From: Dinghao Liu dinghao.liu@zju.edu.cn

[ Upstream commit 28d211919e422f58c1e6c900e5810eee4f1ce4c8 ]

When clk_hw_register_fixed_rate_with_accuracy() fails, clk_data should be freed. It's the same for the subsequent two error paths, but we should also unregister the already registered clocks in them.

Signed-off-by: Dinghao Liu dinghao.liu@zju.edu.cn Signed-off-by: Alexandre Belloni alexandre.belloni@bootlin.com Link: https://lore.kernel.org/r/20201020061226.6572-1-dinghao.liu@zju.edu.cn Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/rtc/rtc-sun6i.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index e2b8b150bcb44..f2818cdd11d82 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -272,7 +272,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, 300000000); if (IS_ERR(rtc->int_osc)) { pr_crit("Couldn't register the internal oscillator\n"); - return; + goto err; }

parents[0] = clk_hw_get_name(rtc->int_osc); @@ -290,7 +290,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, rtc->losc = clk_register(NULL, &rtc->hw); if (IS_ERR(rtc->losc)) { pr_crit("Couldn't register the LOSC clock\n"); - return; + goto err_register; }

of_property_read_string_index(node, "clock-output-names", 1, @@ -301,7 +301,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, &rtc->lock); if (IS_ERR(rtc->ext_losc)) { pr_crit("Couldn't register the LOSC external gate\n"); - return; + goto err_register; }

clk_data->num = 2; @@ -314,6 +314,8 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); return;

+err_register: + clk_hw_unregister_fixed_rate(rtc->int_osc); err: kfree(clk_data); }

From: Jan Kara jack@suse.cz

[ Upstream commit 10f04d40a9fa29785206c619f80d8beedb778837 ]

The on-disk quota format supports quota files with upto 2^32 blocks. Be careful when computing quota file offsets in the quota files from block numbers as they can overflow 32-bit types. Since quota files larger than 4GB would require ~26 millions of quota users, this is mostly a theoretical concern now but better be careful, fuzzers would find the problem sooner or later anyway...

Reviewed-by: Andreas Dilger adilger@dilger.ca Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- fs/quota/quota_tree.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c index a6f856f341dc7..c5562c871c8be 100644 --- a/fs/quota/quota_tree.c +++ b/fs/quota/quota_tree.c @@ -62,7 +62,7 @@ static ssize_t read_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf)

memset(buf, 0, info->dqi_usable_bs); return sb->s_op->quota_read(sb, info->dqi_type, buf, - info->dqi_usable_bs, blk << info->dqi_blocksize_bits); + info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits); }

static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) @@ -71,7 +71,7 @@ static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) ssize_t ret;

ret = sb->s_op->quota_write(sb, info->dqi_type, buf, - info->dqi_usable_bs, blk << info->dqi_blocksize_bits); + info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits); if (ret != info->dqi_usable_bs) { quota_error(sb, "dquota write failed"); if (ret >= 0) @@ -284,7 +284,7 @@ static uint find_free_dqentry(struct qtree_mem_dqinfo *info, blk); goto out_buf; } - dquot->dq_off = (blk << info->dqi_blocksize_bits) + + dquot->dq_off = ((loff_t)blk << info->dqi_blocksize_bits) + sizeof(struct qt_disk_dqdbheader) + i * info->dqi_entry_size; kfree(buf); @@ -559,7 +559,7 @@ static loff_t find_block_dqentry(struct qtree_mem_dqinfo *info, ret = -EIO; goto out_buf; } else { - ret = (blk << info->dqi_blocksize_bits) + sizeof(struct + ret = ((loff_t)blk << info->dqi_blocksize_bits) + sizeof(struct qt_disk_dqdbheader) + i * info->dqi_entry_size; } out_buf:

From: Qinglang Miao miaoqinglang@huawei.com

[ Upstream commit ffa1797040c5da391859a9556be7b735acbe1242 ]

I noticed that iounmap() of msgr_block_addr before return from mpic_msgr_probe() in the error handling case is missing. So use devm_ioremap() instead of just ioremap() when remapping the message register block, so the mapping will be automatically released on probe failure.

Signed-off-by: Qinglang Miao miaoqinglang@huawei.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20201028091551.136400-1-miaoqinglang@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/sysdev/mpic_msgr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c index f6b253e2be409..36ec0bdd8b63c 100644 --- a/arch/powerpc/sysdev/mpic_msgr.c +++ b/arch/powerpc/sysdev/mpic_msgr.c @@ -191,7 +191,7 @@ static int mpic_msgr_probe(struct platform_device *dev)

/* IO map the message register block. */ of_address_to_resource(np, 0, &rsrc); - msgr_block_addr = ioremap(rsrc.start, resource_size(&rsrc)); + msgr_block_addr = devm_ioremap(&dev->dev, rsrc.start, resource_size(&rsrc)); if (!msgr_block_addr) { dev_err(&dev->dev, "Failed to iomap MPIC message registers"); return -EFAULT;

From: Rustam Kovhaev rkovhaev@gmail.com

[ Upstream commit d24396c5290ba8ab04ba505176874c4e04a2d53c ]

when directory item has an invalid value set for ih_entry_count it might trigger use-after-free or out-of-bounds read in bin_search_in_dir_item()

ih_entry_count * IH_SIZE for directory item should not be larger than ih_item_len

Link: https://lore.kernel.org/r/20201101140958.3650143-1-rkovhaev@gmail.com Reported-and-tested-by: syzbot+83b6f7cf9922cae5c4d7@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=83b6f7cf9922cae5c4d7 Signed-off-by: Rustam Kovhaev rkovhaev@gmail.com Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- fs/reiserfs/stree.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 8bf88d690729e..476a7ff494822 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -454,6 +454,12 @@ static int is_leaf(char *buf, int blocksize, struct buffer_head *bh) "(second one): %h", ih); return 0; } + if (is_direntry_le_ih(ih) && (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE))) { + reiserfs_warning(NULL, "reiserfs-5093", + "item entry count seems wrong %h", + ih); + return 0; + } prev_location = ih_location(ih); }

From: Daniel Rosenberg drosen@google.com

[ Upstream commit 7ad08a58bf67594057362e45cbddd3e27e53e557 ]

Expand f2fs's casefolding support to include encrypted directories. To index casefolded+encrypted directories, we use the SipHash of the casefolded name, keyed by a key derived from the directory's fscrypt master key. This ensures that the dirhash doesn't leak information about the plaintext filenames.

Encryption keys are unavailable during roll-forward recovery, so we can't compute the dirhash when recovering a new dentry in an encrypted + casefolded directory. To avoid having to force a checkpoint when a new file is fsync'ed, store the dirhash on-disk appended to i_name.

This patch incorporates work by Eric Biggers ebiggers@google.com and Jaegeuk Kim jaegeuk@kernel.org.

Co-developed-by: Eric Biggers ebiggers@google.com Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Daniel Rosenberg drosen@google.com Reviewed-by: Eric Biggers ebiggers@google.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/f2fs/dir.c | 98 +++++++++++++++++++++++++++++++++++----------- fs/f2fs/f2fs.h | 8 ++-- fs/f2fs/hash.c | 11 +++++- fs/f2fs/inline.c | 4 ++ fs/f2fs/recovery.c | 12 +++++- fs/f2fs/super.c | 6 --- 6 files changed, 106 insertions(+), 33 deletions(-)

diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 4b9ef8bbfa4a9..4ee0b7070c157 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -5,6 +5,7 @@ * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ */ +#include <asm/unaligned.h> #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/sched/signal.h> @@ -206,30 +207,55 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir, /* * Test whether a case-insensitive directory entry matches the filename * being searched for. + * + * Returns 1 for a match, 0 for no match, and -errno on an error. */ -static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name, +static int f2fs_match_ci_name(const struct inode *dir, const struct qstr *name, const u8 *de_name, u32 de_name_len) { const struct super_block *sb = dir->i_sb; const struct unicode_map *um = sb->s_encoding; + struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len); struct qstr entry = QSTR_INIT(de_name, de_name_len); int res;

+ if (IS_ENCRYPTED(dir)) { + const struct fscrypt_str encrypted_name = + FSTR_INIT((u8 *)de_name, de_name_len); + + if (WARN_ON_ONCE(!fscrypt_has_encryption_key(dir))) + return -EINVAL; + + decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL); + if (!decrypted_name.name) + return -ENOMEM; + res = fscrypt_fname_disk_to_usr(dir, 0, 0, &encrypted_name, + &decrypted_name); + if (res < 0) + goto out; + entry.name = decrypted_name.name; + entry.len = decrypted_name.len; + } + res = utf8_strncasecmp_folded(um, name, &entry); - if (res < 0) { - /* - * In strict mode, ignore invalid names. In non-strict mode, - * fall back to treating them as opaque byte sequences. - */ - if (sb_has_strict_encoding(sb) || name->len != entry.len) - return false; - return !memcmp(name->name, entry.name, name->len); + /* + * In strict mode, ignore invalid names. In non-strict mode, + * fall back to treating them as opaque byte sequences. + */ + if (res < 0 && !sb_has_strict_encoding(sb)) { + res = name->len == entry.len && + memcmp(name->name, entry.name, name->len) == 0; + } else { + /* utf8_strncasecmp_folded returns 0 on match */ + res = (res == 0); } - return res == 0; +out: + kfree(decrypted_name.name); + return res; } #endif /* CONFIG_UNICODE */

-static inline bool f2fs_match_name(const struct inode *dir, +static inline int f2fs_match_name(const struct inode *dir, const struct f2fs_filename *fname, const u8 *de_name, u32 de_name_len) { @@ -256,6 +282,7 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d, struct f2fs_dir_entry *de; unsigned long bit_pos = 0; int max_len = 0; + int res = 0;

if (max_slots) *max_slots = 0; @@ -273,10 +300,15 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d, continue; }

- if (de->hash_code == fname->hash && - f2fs_match_name(d->inode, fname, d->filename[bit_pos], - le16_to_cpu(de->name_len))) - goto found; + if (de->hash_code == fname->hash) { + res = f2fs_match_name(d->inode, fname, + d->filename[bit_pos], + le16_to_cpu(de->name_len)); + if (res < 0) + return ERR_PTR(res); + if (res) + goto found; + }

if (max_slots && max_len > *max_slots) *max_slots = max_len; @@ -326,7 +358,11 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, }

de = find_in_block(dir, dentry_page, fname, &max_slots); - if (de) { + if (IS_ERR(de)) { + *res_page = ERR_CAST(de); + de = NULL; + break; + } else if (de) { *res_page = dentry_page; break; } @@ -448,17 +484,39 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, f2fs_put_page(page, 1); }

-static void init_dent_inode(const struct f2fs_filename *fname, +static void init_dent_inode(struct inode *dir, struct inode *inode, + const struct f2fs_filename *fname, struct page *ipage) { struct f2fs_inode *ri;

+ if (!fname) /* tmpfile case? */ + return; + f2fs_wait_on_page_writeback(ipage, NODE, true, true);

/* copy name info. to this inode page */ ri = F2FS_INODE(ipage); ri->i_namelen = cpu_to_le32(fname->disk_name.len); memcpy(ri->i_name, fname->disk_name.name, fname->disk_name.len); + if (IS_ENCRYPTED(dir)) { + file_set_enc_name(inode); + /* + * Roll-forward recovery doesn't have encryption keys available, + * so it can't compute the dirhash for encrypted+casefolded + * filenames. Append it to i_name if possible. Else, disable + * roll-forward recovery of the dentry (i.e., make fsync'ing the + * file force a checkpoint) by setting LOST_PINO. + */ + if (IS_CASEFOLDED(dir)) { + if (fname->disk_name.len + sizeof(f2fs_hash_t) <= + F2FS_NAME_LEN) + put_unaligned(fname->hash, (f2fs_hash_t *) + &ri->i_name[fname->disk_name.len]); + else + file_lost_pino(inode); + } + } set_page_dirty(ipage); }

@@ -541,11 +599,7 @@ struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir, return page; }

- if (fname) { - init_dent_inode(fname, page); - if (IS_ENCRYPTED(dir)) - file_set_enc_name(inode); - } + init_dent_inode(dir, inode, fname, page);

/* * This file should be checkpointed during fsync. diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9a321c52facec..8cba43eb0b24a 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -533,9 +533,11 @@ struct f2fs_filename { #ifdef CONFIG_UNICODE /* * For casefolded directories: the casefolded name, but it's left NULL - * if the original name is not valid Unicode or if the filesystem is - * doing an internal operation where usr_fname is also NULL. In these - * cases we fall back to treating the name as an opaque byte sequence. + * if the original name is not valid Unicode, if the directory is both + * casefolded and encrypted and its encryption key is unavailable, or if + * the filesystem is doing an internal operation where usr_fname is also + * NULL. In all these cases we fall back to treating the name as an + * opaque byte sequence. */ struct fscrypt_str cf_name; #endif diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index de841aaf3c439..e3beac546c63a 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -111,7 +111,9 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname) * If the casefolded name is provided, hash it instead of the * on-disk name. If the casefolded name is *not* provided, that * should only be because the name wasn't valid Unicode, so fall - * back to treating the name as an opaque byte sequence. + * back to treating the name as an opaque byte sequence. Note + * that to handle encrypted directories, the fallback must use + * usr_fname (plaintext) rather than disk_name (ciphertext). */ WARN_ON_ONCE(!fname->usr_fname->name); if (fname->cf_name.name) { @@ -121,6 +123,13 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname) name = fname->usr_fname->name; len = fname->usr_fname->len; } + if (IS_ENCRYPTED(dir)) { + struct qstr tmp = QSTR_INIT(name, len); + + fname->hash = + cpu_to_le32(fscrypt_fname_siphash(dir, &tmp)); + return; + } } #endif fname->hash = cpu_to_le32(TEA_hash_name(name, len)); diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 70384e31788db..92e9852d316ad 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -332,6 +332,10 @@ struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, make_dentry_ptr_inline(dir, &d, inline_dentry); de = f2fs_find_target_dentry(&d, fname, NULL); unlock_page(ipage); + if (IS_ERR(de)) { + *res_page = ERR_CAST(de); + de = NULL; + } if (de) *res_page = ipage; else diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 4f12ade6410a1..0947d36af1a8e 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -5,6 +5,7 @@ * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ */ +#include <asm/unaligned.h> #include <linux/fs.h> #include <linux/f2fs_fs.h> #include "f2fs.h" @@ -128,7 +129,16 @@ static int init_recovered_filename(const struct inode *dir, }

/* Compute the hash of the filename */ - if (IS_CASEFOLDED(dir)) { + if (IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir)) { + /* + * In this case the hash isn't computable without the key, so it + * was saved on-disk. + */ + if (fname->disk_name.len + sizeof(f2fs_hash_t) > F2FS_NAME_LEN) + return -EINVAL; + fname->hash = get_unaligned((f2fs_hash_t *) + &raw_inode->i_name[fname->disk_name.len]); + } else if (IS_CASEFOLDED(dir)) { err = f2fs_init_casefolded_name(dir, fname); if (err) return err; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 00eff2f518079..ba859eeca69a3 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3399,12 +3399,6 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi) struct unicode_map *encoding; __u16 encoding_flags;

- if (f2fs_sb_has_encrypt(sbi)) { - f2fs_err(sbi, - "Can't mount with encoding and encryption"); - return -EINVAL; - } - if (f2fs_sb_read_encoding(sbi->raw_super, &encoding_info, &encoding_flags)) { f2fs_err(sbi,

From: Daeho Jeong daehojeong@google.com

[ Upstream commit 6422a71ef40e4751d59b8c9412e7e2dafe085878 ]

I found out f2fs_free_dic() is invoked in a wrong timing, but f2fs_verify_bio() still needed the dic info and it triggered the below kernel panic. It has been caused by the race condition of pending_pages value between decompression and verity logic, when the same compression cluster had been split in different bios. By split bios, f2fs_verify_bio() ended up with decreasing pending_pages value before it is reset to nr_cpages by f2fs_decompress_pages() and caused the kernel panic.

[ 4416.564763] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 ... [ 4416.896016] Workqueue: fsverity_read_queue f2fs_verity_work [ 4416.908515] pc : fsverity_verify_page+0x20/0x78 [ 4416.913721] lr : f2fs_verify_bio+0x11c/0x29c [ 4416.913722] sp : ffffffc019533cd0 [ 4416.913723] x29: ffffffc019533cd0 x28: 0000000000000402 [ 4416.913724] x27: 0000000000000001 x26: 0000000000000100 [ 4416.913726] x25: 0000000000000001 x24: 0000000000000004 [ 4416.913727] x23: 0000000000001000 x22: 0000000000000000 [ 4416.913728] x21: 0000000000000000 x20: ffffffff2076f9c0 [ 4416.913729] x19: ffffffff2076f9c0 x18: ffffff8a32380c30 [ 4416.913731] x17: ffffffc01f966d97 x16: 0000000000000298 [ 4416.913732] x15: 0000000000000000 x14: 0000000000000000 [ 4416.913733] x13: f074faec89ffffff x12: 0000000000000000 [ 4416.913734] x11: 0000000000001000 x10: 0000000000001000 [ 4416.929176] x9 : ffffffff20d1f5c7 x8 : 0000000000000000 [ 4416.929178] x7 : 626d7464ff286b6b x6 : ffffffc019533ade [ 4416.929179] x5 : 000000008049000e x4 : ffffffff2793e9e0 [ 4416.929180] x3 : 000000008049000e x2 : ffffff89ecfa74d0 [ 4416.929181] x1 : 0000000000000c40 x0 : ffffffff2076f9c0 [ 4416.929184] Call trace: [ 4416.929187] fsverity_verify_page+0x20/0x78 [ 4416.929189] f2fs_verify_bio+0x11c/0x29c [ 4416.929192] f2fs_verity_work+0x58/0x84 [ 4417.050667] process_one_work+0x270/0x47c [ 4417.055354] worker_thread+0x27c/0x4d8 [ 4417.059784] kthread+0x13c/0x320 [ 4417.063693] ret_from_fork+0x10/0x18

Chao pointed this can happen by the below race condition.

Thread A f2fs_post_read_wq fsverity_wq - f2fs_read_multi_pages() - f2fs_alloc_dic - dic->pending_pages = 2 - submit_bio() - submit_bio() - f2fs_post_read_work() handle first bio - f2fs_decompress_work() - __read_end_io() - f2fs_decompress_pages() - dic->pending_pages-- - enqueue f2fs_verity_work() - f2fs_verity_work() handle first bio - f2fs_verify_bio() - dic->pending_pages-- - f2fs_post_read_work() handle second bio - f2fs_decompress_work() - enqueue f2fs_verity_work() - f2fs_verify_pages() - f2fs_free_dic()

- f2fs_verity_work() handle second bio - f2fs_verfy_bio() - use-after-free on dic

Signed-off-by: Daeho Jeong daehojeong@google.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/f2fs/compress.c | 2 -- fs/f2fs/data.c | 58 +++++++++++++++++++++++++++++++++++++--------- fs/f2fs/f2fs.h | 1 + 3 files changed, 48 insertions(+), 13 deletions(-)

diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 14262e0f1cd60..c5fee4d7ea72f 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -798,8 +798,6 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity) if (cops->destroy_decompress_ctx) cops->destroy_decompress_ctx(dic); out_free_dic: - if (verity) - atomic_set(&dic->pending_pages, dic->nr_cpages); if (!verity) f2fs_decompress_end_io(dic->rpages, dic->cluster_size, ret, false); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index be4da52604edc..b29243ee1c3e5 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -202,7 +202,7 @@ static void f2fs_verify_bio(struct bio *bio) dic = (struct decompress_io_ctx *)page_private(page);

if (dic) { - if (atomic_dec_return(&dic->pending_pages)) + if (atomic_dec_return(&dic->verity_pages)) continue; f2fs_verify_pages(dic->rpages, dic->cluster_size); @@ -1027,7 +1027,8 @@ static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)

static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, unsigned nr_pages, unsigned op_flag, - pgoff_t first_idx, bool for_write) + pgoff_t first_idx, bool for_write, + bool for_verity) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct bio *bio; @@ -1049,7 +1050,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, post_read_steps |= 1 << STEP_DECRYPT; if (f2fs_compressed_file(inode)) post_read_steps |= 1 << STEP_DECOMPRESS_NOWQ; - if (f2fs_need_verity(inode, first_idx)) + if (for_verity && f2fs_need_verity(inode, first_idx)) post_read_steps |= 1 << STEP_VERITY;

if (post_read_steps) { @@ -1079,7 +1080,7 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, struct bio *bio;

bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags, - page->index, for_write); + page->index, for_write, true); if (IS_ERR(bio)) return PTR_ERR(bio);

@@ -2133,7 +2134,7 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page, if (bio == NULL) { bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, is_readahead ? REQ_RAHEAD : 0, page->index, - false); + false, true); if (IS_ERR(bio)) { ret = PTR_ERR(bio); bio = NULL; @@ -2180,6 +2181,8 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, const unsigned blkbits = inode->i_blkbits; const unsigned blocksize = 1 << blkbits; struct decompress_io_ctx *dic = NULL; + struct bio_post_read_ctx *ctx; + bool for_verity = false; int i; int ret = 0;

@@ -2245,10 +2248,29 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, goto out_put_dnode; }

+ /* + * It's possible to enable fsverity on the fly when handling a cluster, + * which requires complicated error handling. Instead of adding more + * complexity, let's give a rule where end_io post-processes fsverity + * per cluster. In order to do that, we need to submit bio, if previous + * bio sets a different post-process policy. + */ + if (fsverity_active(cc->inode)) { + atomic_set(&dic->verity_pages, cc->nr_cpages); + for_verity = true; + + if (bio) { + ctx = bio->bi_private; + if (!(ctx->enabled_steps & (1 << STEP_VERITY))) { + __submit_bio(sbi, bio, DATA); + bio = NULL; + } + } + } + for (i = 0; i < dic->nr_cpages; i++) { struct page *page = dic->cpages[i]; block_t blkaddr; - struct bio_post_read_ctx *ctx;

blkaddr = data_blkaddr(dn.inode, dn.node_page, dn.ofs_in_node + i + 1); @@ -2264,17 +2286,31 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, if (!bio) { bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages, is_readahead ? REQ_RAHEAD : 0, - page->index, for_write); + page->index, for_write, for_verity); if (IS_ERR(bio)) { + unsigned int remained = dic->nr_cpages - i; + bool release = false; + ret = PTR_ERR(bio); dic->failed = true; - if (!atomic_sub_return(dic->nr_cpages - i, - &dic->pending_pages)) { + + if (for_verity) { + if (!atomic_sub_return(remained, + &dic->verity_pages)) + release = true; + } else { + if (!atomic_sub_return(remained, + &dic->pending_pages)) + release = true; + } + + if (release) { f2fs_decompress_end_io(dic->rpages, - cc->cluster_size, true, - false); + cc->cluster_size, true, + false); f2fs_free_dic(dic); } + f2fs_put_dnode(&dn); *bio_ret = NULL; return ret; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 14ace0e21d389..72a25387f49bc 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1412,6 +1412,7 @@ struct decompress_io_ctx { size_t rlen; /* valid data length in rbuf */ size_t clen; /* valid data length in cbuf */ atomic_t pending_pages; /* in-flight compressed page count */ + atomic_t verity_pages; /* in-flight page count for verity */ bool failed; /* indicate IO error during decompression */ void *private; /* payload buffer for specified decompression algorithm */ void *private2; /* extra payload buffer */

From: Nicholas Piggin npiggin@gmail.com

[ Upstream commit 59d512e4374b2d8a6ad341475dc94c4a4bdec7d3 ]

This is way to catch some cases of decrementer overflow, when the decrementer has underflowed an odd number of times, while MSR[EE] was disabled.

With a typical small decrementer, a timer that fires when MSR[EE] is disabled will be "lost" if MSR[EE] remains disabled for between 4.3 and 8.6 seconds after the timer expires. In any case, the decrementer interrupt would be taken at 8.6 seconds and the timer would be found at that point.

So this check is for catching extreme latency events, and it prevents those latencies from being a further few seconds long. It's not obvious this is a good tradeoff. This is already a watchdog magnitude event and that situation is not improved a significantly with this check. For large decrementers, it's useless.

Therefore remove this check, which avoids a mftb when enabling hard disabled interrupts (e.g., when enabling after coming from hardware interrupt handlers). Perhaps more importantly, it also removes the clunky MSR[EE] vs PACA_IRQ_HARD_DIS incoherency in soft-interrupt replay which simplifies the code.

Signed-off-by: Nicholas Piggin npiggin@gmail.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20201107014336.2337337-1-npiggin@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/kernel/irq.c | 53 ++------------------------- arch/powerpc/kernel/time.c | 9 ++--- arch/powerpc/platforms/powernv/opal.c | 2 +- 3 files changed, 8 insertions(+), 56 deletions(-)

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 7d0f7682d01df..6b1eca53e36cc 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -102,14 +102,6 @@ static inline notrace unsigned long get_irq_happened(void) return happened; }

-static inline notrace int decrementer_check_overflow(void) -{ - u64 now = get_tb(); - u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); - - return now >= *next_tb; -} - #ifdef CONFIG_PPC_BOOK3E

/* This is called whenever we are re-enabling interrupts @@ -142,35 +134,6 @@ notrace unsigned int __check_irq_replay(void) trace_hardirqs_on(); trace_hardirqs_off();

- /* - * We are always hard disabled here, but PACA_IRQ_HARD_DIS may - * not be set, which means interrupts have only just been hard - * disabled as part of the local_irq_restore or interrupt return - * code. In that case, skip the decrementr check becaus it's - * expensive to read the TB. - * - * HARD_DIS then gets cleared here, but it's reconciled later. - * Either local_irq_disable will replay the interrupt and that - * will reconcile state like other hard interrupts. Or interrupt - * retur will replay the interrupt and in that case it sets - * PACA_IRQ_HARD_DIS by hand (see comments in entry_64.S). - */ - if (happened & PACA_IRQ_HARD_DIS) { - local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; - - /* - * We may have missed a decrementer interrupt if hard disabled. - * Check the decrementer register in case we had a rollover - * while hard disabled. - */ - if (!(happened & PACA_IRQ_DEC)) { - if (decrementer_check_overflow()) { - local_paca->irq_happened |= PACA_IRQ_DEC; - happened |= PACA_IRQ_DEC; - } - } - } - if (happened & PACA_IRQ_DEC) { local_paca->irq_happened &= ~PACA_IRQ_DEC; return 0x900; @@ -186,6 +149,9 @@ notrace unsigned int __check_irq_replay(void) return 0x280; }

+ if (happened & PACA_IRQ_HARD_DIS) + local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; + /* There should be nothing left ! */ BUG_ON(local_paca->irq_happened != 0);

@@ -229,18 +195,6 @@ void replay_soft_interrupts(void) if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) WARN_ON_ONCE(mfmsr() & MSR_EE);

- if (happened & PACA_IRQ_HARD_DIS) { - /* - * We may have missed a decrementer interrupt if hard disabled. - * Check the decrementer register in case we had a rollover - * while hard disabled. - */ - if (!(happened & PACA_IRQ_DEC)) { - if (decrementer_check_overflow()) - happened |= PACA_IRQ_DEC; - } - } - /* * Force the delivery of pending soft-disabled interrupts on PS3. * Any HV call will have this side effect. @@ -345,6 +299,7 @@ notrace void arch_local_irq_restore(unsigned long mask) if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) WARN_ON_ONCE(!(mfmsr() & MSR_EE)); __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; } else { /* * We should already be hard disabled here. We had bugs diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 74efe46f55327..7d372ff3504b2 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -552,14 +552,11 @@ void timer_interrupt(struct pt_regs *regs) struct pt_regs *old_regs; u64 now;

- /* Some implementations of hotplug will get timer interrupts while - * offline, just ignore these and we also need to set - * decrementers_next_tb as MAX to make sure __check_irq_replay - * don't replay timer interrupt when return, otherwise we'll trap - * here infinitely :( + /* + * Some implementations of hotplug will get timer interrupts while + * offline, just ignore these. */ if (unlikely(!cpu_online(smp_processor_id()))) { - *next_tb = ~(u64)0; set_dec(decrementer_max); return; } diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index d95954ad4c0af..c61c3b62c8c62 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -731,7 +731,7 @@ int opal_hmi_exception_early2(struct pt_regs *regs) return 1; }

-/* HMI exception handler called in virtual mode during check_irq_replay. */ +/* HMI exception handler called in virtual mode when irqs are next enabled. */ int opal_handle_hmi_exception(struct pt_regs *regs) { /*

From: Eric Biggers ebiggers@google.com

[ Upstream commit edf7ddbf1c5eb98b720b063b73e20e8a4a1ce673 ]

Missing calls to mntget() (or equivalently, too many calls to mntput()) are hard to detect because mntput() delays freeing mounts using task_work_add(), then again using call_rcu(). As a result, mnt_count can often be decremented to -1 without getting a KASAN use-after-free report. Such cases are still bugs though, and they point to real use-after-frees being possible.

For an example of this, see the bug fixed by commit 1b0b9cc8d379 ("vfs: fsmount: add missing mntget()"), discussed at https://lkml.kernel.org/linux-fsdevel/20190605135401.GB30925@xxxxxxxxxxxxxxx.... This bug *should* have been trivial to find. But actually, it wasn't found until syzkaller happened to use fchdir() to manipulate the reference count just right for the bug to be noticeable.

Address this by making mntput_no_expire() issue a WARN if mnt_count has become negative.

Suggested-by: Miklos Szeredi miklos@szeredi.hu Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/namespace.c | 9 ++++++--- fs/pnode.h | 2 +- 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c index cebaa3e817940..93006abe7946a 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -156,10 +156,10 @@ static inline void mnt_add_count(struct mount *mnt, int n) /* * vfsmount lock must be held for write */ -unsigned int mnt_get_count(struct mount *mnt) +int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP - unsigned int count = 0; + int count = 0; int cpu;

for_each_possible_cpu(cpu) { @@ -1139,6 +1139,7 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); + int count;

rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { @@ -1162,7 +1163,9 @@ static void mntput_no_expire(struct mount *mnt) */ smp_mb(); mnt_add_count(mnt, -1); - if (mnt_get_count(mnt)) { + count = mnt_get_count(mnt); + if (count != 0) { + WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; diff --git a/fs/pnode.h b/fs/pnode.h index 49a058c73e4c7..26f74e092bd98 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -44,7 +44,7 @@ int propagate_mount_busy(struct mount *, int); void propagate_mount_unlock(struct mount *); void mnt_release_group_id(struct mount *); int get_dominating_id(struct mount *mnt, const struct path *root); -unsigned int mnt_get_count(struct mount *mnt); +int mnt_get_count(struct mount *mnt); void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *); void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,

From: Christopher Obbard chris.obbard@collabora.com

[ Upstream commit 72d3e093afae79611fa38f8f2cfab9a888fe66f2 ]

The UML random driver creates a dummy device under the guest, /dev/hw_random. When this file is read from the guest, the driver reads from the host machine's /dev/random, in-turn reading from the host kernel's entropy pool. This entropy pool could have been filled by a hardware random number generator or just the host kernel's internal software entropy generator.

Currently the driver does not fill the guests kernel entropy pool, this requires a userspace tool running inside the guest (like rng-tools) to read from the dummy device provided by this driver, which then would fill the guest's internal entropy pool.

This all seems quite pointless when we are already reading from an entropy pool, so this patch aims to register the device as a hwrng device using the hwrng-core framework. This not only improves and cleans up the driver, but also fills the guest's entropy pool without having to resort to using extra userspace tools in the guest.

This is typically a nuisance when booting a guest: the random pool takes a long time (~200s) to build up enough entropy since the dummy hwrng is not used to fill the guest's pool.

This port was originally attempted by Alexander Neville "dark" (in CC, discussion in Link), but the conversation there stalled since the handling of -EAGAIN errors were no removed and longer handled by the driver. This patch attempts to use the existing method of error handling but utilises the new hwrng core.

The issue can be noticed when booting a UML guest:

[ 2.560000] random: fast init done [ 214.000000] random: crng init done

With the patch applied, filling the pool becomes a lot quicker:

[ 2.560000] random: fast init done [ 12.000000] random: crng init done

Cc: Alexander Neville dark@volatile.bz Link: https://lore.kernel.org/lkml/20190828204609.02a7ff70@TheDarkness/ Link: https://lore.kernel.org/lkml/20190829135001.6a5ff940@TheDarkness.local/ Cc: Sjoerd Simons sjoerd.simons@collabora.co.uk Signed-off-by: Christopher Obbard chris.obbard@collabora.com Acked-by: Anton Ivanov anton.ivanov@cambridgegreys.com Signed-off-by: Richard Weinberger richard@nod.at Signed-off-by: Sasha Levin sashal@kernel.org --- arch/um/drivers/random.c | 101 ++++++++------------------------- drivers/char/hw_random/Kconfig | 16 +++--- 2 files changed, 33 insertions(+), 84 deletions(-)

diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c index ce115fce52f02..e4b9b2ce9abf4 100644 --- a/arch/um/drivers/random.c +++ b/arch/um/drivers/random.c @@ -11,6 +11,7 @@ #include <linux/fs.h> #include <linux/interrupt.h> #include <linux/miscdevice.h> +#include <linux/hw_random.h> #include <linux/delay.h> #include <linux/uaccess.h> #include <init.h> @@ -18,9 +19,8 @@ #include <os.h>

/* - * core module and version information + * core module information */ -#define RNG_VERSION "1.0.0" #define RNG_MODULE_NAME "hw_random"

/* Changed at init time, in the non-modular case, and at module load @@ -28,88 +28,36 @@ * protects against a module being loaded twice at the same time. */ static int random_fd = -1; -static DECLARE_WAIT_QUEUE_HEAD(host_read_wait); +static struct hwrng hwrng = { 0, }; +static DECLARE_COMPLETION(have_data);

-static int rng_dev_open (struct inode *inode, struct file *filp) +static int rng_dev_read(struct hwrng *rng, void *buf, size_t max, bool block) { - /* enforce read-only access to this chrdev */ - if ((filp->f_mode & FMODE_READ) == 0) - return -EINVAL; - if ((filp->f_mode & FMODE_WRITE) != 0) - return -EINVAL; + int ret;

- return 0; -} - -static atomic_t host_sleep_count = ATOMIC_INIT(0); - -static ssize_t rng_dev_read (struct file *filp, char __user *buf, size_t size, - loff_t *offp) -{ - u32 data; - int n, ret = 0, have_data; - - while (size) { - n = os_read_file(random_fd, &data, sizeof(data)); - if (n > 0) { - have_data = n; - while (have_data && size) { - if (put_user((u8) data, buf++)) { - ret = ret ? : -EFAULT; - break; - } - size--; - ret++; - have_data--; - data >>= 8; - } - } - else if (n == -EAGAIN) { - DECLARE_WAITQUEUE(wait, current); - - if (filp->f_flags & O_NONBLOCK) - return ret ? : -EAGAIN; - - atomic_inc(&host_sleep_count); + for (;;) { + ret = os_read_file(random_fd, buf, max); + if (block && ret == -EAGAIN) { add_sigio_fd(random_fd);

- add_wait_queue(&host_read_wait, &wait); - set_current_state(TASK_INTERRUPTIBLE); + ret = wait_for_completion_killable(&have_data);

- schedule(); - remove_wait_queue(&host_read_wait, &wait); + ignore_sigio_fd(random_fd); + deactivate_fd(random_fd, RANDOM_IRQ);

- if (atomic_dec_and_test(&host_sleep_count)) { - ignore_sigio_fd(random_fd); - deactivate_fd(random_fd, RANDOM_IRQ); - } + if (ret < 0) + break; + } else { + break; } - else - return n; - - if (signal_pending (current)) - return ret ? : -ERESTARTSYS; } - return ret; -}

-static const struct file_operations rng_chrdev_ops = { - .owner = THIS_MODULE, - .open = rng_dev_open, - .read = rng_dev_read, - .llseek = noop_llseek, -}; - -/* rng_init shouldn't be called more than once at boot time */ -static struct miscdevice rng_miscdev = { - HWRNG_MINOR, - RNG_MODULE_NAME, - &rng_chrdev_ops, -}; + return ret != -EAGAIN ? ret : 0; +}

static irqreturn_t random_interrupt(int irq, void *data) { - wake_up(&host_read_wait); + complete(&have_data);

return IRQ_HANDLED; } @@ -126,18 +74,19 @@ static int __init rng_init (void) goto out;

random_fd = err; - err = um_request_irq(RANDOM_IRQ, random_fd, IRQ_READ, random_interrupt, 0, "random", NULL); if (err) goto err_out_cleanup_hw;

sigio_broken(random_fd, 1); + hwrng.name = RNG_MODULE_NAME; + hwrng.read = rng_dev_read; + hwrng.quality = 1024;

- err = misc_register (&rng_miscdev); + err = hwrng_register(&hwrng); if (err) { - printk (KERN_ERR RNG_MODULE_NAME ": misc device register " - "failed\n"); + pr_err(RNG_MODULE_NAME " registering failed (%d)\n", err); goto err_out_cleanup_hw; } out: @@ -161,8 +110,8 @@ static void cleanup(void)

static void __exit rng_cleanup(void) { + hwrng_unregister(&hwrng); os_close_file(random_fd); - misc_deregister (&rng_miscdev); }

module_init (rng_init); diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig index e92c4d9469d82..5952210526aaa 100644 --- a/drivers/char/hw_random/Kconfig +++ b/drivers/char/hw_random/Kconfig @@ -540,15 +540,15 @@ endif # HW_RANDOM

config UML_RANDOM depends on UML - tristate "Hardware random number generator" + select HW_RANDOM + tristate "UML Random Number Generator support" help This option enables UML's "hardware" random number generator. It attaches itself to the host's /dev/random, supplying as much entropy as the host has, rather than the small amount the UML gets from its - own drivers. It registers itself as a standard hardware random number - generator, major 10, minor 183, and the canonical device name is - /dev/hwrng. - The way to make use of this is to install the rng-tools package - (check your distro, or download from - http://sourceforge.net/projects/gkernel/). rngd periodically reads - /dev/hwrng and injects the entropy into /dev/random. + own drivers. It registers itself as a rng-core driver thus providing + a device which is usually called /dev/hwrng. This hardware random + number generator does feed into the kernel's random number generator + entropy pool. + + If unsure, say Y.

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit ef4459a6da0955b533ebfc97a7d756ac090f50c9 ]

We've been running into stack overflows in helper threads corrupting memory (e.g. because somebody put printf() or os_info() there), so to avoid those causing hard-to-debug issues later on, allocate a guard page for helper thread stacks and mark it read-only.

Unfortunately, the crash dump at that point is useless as the stack tracer will try to backtrace the *kernel* thread, not the helper thread, but at least we don't survive to a random issue caused by corruption.

Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Richard Weinberger richard@nod.at Signed-off-by: Sasha Levin sashal@kernel.org --- arch/um/drivers/ubd_kern.c | 2 +- arch/um/include/shared/kern_util.h | 2 +- arch/um/kernel/process.c | 11 +++++++---- arch/um/os-Linux/helper.c | 4 ++-- 4 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index b12c1b0d3e1d0..e337702c30c78 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1195,7 +1195,7 @@ static int __init ubd_driver_init(void){ /* Letting ubd=sync be like using ubd#s= instead of ubd#= is * enough. So use anyway the io thread. */ } - stack = alloc_stack(0, 0); + stack = alloc_stack(0); io_pid = start_io_thread(stack + PAGE_SIZE - sizeof(void *), &thread_fd); if(io_pid < 0){ diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index ccafb62e8ccec..c3ccbc2bbd2ce 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -19,7 +19,7 @@ extern int kmalloc_ok; #define UML_ROUND_UP(addr) \ ((((unsigned long) addr) + PAGE_SIZE - 1) & PAGE_MASK)

-extern unsigned long alloc_stack(int order, int atomic); +extern unsigned long alloc_stack(int atomic); extern void free_stack(unsigned long stack, int order);

struct pt_regs; diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 9505a7e87396a..bb352dc446870 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -32,6 +32,7 @@ #include <os.h> #include <skas.h> #include <linux/time-internal.h> +#include <asm/set_memory.h>

/* * This is a per-cpu array. A processor only modifies its entry and it only @@ -62,16 +63,18 @@ void free_stack(unsigned long stack, int order) free_pages(stack, order); }

-unsigned long alloc_stack(int order, int atomic) +unsigned long alloc_stack(int atomic) { - unsigned long page; + unsigned long addr; gfp_t flags = GFP_KERNEL;

if (atomic) flags = GFP_ATOMIC; - page = __get_free_pages(flags, order); + addr = __get_free_pages(flags, 1);

- return page; + set_memory_ro(addr, 1); + + return addr + PAGE_SIZE; }

static inline void set_current(struct task_struct *task) diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index 9fa6e4187d4fb..feb48d796e005 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -45,7 +45,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) unsigned long stack, sp; int pid, fds[2], ret, n;

- stack = alloc_stack(0, __cant_sleep()); + stack = alloc_stack(__cant_sleep()); if (stack == 0) return -ENOMEM;

@@ -116,7 +116,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, unsigned long stack, sp; int pid, status, err;

- stack = alloc_stack(0, __cant_sleep()); + stack = alloc_stack(__cant_sleep()); if (stack == 0) return -ENOMEM;

From: Jeff Layton jlayton@kernel.org

[ Upstream commit 68cbb8056a4c24c6a38ad2b79e0a9764b235e8fa ]

Signed-off-by: Jeff Layton jlayton@kernel.org Reviewed-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ceph/inode.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 526faf4778ce4..2462a9a84b956 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1335,6 +1335,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) in, ceph_vinop(in)); if (in->i_state & I_NEW) discard_new_inode(in); + else + iput(in); goto done; } req->r_target_inode = in;

From: Thomas Gleixner tglx@linutronix.de

[ Upstream commit ba8ea8e7dd6e1662e34e730eadfc52aa6816f9dd ]

can_stop_idle_tick() checks whether the do_timer() duty has been taken over by a CPU on boot. That's silly because the boot CPU always takes over with the initial clockevent device.

But even if no CPU would have installed a clockevent and taken over the duty then the question whether the tick on the current CPU can be stopped or not is moot. In that case the current CPU would have no clockevent either, so there would be nothing to keep ticking.

Remove it.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Frederic Weisbecker frederic@kernel.org Link: https://lore.kernel.org/r/20201206212002.725238293@linutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/time/tick-sched.c | 7 ------- 1 file changed, 7 deletions(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 81632cd5e3b72..e8d351b7f9b03 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -941,13 +941,6 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) */ if (tick_do_timer_cpu == cpu) return false; - /* - * Boot safety: make sure the timekeeping duty has been - * assigned before entering dyntick-idle mode, - * tick_do_timer_cpu is TICK_DO_TIMER_BOOT - */ - if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_BOOT)) - return false;

/* Should not happen for nohz-full */ if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit 9cd2be519d05ee78876d55e8e902b7125f78b74f ]

list_empty_careful() is not racy only if some conditions are met, i.e. no re-adds after del_init. io_cqring_overflow_flush() does list_move(), so it's actually racy.

Remove those checks, we have ->cq_check_overflow for the fast path.

Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/io_uring.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c index 86dac2b2e2763..4b3dbe588d111 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1632,8 +1632,6 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, LIST_HEAD(list);

if (!force) { - if (list_empty_careful(&ctx->cq_overflow_list)) - return true; if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) == rings->cq_ring_entries)) return false; @@ -6548,8 +6546,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)

/* if we have a backlog and couldn't flush it all, return BUSY */ if (test_bit(0, &ctx->sq_check_overflow)) { - if (!list_empty(&ctx->cq_overflow_list) && - !io_cqring_overflow_flush(ctx, false, NULL, NULL)) + if (!io_cqring_overflow_flush(ctx, false, NULL, NULL)) return -EBUSY; }

From: Takashi Iwai tiwai@suse.de

[ Upstream commit 618de0f4ef11acd8cf26902e65493d46cc20cc89 ]

The PCM hw_params core function tries to clear up the PCM buffer before actually using for avoiding the information leak from the previous usages or the usage before a new allocation. It performs the memset() with runtime->dma_bytes, but this might still leave some remaining bytes untouched; namely, the PCM buffer size is aligned in page size for mmap, hence runtime->dma_bytes doesn't necessarily cover all PCM buffer pages, and the remaining bytes are exposed via mmap.

This patch changes the memory clearance to cover the all buffer pages if the stream is supposed to be mmap-ready (that guarantees that the buffer size is aligned in page size).

Reviewed-by: Lars-Peter Clausen lars@metafoo.de Link: https://lore.kernel.org/r/20201218145625.2045-3-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/core/pcm_native.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 47b155a49226f..9f3f8e953ff04 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -755,8 +755,13 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream, runtime->boundary *= 2;

/* clear the buffer for avoiding possible kernel info leaks */ - if (runtime->dma_area && !substream->ops->copy_user) - memset(runtime->dma_area, 0, runtime->dma_bytes); + if (runtime->dma_area && !substream->ops->copy_user) { + size_t size = runtime->dma_bytes; + + if (runtime->info & SNDRV_PCM_INFO_MMAP) + size = PAGE_ALIGN(size); + memset(runtime->dma_area, 0, size); + }

snd_pcm_timer_resolution_change(substream); snd_pcm_set_state(substream, SNDRV_PCM_STATE_SETUP);

From: Chunguang Xu brookxu@tencent.com

[ Upstream commit 82ef1370b0c1757ab4ce29f34c52b4e93839b0aa ]

Commit cfd732377221 ("ext4: add prefetching for block allocation bitmaps") introduced block bitmap prefetch, and expects to read block bitmaps of flex_bg through an IO. However, it seems to ignore the value range of s_log_groups_per_flex. In the scenario where the value of s_log_groups_per_flex is greater than 27, s_mb_prefetch or s_mb_prefetch_limit will overflow, cause a divide zero exception.

In addition, the logic of calculating nr is also flawed, because the size of flexbg is fixed during a single mount, but s_mb_prefetch can be modified, which causes nr to fail to meet the value condition of [1, flexbg_size].

To solve this problem, we need to set the upper limit of s_mb_prefetch. Since we expect to load block bitmaps of a flex_bg through an IO, we can consider determining a reasonable upper limit among the IO limit parameters. After consideration, we chose BLK_MAX_SEGMENT_SIZE. This is a good choice to solve divide zero problem and avoiding performance degradation.

[ Some minor code simplifications to make the changes easy to follow -- TYT ]

Reported-by: Tosk Robot tencent_os_robot@tencent.com Signed-off-by: Chunguang Xu brookxu@tencent.com Reviewed-by: Samuel Liao samuelliao@tencent.com Reviewed-by: Andreas Dilger adilger@dilger.ca Link: https://lore.kernel.org/r/1607051143-24508-1-git-send-email-brookxu@tencent.... Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/mballoc.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 24af9ed5c3e52..ca57c6bfee224 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2395,9 +2395,9 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)

nr = sbi->s_mb_prefetch; if (ext4_has_feature_flex_bg(sb)) { - nr = (group / sbi->s_mb_prefetch) * - sbi->s_mb_prefetch; - nr = nr + sbi->s_mb_prefetch - group; + nr = 1 << sbi->s_log_groups_per_flex; + nr -= group & (nr - 1); + nr = min(nr, sbi->s_mb_prefetch); } prefetch_grp = ext4_mb_prefetch(sb, group, nr, &prefetch_ios); @@ -2733,7 +2733,8 @@ static int ext4_mb_init_backend(struct super_block *sb)

if (ext4_has_feature_flex_bg(sb)) { /* a single flex group is supposed to be read by a single IO */ - sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex; + sbi->s_mb_prefetch = min(1 << sbi->s_es->s_log_groups_per_flex, + BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9)); sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ } else { sbi->s_mb_prefetch = 32;

Hello Sasha,

On 30.12.20 14:02, Sasha Levin wrote:

From: Linus Walleij linus.walleij@linaro.org

[ Upstream commit d6d51a96c7d63b7450860a3037f2d62388286a52 ]

Functions like memset()/memmove()/memcpy() do a lot of memory accesses.

If a bad pointer is passed to one of these functions it is important to catch this. Compiler instrumentation cannot do this since these functions are written in assembly.

KASan replaces these memory functions with instrumented variants.

Unless someone actually wants this, I suggest dropping it.

It's a prerequisite patch for KASan support on ARM32, which is new in v5.11-rc1. Backporting it on its own doesn't add any value IMO.

Cheers Ahmad

The original functions are declared as weak symbols so that the strong definitions in mm/kasan/kasan.c can replace them.

The original functions have aliases with a '__' prefix in their name, so we can call the non-instrumented variant if needed.

We must use __memcpy()/__memset() in place of memcpy()/memset() when we copy .data to RAM and when we clear .bss, because kasan_early_init cannot be called before the initialization of .data and .bss.

For the kernel compression and EFI libstub's custom string libraries we need a special quirk: even if these are built without KASan enabled, they rely on the global headers for their custom string libraries, which means that e.g. memcpy() will be defined to __memcpy() and we get link failures. Since these implementations are written i C rather than assembly we use e.g. __alias(memcpy) to redirected any users back to the local implementation.

Cc: Andrey Ryabinin aryabinin@virtuozzo.com Cc: Alexander Potapenko glider@google.com Cc: Dmitry Vyukov dvyukov@google.com Cc: kasan-dev@googlegroups.com Reviewed-by: Ard Biesheuvel ardb@kernel.org Tested-by: Ard Biesheuvel ardb@kernel.org # QEMU/KVM/mach-virt/LPAE/8G Tested-by: Florian Fainelli f.fainelli@gmail.com # Brahma SoCs Tested-by: Ahmad Fatoum a.fatoum@pengutronix.de # i.MX6Q Reported-by: Russell King - ARM Linux rmk+kernel@armlinux.org.uk Signed-off-by: Ahmad Fatoum a.fatoum@pengutronix.de Signed-off-by: Abbott Liu liuwenliang@huawei.com Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org

---

arch/arm/boot/compressed/string.c | 19 +++++++++++++++++++ arch/arm/include/asm/string.h | 26 ++++++++++++++++++++++++++ arch/arm/kernel/head-common.S | 4 ++-- arch/arm/lib/memcpy.S | 3 +++ arch/arm/lib/memmove.S | 5 ++++- arch/arm/lib/memset.S | 3 +++ 6 files changed, 57 insertions(+), 3 deletions(-)

diff --git a/arch/arm/boot/compressed/string.c b/arch/arm/boot/compressed/string.c index ade5079bebbf9..8c0fa276d9946 100644 --- a/arch/arm/boot/compressed/string.c +++ b/arch/arm/boot/compressed/string.c @@ -7,6 +7,25 @@ #include <linux/string.h> +/*

• • The decompressor is built without KASan but uses the same redirects as the
• • rest of the kernel when CONFIG_KASAN is enabled, defining e.g. memcpy()
• • to __memcpy() but since we are not linking with the main kernel string
• • library in the decompressor, that will lead to link failures.
• • Undefine KASan's versions, define the wrapped functions and alias them to
• • the right names so that when e.g. __memcpy() appear in the code, it will
• • still be linked to this local version of memcpy().
• */

+#ifdef CONFIG_KASAN +#undef memcpy +#undef memmove +#undef memset +void *__memcpy(void *__dest, __const void *__src, size_t __n) __alias(memcpy); +void *__memmove(void *__dest, __const void *__src, size_t count) __alias(memmove); +void *__memset(void *s, int c, size_t count) __alias(memset); +#endif

void *memcpy(void *__dest, __const void *__src, size_t __n) { int i = 0; diff --git a/arch/arm/include/asm/string.h b/arch/arm/include/asm/string.h index 111a1d8a41ddf..6c607c68f3ad7 100644 --- a/arch/arm/include/asm/string.h +++ b/arch/arm/include/asm/string.h @@ -5,6 +5,9 @@ /*

• We don't do inline string functions, since the
• optimised inline asm versions are not small.

• • The __underscore versions of some functions are for KASan to be able
• • to replace them with instrumented versions.
  */

#define __HAVE_ARCH_STRRCHR @@ -15,15 +18,18 @@ extern char * strchr(const char * s, int c); #define __HAVE_ARCH_MEMCPY extern void * memcpy(void *, const void *, __kernel_size_t); +extern void *__memcpy(void *dest, const void *src, __kernel_size_t n); #define __HAVE_ARCH_MEMMOVE extern void * memmove(void *, const void *, __kernel_size_t); +extern void *__memmove(void *dest, const void *src, __kernel_size_t n); #define __HAVE_ARCH_MEMCHR extern void * memchr(const void *, int, __kernel_size_t); #define __HAVE_ARCH_MEMSET extern void * memset(void *, int, __kernel_size_t); +extern void *__memset(void *s, int c, __kernel_size_t n); #define __HAVE_ARCH_MEMSET32 extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t); @@ -39,4 +45,24 @@ static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n) return __memset64(p, v, n * 8, v >> 32); } +/*

• • For files that are not instrumented (e.g. mm/slub.c) we
• • must use non-instrumented versions of the mem*
• • functions named __memcpy() etc. All such kernel code has
• • been tagged with KASAN_SANITIZE_file.o = n, which means
• • that the address sanitization argument isn't passed to the
• • compiler, and __SANITIZE_ADDRESS__ is not set. As a result
• • these defines kick in.
• */

+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) +#define memcpy(dst, src, len) __memcpy(dst, src, len) +#define memmove(dst, src, len) __memmove(dst, src, len) +#define memset(s, c, n) __memset(s, c, n)

+#ifndef __NO_FORTIFY +#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ +#endif

+#endif

#endif diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index 4a3982812a401..6840c7c60a858 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -95,7 +95,7 @@ __mmap_switched: THUMB( ldmia r4!, {r0, r1, r2, r3} ) THUMB( mov sp, r3 ) sub r2, r2, r1

• bl memcpy @ copy .data to RAM

• bl __memcpy @ copy .data to RAM

#endif ARM( ldmia r4!, {r0, r1, sp} ) @@ -103,7 +103,7 @@ __mmap_switched: THUMB( mov sp, r3 ) sub r2, r1, r0 mov r1, #0

• bl memset @ clear .bss

• bl __memset @ clear .bss

ldmia r4, {r0, r1, r2, r3} str r9, [r0] @ Save processor ID diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S index 09a333153dc66..ad4625d16e117 100644 --- a/arch/arm/lib/memcpy.S +++ b/arch/arm/lib/memcpy.S @@ -58,6 +58,8 @@ /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */ +.weak memcpy +ENTRY(__memcpy) ENTRY(mmiocpy) ENTRY(memcpy) @@ -65,3 +67,4 @@ ENTRY(memcpy) ENDPROC(memcpy) ENDPROC(mmiocpy) +ENDPROC(__memcpy) diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S index b50e5770fb44d..fd123ea5a5a4a 100644 --- a/arch/arm/lib/memmove.S +++ b/arch/arm/lib/memmove.S @@ -24,12 +24,14 @@

• occurring in the opposite direction.

*/ +.weak memmove +ENTRY(__memmove) ENTRY(memmove) UNWIND( .fnstart ) subs ip, r0, r1 cmphi r2, ip

• bls	memcpy
  

• bls	__memcpy
  

stmfd sp!, {r0, r4, lr} UNWIND( .fnend ) @@ -222,3 +224,4 @@ ENTRY(memmove) 18: backward_copy_shift push=24 pull=8 ENDPROC(memmove) +ENDPROC(__memmove) diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S index 6ca4535c47fb6..0e7ff0423f50b 100644 --- a/arch/arm/lib/memset.S +++ b/arch/arm/lib/memset.S @@ -13,6 +13,8 @@ .text .align 5 +.weak memset +ENTRY(__memset) ENTRY(mmioset) ENTRY(memset) UNWIND( .fnstart ) @@ -132,6 +134,7 @@ UNWIND( .fnstart ) UNWIND( .fnend ) ENDPROC(memset) ENDPROC(mmioset) +ENDPROC(__memset) ENTRY(__memset32) UNWIND( .fnstart )