From 23a55f4492fcf868d068da31a2cd30c15f46207d Mon Sep 17 00:00:00 2001 From: Ofir Gal Date: Thu, 18 Jul 2024 11:45:12 +0300 Subject: net: introduce helper sendpages_ok() Network drivers are using sendpage_ok() to check the first page of an iterator in order to disable MSG_SPLICE_PAGES. The iterator can represent list of contiguous pages. When MSG_SPLICE_PAGES is enabled skb_splice_from_iter() is being used, it requires all pages in the iterator to be sendable. Therefore it needs to check that each page is sendable. The patch introduces a helper sendpages_ok(), it returns true if all the contiguous pages are sendable. Drivers who want to send contiguous pages with MSG_SPLICE_PAGES may use this helper to check whether the page list is OK. If the helper does not return true, the driver should remove MSG_SPLICE_PAGES flag. Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Ofir Gal Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20240718084515.3833733-2-ofir.gal@volumez.com Signed-off-by: Jens Axboe --- include/linux/net.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 688320b79fcc..b75bc534c1b3 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -322,6 +322,25 @@ static inline bool sendpage_ok(struct page *page) return !PageSlab(page) && page_count(page) >= 1; } +/* + * Check sendpage_ok on contiguous pages. + */ +static inline bool sendpages_ok(struct page *page, size_t len, size_t offset) +{ + struct page *p = page + (offset >> PAGE_SHIFT); + size_t count = 0; + + while (count < len) { + if (!sendpage_ok(p)) + return false; + + p++; + count += PAGE_SIZE; + } + + return true; +} + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, -- cgit v1.2.3 From 5bc46b49c828a6dfaab80b71ecb63fe76a1096d2 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 22 Jul 2024 14:02:20 +0200 Subject: nvme-tcp: check for invalidated or revoked key key_lookup() will always return a key, even if that key is revoked or invalidated. So check for invalid keys before continuing. Signed-off-by: Hannes Reinecke Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- include/linux/nvme-keyring.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme-keyring.h b/include/linux/nvme-keyring.h index e10333d78dbb..19d2b256180f 100644 --- a/include/linux/nvme-keyring.h +++ b/include/linux/nvme-keyring.h @@ -12,7 +12,7 @@ key_serial_t nvme_tls_psk_default(struct key *keyring, const char *hostnqn, const char *subnqn); key_serial_t nvme_keyring_id(void); - +struct key *nvme_tls_key_lookup(key_serial_t key_id); #else static inline key_serial_t nvme_tls_psk_default(struct key *keyring, @@ -24,5 +24,9 @@ static inline key_serial_t nvme_keyring_id(void) { return 0; } +static inline struct key *nvme_tls_key_lookup(key_serial_t key_id) +{ + return ERR_PTR(-ENOTSUPP); +} #endif /* !CONFIG_NVME_KEYRING */ #endif /* _NVME_KEYRING_H */ -- cgit v1.2.3 From 03c3d7c74371a46d967fbf41628874ec04ddda96 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 15 Aug 2024 22:11:31 +0200 Subject: nvme-rdma: send cntlid in the RDMA_CM_REQUEST Private Data When sending a RDMA_CM_REQUEST, the NVMe RDMA Transport Specification allows you to populate the cntlid field in the RDMA_CM_REQUEST Private Data. The cntlid is returned by the target on completion of the first RDMA_CM_REQUEST command (which creates the admin queue). The cntlid field can then be populated by the host when the I/O queues are created (using additional RDMA_CM_REQUEST commands), such that the target can perform extra validation for additional RDMA_CM_REQUEST commands. This additional error code and error message is also added, such that nvme_rdma_cm_msg() will display the proper error message if the target fails the RDMA_CM_REQUEST command because of this extra validation. Signed-off-by: Niklas Cassel Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- include/linux/nvme-rdma.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h index eb2f04d636c8..97c5f00b9aa3 100644 --- a/include/linux/nvme-rdma.h +++ b/include/linux/nvme-rdma.h @@ -25,6 +25,7 @@ enum nvme_rdma_cm_status { NVME_RDMA_CM_NO_RSC = 0x06, NVME_RDMA_CM_INVALID_IRD = 0x07, NVME_RDMA_CM_INVALID_ORD = 0x08, + NVME_RDMA_CM_INVALID_CNTLID = 0x09, }; static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status) @@ -46,6 +47,8 @@ static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status) return "invalid IRD"; case NVME_RDMA_CM_INVALID_ORD: return "Invalid ORD"; + case NVME_RDMA_CM_INVALID_CNTLID: + return "invalid controller ID"; default: return "unrecognized reason"; } @@ -64,7 +67,8 @@ struct nvme_rdma_cm_req { __le16 qid; __le16 hrqsize; __le16 hsqsize; - u8 rsvd[24]; + __le16 cntlid; + u8 rsvd[22]; }; /** -- cgit v1.2.3 From cead0b8991713bdeb5b947758dd62287fcf8da40 Mon Sep 17 00:00:00 2001 From: Anuj Gupta Date: Mon, 26 Aug 2024 16:09:43 +0530 Subject: nvme: rename apptag and appmask to lbat and lbatm Rename apptag and appmask to lbat and lbatm so that it matches the field names used in NVMe spec. Signed-off-by: Anuj Gupta Signed-off-by: Kanchan Joshi Suggested-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch --- include/linux/nvme.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 7b2ae2e43544..b58d9405d65e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -987,8 +987,8 @@ struct nvme_rw_command { __le16 control; __le32 dsmgmt; __le32 reftag; - __le16 apptag; - __le16 appmask; + __le16 lbat; + __le16 lbatm; }; enum { @@ -1057,8 +1057,8 @@ struct nvme_write_zeroes_cmd { __le16 control; __le32 dsmgmt; __le32 reftag; - __le16 apptag; - __le16 appmask; + __le16 lbat; + __le16 lbatm; }; enum nvme_zone_mgmt_action { -- cgit v1.2.3 From b35243a447b9fe6457fa8e1352152b818436ba5a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 26 Aug 2024 19:37:54 +0200 Subject: block: rework bio splitting The current setup with bio_may_exceed_limit and __bio_split_to_limits is a bit of a mess. Change it so that __bio_split_to_limits does all the work and is just a variant of bio_split_to_limits that returns nr_segs. This is done by inlining it and instead have the various bio_split_* helpers directly submit the potentially split bios. To support btrfs, the rw version has a lower level helper split out that just returns the offset to split. This turns out to nicely clean up the btrfs flow as well. Signed-off-by: Christoph Hellwig Acked-by: David Sterba Reviewed-by: Damien Le Moal Tested-by: Hans Holmberg Reviewed-by: Hans Holmberg Link: https://lore.kernel.org/r/20240826173820.1690925-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index a46e2047bea4..faceadb040f9 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -324,8 +324,8 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) void bio_trim(struct bio *bio, sector_t offset, sector_t size); extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); -struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, - unsigned *segs, struct bio_set *bs, unsigned max_bytes); +int bio_split_rw_at(struct bio *bio, const struct queue_limits *lim, + unsigned *segs, unsigned max_bytes); /** * bio_next_split - get next @sectors from a bio, splitting if necessary -- cgit v1.2.3 From 379b122a3ec8033aa43cb70e8ecb6fb7f98aa68f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 26 Aug 2024 19:37:55 +0200 Subject: block: constify the lim argument to queue_limits_max_zone_append_sectors queue_limits_max_zone_append_sectors doesn't change the lim argument, so mark it as const. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Tested-by: Hans Holmberg Reviewed-by: Hans Holmberg Link: https://lore.kernel.org/r/20240826173820.1690925-3-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e85ec73a07d5..ec3ea5d1f99d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1187,7 +1187,8 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l) +static inline unsigned int +queue_limits_max_zone_append_sectors(const struct queue_limits *l) { unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors); -- cgit v1.2.3 From d3bfbfb1248498656cd25c51e41c1e31219bd0dd Mon Sep 17 00:00:00 2001 From: Kundan Kumar Date: Wed, 11 Sep 2024 12:19:34 +0530 Subject: mm: release number of pages of a folio Add a new function unpin_user_folio() to put the refs of a folio by npages count. The check for BIO_PAGE_PINNED flag is removed as it is already checked in bio_release_pages(). Signed-off-by: Kundan Kumar Tested-by: Luis Chamberlain Reviewed-by: Matthew Wilcox (Oracle) Link: https://lore.kernel.org/r/20240911064935.5630-4-kundan.kumar@samsung.com Signed-off-by: Jens Axboe --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..2fd88cd5997d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1597,6 +1597,7 @@ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); +void unpin_user_folio(struct folio *folio, unsigned long npages); void unpin_folios(struct folio **folios, unsigned long nfolios); static inline bool is_cow_mapping(vm_flags_t flags) -- cgit v1.2.3