tail(&block_group->bg_list, &retry_list); + + trace_btrfs_skip_unused_block_group(block_group); + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); + up_write(&space_info->groups_sem); + goto next; + } + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); /* We don't want to force the issue, only flip if it's ok. */ ret = inc_block_group_ro(block_group, 0); @@ -1649,12 +1691,16 @@ next: btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } + list_splice_tail(&retry_list, &fs_info->unused_bgs); spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); return; flip_async: btrfs_end_transaction(trans); + spin_lock(&fs_info->unused_bgs_lock); + list_splice_tail(&retry_list, &fs_info->unused_bgs); + spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); btrfs_put_block_group(block_group); btrfs_discard_punt_unused_bgs_list(fs_info); From 12c5128f101bfa47a08e4c0e1a75cfa2d0872bcd Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 25 Jan 2024 09:53:19 +0000 Subject: [PATCH 191/311] btrfs: add new unused block groups to the list of unused block groups Space reservations for metadata are, most of the time, pessimistic as we reserve space for worst possible cases - where tree heights are at the maximum possible height (8), we need to COW every extent buffer in a tree path, need to split extent buffers, etc. For data, we generally reserve the exact amount of space we are going to allocate. The exception here is when using compression, in which case we reserve space matching the uncompressed size, as the compression only happens at writeback time and in the worst possible case we need that amount of space in case the data is not compressible. This means that when there's not available space in the corresponding space_info object, we may need to allocate a new block group, and then that block group might not be used after all. In this case the block group is never added to the list of unused block groups and ends up never being deleted - except if we unmount and mount again the fs, as when reading block groups from disk we add unused ones to the list of unused block groups (fs_info->unused_bgs). Otherwise a block group is only added to the list of unused block groups when we deallocate the last extent from it, so if no extent is ever allocated, the block group is kept around forever. This also means that if we have a bunch of tasks reserving space in parallel we can end up allocating many block groups that end up never being used or kept around for too long without being used, which has the potential to result in ENOSPC failures in case for example we over allocate too many metadata block groups and then end up in a state without enough unallocated space to allocate a new data block group. This is more likely to happen with metadata reservations as of kernel 6.7, namely since commit 28270e25c69a ("btrfs: always reserve space for delayed refs when starting transaction"), because we started to always reserve space for delayed references when starting a transaction handle for a non-zero number of items, and also to try to reserve space to fill the gap between the delayed block reserve's reserved space and its size. So to avoid this, when finishing the creation a new block group, add the block group to the list of unused block groups if it's still unused at that time. This way the next time the cleaner kthread runs, it will delete the block group if it's still unused and not needed to satisfy existing space reservations. Reported-by: Ivan Shapovalov Link: https://lore.kernel.org/linux-btrfs/9cdbf0ca9cdda1b4c84e15e548af7d7f9f926382.camel@intelfx.name/ CC: stable@vger.kernel.org # 6.7+ Reviewed-by: Johannes Thumshirn Reviewed-by: Josef Bacik Reviewed-by: Boris Burkov Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 5fe37bc82f11..378d9103a207 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2729,6 +2729,37 @@ next: btrfs_dec_delayed_refs_rsv_bg_inserts(fs_info); list_del_init(&block_group->bg_list); clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags); + + /* + * If the block group is still unused, add it to the list of + * unused block groups. The block group may have been created in + * order to satisfy a space reservation, in which case the + * extent allocation only happens later. But often we don't + * actually need to allocate space that we previously reserved, + * so the block group may become unused for a long time. For + * example for metadata we generally reserve space for a worst + * possible scenario, but then don't end up allocating all that + * space or none at all (due to no need to COW, extent buffers + * were already COWed in the current transaction and still + * unwritten, tree heights lower than the maximum possible + * height, etc). For data we generally reserve the axact amount + * of space we are going to allocate later, the exception is + * when using compression, as we must reserve space based on the + * uncompressed data size, because the compression is only done + * when writeback triggered and we don't know how much space we + * are actually going to need, so we reserve the uncompressed + * size because the data may be uncompressible in the worst case. + */ + if (ret == 0) { + bool used; + + spin_lock(&block_group->lock); + used = btrfs_is_block_group_used(block_group); + spin_unlock(&block_group->lock); + + if (!used) + btrfs_mark_bg_unused(block_group); + } } btrfs_trans_release_chunk_metadata(trans); } From 38ee0cb2a2e2ade077442085638eb181b0562971 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 8 Feb 2024 14:31:10 +0200 Subject: [PATCH 192/311] selftests: net: Fix bridge backup port test flakiness The test toggles the carrier of a bridge port in order to test the bridge backup port feature. Due to the linkwatch delayed work the carrier change is not always reflected fast enough to the bridge driver and packets are not forwarded as the test expects, resulting in failures [1]. Fix by busy waiting on the bridge port state until it changes to the desired state following the carrier change. [1] # Backup port # ----------- [...] # TEST: swp1 carrier off [ OK ] # TEST: No forwarding out of swp1 [FAIL] [ 641.995910] br0: port 1(swp1) entered disabled state # TEST: No forwarding out of vx0 [ OK ] Fixes: b408453053fb ("selftests: net: Add bridge backup port and backup nexthop ID test") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Acked-by: Paolo Abeni Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20240208123110.1063930-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- .../selftests/net/test_bridge_backup_port.sh | 23 +++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/tools/testing/selftests/net/test_bridge_backup_port.sh b/tools/testing/selftests/net/test_bridge_backup_port.sh index 70a7d87ba2d2..1b3f89e2b86e 100755 --- a/tools/testing/selftests/net/test_bridge_backup_port.sh +++ b/tools/testing/selftests/net/test_bridge_backup_port.sh @@ -124,6 +124,16 @@ tc_check_packets() [[ $pkts == $count ]] } +bridge_link_check() +{ + local ns=$1; shift + local dev=$1; shift + local state=$1; shift + + bridge -n $ns -d -j link show dev $dev | \ + jq -e ".[][\"state\"] == \"$state\"" &> /dev/null +} + ################################################################################ # Setup @@ -259,6 +269,7 @@ backup_port() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" @@ -268,6 +279,7 @@ backup_port() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding log_test $? 0 "swp1 carrier on" # Configure vx0 as the backup port of swp1 and check that packets are @@ -284,6 +296,7 @@ backup_port() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" @@ -293,6 +306,7 @@ backup_port() log_test $? 0 "Forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding log_test $? 0 "swp1 carrier on" run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" @@ -314,6 +328,7 @@ backup_port() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" @@ -369,6 +384,7 @@ backup_nhid() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" @@ -382,6 +398,7 @@ backup_nhid() log_test $? 0 "Forwarding using VXLAN FDB entry" run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding log_test $? 0 "swp1 carrier on" # Configure nexthop ID 10 as the backup nexthop ID of swp1 and check @@ -398,6 +415,7 @@ backup_nhid() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" @@ -411,6 +429,7 @@ backup_nhid() log_test $? 0 "No forwarding using VXLAN FDB entry" run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding log_test $? 0 "swp1 carrier on" run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" @@ -441,6 +460,7 @@ backup_nhid() log_test $? 0 "No forwarding using VXLAN FDB entry" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" @@ -497,6 +517,7 @@ backup_nhid_invalid() log_test $? 0 "Valid nexthop as backup nexthop" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" @@ -604,7 +625,9 @@ backup_nhid_ping() run_cmd "bridge -n $sw2 link set dev swp1 backup_nhid 10" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled run_cmd "ip -n $sw2 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw2 swp1 disabled run_cmd "ip netns exec $sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66" log_test $? 0 "Ping with backup nexthop ID" From 93590849a05edffaefa11695fab98f621259ded2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 8 Feb 2024 17:55:26 +0200 Subject: [PATCH 193/311] selftests: forwarding: Fix layer 2 miss test flakiness After enabling a multicast querier on the bridge (like the test is doing), the bridge will wait for the Max Response Delay before starting to forward according to its MDB in order to let Membership Reports enough time to be received and processed. Currently, the test is waiting for exactly the default Max Response Delay (10 seconds) which is racy and leads to failures [1]. Fix by reducing the Max Response Delay to 1 second. [1] [...] # TEST: L2 miss - Multicast (IPv4) [FAIL] # Unregistered multicast filter was hit after adding MDB entry Fixes: 8c33266ae26a ("selftests: forwarding: Add layer 2 miss test cases") Signed-off-by: Ido Schimmel Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20240208155529.1199729-2-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/forwarding/tc_flower_l2_miss.sh | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh index 20a7cb7222b8..c2420bb72c12 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -209,14 +209,17 @@ test_l2_miss_multicast() # both registered and unregistered multicast traffic. bridge link set dev $swp2 mcast_router 2 + # Set the Max Response Delay to 100 centiseconds (1 second) so that the + # bridge will start forwarding according to its MDB soon after a + # multicast querier is enabled. + ip link set dev br1 type bridge mcast_query_response_interval 100 + # Forwarding according to MDB entries only takes place when the bridge # detects that there is a valid querier in the network. Set the bridge # as the querier and assign it a valid IPv6 link-local address to be # used as the source address for MLD queries. ip link set dev br1 type bridge mcast_querier 1 ip -6 address add fe80::1/64 nodad dev br1 - # Wait the default Query Response Interval (10 seconds) for the bridge - # to determine that there are no other queriers in the network. sleep 10 test_l2_miss_multicast_ipv4 @@ -224,6 +227,7 @@ test_l2_miss_multicast() ip -6 address del fe80::1/64 dev br1 ip link set dev br1 type bridge mcast_querier 0 + ip link set dev br1 type bridge mcast_query_response_interval 1000 bridge link set dev $swp2 mcast_router 1 } From 7399e2ce4d424f426417496eb289458780eea985 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 8 Feb 2024 17:55:27 +0200 Subject: [PATCH 194/311] selftests: forwarding: Fix bridge MDB test flakiness After enabling a multicast querier on the bridge (like the test is doing), the bridge will wait for the Max Response Delay before starting to forward according to its MDB in order to let Membership Reports enough time to be received and processed. Currently, the test is waiting for exactly the default Max Response Delay (10 seconds) which is racy and leads to failures [1]. Fix by reducing the Max Response Delay to 1 second. [1] [...] # TEST: IPv4 host entries forwarding tests [FAIL] # Packet locally received after flood Fixes: b6d00da08610 ("selftests: forwarding: Add bridge MDB test") Signed-off-by: Ido Schimmel Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20240208155529.1199729-3-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/bridge_mdb.sh | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index 61348f71728c..f94bfb6f45ec 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -1252,14 +1252,17 @@ fwd_test() echo log_info "# Forwarding tests" + # Set the Max Response Delay to 100 centiseconds (1 second) so that the + # bridge will start forwarding according to its MDB soon after a + # multicast querier is enabled. + ip link set dev br0 type bridge mcast_query_response_interval 100 + # Forwarding according to MDB entries only takes place when the bridge # detects that there is a valid querier in the network. Set the bridge # as the querier and assign it a valid IPv6 link-local address to be # used as the source address for MLD queries. ip -6 address add fe80::1/64 nodad dev br0 ip link set dev br0 type bridge mcast_querier 1 - # Wait the default Query Response Interval (10 seconds) for the bridge - # to determine that there are no other queriers in the network. sleep 10 fwd_test_host @@ -1267,6 +1270,7 @@ fwd_test() ip link set dev br0 type bridge mcast_querier 0 ip -6 address del fe80::1/64 dev br0 + ip link set dev br0 type bridge mcast_query_response_interval 1000 } ctrl_igmpv3_is_in_test() From dd6b34589441f2ad4698dd88a664811550148b41 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 8 Feb 2024 17:55:28 +0200 Subject: [PATCH 195/311] selftests: forwarding: Suppress grep warnings Suppress the following grep warnings: [...] INFO: # Port group entries configuration tests - (*, G) TEST: Common port group entries configuration tests (IPv4 (*, G)) [ OK ] TEST: Common port group entries configuration tests (IPv6 (*, G)) [ OK ] grep: warning: stray \ before / grep: warning: stray \ before / grep: warning: stray \ before / TEST: IPv4 (*, G) port group entries configuration tests [ OK ] grep: warning: stray \ before / grep: warning: stray \ before / grep: warning: stray \ before / TEST: IPv6 (*, G) port group entries configuration tests [ OK ] [...] They do not fail the test, but do clutter the output. Fixes: b6d00da08610 ("selftests: forwarding: Add bridge MDB test") Signed-off-by: Ido Schimmel Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20240208155529.1199729-4-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/bridge_mdb.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index f94bfb6f45ec..d9d587454d20 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -329,7 +329,7 @@ __cfg_test_port_ip_star_g() bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00" check_err $? "(*, G) \"permanent\" entry has a pending group timer" - bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00" check_err $? "\"permanent\" source entry has a pending source timer" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -346,7 +346,7 @@ __cfg_test_port_ip_star_g() bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00" check_fail $? "(*, G) EXCLUDE entry does not have a pending group timer" - bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00" check_err $? "\"blocked\" source entry has a pending source timer" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -363,7 +363,7 @@ __cfg_test_port_ip_star_g() bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00" check_err $? "(*, G) INCLUDE entry has a pending group timer" - bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00" check_fail $? "Source entry does not have a pending source timer" bridge mdb del dev br0 port $swp1 grp $grp vid 10 From f97f1fcc96908c97a240ff6cb4474e155abfa0d7 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 8 Feb 2024 17:55:29 +0200 Subject: [PATCH 196/311] selftests: forwarding: Fix bridge locked port test flakiness The redirection test case fails in the netdev CI on debug kernels because an FDB entry is learned despite the presence of a tc filter that redirects incoming traffic [1]. I am unable to reproduce the failure locally, but I can see how it can happen given that learning is first enabled and only then the ingress tc filter is configured. On debug kernels the time window between these two operations is longer compared to regular kernels, allowing random packets to be transmitted and trigger learning. Fix by reversing the order and configure the ingress tc filter before enabling learning. [1] [...] # TEST: Locked port MAB redirect [FAIL] # Locked entry created for redirected traffic Fixes: 38c43a1ce758 ("selftests: forwarding: Add test case for traffic redirection from a locked port") Signed-off-by: Ido Schimmel Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20240208155529.1199729-5-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/bridge_locked_port.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh index 9af9f6964808..c62331b2e006 100755 --- a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh +++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh @@ -327,10 +327,10 @@ locked_port_mab_redirect() RET=0 check_port_mab_support || return 0 - bridge link set dev $swp1 learning on locked on mab on tc qdisc add dev $swp1 clsact tc filter add dev $swp1 ingress protocol all pref 1 handle 101 flower \ action mirred egress redirect dev $swp2 + bridge link set dev $swp1 learning on locked on mab on ping_do $h1 192.0.2.2 check_err $? "Ping did not work with redirection" @@ -349,8 +349,8 @@ locked_port_mab_redirect() check_err $? "Locked entry not created after deleting filter" bridge fdb del `mac_get $h1` vlan 1 dev $swp1 master - tc qdisc del dev $swp1 clsact bridge link set dev $swp1 learning off locked off mab off + tc qdisc del dev $swp1 clsact log_test "Locked port MAB redirect" } From c6e02eefd6ace3da3369c764f15429f5647056af Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Tue, 6 Feb 2024 15:00:46 +0000 Subject: [PATCH 197/311] cifs: change tcon status when need_reconnect is set on it When a tcon is marked for need_reconnect, the intention is to have it reconnected. This change adjusts tcon->status in cifs_tree_connect when need_reconnect is set. Also, this change has a minor correction in resetting need_reconnect on success. It makes sure that it is done with tc_lock held. Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/connect.c | 5 +++++ fs/smb/client/dfs.c | 7 ++++++- fs/smb/client/file.c | 3 +++ 3 files changed, 14 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index bfd568f89710..01c49b29c499 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -4228,6 +4228,11 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru /* only send once per connect */ spin_lock(&tcon->tc_lock); + + /* if tcon is marked for needing reconnect, update state */ + if (tcon->need_reconnect) + tcon->status = TID_NEED_TCON; + if (tcon->status == TID_GOOD) { spin_unlock(&tcon->tc_lock); return 0; diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index a8a1d386da65..449c59830039 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -565,6 +565,11 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru /* only send once per connect */ spin_lock(&tcon->tc_lock); + + /* if tcon is marked for needing reconnect, update state */ + if (tcon->need_reconnect) + tcon->status = TID_NEED_TCON; + if (tcon->status == TID_GOOD) { spin_unlock(&tcon->tc_lock); return 0; @@ -625,8 +630,8 @@ out: spin_lock(&tcon->tc_lock); if (tcon->status == TID_IN_TCON) tcon->status = TID_GOOD; - spin_unlock(&tcon->tc_lock); tcon->need_reconnect = false; + spin_unlock(&tcon->tc_lock); } return rc; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index b75282c204da..f391c9b803d8 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -175,6 +175,9 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) /* only send once per connect */ spin_lock(&tcon->tc_lock); + if (tcon->need_reconnect) + tcon->status = TID_NEED_RECON; + if (tcon->status != TID_NEED_RECON) { spin_unlock(&tcon->tc_lock); return; From a39c757bf0596b17482a507f31c3ef0af0d1d2b4 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Tue, 6 Feb 2024 15:00:47 +0000 Subject: [PATCH 198/311] cifs: handle cases where multiple sessions share connection Based on our implementation of multichannel, it is entirely possible that a server struct may not be found in any channel of an SMB session. In such cases, we should be prepared to move on and search for the server struct in the next session. Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/connect.c | 6 ++++++ fs/smb/client/sess.c | 1 - 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 01c49b29c499..d03253f8f145 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -233,6 +233,12 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) { /* check if iface is still active */ spin_lock(&ses->chan_lock); + if (cifs_ses_get_chan_index(ses, server) == + CIFS_INVAL_CHAN_INDEX) { + spin_unlock(&ses->chan_lock); + continue; + } + if (!cifs_chan_is_iface_active(ses, server)) { spin_unlock(&ses->chan_lock); cifs_chan_update_iface(ses, server); diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 476d54fceb50..8f37373fd333 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -88,7 +88,6 @@ cifs_ses_get_chan_index(struct cifs_ses *ses, if (server) cifs_dbg(VFS, "unable to get chan index for server: 0x%llx", server->conn_id); - WARN_ON(1); return CIFS_INVAL_CHAN_INDEX; } From a5cc98eba2592d6e3c5a4351319595ddde2a5901 Mon Sep 17 00:00:00 2001 From: Steve French Date: Tue, 6 Feb 2024 23:57:18 -0600 Subject: [PATCH 199/311] smb3: clarify mount warning When a user tries to use the "sec=krb5p" mount parameter to encrypt data on connection to a server (when authenticating with Kerberos), we indicate that it is not supported, but do not note the equivalent recommended mount parameter ("sec=krb5,seal") which turns on encryption for that mount (and uses Kerberos for auth). Update the warning message. Reviewed-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/fs_context.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 52cbef2eeb28..aec8dbd1f9db 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -211,7 +211,7 @@ cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_c switch (match_token(value, cifs_secflavor_tokens, args)) { case Opt_sec_krb5p: - cifs_errorf(fc, "sec=krb5p is not supported!\n"); + cifs_errorf(fc, "sec=krb5p is not supported. Use sec=krb5,seal instead\n"); return 1; case Opt_sec_krb5i: ctx->sign = true; From 6e2f90d31fe09f2b852de25125ca875aabd81367 Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Wed, 7 Feb 2024 08:24:15 -0500 Subject: [PATCH 200/311] net: openvswitch: limit the number of recursions from action sets The ovs module allows for some actions to recursively contain an action list for complex scenarios, such as sampling, checking lengths, etc. When these actions are copied into the internal flow table, they are evaluated to validate that such actions make sense, and these calls happen recursively. The ovs-vswitchd userspace won't emit more than 16 recursion levels deep. However, the module has no such limit and will happily accept limits larger than 16 levels nested. Prevent this by tracking the number of recursions happening and manually limiting it to 16 levels nested. The initial implementation of the sample action would track this depth and prevent more than 3 levels of recursion, but this was removed to support the clone use case, rather than limited at the current userspace limit. Fixes: 798c166173ff ("openvswitch: Optimize sample action for the clone use cases") Signed-off-by: Aaron Conole Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240207132416.1488485-2-aconole@redhat.com Signed-off-by: Jakub Kicinski --- net/openvswitch/flow_netlink.c | 49 +++++++++++++++++++++++----------- 1 file changed, 33 insertions(+), 16 deletions(-) diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 88965e2068ac..ebc5728aab4e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -48,6 +48,7 @@ struct ovs_len_tbl { #define OVS_ATTR_NESTED -1 #define OVS_ATTR_VARIABLE -2 +#define OVS_COPY_ACTIONS_MAX_DEPTH 16 static bool actions_may_change_flow(const struct nlattr *actions) { @@ -2545,13 +2546,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log); + u32 mpls_label_count, bool log, + u32 depth); static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; @@ -2602,7 +2605,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, return err; err = __ovs_nla_copy_actions(net, actions, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2617,7 +2621,8 @@ static int validate_and_copy_dec_ttl(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; int start, action_start, err, rem; @@ -2660,7 +2665,8 @@ static int validate_and_copy_dec_ttl(struct net *net, return action_start; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, - vlan_tci, mpls_label_count, log); + vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2674,7 +2680,8 @@ static int validate_and_copy_clone(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { int start, err; u32 exec; @@ -2694,7 +2701,8 @@ static int validate_and_copy_clone(struct net *net, return err; err = __ovs_nla_copy_actions(net, attr, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3063,7 +3071,7 @@ static int validate_and_copy_check_pkt_len(struct net *net, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, - bool log, bool last) + bool log, bool last, u32 depth) { const struct nlattr *acts_if_greater, *acts_if_lesser_eq; struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1]; @@ -3111,7 +3119,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3124,7 +3133,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3152,12 +3162,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { u8 mac_proto = ovs_key_mac_proto(key); const struct nlattr *a; int rem, err; + if (depth > OVS_COPY_ACTIONS_MAX_DEPTH) + return -EOVERFLOW; + nla_for_each_nested(a, attr, rem) { /* Expected argument lengths, (u32)-1 for variable length. */ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = { @@ -3355,7 +3369,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_sample(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3426,7 +3440,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_clone(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3440,7 +3454,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, + depth); if (err) return err; skip_copy = true; @@ -3450,7 +3465,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_DEC_TTL: err = validate_and_copy_dec_ttl(net, a, key, sfa, eth_type, vlan_tci, - mpls_label_count, log); + mpls_label_count, log, + depth); if (err) return err; skip_copy = true; @@ -3495,7 +3511,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, (*sfa)->orig_len = nla_len(attr); err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type, - key->eth.vlan.tci, mpls_label_count, log); + key->eth.vlan.tci, mpls_label_count, log, + 0); if (err) ovs_nla_free_flow_actions(*sfa); From bd128f62c365504e1268dc09fcccdfb1f091e93a Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Wed, 7 Feb 2024 08:24:16 -0500 Subject: [PATCH 201/311] selftests: openvswitch: Add validation for the recursion test Add a test case into the netlink checks that will show the number of nested action recursions won't exceed 16. Going to 17 on a small clone call isn't enough to exhaust the stack on (most) systems, so it should be safe to run even on systems that don't have the fix applied. Signed-off-by: Aaron Conole Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240207132416.1488485-3-aconole@redhat.com Signed-off-by: Jakub Kicinski --- .../selftests/net/openvswitch/openvswitch.sh | 13 ++++ .../selftests/net/openvswitch/ovs-dpctl.py | 71 +++++++++++++++---- 2 files changed, 69 insertions(+), 15 deletions(-) diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index f8499d4c87f3..36e40256ab92 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -502,7 +502,20 @@ test_netlink_checks () { wc -l) == 2 ] || \ return 1 + info "Checking clone depth" ERR_MSG="Flow actions may not be safe on all matching packets" + PRE_TEST=$(dmesg | grep -c "${ERR_MSG}") + ovs_add_flow "test_netlink_checks" nv0 \ + 'in_port(1),eth(),eth_type(0x800),ipv4()' \ + 'clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(drop)))))))))))))))))' \ + >/dev/null 2>&1 && return 1 + POST_TEST=$(dmesg | grep -c "${ERR_MSG}") + + if [ "$PRE_TEST" == "$POST_TEST" ]; then + info "failed - clone depth too large" + return 1 + fi + PRE_TEST=$(dmesg | grep -c "${ERR_MSG}") ovs_add_flow "test_netlink_checks" nv0 \ 'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(0),2' \ diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index b97e621face9..5e0e539a323d 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -299,7 +299,7 @@ class ovsactions(nla): ("OVS_ACTION_ATTR_PUSH_NSH", "none"), ("OVS_ACTION_ATTR_POP_NSH", "flag"), ("OVS_ACTION_ATTR_METER", "none"), - ("OVS_ACTION_ATTR_CLONE", "none"), + ("OVS_ACTION_ATTR_CLONE", "recursive"), ("OVS_ACTION_ATTR_CHECK_PKT_LEN", "none"), ("OVS_ACTION_ATTR_ADD_MPLS", "none"), ("OVS_ACTION_ATTR_DEC_TTL", "none"), @@ -465,29 +465,42 @@ class ovsactions(nla): print_str += "pop_mpls" else: datum = self.get_attr(field[0]) - print_str += datum.dpstr(more) + if field[0] == "OVS_ACTION_ATTR_CLONE": + print_str += "clone(" + print_str += datum.dpstr(more) + print_str += ")" + else: + print_str += datum.dpstr(more) return print_str def parse(self, actstr): + totallen = len(actstr) while len(actstr) != 0: parsed = False + parencount = 0 if actstr.startswith("drop"): # If no reason is provided, the implicit drop is used (i.e no # action). If some reason is given, an explicit action is used. - actstr, reason = parse_extract_field( - actstr, - "drop(", - "([0-9]+)", - lambda x: int(x, 0), - False, - None, - ) + reason = None + if actstr.startswith("drop("): + parencount += 1 + + actstr, reason = parse_extract_field( + actstr, + "drop(", + "([0-9]+)", + lambda x: int(x, 0), + False, + None, + ) + if reason is not None: self["attrs"].append(["OVS_ACTION_ATTR_DROP", reason]) parsed = True else: - return + actstr = actstr[len("drop"): ] + return (totallen - len(actstr)) elif parse_starts_block(actstr, "^(\d+)", False, True): actstr, output = parse_extract_field( @@ -504,6 +517,7 @@ class ovsactions(nla): False, 0, ) + parencount += 1 self["attrs"].append(["OVS_ACTION_ATTR_RECIRC", recircid]) parsed = True @@ -516,12 +530,22 @@ class ovsactions(nla): for flat_act in parse_flat_map: if parse_starts_block(actstr, flat_act[0], False): - actstr += len(flat_act[0]) + actstr = actstr[len(flat_act[0]):] self["attrs"].append([flat_act[1]]) actstr = actstr[strspn(actstr, ", ") :] parsed = True - if parse_starts_block(actstr, "ct(", False): + if parse_starts_block(actstr, "clone(", False): + parencount += 1 + subacts = ovsactions() + actstr = actstr[len("clone("):] + parsedLen = subacts.parse(actstr) + lst = [] + self["attrs"].append(("OVS_ACTION_ATTR_CLONE", subacts)) + actstr = actstr[parsedLen:] + parsed = True + elif parse_starts_block(actstr, "ct(", False): + parencount += 1 actstr = actstr[len("ct(") :] ctact = ovsactions.ctact() @@ -553,6 +577,7 @@ class ovsactions(nla): natact = ovsactions.ctact.natattr() if actstr.startswith("("): + parencount += 1 t = None actstr = actstr[1:] if actstr.startswith("src"): @@ -607,15 +632,29 @@ class ovsactions(nla): actstr = actstr[strspn(actstr, ", ") :] ctact["attrs"].append(["OVS_CT_ATTR_NAT", natact]) - actstr = actstr[strspn(actstr, ",) ") :] + actstr = actstr[strspn(actstr, ", ") :] self["attrs"].append(["OVS_ACTION_ATTR_CT", ctact]) parsed = True - actstr = actstr[strspn(actstr, "), ") :] + actstr = actstr[strspn(actstr, ", ") :] + while parencount > 0: + parencount -= 1 + actstr = actstr[strspn(actstr, " "):] + if len(actstr) and actstr[0] != ")": + raise ValueError("Action str: '%s' unbalanced" % actstr) + actstr = actstr[1:] + + if len(actstr) and actstr[0] == ")": + return (totallen - len(actstr)) + + actstr = actstr[strspn(actstr, ", ") :] + if not parsed: raise ValueError("Action str: '%s' not supported" % actstr) + return (totallen - len(actstr)) + class ovskey(nla): nla_flags = NLA_F_NESTED @@ -2111,6 +2150,8 @@ def main(argv): ovsflow = OvsFlow() ndb = NDB() + sys.setrecursionlimit(100000) + if hasattr(args, "showdp"): found = False for iface in ndb.interfaces: From aae09a6c7783e28d1bcafee85e172fe411923b22 Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Wed, 7 Feb 2024 19:29:02 -0300 Subject: [PATCH 202/311] net/sched: act_mirred: Don't zero blockid when net device is being deleted While testing tdc with parallel tests for mirred to block we caught an intermittent bug. The blockid was being zeroed out when a net device was deleted and, thus, giving us an incorrect blockid value whenever we tried to dump the mirred action. Since we don't increment the block refcount in the control path (and only use the ID), we don't need to zero the blockid field whenever a net device is going down. Fixes: 42f39036cda8 ("net/sched: act_mirred: Allow mirred to block") Signed-off-by: Victor Nogueira Reviewed-by: Simon Horman Reviewed-by: Eric Dumazet Acked-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20240207222902.1469398-1-victor@mojatatu.com Signed-off-by: Jakub Kicinski --- net/sched/act_mirred.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 12386f590b0f..0a1a9e40f237 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -533,8 +533,6 @@ static int mirred_device_event(struct notifier_block *unused, * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); - } else if (m->tcfm_blockid) { - m->tcfm_blockid = 0; } spin_unlock_bh(&m->tcf_lock); } From 15faa1f67ab405d47789d4702f587ec7df7ef03e Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 6 Feb 2024 13:30:54 +0100 Subject: [PATCH 203/311] lan966x: Fix crash when adding interface under a lag There is a crash when adding one of the lan966x interfaces under a lag interface. The issue can be reproduced like this: ip link add name bond0 type bond miimon 100 mode balance-xor ip link set dev eth0 master bond0 The reason is because when adding a interface under the lag it would go through all the ports and try to figure out which other ports are under that lag interface. And the issue is that lan966x can have ports that are NULL pointer as they are not probed. So then iterating over these ports it would just crash as they are NULL pointers. The fix consists in actually checking for NULL pointers before accessing something from the ports. Like we do in other places. Fixes: cabc9d49333d ("net: lan966x: Add lag support for lan966x") Signed-off-by: Horatiu Vultur Reviewed-by: Michal Swiatkowski Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240206123054.3052966-1-horatiu.vultur@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microchip/lan966x/lan966x_lag.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c index 41fa2523d91d..5f2cd9a8cf8f 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c @@ -37,19 +37,24 @@ static void lan966x_lag_set_aggr_pgids(struct lan966x *lan966x) /* Now, set PGIDs for each active LAG */ for (lag = 0; lag < lan966x->num_phys_ports; ++lag) { - struct net_device *bond = lan966x->ports[lag]->bond; + struct lan966x_port *port = lan966x->ports[lag]; int num_active_ports = 0; + struct net_device *bond; unsigned long bond_mask; u8 aggr_idx[16]; - if (!bond || (visited & BIT(lag))) + if (!port || !port->bond || (visited & BIT(lag))) continue; + bond = port->bond; bond_mask = lan966x_lag_get_mask(lan966x, bond); for_each_set_bit(p, &bond_mask, lan966x->num_phys_ports) { struct lan966x_port *port = lan966x->ports[p]; + if (!port) + continue; + lan_wr(ANA_PGID_PGID_SET(bond_mask), lan966x, ANA_PGID(p)); if (port->lag_tx_active) From 2599bb5e0c742ba3de1af2abb56b8a103a671a22 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Feb 2024 08:42:36 -0800 Subject: [PATCH 204/311] net: fill in MODULE_DESCRIPTION()s for xfrm W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the XFRM interface drivers. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240208164244.3818498-2-leitao@debian.org Signed-off-by: Jakub Kicinski --- net/xfrm/xfrm_algo.c | 1 + net/xfrm/xfrm_user.c | 1 + 2 files changed, 2 insertions(+) diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 41533c631431..e6da7e8495c9 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -858,4 +858,5 @@ int xfrm_count_pfkey_enc_supported(void) } EXPORT_SYMBOL_GPL(xfrm_count_pfkey_enc_supported); +MODULE_DESCRIPTION("XFRM Algorithm interface"); MODULE_LICENSE("GPL"); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ad01997c3aa9..f037be190bae 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -3888,5 +3888,6 @@ static void __exit xfrm_user_exit(void) module_init(xfrm_user_init); module_exit(xfrm_user_exit); +MODULE_DESCRIPTION("XFRM User interface"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM); From f73f55b0fcff575fef1854c66d18767a341ebbe2 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Feb 2024 08:42:37 -0800 Subject: [PATCH 205/311] net: fill in MODULE_DESCRIPTION()s for mpoa W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the Multi-Protocol Over ATM (MPOA) driver. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240208164244.3818498-3-leitao@debian.org Signed-off-by: Jakub Kicinski --- net/atm/mpc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 033871e718a3..324e3ab96bb3 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -1532,4 +1532,5 @@ static void __exit atm_mpoa_cleanup(void) module_init(atm_mpoa_init); module_exit(atm_mpoa_cleanup); +MODULE_DESCRIPTION("Multi-Protocol Over ATM (MPOA) driver"); MODULE_LICENSE("GPL"); From 6e2cf0eb6926a5c51bba0aca819e91d7265c849c Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Feb 2024 08:42:38 -0800 Subject: [PATCH 206/311] net: fill in MODULE_DESCRIPTION()s for af_key W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the PF_KEY socket helpers. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240208164244.3818498-4-leitao@debian.org Signed-off-by: Jakub Kicinski --- net/key/af_key.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/key/af_key.c b/net/key/af_key.c index d68d01804dc7..f79fb99271ed 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3924,5 +3924,6 @@ out_unregister_key_proto: module_init(ipsec_pfkey_init); module_exit(ipsec_pfkey_exit); +MODULE_DESCRIPTION("PF_KEY socket helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_KEY); From 2898f3075e6a0b0584781272aac88377e5ced0a0 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Feb 2024 08:42:39 -0800 Subject: [PATCH 207/311] net: fill in MODULE_DESCRIPTION()s for 6LoWPAN W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to IPv6 over Low power Wireless Personal Area Network. Signed-off-by: Breno Leitao Acked-by: Alexander Aring Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240208164244.3818498-5-leitao@debian.org Signed-off-by: Jakub Kicinski --- net/6lowpan/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c index 7b3341cef926..850d4a185f55 100644 --- a/net/6lowpan/core.c +++ b/net/6lowpan/core.c @@ -179,4 +179,5 @@ static void __exit lowpan_module_exit(void) module_init(lowpan_module_init); module_exit(lowpan_module_exit); +MODULE_DESCRIPTION("IPv6 over Low-Power Wireless Personal Area Network core module"); MODULE_LICENSE("GPL"); From 92ab08eb63bbf54caebb425ed8908758c98ae8f2 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Feb 2024 08:42:40 -0800 Subject: [PATCH 208/311] net: fill in MODULE_DESCRIPTION()s for ipv6 modules W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the IPv6 modules. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240208164244.3818498-6-leitao@debian.org Signed-off-by: Jakub Kicinski --- net/ipv6/ah6.c | 1 + net/ipv6/esp6.c | 1 + net/ipv6/ip6_udp_tunnel.c | 1 + net/ipv6/mip6.c | 1 + net/ipv6/sit.c | 1 + net/ipv6/tunnel6.c | 1 + net/ipv6/xfrm6_tunnel.c | 1 + 7 files changed, 7 insertions(+) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 2016e90e6e1d..eb474f0987ae 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -800,5 +800,6 @@ static void __exit ah6_fini(void) module_init(ah6_init); module_exit(ah6_fini); +MODULE_DESCRIPTION("IPv6 AH transformation helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_AH); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 2cc1a45742d8..6e6efe026cdc 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -1301,5 +1301,6 @@ static void __exit esp6_fini(void) module_init(esp6_init); module_exit(esp6_fini); +MODULE_DESCRIPTION("IPv6 ESP transformation helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ESP); diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index a7bf0327b380..c99053189ea8 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -182,4 +182,5 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup); +MODULE_DESCRIPTION("IPv6 Foo over UDP tunnel driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 83d2a8be263f..6a16a5bd0d91 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -405,6 +405,7 @@ static void __exit mip6_fini(void) module_init(mip6_init); module_exit(mip6_fini); +MODULE_DESCRIPTION("IPv6 Mobility driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_DSTOPTS); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ROUTING); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index cc24cefdb85c..5e9f625b76e3 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1956,6 +1956,7 @@ xfrm_tunnel_failed: module_init(sit_init); module_exit(sit_cleanup); +MODULE_DESCRIPTION("IPv6-in-IPv4 tunnel SIT driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 00e8d8b1c9a7..dc4ea9b11794 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -302,4 +302,5 @@ static void __exit tunnel6_fini(void) module_init(tunnel6_init); module_exit(tunnel6_fini); +MODULE_DESCRIPTION("IP-in-IPv6 tunnel driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 1323f2f6928e..f6cb94f82cc3 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -401,5 +401,6 @@ static void __exit xfrm6_tunnel_fini(void) module_init(xfrm6_tunnel_init); module_exit(xfrm6_tunnel_fini); +MODULE_DESCRIPTION("IPv6 XFRM tunnel driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_IPV6); From b058a5d25d921af2be83d70844d389ecfd4a0497 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Feb 2024 08:42:41 -0800 Subject: [PATCH 209/311] net: fill in MODULE_DESCRIPTION()s for ipv4 modules W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the IPv4 modules. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240208164244.3818498-7-leitao@debian.org Signed-off-by: Jakub Kicinski --- net/ipv4/ah4.c | 1 + net/ipv4/esp4.c | 1 + net/ipv4/ip_gre.c | 1 + net/ipv4/ip_tunnel.c | 1 + net/ipv4/ip_vti.c | 1 + net/ipv4/ipip.c | 1 + net/ipv4/tunnel4.c | 1 + net/ipv4/udp_tunnel_core.c | 1 + net/ipv4/xfrm4_tunnel.c | 1 + 9 files changed, 9 insertions(+) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index a2e6e1fdf82b..64aec3dff8ec 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -597,5 +597,6 @@ static void __exit ah4_fini(void) module_init(ah4_init); module_exit(ah4_fini); +MODULE_DESCRIPTION("IPv4 AH transformation library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_AH); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 4ccfc104f13a..4dd9e5040672 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1247,5 +1247,6 @@ static void __exit esp4_fini(void) module_init(esp4_init); module_exit(esp4_fini); +MODULE_DESCRIPTION("IPv4 ESP transformation library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5169c3c72cff..6b9cf5a24c19 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1793,6 +1793,7 @@ static void __exit ipgre_fini(void) module_init(ipgre_init); module_exit(ipgre_fini); +MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index beeae624c412..a4513ffb66cb 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1298,4 +1298,5 @@ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id) } EXPORT_SYMBOL_GPL(ip_tunnel_setup); +MODULE_DESCRIPTION("IPv4 tunnel implementation library"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 9ab9b3ebe0cd..d1d6bb28ed6e 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -721,6 +721,7 @@ static void __exit vti_fini(void) module_init(vti_init); module_exit(vti_fini); +MODULE_DESCRIPTION("Virtual (secure) IP tunneling library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("vti"); MODULE_ALIAS_NETDEV("ip_vti0"); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 27b8f83c6ea2..03afa3871efc 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -658,6 +658,7 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); +MODULE_DESCRIPTION("IP/IP protocol decoder library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ipip"); MODULE_ALIAS_NETDEV("tunl0"); diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index 5048c47c79b2..4c1f836aae38 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -294,4 +294,5 @@ static void __exit tunnel4_fini(void) module_init(tunnel4_init); module_exit(tunnel4_fini); +MODULE_DESCRIPTION("IPv4 XFRM tunnel library"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index a87defb2b167..860aff5f8599 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -253,4 +253,5 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(udp_tunnel_dst_lookup); +MODULE_DESCRIPTION("IPv4 Foo over UDP tunnel driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index 8489fa106583..8cb266af1393 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -114,5 +114,6 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); +MODULE_DESCRIPTION("IPv4 XFRM tunnel driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_IPIP); From a46c31bf2744b9807ba5e3ac8fdae2368d8bb3fa Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Feb 2024 08:42:42 -0800 Subject: [PATCH 210/311] net: fill in MODULE_DESCRIPTION()s for net/sched W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the network schedulers. Suggested-by: Jamal Hadi Salim Signed-off-by: Breno Leitao Reviewed-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20240208164244.3818498-8-leitao@debian.org Signed-off-by: Jakub Kicinski --- net/sched/em_canid.c | 1 + net/sched/em_cmp.c | 1 + net/sched/em_meta.c | 1 + net/sched/em_nbyte.c | 1 + net/sched/em_text.c | 1 + net/sched/em_u32.c | 1 + 6 files changed, 6 insertions(+) diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c index 5ea84decec19..5337bc462755 100644 --- a/net/sched/em_canid.c +++ b/net/sched/em_canid.c @@ -222,6 +222,7 @@ static void __exit exit_em_canid(void) tcf_em_unregister(&em_canid_ops); } +MODULE_DESCRIPTION("ematch classifier to match CAN IDs embedded in skb CAN frames"); MODULE_LICENSE("GPL"); module_init(init_em_canid); diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c index f17b049ea530..c90ad7ea26b4 100644 --- a/net/sched/em_cmp.c +++ b/net/sched/em_cmp.c @@ -87,6 +87,7 @@ static void __exit exit_em_cmp(void) tcf_em_unregister(&em_cmp_ops); } +MODULE_DESCRIPTION("ematch classifier for basic data types(8/16/32 bit) against skb data"); MODULE_LICENSE("GPL"); module_init(init_em_cmp); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 09d8afd04a2a..8996c73c9779 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -1006,6 +1006,7 @@ static void __exit exit_em_meta(void) tcf_em_unregister(&em_meta_ops); } +MODULE_DESCRIPTION("ematch classifier for various internal kernel metadata, skb metadata and sk metadata"); MODULE_LICENSE("GPL"); module_init(init_em_meta); diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index a83b237cbeb0..4f9f21a05d5e 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -68,6 +68,7 @@ static void __exit exit_em_nbyte(void) tcf_em_unregister(&em_nbyte_ops); } +MODULE_DESCRIPTION("ematch classifier for arbitrary skb multi-bytes"); MODULE_LICENSE("GPL"); module_init(init_em_nbyte); diff --git a/net/sched/em_text.c b/net/sched/em_text.c index f176afb70559..420c66203b17 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -147,6 +147,7 @@ static void __exit exit_em_text(void) tcf_em_unregister(&em_text_ops); } +MODULE_DESCRIPTION("ematch classifier for embedded text in skbs"); MODULE_LICENSE("GPL"); module_init(init_em_text); diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c index 71b070da0437..fdec4db5ec89 100644 --- a/net/sched/em_u32.c +++ b/net/sched/em_u32.c @@ -52,6 +52,7 @@ static void __exit exit_em_u32(void) tcf_em_unregister(&em_u32_ops); } +MODULE_DESCRIPTION("ematch skb classifier using 32 bit chunks of data"); MODULE_LICENSE("GPL"); module_init(init_em_u32); From 830bd88cc151412f467423c3db0b29fe623c6487 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Feb 2024 08:42:43 -0800 Subject: [PATCH 211/311] net: fill in MODULE_DESCRIPTION()s for ipvtap W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the IP-VLAN based tap driver. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240208164244.3818498-9-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/ipvlan/ipvtap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index 60944a4beada..1afc4c47be73 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -237,4 +237,5 @@ static void __exit ipvtap_exit(void) module_exit(ipvtap_exit); MODULE_ALIAS_RTNL_LINK("ipvtap"); MODULE_AUTHOR("Sainath Grandhi "); +MODULE_DESCRIPTION("IP-VLAN based tap driver"); MODULE_LICENSE("GPL"); From 6034e059f5d34bceb4adefc3409043bf65c896ea Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Feb 2024 08:42:44 -0800 Subject: [PATCH 212/311] net: fill in MODULE_DESCRIPTION()s for dsa_loop_bdinfo W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the DSA loopback fixed PHY module. Suggested-by: Florian Fainelli Signed-off-by: Breno Leitao Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/20240208164244.3818498-10-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/dsa/dsa_loop_bdinfo.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/dsa/dsa_loop_bdinfo.c b/drivers/net/dsa/dsa_loop_bdinfo.c index 237066d30704..14ca42491512 100644 --- a/drivers/net/dsa/dsa_loop_bdinfo.c +++ b/drivers/net/dsa/dsa_loop_bdinfo.c @@ -32,4 +32,5 @@ static int __init dsa_loop_bdinfo_init(void) } arch_initcall(dsa_loop_bdinfo_init) +MODULE_DESCRIPTION("DSA mock-up switch driver"); MODULE_LICENSE("GPL"); From 4356e9f841f7fbb945521cef3577ba394c65f3fc Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 9 Feb 2024 12:39:31 -0800 Subject: [PATCH 213/311] work around gcc bugs with 'asm goto' with outputs We've had issues with gcc and 'asm goto' before, and we created a 'asm_volatile_goto()' macro for that in the past: see commits 3f0116c3238a ("compiler/gcc4: Add quirk for 'asm goto' miscompilation bug") and a9f180345f53 ("compiler/gcc4: Make quirk for asm_volatile_goto() unconditional"). Then, much later, we ended up removing the workaround in commit 43c249ea0b1e ("compiler-gcc.h: remove ancient workaround for gcc PR 58670") because we no longer supported building the kernel with the affected gcc versions, but we left the macro uses around. Now, Sean Christopherson reports a new version of a very similar problem, which is fixed by re-applying that ancient workaround. But the problem in question is limited to only the 'asm goto with outputs' cases, so instead of re-introducing the old workaround as-is, let's rename and limit the workaround to just that much less common case. It looks like there are at least two separate issues that all hit in this area: (a) some versions of gcc don't mark the asm goto as 'volatile' when it has outputs: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420 which is easy to work around by just adding the 'volatile' by hand. (b) Internal compiler errors: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422 which are worked around by adding the extra empty 'asm' as a barrier, as in the original workaround. but the problem Sean sees may be a third thing since it involves bad code generation (not an ICE) even with the manually added 'volatile'. but the same old workaround works for this case, even if this feels a bit like voodoo programming and may only be hiding the issue. Reported-and-tested-by: Sean Christopherson Link: https://lore.kernel.org/all/20240208220604.140859-1-seanjc@google.com/ Cc: Nick Desaulniers Cc: Uros Bizjak Cc: Jakub Jelinek Cc: Andrew Pinski Signed-off-by: Linus Torvalds --- arch/arc/include/asm/jump_label.h | 4 ++-- arch/arm/include/asm/jump_label.h | 4 ++-- arch/arm64/include/asm/alternative-macros.h | 4 ++-- arch/arm64/include/asm/jump_label.h | 4 ++-- arch/csky/include/asm/jump_label.h | 4 ++-- arch/loongarch/include/asm/jump_label.h | 4 ++-- arch/mips/include/asm/jump_label.h | 4 ++-- arch/parisc/include/asm/jump_label.h | 4 ++-- arch/powerpc/include/asm/jump_label.h | 4 ++-- arch/powerpc/include/asm/uaccess.h | 12 ++++++------ arch/powerpc/kernel/irq_64.c | 2 +- arch/riscv/include/asm/arch_hweight.h | 4 ++-- arch/riscv/include/asm/bitops.h | 8 ++++---- arch/riscv/include/asm/checksum.h | 2 +- arch/riscv/include/asm/cpufeature.h | 4 ++-- arch/riscv/include/asm/jump_label.h | 4 ++-- arch/riscv/lib/csum.c | 10 +++++----- arch/s390/include/asm/jump_label.h | 4 ++-- arch/sparc/include/asm/jump_label.h | 4 ++-- arch/um/include/asm/cpufeature.h | 2 +- arch/x86/include/asm/cpufeature.h | 2 +- arch/x86/include/asm/jump_label.h | 6 +++--- arch/x86/include/asm/rmwcc.h | 2 +- arch/x86/include/asm/special_insns.h | 2 +- arch/x86/include/asm/uaccess.h | 10 +++++----- arch/x86/kvm/svm/svm_ops.h | 6 +++--- arch/x86/kvm/vmx/vmx.c | 4 ++-- arch/x86/kvm/vmx/vmx_ops.h | 6 +++--- arch/xtensa/include/asm/jump_label.h | 4 ++-- include/linux/compiler-gcc.h | 19 +++++++++++++++++++ include/linux/compiler_types.h | 4 ++-- net/netfilter/nft_set_pipapo_avx2.c | 2 +- samples/bpf/asm_goto_workaround.h | 8 ++++---- tools/arch/x86/include/asm/rmwcc.h | 2 +- tools/include/linux/compiler_types.h | 4 ++-- 35 files changed, 96 insertions(+), 77 deletions(-) diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h index 9d9618079739..a339223d9e05 100644 --- a/arch/arc/include/asm/jump_label.h +++ b/arch/arc/include/asm/jump_label.h @@ -31,7 +31,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" "1: \n" "nop \n" ".pushsection __jump_table, \"aw\" \n" @@ -47,7 +47,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" "1: \n" "b %l[l_yes] \n" ".pushsection __jump_table, \"aw\" \n" diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h index e12d7d096fc0..e4eb54f6cd9f 100644 --- a/arch/arm/include/asm/jump_label.h +++ b/arch/arm/include/asm/jump_label.h @@ -11,7 +11,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" WASM(nop) "\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" @@ -25,7 +25,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" WASM(b) " %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h index 210bb43cff2c..d328f549b1a6 100644 --- a/arch/arm64/include/asm/alternative-macros.h +++ b/arch/arm64/include/asm/alternative-macros.h @@ -229,7 +229,7 @@ alternative_has_cap_likely(const unsigned long cpucap) if (!cpucap_is_possible(cpucap)) return false; - asm_volatile_goto( + asm goto( ALTERNATIVE_CB("b %l[l_no]", %[cpucap], alt_cb_patch_nops) : : [cpucap] "i" (cpucap) @@ -247,7 +247,7 @@ alternative_has_cap_unlikely(const unsigned long cpucap) if (!cpucap_is_possible(cpucap)) return false; - asm_volatile_goto( + asm goto( ALTERNATIVE("nop", "b %l[l_yes]", %[cpucap]) : : [cpucap] "i" (cpucap) diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 48ddc0f45d22..6aafbb789991 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -18,7 +18,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: nop \n\t" " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" @@ -35,7 +35,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: b %l[l_yes] \n\t" " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h index 98a3f4b168bd..ef2e37a10a0f 100644 --- a/arch/csky/include/asm/jump_label.h +++ b/arch/csky/include/asm/jump_label.h @@ -12,7 +12,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: nop32 \n" " .pushsection __jump_table, \"aw\" \n" " .align 2 \n" @@ -29,7 +29,7 @@ label: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: bsr32 %l[label] \n" " .pushsection __jump_table, \"aw\" \n" " .align 2 \n" diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h index 3cea299a5ef5..29acfe3de3fa 100644 --- a/arch/loongarch/include/asm/jump_label.h +++ b/arch/loongarch/include/asm/jump_label.h @@ -22,7 +22,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: nop \n\t" JUMP_TABLE_ENTRY : : "i"(&((char *)key)[branch]) : : l_yes); @@ -35,7 +35,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: b %l[l_yes] \n\t" JUMP_TABLE_ENTRY : : "i"(&((char *)key)[branch]) : : l_yes); diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h index 081be98c71ef..ff5d388502d4 100644 --- a/arch/mips/include/asm/jump_label.h +++ b/arch/mips/include/asm/jump_label.h @@ -39,7 +39,7 @@ extern void jump_label_apply_nops(struct module *mod); static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\t" B_INSN " 2f\n\t" + asm goto("1:\t" B_INSN " 2f\n\t" "2:\t.insn\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" @@ -53,7 +53,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t" + asm goto("1:\t" J_INSN " %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" ".popsection\n\t" diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h index 94428798b6aa..317ebc5edc9f 100644 --- a/arch/parisc/include/asm/jump_label.h +++ b/arch/parisc/include/asm/jump_label.h @@ -12,7 +12,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align %1\n\t" @@ -29,7 +29,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b,n %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align %1\n\t" diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 93ce3ec25387..2f2a86ed2280 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop # arch_static_branch\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" @@ -32,7 +32,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes] # arch_static_branch_jump\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index f1f9890f50d3..de10437fd206 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -74,7 +74,7 @@ __pu_failed: \ /* -mprefixed can generate offsets beyond range, fall back hack */ #ifdef CONFIG_PPC_KERNEL_PREFIXED #define __put_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm goto( \ "1: " op " %0,0(%1) # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -83,7 +83,7 @@ __pu_failed: \ : label) #else #define __put_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -97,7 +97,7 @@ __pu_failed: \ __put_user_asm_goto(x, ptr, label, "std") #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm goto( \ "1: stw%X1 %0, %1\n" \ "2: stw%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ @@ -146,7 +146,7 @@ do { \ /* -mprefixed can generate offsets beyond range, fall back hack */ #ifdef CONFIG_PPC_KERNEL_PREFIXED #define __get_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: "op" %0,0(%1) # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ @@ -155,7 +155,7 @@ do { \ : label) #else #define __get_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: "op"%U1%X1 %0, %1 # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ @@ -169,7 +169,7 @@ do { \ __get_user_asm_goto(x, addr, label, "ld") #else /* __powerpc64__ */ #define __get_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: lwz%X1 %0, %1\n" \ "2: lwz%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c index 938e66829eae..d5c48d1b0a31 100644 --- a/arch/powerpc/kernel/irq_64.c +++ b/arch/powerpc/kernel/irq_64.c @@ -230,7 +230,7 @@ again: * This allows interrupts to be unmasked without hard disabling, and * also without new hard interrupts coming in ahead of pending ones. */ - asm_volatile_goto( + asm goto( "1: \n" " lbz 9,%0(13) \n" " cmpwi 9,0 \n" diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h index c20236a0725b..85b2c443823e 100644 --- a/arch/riscv/include/asm/arch_hweight.h +++ b/arch/riscv/include/asm/arch_hweight.h @@ -20,7 +20,7 @@ static __always_inline unsigned int __arch_hweight32(unsigned int w) { #ifdef CONFIG_RISCV_ISA_ZBB - asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : : : legacy); @@ -51,7 +51,7 @@ static inline unsigned int __arch_hweight8(unsigned int w) static __always_inline unsigned long __arch_hweight64(__u64 w) { # ifdef CONFIG_RISCV_ISA_ZBB - asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : : : legacy); diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h index 9ffc35537024..329d8244a9b3 100644 --- a/arch/riscv/include/asm/bitops.h +++ b/arch/riscv/include/asm/bitops.h @@ -39,7 +39,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word) { int num; - asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : : : legacy); @@ -95,7 +95,7 @@ static __always_inline unsigned long variable__fls(unsigned long word) { int num; - asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : : : legacy); @@ -154,7 +154,7 @@ static __always_inline int variable_ffs(int x) if (!x) return 0; - asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : : : legacy); @@ -209,7 +209,7 @@ static __always_inline int variable_fls(unsigned int x) if (!x) return 0; - asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : : : legacy); diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h index a5b60b54b101..88e6f1499e88 100644 --- a/arch/riscv/include/asm/checksum.h +++ b/arch/riscv/include/asm/checksum.h @@ -53,7 +53,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { unsigned long fold_temp; - asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, + asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 5a626ed2c47a..0bd11862b760 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -80,7 +80,7 @@ riscv_has_extension_likely(const unsigned long ext) "ext must be < RISCV_ISA_EXT_MAX"); if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { - asm_volatile_goto( + asm goto( ALTERNATIVE("j %l[l_no]", "nop", 0, %[ext], 1) : : [ext] "i" (ext) @@ -103,7 +103,7 @@ riscv_has_extension_unlikely(const unsigned long ext) "ext must be < RISCV_ISA_EXT_MAX"); if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { - asm_volatile_goto( + asm goto( ALTERNATIVE("nop", "j %l[l_yes]", 0, %[ext], 1) : : [ext] "i" (ext) diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h index 14a5ea8d8ef0..4a35d787c019 100644 --- a/arch/riscv/include/asm/jump_label.h +++ b/arch/riscv/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" @@ -39,7 +39,7 @@ label: static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c index af3df5274ccb..74af3ab520b6 100644 --- a/arch/riscv/lib/csum.c +++ b/arch/riscv/lib/csum.c @@ -53,7 +53,7 @@ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, * support, so nop when Zbb is available and jump when Zbb is * not available. */ - asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, + asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : @@ -170,7 +170,7 @@ do_csum_with_alignment(const unsigned char *buff, int len) * support, so nop when Zbb is available and jump when Zbb is * not available. */ - asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, + asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : @@ -178,7 +178,7 @@ do_csum_with_alignment(const unsigned char *buff, int len) : no_zbb); #ifdef CONFIG_32BIT - asm_volatile_goto(".option push \n\ + asm_goto_output(".option push \n\ .option arch,+zbb \n\ rori %[fold_temp], %[csum], 16 \n\ andi %[offset], %[offset], 1 \n\ @@ -193,7 +193,7 @@ do_csum_with_alignment(const unsigned char *buff, int len) return (unsigned short)csum; #else /* !CONFIG_32BIT */ - asm_volatile_goto(".option push \n\ + asm_goto_output(".option push \n\ .option arch,+zbb \n\ rori %[fold_temp], %[csum], 32 \n\ add %[csum], %[fold_temp], %[csum] \n\ @@ -257,7 +257,7 @@ do_csum_no_alignment(const unsigned char *buff, int len) * support, so nop when Zbb is available and jump when Zbb is * not available. */ - asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, + asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 895f774bbcc5..bf78cf381dfc 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -25,7 +25,7 @@ */ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 0,%l[label]\n" + asm goto("0: brcl 0,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" @@ -39,7 +39,7 @@ label: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 15,%l[label]\n" + asm goto("0: brcl 15,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h index 94eb529dcb77..2718cbea826a 100644 --- a/arch/sparc/include/asm/jump_label.h +++ b/arch/sparc/include/asm/jump_label.h @@ -10,7 +10,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" @@ -26,7 +26,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes]\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h index 4b6d1b526bc1..66fe06db872f 100644 --- a/arch/um/include/asm/cpufeature.h +++ b/arch/um/include/asm/cpufeature.h @@ -75,7 +75,7 @@ extern void setup_clear_cpu_cap(unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" + asm goto("1: jmp 6f\n" "2:\n" ".skip -(((5f-4f) - (2b-1b)) > 0) * " "((5f-4f) - (2b-1b)),0x90\n" diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index a26bebbdff87..a1273698fc43 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -168,7 +168,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto( + asm goto( ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 071572e23d3a..cbbef32517f0 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -24,7 +24,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:" + asm goto("1:" "jmp %l[l_yes] # objtool NOPs this \n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (2 | branch) : : l_yes); @@ -38,7 +38,7 @@ l_yes: static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto("1:" + asm goto("1:" ".byte " __stringify(BYTES_NOP5) "\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); @@ -52,7 +52,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto("1:" + asm goto("1:" "jmp %l[l_yes]\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 4b081e0d3306..363266cbcada 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -13,7 +13,7 @@ #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \ ({ \ bool c = false; \ - asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \ + asm goto (fullop "; j" #cc " %l[cc_label]" \ : : [var] "m" (_var), ## __VA_ARGS__ \ : clobbers : cc_label); \ if (0) { \ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index d6cd9344f6c7..48f8dd47cf68 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -205,7 +205,7 @@ static inline void clwb(volatile void *__p) #ifdef CONFIG_X86_USER_SHADOW_STACK static inline int write_user_shstk_64(u64 __user *addr, u64 val) { - asm_volatile_goto("1: wrussq %[val], (%[addr])\n" + asm goto("1: wrussq %[val], (%[addr])\n" _ASM_EXTABLE(1b, %l[fail]) :: [addr] "r" (addr), [val] "r" (val) :: fail); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 5c367c1290c3..237dc8cdd12b 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -133,7 +133,7 @@ extern int __get_user_bad(void); #ifdef CONFIG_X86_32 #define __put_user_goto_u64(x, addr, label) \ - asm_volatile_goto("\n" \ + asm goto("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ _ASM_EXTABLE_UA(1b, %l2) \ @@ -295,7 +295,7 @@ do { \ } while (0) #define __get_user_asm(x, addr, itype, ltype, label) \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: mov"itype" %[umem],%[output]\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : [output] ltype(x) \ @@ -375,7 +375,7 @@ do { \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ @@ -394,7 +394,7 @@ do { \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ @@ -477,7 +477,7 @@ struct __large_struct { unsigned long buf[100]; }; * aliasing issues. */ #define __put_user_goto(x, addr, itype, ltype, label) \ - asm_volatile_goto("\n" \ + asm goto("\n" \ "1: mov"itype" %0,%1\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h index 36c8af87a707..4e725854c63a 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -8,7 +8,7 @@ #define svm_asm(insn, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) "\n\t" \ + asm goto("1: " __stringify(insn) "\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ ::: clobber : fault); \ return; \ @@ -18,7 +18,7 @@ fault: \ #define svm_asm1(insn, op1, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1 : clobber : fault); \ return; \ @@ -28,7 +28,7 @@ fault: \ #define svm_asm2(insn, op1, op2, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1, op2 : clobber : fault); \ return; \ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e262bc2ba4e5..1111d9d08903 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -738,7 +738,7 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, */ static int kvm_cpu_vmxoff(void) { - asm_volatile_goto("1: vmxoff\n\t" + asm goto("1: vmxoff\n\t" _ASM_EXTABLE(1b, %l[fault]) ::: "cc", "memory" : fault); @@ -2784,7 +2784,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) cr4_set_bits(X86_CR4_VMXE); - asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" + asm goto("1: vmxon %[vmxon_pointer]\n\t" _ASM_EXTABLE(1b, %l[fault]) : : [vmxon_pointer] "m"(vmxon_pointer) : : fault); diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index f41ce3c24123..8060e5fc6dbd 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -94,7 +94,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT - asm_volatile_goto("1: vmread %[field], %[output]\n\t" + asm_goto_output("1: vmread %[field], %[output]\n\t" "jna %l[do_fail]\n\t" _ASM_EXTABLE(1b, %l[do_exception]) @@ -188,7 +188,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) #define vmx_asm1(insn, op1, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ @@ -205,7 +205,7 @@ fault: \ #define vmx_asm2(insn, op1, op2, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ diff --git a/arch/xtensa/include/asm/jump_label.h b/arch/xtensa/include/asm/jump_label.h index c812bf85021c..46c8596259d2 100644 --- a/arch/xtensa/include/asm/jump_label.h +++ b/arch/xtensa/include/asm/jump_label.h @@ -13,7 +13,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "_nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" @@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, * make it reachable and wrap both into a no-transform block * to avoid any assembler interference with this. */ - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" ".begin no-transform\n\t" "_j %l[l_yes]\n\t" "2:\n\t" diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index aebb65bf95a7..c1a963be7d28 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -64,6 +64,25 @@ __builtin_unreachable(); \ } while (0) +/* + * GCC 'asm goto' with outputs miscompiles certain code sequences: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420 + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422 + * + * Work it around via the same compiler barrier quirk that we used + * to use for the old 'asm goto' workaround. + * + * Also, always mark such 'asm goto' statements as volatile: all + * asm goto statements are supposed to be volatile as per the + * documentation, but some versions of gcc didn't actually do + * that for asms with outputs: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 + */ +#define asm_goto_output(x...) \ + do { asm volatile goto(x); asm (""); } while (0) + #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 6f1ca49306d2..663d8791c871 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -362,8 +362,8 @@ struct ftrace_likely_data { #define __member_size(p) __builtin_object_size(p, 1) #endif -#ifndef asm_volatile_goto -#define asm_volatile_goto(x...) asm goto(x) +#ifndef asm_goto_output +#define asm_goto_output(x...) asm goto(x) #endif #ifdef CONFIG_CC_HAS_ASM_INLINE diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 90e275bb3e5d..a3a8ddca9918 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -57,7 +57,7 @@ /* Jump to label if @reg is zero */ #define NFT_PIPAPO_AVX2_NOMATCH_GOTO(reg, label) \ - asm_volatile_goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \ + asm goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \ "je %l[" #label "]" : : : : label) /* Store 256 bits from YMM register into memory. Contrary to bucket load diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h index 7048bb3594d6..634e81d83efd 100644 --- a/samples/bpf/asm_goto_workaround.h +++ b/samples/bpf/asm_goto_workaround.h @@ -4,14 +4,14 @@ #define __ASM_GOTO_WORKAROUND_H /* - * This will bring in asm_volatile_goto and asm_inline macro definitions + * This will bring in asm_goto_output and asm_inline macro definitions * if enabled by compiler and config options. */ #include -#ifdef asm_volatile_goto -#undef asm_volatile_goto -#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto") +#ifdef asm_goto_output +#undef asm_goto_output +#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output") #endif /* diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h index 11ff975242ca..e2ff22b379a4 100644 --- a/tools/arch/x86/include/asm/rmwcc.h +++ b/tools/arch/x86/include/asm/rmwcc.h @@ -4,7 +4,7 @@ #define __GEN_RMWcc(fullop, var, cc, ...) \ do { \ - asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \ + asm goto (fullop "; j" cc " %l[cc_label]" \ : : "m" (var), ## __VA_ARGS__ \ : "memory" : cc_label); \ return 0; \ diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h index 1bdd834bdd57..d09f9dc172a4 100644 --- a/tools/include/linux/compiler_types.h +++ b/tools/include/linux/compiler_types.h @@ -36,8 +36,8 @@ #include #endif -#ifndef asm_volatile_goto -#define asm_volatile_goto(x...) asm goto(x) +#ifndef asm_goto_output +#define asm_goto_output(x...) asm goto(x) #endif #endif /* __LINUX_COMPILER_TYPES_H */ From c57ca512f3b68ddcd62bda9cc24a8f5584ab01b1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 6 Feb 2024 17:18:18 -0800 Subject: [PATCH 214/311] net: tls: factor out tls_*crypt_async_wait() Factor out waiting for async encrypt and decrypt to finish. There are already multiple copies and a subsequent fix will need more. No functional changes. Note that crypto_wait_req() returns wait->err Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Sabrina Dubroca Signed-off-by: David S. Miller --- net/tls/tls_sw.c | 96 +++++++++++++++++++++++------------------------- 1 file changed, 45 insertions(+), 51 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 31e8a94dfc11..6a73714f34cc 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -230,6 +230,20 @@ static void tls_decrypt_done(void *data, int err) spin_unlock_bh(&ctx->decrypt_compl_lock); } +static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx) +{ + int pending; + + spin_lock_bh(&ctx->decrypt_compl_lock); + reinit_completion(&ctx->async_wait.completion); + pending = atomic_read(&ctx->decrypt_pending); + spin_unlock_bh(&ctx->decrypt_compl_lock); + if (pending) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + + return ctx->async_wait.err; +} + static int tls_do_decryption(struct sock *sk, struct scatterlist *sgin, struct scatterlist *sgout, @@ -495,6 +509,28 @@ static void tls_encrypt_done(void *data, int