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

FAILED: patch "[PATCH] mptcp: fix rcv space initialization" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 013e3179dbd2bc756ce1dd90354abac62f65b739 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021902-cleft-esquire-a9ae@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 013e3179dbd2 ("mptcp: fix rcv space initialization") 4fd19a307016 ("mptcp: fix inconsistent state on fastopen race") d109a7767273 ("mptcp: fix possible NULL pointer dereference on close") 8005184fd1ca ("mptcp: refactor sndbuf auto-tuning") a5efdbcece83 ("mptcp: fix delegated action races") 27e5ccc2d5a5 ("mptcp: fix dangling connection hang-up") f6909dc1c1f4 ("mptcp: rename timer related helper to less confusing names") ebc1e08f01eb ("mptcp: drop last_snd and MPTCP_RESET_SCHEDULER") e263691773cd ("mptcp: Remove unnecessary test for __mptcp_init_sock()") 39880bd808ad ("mptcp: get rid of msk->subflow") 17ebf8a4c38b ("mptcp: fix the incorrect judgment for msk->cb_flags") a7384f391875 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 013e3179dbd2bc756ce1dd90354abac62f65b739 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Thu, 8 Feb 2024 19:03:50 +0100 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> 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);

1 year, 8 months

2
1
0 0

[PATCH 5.15 1/2] ext4: regenerate buddy after block freeing failed if under fc replay

by Baokun Li

commit c9b528c35795b711331ed36dc3dbee90d5812d4e upstream. This mostly reverts commit 6bd97bf273bd ("ext4: remove redundant mb_regenerate_buddy()") and reintroduces mb_regenerate_buddy(). Based on code in mb_free_blocks(), fast commit replay can end up marking as free blocks that are already marked as such. This causes corruption of the buddy bitmap so we need to regenerate it in that case. Reported-by: Jan Kara <jack(a)suse.cz> Fixes: 6bd97bf273bd ("ext4: remove redundant mb_regenerate_buddy()") CVE: CVE-2024-26601 Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240104142040.2835097-4-libaokun1@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/mballoc.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 762c2f8b5b2a..63e4c3b9e608 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1168,6 +1168,24 @@ void ext4_mb_generate_buddy(struct super_block *sb, mb_update_avg_fragment_size(sb, grp); } +static void mb_regenerate_buddy(struct ext4_buddy *e4b) +{ + int count; + int order = 1; + void *buddy; + + while ((buddy = mb_find_buddy(e4b, order++, &count))) + ext4_set_bits(buddy, 0, count); + + e4b->bd_info->bb_fragments = 0; + memset(e4b->bd_info->bb_counters, 0, + sizeof(*e4b->bd_info->bb_counters) * + (e4b->bd_sb->s_blocksize_bits + 2)); + + ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, + e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); +} + /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -1846,6 +1864,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, ext4_mark_group_bitmap_corrupted( sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); + } else { + mb_regenerate_buddy(e4b); } goto done; } -- 2.31.1

1 year, 8 months

2
4
0 0

[PATCH v2 1/3] rust: make mutually exclusive with CFI_CLANG

by Conor Dooley

From: Conor Dooley <conor.dooley(a)microchip.com> On RISC-V, and presumably x86/arm64, if CFI_CLANG is enabled loading a rust module will trigger a kernel panic. Support for sanitisers, including kcfi (CFI_CLANG), is in the works, but for now they're nightly-only options in rustc. Make RUST depend on !CFI_CLANG to prevent configuring a kernel without symmetrical support for kfi. Fixes: 2f7ab1267dc9 ("Kbuild: add Rust support") cc: stable(a)vger.kernel.org Signed-off-by: Conor Dooley <conor.dooley(a)microchip.com> --- This probably needs to go to stable. The correct fixes tag for that I am not sure of however, but since CFI_CLANG predates RUST, I blamed the commit adding rust support. --- init/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/init/Kconfig b/init/Kconfig index 8d4e836e1b6b..6cf05824859e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1895,6 +1895,7 @@ config RUST bool "Rust support" depends on HAVE_RUST depends on RUST_IS_AVAILABLE + depends on !CFI_CLANG depends on !MODVERSIONS depends on !GCC_PLUGINS depends on !RANDSTRUCT -- 2.43.0

1 year, 8 months

3
5
0 0

FAILED: patch "[PATCH] mptcp: add needs_id for netlink appending addr" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 584f3894262634596532cf43a5e782e34a0ce374 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022654-senate-unleaded-7ae3@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: 584f38942626 ("mptcp: add needs_id for netlink appending addr") aab4d8564947 ("net: mptcp: use policy generated by YAML spec") 1e07938e29c5 ("net: mptcp: rename netlink handlers to mptcp_pm_nl_<blah>_{doit,dumpit}") 1d0507f46843 ("net: mptcp: convert netlink from small_ops to ops") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 584f3894262634596532cf43a5e782e34a0ce374 Mon Sep 17 00:00:00 2001 From: Geliang Tang <tanggeliang(a)kylinos.cn> Date: Thu, 15 Feb 2024 19:25:29 +0100 Subject: [PATCH] mptcp: add needs_id for netlink appending addr Just the same as userspace PM, a new parameter needs_id is added for in-kernel PM mptcp_pm_nl_append_new_local_addr() too. Add a new helper mptcp_pm_has_addr_attr_id() to check whether an address ID is set from PM or not. In mptcp_pm_nl_get_local_id(), needs_id is always true, but in mptcp_pm_nl_add_addr_doit(), pass mptcp_pm_has_addr_attr_id() to needs_it. Fixes: efd5a4c04e18 ("mptcp: add the address ID assignment bitmap") Cc: stable(a)vger.kernel.org Signed-off-by: Geliang Tang <tanggeliang(a)kylinos.cn> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 287a60381eae..a24c9128dee9 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -901,7 +901,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) } static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; @@ -949,7 +950,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id) { + if (!entry->addr.id && needs_id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, @@ -960,7 +961,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id) + if (!entry->addr.id && needs_id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); @@ -1092,7 +1093,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc entry->ifindex = 0; entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); if (ret < 0) kfree(entry); @@ -1285,6 +1286,18 @@ static int mptcp_nl_add_subflow_or_signal_addr(struct net *net) return 0; } +static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr, + struct genl_info *info) +{ + struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; + + if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, + mptcp_pm_address_nl_policy, info->extack) && + tb[MPTCP_PM_ADDR_ATTR_ID]) + return true; + return false; +} + int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; @@ -1326,7 +1339,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) goto out_free; } } - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, + !mptcp_pm_has_addr_attr_id(attr, info)); if (ret < 0) { GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); goto out_free;

1 year, 8 months

4
5
0 0

[PATCH 5.10 1/2] ext4: regenerate buddy after block freeing failed if under fc replay

by Baokun Li

commit c9b528c35795b711331ed36dc3dbee90d5812d4e upstream. This mostly reverts commit 6bd97bf273bd ("ext4: remove redundant mb_regenerate_buddy()") and reintroduces mb_regenerate_buddy(). Based on code in mb_free_blocks(), fast commit replay can end up marking as free blocks that are already marked as such. This causes corruption of the buddy bitmap so we need to regenerate it in that case. Reported-by: Jan Kara <jack(a)suse.cz> Fixes: 6bd97bf273bd ("ext4: remove redundant mb_regenerate_buddy()") CVE: CVE-2024-26601 Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240104142040.2835097-4-libaokun1@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/mballoc.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 9bec75847b85..5799706e20cc 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -823,6 +823,24 @@ void ext4_mb_generate_buddy(struct super_block *sb, atomic64_add(period, &sbi->s_mb_generation_time); } +static void mb_regenerate_buddy(struct ext4_buddy *e4b) +{ + int count; + int order = 1; + void *buddy; + + while ((buddy = mb_find_buddy(e4b, order++, &count))) + ext4_set_bits(buddy, 0, count); + + e4b->bd_info->bb_fragments = 0; + memset(e4b->bd_info->bb_counters, 0, + sizeof(*e4b->bd_info->bb_counters) * + (e4b->bd_sb->s_blocksize_bits + 2)); + + ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, + e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); +} + /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -1505,6 +1523,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, ext4_mark_group_bitmap_corrupted( sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); + } else { + mb_regenerate_buddy(e4b); } goto done; } -- 2.31.1

1 year, 8 months

1
1
0 0

FAILED: patch "[PATCH] memcg: fix use-after-free in uncharge_batch" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x f1796544a0ca0f14386a679d3d05fbc69235015e # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022702-ignition-astonish-a4f1@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: f1796544a0ca ("memcg: fix use-after-free in uncharge_batch") 1a3e1f40962c ("mm: memcontrol: decouple reference counting from page accounting") 8d22a9351035 ("mm/memcg: fix refcount error while moving and swapping") d9eb1ea2bf87 ("mm: memcontrol: delete unused lrucare handling") 4c6355b25e8b ("mm: memcontrol: charge swapin pages on instantiation") f0e45fb4da29 ("mm: memcontrol: drop unused try/commit/cancel charge API") 9d82c69438d0 ("mm: memcontrol: convert anon and file-thp to new mem_cgroup_charge() API") 468c398233da ("mm: memcontrol: switch to native NR_ANON_THPS counter") be5d0a74c62d ("mm: memcontrol: switch to native NR_ANON_MAPPED counter") 0d1c20722ab3 ("mm: memcontrol: switch to native NR_FILE_PAGES and NR_SHMEM counters") 49e50d277ba2 ("mm: memcontrol: prepare move_account for removal of private page type counters") 9f762dbe19b9 ("mm: memcontrol: prepare uncharging for removal of private page type counters") 3fea5a499d57 ("mm: memcontrol: convert page cache to a new mem_cgroup_charge() API") 6caa6a0703e0 ("mm: memcontrol: move out cgroup swaprate throttling") 14235ab36019 ("mm: shmem: remove rare optimization when swapin races with hole punching") 3fba69a56e16 ("mm: memcontrol: drop @compound parameter from memcg charging API") abb242f57196 ("mm: memcontrol: fix stat-corrupting race in charge moving") f4129ea3591a ("mm: fix NUMA node file count error in replace_page_cache()") ffe945e633b5 ("khugepaged: do not stop collapse if less than half PTEs are referenced") 396bcc5299c2 ("mm: remove CONFIG_TRANSPARENT_HUGE_PAGECACHE") 85b9f46e8ea4 ("mm, thp: track fallbacks due to failed memcg charges separately") dcdf11ee1441 ("mm, shmem: add vmstat for hugepage fallback") 9c315e4d7d8c ("mm: memcg/slab: cache page number in memcg_(un)charge_slab()") 92d0510c3585 ("mm: kmem: switch to nr_pages in (__)memcg_kmem_charge_memcg()") f4b00eab5004 ("mm: kmem: rename memcg_kmem_(un)charge() into memcg_kmem_(un)charge_page()") 50591183fa86 ("mm: kmem: cleanup memcg_kmem_uncharge_memcg() arguments") 10eaec2f63b6 ("mm: kmem: cleanup (__)memcg_kmem_charge_memcg() arguments") 47e29d32afba ("mm/gup: page->hpage_pinned_refcount: exact pin counts for huge pages") 3faa52c03f44 ("mm/gup: track FOLL_PIN pages") 3b78d8347d31 ("mm/gup: pass gup flags to two more routines") c23a0c99793f ("mm/migrate: clean up some minor coding style") 92855270ff08 ("mm/memcontrol.c: cleanup some useless code") f1f6a7dd9b53 ("mm, tree-wide: rename put_user_page*() to unpin_user_page*()") aa4b87fe9ea3 ("powerpc: book3s64: convert to pin_user_pages() and put_user_page()") 19fed0dae94d ("vfio, mm: pin_user_pages (FOLL_PIN) and put_user_page() conversion") 1f815afcfca7 ("media/v4l2-core: pin_user_pages (FOLL_PIN) and put_user_page() conversion") 803e4572d7c5 ("mm/process_vm_access: set FOLL_PIN via pin_user_pages_remote()") 57459435cff5 ("goldish_pipe: convert to pin_user_pages() and put_user_page()") eddb1c228f79 ("mm/gup: introduce pin_user_pages*() and FOLL_PIN") 3c7470b6f684 ("media/v4l2-core: set pages dirty upon releasing DMA buffers") f4000fdf435b ("mm/gup: allow FOLL_FORCE for get_user_pages_fast()") 3567813eae5e ("vfio: fix FOLL_LONGTERM use, simplify get_user_pages_remote() call") c4237f8b1f4f ("mm: fix get_user_pages_remote()'s handling of FOLL_LONGTERM") a707cdd55f0f ("mm/gup: move try_get_compound_head() to top, fix minor issues") a43e982082c2 ("mm/gup: factor out duplicate code from four routines") fac0516b5534 ("mm: thp: don't need care deferred split queue in memcg charge move path") f1fe80d4ae33 ("mm, thp: do not queue fully unmapped pages for deferred split") acbfb087e3b1 ("mm/hugetlb: avoid looping to the same hugepage if !pages and !vmas") 867e5e1de14b ("mm: clean up and clarify lruvec lookup procedure") 242c37b459ce ("include/linux/memcontrol.h: fix comments based on per-node memcg") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f1796544a0ca0f14386a679d3d05fbc69235015e Mon Sep 17 00:00:00 2001 From: Michal Hocko <mhocko(a)suse.com> Date: Fri, 4 Sep 2020 16:35:24 -0700 Subject: [PATCH] memcg: fix use-after-free in uncharge_batch syzbot has reported an use-after-free in the uncharge_batch path BUG: KASAN: use-after-free in instrument_atomic_write include/linux/instrumented.h:71 [inline] BUG: KASAN: use-after-free in atomic64_sub_return include/asm-generic/atomic-instrumented.h:970 [inline] BUG: KASAN: use-after-free in atomic_long_sub_return include/asm-generic/atomic-long.h:113 [inline] BUG: KASAN: use-after-free in page_counter_cancel mm/page_counter.c:54 [inline] BUG: KASAN: use-after-free in page_counter_uncharge+0x3d/0xc0 mm/page_counter.c:155 Write of size 8 at addr ffff8880371c0148 by task syz-executor.0/9304 CPU: 0 PID: 9304 Comm: syz-executor.0 Not tainted 5.8.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1f0/0x31e lib/dump_stack.c:118 print_address_description+0x66/0x620 mm/kasan/report.c:383 __kasan_report mm/kasan/report.c:513 [inline] kasan_report+0x132/0x1d0 mm/kasan/report.c:530 check_memory_region_inline mm/kasan/generic.c:183 [inline] check_memory_region+0x2b5/0x2f0 mm/kasan/generic.c:192 instrument_atomic_write include/linux/instrumented.h:71 [inline] atomic64_sub_return include/asm-generic/atomic-instrumented.h:970 [inline] atomic_long_sub_return include/asm-generic/atomic-long.h:113 [inline] page_counter_cancel mm/page_counter.c:54 [inline] page_counter_uncharge+0x3d/0xc0 mm/page_counter.c:155 uncharge_batch+0x6c/0x350 mm/memcontrol.c:6764 uncharge_page+0x115/0x430 mm/memcontrol.c:6796 uncharge_list mm/memcontrol.c:6835 [inline] mem_cgroup_uncharge_list+0x70/0xe0 mm/memcontrol.c:6877 release_pages+0x13a2/0x1550 mm/swap.c:911 tlb_batch_pages_flush mm/mmu_gather.c:49 [inline] tlb_flush_mmu_free mm/mmu_gather.c:242 [inline] tlb_flush_mmu+0x780/0x910 mm/mmu_gather.c:249 tlb_finish_mmu+0xcb/0x200 mm/mmu_gather.c:328 exit_mmap+0x296/0x550 mm/mmap.c:3185 __mmput+0x113/0x370 kernel/fork.c:1076 exit_mm+0x4cd/0x550 kernel/exit.c:483 do_exit+0x576/0x1f20 kernel/exit.c:793 do_group_exit+0x161/0x2d0 kernel/exit.c:903 get_signal+0x139b/0x1d30 kernel/signal.c:2743 arch_do_signal+0x33/0x610 arch/x86/kernel/signal.c:811 exit_to_user_mode_loop kernel/entry/common.c:135 [inline] exit_to_user_mode_prepare+0x8d/0x1b0 kernel/entry/common.c:166 syscall_exit_to_user_mode+0x5e/0x1a0 kernel/entry/common.c:241 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Commit 1a3e1f40962c ("mm: memcontrol: decouple reference counting from page accounting") reworked the memcg lifetime to be bound the the struct page rather than charges. It also removed the css_put_many from uncharge_batch and that is causing the above splat. uncharge_batch() is supposed to uncharge accumulated charges for all pages freed from the same memcg. The queuing is done by uncharge_page which however drops the memcg reference after it adds charges to the batch. If the current page happens to be the last one holding the reference for its memcg then the memcg is OK to go and the next page to be freed will trigger batched uncharge which needs to access the memcg which is gone already. Fix the issue by taking a reference for the memcg in the current batch. Fixes: 1a3e1f40962c ("mm: memcontrol: decouple reference counting from page accounting") Reported-by: syzbot+b305848212deec86eabe(a)syzkaller.appspotmail.com Reported-by: syzbot+b5ea6fb6f139c8b9482b(a)syzkaller.appspotmail.com Signed-off-by: Michal Hocko <mhocko(a)suse.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Reviewed-by: Shakeel Butt <shakeelb(a)google.com> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Roman Gushchin <guro(a)fb.com> Cc: Hugh Dickins <hughd(a)google.com> Link: https://lkml.kernel.org/r/20200820090341.GC5033@dhcp22.suse.cz Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b807952b4d43..cfa6cbad21d5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6774,6 +6774,9 @@ static void uncharge_batch(const struct uncharge_gather *ug) __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages); memcg_check_events(ug->memcg, ug->dummy_page); local_irq_restore(flags); + + /* drop reference from uncharge_page */ + css_put(&ug->memcg->css); } static void uncharge_page(struct page *page, struct uncharge_gather *ug) @@ -6797,6 +6800,9 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) uncharge_gather_clear(ug); } ug->memcg = page->mem_cgroup; + + /* pairs with css_put in uncharge_batch */ + css_get(&ug->memcg->css); } nr_pages = compound_nr(page);

1 year, 8 months

1
0
0 0

[PATCH 0/2] Disable automatic load CCS load balancing

by Andi Shyti

Hi, this series does basically two things: 1. Disables automatic load balancing as adviced by the hardware workaround. 2. Forces the sharing of the load submitted to CCS among all the CCS available (as of now only DG2 has more than one CCS). This way the user, when sending a query, will see only one CCS available. Andi Andi Shyti (2): drm/i915/gt: Disable HW load balancing for CCS drm/i915/gt: Set default CCS mode '1' drivers/gpu/drm/i915/gt/intel_gt.c | 11 +++++++++++ drivers/gpu/drm/i915/gt/intel_gt_regs.h | 3 +++ drivers/gpu/drm/i915/gt/intel_workarounds.c | 6 ++++++ drivers/gpu/drm/i915/i915_drv.h | 17 +++++++++++++++++ drivers/gpu/drm/i915/i915_query.c | 5 +++-- 5 files changed, 40 insertions(+), 2 deletions(-) -- 2.43.0

1 year, 8 months

3
8
0 0

Backport commit 4f082a753122 "fs/ntfs3: Enhance the attribute size check"

by Doebel, Bjoern

Hi, please backport commit 4f082a753122 "fs/ntfs3: Enhance the attribute size check" to the 6.1 stable branch. Commit message: """ This combines the overflow and boundary check so that all attribute size will be properly examined while enumerating them. """ We have seen Syzkaller reports for the 6.1 stable build and this patch fixes the issue. The issue does not reproduce on any of the other stable branches. Best regards, Bjoern Report: ================================================================== loop4: detected capacity change from 0 to 65536 BUG: KASAN: use-after-free in ntfs_read_mft+0x3187/0x3210 fs/ntfs3/inode.c:163 Read of size 8 at addr ffff888023c28036 by task syz-executor.5/29379 CPU: 1 PID: 29379 Comm: syz-executor.5 Not tainted 6.1.78 #33 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-debian-1.16.0-5 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x70/0x93 lib/dump_stack.c:106 print_address_description.constprop.0+0x81/0x2b0 mm/kasan/report.c:284 print_report+0x116/0x1f6 mm/kasan/report.c:395 kasan_report+0xad/0x130 mm/kasan/report.c:495 ntfs_read_mft+0x3187/0x3210 fs/ntfs3/inode.c:163 ntfs_iget5+0x1a7/0x240 fs/ntfs3/inode.c:524 ntfs_loadlog_and_replay+0x128/0x5e0 fs/ntfs3/fsntfs.c:272 ntfs_fill_super+0xb28/0x22c0 fs/ntfs3/super.c:1018 get_tree_bdev+0x40a/0x700 fs/super.c:1355 vfs_get_tree+0x86/0x2e0 fs/super.c:1562 do_new_mount+0x344/0x6b0 fs/namespace.c:3051 path_mount+0x4c4/0x17e0 fs/namespace.c:3381 do_mount fs/namespace.c:3394 [inline] __do_sys_mount fs/namespace.c:3602 [inline] __se_sys_mount fs/namespace.c:3579 [inline] __x64_sys_mount+0x287/0x310 fs/namespace.c:3579 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x37/0x90 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x64/0xce RIP: 0033:0x7fd43486377e Code: 0f 1f 40 00 48 c7 c2 b8 ff ff ff f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fd4355d6ec8 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007fd4355d6f60 RCX: 00007fd43486377e RDX: 000000002001f800 RSI: 0000000020000040 RDI: 00007fd4355d6f20 RBP: 000000002001f800 R08: 00007fd4355d6f60 R09: 0000000000000003 R10: 0000000000000003 R11: 0000000000000202 R12: 0000000020000040 R13: 00007fd4355d6f20 R14: 000000000001f7f9 R15: 0000000020000000 </TASK> Allocated by task 6435: kasan_save_stack+0x1c/0x40 mm/kasan/common.c:45 kasan_set_track+0x21/0x30 mm/kasan/common.c:52 __kasan_slab_alloc+0x6d/0x70 mm/kasan/common.c:328 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slab.h:737 [inline] slab_alloc_node mm/slub.c:3398 [inline] slab_alloc mm/slub.c:3406 [inline] __kmem_cache_alloc_lru mm/slub.c:3413 [inline] kmem_cache_alloc+0x144/0x320 mm/slub.c:3422 getname_flags.part.0+0x55/0x4f0 fs/namei.c:139 getname_flags+0x9d/0xf0 include/linux/audit.h:320 vfs_fstatat+0x78/0xb0 fs/stat.c:266 vfs_stat include/linux/fs.h:3352 [inline] __do_sys_newstat+0x89/0x110 fs/stat.c:410 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x37/0x90 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x64/0xce Freed by task 6435: kasan_save_stack+0x1c/0x40 mm/kasan/common.c:45 kasan_set_track+0x21/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2a/0x50 mm/kasan/generic.c:516 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free+0x15b/0x1c0 mm/kasan/common.c:200 kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1724 [inline] slab_free_freelist_hook mm/slub.c:1750 [inline] slab_free mm/slub.c:3661 [inline] kmem_cache_free+0x123/0x4c0 mm/slub.c:3683 putname+0x12f/0x170 fs/namei.c:273 vfs_fstatat+0x9b/0xb0 fs/stat.c:268 vfs_stat include/linux/fs.h:3352 [inline] __do_sys_newstat+0x89/0x110 fs/stat.c:410 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x37/0x90 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x64/0xce The buggy address belongs to the object at ffff888023c28000 which belongs to the cache names_cache of size 4096 The buggy address is located 54 bytes inside of 4096-byte region [ffff888023c28000, ffff888023c29000) The buggy address belongs to the physical page: page:0000000034b12153 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x23c28 head:0000000034b12153 order:3 compound_mapcount:0 compound_pincount:0 flags: 0xfffffc0010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0010200 0000000000000000 dead000000000001 ffff88800cf57a00 raw: 0000000000000000 0000000000070007 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888023c27f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888023c27f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc > ffff888023c28000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888023c28080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888023c28100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Amazon Development Center Germany GmbH Krausenstr. 38 10117 Berlin Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss Eingetragen am Amtsgericht Charlottenburg unter HRB 149173 B Sitz: Berlin Ust-ID: DE 289 237 879

1 year, 8 months

2
1
0 0

[PATCH v2 2/8] KVM: x86/xen: inject vCPU upcall vector when local APIC is enabled

by David Woodhouse

From: David Woodhouse <dwmw(a)amazon.co.uk> Linux guests since commit b1c3497e604d ("x86/xen: Add support for HVMOP_set_evtchn_upcall_vector") in v6.0 onwards will use the per-vCPU upcall vector when it's advertised in the Xen CPUID leaves. This upcall is injected through the guest's local APIC as an MSI, unlike the older system vector which was merely injected by the hypervisor any time the CPU was able to receive an interrupt and the upcall_pending flags is set in its vcpu_info. Effectively, that makes the per-CPU upcall edge triggered instead of level triggered, which results in the upcall being lost if the MSI is delivered when the local APIC is *disabled*. Xen checks the vcpu_info->evtchn_upcall_pending flag when the local APIC for a vCPU is software enabled (in fact, on any write to the SPIV register which doesn't disable the APIC). Do the same in KVM since KVM doesn't provide a way for userspace to intervene and trap accesses to the SPIV register of a local APIC emulated by KVM. Fixes: fde0451be8fb3 ("KVM: x86/xen: Support per-vCPU event channel upcall via local APIC") Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Reviewed-by: Paul Durrant <paul(a)xen.org> Cc: stable(a)vger.kernel.org --- arch/x86/kvm/lapic.c | 5 ++++- arch/x86/kvm/xen.c | 2 +- arch/x86/kvm/xen.h | 18 ++++++++++++++++++ 3 files changed, 23 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3242f3da2457..75bc7d3f0022 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -41,6 +41,7 @@ #include "ioapic.h" #include "trace.h" #include "x86.h" +#include "xen.h" #include "cpuid.h" #include "hyperv.h" #include "smm.h" @@ -499,8 +500,10 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) } /* Check if there are APF page ready requests pending */ - if (enabled) + if (enabled) { kvm_make_request(KVM_REQ_APF_READY, apic->vcpu); + kvm_xen_sw_enable_lapic(apic->vcpu); + } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index ccd2dc753fd6..06904696759c 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -568,7 +568,7 @@ void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) kvm_xen_update_runstate_guest(v, state == RUNSTATE_runnable); } -static void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) +void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) { struct kvm_lapic_irq irq = { }; int r; diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index f8f1fe22d090..f5841d9000ae 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -18,6 +18,7 @@ extern struct static_key_false_deferred kvm_xen_enabled; int __kvm_xen_has_interrupt(struct kvm_vcpu *vcpu); void kvm_xen_inject_pending_events(struct kvm_vcpu *vcpu); +void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *vcpu); int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); @@ -36,6 +37,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm, const struct kvm_irq_routing_entry *ue); void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu); +static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu) +{ + /* + * The local APIC is being enabled. If the per-vCPU upcall vector is + * set and the vCPU's evtchn_upcall_pending flag is set, inject the + * interrupt. + */ + if (static_branch_unlikely(&kvm_xen_enabled.key) && + vcpu->arch.xen.vcpu_info_cache.active && + vcpu->arch.xen.upcall_vector && __kvm_xen_has_interrupt(vcpu)) + kvm_xen_inject_vcpu_vector(vcpu); +} + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return static_branch_unlikely(&kvm_xen_enabled.key) && @@ -101,6 +115,10 @@ static inline void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) { } +static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu) +{ +} + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return false; -- 2.43.0

1 year, 8 months

1
0
0 0

[PATCH v2 2/2] landlock: Warn once if a Landlock action is requested while disabled

by Mickaël Salaün

Because sandboxing can be used as an opportunistic security measure, user space may not log unsupported features. Let the system administrator know if an application tries to use Landlock but failed because it isn't enabled at boot time. This may be caused by bootloader configurations with outdated "lsm" kernel's command-line parameter. Cc: stable(a)vger.kernel.org Fixes: 265885daf3e5 ("landlock: Add syscall implementations") Reviewed-by: Kees Cook <keescook(a)chromium.org> Reviewed-by: Günther Noack <gnoack3000(a)gmail.com> Signed-off-by: Mickaël Salaün <mic(a)digikod.net> --- Changes since v1: * Add Kees's and Günther's Reviewed-by. * Rename is_not_initialized() to not_initialized() and invert the logic, as suggested by Günther. This is a cosmetic change without global behavioral changed. * Update link to point to a new subsection. --- security/landlock/syscalls.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 898358f57fa0..6788e73b6681 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -33,6 +33,18 @@ #include "ruleset.h" #include "setup.h" +static bool is_initialized(void) +{ + if (likely(landlock_initialized)) + return true; + + pr_warn_once( + "Disabled but requested by user space. " + "You should enable Landlock at boot time: " + "https://docs.kernel.org/userspace-api/landlock.html#boot-time-configuration…"); + return false; +} + /** * copy_min_struct_from_user - Safe future-proof argument copying * @@ -173,7 +185,7 @@ SYSCALL_DEFINE3(landlock_create_ruleset, /* Build-time checks. */ build_check_abi(); - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; if (flags) { @@ -398,7 +410,7 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, struct landlock_ruleset *ruleset; int err; - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; /* No flag for now. */ @@ -458,7 +470,7 @@ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, struct landlock_cred_security *new_llcred; int err; - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; /* -- 2.44.0

1 year, 8 months

1
0
0 0

[PATCH net] xfrm: Avoid clang fortify warning in copy_to_user_tmpl()

by Nathan Chancellor

After a couple recent changes in LLVM, there is a warning (or error with CONFIG_WERROR=y or W=e) from the compile time fortify source routines, specifically the memset() in copy_to_user_tmpl(). In file included from net/xfrm/xfrm_user.c:14: ... include/linux/fortify-string.h:438:4: error: call to '__write_overflow_field' declared with 'warning' attribute: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror,-Wattribute-warning] 438 | __write_overflow_field(p_size_field, size); | ^ 1 error generated. While ->xfrm_nr has been validated against XFRM_MAX_DEPTH when its value is first assigned in copy_templates() by calling validate_tmpl() first (so there should not be any issue in practice), LLVM/clang cannot really deduce that across the boundaries of these functions. Without that knowledge, it cannot assume that the loop stops before i is greater than XFRM_MAX_DEPTH, which would indeed result a stack buffer overflow in the memset(). To make the bounds of ->xfrm_nr clear to the compiler and add additional defense in case copy_to_user_tmpl() is ever used in a path where ->xfrm_nr has not been properly validated against XFRM_MAX_DEPTH first, add an explicit bound check and early return, which clears up the warning. Cc: stable(a)vger.kernel.org Link: https://github.com/ClangBuiltLinux/linux/issues/1985 Signed-off-by: Nathan Chancellor <nathan(a)kernel.org> --- net/xfrm/xfrm_user.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index f037be190bae..912c1189ba41 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2017,6 +2017,9 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb) if (xp->xfrm_nr == 0) return 0; + if (xp->xfrm_nr > XFRM_MAX_DEPTH) + return -ENOBUFS; + for (i = 0; i < xp->xfrm_nr; i++) { struct xfrm_user_tmpl *up = &vec[i]; struct xfrm_tmpl *kp = &xp->xfrm_vec[i]; --- base-commit: 14dec56fdd4c70a0ebe40077368e367421ea6fef change-id: 20240221-xfrm-avoid-clang-fortify-warning-copy_to_user_tmpl-40cb10b003e3 Best regards, -- Nathan Chancellor <nathan(a)kernel.org>

1 year, 8 months

3
2
0 0

[PATCH 5.15 0/1] rcutorture: Add missing return and use __func__ in warning

by Daniil Dulov

Svacer reports a potential division by zero at rcu_torture_writer() in 5.15 stable release. The problem has been fixed by the following patch that can be cleanly applied to 5.15 branch.

1 year, 8 months

1
1
0 0

FAILED: patch "[PATCH] mm: zswap: fix missing folio cleanup in writeback race path" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x e3b63e966cac0bf78aaa1efede1827a252815a1d # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022612-uncloak-pretext-f4a2@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: e3b63e966cac ("mm: zswap: fix missing folio cleanup in writeback race path") 96c7b0b42239 ("mm: return the folio from __read_swap_cache_async()") e947ba0bbf47 ("mm/zswap: cleanup zswap_writeback_entry()") 32acba4c0483 ("mm/zswap: refactor out __zswap_load()") c75f5c1e0f1d ("mm/zswap: reuse dstmem when decompress") b5ba474f3f51 ("zswap: shrink zswap pool based on memory pressure") a65b0e7607cc ("zswap: make shrinking memcg-aware") ddc1a5cbc05d ("mempolicy: alloc_pages_mpol() for NUMA policy without vma") 23e4883248f0 ("mm: add page_rmappable_folio() wrapper") c36f6e6dff4d ("mempolicy trivia: slightly more consistent naming") 7f1ee4e20708 ("mempolicy trivia: delete those ancient pr_debug()s") 1cb5d11a370f ("mempolicy: fix migrate_pages(2) syscall return nr_failed") 3657fdc2451a ("mm: move vma_policy() and anon_vma_name() decls to mm_types.h") 3022fd7af960 ("shmem: _add_to_page_cache() before shmem_inode_acct_blocks()") 054a9f7ccd0a ("shmem: move memcg charge out of shmem_add_to_page_cache()") 4199f51a7eb2 ("shmem: shmem_acct_blocks() and shmem_inode_acct_blocks()") e3e1a5067fd2 ("shmem: remove vma arg from shmem_get_folio_gfp()") 75c70128a673 ("mm: mempolicy: make mpol_misplaced() to take a folio") cda6d93672ac ("mm: memory: make numa_migrate_prep() to take a folio") 6695cf68b15c ("mm: memory: use a folio in do_numa_page()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e3b63e966cac0bf78aaa1efede1827a252815a1d Mon Sep 17 00:00:00 2001 From: Yosry Ahmed <yosryahmed(a)google.com> Date: Thu, 25 Jan 2024 08:51:27 +0000 Subject: [PATCH] mm: zswap: fix missing folio cleanup in writeback race path In zswap_writeback_entry(), after we get a folio from __read_swap_cache_async(), we grab the tree lock again to check that the swap entry was not invalidated and recycled. If it was, we delete the folio we just added to the swap cache and exit. However, __read_swap_cache_async() returns the folio locked when it is newly allocated, which is always true for this path, and the folio is ref'd. Make sure to unlock and put the folio before returning. This was discovered by code inspection, probably because this path handles a race condition that should not happen often, and the bug would not crash the system, it will only strand the folio indefinitely. Link: https://lkml.kernel.org/r/20240125085127.1327013-1-yosryahmed@google.com Fixes: 04fc7816089c ("mm: fix zswap writeback race condition") Signed-off-by: Yosry Ahmed <yosryahmed(a)google.com> Reviewed-by: Chengming Zhou <zhouchengming(a)bytedance.com> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> Reviewed-by: Nhat Pham <nphamcs(a)gmail.com> Cc: Domenico Cerasuolo <cerasuolodomenico(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index 350dd2fc8159..d2423247acfd 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1440,6 +1440,8 @@ static int zswap_writeback_entry(struct zswap_entry *entry, if (zswap_rb_search(&tree->rbroot, swp_offset(entry->swpentry)) != entry) { spin_unlock(&tree->lock); delete_from_swap_cache(folio); + folio_unlock(folio); + folio_put(folio); return -ENOMEM; } spin_unlock(&tree->lock);

1 year, 8 months

3
6
0 0

FAILED: patch "[PATCH] mm: zswap: fix missing folio cleanup in writeback race path" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x e3b63e966cac0bf78aaa1efede1827a252815a1d # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022611-tropics-deferred-2483@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: e3b63e966cac ("mm: zswap: fix missing folio cleanup in writeback race path") 96c7b0b42239 ("mm: return the folio from __read_swap_cache_async()") e947ba0bbf47 ("mm/zswap: cleanup zswap_writeback_entry()") 32acba4c0483 ("mm/zswap: refactor out __zswap_load()") c75f5c1e0f1d ("mm/zswap: reuse dstmem when decompress") b5ba474f3f51 ("zswap: shrink zswap pool based on memory pressure") a65b0e7607cc ("zswap: make shrinking memcg-aware") ddc1a5cbc05d ("mempolicy: alloc_pages_mpol() for NUMA policy without vma") 23e4883248f0 ("mm: add page_rmappable_folio() wrapper") c36f6e6dff4d ("mempolicy trivia: slightly more consistent naming") 7f1ee4e20708 ("mempolicy trivia: delete those ancient pr_debug()s") 1cb5d11a370f ("mempolicy: fix migrate_pages(2) syscall return nr_failed") 3657fdc2451a ("mm: move vma_policy() and anon_vma_name() decls to mm_types.h") 3022fd7af960 ("shmem: _add_to_page_cache() before shmem_inode_acct_blocks()") 054a9f7ccd0a ("shmem: move memcg charge out of shmem_add_to_page_cache()") 4199f51a7eb2 ("shmem: shmem_acct_blocks() and shmem_inode_acct_blocks()") e3e1a5067fd2 ("shmem: remove vma arg from shmem_get_folio_gfp()") 75c70128a673 ("mm: mempolicy: make mpol_misplaced() to take a folio") cda6d93672ac ("mm: memory: make numa_migrate_prep() to take a folio") 6695cf68b15c ("mm: memory: use a folio in do_numa_page()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e3b63e966cac0bf78aaa1efede1827a252815a1d Mon Sep 17 00:00:00 2001 From: Yosry Ahmed <yosryahmed(a)google.com> Date: Thu, 25 Jan 2024 08:51:27 +0000 Subject: [PATCH] mm: zswap: fix missing folio cleanup in writeback race path In zswap_writeback_entry(), after we get a folio from __read_swap_cache_async(), we grab the tree lock again to check that the swap entry was not invalidated and recycled. If it was, we delete the folio we just added to the swap cache and exit. However, __read_swap_cache_async() returns the folio locked when it is newly allocated, which is always true for this path, and the folio is ref'd. Make sure to unlock and put the folio before returning. This was discovered by code inspection, probably because this path handles a race condition that should not happen often, and the bug would not crash the system, it will only strand the folio indefinitely. Link: https://lkml.kernel.org/r/20240125085127.1327013-1-yosryahmed@google.com Fixes: 04fc7816089c ("mm: fix zswap writeback race condition") Signed-off-by: Yosry Ahmed <yosryahmed(a)google.com> Reviewed-by: Chengming Zhou <zhouchengming(a)bytedance.com> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> Reviewed-by: Nhat Pham <nphamcs(a)gmail.com> Cc: Domenico Cerasuolo <cerasuolodomenico(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index 350dd2fc8159..d2423247acfd 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1440,6 +1440,8 @@ static int zswap_writeback_entry(struct zswap_entry *entry, if (zswap_rb_search(&tree->rbroot, swp_offset(entry->swpentry)) != entry) { spin_unlock(&tree->lock); delete_from_swap_cache(folio); + folio_unlock(folio); + folio_put(folio); return -ENOMEM; } spin_unlock(&tree->lock);

1 year, 8 months

4
4
0 0

FAILED: patch "[PATCH] mm/zswap: invalidate duplicate entry when !zswap_enabled" failed to apply to 6.7-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.7-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.7.y git checkout FETCH_HEAD git cherry-pick -x 678e54d4bb9a4822f8ae99690ac131c5d490cdb1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022622-agony-salvaging-5082@gregkh' --subject-prefix 'PATCH 6.7.y' HEAD^.. Possible dependencies: 678e54d4bb9a ("mm/zswap: invalidate duplicate entry when !zswap_enabled") a65b0e7607cc ("zswap: make shrinking memcg-aware") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 678e54d4bb9a4822f8ae99690ac131c5d490cdb1 Mon Sep 17 00:00:00 2001 From: Chengming Zhou <zhouchengming(a)bytedance.com> Date: Thu, 8 Feb 2024 02:32:54 +0000 Subject: [PATCH] mm/zswap: invalidate duplicate entry when !zswap_enabled We have to invalidate any duplicate entry even when !zswap_enabled since zswap can be disabled anytime. If the folio store success before, then got dirtied again but zswap disabled, we won't invalidate the old duplicate entry in the zswap_store(). So later lru writeback may overwrite the new data in swapfile. Link: https://lkml.kernel.org/r/20240208023254.3873823-1-chengming.zhou@linux.dev Fixes: 42c06a0e8ebe ("mm: kill frontswap") Signed-off-by: Chengming Zhou <zhouchengming(a)bytedance.com> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: Yosry Ahmed <yosryahmed(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index 36903d938c15..db4625af65fb 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1518,7 +1518,7 @@ bool zswap_store(struct folio *folio) if (folio_test_large(folio)) return false; - if (!zswap_enabled || !tree) + if (!tree) return false; /* @@ -1533,6 +1533,10 @@ bool zswap_store(struct folio *folio) zswap_invalidate_entry(tree, dupentry); } spin_unlock(&tree->lock); + + if (!zswap_enabled) + return false; + objcg = get_obj_cgroup_from_folio(folio); if (objcg && !obj_cgroup_may_zswap(objcg)) { memcg = get_mem_cgroup_from_objcg(objcg);

1 year, 8 months

4
4
0 0

[PATCH 6.7.y 0/6] Delay VERW - 6.7.y backport

by Pawan Gupta

This is the backport of recently upstreamed series that moves VERW execution to a later point in exit-to-user path. This is needed because in some cases it may be possible for data accessed after VERW executions may end into MDS affected CPU buffers. Moving VERW closer to ring transition reduces the attack surface. Patch 1/6 includes a minor fix that is queued for upstream: https://lore.kernel.org/lkml/170899674562.398.6398007479766564897.tip-bot2@… Patch 2/6 needed a conflict to be resolved for the hunk swapgs_restore_regs_and_return_to_usermode. Signed-off-by: Pawan Gupta <pawan.kumar.gupta(a)linux.intel.com> --- Pawan Gupta (5): x86/bugs: Add asm helpers for executing VERW x86/entry_64: Add VERW just before userspace transition x86/entry_32: Add VERW just before userspace transition x86/bugs: Use ALTERNATIVE() instead of mds_user_clear static key KVM/VMX: Move VERW closer to VMentry for MDS mitigation Sean Christopherson (1): KVM/VMX: Use BT+JNC, i.e. EFLAGS.CF to select VMRESUME vs. VMLAUNCH Documentation/arch/x86/mds.rst | 38 +++++++++++++++++++++++++----------- arch/x86/entry/entry.S | 23 ++++++++++++++++++++++ arch/x86/entry/entry_32.S | 3 +++ arch/x86/entry/entry_64.S | 11 +++++++++++ arch/x86/entry/entry_64_compat.S | 1 + arch/x86/include/asm/cpufeatures.h | 2 +- arch/x86/include/asm/entry-common.h | 1 - arch/x86/include/asm/nospec-branch.h | 25 ++++++++++++------------ arch/x86/kernel/cpu/bugs.c | 15 ++++++-------- arch/x86/kernel/nmi.c | 3 --- arch/x86/kvm/vmx/run_flags.h | 7 +++++-- arch/x86/kvm/vmx/vmenter.S | 9 ++++++--- arch/x86/kvm/vmx/vmx.c | 20 +++++++++++++++---- 13 files changed, 112 insertions(+), 46 deletions(-) --- base-commit: b631f5b445dc3379f67ff63a2e4c58f22d4975dc change-id: 20240226-delay-verw-backport-6-7-y-a2cb3f26bb90 Best regards, -- Thanks, Pawan

1 year, 8 months

3
12
0 0

[PATCH v4 0/4] usb: dwc3-am62: module removal and errata fixes

by Roger Quadros

Hi, This series fixes errors during module removal. It also implements PHY core voltage selection as per TI recommendation and workaround for Errata i2409 [1]. The workaround needs PHY2 region to be present in device node. The device tree patch will be sent later after the DT binding doc is merged. [1] - https://www.ti.com/lit/er/sprz487d/sprz487d.pdf Signed-off-by: Roger Quadros <rogerq(a)kernel.org> --- Changes in v4: - re-arranged patches into first 2 bug-fixes and added Cc stable for them - Added Acked-by - Link to v3: https://lore.kernel.org/r/20240214-for-v6-9-am62-usb-errata-3-0-v3-0-147ec5… --- Roger Quadros (4): usb: dwc3-am62: fix module unload/reload behavior usb: dwc3-am62: Disable wakeup at remove usb: dwc3-am62: Fix PHY core voltage selection usb: dwc3-am62: add workaround for Errata i2409 drivers/usb/dwc3/dwc3-am62.c | 42 ++++++++++++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 12 deletions(-) --- base-commit: 6613476e225e090cc9aad49be7fa504e290dd33d change-id: 20240206-for-v6-9-am62-usb-errata-3-0-233024ea8e9d Best regards, -- Roger Quadros <rogerq(a)kernel.org>

1 year, 8 months

1
2
0 0

FAILED: patch "[PATCH] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x b820de741ae48ccf50dd95e297889c286ff4f760 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022602-unwrapped-haggler-daae@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: b820de741ae4 ("fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio") 9cf3516c29e6 ("fs: add IOCB flags related to passing back dio completions") f6c73a11133e ("fs.h: Add TRACE_IOCB_STRINGS for use in trace points") 1da8cf961bb1 ("Merge tag 'io_uring-6.0-2022-08-13' of git://git.kernel.dk/linux-block") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b820de741ae48ccf50dd95e297889c286ff4f760 Mon Sep 17 00:00:00 2001 From: Bart Van Assche <bvanassche(a)acm.org> Date: Thu, 15 Feb 2024 12:47:38 -0800 Subject: [PATCH] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio If kiocb_set_cancel_fn() is called for I/O submitted via io_uring, the following kernel warning appears: WARNING: CPU: 3 PID: 368 at fs/aio.c:598 kiocb_set_cancel_fn+0x9c/0xa8 Call trace: kiocb_set_cancel_fn+0x9c/0xa8 ffs_epfile_read_iter+0x144/0x1d0 io_read+0x19c/0x498 io_issue_sqe+0x118/0x27c io_submit_sqes+0x25c/0x5fc __arm64_sys_io_uring_enter+0x104/0xab0 invoke_syscall+0x58/0x11c el0_svc_common+0xb4/0xf4 do_el0_svc+0x2c/0xb0 el0_svc+0x2c/0xa4 el0t_64_sync_handler+0x68/0xb4 el0t_64_sync+0x1a4/0x1a8 Fix this by setting the IOCB_AIO_RW flag for read and write I/O that is submitted by libaio. Suggested-by: Jens Axboe <axboe(a)kernel.dk> Cc: Christoph Hellwig <hch(a)lst.de> Cc: Avi Kivity <avi(a)scylladb.com> Cc: Sandeep Dhavale <dhavale(a)google.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: stable(a)vger.kernel.org Signed-off-by: Bart Van Assche <bvanassche(a)acm.org> Link: https://lore.kernel.org/r/20240215204739.2677806-2-bvanassche@acm.org Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/aio.c b/fs/aio.c index bb2ff48991f3..da18dbcfcb22 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -593,6 +593,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) struct kioctx *ctx = req->ki_ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; @@ -1509,7 +1516,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { diff --git a/include/linux/fs.h b/include/linux/fs.h index ed5966a70495..c2dcc98cb4c8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -352,6 +352,8 @@ enum rw_hint { * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \

1 year, 8 months

3
2
0 0

FAILED: patch "[PATCH] mm/damon/reclaim: fix quota stauts loss due to online tunings" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 1b0ca4e4ff10a2c8402e2cf70132c683e1c772e4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022643-scorn-filtrate-8677@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 1b0ca4e4ff10 ("mm/damon/reclaim: fix quota stauts loss due to online tunings") 66d9faec0745 ("mm/damon/reclaim: add a parameter called skip_anon for avoiding anonymous pages reclamation") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1b0ca4e4ff10a2c8402e2cf70132c683e1c772e4 Mon Sep 17 00:00:00 2001 From: SeongJae Park <sj(a)kernel.org> Date: Fri, 16 Feb 2024 11:40:24 -0800 Subject: [PATCH] mm/damon/reclaim: fix quota stauts loss due to online tunings Patch series "mm/damon: fix quota status loss due to online tunings". DAMON_RECLAIM and DAMON_LRU_SORT is not preserving internal quota status when applying new user parameters, and hence could cause temporal quota accuracy degradation. Fix it by preserving the status. This patch (of 2): For online parameters change, DAMON_RECLAIM creates new scheme based on latest values of the parameters and replaces the old scheme with the new one. When creating it, the internal status of the quota of the old scheme is not preserved. As a result, charging of the quota starts from zero after the online tuning. The data that collected to estimate the throughput of the scheme's action is also reset, and therefore the estimation should start from the scratch again. Because the throughput estimation is being used to convert the time quota to the effective size quota, this could result in temporal time quota inaccuracy. It would be recovered over time, though. In short, the quota accuracy could be temporarily degraded after online parameters update. Fix the problem by checking the case and copying the internal fields for the status. Link: https://lkml.kernel.org/r/20240216194025.9207-1-sj@kernel.org Link: https://lkml.kernel.org/r/20240216194025.9207-2-sj@kernel.org Fixes: e035c280f6df ("mm/damon/reclaim: support online inputs update") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> [5.19+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index ab974e477d2f..66e190f0374a 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -150,9 +150,20 @@ static struct damos *damon_reclaim_new_scheme(void) &damon_reclaim_wmarks); } +static void damon_reclaim_copy_quota_status(struct damos_quota *dst, + struct damos_quota *src) +{ + dst->total_charged_sz = src->total_charged_sz; + dst->total_charged_ns = src->total_charged_ns; + dst->charged_sz = src->charged_sz; + dst->charged_from = src->charged_from; + dst->charge_target_from = src->charge_target_from; + dst->charge_addr_from = src->charge_addr_from; +} + static int damon_reclaim_apply_parameters(void) { - struct damos *scheme; + struct damos *scheme, *old_scheme; struct damos_filter *filter; int err = 0; @@ -164,6 +175,11 @@ static int damon_reclaim_apply_parameters(void) scheme = damon_reclaim_new_scheme(); if (!scheme) return -ENOMEM; + if (!list_empty(&ctx->schemes)) { + damon_for_each_scheme(old_scheme, ctx) + damon_reclaim_copy_quota_status(&scheme->quota, + &old_scheme->quota); + } if (skip_anon) { filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true); if (!filter) {

1 year, 8 months

3
2
0 0

[Regression] 5.4.269 fails to build due to security/apparmor/af_unix.c:583:17: error: too few arguments to function ‘unix_state_lock_nested’

by Philip Müller

Hi Greg, the issue might be due to this patch: https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git/tre… 2024-02-23T15:39:05.6297767Z CC kernel/sys_ni.o 2024-02-23T15:39:05.7583048Z security/apparmor/af_unix.c: In function ‘unix_state_double_lock’: 2024-02-23T15:39:05.7586076Z security/apparmor/af_unix.c:583:17: error: too few arguments to function ‘unix_state_lock_nested’ 2024-02-23T15:39:05.7588374Z 583 | unix_state_lock_nested(sk2); 2024-02-23T15:39:05.7589913Z | ^~~~~~~~~~~~~~~~~~~~~~ 2024-02-23T15:39:05.7591564Z In file included from security/apparmor/include/af_unix.h:15, 2024-02-23T15:39:05.7593341Z from security/apparmor/af_unix.c:17: 2024-02-23T15:39:05.7594989Z ./include/net/af_unix.h:77:20: note: declared here 2024-02-23T15:39:05.7596733Z 77 | static inline void unix_state_lock_nested(struct sock *sk, 2024-02-23T15:39:05.7598516Z | ^~~~~~~~~~~~~~~~~~~~~~ 2024-02-23T15:39:05.7600862Z security/apparmor/af_unix.c:586:17: error: too few arguments to function ‘unix_state_lock_nested’ 2024-02-23T15:39:05.7603177Z 586 | unix_state_lock_nested(sk1); 2024-02-23T15:39:05.7605189Z | ^~~~~~~~~~~~~~~~~~~~~~ 2024-02-23T15:39:05.7606765Z ./include/net/af_unix.h:77:20: note: declared here 2024-02-23T15:39:05.7608497Z 77 | static inline void unix_state_lock_nested(struct sock *sk, 2024-02-23T15:39:05.7610208Z | ^~~~~~~~~~~~~~~~~~~~~~ 2024-02-23T15:39:05.8002385Z make[2]: *** [scripts/Makefile.build:262: security/apparmor/af_unix.o] Error 1 2024-02-23T15:39:05.8005077Z make[2]: *** Waiting for unfinished jobs.... 2024-02-23T15:39:05.8094726Z CC crypto/scatterwalk.o 2024-02-23T15:39:05.9082621Z CC [M] fs/btrfs/sysfs.o 2024-02-23T15:39:06.2502316Z CC kernel/nsproxy.o 2024-02-23T15:39:06.4094246Z make[1]: *** [scripts/Makefile.build:497: security/apparmor] Error 2 2024-02-23T15:39:06.4207119Z make: *** [Makefile:1750: security] Error 2 2024-02-23T15:39:06.4208636Z CC kernel/notifier.o 2024-02-23T15:39:06.4210296Z make: *** Waiting for unfinished jobs.... 2024-02-23T15:39:06.8604827Z CC crypto/proc.o -- Best, Philip

1 year, 8 months

2
7
0 0

[PATCH 6.6.y 0/6] Delay VERW - 6.6.y backport

by Pawan Gupta

This is the backport of recently upstreamed series that moves VERW execution to a later point in exit-to-user path. This is needed because in some cases it may be possible for data accessed after VERW executions may end into MDS affected CPU buffers. Moving VERW closer to ring transition reduces the attack surface. Patch 1/6 includes a minor fix that is queued for upstream: https://lore.kernel.org/lkml/170899674562.398.6398007479766564897.tip-bot2@… Patch 2/6 needed a conflict to be resolved for the hunk swapgs_restore_regs_and_return_to_usermode. This is only compile and boot tested on qemu. Cc: Dave Hansen <dave.hansen(a)linux.intel.com> To: stable(a)vger.kernel.org Signed-off-by: Pawan Gupta <pawan.kumar.gupta(a)linux.intel.com> --- Pawan Gupta (5): x86/bugs: Add asm helpers for executing VERW x86/entry_64: Add VERW just before userspace transition x86/entry_32: Add VERW just before userspace transition x86/bugs: Use ALTERNATIVE() instead of mds_user_clear static key KVM/VMX: Move VERW closer to VMentry for MDS mitigation Sean Christopherson (1): KVM/VMX: Use BT+JNC, i.e. EFLAGS.CF to select VMRESUME vs. VMLAUNCH Documentation/arch/x86/mds.rst | 38 +++++++++++++++++++++++++----------- arch/x86/entry/entry.S | 23 ++++++++++++++++++++++ arch/x86/entry/entry_32.S | 3 +++ arch/x86/entry/entry_64.S | 11 +++++++++++ arch/x86/entry/entry_64_compat.S | 1 + arch/x86/include/asm/cpufeatures.h | 2 +- arch/x86/include/asm/entry-common.h | 1 - arch/x86/include/asm/nospec-branch.h | 25 ++++++++++++------------ arch/x86/kernel/cpu/bugs.c | 15 ++++++-------- arch/x86/kernel/nmi.c | 3 --- arch/x86/kvm/vmx/run_flags.h | 7 +++++-- arch/x86/kvm/vmx/vmenter.S | 9 ++++++--- arch/x86/kvm/vmx/vmx.c | 20 +++++++++++++++---- 13 files changed, 112 insertions(+), 46 deletions(-) --- base-commit: d8a27ea2c98685cdaa5fa66c809c7069a4ff394b change-id: 20240226-delay-verw-backport-6-6-y-2cda3298e600

1 year, 8 months

2
9
0 0

[PATCH] block: ataflop: more blk-mq refactoring fixes

by Michael Schmitz

[ commit d28e4dff085c5a87025c9a0a85fb798bd8e9ca17 upstream ] As it turns out, my earlier patch in commit 86d46fdaa12a (block: ataflop: fix breakage introduced at blk-mq refactoring) was incomplete. This patch fixes any remaining issues found during more testing and code review. Requests exceeding 4 k are handled in 4k segments but __blk_mq_end_request() is never called on these (still sectors outstanding on the request). With redo_fd_request() removed, there is no provision to kick off processing of the next segment, causing requests exceeding 4k to hang. (By setting /sys/block/fd0/queue/max_sectors_k <= 4 as workaround, this behaviour can be avoided). Instead of reintroducing redo_fd_request(), requeue the remainder of the request by calling blk_mq_requeue_request() on incomplete requests (i.e. when blk_update_request() still returns true), and rely on the block layer to queue the residual as new request. Both error handling and formatting needs to release the ST-DMA lock, so call finish_fdc() on these (this was previously handled by redo_fd_request()). finish_fdc() may be called legitimately without the ST-DMA lock held - make sure we only release the lock if we actually held it. In a similar way, early exit due to errors in ataflop_queue_rq() must release the lock. After minor errors, fd_error sets up to recalibrate the drive but never re-runs the current operation (another task handled by redo_fd_request() before). Call do_fd_action() to get the next steps (seek, retry read/write) underway. Signed-off-by: Michael Schmitz <schmitzmic(a)gmail.com> Fixes: 6ec3938cff95f (ataflop: convert to blk-mq) Fixes: 86d46fdaa12a (block: ataflop: fix breakage introduced at blk-mq refactoring) CC: stable(a)vger.kernel.org # 5.10.x Link: https://lore.kernel.org/r/20211024002013.9332-1-schmitzmic@gmail.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> [MSch: v5.10 backport merge conflict fix] --- drivers/block/ataflop.c | 42 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 37 insertions(+), 5 deletions(-) diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index cd612cd04767..224450c90e45 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -456,10 +456,20 @@ static DEFINE_TIMER(fd_timer, check_change); static void fd_end_request_cur(blk_status_t err) { + DPRINT(("fd_end_request_cur(), bytes %d of %d\n", + blk_rq_cur_bytes(fd_request), + blk_rq_bytes(fd_request))); + if (!blk_update_request(fd_request, err, blk_rq_cur_bytes(fd_request))) { + DPRINT(("calling __blk_mq_end_request()\n")); __blk_mq_end_request(fd_request, err); fd_request = NULL; + } else { + /* requeue rest of request */ + DPRINT(("calling blk_mq_requeue_request()\n")); + blk_mq_requeue_request(fd_request, true); + fd_request = NULL; } } @@ -697,12 +707,21 @@ static void fd_error( void ) if (fd_request->error_count >= MAX_ERRORS) { printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive ); fd_end_request_cur(BLK_STS_IOERR); + finish_fdc(); + return; } else if (fd_request->error_count == RECALIBRATE_ERRORS) { printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive ); if (SelectedDrive != -1) SUD.track = -1; } + /* need to re-run request to recalibrate */ + atari_disable_irq( IRQ_MFP_FDC ); + + setup_req_params( SelectedDrive ); + do_fd_action( SelectedDrive ); + + atari_enable_irq( IRQ_MFP_FDC ); } @@ -737,6 +756,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) if (type) { if (--type >= NUM_DISK_MINORS || minor2disktype[type].drive_types > DriveType) { + finish_fdc(); ret = -EINVAL; goto out; } @@ -745,6 +765,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) } if (!UDT || desc->track >= UDT->blocks/UDT->spt/2 || desc->head >= 2) { + finish_fdc(); ret = -EINVAL; goto out; } @@ -785,6 +806,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) wait_for_completion(&format_wait); + finish_fdc(); ret = FormatError ? -EIO : 0; out: blk_mq_unquiesce_queue(q); @@ -819,6 +841,7 @@ static void do_fd_action( int drive ) else { /* all sectors finished */ fd_end_request_cur(BLK_STS_OK); + finish_fdc(); return; } } @@ -1222,8 +1245,8 @@ static void fd_rwsec_done1(int status) } else { /* all sectors finished */ - finish_fdc(); fd_end_request_cur(BLK_STS_OK); + finish_fdc(); } return; @@ -1345,7 +1368,7 @@ static void fd_times_out(struct timer_list *unused) static void finish_fdc( void ) { - if (!NeedSeek) { + if (!NeedSeek || !stdma_is_locked_by(floppy_irq)) { finish_fdc_done( 0 ); } else { @@ -1380,7 +1403,8 @@ static void finish_fdc_done( int dummy ) start_motor_off_timer(); local_irq_save(flags); - stdma_release(); + if (stdma_is_locked_by(floppy_irq)) + stdma_release(); local_irq_restore(flags); DPRINT(("finish_fdc() finished\n")); @@ -1477,7 +1501,9 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, int drive = floppy - unit; int type = floppy->type; - DPRINT(("Queue request: drive %d type %d last %d\n", drive, type, bd->last)); + DPRINT(("Queue request: drive %d type %d sectors %d of %d last %d\n", + drive, type, blk_rq_cur_sectors(bd->rq), + blk_rq_sectors(bd->rq), bd->last)); spin_lock_irq(&ataflop_lock); if (fd_request) { @@ -1499,6 +1525,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, /* drive not connected */ printk(KERN_ERR "Unknown Device: fd%d\n", drive ); fd_end_request_cur(BLK_STS_IOERR); + stdma_release(); goto out; } @@ -1515,11 +1542,13 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, if (--type >= NUM_DISK_MINORS) { printk(KERN_WARNING "fd%d: invalid disk format", drive ); fd_end_request_cur(BLK_STS_IOERR); + stdma_release(); goto out; } if (minor2disktype[type].drive_types > DriveType) { printk(KERN_WARNING "fd%d: unsupported disk format", drive ); fd_end_request_cur(BLK_STS_IOERR); + stdma_release(); goto out; } type = minor2disktype[type].index; @@ -1620,6 +1649,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* what if type > 0 here? Overwrite specified entry ? */ if (type) { /* refuse to re-set a predefined type for now */ + finish_fdc(); return -EINVAL; } @@ -1687,8 +1717,10 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* sanity check */ if (setprm.track != dtp->blocks/dtp->spt/2 || - setprm.head != 2) + setprm.head != 2) { + finish_fdc(); return -EINVAL; + } UDT = dtp; set_capacity(floppy->disk, UDT->blocks); -- 2.17.1

1 year, 8 months

2
1
0 0

[PATCH 4.19.y 0/2] KVM: arm64: VGIC ITS fix backports

by Oliver Upton

Oliver Upton (2): KVM: arm64: vgic-its: Test for valid IRQ in its_sync_lpi_pending_table() KVM: arm64: vgic-its: Test for valid IRQ in MOVALL handler virt/kvm/arm/vgic/vgic-its.c | 5 +++++ 1 file changed, 5 insertions(+) base-commit: ab219d38aef198d26083cc800954d352acd5137b -- 2.44.0.rc1.240.g4c46232300-goog

1 year, 8 months

2
3
0 0

FAILED: patch "[PATCH] mm/zswap: invalidate duplicate entry when !zswap_enabled" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 678e54d4bb9a4822f8ae99690ac131c5d490cdb1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022622-resent-ripeness-43f1@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: 678e54d4bb9a ("mm/zswap: invalidate duplicate entry when !zswap_enabled") a65b0e7607cc ("zswap: make shrinking memcg-aware") ddc1a5cbc05d ("mempolicy: alloc_pages_mpol() for NUMA policy without vma") 23e4883248f0 ("mm: add page_rmappable_folio() wrapper") c36f6e6dff4d ("mempolicy trivia: slightly more consistent naming") 7f1ee4e20708 ("mempolicy trivia: delete those ancient pr_debug()s") 1cb5d11a370f ("mempolicy: fix migrate_pages(2) syscall return nr_failed") 3657fdc2451a ("mm: move vma_policy() and anon_vma_name() decls to mm_types.h") 3022fd7af960 ("shmem: _add_to_page_cache() before shmem_inode_acct_blocks()") 054a9f7ccd0a ("shmem: move memcg charge out of shmem_add_to_page_cache()") 4199f51a7eb2 ("shmem: shmem_acct_blocks() and shmem_inode_acct_blocks()") e3e1a5067fd2 ("shmem: remove vma arg from shmem_get_folio_gfp()") 75c70128a673 ("mm: mempolicy: make mpol_misplaced() to take a folio") cda6d93672ac ("mm: memory: make numa_migrate_prep() to take a folio") 6695cf68b15c ("mm: memory: use a folio in do_numa_page()") 667ffc31aa95 ("mm: huge_memory: use a folio in do_huge_pmd_numa_page()") 73eab3ca481e ("mm: migrate: convert migrate_misplaced_page() to migrate_misplaced_folio()") 2ac9e99f3b21 ("mm: migrate: convert numamigrate_isolate_page() to numamigrate_isolate_folio()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 678e54d4bb9a4822f8ae99690ac131c5d490cdb1 Mon Sep 17 00:00:00 2001 From: Chengming Zhou <zhouchengming(a)bytedance.com> Date: Thu, 8 Feb 2024 02:32:54 +0000 Subject: [PATCH] mm/zswap: invalidate duplicate entry when !zswap_enabled We have to invalidate any duplicate entry even when !zswap_enabled since zswap can be disabled anytime. If the folio store success before, then got dirtied again but zswap disabled, we won't invalidate the old duplicate entry in the zswap_store(). So later lru writeback may overwrite the new data in swapfile. Link: https://lkml.kernel.org/r/20240208023254.3873823-1-chengming.zhou@linux.dev Fixes: 42c06a0e8ebe ("mm: kill frontswap") Signed-off-by: Chengming Zhou <zhouchengming(a)bytedance.com> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: Yosry Ahmed <yosryahmed(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index 36903d938c15..db4625af65fb 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1518,7 +1518,7 @@ bool zswap_store(struct folio *folio) if (folio_test_large(folio)) return false; - if (!zswap_enabled || !tree) + if (!tree) return false; /* @@ -1533,6 +1533,10 @@ bool zswap_store(struct folio *folio) zswap_invalidate_entry(tree, dupentry); } spin_unlock(&tree->lock); + + if (!zswap_enabled) + return false; + objcg = get_obj_cgroup_from_folio(folio); if (objcg && !obj_cgroup_may_zswap(objcg)) { memcg = get_mem_cgroup_from_objcg(objcg);

1 year, 8 months

4
3
0 0

FAILED: patch "[PATCH] PCI/MSI: Prevent MSI hardware interrupt number truncation" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x db744ddd59be798c2627efbfc71f707f5a935a40 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022609-womanless-imprison-678c@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: db744ddd59be ("PCI/MSI: Prevent MSI hardware interrupt number truncation") aa423ac4221a ("PCI/MSI: Split out irqdomain code") a01e09ef1237 ("PCI/MSI: Split out !IRQDOMAIN code") 54324c2f3d72 ("PCI/MSI: Split out CONFIG_PCI_MSI independent part") 288c81ce4be7 ("PCI/MSI: Move code into a separate directory") 29a03ada4a00 ("PCI/MSI: Cleanup include zoo") ae72f3156729 ("PCI/MSI: Make arch_restore_msi_irqs() less horrible.") e58f2259b91c ("genirq/msi, treewide: Use a named struct for PCI/MSI attributes") ade044a3d0f0 ("PCI/MSI: Remove msi_desc_to_pci_sysdata()") 9e8688c5f299 ("PCI/MSI: Make pci_msi_domain_write_msg() static") 29bbc35e29d9 ("PCI/MSI: Fix pci_irq_vector()/pci_irq_get_affinity()") c36e33e2f477 ("Merge tag 'irq-urgent-2021-11-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From db744ddd59be798c2627efbfc71f707f5a935a40 Mon Sep 17 00:00:00 2001 From: Vidya Sagar <vidyas(a)nvidia.com> Date: Mon, 15 Jan 2024 19:26:49 +0530 Subject: [PATCH] PCI/MSI: Prevent MSI hardware interrupt number truncation While calculating the hardware interrupt number for a MSI interrupt, the higher bits (i.e. from bit-5 onwards a.k.a domain_nr >= 32) of the PCI domain number gets truncated because of the shifted value casting to return type of pci_domain_nr() which is 'int'. This for example is resulting in same hardware interrupt number for devices 0019:00:00.0 and 0039:00:00.0. To address this cast the PCI domain number to 'irq_hw_number_t' before left shifting it to calculate the hardware interrupt number. Please note that this fixes the issue only on 64-bit systems and doesn't change the behavior for 32-bit systems i.e. the 32-bit systems continue to have the issue. Since the issue surfaces only if there are too many PCIe controllers in the system which usually is the case in modern server systems and they don't tend to run 32-bit kernels. Fixes: 3878eaefb89a ("PCI/MSI: Enhance core to support hierarchy irqdomain") Signed-off-by: Vidya Sagar <vidyas(a)nvidia.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Shanker Donthineni <sdonthineni(a)nvidia.com> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20240115135649.708536-1-vidyas@nvidia.com diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index c8be056c248d..cfd84a899c82 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -61,7 +61,7 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) return (irq_hw_number_t)desc->msi_index | pci_dev_id(dev) << 11 | - (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; + ((irq_hw_number_t)(pci_domain_nr(dev->bus) & 0xFFFFFFFF)) << 27; } static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,

1 year, 8 months

3
2
0 0

[PATCH 5.15.y] cifs: fix mid leak during reconnection after timeout threshold

by Harshit Mogalapalli

From: Shyam Prasad N <nspmangalore(a)gmail.com> commit 69cba9d3c1284e0838ae408830a02c4a063104bc upstream. When the number of responses with status of STATUS_IO_TIMEOUT exceeds a specified threshold (NUM_STATUS_IO_TIMEOUT), we reconnect the connection. But we do not return the mid, or the credits returned for the mid, or reduce the number of in-flight requests. This bug could result in the server->in_flight count to go bad, and also cause a leak in the mids. This change moves the check to a few lines below where the response is decrypted, even of the response is read from the transform header. This way, the code for returning the mids can be reused. Also, the cifs_reconnect was reconnecting just the transport connection before. In case of multi-channel, this may not be what we want to do after several timeouts. Changed that to reconnect the session and the tree too. Also renamed NUM_STATUS_IO_TIMEOUT to a more appropriate name MAX_STATUS_IO_TIMEOUT. Fixes: 8e670f77c4a5 ("Handle STATUS_IO_TIMEOUT gracefully") Signed-off-by: Shyam Prasad N <sprasad(a)microsoft.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> [Harshit: Backport to 5.15.y] Conflicts: fs/cifs/connect.c -- 5.15.y doesn't have commit 183eea2ee5ba ("cifs: reconnect only the connection and not smb session where possible") -- User cifs_reconnect(server) instead of cifs_reconnect(server, true) Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> --- Would be nice to get a review from author/maintainer of the upstream patch. A backport request was made previously but the patch didnot apply cleanly then: https://lore.kernel.org/all/CANT5p=oPGnCd4H5ppMbAiHsAKMor3LT_aQRqU7tKu=q6q1… xfstests with cifs done: before and after patching with this patch on 5.15.149. There is no change in test results before and after the patch. Ran: cifs/001 generic/001 generic/002 generic/005 generic/006 generic/007 generic/010 generic/011 generic/013 generic/014 generic/023 generic/024 generic/028 generic/029 generic/030 generic/036 generic/069 generic/074 generic/075 generic/084 generic/091 generic/095 generic/098 generic/100 generic/109 generic/112 generic/113 generic/124 generic/127 generic/129 generic/130 generic/132 generic/133 generic/135 generic/141 generic/169 generic/198 generic/207 generic/208 generic/210 generic/211 generic/212 generic/221 generic/239 generic/241 generic/245 generic/246 generic/247 generic/248 generic/249 generic/257 generic/263 generic/285 generic/286 generic/308 generic/309 generic/310 generic/315 generic/323 generic/339 generic/340 generic/344 generic/345 generic/346 generic/354 generic/360 generic/393 generic/394 Not run: generic/010 generic/286 generic/315 Failures: generic/075 generic/112 generic/127 generic/285 Failed 4 of 68 tests SECTION -- smb3 ========================= Ran: cifs/001 generic/001 generic/002 generic/005 generic/006 generic/007 generic/010 generic/011 generic/013 generic/014 generic/023 generic/024 generic/028 generic/029 generic/030 generic/036 generic/069 generic/074 generic/075 generic/084 generic/091 generic/095 generic/098 generic/100 generic/109 generic/112 generic/113 generic/124 generic/127 generic/129 generic/130 generic/132 generic/133 generic/135 generic/141 generic/169 generic/198 generic/207 generic/208 generic/210 generic/211 generic/212 generic/221 generic/239 generic/241 generic/245 generic/246 generic/247 generic/248 generic/249 generic/257 generic/263 generic/285 generic/286 generic/308 generic/309 generic/310 generic/315 generic/323 generic/339 generic/340 generic/344 generic/345 generic/346 generic/354 generic/360 generic/393 generic/394 Not run: generic/010 generic/014 generic/129 generic/130 generic/239 Failures: generic/075 generic/091 generic/112 generic/127 generic/263 generic/285 generic/286 Failed 7 of 68 tests SECTION -- smb21 ========================= Ran: cifs/001 generic/001 generic/002 generic/005 generic/006 generic/007 generic/010 generic/011 generic/013 generic/014 generic/023 generic/024 generic/028 generic/029 generic/030 generic/036 generic/069 generic/074 generic/075 generic/084 generic/091 generic/095 generic/098 generic/100 generic/109 generic/112 generic/113 generic/124 generic/127 generic/129 generic/130 generic/132 generic/133 generic/135 generic/141 generic/169 generic/198 generic/207 generic/208 generic/210 generic/211 generic/212 generic/221 generic/239 generic/241 generic/245 generic/246 generic/247 generic/248 generic/249 generic/257 generic/263 generic/285 generic/286 generic/308 generic/309 generic/310 generic/315 generic/323 generic/339 generic/340 generic/344 generic/345 generic/346 generic/354 generic/360 generic/393 generic/394 Not run: generic/010 generic/014 generic/129 generic/130 generic/239 generic/286 generic/315 Failures: generic/075 generic/112 generic/127 generic/285 Failed 4 of 68 tests SECTION -- smb2 ========================= Ran: cifs/001 generic/001 generic/002 generic/005 generic/006 generic/007 generic/010 generic/011 generic/013 generic/014 generic/023 generic/024 generic/028 generic/029 generic/030 generic/036 generic/069 generic/074 generic/075 generic/084 generic/091 generic/095 generic/098 generic/100 generic/109 generic/112 generic/113 generic/124 generic/127 generic/129 generic/130 generic/132 generic/133 generic/135 generic/141 generic/169 generic/198 generic/207 generic/208 generic/210 generic/211 generic/212 generic/221 generic/239 generic/241 generic/245 generic/246 generic/247 generic/248 generic/249 generic/257 generic/263 generic/285 generic/286 generic/308 generic/309 generic/310 generic/315 generic/323 generic/339 generic/340 generic/344 generic/345 generic/346 generic/354 generic/360 generic/393 generic/394 Not run: generic/010 generic/286 generic/315 Failures: generic/075 generic/112 generic/127 generic/285 Failed 4 of 68 tests --- fs/cifs/connect.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a521c705b0d7..a3e4811b7871 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -59,7 +59,7 @@ extern bool disable_legacy_dialects; #define TLINK_IDLE_EXPIRE (600 * HZ) /* Drop the connection to not overload the server */ -#define NUM_STATUS_IO_TIMEOUT 5 +#define MAX_STATUS_IO_TIMEOUT 5 struct mount_ctx { struct cifs_sb_info *cifs_sb; @@ -965,6 +965,7 @@ cifs_demultiplex_thread(void *p) struct mid_q_entry *mids[MAX_COMPOUND]; char *bufs[MAX_COMPOUND]; unsigned int noreclaim_flag, num_io_timeout = 0; + bool pending_reconnect = false; noreclaim_flag = memalloc_noreclaim_save(); cifs_dbg(FYI, "Demultiplex PID: %d\n", task_pid_nr(current)); @@ -1004,6 +1005,8 @@ cifs_demultiplex_thread(void *p) cifs_dbg(FYI, "RFC1002 header 0x%x\n", pdu_length); if (!is_smb_response(server, buf[0])) continue; + + pending_reconnect = false; next_pdu: server->pdu_size = pdu_length; @@ -1063,10 +1066,13 @@ cifs_demultiplex_thread(void *p) if (server->ops->is_status_io_timeout && server->ops->is_status_io_timeout(buf)) { num_io_timeout++; - if (num_io_timeout > NUM_STATUS_IO_TIMEOUT) { - cifs_reconnect(server); + if (num_io_timeout > MAX_STATUS_IO_TIMEOUT) { + cifs_server_dbg(VFS, + "Number of request timeouts exceeded %d. Reconnecting", + MAX_STATUS_IO_TIMEOUT); + + pending_reconnect = true; num_io_timeout = 0; - continue; } } @@ -1113,6 +1119,11 @@ cifs_demultiplex_thread(void *p) buf = server->smallbuf; goto next_pdu; } + + /* do this reconnect at the very end after processing all MIDs */ + if (pending_reconnect) + cifs_reconnect(server); + } /* end while !EXITING */ /* buffer usually freed in free_mid - need to free it here on exit */ -- 2.43.0

1 year, 8 months

3
2
0 0

FAILED: patch "[PATCH] mm: zswap: fix missing folio cleanup in writeback race path" failed to apply to 6.7-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.7-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.7.y git checkout FETCH_HEAD git cherry-pick -x e3b63e966cac0bf78aaa1efede1827a252815a1d # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022610-amino-basically-add3@gregkh' --subject-prefix 'PATCH 6.7.y' HEAD^.. Possible dependencies: e3b63e966cac ("mm: zswap: fix missing folio cleanup in writeback race path") 96c7b0b42239 ("mm: return the folio from __read_swap_cache_async()") e947ba0bbf47 ("mm/zswap: cleanup zswap_writeback_entry()") 32acba4c0483 ("mm/zswap: refactor out __zswap_load()") c75f5c1e0f1d ("mm/zswap: reuse dstmem when decompress") b5ba474f3f51 ("zswap: shrink zswap pool based on memory pressure") a65b0e7607cc ("zswap: make shrinking memcg-aware") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e3b63e966cac0bf78aaa1efede1827a252815a1d Mon Sep 17 00:00:00 2001 From: Yosry Ahmed <yosryahmed(a)google.com> Date: Thu, 25 Jan 2024 08:51:27 +0000 Subject: [PATCH] mm: zswap: fix missing folio cleanup in writeback race path In zswap_writeback_entry(), after we get a folio from __read_swap_cache_async(), we grab the tree lock again to check that the swap entry was not invalidated and recycled. If it was, we delete the folio we just added to the swap cache and exit. However, __read_swap_cache_async() returns the folio locked when it is newly allocated, which is always true for this path, and the folio is ref'd. Make sure to unlock and put the folio before returning. This was discovered by code inspection, probably because this path handles a race condition that should not happen often, and the bug would not crash the system, it will only strand the folio indefinitely. Link: https://lkml.kernel.org/r/20240125085127.1327013-1-yosryahmed@google.com Fixes: 04fc7816089c ("mm: fix zswap writeback race condition") Signed-off-by: Yosry Ahmed <yosryahmed(a)google.com> Reviewed-by: Chengming Zhou <zhouchengming(a)bytedance.com> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> Reviewed-by: Nhat Pham <nphamcs(a)gmail.com> Cc: Domenico Cerasuolo <cerasuolodomenico(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index 350dd2fc8159..d2423247acfd 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1440,6 +1440,8 @@ static int zswap_writeback_entry(struct zswap_entry *entry, if (zswap_rb_search(&tree->rbroot, swp_offset(entry->swpentry)) != entry) { spin_unlock(&tree->lock); delete_from_swap_cache(folio); + folio_unlock(folio); + folio_put(folio); return -ENOMEM; } spin_unlock(&tree->lock);

1 year, 8 months

3
4
0 0

[PATCH v4 2/2] fs/aio: Make io_cancel() generate completions again

by Bart Van Assche

The following patch accidentally removed the code for delivering completions for cancelled reads and writes to user space: "[PATCH 04/33] aio: remove retry-based AIO" (https://lore.kernel.org/all/1363883754-27966-5-git-send-email-koverstreet@g…) From that patch: - if (kiocbIsCancelled(iocb)) { - ret = -EINTR; - aio_complete(iocb, ret, 0); - /* must not access the iocb after this */ - goto out; - } This leads to a leak in user space of a struct iocb. Hence this patch that restores the code that reports to user space that a read or write has been cancelled successfully. Fixes: 41003a7bcfed ("aio: remove retry-based AIO") Cc: Christoph Hellwig <hch(a)lst.de> Cc: Avi Kivity <avi(a)scylladb.com> Cc: Sandeep Dhavale <dhavale(a)google.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Bart Van Assche <bvanassche(a)acm.org> --- fs/aio.c | 27 +++++++++++---------------- 1 file changed, 11 insertions(+), 16 deletions(-) diff --git a/fs/aio.c b/fs/aio.c index da18dbcfcb22..28223f511931 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -2165,14 +2165,11 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, #endif /* sys_io_cancel: - * Attempts to cancel an iocb previously passed to io_submit. If - * the operation is successfully cancelled, the resulting event is - * copied into the memory pointed to by result without being placed - * into the completion queue and 0 is returned. May fail with - * -EFAULT if any of the data structures pointed to are invalid. - * May fail with -EINVAL if aio_context specified by ctx_id is - * invalid. May fail with -EAGAIN if the iocb specified was not - * cancelled. Will fail with -ENOSYS if not implemented. + * Attempts to cancel an iocb previously passed to io_submit(). If the + * operation is successfully cancelled 0 is returned. May fail with + * -EFAULT if any of the data structures pointed to are invalid. May + * fail with -EINVAL if aio_context specified by ctx_id is invalid. Will + * fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result) @@ -2203,14 +2200,12 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, } spin_unlock_irq(&ctx->ctx_lock); - if (!ret) { - /* - * The result argument is no longer used - the io_event is - * always delivered via the ring buffer. -EINPROGRESS indicates - * cancellation is progress: - */ - ret = -EINPROGRESS; - } + /* + * The result argument is no longer used - the io_event is always + * delivered via the ring buffer. + */ + if (ret == 0 && kiocb->rw.ki_flags & IOCB_AIO_RW) + aio_complete_rw(&kiocb->rw, -EINTR); percpu_ref_put(&ctx->users);

1 year, 8 months

3
4
0 0

[PATCH 6.1.y 1/2] erofs: simplify compression configuration parser

by Yue Hu

From: Gao Xiang <hsiangkao(a)linux.alibaba.com> [ Upstream commit efb4fb02cef3ab410b603c8f0e1c67f61d55f542 ] Move erofs_load_compr_cfgs() into decompressor.c as well as introduce a callback instead of a hard-coded switch for each algorithm for simplicity. Reviewed-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Gao Xiang <hsiangkao(a)linux.alibaba.com> Link: https://lore.kernel.org/r/20231022130957.11398-1-xiang@kernel.org Stable-dep-of: 118a8cf504d7 ("erofs: fix inconsistent per-file compression format") Signed-off-by: Yue Hu <huyue2(a)coolpad.com> --- fs/erofs/compress.h | 4 ++ fs/erofs/decompressor.c | 60 ++++++++++++++++++++++++++++-- fs/erofs/decompressor_lzma.c | 4 +- fs/erofs/internal.h | 28 ++------------ fs/erofs/super.c | 72 +++++------------------------------- 5 files changed, 76 insertions(+), 92 deletions(-) diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h index 26fa170090b8..c4a3187bdb8f 100644 --- a/fs/erofs/compress.h +++ b/fs/erofs/compress.h @@ -21,6 +21,8 @@ struct z_erofs_decompress_req { }; struct z_erofs_decompressor { + int (*config)(struct super_block *sb, struct erofs_super_block *dsb, + void *data, int size); int (*decompress)(struct z_erofs_decompress_req *rq, struct page **pagepool); char *name; @@ -93,6 +95,8 @@ int z_erofs_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); /* prototypes for specific algorithms */ +int z_erofs_load_lzma_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size); int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); #endif diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 0cfad74374ca..ae3cfd018d99 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -24,11 +24,11 @@ struct z_erofs_lz4_decompress_ctx { unsigned int oend; }; -int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int size) +static int z_erofs_load_lz4_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size) { struct erofs_sb_info *sbi = EROFS_SB(sb); + struct z_erofs_lz4_cfgs *lz4 = data; u16 distance; if (lz4) { @@ -374,17 +374,71 @@ static struct z_erofs_decompressor decompressors[] = { .name = "interlaced" }, [Z_EROFS_COMPRESSION_LZ4] = { + .config = z_erofs_load_lz4_config, .decompress = z_erofs_lz4_decompress, .name = "lz4" }, #ifdef CONFIG_EROFS_FS_ZIP_LZMA [Z_EROFS_COMPRESSION_LZMA] = { + .config = z_erofs_load_lzma_config, .decompress = z_erofs_lzma_decompress, .name = "lzma" }, #endif }; +int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + unsigned int algs, alg; + erofs_off_t offset; + int size, ret = 0; + + if (!erofs_sb_has_compr_cfgs(sbi)) { + sbi->available_compr_algs = Z_EROFS_COMPRESSION_LZ4; + return z_erofs_load_lz4_config(sb, dsb, NULL, 0); + } + + sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); + if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { + erofs_err(sb, "unidentified algorithms %x, please upgrade kernel", + sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); + return -EOPNOTSUPP; + } + + offset = EROFS_SUPER_OFFSET + sbi->sb_size; + alg = 0; + for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { + void *data; + + if (!(algs & 1)) + continue; + + data = erofs_read_metadata(sb, &buf, &offset, &size); + if (IS_ERR(data)) { + ret = PTR_ERR(data); + break; + } + + if (alg >= ARRAY_SIZE(decompressors) || + !decompressors[alg].config) { + erofs_err(sb, "algorithm %d isn't enabled on this kernel", + alg); + ret = -EOPNOTSUPP; + } else { + ret = decompressors[alg].config(sb, + dsb, data, size); + } + + kfree(data); + if (ret) + break; + } + erofs_put_metabuf(&buf); + return ret; +} + int z_erofs_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool) { diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 49addc345aeb..970464c4b676 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -72,10 +72,10 @@ int z_erofs_lzma_init(void) } int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size) + struct erofs_super_block *dsb, void *data, int size) { static DEFINE_MUTEX(lzma_resize_mutex); + struct z_erofs_lzma_cfgs *lzma = data; unsigned int dict_size, i; struct z_erofs_lzma *strm, *head = NULL; int err; diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index d8d09fc3ed65..79a7a5815ea6 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -471,6 +471,8 @@ struct erofs_map_dev { /* data.c */ extern const struct file_operations erofs_file_fops; +void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp); void erofs_unmap_metabuf(struct erofs_buf *buf); void erofs_put_metabuf(struct erofs_buf *buf); void *erofs_bread(struct erofs_buf *buf, struct inode *inode, @@ -565,9 +567,7 @@ void z_erofs_exit_zip_subsystem(void); int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, struct erofs_workgroup *egrp); int erofs_try_to_free_cached_page(struct page *page); -int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int len); +int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb); #else static inline void erofs_shrinker_register(struct super_block *sb) {} static inline void erofs_shrinker_unregister(struct super_block *sb) {} @@ -575,36 +575,14 @@ static inline int erofs_init_shrinker(void) { return 0; } static inline void erofs_exit_shrinker(void) {} static inline int z_erofs_init_zip_subsystem(void) { return 0; } static inline void z_erofs_exit_zip_subsystem(void) {} -static inline int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int len) -{ - if (lz4 || dsb->u1.lz4_max_distance) { - erofs_err(sb, "lz4 algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} #endif /* !CONFIG_EROFS_FS_ZIP */ #ifdef CONFIG_EROFS_FS_ZIP_LZMA int z_erofs_lzma_init(void); void z_erofs_lzma_exit(void); -int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size); #else static inline int z_erofs_lzma_init(void) { return 0; } static inline int z_erofs_lzma_exit(void) { return 0; } -static inline int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size) { - if (lzma) { - erofs_err(sb, "lzma algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} #endif /* !CONFIG_EROFS_FS_ZIP */ /* flags for erofs_fscache_register_cookie() */ diff --git a/fs/erofs/super.c b/fs/erofs/super.c index bd8bf8fc2f5d..f2647126cb2f 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -126,8 +126,8 @@ static bool check_layout_compatibility(struct super_block *sb, #ifdef CONFIG_EROFS_FS_ZIP /* read variable-sized metadata, offset will be aligned by 4-byte */ -static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, - erofs_off_t *offset, int *lengthp) +void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp) { u8 *buffer, *ptr; int len, i, cnt; @@ -159,64 +159,15 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, } return buffer; } - -static int erofs_load_compr_cfgs(struct super_block *sb, - struct erofs_super_block *dsb) -{ - struct erofs_sb_info *sbi = EROFS_SB(sb); - struct erofs_buf buf = __EROFS_BUF_INITIALIZER; - unsigned int algs, alg; - erofs_off_t offset; - int size, ret = 0; - - sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); - if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { - erofs_err(sb, "try to load compressed fs with unsupported algorithms %x", - sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); - return -EINVAL; - } - - offset = EROFS_SUPER_OFFSET + sbi->sb_size; - alg = 0; - for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { - void *data; - - if (!(algs & 1)) - continue; - - data = erofs_read_metadata(sb, &buf, &offset, &size); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - - switch (alg) { - case Z_EROFS_COMPRESSION_LZ4: - ret = z_erofs_load_lz4_config(sb, dsb, data, size); - break; - case Z_EROFS_COMPRESSION_LZMA: - ret = z_erofs_load_lzma_config(sb, dsb, data, size); - break; - default: - DBG_BUGON(1); - ret = -EFAULT; - } - kfree(data); - if (ret) - break; - } - erofs_put_metabuf(&buf); - return ret; -} #else -static int erofs_load_compr_cfgs(struct super_block *sb, - struct erofs_super_block *dsb) +static int z_erofs_parse_cfgs(struct super_block *sb, + struct erofs_super_block *dsb) { - if (dsb->u1.available_compr_algs) { - erofs_err(sb, "try to load compressed fs when compression is disabled"); - return -EINVAL; - } - return 0; + if (!dsb->u1.available_compr_algs) + return 0; + + erofs_err(sb, "compression disabled, unable to mount compressed EROFS"); + return -EOPNOTSUPP; } #endif @@ -398,10 +349,7 @@ static int erofs_read_superblock(struct super_block *sb) } /* parse on-disk compression configurations */ - if (erofs_sb_has_compr_cfgs(sbi)) - ret = erofs_load_compr_cfgs(sb, dsb); - else - ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0); + ret = z_erofs_parse_cfgs(sb, dsb); if (ret < 0) goto out; -- 2.17.1

1 year, 8 months

3
4
0 0

[PATCH v2] nvmem: rmem: Fix return value of rmem_read()

by Joy Chakraborty

reg_read() callback registered with nvmem core expects an integer error as a return value but rmem_read() returns the number of bytes read, as a result error checks in nvmem core fail even when they shouldn't. Return 0 on success where number of bytes read match the number of bytes requested and a negative error -EINVAL on all other cases. Fixes: 5a3fa75a4d9c ("nvmem: Add driver to expose reserved memory as nvmem") Cc: stable(a)vger.kernel.org Signed-off-by: Joy Chakraborty <joychakr(a)google.com> --- drivers/nvmem/rmem.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/nvmem/rmem.c b/drivers/nvmem/rmem.c index 752d0bf4445e..a74dfa279ff4 100644 --- a/drivers/nvmem/rmem.c +++ b/drivers/nvmem/rmem.c @@ -46,7 +46,12 @@ static int rmem_read(void *context, unsigned int offset, memunmap(addr); - return count; + if (count != bytes) { + dev_err(priv->dev, "Failed read memory (%d)\n", count); + return -EINVAL; + } + + return 0; } static int rmem_probe(struct platform_device *pdev) -- 2.43.0.594.gd9cf4e227d-goog

1 year, 8 months

3
13
0 0

Re: Follow Up

by Olivia Stewart

Hi, I wanted to check with you if you had a time to go through my previous email, Let me know your thoughts about acquiring this email list Regards, *Olivia* ______________________________________________________________________________________________ Hi, I hope you are the right person to discuss about *Healthcare Leads*, which includes complete contact details, and tele-verified email addresses. Please find the Leads Breakdown Chart below: *Criteria* *Counts* *Criteria* *Counts* *Criteria* *Counts* Allergy immunology 5,064 Healthcare Technology 20,540 Plastic surgery 8,371 Anesthesiology 30,155 Nephrology 6,606 Preventive medicine 6,642 Cardiology 24,577 Neurological surgery 7,066 Psychiatry 4,315 Dermatology 8,467 Neurology 13,354 Radiology 32,763 Emergency medicine 22,300 Obgyn 35,163 Surgery 39,517 Endocrinology diabetes metabolism 3,756 Oncology 17,881 Urology 10,135 Family practice1 62,544 Ophthalmology 15,237 Physician 100,000 Gastroenterology 11,913 Orthopedics 22,145 Doctors 128,000 General practice 12,957 Other 15,559 Dentists 150,200 Geriatrics Doctors 9,634 Otolaryngology 9,539 Osteopathic 25,000 Infectious disease 5,677 Pathology 15,467 Acupuncture 5,000 Internal medicine1 120,029 Pediatrics 55,684 Chiropractors 11,000 Haematology Doctors 12,850 Physical medicine 8,437 Rheumatology 5,000 *Data Fields:* Every lead includes Name, Company, Job Title, Website, Physical Address, Industry, *Phone Number and Verified/Opt-In Email Address.* Please let me know if you have any queries about our custom opt-in list and I would love to answer them. Kindly share your thoughts. Warm Regards, *Olivia Stewart* *Marketing Executive * ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- We respect your privacy, if you want to remove it from this list. Please reply with the subject line as “Leave Out”.

1 year, 8 months

1
0
0 0

[PATCH net 00/10] mptcp: more misc. fixes for v6.8

by Matthieu Baerts (NGI0)

This series includes 6 types of fixes: - Patch 1 fixes v4 mapped in v6 addresses support for the userspace PM, when asking to delete a subflow. It was done everywhere else, but not there. Patch 2 validates the modification, thanks to a subtest in mptcp_join.sh. These patches can be backported up to v5.19. - Patch 3 is a small fix for a recent bug-fix patch, just to avoid printing an irrelevant warning (pr_warn()) once. It can be backported up to v5.6, alongside the bug-fix that has been introduced in the v6.8-rc5. - Patches 4 to 6 are fixes for bugs found by Paolo while working on TCP_NOTSENT_LOWAT support for MPTCP. These fixes can improve the performances in some cases. Patches can be backported up to v5.6, v5.11 and v6.7 respectively. - Patch 7 makes sure 'ss -M' is available when starting MPTCP Join selftest as it is required for some subtests since v5.18. - Patch 8 fixes a possible double-free on socket dismantle. The issue always existed, but was unnoticed because it was not causing any problem so far. This fix can be backported up to v5.6. - Patch 9 is a fix for a very recent patch causing lockdep warnings in subflow diag. The patch causing the regression -- which fixes another issue present since v5.7 -- should be part of the future v6.8-rc6. Patch 10 validates the modification, thanks to a new subtest in diag.sh. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Davide Caratti (1): mptcp: fix double-free on socket dismantle Geliang Tang (3): mptcp: map v4 address to v6 when destroying subflow selftests: mptcp: rm subflow with v4/v4mapped addr selftests: mptcp: join: add ss mptcp support check Matthieu Baerts (NGI0) (1): mptcp: avoid printing warning once on client side Paolo Abeni (5): mptcp: push at DSS boundaries mptcp: fix snd_wnd initialization for passive socket mptcp: fix potential wake-up event loss mptcp: fix possible deadlock in subflow diag selftests: mptcp: explicitly trigger the listener diag code-path net/mptcp/diag.c | 3 ++ net/mptcp/options.c | 2 +- net/mptcp/pm_userspace.c | 10 +++++ net/mptcp/protocol.c | 52 ++++++++++++++++++++++++- net/mptcp/protocol.h | 21 +++++----- tools/testing/selftests/net/mptcp/diag.sh | 30 +++++++++++++- tools/testing/selftests/net/mptcp/mptcp_join.sh | 33 ++++++++++------ tools/testing/selftests/net/mptcp/mptcp_lib.sh | 4 +- 8 files changed, 128 insertions(+), 27 deletions(-) --- base-commit: b0b1210bc150fbd741b4b9fce8a24541306b40fc change-id: 20240223-upstream-net-20240223-misc-fixes-1630cd6b3b0a Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

1 year, 8 months

3
11
0 0

[PATCHi V2] wifi: rtw88: Add missing VID/PIDs doe 8811CU and 8821CU

by Larry Finger

From: Nick Morrow <morrownr(a)gmail.com> Purpose: Add VID/PIDs that are known to be missing for this driver. - removed /* 8811CU */ and /* 8821CU */ as they are redundant since the file is specific to those chips. - removed /* TOTOLINK A650UA v3 */ as the manufacturer. It has a REALTEK VID so it may not be specific to this adapter. Source is https://1EHFQ.trk.elasticemail.com/tracking/click?d=I82H0YR_W_h175Lb3Nkb0D8… Verified and tested. Signed-off-by: Nick Morrow <morrownr(a)gmail.com> Signed-off-by: Larry Finger <Larry.Finger(a)lwfinger.net> Acked-by: Ping-Ke Shih <pkshih(a)realtek.com> Cc: stable(a)vger.kernel.org --- .../net/wireless/realtek/rtw88/rtw8821cu.c | 40 ++++++++++++------- 1 file changed, 26 insertions(+), 14 deletions(-) diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c index 7a5cbdc31ef7..e2c7d9f87683 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c @@ -9,24 +9,36 @@ #include "usb.h" static const struct usb_device_id rtw_8821cu_id_table[] = { - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb82b, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x2006, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8731, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb820, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc821, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb82b, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc80c, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc820, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc821, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82a, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82b, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc811, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8811CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8811, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8811CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x2006, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* TOTOLINK A650UA v3 */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82c, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x331d, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* D-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xc811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* Edimax */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xd811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* Edimax */ {}, }; MODULE_DEVICE_TABLE(usb, rtw_8821cu_id_table); -- 2.43.2 https://1EHFQ.trk.elasticemail.com/tracking/unsubscribe?d=enVLNtTvRHoJzm7zg…

1 year, 8 months

1
0
0 0

RE: [PATCH] wifi:rtw88: Add missing VID/PIDs

by Ping-Ke Shih

> -----Original Message----- > From: Larry Finger <Larry.Finger(a)gmail.com> > Sent: Tuesday, February 27, 2024 9:41 AM > To: Kalle Valo <kvalo(a)kernel.org> > Cc: Johannes Berg <johannes(a)sipsolutions.net>; linux-wireless(a)vger.kernel.org; Nick Morrow > <morrownr(a)gmail.com>; Larry Finger <Larry.Finger(a)lwfinger.net>; stable(a)vger.kernel.org > Subject: [PATCH] wifi:rtw88: Add missing VID/PIDs Missing a space between "wifi:" and "rtw88:", and suggest to mention 8811CU and 8821CU in subject. Others look good to me. > > From: Nick Morrow <morrownr(a)gmail.com> > > Purpose: Add VID/PIDs that are known to be missing for this driver. > - removed /* 8811CU */ and /* 8821CU */ as they are redundant > since the file is specific to those chips. > - removed /* TOTOLINK A650UA v3 */ as the manufacturer. It has a REALTEK > VID so it may not be specific to this adapter. > > Source is > https://1EHFQ.trk.elasticemail.com/tracking/click?d=I82H0YR_W_h175Lb3Nkb0D8… > 0SPxd1Olp3PNJEm7h1Gft8lKFiXqYf1jEjniUnBHTdCi0Ypi2Y9ugy88eGHqb5MB9U0M7ZbBBaOwoaG0eHpd73dxUfRcicgS3TFBvw > 066sdoIh1JxdrADO_ro60 > Verified and tested. > > Signed-off-by: Nick Morrow <morrownr(a)gmail.com> > Signed-off-by: Larry Finger <Larry.Finger(a)lwfinger.net> > Cc: stable(a)vger.kernel.org Acked-by: Ping-Ke Shih <pkshih(a)realtek.com>

1 year, 8 months

1
0
0 0

[PATCH] wifi:rtw88: Add missing VID/PIDs

by Larry Finger

From: Nick Morrow <morrownr(a)gmail.com> Purpose: Add VID/PIDs that are known to be missing for this driver. - removed /* 8811CU */ and /* 8821CU */ as they are redundant since the file is specific to those chips. - removed /* TOTOLINK A650UA v3 */ as the manufacturer. It has a REALTEK VID so it may not be specific to this adapter. Source is https://1EHFQ.trk.elasticemail.com/tracking/click?d=I82H0YR_W_h175Lb3Nkb0D8… Verified and tested. Signed-off-by: Nick Morrow <morrownr(a)gmail.com> Signed-off-by: Larry Finger <Larry.Finger(a)lwfinger.net> Cc: stable(a)vger.kernel.org --- .../net/wireless/realtek/rtw88/rtw8821cu.c | 40 ++++++++++++------- 1 file changed, 26 insertions(+), 14 deletions(-) diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c index 7a5cbdc31ef7..e2c7d9f87683 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c @@ -9,24 +9,36 @@ #include "usb.h" static const struct usb_device_id rtw_8821cu_id_table[] = { - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb82b, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x2006, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8731, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb820, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc821, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb82b, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc80c, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc820, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc821, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82a, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82b, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc811, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8811CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8811, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8811CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x2006, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* TOTOLINK A650UA v3 */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82c, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x331d, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* D-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xc811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* Edimax */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xd811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* Edimax */ {}, }; MODULE_DEVICE_TABLE(usb, rtw_8821cu_id_table); -- 2.43.2 https://1EHFQ.trk.elasticemail.com/tracking/unsubscribe?d=GtKKPX7rhUiB3wTyG…

1 year, 8 months

1
0
0 0

[PATCH v1] usb: typec: altmodes/displayport: add null pointer check for sysfs nodes

by RD Babiera

The DisplayPort driver's sysfs nodes may be present to the userspace before typec_altmode_set_drvdata() completes in dp_altmode_probe. This means that a sysfs read can trigger a NULL pointer error by deferencing dp->hpd in hpd_show or dp->lock in pin_assignment_show, as dev_get_drvdata() returns NULL in those cases. Verify dp drvdata is present in sysfs reads and writes before proceeding. Fixes: 0e3bb7d6894d ("usb: typec: Add driver for DisplayPort alternate mode") Cc: stable(a)vger.kernel.org Signed-off-by: RD Babiera <rdbabiera(a)google.com> --- drivers/usb/typec/altmodes/displayport.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 5a80776c7255..0423326219d8 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -518,6 +518,9 @@ configuration_store(struct device *dev, struct device_attribute *attr, int con; int ret = 0; + if (!dp) + return -ENODEV; + con = sysfs_match_string(configurations, buf); if (con < 0) return con; @@ -563,6 +566,9 @@ static ssize_t configuration_show(struct device *dev, u8 cur; int i; + if (!dp) + return -ENODEV; + mutex_lock(&dp->lock); cap = DP_CAP_CAPABILITY(dp->alt->vdo); @@ -615,6 +621,9 @@ pin_assignment_store(struct device *dev, struct device_attribute *attr, u32 conf; int ret; + if (!dp) + return -ENODEV; + ret = sysfs_match_string(pin_assignments, buf); if (ret < 0) return ret; @@ -666,6 +675,9 @@ static ssize_t pin_assignment_show(struct device *dev, u8 cur; int i; + if (!dp) + return -ENODEV; + mutex_lock(&dp->lock); cur = get_count_order(DP_CONF_GET_PIN_ASSIGN(dp->data.conf)); @@ -698,6 +710,9 @@ static ssize_t hpd_show(struct device *dev, struct device_attribute *attr, char { struct dp_altmode *dp = dev_get_drvdata(dev); + if (!dp) + return -ENODEV; + return sysfs_emit(buf, "%d\n", dp->hpd); } static DEVICE_ATTR_RO(hpd); base-commit: f1a27f081c1fa1eeebf38406e45f29636114470f -- 2.43.0.429.g432eaa2c6b-goog

1 year, 8 months

2
2
0 0

Re: [REGRESSION 6.1.70] system calls with CIFS mounts failing with "Resource temporarily unavailable"

by Mohamed Abuelfotoh, Hazem

It looks like both 5.15.146 and 5.10.206 are impacted by this regression as they both have the bad commit 33eae65c6f (smb: client: fix OOB in SMB2_query_info_init()). We tried to apply the proposed fix eb3e28c1e89b ("smb3: Replace smb2pdu 1-element arrays with flex-arrays”) but there are a lot of dependencies required to do the backport. Is it possible to consider the simple fix that Paulo proposed as a solution for 5.10 and 5.15. We were lucky with 5.4 as it doesn’t have the bad commit because of merge conflict reported in https://lore.kernel.org/all/2023122857-doubling-crazed-27f4@gregkh/T/#m3aa0… diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 05ff8a457a3d..aed5067661de 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3556,7 +3556,7 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, iov[0].iov_base = (char *)req; /* 1 for Buffer */ - iov[0].iov_len = len; + iov[0].iov_len = len - 1; return 0; } Hazem

1 year, 8 months

9
19
0 0

[tip: x86/misc] x86/nmi: Fix the inverse "in NMI handler" check

by tip-bot2 for Breno Leitao

The following commit has been merged into the x86/misc branch of tip: Commit-ID: d54e56f31a34fa38fcb5e91df609f9633419a79a Gitweb: https://git.kernel.org/tip/d54e56f31a34fa38fcb5e91df609f9633419a79a Author: Breno Leitao <leitao(a)debian.org> AuthorDate: Wed, 07 Feb 2024 08:52:35 -08:00 Committer: Thomas Gleixner <tglx(a)linutronix.de> CommitterDate: Mon, 26 Feb 2024 23:41:30 +01:00 x86/nmi: Fix the inverse "in NMI handler" check Commit 344da544f177 ("x86/nmi: Print reasons why backtrace NMIs are ignored") creates a super nice framework to diagnose NMIs. Every time nmi_exc() is called, it increments a per_cpu counter (nsp->idt_nmi_seq). At its exit, it also increments the same counter. By reading this counter it can be seen how many times that function was called (dividing by 2), and, if the function is still being executed, by checking the idt_nmi_seq's least significant bit. On the check side (nmi_backtrace_stall_check()), that variable is queried to check if the NMI is still being executed, but, there is a mistake in the bitwise operation. That code wants to check if the least significant bit of the idt_nmi_seq is set or not, but does the opposite, and checks for all the other bits, which will always be true after the first exc_nmi() executed successfully. This appends the misleading string to the dump "(CPU currently in NMI handler function)" Fix it by checking the least significant bit, and if it is set, append the string. Fixes: 344da544f177 ("x86/nmi: Print reasons why backtrace NMIs are ignored") Signed-off-by: Breno Leitao <leitao(a)debian.org> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Paul E. McKenney <paulmck(a)kernel.org> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20240207165237.1048837-1-leitao@debian.org --- arch/x86/kernel/nmi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index d238679..c95dc1b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -639,7 +639,7 @@ void nmi_backtrace_stall_check(const struct cpumask *btp) msgp = nmi_check_stall_msg[idx]; if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1)) modp = ", but OK because ignore_nmis was set"; - if (nmi_seq & ~0x1) + if (nmi_seq & 0x1) msghp = " (CPU currently in NMI handler function)"; else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq) msghp = " (CPU exited one NMI handler function)";

1 year, 8 months

1
0
0 0

Re: Kernel 6.6.17-LTS breaks almost all bash scripts involving a directory

by Konstantin Ryabitsev

On Mon, Feb 26, 2024 at 05:27:50PM +0200, Радослав Ненчовски wrote: > Hi. IDK how more clear to write it in the title, so let me explain what the > problem is. I'm sending your message to stable instead, because helpdesk is only for requesting help with kernel.org infrastructure. Stable folks, please see below. -K > In the past 4 or 5 years I've been using this script (with an alias) to > compress a single folder: > 7z a "$1.7z" "$1"/ -mx=0 -mmt=8 > > I know it doesn't look like much but essentially it creates a 7z archive > (with "store" level of compression) with a name I've entered right after the > alias. For instance: 7z0 "my dir" will create "my dir.7z". > And in the past 4 or 5 years this script was working just fine because it > was recognizing the slash as an indication that the target to compress is a > directory. > However, ever since 6.6.17-LTS arrived (altough I've heard the same > complaints from people who use the regular rolling kernel, but they didn't > tell me which version) bash stopped recognizing the slash as an indication > for directory and thinks of it as the entire root directory, thus it > attempts to compress not only "my dir" but also the whole root (/) > directory. And it doesn't matter whether I'll put the slash between the > quotes or outside of them - the result is the same. And, naturally, it > throws out an unlimited number of errors about "access denied" to everything > in root. I can't even begin to comprehend why on Earth you or whoever writes > the kernel would make this change. Forget about me but ALL linux sysadmins I > know use all kinds of scripts and changing the slash at the end of a word to > mean "root" instead of a sign for directory is a rude way to ruin their > work. Since this change occurred, I can no longer put a directory in an > archive through CLI and I have to do it through GUI, which is about 10 times > slower. I have a DE and I can do that but what about the sysadmins who > usually use linux without a DE or directly SSH into the distro they're > admins of? With this change you're literally hindering their job! > > I downgraded the kernel to 6.6.15-LTS and the problem disappeared - now the > slash is properly recognized as a sign for directory. > > The point is: *it is urgent that you undo this change back to the way it > was! I'm pretty sure sysadmins will begin to email you about this, if they > haven't already. > *

1 year, 8 months

3
2
0 0

[PATCH 6.6.y] selftests: mptcp: add mptcp_lib_get_counter

by Matthieu Baerts (NGI0)

From: Geliang Tang <geliang.tang(a)suse.com> To avoid duplicated code in different MPTCP selftests, we can add and use helpers defined in mptcp_lib.sh. The helper get_counter() in mptcp_join.sh and get_mib_counter() in mptcp_connect.sh have the same functionality, export get_counter() into mptcp_lib.sh and rename it as mptcp_lib_get_counter(). Use this new helper instead of get_counter() and get_mib_counter(). Use this helper in test_prio() in userspace_pm.sh too instead of open-coding. Reviewed-by: Matthieu Baerts <matttbe(a)kernel.org> Signed-off-by: Geliang Tang <geliang.tang(a)suse.com> Signed-off-by: Mat Martineau <martineau(a)kernel.org> Link: https://lore.kernel.org/r/20231128-send-net-next-2023107-v4-11-8d6b94150f6b… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Stable-dep-of: acaef88f2624 ("selftests: mptcp: diag: check CURRESTAB counters") (cherry picked from commit 61c131f5d4d2b79904af2fdcb2839a9db8e7c55c) Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Notes: - this patch is needed for "selftests: mptcp: diag: check CURRESTAB counters" that has been added to the queue for v6.6 today, to avoid failures and this message: ./diag.sh: line 62: mptcp_lib_get_counter: command not found - conflicts in mptcp_lib.sh because the new helper expected to be placed after mptcp_lib_kill_wait() which has not been backported. --- .../selftests/net/mptcp/mptcp_connect.sh | 41 +++------ .../testing/selftests/net/mptcp/mptcp_join.sh | 88 ++++++++----------- .../testing/selftests/net/mptcp/mptcp_lib.sh | 16 ++++ .../selftests/net/mptcp/userspace_pm.sh | 14 +-- 4 files changed, 73 insertions(+), 86 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index b1fc8afd072d..10cd322e05c4 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -341,21 +341,6 @@ do_ping() return 0 } -# $1: ns, $2: MIB counter -get_mib_counter() -{ - local listener_ns="${1}" - local mib="${2}" - - # strip the header - ip netns exec "${listener_ns}" \ - nstat -z -a "${mib}" | \ - tail -n+2 | \ - while read a count c rest; do - echo $count - done -} - # $1: ns, $2: port wait_local_port_listen() { @@ -441,12 +426,12 @@ do_transfer() nstat -n fi - local stat_synrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local stat_csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + local stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + local stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + local stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -509,11 +494,11 @@ do_transfer() check_transfer $cin $sout "file received by server" rets=$? - local stat_synrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue") + local stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + local stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + local stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + local stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -542,8 +527,8 @@ do_transfer() fi if $checksum; then - local csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) if [ $csum_err_s_nr -gt 0 ]; then diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index bc85570a6b26..a72104dae2b9 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -611,25 +611,9 @@ wait_local_port_listen() done } -# $1: ns ; $2: counter -get_counter() -{ - local ns="${1}" - local counter="${2}" - local count - - count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}') - if [ -z "${count}" ]; then - mptcp_lib_fail_if_expected_feature "${counter} counter" - return 1 - fi - - echo "${count}" -} - rm_addr_count() { - get_counter "${1}" "MPTcpExtRmAddr" + mptcp_lib_get_counter "${1}" "MPTcpExtRmAddr" } # $1: ns, $2: old rm_addr counter in $ns @@ -649,7 +633,7 @@ wait_rm_addr() rm_sf_count() { - get_counter "${1}" "MPTcpExtRmSubflow" + mptcp_lib_get_counter "${1}" "MPTcpExtRmSubflow" } # $1: ns, $2: old rm_sf counter in $ns @@ -672,11 +656,11 @@ wait_mpj() local ns="${1}" local cnt old_cnt - old_cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") + old_cnt=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPJoinAckRx") local i for i in $(seq 10); do - cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") + cnt=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPJoinAckRx") [ "$cnt" = "${old_cnt}" ] || break sleep 0.1 done @@ -1271,7 +1255,7 @@ chk_csum_nr() fi print_check "sum" - count=$(get_counter ${ns1} "MPTcpExtDataCsumErr") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then extra_msg="$extra_msg ns1=$count" fi @@ -1284,7 +1268,7 @@ chk_csum_nr() print_ok fi print_check "csum" - count=$(get_counter ${ns2} "MPTcpExtDataCsumErr") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then extra_msg="$extra_msg ns2=$count" fi @@ -1328,7 +1312,7 @@ chk_fail_nr() fi print_check "ftx" - count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then extra_msg="$extra_msg,tx=$count" fi @@ -1342,7 +1326,7 @@ chk_fail_nr() fi print_check "failrx" - count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then extra_msg="$extra_msg,rx=$count" fi @@ -1375,7 +1359,7 @@ chk_fclose_nr() fi print_check "ctx" - count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$fclose_tx" ]; then @@ -1386,7 +1370,7 @@ chk_fclose_nr() fi print_check "fclzrx" - count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$fclose_rx" ]; then @@ -1416,7 +1400,7 @@ chk_rst_nr() fi print_check "rtx" - count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPRstTx") if [ -z "$count" ]; then print_skip # accept more rst than expected except if we don't expect any @@ -1428,7 +1412,7 @@ chk_rst_nr() fi print_check "rstrx" - count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPRstRx") if [ -z "$count" ]; then print_skip # accept more rst than expected except if we don't expect any @@ -1449,7 +1433,7 @@ chk_infi_nr() local count print_check "itx" - count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtInfiniteMapTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$infi_tx" ]; then @@ -1459,7 +1443,7 @@ chk_infi_nr() fi print_check "infirx" - count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtInfiniteMapRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$infi_rx" ]; then @@ -1488,7 +1472,7 @@ chk_join_nr() fi print_check "syn" - count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_nr" ]; then @@ -1499,7 +1483,7 @@ chk_join_nr() print_check "synack" with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) - count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_ack_nr" ]; then @@ -1516,7 +1500,7 @@ chk_join_nr() fi print_check "ack" - count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$ack_nr" ]; then @@ -1549,8 +1533,8 @@ chk_stale_nr() print_check "stale" - stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale") - recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover") + stale_nr=$(mptcp_lib_get_counter ${ns} "MPTcpExtSubflowStale") + recover_nr=$(mptcp_lib_get_counter ${ns} "MPTcpExtSubflowRecover") if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then print_skip elif [ $stale_nr -lt $stale_min ] || @@ -1587,7 +1571,7 @@ chk_add_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) print_check "add" - count=$(get_counter ${ns2} "MPTcpExtAddAddr") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtAddAddr") if [ -z "$count" ]; then print_skip # if the test configured a short timeout tolerate greater then expected @@ -1599,7 +1583,7 @@ chk_add_nr() fi print_check "echo" - count=$(get_counter ${ns1} "MPTcpExtEchoAdd") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtEchoAdd") if [ -z "$count" ]; then print_skip elif [ "$count" != "$echo_nr" ]; then @@ -1610,7 +1594,7 @@ chk_add_nr() if [ $port_nr -gt 0 ]; then print_check "pt" - count=$(get_counter ${ns2} "MPTcpExtPortAdd") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtPortAdd") if [ -z "$count" ]; then print_skip elif [ "$count" != "$port_nr" ]; then @@ -1620,7 +1604,7 @@ chk_add_nr() fi print_check "syn" - count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_nr" ]; then @@ -1631,7 +1615,7 @@ chk_add_nr() fi print_check "synack" - count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_ack_nr" ]; then @@ -1642,7 +1626,7 @@ chk_add_nr() fi print_check "ack" - count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$ack_nr" ]; then @@ -1653,7 +1637,7 @@ chk_add_nr() fi print_check "syn" - count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mis_syn_nr" ]; then @@ -1664,7 +1648,7 @@ chk_add_nr() fi print_check "ack" - count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mis_ack_nr" ]; then @@ -1686,7 +1670,7 @@ chk_add_tx_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) print_check "add TX" - count=$(get_counter ${ns1} "MPTcpExtAddAddrTx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtAddAddrTx") if [ -z "$count" ]; then print_skip # if the test configured a short timeout tolerate greater then expected @@ -1698,7 +1682,7 @@ chk_add_tx_nr() fi print_check "echo TX" - count=$(get_counter ${ns2} "MPTcpExtEchoAddTx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtEchoAddTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$echo_tx_nr" ]; then @@ -1736,7 +1720,7 @@ chk_rm_nr() fi print_check "rm" - count=$(get_counter ${addr_ns} "MPTcpExtRmAddr") + count=$(mptcp_lib_get_counter ${addr_ns} "MPTcpExtRmAddr") if [ -z "$count" ]; then print_skip elif [ "$count" != "$rm_addr_nr" ]; then @@ -1746,13 +1730,13 @@ chk_rm_nr() fi print_check "rmsf" - count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow") + count=$(mptcp_lib_get_counter ${subflow_ns} "MPTcpExtRmSubflow") if [ -z "$count" ]; then print_skip elif [ -n "$simult" ]; then local cnt suffix - cnt=$(get_counter ${addr_ns} "MPTcpExtRmSubflow") + cnt=$(mptcp_lib_get_counter ${addr_ns} "MPTcpExtRmSubflow") # in case of simult flush, the subflow removal count on each side is # unreliable @@ -1778,7 +1762,7 @@ chk_rm_tx_nr() local rm_addr_tx_nr=$1 print_check "rm TX" - count=$(get_counter ${ns2} "MPTcpExtRmAddrTx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtRmAddrTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$rm_addr_tx_nr" ]; then @@ -1795,7 +1779,7 @@ chk_prio_nr() local count print_check "ptx" - count=$(get_counter ${ns1} "MPTcpExtMPPrioTx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mp_prio_nr_tx" ]; then @@ -1805,7 +1789,7 @@ chk_prio_nr() fi print_check "prx" - count=$(get_counter ${ns1} "MPTcpExtMPPrioRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mp_prio_nr_rx" ]; then @@ -1905,7 +1889,7 @@ wait_attempt_fail() while [ $time -lt $timeout_ms ]; do local cnt - cnt=$(get_counter ${ns} "TcpAttemptFails") + cnt=$(mptcp_lib_get_counter ${ns} "TcpAttemptFails") [ "$cnt" = 1 ] && return 1 time=$((time + 100)) diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 4cd4297ca86d..2b10f200de40 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -216,3 +216,19 @@ mptcp_lib_kill_wait() { kill "${1}" > /dev/null 2>&1 wait "${1}" 2>/dev/null } + +# $1: ns, $2: MIB counter +mptcp_lib_get_counter() { + local ns="${1}" + local counter="${2}" + local count + + count=$(ip netns exec "${ns}" nstat -asz "${counter}" | + awk 'NR==1 {next} {print $2}') + if [ -z "${count}" ]; then + mptcp_lib_fail_if_expected_feature "${counter} counter" + return 1 + fi + + echo "${count}" +} diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 0e573c6c393a..0e748068ee95 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -887,9 +887,10 @@ test_prio() # Check TX print_test "MP_PRIO TX" - count=$(ip netns exec "$ns2" nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count != 1 ]; then + count=$(mptcp_lib_get_counter "$ns2" "MPTcpExtMPPrioTx") + if [ -z "$count" ]; then + test_skip + elif [ $count != 1 ]; then test_fail "Count != 1: ${count}" else test_pass @@ -897,9 +898,10 @@ test_prio() # Check RX print_test "MP_PRIO RX" - count=$(ip netns exec "$ns1" nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count != 1 ]; then + count=$(mptcp_lib_get_counter "$ns1" "MPTcpExtMPPrioRx") + if [ -z "$count" ]; then + test_skip + elif [ $count != 1 ]; then test_fail "Count != 1: ${count}" else test_pass -- 2.43.0

1 year, 8 months

1
0
0 0

[PATCH 5.4.y 0/2] KVM: arm64: VGIC ITS fix backports

by Oliver Upton

Oliver Upton (2): KVM: arm64: vgic-its: Test for valid IRQ in its_sync_lpi_pending_table() KVM: arm64: vgic-its: Test for valid IRQ in MOVALL handler virt/kvm/arm/vgic/vgic-its.c | 5 +++++ 1 file changed, 5 insertions(+) base-commit: 6e1f54a4985b63bc1b55a09e5e75a974c5d6719b -- 2.44.0.rc1.240.g4c46232300-goog

1 year, 8 months

1
2
0 0

FAILED: patch "[PATCH] selftests: mptcp: join: stop transfer when check is done" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 04b57c9e096a9479fe0ad31e3956e336fa589cb2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021924-setback-disinfect-0bd6@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: 04b57c9e096a ("selftests: mptcp: join: stop transfer when check is done (part 2)") b9fb176081fb ("selftests: mptcp: userspace pm send RM_ADDR for ID 0") e3b47e460b4b ("selftests: mptcp: userspace pm remove initial subflow") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 04b57c9e096a9479fe0ad31e3956e336fa589cb2 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" <matttbe(a)kernel.org> Date: Wed, 31 Jan 2024 22:49:54 +0100 Subject: [PATCH] selftests: mptcp: join: stop transfer when check is done (part 2) Since the "Fixes" commits mentioned below, the newly added "userspace pm" subtests of mptcp_join selftests are launching the whole transfer in the background, do the required checks, then wait for the end of transfer. There is no need to wait longer, especially because the checks at the end of the transfer are ignored (which is fine). This saves quite a few seconds on slow environments. While at it, use 'mptcp_lib_kill_wait()' helper everywhere, instead of on a specific one with 'kill_tests_wait()'. Fixes: b2e2248f365a ("selftests: mptcp: userspace pm create id 0 subflow") Fixes: e3b47e460b4b ("selftests: mptcp: userspace pm remove initial subflow") Fixes: b9fb176081fb ("selftests: mptcp: userspace pm send RM_ADDR for ID 0") Cc: stable(a)vger.kernel.org Reviewed-and-tested-by: Geliang Tang <geliang(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 85bcc95f4ede..c07386e21e0a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -643,13 +643,6 @@ kill_events_pids() mptcp_lib_kill_wait $evts_ns2_pid } -kill_tests_wait() -{ - #shellcheck disable=SC2046 - kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1) - wait -} - pm_nl_set_limits() { local ns=$1 @@ -3494,7 +3487,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 2 2 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm remove initial subflow @@ -3518,7 +3511,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm send RM_ADDR for ID 0 @@ -3544,7 +3537,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi } @@ -3558,7 +3551,8 @@ endpoint_tests() pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal speed=slow \ - run_tests $ns1 $ns2 10.0.1.1 2>/dev/null & + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! wait_mpj $ns1 pm_nl_check_endpoint "creation" \ @@ -3573,7 +3567,7 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags signal pm_nl_check_endpoint "modif is allowed" \ $ns2 10.0.2.2 id 1 flags signal - kill_tests_wait + mptcp_lib_kill_wait $tests_pid fi if reset "delete and re-add" && @@ -3582,7 +3576,8 @@ endpoint_tests() pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow test_linkfail=4 speed=20 \ - run_tests $ns1 $ns2 10.0.1.1 2>/dev/null & + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! wait_mpj $ns2 chk_subflow_nr "before delete" 2 @@ -3597,7 +3592,7 @@ endpoint_tests() wait_mpj $ns2 chk_subflow_nr "after re-add" 2 chk_mptcp_info subflows 1 subflows 1 - kill_tests_wait + mptcp_lib_kill_wait $tests_pid fi }

1 year, 8 months

2
1
0 0

FAILED: patch "[PATCH] selftests: mptcp: join: stop transfer when check is done" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 31ee4ad86afd6ed6f4bb1b38c43011216080c42a # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021917-nuzzle-magenta-7de4@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: 31ee4ad86afd ("selftests: mptcp: join: stop transfer when check is done (part 1)") 80775412882e ("selftests: mptcp: add chk_subflows_total helper") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 31ee4ad86afd6ed6f4bb1b38c43011216080c42a Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" <matttbe(a)kernel.org> Date: Wed, 31 Jan 2024 22:49:53 +0100 Subject: [PATCH] selftests: mptcp: join: stop transfer when check is done (part 1) Since the "Fixes" commit mentioned below, "userspace pm" subtests of mptcp_join selftests introduced in v6.5 are launching the whole transfer in the background, do the required checks, then wait for the end of transfer. There is no need to wait longer, especially because the checks at the end of the transfer are ignored (which is fine). This saves quite a few seconds in slow environments. Note that old versions will need commit bdbef0a6ff10 ("selftests: mptcp: add mptcp_lib_kill_wait") as well to get 'mptcp_lib_kill_wait()' helper. Fixes: 4369c198e599 ("selftests: mptcp: test userspace pm out of transfer") Cc: stable(a)vger.kernel.org # 6.5.x: bdbef0a6ff10: selftests: mptcp: add mptcp_lib_kill_wait Cc: stable(a)vger.kernel.org # 6.5.x Reviewed-and-tested-by: Geliang Tang <geliang(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3a5b63026191..85bcc95f4ede 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3453,7 +3453,7 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm create destroy subflow @@ -3475,7 +3475,7 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm create id 0 subflow

1 year, 8 months

2
1
0 0

[PATCH 6.6.y] mptcp: userspace pm send RM_ADDR for ID 0

by Matthieu Baerts (NGI0)

From: Geliang Tang <geliang.tang(a)suse.com> This patch adds the ability to send RM_ADDR for local ID 0. Check whether id 0 address is removed, if not, put id 0 into a removing list, pass it to mptcp_pm_remove_addr() to remove id 0 address. There is no reason not to allow the userspace to remove the initial address (ID 0). This special case was not taken into account not letting the userspace to delete all addresses as announced. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/379 Reviewed-by: Matthieu Baerts <matttbe(a)kernel.org> Signed-off-by: Geliang Tang <geliang.tang(a)suse.com> Signed-off-by: Mat Martineau <martineau(a)kernel.org> Link: https://lore.kernel.org/r/20231025-send-net-next-20231025-v1-3-db8f25f798eb… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> (cherry picked from commit 84c531f54ad9a124a924c9505d74e33d16965146) Fixes: d9a4594edabf ("mptcp: netlink: Add MPTCP_PM_CMD_REMOVE") Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Notes: - As mentioned in [1], the 'Fixes' tag has been accidentally dropped: [1] https://lore.kernel.org/stable/a7a3675a-4531-4559-bea2-c7689317764a@kernel.… - Conflict in pm_userspace.c because the new helper function expected to be on top of mptcp_pm_nl_remove_doit() which has been recently renamed in commit 1e07938e29c5 ("net: mptcp: rename netlink handlers to mptcp_pm_nl_<blah>_{doit,dumpit}"). --- net/mptcp/pm_userspace.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 3b34b7cf56c9..ecd166ce047d 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -220,6 +220,40 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) return err; } +static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk, + struct genl_info *info) +{ + struct mptcp_rm_list list = { .nr = 0 }; + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + bool has_id_0 = false; + int err = -EINVAL; + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + if (subflow->local_id == 0) { + has_id_0 = true; + break; + } + } + if (!has_id_0) { + GENL_SET_ERR_MSG(info, "address with id 0 not found"); + goto remove_err; + } + + list.ids[list.nr++] = 0; + + spin_lock_bh(&msk->pm.lock); + mptcp_pm_remove_addr(msk, &list); + spin_unlock_bh(&msk->pm.lock); + + err = 0; + +remove_err: + release_sock(sk); + return err; +} + int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; @@ -251,6 +285,11 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) goto remove_err; } + if (id_val == 0) { + err = mptcp_userspace_pm_remove_id_zero_address(msk, info); + goto remove_err; + } + lock_sock((struct sock *)msk); list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { -- 2.43.0

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x b820de741ae48ccf50dd95e297889c286ff4f760 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022601-stem-comfort-1bb5@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: b820de741ae4 ("fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio") 9cf3516c29e6 ("fs: add IOCB flags related to passing back dio completions") f6c73a11133e ("fs.h: Add TRACE_IOCB_STRINGS for use in trace points") 1da8cf961bb1 ("Merge tag 'io_uring-6.0-2022-08-13' of git://git.kernel.dk/linux-block") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b820de741ae48ccf50dd95e297889c286ff4f760 Mon Sep 17 00:00:00 2001 From: Bart Van Assche <bvanassche(a)acm.org> Date: Thu, 15 Feb 2024 12:47:38 -0800 Subject: [PATCH] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio If kiocb_set_cancel_fn() is called for I/O submitted via io_uring, the following kernel warning appears: WARNING: CPU: 3 PID: 368 at fs/aio.c:598 kiocb_set_cancel_fn+0x9c/0xa8 Call trace: kiocb_set_cancel_fn+0x9c/0xa8 ffs_epfile_read_iter+0x144/0x1d0 io_read+0x19c/0x498 io_issue_sqe+0x118/0x27c io_submit_sqes+0x25c/0x5fc __arm64_sys_io_uring_enter+0x104/0xab0 invoke_syscall+0x58/0x11c el0_svc_common+0xb4/0xf4 do_el0_svc+0x2c/0xb0 el0_svc+0x2c/0xa4 el0t_64_sync_handler+0x68/0xb4 el0t_64_sync+0x1a4/0x1a8 Fix this by setting the IOCB_AIO_RW flag for read and write I/O that is submitted by libaio. Suggested-by: Jens Axboe <axboe(a)kernel.dk> Cc: Christoph Hellwig <hch(a)lst.de> Cc: Avi Kivity <avi(a)scylladb.com> Cc: Sandeep Dhavale <dhavale(a)google.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: stable(a)vger.kernel.org Signed-off-by: Bart Van Assche <bvanassche(a)acm.org> Link: https://lore.kernel.org/r/20240215204739.2677806-2-bvanassche@acm.org Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/aio.c b/fs/aio.c index bb2ff48991f3..da18dbcfcb22 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -593,6 +593,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) struct kioctx *ctx = req->ki_ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; @@ -1509,7 +1516,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { diff --git a/include/linux/fs.h b/include/linux/fs.h index ed5966a70495..c2dcc98cb4c8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -352,6 +352,8 @@ enum rw_hint { * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \

1 year, 8 months

2
1
0 0

FAILED: patch "[PATCH] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x b820de741ae48ccf50dd95e297889c286ff4f760 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022654-stainless-aground-196f@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: b820de741ae4 ("fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio") 9cf3516c29e6 ("fs: add IOCB flags related to passing back dio completions") f6c73a11133e ("fs.h: Add TRACE_IOCB_STRINGS for use in trace points") 1da8cf961bb1 ("Merge tag 'io_uring-6.0-2022-08-13' of git://git.kernel.dk/linux-block") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b820de741ae48ccf50dd95e297889c286ff4f760 Mon Sep 17 00:00:00 2001 From: Bart Van Assche <bvanassche(a)acm.org> Date: Thu, 15 Feb 2024 12:47:38 -0800 Subject: [PATCH] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio If kiocb_set_cancel_fn() is called for I/O submitted via io_uring, the following kernel warning appears: WARNING: CPU: 3 PID: 368 at fs/aio.c:598 kiocb_set_cancel_fn+0x9c/0xa8 Call trace: kiocb_set_cancel_fn+0x9c/0xa8 ffs_epfile_read_iter+0x144/0x1d0 io_read+0x19c/0x498 io_issue_sqe+0x118/0x27c io_submit_sqes+0x25c/0x5fc __arm64_sys_io_uring_enter+0x104/0xab0 invoke_syscall+0x58/0x11c el0_svc_common+0xb4/0xf4 do_el0_svc+0x2c/0xb0 el0_svc+0x2c/0xa4 el0t_64_sync_handler+0x68/0xb4 el0t_64_sync+0x1a4/0x1a8 Fix this by setting the IOCB_AIO_RW flag for read and write I/O that is submitted by libaio. Suggested-by: Jens Axboe <axboe(a)kernel.dk> Cc: Christoph Hellwig <hch(a)lst.de> Cc: Avi Kivity <avi(a)scylladb.com> Cc: Sandeep Dhavale <dhavale(a)google.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: stable(a)vger.kernel.org Signed-off-by: Bart Van Assche <bvanassche(a)acm.org> Link: https://lore.kernel.org/r/20240215204739.2677806-2-bvanassche@acm.org Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/aio.c b/fs/aio.c index bb2ff48991f3..da18dbcfcb22 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -593,6 +593,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) struct kioctx *ctx = req->ki_ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; @@ -1509,7 +1516,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { diff --git a/include/linux/fs.h b/include/linux/fs.h index ed5966a70495..c2dcc98cb4c8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -352,6 +352,8 @@ enum rw_hint { * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \

1 year, 8 months

2
1
0 0

FAILED: patch "[PATCH] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x b820de741ae48ccf50dd95e297889c286ff4f760 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022653-schedule-unloaded-e4ed@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: b820de741ae4 ("fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio") 9cf3516c29e6 ("fs: add IOCB flags related to passing back dio completions") f6c73a11133e ("fs.h: Add TRACE_IOCB_STRINGS for use in trace points") 1da8cf961bb1 ("Merge tag 'io_uring-6.0-2022-08-13' of git://git.kernel.dk/linux-block") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b820de741ae48ccf50dd95e297889c286ff4f760 Mon Sep 17 00:00:00 2001 From: Bart Van Assche <bvanassche(a)acm.org> Date: Thu, 15 Feb 2024 12:47:38 -0800 Subject: [PATCH] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio If kiocb_set_cancel_fn() is called for I/O submitted via io_uring, the following kernel warning appears: WARNING: CPU: 3 PID: 368 at fs/aio.c:598 kiocb_set_cancel_fn+0x9c/0xa8 Call trace: kiocb_set_cancel_fn+0x9c/0xa8 ffs_epfile_read_iter+0x144/0x1d0 io_read+0x19c/0x498 io_issue_sqe+0x118/0x27c io_submit_sqes+0x25c/0x5fc __arm64_sys_io_uring_enter+0x104/0xab0 invoke_syscall+0x58/0x11c el0_svc_common+0xb4/0xf4 do_el0_svc+0x2c/0xb0 el0_svc+0x2c/0xa4 el0t_64_sync_handler+0x68/0xb4 el0t_64_sync+0x1a4/0x1a8 Fix this by setting the IOCB_AIO_RW flag for read and write I/O that is submitted by libaio. Suggested-by: Jens Axboe <axboe(a)kernel.dk> Cc: Christoph Hellwig <hch(a)lst.de> Cc: Avi Kivity <avi(a)scylladb.com> Cc: Sandeep Dhavale <dhavale(a)google.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: stable(a)vger.kernel.org Signed-off-by: Bart Van Assche <bvanassche(a)acm.org> Link: https://lore.kernel.org/r/20240215204739.2677806-2-bvanassche@acm.org Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/aio.c b/fs/aio.c index bb2ff48991f3..da18dbcfcb22 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -593,6 +593,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) struct kioctx *ctx = req->ki_ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; @@ -1509,7 +1516,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { diff --git a/include/linux/fs.h b/include/linux/fs.h index ed5966a70495..c2dcc98cb4c8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -352,6 +352,8 @@ enum rw_hint { * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \

1 year, 8 months

2
1
0 0

FAILED: patch "[PATCH] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x b820de741ae48ccf50dd95e297889c286ff4f760 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022651-shrimp-freezing-6b17@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: b820de741ae4 ("fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio") 9cf3516c29e6 ("fs: add IOCB flags related to passing back dio completions") f6c73a11133e ("fs.h: Add TRACE_IOCB_STRINGS for use in trace points") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b820de741ae48ccf50dd95e297889c286ff4f760 Mon Sep 17 00:00:00 2001 From: Bart Van Assche <bvanassche(a)acm.org> Date: Thu, 15 Feb 2024 12:47:38 -0800 Subject: [PATCH] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio If kiocb_set_cancel_fn() is called for I/O submitted via io_uring, the following kernel warning appears: WARNING: CPU: 3 PID: 368 at fs/aio.c:598 kiocb_set_cancel_fn+0x9c/0xa8 Call trace: kiocb_set_cancel_fn+0x9c/0xa8 ffs_epfile_read_iter+0x144/0x1d0 io_read+0x19c/0x498 io_issue_sqe+0x118/0x27c io_submit_sqes+0x25c/0x5fc __arm64_sys_io_uring_enter+0x104/0xab0 invoke_syscall+0x58/0x11c el0_svc_common+0xb4/0xf4 do_el0_svc+0x2c/0xb0 el0_svc+0x2c/0xa4 el0t_64_sync_handler+0x68/0xb4 el0t_64_sync+0x1a4/0x1a8 Fix this by setting the IOCB_AIO_RW flag for read and write I/O that is submitted by libaio. Suggested-by: Jens Axboe <axboe(a)kernel.dk> Cc: Christoph Hellwig <hch(a)lst.de> Cc: Avi Kivity <avi(a)scylladb.com> Cc: Sandeep Dhavale <dhavale(a)google.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: stable(a)vger.kernel.org Signed-off-by: Bart Van Assche <bvanassche(a)acm.org> Link: https://lore.kernel.org/r/20240215204739.2677806-2-bvanassche@acm.org Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/aio.c b/fs/aio.c index bb2ff48991f3..da18dbcfcb22 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -593,6 +593,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) struct kioctx *ctx = req->ki_ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; @@ -1509,7 +1516,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { diff --git a/include/linux/fs.h b/include/linux/fs.h index ed5966a70495..c2dcc98cb4c8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -352,6 +352,8 @@ enum rw_hint { * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \

1 year, 8 months

2
1
0 0

[PATCH 6.7.y] selftests: mptcp: add mptcp_lib_get_counter

by Matthieu Baerts (NGI0)

From: Geliang Tang <geliang.tang(a)suse.com> To avoid duplicated code in different MPTCP selftests, we can add and use helpers defined in mptcp_lib.sh. The helper get_counter() in mptcp_join.sh and get_mib_counter() in mptcp_connect.sh have the same functionality, export get_counter() into mptcp_lib.sh and rename it as mptcp_lib_get_counter(). Use this new helper instead of get_counter() and get_mib_counter(). Use this helper in test_prio() in userspace_pm.sh too instead of open-coding. Reviewed-by: Matthieu Baerts <matttbe(a)kernel.org> Signed-off-by: Geliang Tang <geliang.tang(a)suse.com> Signed-off-by: Mat Martineau <martineau(a)kernel.org> Link: https://lore.kernel.org/r/20231128-send-net-next-2023107-v4-11-8d6b94150f6b… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Stable-dep-of: acaef88f2624 ("selftests: mptcp: diag: check CURRESTAB counters") (cherry picked from commit 61c131f5d4d2b79904af2fdcb2839a9db8e7c55c) Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Notes: - this patch is needed for "selftests: mptcp: diag: check CURRESTAB counters" that has been added to the queue for v6.7 today, to avoid failures and this message: ./diag.sh: line 62: mptcp_lib_get_counter: command not found - conflicts in mptcp_lib.sh because the new helper expected to be placed after mptcp_lib_kill_wait() which has not been backported. --- .../selftests/net/mptcp/mptcp_connect.sh | 41 +++------ .../testing/selftests/net/mptcp/mptcp_join.sh | 88 ++++++++----------- .../testing/selftests/net/mptcp/mptcp_lib.sh | 16 ++++ .../selftests/net/mptcp/userspace_pm.sh | 14 +-- 4 files changed, 73 insertions(+), 86 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index b1fc8afd072d..10cd322e05c4 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -341,21 +341,6 @@ do_ping() return 0 } -# $1: ns, $2: MIB counter -get_mib_counter() -{ - local listener_ns="${1}" - local mib="${2}" - - # strip the header - ip netns exec "${listener_ns}" \ - nstat -z -a "${mib}" | \ - tail -n+2 | \ - while read a count c rest; do - echo $count - done -} - # $1: ns, $2: port wait_local_port_listen() { @@ -441,12 +426,12 @@ do_transfer() nstat -n fi - local stat_synrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local stat_csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + local stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + local stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + local stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -509,11 +494,11 @@ do_transfer() check_transfer $cin $sout "file received by server" rets=$? - local stat_synrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue") + local stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + local stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + local stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + local stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -542,8 +527,8 @@ do_transfer() fi if $checksum; then - local csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) if [ $csum_err_s_nr -gt 0 ]; then diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 2f28d594b2c5..be10b971e912 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -611,25 +611,9 @@ wait_local_port_listen() done } -# $1: ns ; $2: counter -get_counter() -{ - local ns="${1}" - local counter="${2}" - local count - - count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}') - if [ -z "${count}" ]; then - mptcp_lib_fail_if_expected_feature "${counter} counter" - return 1 - fi - - echo "${count}" -} - rm_addr_count() { - get_counter "${1}" "MPTcpExtRmAddr" + mptcp_lib_get_counter "${1}" "MPTcpExtRmAddr" } # $1: ns, $2: old rm_addr counter in $ns @@ -649,7 +633,7 @@ wait_rm_addr() rm_sf_count() { - get_counter "${1}" "MPTcpExtRmSubflow" + mptcp_lib_get_counter "${1}" "MPTcpExtRmSubflow" } # $1: ns, $2: old rm_sf counter in $ns @@ -672,11 +656,11 @@ wait_mpj() local ns="${1}" local cnt old_cnt - old_cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") + old_cnt=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPJoinAckRx") local i for i in $(seq 10); do - cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") + cnt=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPJoinAckRx") [ "$cnt" = "${old_cnt}" ] || break sleep 0.1 done @@ -1271,7 +1255,7 @@ chk_csum_nr() fi print_check "sum" - count=$(get_counter ${ns1} "MPTcpExtDataCsumErr") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then extra_msg="$extra_msg ns1=$count" fi @@ -1284,7 +1268,7 @@ chk_csum_nr() print_ok fi print_check "csum" - count=$(get_counter ${ns2} "MPTcpExtDataCsumErr") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then extra_msg="$extra_msg ns2=$count" fi @@ -1328,7 +1312,7 @@ chk_fail_nr() fi print_check "ftx" - count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then extra_msg="$extra_msg,tx=$count" fi @@ -1342,7 +1326,7 @@ chk_fail_nr() fi print_check "failrx" - count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then extra_msg="$extra_msg,rx=$count" fi @@ -1375,7 +1359,7 @@ chk_fclose_nr() fi print_check "ctx" - count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$fclose_tx" ]; then @@ -1386,7 +1370,7 @@ chk_fclose_nr() fi print_check "fclzrx" - count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$fclose_rx" ]; then @@ -1416,7 +1400,7 @@ chk_rst_nr() fi print_check "rtx" - count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPRstTx") if [ -z "$count" ]; then print_skip # accept more rst than expected except if we don't expect any @@ -1428,7 +1412,7 @@ chk_rst_nr() fi print_check "rstrx" - count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPRstRx") if [ -z "$count" ]; then print_skip # accept more rst than expected except if we don't expect any @@ -1449,7 +1433,7 @@ chk_infi_nr() local count print_check "itx" - count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtInfiniteMapTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$infi_tx" ]; then @@ -1459,7 +1443,7 @@ chk_infi_nr() fi print_check "infirx" - count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtInfiniteMapRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$infi_rx" ]; then @@ -1488,7 +1472,7 @@ chk_join_nr() fi print_check "syn" - count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_nr" ]; then @@ -1499,7 +1483,7 @@ chk_join_nr() print_check "synack" with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) - count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_ack_nr" ]; then @@ -1516,7 +1500,7 @@ chk_join_nr() fi print_check "ack" - count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$ack_nr" ]; then @@ -1549,8 +1533,8 @@ chk_stale_nr() print_check "stale" - stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale") - recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover") + stale_nr=$(mptcp_lib_get_counter ${ns} "MPTcpExtSubflowStale") + recover_nr=$(mptcp_lib_get_counter ${ns} "MPTcpExtSubflowRecover") if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then print_skip elif [ $stale_nr -lt $stale_min ] || @@ -1587,7 +1571,7 @@ chk_add_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) print_check "add" - count=$(get_counter ${ns2} "MPTcpExtAddAddr") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtAddAddr") if [ -z "$count" ]; then print_skip # if the test configured a short timeout tolerate greater then expected @@ -1599,7 +1583,7 @@ chk_add_nr() fi print_check "echo" - count=$(get_counter ${ns1} "MPTcpExtEchoAdd") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtEchoAdd") if [ -z "$count" ]; then print_skip elif [ "$count" != "$echo_nr" ]; then @@ -1610,7 +1594,7 @@ chk_add_nr() if [ $port_nr -gt 0 ]; then print_check "pt" - count=$(get_counter ${ns2} "MPTcpExtPortAdd") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtPortAdd") if [ -z "$count" ]; then print_skip elif [ "$count" != "$port_nr" ]; then @@ -1620,7 +1604,7 @@ chk_add_nr() fi print_check "syn" - count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_nr" ]; then @@ -1631,7 +1615,7 @@ chk_add_nr() fi print_check "synack" - count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_ack_nr" ]; then @@ -1642,7 +1626,7 @@ chk_add_nr() fi print_check "ack" - count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$ack_nr" ]; then @@ -1653,7 +1637,7 @@ chk_add_nr() fi print_check "syn" - count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mis_syn_nr" ]; then @@ -1664,7 +1648,7 @@ chk_add_nr() fi print_check "ack" - count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mis_ack_nr" ]; then @@ -1686,7 +1670,7 @@ chk_add_tx_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) print_check "add TX" - count=$(get_counter ${ns1} "MPTcpExtAddAddrTx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtAddAddrTx") if [ -z "$count" ]; then print_skip # if the test configured a short timeout tolerate greater then expected @@ -1698,7 +1682,7 @@ chk_add_tx_nr() fi print_check "echo TX" - count=$(get_counter ${ns2} "MPTcpExtEchoAddTx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtEchoAddTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$echo_tx_nr" ]; then @@ -1736,7 +1720,7 @@ chk_rm_nr() fi print_check "rm" - count=$(get_counter ${addr_ns} "MPTcpExtRmAddr") + count=$(mptcp_lib_get_counter ${addr_ns} "MPTcpExtRmAddr") if [ -z "$count" ]; then print_skip elif [ "$count" != "$rm_addr_nr" ]; then @@ -1746,13 +1730,13 @@ chk_rm_nr() fi print_check "rmsf" - count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow") + count=$(mptcp_lib_get_counter ${subflow_ns} "MPTcpExtRmSubflow") if [ -z "$count" ]; then print_skip elif [ -n "$simult" ]; then local cnt suffix - cnt=$(get_counter ${addr_ns} "MPTcpExtRmSubflow") + cnt=$(mptcp_lib_get_counter ${addr_ns} "MPTcpExtRmSubflow") # in case of simult flush, the subflow removal count on each side is # unreliable @@ -1781,7 +1765,7 @@ chk_rm_tx_nr() local rm_addr_tx_nr=$1 print_check "rm TX" - count=$(get_counter ${ns2} "MPTcpExtRmAddrTx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtRmAddrTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$rm_addr_tx_nr" ]; then @@ -1798,7 +1782,7 @@ chk_prio_nr() local count print_check "ptx" - count=$(get_counter ${ns1} "MPTcpExtMPPrioTx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mp_prio_nr_tx" ]; then @@ -1808,7 +1792,7 @@ chk_prio_nr() fi print_check "prx" - count=$(get_counter ${ns1} "MPTcpExtMPPrioRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mp_prio_nr_rx" ]; then @@ -1908,7 +1892,7 @@ wait_attempt_fail() while [ $time -lt $timeout_ms ]; do local cnt - cnt=$(get_counter ${ns} "TcpAttemptFails") + cnt=$(mptcp_lib_get_counter ${ns} "TcpAttemptFails") [ "$cnt" = 1 ] && return 1 time=$((time + 100)) diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 4cd4297ca86d..2b10f200de40 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -216,3 +216,19 @@ mptcp_lib_kill_wait() { kill "${1}" > /dev/null 2>&1 wait "${1}" 2>/dev/null } + +# $1: ns, $2: MIB counter +mptcp_lib_get_counter() { + local ns="${1}" + local counter="${2}" + local count + + count=$(ip netns exec "${ns}" nstat -asz "${counter}" | + awk 'NR==1 {next} {print $2}') + if [ -z "${count}" ]; then + mptcp_lib_fail_if_expected_feature "${counter} counter" + return 1 + fi + + echo "${count}" +} diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 0e573c6c393a..0e748068ee95 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -887,9 +887,10 @@ test_prio() # Check TX print_test "MP_PRIO TX" - count=$(ip netns exec "$ns2" nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count != 1 ]; then + count=$(mptcp_lib_get_counter "$ns2" "MPTcpExtMPPrioTx") + if [ -z "$count" ]; then + test_skip + elif [ $count != 1 ]; then test_fail "Count != 1: ${count}" else test_pass @@ -897,9 +898,10 @@ test_prio() # Check RX print_test "MP_PRIO RX" - count=$(ip netns exec "$ns1" nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count != 1 ]; then + count=$(mptcp_lib_get_counter "$ns1" "MPTcpExtMPPrioRx") + if [ -z "$count" ]; then + test_skip + elif [ $count != 1 ]; then test_fail "Count != 1: ${count}" else test_pass -- 2.43.0

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] selftests: mptcp: join: stop transfer when check is done" failed to apply to 6.7-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.7-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.7.y git checkout FETCH_HEAD git cherry-pick -x 04b57c9e096a9479fe0ad31e3956e336fa589cb2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021925-saloon-pursuit-2736@gregkh' --subject-prefix 'PATCH 6.7.y' HEAD^.. Possible dependencies: 04b57c9e096a ("selftests: mptcp: join: stop transfer when check is done (part 2)") b9fb176081fb ("selftests: mptcp: userspace pm send RM_ADDR for ID 0") e3b47e460b4b ("selftests: mptcp: userspace pm remove initial subflow") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 04b57c9e096a9479fe0ad31e3956e336fa589cb2 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" <matttbe(a)kernel.org> Date: Wed, 31 Jan 2024 22:49:54 +0100 Subject: [PATCH] selftests: mptcp: join: stop transfer when check is done (part 2) Since the "Fixes" commits mentioned below, the newly added "userspace pm" subtests of mptcp_join selftests are launching the whole transfer in the background, do the required checks, then wait for the end of transfer. There is no need to wait longer, especially because the checks at the end of the transfer are ignored (which is fine). This saves quite a few seconds on slow environments. While at it, use 'mptcp_lib_kill_wait()' helper everywhere, instead of on a specific one with 'kill_tests_wait()'. Fixes: b2e2248f365a ("selftests: mptcp: userspace pm create id 0 subflow") Fixes: e3b47e460b4b ("selftests: mptcp: userspace pm remove initial subflow") Fixes: b9fb176081fb ("selftests: mptcp: userspace pm send RM_ADDR for ID 0") Cc: stable(a)vger.kernel.org Reviewed-and-tested-by: Geliang Tang <geliang(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 85bcc95f4ede..c07386e21e0a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -643,13 +643,6 @@ kill_events_pids() mptcp_lib_kill_wait $evts_ns2_pid } -kill_tests_wait() -{ - #shellcheck disable=SC2046 - kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1) - wait -} - pm_nl_set_limits() { local ns=$1 @@ -3494,7 +3487,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 2 2 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm remove initial subflow @@ -3518,7 +3511,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm send RM_ADDR for ID 0 @@ -3544,7 +3537,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi } @@ -3558,7 +3551,8 @@ endpoint_tests() pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal speed=slow \ - run_tests $ns1 $ns2 10.0.1.1 2>/dev/null & + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! wait_mpj $ns1 pm_nl_check_endpoint "creation" \ @@ -3573,7 +3567,7 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags signal pm_nl_check_endpoint "modif is allowed" \ $ns2 10.0.2.2 id 1 flags signal - kill_tests_wait + mptcp_lib_kill_wait $tests_pid fi if reset "delete and re-add" && @@ -3582,7 +3576,8 @@ endpoint_tests() pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow test_linkfail=4 speed=20 \ - run_tests $ns1 $ns2 10.0.1.1 2>/dev/null & + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! wait_mpj $ns2 chk_subflow_nr "before delete" 2 @@ -3597,7 +3592,7 @@ endpoint_tests() wait_mpj $ns2 chk_subflow_nr "after re-add" 2 chk_mptcp_info subflows 1 subflows 1 - kill_tests_wait + mptcp_lib_kill_wait $tests_pid fi }

1 year, 8 months

2
1
0 0

FAILED: patch "[PATCH] selftests: mptcp: join: stop transfer when check is done" failed to apply to 6.7-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.7-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.7.y git checkout FETCH_HEAD git cherry-pick -x 31ee4ad86afd6ed6f4bb1b38c43011216080c42a # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021916-striking-evoke-4847@gregkh' --subject-prefix 'PATCH 6.7.y' HEAD^.. Possible dependencies: 31ee4ad86afd ("selftests: mptcp: join: stop transfer when check is done (part 1)") 80775412882e ("selftests: mptcp: add chk_subflows_total helper") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 31ee4ad86afd6ed6f4bb1b38c43011216080c42a Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" <matttbe(a)kernel.org> Date: Wed, 31 Jan 2024 22:49:53 +0100 Subject: [PATCH] selftests: mptcp: join: stop transfer when check is done (part 1) Since the "Fixes" commit mentioned below, "userspace pm" subtests of mptcp_join selftests introduced in v6.5 are launching the whole transfer in the background, do the required checks, then wait for the end of transfer. There is no need to wait longer, especially because the checks at the end of the transfer are ignored (which is fine). This saves quite a few seconds in slow environments. Note that old versions will need commit bdbef0a6ff10 ("selftests: mptcp: add mptcp_lib_kill_wait") as well to get 'mptcp_lib_kill_wait()' helper. Fixes: 4369c198e599 ("selftests: mptcp: test userspace pm out of transfer") Cc: stable(a)vger.kernel.org # 6.5.x: bdbef0a6ff10: selftests: mptcp: add mptcp_lib_kill_wait Cc: stable(a)vger.kernel.org # 6.5.x Reviewed-and-tested-by: Geliang Tang <geliang(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Link: https://lore.kernel.org/r/20240131-upstream-net-20240131-mptcp-ci-issues-v1… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3a5b63026191..85bcc95f4ede 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3453,7 +3453,7 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm create destroy subflow @@ -3475,7 +3475,7 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm create id 0 subflow

1 year, 8 months

2
1
0 0

[tip: x86/urgent] x86/cpu: Allow reducing x86_phys_bits during early_identify_cpu()

by tip-bot2 for Paolo Bonzini

The following commit has been merged into the x86/urgent branch of tip: Commit-ID: 9a458198eba98b7207669a166e64d04b04cb651b Gitweb: https://git.kernel.org/tip/9a458198eba98b7207669a166e64d04b04cb651b Author: Paolo Bonzini <pbonzini(a)redhat.com> AuthorDate: Thu, 01 Feb 2024 00:09:01 +01:00 Committer: Dave Hansen <dave.hansen(a)linux.intel.com> CommitterDate: Mon, 26 Feb 2024 08:16:15 -08:00 x86/cpu: Allow reducing x86_phys_bits during early_identify_cpu() In commit fbf6449f84bf ("x86/sev-es: Set x86_virt_bits to the correct value straight away, instead of a two-phase approach"), the initialization of c->x86_phys_bits was moved after this_cpu->c_early_init(c). This is incorrect because early_init_amd() expected to be able to reduce the value according to the contents of CPUID leaf 0x8000001f. Fortunately, the bug was negated by init_amd()'s call to early_init_amd(), which does reduce x86_phys_bits in the end. However, this is very late in the boot process and, most notably, the wrong value is used for x86_phys_bits when setting up MTRRs. To fix this, call get_cpu_address_sizes() as soon as X86_FEATURE_CPUID is set/cleared, and c->extended_cpuid_level is retrieved. Fixes: fbf6449f84bf ("x86/sev-es: Set x86_virt_bits to the correct value straight away, instead of a two-phase approach") Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> Cc:stable@vger.kernel.org Link: https://lore.kernel.org/all/20240131230902.1867092-2-pbonzini%40redhat.com --- arch/x86/kernel/cpu/common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0b97bcd..fbc4e60 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1589,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) get_cpu_vendor(c); get_cpu_cap(c); setup_force_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); cpu_parse_early_param(); if (this_cpu->c_early_init) @@ -1601,10 +1602,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_bsp_init(c); } else { setup_clear_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); } - get_cpu_address_sizes(c); - setup_force_cpu_cap(X86_FEATURE_ALWAYS); cpu_set_bug_bits(c);

1 year, 8 months

1
0
0 0

[tip: x86/urgent] x86/cpu/intel: Detect TME keyid bits before setting MTRR mask registers

by tip-bot2 for Paolo Bonzini

The following commit has been merged into the x86/urgent branch of tip: Commit-ID: 6890cb1ace350b4386c8aee1343dc3b3ddd214da Gitweb: https://git.kernel.org/tip/6890cb1ace350b4386c8aee1343dc3b3ddd214da Author: Paolo Bonzini <pbonzini(a)redhat.com> AuthorDate: Thu, 01 Feb 2024 00:09:02 +01:00 Committer: Dave Hansen <dave.hansen(a)linux.intel.com> CommitterDate: Mon, 26 Feb 2024 08:16:16 -08:00 x86/cpu/intel: Detect TME keyid bits before setting MTRR mask registers MKTME repurposes the high bit of physical address to key id for encryption key and, even though MAXPHYADDR in CPUID[0x80000008] remains the same, the valid bits in the MTRR mask register are based on the reduced number of physical address bits. detect_tme() in arch/x86/kernel/cpu/intel.c detects TME and subtracts it from the total usable physical bits, but it is called too late. Move the call to early_init_intel() so that it is called in setup_arch(), before MTRRs are setup. This fixes boot on TDX-enabled systems, which until now only worked with "disable_mtrr_cleanup". Without the patch, the values written to the MTRRs mask registers were 52-bit wide (e.g. 0x000fffff_80000800) and the writes failed; with the patch, the values are 46-bit wide, which matches the reduced MAXPHYADDR that is shown in /proc/cpuinfo. Reported-by: Zixi Chen <zixchen(a)redhat.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> Cc:stable@vger.kernel.org Link: https://lore.kernel.org/all/20240131230902.1867092-3-pbonzini%40redhat.com --- arch/x86/kernel/cpu/intel.c | 178 +++++++++++++++++------------------ 1 file changed, 91 insertions(+), 87 deletions(-) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index a927a8f..40dec9b 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) return false; } +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme_early(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -322,6 +406,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (detect_extended_topology_early(c) < 0) detect_ht_early(c); + + /* + * Adjust the number of physical bits early because it affects the + * valid bits of the MTRR mask registers. + */ + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme_early(c); } static void bsp_init_intel(struct cpuinfo_x86 *c) @@ -482,90 +573,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -#define MSR_IA32_TME_ACTIVATE 0x982 - -/* Helpers to access TME_ACTIVATE MSR */ -#define TME_ACTIVATE_LOCKED(x) (x & 0x1) -#define TME_ACTIVATE_ENABLED(x) (x & 0x2) - -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - -#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ - -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - -static void detect_tme(struct cpuinfo_x86 *c) -{ - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; - - rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { - pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; - return; - } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: - keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } - - /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. - */ - c->x86_phys_bits -= keyid_bits; -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -702,9 +709,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_ia32_feat_ctl(c); - if (cpu_has(c, X86_FEATURE_TME)) - detect_tme(c); - init_intel_misc_features(c); split_lock_init();

1 year, 8 months

1
0
0 0

[PATCH] landlock: Warn once if a Landlock action is requested while disabled

by Mickaël Salaün

Because sandboxing can be used as an opportunistic security measure, user space may not log unsupported features. Let the system administrator know if an application tries to use Landlock but failed because it isn't enabled at boot time. This may be caused by bootloader configurations with outdated "lsm" kernel's command-line parameter. Cc: Günther Noack <gnoack(a)google.com> Cc: stable(a)vger.kernel.org Fixes: 265885daf3e5 ("landlock: Add syscall implementations") Signed-off-by: Mickaël Salaün <mic(a)digikod.net> --- security/landlock/syscalls.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index f0bc50003b46..b5b424819dee 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -33,6 +33,18 @@ #include "ruleset.h" #include "setup.h" +static bool is_not_initialized(void) +{ + if (likely(landlock_initialized)) + return false; + + pr_warn_once( + "Disabled but requested by user space. " + "You should enable Landlock at boot time: " + "https://docs.kernel.org/userspace-api/landlock.html#kernel-support\n"); + return true; +} + /** * copy_min_struct_from_user - Safe future-proof argument copying * @@ -173,7 +185,7 @@ SYSCALL_DEFINE3(landlock_create_ruleset, /* Build-time checks. */ build_check_abi(); - if (!landlock_initialized) + if (is_not_initialized()) return -EOPNOTSUPP; if (flags) { @@ -407,7 +419,7 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, struct landlock_ruleset *ruleset; int err; - if (!landlock_initialized) + if (is_not_initialized()) return -EOPNOTSUPP; /* No flag for now. */ @@ -467,7 +479,7 @@ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, struct landlock_cred_security *new_llcred; int err; - if (!landlock_initialized) + if (is_not_initialized()) return -EOPNOTSUPP; /* -- 2.43.0

1 year, 8 months

3
4
0 0

[PATCH 5.10 0/1] rcutorture: Add missing return and use __func__ in warning

by Daniil Dulov

Svacer reports a potential division by zero at rcu_torture_writer() in 5.10 stable release. The problem has been fixed by the following patch that can be cleanly applied to 5.10 branches.

1 year, 8 months

1
1
0 0

[PATCH v2 1/3] PCI/DPC: Request DPC only if also requesting AER

by Bjorn Helgaas

From: Bjorn Helgaas <bhelgaas(a)google.com> When booting with "pci=noaer", we don't request control of AER, but we previously *did* request control of DPC, as in the dmesg log attached at the bugzilla below: Command line: ... pci=noaer acpi PNP0A08:00: _OSC: OS supports [ExtendedConfig ASPM ClockPM Segments MSI EDR HPX-Type3] acpi PNP0A08:00: _OSC: OS now controls [PCIeHotplug SHPCHotplug PME PCIeCapability LTR DPC] That's illegal per PCI Firmware Spec, r3.3, sec 4.5.1, table 4-5, which says: If the operating system sets this bit [OSC_PCI_EXPRESS_DPC_CONTROL], it must also set bit 7 of the Support field (indicating support for Error Disconnect Recover notifications) and bits 3 and 4 of the Control field (requesting control of PCI Express Advanced Error Reporting and the PCI Express Capability Structure). Request DPC control only if we have also requested AER control. Fixes: ac1c8e35a326 ("PCI/DPC: Add Error Disconnect Recover (EDR) support") Link: https://bugzilla.kernel.org/show_bug.cgi?id=218491#c12 Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com> Cc: <stable(a)vger.kernel.org> # v5.7+ Cc: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy(a)linux.intel.com> Cc: Matthew W Carlis <mattc(a)purestorage.com> Cc: Keith Busch <kbusch(a)kernel.org> Cc: Lukas Wunner <lukas(a)wunner.de> Cc: Mika Westerberg <mika.westerberg(a)linux.intel.com> Cc: Jesse Brandeburg <jesse.brandeburg(a)intel.com> --- drivers/acpi/pci_root.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 58b89b8d950e..efc292b6214e 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -518,17 +518,19 @@ static u32 calculate_control(void) if (IS_ENABLED(CONFIG_HOTPLUG_PCI_SHPC)) control |= OSC_PCI_SHPC_NATIVE_HP_CONTROL; - if (pci_aer_available()) + if (pci_aer_available()) { control |= OSC_PCI_EXPRESS_AER_CONTROL; - /* - * Per the Downstream Port Containment Related Enhancements ECN to - * the PCI Firmware Spec, r3.2, sec 4.5.1, table 4-5, - * OSC_PCI_EXPRESS_DPC_CONTROL indicates the OS supports both DPC - * and EDR. - */ - if (IS_ENABLED(CONFIG_PCIE_DPC) && IS_ENABLED(CONFIG_PCIE_EDR)) - control |= OSC_PCI_EXPRESS_DPC_CONTROL; + /* + * Per PCI Firmware Spec, r3.3, sec 4.5.1, table 4-5, the + * OS can request DPC control only if it has advertised + * OSC_PCI_EDR_SUPPORT and requested both + * OSC_PCI_EXPRESS_CAPABILITY_CONTROL and + * OSC_PCI_EXPRESS_AER_CONTROL. + */ + if (IS_ENABLED(CONFIG_PCIE_DPC)) + control |= OSC_PCI_EXPRESS_DPC_CONTROL; + } return control; } -- 2.34.1

1 year, 8 months

2
5
0 0

[PATCH] cxl/acpi: Fix load failures due to single window creation failure

by Dan Williams

The expectation is that cxl_parse_cfwms() continues in the face the of failure as evidenced by code like: cxlrd = cxl_root_decoder_alloc(root_port, ways, cxl_calc_hb); if (IS_ERR(cxlrd)) return 0; There are other error paths in that function which mistakenly follow idiomatic expectations and return an error when they should not. Most of those mistakes are innocuous checks that hardly ever fail in practice. However, a recent change succeed in making the implementation more fragile by applying an idiomatic, but still wrong "fix" [1]. In this failure case the kernel reports: cxl root0: Failed to populate active decoder targets cxl_acpi ACPI0017:00: Failed to add decode range: [mem 0x00000000-0x7fffffff flags 0x200] ...which is a real issue with that one window (to be fixed separately), but ends up failing the entirety of cxl_acpi_probe(). Undo that recent breakage while also removing the confusion about ignoring errors. Update all exits paths to return an error per typical expectations and let an outer wrapper function handle dropping the error. Fixes: 91019b5bc7c2 ("cxl/acpi: Return 'rc' instead of '0' in cxl_parse_cfmws()") [1] Cc: <stable(a)vger.kernel.org> Cc: Breno Leitao <leitao(a)debian.org> Cc: Alison Schofield <alison.schofield(a)intel.com> Cc: Vishal Verma <vishal.l.verma(a)intel.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> --- drivers/cxl/acpi.c | 45 +++++++++++++++++++++++++++------------------ 1 file changed, 27 insertions(+), 18 deletions(-) diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index dcf2b39e1048..53d2dff0c7a3 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -316,31 +316,27 @@ static const struct cxl_root_ops acpi_root_ops = { .qos_class = cxl_acpi_qos_class, }; -static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, - const unsigned long end) +static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws, + struct cxl_cfmws_context *ctx) { int target_map[CXL_DECODER_MAX_INTERLEAVE]; - struct cxl_cfmws_context *ctx = arg; struct cxl_port *root_port = ctx->root_port; struct resource *cxl_res = ctx->cxl_res; struct cxl_cxims_context cxims_ctx; struct cxl_root_decoder *cxlrd; struct device *dev = ctx->dev; - struct acpi_cedt_cfmws *cfmws; cxl_calc_hb_fn cxl_calc_hb; struct cxl_decoder *cxld; unsigned int ways, i, ig; struct resource *res; int rc; - cfmws = (struct acpi_cedt_cfmws *) header; - rc = cxl_acpi_cfmws_verify(dev, cfmws); if (rc) { dev_err(dev, "CFMWS range %#llx-%#llx not registered\n", cfmws->base_hpa, cfmws->base_hpa + cfmws->window_size - 1); - return 0; + return rc; } rc = eiw_to_ways(cfmws->interleave_ways, &ways); @@ -376,7 +372,7 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, cxlrd = cxl_root_decoder_alloc(root_port, ways, cxl_calc_hb); if (IS_ERR(cxlrd)) - return 0; + return PTR_ERR(cxlrd); cxld = &cxlrd->cxlsd.cxld; cxld->flags = cfmws_to_decoder_flags(cfmws->restrictions); @@ -420,16 +416,7 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, put_device(&cxld->dev); else rc = cxl_decoder_autoremove(dev, cxld); - if (rc) { - dev_err(dev, "Failed to add decode range: %pr", res); - return rc; - } - dev_dbg(dev, "add: %s node: %d range [%#llx - %#llx]\n", - dev_name(&cxld->dev), - phys_to_target_node(cxld->hpa_range.start), - cxld->hpa_range.start, cxld->hpa_range.end); - - return 0; + return rc; err_insert: kfree(res->name); @@ -438,6 +425,28 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, return -ENOMEM; } +static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, + const unsigned long end) +{ + struct acpi_cedt_cfmws *cfmws = (struct acpi_cedt_cfmws *)header; + struct cxl_cfmws_context *ctx = arg; + struct device *dev = ctx->dev; + int rc; + + dev_dbg(dev, "decode range: node: %d range [%#llx - %#llx]\n", + phys_to_target_node(cfmws->base_hpa), cfmws->base_hpa, + cfmws->base_hpa + cfmws->window_size - 1); + rc = __cxl_parse_cfmws(cfmws, ctx); + if (rc) + dev_err(dev, + "Failed to add decode range: [%#llx - %#llx] (%d)\n", + cfmws->base_hpa, + cfmws->base_hpa + cfmws->window_size - 1, rc); + + /* never fail cxl_acpi load for a single window failure */ + return 0; +} + __mock struct acpi_device *to_cxl_host_bridge(struct device *host, struct device *dev) {

1 year, 8 months

2
8
0 0

[PATCH 0/2] possible deadlock in sco_conn_del

by Alexander Ofitserov

This bug was found by syzkaller. This series of patches is fix for this particular bug. Both of these patches were taken from upstream and applied clearly without any conflicts. First one is the fix for the problem and another one is for fix first patch. Luiz Augusto von Dentz (1): Bluetooth: SCO: Fix possible circular locking dependency on sco_connect_cfm Pauli Virtanen (1): Bluetooth: SCO: fix sco_conn related locking and validity issues net/bluetooth/sco.c | 76 ++++++++++++++++++++++++++------------------- 1 file changed, 44 insertions(+), 32 deletions(-) -- 2.42.1

1 year, 8 months

1
2
0 0

FAILED: patch "[PATCH] mptcp: fix data races on local_id" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x a7cfe776637004a4c938fde78be4bd608c32c3ef # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022611-duh-rising-d12e@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: a7cfe7766370 ("mptcp: fix data races on local_id") 84c531f54ad9 ("mptcp: userspace pm send RM_ADDR for ID 0") f1f26512a9bf ("mptcp: use plain bool instead of custom binary enum") 1e07938e29c5 ("net: mptcp: rename netlink handlers to mptcp_pm_nl_<blah>_{doit,dumpit}") 1d0507f46843 ("net: mptcp: convert netlink from small_ops to ops") fce68b03086f ("mptcp: add scheduled in mptcp_subflow_context") 1730b2b2c5a5 ("mptcp: add sched in mptcp_sock") 740ebe35bd3f ("mptcp: add struct mptcp_sched_ops") a7384f391875 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a7cfe776637004a4c938fde78be4bd608c32c3ef Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Thu, 15 Feb 2024 19:25:31 +0100 Subject: [PATCH] mptcp: fix data races on local_id The local address id is accessed lockless by the NL PM, add all the required ONCE annotation. There is a caveat: the local id can be initialized late in the subflow life-cycle, and its validity is controlled by the local_id_valid flag. Remove such flag and encode the validity in the local_id field itself with negative value before initialization. That allows accessing the field consistently with a single read operation. Fixes: 0ee4261a3681 ("mptcp: implement mptcp_pm_remove_subflow") Cc: stable(a)vger.kernel.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index e57c5f47f035..6ff6f14674aa 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -65,7 +65,7 @@ static int subflow_get_info(struct sock *sk, struct sk_buff *skb) sf->map_data_len) || nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) || nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) || - nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) { + nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) { err = -EMSGSIZE; goto nla_failure; } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index a24c9128dee9..912e25077437 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -800,7 +800,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int how = RCV_SHUTDOWN | SEND_SHUTDOWN; - u8 id = subflow->local_id; + u8 id = subflow_get_local_id(subflow); if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id) continue; @@ -809,7 +809,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", - i, rm_id, subflow->local_id, subflow->remote_id, + i, rm_id, id, subflow->remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, how); @@ -1994,7 +1994,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) if (WARN_ON_ONCE(!sf)) return -EINVAL; - if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id)) + if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf))) return -EMSGSIZE; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index e582b3b2d174..d396a5973429 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -234,7 +234,7 @@ static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk, lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { - if (subflow->local_id == 0) { + if (READ_ONCE(subflow->local_id) == 0) { has_id_0 = true; break; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8ef2927ebca2..948606a537da 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -85,7 +85,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) subflow->subflow_id = msk->subflow_id++; /* This is the first subflow, always with id 0 */ - subflow->local_id_valid = 1; + WRITE_ONCE(subflow->local_id, 0); mptcp_sock_graft(msk->first, sk->sk_socket); iput(SOCK_INODE(ssock)); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index ed50f2015dc3..631a7f445f34 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -491,10 +491,9 @@ struct mptcp_subflow_context { remote_key_valid : 1, /* received the peer key from */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1, /* local_id is correctly initialized */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ - __unused : 9; + __unused : 10; bool data_avail; bool scheduled; u32 remote_nonce; @@ -505,7 +504,7 @@ struct mptcp_subflow_context { u8 hmac[MPTCPOPT_HMAC_LEN]; /* MPJ subflow only */ u64 iasn; /* initial ack sequence number, MPC subflows only */ }; - u8 local_id; + s16 local_id; /* if negative not initialized yet */ u8 remote_id; u8 reset_seen:1; u8 reset_transient:1; @@ -556,6 +555,7 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow) { memset(&subflow->reset, 0, sizeof(subflow->reset)); subflow->request_mptcp = 1; + WRITE_ONCE(subflow->local_id, -1); } static inline u64 @@ -1022,6 +1022,15 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow) +{ + int local_id = READ_ONCE(subflow->local_id); + + if (local_id < 0) + return 0; + return local_id; +} + void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index c34ecadee120..015184bbf06c 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -577,8 +577,8 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id) { - subflow->local_id = local_id; - subflow->local_id_valid = 1; + WARN_ON_ONCE(local_id < 0 || local_id > 255); + WRITE_ONCE(subflow->local_id, local_id); } static int subflow_chk_local_id(struct sock *sk) @@ -587,7 +587,7 @@ static int subflow_chk_local_id(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(subflow->conn); int err; - if (likely(subflow->local_id_valid)) + if (likely(subflow->local_id >= 0)) return 0; err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk); @@ -1731,6 +1731,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, pr_debug("subflow=%p", ctx); ctx->tcp_sock = sk; + WRITE_ONCE(ctx->local_id, -1); return ctx; } @@ -1966,7 +1967,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->idsn = subflow_req->idsn; /* this is the first subflow, id is always 0 */ - new_ctx->local_id_valid = 1; + subflow_set_local_id(new_ctx, 0); } else if (subflow_req->mp_join) { new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->mp_join = 1;

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] mptcp: add needs_id for netlink appending addr" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 584f3894262634596532cf43a5e782e34a0ce374 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022626-oversold-imply-5fed@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 584f38942626 ("mptcp: add needs_id for netlink appending addr") aab4d8564947 ("net: mptcp: use policy generated by YAML spec") 1e07938e29c5 ("net: mptcp: rename netlink handlers to mptcp_pm_nl_<blah>_{doit,dumpit}") 1d0507f46843 ("net: mptcp: convert netlink from small_ops to ops") 740ebe35bd3f ("mptcp: add struct mptcp_sched_ops") 6ba7ce89905c ("mptcp: unify pm set_flags interfaces") a963853fd465 ("mptcp: use net instead of sock_net") dfc8d0603033 ("mptcp: implement delayed seq generation for passive fastopen") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 584f3894262634596532cf43a5e782e34a0ce374 Mon Sep 17 00:00:00 2001 From: Geliang Tang <tanggeliang(a)kylinos.cn> Date: Thu, 15 Feb 2024 19:25:29 +0100 Subject: [PATCH] mptcp: add needs_id for netlink appending addr Just the same as userspace PM, a new parameter needs_id is added for in-kernel PM mptcp_pm_nl_append_new_local_addr() too. Add a new helper mptcp_pm_has_addr_attr_id() to check whether an address ID is set from PM or not. In mptcp_pm_nl_get_local_id(), needs_id is always true, but in mptcp_pm_nl_add_addr_doit(), pass mptcp_pm_has_addr_attr_id() to needs_it. Fixes: efd5a4c04e18 ("mptcp: add the address ID assignment bitmap") Cc: stable(a)vger.kernel.org Signed-off-by: Geliang Tang <tanggeliang(a)kylinos.cn> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 287a60381eae..a24c9128dee9 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -901,7 +901,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) } static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; @@ -949,7 +950,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id) { + if (!entry->addr.id && needs_id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, @@ -960,7 +961,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id) + if (!entry->addr.id && needs_id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); @@ -1092,7 +1093,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc entry->ifindex = 0; entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); if (ret < 0) kfree(entry); @@ -1285,6 +1286,18 @@ static int mptcp_nl_add_subflow_or_signal_addr(struct net *net) return 0; } +static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr, + struct genl_info *info) +{ + struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; + + if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, + mptcp_pm_address_nl_policy, info->extack) && + tb[MPTCP_PM_ADDR_ATTR_ID]) + return true; + return false; +} + int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; @@ -1326,7 +1339,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) goto out_free; } } - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, + !mptcp_pm_has_addr_attr_id(attr, info)); if (ret < 0) { GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); goto out_free;

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] usb: roles: fix NULL pointer issue when put module's" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 1c9be13846c0b2abc2480602f8ef421360e1ad9e # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022632-wise-dose-46ed@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: 1c9be13846c0 ("usb: roles: fix NULL pointer issue when put module's reference") 044a61158b9e ("USB: roles: make role_class a static const structure") 1aaba11da9aa ("driver core: class: remove module * from class_create()") 6e30a66433af ("driver core: class: remove struct module owner out of struct class") 0b2a1a3938aa ("driver core: class: Clear private pointer on registration failures") 71a7507afbc3 ("Merge tag 'driver-core-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1c9be13846c0b2abc2480602f8ef421360e1ad9e Mon Sep 17 00:00:00 2001 From: Xu Yang <xu.yang_2(a)nxp.com> Date: Mon, 29 Jan 2024 17:37:38 +0800 Subject: [PATCH] usb: roles: fix NULL pointer issue when put module's reference In current design, usb role class driver will get usb_role_switch parent's module reference after the user get usb_role_switch device and put the reference after the user put the usb_role_switch device. However, the parent device of usb_role_switch may be removed before the user put the usb_role_switch. If so, then, NULL pointer issue will be met when the user put the parent module's reference. This will save the module pointer in structure of usb_role_switch. Then, we don't need to find module by iterating long relations. Fixes: 5c54fcac9a9d ("usb: roles: Take care of driver module reference counting") cc: stable(a)vger.kernel.org Signed-off-by: Xu Yang <xu.yang_2(a)nxp.com> Acked-by: Heikki Krogerus <heikki.krogerus(a)linux.intel.com> Link: https://lore.kernel.org/r/20240129093739.2371530-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index ae41578bd014..2bad038fb9ad 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -21,6 +21,7 @@ static const struct class role_class = { struct usb_role_switch { struct device dev; struct mutex lock; /* device lock*/ + struct module *module; /* the module this device depends on */ enum usb_role role; /* From descriptor */ @@ -135,7 +136,7 @@ struct usb_role_switch *usb_role_switch_get(struct device *dev) usb_role_switch_match); if (!IS_ERR_OR_NULL(sw)) - WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + WARN_ON(!try_module_get(sw->module)); return sw; } @@ -157,7 +158,7 @@ struct usb_role_switch *fwnode_usb_role_switch_get(struct fwnode_handle *fwnode) sw = fwnode_connection_find_match(fwnode, "usb-role-switch", NULL, usb_role_switch_match); if (!IS_ERR_OR_NULL(sw)) - WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + WARN_ON(!try_module_get(sw->module)); return sw; } @@ -172,7 +173,7 @@ EXPORT_SYMBOL_GPL(fwnode_usb_role_switch_get); void usb_role_switch_put(struct usb_role_switch *sw) { if (!IS_ERR_OR_NULL(sw)) { - module_put(sw->dev.parent->driver->owner); + module_put(sw->module); put_device(&sw->dev); } } @@ -189,15 +190,18 @@ struct usb_role_switch * usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) { struct device *dev; + struct usb_role_switch *sw = NULL; if (!fwnode) return NULL; dev = class_find_device_by_fwnode(&role_class, fwnode); - if (dev) - WARN_ON(!try_module_get(dev->parent->driver->owner)); + if (dev) { + sw = to_role_switch(dev); + WARN_ON(!try_module_get(sw->module)); + } - return dev ? to_role_switch(dev) : NULL; + return sw; } EXPORT_SYMBOL_GPL(usb_role_switch_find_by_fwnode); @@ -338,6 +342,7 @@ usb_role_switch_register(struct device *parent, sw->set = desc->set; sw->get = desc->get; + sw->module = parent->driver->owner; sw->dev.parent = parent; sw->dev.fwnode = desc->fwnode; sw->dev.class = &role_class;

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] usb: roles: fix NULL pointer issue when put module's" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 1c9be13846c0b2abc2480602f8ef421360e1ad9e # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022630-streak-bleep-1f75@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: 1c9be13846c0 ("usb: roles: fix NULL pointer issue when put module's reference") 044a61158b9e ("USB: roles: make role_class a static const structure") 1aaba11da9aa ("driver core: class: remove module * from class_create()") 6e30a66433af ("driver core: class: remove struct module owner out of struct class") 0b2a1a3938aa ("driver core: class: Clear private pointer on registration failures") 71a7507afbc3 ("Merge tag 'driver-core-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1c9be13846c0b2abc2480602f8ef421360e1ad9e Mon Sep 17 00:00:00 2001 From: Xu Yang <xu.yang_2(a)nxp.com> Date: Mon, 29 Jan 2024 17:37:38 +0800 Subject: [PATCH] usb: roles: fix NULL pointer issue when put module's reference In current design, usb role class driver will get usb_role_switch parent's module reference after the user get usb_role_switch device and put the reference after the user put the usb_role_switch device. However, the parent device of usb_role_switch may be removed before the user put the usb_role_switch. If so, then, NULL pointer issue will be met when the user put the parent module's reference. This will save the module pointer in structure of usb_role_switch. Then, we don't need to find module by iterating long relations. Fixes: 5c54fcac9a9d ("usb: roles: Take care of driver module reference counting") cc: stable(a)vger.kernel.org Signed-off-by: Xu Yang <xu.yang_2(a)nxp.com> Acked-by: Heikki Krogerus <heikki.krogerus(a)linux.intel.com> Link: https://lore.kernel.org/r/20240129093739.2371530-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index ae41578bd014..2bad038fb9ad 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -21,6 +21,7 @@ static const struct class role_class = { struct usb_role_switch { struct device dev; struct mutex lock; /* device lock*/ + struct module *module; /* the module this device depends on */ enum usb_role role; /* From descriptor */ @@ -135,7 +136,7 @@ struct usb_role_switch *usb_role_switch_get(struct device *dev) usb_role_switch_match); if (!IS_ERR_OR_NULL(sw)) - WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + WARN_ON(!try_module_get(sw->module)); return sw; } @@ -157,7 +158,7 @@ struct usb_role_switch *fwnode_usb_role_switch_get(struct fwnode_handle *fwnode) sw = fwnode_connection_find_match(fwnode, "usb-role-switch", NULL, usb_role_switch_match); if (!IS_ERR_OR_NULL(sw)) - WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + WARN_ON(!try_module_get(sw->module)); return sw; } @@ -172,7 +173,7 @@ EXPORT_SYMBOL_GPL(fwnode_usb_role_switch_get); void usb_role_switch_put(struct usb_role_switch *sw) { if (!IS_ERR_OR_NULL(sw)) { - module_put(sw->dev.parent->driver->owner); + module_put(sw->module); put_device(&sw->dev); } } @@ -189,15 +190,18 @@ struct usb_role_switch * usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) { struct device *dev; + struct usb_role_switch *sw = NULL; if (!fwnode) return NULL; dev = class_find_device_by_fwnode(&role_class, fwnode); - if (dev) - WARN_ON(!try_module_get(dev->parent->driver->owner)); + if (dev) { + sw = to_role_switch(dev); + WARN_ON(!try_module_get(sw->module)); + } - return dev ? to_role_switch(dev) : NULL; + return sw; } EXPORT_SYMBOL_GPL(usb_role_switch_find_by_fwnode); @@ -338,6 +342,7 @@ usb_role_switch_register(struct device *parent, sw->set = desc->set; sw->get = desc->get; + sw->module = parent->driver->owner; sw->dev.parent = parent; sw->dev.fwnode = desc->fwnode; sw->dev.class = &role_class;

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] irqchip/gic-v3-its: Do not assume vPE tables are preallocated" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x ec4308ecfc887128a468f03fb66b767559c57c23 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022602-daunting-dreamland-882c@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: ec4308ecfc88 ("irqchip/gic-v3-its: Do not assume vPE tables are preallocated") c0cdc89072a3 ("irqchip/gic-v3-its: Give the percpu rdist struct its own flags field") 5e5168461c22 ("irqchip/gic-v4.1: VPE table (aka GICR_VPROPBASER) allocation") b25319d279b6 ("irqchip/gic-v3: Detect GICv4.1 supporting RVPEID") 576a83429757 ("irqchip/gic-v3-its: Kill its->device_ids and use TYPER copy instead") ffedbf0cba15 ("irqchip/gic-v3-its: Kill its->ite_size and use TYPER copy instead") 0dd57fed6b46 ("irqchip/gic-v3-its: Make is_v4 use a TYPER copy") 8424312516e5 ("irqchip/gic-v3-its: Use the exact ITSList for VMOVP") 5f51f803826e ("irqchip/gic-v3: Add EPPI range support") 81a43273045b ("irqchip/gic-v3: Dynamically allocate PPI NMI refcounts") 1a60e1e64391 ("irqchip/gic: Prepare for more than 16 PPIs") 211bddd210a6 ("irqchip/gic-v3: Add ESPI range support") e91b036e1c20 ("irqchip/gic-v3: Add INTID range and convertion primitives") 13d22e2e1f35 ("irqchip/gic: Rework gic_configure_irq to take the full ICFGR base") 3d8dfe75ef69 ("Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ec4308ecfc887128a468f03fb66b767559c57c23 Mon Sep 17 00:00:00 2001 From: Oliver Upton <oliver.upton(a)linux.dev> Date: Mon, 19 Feb 2024 18:58:06 +0000 Subject: [PATCH] irqchip/gic-v3-its: Do not assume vPE tables are preallocated The GIC/ITS code is designed to ensure to pick up any preallocated LPI tables on the redistributors, as enabling LPIs is a one-way switch. There is no such restriction for vLPIs, and for GICv4.1 it is expected to allocate a new vPE table at boot. This works as intended when initializing an ITS, however when setting up a redistributor in cpu_init_lpis() the early return for preallocated RD tables skips straight past the GICv4 setup. This all comes to a head when trying to kexec() into a new kernel, as the new kernel silently fails to set up GICv4, leading to a complete loss of SGIs and LPIs for KVM VMs. Slap a band-aid on the problem by ensuring its_cpu_init_lpis() always initializes GICv4 on the way out, even if the other RD tables were preallocated. Fixes: 6479450f72c1 ("irqchip/gic-v4: Fix occasional VLPI drop") Reported-by: George Cherian <gcherian(a)marvell.com> Co-developed-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20240219185809.286724-2-oliver.upton@linux.dev diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 53abd4779914..b822752c4261 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3181,6 +3181,7 @@ static void its_cpu_init_lpis(void) val |= GICR_CTLR_ENABLE_LPIS; writel_relaxed(val, rbase + GICR_CTLR); +out: if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); @@ -3216,7 +3217,6 @@ static void its_cpu_init_lpis(void) /* Make sure the GIC has seen the above */ dsb(sy); -out: gic_data_rdist()->flags |= RD_LOCAL_LPI_ENABLED; pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n", smp_processor_id(),

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] irqchip/gic-v3-its: Do not assume vPE tables are preallocated" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x ec4308ecfc887128a468f03fb66b767559c57c23 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022658-brethren-stopper-8b5e@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: ec4308ecfc88 ("irqchip/gic-v3-its: Do not assume vPE tables are preallocated") c0cdc89072a3 ("irqchip/gic-v3-its: Give the percpu rdist struct its own flags field") 5e5168461c22 ("irqchip/gic-v4.1: VPE table (aka GICR_VPROPBASER) allocation") b25319d279b6 ("irqchip/gic-v3: Detect GICv4.1 supporting RVPEID") 576a83429757 ("irqchip/gic-v3-its: Kill its->device_ids and use TYPER copy instead") ffedbf0cba15 ("irqchip/gic-v3-its: Kill its->ite_size and use TYPER copy instead") 0dd57fed6b46 ("irqchip/gic-v3-its: Make is_v4 use a TYPER copy") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ec4308ecfc887128a468f03fb66b767559c57c23 Mon Sep 17 00:00:00 2001 From: Oliver Upton <oliver.upton(a)linux.dev> Date: Mon, 19 Feb 2024 18:58:06 +0000 Subject: [PATCH] irqchip/gic-v3-its: Do not assume vPE tables are preallocated The GIC/ITS code is designed to ensure to pick up any preallocated LPI tables on the redistributors, as enabling LPIs is a one-way switch. There is no such restriction for vLPIs, and for GICv4.1 it is expected to allocate a new vPE table at boot. This works as intended when initializing an ITS, however when setting up a redistributor in cpu_init_lpis() the early return for preallocated RD tables skips straight past the GICv4 setup. This all comes to a head when trying to kexec() into a new kernel, as the new kernel silently fails to set up GICv4, leading to a complete loss of SGIs and LPIs for KVM VMs. Slap a band-aid on the problem by ensuring its_cpu_init_lpis() always initializes GICv4 on the way out, even if the other RD tables were preallocated. Fixes: 6479450f72c1 ("irqchip/gic-v4: Fix occasional VLPI drop") Reported-by: George Cherian <gcherian(a)marvell.com> Co-developed-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20240219185809.286724-2-oliver.upton@linux.dev diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 53abd4779914..b822752c4261 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3181,6 +3181,7 @@ static void its_cpu_init_lpis(void) val |= GICR_CTLR_ENABLE_LPIS; writel_relaxed(val, rbase + GICR_CTLR); +out: if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); @@ -3216,7 +3217,6 @@ static void its_cpu_init_lpis(void) /* Make sure the GIC has seen the above */ dsb(sy); -out: gic_data_rdist()->flags |= RD_LOCAL_LPI_ENABLED; pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n", smp_processor_id(),

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] irqchip/gic-v3-its: Do not assume vPE tables are preallocated" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x ec4308ecfc887128a468f03fb66b767559c57c23 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022654-drained-afterglow-ddb6@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: ec4308ecfc88 ("irqchip/gic-v3-its: Do not assume vPE tables are preallocated") c0cdc89072a3 ("irqchip/gic-v3-its: Give the percpu rdist struct its own flags field") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ec4308ecfc887128a468f03fb66b767559c57c23 Mon Sep 17 00:00:00 2001 From: Oliver Upton <oliver.upton(a)linux.dev> Date: Mon, 19 Feb 2024 18:58:06 +0000 Subject: [PATCH] irqchip/gic-v3-its: Do not assume vPE tables are preallocated The GIC/ITS code is designed to ensure to pick up any preallocated LPI tables on the redistributors, as enabling LPIs is a one-way switch. There is no such restriction for vLPIs, and for GICv4.1 it is expected to allocate a new vPE table at boot. This works as intended when initializing an ITS, however when setting up a redistributor in cpu_init_lpis() the early return for preallocated RD tables skips straight past the GICv4 setup. This all comes to a head when trying to kexec() into a new kernel, as the new kernel silently fails to set up GICv4, leading to a complete loss of SGIs and LPIs for KVM VMs. Slap a band-aid on the problem by ensuring its_cpu_init_lpis() always initializes GICv4 on the way out, even if the other RD tables were preallocated. Fixes: 6479450f72c1 ("irqchip/gic-v4: Fix occasional VLPI drop") Reported-by: George Cherian <gcherian(a)marvell.com> Co-developed-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20240219185809.286724-2-oliver.upton@linux.dev diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 53abd4779914..b822752c4261 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3181,6 +3181,7 @@ static void its_cpu_init_lpis(void) val |= GICR_CTLR_ENABLE_LPIS; writel_relaxed(val, rbase + GICR_CTLR); +out: if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); @@ -3216,7 +3217,6 @@ static void its_cpu_init_lpis(void) /* Make sure the GIC has seen the above */ dsb(sy); -out: gic_data_rdist()->flags |= RD_LOCAL_LPI_ENABLED; pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n", smp_processor_id(),

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] irqchip/gic-v3-its: Do not assume vPE tables are preallocated" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x ec4308ecfc887128a468f03fb66b767559c57c23 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022650-washroom-undusted-2aff@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: ec4308ecfc88 ("irqchip/gic-v3-its: Do not assume vPE tables are preallocated") c0cdc89072a3 ("irqchip/gic-v3-its: Give the percpu rdist struct its own flags field") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ec4308ecfc887128a468f03fb66b767559c57c23 Mon Sep 17 00:00:00 2001 From: Oliver Upton <oliver.upton(a)linux.dev> Date: Mon, 19 Feb 2024 18:58:06 +0000 Subject: [PATCH] irqchip/gic-v3-its: Do not assume vPE tables are preallocated The GIC/ITS code is designed to ensure to pick up any preallocated LPI tables on the redistributors, as enabling LPIs is a one-way switch. There is no such restriction for vLPIs, and for GICv4.1 it is expected to allocate a new vPE table at boot. This works as intended when initializing an ITS, however when setting up a redistributor in cpu_init_lpis() the early return for preallocated RD tables skips straight past the GICv4 setup. This all comes to a head when trying to kexec() into a new kernel, as the new kernel silently fails to set up GICv4, leading to a complete loss of SGIs and LPIs for KVM VMs. Slap a band-aid on the problem by ensuring its_cpu_init_lpis() always initializes GICv4 on the way out, even if the other RD tables were preallocated. Fixes: 6479450f72c1 ("irqchip/gic-v4: Fix occasional VLPI drop") Reported-by: George Cherian <gcherian(a)marvell.com> Co-developed-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20240219185809.286724-2-oliver.upton@linux.dev diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 53abd4779914..b822752c4261 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3181,6 +3181,7 @@ static void its_cpu_init_lpis(void) val |= GICR_CTLR_ENABLE_LPIS; writel_relaxed(val, rbase + GICR_CTLR); +out: if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); @@ -3216,7 +3217,6 @@ static void its_cpu_init_lpis(void) /* Make sure the GIC has seen the above */ dsb(sy); -out: gic_data_rdist()->flags |= RD_LOCAL_LPI_ENABLED; pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n", smp_processor_id(),

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] scsi: sd: usb_storage: uas: Access media prior to querying" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 321da3dc1f3c92a12e3c5da934090d2992a8814c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022657-skintight-fetal-ec4b@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 321da3dc1f3c ("scsi: sd: usb_storage: uas: Access media prior to querying device properties") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 321da3dc1f3c92a12e3c5da934090d2992a8814c Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" <martin.petersen(a)oracle.com> Date: Tue, 13 Feb 2024 09:33:06 -0500 Subject: [PATCH] scsi: sd: usb_storage: uas: Access media prior to querying device properties It has been observed that some USB/UAS devices return generic properties hardcoded in firmware for mode pages for a period of time after a device has been discovered. The reported properties are either garbage or they do not accurately reflect the characteristics of the physical storage device attached in the case of a bridge. Prior to commit 1e029397d12f ("scsi: sd: Reorganize DIF/DIX code to avoid calling revalidate twice") we would call revalidate several times during device discovery. As a result, incorrect values would eventually get replaced with ones accurately describing the attached storage. When we did away with the redundant revalidate pass, several cases were reported where devices reported nonsensical values or would end up in write-protected state. An initial attempt at addressing this issue involved introducing a delayed second revalidate invocation. However, this approach still left some devices reporting incorrect characteristics. Tasos Sahanidis debugged the problem further and identified that introducing a READ operation prior to MODE SENSE fixed the problem and that it wasn't a timing issue. Issuing a READ appears to cause the devices to update their state to reflect the actual properties of the storage media. Device properties like vendor, model, and storage capacity appear to be correctly reported from the get-go. It is unclear why these devices defer populating the remaining characteristics. Match the behavior of a well known commercial operating system and trigger a READ operation prior to querying device characteristics to force the device to populate the mode pages. The additional READ is triggered by a flag set in the USB storage and UAS drivers. We avoid issuing the READ for other transport classes since some storage devices identify Linux through our particular discovery command sequence. Link: https://lore.kernel.org/r/20240213143306.2194237-1-martin.petersen@oracle.c… Fixes: 1e029397d12f ("scsi: sd: Reorganize DIF/DIX code to avoid calling revalidate twice") Cc: stable(a)vger.kernel.org Reported-by: Tasos Sahanidis <tasos(a)tasossah.com> Reviewed-by: Ewan D. Milne <emilne(a)redhat.com> Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Tested-by: Tasos Sahanidis <tasos(a)tasossah.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 0833b3e6aa6e..bdd0acf7fa3c 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3407,6 +3407,24 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp, return true; } +static void sd_read_block_zero(struct scsi_disk *sdkp) +{ + unsigned int buf_len = sdkp->device->sector_size; + char *buffer, cmd[10] = { }; + + buffer = kmalloc(buf_len, GFP_KERNEL); + if (!buffer) + return; + + cmd[0] = READ_10; + put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be16(1, &cmd[7]); /* Transfer 1 logical block */ + + scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, buffer, buf_len, + SD_TIMEOUT, sdkp->max_retries, NULL); + kfree(buffer); +} + /** * sd_revalidate_disk - called the first time a new disk is seen, * performs disk spin up, read_capacity, etc. @@ -3446,7 +3464,13 @@ static int sd_revalidate_disk(struct gendisk *disk) */ if (sdkp->media_present) { sd_read_capacity(sdkp, buffer); - + /* + * Some USB/UAS devices return generic values for mode pages + * until the media has been accessed. Trigger a READ operation + * to force the device to populate mode pages. + */ + if (sdp->read_before_ms) + sd_read_block_zero(sdkp); /* * set the default to rotational. All non-rotational devices * support the block characteristics VPD page, which will diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index c54e9805da53..12cf9940e5b6 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -179,6 +179,13 @@ static int slave_configure(struct scsi_device *sdev) */ sdev->use_192_bytes_for_3f = 1; + /* + * Some devices report generic values until the media has been + * accessed. Force a READ(10) prior to querying device + * characteristics. + */ + sdev->read_before_ms = 1; + /* * Some devices don't like MODE SENSE with page=0x3f, * which is the command used for checking if a device diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 9707f53cfda9..71ace274761f 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -878,6 +878,13 @@ static int uas_slave_configure(struct scsi_device *sdev) if (devinfo->flags & US_FL_CAPACITY_HEURISTICS) sdev->guess_capacity = 1; + /* + * Some devices report generic values until the media has been + * accessed. Force a READ(10) prior to querying device + * characteristics. + */ + sdev->read_before_ms = 1; + /* * Some devices don't like MODE SENSE with page=0x3f, * which is the command used for checking if a device diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 5ec1e71a09de..01c02cb76ea6 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -208,6 +208,7 @@ struct scsi_device { unsigned use_10_for_rw:1; /* first try 10-byte read / write */ unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */ unsigned set_dbd_for_ms:1; /* Set "DBD" field in mode sense */ + unsigned read_before_ms:1; /* perform a READ before MODE SENSE */ unsigned no_report_opcodes:1; /* no REPORT SUPPORTED OPERATION CODES */ unsigned no_write_same:1; /* no WRITE SAME command */ unsigned use_16_for_rw:1; /* Use read/write(16) over read/write(10) */

1 year, 8 months

1
0
0 0

[PATCH] serial: Lock console when calling into driver before registration

by Peter Collingbourne

During the handoff from earlycon to the real console driver, we have two separate drivers operating on the same device concurrently. In the case of the 8250 driver these concurrent accesses cause problems due to the driver's use of banked registers, controlled by LCR.DLAB. It is possible for the setup(), config_port(), pm() and set_mctrl() callbacks to set DLAB, which can cause the earlycon code that intends to access TX to instead access DLL, leading to missed output and corruption on the serial line due to unintended modifications to the baud rate. In particular, for setup() we have: univ8250_console_setup() -> serial8250_console_setup() -> uart_set_options() -> serial8250_set_termios() -> serial8250_do_set_termios() -> serial8250_do_set_divisor() For config_port() we have: serial8250_config_port() -> autoconfig() For pm() we have: serial8250_pm() -> serial8250_do_pm() -> serial8250_set_sleep() For set_mctrl() we have (for some devices): serial8250_set_mctrl() -> omap8250_set_mctrl() -> __omap8250_set_mctrl() To avoid such problems, let's make it so that the console is locked during pre-registration calls to these callbacks, which will prevent the earlycon driver from running concurrently. Remove the partial solution to this problem in the 8250 driver that locked the console only during autoconfig_irq(), as this would result in a deadlock with the new approach. The console continues to be locked during autoconfig_irq() because it can only be called through uart_configure_port(). Although this patch introduces more locking than strictly necessary (and in particular it also locks during the call to rs485_config() which is not affected by this issue as far as I can tell), it follows the principle that it is the responsibility of the generic console code to manage the earlycon handoff by ensuring that earlycon and real console driver code cannot run concurrently, and not the individual drivers. Signed-off-by: Peter Collingbourne <pcc(a)google.com> Link: https://linux-review.googlesource.com/id/I7cf8124dcebf8618e6b2ee543fa5b2553… Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable(a)vger.kernel.org --- drivers/tty/serial/8250/8250_port.c | 6 ------ drivers/tty/serial/serial_core.c | 10 ++++++++++ kernel/printk/printk.c | 20 +++++++++++++++++--- 3 files changed, 27 insertions(+), 9 deletions(-) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 8ca061d3bbb9..1d65055dde27 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1329,9 +1329,6 @@ static void autoconfig_irq(struct uart_8250_port *up) inb_p(ICP); } - if (uart_console(port)) - console_lock(); - /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); @@ -1371,9 +1368,6 @@ static void autoconfig_irq(struct uart_8250_port *up) if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); - if (uart_console(port)) - console_unlock(); - port->irq = (irq > 0) ? irq : 0; } diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index d6a58a9e072a..128aa0e0ae24 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2608,7 +2608,11 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } + if (uart_console(port)) + console_lock(); port->ops->config_port(port, flags); + if (uart_console(port)) + console_unlock(); } if (port->type != PORT_UNKNOWN) { @@ -2616,6 +2620,9 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_report_port(drv, port); + if (uart_console(port)) + console_lock(); + /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); @@ -2632,6 +2639,9 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_rs485_config(port); + if (uart_console(port)) + console_unlock(); + /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index f2444b581e16..db69545e6250 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3263,6 +3263,20 @@ static int __init keep_bootcon_setup(char *str) early_param("keep_bootcon", keep_bootcon_setup); +static int console_call_setup(struct console *newcon, char *options) +{ + int err; + + if (!newcon->setup) + return 0; + + console_lock(); + err = newcon->setup(newcon, options); + console_unlock(); + + return err; +} + /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected @@ -3298,8 +3312,8 @@ static int try_enable_preferred_console(struct console *newcon, if (_braille_register_console(newcon, c)) return 0; - if (newcon->setup && - (err = newcon->setup(newcon, c->options)) != 0) + err = console_call_setup(newcon, c->options); + if (err != 0) return err; } newcon->flags |= CON_ENABLED; @@ -3325,7 +3339,7 @@ static void try_enable_default_console(struct console *newcon) if (newcon->index < 0) newcon->index = 0; - if (newcon->setup && newcon->setup(newcon, NULL) != 0) + if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; -- 2.44.0.rc1.240.g4c46232300-goog

1 year, 8 months

2
1
0 0

Re: [PATCH] mfd: twl6030-irq: Revert to use of_match_device()

by Andreas Schwab

On Okt 29 2023, Peter Ujfalusi wrote: > The core twl chip is probed via i2c and the dev->driver->of_match_table is > NULL, causing the driver to fail to probe. > > This partially reverts commit 1e0c866887f4. > > Fixes: 1e0c866887f4 ("mfd: Use device_get_match_data() in a bunch of drivers") That commit id does not exist, which is why it hasn't been picked up by stable. The correct commit id is 830fafce06e6f. -- Andreas Schwab, SUSE Labs, schwab(a)suse.de GPG Key fingerprint = 0196 BAD8 1CE9 1970 F4BE 1748 E4D4 88E3 0EEA B9D7 "And now for something completely different."

1 year, 8 months

3
2
0 0

Request to include a couple of fixes to stable branches

by Shyam Prasad N

Hi stable maintainers, We seem to have missed adding the stable tag to a couple of important patches that went upstream for fs/smb/client. Can you please include them in all the stable trees? https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -- Regards, Shyam

1 year, 8 months

2
2
0 0

[PATCH v1] mtd: rawnand: meson: fix scrambling mode value in command macro

by Arseniy Krasnov

Scrambling mode is enabled by value (1 << 19). NFC_CMD_SCRAMBLER_ENABLE is already (1 << 19), so there is no need to shift it again in CMDRWGEN macro. Signed-off-by: Arseniy Krasnov <avkrasnov(a)salutedevices.com> Cc: <Stable(a)vger.kernel.org> Fixes: 8fae856c5350 ("mtd: rawnand: meson: add support for Amlogic NAND flash controller") --- drivers/mtd/nand/raw/meson_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index cdb58aca59c0..2a96a87cf79c 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -63,7 +63,7 @@ #define CMDRWGEN(cmd_dir, ran, bch, short_mode, page_size, pages) \ ( \ (cmd_dir) | \ - ((ran) << 19) | \ + (ran) | \ ((bch) << 14) | \ ((short_mode) << 13) | \ (((page_size) & 0x7f) << 6) | \ -- 2.35.0

1 year, 8 months

2
1
0 0

[PATCH 0/7] 5.4 backport of recent mds improvement patches

by Nikolay Borisov

Here's the recently merged mds improvement patches adapted to latest stable tree. I've only compile tested them, but since I have also done similar backports for older kernels I'm sure they should work. The main difference is in the definition of the CLEAR_CPU_BUFFERS macro since 5.4 doesn't contains the alternative relocation handling logic hence the verw instruction is moved out of the alternative definition and instead we have a jump which skips the verw instruction there. That way the relocation will be handled by the toolchain rather than the kernel. H. Peter Anvin (Intel) (1): x86/asm: Add _ASM_RIP() macro for x86-64 (%rip) suffix Pawan Gupta (5): x86/bugs: Add asm helpers for executing VERW x86/entry_64: Add VERW just before userspace transition x86/entry_32: Add VERW just before userspace transition x86/bugs: Use ALTERNATIVE() instead of mds_user_clear static key KVM/VMX: Move VERW closer to VMentry for MDS mitigation Sean Christopherson (1): KVM/VMX: Use BT+JNC, i.e. EFLAGS.CF to select VMRESUME vs. VMLAUNCH Documentation/x86/mds.rst | 38 ++++++++++++++++++++-------- arch/x86/entry/Makefile | 2 +- arch/x86/entry/common.c | 2 -- arch/x86/entry/entry.S | 23 +++++++++++++++++ arch/x86/entry/entry_32.S | 3 +++ arch/x86/entry/entry_64.S | 10 ++++++++ arch/x86/entry/entry_64_compat.S | 1 + arch/x86/include/asm/asm.h | 6 ++++- arch/x86/include/asm/cpufeatures.h | 2 +- arch/x86/include/asm/irqflags.h | 1 + arch/x86/include/asm/nospec-branch.h | 26 ++++++++++--------- arch/x86/kernel/cpu/bugs.c | 15 +++++------ arch/x86/kernel/nmi.c | 3 --- arch/x86/kvm/vmx/run_flags.h | 7 +++-- arch/x86/kvm/vmx/vmenter.S | 9 ++++--- arch/x86/kvm/vmx/vmx.c | 12 ++++++--- 16 files changed, 111 insertions(+), 49 deletions(-) create mode 100644 arch/x86/entry/entry.S -- 2.34.1

1 year, 8 months

2
8
0 0

FAILED: patch "[PATCH] crypto: virtio/akcipher - Fix stack overflow on memcpy" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x c0ec2a712daf133d9996a8a1b7ee2d4996080363 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022629-defog-preoccupy-2fb8@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: c0ec2a712daf ("crypto: virtio/akcipher - Fix stack overflow on memcpy") 0756ad15b1fe ("virtio-crypto: use private buffer for control request") 6fd763d15586 ("virtio-crypto: change code style") 59ca6c93387d ("virtio-crypto: implement RSA algorithm") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From c0ec2a712daf133d9996a8a1b7ee2d4996080363 Mon Sep 17 00:00:00 2001 From: zhenwei pi <pizhenwei(a)bytedance.com> Date: Tue, 30 Jan 2024 19:27:40 +0800 Subject: [PATCH] crypto: virtio/akcipher - Fix stack overflow on memcpy sizeof(struct virtio_crypto_akcipher_session_para) is less than sizeof(struct virtio_crypto_op_ctrl_req::u), copying more bytes from stack variable leads stack overflow. Clang reports this issue by commands: make -j CC=clang-14 mrproper >/dev/null 2>&1 make -j O=/tmp/crypto-build CC=clang-14 allmodconfig >/dev/null 2>&1 make -j O=/tmp/crypto-build W=1 CC=clang-14 drivers/crypto/virtio/ virtio_crypto_akcipher_algs.o Fixes: 59ca6c93387d ("virtio-crypto: implement RSA algorithm") Link: https://lore.kernel.org/all/0a194a79-e3a3-45e7-be98-83abd3e1cb7e@roeck-us.n… Cc: <stable(a)vger.kernel.org> Signed-off-by: zhenwei pi <pizhenwei(a)bytedance.com> Tested-by: Nathan Chancellor <nathan(a)kernel.org> # build Acked-by: Michael S. Tsirkin <mst(a)redhat.com> Acked-by: Jason Wang <jasowang(a)redhat.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c index 2621ff8a9376..de53eddf6796 100644 --- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -104,7 +104,8 @@ static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request * } static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx, - struct virtio_crypto_ctrl_header *header, void *para, + struct virtio_crypto_ctrl_header *header, + struct virtio_crypto_akcipher_session_para *para, const uint8_t *key, unsigned int keylen) { struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3]; @@ -128,7 +129,7 @@ static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher ctrl = &vc_ctrl_req->ctrl; memcpy(&ctrl->header, header, sizeof(ctrl->header)); - memcpy(&ctrl->u, para, sizeof(ctrl->u)); + memcpy(&ctrl->u.akcipher_create_session.para, para, sizeof(*para)); input = &vc_ctrl_req->input; input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] crypto: virtio/akcipher - Fix stack overflow on memcpy" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x c0ec2a712daf133d9996a8a1b7ee2d4996080363 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022621-shine-synergy-f0c6@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: c0ec2a712daf ("crypto: virtio/akcipher - Fix stack overflow on memcpy") 0756ad15b1fe ("virtio-crypto: use private buffer for control request") 6fd763d15586 ("virtio-crypto: change code style") 59ca6c93387d ("virtio-crypto: implement RSA algorithm") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From c0ec2a712daf133d9996a8a1b7ee2d4996080363 Mon Sep 17 00:00:00 2001 From: zhenwei pi <pizhenwei(a)bytedance.com> Date: Tue, 30 Jan 2024 19:27:40 +0800 Subject: [PATCH] crypto: virtio/akcipher - Fix stack overflow on memcpy sizeof(struct virtio_crypto_akcipher_session_para) is less than sizeof(struct virtio_crypto_op_ctrl_req::u), copying more bytes from stack variable leads stack overflow. Clang reports this issue by commands: make -j CC=clang-14 mrproper >/dev/null 2>&1 make -j O=/tmp/crypto-build CC=clang-14 allmodconfig >/dev/null 2>&1 make -j O=/tmp/crypto-build W=1 CC=clang-14 drivers/crypto/virtio/ virtio_crypto_akcipher_algs.o Fixes: 59ca6c93387d ("virtio-crypto: implement RSA algorithm") Link: https://lore.kernel.org/all/0a194a79-e3a3-45e7-be98-83abd3e1cb7e@roeck-us.n… Cc: <stable(a)vger.kernel.org> Signed-off-by: zhenwei pi <pizhenwei(a)bytedance.com> Tested-by: Nathan Chancellor <nathan(a)kernel.org> # build Acked-by: Michael S. Tsirkin <mst(a)redhat.com> Acked-by: Jason Wang <jasowang(a)redhat.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c index 2621ff8a9376..de53eddf6796 100644 --- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -104,7 +104,8 @@ static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request * } static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx, - struct virtio_crypto_ctrl_header *header, void *para, + struct virtio_crypto_ctrl_header *header, + struct virtio_crypto_akcipher_session_para *para, const uint8_t *key, unsigned int keylen) { struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3]; @@ -128,7 +129,7 @@ static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher ctrl = &vc_ctrl_req->ctrl; memcpy(&ctrl->header, header, sizeof(ctrl->header)); - memcpy(&ctrl->u, para, sizeof(ctrl->u)); + memcpy(&ctrl->u.akcipher_create_session.para, para, sizeof(*para)); input = &vc_ctrl_req->input; input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] KVM: arm64: vgic-its: Test for valid IRQ in" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 8d3a7dfb801d157ac423261d7cd62c33e95375f8 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022635-thinner-disinfect-f761@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: 8d3a7dfb801d ("KVM: arm64: vgic-its: Test for valid IRQ in its_sync_lpi_pending_table()") 9ed24f4b712b ("KVM: arm64: Move virt/kvm/arm to arch/arm64") 3b50142d8528 ("MAINTAINERS: sort field names for all entries") 4400b7d68f6e ("MAINTAINERS: sort entries by entry name") b032227c6293 ("Merge tag 'nios2-v5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/lftan/nios2") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8d3a7dfb801d157ac423261d7cd62c33e95375f8 Mon Sep 17 00:00:00 2001 From: Oliver Upton <oliver.upton(a)linux.dev> Date: Wed, 21 Feb 2024 09:27:31 +0000 Subject: [PATCH] KVM: arm64: vgic-its: Test for valid IRQ in its_sync_lpi_pending_table() vgic_get_irq() may not return a valid descriptor if there is no ITS that holds a valid translation for the specified INTID. If that is the case, it is safe to silently ignore it and continue processing the LPI pending table. Cc: stable(a)vger.kernel.org Fixes: 33d3bc9556a7 ("KVM: arm64: vgic-its: Read initial LPI pending table") Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Link: https://lore.kernel.org/r/20240221092732.4126848-2-oliver.upton@linux.dev Signed-off-by: Marc Zyngier <maz(a)kernel.org> diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index e2764d0ffa9f..082448de27ed 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -468,6 +468,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) } irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); + if (!irq) + continue; + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] KVM: arm64: vgic-its: Test for valid IRQ in" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 8d3a7dfb801d157ac423261d7cd62c33e95375f8 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022634-rut-premises-24cc@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: 8d3a7dfb801d ("KVM: arm64: vgic-its: Test for valid IRQ in its_sync_lpi_pending_table()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8d3a7dfb801d157ac423261d7cd62c33e95375f8 Mon Sep 17 00:00:00 2001 From: Oliver Upton <oliver.upton(a)linux.dev> Date: Wed, 21 Feb 2024 09:27:31 +0000 Subject: [PATCH] KVM: arm64: vgic-its: Test for valid IRQ in its_sync_lpi_pending_table() vgic_get_irq() may not return a valid descriptor if there is no ITS that holds a valid translation for the specified INTID. If that is the case, it is safe to silently ignore it and continue processing the LPI pending table. Cc: stable(a)vger.kernel.org Fixes: 33d3bc9556a7 ("KVM: arm64: vgic-its: Read initial LPI pending table") Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Link: https://lore.kernel.org/r/20240221092732.4126848-2-oliver.upton@linux.dev Signed-off-by: Marc Zyngier <maz(a)kernel.org> diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index e2764d0ffa9f..082448de27ed 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -468,6 +468,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) } irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); + if (!irq) + continue; + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] KVM: arm64: vgic-its: Test for valid IRQ in MOVALL handler" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 85a71ee9a0700f6c18862ef3b0011ed9dad99aca # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022619-opulently-accustom-dbe1@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: 85a71ee9a070 ("KVM: arm64: vgic-its: Test for valid IRQ in MOVALL handler") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 85a71ee9a0700f6c18862ef3b0011ed9dad99aca Mon Sep 17 00:00:00 2001 From: Oliver Upton <oliver.upton(a)linux.dev> Date: Wed, 21 Feb 2024 09:27:32 +0000 Subject: [PATCH] KVM: arm64: vgic-its: Test for valid IRQ in MOVALL handler It is possible that an LPI mapped in a different ITS gets unmapped while handling the MOVALL command. If that is the case, there is no state that can be migrated to the destination. Silently ignore it and continue migrating other LPIs. Cc: stable(a)vger.kernel.org Fixes: ff9c114394aa ("KVM: arm/arm64: GICv4: Handle MOVALL applied to a vPE") Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Link: https://lore.kernel.org/r/20240221092732.4126848-3-oliver.upton@linux.dev Signed-off-by: Marc Zyngier <maz(a)kernel.org> diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 082448de27ed..28a93074eca1 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -1435,6 +1435,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, for (i = 0; i < irq_count; i++) { irq = vgic_get_irq(kvm, NULL, intids[i]); + if (!irq) + continue; update_affinity(irq, vcpu2);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] KVM: arm64: vgic-its: Test for valid IRQ in MOVALL handler" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 85a71ee9a0700f6c18862ef3b0011ed9dad99aca # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022618-maternal-runny-28b5@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: 85a71ee9a070 ("KVM: arm64: vgic-its: Test for valid IRQ in MOVALL handler") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 85a71ee9a0700f6c18862ef3b0011ed9dad99aca Mon Sep 17 00:00:00 2001 From: Oliver Upton <oliver.upton(a)linux.dev> Date: Wed, 21 Feb 2024 09:27:32 +0000 Subject: [PATCH] KVM: arm64: vgic-its: Test for valid IRQ in MOVALL handler It is possible that an LPI mapped in a different ITS gets unmapped while handling the MOVALL command. If that is the case, there is no state that can be migrated to the destination. Silently ignore it and continue migrating other LPIs. Cc: stable(a)vger.kernel.org Fixes: ff9c114394aa ("KVM: arm/arm64: GICv4: Handle MOVALL applied to a vPE") Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Link: https://lore.kernel.org/r/20240221092732.4126848-3-oliver.upton@linux.dev Signed-off-by: Marc Zyngier <maz(a)kernel.org> diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 082448de27ed..28a93074eca1 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -1435,6 +1435,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, for (i = 0; i < irq_count; i++) { irq = vgic_get_irq(kvm, NULL, intids[i]); + if (!irq) + continue; update_affinity(irq, vcpu2);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] cachefiles: fix memory leak in cachefiles_add_cache()" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x e21a2f17566cbd64926fb8f16323972f7a064444 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022639-selection-angrily-d6ff@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: e21a2f17566c ("cachefiles: fix memory leak in cachefiles_add_cache()") d1065b0a6fd9 ("cachefiles: Implement cache registration and withdrawal") 32759f7d7af5 ("cachefiles: Implement a function to get/create a directory in the cache") 1bd9c4e4f049 ("vfs, cachefiles: Mark a backing file in use with an inode flag") 80f94f29f677 ("cachefiles: Provide a function to check how much space there is") 8667d434b2a9 ("cachefiles: Register a miscdev and parse commands over it") 254947d47945 ("cachefiles: Add security derivation") 1493bf74bcf2 ("cachefiles: Add cache error reporting macro") ecf5a6ce15f9 ("cachefiles: Add a couple of tracepoints for logging errors") a70f6526267e ("cachefiles: Add some error injection support") 8390fbc46570 ("cachefiles: Define structs") 77443f6171f3 ("cachefiles: Introduce rewritten driver") 850cba069c26 ("cachefiles: Delete the cachefiles driver pending rewrite") b6773cdb0e9f ("Merge tag 'for-5.16/ki_complete-2021-10-29' of git://git.kernel.dk/linux-block") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e21a2f17566cbd64926fb8f16323972f7a064444 Mon Sep 17 00:00:00 2001 From: Baokun Li <libaokun1(a)huawei.com> Date: Sat, 17 Feb 2024 16:14:31 +0800 Subject: [PATCH] cachefiles: fix memory leak in cachefiles_add_cache() The following memory leak was reported after unbinding /dev/cachefiles: ================================================================== unreferenced object 0xffff9b674176e3c0 (size 192): comm "cachefilesd2", pid 680, jiffies 4294881224 hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace (crc ea38a44b): [<ffffffff8eb8a1a5>] kmem_cache_alloc+0x2d5/0x370 [<ffffffff8e917f86>] prepare_creds+0x26/0x2e0 [<ffffffffc002eeef>] cachefiles_determine_cache_security+0x1f/0x120 [<ffffffffc00243ec>] cachefiles_add_cache+0x13c/0x3a0 [<ffffffffc0025216>] cachefiles_daemon_write+0x146/0x1c0 [<ffffffff8ebc4a3b>] vfs_write+0xcb/0x520 [<ffffffff8ebc5069>] ksys_write+0x69/0xf0 [<ffffffff8f6d4662>] do_syscall_64+0x72/0x140 [<ffffffff8f8000aa>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 ================================================================== Put the reference count of cache_cred in cachefiles_daemon_unbind() to fix the problem. And also put cache_cred in cachefiles_add_cache() error branch to avoid memory leaks. Fixes: 9ae326a69004 ("CacheFiles: A cache that backs onto a mounted filesystem") CC: stable(a)vger.kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Link: https://lore.kernel.org/r/20240217081431.796809-1-libaokun1@huawei.com Acked-by: David Howells <dhowells(a)redhat.com> Reviewed-by: Jingbo Xu <jefflexu(a)linux.alibaba.com> Reviewed-by: Jeff Layton <jlayton(a)kernel.org> Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c index 7077f72e6f47..f449f7340aad 100644 --- a/fs/cachefiles/cache.c +++ b/fs/cachefiles/cache.c @@ -168,6 +168,8 @@ int cachefiles_add_cache(struct cachefiles_cache *cache) dput(root); error_open_root: cachefiles_end_secure(cache, saved_cred); + put_cred(cache->cache_cred); + cache->cache_cred = NULL; error_getsec: fscache_relinquish_cache(cache_cookie); cache->cache = NULL; diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 3f24905f4066..6465e2574230 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -816,6 +816,7 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) cachefiles_put_directory(cache->graveyard); cachefiles_put_directory(cache->store); mntput(cache->mnt); + put_cred(cache->cache_cred); kfree(cache->rootdirname); kfree(cache->secctx);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] cachefiles: fix memory leak in cachefiles_add_cache()" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x e21a2f17566cbd64926fb8f16323972f7a064444 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022638-jingling-atlas-4340@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: e21a2f17566c ("cachefiles: fix memory leak in cachefiles_add_cache()") d1065b0a6fd9 ("cachefiles: Implement cache registration and withdrawal") 32759f7d7af5 ("cachefiles: Implement a function to get/create a directory in the cache") 1bd9c4e4f049 ("vfs, cachefiles: Mark a backing file in use with an inode flag") 80f94f29f677 ("cachefiles: Provide a function to check how much space there is") 8667d434b2a9 ("cachefiles: Register a miscdev and parse commands over it") 254947d47945 ("cachefiles: Add security derivation") 1493bf74bcf2 ("cachefiles: Add cache error reporting macro") ecf5a6ce15f9 ("cachefiles: Add a couple of tracepoints for logging errors") a70f6526267e ("cachefiles: Add some error injection support") 8390fbc46570 ("cachefiles: Define structs") 77443f6171f3 ("cachefiles: Introduce rewritten driver") 850cba069c26 ("cachefiles: Delete the cachefiles driver pending rewrite") b6773cdb0e9f ("Merge tag 'for-5.16/ki_complete-2021-10-29' of git://git.kernel.dk/linux-block") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e21a2f17566cbd64926fb8f16323972f7a064444 Mon Sep 17 00:00:00 2001 From: Baokun Li <libaokun1(a)huawei.com> Date: Sat, 17 Feb 2024 16:14:31 +0800 Subject: [PATCH] cachefiles: fix memory leak in cachefiles_add_cache() The following memory leak was reported after unbinding /dev/cachefiles: ================================================================== unreferenced object 0xffff9b674176e3c0 (size 192): comm "cachefilesd2", pid 680, jiffies 4294881224 hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace (crc ea38a44b): [<ffffffff8eb8a1a5>] kmem_cache_alloc+0x2d5/0x370 [<ffffffff8e917f86>] prepare_creds+0x26/0x2e0 [<ffffffffc002eeef>] cachefiles_determine_cache_security+0x1f/0x120 [<ffffffffc00243ec>] cachefiles_add_cache+0x13c/0x3a0 [<ffffffffc0025216>] cachefiles_daemon_write+0x146/0x1c0 [<ffffffff8ebc4a3b>] vfs_write+0xcb/0x520 [<ffffffff8ebc5069>] ksys_write+0x69/0xf0 [<ffffffff8f6d4662>] do_syscall_64+0x72/0x140 [<ffffffff8f8000aa>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 ================================================================== Put the reference count of cache_cred in cachefiles_daemon_unbind() to fix the problem. And also put cache_cred in cachefiles_add_cache() error branch to avoid memory leaks. Fixes: 9ae326a69004 ("CacheFiles: A cache that backs onto a mounted filesystem") CC: stable(a)vger.kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Link: https://lore.kernel.org/r/20240217081431.796809-1-libaokun1@huawei.com Acked-by: David Howells <dhowells(a)redhat.com> Reviewed-by: Jingbo Xu <jefflexu(a)linux.alibaba.com> Reviewed-by: Jeff Layton <jlayton(a)kernel.org> Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c index 7077f72e6f47..f449f7340aad 100644 --- a/fs/cachefiles/cache.c +++ b/fs/cachefiles/cache.c @@ -168,6 +168,8 @@ int cachefiles_add_cache(struct cachefiles_cache *cache) dput(root); error_open_root: cachefiles_end_secure(cache, saved_cred); + put_cred(cache->cache_cred); + cache->cache_cred = NULL; error_getsec: fscache_relinquish_cache(cache_cookie); cache->cache = NULL; diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 3f24905f4066..6465e2574230 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -816,6 +816,7 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) cachefiles_put_directory(cache->graveyard); cachefiles_put_directory(cache->store); mntput(cache->mnt); + put_cred(cache->cache_cred); kfree(cache->rootdirname); kfree(cache->secctx);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] cachefiles: fix memory leak in cachefiles_add_cache()" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x e21a2f17566cbd64926fb8f16323972f7a064444 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022636-prevail-headway-01c9@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: e21a2f17566c ("cachefiles: fix memory leak in cachefiles_add_cache()") d1065b0a6fd9 ("cachefiles: Implement cache registration and withdrawal") 32759f7d7af5 ("cachefiles: Implement a function to get/create a directory in the cache") 1bd9c4e4f049 ("vfs, cachefiles: Mark a backing file in use with an inode flag") 80f94f29f677 ("cachefiles: Provide a function to check how much space there is") 8667d434b2a9 ("cachefiles: Register a miscdev and parse commands over it") 254947d47945 ("cachefiles: Add security derivation") 1493bf74bcf2 ("cachefiles: Add cache error reporting macro") ecf5a6ce15f9 ("cachefiles: Add a couple of tracepoints for logging errors") a70f6526267e ("cachefiles: Add some error injection support") 8390fbc46570 ("cachefiles: Define structs") 77443f6171f3 ("cachefiles: Introduce rewritten driver") 850cba069c26 ("cachefiles: Delete the cachefiles driver pending rewrite") b6773cdb0e9f ("Merge tag 'for-5.16/ki_complete-2021-10-29' of git://git.kernel.dk/linux-block") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e21a2f17566cbd64926fb8f16323972f7a064444 Mon Sep 17 00:00:00 2001 From: Baokun Li <libaokun1(a)huawei.com> Date: Sat, 17 Feb 2024 16:14:31 +0800 Subject: [PATCH] cachefiles: fix memory leak in cachefiles_add_cache() The following memory leak was reported after unbinding /dev/cachefiles: ================================================================== unreferenced object 0xffff9b674176e3c0 (size 192): comm "cachefilesd2", pid 680, jiffies 4294881224 hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace (crc ea38a44b): [<ffffffff8eb8a1a5>] kmem_cache_alloc+0x2d5/0x370 [<ffffffff8e917f86>] prepare_creds+0x26/0x2e0 [<ffffffffc002eeef>] cachefiles_determine_cache_security+0x1f/0x120 [<ffffffffc00243ec>] cachefiles_add_cache+0x13c/0x3a0 [<ffffffffc0025216>] cachefiles_daemon_write+0x146/0x1c0 [<ffffffff8ebc4a3b>] vfs_write+0xcb/0x520 [<ffffffff8ebc5069>] ksys_write+0x69/0xf0 [<ffffffff8f6d4662>] do_syscall_64+0x72/0x140 [<ffffffff8f8000aa>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 ================================================================== Put the reference count of cache_cred in cachefiles_daemon_unbind() to fix the problem. And also put cache_cred in cachefiles_add_cache() error branch to avoid memory leaks. Fixes: 9ae326a69004 ("CacheFiles: A cache that backs onto a mounted filesystem") CC: stable(a)vger.kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Link: https://lore.kernel.org/r/20240217081431.796809-1-libaokun1@huawei.com Acked-by: David Howells <dhowells(a)redhat.com> Reviewed-by: Jingbo Xu <jefflexu(a)linux.alibaba.com> Reviewed-by: Jeff Layton <jlayton(a)kernel.org> Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c index 7077f72e6f47..f449f7340aad 100644 --- a/fs/cachefiles/cache.c +++ b/fs/cachefiles/cache.c @@ -168,6 +168,8 @@ int cachefiles_add_cache(struct cachefiles_cache *cache) dput(root); error_open_root: cachefiles_end_secure(cache, saved_cred); + put_cred(cache->cache_cred); + cache->cache_cred = NULL; error_getsec: fscache_relinquish_cache(cache_cookie); cache->cache = NULL; diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 3f24905f4066..6465e2574230 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -816,6 +816,7 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) cachefiles_put_directory(cache->graveyard); cachefiles_put_directory(cache->store); mntput(cache->mnt); + put_cred(cache->cache_cred); kfree(cache->rootdirname); kfree(cache->secctx);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] cachefiles: fix memory leak in cachefiles_add_cache()" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x e21a2f17566cbd64926fb8f16323972f7a064444 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022635-princess-penniless-bfa6@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: e21a2f17566c ("cachefiles: fix memory leak in cachefiles_add_cache()") d1065b0a6fd9 ("cachefiles: Implement cache registration and withdrawal") 32759f7d7af5 ("cachefiles: Implement a function to get/create a directory in the cache") 1bd9c4e4f049 ("vfs, cachefiles: Mark a backing file in use with an inode flag") 80f94f29f677 ("cachefiles: Provide a function to check how much space there is") 8667d434b2a9 ("cachefiles: Register a miscdev and parse commands over it") 254947d47945 ("cachefiles: Add security derivation") 1493bf74bcf2 ("cachefiles: Add cache error reporting macro") ecf5a6ce15f9 ("cachefiles: Add a couple of tracepoints for logging errors") a70f6526267e ("cachefiles: Add some error injection support") 8390fbc46570 ("cachefiles: Define structs") 77443f6171f3 ("cachefiles: Introduce rewritten driver") 850cba069c26 ("cachefiles: Delete the cachefiles driver pending rewrite") b6773cdb0e9f ("Merge tag 'for-5.16/ki_complete-2021-10-29' of git://git.kernel.dk/linux-block") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e21a2f17566cbd64926fb8f16323972f7a064444 Mon Sep 17 00:00:00 2001 From: Baokun Li <libaokun1(a)huawei.com> Date: Sat, 17 Feb 2024 16:14:31 +0800 Subject: [PATCH] cachefiles: fix memory leak in cachefiles_add_cache() The following memory leak was reported after unbinding /dev/cachefiles: ================================================================== unreferenced object 0xffff9b674176e3c0 (size 192): comm "cachefilesd2", pid 680, jiffies 4294881224 hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace (crc ea38a44b): [<ffffffff8eb8a1a5>] kmem_cache_alloc+0x2d5/0x370 [<ffffffff8e917f86>] prepare_creds+0x26/0x2e0 [<ffffffffc002eeef>] cachefiles_determine_cache_security+0x1f/0x120 [<ffffffffc00243ec>] cachefiles_add_cache+0x13c/0x3a0 [<ffffffffc0025216>] cachefiles_daemon_write+0x146/0x1c0 [<ffffffff8ebc4a3b>] vfs_write+0xcb/0x520 [<ffffffff8ebc5069>] ksys_write+0x69/0xf0 [<ffffffff8f6d4662>] do_syscall_64+0x72/0x140 [<ffffffff8f8000aa>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 ================================================================== Put the reference count of cache_cred in cachefiles_daemon_unbind() to fix the problem. And also put cache_cred in cachefiles_add_cache() error branch to avoid memory leaks. Fixes: 9ae326a69004 ("CacheFiles: A cache that backs onto a mounted filesystem") CC: stable(a)vger.kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Link: https://lore.kernel.org/r/20240217081431.796809-1-libaokun1@huawei.com Acked-by: David Howells <dhowells(a)redhat.com> Reviewed-by: Jingbo Xu <jefflexu(a)linux.alibaba.com> Reviewed-by: Jeff Layton <jlayton(a)kernel.org> Signed-off-by: Christian Brauner <brauner(a)kernel.org> diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c index 7077f72e6f47..f449f7340aad 100644 --- a/fs/cachefiles/cache.c +++ b/fs/cachefiles/cache.c @@ -168,6 +168,8 @@ int cachefiles_add_cache(struct cachefiles_cache *cache) dput(root); error_open_root: cachefiles_end_secure(cache, saved_cred); + put_cred(cache->cache_cred); + cache->cache_cred = NULL; error_getsec: fscache_relinquish_cache(cache_cookie); cache->cache = NULL; diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 3f24905f4066..6465e2574230 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -816,6 +816,7 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) cachefiles_put_directory(cache->graveyard); cachefiles_put_directory(cache->store); mntput(cache->mnt); + put_cred(cache->cache_cred); kfree(cache->rootdirname); kfree(cache->secctx);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] platform/x86: touchscreen_dmi: Allow partial (prefix) matches" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x dbcbfd662a725641d118fb3ae5ffb7be4e3d0fb0 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022608-trombone-banker-5ed4@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: dbcbfd662a72 ("platform/x86: touchscreen_dmi: Allow partial (prefix) matches for ACPI names") 87eaede45385 ("platform/x86: touchscreen_dmi: Handle device properties with software node API") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From dbcbfd662a725641d118fb3ae5ffb7be4e3d0fb0 Mon Sep 17 00:00:00 2001 From: Hans de Goede <hdegoede(a)redhat.com> Date: Mon, 12 Feb 2024 13:06:07 +0100 Subject: [PATCH] platform/x86: touchscreen_dmi: Allow partial (prefix) matches for ACPI names On some devices the ACPI name of the touchscreen is e.g. either MSSL1680:00 or MSSL1680:01 depending on the BIOS version. This happens for example on the "Chuwi Hi8 Air" tablet where the initial commit's ts_data uses "MSSL1680:00" but the tablets from the github issue and linux-hardware.org probe linked below both use "MSSL1680:01". Replace the strcmp() match on ts_data->acpi_name with a strstarts() check to allow using a partial match on just the ACPI HID of "MSSL1680" and change the ts_data->acpi_name for the "Chuwi Hi8 Air" accordingly to fix the touchscreen not working on models where it is "MSSL1680:01". Note this drops the length check for I2C_NAME_SIZE. This never was necessary since the ACPI names used are never more then 11 chars and I2C_NAME_SIZE is 20 so the replaced strncmp() would always stop long before reaching I2C_NAME_SIZE. Link: https://linux-hardware.org/?computer=AC4301C0542A Fixes: bbb97d728f77 ("platform/x86: touchscreen_dmi: Add info for the Chuwi Hi8 Air tablet") Closes: https://github.com/onitake/gsl-firmware/issues/91 Cc: stable(a)vger.kernel.org Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy(a)linux.intel.com> Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> Link: https://lore.kernel.org/r/20240212120608.30469-1-hdegoede@redhat.com diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 7aee5e9ff2b8..969477c83e56 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -81,7 +81,7 @@ static const struct property_entry chuwi_hi8_air_props[] = { }; static const struct ts_dmi_data chuwi_hi8_air_data = { - .acpi_name = "MSSL1680:00", + .acpi_name = "MSSL1680", .properties = chuwi_hi8_air_props, }; @@ -1821,7 +1821,7 @@ static void ts_dmi_add_props(struct i2c_client *client) int error; if (has_acpi_companion(dev) && - !strncmp(ts_data->acpi_name, client->name, I2C_NAME_SIZE)) { + strstarts(client->name, ts_data->acpi_name)) { error = device_create_managed_software_node(dev, ts_data->properties, NULL); if (error) dev_err(dev, "failed to add properties: %d\n", error);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] platform/x86: touchscreen_dmi: Allow partial (prefix) matches" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x dbcbfd662a725641d118fb3ae5ffb7be4e3d0fb0 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022607-tainted-tinderbox-4920@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: dbcbfd662a72 ("platform/x86: touchscreen_dmi: Allow partial (prefix) matches for ACPI names") 87eaede45385 ("platform/x86: touchscreen_dmi: Handle device properties with software node API") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From dbcbfd662a725641d118fb3ae5ffb7be4e3d0fb0 Mon Sep 17 00:00:00 2001 From: Hans de Goede <hdegoede(a)redhat.com> Date: Mon, 12 Feb 2024 13:06:07 +0100 Subject: [PATCH] platform/x86: touchscreen_dmi: Allow partial (prefix) matches for ACPI names On some devices the ACPI name of the touchscreen is e.g. either MSSL1680:00 or MSSL1680:01 depending on the BIOS version. This happens for example on the "Chuwi Hi8 Air" tablet where the initial commit's ts_data uses "MSSL1680:00" but the tablets from the github issue and linux-hardware.org probe linked below both use "MSSL1680:01". Replace the strcmp() match on ts_data->acpi_name with a strstarts() check to allow using a partial match on just the ACPI HID of "MSSL1680" and change the ts_data->acpi_name for the "Chuwi Hi8 Air" accordingly to fix the touchscreen not working on models where it is "MSSL1680:01". Note this drops the length check for I2C_NAME_SIZE. This never was necessary since the ACPI names used are never more then 11 chars and I2C_NAME_SIZE is 20 so the replaced strncmp() would always stop long before reaching I2C_NAME_SIZE. Link: https://linux-hardware.org/?computer=AC4301C0542A Fixes: bbb97d728f77 ("platform/x86: touchscreen_dmi: Add info for the Chuwi Hi8 Air tablet") Closes: https://github.com/onitake/gsl-firmware/issues/91 Cc: stable(a)vger.kernel.org Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy(a)linux.intel.com> Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> Link: https://lore.kernel.org/r/20240212120608.30469-1-hdegoede@redhat.com diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 7aee5e9ff2b8..969477c83e56 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -81,7 +81,7 @@ static const struct property_entry chuwi_hi8_air_props[] = { }; static const struct ts_dmi_data chuwi_hi8_air_data = { - .acpi_name = "MSSL1680:00", + .acpi_name = "MSSL1680", .properties = chuwi_hi8_air_props, }; @@ -1821,7 +1821,7 @@ static void ts_dmi_add_props(struct i2c_client *client) int error; if (has_acpi_companion(dev) && - !strncmp(ts_data->acpi_name, client->name, I2C_NAME_SIZE)) { + strstarts(client->name, ts_data->acpi_name)) { error = device_create_managed_software_node(dev, ts_data->properties, NULL); if (error) dev_err(dev, "failed to add properties: %d\n", error);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] mm/swap: fix race when skipping swapcache" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 13ddaf26be324a7f951891ecd9ccd04466d27458 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022608-green-engaging-46db@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: 13ddaf26be32 ("mm/swap: fix race when skipping swapcache") c9edc242811d ("swap: add swap_cache_get_folio()") 1baec203b77c ("mm/khugepaged: try to free transhuge swapcache when possible") 442701e7058b ("mm/swap: remove swap_cache_info statistics") 014bb1de4fc1 ("mm: create new mm/swap.h header file") 1493a1913e34 ("mm/swap: remember PG_anon_exclusive via a swp pte bit") 6c287605fd56 ("mm: remember exclusively mapped anonymous pages with PG_anon_exclusive") 78fbe906cc90 ("mm/page-flags: reuse PG_mappedtodisk as PG_anon_exclusive for PageAnon() pages") 6c54dc6c7437 ("mm/rmap: use page_move_anon_rmap() when reusing a mapped PageAnon() page exclusively") 28c5209dfd5f ("mm/rmap: pass rmap flags to hugepage_add_anon_rmap()") f1e2db12e45b ("mm/rmap: remove do_page_add_anon_rmap()") 14f9135d5470 ("mm/rmap: convert RMAP flags to a proper distinct rmap_t type") fb3d824d1a46 ("mm/rmap: split page_dup_rmap() into page_dup_file_rmap() and page_try_dup_anon_rmap()") b51ad4f8679e ("mm/memory: slightly simplify copy_present_pte()") 623a1ddfeb23 ("mm/hugetlb: take src_mm->write_protect_seq in copy_hugetlb_page_range()") 3bff7e3f1f16 ("mm/huge_memory: streamline COW logic in do_huge_pmd_wp_page()") c145e0b47c77 ("mm: streamline COW logic in do_swap_page()") 84d60fdd3733 ("mm: slightly clarify KSM logic in do_swap_page()") 53a05ad9f21d ("mm: optimize do_wp_page() for exclusive pages in the swapcache") 6b1f86f8e9c7 ("Merge tag 'folio-5.18b' of git://git.infradead.org/users/willy/pagecache") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 13ddaf26be324a7f951891ecd9ccd04466d27458 Mon Sep 17 00:00:00 2001 From: Kairui Song <kasong(a)tencent.com> Date: Wed, 7 Feb 2024 02:25:59 +0800 Subject: [PATCH] mm/swap: fix race when skipping swapcache When skipping swapcache for SWP_SYNCHRONOUS_IO, if two or more threads swapin the same entry at the same time, they get different pages (A, B). Before one thread (T0) finishes the swapin and installs page (A) to the PTE, another thread (T1) could finish swapin of page (B), swap_free the entry, then swap out the possibly modified page reusing the same entry. It breaks the pte_same check in (T0) because PTE value is unchanged, causing ABA problem. Thread (T0) will install a stalled page (A) into the PTE and cause data corruption. One possible callstack is like this: CPU0 CPU1 ---- ---- do_swap_page() do_swap_page() with same entry <direct swapin path> <direct swapin path> <alloc page A> <alloc page B> swap_read_folio() <- read to page A swap_read_folio() <- read to page B <slow on later locks or interrupt> <finished swapin first> ... set_pte_at() swap_free() <- entry is free <write to page B, now page A stalled> <swap out page B to same swap entry> pte_same() <- Check pass, PTE seems unchanged, but page A is stalled! swap_free() <- page B content lost! set_pte_at() <- staled page A installed! And besides, for ZRAM, swap_free() allows the swap device to discard the entry content, so even if page (B) is not modified, if swap_read_folio() on CPU0 happens later than swap_free() on CPU1, it may also cause data loss. To fix this, reuse swapcache_prepare which will pin the swap entry using the cache flag, and allow only one thread to swap it in, also prevent any parallel code from putting the entry in the cache. Release the pin after PT unlocked. Racers just loop and wait since it's a rare and very short event. A schedule_timeout_uninterruptible(1) call is added to avoid repeated page faults wasting too much CPU, causing livelock or adding too much noise to perf statistics. A similar livelock issue was described in commit 029c4628b2eb ("mm: swap: get rid of livelock in swapin readahead") Reproducer: This race issue can be triggered easily using a well constructed reproducer and patched brd (with a delay in read path) [1]: With latest 6.8 mainline, race caused data loss can be observed easily: $ gcc -g -lpthread test-thread-swap-race.c && ./a.out Polulating 32MB of memory region... Keep swapping out... Starting round 0... Spawning 65536 workers... 32746 workers spawned, wait for done... Round 0: Error on 0x5aa00, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x395200, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x3fd000, expected 32746, got 32737, 9 data loss! Round 0 Failed, 15 data loss! This reproducer spawns multiple threads sharing the same memory region using a small swap device. Every two threads updates mapped pages one by one in opposite direction trying to create a race, with one dedicated thread keep swapping out the data out using madvise. The reproducer created a reproduce rate of about once every 5 minutes, so the race should be totally possible in production. After this patch, I ran the reproducer for over a few hundred rounds and no data loss observed. Performance overhead is minimal, microbenchmark swapin 10G from 32G zram: Before: 10934698 us After: 11157121 us Cached: 13155355 us (Dropping SWP_SYNCHRONOUS_IO flag) [kasong(a)tencent.com: v4] Link: https://lkml.kernel.org/r/20240219082040.7495-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20240206182559.32264-1-ryncsn@gmail.com Fixes: 0bcac06f27d7 ("mm, swap: skip swapcache for swapin of synchronous device") Reported-by: "Huang, Ying" <ying.huang(a)intel.com> Closes: https://lore.kernel.org/lkml/87bk92gqpx.fsf_-_@yhuang6-desk2.ccr.corp.intel… Link: https://github.com/ryncsn/emm-test-project/tree/master/swap-stress-race [1] Signed-off-by: Kairui Song <kasong(a)tencent.com> Reviewed-by: "Huang, Ying" <ying.huang(a)intel.com> Acked-by: Yu Zhao <yuzhao(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Acked-by: Chris Li <chrisl(a)kernel.org> Cc: Hugh Dickins <hughd(a)google.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Yosry Ahmed <yosryahmed(a)google.com> Cc: Yu Zhao <yuzhao(a)google.com> Cc: Barry Song <21cnbao(a)gmail.com> Cc: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/swap.h b/include/linux/swap.h index 4db00ddad261..8d28f6091a32 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -549,6 +549,11 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } +static inline int swapcache_prepare(swp_entry_t swp) +{ + return 0; +} + static inline void swap_free(swp_entry_t swp) { } diff --git a/mm/memory.c b/mm/memory.c index 15f8b10ea17c..0bfc8b007c01 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3799,6 +3799,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; + bool need_clear_cache = false; bool exclusive = false; swp_entry_t entry; pte_t pte; @@ -3867,6 +3868,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { + /* + * Prevent parallel swapin from proceeding with + * the cache flag. Otherwise, another thread may + * finish swapin first, free the entry, and swapout + * reusing the same entry. It's undetectable as + * pte_same() returns true due to entry reuse. + */ + if (swapcache_prepare(entry)) { + /* Relax a bit to prevent rapid repeated page faults */ + schedule_timeout_uninterruptible(1); + goto out; + } + need_clear_cache = true; + /* skip swapcache */ folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false); @@ -4117,6 +4132,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out: + /* Clear the swap cache pin for direct swapin after PTL unlock */ + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; @@ -4131,6 +4149,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) folio_unlock(swapcache); folio_put(swapcache); } + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; diff --git a/mm/swap.h b/mm/swap.h index 758c46ca671e..fc2f6ade7f80 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -41,6 +41,7 @@ void __delete_from_swap_cache(struct folio *folio, void delete_from_swap_cache(struct folio *folio); void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry); struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct folio *filemap_get_incore_folio(struct address_space *mapping, @@ -97,6 +98,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc) return 0; } +static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ +} + static inline struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 556ff7347d5f..746aa9da5302 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3365,6 +3365,19 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char usage; + + ci = lock_cluster_or_swap_info(si, offset); + usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); + unlock_cluster_or_swap_info(si, ci); + if (!usage) + free_swap_slot(entry); +} + struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry));

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] mm/swap: fix race when skipping swapcache" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 13ddaf26be324a7f951891ecd9ccd04466d27458 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022604-labrador-edgy-5b56@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: 13ddaf26be32 ("mm/swap: fix race when skipping swapcache") c9edc242811d ("swap: add swap_cache_get_folio()") 1baec203b77c ("mm/khugepaged: try to free transhuge swapcache when possible") 442701e7058b ("mm/swap: remove swap_cache_info statistics") 014bb1de4fc1 ("mm: create new mm/swap.h header file") 1493a1913e34 ("mm/swap: remember PG_anon_exclusive via a swp pte bit") 6c287605fd56 ("mm: remember exclusively mapped anonymous pages with PG_anon_exclusive") 78fbe906cc90 ("mm/page-flags: reuse PG_mappedtodisk as PG_anon_exclusive for PageAnon() pages") 6c54dc6c7437 ("mm/rmap: use page_move_anon_rmap() when reusing a mapped PageAnon() page exclusively") 28c5209dfd5f ("mm/rmap: pass rmap flags to hugepage_add_anon_rmap()") f1e2db12e45b ("mm/rmap: remove do_page_add_anon_rmap()") 14f9135d5470 ("mm/rmap: convert RMAP flags to a proper distinct rmap_t type") fb3d824d1a46 ("mm/rmap: split page_dup_rmap() into page_dup_file_rmap() and page_try_dup_anon_rmap()") b51ad4f8679e ("mm/memory: slightly simplify copy_present_pte()") 623a1ddfeb23 ("mm/hugetlb: take src_mm->write_protect_seq in copy_hugetlb_page_range()") 3bff7e3f1f16 ("mm/huge_memory: streamline COW logic in do_huge_pmd_wp_page()") c145e0b47c77 ("mm: streamline COW logic in do_swap_page()") 84d60fdd3733 ("mm: slightly clarify KSM logic in do_swap_page()") 53a05ad9f21d ("mm: optimize do_wp_page() for exclusive pages in the swapcache") 6b1f86f8e9c7 ("Merge tag 'folio-5.18b' of git://git.infradead.org/users/willy/pagecache") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 13ddaf26be324a7f951891ecd9ccd04466d27458 Mon Sep 17 00:00:00 2001 From: Kairui Song <kasong(a)tencent.com> Date: Wed, 7 Feb 2024 02:25:59 +0800 Subject: [PATCH] mm/swap: fix race when skipping swapcache When skipping swapcache for SWP_SYNCHRONOUS_IO, if two or more threads swapin the same entry at the same time, they get different pages (A, B). Before one thread (T0) finishes the swapin and installs page (A) to the PTE, another thread (T1) could finish swapin of page (B), swap_free the entry, then swap out the possibly modified page reusing the same entry. It breaks the pte_same check in (T0) because PTE value is unchanged, causing ABA problem. Thread (T0) will install a stalled page (A) into the PTE and cause data corruption. One possible callstack is like this: CPU0 CPU1 ---- ---- do_swap_page() do_swap_page() with same entry <direct swapin path> <direct swapin path> <alloc page A> <alloc page B> swap_read_folio() <- read to page A swap_read_folio() <- read to page B <slow on later locks or interrupt> <finished swapin first> ... set_pte_at() swap_free() <- entry is free <write to page B, now page A stalled> <swap out page B to same swap entry> pte_same() <- Check pass, PTE seems unchanged, but page A is stalled! swap_free() <- page B content lost! set_pte_at() <- staled page A installed! And besides, for ZRAM, swap_free() allows the swap device to discard the entry content, so even if page (B) is not modified, if swap_read_folio() on CPU0 happens later than swap_free() on CPU1, it may also cause data loss. To fix this, reuse swapcache_prepare which will pin the swap entry using the cache flag, and allow only one thread to swap it in, also prevent any parallel code from putting the entry in the cache. Release the pin after PT unlocked. Racers just loop and wait since it's a rare and very short event. A schedule_timeout_uninterruptible(1) call is added to avoid repeated page faults wasting too much CPU, causing livelock or adding too much noise to perf statistics. A similar livelock issue was described in commit 029c4628b2eb ("mm: swap: get rid of livelock in swapin readahead") Reproducer: This race issue can be triggered easily using a well constructed reproducer and patched brd (with a delay in read path) [1]: With latest 6.8 mainline, race caused data loss can be observed easily: $ gcc -g -lpthread test-thread-swap-race.c && ./a.out Polulating 32MB of memory region... Keep swapping out... Starting round 0... Spawning 65536 workers... 32746 workers spawned, wait for done... Round 0: Error on 0x5aa00, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x395200, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x3fd000, expected 32746, got 32737, 9 data loss! Round 0 Failed, 15 data loss! This reproducer spawns multiple threads sharing the same memory region using a small swap device. Every two threads updates mapped pages one by one in opposite direction trying to create a race, with one dedicated thread keep swapping out the data out using madvise. The reproducer created a reproduce rate of about once every 5 minutes, so the race should be totally possible in production. After this patch, I ran the reproducer for over a few hundred rounds and no data loss observed. Performance overhead is minimal, microbenchmark swapin 10G from 32G zram: Before: 10934698 us After: 11157121 us Cached: 13155355 us (Dropping SWP_SYNCHRONOUS_IO flag) [kasong(a)tencent.com: v4] Link: https://lkml.kernel.org/r/20240219082040.7495-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20240206182559.32264-1-ryncsn@gmail.com Fixes: 0bcac06f27d7 ("mm, swap: skip swapcache for swapin of synchronous device") Reported-by: "Huang, Ying" <ying.huang(a)intel.com> Closes: https://lore.kernel.org/lkml/87bk92gqpx.fsf_-_@yhuang6-desk2.ccr.corp.intel… Link: https://github.com/ryncsn/emm-test-project/tree/master/swap-stress-race [1] Signed-off-by: Kairui Song <kasong(a)tencent.com> Reviewed-by: "Huang, Ying" <ying.huang(a)intel.com> Acked-by: Yu Zhao <yuzhao(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Acked-by: Chris Li <chrisl(a)kernel.org> Cc: Hugh Dickins <hughd(a)google.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Yosry Ahmed <yosryahmed(a)google.com> Cc: Yu Zhao <yuzhao(a)google.com> Cc: Barry Song <21cnbao(a)gmail.com> Cc: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/swap.h b/include/linux/swap.h index 4db00ddad261..8d28f6091a32 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -549,6 +549,11 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } +static inline int swapcache_prepare(swp_entry_t swp) +{ + return 0; +} + static inline void swap_free(swp_entry_t swp) { } diff --git a/mm/memory.c b/mm/memory.c index 15f8b10ea17c..0bfc8b007c01 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3799,6 +3799,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; + bool need_clear_cache = false; bool exclusive = false; swp_entry_t entry; pte_t pte; @@ -3867,6 +3868,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { + /* + * Prevent parallel swapin from proceeding with + * the cache flag. Otherwise, another thread may + * finish swapin first, free the entry, and swapout + * reusing the same entry. It's undetectable as + * pte_same() returns true due to entry reuse. + */ + if (swapcache_prepare(entry)) { + /* Relax a bit to prevent rapid repeated page faults */ + schedule_timeout_uninterruptible(1); + goto out; + } + need_clear_cache = true; + /* skip swapcache */ folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false); @@ -4117,6 +4132,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out: + /* Clear the swap cache pin for direct swapin after PTL unlock */ + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; @@ -4131,6 +4149,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) folio_unlock(swapcache); folio_put(swapcache); } + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; diff --git a/mm/swap.h b/mm/swap.h index 758c46ca671e..fc2f6ade7f80 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -41,6 +41,7 @@ void __delete_from_swap_cache(struct folio *folio, void delete_from_swap_cache(struct folio *folio); void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry); struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct folio *filemap_get_incore_folio(struct address_space *mapping, @@ -97,6 +98,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc) return 0; } +static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ +} + static inline struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 556ff7347d5f..746aa9da5302 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3365,6 +3365,19 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char usage; + + ci = lock_cluster_or_swap_info(si, offset); + usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); + unlock_cluster_or_swap_info(si, ci); + if (!usage) + free_swap_slot(entry); +} + struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry));

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] mm/swap: fix race when skipping swapcache" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 13ddaf26be324a7f951891ecd9ccd04466d27458 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022601-skinny-audacious-d173@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: 13ddaf26be32 ("mm/swap: fix race when skipping swapcache") c9edc242811d ("swap: add swap_cache_get_folio()") 1baec203b77c ("mm/khugepaged: try to free transhuge swapcache when possible") 442701e7058b ("mm/swap: remove swap_cache_info statistics") 014bb1de4fc1 ("mm: create new mm/swap.h header file") 1493a1913e34 ("mm/swap: remember PG_anon_exclusive via a swp pte bit") 6c287605fd56 ("mm: remember exclusively mapped anonymous pages with PG_anon_exclusive") 78fbe906cc90 ("mm/page-flags: reuse PG_mappedtodisk as PG_anon_exclusive for PageAnon() pages") 6c54dc6c7437 ("mm/rmap: use page_move_anon_rmap() when reusing a mapped PageAnon() page exclusively") 28c5209dfd5f ("mm/rmap: pass rmap flags to hugepage_add_anon_rmap()") f1e2db12e45b ("mm/rmap: remove do_page_add_anon_rmap()") 14f9135d5470 ("mm/rmap: convert RMAP flags to a proper distinct rmap_t type") fb3d824d1a46 ("mm/rmap: split page_dup_rmap() into page_dup_file_rmap() and page_try_dup_anon_rmap()") b51ad4f8679e ("mm/memory: slightly simplify copy_present_pte()") 623a1ddfeb23 ("mm/hugetlb: take src_mm->write_protect_seq in copy_hugetlb_page_range()") 3bff7e3f1f16 ("mm/huge_memory: streamline COW logic in do_huge_pmd_wp_page()") c145e0b47c77 ("mm: streamline COW logic in do_swap_page()") 84d60fdd3733 ("mm: slightly clarify KSM logic in do_swap_page()") 53a05ad9f21d ("mm: optimize do_wp_page() for exclusive pages in the swapcache") 6b1f86f8e9c7 ("Merge tag 'folio-5.18b' of git://git.infradead.org/users/willy/pagecache") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 13ddaf26be324a7f951891ecd9ccd04466d27458 Mon Sep 17 00:00:00 2001 From: Kairui Song <kasong(a)tencent.com> Date: Wed, 7 Feb 2024 02:25:59 +0800 Subject: [PATCH] mm/swap: fix race when skipping swapcache When skipping swapcache for SWP_SYNCHRONOUS_IO, if two or more threads swapin the same entry at the same time, they get different pages (A, B). Before one thread (T0) finishes the swapin and installs page (A) to the PTE, another thread (T1) could finish swapin of page (B), swap_free the entry, then swap out the possibly modified page reusing the same entry. It breaks the pte_same check in (T0) because PTE value is unchanged, causing ABA problem. Thread (T0) will install a stalled page (A) into the PTE and cause data corruption. One possible callstack is like this: CPU0 CPU1 ---- ---- do_swap_page() do_swap_page() with same entry <direct swapin path> <direct swapin path> <alloc page A> <alloc page B> swap_read_folio() <- read to page A swap_read_folio() <- read to page B <slow on later locks or interrupt> <finished swapin first> ... set_pte_at() swap_free() <- entry is free <write to page B, now page A stalled> <swap out page B to same swap entry> pte_same() <- Check pass, PTE seems unchanged, but page A is stalled! swap_free() <- page B content lost! set_pte_at() <- staled page A installed! And besides, for ZRAM, swap_free() allows the swap device to discard the entry content, so even if page (B) is not modified, if swap_read_folio() on CPU0 happens later than swap_free() on CPU1, it may also cause data loss. To fix this, reuse swapcache_prepare which will pin the swap entry using the cache flag, and allow only one thread to swap it in, also prevent any parallel code from putting the entry in the cache. Release the pin after PT unlocked. Racers just loop and wait since it's a rare and very short event. A schedule_timeout_uninterruptible(1) call is added to avoid repeated page faults wasting too much CPU, causing livelock or adding too much noise to perf statistics. A similar livelock issue was described in commit 029c4628b2eb ("mm: swap: get rid of livelock in swapin readahead") Reproducer: This race issue can be triggered easily using a well constructed reproducer and patched brd (with a delay in read path) [1]: With latest 6.8 mainline, race caused data loss can be observed easily: $ gcc -g -lpthread test-thread-swap-race.c && ./a.out Polulating 32MB of memory region... Keep swapping out... Starting round 0... Spawning 65536 workers... 32746 workers spawned, wait for done... Round 0: Error on 0x5aa00, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x395200, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x3fd000, expected 32746, got 32737, 9 data loss! Round 0 Failed, 15 data loss! This reproducer spawns multiple threads sharing the same memory region using a small swap device. Every two threads updates mapped pages one by one in opposite direction trying to create a race, with one dedicated thread keep swapping out the data out using madvise. The reproducer created a reproduce rate of about once every 5 minutes, so the race should be totally possible in production. After this patch, I ran the reproducer for over a few hundred rounds and no data loss observed. Performance overhead is minimal, microbenchmark swapin 10G from 32G zram: Before: 10934698 us After: 11157121 us Cached: 13155355 us (Dropping SWP_SYNCHRONOUS_IO flag) [kasong(a)tencent.com: v4] Link: https://lkml.kernel.org/r/20240219082040.7495-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20240206182559.32264-1-ryncsn@gmail.com Fixes: 0bcac06f27d7 ("mm, swap: skip swapcache for swapin of synchronous device") Reported-by: "Huang, Ying" <ying.huang(a)intel.com> Closes: https://lore.kernel.org/lkml/87bk92gqpx.fsf_-_@yhuang6-desk2.ccr.corp.intel… Link: https://github.com/ryncsn/emm-test-project/tree/master/swap-stress-race [1] Signed-off-by: Kairui Song <kasong(a)tencent.com> Reviewed-by: "Huang, Ying" <ying.huang(a)intel.com> Acked-by: Yu Zhao <yuzhao(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Acked-by: Chris Li <chrisl(a)kernel.org> Cc: Hugh Dickins <hughd(a)google.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Yosry Ahmed <yosryahmed(a)google.com> Cc: Yu Zhao <yuzhao(a)google.com> Cc: Barry Song <21cnbao(a)gmail.com> Cc: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/swap.h b/include/linux/swap.h index 4db00ddad261..8d28f6091a32 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -549,6 +549,11 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } +static inline int swapcache_prepare(swp_entry_t swp) +{ + return 0; +} + static inline void swap_free(swp_entry_t swp) { } diff --git a/mm/memory.c b/mm/memory.c index 15f8b10ea17c..0bfc8b007c01 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3799,6 +3799,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; + bool need_clear_cache = false; bool exclusive = false; swp_entry_t entry; pte_t pte; @@ -3867,6 +3868,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { + /* + * Prevent parallel swapin from proceeding with + * the cache flag. Otherwise, another thread may + * finish swapin first, free the entry, and swapout + * reusing the same entry. It's undetectable as + * pte_same() returns true due to entry reuse. + */ + if (swapcache_prepare(entry)) { + /* Relax a bit to prevent rapid repeated page faults */ + schedule_timeout_uninterruptible(1); + goto out; + } + need_clear_cache = true; + /* skip swapcache */ folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false); @@ -4117,6 +4132,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out: + /* Clear the swap cache pin for direct swapin after PTL unlock */ + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; @@ -4131,6 +4149,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) folio_unlock(swapcache); folio_put(swapcache); } + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; diff --git a/mm/swap.h b/mm/swap.h index 758c46ca671e..fc2f6ade7f80 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -41,6 +41,7 @@ void __delete_from_swap_cache(struct folio *folio, void delete_from_swap_cache(struct folio *folio); void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry); struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct folio *filemap_get_incore_folio(struct address_space *mapping, @@ -97,6 +98,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc) return 0; } +static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ +} + static inline struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 556ff7347d5f..746aa9da5302 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3365,6 +3365,19 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char usage; + + ci = lock_cluster_or_swap_info(si, offset); + usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); + unlock_cluster_or_swap_info(si, ci); + if (!usage) + free_swap_slot(entry); +} + struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry));

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] mm/swap: fix race when skipping swapcache" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 13ddaf26be324a7f951891ecd9ccd04466d27458 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022658-expensive-autograph-1b92@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: 13ddaf26be32 ("mm/swap: fix race when skipping swapcache") c9edc242811d ("swap: add swap_cache_get_folio()") 1baec203b77c ("mm/khugepaged: try to free transhuge swapcache when possible") 442701e7058b ("mm/swap: remove swap_cache_info statistics") 014bb1de4fc1 ("mm: create new mm/swap.h header file") 1493a1913e34 ("mm/swap: remember PG_anon_exclusive via a swp pte bit") 6c287605fd56 ("mm: remember exclusively mapped anonymous pages with PG_anon_exclusive") 78fbe906cc90 ("mm/page-flags: reuse PG_mappedtodisk as PG_anon_exclusive for PageAnon() pages") 6c54dc6c7437 ("mm/rmap: use page_move_anon_rmap() when reusing a mapped PageAnon() page exclusively") 28c5209dfd5f ("mm/rmap: pass rmap flags to hugepage_add_anon_rmap()") f1e2db12e45b ("mm/rmap: remove do_page_add_anon_rmap()") 14f9135d5470 ("mm/rmap: convert RMAP flags to a proper distinct rmap_t type") fb3d824d1a46 ("mm/rmap: split page_dup_rmap() into page_dup_file_rmap() and page_try_dup_anon_rmap()") b51ad4f8679e ("mm/memory: slightly simplify copy_present_pte()") 623a1ddfeb23 ("mm/hugetlb: take src_mm->write_protect_seq in copy_hugetlb_page_range()") 3bff7e3f1f16 ("mm/huge_memory: streamline COW logic in do_huge_pmd_wp_page()") c145e0b47c77 ("mm: streamline COW logic in do_swap_page()") 84d60fdd3733 ("mm: slightly clarify KSM logic in do_swap_page()") 53a05ad9f21d ("mm: optimize do_wp_page() for exclusive pages in the swapcache") 6b1f86f8e9c7 ("Merge tag 'folio-5.18b' of git://git.infradead.org/users/willy/pagecache") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 13ddaf26be324a7f951891ecd9ccd04466d27458 Mon Sep 17 00:00:00 2001 From: Kairui Song <kasong(a)tencent.com> Date: Wed, 7 Feb 2024 02:25:59 +0800 Subject: [PATCH] mm/swap: fix race when skipping swapcache When skipping swapcache for SWP_SYNCHRONOUS_IO, if two or more threads swapin the same entry at the same time, they get different pages (A, B). Before one thread (T0) finishes the swapin and installs page (A) to the PTE, another thread (T1) could finish swapin of page (B), swap_free the entry, then swap out the possibly modified page reusing the same entry. It breaks the pte_same check in (T0) because PTE value is unchanged, causing ABA problem. Thread (T0) will install a stalled page (A) into the PTE and cause data corruption. One possible callstack is like this: CPU0 CPU1 ---- ---- do_swap_page() do_swap_page() with same entry <direct swapin path> <direct swapin path> <alloc page A> <alloc page B> swap_read_folio() <- read to page A swap_read_folio() <- read to page B <slow on later locks or interrupt> <finished swapin first> ... set_pte_at() swap_free() <- entry is free <write to page B, now page A stalled> <swap out page B to same swap entry> pte_same() <- Check pass, PTE seems unchanged, but page A is stalled! swap_free() <- page B content lost! set_pte_at() <- staled page A installed! And besides, for ZRAM, swap_free() allows the swap device to discard the entry content, so even if page (B) is not modified, if swap_read_folio() on CPU0 happens later than swap_free() on CPU1, it may also cause data loss. To fix this, reuse swapcache_prepare which will pin the swap entry using the cache flag, and allow only one thread to swap it in, also prevent any parallel code from putting the entry in the cache. Release the pin after PT unlocked. Racers just loop and wait since it's a rare and very short event. A schedule_timeout_uninterruptible(1) call is added to avoid repeated page faults wasting too much CPU, causing livelock or adding too much noise to perf statistics. A similar livelock issue was described in commit 029c4628b2eb ("mm: swap: get rid of livelock in swapin readahead") Reproducer: This race issue can be triggered easily using a well constructed reproducer and patched brd (with a delay in read path) [1]: With latest 6.8 mainline, race caused data loss can be observed easily: $ gcc -g -lpthread test-thread-swap-race.c && ./a.out Polulating 32MB of memory region... Keep swapping out... Starting round 0... Spawning 65536 workers... 32746 workers spawned, wait for done... Round 0: Error on 0x5aa00, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x395200, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x3fd000, expected 32746, got 32737, 9 data loss! Round 0 Failed, 15 data loss! This reproducer spawns multiple threads sharing the same memory region using a small swap device. Every two threads updates mapped pages one by one in opposite direction trying to create a race, with one dedicated thread keep swapping out the data out using madvise. The reproducer created a reproduce rate of about once every 5 minutes, so the race should be totally possible in production. After this patch, I ran the reproducer for over a few hundred rounds and no data loss observed. Performance overhead is minimal, microbenchmark swapin 10G from 32G zram: Before: 10934698 us After: 11157121 us Cached: 13155355 us (Dropping SWP_SYNCHRONOUS_IO flag) [kasong(a)tencent.com: v4] Link: https://lkml.kernel.org/r/20240219082040.7495-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20240206182559.32264-1-ryncsn@gmail.com Fixes: 0bcac06f27d7 ("mm, swap: skip swapcache for swapin of synchronous device") Reported-by: "Huang, Ying" <ying.huang(a)intel.com> Closes: https://lore.kernel.org/lkml/87bk92gqpx.fsf_-_@yhuang6-desk2.ccr.corp.intel… Link: https://github.com/ryncsn/emm-test-project/tree/master/swap-stress-race [1] Signed-off-by: Kairui Song <kasong(a)tencent.com> Reviewed-by: "Huang, Ying" <ying.huang(a)intel.com> Acked-by: Yu Zhao <yuzhao(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Acked-by: Chris Li <chrisl(a)kernel.org> Cc: Hugh Dickins <hughd(a)google.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Yosry Ahmed <yosryahmed(a)google.com> Cc: Yu Zhao <yuzhao(a)google.com> Cc: Barry Song <21cnbao(a)gmail.com> Cc: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/swap.h b/include/linux/swap.h index 4db00ddad261..8d28f6091a32 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -549,6 +549,11 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } +static inline int swapcache_prepare(swp_entry_t swp) +{ + return 0; +} + static inline void swap_free(swp_entry_t swp) { } diff --git a/mm/memory.c b/mm/memory.c index 15f8b10ea17c..0bfc8b007c01 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3799,6 +3799,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; + bool need_clear_cache = false; bool exclusive = false; swp_entry_t entry; pte_t pte; @@ -3867,6 +3868,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { + /* + * Prevent parallel swapin from proceeding with + * the cache flag. Otherwise, another thread may + * finish swapin first, free the entry, and swapout + * reusing the same entry. It's undetectable as + * pte_same() returns true due to entry reuse. + */ + if (swapcache_prepare(entry)) { + /* Relax a bit to prevent rapid repeated page faults */ + schedule_timeout_uninterruptible(1); + goto out; + } + need_clear_cache = true; + /* skip swapcache */ folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false); @@ -4117,6 +4132,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out: + /* Clear the swap cache pin for direct swapin after PTL unlock */ + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; @@ -4131,6 +4149,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) folio_unlock(swapcache); folio_put(swapcache); } + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; diff --git a/mm/swap.h b/mm/swap.h index 758c46ca671e..fc2f6ade7f80 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -41,6 +41,7 @@ void __delete_from_swap_cache(struct folio *folio, void delete_from_swap_cache(struct folio *folio); void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry); struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct folio *filemap_get_incore_folio(struct address_space *mapping, @@ -97,6 +98,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc) return 0; } +static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ +} + static inline struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 556ff7347d5f..746aa9da5302 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3365,6 +3365,19 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char usage; + + ci = lock_cluster_or_swap_info(si, offset); + usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); + unlock_cluster_or_swap_info(si, ci); + if (!usage) + free_swap_slot(entry); +} + struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry));

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] cxl/acpi: Fix load failures due to single window creation" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 5c6224bfabbf7f3e491c51ab50fd2c6f92ba1141 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022643-rearview-spouse-b8a1@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 5c6224bfabbf ("cxl/acpi: Fix load failures due to single window creation failure") 790815902ec6 ("cxl: Add support for _DSM Function for retrieving QTG ID") 91019b5bc7c2 ("cxl/acpi: Return 'rc' instead of '0' in cxl_parse_cfmws()") 4cf67d3cc999 ("cxl/acpi: Fix a use-after-free in cxl_parse_cfmws()") d35b495ddf92 ("cxl/port: Fix find_cxl_root() for RCDs and simplify it") a32320b71f08 ("cxl/region: Add region autodiscovery") 32ce3f185bbb ("cxl/port: Split endpoint and switch port probe") 9995576cef48 ("cxl/region: Move region-position validation to a helper") 86987c766276 ("cxl/region: Cleanup target list on attach error") 1b9b7a6fd618 ("cxl/region: Validate region mode vs decoder mode") 7d505f982f53 ("cxl/region: Add a mode attribute for regions") 02fedf146656 ("Merge branch 'for-6.2/cxl-xor' into for-6.2/cxl") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 5c6224bfabbf7f3e491c51ab50fd2c6f92ba1141 Mon Sep 17 00:00:00 2001 From: Dan Williams <dan.j.williams(a)intel.com> Date: Fri, 16 Feb 2024 19:11:34 -0800 Subject: [PATCH] cxl/acpi: Fix load failures due to single window creation failure The expectation is that cxl_parse_cfwms() continues in the face the of failure as evidenced by code like: cxlrd = cxl_root_decoder_alloc(root_port, ways, cxl_calc_hb); if (IS_ERR(cxlrd)) return 0; There are other error paths in that function which mistakenly follow idiomatic expectations and return an error when they should not. Most of those mistakes are innocuous checks that hardly ever fail in practice. However, a recent change succeed in making the implementation more fragile by applying an idiomatic, but still wrong "fix" [1]. In this failure case the kernel reports: cxl root0: Failed to populate active decoder targets cxl_acpi ACPI0017:00: Failed to add decode range: [mem 0x00000000-0x7fffffff flags 0x200] ...which is a real issue with that one window (to be fixed separately), but ends up failing the entirety of cxl_acpi_probe(). Undo that recent breakage while also removing the confusion about ignoring errors. Update all exits paths to return an error per typical expectations and let an outer wrapper function handle dropping the error. Fixes: 91019b5bc7c2 ("cxl/acpi: Return 'rc' instead of '0' in cxl_parse_cfmws()") [1] Cc: <stable(a)vger.kernel.org> Cc: Breno Leitao <leitao(a)debian.org> Cc: Alison Schofield <alison.schofield(a)intel.com> Cc: Vishal Verma <vishal.l.verma(a)intel.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index dcf2b39e1048..1a3e6aafbdcc 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -316,31 +316,27 @@ static const struct cxl_root_ops acpi_root_ops = { .qos_class = cxl_acpi_qos_class, }; -static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, - const unsigned long end) +static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws, + struct cxl_cfmws_context *ctx) { int target_map[CXL_DECODER_MAX_INTERLEAVE]; - struct cxl_cfmws_context *ctx = arg; struct cxl_port *root_port = ctx->root_port; struct resource *cxl_res = ctx->cxl_res; struct cxl_cxims_context cxims_ctx; struct cxl_root_decoder *cxlrd; struct device *dev = ctx->dev; - struct acpi_cedt_cfmws *cfmws; cxl_calc_hb_fn cxl_calc_hb; struct cxl_decoder *cxld; unsigned int ways, i, ig; struct resource *res; int rc; - cfmws = (struct acpi_cedt_cfmws *) header; - rc = cxl_acpi_cfmws_verify(dev, cfmws); if (rc) { dev_err(dev, "CFMWS range %#llx-%#llx not registered\n", cfmws->base_hpa, cfmws->base_hpa + cfmws->window_size - 1); - return 0; + return rc; } rc = eiw_to_ways(cfmws->interleave_ways, &ways); @@ -376,7 +372,7 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, cxlrd = cxl_root_decoder_alloc(root_port, ways, cxl_calc_hb); if (IS_ERR(cxlrd)) - return 0; + return PTR_ERR(cxlrd); cxld = &cxlrd->cxlsd.cxld; cxld->flags = cfmws_to_decoder_flags(cfmws->restrictions); @@ -420,16 +416,7 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, put_device(&cxld->dev); else rc = cxl_decoder_autoremove(dev, cxld); - if (rc) { - dev_err(dev, "Failed to add decode range: %pr", res); - return rc; - } - dev_dbg(dev, "add: %s node: %d range [%#llx - %#llx]\n", - dev_name(&cxld->dev), - phys_to_target_node(cxld->hpa_range.start), - cxld->hpa_range.start, cxld->hpa_range.end); - - return 0; + return rc; err_insert: kfree(res->name); @@ -438,6 +425,29 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, return -ENOMEM; } +static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, + const unsigned long end) +{ + struct acpi_cedt_cfmws *cfmws = (struct acpi_cedt_cfmws *)header; + struct cxl_cfmws_context *ctx = arg; + struct device *dev = ctx->dev; + int rc; + + rc = __cxl_parse_cfmws(cfmws, ctx); + if (rc) + dev_err(dev, + "Failed to add decode range: [%#llx - %#llx] (%d)\n", + cfmws->base_hpa, + cfmws->base_hpa + cfmws->window_size - 1, rc); + else + dev_dbg(dev, "decode range: node: %d range [%#llx - %#llx]\n", + phys_to_target_node(cfmws->base_hpa), cfmws->base_hpa, + cfmws->base_hpa + cfmws->window_size - 1); + + /* never fail cxl_acpi load for a single window failure */ + return 0; +} + __mock struct acpi_device *to_cxl_host_bridge(struct device *host, struct device *dev) {

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] drm/amd/display: Only allow dig mapping to pwrseq in new asic" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 4e73826089ce899357580bbf6e0afe4e6f9900b7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022602-handshake-spoiled-e4a5@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: 4e73826089ce ("drm/amd/display: Only allow dig mapping to pwrseq in new asic") b17ef04bf3a4 ("drm/amd/display: Pass pwrseq inst for backlight and ABM") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 4e73826089ce899357580bbf6e0afe4e6f9900b7 Mon Sep 17 00:00:00 2001 From: Lewis Huang <lewis.huang(a)amd.com> Date: Wed, 31 Jan 2024 17:20:17 +0800 Subject: [PATCH] drm/amd/display: Only allow dig mapping to pwrseq in new asic [Why] The old asic only have 1 pwrseq hw. We don't need to map the diginst to pwrseq inst in old asic. [How] 1. Only mapping dig to pwrseq for new asic. 2. Move mapping function into dcn specific panel control component Cc: Stable <stable(a)vger.kernel.org> # v6.6+ Cc: Mario Limonciello <mario.limonciello(a)amd.com> Link: https://gitlab.freedesktop.org/drm/amd/-/issues/3122 Reviewed-by: Anthony Koo <anthony.koo(a)amd.com> Acked-by: Rodrigo Siqueira <rodrigo.siqueira(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Lewis Huang <lewis.huang(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c index e8570060d007..5bca67407c5b 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c @@ -290,4 +290,5 @@ void dce_panel_cntl_construct( dce_panel_cntl->base.funcs = &dce_link_panel_cntl_funcs; dce_panel_cntl->base.ctx = init_data->ctx; dce_panel_cntl->base.inst = init_data->inst; + dce_panel_cntl->base.pwrseq_inst = 0; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c index ad0df1a72a90..9e96a3ace207 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c @@ -215,4 +215,5 @@ void dcn301_panel_cntl_construct( dcn301_panel_cntl->base.funcs = &dcn301_link_panel_cntl_funcs; dcn301_panel_cntl->base.ctx = init_data->ctx; dcn301_panel_cntl->base.inst = init_data->inst; + dcn301_panel_cntl->base.pwrseq_inst = 0; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c index 03248422d6ff..281be20b1a10 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c @@ -154,8 +154,24 @@ void dcn31_panel_cntl_construct( struct dcn31_panel_cntl *dcn31_panel_cntl, const struct panel_cntl_init_data *init_data) { + uint8_t pwrseq_inst = 0xF; + dcn31_panel_cntl->base.funcs = &dcn31_link_panel_cntl_funcs; dcn31_panel_cntl->base.ctx = init_data->ctx; dcn31_panel_cntl->base.inst = init_data->inst; - dcn31_panel_cntl->base.pwrseq_inst = init_data->pwrseq_inst; + + switch (init_data->eng_id) { + case ENGINE_ID_DIGA: + pwrseq_inst = 0; + break; + case ENGINE_ID_DIGB: + pwrseq_inst = 1; + break; + default: + DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", init_data->eng_id); + ASSERT(false); + break; + } + + dcn31_panel_cntl->base.pwrseq_inst = pwrseq_inst; } diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h index 5dcbaa2db964..e97d964a1791 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h @@ -57,7 +57,7 @@ struct panel_cntl_funcs { struct panel_cntl_init_data { struct dc_context *ctx; uint32_t inst; - uint32_t pwrseq_inst; + uint32_t eng_id; }; struct panel_cntl { diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c index 37d3027c32dc..cf22b8f28ba6 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c @@ -370,30 +370,6 @@ static enum transmitter translate_encoder_to_transmitter( } } -static uint8_t translate_dig_inst_to_pwrseq_inst(struct dc_link *link) -{ - uint8_t pwrseq_inst = 0xF; - struct dc_context *dc_ctx = link->dc->ctx; - - DC_LOGGER_INIT(dc_ctx->logger); - - switch (link->eng_id) { - case ENGINE_ID_DIGA: - pwrseq_inst = 0; - break; - case ENGINE_ID_DIGB: - pwrseq_inst = 1; - break; - default: - DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", link->eng_id); - ASSERT(false); - break; - } - - return pwrseq_inst; -} - - static void link_destruct(struct dc_link *link) { int i; @@ -657,7 +633,7 @@ static bool construct_phy(struct dc_link *link, link->link_id.id == CONNECTOR_ID_LVDS)) { panel_cntl_init_data.ctx = dc_ctx; panel_cntl_init_data.inst = panel_cntl_init_data.ctx->dc_edp_id_count; - panel_cntl_init_data.pwrseq_inst = translate_dig_inst_to_pwrseq_inst(link); + panel_cntl_init_data.eng_id = link->eng_id; link->panel_cntl = link->dc->res_pool->funcs->panel_cntl_create( &panel_cntl_init_data);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] drm/meson: Don't remove bridges which are created by other" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x bd915ae73a2d78559b376ad2caf5e4ef51de2455 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022642-retool-clover-ecd7@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: bd915ae73a2d ("drm/meson: Don't remove bridges which are created by other drivers") 42dcf15f901c ("drm/meson: add DSI encoder") 6a044642988b ("drm/meson: fix unbind path if HDMI fails to bind") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From bd915ae73a2d78559b376ad2caf5e4ef51de2455 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl <martin.blumenstingl(a)googlemail.com> Date: Thu, 15 Feb 2024 23:04:42 +0100 Subject: [PATCH] drm/meson: Don't remove bridges which are created by other drivers Stop calling drm_bridge_remove() for bridges allocated/managed by other drivers in the remove paths of meson_encoder_{cvbs,dsi,hdmi}. drm_bridge_remove() unregisters the bridge so it cannot be used anymore. Doing so for bridges we don't own can lead to the video pipeline not being able to come up after -EPROBE_DEFER of the VPU because we're unregistering a bridge that's managed by another driver. The other driver doesn't know that we have unregistered it's bridge and on subsequent .probe() we're not able to find those bridges anymore (since nobody re-creates them). This fixes probe errors on Meson8b boards with the CVBS outputs enabled. Fixes: 09847723c12f ("drm/meson: remove drm bridges at aggregate driver unbind time") Fixes: 42dcf15f901c ("drm/meson: add DSI encoder") Cc: <stable(a)vger.kernel.org> Reported-by: Steve Morvai <stevemorvai(a)hotmail.com> Signed-off-by: Martin Blumenstingl <martin.blumenstingl(a)googlemail.com> Reviewed-by: Neil Armstrong <neil.armstrong(a)linaro.org> Tested-by: Steve Morvai <stevemorvai(a)hotmail.com> Link: https://lore.kernel.org/r/20240215220442.1343152-1-martin.blumenstingl@goog… Reviewed-by: Neil Armstrong <neil.armstrong(a)linaro.org> Signed-off-by: Neil Armstrong <neil.armstrong(a)linaro.org> Link: https://patchwork.freedesktop.org/patch/msgid/20240215220442.1343152-1-mart… diff --git a/drivers/gpu/drm/meson/meson_encoder_cvbs.c b/drivers/gpu/drm/meson/meson_encoder_cvbs.c index 3f73b211fa8e..3407450435e2 100644 --- a/drivers/gpu/drm/meson/meson_encoder_cvbs.c +++ b/drivers/gpu/drm/meson/meson_encoder_cvbs.c @@ -294,6 +294,5 @@ void meson_encoder_cvbs_remove(struct meson_drm *priv) if (priv->encoders[MESON_ENC_CVBS]) { meson_encoder_cvbs = priv->encoders[MESON_ENC_CVBS]; drm_bridge_remove(&meson_encoder_cvbs->bridge); - drm_bridge_remove(meson_encoder_cvbs->next_bridge); } } diff --git a/drivers/gpu/drm/meson/meson_encoder_dsi.c b/drivers/gpu/drm/meson/meson_encoder_dsi.c index 3f93c70488ca..311b91630fbe 100644 --- a/drivers/gpu/drm/meson/meson_encoder_dsi.c +++ b/drivers/gpu/drm/meson/meson_encoder_dsi.c @@ -168,6 +168,5 @@ void meson_encoder_dsi_remove(struct meson_drm *priv) if (priv->encoders[MESON_ENC_DSI]) { meson_encoder_dsi = priv->encoders[MESON_ENC_DSI]; drm_bridge_remove(&meson_encoder_dsi->bridge); - drm_bridge_remove(meson_encoder_dsi->next_bridge); } } diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c index 25ea76558690..c4686568c9ca 100644 --- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c +++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c @@ -474,6 +474,5 @@ void meson_encoder_hdmi_remove(struct meson_drm *priv) if (priv->encoders[MESON_ENC_HDMI]) { meson_encoder_hdmi = priv->encoders[MESON_ENC_HDMI]; drm_bridge_remove(&meson_encoder_hdmi->bridge); - drm_bridge_remove(meson_encoder_hdmi->next_bridge); } }

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix deadlock with fiemap and extent locking" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x b0ad381fa7690244802aed119b478b4bdafc31dd # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022655-fled-exes-9ef4@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: b0ad381fa769 ("btrfs: fix deadlock with fiemap and extent locking") 519b7e13b5ae ("btrfs: lock the inode in shared mode before starting fiemap") b3e744fe6d28 ("btrfs: use cached state when looking for delalloc ranges with fiemap") 8c6e53a79d16 ("btrfs: allow passing a cached state record to count_range_bits()") 8ddc8274e4be ("btrfs: search for delalloc more efficiently during lseek/fiemap") af979fd618a4 ("btrfs: skip unnecessary delalloc searches during lseek/fiemap") 40daf3e095db ("btrfs: add an early exit when searching for delalloc range for lseek/fiemap") af142b6f44d3 ("btrfs: move file prototypes to file.h") 7572dec8f522 ("btrfs: move ioctl prototypes into ioctl.h") c7a03b524d30 ("btrfs: move uuid tree prototypes to uuid-tree.h") 7c8ede162805 ("btrfs: move file-item prototypes into their own header") f2b39277b87d ("btrfs: move dir-item prototypes into dir-item.h") 59b818e064ab ("btrfs: move defrag related prototypes to their own header") a6a01ca61f49 ("btrfs: move the file defrag code into defrag.c") 6e3df18ba7e8 ("btrfs: move the auto defrag code to defrag.c") 2885fd632050 ("btrfs: move inode prototypes to btrfs_inode.h") 911bd75aca73 ("btrfs: remove unused function prototypes") 45c40c8f9541 ("btrfs: move root tree prototypes to their own header") 2839c2c142dd ("btrfs: move delalloc space related prototypes to delalloc-space.h") a0231804affe ("btrfs: move extent-tree helpers into their own header file") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b0ad381fa7690244802aed119b478b4bdafc31dd Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Mon, 12 Feb 2024 11:56:02 -0500 Subject: [PATCH] btrfs: fix deadlock with fiemap and extent locking While working on the patchset to remove extent locking I got a lockdep splat with fiemap and pagefaulting with my new extent lock replacement lock. This deadlock exists with our normal code, we just don't have lockdep annotations with the extent locking so we've never noticed it. Since we're copying the fiemap extent to user space on every iteration we have the chance of pagefaulting. Because we hold the extent lock for the entire range we could mkwrite into a range in the file that we have mmap'ed. This would deadlock with the following stack trace [<0>] lock_extent+0x28d/0x2f0 [<0>] btrfs_page_mkwrite+0x273/0x8a0 [<0>] do_page_mkwrite+0x50/0xb0 [<0>] do_fault+0xc1/0x7b0 [<0>] __handle_mm_fault+0x2fa/0x460 [<0>] handle_mm_fault+0xa4/0x330 [<0>] do_user_addr_fault+0x1f4/0x800 [<0>] exc_page_fault+0x7c/0x1e0 [<0>] asm_exc_page_fault+0x26/0x30 [<0>] rep_movs_alternative+0x33/0x70 [<0>] _copy_to_user+0x49/0x70 [<0>] fiemap_fill_next_extent+0xc8/0x120 [<0>] emit_fiemap_extent+0x4d/0xa0 [<0>] extent_fiemap+0x7f8/0xad0 [<0>] btrfs_fiemap+0x49/0x80 [<0>] __x64_sys_ioctl+0x3e1/0xb50 [<0>] do_syscall_64+0x94/0x1a0 [<0>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 I wrote an fstest to reproduce this deadlock without my replacement lock and verified that the deadlock exists with our existing locking. To fix this simply don't take the extent lock for the entire duration of the fiemap. This is safe in general because we keep track of where we are when we're searching the tree, so if an ordered extent updates in the middle of our fiemap call we'll still emit the correct extents because we know what offset we were on before. The only place we maintain the lock is searching delalloc. Since the delalloc stuff can change during writeback we want to lock the extent range so we have a consistent view of delalloc at the time we're checking to see if we need to set the delalloc flag. With this patch applied we no longer deadlock with my testcase. CC: stable(a)vger.kernel.org # 6.1+ Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a0ffd41c5cc1..61d961a30dee 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2689,16 +2689,34 @@ static int fiemap_process_hole(struct btrfs_inode *inode, * it beyond i_size. */ while (cur_offset < end && cur_offset < i_size) { + struct extent_state *cached_state = NULL; u64 delalloc_start; u64 delalloc_end; u64 prealloc_start; + u64 lockstart; + u64 lockend; u64 prealloc_len = 0; bool delalloc; + lockstart = round_down(cur_offset, inode->root->fs_info->sectorsize); + lockend = round_up(end, inode->root->fs_info->sectorsize); + + /* + * We are only locking for the delalloc range because that's the + * only thing that can change here. With fiemap we have a lock + * on the inode, so no buffered or direct writes can happen. + * + * However mmaps and normal page writeback will cause this to + * change arbitrarily. We have to lock the extent lock here to + * make sure that nobody messes with the tree while we're doing + * btrfs_find_delalloc_in_range. + */ + lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); delalloc = btrfs_find_delalloc_in_range(inode, cur_offset, end, delalloc_cached_state, &delalloc_start, &delalloc_end); + unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); if (!delalloc) break; @@ -2866,15 +2884,15 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { const u64 ino = btrfs_ino(inode); - struct extent_state *cached_state = NULL; struct extent_state *delalloc_cached_state = NULL; struct btrfs_path *path; struct fiemap_cache cache = { 0 }; struct btrfs_backref_share_check_ctx *backref_ctx; u64 last_extent_end; u64 prev_extent_end; - u64 lockstart; - u64 lockend; + u64 range_start; + u64 range_end; + const u64 sectorsize = inode->root->fs_info->sectorsize; bool stopped = false; int ret; @@ -2885,12 +2903,11 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, goto out; } - lockstart = round_down(start, inode->root->fs_info->sectorsize); - lockend = round_up(start + len, inode->root->fs_info->sectorsize); - prev_extent_end = lockstart; + range_start = round_down(start, sectorsize); + range_end = round_up(start + len, sectorsize); + prev_extent_end = range_start; btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); - lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end); if (ret < 0) @@ -2898,7 +2915,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, btrfs_release_path(path); path->reada = READA_FORWARD; - ret = fiemap_search_slot(inode, path, lockstart); + ret = fiemap_search_slot(inode, path, range_start); if (ret < 0) { goto out_unlock; } else if (ret > 0) { @@ -2910,7 +2927,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, goto check_eof_delalloc; } - while (prev_extent_end < lockend) { + while (prev_extent_end < range_end) { struct extent_buffer *leaf = path->nodes[0]; struct btrfs_file_extent_item *ei; struct btrfs_key key; @@ -2933,19 +2950,19 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, * The first iteration can leave us at an extent item that ends * before our range's start. Move to the next item. */ - if (extent_end <= lockstart) + if (extent_end <= range_start) goto next_item; backref_ctx->curr_leaf_bytenr = leaf->start; /* We have in implicit hole (NO_HOLES feature enabled). */ if (prev_extent_end < key.offset) { - const u64 range_end = min(key.offset, lockend) - 1; + const u64 hole_end = min(key.offset, range_end) - 1; ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, 0, 0, 0, - prev_extent_end, range_end); + prev_extent_end, hole_end); if (ret < 0) { goto out_unlock; } else if (ret > 0) { @@ -2955,7 +2972,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, } /* We've reached the end of the fiemap range, stop. */ - if (key.offset >= lockend) { + if (key.offset >= range_end) { stopped = true; break; } @@ -3049,29 +3066,41 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, btrfs_free_path(path); path = NULL; - if (!stopped && prev_extent_end < lockend) { + if (!stopped && prev_extent_end < range_end) { ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, - 0, 0, 0, prev_extent_end, lockend - 1); + 0, 0, 0, prev_extent_end, range_end - 1); if (ret < 0) goto out_unlock; - prev_extent_end = lockend; + prev_extent_end = range_end; } if (cache.cached && cache.offset + cache.len >= last_extent_end) { const u64 i_size = i_size_read(&inode->vfs_inode); if (prev_extent_end < i_size) { + struct extent_state *cached_state = NULL; u64 delalloc_start; u64 delalloc_end; + u64 lockstart; + u64 lockend; bool delalloc; + lockstart = round_down(prev_extent_end, sectorsize); + lockend = round_up(i_size, sectorsize); + + /* + * See the comment in fiemap_process_hole as to why + * we're doing the locking here. + */ + lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); delalloc = btrfs_find_delalloc_in_range(inode, prev_extent_end, i_size - 1, &delalloc_cached_state, &delalloc_start, &delalloc_end); + unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); if (!delalloc) cache.flags |= FIEMAP_EXTENT_LAST; } else { @@ -3082,7 +3111,6 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, ret = emit_last_fiemap_cache(fieinfo, &cache); out_unlock: - unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); out: free_extent_state(delalloc_cached_state);

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: defrag: avoid unnecessary defrag caused by incorrect" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x e42b9d8b9ea2672811285e6a7654887ff64d23f3 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022640-deepness-manatee-1a30@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: e42b9d8b9ea2 ("btrfs: defrag: avoid unnecessary defrag caused by incorrect extent size") a6a01ca61f49 ("btrfs: move the file defrag code into defrag.c") 6e3df18ba7e8 ("btrfs: move the auto defrag code to defrag.c") 07e81dc94474 ("btrfs: move accessor helpers into accessors.h") ad1ac5012c2b ("btrfs: move btrfs_map_token to accessors") 55e5cfd36da5 ("btrfs: remove fs_info::pending_changes and related code") 7966a6b5959b ("btrfs: move fs_info::flags enum to fs.h") fc97a410bd78 ("btrfs: move mount option definitions to fs.h") 0d3a9cf8c306 ("btrfs: convert incompat and compat flag test helpers to macros") ec8eb376e271 ("btrfs: move BTRFS_FS_STATE* definitions and helpers to fs.h") 9b569ea0be6f ("btrfs: move the printk helpers out of ctree.h") e118578a8df7 ("btrfs: move assert helpers out of ctree.h") c7f13d428ea1 ("btrfs: move fs wide helpers out of ctree.h") 63a7cb130718 ("btrfs: auto enable discard=async when possible") 7a66eda351ba ("btrfs: move the btrfs_verity_descriptor_item defs up in ctree.h") 956504a331a6 ("btrfs: move trans_handle_cachep out of ctree.h") f1e5c6185ca1 ("btrfs: move flush related definitions to space-info.h") ed4c491a3db2 ("btrfs: move BTRFS_MAX_MIRRORS into scrub.c") 4300c58f8090 ("btrfs: move btrfs on-disk definitions out of ctree.h") d60d956eb41f ("btrfs: remove unused set/clear_pending_info helpers") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e42b9d8b9ea2672811285e6a7654887ff64d23f3 Mon Sep 17 00:00:00 2001 From: Qu Wenruo <wqu(a)suse.com> Date: Wed, 7 Feb 2024 10:00:42 +1030 Subject: [PATCH] btrfs: defrag: avoid unnecessary defrag caused by incorrect extent size [BUG] With the following file extent layout, defrag would do unnecessary IO and result more on-disk space usage. # mkfs.btrfs -f $dev # mount $dev $mnt # xfs_io -f -c "pwrite 0 40m" $mnt/foobar # sync # xfs_io -f -c "pwrite 40m 16k" $mnt/foobar # sync Above command would lead to the following file extent layout: item 6 key (257 EXTENT_DATA 0) itemoff 15816 itemsize 53 generation 7 type 1 (regular) extent data disk byte 298844160 nr 41943040 extent data offset 0 nr 41943040 ram 41943040 extent compression 0 (none) item 7 key (257 EXTENT_DATA 41943040) itemoff 15763 itemsize 53 generation 8 type 1 (regular) extent data disk byte 13631488 nr 16384 extent data offset 0 nr 16384 ram 16384 extent compression 0 (none) Which is mostly fine. We can allow the final 16K to be merged with the previous 40M, but it's upon the end users' preference. But if we defrag the file using the default parameters, it would result worse file layout: # btrfs filesystem defrag $mnt/foobar # sync item 6 key (257 EXTENT_DATA 0) itemoff 15816 itemsize 53 generation 7 type 1 (regular) extent data disk byte 298844160 nr 41943040 extent data offset 0 nr 8650752 ram 41943040 extent compression 0 (none) item 7 key (257 EXTENT_DATA 8650752) itemoff 15763 itemsize 53 generation 9 type 1 (regular) extent data disk byte 340787200 nr 33292288 extent data offset 0 nr 33292288 ram 33292288 extent compression 0 (none) item 8 key (257 EXTENT_DATA 41943040) itemoff 15710 itemsize 53 generation 8 type 1 (regular) extent data disk byte 13631488 nr 16384 extent data offset 0 nr 16384 ram 16384 extent compression 0 (none) Note the original 40M extent is still there, but a new 32M extent is created for no benefit at all. [CAUSE] There is an existing check to make sure we won't defrag a large enough extent (the threshold is by default 32M). But the check is using the length to the end of the extent: range_len = em->len - (cur - em->start); /* Skip too large extent */ if (range_len >= extent_thresh) goto next; This means, for the first 8MiB of the extent, the range_len is always smaller than the default threshold, and would not be defragged. But after the first 8MiB, the remaining part would fit the requirement, and be defragged. Such different behavior inside the same extent caused the above problem, and we should avoid different defrag decision inside the same extent. [FIX] Instead of using @range_len, just use @em->len, so that we have a consistent decision among the same file extent. Now with this fix, we won't touch the extent, thus not making it any worse. Reported-by: Filipe Manana <fdmanana(a)suse.com> Fixes: 0cb5950f3f3b ("btrfs: fix deadlock when reserving space during defrag") CC: stable(a)vger.kernel.org # 6.1+ Reviewed-by: Boris Burkov <boris(a)bur.io> Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c index c276b136ab63..5b0b64571418 100644 --- a/fs/btrfs/defrag.c +++ b/fs/btrfs/defrag.c @@ -1046,7 +1046,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode, goto add; /* Skip too large extent */ - if (range_len >= extent_thresh) + if (em->len >= extent_thresh) goto next; /*

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] LoongArch: Update cpu_sibling_map when disabling nonboot CPUs" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 752cd08da320a667a833803a8fd6bb266114cce5 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024022657-dash-dividers-8bff@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 752cd08da320 ("LoongArch: Update cpu_sibling_map when disabling nonboot CPUs") f6f0c9a74a48 ("LoongArch: Add SMT (Simultaneous Multi-Threading) support") 366bb35a8e48 ("LoongArch: Add suspend (ACPI S3) support") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 752cd08da320a667a833803a8fd6bb266114cce5 Mon Sep 17 00:00:00 2001 From: Huacai Chen <chenhuacai(a)kernel.org> Date: Fri, 23 Feb 2024 14:36:31 +0800 Subject: [PATCH] LoongArch: Update cpu_sibling_map when disabling nonboot CPUs Update cpu_sibling_map when disabling nonboot CPUs by defining & calling clear_cpu_sibling_map(), otherwise we get such errors on SMT systems: jump label: negative count! WARNING: CPU: 6 PID: 45 at kernel/jump_label.c:263 __static_key_slow_dec_cpuslocked+0xec/0x100 CPU: 6 PID: 45 Comm: cpuhp/6 Not tainted 6.8.0-rc5+ #1340 pc 90000000004c302c ra 90000000004c302c tp 90000001005bc000 sp 90000001005bfd20 a0 000000000000001b a1 900000000224c278 a2 90000001005bfb58 a3 900000000224c280 a4 900000000224c278 a5 90000001005bfb50 a6 0000000000000001 a7 0000000000000001 t0 ce87a4763eb5234a t1 ce87a4763eb5234a t2 0000000000000000 t3 0000000000000000 t4 0000000000000006 t5 0000000000000000 t6 0000000000000064 t7 0000000000001964 t8 000000000009ebf6 u0 9000000001f2a068 s9 0000000000000000 s0 900000000246a2d8 s1 ffffffffffffffff s2 ffffffffffffffff s3 90000000021518c0 s4 0000000000000040 s5 9000000002151058 s6 9000000009828e40 s7 00000000000000b4 s8 0000000000000006 ra: 90000000004c302c __static_key_slow_dec_cpuslocked+0xec/0x100 ERA: 90000000004c302c __static_key_slow_dec_cpuslocked+0xec/0x100 CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) PRMD: 00000004 (PPLV0 +PIE -PWE) EUEN: 00000000 (-FPE -SXE -ASXE -BTE) ECFG: 00071c1c (LIE=2-4,10-12 VS=7) ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0) PRID: 0014d000 (Loongson-64bit, Loongson-3A6000-HV) CPU: 6 PID: 45 Comm: cpuhp/6 Not tainted 6.8.0-rc5+ #1340 Stack : 0000000000000000 900000000203f258 900000000179afc8 90000001005bc000 90000001005bf980 0000000000000000 90000001005bf988 9000000001fe0be0 900000000224c280 900000000224c278 90000001005bf8c0 0000000000000001 0000000000000001 ce87a4763eb5234a 0000000007f38000 90000001003f8cc0 0000000000000000 0000000000000006 0000000000000000 4c206e6f73676e6f 6f4c203a656d616e 000000000009ec99 0000000007f38000 0000000000000000 900000000214b000 9000000001fe0be0 0000000000000004 0000000000000000 0000000000000107 0000000000000009 ffffffffffafdabe 00000000000000b4 0000000000000006 90000000004c302c 9000000000224528 00005555939a0c7c 00000000000000b0 0000000000000004 0000000000000000 0000000000071c1c ... Call Trace: [<9000000000224528>] show_stack+0x48/0x1a0 [<900000000179afc8>] dump_stack_lvl+0x78/0xa0 [<9000000000263ed0>] __warn+0x90/0x1a0 [<90000000017419b8>] report_bug+0x1b8/0x280 [<900000000179c564>] do_bp+0x264/0x420 [<90000000004c302c>] __static_key_slow_dec_cpuslocked+0xec/0x100 [<90000000002b4d7c>] sched_cpu_deactivate+0x2fc/0x300 [<9000000000266498>] cpuhp_invoke_callback+0x178/0x8a0 [<9000000000267f70>] cpuhp_thread_fun+0xf0/0x240 [<90000000002a117c>] smpboot_thread_fn+0x1dc/0x2e0 [<900000000029a720>] kthread+0x140/0x160 [<9000000000222288>] ret_from_kernel_thread+0xc/0xa4 Cc: stable(a)vger.kernel.org Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn> diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 87b7190fe48e..aabee0b280fe 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -88,6 +88,73 @@ void show_ipi_list(struct seq_file *p, int prec) } } +static inline void set_cpu_core_map(int cpu) +{ + int i; + + cpumask_set_cpu(cpu, &cpu_core_setup_map); + + for_each_cpu(i, &cpu_core_setup_map) { + if (cpu_data[cpu].package == cpu_data[i].package) { + cpumask_set_cpu(i, &cpu_core_map[cpu]); + cpumask_set_cpu(cpu, &cpu_core_map[i]); + } + } +} + +static inline void set_cpu_sibling_map(int cpu) +{ + int i; + + cpumask_set_cpu(cpu, &cpu_sibling_setup_map); + + for_each_cpu(i, &cpu_sibling_setup_map) { + if (cpus_are_siblings(cpu, i)) { + cpumask_set_cpu(i, &cpu_sibling_map[cpu]); + cpumask_set_cpu(cpu, &cpu_sibling_map[i]); + } + } +} + +static inline void clear_cpu_sibling_map(int cpu) +{ + int i; + + for_each_cpu(i, &cpu_sibling_setup_map) { + if (cpus_are_siblings(cpu, i)) { + cpumask_clear_cpu(i, &cpu_sibling_map[cpu]); + cpumask_clear_cpu(cpu, &cpu_sibling_map[i]); + } + } + + cpumask_clear_cpu(cpu, &cpu_sibling_setup_map); +} + +/* + * Calculate a new cpu_foreign_map mask whenever a + * new cpu appears or disappears. + */ +void calculate_cpu_foreign_map(void) +{ + int i, k, core_present; + cpumask_t temp_foreign_map; + + /* Re-calculate the mask */ + cpumask_clear(&temp_foreign_map); + for_each_online_cpu(i) { + core_present = 0; + for_each_cpu(k, &temp_foreign_map) + if (cpus_are_siblings(i, k)) + core_present = 1; + if (!core_present) + cpumask_set_cpu(i, &temp_foreign_map); + } + + for_each_online_cpu(i) + cpumask_andnot(&cpu_foreign_map[i], + &temp_foreign_map, &cpu_sibling_map[i]); +} + /* Send mailbox buffer via Mail_Send */ static void csr_mail_send(uint64_t data, int cpu, int mailbox) { @@ -303,6 +370,7 @@ int loongson_cpu_disable(void) numa_remove_cpu(cpu); #endif set_cpu_online(cpu, false); + clear_cpu_sibling_map(cpu); calculate_cpu_foreign_map(); local_irq_save(flags); irq_migrate_all_off_this_cpu(); @@ -380,59 +448,6 @@ static int __init ipi_pm_init(void) core_initcall(ipi_pm_init); #endif -static inline void set_cpu_sibling_map(int cpu) -{ - int i; - - cpumask_set_cpu(cpu, &cpu_sibling_setup_map); - - for_each_cpu(i, &cpu_sibling_setup_map) { - if (cpus_are_siblings(cpu, i)) { - cpumask_set_cpu(i, &cpu_sibling_map[cpu]); - cpumask_set_cpu(cpu, &cpu_sibling_map[i]); - } - } -} - -static inline void set_cpu_core_map(int cpu) -{ - int i; - - cpumask_set_cpu(cpu, &cpu_core_setup_map); - - for_each_cpu(i, &cpu_core_setup_map) { - if (cpu_data[cpu].package == cpu_data[i].package) { - cpumask_set_cpu(i, &cpu_core_map[cpu]); - cpumask_set_cpu(cpu, &cpu_core_map[i]); - } - } -} - -/* - * Calculate a new cpu_foreign_map mask whenever a - * new cpu appears or disappears. - */ -void calculate_cpu_foreign_map(void) -{ - int i, k, core_present; - cpumask_t temp_foreign_map; - - /* Re-calculate the mask */ - cpumask_clear(&temp_foreign_map); - for_each_online_cpu(i) { - core_present = 0; - for_each_cpu(k, &temp_foreign_map) - if (cpus_are_siblings(i, k)) - core_present = 1; - if (!core_present) - cpumask_set_cpu(i, &temp_foreign_map); - } - - for_each_online_cpu(i) - cpumask_andnot(&cpu_foreign_map[i], - &temp_foreign_map, &cpu_sibling_map[i]); -} - /* Preload SMP state for boot cpu */ void smp_prepare_boot_cpu(void) {

1 year, 8 months

1
0
0 0

[PATCH 0/3] Support intra-function call validation

by $(name)

From: Rui Qi <qirui.001(a)bytedance.com> Since kernel version 5.4.250 LTS, there has been an issue with the kernel live patching feature becoming unavailable. When compiling the sample code for kernel live patching, the following message is displayed when enabled: livepatch: klp_check_stack: kworker/u256:6:23490 has an unreliable stack After investigation, it was found that this is due to objtool not supporting intra-function calls, resulting in incorrect orc entry generation. This patchset adds support for intra-function calls, allowing the kernel live patching feature to work correctly. Alexandre Chartre (2): objtool: is_fentry_call() crashes if call has no destination objtool: Add support for intra-function calls Rui Qi (1): x86/speculation: Support intra-function call validation arch/x86/include/asm/nospec-branch.h | 7 ++ include/linux/frame.h | 11 ++++ .../Documentation/stack-validation.txt | 8 +++ tools/objtool/arch/x86/decode.c | 6 ++ tools/objtool/check.c | 64 +++++++++++++++++-- 5 files changed, 91 insertions(+), 5 deletions(-) -- 2.39.2 (Apple Git-143)

1 year, 8 months

2
4
0 0

[PATCH 5.15] media: atomisp: sh_css: check ia_css_pipeline_create_and_add_stage() return code

by Alexandra Diupina

commit 912680064f94 ("media: atomisp: make sh_css similar to Intel Aero driver") removes the affected code, but in versions tags/v5.8-rc1~10^2~220 - tags/v5.17-rc1~114^2~261 there is no check for the return value of the ia_css_pipeline_create_and_add_stage() function. ia_css_pipeline_create_and_add_stage() may return an error code, so check and return it on error. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 7796e455170e ("media: staging: media: atomisp: Fix alignment and line length issues") Signed-off-by: Alexandra Diupina <adiupina(a)astralinux.ru> --- drivers/staging/media/atomisp/pci/sh_css.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/staging/media/atomisp/pci/sh_css.c b/drivers/staging/media/atomisp/pci/sh_css.c index ba25d0da8b81..8502adb75a5a 100644 --- a/drivers/staging/media/atomisp/pci/sh_css.c +++ b/drivers/staging/media/atomisp/pci/sh_css.c @@ -7912,6 +7912,10 @@ create_host_regular_capture_pipeline(struct ia_css_pipe *pipe) out_frames, in_frame, NULL); err = ia_css_pipeline_create_and_add_stage(me, &stage_desc, NULL); + if (err) { + IA_CSS_LEAVE_ERR_PRIVATE(err); + return err; + } } else if (need_pp && current_stage) { in_frame = current_stage->args.out_frame[0]; err = add_capture_pp_stage(pipe, me, in_frame, -- 2.30.2

1 year, 8 months

2
1
0 0

[PATCH 0/3] Support intra-function call validation

by $(uname)

From: Rui Qi <qirui.001(a)bytedance.com> Since kernel version 5.4.250 LTS, there has been an issue with the kernel live patching feature becoming unavailable. When compiling the sample code for kernel live patching, the following message is displayed when enabled: livepatch: klp_check_stack: kworker/u256:6:23490 has an unreliable stack After investigation, it was found that this is due to objtool not supporting intra-function calls, resulting in incorrect orc entry generation. This patchset adds support for intra-function calls, allowing the kernel live patching feature to work correctly. Alexandre Chartre (2): objtool: is_fentry_call() crashes if call has no destination objtool: Add support for intra-function calls Rui Qi (1): x86/speculation: Support intra-function call validation arch/x86/include/asm/nospec-branch.h | 7 ++ include/linux/frame.h | 11 ++++ .../Documentation/stack-validation.txt | 8 +++ tools/objtool/arch/x86/decode.c | 6 ++ tools/objtool/check.c | 64 +++++++++++++++++-- 5 files changed, 91 insertions(+), 5 deletions(-) -- 2.39.2 (Apple Git-143)

1 year, 8 months

1
0
0 0

[PATCH V2] usb: dwc3: gadget: Fix suspend/resume warning when no-gadget is connected

by Michael Trimarchi

This patch restore the logic but protects the variable using a spinlock without moving the code [ 45.597274] dwc3 31000000.usb: wait for SETUP phase timed out [ 45.599140] dwc3 31000000.usb: failed to set STALL on ep0out [ 45.601069] ------------[ cut here ]------------ [ 45.601073] WARNING: CPU: 0 PID: 150 at drivers/usb/dwc3/ep0.c:289 dwc3_ep0_out_start+0xcc/0xd4 [ 45.601102] Modules linked in: cfg80211 rfkill ipv6 rpmsg_ctrl rpmsg_char crct10dif_ce rti_wdt k3_j72xx_bandgap rtc_ti_k3 omap_mailbox sa2ul authenc [last unloaded: ti_k3_r5_remoteproc] [ 45.601151] CPU: 0 PID: 150 Comm: sh Not tainted 6.8.0-rc5 #1 [ 45.601159] Hardware name: BSH - CCM-M3 (DT) [ 45.601164] pstate: 600000c5 (nZCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 45.601172] pc : dwc3_ep0_out_start+0xcc/0xd4 [ 45.601179] lr : dwc3_ep0_out_start+0x50/0xd4 [ 45.601186] sp : ffff8000832739e0 [ 45.601189] x29: ffff8000832739e0 x28: ffff800082a21000 x27: ffff8000808dc630 [ 45.601200] x26: 0000000000000002 x25: ffff800082530a44 x24: 0000000000000000 [ 45.601210] x23: ffff000000e079a0 x22: ffff000000e07a68 x21: 0000000000000001 [ 45.601219] x20: ffff000000e07880 x19: ffff000000e07880 x18: 0000000000000040 [ 45.601229] x17: ffff7fff8e1ce000 x16: ffff800080000000 x15: fffffffffffe5260 [ 45.601239] x14: 0000000000000000 x13: 206e6f204c4c4154 x12: 5320746573206f74 [ 45.601249] x11: 0000000000000001 x10: 000000000000000a x9 : ffff800083273930 [ 45.601259] x8 : 000000000000000a x7 : ffffffffffff3f0c x6 : ffffffffffff3f00 [ 45.601268] x5 : ffffffffffff3f0c x4 : 0000000000000000 x3 : 0000000000000000 [ 45.601278] x2 : 0000000000000000 x1 : ffff000004e7e600 x0 : 00000000ffffff92 [ 45.601289] Call trace: [ 45.601293] dwc3_ep0_out_start+0xcc/0xd4 [ 45.601301] dwc3_ep0_stall_and_restart+0x98/0xbc [ 45.601309] dwc3_ep0_reset_state+0x5c/0x88 [ 45.601315] dwc3_gadget_soft_disconnect+0x144/0x160 [ 45.601323] dwc3_gadget_suspend+0x18/0xb0 [ 45.601329] dwc3_suspend_common+0x5c/0x18c [ 45.601341] dwc3_suspend+0x20/0x44 [ 45.601350] platform_pm_suspend+0x2c/0x6c [ 45.601360] __device_suspend+0x10c/0x34c [ 45.601372] dpm_suspend+0x1a8/0x240 [ 45.601382] dpm_suspend_start+0x80/0x9c [ 45.601391] suspend_devices_and_enter+0x1c4/0x584 [ 45.601402] pm_suspend+0x1b0/0x264 [ 45.601408] state_store+0x80/0xec [ 45.601415] kobj_attr_store+0x18/0x2c [ 45.601426] sysfs_kf_write+0x44/0x54 [ 45.601434] kernfs_fop_write_iter+0x120/0x1ec [ 45.601445] vfs_write+0x23c/0x358 [ 45.601458] ksys_write+0x70/0x104 [ 45.601467] __arm64_sys_write+0x1c/0x28 [ 45.601477] invoke_syscall+0x48/0x114 [ 45.601488] el0_svc_common.constprop.0+0x40/0xe0 [ 45.601498] do_el0_svc+0x1c/0x28 [ 45.601506] el0_svc+0x34/0xb8 [ 45.601516] el0t_64_sync_handler+0x100/0x12c [ 45.601522] el0t_64_sync+0x190/0x194 [ 45.601531] ---[ end trace 0000000000000000 ]--- [ 45.608794] Disabling non-boot CPUs ... [ 45.611029] psci: CPU1 killed (polled 0 ms) [ 45.611837] Enabling non-boot CPUs ... [ 45.612247] Detected VIPT I-cache on CPU1 Tested on a am62x board Fixes: 61a348857e86 ("usb: dwc3: gadget: Fix NULL pointer dereference in dwc3_gadget_suspend) Cc: stable(a)vger.kernel.org Signed-off-by: Michael Trimarchi <michael(a)amarulasolutions.com> --- V1->V2: Add cc to stable --- drivers/usb/dwc3/gadget.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 4c8dd6724678..4c88e44127b5 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4703,13 +4703,19 @@ int dwc3_gadget_suspend(struct dwc3 *dwc) unsigned long flags; int ret; + spin_lock_irqsave(&dwc->lock, flags); + if (!dwc->gadget_driver) { + spin_unlock_irqrestore(&dwc->lock, flags); + return 0; + } + spin_unlock_irqrestore(&dwc->lock, flags); + ret = dwc3_gadget_soft_disconnect(dwc); if (ret) goto err; spin_lock_irqsave(&dwc->lock, flags); - if (dwc->gadget_driver) - dwc3_disconnect_gadget(dwc); + dwc3_disconnect_gadget(dwc); spin_unlock_irqrestore(&dwc->lock, flags); return 0; -- 2.40.1

1 year, 8 months

2
1
0 0

[PATCH] Revert "usb: typec: tcpm: reset counter when enter into unattached state after try role"

by Ondřej Jirman

From: Ondrej Jirman <megi(a)xff.cz> The reverted commit makes the state machine only ever go from SRC_ATTACH_WAIT to SNK_TRY in endless loop when toggling. After revert it goes to SRC_ATTACHED after initially trying SNK_TRY earlier, as it should for toggling to ever detect the power source mode and the port is again able to provide power to attached power sinks. This reverts commit 2d6d80127006ae3da26b1f21a65eccf957f2d1e5. Cc: stable(a)vger.kernel.org Fixes: 2d6d80127006 ("usb: typec: tcpm: reset counter when enter into unattached state after try role") Signed-of-by: Ondrej Jirman <megi(a)xff.cz> --- drivers/usb/typec/tcpm/tcpm.c | 3 --- 1 file changed, 3 deletions(-) See https://lore.kernel.org/all/odggrbbgjpardze76qiv57mw6tllisyu5sbrta37iadjzwa… for more. diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index f7d7daa60c8d..295ae7eb912c 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -3743,9 +3743,6 @@ static void tcpm_detach(struct tcpm_port *port) if (tcpm_port_is_disconnected(port)) port->hard_reset_count = 0; - port->try_src_count = 0; - port->try_snk_count = 0; - if (!port->attached) return; -- 2.43.0

1 year, 8 months

2
1
0 0

[PATCH stable 4.19] mm: memcontrol: switch to rcu protection in drain_all_stock()

by GONG, Ruiqi

From: Roman Gushchin <guro(a)fb.com> commit e1a366be5cb4f849ec4de170d50eebc08bb0af20 upstream. Commit 72f0184c8a00 ("mm, memcg: remove hotplug locking from try_charge") introduced css_tryget()/css_put() calls in drain_all_stock(), which are supposed to protect the target memory cgroup from being released during the mem_cgroup_is_descendant() call. However, it's not completely safe. In theory, memcg can go away between reading stock->cached pointer and calling css_tryget(). This can happen if drain_all_stock() races with drain_local_stock() performed on the remote cpu as a result of a work, scheduled by the previous invocation of drain_all_stock(). The race is a bit theoretical and there are few chances to trigger it, but the current code looks a bit confusing, so it makes sense to fix it anyway. The code looks like as if css_tryget() and css_put() are used to protect stocks drainage. It's not necessary because stocked pages are holding references to the cached cgroup. And it obviously won't work for works, scheduled on other cpus. So, let's read the stock->cached pointer and evaluate the memory cgroup inside a rcu read section, and get rid of css_tryget()/css_put() calls. Link: http://lkml.kernel.org/r/20190802192241.3253165-1-guro@fb.com Signed-off-by: Roman Gushchin <guro(a)fb.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: Hillf Danton <hdanton(a)sina.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Vladimir Davydov <vdavydov.dev(a)gmail.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: stable(a)vger.kernel.org # 4.19 Fixes: cdec2e4265df ("memcg: coalesce charging via percpu storage") Signed-off-by: GONG, Ruiqi <gongruiqi1(a)huawei.com> --- This patch [1] fixed a UAF problem in drain_all_stock() existed prior to 5.9, and following discussions [2] mentioned that the fix depends on an RCU read protection to stock->cached (introduced in 5.4), which doesn't existed in 4.19. So backport this part to 4.19 as well. [1]: https://lore.kernel.org/all/20240221081801.69764-1-gongruiqi1@huawei.com/ [2]: https://lore.kernel.org/all/ZdXLgjpUfpwEwAe0@tiehlicka/ mm/memcontrol.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8c04296df1c7..d187bfb43b1f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2094,21 +2094,22 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); struct mem_cgroup *memcg; + bool flush = false; + rcu_read_lock(); memcg = stock->cached; - if (!memcg || !stock->nr_pages || !css_tryget(&memcg->css)) - continue; - if (!mem_cgroup_is_descendant(memcg, root_memcg)) { - css_put(&memcg->css); - continue; - } - if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) { + if (memcg && stock->nr_pages && + mem_cgroup_is_descendant(memcg, root_memcg)) + flush = true; + rcu_read_unlock(); + + if (flush && + !test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) { if (cpu == curcpu) drain_local_stock(&stock->work); else schedule_work_on(cpu, &stock->work); } - css_put(&memcg->css); } put_cpu(); mutex_unlock(&percpu_charge_mutex); -- 2.25.1

1 year, 8 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror