From 94623f579ce338b5fa61b5acaa5beb8aa657fb9e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 3 Apr 2023 13:54:37 +0200 Subject: netfilter: br_netfilter: fix recent physdev match breakage Recent attempt to ensure PREROUTING hook is executed again when a decrypted ipsec packet received on a bridge passes through the network stack a second time broke the physdev match in INPUT hook. We can't discard the nf_bridge info strct from sabotage_in hook, as this is needed by the physdev match. Keep the struct around and handle this with another conditional instead. Fixes: 2b272bb558f1 ("netfilter: br_netfilter: disable sabotage_in hook after first suppression") Reported-and-tested-by: Farid BENAMROUCHE Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ff7ad331fb82..1ec3530c8191 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -294,6 +294,7 @@ struct nf_bridge_info { u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; + u8 sabotage_in_done:1; __u16 frag_max_size; struct net_device *physindev; -- cgit v1.3.1 From c55c0e91c813589dc55bea6bf9a9fbfaa10ae41d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 17 Apr 2023 10:21:36 +0200 Subject: netfilter: nf_tables: fix ifdef to also consider nf_tables=m nftables can be built as a module, so fix the preprocessor conditional accordingly. Fixes: 478b360a47b7 ("netfilter: nf_tables: fix nf_trace always-on with XT_TRACE=n") Reported-by: Florian Fainelli Reported-by: Jakub Kicinski Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1ec3530c8191..dbcaac8b6966 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4713,7 +4713,7 @@ static inline void nf_reset_ct(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -4733,7 +4733,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif -- cgit v1.3.1 From 47ebd0310e89c087f56e58c103c44b72a2f6b216 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 13 Apr 2023 15:12:20 +0200 Subject: mm: kmsan: handle alloc failures in kmsan_vmap_pages_range_noflush() As reported by Dipanjan Das, when KMSAN is used together with kernel fault injection (or, generally, even without the latter), calls to kcalloc() or __vmap_pages_range_noflush() may fail, leaving the metadata mappings for the virtual mapping in an inconsistent state. When these metadata mappings are accessed later, the kernel crashes. To address the problem, we return a non-zero error code from kmsan_vmap_pages_range_noflush() in the case of any allocation/mapping failure inside it, and make vmap_pages_range_noflush() return an error if KMSAN fails to allocate the metadata. This patch also removes KMSAN_WARN_ON() from vmap_pages_range_noflush(), as these allocation failures are not fatal anymore. Link: https://lkml.kernel.org/r/20230413131223.4135168-1-glider@google.com Fixes: b073d7f8aee4 ("mm: kmsan: maintain KMSAN metadata for page operations") Signed-off-by: Alexander Potapenko Reported-by: Dipanjan Das Link: https://lore.kernel.org/linux-mm/CANX2M5ZRrRA64k0hOif02TjmY9kbbO2aCBPyq79es34RXZ=cAw@mail.gmail.com/ Reviewed-by: Marco Elver Cc: Christoph Hellwig Cc: Dmitry Vyukov Cc: Uladzislau Rezki (Sony) Cc: Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 20 +++++++++++--------- mm/kmsan/shadow.c | 27 ++++++++++++++++++--------- mm/vmalloc.c | 6 +++++- 3 files changed, 34 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index e38ae3c34618..c7ff3aefc5a1 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -134,11 +134,12 @@ void kmsan_kfree_large(const void *ptr); * @page_shift: page_shift passed to vmap_range_noflush(). * * KMSAN maps shadow and origin pages of @pages into contiguous ranges in - * vmalloc metadata address range. + * vmalloc metadata address range. Returns 0 on success, callers must check + * for non-zero return value. */ -void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift); +int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages, + unsigned int page_shift); /** * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. @@ -281,12 +282,13 @@ static inline void kmsan_kfree_large(const void *ptr) { } -static inline void kmsan_vmap_pages_range_noflush(unsigned long start, - unsigned long end, - pgprot_t prot, - struct page **pages, - unsigned int page_shift) +static inline int kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift) { + return 0; } static inline void kmsan_vunmap_range_noflush(unsigned long start, diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c index a787c04e9583..b8bb95eea5e3 100644 --- a/mm/kmsan/shadow.c +++ b/mm/kmsan/shadow.c @@ -216,27 +216,29 @@ void kmsan_free_page(struct page *page, unsigned int order) kmsan_leave_runtime(); } -void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift) +int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages, + unsigned int page_shift) { unsigned long shadow_start, origin_start, shadow_end, origin_end; struct page **s_pages, **o_pages; - int nr, mapped; + int nr, mapped, err = 0; if (!kmsan_enabled) - return; + return 0; shadow_start = vmalloc_meta((void *)start, KMSAN_META_SHADOW); shadow_end = vmalloc_meta((void *)end, KMSAN_META_SHADOW); if (!shadow_start) - return; + return 0; nr = (end - start) / PAGE_SIZE; s_pages = kcalloc(nr, sizeof(*s_pages), GFP_KERNEL); o_pages = kcalloc(nr, sizeof(*o_pages), GFP_KERNEL); - if (!s_pages || !o_pages) + if (!s_pages || !o_pages) { + err = -ENOMEM; goto ret; + } for (int i = 0; i < nr; i++) { s_pages[i] = shadow_page_for(pages[i]); o_pages[i] = origin_page_for(pages[i]); @@ -249,10 +251,16 @@ void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, kmsan_enter_runtime(); mapped = __vmap_pages_range_noflush(shadow_start, shadow_end, prot, s_pages, page_shift); - KMSAN_WARN_ON(mapped); + if (mapped) { + err = mapped; + goto ret; + } mapped = __vmap_pages_range_noflush(origin_start, origin_end, prot, o_pages, page_shift); - KMSAN_WARN_ON(mapped); + if (mapped) { + err = mapped; + goto ret; + } kmsan_leave_runtime(); flush_tlb_kernel_range(shadow_start, shadow_end); flush_tlb_kernel_range(origin_start, origin_end); @@ -262,6 +270,7 @@ void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, ret: kfree(s_pages); kfree(o_pages); + return err; } /* Allocate metadata for pages allocated at boot time. */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a50072066221..1355d95cce1c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -605,7 +605,11 @@ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { - kmsan_vmap_pages_range_noflush(addr, end, prot, pages, page_shift); + int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages, + page_shift); + + if (ret) + return ret; return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift); } -- cgit v1.3.1 From fdea03e12aa2a44a7bb34144208be97fc25dfd90 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 13 Apr 2023 15:12:21 +0200 Subject: mm: kmsan: handle alloc failures in kmsan_ioremap_page_range() Similarly to kmsan_vmap_pages_range_noflush(), kmsan_ioremap_page_range() must also properly handle allocation/mapping failures. In the case of such, it must clean up the already created metadata mappings and return an error code, so that the error can be propagated to ioremap_page_range(). Without doing so, KMSAN may silently fail to bring the metadata for the page range into a consistent state, which will result in user-visible crashes when trying to access them. Link: https://lkml.kernel.org/r/20230413131223.4135168-2-glider@google.com Fixes: b073d7f8aee4 ("mm: kmsan: maintain KMSAN metadata for page operations") Signed-off-by: Alexander Potapenko Reported-by: Dipanjan Das Link: https://lore.kernel.org/linux-mm/CANX2M5ZRrRA64k0hOif02TjmY9kbbO2aCBPyq79es34RXZ=cAw@mail.gmail.com/ Reviewed-by: Marco Elver Cc: Christoph Hellwig Cc: Dmitry Vyukov Cc: Uladzislau Rezki (Sony) Cc: Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 19 +++++++++--------- mm/kmsan/hooks.c | 55 +++++++++++++++++++++++++++++++++++++++++++-------- mm/vmalloc.c | 4 ++-- 3 files changed, 59 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index c7ff3aefc5a1..30b17647ce3c 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -160,11 +160,12 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); * @page_shift: page_shift argument passed to vmap_range_noflush(). * * KMSAN creates new metadata pages for the physical pages mapped into the - * virtual memory. + * virtual memory. Returns 0 on success, callers must check for non-zero return + * value. */ -void kmsan_ioremap_page_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift); +int kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); /** * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. @@ -296,12 +297,12 @@ static inline void kmsan_vunmap_range_noflush(unsigned long start, { } -static inline void kmsan_ioremap_page_range(unsigned long start, - unsigned long end, - phys_addr_t phys_addr, - pgprot_t prot, - unsigned int page_shift) +static inline int kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift) { + return 0; } static inline void kmsan_iounmap_page_range(unsigned long start, diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c index 3807502766a3..ec0da72e65aa 100644 --- a/mm/kmsan/hooks.c +++ b/mm/kmsan/hooks.c @@ -148,35 +148,74 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end) * into the virtual memory. If those physical pages already had shadow/origin, * those are ignored. */ -void kmsan_ioremap_page_range(unsigned long start, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift) +int kmsan_ioremap_page_range(unsigned long start, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift) { gfp_t gfp_mask = GFP_KERNEL | __GFP_ZERO; struct page *shadow, *origin; unsigned long off = 0; - int nr; + int nr, err = 0, clean = 0, mapped; if (!kmsan_enabled || kmsan_in_runtime()) - return; + return 0; nr = (end - start) / PAGE_SIZE; kmsan_enter_runtime(); - for (int i = 0; i < nr; i++, off += PAGE_SIZE) { + for (int i = 0; i < nr; i++, off += PAGE_SIZE, clean = i) { shadow = alloc_pages(gfp_mask, 1); origin = alloc_pages(gfp_mask, 1); - __vmap_pages_range_noflush( + if (!shadow || !origin) { + err = -ENOMEM; + goto ret; + } + mapped = __vmap_pages_range_noflush( vmalloc_shadow(start + off), vmalloc_shadow(start + off + PAGE_SIZE), prot, &shadow, PAGE_SHIFT); - __vmap_pages_range_noflush( + if (mapped) { + err = mapped; + goto ret; + } + shadow = NULL; + mapped = __vmap_pages_range_noflush( vmalloc_origin(start + off), vmalloc_origin(start + off + PAGE_SIZE), prot, &origin, PAGE_SHIFT); + if (mapped) { + __vunmap_range_noflush( + vmalloc_shadow(start + off), + vmalloc_shadow(start + off + PAGE_SIZE)); + err = mapped; + goto ret; + } + origin = NULL; + } + /* Page mapping loop finished normally, nothing to clean up. */ + clean = 0; + +ret: + if (clean > 0) { + /* + * Something went wrong. Clean up shadow/origin pages allocated + * on the last loop iteration, then delete mappings created + * during the previous iterations. + */ + if (shadow) + __free_pages(shadow, 1); + if (origin) + __free_pages(origin, 1); + __vunmap_range_noflush( + vmalloc_shadow(start), + vmalloc_shadow(start + clean * PAGE_SIZE)); + __vunmap_range_noflush( + vmalloc_origin(start), + vmalloc_origin(start + clean * PAGE_SIZE)); } flush_cache_vmap(vmalloc_shadow(start), vmalloc_shadow(end)); flush_cache_vmap(vmalloc_origin(start), vmalloc_origin(end)); kmsan_leave_runtime(); + return err; } void kmsan_iounmap_page_range(unsigned long start, unsigned long end) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 1355d95cce1c..31ff782d368b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -313,8 +313,8 @@ int ioremap_page_range(unsigned long addr, unsigned long end, ioremap_max_page_shift); flush_cache_vmap(addr, end); if (!err) - kmsan_ioremap_page_range(addr, end, phys_addr, prot, - ioremap_max_page_shift); + err = kmsan_ioremap_page_range(addr, end, phys_addr, prot, + ioremap_max_page_shift); return err; } -- cgit v1.3.1 From f52cc627b832e08a7bcf1b7e81e650ec308fe1d8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 13 Apr 2023 15:25:47 -0700 Subject: Revert "net/mlx5: Enable management PF initialization" This reverts commit fe998a3c77b9f989a30a2a01fb00d3729a6d53a4. Paul reports that it causes a regression with IB on CX4 and FW 12.18.1000. In addition I think that the concept of "management PF" is not fully accepted and requires a discussion. Fixes: fe998a3c77b9 ("net/mlx5: Enable management PF initialization") Reported-by: Paul Moore Link: https://lore.kernel.org/all/CAHC9VhQ7A4+msL38WpbOMYjAqLp0EtOjeLh4Dc6SQtD6OUvCQg@mail.gmail.com/ Link: https://lore.kernel.org/r/20230413222547.56901-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/dev.c | 6 ------ drivers/net/ethernet/mellanox/mlx5/core/ecpf.c | 8 -------- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- include/linux/mlx5/driver.h | 5 ----- 4 files changed, 1 insertion(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 445fe30c3d0b..2e7806001fdc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -59,9 +59,6 @@ bool mlx5_eth_supported(struct mlx5_core_dev *dev) if (!IS_ENABLED(CONFIG_MLX5_CORE_EN)) return false; - if (mlx5_core_is_management_pf(dev)) - return false; - if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) return false; @@ -201,9 +198,6 @@ bool mlx5_rdma_supported(struct mlx5_core_dev *dev) if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return false; - if (mlx5_core_is_management_pf(dev)) - return false; - if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 7c9c4e40c019..d000236ddbac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -75,10 +75,6 @@ int mlx5_ec_init(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return 0; - /* Management PF don't have a peer PF */ - if (mlx5_core_is_management_pf(dev)) - return 0; - return mlx5_host_pf_init(dev); } @@ -89,10 +85,6 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return; - /* Management PF don't have a peer PF */ - if (mlx5_core_is_management_pf(dev)) - return; - mlx5_host_pf_cleanup(dev); err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 8bdf28762f41..19fed514fc17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1488,7 +1488,7 @@ int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 * void *hca_caps; int err; - if (!mlx5_core_is_ecpf(dev) || mlx5_core_is_management_pf(dev)) { + if (!mlx5_core_is_ecpf(dev)) { *max_sfs = 0; return 0; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f33389b42209..7e225e41d55b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1211,11 +1211,6 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } -static inline bool mlx5_core_is_management_pf(const struct mlx5_core_dev *dev) -{ - return MLX5_CAP_GEN(dev, num_ports) == 1 && !MLX5_CAP_GEN(dev, native_port_num); -} - static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; -- cgit v1.3.1