err) schedule_delayed_work(&ctx->tx_work.work, 1); } +static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx) +{ + int pending; + + spin_lock_bh(&ctx->encrypt_compl_lock); + ctx->async_notify = true; + + pending = atomic_read(&ctx->encrypt_pending); + spin_unlock_bh(&ctx->encrypt_compl_lock); + if (pending) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + else + reinit_completion(&ctx->async_wait.completion); + + /* There can be no concurrent accesses, since we have no + * pending encrypt operations + */ + WRITE_ONCE(ctx->async_notify, false); + + return ctx->async_wait.err; +} + static int tls_do_encryption(struct sock *sk, struct tls_context *tls_ctx, struct tls_sw_context_tx *ctx, @@ -984,7 +1020,6 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, int num_zc = 0; int orig_size; int ret = 0; - int pending; if (!eor && (msg->msg_flags & MSG_EOR)) return -EINVAL; @@ -1163,24 +1198,12 @@ trim_sgl: if (!num_async) { goto send_end; } else if (num_zc) { + int err; + /* Wait for pending encryptions to get completed */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - else - reinit_completion(&ctx->async_wait.completion); - - /* There can be no concurrent accesses, since we have no - * pending encrypt operations - */ - WRITE_ONCE(ctx->async_notify, false); - - if (ctx->async_wait.err) { - ret = ctx->async_wait.err; + err = tls_encrypt_async_wait(ctx); + if (err) { + ret = err; copied = 0; } } @@ -1229,7 +1252,6 @@ void tls_sw_splice_eof(struct socket *sock) ssize_t copied = 0; bool retrying = false; int ret = 0; - int pending; if (!ctx->open_rec) return; @@ -1264,22 +1286,7 @@ retry: } /* Wait for pending encryptions to get completed */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - else - reinit_completion(&ctx->async_wait.completion); - - /* There can be no concurrent accesses, since we have no pending - * encrypt operations - */ - WRITE_ONCE(ctx->async_notify, false); - - if (ctx->async_wait.err) + if (tls_encrypt_async_wait(ctx)) goto unlock; /* Transmit if any encryptions have completed */ @@ -2109,16 +2116,10 @@ put_on_rx_list: recv_end: if (async) { - int ret, pending; + int ret; /* Wait for all previously submitted records to be decrypted */ - spin_lock_bh(&ctx->decrypt_compl_lock); - reinit_completion(&ctx->async_wait.completion); - pending = atomic_read(&ctx->decrypt_pending); - spin_unlock_bh(&ctx->decrypt_compl_lock); - ret = 0; - if (pending) - ret = crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + ret = tls_decrypt_async_wait(ctx); __skb_queue_purge(&ctx->async_hold); if (ret) { @@ -2435,16 +2436,9 @@ void tls_sw_release_resources_tx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec, *tmp; - int pending; /* Wait for any pending async encryptions to complete */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + tls_encrypt_async_wait(ctx); tls_tx_records(sk, -1); From aec7961916f3f9e88766e2688992da6980f11b8d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 6 Feb 2024 17:18:19 -0800 Subject: [PATCH 215/311] tls: fix race between async notify and socket close The submitting thread (one which called recvmsg/sendmsg) may exit as soon as the async crypto handler calls complete() so any code past that point risks touching already freed data. Try to avoid the locking and extra flags altogether. Have the main thread hold an extra reference, this way we can depend solely on the atomic ref counter for synchronization. Don't futz with reiniting the completion, either, we are now tightly controlling when completion fires. Reported-by: valis Fixes: 0cada33241d9 ("net/tls: fix race condition causing kernel panic") Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Eric Dumazet Reviewed-by: Sabrina Dubroca Signed-off-by: David S. Miller --- include/net/tls.h | 5 ----- net/tls/tls_sw.c | 43 ++++++++++--------------------------------- 2 files changed, 10 insertions(+), 38 deletions(-) diff --git a/include/net/tls.h b/include/net/tls.h index 962f0c501111..340ad43971e4 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -97,9 +97,6 @@ struct tls_sw_context_tx { struct tls_rec *open_rec; struct list_head tx_list; atomic_t encrypt_pending; - /* protect crypto_wait with encrypt_pending */ - spinlock_t encrypt_compl_lock; - int async_notify; u8 async_capable:1; #define BIT_TX_SCHEDULED 0 @@ -136,8 +133,6 @@ struct tls_sw_context_rx { struct tls_strparser strp; atomic_t decrypt_pending; - /* protect crypto_wait with decrypt_pending*/ - spinlock_t decrypt_compl_lock; struct sk_buff_head async_hold; struct wait_queue_head wq; }; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 6a73714f34cc..635305bebfef 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -224,22 +224,15 @@ static void tls_decrypt_done(void *data, int err) kfree(aead_req); - spin_lock_bh(&ctx->decrypt_compl_lock); - if (!atomic_dec_return(&ctx->decrypt_pending)) + if (atomic_dec_and_test(&ctx->decrypt_pending)) complete(&ctx->async_wait.completion); - spin_unlock_bh(&ctx->decrypt_compl_lock); } static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx) { - int pending; - - spin_lock_bh(&ctx->decrypt_compl_lock); - reinit_completion(&ctx->async_wait.completion); - pending = atomic_read(&ctx->decrypt_pending); - spin_unlock_bh(&ctx->decrypt_compl_lock); - if (pending) + if (!atomic_dec_and_test(&ctx->decrypt_pending)) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + atomic_inc(&ctx->decrypt_pending); return ctx->async_wait.err; } @@ -267,6 +260,7 @@ static int tls_do_decryption(struct sock *sk, aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, tls_decrypt_done, aead_req); + DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->decrypt_pending) < 1); atomic_inc(&ctx->decrypt_pending); } else { aead_request_set_callback(aead_req, @@ -455,7 +449,6 @@ static void tls_encrypt_done(void *data, int err) struct sk_msg *msg_en; bool ready = false; struct sock *sk; - int pending; msg_en = &rec->msg_encrypted; @@ -494,12 +487,8 @@ static void tls_encrypt_done(void *data, int err) ready = true; } - spin_lock_bh(&ctx->encrypt_compl_lock); - pending = atomic_dec_return(&ctx->encrypt_pending); - - if (!pending && ctx->async_notify) + if (atomic_dec_and_test(&ctx->encrypt_pending)) complete(&ctx->async_wait.completion); - spin_unlock_bh(&ctx->encrypt_compl_lock); if (!ready) return; @@ -511,22 +500,9 @@ static void tls_encrypt_done(void *data, int err) static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx) { - int pending; - - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - if (pending) + if (!atomic_dec_and_test(&ctx->encrypt_pending)) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - else - reinit_completion(&ctx->async_wait.completion); - - /* There can be no concurrent accesses, since we have no - * pending encrypt operations - */ - WRITE_ONCE(ctx->async_notify, false); + atomic_inc(&ctx->encrypt_pending); return ctx->async_wait.err; } @@ -577,6 +553,7 @@ static int tls_do_encryption(struct sock *sk, /* Add the record in tx_list */ list_add_tail((struct list_head *)&rec->list, &ctx->tx_list); + DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->encrypt_pending) < 1); atomic_inc(&ctx->encrypt_pending); rc = crypto_aead_encrypt(aead_req); @@ -2601,7 +2578,7 @@ static struct tls_sw_context_tx *init_ctx_tx(struct tls_context *ctx, struct soc } crypto_init_wait(&sw_ctx_tx->async_wait); - spin_lock_init(&sw_ctx_tx->encrypt_compl_lock); + atomic_set(&sw_ctx_tx->encrypt_pending, 1); INIT_LIST_HEAD(&sw_ctx_tx->tx_list); INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler); sw_ctx_tx->tx_work.sk = sk; @@ -2622,7 +2599,7 @@ static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx) } crypto_init_wait(&sw_ctx_rx->async_wait); - spin_lock_init(&sw_ctx_rx->decrypt_compl_lock); + atomic_set(&sw_ctx_rx->decrypt_pending, 1); init_waitqueue_head(&sw_ctx_rx->wq); skb_queue_head_init(&sw_ctx_rx->rx_list); skb_queue_head_init(&sw_ctx_rx->async_hold); From e01e3934a1b2d122919f73bc6ddbe1cdafc4bbdb Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 6 Feb 2024 17:18:20 -0800 Subject: [PATCH 216/311] tls: fix race between tx work scheduling and socket close Similarly to previous commit, the submitting thread (recvmsg/sendmsg) may exit as soon as the async crypto handler calls complete(). Reorder scheduling the work before calling complete(). This seems more logical in the first place, as it's the inverse order of what the submitting thread will do. Reported-by: valis Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance") Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Sabrina Dubroca Signed-off-by: David S. Miller --- net/tls/tls_sw.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 635305bebfef..9374a61cef00 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -447,7 +447,6 @@ static void tls_encrypt_done(void *data, int err) struct tls_rec *rec = data; struct scatterlist *sge; struct sk_msg *msg_en; - bool ready = false; struct sock *sk; msg_en = &rec->msg_encrypted; @@ -483,19 +482,16 @@ static void tls_encrypt_done(void *data, int err) /* If received record is at head of tx_list, schedule tx */ first_rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); - if (rec == first_rec) - ready = true; + if (rec == first_rec) { + /* Schedule the transmission */ + if (!test_and_set_bit(BIT_TX_SCHEDULED, + &ctx->tx_bitmask)) + schedule_delayed_work(&ctx->tx_work.work, 1); + } } if (atomic_dec_and_test(&ctx->encrypt_pending)) complete(&ctx->async_wait.completion); - - if (!ready) - return; - - /* Schedule the transmission */ - if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) - schedule_delayed_work(&ctx->tx_work.work, 1); } static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx) From 8590541473188741055d27b955db0777569438e3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 6 Feb 2024 17:18:21 -0800 Subject: [PATCH 217/311] net: tls: handle backlogging of crypto requests Since we're setting the CRYPTO_TFM_REQ_MAY_BACKLOG flag on our requests to the crypto API, crypto_aead_{encrypt,decrypt} can return -EBUSY instead of -EINPROGRESS in valid situations. For example, when the cryptd queue for AESNI is full (easy to trigger with an artificially low cryptd.cryptd_max_cpu_qlen), requests will be enqueued to the backlog but still processed. In that case, the async callback will also be called twice: first with err == -EINPROGRESS, which it seems we can just ignore, then with err == 0. Compared to Sabrina's original patch this version uses the new tls_*crypt_async_wait() helpers and converts the EBUSY to EINPROGRESS to avoid having to modify all the error handling paths. The handling is identical. Fixes: a54667f6728c ("tls: Add support for encryption using async offload accelerator") Fixes: 94524d8fc965 ("net/tls: Add support for async decryption of tls records") Co-developed-by: Sabrina Dubroca Signed-off-by: Sabrina Dubroca Link: https://lore.kernel.org/netdev/9681d1febfec295449a62300938ed2ae66983f28.1694018970.git.sd@queasysnail.net/ Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_sw.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9374a61cef00..63bef5666e36 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -196,6 +196,17 @@ static void tls_decrypt_done(void *data, int err) struct sock *sk; int aead_size; + /* If requests get too backlogged crypto API returns -EBUSY and calls + * ->complete(-EINPROGRESS) immediately followed by ->complete(0) + * to make waiting for backlog to flush with crypto_wait_req() easier. + * First wait converts -EBUSY -> -EINPROGRESS, and the second one + * -EINPROGRESS -> 0. + * We have a single struct crypto_async_request per direction, this + * scheme doesn't help us, so just ignore the first ->complete(). + */ + if (err == -EINPROGRESS) + return; + aead_size = sizeof(*aead_req) + crypto_aead_reqsize(aead); aead_size = ALIGN(aead_size, __alignof__(*dctx)); dctx = (void *)((u8 *)aead_req + aead_size); @@ -269,6 +280,10 @@ static int tls_do_decryption(struct sock *sk, } ret = crypto_aead_decrypt(aead_req); + if (ret == -EBUSY) { + ret = tls_decrypt_async_wait(ctx); + ret = ret ?: -EINPROGRESS; + } if (ret == -EINPROGRESS) { if (darg->async) return 0; @@ -449,6 +464,9 @@ static void tls_encrypt_done(void *data, int err) struct sk_msg *msg_en; struct sock *sk; + if (err == -EINPROGRESS) /* see the comment in tls_decrypt_done() */ + return; + msg_en = &rec->msg_encrypted; sk = rec->sk; @@ -553,6 +571,10 @@ static int tls_do_encryption(struct sock *sk, atomic_inc(&ctx->encrypt_pending); rc = crypto_aead_encrypt(aead_req); + if (rc == -EBUSY) { + rc = tls_encrypt_async_wait(ctx); + rc = rc ?: -EINPROGRESS; + } if (!rc || rc != -EINPROGRESS) { atomic_dec(&ctx->encrypt_pending); sge->offset -= prot->prepend_size; From 32b55c5ff9103b8508c1e04bfa5a08c64e7a925f Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 6 Feb 2024 17:18:22 -0800 Subject: [PATCH 218/311] net: tls: fix use-after-free with partial reads and async decrypt tls_decrypt_sg doesn't take a reference on the pages from clear_skb, so the put_page() in tls_decrypt_done releases them, and we trigger a use-after-free in process_rx_list when we try to read from the partially-read skb. Fixes: fd31f3996af2 ("tls: rx: decrypt into a fresh skb") Signed-off-by: Sabrina Dubroca Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_sw.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 63bef5666e36..a6eff21ade23 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -63,6 +63,7 @@ struct tls_decrypt_ctx { u8 iv[TLS_MAX_IV_SIZE]; u8 aad[TLS_MAX_AAD_SIZE]; u8 tail; + bool free_sgout; struct scatterlist sg[]; }; @@ -187,7 +188,6 @@ static void tls_decrypt_done(void *data, int err) struct aead_request *aead_req = data; struct crypto_aead *aead = crypto_aead_reqtfm(aead_req); struct scatterlist *sgout = aead_req->dst; - struct scatterlist *sgin = aead_req->src; struct tls_sw_context_rx *ctx; struct tls_decrypt_ctx *dctx; struct tls_context *tls_ctx; @@ -224,7 +224,7 @@ static void tls_decrypt_done(void *data, int err) } /* Free the destination pages if skb was not decrypted inplace */ - if (sgout != sgin) { + if (dctx->free_sgout) { /* Skip the first S/G entry as it points to AAD */ for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { if (!sg) @@ -1583,6 +1583,7 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov, } else if (out_sg) { memcpy(sgout, out_sg, n_sgout * sizeof(*sgout)); } + dctx->free_sgout = !!pages; /* Prepare and submit AEAD request */ err = tls_do_decryption(sk, sgin, sgout, dctx->iv, From 49d821064c44cb5ffdf272905236012ea9ce50e3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 6 Feb 2024 17:18:23 -0800 Subject: [PATCH 219/311] selftests: tls: use exact comparison in recv_partial This exact case was fail for async crypto and we weren't catching it. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- tools/testing/selftests/net/tls.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 7799e042a971..bc36c91c4480 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1002,12 +1002,12 @@ TEST_F(tls, recv_partial) memset(recv_mem, 0, sizeof(recv_mem)); EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), - MSG_WAITALL), -1); + EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_first), + MSG_WAITALL), strlen(test_str_first)); EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0); memset(recv_mem, 0, sizeof(recv_mem)); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), - MSG_WAITALL), -1); + EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_second), + MSG_WAITALL), strlen(test_str_second)); EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)), 0); } From ac437a51ce662364062f704e321227f6728e6adc Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 6 Feb 2024 17:18:24 -0800 Subject: [PATCH 220/311] net: tls: fix returned read length with async decrypt We double count async, non-zc rx data. The previous fix was lucky because if we fully zc async_copy_bytes is 0 so we add 0. Decrypted already has all the bytes we handled, in all cases. We don't have to adjust anything, delete the erroneous line. Fixes: 4d42cd6bc2ac ("tls: rx: fix return value for async crypto") Co-developed-by: Sabrina Dubroca Signed-off-by: Sabrina Dubroca Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_sw.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index a6eff21ade23..9fbc70200cd0 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2132,7 +2132,6 @@ recv_end: else err = process_rx_list(ctx, msg, &control, 0, async_copy_bytes, is_peek); - decrypted += max(err, 0); } copied += decrypted; From 6f98e44984d5eff599906c0376c027df985bf38b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 10 Feb 2024 17:40:06 +0100 Subject: [PATCH 221/311] spi: ppc4xx: Fix fallout from include cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver uses several symbols declared in , e.g module_platform_driver(). Include this header explicitly now that doesn't include any more. Fixes: ef175b29a242 ("of: Stop circularly including of_device.h and of_platform.h") Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20240210164006.208149-6-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown --- drivers/spi/spi-ppc4xx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c index 412d6e678224..2290b40459ef 100644 --- a/drivers/spi/spi-ppc4xx.c +++ b/drivers/spi/spi-ppc4xx.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include From de4af897ddf242aea18ee90d3ad2e21b4e64359c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 10 Feb 2024 17:40:07 +0100 Subject: [PATCH 222/311] spi: ppc4xx: Fix fallout from rename in struct spi_bitbang MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I failed to adapt this driver because it's not enabled in a powerpc allmodconfig build and also wasn't hit by my grep expertise. Fix accordingly. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202402100815.XQXw9XCF-lkp@intel.com/ Fixes: 2259233110d9 ("spi: bitbang: Follow renaming of SPI "master" to "controller"") Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20240210164006.208149-7-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown --- drivers/spi/spi-ppc4xx.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c index 2290b40459ef..2d5536efa9f8 100644 --- a/drivers/spi/spi-ppc4xx.c +++ b/drivers/spi/spi-ppc4xx.c @@ -364,22 +364,22 @@ static int spi_ppc4xx_of_probe(struct platform_device *op) /* Setup the state for the bitbang driver */ bbp = &hw->bitbang; - bbp->master = hw->host; + bbp->ctlr = hw->host; bbp->setup_transfer = spi_ppc4xx_setupxfer; bbp->txrx_bufs = spi_ppc4xx_txrx; bbp->use_dma = 0; - bbp->master->setup = spi_ppc4xx_setup; - bbp->master->cleanup = spi_ppc4xx_cleanup; - bbp->master->bits_per_word_mask = SPI_BPW_MASK(8); - bbp->master->use_gpio_descriptors = true; + bbp->ctlr->setup = spi_ppc4xx_setup; + bbp->ctlr->cleanup = spi_ppc4xx_cleanup; + bbp->ctlr->bits_per_word_mask = SPI_BPW_MASK(8); + bbp->ctlr->use_gpio_descriptors = true; /* * The SPI core will count the number of GPIO descriptors to figure * out the number of chip selects available on the platform. */ - bbp->master->num_chipselect = 0; + bbp->ctlr->num_chipselect = 0; /* the spi->mode bits understood by this driver: */ - bbp->master->mode_bits = + bbp->ctlr->mode_bits = SPI_CPHA | SPI_CPOL | SPI_CS_HIGH | SPI_LSB_FIRST; /* Get the clock for the OPB */ From b3aa619a8b4706f35cb62f780c14e68796b37f3f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 10 Feb 2024 17:40:08 +0100 Subject: [PATCH 223/311] spi: ppc4xx: Drop write-only variable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 24778be20f87 ("spi: convert drivers to use bits_per_word_mask") the bits_per_word variable is only written to. The check that was there before isn't needed any more as the spi core ensures that only 8 bit transfers are used, so the variable can go away together with all assignments to it. Fixes: 24778be20f87 ("spi: convert drivers to use bits_per_word_mask") Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20240210164006.208149-8-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown --- drivers/spi/spi-ppc4xx.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c index 2d5536efa9f8..942c3117ab3a 100644 --- a/drivers/spi/spi-ppc4xx.c +++ b/drivers/spi/spi-ppc4xx.c @@ -168,10 +168,8 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t) int scr; u8 cdm = 0; u32 speed; - u8 bits_per_word; /* Start with the generic configuration for this device. */ - bits_per_word = spi->bits_per_word; speed = spi->max_speed_hz; /* @@ -179,9 +177,6 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t) * the transfer to overwrite the generic configuration with zeros. */ if (t) { - if (t->bits_per_word) - bits_per_word = t->bits_per_word; - if (t->speed_hz) speed = min(t->speed_hz, spi->max_speed_hz); } From 841c35169323cd833294798e58b9bf63fa4fa1de Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 11 Feb 2024 12:18:13 -0800 Subject: [PATCH 224/311] Linux 6.8-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index a171eafce2a3..7e0b2ad98905 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* From bc4cbc9d260ba8358ca63662919f4bb223cb603b Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Tue, 6 Feb 2024 12:05:29 +0100 Subject: [PATCH 225/311] tools/rtla: Fix Makefile compiler options for clang The following errors are showing up when compiling rtla with clang: $ make HOSTCC=clang CC=clang LLVM_IAS=1 [...] clang -O -g -DVERSION=\"6.8.0-rc1\" -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables -fstack-clash-protection -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized $(pkg-config --cflags libtracefs) -c -o src/utils.o src/utils.c clang: warning: optimization flag '-ffat-lto-objects' is not supported [-Wignored-optimization-argument] warning: unknown warning option '-Wno-maybe-uninitialized'; did you mean '-Wno-uninitialized'? [-Wunknown-warning-option] 1 warning generated. clang -o rtla -ggdb src/osnoise.o src/osnoise_hist.o src/osnoise_top.o src/rtla.o src/timerlat_aa.o src/timerlat.o src/timerlat_hist.o src/timerlat_top.o src/timerlat_u.o src/trace.o src/utils.o $(pkg-config --libs libtracefs) src/osnoise.o: file not recognized: file format not recognized clang: error: linker command failed with exit code 1 (use -v to see invocation) make: *** [Makefile:110: rtla] Error 1 Solve these issues by: - removing -ffat-lto-objects and -Wno-maybe-uninitialized if using clang - informing the linker about -flto=auto Link: https://lore.kernel.org/linux-trace-kernel/567ac1b94effc228ce9a0225b9df7232a9b35b55.1707217097.git.bristot@kernel.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Bill Wendling Cc: Justin Stitt Fixes: 1a7b22ab15eb ("tools/rtla: Build with EXTRA_{C,LD}FLAGS") Suggested-by: Donald Zickus Signed-off-by: Daniel Bristot de Oliveira --- tools/tracing/rtla/Makefile | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index 2456a399eb9a..afd18c678ff5 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \ -fasynchronous-unwind-tables -fstack-clash-protection WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized +ifeq ($(CC),clang) + FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS)) + WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS)) +endif + TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs) CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -LDFLAGS := -ggdb $(EXTRA_LDFLAGS) +LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS) LIBS := $$($(PKG_CONFIG) --libs libtracefs) SRC := $(wildcard src/*.c) From 64dc40f7523369912d7adb22c8cb655f71610505 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Tue, 6 Feb 2024 12:05:30 +0100 Subject: [PATCH 226/311] tools/rtla: Fix uninitialized bucket/data->bucket_size warning When compiling rtla with clang, I am getting the following warnings: $ make HOSTCC=clang CC=clang LLVM_IAS=1 [..] clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables -fstack-clash-protection -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS $(pkg-config --cflags libtracefs) -c -o src/osnoise_hist.o src/osnoise_hist.c src/osnoise_hist.c:138:6: warning: variable 'bucket' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] 138 | if (data->bucket_size) | ^~~~~~~~~~~~~~~~~ src/osnoise_hist.c:149:6: note: uninitialized use occurs here 149 | if (bucket < entries) | ^~~~~~ src/osnoise_hist.c:138:2: note: remove the 'if' if its condition is always true 138 | if (data->bucket_size) | ^~~~~~~~~~~~~~~~~~~~~~ 139 | bucket = duration / data->bucket_size; src/osnoise_hist.c:132:12: note: initialize the variable 'bucket' to silence this warning 132 | int bucket; | ^ | = 0 1 warning generated. [...] clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables -fstack-clash-protection -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS $(pkg-config --cflags libtracefs) -c -o src/timerlat_hist.o src/timerlat_hist.c src/timerlat_hist.c:181:6: warning: variable 'bucket' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] 181 | if (data->bucket_size) | ^~~~~~~~~~~~~~~~~ src/timerlat_hist.c:204:6: note: uninitialized use occurs here 204 | if (bucket < entries) | ^~~~~~ src/timerlat_hist.c:181:2: note: remove the 'if' if its condition is always true 181 | if (data->bucket_size) | ^~~~~~~~~~~~~~~~~~~~~~ 182 | bucket = latency / data->bucket_size; src/timerlat_hist.c:175:12: note: initialize the variable 'bucket' to silence this warning 175 | int bucket; | ^ | = 0 1 warning generated. This is a legit warning, but data->bucket_size is always > 0 (see timerlat_hist_parse_args()), so the if is not necessary. Remove the unneeded if (data->bucket_size) to avoid the warning. Link: https://lkml.kernel.org/r/6e1b1665cd99042ae705b3e0fc410858c4c42346.1707217097.git.bristot@kernel.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Bill Wendling Cc: Justin Stitt Cc: Donald Zickus Fixes: 1eeb6328e8b3 ("rtla/timerlat: Add timerlat hist mode") Fixes: 829a6c0b5698 ("rtla/osnoise: Add the hist mode") Signed-off-by: Daniel Bristot de Oliveira --- tools/tracing/rtla/src/osnoise_hist.c | 3 +-- tools/tracing/rtla/src/timerlat_hist.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index 8f81fa007364..67128171c29d 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -135,8 +135,7 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu, if (params->output_divisor) duration = duration / params->output_divisor; - if (data->bucket_size) - bucket = duration / data->bucket_size; + bucket = duration / data->bucket_size; total_duration = duration * count; diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 47d3d8b53cb2..3a5b8c409e7d 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -178,8 +178,7 @@ timerlat_hist_update(struct osnoise_tool *tool, int cpu, if (params->output_divisor) latency = latency / params->output_divisor; - if (data->bucket_size) - bucket = latency / data->bucket_size; + bucket = latency / data->bucket_size; if (!context) { hist = data->hist[cpu].irq; From 30369084ac6e27479a347899e74f523e6ca29b89 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Tue, 6 Feb 2024 12:05:31 +0100 Subject: [PATCH 227/311] tools/rtla: Fix clang warning about mount_point var size clang is reporting this warning: $ make HOSTCC=clang CC=clang LLVM_IAS=1 [...] clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables -fstack-clash-protection -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS $(pkg-config --cflags libtracefs) -c -o src/utils.o src/utils.c src/utils.c:548:66: warning: 'fscanf' may overflow; destination buffer in argument 3 has size 1024, but the corresponding specifier may require size 1025 [-Wfortify-source] 548 | while (fscanf(fp, "%*s %" STR(MAX_PATH) "s %99s %*s %*d %*d\n", mount_point, type) == 2) { | ^ Increase mount_point variable size to MAX_PATH+1 to avoid the overflow. Link: https://lkml.kernel.org/r/1b46712e93a2f4153909514a36016959dcc4021c.1707217097.git.bristot@kernel.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Bill Wendling Cc: Justin Stitt Cc: Donald Zickus Fixes: a957cbc02531 ("rtla: Add -C cgroup support") Signed-off-by: Daniel Bristot de Oliveira --- tools/tracing/rtla/src/utils.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index c769d7b3842c..b998b24edf1e 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -536,7 +536,7 @@ int set_cpu_dma_latency(int32_t latency) */ static const int find_mount(const char *fs, char *mp, int sizeof_mp) { - char mount_point[MAX_PATH]; + char mount_point[MAX_PATH+1]; char type[100]; int found = 0; FILE *fp; From 084ce16df0f060efd371092a09a7ae74a536dc11 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Tue, 6 Feb 2024 12:05:32 +0100 Subject: [PATCH 228/311] tools/rtla: Remove unused sched_getattr() function Clang is reporting: $ make HOSTCC=clang CC=clang LLVM_IAS=1 [...] clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables -fstack-clash-protection -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS $(pkg-config --cflags libtracefs) -c -o src/utils.o src/utils.c src/utils.c:241:19: warning: unused function 'sched_getattr' [-Wunused-function] 241 | static inline int sched_getattr(pid_t pid, struct sched_attr *attr, | ^~~~~~~~~~~~~ 1 warning generated. Which is correct, so remove the unused function. Link: https://lkml.kernel.org/r/eaed7ba122c4ae88ce71277c824ef41cbf789385.1707217097.git.bristot@kernel.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Bill Wendling Cc: Justin Stitt Cc: Donald Zickus Fixes: b1696371d865 ("rtla: Helper functions for rtla") Signed-off-by: Daniel Bristot de Oliveira --- tools/tracing/rtla/src/utils.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index b998b24edf1e..5fcd6495ff05 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -238,12 +238,6 @@ static inline int sched_setattr(pid_t pid, const struct sched_attr *attr, return syscall(__NR_sched_setattr, pid, attr, flags); } -static inline int sched_getattr(pid_t pid, struct sched_attr *attr, - unsigned int size, unsigned int flags) -{ - return syscall(__NR_sched_getattr, pid, attr, size, flags); -} - int __set_sched_attr(int pid, struct sched_attr *attr) { int flags = 0; From f9b2c87105c989a7b259c6da87673ada96dce2f8 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Tue, 6 Feb 2024 12:05:33 +0100 Subject: [PATCH 229/311] tools/rv: Fix Makefile compiler options for clang The following errors are showing up when compiling rv with clang: $ make HOSTCC=clang CC=clang LLVM_IAS=1 [...] clang -O -g -DVERSION=\"6.8.0-rc1\" -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables -fstack-clash-protection -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized $(pkg-config --cflags libtracefs) -I include -c -o src/utils.o src/utils.c clang: warning: optimization flag '-ffat-lto-objects' is not supported [-Wignored-optimization-argument] warning: unknown warning option '-Wno-maybe-uninitialized'; did you mean '-Wno-uninitialized'? [-Wunknown-warning-option] 1 warning generated. clang -o rv -ggdb src/in_kernel.o src/rv.o src/trace.o src/utils.o $(pkg-config --libs libtracefs) src/in_kernel.o: file not recognized: file format not recognized clang: error: linker command failed with exit code 1 (use -v to see invocation) make: *** [Makefile:110: rv] Error 1 Solve these issues by: - removing -ffat-lto-objects and -Wno-maybe-uninitialized if using clang - informing the linker about -flto=auto Link: https://lkml.kernel.org/r/ed94a8ddc2ca8c8ef663cfb7ae9dd196c4a66b33.1707217097.git.bristot@kernel.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Bill Wendling Cc: Justin Stitt Fixes: 4bc4b131d44c ("rv: Add rv tool") Suggested-by: Donald Zickus Signed-off-by: Daniel Bristot de Oliveira --- tools/verification/rv/Makefile | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/verification/rv/Makefile b/tools/verification/rv/Makefile index 3d0f3888a58c..485f8aeddbe0 100644 --- a/tools/verification/rv/Makefile +++ b/tools/verification/rv/Makefile @@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \ -fasynchronous-unwind-tables -fstack-clash-protection WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized +ifeq ($(CC),clang) + FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS)) + WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS)) +endif + TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs) CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -I include -LDFLAGS := -ggdb $(EXTRA_LDFLAGS) +LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS) LIBS := $$($(PKG_CONFIG) --libs libtracefs) SRC := $(wildcard src/*.c) From 61ec586bc0815959d3314cf7ce242529c977b357 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Tue, 6 Feb 2024 12:05:34 +0100 Subject: [PATCH 230/311] tools/rv: Fix curr_reactor uninitialized variable clang is reporting: $ make HOSTCC=clang CC=clang LLVM_IAS=1 clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables -fstack-clash-protection -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS $(pkg-config --cflags libtracefs) -I include -c -o src/in_kernel.o src/in_kernel.c [...] src/in_kernel.c:227:6: warning: variable 'curr_reactor' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized] 227 | if (!end) | ^~~~ src/in_kernel.c:242:9: note: uninitialized use occurs here 242 | return curr_reactor; | ^~~~~~~~~~~~ src/in_kernel.c:227:2: note: remove the 'if' if its condition is always false 227 | if (!end) | ^~~~~~~~~ 228 | goto out_free; | ~~~~~~~~~~~~~ src/in_kernel.c:221:6: warning: variable 'curr_reactor' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized] 221 | if (!start) | ^~~~~~ src/in_kernel.c:242:9: note: uninitialized use occurs here 242 | return curr_reactor; | ^~~~~~~~~~~~ src/in_kernel.c:221:2: note: remove the 'if' if its condition is always false 221 | if (!start) | ^~~~~~~~~~~ 222 | goto out_free; | ~~~~~~~~~~~~~ src/in_kernel.c:215:20: note: initialize the variable 'curr_reactor' to silence this warning 215 | char *curr_reactor; | ^ | = NULL 2 warnings generated. Which is correct. Setting curr_reactor to NULL avoids the problem. Link: https://lkml.kernel.org/r/3a35551149e5ee0cb0950035afcb8082c3b5d05b.1707217097.git.bristot@kernel.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Bill Wendling Cc: Justin Stitt Cc: Donald Zickus Fixes: 6d60f89691fc ("tools/rv: Add in-kernel monitor interface") Signed-off-by: Daniel Bristot de Oliveira --- tools/verification/rv/src/in_kernel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/verification/rv/src/in_kernel.c b/tools/verification/rv/src/in_kernel.c index ad28582bcf2b..f04479ecc96c 100644 --- a/tools/verification/rv/src/in_kernel.c +++ b/tools/verification/rv/src/in_kernel.c @@ -210,9 +210,9 @@ static char *ikm_read_reactor(char *monitor_name) static char *ikm_get_current_reactor(char *monitor_name) { char *reactors = ikm_read_reactor(monitor_name); + char *curr_reactor = NULL; char *start; char *end; - char *curr_reactor; if (!reactors) return NULL; From 119ff04864a24470b1e531bb53e5c141aa8fefb0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Feb 2024 14:43:21 +0000 Subject: [PATCH 231/311] tcp: move tp->scaling_ratio to tcp_sock_read_txrx group tp->scaling_ratio is a read mostly field, used in rx and tx fast paths. Fixes: d5fed5addb2b ("tcp: reorganize tcp_sock fast path variables") Signed-off-by: Eric Dumazet Cc: Coco Li Cc: Wei Wang Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- Documentation/networking/net_cachelines/tcp_sock.rst | 2 +- include/linux/tcp.h | 2 +- net/ipv4/tcp.c | 3 ++- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst index 97d7a5c8e01c..803912291479 100644 --- a/Documentation/networking/net_cachelines/tcp_sock.rst +++ b/Documentation/networking/net_cachelines/tcp_sock.rst @@ -38,7 +38,7 @@ u32 max_window read_mostly - u32 mss_cache read_mostly read_mostly tcp_rate_check_app_limited,tcp_current_mss,tcp_sync_mss,tcp_sndbuf_expand,tcp_tso_should_defer(tx);tcp_update_pacing_rate,tcp_clean_rtx_queue(rx) u32 window_clamp read_mostly read_write tcp_rcv_space_adjust,__tcp_select_window u32 rcv_ssthresh read_mostly - __tcp_select_window -u82 scaling_ratio +u8 scaling_ratio read_mostly read_mostly tcp_win_from_space struct tcp_rack u16 advmss - read_mostly tcp_rcv_space_adjust u8 compressed_ack diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 89b290d8c8dc..168f5dca6609 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -221,6 +221,7 @@ struct tcp_sock { u32 lost_out; /* Lost packets */ u32 sacked_out; /* SACK'd packets */ u16 tcp_header_len; /* Bytes of tcp header to send */ + u8 scaling_ratio; /* see tcp_win_from_space() */ u8 chrono_type : 2, /* current chronograph type */ repair : 1, is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ @@ -352,7 +353,6 @@ struct tcp_sock { u32 compressed_ack_rcv_nxt; struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ - u8 scaling_ratio; /* see tcp_win_from_space() */ /* Information of the most recently (s)acked skb */ struct tcp_rack { u64 mstamp; /* (Re)sent time of the skb */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7e2481b9eae1..c82dc42f57c6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4615,7 +4615,8 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32); /* RX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq); From 666a877deab2bcf8fd11c962d69e687e18168a6f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Feb 2024 14:43:22 +0000 Subject: [PATCH 232/311] tcp: move tp->tcp_usec_ts to tcp_sock_read_txrx group tp->tcp_usec_ts is a read mostly field, used in rx and tx fast paths. Fixes: d5fed5addb2b ("tcp: reorganize tcp_sock fast path variables") Signed-off-by: Eric Dumazet Cc: Coco Li Cc: Wei Wang Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- Documentation/networking/net_cachelines/tcp_sock.rst | 2 +- include/linux/tcp.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst index 803912291479..1c154cbd1848 100644 --- a/Documentation/networking/net_cachelines/tcp_sock.rst +++ b/Documentation/networking/net_cachelines/tcp_sock.rst @@ -44,7 +44,7 @@ u16 advmss - read_m u8 compressed_ack u8:2 dup_ack_counter u8:1 tlp_retrans -u8:1 tcp_usec_ts +u8:1 tcp_usec_ts read_mostly read_mostly u32 chrono_start read_write - tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data) u32[3] chrono_stat read_write - tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data) u8:2 chrono_type read_write - tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 168f5dca6609..a1c47a6d69b0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -224,6 +224,7 @@ struct tcp_sock { u8 scaling_ratio; /* see tcp_win_from_space() */ u8 chrono_type : 2, /* current chronograph type */ repair : 1, + tcp_usec_ts : 1, /* TSval values in usec */ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ __cacheline_group_end(tcp_sock_read_txrx); @@ -368,8 +369,7 @@ struct tcp_sock { u8 compressed_ack; u8 dup_ack_counter:2, tlp_retrans:1, /* TLP is a retransmission */ - tcp_usec_ts:1, /* TSval values in usec */ - unused:4; + unused:5; u8 thin_lto : 1,/* Use linear timeouts for thin streams */ recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ From c353c7b7ffb7ae6ed8f3339906fe33c8be6cf344 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Feb 2024 14:43:23 +0000 Subject: [PATCH 233/311] net-device: move lstats in net_device_read_txrx dev->lstats is notably used from loopback ndo_start_xmit() and other virtual drivers. Per cpu stats updates are dirtying per-cpu data, but the pointer itself is read-only. Fixes: 43a71cd66b9c ("net-device: reorganize net_device fast path variables") Signed-off-by: Eric Dumazet Cc: Coco Li Cc: Simon Horman Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- Documentation/networking/net_cachelines/net_device.rst | 4 ++-- include/linux/netdevice.h | 10 +++++----- net/core/dev.c | 3 ++- 3 files changed, 9 insertions(+), 8 deletions(-) diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index e75a53593bb9..dceb49d56a91 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -136,8 +136,8 @@ struct_netpoll_info* npinfo - possible_net_t nd_net - read_mostly (dev_net)napi_busy_loop,tcp_v(4/6)_rcv,ip(v6)_rcv,ip(6)_input,ip(6)_input_finish void* ml_priv enum_netdev_ml_priv_type ml_priv_type -struct_pcpu_lstats__percpu* lstats -struct_pcpu_sw_netstats__percpu* tstats +struct_pcpu_lstats__percpu* lstats read_mostly dev_lstats_add() +struct_pcpu_sw_netstats__percpu* tstats read_mostly dev_sw_netstats_tx_add() struct_pcpu_dstats__percpu* dstats struct_garp_port* garp_port struct_mrp_port* mrp_port diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 118c40258d07..ef7bfbb98497 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2141,6 +2141,11 @@ struct net_device { /* TXRX read-mostly hotpath */ __cacheline_group_begin(net_device_read_txrx); + union { + struct pcpu_lstats __percpu *lstats; + struct pcpu_sw_netstats __percpu *tstats; + struct pcpu_dstats __percpu *dstats; + }; unsigned int flags; unsigned short hard_header_len; netdev_features_t features; @@ -2395,11 +2400,6 @@ struct net_device { enum netdev_ml_priv_type ml_priv_type; enum netdev_stat_type pcpu_stat_type:8; - union { - struct pcpu_lstats __percpu *lstats; - struct pcpu_sw_netstats __percpu *tstats; - struct pcpu_dstats __percpu *dstats; - }; #if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; diff --git a/net/core/dev.c b/net/core/dev.c index cb2dab0feee0..9bb792cecc16 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -11652,11 +11652,12 @@ static void __init net_dev_struct_check(void) CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160); /* TXRX read-mostly hotpath */ + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); - CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30); + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38); /* RX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); From 14f08c976ffe0d2117c6199c32663df1cbc45c65 Mon Sep 17 00:00:00 2001 From: limingming3 Date: Wed, 7 Feb 2024 14:51:42 +0800 Subject: [PATCH 234/311] tools/rtla: Replace setting prio with nice for SCHED_OTHER Since the sched_priority for SCHED_OTHER is always 0, it makes no sence to set it. Setting nice for SCHED_OTHER seems more meaningful. Link: https://lkml.kernel.org/r/20240207065142.1753909-1-limingming3@lixiang.com Cc: stable@vger.kernel.org Fixes: b1696371d865 ("rtla: Helper functions for rtla") Signed-off-by: limingming3 Signed-off-by: Daniel Bristot de Oliveira --- tools/tracing/rtla/src/utils.c | 6 +++--- tools/tracing/rtla/src/utils.h | 2 ++ 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index 5fcd6495ff05..9ac71a66840c 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -473,13 +473,13 @@ int parse_prio(char *arg, struct sched_attr *sched_param) if (prio == INVALID_VAL) return -1; - if (prio < sched_get_priority_min(SCHED_OTHER)) + if (prio < MIN_NICE) return -1; - if (prio > sched_get_priority_max(SCHED_OTHER)) + if (prio > MAX_NICE) return -1; sched_param->sched_policy = SCHED_OTHER; - sched_param->sched_priority = prio; + sched_param->sched_nice = prio; break; default: return -1; diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h index 04ed1e650495..d44513e6c66a 100644 --- a/tools/tracing/rtla/src/utils.h +++ b/tools/tracing/rtla/src/utils.h @@ -9,6 +9,8 @@ */ #define BUFF_U64_STR_SIZE 24 #define MAX_PATH 1024 +#define MAX_NICE 20 +#define MIN_NICE -19 #define container_of(ptr, type, member)({ \ const typeof(((type *)0)->member) *__mptr = (ptr); \ From b5f319360371087d52070d8f3fc7789e80ce69a6 Mon Sep 17 00:00:00 2001 From: John Kacur Date: Fri, 2 Feb 2024 19:16:07 -0500 Subject: [PATCH 235/311] tools/rtla: Exit with EXIT_SUCCESS when help is invoked Fix rtla so that the following commands exit with 0 when help is invoked rtla osnoise top -h rtla osnoise hist -h rtla timerlat top -h rtla timerlat hist -h Link: https://lore.kernel.org/linux-trace-devel/20240203001607.69703-1-jkacur@redhat.com Cc: stable@vger.kernel.org Fixes: 1eeb6328e8b3 ("rtla/timerlat: Add timerlat hist mode") Signed-off-by: John Kacur Signed-off-by: Daniel Bristot de Oliveira --- tools/tracing/rtla/src/osnoise_hist.c | 6 +++++- tools/tracing/rtla/src/osnoise_top.c | 6 +++++- tools/tracing/rtla/src/timerlat_hist.c | 6 +++++- tools/tracing/rtla/src/timerlat_top.c | 6 +++++- 4 files changed, 20 insertions(+), 4 deletions(-) diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index 67128171c29d..01870d50942a 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -479,7 +479,11 @@ static void osnoise_hist_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index f7c959be8677..457360db0767 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -331,7 +331,11 @@ static void osnoise_top_usage(struct osnoise_top_params *params, char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 3a5b8c409e7d..dbf154082f95 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -545,7 +545,11 @@ static void timerlat_hist_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 1640f121baca..3e9af2c38688 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -375,7 +375,11 @@ static void timerlat_top_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* From bdd70eb68913c960acb895b00a8c62eb64715b1f Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 8 Feb 2024 19:03:49 +0100 Subject: [PATCH 236/311] mptcp: drop the push_pending field Such field is there to avoid acquiring the data lock in a few spots, but it adds complexity to the already non trivial locking schema. All the relevant call sites (mptcp-level re-injection, set socket options), are slow-path, drop such field in favor of 'cb_flags', adding the relevant locking. This patch could be seen as an improvement, instead of a fix. But it simplifies the next patch. The 'Fixes' tag has been added to help having this series backported to stable. Fixes: e9d09baca676 ("mptcp: avoid atomic bit manipulation when possible") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 12 ++++++------ net/mptcp/protocol.h | 1 - 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 028e8b473626..2111819016af 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1505,8 +1505,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk, void mptcp_check_and_set_pending(struct sock *sk) { - if (mptcp_send_head(sk)) - mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING); + if (mptcp_send_head(sk)) { + mptcp_data_lock(sk); + mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING); + mptcp_data_unlock(sk); + } } static int __subflow_push_pending(struct sock *sk, struct sock *ssk, @@ -3142,7 +3145,6 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); WRITE_ONCE(msk->flags, 0); msk->cb_flags = 0; - msk->push_pending = 0; msk->recovery = false; msk->can_ack = false; msk->fully_established = false; @@ -3330,8 +3332,7 @@ static void mptcp_release_cb(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); for (;;) { - unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) | - msk->push_pending; + unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); struct list_head join_list; if (!flags) @@ -3347,7 +3348,6 @@ static void mptcp_release_cb(struct sock *sk) * datapath acquires the msk socket spinlock while helding * the subflow socket lock */ - msk->push_pending = 0; msk->cb_flags &= ~flags; spin_unlock_bh(&sk->sk_lock.slock); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3517f2d24a22..b905f1868298 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -286,7 +286,6 @@ struct mptcp_sock { int rmem_released; unsigned long flags; unsigned long cb_flags; - unsigned long push_pending; bool recovery; /* closing subflow write queue reinjected */ bool can_ack; bool fully_established; From 013e3179dbd2bc756ce1dd90354abac62f65b739 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 8 Feb 2024 19:03:50 +0100 Subject: [PATCH 237/311] mptcp: fix rcv space initialization mptcp_rcv_space_init() is supposed to happen under the msk socket lock, but active msk socket does that without such protection. Leverage the existing mptcp_propagate_state() helper to that extent. We need to ensure mptcp_rcv_space_init will happen before mptcp_rcv_space_adjust(), and the release_cb does not assure that: explicitly check for such condition. While at it, move the wnd_end initialization out of mptcp_rcv_space_init(), it never belonged there. Note that the race does not produce ill effect in practice, but change allows cleaning-up and defying better the locking model. Fixes: a6b118febbab ("mptcp: add receive buffer auto-tuning") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 10 ++++++---- net/mptcp/protocol.h | 3 ++- net/mptcp/subflow.c | 4 ++-- 3 files changed, 10 insertions(+), 7 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2111819016af..7632eafb683b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1963,6 +1963,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (copied <= 0) return; + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); + msk->rcvq_space.copied += copied; mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); @@ -3160,6 +3163,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->bytes_received = 0; msk->bytes_sent = 0; msk->bytes_retrans = 0; + msk->rcvspace_init = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); @@ -3247,6 +3251,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) { const struct tcp_sock *tp = tcp_sk(ssk); + msk->rcvspace_init = 1; msk->rcvq_space.copied = 0; msk->rcvq_space.rtt_us = 0; @@ -3257,8 +3262,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) TCP_INIT_CWND * tp->advmss); if (msk->rcvq_space.space == 0) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; - - WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); } void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) @@ -3478,10 +3481,9 @@ void mptcp_finish_connect(struct sock *ssk) WRITE_ONCE(msk->write_seq, subflow->idsn + 1); WRITE_ONCE(msk->snd_nxt, msk->write_seq); WRITE_ONCE(msk->snd_una, msk->write_seq); + WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); mptcp_pm_new_connection(msk, ssk, 0); - - mptcp_rcv_space_init(msk, ssk); } void mptcp_sock_graft(struct sock *sk, struct socket *parent) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index b905f1868298..9f5ee82e3473 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -304,7 +304,8 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1, - free_first:1; + free_first:1, + rcvspace_init:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 0dcb721c89d1..56b2ac2f2f22 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -424,6 +424,8 @@ void __mptcp_sync_state(struct sock *sk, int state) struct mptcp_sock *msk = mptcp_sk(sk); __mptcp_propagate_sndbuf(sk, msk->first); + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); if (sk->sk_state == TCP_SYN_SENT) { mptcp_set_state(sk, state); sk->sk_state_change(sk); @@ -545,7 +547,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } } else if (mptcp_check_fallback(sk)) { fallback: - mptcp_rcv_space_init(msk, sk); mptcp_propagate_state(parent, sk); } return; @@ -1744,7 +1745,6 @@ static void subflow_state_change(struct sock *sk) msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { mptcp_do_fallback(sk); - mptcp_rcv_space_init(msk, sk); pr_fallback(msk); subflow->conn_finished = 1; mptcp_propagate_state(parent, sk); From 3f83d8a77eeeb47011b990fd766a421ee64f1d73 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 8 Feb 2024 19:03:51 +0100 Subject: [PATCH 238/311] mptcp: fix more tx path fields initialization The 'msk->write_seq' and 'msk->snd_nxt' are always updated under the msk socket lock, except at MPC handshake completiont time. Builds-up on the previous commit to move such init under the relevant lock. There are no known problems caused by the potential race, the primary goal is consistency. Fixes: 6d0060f600ad ("mptcp: Write MPTCP DSS headers to outgoing data packets") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 6 ++---- net/mptcp/subflow.c | 13 +++++++++++-- 2 files changed, 13 insertions(+), 6 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7632eafb683b..8cb6a873dae9 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3478,10 +3478,8 @@ void mptcp_finish_connect(struct sock *ssk) * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); - WRITE_ONCE(msk->write_seq, subflow->idsn + 1); - WRITE_ONCE(msk->snd_nxt, msk->write_seq); - WRITE_ONCE(msk->snd_una, msk->write_seq); - WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); + WRITE_ONCE(msk->snd_una, subflow->idsn + 1); + WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); mptcp_pm_new_connection(msk, ssk, 0); } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 56b2ac2f2f22..c2df34ebcf28 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -421,12 +421,21 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc void __mptcp_sync_state(struct sock *sk, int state) { + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); + struct sock *ssk = msk->first; - __mptcp_propagate_sndbuf(sk, msk->first); + subflow = mptcp_subflow_ctx(ssk); + __mptcp_propagate_sndbuf(sk, ssk); if (!msk->rcvspace_init) - mptcp_rcv_space_init(msk, msk->first); + mptcp_rcv_space_init(msk, ssk); + if (sk->sk_state == TCP_SYN_SENT) { + /* subflow->idsn is always available is TCP_SYN_SENT state, + * even for the FASTOPEN scenarios + */ + WRITE_ONCE(msk->write_seq, subflow->idsn + 1); + WRITE_ONCE(msk->snd_nxt, msk->write_seq); mptcp_set_state(sk, state); sk->sk_state_change(sk); } From e4a0fa47e816e186f6b4c0055d07eeec42d11871 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 8 Feb 2024 19:03:52 +0100 Subject: [PATCH 239/311] mptcp: corner case locking for rx path fields initialization Most MPTCP-level related fields are under the mptcp data lock protection, but are written one-off without such lock at MPC complete time, both for the client and the server Leverage the mptcp_propagate_state() infrastructure to move such initialization under the proper lock client-wise. The server side critical init steps are done by mptcp_subflow_fully_established(): ensure the caller properly held the relevant lock, and avoid acquiring the same lock in the nested scopes. There are no real potential races, as write access to such fields is implicitly serialized by the MPTCP state machine; the primary goal is consistency. Fixes: d22f4988ffec ("mptcp: process MP_CAPABLE data option") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- net/mptcp/fastopen.c | 6 ++--- net/mptcp/options.c | 9 +++---- net/mptcp/protocol.c | 9 ++++--- net/mptcp/protocol.h | 9 +++---- net/mptcp/subflow.c | 56 +++++++++++++++++++++++++------------------- 5 files changed, 50 insertions(+), 39 deletions(-) diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index 74698582a285..ad28da655f8b 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -59,13 +59,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf mptcp_data_unlock(sk); } -void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt) +void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) { struct sock *sk = (struct sock *)msk; struct sk_buff *skb; - mptcp_data_lock(sk); skb = skb_peek_tail(&sk->sk_receive_queue); if (skb) { WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq); @@ -77,5 +76,4 @@ void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_ } pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq); - mptcp_data_unlock(sk); } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index d2527d189a79..e3e96a49f922 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -962,9 +962,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ - subflow->fully_established = 1; - WRITE_ONCE(msk->fully_established, true); - goto check_notify; + goto set_fully_established; } /* If the first established packet does not contain MP_CAPABLE + data @@ -986,7 +984,10 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, set_fully_established: if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); - mptcp_subflow_fully_established(subflow, mp_opt); + + mptcp_data_lock((struct sock *)msk); + __mptcp_subflow_fully_established(msk, subflow, mp_opt); + mptcp_data_unlock((struct sock *)msk); check_notify: /* if the subflow is not already linked into the conn_list, we can't diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8cb6a873dae9..8ef2927ebca2 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3186,6 +3186,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; if (!nsk) @@ -3226,7 +3227,8 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, /* The msk maintain a ref to each subflow in the connections list */ WRITE_ONCE(msk->first, ssk); - list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list); + subflow = mptcp_subflow_ctx(ssk); + list_add(&subflow->node, &msk->conn_list); sock_hold(ssk); /* new mpc subflow takes ownership of the newly @@ -3241,6 +3243,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); + + if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) + __mptcp_subflow_fully_established(msk, subflow, mp_opt); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ @@ -3478,8 +3483,6 @@ void mptcp_finish_connect(struct sock *ssk) * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); - WRITE_ONCE(msk->snd_una, subflow->idsn + 1); - WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); mptcp_pm_new_connection(msk, ssk, 0); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 9f5ee82e3473..fefcbf585411 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -622,8 +622,9 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net); unsigned int mptcp_close_timeout(const struct sock *sk); int mptcp_get_pm_type(const struct net *net); const char *mptcp_get_scheduler(const struct net *net); -void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt); +void __mptcp_subflow_fully_established(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); void mptcp_check_and_set_pending(struct sock *sk); void __mptcp_push_pending(struct sock *sk, unsigned int flags); @@ -952,8 +953,8 @@ void mptcp_event_pm_listener(const struct sock *ssk, enum mptcp_event_type event); bool mptcp_userspace_pm_active(const struct mptcp_sock *msk); -void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt); +void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt); void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index c2df34ebcf28..c34ecadee120 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -441,20 +441,6 @@ void __mptcp_sync_state(struct sock *sk, int state) } } -static void mptcp_propagate_state(struct sock *sk, struct sock *ssk) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - - mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) { - __mptcp_sync_state(sk, ssk->sk_state); - } else { - msk->pending_state = ssk->sk_state; - __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); - } - mptcp_data_unlock(sk); -} - static void subflow_set_remote_key(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt) @@ -476,6 +462,31 @@ static void subflow_set_remote_key(struct mptcp_sock *msk, atomic64_set(&msk->rcv_wnd_sent, subflow->iasn); } +static void mptcp_propagate_state(struct sock *sk, struct sock *ssk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_data_lock(sk); + if (mp_opt) { + /* Options are available only in the non fallback cases + * avoid updating rx path fields otherwise + */ + WRITE_ONCE(msk->snd_una, subflow->idsn + 1); + WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); + subflow_set_remote_key(msk, subflow, mp_opt); + } + + if (!sock_owned_by_user(sk)) { + __mptcp_sync_state(sk, ssk->sk_state); + } else { + msk->pending_state = ssk->sk_state; + __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); + } + mptcp_data_unlock(sk); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -510,10 +521,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (mp_opt.deny_join_id0) WRITE_ONCE(msk->pm.remote_deny_join_id0, true); subflow->mp_capable = 1; - subflow_set_remote_key(msk, subflow, &mp_opt); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, &mp_opt); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -556,7 +566,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } } else if (mptcp_check_fallback(sk)) { fallback: - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, NULL); } return; @@ -741,17 +751,16 @@ void mptcp_subflow_drop_ctx(struct sock *ssk) kfree_rcu(ctx, rcu); } -void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt) +void __mptcp_subflow_fully_established(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) { - struct mptcp_sock *msk = mptcp_sk(subflow->conn); - subflow_set_remote_key(msk, subflow, mp_opt); subflow->fully_established = 1; WRITE_ONCE(msk->fully_established, true); if (subflow->is_mptfo) - mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); + __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); } static struct sock *subflow_syn_recv_sock(const struct sock *sk, @@ -844,7 +853,6 @@ create_child: * mpc option */ if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) { - mptcp_subflow_fully_established(ctx, &mp_opt); mptcp_pm_fully_established(owner, child); ctx->pm_notified = 1; } @@ -1756,7 +1764,7 @@ static void subflow_state_change(struct sock *sk) mptcp_do_fallback(sk); pr_fallback(msk); subflow->conn_finished = 1; - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, NULL); } /* as recvmsg() does not acquire the subflow socket for ssk selection From f012d796a6de662692159c539689e47e662853a8 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 8 Feb 2024 19:03:53 +0100 Subject: [PATCH 240/311] mptcp: check addrs list in userspace_pm_get_local_id Before adding a new entry in mptcp_userspace_pm_get_local_id(), it's better to check whether this address is already in userspace pm local address list. If it's in the list, no need to add a new entry, just return it's address ID and use this address. Fixes: 8b20137012d9 ("mptcp: read attributes of addr entries managed by userspace PMs") Cc: stable@vger.kernel.org Signed-off-by: Geliang Tang Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- net/mptcp/pm_userspace.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index efecbe3cf415..4f3901d5b8ef 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -130,10 +130,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { - struct mptcp_pm_addr_entry new_entry; + struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry; __be16 msk_sport = ((struct inet_sock *) inet_sk((struct sock *)msk))->inet_sport; + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&e->addr, skc, false)) { + entry = e; + break; + } + } + spin_unlock_bh(&msk->pm.lock); + if (entry) + return entry->addr.id; + memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry)); new_entry.addr = *skc; new_entry.addr.id = 0; From 337cebbd850f94147cee05252778f8f78b8c337f Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 8 Feb 2024 19:03:54 +0100 Subject: [PATCH 241/311] mptcp: really cope with fastopen race Fastopen and PM-trigger subflow shutdown can race, as reported by syzkaller. In my first attempt to close such race, I missed the fact that the subflow status can change again before the subflow_state_change callback is invoked. Address the issue additionally copying with all the states directly reachable from TCP_FIN_WAIT1. Fixes: 1e777f39b4d7 ("mptcp: add MSG_FASTOPEN sendmsg flag support") Fixes: 4fd19a307016 ("mptcp: fix inconsistent state on fastopen race") Cc: stable@vger.kernel.org Reported-by: syzbot+c53d4d3ddb327e80bc51@syzkaller.appspotmail.com Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/458 Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- net/mptcp/protocol.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index fefcbf585411..ed50f2015dc3 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1129,7 +1129,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) && + return (1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) && is_active_ssk(subflow) && !subflow->conn_finished; } From 68990d006d42b6ef7910fa263f87e9e0d812113b Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 8 Feb 2024 19:03:55 +0100 Subject: [PATCH 242/311] MAINTAINERS: update Geliang's email address Update my email-address in MAINTAINERS and .mailmap entries to my kernel.org account. Suggested-by: Mat Martineau Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- .mailmap | 9 +++++---- MAINTAINERS | 2 +- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/.mailmap b/.mailmap index 04998f7bda81..327e7eddd146 100644 --- a/.mailmap +++ b/.mailmap @@ -191,10 +191,11 @@ Gao Xiang Gao Xiang Gao Xiang Gao Xiang -Geliang Tang -Geliang Tang -Geliang Tang -Geliang Tang +Geliang Tang +Geliang Tang +Geliang Tang +Geliang Tang +Geliang Tang Georgi Djakov Gerald Schaefer Gerald Schaefer diff --git a/MAINTAINERS b/MAINTAINERS index 3dfe7ea25320..aa9776031121 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15324,7 +15324,7 @@ K: \bmdo_ NETWORKING [MPTCP] M: Matthieu Baerts M: Mat Martineau -R: Geliang Tang +R: Geliang Tang L: netdev@vger.kernel.org L: mptcp@lists.linux.dev S: Maintained From 5b3fbd61b9d1f4ed2db95aaf03f9adae0373784d Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 9 Feb 2024 01:55:18 -0800 Subject: [PATCH 243/311] net: sysfs: Fix /sys/class/net/ path for statistics The Documentation/ABI/testing/sysfs-class-net-statistics documentation is pointing to the wrong path for the interface. Documentation is pointing to /sys/class/, instead of /sys/class/net/. Fix it by adding the `net/` directory before the interface. Fixes: 6044f9700645 ("net: sysfs: document /sys/class/net/statistics/*") Signed-off-by: Breno Leitao Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- .../ABI/testing/sysfs-class-net-statistics | 48 +++++++++---------- 1 file changed, 24 insertions(+), 24 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics index 55db27815361..53e508c6936a 100644 --- a/Documentation/ABI/testing/sysfs-class-net-statistics +++ b/Documentation/ABI/testing/sysfs-class-net-statistics @@ -1,4 +1,4 @@ -What: /sys/class//statistics/collisions +What: /sys/class/net//statistics/collisions Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -6,7 +6,7 @@ Description: Indicates the number of collisions seen by this network device. This value might not be relevant with all MAC layers. -What: /sys/class//statistics/multicast +What: /sys/class/net//statistics/multicast Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -14,7 +14,7 @@ Description: Indicates the number of multicast packets received by this network device. -What: /sys/class//statistics/rx_bytes +What: /sys/class/net//statistics/rx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -23,7 +23,7 @@ Description: See the network driver for the exact meaning of when this value is incremented. -What: /sys/class//statistics/rx_compressed +What: /sys/class/net//statistics/rx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -32,7 +32,7 @@ Description: network device. This value might only be relevant for interfaces that support packet compression (e.g: PPP). -What: /sys/class//statistics/rx_crc_errors +What: /sys/class/net//statistics/rx_crc_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -41,7 +41,7 @@ Description: by this network device. Note that the specific meaning might depend on the MAC layer used by the interface. -What: /sys/class//statistics/rx_dropped +What: /sys/class/net//statistics/rx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -51,7 +51,7 @@ Description: packet processing. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_errors +What: /sys/class/net//statistics/rx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -59,7 +59,7 @@ Description: Indicates the number of receive errors on this network device. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_fifo_errors +What: /sys/class/net//statistics/rx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -68,7 +68,7 @@ Description: network device. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_frame_errors +What: /sys/class/net//statistics/rx_frame_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -78,7 +78,7 @@ Description: on the MAC layer protocol used. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_length_errors +What: /sys/class/net//statistics/rx_length_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -87,7 +87,7 @@ Description: error, oversized or undersized. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_missed_errors +What: /sys/class/net//statistics/rx_missed_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -96,7 +96,7 @@ Description: due to lack of capacity in the receive side. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_nohandler +What: /sys/class/net//statistics/rx_nohandler Date: February 2016 KernelVersion: 4.6 Contact: netdev@vger.kernel.org @@ -104,7 +104,7 @@ Description: Indicates the number of received packets that were dropped on an inactive device by the network core. -What: /sys/class//statistics/rx_over_errors +What: /sys/class/net//statistics/rx_over_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -114,7 +114,7 @@ Description: (e.g: larger than MTU). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_packets +What: /sys/class/net//statistics/rx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -122,7 +122,7 @@ Description: Indicates the total number of good packets received by this network device. -What: /sys/class//statistics/tx_aborted_errors +What: /sys/class/net//statistics/tx_aborted_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -132,7 +132,7 @@ Description: a medium collision). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/tx_bytes +What: /sys/class/net//statistics/tx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -143,7 +143,7 @@ Description: transmitted packets or all packets that have been queued for transmission. -What: /sys/class//statistics/tx_carrier_errors +What: /sys/class/net//statistics/tx_carrier_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -152,7 +152,7 @@ Description: because of carrier errors (e.g: physical link down). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/tx_compressed +What: /sys/class/net//statistics/tx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -161,7 +161,7 @@ Description: this might only be relevant for devices that support compression (e.g: PPP). -What: /sys/class//statistics/tx_dropped +What: /sys/class/net//statistics/tx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -170,7 +170,7 @@ Description: See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_errors +What: /sys/class/net//statistics/tx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -179,7 +179,7 @@ Description: a network device. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_fifo_errors +What: /sys/class/net//statistics/tx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -188,7 +188,7 @@ Description: FIFO error. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_heartbeat_errors +What: /sys/class/net//statistics/tx_heartbeat_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -197,7 +197,7 @@ Description: reported as heartbeat errors. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_packets +What: /sys/class/net//statistics/tx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -206,7 +206,7 @@ Description: device. See the driver for whether this reports the number of all attempted or successful transmissions. -What: /sys/class//statistics/tx_window_errors +What: /sys/class/net//statistics/tx_window_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org From e56c671c2272d939d48a66be7e73b92b74c560c2 Mon Sep 17 00:00:00 2001 From: Vaishnav Achath Date: Mon, 12 Feb 2024 17:30:49 +0530 Subject: [PATCH 244/311] spi: omap2-mcspi: Revert FIFO support without DMA MCSPI controller have few limitations regarding the transaction size when the FIFO buffer is enabled and the WCNT feature is used to find the end of word, in this case if WCNT is not a multiple of the FIFO Almost Empty Level (AEL), then the FIFO empty event is not generated correctly. In addition to this limitation, few other unknown sequence of events that causes the FIFO empty status to not reflect the exact status were found when FIFO is being used without DMA enabled during extended testing in AM65x platform. Till the exact root cause is found and fixed, revert the FIFO support without DMA. See J721E Technical Reference Manual (SPRUI1C), section 12.1.5 for further details: http://www.ti.com/lit/pdf/spruil1 This reverts commit 75223bbea840e ("spi: omap2-mcspi: Add FIFO support without DMA") Signed-off-by: Vaishnav Achath Link: https://msgid.link/r/20240212120049.438495-1-vaishnav.a@ti.com Signed-off-by: Mark Brown --- drivers/spi/spi-omap2-mcspi.c | 137 ++-------------------------------- 1 file changed, 8 insertions(+), 129 deletions(-) diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index a0c9fea908f5..ddf1c684bcc7 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -53,8 +53,6 @@ /* per-register bitmasks: */ #define OMAP2_MCSPI_IRQSTATUS_EOW BIT(17) -#define OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY BIT(0) -#define OMAP2_MCSPI_IRQSTATUS_RX0_FULL BIT(2) #define OMAP2_MCSPI_MODULCTRL_SINGLE BIT(0) #define OMAP2_MCSPI_MODULCTRL_MS BIT(2) @@ -293,7 +291,7 @@ static void omap2_mcspi_set_mode(struct spi_controller *ctlr) } static void omap2_mcspi_set_fifo(const struct spi_device *spi, - struct spi_transfer *t, int enable, int dma_enabled) + struct spi_transfer *t, int enable) { struct spi_controller *ctlr = spi->controller; struct omap2_mcspi_cs *cs = spi->controller_state; @@ -314,28 +312,20 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi, max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH / 2; else max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH; - if (dma_enabled) - wcnt = t->len / bytes_per_word; - else - wcnt = 0; + + wcnt = t->len / bytes_per_word; if (wcnt > OMAP2_MCSPI_MAX_FIFOWCNT) goto disable_fifo; xferlevel = wcnt << 16; if (t->rx_buf != NULL) { chconf |= OMAP2_MCSPI_CHCONF_FFER; - if (dma_enabled) - xferlevel |= (bytes_per_word - 1) << 8; - else - xferlevel |= (max_fifo_depth - 1) << 8; + xferlevel |= (bytes_per_word - 1) << 8; } if (t->tx_buf != NULL) { chconf |= OMAP2_MCSPI_CHCONF_FFET; - if (dma_enabled) - xferlevel |= bytes_per_word - 1; - else - xferlevel |= (max_fifo_depth - 1); + xferlevel |= bytes_per_word - 1; } mcspi_write_reg(ctlr, OMAP2_MCSPI_XFERLEVEL, xferlevel); @@ -892,113 +882,6 @@ out: return count - c; } -static unsigned -omap2_mcspi_txrx_piofifo(struct spi_device *spi, struct spi_transfer *xfer) -{ - struct omap2_mcspi_cs *cs = spi->controller_state; - struct omap2_mcspi *mcspi; - unsigned int count, c; - unsigned int iter, cwc; - int last_request; - void __iomem *base = cs->base; - void __iomem *tx_reg; - void __iomem *rx_reg; - void __iomem *chstat_reg; - void __iomem *irqstat_reg; - int word_len, bytes_per_word; - u8 *rx; - const u8 *tx; - - mcspi = spi_controller_get_devdata(spi->controller); - count = xfer->len; - c = count; - word_len = cs->word_len; - bytes_per_word = mcspi_bytes_per_word(word_len); - - /* - * We store the pre-calculated register addresses on stack to speed - * up the transfer loop. - */ - tx_reg = base + OMAP2_MCSPI_TX0; - rx_reg = base + OMAP2_MCSPI_RX0; - chstat_reg = base + OMAP2_MCSPI_CHSTAT0; - irqstat_reg = base + OMAP2_MCSPI_IRQSTATUS; - - if (c < (word_len >> 3)) - return 0; - - rx = xfer->rx_buf; - tx = xfer->tx_buf; - - do { - /* calculate number of words in current iteration */ - cwc = min((unsigned int)mcspi->fifo_depth / bytes_per_word, - c / bytes_per_word); - last_request = cwc != (mcspi->fifo_depth / bytes_per_word); - if (tx) { - if (mcspi_wait_for_reg_bit(irqstat_reg, - OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY) < 0) { - dev_err(&spi->dev, "TX Empty timed out\n"); - goto out; - } - writel_relaxed(OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY, irqstat_reg); - - for (iter = 0; iter < cwc; iter++, tx += bytes_per_word) { - if (bytes_per_word == 1) - writel_relaxed(*tx, tx_reg); - else if (bytes_per_word == 2) - writel_relaxed(*((u16 *)tx), tx_reg); - else if (bytes_per_word == 4) - writel_relaxed(*((u32 *)tx), tx_reg); - } - } - - if (rx) { - if (!last_request && - mcspi_wait_for_reg_bit(irqstat_reg, - OMAP2_MCSPI_IRQSTATUS_RX0_FULL) < 0) { - dev_err(&spi->dev, "RX_FULL timed out\n"); - goto out; - } - writel_relaxed(OMAP2_MCSPI_IRQSTATUS_RX0_FULL, irqstat_reg); - - for (iter = 0; iter < cwc; iter++, rx += bytes_per_word) { - if (last_request && - mcspi_wait_for_reg_bit(chstat_reg, - OMAP2_MCSPI_CHSTAT_RXS) < 0) { - dev_err(&spi->dev, "RXS timed out\n"); - goto out; - } - if (bytes_per_word == 1) - *rx = readl_relaxed(rx_reg); - else if (bytes_per_word == 2) - *((u16 *)rx) = readl_relaxed(rx_reg); - else if (bytes_per_word == 4) - *((u32 *)rx) = readl_relaxed(rx_reg); - } - } - - if (last_request) { - if (mcspi_wait_for_reg_bit(chstat_reg, - OMAP2_MCSPI_CHSTAT_EOT) < 0) { - dev_err(&spi->dev, "EOT timed out\n"); - goto out; - } - if (mcspi_wait_for_reg_bit(chstat_reg, - OMAP2_MCSPI_CHSTAT_TXFFE) < 0) { - dev_err(&spi->dev, "TXFFE timed out\n"); - goto out; - } - omap2_mcspi_set_enable(spi, 0); - } - c -= cwc * bytes_per_word; - } while (c >= bytes_per_word); - -out: - omap2_mcspi_set_enable(spi, 1); - return count - c; -} - static u32 omap2_mcspi_calc_divisor(u32 speed_hz, u32 ref_clk_hz) { u32 div; @@ -1323,9 +1206,7 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr, if ((mcspi_dma->dma_rx && mcspi_dma->dma_tx) && ctlr->cur_msg_mapped && ctlr->can_dma(ctlr, spi, t)) - omap2_mcspi_set_fifo(spi, t, 1, 1); - else if (t->len > OMAP2_MCSPI_MAX_FIFODEPTH) - omap2_mcspi_set_fifo(spi, t, 1, 0); + omap2_mcspi_set_fifo(spi, t, 1); omap2_mcspi_set_enable(spi, 1); @@ -1338,8 +1219,6 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr, ctlr->cur_msg_mapped && ctlr->can_dma(ctlr, spi, t)) count = omap2_mcspi_txrx_dma(spi, t); - else if (mcspi->fifo_depth > 0) - count = omap2_mcspi_txrx_piofifo(spi, t); else count = omap2_mcspi_txrx_pio(spi, t); @@ -1352,7 +1231,7 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr, omap2_mcspi_set_enable(spi, 0); if (mcspi->fifo_depth > 0) - omap2_mcspi_set_fifo(spi, t, 0, 0); + omap2_mcspi_set_fifo(spi, t, 0); out: /* Restore defaults if they were overriden */ @@ -1375,7 +1254,7 @@ out: omap2_mcspi_set_cs(spi, !(spi->mode & SPI_CS_HIGH)); if (mcspi->fifo_depth > 0 && t) - omap2_mcspi_set_fifo(spi, t, 0, 0); + omap2_mcspi_set_fifo(spi, t, 0); return status; } From 8f44e3808200c1434c26ef459722f88f48b306df Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 12 Feb 2024 10:20:27 +0200 Subject: [PATCH 245/311] spi: intel-pci: Add support for Lunar Lake-M SPI serial flash Add Intel Lunar Lake-M PCI ID to the driver list of supported devices. This is the same controller found in previous generations. Signed-off-by: Mika Westerberg Link: https://msgid.link/r/20240212082027.2462849-1-mika.westerberg@linux.intel.com Signed-off-by: Mark Brown --- drivers/spi/spi-intel-pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index 07d20ca1164c..4337ca51d7aa 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -85,6 +85,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0xa2a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0xa823), (unsigned long)&cnl_info }, { }, }; MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids); From 2f0dbb24f78a333433a2b875c0b76bf55c119cd4 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sun, 11 Feb 2024 16:58:17 +0000 Subject: [PATCH 246/311] regmap: kunit: Ensure that changed bytes are actually different During the cache sync test we verify that values we expect to have been written only to the cache do not appear in the hardware. This works most of the time but since we randomly generate both the original and new values there is a low probability that these values may actually be the same. Wrap get_random_bytes() to ensure that the values are different, there are other tests which should have similar verification that we actually changed something. While we're at it refactor the test to use three changed values rather than attempting to use one of them twice, that just complicates checking that our new values are actually new. We use random generation to try to avoid data dependencies in the tests. Reported-by: Guenter Roeck Reviewed-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Mark Brown Link: https://msgid.link/r/20240211-regmap-kunit-random-change-v3-1-e387a9ea4468@kernel.org Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-kunit.c | 54 +++++++++++++++++++++--------- 1 file changed, 38 insertions(+), 16 deletions(-) diff --git a/drivers/base/regmap/regmap-kunit.c b/drivers/base/regmap/regmap-kunit.c index 4eb18f5d3265..0d957c5f1bcc 100644 --- a/drivers/base/regmap/regmap-kunit.c +++ b/drivers/base/regmap/regmap-kunit.c @@ -9,6 +9,23 @@ #define BLOCK_TEST_SIZE 12 +static void get_changed_bytes(void *orig, void *new, size_t size) +{ + char *o = orig; + char *n = new; + int i; + + get_random_bytes(new, size); + + /* + * This could be nicer and more efficient but we shouldn't + * super care. + */ + for (i = 0; i < size; i++) + while (n[i] == o[i]) + get_random_bytes(&n[i], 1); +} + static const struct regmap_config test_regmap_config = { .max_register = BLOCK_TEST_SIZE, .reg_stride = 1, @@ -1252,7 +1269,7 @@ static void raw_sync(struct kunit *test) struct regmap *map; struct regmap_config config; struct regmap_ram_data *data; - u16 val[2]; + u16 val[3]; u16 *hw_buf; unsigned int rval; int i; @@ -1266,17 +1283,13 @@ static void raw_sync(struct kunit *test) hw_buf = (u16 *)data->vals; - get_random_bytes(&val, sizeof(val)); + get_changed_bytes(&hw_buf[2], &val[0], sizeof(val)); /* Do a regular write and a raw write in cache only mode */ regcache_cache_only(map, true); - KUNIT_EXPECT_EQ(test, 0, regmap_raw_write(map, 2, val, sizeof(val))); - if (config.val_format_endian == REGMAP_ENDIAN_BIG) - KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 6, - be16_to_cpu(val[0]))); - else - KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 6, - le16_to_cpu(val[0]))); + KUNIT_EXPECT_EQ(test, 0, regmap_raw_write(map, 2, val, + sizeof(u16) * 2)); + KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 4, val[2])); /* We should read back the new values, and defaults for the rest */ for (i = 0; i < config.max_register + 1; i++) { @@ -1285,24 +1298,34 @@ static void raw_sync(struct kunit *test) switch (i) { case 2: case 3: - case 6: if (config.val_format_endian == REGMAP_ENDIAN_BIG) { KUNIT_EXPECT_EQ(test, rval, - be16_to_cpu(val[i % 2])); + be16_to_cpu(val[i - 2])); } else { KUNIT_EXPECT_EQ(test, rval, - le16_to_cpu(val[i % 2])); + le16_to_cpu(val[i - 2])); } break; + case 4: + KUNIT_EXPECT_EQ(test, rval, val[i - 2]); + break; default: KUNIT_EXPECT_EQ(test, config.reg_defaults[i].def, rval); break; } } + + /* + * The value written via _write() was translated by the core, + * translate the original copy for comparison purposes. + */ + if (config.val_format_endian == REGMAP_ENDIAN_BIG) + val[2] = cpu_to_be16(val[2]); + else + val[2] = cpu_to_le16(val[2]); /* The values should not appear in the "hardware" */ - KUNIT_EXPECT_MEMNEQ(test, &hw_buf[2], val, sizeof(val)); - KUNIT_EXPECT_MEMNEQ(test, &hw_buf[6], val, sizeof(u16)); + KUNIT_EXPECT_MEMNEQ(test, &hw_buf[2], &val[0], sizeof(val)); for (i = 0; i < config.max_register + 1; i++) data->written[i] = false; @@ -1313,8 +1336,7 @@ static void raw_sync(struct kunit *test) KUNIT_EXPECT_EQ(test, 0, regcache_sync(map)); /* The values should now appear in the "hardware" */ - KUNIT_EXPECT_MEMEQ(test, &hw_buf[2], val, sizeof(val)); - KUNIT_EXPECT_MEMEQ(test, &hw_buf[6], val, sizeof(u16)); + KUNIT_EXPECT_MEMEQ(test, &hw_buf[2], &val[0], sizeof(val)); regmap_exit(map); } From 7d8c67dd5d4f2ed1907e192c73dd948d35145641 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 12 Jan 2024 10:59:03 -0800 Subject: [PATCH 247/311] xen/xenbus: document will_handle argument for xenbus_watch_path() Commit 2e85d32b1c86 ("xen/xenbus: Add 'will_handle' callback support in xenbus_watch_path()") added will_handle argument to xenbus_watch_path() and its wrapper, xenbus_watch_pathfmt(), but didn't document it on the kerneldoc comments of the function. This is causing warnings that reported by kernel test robot. Add the documentation to fix it. Fixes: 2e85d32b1c86 ("xen/xenbus: Add 'will_handle' callback support in xenbus_watch_path()") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202401121154.FI8jDGun-lkp@intel.com/ Signed-off-by: SeongJae Park Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20240112185903.83737-1-sj@kernel.org Signed-off-by: Juergen Gross --- drivers/xen/xenbus/xenbus_client.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 32835b4b9bc5..51b3124b0d56 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -116,14 +116,15 @@ EXPORT_SYMBOL_GPL(xenbus_strstate); * @dev: xenbus device * @path: path to watch * @watch: watch to register + * @will_handle: events queuing determine callback * @callback: callback to register * * Register a @watch on the given path, using the given xenbus_watch structure - * for storage, and the given @callback function as the callback. On success, - * the given @path will be saved as @watch->node, and remains the - * caller's to free. On error, @watch->node will - * be NULL, the device will switch to %XenbusStateClosing, and the error will - * be saved in the store. + * for storage, @will_handle function as the callback to determine if each + * event need to be queued, and the given @callback function as the callback. + * On success, the given @path will be saved as @watch->node, and remains the + * caller's to free. On error, @watch->node will be NULL, the device will + * switch to %XenbusStateClosing, and the error will be saved in the store. * * Returns: %0 on success or -errno on error */ @@ -158,11 +159,13 @@ EXPORT_SYMBOL_GPL(xenbus_watch_path); * xenbus_watch_pathfmt - register a watch on a sprintf-formatted path * @dev: xenbus device * @watch: watch to register + * @will_handle: events queuing determine callback * @callback: callback to register * @pathfmt: format of path to watch * * Register a watch on the given @path, using the given xenbus_watch - * structure for storage, and the given @callback function as the + * structure for storage, @will_handle function as the callback to determine if + * each event need to be queued, and the given @callback function as the * callback. On success, the watched path (@path/@path2) will be saved * as @watch->node, and becomes the caller's to kfree(). * On error, watch->node will be NULL, so the caller has nothing to From 3693bb4465e6e32a204a5b86d3ec7e6b9f7e67c2 Mon Sep 17 00:00:00 2001 From: Kunwu Chan Date: Fri, 19 Jan 2024 17:49:48 +0800 Subject: [PATCH 248/311] x86/xen: Add some null pointer checking to smp.c kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Ensure the allocation was successful by checking the pointer validity. Signed-off-by: Kunwu Chan Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202401161119.iof6BQsf-lkp@intel.com/ Suggested-by: Markus Elfring Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20240119094948.275390-1-chentao@kylinos.cn Signed-off-by: Juergen Gross --- arch/x86/xen/smp.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 4b0d6fff88de..1fb9a1644d94 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -65,6 +65,8 @@ int xen_smp_intr_init(unsigned int cpu) char *resched_name, *callfunc_name, *debug_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); + if (!resched_name) + goto fail_mem; per_cpu(xen_resched_irq, cpu).name = resched_name; rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu, @@ -77,6 +79,8 @@ int xen_smp_intr_init(unsigned int cpu) per_cpu(xen_resched_irq, cpu).irq = rc; callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu); + if (!callfunc_name) + goto fail_mem; per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR, cpu, @@ -90,6 +94,9 @@ int xen_smp_intr_init(unsigned int cpu) if (!xen_fifo_events) { debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); + if (!debug_name) + goto fail_mem; + per_cpu(xen_debug_irq, cpu).name = debug_name; rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, @@ -101,6 +108,9 @@ int xen_smp_intr_init(unsigned int cpu) } callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu); + if (!callfunc_name) + goto fail_mem; + per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, cpu, @@ -114,6 +124,8 @@ int xen_smp_intr_init(unsigned int cpu) return 0; + fail_mem: + rc = -ENOMEM; fail: xen_smp_intr_free(cpu); return rc; From d55347bfe4e66dce2e1e7501e5492f4af3e315f8 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 11 Feb 2024 08:08:37 -0800 Subject: [PATCH 249/311] MIPS: Add 'memory' clobber to csum_ipv6_magic() inline assembler After 'lib: checksum: Use aligned accesses for ip_fast_csum and csum_ipv6_magic tests' was applied, the test_csum_ipv6_magic unit test started failing for all mips platforms, both little and bit endian. Oddly enough, adding debug code into test_csum_ipv6_magic() made the problem disappear. The gcc manual says: "The "memory" clobber tells the compiler that the assembly code performs memory reads or writes to items other than those listed in the input and output operands (for example, accessing the memory pointed to by one of the input parameters) " This is definitely the case for csum_ipv6_magic(). Indeed, adding the 'memory' clobber fixes the problem. Cc: Charlie Jenkins Cc: Palmer Dabbelt Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Guenter Roeck Reviewed-by: Charlie Jenkins Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/checksum.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h index 4044eaf989ac..0921ddda11a4 100644 --- a/arch/mips/include/asm/checksum.h +++ b/arch/mips/include/asm/checksum.h @@ -241,7 +241,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " .set pop" : "=&r" (sum), "=&r" (tmp) : "r" (saddr), "r" (daddr), - "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)); + "0" (htonl(len)), "r" (htonl(proto)), "r" (sum) + : "memory"); return csum_fold(sum); } From 11ba1728be3edb6928791f4c622f154ebe228ae6 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Fri, 2 Feb 2024 12:30:26 +0000 Subject: [PATCH 250/311] ptrace: Introduce exception_ip arch hook On architectures with delay slot, architecture level instruction pointer (or program counter) in pt_regs may differ from where exception was triggered. Introduce exception_ip hook to invoke architecture code and determine actual instruction pointer to the exception. Link: https://lore.kernel.org/lkml/00d1b813-c55f-4365-8d81-d70258e10b16@app.fastmail.com/ Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/ptrace.h | 2 ++ arch/mips/kernel/ptrace.c | 7 +++++++ include/linux/ptrace.h | 4 ++++ 3 files changed, 13 insertions(+) diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index daf3cf244ea9..701a233583c2 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -154,6 +154,8 @@ static inline long regs_return_value(struct pt_regs *regs) } #define instruction_pointer(regs) ((regs)->cp0_epc) +extern unsigned long exception_ip(struct pt_regs *regs); +#define exception_ip(regs) exception_ip(regs) #define profile_pc(regs) instruction_pointer(regs) extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall); diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index d9df543f7e2c..59288c13b581 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -31,6 +31,7 @@ #include #include +#include #include #include #include @@ -48,6 +49,12 @@ #define CREATE_TRACE_POINTS #include +unsigned long exception_ip(struct pt_regs *regs) +{ + return exception_epc(regs); +} +EXPORT_SYMBOL(exception_ip); + /* * Called by kernel/ptrace.c when detaching.. * diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index eaaef3ffec22..90507d4afcd6 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -393,6 +393,10 @@ static inline void user_single_step_report(struct pt_regs *regs) #define current_user_stack_pointer() user_stack_pointer(current_pt_regs()) #endif +#ifndef exception_ip +#define exception_ip(x) instruction_pointer(x) +#endif + extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); From 9d6e21ddf20293b3880ae55b9d14de91c5891c59 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Fri, 2 Feb 2024 12:30:27 +0000 Subject: [PATCH 251/311] MIPS: Clear Cause.BD in instruction_pointer_set Clear Cause.BD after we use instruction_pointer_set to override EPC. This can prevent exception_epc check against instruction code at new return address. It won't be considered as "in delay slot" after epc being overridden anyway. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/ptrace.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index 701a233583c2..d14d0e37ad02 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -60,6 +60,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->cp0_epc = val; + regs->cp0_cause &= ~CAUSEF_BD; } /* Query offset/name of register from its name/offset */ From 8fa5070833886268e4fb646daaca99f725b378e9 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Fri, 2 Feb 2024 12:30:28 +0000 Subject: [PATCH 252/311] mm/memory: Use exception ip to search exception tables On architectures with delay slot, instruction_pointer() may differ from where exception was triggered. Use exception_ip we just introduced to search exception tables to get rid of the problem. Fixes: 4bce37a68ff8 ("mips/mm: Convert to using lock_mm_and_find_vma()") Reported-by: Xi Ruoyao Link: https://lore.kernel.org/r/75e9fd7b08562ad9b456a5bdaacb7cc220311cc9.camel@xry111.site/ Suggested-by: Linus Torvalds Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- mm/memory.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 89bcae0b224d..15f8b10ea17c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5478,7 +5478,7 @@ static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs return true; if (regs && !user_mode(regs)) { - unsigned long ip = instruction_pointer(regs); + unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } @@ -5503,7 +5503,7 @@ static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_r { mmap_read_unlock(mm); if (regs && !user_mode(regs)) { - unsigned long ip = instruction_pointer(regs); + unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } From 73d9629e1c8c1982f13688c4d1019c3994647ccc Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Thu, 8 Feb 2024 10:03:33 -0800 Subject: [PATCH 253/311] i40e: Do not allow untrusted VF to remove administratively set MAC Currently when PF administratively sets VF's MAC address and the VF is put down (VF tries to delete all MACs) then the MAC is removed from MAC filters and primary VF MAC is zeroed. Do not allow untrusted VF to remove primary MAC when it was set administratively by PF. Reproducer: 1) Create VF 2) Set VF interface up 3) Administratively set the VF's MAC 4) Put VF interface down [root@host ~]# echo 1 > /sys/class/net/enp2s0f0/device/sriov_numvfs [root@host ~]# ip link set enp2s0f0v0 up [root@host ~]# ip link set enp2s0f0 vf 0 mac fe:6c:b5:da:c7:7d [root@host ~]# ip link show enp2s0f0 23: enp2s0f0: mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000 link/ether 3c:ec:ef:b7:dd:04 brd ff:ff:ff:ff:ff:ff vf 0 link/ether fe:6c:b5:da:c7:7d brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off [root@host ~]# ip link set enp2s0f0v0 down [root@host ~]# ip link show enp2s0f0 23: enp2s0f0: mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000 link/ether 3c:ec:ef:b7:dd:04 brd ff:ff:ff:ff:ff:ff vf 0 link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off Fixes: 700bbf6c1f9e ("i40e: allow VF to remove any MAC filter") Fixes: ceb29474bbbc ("i40e: Add support for VF to specify its primary MAC address") Signed-off-by: Ivan Vecera Reviewed-by: Simon Horman Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20240208180335.1844996-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 38 ++++++++++++++++--- 1 file changed, 33 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 908cdbd3ec5d..b34c71770887 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2848,6 +2848,24 @@ error_param: (u8 *)&stats, sizeof(stats)); } +/** + * i40e_can_vf_change_mac + * @vf: pointer to the VF info + * + * Return true if the VF is allowed to change its MAC filters, false otherwise + */ +static bool i40e_can_vf_change_mac(struct i40e_vf *vf) +{ + /* If the VF MAC address has been set administratively (via the + * ndo_set_vf_mac command), then deny permission to the VF to + * add/delete unicast MAC addresses, unless the VF is trusted + */ + if (vf->pf_set_mac && !vf->trusted) + return false; + + return true; +} + #define I40E_MAX_MACVLAN_PER_HW 3072 #define I40E_MAX_MACVLAN_PER_PF(num_ports) (I40E_MAX_MACVLAN_PER_HW / \ (num_ports)) @@ -2907,8 +2925,8 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, * The VF may request to set the MAC address filter already * assigned to it so do not return an error in that case. */ - if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) && - !is_multicast_ether_addr(addr) && vf->pf_set_mac && + if (!i40e_can_vf_change_mac(vf) && + !is_multicast_ether_addr(addr) && !ether_addr_equal(addr, vf->default_lan_addr.addr)) { dev_err(&pf->pdev->dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); @@ -3114,19 +3132,29 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) ret = -EINVAL; goto error_param; } - if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr)) - was_unimac_deleted = true; } vsi = pf->vsi[vf->lan_vsi_idx]; spin_lock_bh(&vsi->mac_filter_hash_lock); /* delete addresses from the list */ - for (i = 0; i < al->num_elements; i++) + for (i = 0; i < al->num_elements; i++) { + const u8 *addr = al->list[i].addr; + + /* Allow to delete VF primary MAC only if it was not set + * administratively by PF or if VF is trusted. + */ + if (ether_addr_equal(addr, vf->default_lan_addr.addr) && + i40e_can_vf_change_mac(vf)) + was_unimac_deleted = true; + else + continue; + if (i40e_del_mac_filter(vsi, al->list[i].addr)) { ret = -EINVAL; spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } + } spin_unlock_bh(&vsi->mac_filter_hash_lock); From c2b3ec36b422a331e153a9e40d14adcf82685cee Mon Sep 17 00:00:00 2001 From: Maxim Galaganov Date: Fri, 9 Feb 2024 16:25:11 +0300 Subject: [PATCH 254/311] selftests: net: ip_local_port_range: define IPPROTO_MPTCP Older glibc's netinet/in.h may leave IPPROTO_MPTCP undefined when building ip_local_port_range.c, that leads to "error: use of undeclared identifier 'IPPROTO_MPTCP'". Define IPPROTO_MPTCP in such cases, just like in other MPTCP selftests. Fixes: 122db5e3634b ("selftests/net: add MPTCP coverage for IP_LOCAL_PORT_RANGE") Reported-by: Linux Kernel Functional Testing Closes: https://lore.kernel.org/netdev/CA+G9fYvGO5q4o_Td_kyQgYieXWKw6ktMa-Q0sBu6S-0y3w2aEQ@mail.gmail.com/ Signed-off-by: Maxim Galaganov Tested-by: Linux Kernel Functional Testing Link: https://lore.kernel.org/r/20240209132512.254520-1-max@internet.ru Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/ip_local_port_range.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/net/ip_local_port_range.c b/tools/testing/selftests/net/ip_local_port_range.c index 0f217a1cc837..6ebd58869a63 100644 --- a/tools/testing/selftests/net/ip_local_port_range.c +++ b/tools/testing/selftests/net/ip_local_port_range.c @@ -16,6 +16,10 @@ #define IP_LOCAL_PORT_RANGE 51 #endif +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif + static __u32 pack_port_range(__u16 lo, __u16 hi) { return (hi << 16) | (lo << 0); From c73729b64bb692186da080602cd13612783f52ac Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Wed, 8 Nov 2023 17:01:03 +0100 Subject: [PATCH 255/311] i40e: Fix waiting for queues of all VSIs to be disabled The function i40e_pf_wait_queues_disabled() iterates all PF's VSIs up to 'pf->hw.func_caps.num_vsis' but this is incorrect because the real number of VSIs can be up to 'pf->num_alloc_vsi' that can be higher. Fix this loop. Fixes: 69129dc39fac ("i40e: Modify Tx disable wait flow in case of DCB reconfiguration") Signed-off-by: Ivan Vecera Reviewed-by: Jacob Keller Reviewed-by: Wojciech Drewek Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 6e7fd473abfd..7a416e923b36 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5360,7 +5360,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf) { int v, ret = 0; - for (v = 0; v < pf->hw.func_caps.num_vsis; v++) { + for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v]) { ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]); if (ret) From 343bb39e1f25a73a38a03d98ca383495c0ed6e92 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Thu, 30 Nov 2023 20:31:34 +0100 Subject: [PATCH 256/311] i40e: Fix wrong mask used during DCB config Mask used for clearing PRTDCB_RETSTCC register in function i40e_dcb_hw_rx_ets_bw_config() is incorrect as there is used define I40E_PRTDCB_RETSTCC_ETSTC_SHIFT instead of define I40E_PRTDCB_RETSTCC_ETSTC_MASK. The PRTDCB_RETSTCC register is used to configure whether ETS or strict priority is used as TSA in Rx for particular TC. In practice it means that once the register is set to use ETS as TSA then it is not possible to switch back to strict priority without CoreR reset. Fix the value in the clearing mask. Fixes: 90bc8e003be2 ("i40e: Add hardware configuration for software based DCB") Signed-off-by: Ivan Vecera Reviewed-by: Przemek Kitszel Reviewed-by: Simon Horman Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_dcb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 9d88ed6105fd..8db1eb0c1768 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -1523,7 +1523,7 @@ void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share, reg = rd32(hw, I40E_PRTDCB_RETSTCC(i)); reg &= ~(I40E_PRTDCB_RETSTCC_BWSHARE_MASK | I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK | - I40E_PRTDCB_RETSTCC_ETSTC_SHIFT); + I40E_PRTDCB_RETSTCC_ETSTC_MASK); reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_BWSHARE_MASK, bw_share[i]); reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK, From 89a373e9131d4200038a0ef232dad80212209de0 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Tue, 6 Feb 2024 13:41:31 +0100 Subject: [PATCH 257/311] i40e: avoid double calling i40e_pf_rxq_wait() Currently, when interface is being brought down and i40e_vsi_stop_rings() is called, i40e_pf_rxq_wait() is called two times, which is wrong. To showcase this scenario, simplified call stack looks as follows: i40e_vsi_stop_rings() i40e_control wait rx_q() i40e_control_rx_q() i40e_pf_rxq_wait() i40e_vsi_wait_queues_disabled() i40e_pf_rxq_wait() // redundant call To fix this, let us s/i40e_control_wait_rx_q/i40e_control_rx_q within i40e_vsi_stop_rings(). Fixes: 65662a8dcdd0 ("i40e: Fix logic of disabling queues") Reviewed-by: Simon Horman Signed-off-by: Maciej Fijalkowski Reviewed-by: Ivan Vecera Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_main.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 7a416e923b36..06078c4d54e8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4926,7 +4926,7 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi) void i40e_vsi_stop_rings(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; - int pf_q, err, q_end; + int pf_q, q_end; /* When port TX is suspended, don't wait */ if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state)) @@ -4936,16 +4936,10 @@ void i40e_vsi_stop_rings(struct i40e_vsi *vsi) for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false); - for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) { - err = i40e_control_wait_rx_q(pf, pf_q, false); - if (err) - dev_info(&pf->pdev->dev, - "VSI seid %d Rx ring %d disable timeout\n", - vsi->seid, pf_q); - } + for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) + i40e_control_rx_q(pf, pf_q, false); msleep(I40E_DISABLE_TX_GAP_MSEC); - pf_q = vsi->base_queue; for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0); From 6ed8187bb36c14f5ea91be0bf20117379df2d25a Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Tue, 6 Feb 2024 13:41:32 +0100 Subject: [PATCH 258/311] i40e: take into account XDP Tx queues when stopping rings Seth reported that on his side XDP traffic can not survive a round of down/up against i40e interface. Dmesg output was telling us that we were not able to disable the very first XDP ring. That was due to the fact that in i40e_vsi_stop_rings() in a pre-work that is done before calling i40e_vsi_wait_queues_disabled(), XDP Tx queues were not taken into the account. To fix this, let us distinguish between Rx and Tx queue boundaries and take into the account XDP queues for Tx side. Reported-by: Seth Forshee Closes: https://lore.kernel.org/netdev/ZbkE7Ep1N1Ou17sA@do-x1extreme/ Fixes: 65662a8dcdd0 ("i40e: Fix logic of disabling queues") Tested-by: Seth Forshee Reviewed-by: Simon Horman Signed-off-by: Maciej Fijalkowski Reviewed-by: Ivan Vecera Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_main.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 06078c4d54e8..54eb55464e31 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4926,21 +4926,23 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi) void i40e_vsi_stop_rings(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; - int pf_q, q_end; + u32 pf_q, tx_q_end, rx_q_end; /* When port TX is suspended, don't wait */ if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state)) return i40e_vsi_stop_rings_no_wait(vsi); - q_end = vsi->base_queue + vsi->num_queue_pairs; - for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) - i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false); + tx_q_end = vsi->base_queue + + vsi->alloc_queue_pairs * (i40e_enabled_xdp_vsi(vsi) ? 2 : 1); + for (pf_q = vsi->base_queue; pf_q < tx_q_end; pf_q++) + i40e_pre_tx_queue_cfg(&pf->hw, pf_q, false); - for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) + rx_q_end = vsi->base_queue + vsi->num_queue_pairs; + for (pf_q = vsi->base_queue; pf_q < rx_q_end; pf_q++) i40e_control_rx_q(pf, pf_q, false); msleep(I40E_DISABLE_TX_GAP_MSEC); - for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) + for (pf_q = vsi->base_queue; pf_q < tx_q_end; pf_q++) wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0); i40e_vsi_wait_queues_disabled(vsi); From 1692b9775e745f84b69dc8ad0075b0855a43db4e Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 8 Feb 2024 09:48:27 +0000 Subject: [PATCH 259/311] net: stmmac: xgmac: use #define for string constants The cited commit introduces and uses the string constants dpp_tx_err and dpp_rx_err. These are assigned to constant fields of the array dwxgmac3_error_desc. It has been reported that on GCC 6 and 7.5.0 this results in warnings such as: .../dwxgmac2_core.c:836:20: error: initialiser element is not constant { true, "TDPES0", dpp_tx_err }, I have been able to reproduce this using: GCC 7.5.0, 8.4.0, 9.4.0 and 10.5.0. But not GCC 13.2.0. So it seems this effects older compilers but not newer ones. As Jon points out in his report, the minimum compiler supported by the kernel is GCC 5.1, so it does seem that this ought to be fixed. It is not clear to me what combination of 'const', if any, would address this problem. So this patch takes of using #defines for the string constants Compile tested only. Fixes: 46eba193d04f ("net: stmmac: xgmac: fix handling of DPP safety error for DMA channels") Reported-by: Jon Hunter Closes: https://lore.kernel.org/netdev/c25eb595-8d91-40ea-9f52-efa15ebafdbc@nvidia.com/ Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202402081135.lAxxBXHk-lkp@intel.com/ Signed-off-by: Simon Horman Link: https://lore.kernel.org/r/20240208-xgmac-const-v1-1-e69a1eeabfc8@kernel.org Signed-off-by: Jakub Kicinski --- .../ethernet/stmicro/stmmac/dwxgmac2_core.c | 69 ++++++++++--------- 1 file changed, 35 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 323c57f03c93..1af2f89a0504 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -830,41 +830,42 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= { { false, "UNKNOWN", "Unknown Error" }, /* 31 */ }; -static const char * const dpp_rx_err = "Read Rx Descriptor Parity checker Error"; -static const char * const dpp_tx_err = "Read Tx Descriptor Parity checker Error"; +#define DPP_RX_ERR "Read Rx Descriptor Parity checker Error" +#define DPP_TX_ERR "Read Tx Descriptor Parity checker Error" + static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = { - { true, "TDPES0", dpp_tx_err }, - { true, "TDPES1", dpp_tx_err }, - { true, "TDPES2", dpp_tx_err }, - { true, "TDPES3", dpp_tx_err }, - { true, "TDPES4", dpp_tx_err }, - { true, "TDPES5", dpp_tx_err }, - { true, "TDPES6", dpp_tx_err }, - { true, "TDPES7", dpp_tx_err }, - { true, "TDPES8", dpp_tx_err }, - { true, "TDPES9", dpp_tx_err }, - { true, "TDPES10", dpp_tx_err }, - { true, "TDPES11", dpp_tx_err }, - { true, "TDPES12", dpp_tx_err }, - { true, "TDPES13", dpp_tx_err }, - { true, "TDPES14", dpp_tx_err }, - { true, "TDPES15", dpp_tx_err }, - { true, "RDPES0", dpp_rx_err }, - { true, "RDPES1", dpp_rx_err }, - { true, "RDPES2", dpp_rx_err }, - { true, "RDPES3", dpp_rx_err }, - { true, "RDPES4", dpp_rx_err }, - { true, "RDPES5", dpp_rx_err }, - { true, "RDPES6", dpp_rx_err }, - { true, "RDPES7", dpp_rx_err }, - { true, "RDPES8", dpp_rx_err }, - { true, "RDPES9", dpp_rx_err }, - { true, "RDPES10", dpp_rx_err }, - { true, "RDPES11", dpp_rx_err }, - { true, "RDPES12", dpp_rx_err }, - { true, "RDPES13", dpp_rx_err }, - { true, "RDPES14", dpp_rx_err }, - { true, "RDPES15", dpp_rx_err }, + { true, "TDPES0", DPP_TX_ERR }, + { true, "TDPES1", DPP_TX_ERR }, + { true, "TDPES2", DPP_TX_ERR }, + { true, "TDPES3", DPP_TX_ERR }, + { true, "TDPES4", DPP_TX_ERR }, + { true, "TDPES5", DPP_TX_ERR }, + { true, "TDPES6", DPP_TX_ERR }, + { true, "TDPES7", DPP_TX_ERR }, + { true, "TDPES8", DPP_TX_ERR }, + { true, "TDPES9", DPP_TX_ERR }, + { true, "TDPES10", DPP_TX_ERR }, + { true, "TDPES11", DPP_TX_ERR }, + { true, "TDPES12", DPP_TX_ERR }, + { true, "TDPES13", DPP_TX_ERR }, + { true, "TDPES14", DPP_TX_ERR }, + { true, "TDPES15", DPP_TX_ERR }, + { true, "RDPES0", DPP_RX_ERR }, + { true, "RDPES1", DPP_RX_ERR }, + { true, "RDPES2", DPP_RX_ERR }, + { true, "RDPES3", DPP_RX_ERR }, + { true, "RDPES4", DPP_RX_ERR }, + { true, "RDPES5", DPP_RX_ERR }, + { true, "RDPES6", DPP_RX_ERR }, + { true, "RDPES7", DPP_RX_ERR }, + { true, "RDPES8", DPP_RX_ERR }, + { true, "RDPES9", DPP_RX_ERR }, + { true, "RDPES10", DPP_RX_ERR }, + { true, "RDPES11", DPP_RX_ERR }, + { true, "RDPES12", DPP_RX_ERR }, + { true, "RDPES13", DPP_RX_ERR }, + { true, "RDPES14", DPP_RX_ERR }, + { true, "RDPES15", DPP_RX_ERR }, }; static void dwxgmac3_handle_dma_err(struct net_device *ndev, From 2f74258d997c8b93627041d94daa265b5f0d1b4d Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Fri, 9 Feb 2024 16:13:07 -0800 Subject: [PATCH 260/311] ionic: minimal work with 0 budget We should be doing as little as possible besides freeing Tx space when our napi routines are called with budget of 0, so jump out before doing anything besides Tx cleaning. See commit afbed3f74830 ("net/mlx5e: do as little as possible in napi poll when budget is 0") for more info. Fixes: fe8c30b50835 ("ionic: separate interrupt for Tx and Rx") Reviewed-by: Brett Creeley Signed-off-by: Shannon Nelson Link: https://lore.kernel.org/r/20240210001307.48450-1-shannon.nelson@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 54cd96b035d6..6f4776759863 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -579,6 +579,9 @@ int ionic_tx_napi(struct napi_struct *napi, int budget) work_done = ionic_cq_service(cq, budget, ionic_tx_service, NULL, NULL); + if (unlikely(!budget)) + return budget; + if (work_done < budget && napi_complete_done(napi, work_done)) { ionic_dim_update(qcq, IONIC_LIF_F_TX_DIM_INTR); flags |= IONIC_INTR_CRED_UNMASK; @@ -607,6 +610,9 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) u32 work_done = 0; u32 flags = 0; + if (unlikely(!budget)) + return budget; + lif = cq->bound_q->lif; idev = &lif->ionic->idev; @@ -656,6 +662,9 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) tx_work_done = ionic_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT, ionic_tx_service, NULL, NULL); + if (unlikely(!budget)) + return budget; + rx_work_done = ionic_cq_service(rxcq, budget, ionic_rx_service, NULL, NULL); From 3e36031cc0540ca97b615cbb940331892cbd3d21 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Fri, 9 Feb 2024 16:20:02 -0800 Subject: [PATCH 261/311] pds_core: no health-thread in VF path The VFs don't run the health thread, so don't try to stop or restart the non-existent timer or work item. Fixes: d9407ff11809 ("pds_core: Prevent health thread from running during reset/remove") Reviewed-by: Brett Creeley Signed-off-by: Shannon Nelson Link: https://lore.kernel.org/r/20240210002002.49483-1-shannon.nelson@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/main.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index cdbf053b5376..0050c5894563 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -451,6 +451,9 @@ static void pdsc_remove(struct pci_dev *pdev) static void pdsc_stop_health_thread(struct pdsc *pdsc) { + if (pdsc->pdev->is_virtfn) + return; + timer_shutdown_sync(&pdsc->wdtimer); if (pdsc->health_work.func) cancel_work_sync(&pdsc->health_work); @@ -458,6 +461,9 @@ static void pdsc_stop_health_thread(struct pdsc *pdsc) static void pdsc_restart_health_thread(struct pdsc *pdsc) { + if (pdsc->pdev->is_virtfn) + return; + timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0); mod_timer(&pdsc->wdtimer, jiffies + 1); } From 9f30831390ede02d9fcd54fd9ea5a585ab649f4a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 9 Feb 2024 18:12:48 +0000 Subject: [PATCH 262/311] net: add rcu safety to rtnl_prop_list_size() rtnl_prop_list_size() can be called while alternative names are added or removed concurrently. if_nlmsg_size() / rtnl_calcit() can indeed be called without RTNL held. Use explicit RCU protection to avoid UAF. Fixes: 88f4fb0c7496 ("net: rtnetlink: put alternative names to getlink message") Signed-off-by: Eric Dumazet Cc: Jiri Pirko Link: https://lore.kernel.org/r/20240209181248.96637-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/core/dev.c | 2 +- net/core/rtnetlink.c | 15 +++++++++------ 2 files changed, 10 insertions(+), 7 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 9bb792cecc16..73a021973007 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -336,7 +336,7 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name) return -ENOMEM; netdev_name_node_add(net, name_node); /* The node that holds dev->name acts as a head of per-device list. */ - list_add_tail(&name_node->list, &dev->name_node->list); + list_add_tail_rcu(&name_node->list, &dev->name_node->list); return 0; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f6f29eb03ec2..9c4f427f3a50 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1020,14 +1020,17 @@ static size_t rtnl_xdp_size(void) static size_t rtnl_prop_list_size(const struct net_device *dev) { struct netdev_name_node *name_node; - size_t size; + unsigned int cnt = 0; - if (list_empty(&dev->name_node->list)) + rcu_read_lock(); + list_for_each_entry_rcu(name_node, &dev->name_node->list, list) + cnt++; + rcu_read_unlock(); + + if (!cnt) return 0; - size = nla_total_size(0); - list_for_each_entry(name_node, &dev->name_node->list, list) - size += nla_total_size(ALTIFNAMSIZ); - return size; + + return nla_total_size(0) + cnt * nla_total_size(ALTIFNAMSIZ); } static size_t rtnl_proto_down_size(const struct net_device *dev) From b2c52b8c128ea07f1632c516cec0d72cb63b5599 Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Sun, 28 Jan 2024 17:50:43 +0100 Subject: [PATCH 263/311] xen/privcmd: Use memdup_array_user() in alloc_ioreq() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * The function “memdup_array_user” was added with the commit 313ebe47d75558511aa1237b6e35c663b5c0ec6f ("string.h: add array-wrappers for (v)memdup_user()"). Thus use it accordingly. This issue was detected by using the Coccinelle software. * Delete a label which became unnecessary with this refactoring. Signed-off-by: Markus Elfring Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/41e333f7-1f3a-41b6-a121-a3c0ae54e36f@web.de Signed-off-by: Juergen Gross --- drivers/xen/privcmd.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 35b6e306026a..67dfa4778864 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -1223,18 +1223,13 @@ struct privcmd_kernel_ioreq *alloc_ioreq(struct privcmd_ioeventfd *ioeventfd) kioreq->ioreq = (struct ioreq *)(page_to_virt(pages[0])); mmap_write_unlock(mm); - size = sizeof(*ports) * kioreq->vcpus; - ports = kzalloc(size, GFP_KERNEL); - if (!ports) { - ret = -ENOMEM; + ports = memdup_array_user(u64_to_user_ptr(ioeventfd->ports), + kioreq->vcpus, sizeof(*ports)); + if (IS_ERR(ports)) { + ret = PTR_ERR(ports); goto error_kfree; } - if (copy_from_user(ports, u64_to_user_ptr(ioeventfd->ports), size)) { - ret = -EFAULT; - goto error_kfree_ports; - } - for (i = 0; i < kioreq->vcpus; i++) { kioreq->ports[i].vcpu = i; kioreq->ports[i].port = ports[i]; @@ -1256,7 +1251,7 @@ struct privcmd_kernel_ioreq *alloc_ioreq(struct privcmd_ioeventfd *ioeventfd) error_unbind: while (--i >= 0) unbind_from_irqhandler(irq_from_evtchn(ports[i]), &kioreq->ports[i]); -error_kfree_ports: + kfree(ports); error_kfree: kfree(kioreq); From 2528dcbea94496f080aad9311327baedc11831d7 Mon Sep 17 00:00:00 2001 From: "Ricardo B. Marliere" Date: Sat, 3 Feb 2024 15:53:37 -0300 Subject: [PATCH 264/311] xen: pcpu: make xen_pcpu_subsys const Now that the driver core can properly handle constant struct bus_type, move the xen_pcpu_subsys variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman Suggested-by: Greg Kroah-Hartman Signed-off-by: Ricardo B. Marliere Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20240203-bus_cleanup-xen-v1-1-c2f5fe89ed95@marliere.net Signed-off-by: Juergen Gross --- drivers/xen/pcpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index 508655273145..c63f317e3df3 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -65,7 +65,7 @@ struct pcpu { uint32_t flags; }; -static struct bus_type xen_pcpu_subsys = { +static const struct bus_type xen_pcpu_subsys = { .name = "xen_cpu", .dev_name = "xen_cpu", }; From b0f2f82c9c16427722b8782371c2efe82b1f815c Mon Sep 17 00:00:00 2001 From: "Ricardo B. Marliere" Date: Sat, 3 Feb 2024 15:53:38 -0300 Subject: [PATCH 265/311] xen: balloon: make balloon_subsys const Now that the driver core can properly handle constant struct bus_type, move the balloon_subsys variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman Suggested-by: Greg Kroah-Hartman Signed-off-by: Ricardo B. Marliere Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20240203-bus_cleanup-xen-v1-2-c2f5fe89ed95@marliere.net Signed-off-by: Juergen Gross --- drivers/xen/xen-balloon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c index 8cd583db20b1..b293d7652f15 100644 --- a/drivers/xen/xen-balloon.c +++ b/drivers/xen/xen-balloon.c @@ -237,7 +237,7 @@ static const struct attribute_group *balloon_groups[] = { NULL }; -static struct bus_type balloon_subsys = { +static const struct bus_type balloon_subsys = { .name = BALLOON_CLASS_NAME, .dev_name = BALLOON_CLASS_NAME, }; From bf5802238dc181b1f7375d358af1d01cd72d1c11 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 6 Feb 2024 09:03:24 -0800 Subject: [PATCH 266/311] xen/gntalloc: Replace UAPI 1-element array Without changing the structure size (since it is UAPI), add a proper flexible array member, and reference it in the kernel so that it will not be trip the array-bounds sanitizer[1]. Link: https://github.com/KSPP/linux/issues/113 [1] Cc: Juergen Gross Cc: Stefano Stabellini Cc: Oleksandr Tyshchenko Cc: Gustavo A. R. Silva Cc: xen-devel@lists.xenproject.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20240206170320.work.437-kees@kernel.org Signed-off-by: Juergen Gross --- drivers/xen/gntalloc.c | 2 +- include/uapi/xen/gntalloc.h | 5 ++++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c index 26ffb8755ffb..f93f73ecefee 100644 --- a/drivers/xen/gntalloc.c +++ b/drivers/xen/gntalloc.c @@ -317,7 +317,7 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv, rc = -EFAULT; goto out_free; } - if (copy_to_user(arg->gref_ids, gref_ids, + if (copy_to_user(arg->gref_ids_flex, gref_ids, sizeof(gref_ids[0]) * op.count)) { rc = -EFAULT; goto out_free; diff --git a/include/uapi/xen/gntalloc.h b/include/uapi/xen/gntalloc.h index 48d2790ef928..3109282672f3 100644 --- a/include/uapi/xen/gntalloc.h +++ b/include/uapi/xen/gntalloc.h @@ -31,7 +31,10 @@ struct ioctl_gntalloc_alloc_gref { __u64 index; /* The grant references of the newly created grant, one per page */ /* Variable size, depending on count */ - __u32 gref_ids[1]; + union { + __u32 gref_ids[1]; + __DECLARE_FLEX_ARRAY(__u32, gref_ids_flex); + }; }; #define GNTALLOC_FLAG_WRITABLE 1 From fa765c4b4aed2d64266b694520ecb025c862c5a9 Mon Sep 17 00:00:00 2001 From: Maximilian Heyne Date: Wed, 24 Jan 2024 16:31:28 +0000 Subject: [PATCH 267/311] xen/events: close evtchn after mapping cleanup shutdown_pirq and startup_pirq are not taking the irq_mapping_update_lock because they can't due to lock inversion. Both are called with the irq_desc->lock being taking. The lock order, however, is first irq_mapping_update_lock and then irq_desc->lock. This opens multiple races: - shutdown_pirq can be interrupted by a function that allocates an event channel: CPU0 CPU1 shutdown_pirq { xen_evtchn_close(e) __startup_pirq { EVTCHNOP_bind_pirq -> returns just freed evtchn e set_evtchn_to_irq(e, irq) } xen_irq_info_cleanup() { set_evtchn_to_irq(e, -1) } } Assume here event channel e refers here to the same event channel number. After this race the evtchn_to_irq mapping for e is invalid (-1). - __startup_pirq races with __unbind_from_irq in a similar way. Because __startup_pirq doesn't take irq_mapping_update_lock it can grab the evtchn that __unbind_from_irq is currently freeing and cleaning up. In this case even though the event channel is allocated, its mapping can be unset in evtchn_to_irq. The fix is to first cleanup the mappings and then close the event channel. In this way, when an event channel gets allocated it's potential previous evtchn_to_irq mappings are guaranteed to be unset already. This is also the reverse order of the allocation where first the event channel is allocated and then the mappings are setup. On a 5.10 kernel prior to commit 3fcdaf3d7634 ("xen/events: modify internal [un]bind interfaces"), we hit a BUG like the following during probing of NVMe devices. The issue is that during nvme_setup_io_queues, pci_free_irq is called for every device which results in a call to shutdown_pirq. With many nvme devices it's therefore likely to hit this race during boot because there will be multiple calls to shutdown_pirq and startup_pirq are running potentially in parallel. ------------[ cut here ]------------ blkfront: xvda: barrier or flush: disabled; persistent grants: enabled; indirect descriptors: enabled; bounce buffer: enabled kernel BUG at drivers/xen/events/events_base.c:499! invalid opcode: 0000 [#1] SMP PTI CPU: 44 PID: 375 Comm: kworker/u257:23 Not tainted 5.10.201-191.748.amzn2.x86_64 #1 Hardware name: Xen HVM domU, BIOS 4.11.amazon 08/24/2006 Workqueue: nvme-reset-wq nvme_reset_work RIP: 0010:bind_evtchn_to_cpu+0xdf/0xf0 Code: 5d 41 5e c3 cc cc cc cc 44 89 f7 e8 2b 55 ad ff 49 89 c5 48 85 c0 0f 84 64 ff ff ff 4c 8b 68 30 41 83 fe ff 0f 85 60 ff ff ff <0f> 0b 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 0f 1f 44 00 00 RSP: 0000:ffffc9000d533b08 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000006 RDX: 0000000000000028 RSI: 00000000ffffffff RDI: 00000000ffffffff RBP: ffff888107419680 R08: 0000000000000000 R09: ffffffff82d72b00 R10: 0000000000000000 R11: 0000000000000000 R12: 00000000000001ed R13: 0000000000000000 R14: 00000000ffffffff R15: 0000000000000002 FS: 0000000000000000(0000) GS:ffff88bc8b500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000002610001 CR4: 00000000001706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? show_trace_log_lvl+0x1c1/0x2d9 ? show_trace_log_lvl+0x1c1/0x2d9 ? set_affinity_irq+0xdc/0x1c0 ? __die_body.cold+0x8/0xd ? die+0x2b/0x50 ? do_trap+0x90/0x110 ? bind_evtchn_to_cpu+0xdf/0xf0 ? do_error_trap+0x65/0x80 ? bind_evtchn_to_cpu+0xdf/0xf0 ? exc_invalid_op+0x4e/0x70 ? bind_evtchn_to_cpu+0xdf/0xf0 ? asm_exc_invalid_op+0x12/0x20 ? bind_evtchn_to_cpu+0xdf/0xf0 ? bind_evtchn_to_cpu+0xc5/0xf0 set_affinity_irq+0xdc/0x1c0 irq_do_set_affinity+0x1d7/0x1f0 irq_setup_affinity+0xd6/0x1a0 irq_startup+0x8a/0xf0 __setup_irq+0x639/0x6d0 ? nvme_suspend+0x150/0x150 request_threaded_irq+0x10c/0x180 ? nvme_suspend+0x150/0x150 pci_request_irq+0xa8/0xf0 ? __blk_mq_free_request+0x74/0xa0 queue_request_irq+0x6f/0x80 nvme_create_queue+0x1af/0x200 nvme_create_io_queues+0xbd/0xf0 nvme_setup_io_queues+0x246/0x320 ? nvme_irq_check+0x30/0x30 nvme_reset_work+0x1c8/0x400 process_one_work+0x1b0/0x350 worker_thread+0x49/0x310 ? process_one_work+0x350/0x350 kthread+0x11b/0x140 ? __kthread_bind_mask+0x60/0x60 ret_from_fork+0x22/0x30 Modules linked in: ---[ end trace a11715de1eee1873 ]--- Fixes: d46a78b05c0e ("xen: implement pirq type event channels") Cc: stable@vger.kernel.org Co-debugged-by: Andrew Panyakin Signed-off-by: Maximilian Heyne Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20240124163130.31324-1-mheyne@amazon.de Signed-off-by: Juergen Gross --- drivers/xen/events/events_base.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index b8cfea7812d6..3b9f080109d7 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -923,8 +923,8 @@ static void shutdown_pirq(struct irq_data *data) return; do_mask(info, EVT_MASK_REASON_EXPLICIT); - xen_evtchn_close(evtchn); xen_irq_info_cleanup(info); + xen_evtchn_close(evtchn); } static void enable_pirq(struct irq_data *data) @@ -956,6 +956,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi); static void __unbind_from_irq(struct irq_info *info, unsigned int irq) { evtchn_port_t evtchn; + bool close_evtchn = false; if (!info) { xen_irq_free_desc(irq); @@ -975,7 +976,7 @@ static void __unbind_from_irq(struct irq_info *info, unsigned int irq) struct xenbus_device *dev; if (!info->is_static) - xen_evtchn_close(evtchn); + close_evtchn = true; switch (info->type) { case IRQT_VIRQ: @@ -995,6 +996,9 @@ static void __unbind_from_irq(struct irq_info *info, unsigned int irq) } xen_irq_info_cleanup(info); + + if (close_evtchn) + xen_evtchn_close(evtchn); } xen_free_irq(info); From f1acf1ac84d2ae97b7889b87223c1064df850069 Mon Sep 17 00:00:00 2001 From: Allison Henderson Date: Thu, 8 Feb 2024 19:28:54 -0700 Subject: [PATCH 268/311] net:rds: Fix possible deadlock in rds_message_put Functions rds_still_queued and rds_clear_recv_queue lock a given socket in order to safely iterate over the incoming rds messages. However calling rds_inc_put while under this lock creates a potential deadlock. rds_inc_put may eventually call rds_message_purge, which will lock m_rs_lock. This is the incorrect locking order since m_rs_lock is meant to be locked before the socket. To fix this, we move the message item to a local list or variable that wont need rs_recv_lock protection. Then we can safely call rds_inc_put on any item stored locally after rs_recv_lock is released. Fixes: bdbe6fbc6a2f ("RDS: recv.c") Reported-by: syzbot+f9db6ff27b9bfdcfeca0@syzkaller.appspotmail.com Reported-by: syzbot+dcd73ff9291e6d34b3ab@syzkaller.appspotmail.com Signed-off-by: Allison Henderson Link: https://lore.kernel.org/r/20240209022854.200292-1-allison.henderson@oracle.com Signed-off-by: Paolo Abeni --- net/rds/recv.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/net/rds/recv.c b/net/rds/recv.c index c71b923764fd..5627f80013f8 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -425,6 +425,7 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, struct sock *sk = rds_rs_to_sk(rs); int ret = 0; unsigned long flags; + struct rds_incoming *to_drop = NULL; write_lock_irqsave(&rs->rs_recv_lock, flags); if (!list_empty(&inc->i_item)) { @@ -435,11 +436,14 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, -be32_to_cpu(inc->i_hdr.h_len), inc->i_hdr.h_dport); list_del_init(&inc->i_item); - rds_inc_put(inc); + to_drop = inc; } } write_unlock_irqrestore(&rs->rs_recv_lock, flags); + if (to_drop) + rds_inc_put(to_drop); + rdsdebug("inc %p rs %p still %d dropped %d\n", inc, rs, ret, drop); return ret; } @@ -758,16 +762,21 @@ void rds_clear_recv_queue(struct rds_sock *rs) struct sock *sk = rds_rs_to_sk(rs); struct rds_incoming *inc, *tmp; unsigned long flags; + LIST_HEAD(to_drop); write_lock_irqsave(&rs->rs_recv_lock, flags); list_for_each_entry_safe(inc, tmp, &rs->rs_recv_queue, i_item) { rds_recv_rcvbuf_delta(rs, sk, inc->i_conn->c_lcong, -be32_to_cpu(inc->i_hdr.h_len), inc->i_hdr.h_dport); + list_move(&inc->i_item, &to_drop); + } + write_unlock_irqrestore(&rs->rs_recv_lock, flags); + + list_for_each_entry_safe(inc, tmp, &to_drop, i_item) { list_del_init(&inc->i_item); rds_inc_put(inc); } - write_unlock_irqrestore(&rs->rs_recv_lock, flags); } /* From 8929f95b2b587791a7dcd04cc91520194a76d3a6 Mon Sep 17 00:00:00 2001 From: Keqi Wang Date: Fri, 9 Feb 2024 17:16:59 +0800 Subject: [PATCH 269/311] connector/cn_proc: revert "connector: Fix proc_event_num_listeners count not cleared" This reverts commit c46bfba1337d ("connector: Fix proc_event_num_listeners count not cleared"). It is not accurate to reset proc_event_num_listeners according to cn_netlink_send_mult() return value -ESRCH. In the case of stress-ng netlink-proc, -ESRCH will always be returned, because netlink_broadcast_filtered will return -ESRCH, which may cause stress-ng netlink-proc performance degradation. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202401112259.b23a1567-oliver.sang@intel.com Fixes: c46bfba1337d ("connector: Fix proc_event_num_listeners count not cleared") Signed-off-by: Keqi Wang Link: https://lore.kernel.org/r/20240209091659.68723-1-wangkeqi_chris@163.com Signed-off-by: Paolo Abeni --- drivers/connector/cn_proc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 3d5e6d705fc6..44b19e696176 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -108,9 +108,8 @@ static inline void send_msg(struct cn_msg *msg) filter_data[1] = 0; } - if (cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, - cn_filter, (void *)filter_data) == -ESRCH) - atomic_set(&proc_event_num_listeners, 0); + cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, + cn_filter, (void *)filter_data); local_unlock(&local_event.lock); } From 1741a8269e1c51fa08d4bfdf34667387a6eb10ec Mon Sep 17 00:00:00 2001 From: Manuel Fombuena Date: Sun, 11 Feb 2024 19:04:29 +0000 Subject: [PATCH 270/311] HID: multitouch: Add required quirk for Synaptics 0xcddc device Add support for the pointing stick (Accupoint) and 2 mouse buttons. Present on some Toshiba/dynabook Portege X30 and X40 laptops. It should close https://bugzilla.kernel.org/show_bug.cgi?id=205817 Signed-off-by: Manuel Fombuena Signed-off-by: Jiri Kosina --- drivers/hid/hid-multitouch.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index fd5b0637dad6..3e91e4d6ba6f 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -2151,6 +2151,10 @@ static const struct hid_device_id mt_devices[] = { HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_SYNAPTICS, 0xcd7e) }, + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_SYNAPTICS, 0xcddc) }, + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_SYNAPTICS, 0xce08) }, From bdab6c94bb24758081625e619330b04cfd56570a Mon Sep 17 00:00:00 2001 From: Even Xu Date: Fri, 9 Feb 2024 14:52:32 +0800 Subject: [PATCH 271/311] HID: Intel-ish-hid: Ishtp: Fix sensor reads after ACPI S3 suspend After legacy suspend/resume via ACPI S3, sensor read operation fails with timeout. Also, it will cause delay in resume operation as there will be retries on failure. This is caused by commit f645a90e8ff7 ("HID: intel-ish-hid: ishtp-hid-client: use helper functions for connection"), which used helper functions to simplify connect, reset and disconnect process. Also avoid freeing and allocating client buffers again during reconnect process. But there is a case, when ISH firmware resets after ACPI S3 suspend, ishtp bus driver frees client buffers. Since there is no realloc again during reconnect, there are no client buffers available to send connection requests to the firmware. Without successful connection to the firmware, subsequent sensor reads will timeout. To address this issue, ishtp bus driver does not free client buffers on warm reset after S3 resume. Simply add the buffers from the read list to free list of buffers. Fixes: f645a90e8ff7 ("HID: intel-ish-hid: ishtp-hid-client: use helper functions for connection") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218442 Signed-off-by: Even Xu Acked-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina --- drivers/hid/intel-ish-hid/ishtp/bus.c | 2 ++ drivers/hid/intel-ish-hid/ishtp/client.c | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index aa6cb033bb06..03d5601ce807 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -722,6 +722,8 @@ void ishtp_bus_remove_all_clients(struct ishtp_device *ishtp_dev, spin_lock_irqsave(&ishtp_dev->cl_list_lock, flags); list_for_each_entry(cl, &ishtp_dev->cl_list, link) { cl->state = ISHTP_CL_DISCONNECTED; + if (warm_reset && cl->device->reference_count) + continue; /* * Wake any pending process. The waiter would check dev->state diff --git a/drivers/hid/intel-ish-hid/ishtp/client.c b/drivers/hid/intel-ish-hid/ishtp/client.c index 82c907f01bd3..8a7f2f6a4f86 100644 --- a/drivers/hid/intel-ish-hid/ishtp/client.c +++ b/drivers/hid/intel-ish-hid/ishtp/client.c @@ -49,7 +49,9 @@ static void ishtp_read_list_flush(struct ishtp_cl *cl) list_for_each_entry_safe(rb, next, &cl->dev->read_list.list, list) if (rb->cl && ishtp_cl_cmp_id(cl, rb->cl)) { list_del(&rb->list); - ishtp_io_rb_free(rb); + spin_lock(&cl->free_list_spinlock); + list_add_tail(&rb->list, &cl->free_rb_list.list); + spin_unlock(&cl->free_list_spinlock); } spin_unlock_irqrestore(&cl->dev->read_list_spinlock, flags); } From 25236c91b5ab4a26a56ba2e79b8060cf4e047839 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 9 Feb 2024 14:04:53 -0800 Subject: [PATCH 272/311] af_unix: Fix task hung while purging oob_skb in GC. syzbot reported a task hung; at the same time, GC was looping infinitely in list_for_each_entry_safe() for OOB skb. [0] syzbot demonstrated that the list_for_each_entry_safe() was not actually safe in this case. A single skb could have references for multiple sockets. If we free such a skb in the list_for_each_entry_safe(), the current and next sockets could be unlinked in a single iteration. unix_notinflight() uses list_del_init() to unlink the socket, so the prefetched next socket forms a loop itself and list_for_each_entry_safe() never stops. Here, we must use while() and make sure we always fetch the first socket. [0]: Sending NMI from CPU 0 to CPUs 1: NMI backtrace for cpu 1 CPU: 1 PID: 5065 Comm: syz-executor236 Not tainted 6.8.0-rc3-syzkaller-00136-g1f719a2f3fa6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 RIP: 0010:preempt_count arch/x86/include/asm/preempt.h:26 [inline] RIP: 0010:check_kcov_mode kernel/kcov.c:173 [inline] RIP: 0010:__sanitizer_cov_trace_pc+0xd/0x60 kernel/kcov.c:207 Code: cc cc cc cc 66 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 65 48 8b 14 25 40 c2 03 00 <65> 8b 05 b4 7c 78 7e a9 00 01 ff 00 48 8b 34 24 74 0f f6 c4 01 74 RSP: 0018:ffffc900033efa58 EFLAGS: 00000283 RAX: ffff88807b077800 RBX: ffff88807b077800 RCX: 1ffffffff27b1189 RDX: ffff88802a5a3b80 RSI: ffffffff8968488d RDI: ffff88807b077f70 RBP: ffffc900033efbb0 R08: 0000000000000001 R09: fffffbfff27a900c R10: ffffffff93d48067 R11: ffffffff8ae000eb R12: ffff88807b077800 R13: dffffc0000000000 R14: ffff88807b077e40 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000564f4fc1e3a8 CR3: 000000000d57a000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: unix_gc+0x563/0x13b0 net/unix/garbage.c:319 unix_release_sock+0xa93/0xf80 net/unix/af_unix.c:683 unix_release+0x91/0xf0 net/unix/af_unix.c:1064 __sock_release+0xb0/0x270 net/socket.c:659 sock_close+0x1c/0x30 net/socket.c:1421 __fput+0x270/0xb80 fs/file_table.c:376 task_work_run+0x14f/0x250 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0xa8a/0x2ad0 kernel/exit.c:871 do_group_exit+0xd4/0x2a0 kernel/exit.c:1020 __do_sys_exit_group kernel/exit.c:1031 [inline] __se_sys_exit_group kernel/exit.c:1029 [inline] __x64_sys_exit_group+0x3e/0x50 kernel/exit.c:1029 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xd5/0x270 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x6f/0x77 RIP: 0033:0x7f9d6cbdac09 Code: Unable to access opcode bytes at 0x7f9d6cbdabdf. RSP: 002b:00007fff5952feb8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9d6cbdac09 RDX: 000000000000003c RSI: 00000000000000e7 RDI: 0000000000000000 RBP: 00007f9d6cc552b0 R08: ffffffffffffffb8 R09: 0000000000000006 R10: 0000000000000006 R11: 0000000000000246 R12: 00007f9d6cc552b0 R13: 0000000000000000 R14: 00007f9d6cc55d00 R15: 00007f9d6cbabe70 Reported-by: syzbot+4fa4a2d1f5a5ee06f006@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=4fa4a2d1f5a5ee06f006 Fixes: 1279f9d9dec2 ("af_unix: Call kfree_skb() for dead unix_(sk)->oob_skb in GC.") Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20240209220453.96053-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni --- net/unix/garbage.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 8f63f0b4bf01..2ff7ddbaa782 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -315,10 +315,11 @@ void unix_gc(void) __skb_queue_purge(&hitlist); #if IS_ENABLED(CONFIG_AF_UNIX_OOB) - list_for_each_entry_safe(u, next, &gc_candidates, link) { - struct sk_buff *skb = u->oob_skb; + while (!list_empty(&gc_candidates)) { + u = list_entry(gc_candidates.next, struct unix_sock, link); + if (u->oob_skb) { + struct sk_buff *skb = u->oob_skb; - if (skb) { u->oob_skb = NULL; kfree_skb(skb); } From ab41a31dd5e2681803642b6d08590b61867840ec Mon Sep 17 00:00:00 2001 From: Tatsunosuke Tobita Date: Thu, 1 Feb 2024 13:40:55 +0900 Subject: [PATCH 273/311] HID: wacom: generic: Avoid reporting a serial of '0' to userspace The xf86-input-wacom driver does not treat '0' as a valid serial number and will drop any input report which contains an MSC_SERIAL = 0 event. The kernel driver already takes care to avoid sending any MSC_SERIAL event if the value of serial[0] == 0 (which is the case for devices that don't actually report a serial number), but this is not quite sufficient. Only the lower 32 bits of the serial get reported to userspace, so if this portion of the serial is zero then there can still be problems. This commit allows the driver to report either the lower 32 bits if they are non-zero or the upper 32 bits otherwise. Signed-off-by: Jason Gerecke Signed-off-by: Tatsunosuke Tobita Fixes: f85c9dc678a5 ("HID: wacom: generic: Support tool ID and additional tool types") CC: stable@vger.kernel.org # v4.10 Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index da8a01fedd39..fbe10fbc5769 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2575,7 +2575,14 @@ static void wacom_wac_pen_report(struct hid_device *hdev, wacom_wac->hid_data.tipswitch); input_report_key(input, wacom_wac->tool[0], sense); if (wacom_wac->serial[0]) { - input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]); + /* + * xf86-input-wacom does not accept a serial number + * of '0'. Report the low 32 bits if possible, but + * if they are zero, report the upper ones instead. + */ + __u32 serial_lo = wacom_wac->serial[0] & 0xFFFFFFFFu; + __u32 serial_hi = wacom_wac->serial[0] >> 32; + input_event(input, EV_MSC, MSC_SERIAL, (int)(serial_lo ? serial_lo : serial_hi)); input_report_abs(input, ABS_MISC, sense ? id : 0); } From e083dd032eeba9e28e4703cd5aaf4a409ebc3837 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 10 Feb 2024 22:11:52 -0800 Subject: [PATCH 274/311] net: ti: icssg-prueth: add dependency for PTP When CONFIG_PTP_1588_CLOCK=m and CONFIG_TI_ICSSG_PRUETH=y, there are kconfig dependency warnings and build errors referencing PTP functions. Fix these by making TI_ICSSG_PRUETH depend on PTP_1588_CLOCK_OPTIONAL. Fixes these build errors and warnings: WARNING: unmet direct dependencies detected for TI_ICSS_IEP Depends on [m]: NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_TI [=y] && PTP_1588_CLOCK_OPTIONAL [=m] && TI_PRUSS [=y] Selected by [y]: - TI_ICSSG_PRUETH [=y] && NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_TI [=y] && PRU_REMOTEPROC [=y] && ARCH_K3 [=y] && OF [=y] && TI_K3_UDMA_GLUE_LAYER [=y] aarch64-linux-ld: drivers/net/ethernet/ti/icssg/icss_iep.o: in function `icss_iep_get_ptp_clock_idx': icss_iep.c:(.text+0x1d4): undefined reference to `ptp_clock_index' aarch64-linux-ld: drivers/net/ethernet/ti/icssg/icss_iep.o: in function `icss_iep_exit': icss_iep.c:(.text+0xde8): undefined reference to `ptp_clock_unregister' aarch64-linux-ld: drivers/net/ethernet/ti/icssg/icss_iep.o: in function `icss_iep_init': icss_iep.c:(.text+0x176c): undefined reference to `ptp_clock_register' Fixes: 186734c15886 ("net: ti: icssg-prueth: add packet timestamping and ptp support") Signed-off-by: Randy Dunlap Cc: Roger Quadros Cc: Md Danish Anwar Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: netdev@vger.kernel.org Reviewed-by: MD Danish Anwar Link: https://lore.kernel.org/r/20240211061152.14696-1-rdunlap@infradead.org Signed-off-by: Paolo Abeni --- drivers/net/ethernet/ti/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index be01450c20dc..1530d13984d4 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -189,6 +189,7 @@ config TI_ICSSG_PRUETH select TI_K3_CPPI_DESC_POOL depends on PRU_REMOTEPROC depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER + depends on PTP_1588_CLOCK_OPTIONAL help Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem. This subsystem is available starting with the AM65 platform. From 269e31aecdd0b70f53a05def79480f15cbcc0fd6 Mon Sep 17 00:00:00 2001 From: Ralf Schlatterbeck Date: Fri, 2 Feb 2024 12:53:30 +0100 Subject: [PATCH 275/311] spi-mxs: Fix chipselect glitch There was a change in the mxs-dma engine that uses a new custom flag. The change was not applied to the mxs spi driver. This results in chipselect being deasserted too early. This fixes the chipselect problem by using the new flag in the mxs-spi driver. Fixes: ceeeb99cd821 ("dmaengine: mxs: rename custom flag") Signed-off-by: Ralf Schlatterbeck Link: https://msgid.link/r/20240202115330.wxkbfmvd76sy3a6a@runtux.com Signed-off-by: Mark Brown --- drivers/spi/spi-mxs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c index 1bf080339b5a..88cbe4f00cc3 100644 --- a/drivers/spi/spi-mxs.c +++ b/drivers/spi/spi-mxs.c @@ -39,6 +39,7 @@ #include #include #include +#include #define DRIVER_NAME "mxs-spi" @@ -252,7 +253,7 @@ static int mxs_spi_txrx_dma(struct mxs_spi *spi, desc = dmaengine_prep_slave_sg(ssp->dmach, &dma_xfer[sg_count].sg, 1, (flags & TXRX_WRITE) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM, - DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + DMA_PREP_INTERRUPT | MXS_DMA_CTRL_WAIT4END); if (!desc) { dev_err(ssp->dev, From 4e06ec0774f5bebf10e27bc7a5ace4b48ae0fa56 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 24 Jan 2024 13:07:33 -0600 Subject: [PATCH 276/311] dt-bindings: ufs: samsung,exynos-ufs: Add size constraints on "samsung,sysreg" The 'phandle-array' type is a bit ambiguous. It can be either just an array of phandles or an array of phandles plus args. "samsung,sysreg" is the latter and needs to be constrained to a single entry with a phandle and offset. Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20240124190733.1554314-1-robh@kernel.org Signed-off-by: Rob Herring --- .../devicetree/bindings/ufs/samsung,exynos-ufs.yaml | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml index 88cc1e3a0c88..b2b509b3944d 100644 --- a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml +++ b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml @@ -55,9 +55,12 @@ properties: samsung,sysreg: $ref: /schemas/types.yaml#/definitions/phandle-array - description: Should be phandle/offset pair. The phandle to the syscon node - which indicates the FSYSx sysreg interface and the offset of - the control register for UFS io coherency setting. + items: + - items: + - description: phandle to FSYSx sysreg node + - description: offset of the control register for UFS io coherency setting + description: + Phandle and offset to the FSYSx sysreg for UFS io coherency setting. dma-coherent: true From feefe1f49d26bad9d8997096e3a200280fa7b1c5 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 31 Jan 2024 17:18:04 +0000 Subject: [PATCH 277/311] btrfs: don't reserve space for checksums when writing to nocow files Currently when doing a write to a file we always reserve metadata space for inserting data checksums. However we don't need to do it if we have a nodatacow file (-o nodatacow mount option or chattr +C) or if checksums are disabled (-o nodatasum mount option), as in that case we are only adding unnecessary pressure to metadata reservations. For example on x86_64, with the default node size of 16K, a 4K buffered write into a nodatacow file is reserving 655360 bytes of metadata space, as it's accounting for checksums. After this change, which stops reserving space for checksums if we have a nodatacow file or checksums are disabled, we only need to reserve 393216 bytes of metadata. CC: stable@vger.kernel.org # 6.1+ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/delalloc-space.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 2833e8ef4c09..acf9f4b6c044 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -245,7 +245,6 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv = &inode->block_rsv; u64 reserve_size = 0; u64 qgroup_rsv_size = 0; - u64 csum_leaves; unsigned outstanding_extents; lockdep_assert_held(&inode->lock); @@ -260,10 +259,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, outstanding_extents); reserve_size += btrfs_calc_metadata_size(fs_info, 1); } - csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, - inode->csum_bytes); - reserve_size += btrfs_calc_insert_metadata_size(fs_info, - csum_leaves); + if (!(inode->flags & BTRFS_INODE_NODATASUM)) { + u64 csum_leaves; + + csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes); + reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves); + } /* * For qgroup rsv, the calculation is very simple: * account one nodesize for each outstanding extent @@ -278,14 +279,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, spin_unlock(&block_rsv->lock); } -static void calc_inode_reservations(struct btrfs_fs_info *fs_info, +static void calc_inode_reservations(struct btrfs_inode *inode, u64 num_bytes, u64 disk_num_bytes, u64 *meta_reserve, u64 *qgroup_reserve) { + struct btrfs_fs_info *fs_info = inode->root->fs_info; u64 nr_extents = count_max_extents(fs_info, num_bytes); - u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); + u64 csum_leaves; u64 inode_update = btrfs_calc_metadata_size(fs_info, 1); + if (inode->flags & BTRFS_INODE_NODATASUM) + csum_leaves = 0; + else + csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); + *meta_reserve = btrfs_calc_insert_metadata_size(fs_info, nr_extents + csum_leaves); @@ -337,7 +344,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, * everything out and try again, which is bad. This way we just * over-reserve slightly, and clean up the mess when we are done. */ - calc_inode_reservations(fs_info, num_bytes, disk_num_bytes, + calc_inode_reservations(inode, num_bytes, disk_num_bytes, &meta_reserve, &qgroup_reserve); ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true, noflush); @@ -359,7 +366,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, nr_extents = count_max_extents(fs_info, num_bytes); spin_lock(&inode->lock); btrfs_mod_outstanding_extents(inode, nr_extents); - inode->csum_bytes += disk_num_bytes; + if (!(inode->flags & BTRFS_INODE_NODATASUM)) + inode->csum_bytes += disk_num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); @@ -393,7 +401,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, num_bytes = ALIGN(num_bytes, fs_info->sectorsize); spin_lock(&inode->lock); - inode->csum_bytes -= num_bytes; + if (!(inode->flags & BTRFS_INODE_NODATASUM)) + inode->csum_bytes -= num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); From 1bd96c92c6a0a4d43815eb685c15aa4b78879dc9 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 2 Feb 2024 12:09:22 +0000 Subject: [PATCH 278/311] btrfs: reject encoded write if inode has nodatasum flag set Currently we allow an encoded write against inodes that have the NODATASUM flag set, either because they are NOCOW files or they were created while the filesystem was mounted with "-o nodatasum". This results in having compressed extents without corresponding checksums, which is a filesystem inconsistency reported by 'btrfs check'. For example, running btrfs/281 with MOUNT_OPTIONS="-o nodatacow" triggers this and 'btrfs check' errors out with: [1/7] checking root items [2/7] checking extents [3/7] checking free space tree [4/7] checking fs roots root 256 inode 257 errors 1040, bad file extent, some csum missing root 256 inode 258 errors 1040, bad file extent, some csum missing ERROR: errors found in fs roots (...) So reject encoded writes if the target inode has NODATASUM set. CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Johannes Thumshirn Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d232eca1bbee..5f39462dceb0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10288,6 +10288,13 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE) return -EINVAL; + /* + * Compressed extents should always have checksums, so error out if we + * have a NOCOW file or inode was created while mounted with NODATASUM. + */ + if (inode->flags & BTRFS_INODE_NODATASUM) + return -EINVAL; + orig_count = iov_iter_count(from); /* The extent size must be sane. */ From 88e81a67773017a2b93f6d5fe7c78bb0c5a6e4dd Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 12 Feb 2024 21:50:53 +0000 Subject: [PATCH 279/311] btrfs: zoned: fix chunk map leak when loading block group zone info At btrfs_load_block_group_zone_info() we never drop a reference on the chunk map we have looked up, therefore leaking a reference on it. So add the missing btrfs_free_chunk_map() at the end of the function. Fixes: 7dc66abb5a47 ("btrfs: use a dedicated data structure for chunk maps") Reported-by: Johannes Thumshirn Reviewed-by: Johannes Thumshirn Tested-by: Johannes Thumshirn Reviewed-by: Anand Jain Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index ac9bbe0c4ffe..afeb1dc1f43a 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1687,6 +1687,7 @@ out: } bitmap_free(active); kfree(zone_info); + btrfs_free_chunk_map(map); return ret; } From 2f6397e448e689adf57e6788c90f913abd7e1af8 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 2 Feb 2024 14:32:17 +0000 Subject: [PATCH 280/311] btrfs: don't refill whole delayed refs block reserve when starting transaction Since commit 28270e25c69a ("btrfs: always reserve space for delayed refs when starting transaction") we started not only to reserve metadata space for the delayed refs a caller of btrfs_start_transaction() might generate but also to try to fully refill the delayed refs block reserve, because there are several case where we generate delayed refs and haven't reserved space for them, relying on the global block reserve. Relying too much on the global block reserve is not always safe, and can result in hitting -ENOSPC during transaction commits or worst, in rare cases, being unable to mount a filesystem that needs to do orphan cleanup or anything that requires modifying the filesystem during mount, and has no more unallocated space and the metadata space is nearly full. This was explained in detail in that commit's change log. However the gap between the reserved amount and the size of the delayed refs block reserve can be huge, so attempting to reserve space for such a gap can result in allocating many metadata block groups that end up not being used. After a recent patch, with the subject: "btrfs: add new unused block groups to the list of unused block groups" We started to add new block groups that are unused to the list of unused block groups, to avoid having them around for a very long time in case they are never used, because a block group is only added to the list of unused block groups when we deallocate the last extent or when mounting the filesystem and the block group has 0 bytes used. This is not a problem introduced by the commit mentioned earlier, it always existed as our metadata space reservations are, most of the time, pessimistic and end up not using all the space they reserved, so we can occasionally end up with one or two unused metadata block groups for a long period. However after that commit mentioned earlier, we are just more pessimistic in the metadata space reservations when starting a transaction and therefore the issue is more likely to happen. This however is not always enough because we might create unused metadata block groups when reserving metadata space at a high rate if there's always a gap in the delayed refs block reserve and the cleaner kthread isn't triggered often enough or is busy with other work (running delayed iputs, cleaning deleted roots, etc), not to mention the block group's allocated space is only usable for a new block group after the transaction used to remove it is committed. A user reported that he's getting a lot of allocated metadata block groups but the usage percentage of metadata space was very low compared to the total allocated space, specially after running a series of block group relocations. So for now stop trying to refill the gap in the delayed refs block reserve and reserve space only for the delayed refs we are expected to generate when starting a transaction. CC: stable@vger.kernel.org # 6.7+ Reported-by: Ivan Shapovalov Link: https://lore.kernel.org/linux-btrfs/9cdbf0ca9cdda1b4c84e15e548af7d7f9f926382.camel@intelfx.name/ Link: https://lore.kernel.org/linux-btrfs/CAL3q7H6802ayLHUJFztzZAVzBLJAGdFx=6FHNNy87+obZXXZpQ@mail.gmail.com/ Tested-by: Ivan Shapovalov Reported-by: Heddxh Link: https://lore.kernel.org/linux-btrfs/CAE93xANEby6RezOD=zcofENYZOT-wpYygJyauyUAZkLv6XVFOA@mail.gmail.com/ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/transaction.c | 38 ++------------------------------------ 1 file changed, 2 insertions(+), 36 deletions(-) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 5b3333ceef04..c52807d97efa 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -564,56 +564,22 @@ static int btrfs_reserve_trans_metadata(struct btrfs_fs_info *fs_info, u64 num_bytes, u64 *delayed_refs_bytes) { - struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv; struct btrfs_space_info *si = fs_info->trans_block_rsv.space_info; - u64 extra_delayed_refs_bytes = 0; - u64 bytes; + u64 bytes = num_bytes + *delayed_refs_bytes; int ret; - /* - * If there's a gap between the size of the delayed refs reserve and - * its reserved space, than some tasks have added delayed refs or bumped - * its size otherwise (due to block group creation or removal, or block - * group item update). Also try to allocate that gap in order to prevent - * using (and possibly abusing) the global reserve when committing the - * transaction. - */ - if (flush == BTRFS_RESERVE_FLUSH_ALL && - !btrfs_block_rsv_full(delayed_refs_rsv)) { - spin_lock(&delayed_refs_rsv->lock); - if (delayed_refs_rsv->size > delayed_refs_rsv->reserved) - extra_delayed_refs_bytes = delayed_refs_rsv->size - - delayed_refs_rsv->reserved; - spin_unlock(&delayed_refs_rsv->lock); - } - - bytes = num_bytes + *delayed_refs_bytes + extra_delayed_refs_bytes; - /* * We want to reserve all the bytes we may need all at once, so we only * do 1 enospc flushing cycle per transaction start. */ ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush); - if (ret == 0) { - if (extra_delayed_refs_bytes > 0) - btrfs_migrate_to_delayed_refs_rsv(fs_info, - extra_delayed_refs_bytes); - return 0; - } - - if (extra_delayed_refs_bytes > 0) { - bytes -= extra_delayed_refs_bytes; - ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush); - if (ret == 0) - return 0; - } /* * If we are an emergency flush, which can steal from the global block * reserve, then attempt to not reserve space for the delayed refs, as * we will consume space for them from the global block reserve. */ - if (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) { + if (ret && flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) { bytes -= *delayed_refs_bytes; *delayed_refs_bytes = 0; ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush); From e58779f47e5eeb4fc9e3707951b81fbe31de5e3b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 12 Feb 2024 10:39:41 +0100 Subject: [PATCH 281/311] selftests: net: cope with slow env in gro.sh test The gro self-tests sends the packets to be aggregated with multiple write operations. When running is slow environment, it's hard to guarantee that the GRO engine will wait for the last packet in an intended train. The above causes almost deterministic failures in our CI for the 'large' test-case. Address the issue explicitly ignoring failures for such case in slow environments (KSFT_MACHINE_SLOW==true). Fixes: 7d1575014a63 ("selftests/net: GRO coalesce test") Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni Link: https://lore.kernel.org/r/97d3ba83f5a2bfeb36f6bc0fb76724eb3dafb608.1707729403.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/gro.sh | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh index 19352f106c1d..02c21ff4ca81 100755 --- a/tools/testing/selftests/net/gro.sh +++ b/tools/testing/selftests/net/gro.sh @@ -31,6 +31,11 @@ run_test() { 1>>log.txt wait "${server_pid}" exit_code=$? + if [[ ${test} == "large" && -n "${KSFT_MACHINE_SLOW}" && \ + ${exit_code} -ne 0 ]]; then + echo "Ignoring errors due to slow environment" 1>&2 + exit_code=0 + fi if [[ "${exit_code}" -eq 0 ]]; then break; fi From a7ee79b9c4553498c78552d12321d85b645f02ca Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 12 Feb 2024 10:43:31 +0100 Subject: [PATCH 282/311] selftests: net: cope with slow env in so_txtime.sh test The mentioned test is failing in slow environments: # SO_TXTIME ipv4 clock monotonic # ./so_txtime: recv: timeout: Resource temporarily unavailable not ok 1 selftests: net: so_txtime.sh # exit=1 Tuning the tolerance in the test binary is error-prone and doomed to failures is slow-enough environment. Just resort to suppress any error in such cases. Note to suppress them we need first to refactor a bit the code moving it to explicit error handling. Fixes: af5136f95045 ("selftests/net: SO_TXTIME with ETF and FQ") Signed-off-by: Paolo Abeni Link: https://lore.kernel.org/r/2142d9ed4b5c5aa07dd1b455779625d91b175373.1707730902.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/so_txtime.sh | 29 ++++++++++++++++++++---- 1 file changed, 25 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh index 3f06f4d286a9..5e861ad32a42 100755 --- a/tools/testing/selftests/net/so_txtime.sh +++ b/tools/testing/selftests/net/so_txtime.sh @@ -5,6 +5,7 @@ set -e +readonly ksft_skip=4 readonly DEV="veth0" readonly BIN="./so_txtime" @@ -46,7 +47,7 @@ ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}" ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad -do_test() { +run_test() { local readonly IP="$1" local readonly CLOCK="$2" local readonly TXARGS="$3" @@ -64,12 +65,25 @@ do_test() { fi local readonly START="$(date +%s%N --date="+ 0.1 seconds")" + ip netns exec "${NS2}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${RXARGS}" -r & ip netns exec "${NS1}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${TXARGS}" wait "$!" } +do_test() { + run_test $@ + [ $? -ne 0 ] && ret=1 +} + +do_fail_test() { + run_test $@ + [ $? -eq 0 ] && ret=1 +} + ip netns exec "${NS1}" tc qdisc add dev "${DEV}" root fq +set +e +ret=0 do_test 4 mono a,-1 a,-1 do_test 6 mono a,0 a,0 do_test 6 mono a,10 a,10 @@ -77,13 +91,20 @@ do_test 4 mono a,10,b,20 a,10,b,20 do_test 6 mono a,20,b,10 b,20,a,20 if ip netns exec "${NS1}" tc qdisc replace dev "${DEV}" root etf clockid CLOCK_TAI delta 400000; then - ! do_test 4 tai a,-1 a,-1 - ! do_test 6 tai a,0 a,0 + do_fail_test 4 tai a,-1 a,-1 + do_fail_test 6 tai a,0 a,0 do_test 6 tai a,10 a,10 do_test 4 tai a,10,b,20 a,10,b,20 do_test 6 tai a,20,b,10 b,10,a,20 else echo "tc ($(tc -V)) does not support qdisc etf. skipping" + [ $ret -eq 0 ] && ret=$ksft_skip fi -echo OK. All tests passed +if [ $ret -eq 0 ]; then + echo OK. All tests passed +elif [[ $ret -ne $ksft_skip && -n "$KSFT_MACHINE_SLOW" ]]; then + echo "Ignoring errors due to slow environment" 1>&2 + ret=0 +fi +exit $ret From a71d0908e32f3dd41e355d83eeadd44d94811fd6 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 12 Feb 2024 11:19:23 +0100 Subject: [PATCH 283/311] selftests: net: more strict check in net_helper The helper waiting for a listener port can match any socket whose hexadecimal representation of source or destination addresses matches that of the given port. Additionally, any socket state is accepted. All the above can let the helper return successfully before the relevant listener is actually ready, with unexpected results. So far I could not find any related failure in the netdev CI, but the next patch is going to make the critical event more easily reproducible. Address the issue matching the port hex only vs the relevant socket field and additionally checking the socket state for TCP sockets. Fixes: 3bdd9fd29cb0 ("selftests/net: synchronize udpgro tests' tx and rx connection") Signed-off-by: Paolo Abeni Link: https://lore.kernel.org/r/192b3dbc443d953be32991d1b0ca432bd4c65008.1707731086.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/net_helper.sh | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh index 4fe0befa13fb..6596fe03c77f 100644 --- a/tools/testing/selftests/net/net_helper.sh +++ b/tools/testing/selftests/net/net_helper.sh @@ -8,13 +8,16 @@ wait_local_port_listen() local listener_ns="${1}" local port="${2}" local protocol="${3}" - local port_hex + local pattern local i - port_hex="$(printf "%04X" "${port}")" + pattern=":$(printf "%04X" "${port}") " + + # for tcp protocol additionally check the socket state + [ ${protocol} = "tcp" ] && pattern="${pattern}0A" for i in $(seq 10); do - if ip netns exec "${listener_ns}" cat /proc/net/"${protocol}"* | \ - grep -q "${port_hex}"; then + if ip netns exec "${listener_ns}" awk '{print $2" "$4}' \ + /proc/net/"${protocol}"* | grep -q "${pattern}"; then break fi sleep 0.1 From 20622dc934e178ef11fad396eb272597f21bffe2 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 12 Feb 2024 11:19:24 +0100 Subject: [PATCH 284/311] selftests: net: more pmtu.sh fixes The netdev CI is reporting failures for the pmtu test: [ 115.929264] br0: port 2(vxlan_a) entered forwarding state # 2024/02/08 17:33:22 socat[7871] E bind(7, {AF=10 [0000:0000:0000:0000:0000:0000:0000:0000]:50000}, 28): Address already in use # 2024/02/08 17:33:22 socat[7877] E write(7, 0x5598fb6ff000, 8192): Connection refused # TEST: IPv6, bridged vxlan4: PMTU exceptions [FAIL] # File size 0 mismatches exepcted value in locally bridged vxlan test The root cause is apparently a socket created by a previous iteration of the relevant loop still lasting in LAST_ACK state. Note that even the file size check is racy, the receiver process dumping the file could still be running in background Allow the listener to bound on the same local port via SO_REUSEADDR and collect file output file size only after the listener completion. Fixes: 136a1b434bbb ("selftests: net: test vxlan pmtu exceptions with tcp") Signed-off-by: Paolo Abeni Link: https://lore.kernel.org/r/4f51c11a1ce7ca7a4dabd926cffff63dadac9ba1.1707731086.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/pmtu.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index d65fdd407d73..cfc84958025a 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -1336,16 +1336,16 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { else TCPDST="TCP:[${dst}]:50000" fi - ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile & + ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000,reuseaddr STDOUT > $tmpoutfile & local socat_pid=$! wait_local_port_listen ${NS_B} 50000 tcp dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 + wait ${socat_pid} size=$(du -sb $tmpoutfile) size=${size%%/tmp/*} - wait ${socat_pid} [ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1 done From 858b31133dbec88465bcc0a006f4dc43173662b8 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Mon, 12 Feb 2024 00:30:38 +0530 Subject: [PATCH 285/311] octeontx2-af: Remove the PF_FUNC validation for NPC transmit rules NPC transmit side mcam rules can use the pcifunc (in packet metadata added by hardware) of transmitting device for mcam lookup similar to the channel of receiving device at receive side. The commit 18603683d766 ("octeontx2-af: Remove channel verification while installing MCAM rules") removed the receive side channel verification to save hardware MCAM filters while switching packets across interfaces but missed removing transmit side checks. This patch removes transmit side rules validation. Fixes: 18603683d766 ("octeontx2-af: Remove channel verification while installing MCAM rules") Signed-off-by: Subbaraya Sundeep Signed-off-by: David S. Miller --- .../ethernet/marvell/octeontx2/af/rvu_npc.c | 32 ------------------- 1 file changed, 32 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 8cfd74ad991c..e5d6156655ba 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -61,28 +61,6 @@ int rvu_npc_get_tx_nibble_cfg(struct rvu *rvu, u64 nibble_ena) return 0; } -static int npc_mcam_verify_pf_func(struct rvu *rvu, - struct mcam_entry *entry_data, u8 intf, - u16 pcifunc) -{ - u16 pf_func, pf_func_mask; - - if (is_npc_intf_rx(intf)) - return 0; - - pf_func_mask = (entry_data->kw_mask[0] >> 32) & - NPC_KEX_PF_FUNC_MASK; - pf_func = (entry_data->kw[0] >> 32) & NPC_KEX_PF_FUNC_MASK; - - pf_func = be16_to_cpu((__force __be16)pf_func); - if (pf_func_mask != NPC_KEX_PF_FUNC_MASK || - ((pf_func & ~RVU_PFVF_FUNC_MASK) != - (pcifunc & ~RVU_PFVF_FUNC_MASK))) - return -EINVAL; - - return 0; -} - void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf) { int blkaddr; @@ -2851,12 +2829,6 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu, else nix_intf = pfvf->nix_rx_intf; - if (!is_pffunc_af(pcifunc) && - npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, pcifunc)) { - rc = NPC_MCAM_INVALID_REQ; - goto exit; - } - /* For AF installed rules, the nix_intf should be set to target NIX */ if (is_pffunc_af(req->hdr.pcifunc)) nix_intf = req->intf; @@ -3208,10 +3180,6 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu, if (!is_npc_interface_valid(rvu, req->intf)) return NPC_MCAM_INVALID_REQ; - if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, - req->hdr.pcifunc)) - return NPC_MCAM_INVALID_REQ; - /* Try to allocate a MCAM entry */ entry_req.hdr.pcifunc = req->hdr.pcifunc; entry_req.contig = true; From 6cf9ff463317217d95732a6cce6fbdd12508921a Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Mon, 12 Feb 2024 17:34:02 +0300 Subject: [PATCH 286/311] net: smc: fix spurious error message from __sock_release() Commit 67f562e3e147 ("net/smc: transfer fasync_list in case of fallback") leaves the socket's fasync list pointer within a container socket as well. When the latter is destroyed, '__sock_release()' warns about its non-empty fasync list, which is a dangling pointer to previously freed fasync list of an underlying TCP socket. Fix this spurious warning by nullifying fasync list of a container socket. Fixes: 67f562e3e147 ("net/smc: transfer fasync_list in case of fallback") Signed-off-by: Dmitry Antipov Signed-off-by: David S. Miller --- net/smc/af_smc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index a2cb30af46cb..0f53a5c6fd9d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -924,6 +924,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) smc->clcsock->file->private_data = smc->clcsock; smc->clcsock->wq.fasync_list = smc->sk.sk_socket->wq.fasync_list; + smc->sk.sk_socket->wq.fasync_list = NULL; /* There might be some wait entries remaining * in smc sk->sk_wq and they should be woken up From 5d07e432cb387b9f7d4f0e07245705744c7fb05b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 13 Feb 2024 11:07:50 +0100 Subject: [PATCH 287/311] bnad: fix work_queue type mismatch clang-16 warns about a function pointer cast: drivers/net/ethernet/brocade/bna/bnad.c:1995:4: error: cast from 'void (*)(struct delayed_work *)' to 'work_func_t' (aka 'void (*)(struct work_struct *)') converts to incompatible function type [-Werror,-Wcast-function-type-strict] 1995 | (work_func_t)bnad_tx_cleanup); drivers/net/ethernet/brocade/bna/bnad.c:2252:4: error: cast from 'void (*)(void *)' to 'work_func_t' (aka 'void (*)(struct work_struct *)') converts to incompatible function type [-Werror,-Wcast-function-type-strict] 2252 | (work_func_t)(bnad_rx_cleanup)); The problem here is mixing up work_struct and delayed_work, which relies the former being the first member of the latter. Change the code to use consistent types here to address the warning and make it more robust against workqueue interface changes. Side note: the use of a delayed workqueue for cleaning up TX descriptors is probably a bad idea since this introduces a noticeable delay. The driver currently does not appear to use BQL, but if one wanted to add that, this would have to be changed as well. Fixes: 01b54b145185 ("bna: tx rx cleanup fix") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/brocade/bna/bnad.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 31191b520b58..c32174484a96 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -1091,10 +1091,10 @@ bnad_cb_tx_resume(struct bnad *bnad, struct bna_tx *tx) * Free all TxQs buffers and then notify TX_E_CLEANUP_DONE to Tx fsm. */ static void -bnad_tx_cleanup(struct delayed_work *work) +bnad_tx_cleanup(struct work_struct *work) { struct bnad_tx_info *tx_info = - container_of(work, struct bnad_tx_info, tx_cleanup_work); + container_of(work, struct bnad_tx_info, tx_cleanup_work.work); struct bnad *bnad = NULL; struct bna_tcb *tcb; unsigned long flags; @@ -1170,7 +1170,7 @@ bnad_cb_rx_stall(struct bnad *bnad, struct bna_rx *rx) * Free all RxQs buffers and then notify RX_E_CLEANUP_DONE to Rx fsm. */ static void -bnad_rx_cleanup(void *work) +bnad_rx_cleanup(struct work_struct *work) { struct bnad_rx_info *rx_info = container_of(work, struct bnad_rx_info, rx_cleanup_work); @@ -1991,8 +1991,7 @@ bnad_setup_tx(struct bnad *bnad, u32 tx_id) } tx_info->tx = tx; - INIT_DELAYED_WORK(&tx_info->tx_cleanup_work, - (work_func_t)bnad_tx_cleanup); + INIT_DELAYED_WORK(&tx_info->tx_cleanup_work, bnad_tx_cleanup); /* Register ISR for the Tx object */ if (intr_info->intr_type == BNA_INTR_T_MSIX) { @@ -2248,8 +2247,7 @@ bnad_setup_rx(struct bnad *bnad, u32 rx_id) rx_info->rx = rx; spin_unlock_irqrestore(&bnad->bna_lock, flags); - INIT_WORK(&rx_info->rx_cleanup_work, - (work_func_t)(bnad_rx_cleanup)); + INIT_WORK(&rx_info->rx_cleanup_work, bnad_rx_cleanup); /* * Init NAPI, so that state is set to NAPI_STATE_SCHED, From 9b23fceb4158a3636ce4a2bda28ab03dcfa6a26f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 13 Feb 2024 11:16:34 +0100 Subject: [PATCH 288/311] ethernet: cpts: fix function pointer cast warnings clang-16 warns about the mismatched prototypes for the devm_* callbacks: drivers/net/ethernet/ti/cpts.c:691:12: error: cast from 'void (*)(struct clk_hw *)' to 'void (*)(void *)' converts to incompatible function type [-Werror,-Wcast-function-type-strict] 691 | (void(*)(void *))clk_hw_unregister_mux, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ include/linux/device.h:406:34: note: expanded from macro 'devm_add_action_or_reset' 406 | __devm_add_action_or_reset(dev, action, data, #action) | ^~~~~~ drivers/net/ethernet/ti/cpts.c:703:12: error: cast from 'void (*)(struct device_node *)' to 'void (*)(void *)' converts to incompatible function type [-Werror,-Wcast-function-type-strict] 703 | (void(*)(void *))of_clk_del_provider, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ include/linux/device.h:406:34: note: expanded from macro 'devm_add_action_or_reset' 406 | __devm_add_action_or_reset(dev, action, data, #action) Use separate helper functions for this instead, using the expected prototypes with a void* argument. Fixes: a3047a81ba13 ("net: ethernet: ti: cpts: add support for ext rftclk selection") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/cpts.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index bcccf43d368b..dbbea9146040 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -638,6 +638,16 @@ static void cpts_calc_mult_shift(struct cpts *cpts) freq, cpts->cc.mult, cpts->cc.shift, (ns - NSEC_PER_SEC)); } +static void cpts_clk_unregister(void *clk) +{ + clk_hw_unregister_mux(clk); +} + +static void cpts_clk_del_provider(void *np) +{ + of_clk_del_provider(np); +} + static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node) { struct device_node *refclk_np; @@ -687,9 +697,7 @@ static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node) goto mux_fail; } - ret = devm_add_action_or_reset(cpts->dev, - (void(*)(void *))clk_hw_unregister_mux, - clk_hw); + ret = devm_add_action_or_reset(cpts->dev, cpts_clk_unregister, clk_hw); if (ret) { dev_err(cpts->dev, "add clkmux unreg action %d", ret); goto mux_fail; @@ -699,8 +707,7 @@ static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node) if (ret) goto mux_fail; - ret = devm_add_action_or_reset(cpts->dev, - (void(*)(void *))of_clk_del_provider, + ret = devm_add_action_or_reset(cpts->dev, cpts_clk_del_provider, refclk_np); if (ret) { dev_err(cpts->dev, "add clkmux provider unreg action %d", ret); From 6cdedc18ba7b9dacc36466e27e3267d201948c8d Mon Sep 17 00:00:00 2001 From: Ziqi Zhao Date: Fri, 21 Jul 2023 09:22:26 -0700 Subject: [PATCH 289/311] can: j1939: prevent deadlock by changing j1939_socks_lock to rwlock The following 3 locks would race against each other, causing the deadlock situation in the Syzbot bug report: - j1939_socks_lock - active_session_list_lock - sk_session_queue_lock A reasonable fix is to change j1939_socks_lock to an rwlock, since in the rare situations where a write lock is required for the linked list that j1939_socks_lock is protecting, the code does not attempt to acquire any more locks. This would break the circular lock dependency, where, for example, the current thread already locks j1939_socks_lock and attempts to acquire sk_session_queue_lock, and at the same time, another thread attempts to acquire j1939_socks_lock while holding sk_session_queue_lock. NOTE: This patch along does not fix the unregister_netdevice bug reported by Syzbot; instead, it solves a deadlock situation to prepare for one or more further patches to actually fix the Syzbot bug, which appears to be a reference counting problem within the j1939 codebase. Reported-by: Signed-off-by: Ziqi Zhao Reviewed-by: Oleksij Rempel Acked-by: Oleksij Rempel Link: https://lore.kernel.org/all/20230721162226.8639-1-astrajoan@yahoo.com [mkl: remove unrelated newline change] Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- net/can/j1939/j1939-priv.h | 2 +- net/can/j1939/main.c | 2 +- net/can/j1939/socket.c | 24 ++++++++++++------------ 3 files changed, 14 insertions(+), 14 deletions(-) diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 16af1a7f80f6..74f15592d170 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -86,7 +86,7 @@ struct j1939_priv { unsigned int tp_max_packet_size; /* lock for j1939_socks list */ - spinlock_t j1939_socks_lock; + rwlock_t j1939_socks_lock; struct list_head j1939_socks; struct kref rx_kref; diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index ecff1c947d68..a6fb89fa6278 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) return ERR_PTR(-ENOMEM); j1939_tp_init(priv); - spin_lock_init(&priv->j1939_socks_lock); + rwlock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); mutex_lock(&j1939_netdev_lock); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 14c431663233..94cfc2315e54 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk) jsk->state |= J1939_SOCK_BOUND; j1939_priv_get(priv); - spin_lock_bh(&priv->j1939_socks_lock); + write_lock_bh(&priv->j1939_socks_lock); list_add_tail(&jsk->list, &priv->j1939_socks); - spin_unlock_bh(&priv->j1939_socks_lock); + write_unlock_bh(&priv->j1939_socks_lock); } static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) { - spin_lock_bh(&priv->j1939_socks_lock); + write_lock_bh(&priv->j1939_socks_lock); list_del_init(&jsk->list); - spin_unlock_bh(&priv->j1939_socks_lock); + write_unlock_bh(&priv->j1939_socks_lock); j1939_priv_put(priv); jsk->state &= ~J1939_SOCK_BOUND; @@ -329,13 +329,13 @@ bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb) struct j1939_sock *jsk; bool match = false; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { match = j1939_sk_recv_match_one(jsk, skcb); if (match) break; } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); return match; } @@ -344,11 +344,11 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sock *jsk; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { j1939_sk_recv_one(jsk, skb); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); } static void j1939_sk_sock_destruct(struct sock *sk) @@ -1080,12 +1080,12 @@ void j1939_sk_errqueue(struct j1939_session *session, } /* spread RX notifications to all sockets subscribed to this session */ - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { if (j1939_sk_recv_match_one(jsk, &session->skcb)) __j1939_sk_errqueue(session, &jsk->sk, type); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); }; void j1939_sk_send_loop_abort(struct sock *sk, int err) @@ -1273,7 +1273,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) struct j1939_sock *jsk; int error_code = ENETDOWN; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { jsk->sk.sk_err = error_code; if (!sock_flag(&jsk->sk, SOCK_DEAD)) @@ -1281,7 +1281,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) j1939_sk_queue_drop_all(priv, jsk, error_code); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); } static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, From efe7cf828039aedb297c1f9920b638fffee6aabc Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 20 Oct 2023 15:38:14 +0200 Subject: [PATCH 290/311] can: j1939: Fix UAF in j1939_sk_match_filter during setsockopt(SO_J1939_FILTER) Lock jsk->sk to prevent UAF when setsockopt(..., SO_J1939_FILTER, ...) modifies jsk->filters while receiving packets. Following trace was seen on affected system: ================================================================== BUG: KASAN: slab-use-after-free in j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939] Read of size 4 at addr ffff888012144014 by task j1939/350 CPU: 0 PID: 350 Comm: j1939 Tainted: G W OE 6.5.0-rc5 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Call Trace: print_report+0xd3/0x620 ? kasan_complete_mode_report_info+0x7d/0x200 ? j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939] kasan_report+0xc2/0x100 ? j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939] __asan_load4+0x84/0xb0 j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939] j1939_sk_recv+0x20b/0x320 [can_j1939] ? __kasan_check_write+0x18/0x20 ? __pfx_j1939_sk_recv+0x10/0x10 [can_j1939] ? j1939_simple_recv+0x69/0x280 [can_j1939] ? j1939_ac_recv+0x5e/0x310 [can_j1939] j1939_can_recv+0x43f/0x580 [can_j1939] ? __pfx_j1939_can_recv+0x10/0x10 [can_j1939] ? raw_rcv+0x42/0x3c0 [can_raw] ? __pfx_j1939_can_recv+0x10/0x10 [can_j1939] can_rcv_filter+0x11f/0x350 [can] can_receive+0x12f/0x190 [can] ? __pfx_can_rcv+0x10/0x10 [can] can_rcv+0xdd/0x130 [can] ? __pfx_can_rcv+0x10/0x10 [can] __netif_receive_skb_one_core+0x13d/0x150 ? __pfx___netif_receive_skb_one_core+0x10/0x10 ? __kasan_check_write+0x18/0x20 ? _raw_spin_lock_irq+0x8c/0xe0 __netif_receive_skb+0x23/0xb0 process_backlog+0x107/0x260 __napi_poll+0x69/0x310 net_rx_action+0x2a1/0x580 ? __pfx_net_rx_action+0x10/0x10 ? __pfx__raw_spin_lock+0x10/0x10 ? handle_irq_event+0x7d/0xa0 __do_softirq+0xf3/0x3f8 do_softirq+0x53/0x80 __local_bh_enable_ip+0x6e/0x70 netif_rx+0x16b/0x180 can_send+0x32b/0x520 [can] ? __pfx_can_send+0x10/0x10 [can] ? __check_object_size+0x299/0x410 raw_sendmsg+0x572/0x6d0 [can_raw] ? __pfx_raw_sendmsg+0x10/0x10 [can_raw] ? apparmor_socket_sendmsg+0x2f/0x40 ? __pfx_raw_sendmsg+0x10/0x10 [can_raw] sock_sendmsg+0xef/0x100 sock_write_iter+0x162/0x220 ? __pfx_sock_write_iter+0x10/0x10 ? __rtnl_unlock+0x47/0x80 ? security_file_permission+0x54/0x320 vfs_write+0x6ba/0x750 ? __pfx_vfs_write+0x10/0x10 ? __fget_light+0x1ca/0x1f0 ? __rcu_read_unlock+0x5b/0x280 ksys_write+0x143/0x170 ? __pfx_ksys_write+0x10/0x10 ? __kasan_check_read+0x15/0x20 ? fpregs_assert_state_consistent+0x62/0x70 __x64_sys_write+0x47/0x60 do_syscall_64+0x60/0x90 ? do_syscall_64+0x6d/0x90 ? irqentry_exit+0x3f/0x50 ? exc_page_fault+0x79/0xf0 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Allocated by task 348: kasan_save_stack+0x2a/0x50 kasan_set_track+0x29/0x40 kasan_save_alloc_info+0x1f/0x30 __kasan_kmalloc+0xb5/0xc0 __kmalloc_node_track_caller+0x67/0x160 j1939_sk_setsockopt+0x284/0x450 [can_j1939] __sys_setsockopt+0x15c/0x2f0 __x64_sys_setsockopt+0x6b/0x80 do_syscall_64+0x60/0x90 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 349: kasan_save_stack+0x2a/0x50 kasan_set_track+0x29/0x40 kasan_save_free_info+0x2f/0x50 __kasan_slab_free+0x12e/0x1c0 __kmem_cache_free+0x1b9/0x380 kfree+0x7a/0x120 j1939_sk_setsockopt+0x3b2/0x450 [can_j1939] __sys_setsockopt+0x15c/0x2f0 __x64_sys_setsockopt+0x6b/0x80 do_syscall_64+0x60/0x90 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Fixes: 9d71dd0c70099 ("can: add support of SAE J1939 protocol") Reported-by: Sili Luo Suggested-by: Sili Luo Acked-by: Oleksij Rempel Cc: stable@vger.kernel.org Signed-off-by: Oleksij Rempel Link: https://lore.kernel.org/all/20231020133814.383996-1-o.rempel@pengutronix.de Signed-off-by: Marc Kleine-Budde --- net/can/j1939/j1939-priv.h | 1 + net/can/j1939/socket.c | 22 ++++++++++++++++++---- 2 files changed, 19 insertions(+), 4 deletions(-) diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 74f15592d170..31a93cae5111 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -301,6 +301,7 @@ struct j1939_sock { int ifindex; struct j1939_addr addr; + spinlock_t filters_lock; struct j1939_filter *filters; int nfilters; pgn_t pgn_rx_filter; diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 94cfc2315e54..305dd72c844c 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk, static bool j1939_sk_match_filter(struct j1939_sock *jsk, const struct j1939_sk_buff_cb *skcb) { - const struct j1939_filter *f = jsk->filters; - int nfilter = jsk->nfilters; + const struct j1939_filter *f; + int nfilter; + + spin_lock_bh(&jsk->filters_lock); + + f = jsk->filters; + nfilter = jsk->nfilters; if (!nfilter) /* receive all when no filters are assigned */ - return true; + goto filter_match_found; for (; nfilter; ++f, --nfilter) { if ((skcb->addr.pgn & f->pgn_mask) != f->pgn) @@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk, continue; if ((skcb->addr.src_name & f->name_mask) != f->name) continue; - return true; + goto filter_match_found; } + + spin_unlock_bh(&jsk->filters_lock); return false; + +filter_match_found: + spin_unlock_bh(&jsk->filters_lock); + return true; } static bool j1939_sk_recv_match_one(struct j1939_sock *jsk, @@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + spin_lock_init(&jsk->filters_lock); /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ sock_set_flag(sk, SOCK_RCU_FREE); @@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, } lock_sock(&jsk->sk); + spin_lock_bh(&jsk->filters_lock); ofilters = jsk->filters; jsk->filters = filters; jsk->nfilters = count; + spin_unlock_bh(&jsk->filters_lock); release_sock(&jsk->sk); kfree(ofilters); return 0; From 2aa0a5e65eae27dbd96faca92c84ecbf6f492d42 Mon Sep 17 00:00:00 2001 From: Maxime Jayat Date: Mon, 6 Nov 2023 19:01:58 +0100 Subject: [PATCH 291/311] can: netlink: Fix TDCO calculation using the old data bittiming The TDCO calculation was done using the currently applied data bittiming, instead of the newly computed data bittiming, which means that the TDCO had an invalid value unless setting the same data bittiming twice. Fixes: d99755f71a80 ("can: netlink: add interface for CAN-FD Transmitter Delay Compensation (TDC)") Signed-off-by: Maxime Jayat Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/all/40579c18-63c0-43a4-8d4c-f3a6c1c0b417@munic.io Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 036d85ef07f5..dfdc039d92a6 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -346,7 +346,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], /* Neither of TDC parameters nor TDC flags are * provided: do calculation */ - can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming, + can_calc_tdco(&priv->tdc, priv->tdc_const, &dbt, &priv->ctrlmode, priv->ctrlmode_supported); } /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly * turned off. TDC is disabled: do nothing From c56d055893cbe97848611855d1c97d0ab171eccc Mon Sep 17 00:00:00 2001 From: Kunwu Chan Date: Mon, 15 Jan 2024 16:28:25 +0800 Subject: [PATCH 292/311] igb: Fix string truncation warnings in igb_set_fw_version MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 1978d3ead82c ("intel: fix string truncation warnings") fixes '-Wformat-truncation=' warnings in igb_main.c by using kasprintf. drivers/net/ethernet/intel/igb/igb_main.c:3092:53: warning：‘%d’ directive output may be truncated writing between 1 and 5 bytes into a region of size between 1 and 13 [-Wformat-truncation=] 3092 | "%d.%d, 0x%08x, %d.%d.%d", | ^~ drivers/net/ethernet/intel/igb/igb_main.c:3092:34: note：directive argument in the range [0, 65535] 3092 | "%d.%d, 0x%08x, %d.%d.%d", | ^~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/intel/igb/igb_main.c:3092:34: note：directive argument in the range [0, 65535] drivers/net/ethernet/intel/igb/igb_main.c:3090:25: note：‘snprintf’ output between 23 and 43 bytes into a destination of size 32 kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Fix this warning by using a larger space for adapter->fw_version, and then fall back and continue to use snprintf. Fixes: 1978d3ead82c ("intel: fix string truncation warnings") Signed-off-by: Kunwu Chan Cc: Kunwu Chan Suggested-by: Jakub Kicinski Reviewed-by: Simon Horman Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb.h | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 35 ++++++++++++----------- 2 files changed, 19 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index a2b759531cb7..3c2dc7bdebb5 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -637,7 +637,7 @@ struct igb_adapter { struct timespec64 period; } perout[IGB_N_PEROUT]; - char fw_version[32]; + char fw_version[48]; #ifdef CONFIG_IGB_HWMON struct hwmon_buff *igb_hwmon_buff; bool ets; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 4df8d4153aa5..cebb44f51d5f 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3069,7 +3069,6 @@ void igb_set_fw_version(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; struct e1000_fw_version fw; - char *lbuf; igb_get_fw_version(hw, &fw); @@ -3077,34 +3076,36 @@ void igb_set_fw_version(struct igb_adapter *adapter) case e1000_i210: case e1000_i211: if (!(igb_get_flash_presence_i210(hw))) { - lbuf = kasprintf(GFP_KERNEL, "%2d.%2d-%d", - fw.invm_major, fw.invm_minor, - fw.invm_img_type); + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%2d.%2d-%d", + fw.invm_major, fw.invm_minor, + fw.invm_img_type); break; } fallthrough; default: /* if option rom is valid, display its version too */ if (fw.or_valid) { - lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x, %d.%d.%d", - fw.eep_major, fw.eep_minor, - fw.etrack_id, fw.or_major, fw.or_build, - fw.or_patch); + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%d.%d, 0x%08x, %d.%d.%d", + fw.eep_major, fw.eep_minor, fw.etrack_id, + fw.or_major, fw.or_build, fw.or_patch); /* no option rom */ } else if (fw.etrack_id != 0X0000) { - lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x", - fw.eep_major, fw.eep_minor, - fw.etrack_id); + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%d.%d, 0x%08x", + fw.eep_major, fw.eep_minor, fw.etrack_id); } else { - lbuf = kasprintf(GFP_KERNEL, "%d.%d.%d", fw.eep_major, - fw.eep_minor, fw.eep_build); + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%d.%d.%d", + fw.eep_major, fw.eep_minor, fw.eep_build); } break; } - - /* the truncate happens here if it doesn't fit */ - strscpy(adapter->fw_version, lbuf, sizeof(adapter->fw_version)); - kfree(lbuf); } /** From 55ea989977f4e11a1c3bdfabb51295090bb0f7d6 Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Wed, 24 Jan 2024 07:57:00 +0200 Subject: [PATCH 293/311] igc: Remove temporary workaround PHY_CONTROL register works as defined in the IEEE 802.3 specification (IEEE 802.3-2008 22.2.4.1). Tidy up the temporary workaround. User impact: PHY can now be powered down when the ethernet link is down. Testing hints: ip link set down (or just disconnect the ethernet cable). Oldest tested NVM version is: 1045:740. Fixes: 5586838fe9ce ("igc: Add code for PHY support") Signed-off-by: Sasha Neftin Reviewed-by: Paul Menzel Tested-by: Naama Meir Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_phy.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 7cd8716d2ffa..861f37076861 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -130,11 +130,7 @@ void igc_power_down_phy_copper(struct igc_hw *hw) /* The PHY will retain its settings across a power down/up cycle */ hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg); mii_reg |= MII_CR_POWER_DOWN; - - /* Temporary workaround - should be removed when PHY will implement - * IEEE registers as properly - */ - /* hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);*/ + hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg); usleep_range(1000, 2000); } From f6374a82fc85bf911d033e2fa791372ce3356270 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 8 Feb 2024 15:46:03 +0100 Subject: [PATCH 294/311] netfilter: nft_set_pipapo: fix missing : in kdoc Add missing : in kdoc field names. Fixes: 8683f4b9950d ("nft_set_pipapo: Prepare for vectorised implementation: helpers") Reported-by: Paolo Abeni Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_set_pipapo.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index f59a0cd81105..3842c7341a9f 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -144,10 +144,10 @@ struct nft_pipapo_scratch { /** * struct nft_pipapo_match - Data used for lookup and matching - * @field_count Amount of fields in set + * @field_count: Amount of fields in set * @scratch: Preallocated per-CPU maps for partial matching results * @bsize_max: Maximum lookup table bucket size of all fields, in longs - * @rcu Matching data is swapped on commits + * @rcu: Matching data is swapped on commits * @f: Fields, with lookup and mapping tables */ struct nft_pipapo_match { From 0f1ae2821fa4b13ab0f5ad7ff89fa57efcb04fe0 Mon Sep 17 00:00:00 2001 From: Kyle Swenson Date: Thu, 8 Feb 2024 23:56:31 +0000 Subject: [PATCH 295/311] netfilter: nat: restore default DNAT behavior When a DNAT rule is configured via iptables with different port ranges, iptables -t nat -A PREROUTING -p tcp -d 10.0.0.2 -m tcp --dport 32000:32010 -j DNAT --to-destination 192.168.0.10:21000-21010 we seem to be DNATing to some random port on the LAN side. While this is expected if --random is passed to the iptables command, it is not expected without passing --random. The expected behavior (and the observed behavior prior to the commit in the "Fixes" tag) is the traffic will be DNAT'd to 192.168.0.10:21000 unless there is a tuple collision with that destination. In that case, we expect the traffic to be instead DNAT'd to 192.168.0.10:21001, so on so forth until the end of the range. This patch intends to restore the behavior observed prior to the "Fixes" tag. Fixes: 6ed5943f8735 ("netfilter: nat: remove l4 protocol port rovers") Signed-off-by: Kyle Swenson Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index c3d7ecbc777c..016c816d91cb 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -551,8 +551,11 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple, find_free_id: if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) off = (ntohs(*keyptr) - ntohs(range->base_proto.all)); - else + else if ((range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL) || + maniptype != NF_NAT_MANIP_DST) off = get_random_u16(); + else + off = 0; attempts = range_size; if (attempts > NF_NAT_MAX_ATTEMPTS) From 84443741faab9045d53f022a9ac6a6633067a481 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 14 Feb 2024 15:42:35 +0100 Subject: [PATCH 296/311] netfilter: nf_tables: fix bidirectional offload regression Commit 8f84780b84d6 ("netfilter: flowtable: allow unidirectional rules") made unidirectional flow offload possible, while completely ignoring (and breaking) bidirectional flow offload for nftables. Add the missing flag that was left out as an exercise for the reader :) Cc: Vlad Buslov Fixes: 8f84780b84d6 ("netfilter: flowtable: allow unidirectional rules") Reported-by: Daniel Golle Signed-off-by: Felix Fietkau Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_flow_offload.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 397351fa4d5f..ab9576098701 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -361,6 +361,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } + __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); ret = flow_offload_add(flowtable, flow); if (ret < 0) goto err_flow_add; From dadd1701ae11a204dd4bea8086905a9576c4b63c Mon Sep 17 00:00:00 2001 From: Dave Ertman Date: Tue, 13 Feb 2024 10:39:55 -0800 Subject: [PATCH 297/311] ice: Add check for lport extraction to LAG init To fully support initializing the LAG support code, a DDP package that extracts the logical port from the metadata is required. If such a package is not present, there could be difficulties in supporting some bond types. Add a check into the initialization flow that will bypass the new paths if any of the support pieces are missing. Reviewed-by: Przemek Kitszel Fixes: df006dd4b1dc ("ice: Add initial support framework for LAG") Signed-off-by: Dave Ertman Reviewed-by: Marcin Szycik Reviewed-by: Simon Horman Tested-by: Sujai Buvaneswaran Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20240213183957.1483857-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_lag.c | 25 ++++++++++++++++++++++-- drivers/net/ethernet/intel/ice/ice_lag.h | 3 +++ 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 2a25323105e5..467372d541d2 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -151,6 +151,27 @@ ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport) return NULL; } +/** + * ice_pkg_has_lport_extract - check if lport extraction supported + * @hw: HW struct + */ +static bool ice_pkg_has_lport_extract(struct ice_hw *hw) +{ + int i; + + for (i = 0; i < hw->blk[ICE_BLK_SW].es.count; i++) { + u16 offset; + u8 fv_prot; + + ice_find_prot_off(hw, ICE_BLK_SW, ICE_SW_DEFAULT_PROFILE, i, + &fv_prot, &offset); + if (fv_prot == ICE_FV_PROT_MDID && + offset == ICE_LP_EXT_BUF_OFFSET) + return true; + } + return false; +} + /** * ice_lag_find_primary - returns pointer to primary interfaces lag struct * @lag: local interfaces lag struct @@ -1206,7 +1227,7 @@ static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf) } /** - * ice_lag_init_feature_support_flag - Check for NVM support for LAG + * ice_lag_init_feature_support_flag - Check for package and NVM support for LAG * @pf: PF struct */ static void ice_lag_init_feature_support_flag(struct ice_pf *pf) @@ -1219,7 +1240,7 @@ static void ice_lag_init_feature_support_flag(struct ice_pf *pf) else ice_clear_feature_support(pf, ICE_F_ROCE_LAG); - if (caps->sriov_lag) + if (caps->sriov_lag && ice_pkg_has_lport_extract(&pf->hw)) ice_set_feature_support(pf, ICE_F_SRIOV_LAG); else ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index ede833dfa658..183b38792ef2 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -17,6 +17,9 @@ enum ice_lag_role { #define ICE_LAG_INVALID_PORT 0xFF #define ICE_LAG_RESET_RETRIES 5 +#define ICE_SW_DEFAULT_PROFILE 0 +#define ICE_FV_PROT_MDID 255 +#define ICE_LP_EXT_BUF_OFFSET 32 struct ice_pf; struct ice_vf; From 2ec197fda25f57afccac7f2846e509471488614c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 13 Feb 2024 06:20:55 -0800 Subject: [PATCH 298/311] selftests: tls: increase the wait in poll_partial_rec_async Test runners on debug kernels occasionally fail with: # # RUN tls_err.13_aes_gcm.poll_partial_rec_async ... # # tls.c:1883:poll_partial_rec_async:Expected poll(&pfd, 1, 5) (0) == 1 (1) # # tls.c:1870:poll_partial_rec_async:Expected status (256) == 0 (0) # # poll_partial_rec_async: Test failed at step #17 # # FAIL tls_err.13_aes_gcm.poll_partial_rec_async # not ok 699 tls_err.13_aes_gcm.poll_partial_rec_async # # FAILED: 698 / 699 tests passed. This points to the second poll() in the test which is expected to wait for the sender to send the rest of the data. Apparently under some conditions that doesn't happen within 5ms, bump the timeout to 20ms. Fixes: 23fcb62bc19c ("selftests: tls: add tests for poll behavior") Link: https://lore.kernel.org/r/20240213142055.395564-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index bc36c91c4480..49c84602707f 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1874,13 +1874,13 @@ TEST_F(tls_err, poll_partial_rec_async) /* Child should sleep in poll(), never get a wake */ pfd.fd = self->cfd2; pfd.events = POLLIN; - EXPECT_EQ(poll(&pfd, 1, 5), 0); + EXPECT_EQ(poll(&pfd, 1, 20), 0); EXPECT_EQ(write(p[1], &token, 1), 1); /* Barrier #1 */ pfd.fd = self->cfd2; pfd.events = POLLIN; - EXPECT_EQ(poll(&pfd, 1, 5), 1); + EXPECT_EQ(poll(&pfd, 1, 20), 1); exit(!_metadata->passed); } From 488b6d91b07112eaaaa4454332c1480894d4e06e Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Tue, 13 Feb 2024 03:04:28 -0800 Subject: [PATCH 299/311] net-timestamp: make sk_tskey more predictable in error path When SOF_TIMESTAMPING_OPT_ID is used to ambiguate timestamped datagrams, the sk_tskey can become unpredictable in case of any error happened during sendmsg(). Move increment later in the code and make decrement of sk_tskey in error path. This solution is still racy in case of multiple threads doing snedmsg() over the very same socket in parallel, but still makes error path much more predictable. Fixes: 09c2d251b707 ("net-timestamp: add key to disambiguate concurrent datagrams") Reported-by: Andy Lutomirski Signed-off-by: Vadim Fedorenko Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20240213110428.1681540-1-vadfed@meta.com Signed-off-by: Paolo Abeni --- net/ipv4/ip_output.c | 13 ++++++++----- net/ipv6/ip6_output.c | 13 ++++++++----- 2 files changed, 16 insertions(+), 10 deletions(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 41537d18eecf..67d846622365 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -972,8 +972,8 @@ static int __ip_append_data(struct sock *sk, unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; + bool paged, hold_tskey, extra_uref = false; unsigned int wmem_alloc_delta = 0; - bool paged, extra_uref = false; u32 tskey = 0; skb = skb_peek_tail(queue); @@ -982,10 +982,6 @@ static int __ip_append_data(struct sock *sk, mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; - if (cork->tx_flags & SKBTX_ANY_TSTAMP && - READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) - tskey = atomic_inc_return(&sk->sk_tskey) - 1; - hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); @@ -1052,6 +1048,11 @@ static int __ip_append_data(struct sock *sk, cork->length += length; + hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; + if (hold_tskey) + tskey = atomic_inc_return(&sk->sk_tskey) - 1; + /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, @@ -1274,6 +1275,8 @@ error: cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (hold_tskey) + atomic_dec(&sk->sk_tskey); return err; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a722a43dd668..31b86fe661aa 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1424,11 +1424,11 @@ static int __ip6_append_data(struct sock *sk, bool zc = false; u32 tskey = 0; struct rt6_info *rt = (struct rt6_info *)cork->dst; + bool paged, hold_tskey, extra_uref = false; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; unsigned int maxnonfragsize, headersize; unsigned int wmem_alloc_delta = 0; - bool paged, extra_uref = false; skb = skb_peek_tail(queue); if (!skb) { @@ -1440,10 +1440,6 @@ static int __ip6_append_data(struct sock *sk, mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; - if (cork->tx_flags & SKBTX_ANY_TSTAMP && - READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) - tskey = atomic_inc_return(&sk->sk_tskey) - 1; - hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + @@ -1538,6 +1534,11 @@ emsgsize: flags &= ~MSG_SPLICE_PAGES; } + hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; + if (hold_tskey) + tskey = atomic_inc_return(&sk->sk_tskey) - 1; + /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. @@ -1794,6 +1795,8 @@ error: cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (hold_tskey) + atomic_dec(&sk->sk_tskey); return err; } From e5b2e810daf9f2d87fe132eb4d2a85fb08a0db98 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 13 Feb 2024 09:33:39 -0800 Subject: [PATCH 300/311] net: bcmasp: Handle RX buffer allocation failure The buffer_pg variable needs to hold an order-5 allocation (32 x PAGE_SIZE) which, under memory pressure may fail to be allocated. Deal with that error condition properly to avoid doing a NULL pointer de-reference in the subsequent call to dma_map_page(). In addition, the err_reclaim_tx error label in bcmasp_netif_init() needs to ensure that the TX NAPI object is properly deleted, otherwise unregister_netdev() will spin forever attempting to test and clear the NAPI_STATE_HASHED bit. Fixes: 490cb412007d ("net: bcmasp: Add support for ASP2.0 Ethernet controller") Signed-off-by: Florian Fainelli Reviewed-by: Justin Chen Link: https://lore.kernel.org/r/20240213173339.3438713-1-florian.fainelli@broadcom.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index 53e542881255..f59557b0cd51 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -684,6 +684,8 @@ static int bcmasp_init_rx(struct bcmasp_intf *intf) intf->rx_buf_order = get_order(RING_BUFFER_SIZE); buffer_pg = alloc_pages(GFP_KERNEL, intf->rx_buf_order); + if (!buffer_pg) + return -ENOMEM; dma = dma_map_page(kdev, buffer_pg, 0, RING_BUFFER_SIZE, DMA_FROM_DEVICE); @@ -1092,6 +1094,7 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect) return 0; err_reclaim_tx: + netif_napi_del(&intf->tx_napi); bcmasp_reclaim_free_all_tx(intf); err_phy_disconnect: if (phydev) From 4e45170d9acc2d5ae8f545bf3f2f67504a361338 Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Wed, 14 Feb 2024 11:22:24 +0300 Subject: [PATCH 301/311] net: sctp: fix skb leak in sctp_inq_free() In case of GSO, 'chunk->skb' pointer may point to an entry from fraglist created in 'sctp_packet_gso_append()'. To avoid freeing random fraglist entry (and so undefined behavior and/or memory leak), introduce 'sctp_inq_chunk_free()' helper to ensure that 'chunk->skb' is set to 'chunk->head_skb' (i.e. fraglist head) before calling 'sctp_chunk_free()', and use the aforementioned helper in 'sctp_inq_pop()' as well. Reported-by: syzbot+8bb053b5d63595ab47db@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?id=0d8351bbe54fd04a492c2daab0164138db008042 Fixes: 90017accff61 ("sctp: Add GSO support") Suggested-by: Xin Long Signed-off-by: Dmitry Antipov Acked-by: Xin Long Link: https://lore.kernel.org/r/20240214082224.10168-1-dmantipov@yandex.ru Signed-off-by: Jakub Kicinski --- net/sctp/inqueue.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 7182c5a450fb..5c1652181805 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -38,6 +38,14 @@ void sctp_inq_init(struct sctp_inq *queue) INIT_WORK(&queue->immediate, NULL); } +/* Properly release the chunk which is being worked on. */ +static inline void sctp_inq_chunk_free(struct sctp_chunk *chunk) +{ + if (chunk->head_skb) + chunk->skb = chunk->head_skb; + sctp_chunk_free(chunk); +} + /* Release the memory associated with an SCTP inqueue. */ void sctp_inq_free(struct sctp_inq *queue) { @@ -53,7 +61,7 @@ void sctp_inq_free(struct sctp_inq *queue) * free it as well. */ if (queue->in_progress) { - sctp_chunk_free(queue->in_progress); + sctp_inq_chunk_free(queue->in_progress); queue->in_progress = NULL; } } @@ -130,9 +138,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) goto new_skb; } - if (chunk->head_skb) - chunk->skb = chunk->head_skb; - sctp_chunk_free(chunk); + sctp_inq_chunk_free(chunk); chunk = queue->in_progress = NULL; } else { /* Nothing to do. Next chunk in the packet, please. */ From dc34ebd5c018b0edf47f39d11083ad8312733034 Mon Sep 17 00:00:00 2001 From: Gavrilov Ilia Date: Wed, 14 Feb 2024 09:01:50 +0000 Subject: [PATCH 302/311] pppoe: Fix memory leak in pppoe_sendmsg() syzbot reports a memory leak in pppoe_sendmsg [1]. The problem is in the pppoe_recvmsg() function that handles errors in the wrong order. For the skb_recv_datagram() function, check the pointer to skb for NULL first, and then check the 'error' variable, because the skb_recv_datagram() function can set 'error' to -EAGAIN in a loop but return a correct pointer to socket buffer after a number of attempts, though 'error' remains set to -EAGAIN. skb_recv_datagram __skb_recv_datagram // Loop. if (err == -EAGAIN) then // go to the next loop iteration __skb_try_recv_datagram // if (skb != NULL) then return 'skb' // else if a signal is received then // return -EAGAIN Found by InfoTeCS on behalf of Linux Verification Center (linuxtesting.org) with Syzkaller. Link: https://syzkaller.appspot.com/bug?extid=6bdfd184eac7709e5cc9 [1] Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+6bdfd184eac7709e5cc9@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=6bdfd184eac7709e5cc9 Signed-off-by: Gavrilov Ilia Reviewed-by: Guillaume Nault Link: https://lore.kernel.org/r/20240214085814.3894917-1-Ilia.Gavrilov@infotecs.ru Signed-off-by: Jakub Kicinski --- drivers/net/ppp/pppoe.c | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 8e7238e97d0a..2ea4f4890d23 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -1007,26 +1007,21 @@ static int pppoe_recvmsg(struct socket *sock, struct msghdr *m, struct sk_buff *skb; int error = 0; - if (sk->sk_state & PPPOX_BOUND) { - error = -EIO; - goto end; - } + if (sk->sk_state & PPPOX_BOUND) + return -EIO; skb = skb_recv_datagram(sk, flags, &error); - if (error < 0) - goto end; + if (!skb) + return error; - if (skb) { - total_len = min_t(size_t, total_len, skb->len); - error = skb_copy_datagram_msg(skb, 0, m, total_len); - if (error == 0) { - consume_skb(skb); - return total_len; - } + total_len = min_t(size_t, total_len, skb->len); + error = skb_copy_datagram_msg(skb, 0, m, total_len); + if (error == 0) { + consume_skb(skb); + return total_len; } kfree_skb(skb); -end: return error; } From ed4adc07207d9165a4b3b36199231a22e9f51a55 Mon Sep 17 00:00:00 2001 From: Paul Barker Date: Wed, 14 Feb 2024 15:12:04 +0000 Subject: [PATCH 303/311] net: ravb: Count packets instead of descriptors in GbEth RX path The units of "work done" in the RX path should be packets instead of descriptors, as large packets can be spread over multiple descriptors. Fixes: 1c59eb678cbd ("ravb: Fillup ravb_rx_gbeth() stub") Signed-off-by: Paul Barker Reviewed-by: Sergey Shtylyov Link: https://lore.kernel.org/r/20240214151204.2976-1-paul.barker.ct@bp.renesas.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/renesas/ravb_main.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 0e3731f50fc2..f7566cfa45ca 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -772,29 +772,25 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) struct ravb_rx_desc *desc; struct sk_buff *skb; dma_addr_t dma_addr; + int rx_packets = 0; u8 desc_status; - int boguscnt; u16 pkt_len; u8 die_dt; int entry; int limit; + int i; entry = priv->cur_rx[q] % priv->num_rx_ring[q]; - boguscnt = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; + limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; stats = &priv->stats[q]; - boguscnt = min(boguscnt, *quota); - limit = boguscnt; desc = &priv->gbeth_rx_ring[entry]; - while (desc->die_dt != DT_FEMPTY) { + for (i = 0; i < limit && rx_packets < *quota && desc->die_dt != DT_FEMPTY; i++) { /* Descriptor type must be checked before all other reads */ dma_rmb(); desc_status = desc->msc; pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS; - if (--boguscnt < 0) - break; - /* We use 0-byte descriptors to mark the DMA mapping errors */ if (!pkt_len) continue; @@ -820,7 +816,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) skb_put(skb, pkt_len); skb->protocol = eth_type_trans(skb, ndev); napi_gro_receive(&priv->napi[q], skb); - stats->rx_packets++; + rx_packets++; stats->rx_bytes += pkt_len; break; case DT_FSTART: @@ -848,7 +844,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) eth_type_trans(priv->rx_1st_skb, ndev); napi_gro_receive(&priv->napi[q], priv->rx_1st_skb); - stats->rx_packets++; + rx_packets++; stats->rx_bytes += pkt_len; break; } @@ -887,9 +883,9 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) desc->die_dt = DT_FEMPTY; } - *quota -= limit - (++boguscnt); - - return boguscnt <= 0; + stats->rx_packets += rx_packets; + *quota -= rx_packets; + return *quota == 0; } /* Packet receive function for Ethernet AVB */ From 5b8e3464071a4401978a91d2e9f0beca308996c2 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Wed, 14 Feb 2024 07:27:35 -0800 Subject: [PATCH 304/311] net: fill in MODULE_DESCRIPTION()s for xen-netback W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the Xen backend network module. Signed-off-by: Breno Leitao Acked-by: Paul Durrant Link: https://lore.kernel.org/r/20240214152741.670178-2-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/xen-netback/netback.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index fab361a250d6..ef76850d9bcd 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1778,5 +1778,6 @@ static void __exit netback_fini(void) } module_exit(netback_fini); +MODULE_DESCRIPTION("Xen backend network device module"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("xen-backend:vif"); From c0872309ac8432e309824ece24238e8fd2768ef8 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Wed, 14 Feb 2024 07:27:36 -0800 Subject: [PATCH 305/311] net: fill in MODULE_DESCRIPTION()s for ieee802154/fakelb W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the IEEE 802.15.4 loopback driver. Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240214152741.670178-3-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/ieee802154/fakelb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c index 35e55f198e05..2930141d7dd2 100644 --- a/drivers/net/ieee802154/fakelb.c +++ b/drivers/net/ieee802154/fakelb.c @@ -259,4 +259,5 @@ static __exit void fake_remove_module(void) module_init(fakelb_init_module); module_exit(fake_remove_module); +MODULE_DESCRIPTION("IEEE 802.15.4 loopback driver"); MODULE_LICENSE("GPL"); From 44c1197bcef49bdf1021bef7cdb32520b2bc1ce4 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Wed, 14 Feb 2024 07:27:37 -0800 Subject: [PATCH 306/311] net: fill in MODULE_DESCRIPTION()s for plip W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the PLIP (parallel port) network module Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240214152741.670178-4-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/plip/plip.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c index 40ce8abe6999..cc7d1113ece0 100644 --- a/drivers/net/plip/plip.c +++ b/drivers/net/plip/plip.c @@ -1437,4 +1437,5 @@ static int __init plip_init (void) module_init(plip_init); module_exit(plip_cleanup_module); +MODULE_DESCRIPTION("PLIP (parallel port) network module"); MODULE_LICENSE("GPL"); From 4ad9e85874393eec74edf2d2c7b7c7ba11f78d20 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Wed, 14 Feb 2024 07:27:38 -0800 Subject: [PATCH 307/311] net: fill in MODULE_DESCRIPTION()s for fddik/skfp W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the SysKonnect FDDI PCI module. Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240214152741.670178-5-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/fddi/skfp/skfddi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/fddi/skfp/skfddi.c b/drivers/net/fddi/skfp/skfddi.c index 2b6a607ac0b7..a273362c9e70 100644 --- a/drivers/net/fddi/skfp/skfddi.c +++ b/drivers/net/fddi/skfp/skfddi.c @@ -153,6 +153,7 @@ static const struct pci_device_id skfddi_pci_tbl[] = { { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(pci, skfddi_pci_tbl); +MODULE_DESCRIPTION("SysKonnect FDDI PCI driver"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Mirko Lindner "); From e1e5ef2aefc2ab77dacf77626f9f25f332ba91b7 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Wed, 14 Feb 2024 07:27:39 -0800 Subject: [PATCH 308/311] net: fill in MODULE_DESCRIPTION()s for ppp W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the PPP modules. Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240214152741.670178-6-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/ppp/bsd_comp.c | 1 + drivers/net/ppp/ppp_async.c | 1 + drivers/net/ppp/ppp_deflate.c | 1 + drivers/net/ppp/ppp_generic.c | 1 + drivers/net/ppp/ppp_synctty.c | 1 + 5 files changed, 5 insertions(+) diff --git a/drivers/net/ppp/bsd_comp.c b/drivers/net/ppp/bsd_comp.c index db0dc36d12e3..55954594e157 100644 --- a/drivers/net/ppp/bsd_comp.c +++ b/drivers/net/ppp/bsd_comp.c @@ -1166,5 +1166,6 @@ static void __exit bsdcomp_cleanup(void) module_init(bsdcomp_init); module_exit(bsdcomp_cleanup); +MODULE_DESCRIPTION("PPP BSD-Compress compression module"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("ppp-compress-" __stringify(CI_BSD_COMPRESS)); diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 125793d8aefa..c33c3db3cc08 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -87,6 +87,7 @@ struct asyncppp { static int flag_time = HZ; module_param(flag_time, int, 0); MODULE_PARM_DESC(flag_time, "ppp_async: interval between flagged packets (in clock ticks)"); +MODULE_DESCRIPTION("PPP async serial channel module"); MODULE_LICENSE("GPL"); MODULE_ALIAS_LDISC(N_PPP); diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c index e6d48e5c65a3..4d2ff63f2ee2 100644 --- a/drivers/net/ppp/ppp_deflate.c +++ b/drivers/net/ppp/ppp_deflate.c @@ -630,6 +630,7 @@ static void __exit deflate_cleanup(void) module_init(deflate_init); module_exit(deflate_cleanup); +MODULE_DESCRIPTION("PPP Deflate compression module"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE)); MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE_DRAFT)); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 0193af2d31c9..3dd52bf28f15 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -3604,6 +3604,7 @@ EXPORT_SYMBOL(ppp_input_error); EXPORT_SYMBOL(ppp_output_wakeup); EXPORT_SYMBOL(ppp_register_compressor); EXPORT_SYMBOL(ppp_unregister_compressor); +MODULE_DESCRIPTION("Generic PPP layer driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CHARDEV(PPP_MAJOR, 0); MODULE_ALIAS_RTNL_LINK("ppp"); diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index 52d05ce4a281..45bf59ac8f57 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -724,5 +724,6 @@ ppp_sync_cleanup(void) module_init(ppp_sync_init); module_exit(ppp_sync_cleanup); +MODULE_DESCRIPTION("PPP synchronous TTY channel module"); MODULE_LICENSE("GPL"); MODULE_ALIAS_LDISC(N_SYNC_PPP); From 9de69f0e99585d84baab4fbb0b3b97c02cf069f1 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Wed, 14 Feb 2024 07:27:40 -0800 Subject: [PATCH 309/311] net: fill in MODULE_DESCRIPTION()s for mdio_devres W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the PHY MDIO helpers. Suggested-by: Andrew Lunn Signed-off-by: Breno Leitao Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20240214152741.670178-7-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/phy/mdio_devres.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c index 69b829e6ab35..7fd3377dbd79 100644 --- a/drivers/net/phy/mdio_devres.c +++ b/drivers/net/phy/mdio_devres.c @@ -131,4 +131,5 @@ int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, EXPORT_SYMBOL(__devm_of_mdiobus_register); #endif /* CONFIG_OF_MDIO */ +MODULE_DESCRIPTION("Network MDIO bus devres helpers"); MODULE_LICENSE("GPL"); From 538b22e74287864014b3be7481042fb904a0cc0d Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Wed, 14 Feb 2024 07:27:41 -0800 Subject: [PATCH 310/311] net: fill in MODULE_DESCRIPTION()s for missing arcnet W=1 builds now warn if module is built without a MODULE_DESCRIPTION(). Add descriptions to the ARC modules. Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240214152741.670178-8-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/arcnet/arc-rawmode.c | 1 + drivers/net/arcnet/arc-rimi.c | 1 + drivers/net/arcnet/capmode.c | 1 + drivers/net/arcnet/com20020-pci.c | 1 + drivers/net/arcnet/com20020.c | 1 + drivers/net/arcnet/com20020_cs.c | 1 + drivers/net/arcnet/com90io.c | 1 + drivers/net/arcnet/com90xx.c | 1 + drivers/net/arcnet/rfc1051.c | 1 + drivers/net/arcnet/rfc1201.c | 1 + 10 files changed, 10 insertions(+) diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c index 8c651fdee039..57f1729066f2 100644 --- a/drivers/net/arcnet/arc-rawmode.c +++ b/drivers/net/arcnet/arc-rawmode.c @@ -186,4 +186,5 @@ static void __exit arcnet_raw_exit(void) module_init(arcnet_raw_init); module_exit(arcnet_raw_exit); +MODULE_DESCRIPTION("ARCnet raw mode packet interface module"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 8c3ccc7c83cd..53d10a04d1bd 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -312,6 +312,7 @@ module_param(node, int, 0); module_param(io, int, 0); module_param(irq, int, 0); module_param_string(device, device, sizeof(device), 0); +MODULE_DESCRIPTION("ARCnet COM90xx RIM I chipset driver"); MODULE_LICENSE("GPL"); static struct net_device *my_dev; diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c index c09b567845e1..7a0a79973769 100644 --- a/drivers/net/arcnet/capmode.c +++ b/drivers/net/arcnet/capmode.c @@ -265,4 +265,5 @@ static void __exit capmode_module_exit(void) module_init(capmode_module_init); module_exit(capmode_module_exit); +MODULE_DESCRIPTION("ARCnet CAP mode packet interface module"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 7b5c8bb02f11..c5e571ec94c9 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -61,6 +61,7 @@ module_param(timeout, int, 0); module_param(backplane, int, 0); module_param(clockp, int, 0); module_param(clockm, int, 0); +MODULE_DESCRIPTION("ARCnet COM20020 chipset PCI driver"); MODULE_LICENSE("GPL"); static void led_tx_set(struct led_classdev *led_cdev, diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index 06e1651b594b..a0053e3992a3 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -399,6 +399,7 @@ EXPORT_SYMBOL(com20020_found); EXPORT_SYMBOL(com20020_netdev_ops); #endif +MODULE_DESCRIPTION("ARCnet COM20020 chipset core driver"); MODULE_LICENSE("GPL"); #ifdef MODULE diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index dc3253b318da..75f08aa7528b 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -97,6 +97,7 @@ module_param(backplane, int, 0); module_param(clockp, int, 0); module_param(clockm, int, 0); +MODULE_DESCRIPTION("ARCnet COM20020 chipset PCMCIA driver"); MODULE_LICENSE("GPL"); /*====================================================================*/ diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 37b47749fc8b..3b463fbc6402 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -350,6 +350,7 @@ static char device[9]; /* use eg. device=arc1 to change name */ module_param_hw(io, int, ioport, 0); module_param_hw(irq, int, irq, 0); module_param_string(device, device, sizeof(device), 0); +MODULE_DESCRIPTION("ARCnet COM90xx IO mapped chipset driver"); MODULE_LICENSE("GPL"); #ifndef MODULE diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index f49dae194284..b3b287c16561 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -645,6 +645,7 @@ static void com90xx_copy_from_card(struct net_device *dev, int bufnum, TIME(dev, "memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); } +MODULE_DESCRIPTION("ARCnet COM90xx normal chipset driver"); MODULE_LICENSE("GPL"); static int __init com90xx_init(void) diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c index a7752a5b647f..46519ca63a0a 100644 --- a/drivers/net/arcnet/rfc1051.c +++ b/drivers/net/arcnet/rfc1051.c @@ -78,6 +78,7 @@ static void __exit arcnet_rfc1051_exit(void) module_init(arcnet_rfc1051_init); module_exit(arcnet_rfc1051_exit); +MODULE_DESCRIPTION("ARCNet packet format (RFC 1051) module"); MODULE_LICENSE("GPL"); /* Determine a packet's protocol ID. diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c index a4c856282674..0edf35d971c5 100644 --- a/drivers/net/arcnet/rfc1201.c +++ b/drivers/net/arcnet/rfc1201.c @@ -35,6 +35,7 @@ #include "arcdevice.h" +MODULE_DESCRIPTION("ARCNet packet format (RFC 1201) module"); MODULE_LICENSE("GPL"); static __be16 type_trans(struct sk_buff *skb, struct net_device *dev); From 68fb3ca0e408e00db1c3f8fccdfa19e274c033be Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 15 Feb 2024 11:14:33 -0800 Subject: [PATCH 311/311] update workarounds for gcc "asm goto" issue In commit 4356e9f841f7 ("work around gcc bugs with 'asm goto' with outputs") I did the gcc workaround unconditionally, because the cause of the bad code generation wasn't entirely clear. In the meantime, Jakub Jelinek debugged the issue, and has come up with a fix in gcc [2], which also got backported to the still maintained branches of gcc-11, gcc-12 and gcc-13. Note that while the fix technically wasn't in the original gcc-14 branch, Jakub says: "while it is true that no GCC 14 snapshots until today (or whenever the fix will be committed) have the fix, for GCC trunk it is up to the distros to use the latest snapshot if they use it at all and would allow better testing of the kernel code without the workaround, so that if there are other issues they won't be discovered years later. Most userland code doesn't actually use asm goto with outputs..." so we will consider gcc-14 to be fixed - if somebody is using gcc snapshots of the gcc-14 before the fix, they should upgrade. Note that while the bug goes back to gcc-11, in practice other gcc changes seem to have effectively hidden it since gcc-12.1 as per a bisect by Jakub. So even a gcc-14 snapshot without the fix likely doesn't show actual problems. Also, make the default 'asm_goto_output()' macro mark the asm as volatile by hand, because of an unrelated gcc issue [1] where it doesn't match the documented behavior ("asm goto is always volatile"). Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979 [1] Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 [2] Link: https://lore.kernel.org/all/20240208220604.140859-1-seanjc@google.com/ Requested-by: Jakub Jelinek Cc: Uros Bizjak Cc: Nick Desaulniers Cc: Sean Christopherson Cc: Andrew Pinski Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 7 ++++--- include/linux/compiler_types.h | 9 ++++++++- init/Kconfig | 9 +++++++++ 3 files changed, 21 insertions(+), 4 deletions(-) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c1a963be7d28..75bd1692d2e3 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -67,10 +67,9 @@ /* * GCC 'asm goto' with outputs miscompiles certain code sequences: * - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420 - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422 + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 * - * Work it around via the same compiler barrier quirk that we used + * Work around it via the same compiler barrier quirk that we used * to use for the old 'asm goto' workaround. * * Also, always mark such 'asm goto' statements as volatile: all @@ -80,8 +79,10 @@ * * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 */ +#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND #define asm_goto_output(x...) \ do { asm volatile goto(x); asm (""); } while (0) +#endif #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 663d8791c871..0caf354cb94b 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -362,8 +362,15 @@ struct ftrace_likely_data { #define __member_size(p) __builtin_object_size(p, 1) #endif +/* + * Some versions of gcc do not mark 'asm goto' volatile: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979 + * + * We do it here by hand, because it doesn't hurt. + */ #ifndef asm_goto_output -#define asm_goto_output(x...) asm goto(x) +#define asm_goto_output(x...) asm volatile goto(x) #endif #ifdef CONFIG_CC_HAS_ASM_INLINE diff --git a/init/Kconfig b/init/Kconfig index deda3d14135b..8426d59cc634 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -89,6 +89,15 @@ config CC_HAS_ASM_GOTO_TIED_OUTPUT # Detect buggy gcc and clang, fixed in gcc-11 clang-14. def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) +config GCC_ASM_GOTO_OUTPUT_WORKAROUND + bool + depends on CC_IS_GCC && CC_HAS_ASM_GOTO_OUTPUT + # Fixed in GCC 14, 13.3, 12.4 and 11.5 + # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 + default y if GCC_VERSION < 110500 + default y if GCC_VERSION >= 120000 && GCC_VERSION < 120400 + default y if GCC_VERSION >= 130000 && GCC_VERSION < 130300 + config TOOLS_SUPPORT_RELR def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh)