From b95181f3929ff98949fa9460ca93eccebbf2d7fc Mon Sep 17 00:00:00 2001 From: You-Kai Zheng Date: Tue, 16 Jun 2026 18:39:07 +0800 Subject: btrfs: declare btrfs_ioctl_search_args_v2::buf as __u8 The variable-sized buffer buf in struct btrfs_ioctl_search_args_v2 is declared as __u64[], but it holds a packed byte stream of search results, where all offsets into the buffer are in bytes. Declaring buf as __u64[] makes it easy for user space to write incorrect pointer arithmetic: adding a byte offset directly to a __u64 pointer scales the offset by 8, landing at byte position offset*8 instead of offset. This recently caused an infinite loop in btrfs-progs: the accessor read all-zero data from misaddressed items, which fed zeroed search keys back into the ioctl loop and spun forever. The issue was worked around at the time by disabling TREE_SEARCH_V2 entirely in btrfs-progs (d73e69824854: "btrfs-progs: temporarily disable usage of v2 of search tree ioctl"). The kernel side already treats buf as a byte buffer, so change the declaration to __u8[] to match the actual semantics and prevent similar misuse in user space. The change is ABI compatible: both the structure size and alignment are unchanged. Fixes: cc68a8a5a433 ("btrfs: new ioctl TREE_SEARCH_V2") Reviewed-by: Qu Wenruo Signed-off-by: You-Kai Zheng Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 9b576603b3f1..0a13baf3d8d1 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -598,7 +598,7 @@ struct btrfs_ioctl_search_args_v2 { __u64 buf_size; /* in - size of buffer * out - on EOVERFLOW: needed size * to store item */ - __u64 buf[]; /* out - found items */ + __u8 buf[]; /* out - found items */ }; /* With a @src_length of zero, the range from @src_offset->EOF is cloned! */ -- cgit From af78c0020480aba3132fb9fa4db0fd1fb949feaa Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 22 Jul 2026 14:42:15 +0100 Subject: io_uring/zcrx: drop "notif" from stats struct names Keep zcrx statistics generic and don't stick "notif" to its uapi definitions. Stats dosn't need to be bound to notification details, it makes it cleaner and more readable. Signed-off-by: Pavel Begunkov Link: https://patch.msgid.link/6a39676b6f71b67d3f89c6ebab7a3739873834a3.1784726895.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/query.h | 6 +++--- include/uapi/linux/io_uring/zcrx.h | 4 ++-- io_uring/query.c | 4 ++-- io_uring/zcrx.c | 4 ++-- io_uring/zcrx.h | 2 +- 5 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/io_uring/query.h b/include/uapi/linux/io_uring/query.h index 1a68eca7c6b4..708bcdd585dd 100644 --- a/include/uapi/linux/io_uring/query.h +++ b/include/uapi/linux/io_uring/query.h @@ -66,10 +66,10 @@ struct io_uring_query_zcrx { struct io_uring_query_zcrx_notif { /* Bitmask of supported ZCRX_NOTIF_* flags */ __u32 notif_flags; - /* Size of io_uring_zcrx_notif_stats */ - __u32 notif_stats_size; + /* Size of zcrx_stats */ + __u32 stats_size; /* Required alignment for the stats struct within the region (ie stats_offset) */ - __u32 notif_stats_off_alignment; + __u32 stats_off_alignment; __u32 __resv1; __u64 __resv2[4]; }; diff --git a/include/uapi/linux/io_uring/zcrx.h b/include/uapi/linux/io_uring/zcrx.h index 15c05c45ce36..99e56ec26ead 100644 --- a/include/uapi/linux/io_uring/zcrx.h +++ b/include/uapi/linux/io_uring/zcrx.h @@ -76,11 +76,11 @@ enum zcrx_notification_type { }; enum zcrx_notification_desc_flags { - /* If set, stats_offset holds a valid offset to a notif_stats struct */ + /* If set, stats_offset holds a valid offset to a zcrx_stats struct */ ZCRX_NOTIF_DESC_FLAG_STATS = 1 << 0, }; -struct zcrx_notif_stats { +struct zcrx_stats { __u64 copy_count; /* cumulative copy-fallback CQEs */ __u64 copy_bytes; /* cumulative bytes copied */ }; diff --git a/io_uring/query.c b/io_uring/query.c index d529d94aa8f4..2e48fddd8d3a 100644 --- a/io_uring/query.c +++ b/io_uring/query.c @@ -50,8 +50,8 @@ static ssize_t io_query_zcrx_notif(union io_query_data *data) struct io_uring_query_zcrx_notif *e = &data->zcrx_notif; e->notif_flags = ZCRX_NOTIF_TYPE_MASK; - e->notif_stats_size = sizeof(struct zcrx_notif_stats); - e->notif_stats_off_alignment = __alignof__(struct zcrx_notif_stats); + e->stats_size = sizeof(struct zcrx_stats); + e->stats_off_alignment = __alignof__(struct zcrx_stats); e->__resv1 = 0; memset(&e->__resv2, 0, sizeof(e->__resv2)); return sizeof(*e); diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 49163f9c39df..53dcb5110719 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -863,12 +863,12 @@ static int zcrx_validate_notif_stats(struct io_zcrx_ifq *ifq, used = reg->offsets.rqes + sizeof(struct io_uring_zcrx_rqe) * reg->rq_entries; - if (!IS_ALIGNED(stats_off, __alignof__(struct zcrx_notif_stats))) + if (!IS_ALIGNED(stats_off, __alignof__(struct zcrx_stats))) return -EINVAL; if (stats_off < used) return -ERANGE; if (check_add_overflow(stats_off, - sizeof(struct zcrx_notif_stats), + sizeof(struct zcrx_stats), &end)) return -ERANGE; if (end > io_region_size(&ifq->rq_region)) diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h index fa00900e479e..a8d301b6191f 100644 --- a/io_uring/zcrx.h +++ b/io_uring/zcrx.h @@ -80,7 +80,7 @@ struct io_zcrx_ifq { u32 allowed_notif_mask; u32 fired_notifs; u64 notif_data; - struct zcrx_notif_stats *notif_stats; + struct zcrx_stats *notif_stats; }; #if defined(CONFIG_IO_URING_ZCRX) -- cgit From 201e30810223a40275f17c5e6ee410fa857b6b44 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 22 Jul 2026 14:42:16 +0100 Subject: io_uring/zcrx: rename ZCRX_NOTIF_NO_BUFFERS ZCRX_NOTIF_NO_BUFFERS tells when page pool fails to allocate memory from zcrx. "No buffers" could be more confusing, rename it to ZCRX_NOTIF_ALLOC_FAIL. Signed-off-by: Pavel Begunkov Link: https://patch.msgid.link/29bd4fc069bc89691868beba0627ffbe570c2722.1784726895.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/zcrx.h | 2 +- io_uring/zcrx.c | 2 +- io_uring/zcrx.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/io_uring/zcrx.h b/include/uapi/linux/io_uring/zcrx.h index 99e56ec26ead..abb898d59a4b 100644 --- a/include/uapi/linux/io_uring/zcrx.h +++ b/include/uapi/linux/io_uring/zcrx.h @@ -69,7 +69,7 @@ enum zcrx_features { }; enum zcrx_notification_type { - ZCRX_NOTIF_NO_BUFFERS, + ZCRX_NOTIF_ALLOC_FAIL, ZCRX_NOTIF_COPY, __ZCRX_NOTIF_TYPE_LAST, diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 53dcb5110719..872d5794d3de 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -1244,7 +1244,7 @@ static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp) allocated = io_zcrx_refill_slow(pp, ifq, netmems, to_alloc); if (!allocated) { - zcrx_send_notif(ifq, ZCRX_NOTIF_NO_BUFFERS); + zcrx_send_notif(ifq, ZCRX_NOTIF_ALLOC_FAIL); return 0; } out_return: diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h index a8d301b6191f..d16206eb9e30 100644 --- a/io_uring/zcrx.h +++ b/io_uring/zcrx.h @@ -11,7 +11,7 @@ #define ZCRX_SUPPORTED_REG_FLAGS (ZCRX_REG_IMPORT | ZCRX_REG_NODEV) #define ZCRX_FEATURES (ZCRX_FEATURE_RX_PAGE_SIZE |\ ZCRX_FEATURE_NOTIFICATION) -#define ZCRX_NOTIF_TYPE_MASK ((1U << ZCRX_NOTIF_NO_BUFFERS) | (1U << ZCRX_NOTIF_COPY)) +#define ZCRX_NOTIF_TYPE_MASK ((1U << ZCRX_NOTIF_ALLOC_FAIL) | (1U << ZCRX_NOTIF_COPY)) struct io_zcrx_mem { unsigned long size; -- cgit From e366c15e1610ef11d0717ecd875ae63050282676 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 22 Jul 2026 14:42:17 +0100 Subject: io_uring/zcrx: rename notif to event "Notification" is too long and the abbreviated version is used in several places, which is inconsistent and more ambiguous for users. Rename it to event, which is easier to keep consistent. To keep the change small, only change uapi/ + do necessary fix ups, and the rest of internals can be adjusted in the next release. Signed-off-by: Pavel Begunkov Link: https://patch.msgid.link/f95ca6717da3c8d3649a1a7f0d883a563f545052.1784726895.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/query.h | 8 ++++---- include/uapi/linux/io_uring/zcrx.h | 28 ++++++++++++++-------------- io_uring/query.c | 8 ++++---- io_uring/zcrx.c | 30 +++++++++++++++--------------- io_uring/zcrx.h | 5 +++-- 5 files changed, 40 insertions(+), 39 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/io_uring/query.h b/include/uapi/linux/io_uring/query.h index 708bcdd585dd..e6493e4a7a4d 100644 --- a/include/uapi/linux/io_uring/query.h +++ b/include/uapi/linux/io_uring/query.h @@ -23,7 +23,7 @@ enum { IO_URING_QUERY_OPCODES = 0, IO_URING_QUERY_ZCRX = 1, IO_URING_QUERY_SCQ = 2, - IO_URING_QUERY_ZCRX_NOTIF = 3, + IO_URING_QUERY_ZCRX_EVENT = 3, __IO_URING_QUERY_MAX, }; @@ -63,9 +63,9 @@ struct io_uring_query_zcrx { __u64 __resv2; }; -struct io_uring_query_zcrx_notif { - /* Bitmask of supported ZCRX_NOTIF_* flags */ - __u32 notif_flags; +struct io_uring_query_zcrx_event { + /* Bitmask of supported ZCRX_EVENT_* flags */ + __u32 event_flags; /* Size of zcrx_stats */ __u32 stats_size; /* Required alignment for the stats struct within the region (ie stats_offset) */ diff --git a/include/uapi/linux/io_uring/zcrx.h b/include/uapi/linux/io_uring/zcrx.h index abb898d59a4b..e01bc0e34b24 100644 --- a/include/uapi/linux/io_uring/zcrx.h +++ b/include/uapi/linux/io_uring/zcrx.h @@ -65,19 +65,19 @@ enum zcrx_features { * value in struct io_uring_zcrx_ifq_reg::rx_buf_len. */ ZCRX_FEATURE_RX_PAGE_SIZE = 1 << 0, - ZCRX_FEATURE_NOTIFICATION = 1 << 1, + ZCRX_FEATURE_EVENT = 1 << 1, }; -enum zcrx_notification_type { - ZCRX_NOTIF_ALLOC_FAIL, - ZCRX_NOTIF_COPY, +enum zcrx_event_type { + ZCRX_EVENT_ALLOC_FAIL, + ZCRX_EVENT_COPY, - __ZCRX_NOTIF_TYPE_LAST, + __ZCRX_EVENT_TYPE_LAST, }; -enum zcrx_notification_desc_flags { +enum zcrx_event_desc_flags { /* If set, stats_offset holds a valid offset to a zcrx_stats struct */ - ZCRX_NOTIF_DESC_FLAG_STATS = 1 << 0, + ZCRX_EVENT_DESC_FLAG_STATS = 1 << 0, }; struct zcrx_stats { @@ -85,10 +85,10 @@ struct zcrx_stats { __u64 copy_bytes; /* cumulative bytes copied */ }; -struct zcrx_notification_desc { +struct zcrx_event_desc { __u64 user_data; __u32 type_mask; - __u32 flags; /* see enum zcrx_notification_desc_flags */ + __u32 flags; /* see enum zcrx_event_desc_flags */ __u64 stats_offset; /* offset from the beginning of refill ring region for stats */ __u64 __resv2[9]; }; @@ -108,14 +108,14 @@ struct io_uring_zcrx_ifq_reg { struct io_uring_zcrx_offsets offsets; __u32 zcrx_id; __u32 rx_buf_len; - __u64 notif_desc; /* see struct zcrx_notification_desc */ + __u64 event_desc; /* see struct zcrx_event_desc */ __u64 __resv[2]; }; enum zcrx_ctrl_op { ZCRX_CTRL_FLUSH_RQ, ZCRX_CTRL_EXPORT, - ZCRX_CTRL_ARM_NOTIFICATION, + ZCRX_CTRL_ARM_EVENT, __ZCRX_CTRL_LAST, }; @@ -129,8 +129,8 @@ struct zcrx_ctrl_export { __u32 __resv1[11]; }; -struct zcrx_ctrl_arm_notif { - __u32 notif_type; +struct zcrx_ctrl_arm_event { + __u32 event_type; /* see enum zcrx_event_type */ __u32 __resv[11]; }; @@ -142,7 +142,7 @@ struct zcrx_ctrl { union { struct zcrx_ctrl_export zc_export; struct zcrx_ctrl_flush_rq zc_flush; - struct zcrx_ctrl_arm_notif zc_arm_notif; + struct zcrx_ctrl_arm_event zc_arm_event; }; }; diff --git a/io_uring/query.c b/io_uring/query.c index 2e48fddd8d3a..88a325736992 100644 --- a/io_uring/query.c +++ b/io_uring/query.c @@ -9,7 +9,7 @@ union io_query_data { struct io_uring_query_opcode opcodes; struct io_uring_query_zcrx zcrx; - struct io_uring_query_zcrx_notif zcrx_notif; + struct io_uring_query_zcrx_event zcrx_notif; struct io_uring_query_scq scq; }; @@ -47,9 +47,9 @@ static ssize_t io_query_zcrx(union io_query_data *data) static ssize_t io_query_zcrx_notif(union io_query_data *data) { - struct io_uring_query_zcrx_notif *e = &data->zcrx_notif; + struct io_uring_query_zcrx_event *e = &data->zcrx_notif; - e->notif_flags = ZCRX_NOTIF_TYPE_MASK; + e->event_flags = ZCRX_EVENT_TYPE_MASK; e->stats_size = sizeof(struct zcrx_stats); e->stats_off_alignment = __alignof__(struct zcrx_stats); e->__resv1 = 0; @@ -96,7 +96,7 @@ static int io_handle_query_entry(union io_query_data *data, void __user *uhdr, case IO_URING_QUERY_ZCRX: ret = io_query_zcrx(data); break; - case IO_URING_QUERY_ZCRX_NOTIF: + case IO_URING_QUERY_ZCRX_EVENT: ret = io_query_zcrx_notif(data); break; case IO_URING_QUERY_SCQ: diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 872d5794d3de..7d9fcf34539a 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -766,7 +766,7 @@ static int import_zcrx(struct io_ring_ctx *ctx, return -EINVAL; if (reg->if_rxq || reg->rq_entries || reg->area_ptr || reg->region_ptr) return -EINVAL; - if (reg->notif_desc) + if (reg->event_desc) return -EINVAL; if (reg->flags & ~ZCRX_REG_IMPORT) return -EINVAL; @@ -855,7 +855,7 @@ netdev_put_unlock: static int zcrx_validate_notif_stats(struct io_zcrx_ifq *ifq, const struct io_uring_zcrx_ifq_reg *reg, - const struct zcrx_notification_desc *notif) + const struct zcrx_event_desc *notif) { size_t stats_off = notif->stats_offset; size_t used, end; @@ -883,7 +883,7 @@ static int zcrx_validate_notif_stats(struct io_zcrx_ifq *ifq, int io_register_zcrx(struct io_ring_ctx *ctx, struct io_uring_zcrx_ifq_reg __user *arg) { - struct zcrx_notification_desc notif; + struct zcrx_event_desc notif; struct io_uring_zcrx_area_reg area; struct io_uring_zcrx_ifq_reg reg; struct io_uring_region_desc rd; @@ -928,14 +928,14 @@ int io_register_zcrx(struct io_ring_ctx *ctx, return -EFAULT; memset(¬if, 0, sizeof(notif)); - if (reg.notif_desc && copy_from_user(¬if, u64_to_user_ptr(reg.notif_desc), + if (reg.event_desc && copy_from_user(¬if, u64_to_user_ptr(reg.event_desc), sizeof(notif))) return -EFAULT; - if (notif.type_mask & ~ZCRX_NOTIF_TYPE_MASK) + if (notif.type_mask & ~ZCRX_EVENT_TYPE_MASK) return -EINVAL; - if (notif.flags & ~ZCRX_NOTIF_DESC_FLAG_STATS) + if (notif.flags & ~ZCRX_EVENT_DESC_FLAG_STATS) return -EINVAL; - if (!(notif.flags & ZCRX_NOTIF_DESC_FLAG_STATS)) { + if (!(notif.flags & ZCRX_EVENT_DESC_FLAG_STATS)) { if (notif.stats_offset) return -EINVAL; } @@ -970,7 +970,7 @@ int io_register_zcrx(struct io_ring_ctx *ctx, if (ret) goto err; - if (notif.flags & ZCRX_NOTIF_DESC_FLAG_STATS) { + if (notif.flags & ZCRX_EVENT_DESC_FLAG_STATS) { ret = zcrx_validate_notif_stats(ifq, ®, ¬if); if (ret) goto err; @@ -1244,7 +1244,7 @@ static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp) allocated = io_zcrx_refill_slow(pp, ifq, netmems, to_alloc); if (!allocated) { - zcrx_send_notif(ifq, ZCRX_NOTIF_ALLOC_FAIL); + zcrx_send_notif(ifq, ZCRX_EVENT_ALLOC_FAIL); return 0; } out_return: @@ -1398,16 +1398,16 @@ static int zcrx_flush_rq(struct io_ring_ctx *ctx, struct io_zcrx_ifq *zcrx, static int zcrx_arm_notif(struct io_ring_ctx *ctx, struct io_zcrx_ifq *zcrx, struct zcrx_ctrl *ctrl) { - const struct zcrx_ctrl_arm_notif *an = &ctrl->zc_arm_notif; + const struct zcrx_ctrl_arm_event *an = &ctrl->zc_arm_event; unsigned type_mask; - if (an->notif_type >= __ZCRX_NOTIF_TYPE_LAST) + if (an->event_type >= __ZCRX_EVENT_TYPE_LAST) return -EINVAL; if (!mem_is_zero(&an->__resv, sizeof(an->__resv))) return -EINVAL; guard(spinlock_bh)(&zcrx->ctx_lock); - type_mask = 1U << an->notif_type; + type_mask = 1U << an->event_type; if (type_mask & ~zcrx->fired_notifs) return -EINVAL; zcrx->fired_notifs &= ~type_mask; @@ -1420,7 +1420,7 @@ int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) struct io_zcrx_ifq *zcrx; BUILD_BUG_ON(sizeof(ctrl.zc_export) != sizeof(ctrl.zc_flush)); - BUILD_BUG_ON(sizeof(ctrl.zc_export) != sizeof(ctrl.zc_arm_notif)); + BUILD_BUG_ON(sizeof(ctrl.zc_export) != sizeof(ctrl.zc_arm_event)); if (nr_args) return -EINVAL; @@ -1438,7 +1438,7 @@ int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) return zcrx_flush_rq(ctx, zcrx, &ctrl); case ZCRX_CTRL_EXPORT: return zcrx_export(ctx, zcrx, &ctrl, arg); - case ZCRX_CTRL_ARM_NOTIFICATION: + case ZCRX_CTRL_ARM_EVENT: return zcrx_arm_notif(ctx, zcrx, &ctrl); } @@ -1584,7 +1584,7 @@ static int io_zcrx_copy_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq, zcrx_stat_add(&ifq->notif_stats->copy_count, 1); zcrx_stat_add(&ifq->notif_stats->copy_bytes, ret); } - zcrx_send_notif(ifq, ZCRX_NOTIF_COPY); + zcrx_send_notif(ifq, ZCRX_EVENT_COPY); } return ret; diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h index d16206eb9e30..c1005f23caff 100644 --- a/io_uring/zcrx.h +++ b/io_uring/zcrx.h @@ -10,8 +10,9 @@ #define ZCRX_SUPPORTED_REG_FLAGS (ZCRX_REG_IMPORT | ZCRX_REG_NODEV) #define ZCRX_FEATURES (ZCRX_FEATURE_RX_PAGE_SIZE |\ - ZCRX_FEATURE_NOTIFICATION) -#define ZCRX_NOTIF_TYPE_MASK ((1U << ZCRX_NOTIF_ALLOC_FAIL) | (1U << ZCRX_NOTIF_COPY)) + ZCRX_FEATURE_EVENT) +#define ZCRX_EVENT_TYPE_MASK ((1U << ZCRX_EVENT_ALLOC_FAIL) |\ + (1U << ZCRX_EVENT_COPY)) struct io_zcrx_mem { unsigned long size; -- cgit From cdcc4e46180df8161f4d2f3c6fd6beaf6990133d Mon Sep 17 00:00:00 2001 From: Yizhou Zhao Date: Fri, 31 Jul 2026 22:27:43 +0800 Subject: ipvs: separate destination availability state IPVS configuration paths update destination availability while connection accounting updates destination overload state. The two independent states share dest->flags, so their read-modify-write updates can race and lose one another. Keep OVERLOAD in flags, where the preceding patch serializes its updates with dst_lock, and move AVAILABLE to cflags. This keeps configuration- controlled availability out of the scheduler hot cacheline until a scheduler needs to check it. It also prevents availability updates from clobbering overload state. The destination status bits are not exposed through the IPVS sockopt or netlink interfaces, so keep their definitions in the internal IPVS header. Readers can still observe stale destination state; this does not provide a cross-field snapshot. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Reported-by: Yizhou Zhao Reported-by: Yuxiang Yang Reported-by: Ao Wang Reported-by: Xuewei Feng Reported-by: Qi Li Reported-by: Ke Xu Link: https://lore.kernel.org/all/8913381c-1e02-35c7-0ec4-61de5a12fd35@ssi.bg/ Assisted-by: Claude-Code:GLM-5.2 Suggested-by: Julian Anastasov Signed-off-by: Yizhou Zhao Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 7 +++++++ include/uapi/linux/ip_vs.h | 6 ------ net/netfilter/ipvs/ip_vs_conn.c | 4 ++-- net/netfilter/ipvs/ip_vs_core.c | 6 +++--- net/netfilter/ipvs/ip_vs_ctl.c | 4 ++-- net/netfilter/ipvs/ip_vs_dh.c | 4 ++-- net/netfilter/ipvs/ip_vs_lblc.c | 2 +- net/netfilter/ipvs/ip_vs_lblcr.c | 8 ++++---- net/netfilter/ipvs/ip_vs_xmit.c | 4 ++-- 9 files changed, 23 insertions(+), 22 deletions(-) (limited to 'include/uapi') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index e99382930617..fc2ef5ef31a6 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -36,6 +36,12 @@ #define IP_VS_HDR_INVERSE 1 #define IP_VS_HDR_ICMP 2 +/* Destination Server Flags */ +#define IP_VS_DEST_F_OVERLOAD 0x0002 /* server is overloaded */ + +/* Destination Server Config Flags */ +#define IP_VS_DEST_CF_AVAILABLE 0x0001 /* server is available */ + /* conn_tab limits (as per Kconfig) */ #define IP_VS_CONN_TAB_MIN_BITS 8 #if BITS_PER_LONG > 32 @@ -976,6 +982,7 @@ struct ip_vs_dest { volatile unsigned int flags; /* dest status flags */ atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ + unsigned long cflags; /* config flags */ atomic_t last_weight; /* server latest weight */ __u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index 1ed234e7f251..2c37c6ac7525 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -28,12 +28,6 @@ #define IP_VS_SVC_F_SCHED_SH_FALLBACK IP_VS_SVC_F_SCHED1 /* SH fallback */ #define IP_VS_SVC_F_SCHED_SH_PORT IP_VS_SVC_F_SCHED2 /* SH use port */ -/* - * Destination Server Flags - */ -#define IP_VS_DEST_F_AVAILABLE 0x0001 /* server is available */ -#define IP_VS_DEST_F_OVERLOAD 0x0002 /* server is overloaded */ - /* * IPVS sync daemon states */ diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index abf52a226fee..6fa3e1dc534c 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1279,7 +1279,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest) * Checking the dest server status. */ if ((dest == NULL) || - !(dest->flags & IP_VS_DEST_F_AVAILABLE) || + !(dest->cflags & IP_VS_DEST_CF_AVAILABLE) || expire_quiescent_template(ipvs, dest) || (cdest && (dest != cdest))) { IP_VS_DBG_BUF(9, "check_template: dest not available for " @@ -2020,7 +2020,7 @@ repeat: cp = ip_vs_hn0_to_conn(hn); resched_score++; dest = cp->dest; - if (!dest || (dest->flags & IP_VS_DEST_F_AVAILABLE)) + if (!dest || (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) continue; if (atomic_read(&cp->n_control)) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 0bdaeb4ed61e..95af77b68851 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -302,7 +302,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; - if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { + if (dest && (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; @@ -338,7 +338,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; - if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { + if (dest && (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; @@ -2210,7 +2210,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state } /* Check the server status */ - if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { + if (cp && cp->dest && !(cp->dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { /* the destination server is not available */ if (sysctl_expire_nodest_conn(ipvs)) { bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 974773642af8..8f9a8e491ad6 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1402,7 +1402,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, } /* set the dest status flags */ - dest->flags |= IP_VS_DEST_F_AVAILABLE; + dest->cflags |= IP_VS_DEST_CF_AVAILABLE; if (READ_ONCE(dest->u_threshold) != udest->u_threshold || READ_ONCE(dest->l_threshold) != udest->l_threshold) { @@ -1662,7 +1662,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, int svcupd) { - dest->flags &= ~IP_VS_DEST_F_AVAILABLE; + dest->cflags &= ~IP_VS_DEST_CF_AVAILABLE; spin_lock_bh(&dest->dst_lock); __ip_vs_dst_cache_reset(dest); diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index e1f62f6b25e2..43abed7a26a6 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -219,8 +219,8 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, s = (struct ip_vs_dh_state *) svc->sched_data; dest = ip_vs_dh_get(svc->af, s, &iph->daddr); - if (!dest - || !(dest->flags & IP_VS_DEST_F_AVAILABLE) + if (!dest || + !(dest->cflags & IP_VS_DEST_CF_AVAILABLE) || atomic_read(&dest->weight) <= 0 || is_overloaded(dest)) { ip_vs_scheduler_err(svc, "no destination available"); diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 15ccb2b2fa1f..693bcc82ccb7 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -502,7 +502,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, */ dest = en->dest; - if ((dest->flags & IP_VS_DEST_F_AVAILABLE) && + if ((dest->cflags & IP_VS_DEST_CF_AVAILABLE) && atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc)) goto out; } diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index c90ea897c3f7..f53f05ceea36 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -169,8 +169,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) if (least->flags & IP_VS_DEST_F_OVERLOAD) continue; - if ((atomic_read(&least->weight) > 0) - && (least->flags & IP_VS_DEST_F_AVAILABLE)) { + if ((atomic_read(&least->weight) > 0) && + (least->cflags & IP_VS_DEST_CF_AVAILABLE)) { loh = ip_vs_dest_conn_overhead(least); goto nextstage; } @@ -186,8 +186,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) doh = ip_vs_dest_conn_overhead(dest); if (((__s64)loh * atomic_read(&dest->weight) > - (__s64)doh * atomic_read(&least->weight)) - && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { + (__s64)doh * atomic_read(&least->weight)) && + (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index c4508f3f43dd..fc7403186394 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -351,7 +351,7 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, * stored in dest_trash. */ if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)) && - dest->flags & IP_VS_DEST_F_AVAILABLE) + dest->cflags & IP_VS_DEST_CF_AVAILABLE) __ip_vs_dst_set(dest, dest_dst, &rt->dst, 0); else noref = 0; @@ -530,7 +530,7 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, * stored in dest_trash. */ if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)) && - dest->flags & IP_VS_DEST_F_AVAILABLE) + dest->cflags & IP_VS_DEST_CF_AVAILABLE) __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie); else noref = 0; -- cgit