From 3152a974678a1e80c3c16d4b86522ecc500be529 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:05 -0800 Subject: [PATCH 01/33] ath6kl: add ath6kl_ prefix to crypto_type Prevent a namespace conflict as in following patches as skbuff.h will include the crypto API. Acked-by: David S. Miller Cc: Kalle Valo Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/net/wireless/ath/ath6kl/cfg80211.c | 2 +- drivers/net/wireless/ath/ath6kl/common.h | 2 +- drivers/net/wireless/ath/ath6kl/wmi.c | 6 +++--- drivers/net/wireless/ath/ath6kl/wmi.h | 6 +++--- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index e121187f371f..fa049c4ae315 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -1322,7 +1322,7 @@ static int ath6kl_cfg80211_set_default_key(struct wiphy *wiphy, struct ath6kl_vif *vif = netdev_priv(ndev); struct ath6kl_key *key = NULL; u8 key_usage; - enum crypto_type key_type = NONE_CRYPT; + enum ath6kl_crypto_type key_type = NONE_CRYPT; ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: index %d\n", __func__, key_index); diff --git a/drivers/net/wireless/ath/ath6kl/common.h b/drivers/net/wireless/ath/ath6kl/common.h index 4f82e8632d37..d6e5234f67a1 100644 --- a/drivers/net/wireless/ath/ath6kl/common.h +++ b/drivers/net/wireless/ath/ath6kl/common.h @@ -67,7 +67,7 @@ struct ath6kl_llc_snap_hdr { __be16 eth_type; } __packed; -enum crypto_type { +enum ath6kl_crypto_type { NONE_CRYPT = 0x01, WEP_CRYPT = 0x02, TKIP_CRYPT = 0x04, diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c index 777acc564ac9..9d7ac1ab2d02 100644 --- a/drivers/net/wireless/ath/ath6kl/wmi.c +++ b/drivers/net/wireless/ath/ath6kl/wmi.c @@ -1849,9 +1849,9 @@ int ath6kl_wmi_connect_cmd(struct wmi *wmi, u8 if_idx, enum network_type nw_type, enum dot11_auth_mode dot11_auth_mode, enum auth_mode auth_mode, - enum crypto_type pairwise_crypto, + enum ath6kl_crypto_type pairwise_crypto, u8 pairwise_crypto_len, - enum crypto_type group_crypto, + enum ath6kl_crypto_type group_crypto, u8 group_crypto_len, int ssid_len, u8 *ssid, u8 *bssid, u16 channel, u32 ctrl_flags, u8 nw_subtype) @@ -2301,7 +2301,7 @@ int ath6kl_wmi_disctimeout_cmd(struct wmi *wmi, u8 if_idx, u8 timeout) } int ath6kl_wmi_addkey_cmd(struct wmi *wmi, u8 if_idx, u8 key_index, - enum crypto_type key_type, + enum ath6kl_crypto_type key_type, u8 key_usage, u8 key_len, u8 *key_rsc, unsigned int key_rsc_len, u8 *key_material, diff --git a/drivers/net/wireless/ath/ath6kl/wmi.h b/drivers/net/wireless/ath/ath6kl/wmi.h index a60bb49fe920..784940ba4c90 100644 --- a/drivers/net/wireless/ath/ath6kl/wmi.h +++ b/drivers/net/wireless/ath/ath6kl/wmi.h @@ -2556,9 +2556,9 @@ int ath6kl_wmi_connect_cmd(struct wmi *wmi, u8 if_idx, enum network_type nw_type, enum dot11_auth_mode dot11_auth_mode, enum auth_mode auth_mode, - enum crypto_type pairwise_crypto, + enum ath6kl_crypto_type pairwise_crypto, u8 pairwise_crypto_len, - enum crypto_type group_crypto, + enum ath6kl_crypto_type group_crypto, u8 group_crypto_len, int ssid_len, u8 *ssid, u8 *bssid, u16 channel, u32 ctrl_flags, u8 nw_subtype); @@ -2610,7 +2610,7 @@ int ath6kl_wmi_config_debug_module_cmd(struct wmi *wmi, u32 valid, u32 config); int ath6kl_wmi_get_stats_cmd(struct wmi *wmi, u8 if_idx); int ath6kl_wmi_addkey_cmd(struct wmi *wmi, u8 if_idx, u8 key_index, - enum crypto_type key_type, + enum ath6kl_crypto_type key_type, u8 key_usage, u8 key_len, u8 *key_rsc, unsigned int key_rsc_len, u8 *key_material, From 0fc07791bc775478d9450ca9c6c674b45f6c1998 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:06 -0800 Subject: [PATCH 02/33] datagram: open-code copy_page_to_iter This will be useful to consolidate skb_copy_and_hash_datagram_iter and skb_copy_and_csum_datagram to a single code path. Acked-by: David S. Miller Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- net/core/datagram.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/core/datagram.c b/net/core/datagram.c index 57f3a6fcfc1e..abe642181b64 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -445,11 +445,14 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset, end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { + struct page *page = skb_frag_page(frag); + u8 *vaddr = kmap(page); + if (copy > len) copy = len; - n = copy_page_to_iter(skb_frag_page(frag), - frag->page_offset + offset - - start, copy, to); + n = copy_to_iter(vaddr + frag->page_offset + + offset - start, copy, to); + kunmap(page); offset += n; if (n != copy) goto short_copy; From cb002d074dabfaa2248507fd9478d16a542e4f1e Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:07 -0800 Subject: [PATCH 03/33] iov_iter: pass void csum pointer to csum_and_copy_to_iter The single caller to csum_and_copy_to_iter is skb_copy_and_csum_datagram and we are trying to unite its logic with skb_copy_datagram_iter by passing a callback to the copy function that we want to apply. Thus, we need to make the checksum pointer private to the function. Acked-by: David S. Miller Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/uio.h | 2 +- lib/iov_iter.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/uio.h b/include/linux/uio.h index 55ce99ddb912..41d1f8d3313d 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -266,7 +266,7 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } -size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); +size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 54c248526b55..63a8999a234d 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1464,10 +1464,11 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, } EXPORT_SYMBOL(csum_and_copy_from_iter_full); -size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, +size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump, struct iov_iter *i) { const char *from = addr; + __wsum *csum = csump; __wsum sum, next; size_t off = 0; From 950fcaecd5cc6c014bb96506fd0652a501c85276 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:08 -0800 Subject: [PATCH 04/33] datagram: consolidate datagram copy to iter helpers skb_copy_datagram_iter and skb_copy_and_csum_datagram are essentialy the same but with a couple of differences: The first is the copy operation used which either a simple copy or a csum_and_copy, and the second are the behavior on the "short copy" path where simply copy needs to return the number of bytes successfully copied while csum_and_copy needs to fault immediately as the checksum is partial. Introduce __skb_datagram_iter that additionally accepts: 1. copy operation function pointer 2. private data that goes with the copy operation 3. fault_short flag to indicate the action on short copy Suggested-by: David S. Miller Acked-by: David S. Miller Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- net/core/datagram.c | 136 ++++++++++++++------------------------------ 1 file changed, 42 insertions(+), 94 deletions(-) diff --git a/net/core/datagram.c b/net/core/datagram.c index abe642181b64..382543302ae5 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -408,27 +408,20 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) } EXPORT_SYMBOL(skb_kill_datagram); -/** - * skb_copy_datagram_iter - Copy a datagram to an iovec iterator. - * @skb: buffer to copy - * @offset: offset in the buffer to start copying from - * @to: iovec iterator to copy to - * @len: amount of data to copy from buffer to iovec - */ -int skb_copy_datagram_iter(const struct sk_buff *skb, int offset, - struct iov_iter *to, int len) +int __skb_datagram_iter(const struct sk_buff *skb, int offset, + struct iov_iter *to, int len, bool fault_short, + size_t (*cb)(const void *, size_t, void *, struct iov_iter *), + void *data) { int start = skb_headlen(skb); int i, copy = start - offset, start_off = offset, n; struct sk_buff *frag_iter; - trace_skb_copy_datagram_iovec(skb, len); - /* Copy header. */ if (copy > 0) { if (copy > len) copy = len; - n = copy_to_iter(skb->data + offset, copy, to); + n = cb(skb->data + offset, copy, data, to); offset += n; if (n != copy) goto short_copy; @@ -450,8 +443,8 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset, if (copy > len) copy = len; - n = copy_to_iter(vaddr + frag->page_offset + - offset - start, copy, to); + n = cb(vaddr + frag->page_offset + + offset - start, copy, data, to); kunmap(page); offset += n; if (n != copy) @@ -471,8 +464,8 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset, if ((copy = end - offset) > 0) { if (copy > len) copy = len; - if (skb_copy_datagram_iter(frag_iter, offset - start, - to, copy)) + if (__skb_datagram_iter(frag_iter, offset - start, + to, copy, short_copy, cb, data)) goto fault; if ((len -= copy) == 0) return 0; @@ -493,11 +486,32 @@ fault: return -EFAULT; short_copy: - if (iov_iter_count(to)) + if (fault_short || iov_iter_count(to)) goto fault; return 0; } + +static size_t simple_copy_to_iter(const void *addr, size_t bytes, + void *data __always_unused, struct iov_iter *i) +{ + return copy_to_iter(addr, bytes, i); +} + +/** + * skb_copy_datagram_iter - Copy a datagram to an iovec iterator. + * @skb: buffer to copy + * @offset: offset in the buffer to start copying from + * @to: iovec iterator to copy to + * @len: amount of data to copy from buffer to iovec + */ +int skb_copy_datagram_iter(const struct sk_buff *skb, int offset, + struct iov_iter *to, int len) +{ + trace_skb_copy_datagram_iovec(skb, len); + return __skb_datagram_iter(skb, offset, to, len, false, + simple_copy_to_iter, NULL); +} EXPORT_SYMBOL(skb_copy_datagram_iter); /** @@ -648,87 +662,21 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) } EXPORT_SYMBOL(zerocopy_sg_from_iter); +/** + * skb_copy_and_csum_datagram_iter - Copy datagram to an iovec iterator + * and update a checksum. + * @skb: buffer to copy + * @offset: offset in the buffer to start copying from + * @to: iovec iterator to copy to + * @len: amount of data to copy from buffer to iovec + * @csump: checksum pointer + */ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, __wsum *csump) { - int start = skb_headlen(skb); - int i, copy = start - offset, start_off = offset; - struct sk_buff *frag_iter; - int pos = 0; - int n; - - /* Copy header. */ - if (copy > 0) { - if (copy > len) - copy = len; - n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to); - offset += n; - if (n != copy) - goto fault; - if ((len -= copy) == 0) - return 0; - pos = copy; - } - - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - int end; - const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - - WARN_ON(start > offset + len); - - end = start + skb_frag_size(frag); - if ((copy = end - offset) > 0) { - __wsum csum2 = 0; - struct page *page = skb_frag_page(frag); - u8 *vaddr = kmap(page); - - if (copy > len) - copy = len; - n = csum_and_copy_to_iter(vaddr + frag->page_offset + - offset - start, copy, - &csum2, to); - kunmap(page); - offset += n; - if (n != copy) - goto fault; - *csump = csum_block_add(*csump, csum2, pos); - if (!(len -= copy)) - return 0; - pos += copy; - } - start = end; - } - - skb_walk_frags(skb, frag_iter) { - int end; - - WARN_ON(start > offset + len); - - end = start + frag_iter->len; - if ((copy = end - offset) > 0) { - __wsum csum2 = 0; - if (copy > len) - copy = len; - if (skb_copy_and_csum_datagram(frag_iter, - offset - start, - to, copy, - &csum2)) - goto fault; - *csump = csum_block_add(*csump, csum2, pos); - if ((len -= copy) == 0) - return 0; - offset += copy; - pos += copy; - } - start = end; - } - if (!len) - return 0; - -fault: - iov_iter_revert(to, offset - start_off); - return -EFAULT; + return __skb_datagram_iter(skb, offset, to, len, true, + csum_and_copy_to_iter, csump); } __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) From d05f443554b3c7dc6d46e3ba9c3c4de468875d4f Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:09 -0800 Subject: [PATCH 05/33] iov_iter: introduce hash_and_copy_to_iter helper Allow consumers that want to use iov iterator helpers and also update a predefined hash calculation online when copying data. This is useful when copying incoming network buffers to a local iterator and calculate a digest on the incoming stream. nvme-tcp host driver that will be introduced in following patches is the first consumer via skb_copy_and_hash_datagram_iter. Acked-by: David S. Miller Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/uio.h | 3 +++ lib/iov_iter.c | 16 ++++++++++++++++ 2 files changed, 19 insertions(+) diff --git a/include/linux/uio.h b/include/linux/uio.h index 41d1f8d3313d..ecf584f6b82d 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -11,6 +11,7 @@ #include #include +#include #include struct page; @@ -269,6 +270,8 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); +size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, + struct iov_iter *i); int import_iovec(int type, const struct iovec __user * uvector, unsigned nr_segs, unsigned fast_segs, diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 63a8999a234d..1928009f506e 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -6,6 +6,7 @@ #include #include #include +#include #define PIPE_PARANOIA /* for now */ @@ -1511,6 +1512,21 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump, } EXPORT_SYMBOL(csum_and_copy_to_iter); +size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, + struct iov_iter *i) +{ + struct ahash_request *hash = hashp; + struct scatterlist sg; + size_t copied; + + copied = copy_to_iter(addr, bytes, i); + sg_init_one(&sg, addr, copied); + ahash_request_set_crypt(hash, &sg, NULL, copied); + crypto_ahash_update(hash); + return copied; +} +EXPORT_SYMBOL(hash_and_copy_to_iter); + int iov_iter_npages(const struct iov_iter *i, int maxpages) { size_t size = i->count; From 65d69e2505bb64f6a8d7f417f6e46e2a351174c6 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:10 -0800 Subject: [PATCH 06/33] datagram: introduce skb_copy_and_hash_datagram_iter helper Introduce a helper to copy datagram into an iovec iterator but also update a predefined hash. This is useful for consumers of skb_copy_datagram_iter to also support inflight data digest without having to finish to copy and only then traverse the iovec and calculate the digest hash. Acked-by: David S. Miller Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/skbuff.h | 3 +++ net/core/datagram.c | 20 +++++++++++++++++++- 2 files changed, 22 insertions(+), 1 deletion(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0d1b2c3f127b..b96c809c29eb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3325,6 +3325,9 @@ static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); +int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset, + struct iov_iter *to, int len, + struct ahash_request *hash); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); diff --git a/net/core/datagram.c b/net/core/datagram.c index 382543302ae5..ef262282c8be 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -465,7 +465,7 @@ int __skb_datagram_iter(const struct sk_buff *skb, int offset, if (copy > len) copy = len; if (__skb_datagram_iter(frag_iter, offset - start, - to, copy, short_copy, cb, data)) + to, copy, fault_short, cb, data)) goto fault; if ((len -= copy) == 0) return 0; @@ -492,6 +492,24 @@ short_copy: return 0; } +/** + * skb_copy_and_hash_datagram_iter - Copy datagram to an iovec iterator + * and update a hash. + * @skb: buffer to copy + * @offset: offset in the buffer to start copying from + * @to: iovec iterator to copy to + * @len: amount of data to copy from buffer to iovec + * @hash: hash request to update + */ +int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset, + struct iov_iter *to, int len, + struct ahash_request *hash) +{ + return __skb_datagram_iter(skb, offset, to, len, true, + hash_and_copy_to_iter, hash); +} +EXPORT_SYMBOL(skb_copy_and_hash_datagram_iter); + static size_t simple_copy_to_iter(const void *addr, size_t bytes, void *data __always_unused, struct iov_iter *i) { From 1672ddb8d691e4433806373ec4104f37a86efab0 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:11 -0800 Subject: [PATCH 07/33] nvmet: Add install_queue callout nvmet-tcp will implement it to allocate queue commands which are only known at nvmf connect time (sq size). Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/fabrics-cmd.c | 10 ++++++++++ drivers/nvme/target/nvmet.h | 1 + 2 files changed, 11 insertions(+) diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 328ae46d8344..ee7d84621d65 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -121,6 +121,16 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req) req->rsp->sq_head = cpu_to_le16(0xffff); } + if (ctrl->ops->install_queue) { + u16 ret = ctrl->ops->install_queue(req->sq); + + if (ret) { + pr_err("failed to install queue %d cntlid %d ret %x\n", + qid, ret, ctrl->cntlid); + return ret; + } + } + return 0; } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 7d8b7a7d572a..89df51ee5bdf 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -279,6 +279,7 @@ struct nvmet_fabrics_ops { void (*delete_ctrl)(struct nvmet_ctrl *ctrl); void (*disc_traddr)(struct nvmet_req *req, struct nvmet_port *port, char *traddr); + u16 (*install_queue)(struct nvmet_sq *nvme_sq); }; #define NVMET_MAX_INLINE_BIOVEC 8 From 3b49fa807284ec30669a95fd5f3806e127d29f4d Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:12 -0800 Subject: [PATCH 08/33] nvme-fabrics: allow user passing header digest Header digest is a nvme-tcp specific feature, but nothing prevents other transports reusing the concept so do not associate with tcp transport solely. Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fabrics.c | 5 +++++ drivers/nvme/host/fabrics.h | 2 ++ 2 files changed, 7 insertions(+) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 10074ac7731b..4272f8a95db3 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -614,6 +614,7 @@ static const match_table_t opt_tokens = { { NVMF_OPT_HOST_ID, "hostid=%s" }, { NVMF_OPT_DUP_CONNECT, "duplicate_connect" }, { NVMF_OPT_DISABLE_SQFLOW, "disable_sqflow" }, + { NVMF_OPT_HDR_DIGEST, "hdr_digest" }, { NVMF_OPT_ERR, NULL } }; @@ -633,6 +634,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY; opts->kato = NVME_DEFAULT_KATO; opts->duplicate_connect = false; + opts->hdr_digest = false; options = o = kstrdup(buf, GFP_KERNEL); if (!options) @@ -827,6 +829,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, case NVMF_OPT_DISABLE_SQFLOW: opts->disable_sqflow = true; break; + case NVMF_OPT_HDR_DIGEST: + opts->hdr_digest = true; + break; default: pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", p); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index ecd9a006a091..a6127f1a9e8e 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -59,6 +59,7 @@ enum { NVMF_OPT_HOST_ID = 1 << 12, NVMF_OPT_DUP_CONNECT = 1 << 13, NVMF_OPT_DISABLE_SQFLOW = 1 << 14, + NVMF_OPT_HDR_DIGEST = 1 << 15, }; /** @@ -103,6 +104,7 @@ struct nvmf_ctrl_options { struct nvmf_host *host; int max_reconnects; bool disable_sqflow; + bool hdr_digest; }; /* From 20d44e86321299f61bb782a39aaa30f579823f58 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:13 -0800 Subject: [PATCH 09/33] nvme-fabrics: allow user passing data digest Data digest is a nvme-tcp specific feature, but nothing prevents other transports reusing the concept so do not associate with tcp transport solely. Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fabrics.c | 5 +++++ drivers/nvme/host/fabrics.h | 2 ++ 2 files changed, 7 insertions(+) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 4272f8a95db3..9c62c6838b76 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -615,6 +615,7 @@ static const match_table_t opt_tokens = { { NVMF_OPT_DUP_CONNECT, "duplicate_connect" }, { NVMF_OPT_DISABLE_SQFLOW, "disable_sqflow" }, { NVMF_OPT_HDR_DIGEST, "hdr_digest" }, + { NVMF_OPT_DATA_DIGEST, "data_digest" }, { NVMF_OPT_ERR, NULL } }; @@ -635,6 +636,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->kato = NVME_DEFAULT_KATO; opts->duplicate_connect = false; opts->hdr_digest = false; + opts->data_digest = false; options = o = kstrdup(buf, GFP_KERNEL); if (!options) @@ -832,6 +834,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, case NVMF_OPT_HDR_DIGEST: opts->hdr_digest = true; break; + case NVMF_OPT_DATA_DIGEST: + opts->data_digest = true; + break; default: pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", p); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index a6127f1a9e8e..524a02a67817 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -60,6 +60,7 @@ enum { NVMF_OPT_DUP_CONNECT = 1 << 13, NVMF_OPT_DISABLE_SQFLOW = 1 << 14, NVMF_OPT_HDR_DIGEST = 1 << 15, + NVMF_OPT_DATA_DIGEST = 1 << 16, }; /** @@ -105,6 +106,7 @@ struct nvmf_ctrl_options { int max_reconnects; bool disable_sqflow; bool hdr_digest; + bool data_digest; }; /* From fc221d05447aa6db686a6724dd08aa6cce0924d1 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:14 -0800 Subject: [PATCH 10/33] nvme-tcp: Add protocol header Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/nvme-tcp.h | 189 +++++++++++++++++++++++++++++++++++++++ include/linux/nvme.h | 1 + 2 files changed, 190 insertions(+) create mode 100644 include/linux/nvme-tcp.h diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h new file mode 100644 index 000000000000..03d87c0550a9 --- /dev/null +++ b/include/linux/nvme-tcp.h @@ -0,0 +1,189 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVMe over Fabrics TCP protocol header. + * Copyright (c) 2018 Lightbits Labs. All rights reserved. + */ + +#ifndef _LINUX_NVME_TCP_H +#define _LINUX_NVME_TCP_H + +#include + +#define NVME_TCP_DISC_PORT 8009 +#define NVME_TCP_ADMIN_CCSZ SZ_8K +#define NVME_TCP_DIGEST_LENGTH 4 + +enum nvme_tcp_pfv { + NVME_TCP_PFV_1_0 = 0x0, +}; + +enum nvme_tcp_fatal_error_status { + NVME_TCP_FES_INVALID_PDU_HDR = 0x01, + NVME_TCP_FES_PDU_SEQ_ERR = 0x02, + NVME_TCP_FES_HDR_DIGEST_ERR = 0x03, + NVME_TCP_FES_DATA_OUT_OF_RANGE = 0x04, + NVME_TCP_FES_R2T_LIMIT_EXCEEDED = 0x05, + NVME_TCP_FES_DATA_LIMIT_EXCEEDED = 0x05, + NVME_TCP_FES_UNSUPPORTED_PARAM = 0x06, +}; + +enum nvme_tcp_digest_option { + NVME_TCP_HDR_DIGEST_ENABLE = (1 << 0), + NVME_TCP_DATA_DIGEST_ENABLE = (1 << 1), +}; + +enum nvme_tcp_pdu_type { + nvme_tcp_icreq = 0x0, + nvme_tcp_icresp = 0x1, + nvme_tcp_h2c_term = 0x2, + nvme_tcp_c2h_term = 0x3, + nvme_tcp_cmd = 0x4, + nvme_tcp_rsp = 0x5, + nvme_tcp_h2c_data = 0x6, + nvme_tcp_c2h_data = 0x7, + nvme_tcp_r2t = 0x9, +}; + +enum nvme_tcp_pdu_flags { + NVME_TCP_F_HDGST = (1 << 0), + NVME_TCP_F_DDGST = (1 << 1), + NVME_TCP_F_DATA_LAST = (1 << 2), + NVME_TCP_F_DATA_SUCCESS = (1 << 3), +}; + +/** + * struct nvme_tcp_hdr - nvme tcp pdu common header + * + * @type: pdu type + * @flags: pdu specific flags + * @hlen: pdu header length + * @pdo: pdu data offset + * @plen: pdu wire byte length + */ +struct nvme_tcp_hdr { + __u8 type; + __u8 flags; + __u8 hlen; + __u8 pdo; + __le32 plen; +}; + +/** + * struct nvme_tcp_icreq_pdu - nvme tcp initialize connection request pdu + * + * @hdr: pdu generic header + * @pfv: pdu version format + * @hpda: host pdu data alignment (dwords, 0's based) + * @digest: digest types enabled + * @maxr2t: maximum r2ts per request supported + */ +struct nvme_tcp_icreq_pdu { + struct nvme_tcp_hdr hdr; + __le16 pfv; + __u8 hpda; + __u8 digest; + __le32 maxr2t; + __u8 rsvd2[112]; +}; + +/** + * struct nvme_tcp_icresp_pdu - nvme tcp initialize connection response pdu + * + * @hdr: pdu common header + * @pfv: pdu version format + * @cpda: controller pdu data alignment (dowrds, 0's based) + * @digest: digest types enabled + * @maxdata: maximum data capsules per r2t supported + */ +struct nvme_tcp_icresp_pdu { + struct nvme_tcp_hdr hdr; + __le16 pfv; + __u8 cpda; + __u8 digest; + __le32 maxdata; + __u8 rsvd[112]; +}; + +/** + * struct nvme_tcp_term_pdu - nvme tcp terminate connection pdu + * + * @hdr: pdu common header + * @fes: fatal error status + * @fei: fatal error information + */ +struct nvme_tcp_term_pdu { + struct nvme_tcp_hdr hdr; + __le16 fes; + __le32 fei; + __u8 rsvd[8]; +}; + +/** + * struct nvme_tcp_cmd_pdu - nvme tcp command capsule pdu + * + * @hdr: pdu common header + * @cmd: nvme command + */ +struct nvme_tcp_cmd_pdu { + struct nvme_tcp_hdr hdr; + struct nvme_command cmd; +}; + +/** + * struct nvme_tcp_rsp_pdu - nvme tcp response capsule pdu + * + * @hdr: pdu common header + * @hdr: nvme-tcp generic header + * @cqe: nvme completion queue entry + */ +struct nvme_tcp_rsp_pdu { + struct nvme_tcp_hdr hdr; + struct nvme_completion cqe; +}; + +/** + * struct nvme_tcp_r2t_pdu - nvme tcp ready-to-transfer pdu + * + * @hdr: pdu common header + * @command_id: nvme command identifier which this relates to + * @ttag: transfer tag (controller generated) + * @r2t_offset: offset from the start of the command data + * @r2t_length: length the host is allowed to send + */ +struct nvme_tcp_r2t_pdu { + struct nvme_tcp_hdr hdr; + __u16 command_id; + __u16 ttag; + __le32 r2t_offset; + __le32 r2t_length; + __u8 rsvd[4]; +}; + +/** + * struct nvme_tcp_data_pdu - nvme tcp data pdu + * + * @hdr: pdu common header + * @command_id: nvme command identifier which this relates to + * @ttag: transfer tag (controller generated) + * @data_offset: offset from the start of the command data + * @data_length: length of the data stream + */ +struct nvme_tcp_data_pdu { + struct nvme_tcp_hdr hdr; + __u16 command_id; + __u16 ttag; + __le32 data_offset; + __le32 data_length; + __u8 rsvd[4]; +}; + +union nvme_tcp_pdu { + struct nvme_tcp_icreq_pdu icreq; + struct nvme_tcp_icresp_pdu icresp; + struct nvme_tcp_cmd_pdu cmd; + struct nvme_tcp_rsp_pdu rsp; + struct nvme_tcp_r2t_pdu r2t; + struct nvme_tcp_data_pdu data; +}; + +#endif /* _LINUX_NVME_TCP_H */ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 88812cb15be0..4d7907e3771e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -52,6 +52,7 @@ enum { enum { NVMF_TRTYPE_RDMA = 1, /* RDMA */ NVMF_TRTYPE_FC = 2, /* Fibre Channel */ + NVMF_TRTYPE_TCP = 3, /* TCP/IP */ NVMF_TRTYPE_LOOP = 254, /* Reserved for host usage */ NVMF_TRTYPE_MAX, }; From 872d26a391da92ed8f0c0f5cb5fef428067b7f30 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:15 -0800 Subject: [PATCH 11/33] nvmet-tcp: add NVMe over TCP target driver This patch implements the TCP transport driver for the NVMe over Fabrics target stack. This allows exporting NVMe over Fabrics functionality over good old TCP/IP. The driver implements the TP 8000 of how nvme over fabrics capsules and data are encapsulated in nvme-tcp pdus and exchaged on top of a TCP byte stream. nvme-tcp header and data digest are supported as well. Signed-off-by: Sagi Grimberg Signed-off-by: Roy Shterman Signed-off-by: Solganik Alexander Signed-off-by: Christoph Hellwig --- drivers/nvme/target/Kconfig | 10 + drivers/nvme/target/Makefile | 2 + drivers/nvme/target/tcp.c | 1737 ++++++++++++++++++++++++++++++++++ 3 files changed, 1749 insertions(+) create mode 100644 drivers/nvme/target/tcp.c diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig index 3c7b61ddb0d1..d94f25cde019 100644 --- a/drivers/nvme/target/Kconfig +++ b/drivers/nvme/target/Kconfig @@ -60,3 +60,13 @@ config NVME_TARGET_FCLOOP to test NVMe-FC transport interfaces. If unsure, say N. + +config NVME_TARGET_TCP + tristate "NVMe over Fabrics TCP target support" + depends on INET + depends on NVME_TARGET + help + This enables the NVMe TCP target support, which allows exporting NVMe + devices over TCP. + + If unsure, say N. diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile index 8118c93391c6..8c3ad0fb6860 100644 --- a/drivers/nvme/target/Makefile +++ b/drivers/nvme/target/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_NVME_TARGET_LOOP) += nvme-loop.o obj-$(CONFIG_NVME_TARGET_RDMA) += nvmet-rdma.o obj-$(CONFIG_NVME_TARGET_FC) += nvmet-fc.o obj-$(CONFIG_NVME_TARGET_FCLOOP) += nvme-fcloop.o +obj-$(CONFIG_NVME_TARGET_TCP) += nvmet-tcp.o nvmet-y += core.o configfs.o admin-cmd.o fabrics-cmd.o \ discovery.o io-cmd-file.o io-cmd-bdev.o @@ -12,3 +13,4 @@ nvme-loop-y += loop.o nvmet-rdma-y += rdma.o nvmet-fc-y += fc.o nvme-fcloop-y += fcloop.o +nvmet-tcp-y += tcp.o diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c new file mode 100644 index 000000000000..d31bec260160 --- /dev/null +++ b/drivers/nvme/target/tcp.c @@ -0,0 +1,1737 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVMe over Fabrics TCP target. + * Copyright (c) 2018 Lightbits Labs. All rights reserved. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "nvmet.h" + +#define NVMET_TCP_DEF_INLINE_DATA_SIZE (4 * PAGE_SIZE) + +#define NVMET_TCP_RECV_BUDGET 8 +#define NVMET_TCP_SEND_BUDGET 8 +#define NVMET_TCP_IO_WORK_BUDGET 64 + +enum nvmet_tcp_send_state { + NVMET_TCP_SEND_DATA_PDU, + NVMET_TCP_SEND_DATA, + NVMET_TCP_SEND_R2T, + NVMET_TCP_SEND_DDGST, + NVMET_TCP_SEND_RESPONSE +}; + +enum nvmet_tcp_recv_state { + NVMET_TCP_RECV_PDU, + NVMET_TCP_RECV_DATA, + NVMET_TCP_RECV_DDGST, + NVMET_TCP_RECV_ERR, +}; + +enum { + NVMET_TCP_F_INIT_FAILED = (1 << 0), +}; + +struct nvmet_tcp_cmd { + struct nvmet_tcp_queue *queue; + struct nvmet_req req; + + struct nvme_tcp_cmd_pdu *cmd_pdu; + struct nvme_tcp_rsp_pdu *rsp_pdu; + struct nvme_tcp_data_pdu *data_pdu; + struct nvme_tcp_r2t_pdu *r2t_pdu; + + u32 rbytes_done; + u32 wbytes_done; + + u32 pdu_len; + u32 pdu_recv; + int sg_idx; + int nr_mapped; + struct msghdr recv_msg; + struct kvec *iov; + u32 flags; + + struct list_head entry; + struct llist_node lentry; + + /* send state */ + u32 offset; + struct scatterlist *cur_sg; + enum nvmet_tcp_send_state state; + + __le32 exp_ddgst; + __le32 recv_ddgst; +}; + +enum nvmet_tcp_queue_state { + NVMET_TCP_Q_CONNECTING, + NVMET_TCP_Q_LIVE, + NVMET_TCP_Q_DISCONNECTING, +}; + +struct nvmet_tcp_queue { + struct socket *sock; + struct nvmet_tcp_port *port; + struct work_struct io_work; + int cpu; + struct nvmet_cq nvme_cq; + struct nvmet_sq nvme_sq; + + /* send state */ + struct nvmet_tcp_cmd *cmds; + unsigned int nr_cmds; + struct list_head free_list; + struct llist_head resp_list; + struct list_head resp_send_list; + int send_list_len; + struct nvmet_tcp_cmd *snd_cmd; + + /* recv state */ + int offset; + int left; + enum nvmet_tcp_recv_state rcv_state; + struct nvmet_tcp_cmd *cmd; + union nvme_tcp_pdu pdu; + + /* digest state */ + bool hdr_digest; + bool data_digest; + struct ahash_request *snd_hash; + struct ahash_request *rcv_hash; + + spinlock_t state_lock; + enum nvmet_tcp_queue_state state; + + struct sockaddr_storage sockaddr; + struct sockaddr_storage sockaddr_peer; + struct work_struct release_work; + + int idx; + struct list_head queue_list; + + struct nvmet_tcp_cmd connect; + + struct page_frag_cache pf_cache; + + void (*data_ready)(struct sock *); + void (*state_change)(struct sock *); + void (*write_space)(struct sock *); +}; + +struct nvmet_tcp_port { + struct socket *sock; + struct work_struct accept_work; + struct nvmet_port *nport; + struct sockaddr_storage addr; + int last_cpu; + void (*data_ready)(struct sock *); +}; + +static DEFINE_IDA(nvmet_tcp_queue_ida); +static LIST_HEAD(nvmet_tcp_queue_list); +static DEFINE_MUTEX(nvmet_tcp_queue_mutex); + +static struct workqueue_struct *nvmet_tcp_wq; +static struct nvmet_fabrics_ops nvmet_tcp_ops; +static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c); +static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd); + +static inline u16 nvmet_tcp_cmd_tag(struct nvmet_tcp_queue *queue, + struct nvmet_tcp_cmd *cmd) +{ + return cmd - queue->cmds; +} + +static inline bool nvmet_tcp_has_data_in(struct nvmet_tcp_cmd *cmd) +{ + return nvme_is_write(cmd->req.cmd) && + cmd->rbytes_done < cmd->req.transfer_len; +} + +static inline bool nvmet_tcp_need_data_in(struct nvmet_tcp_cmd *cmd) +{ + return nvmet_tcp_has_data_in(cmd) && !cmd->req.rsp->status; +} + +static inline bool nvmet_tcp_need_data_out(struct nvmet_tcp_cmd *cmd) +{ + return !nvme_is_write(cmd->req.cmd) && + cmd->req.transfer_len > 0 && + !cmd->req.rsp->status; +} + +static inline bool nvmet_tcp_has_inline_data(struct nvmet_tcp_cmd *cmd) +{ + return nvme_is_write(cmd->req.cmd) && cmd->pdu_len && + !cmd->rbytes_done; +} + +static inline struct nvmet_tcp_cmd * +nvmet_tcp_get_cmd(struct nvmet_tcp_queue *queue) +{ + struct nvmet_tcp_cmd *cmd; + + cmd = list_first_entry_or_null(&queue->free_list, + struct nvmet_tcp_cmd, entry); + if (!cmd) + return NULL; + list_del_init(&cmd->entry); + + cmd->rbytes_done = cmd->wbytes_done = 0; + cmd->pdu_len = 0; + cmd->pdu_recv = 0; + cmd->iov = NULL; + cmd->flags = 0; + return cmd; +} + +static inline void nvmet_tcp_put_cmd(struct nvmet_tcp_cmd *cmd) +{ + if (unlikely(cmd == &cmd->queue->connect)) + return; + + list_add_tail(&cmd->entry, &cmd->queue->free_list); +} + +static inline u8 nvmet_tcp_hdgst_len(struct nvmet_tcp_queue *queue) +{ + return queue->hdr_digest ? NVME_TCP_DIGEST_LENGTH : 0; +} + +static inline u8 nvmet_tcp_ddgst_len(struct nvmet_tcp_queue *queue) +{ + return queue->data_digest ? NVME_TCP_DIGEST_LENGTH : 0; +} + +static inline void nvmet_tcp_hdgst(struct ahash_request *hash, + void *pdu, size_t len) +{ + struct scatterlist sg; + + sg_init_one(&sg, pdu, len); + ahash_request_set_crypt(hash, &sg, pdu + len, len); + crypto_ahash_digest(hash); +} + +static int nvmet_tcp_verify_hdgst(struct nvmet_tcp_queue *queue, + void *pdu, size_t len) +{ + struct nvme_tcp_hdr *hdr = pdu; + __le32 recv_digest; + __le32 exp_digest; + + if (unlikely(!(hdr->flags & NVME_TCP_F_HDGST))) { + pr_err("queue %d: header digest enabled but no header digest\n", + queue->idx); + return -EPROTO; + } + + recv_digest = *(__le32 *)(pdu + hdr->hlen); + nvmet_tcp_hdgst(queue->rcv_hash, pdu, len); + exp_digest = *(__le32 *)(pdu + hdr->hlen); + if (recv_digest != exp_digest) { + pr_err("queue %d: header digest error: recv %#x expected %#x\n", + queue->idx, le32_to_cpu(recv_digest), + le32_to_cpu(exp_digest)); + return -EPROTO; + } + + return 0; +} + +static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu) +{ + struct nvme_tcp_hdr *hdr = pdu; + u8 digest_len = nvmet_tcp_hdgst_len(queue); + u32 len; + + len = le32_to_cpu(hdr->plen) - hdr->hlen - + (hdr->flags & NVME_TCP_F_HDGST ? digest_len : 0); + + if (unlikely(len && !(hdr->flags & NVME_TCP_F_DDGST))) { + pr_err("queue %d: data digest flag is cleared\n", queue->idx); + return -EPROTO; + } + + return 0; +} + +static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd) +{ + struct scatterlist *sg; + int i; + + sg = &cmd->req.sg[cmd->sg_idx]; + + for (i = 0; i < cmd->nr_mapped; i++) + kunmap(sg_page(&sg[i])); +} + +static void nvmet_tcp_map_pdu_iovec(struct nvmet_tcp_cmd *cmd) +{ + struct kvec *iov = cmd->iov; + struct scatterlist *sg; + u32 length, offset, sg_offset; + + length = cmd->pdu_len; + cmd->nr_mapped = DIV_ROUND_UP(length, PAGE_SIZE); + offset = cmd->rbytes_done; + cmd->sg_idx = DIV_ROUND_UP(offset, PAGE_SIZE); + sg_offset = offset % PAGE_SIZE; + sg = &cmd->req.sg[cmd->sg_idx]; + + while (length) { + u32 iov_len = min_t(u32, length, sg->length - sg_offset); + + iov->iov_base = kmap(sg_page(sg)) + sg->offset + sg_offset; + iov->iov_len = iov_len; + + length -= iov_len; + sg = sg_next(sg); + iov++; + } + + iov_iter_kvec(&cmd->recv_msg.msg_iter, READ, cmd->iov, + cmd->nr_mapped, cmd->pdu_len); +} + +static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) +{ + queue->rcv_state = NVMET_TCP_RECV_ERR; + if (queue->nvme_sq.ctrl) + nvmet_ctrl_fatal_error(queue->nvme_sq.ctrl); + else + kernel_sock_shutdown(queue->sock, SHUT_RDWR); +} + +static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) +{ + struct nvme_sgl_desc *sgl = &cmd->req.cmd->common.dptr.sgl; + u32 len = le32_to_cpu(sgl->length); + + if (!cmd->req.data_len) + return 0; + + if (sgl->type == ((NVME_SGL_FMT_DATA_DESC << 4) | + NVME_SGL_FMT_OFFSET)) { + if (!nvme_is_write(cmd->req.cmd)) + return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + + if (len > cmd->req.port->inline_data_size) + return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR; + cmd->pdu_len = len; + } + cmd->req.transfer_len += len; + + cmd->req.sg = sgl_alloc(len, GFP_KERNEL, &cmd->req.sg_cnt); + if (!cmd->req.sg) + return NVME_SC_INTERNAL; + cmd->cur_sg = cmd->req.sg; + + if (nvmet_tcp_has_data_in(cmd)) { + cmd->iov = kmalloc_array(cmd->req.sg_cnt, + sizeof(*cmd->iov), GFP_KERNEL); + if (!cmd->iov) + goto err; + } + + return 0; +err: + sgl_free(cmd->req.sg); + return NVME_SC_INTERNAL; +} + +static void nvmet_tcp_ddgst(struct ahash_request *hash, + struct nvmet_tcp_cmd *cmd) +{ + ahash_request_set_crypt(hash, cmd->req.sg, + (void *)&cmd->exp_ddgst, cmd->req.transfer_len); + crypto_ahash_digest(hash); +} + +static void nvmet_setup_c2h_data_pdu(struct nvmet_tcp_cmd *cmd) +{ + struct nvme_tcp_data_pdu *pdu = cmd->data_pdu; + struct nvmet_tcp_queue *queue = cmd->queue; + u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue); + u8 ddgst = nvmet_tcp_ddgst_len(cmd->queue); + + cmd->offset = 0; + cmd->state = NVMET_TCP_SEND_DATA_PDU; + + pdu->hdr.type = nvme_tcp_c2h_data; + pdu->hdr.flags = NVME_TCP_F_DATA_LAST; + pdu->hdr.hlen = sizeof(*pdu); + pdu->hdr.pdo = pdu->hdr.hlen + hdgst; + pdu->hdr.plen = + cpu_to_le32(pdu->hdr.hlen + hdgst + + cmd->req.transfer_len + ddgst); + pdu->command_id = cmd->req.rsp->command_id; + pdu->data_length = cpu_to_le32(cmd->req.transfer_len); + pdu->data_offset = cpu_to_le32(cmd->wbytes_done); + + if (queue->data_digest) { + pdu->hdr.flags |= NVME_TCP_F_DDGST; + nvmet_tcp_ddgst(queue->snd_hash, cmd); + } + + if (cmd->queue->hdr_digest) { + pdu->hdr.flags |= NVME_TCP_F_HDGST; + nvmet_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu)); + } +} + +static void nvmet_setup_r2t_pdu(struct nvmet_tcp_cmd *cmd) +{ + struct nvme_tcp_r2t_pdu *pdu = cmd->r2t_pdu; + struct nvmet_tcp_queue *queue = cmd->queue; + u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue); + + cmd->offset = 0; + cmd->state = NVMET_TCP_SEND_R2T; + + pdu->hdr.type = nvme_tcp_r2t; + pdu->hdr.flags = 0; + pdu->hdr.hlen = sizeof(*pdu); + pdu->hdr.pdo = 0; + pdu->hdr.plen = cpu_to_le32(pdu->hdr.hlen + hdgst); + + pdu->command_id = cmd->req.cmd->common.command_id; + pdu->ttag = nvmet_tcp_cmd_tag(cmd->queue, cmd); + pdu->r2t_length = cpu_to_le32(cmd->req.transfer_len - cmd->rbytes_done); + pdu->r2t_offset = cpu_to_le32(cmd->rbytes_done); + if (cmd->queue->hdr_digest) { + pdu->hdr.flags |= NVME_TCP_F_HDGST; + nvmet_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu)); + } +} + +static void nvmet_setup_response_pdu(struct nvmet_tcp_cmd *cmd) +{ + struct nvme_tcp_rsp_pdu *pdu = cmd->rsp_pdu; + struct nvmet_tcp_queue *queue = cmd->queue; + u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue); + + cmd->offset = 0; + cmd->state = NVMET_TCP_SEND_RESPONSE; + + pdu->hdr.type = nvme_tcp_rsp; + pdu->hdr.flags = 0; + pdu->hdr.hlen = sizeof(*pdu); + pdu->hdr.pdo = 0; + pdu->hdr.plen = cpu_to_le32(pdu->hdr.hlen + hdgst); + if (cmd->queue->hdr_digest) { + pdu->hdr.flags |= NVME_TCP_F_HDGST; + nvmet_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu)); + } +} + +static void nvmet_tcp_process_resp_list(struct nvmet_tcp_queue *queue) +{ + struct llist_node *node; + + node = llist_del_all(&queue->resp_list); + if (!node) + return; + + while (node) { + struct nvmet_tcp_cmd *cmd = llist_entry(node, + struct nvmet_tcp_cmd, lentry); + + list_add(&cmd->entry, &queue->resp_send_list); + node = node->next; + queue->send_list_len++; + } +} + +static struct nvmet_tcp_cmd *nvmet_tcp_fetch_cmd(struct nvmet_tcp_queue *queue) +{ + queue->snd_cmd = list_first_entry_or_null(&queue->resp_send_list, + struct nvmet_tcp_cmd, entry); + if (!queue->snd_cmd) { + nvmet_tcp_process_resp_list(queue); + queue->snd_cmd = + list_first_entry_or_null(&queue->resp_send_list, + struct nvmet_tcp_cmd, entry); + if (unlikely(!queue->snd_cmd)) + return NULL; + } + + list_del_init(&queue->snd_cmd->entry); + queue->send_list_len--; + + if (nvmet_tcp_need_data_out(queue->snd_cmd)) + nvmet_setup_c2h_data_pdu(queue->snd_cmd); + else if (nvmet_tcp_need_data_in(queue->snd_cmd)) + nvmet_setup_r2t_pdu(queue->snd_cmd); + else + nvmet_setup_response_pdu(queue->snd_cmd); + + return queue->snd_cmd; +} + +static void nvmet_tcp_queue_response(struct nvmet_req *req) +{ + struct nvmet_tcp_cmd *cmd = + container_of(req, struct nvmet_tcp_cmd, req); + struct nvmet_tcp_queue *queue = cmd->queue; + + llist_add(&cmd->lentry, &queue->resp_list); + queue_work_on(cmd->queue->cpu, nvmet_tcp_wq, &cmd->queue->io_work); +} + +static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd) +{ + u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue); + int left = sizeof(*cmd->data_pdu) - cmd->offset + hdgst; + int ret; + + ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->data_pdu), + offset_in_page(cmd->data_pdu) + cmd->offset, + left, MSG_DONTWAIT | MSG_MORE); + if (ret <= 0) + return ret; + + cmd->offset += ret; + left -= ret; + + if (left) + return -EAGAIN; + + cmd->state = NVMET_TCP_SEND_DATA; + cmd->offset = 0; + return 1; +} + +static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd) +{ + struct nvmet_tcp_queue *queue = cmd->queue; + int ret; + + while (cmd->cur_sg) { + struct page *page = sg_page(cmd->cur_sg); + u32 left = cmd->cur_sg->length - cmd->offset; + + ret = kernel_sendpage(cmd->queue->sock, page, cmd->offset, + left, MSG_DONTWAIT | MSG_MORE); + if (ret <= 0) + return ret; + + cmd->offset += ret; + cmd->wbytes_done += ret; + + /* Done with sg?*/ + if (cmd->offset == cmd->cur_sg->length) { + cmd->cur_sg = sg_next(cmd->cur_sg); + cmd->offset = 0; + } + } + + if (queue->data_digest) { + cmd->state = NVMET_TCP_SEND_DDGST; + cmd->offset = 0; + } else { + nvmet_setup_response_pdu(cmd); + } + return 1; + +} + +static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd, + bool last_in_batch) +{ + u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue); + int left = sizeof(*cmd->rsp_pdu) - cmd->offset + hdgst; + int flags = MSG_DONTWAIT; + int ret; + + if (!last_in_batch && cmd->queue->send_list_len) + flags |= MSG_MORE; + else + flags |= MSG_EOR; + + ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->rsp_pdu), + offset_in_page(cmd->rsp_pdu) + cmd->offset, left, flags); + if (ret <= 0) + return ret; + cmd->offset += ret; + left -= ret; + + if (left) + return -EAGAIN; + + kfree(cmd->iov); + sgl_free(cmd->req.sg); + cmd->queue->snd_cmd = NULL; + nvmet_tcp_put_cmd(cmd); + return 1; +} + +static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch) +{ + u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue); + int left = sizeof(*cmd->r2t_pdu) - cmd->offset + hdgst; + int flags = MSG_DONTWAIT; + int ret; + + if (!last_in_batch && cmd->queue->send_list_len) + flags |= MSG_MORE; + else + flags |= MSG_EOR; + + ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->r2t_pdu), + offset_in_page(cmd->r2t_pdu) + cmd->offset, left, flags); + if (ret <= 0) + return ret; + cmd->offset += ret; + left -= ret; + + if (left) + return -EAGAIN; + + cmd->queue->snd_cmd = NULL; + return 1; +} + +static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd) +{ + struct nvmet_tcp_queue *queue = cmd->queue; + struct msghdr msg = { .msg_flags = MSG_DONTWAIT }; + struct kvec iov = { + .iov_base = &cmd->exp_ddgst + cmd->offset, + .iov_len = NVME_TCP_DIGEST_LENGTH - cmd->offset + }; + int ret; + + ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); + if (unlikely(ret <= 0)) + return ret; + + cmd->offset += ret; + nvmet_setup_response_pdu(cmd); + return 1; +} + +static int nvmet_tcp_try_send_one(struct nvmet_tcp_queue *queue, + bool last_in_batch) +{ + struct nvmet_tcp_cmd *cmd = queue->snd_cmd; + int ret = 0; + + if (!cmd || queue->state == NVMET_TCP_Q_DISCONNECTING) { + cmd = nvmet_tcp_fetch_cmd(queue); + if (unlikely(!cmd)) + return 0; + } + + if (cmd->state == NVMET_TCP_SEND_DATA_PDU) { + ret = nvmet_try_send_data_pdu(cmd); + if (ret <= 0) + goto done_send; + } + + if (cmd->state == NVMET_TCP_SEND_DATA) { + ret = nvmet_try_send_data(cmd); + if (ret <= 0) + goto done_send; + } + + if (cmd->state == NVMET_TCP_SEND_DDGST) { + ret = nvmet_try_send_ddgst(cmd); + if (ret <= 0) + goto done_send; + } + + if (cmd->state == NVMET_TCP_SEND_R2T) { + ret = nvmet_try_send_r2t(cmd, last_in_batch); + if (ret <= 0) + goto done_send; + } + + if (cmd->state == NVMET_TCP_SEND_RESPONSE) + ret = nvmet_try_send_response(cmd, last_in_batch); + +done_send: + if (ret < 0) { + if (ret == -EAGAIN) + return 0; + return ret; + } + + return 1; +} + +static int nvmet_tcp_try_send(struct nvmet_tcp_queue *queue, + int budget, int *sends) +{ + int i, ret = 0; + + for (i = 0; i < budget; i++) { + ret = nvmet_tcp_try_send_one(queue, i == budget - 1); + if (ret <= 0) + break; + (*sends)++; + } + + return ret; +} + +static void nvmet_prepare_receive_pdu(struct nvmet_tcp_queue *queue) +{ + queue->offset = 0; + queue->left = sizeof(struct nvme_tcp_hdr); + queue->cmd = NULL; + queue->rcv_state = NVMET_TCP_RECV_PDU; +} + +static void nvmet_tcp_free_crypto(struct nvmet_tcp_queue *queue) +{ + struct crypto_ahash *tfm = crypto_ahash_reqtfm(queue->rcv_hash); + + ahash_request_free(queue->rcv_hash); + ahash_request_free(queue->snd_hash); + crypto_free_ahash(tfm); +} + +static int nvmet_tcp_alloc_crypto(struct nvmet_tcp_queue *queue) +{ + struct crypto_ahash *tfm; + + tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + queue->snd_hash = ahash_request_alloc(tfm, GFP_KERNEL); + if (!queue->snd_hash) + goto free_tfm; + ahash_request_set_callback(queue->snd_hash, 0, NULL, NULL); + + queue->rcv_hash = ahash_request_alloc(tfm, GFP_KERNEL); + if (!queue->rcv_hash) + goto free_snd_hash; + ahash_request_set_callback(queue->rcv_hash, 0, NULL, NULL); + + return 0; +free_snd_hash: + ahash_request_free(queue->snd_hash); +free_tfm: + crypto_free_ahash(tfm); + return -ENOMEM; +} + + +static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) +{ + struct nvme_tcp_icreq_pdu *icreq = &queue->pdu.icreq; + struct nvme_tcp_icresp_pdu *icresp = &queue->pdu.icresp; + struct msghdr msg = {}; + struct kvec iov; + int ret; + + if (le32_to_cpu(icreq->hdr.plen) != sizeof(struct nvme_tcp_icreq_pdu)) { + pr_err("bad nvme-tcp pdu length (%d)\n", + le32_to_cpu(icreq->hdr.plen)); + nvmet_tcp_fatal_error(queue); + } + + if (icreq->pfv != NVME_TCP_PFV_1_0) { + pr_err("queue %d: bad pfv %d\n", queue->idx, icreq->pfv); + return -EPROTO; + } + + if (icreq->hpda != 0) { + pr_err("queue %d: unsupported hpda %d\n", queue->idx, + icreq->hpda); + return -EPROTO; + } + + if (icreq->maxr2t != 0) { + pr_err("queue %d: unsupported maxr2t %d\n", queue->idx, + le16_to_cpu(icreq->maxr2t) + 1); + return -EPROTO; + } + + queue->hdr_digest = !!(icreq->digest & NVME_TCP_HDR_DIGEST_ENABLE); + queue->data_digest = !!(icreq->digest & NVME_TCP_DATA_DIGEST_ENABLE); + if (queue->hdr_digest || queue->data_digest) { + ret = nvmet_tcp_alloc_crypto(queue); + if (ret) + return ret; + } + + memset(icresp, 0, sizeof(*icresp)); + icresp->hdr.type = nvme_tcp_icresp; + icresp->hdr.hlen = sizeof(*icresp); + icresp->hdr.pdo = 0; + icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen); + icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0); + icresp->maxdata = 0xffff; /* FIXME: support r2t */ + icresp->cpda = 0; + if (queue->hdr_digest) + icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE; + if (queue->data_digest) + icresp->digest |= NVME_TCP_DATA_DIGEST_ENABLE; + + iov.iov_base = icresp; + iov.iov_len = sizeof(*icresp); + ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); + if (ret < 0) + goto free_crypto; + + queue->state = NVMET_TCP_Q_LIVE; + nvmet_prepare_receive_pdu(queue); + return 0; +free_crypto: + if (queue->hdr_digest || queue->data_digest) + nvmet_tcp_free_crypto(queue); + return ret; +} + +static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, + struct nvmet_tcp_cmd *cmd, struct nvmet_req *req) +{ + int ret; + + /* recover the expected data transfer length */ + req->data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); + + if (!nvme_is_write(cmd->req.cmd) || + req->data_len > cmd->req.port->inline_data_size) { + nvmet_prepare_receive_pdu(queue); + return; + } + + ret = nvmet_tcp_map_data(cmd); + if (unlikely(ret)) { + pr_err("queue %d: failed to map data\n", queue->idx); + nvmet_tcp_fatal_error(queue); + return; + } + + queue->rcv_state = NVMET_TCP_RECV_DATA; + nvmet_tcp_map_pdu_iovec(cmd); + cmd->flags |= NVMET_TCP_F_INIT_FAILED; +} + +static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) +{ + struct nvme_tcp_data_pdu *data = &queue->pdu.data; + struct nvmet_tcp_cmd *cmd; + + cmd = &queue->cmds[data->ttag]; + + if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) { + pr_err("ttag %u unexpected data offset %u (expected %u)\n", + data->ttag, le32_to_cpu(data->data_offset), + cmd->rbytes_done); + /* FIXME: use path and transport errors */ + nvmet_req_complete(&cmd->req, + NVME_SC_INVALID_FIELD | NVME_SC_DNR); + return -EPROTO; + } + + cmd->pdu_len = le32_to_cpu(data->data_length); + cmd->pdu_recv = 0; + nvmet_tcp_map_pdu_iovec(cmd); + queue->cmd = cmd; + queue->rcv_state = NVMET_TCP_RECV_DATA; + + return 0; +} + +static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) +{ + struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr; + struct nvme_command *nvme_cmd = &queue->pdu.cmd.cmd; + struct nvmet_req *req; + int ret; + + if (unlikely(queue->state == NVMET_TCP_Q_CONNECTING)) { + if (hdr->type != nvme_tcp_icreq) { + pr_err("unexpected pdu type (%d) before icreq\n", + hdr->type); + nvmet_tcp_fatal_error(queue); + return -EPROTO; + } + return nvmet_tcp_handle_icreq(queue); + } + + if (hdr->type == nvme_tcp_h2c_data) { + ret = nvmet_tcp_handle_h2c_data_pdu(queue); + if (unlikely(ret)) + return ret; + return 0; + } + + queue->cmd = nvmet_tcp_get_cmd(queue); + if (unlikely(!queue->cmd)) { + /* This should never happen */ + pr_err("queue %d: out of commands (%d) send_list_len: %d, opcode: %d", + queue->idx, queue->nr_cmds, queue->send_list_len, + nvme_cmd->common.opcode); + nvmet_tcp_fatal_error(queue); + return -ENOMEM; + } + + req = &queue->cmd->req; + memcpy(req->cmd, nvme_cmd, sizeof(*nvme_cmd)); + + if (unlikely(!nvmet_req_init(req, &queue->nvme_cq, + &queue->nvme_sq, &nvmet_tcp_ops))) { + pr_err("failed cmd %p id %d opcode %d, data_len: %d\n", + req->cmd, req->cmd->common.command_id, + req->cmd->common.opcode, + le32_to_cpu(req->cmd->common.dptr.sgl.length)); + + nvmet_tcp_handle_req_failure(queue, queue->cmd, req); + return -EAGAIN; + } + + ret = nvmet_tcp_map_data(queue->cmd); + if (unlikely(ret)) { + pr_err("queue %d: failed to map data\n", queue->idx); + if (nvmet_tcp_has_inline_data(queue->cmd)) + nvmet_tcp_fatal_error(queue); + else + nvmet_req_complete(req, ret); + ret = -EAGAIN; + goto out; + } + + if (nvmet_tcp_need_data_in(queue->cmd)) { + if (nvmet_tcp_has_inline_data(queue->cmd)) { + queue->rcv_state = NVMET_TCP_RECV_DATA; + nvmet_tcp_map_pdu_iovec(queue->cmd); + return 0; + } + /* send back R2T */ + nvmet_tcp_queue_response(&queue->cmd->req); + goto out; + } + + nvmet_req_execute(&queue->cmd->req); +out: + nvmet_prepare_receive_pdu(queue); + return ret; +} + +static const u8 nvme_tcp_pdu_sizes[] = { + [nvme_tcp_icreq] = sizeof(struct nvme_tcp_icreq_pdu), + [nvme_tcp_cmd] = sizeof(struct nvme_tcp_cmd_pdu), + [nvme_tcp_h2c_data] = sizeof(struct nvme_tcp_data_pdu), +}; + +static inline u8 nvmet_tcp_pdu_size(u8 type) +{ + size_t idx = type; + + return (idx < ARRAY_SIZE(nvme_tcp_pdu_sizes) && + nvme_tcp_pdu_sizes[idx]) ? + nvme_tcp_pdu_sizes[idx] : 0; +} + +static inline bool nvmet_tcp_pdu_valid(u8 type) +{ + switch (type) { + case nvme_tcp_icreq: + case nvme_tcp_cmd: + case nvme_tcp_h2c_data: + /* fallthru */ + return true; + } + + return false; +} + +static int nvmet_tcp_try_recv_pdu(struct nvmet_tcp_queue *queue) +{ + struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr; + int len; + struct kvec iov; + struct msghdr msg = { .msg_flags = MSG_DONTWAIT }; + +recv: + iov.iov_base = (void *)&queue->pdu + queue->offset; + iov.iov_len = queue->left; + len = kernel_recvmsg(queue->sock, &msg, &iov, 1, + iov.iov_len, msg.msg_flags); + if (unlikely(len < 0)) + return len; + + queue->offset += len; + queue->left -= len; + if (queue->left) + return -EAGAIN; + + if (queue->offset == sizeof(struct nvme_tcp_hdr)) { + u8 hdgst = nvmet_tcp_hdgst_len(queue); + + if (unlikely(!nvmet_tcp_pdu_valid(hdr->type))) { + pr_err("unexpected pdu type %d\n", hdr->type); + nvmet_tcp_fatal_error(queue); + return -EIO; + } + + if (unlikely(hdr->hlen != nvmet_tcp_pdu_size(hdr->type))) { + pr_err("pdu %d bad hlen %d\n", hdr->type, hdr->hlen); + return -EIO; + } + + queue->left = hdr->hlen - queue->offset + hdgst; + goto recv; + } + + if (queue->hdr_digest && + nvmet_tcp_verify_hdgst(queue, &queue->pdu, queue->offset)) { + nvmet_tcp_fatal_error(queue); /* fatal */ + return -EPROTO; + } + + if (queue->data_digest && + nvmet_tcp_check_ddgst(queue, &queue->pdu)) { + nvmet_tcp_fatal_error(queue); /* fatal */ + return -EPROTO; + } + + return nvmet_tcp_done_recv_pdu(queue); +} + +static void nvmet_tcp_prep_recv_ddgst(struct nvmet_tcp_cmd *cmd) +{ + struct nvmet_tcp_queue *queue = cmd->queue; + + nvmet_tcp_ddgst(queue->rcv_hash, cmd); + queue->offset = 0; + queue->left = NVME_TCP_DIGEST_LENGTH; + queue->rcv_state = NVMET_TCP_RECV_DDGST; +} + +static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue) +{ + struct nvmet_tcp_cmd *cmd = queue->cmd; + int ret; + + while (msg_data_left(&cmd->recv_msg)) { + ret = sock_recvmsg(cmd->queue->sock, &cmd->recv_msg, + cmd->recv_msg.msg_flags); + if (ret <= 0) + return ret; + + cmd->pdu_recv += ret; + cmd->rbytes_done += ret; + } + + nvmet_tcp_unmap_pdu_iovec(cmd); + + if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) && + cmd->rbytes_done == cmd->req.transfer_len) { + if (queue->data_digest) { + nvmet_tcp_prep_recv_ddgst(cmd); + return 0; + } + nvmet_req_execute(&cmd->req); + } + + nvmet_prepare_receive_pdu(queue); + return 0; +} + +static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue) +{ + struct nvmet_tcp_cmd *cmd = queue->cmd; + int ret; + struct msghdr msg = { .msg_flags = MSG_DONTWAIT }; + struct kvec iov = { + .iov_base = (void *)&cmd->recv_ddgst + queue->offset, + .iov_len = queue->left + }; + + ret = kernel_recvmsg(queue->sock, &msg, &iov, 1, + iov.iov_len, msg.msg_flags); + if (unlikely(ret < 0)) + return ret; + + queue->offset += ret; + queue->left -= ret; + if (queue->left) + return -EAGAIN; + + if (queue->data_digest && cmd->exp_ddgst != cmd->recv_ddgst) { + pr_err("queue %d: cmd %d pdu (%d) data digest error: recv %#x expected %#x\n", + queue->idx, cmd->req.cmd->common.command_id, + queue->pdu.cmd.hdr.type, le32_to_cpu(cmd->recv_ddgst), + le32_to_cpu(cmd->exp_ddgst)); + nvmet_tcp_finish_cmd(cmd); + nvmet_tcp_fatal_error(queue); + ret = -EPROTO; + goto out; + } + + if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) && + cmd->rbytes_done == cmd->req.transfer_len) + nvmet_req_execute(&cmd->req); + ret = 0; +out: + nvmet_prepare_receive_pdu(queue); + return ret; +} + +static int nvmet_tcp_try_recv_one(struct nvmet_tcp_queue *queue) +{ + int result; + + if (unlikely(queue->rcv_state == NVMET_TCP_RECV_ERR)) + return 0; + + if (queue->rcv_state == NVMET_TCP_RECV_PDU) { + result = nvmet_tcp_try_recv_pdu(queue); + if (result != 0) + goto done_recv; + } + + if (queue->rcv_state == NVMET_TCP_RECV_DATA) { + result = nvmet_tcp_try_recv_data(queue); + if (result != 0) + goto done_recv; + } + + if (queue->rcv_state == NVMET_TCP_RECV_DDGST) { + result = nvmet_tcp_try_recv_ddgst(queue); + if (result != 0) + goto done_recv; + } + +done_recv: + if (result < 0) { + if (result == -EAGAIN) + return 0; + return result; + } + return 1; +} + +static int nvmet_tcp_try_recv(struct nvmet_tcp_queue *queue, + int budget, int *recvs) +{ + int i, ret = 0; + + for (i = 0; i < budget; i++) { + ret = nvmet_tcp_try_recv_one(queue); + if (ret <= 0) + break; + (*recvs)++; + } + + return ret; +} + +static void nvmet_tcp_schedule_release_queue(struct nvmet_tcp_queue *queue) +{ + spin_lock(&queue->state_lock); + if (queue->state != NVMET_TCP_Q_DISCONNECTING) { + queue->state = NVMET_TCP_Q_DISCONNECTING; + schedule_work(&queue->release_work); + } + spin_unlock(&queue->state_lock); +} + +static void nvmet_tcp_io_work(struct work_struct *w) +{ + struct nvmet_tcp_queue *queue = + container_of(w, struct nvmet_tcp_queue, io_work); + bool pending; + int ret, ops = 0; + + do { + pending = false; + + ret = nvmet_tcp_try_recv(queue, NVMET_TCP_RECV_BUDGET, &ops); + if (ret > 0) { + pending = true; + } else if (ret < 0) { + if (ret == -EPIPE || ret == -ECONNRESET) + kernel_sock_shutdown(queue->sock, SHUT_RDWR); + else + nvmet_tcp_fatal_error(queue); + return; + } + + ret = nvmet_tcp_try_send(queue, NVMET_TCP_SEND_BUDGET, &ops); + if (ret > 0) { + /* transmitted message/data */ + pending = true; + } else if (ret < 0) { + if (ret == -EPIPE || ret == -ECONNRESET) + kernel_sock_shutdown(queue->sock, SHUT_RDWR); + else + nvmet_tcp_fatal_error(queue); + return; + } + + } while (pending && ops < NVMET_TCP_IO_WORK_BUDGET); + + /* + * We exahusted our budget, requeue our selves + */ + if (pending) + queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work); +} + +static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue, + struct nvmet_tcp_cmd *c) +{ + u8 hdgst = nvmet_tcp_hdgst_len(queue); + + c->queue = queue; + c->req.port = queue->port->nport; + + c->cmd_pdu = page_frag_alloc(&queue->pf_cache, + sizeof(*c->cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); + if (!c->cmd_pdu) + return -ENOMEM; + c->req.cmd = &c->cmd_pdu->cmd; + + c->rsp_pdu = page_frag_alloc(&queue->pf_cache, + sizeof(*c->rsp_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); + if (!c->rsp_pdu) + goto out_free_cmd; + c->req.rsp = &c->rsp_pdu->cqe; + + c->data_pdu = page_frag_alloc(&queue->pf_cache, + sizeof(*c->data_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); + if (!c->data_pdu) + goto out_free_rsp; + + c->r2t_pdu = page_frag_alloc(&queue->pf_cache, + sizeof(*c->r2t_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); + if (!c->r2t_pdu) + goto out_free_data; + + c->recv_msg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL; + + list_add_tail(&c->entry, &queue->free_list); + + return 0; +out_free_data: + page_frag_free(c->data_pdu); +out_free_rsp: + page_frag_free(c->rsp_pdu); +out_free_cmd: + page_frag_free(c->cmd_pdu); + return -ENOMEM; +} + +static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c) +{ + page_frag_free(c->r2t_pdu); + page_frag_free(c->data_pdu); + page_frag_free(c->rsp_pdu); + page_frag_free(c->cmd_pdu); +} + +static int nvmet_tcp_alloc_cmds(struct nvmet_tcp_queue *queue) +{ + struct nvmet_tcp_cmd *cmds; + int i, ret = -EINVAL, nr_cmds = queue->nr_cmds; + + cmds = kcalloc(nr_cmds, sizeof(struct nvmet_tcp_cmd), GFP_KERNEL); + if (!cmds) + goto out; + + for (i = 0; i < nr_cmds; i++) { + ret = nvmet_tcp_alloc_cmd(queue, cmds + i); + if (ret) + goto out_free; + } + + queue->cmds = cmds; + + return 0; +out_free: + while (--i >= 0) + nvmet_tcp_free_cmd(cmds + i); + kfree(cmds); +out: + return ret; +} + +static void nvmet_tcp_free_cmds(struct nvmet_tcp_queue *queue) +{ + struct nvmet_tcp_cmd *cmds = queue->cmds; + int i; + + for (i = 0; i < queue->nr_cmds; i++) + nvmet_tcp_free_cmd(cmds + i); + + nvmet_tcp_free_cmd(&queue->connect); + kfree(cmds); +} + +static void nvmet_tcp_restore_socket_callbacks(struct nvmet_tcp_queue *queue) +{ + struct socket *sock = queue->sock; + + write_lock_bh(&sock->sk->sk_callback_lock); + sock->sk->sk_data_ready = queue->data_ready; + sock->sk->sk_state_change = queue->state_change; + sock->sk->sk_write_space = queue->write_space; + sock->sk->sk_user_data = NULL; + write_unlock_bh(&sock->sk->sk_callback_lock); +} + +static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd) +{ + nvmet_req_uninit(&cmd->req); + nvmet_tcp_unmap_pdu_iovec(cmd); + sgl_free(cmd->req.sg); +} + +static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue) +{ + struct nvmet_tcp_cmd *cmd = queue->cmds; + int i; + + for (i = 0; i < queue->nr_cmds; i++, cmd++) { + if (nvmet_tcp_need_data_in(cmd)) + nvmet_tcp_finish_cmd(cmd); + } + + if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect)) { + /* failed in connect */ + nvmet_tcp_finish_cmd(&queue->connect); + } +} + +static void nvmet_tcp_release_queue_work(struct work_struct *w) +{ + struct nvmet_tcp_queue *queue = + container_of(w, struct nvmet_tcp_queue, release_work); + + mutex_lock(&nvmet_tcp_queue_mutex); + list_del_init(&queue->queue_list); + mutex_unlock(&nvmet_tcp_queue_mutex); + + nvmet_tcp_restore_socket_callbacks(queue); + flush_work(&queue->io_work); + + nvmet_tcp_uninit_data_in_cmds(queue); + nvmet_sq_destroy(&queue->nvme_sq); + cancel_work_sync(&queue->io_work); + sock_release(queue->sock); + nvmet_tcp_free_cmds(queue); + if (queue->hdr_digest || queue->data_digest) + nvmet_tcp_free_crypto(queue); + ida_simple_remove(&nvmet_tcp_queue_ida, queue->idx); + + kfree(queue); +} + +static void nvmet_tcp_data_ready(struct sock *sk) +{ + struct nvmet_tcp_queue *queue; + + read_lock_bh(&sk->sk_callback_lock); + queue = sk->sk_user_data; + if (likely(queue)) + queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work); + read_unlock_bh(&sk->sk_callback_lock); +} + +static void nvmet_tcp_write_space(struct sock *sk) +{ + struct nvmet_tcp_queue *queue; + + read_lock_bh(&sk->sk_callback_lock); + queue = sk->sk_user_data; + if (unlikely(!queue)) + goto out; + + if (unlikely(queue->state == NVMET_TCP_Q_CONNECTING)) { + queue->write_space(sk); + goto out; + } + + if (sk_stream_is_writeable(sk)) { + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work); + } +out: + read_unlock_bh(&sk->sk_callback_lock); +} + +static void nvmet_tcp_state_change(struct sock *sk) +{ + struct nvmet_tcp_queue *queue; + + write_lock_bh(&sk->sk_callback_lock); + queue = sk->sk_user_data; + if (!queue) + goto done; + + switch (sk->sk_state) { + case TCP_FIN_WAIT1: + case TCP_CLOSE_WAIT: + case TCP_CLOSE: + /* FALLTHRU */ + sk->sk_user_data = NULL; + nvmet_tcp_schedule_release_queue(queue); + break; + default: + pr_warn("queue %d unhandled state %d\n", + queue->idx, sk->sk_state); + } +done: + write_unlock_bh(&sk->sk_callback_lock); +} + +static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue) +{ + struct socket *sock = queue->sock; + struct linger sol = { .l_onoff = 1, .l_linger = 0 }; + int ret; + + ret = kernel_getsockname(sock, + (struct sockaddr *)&queue->sockaddr); + if (ret < 0) + return ret; + + ret = kernel_getpeername(sock, + (struct sockaddr *)&queue->sockaddr_peer); + if (ret < 0) + return ret; + + /* + * Cleanup whatever is sitting in the TCP transmit queue on socket + * close. This is done to prevent stale data from being sent should + * the network connection be restored before TCP times out. + */ + ret = kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER, + (char *)&sol, sizeof(sol)); + if (ret) + return ret; + + write_lock_bh(&sock->sk->sk_callback_lock); + sock->sk->sk_user_data = queue; + queue->data_ready = sock->sk->sk_data_ready; + sock->sk->sk_data_ready = nvmet_tcp_data_ready; + queue->state_change = sock->sk->sk_state_change; + sock->sk->sk_state_change = nvmet_tcp_state_change; + queue->write_space = sock->sk->sk_write_space; + sock->sk->sk_write_space = nvmet_tcp_write_space; + write_unlock_bh(&sock->sk->sk_callback_lock); + + return 0; +} + +static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port, + struct socket *newsock) +{ + struct nvmet_tcp_queue *queue; + int ret; + + queue = kzalloc(sizeof(*queue), GFP_KERNEL); + if (!queue) + return -ENOMEM; + + INIT_WORK(&queue->release_work, nvmet_tcp_release_queue_work); + INIT_WORK(&queue->io_work, nvmet_tcp_io_work); + queue->sock = newsock; + queue->port = port; + queue->nr_cmds = 0; + spin_lock_init(&queue->state_lock); + queue->state = NVMET_TCP_Q_CONNECTING; + INIT_LIST_HEAD(&queue->free_list); + init_llist_head(&queue->resp_list); + INIT_LIST_HEAD(&queue->resp_send_list); + + queue->idx = ida_simple_get(&nvmet_tcp_queue_ida, 0, 0, GFP_KERNEL); + if (queue->idx < 0) { + ret = queue->idx; + goto out_free_queue; + } + + ret = nvmet_tcp_alloc_cmd(queue, &queue->connect); + if (ret) + goto out_ida_remove; + + ret = nvmet_sq_init(&queue->nvme_sq); + if (ret) + goto out_free_connect; + + port->last_cpu = cpumask_next_wrap(port->last_cpu, + cpu_online_mask, -1, false); + queue->cpu = port->last_cpu; + nvmet_prepare_receive_pdu(queue); + + mutex_lock(&nvmet_tcp_queue_mutex); + list_add_tail(&queue->queue_list, &nvmet_tcp_queue_list); + mutex_unlock(&nvmet_tcp_queue_mutex); + + ret = nvmet_tcp_set_queue_sock(queue); + if (ret) + goto out_destroy_sq; + + queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work); + + return 0; +out_destroy_sq: + mutex_lock(&nvmet_tcp_queue_mutex); + list_del_init(&queue->queue_list); + mutex_unlock(&nvmet_tcp_queue_mutex); + nvmet_sq_destroy(&queue->nvme_sq); +out_free_connect: + nvmet_tcp_free_cmd(&queue->connect); +out_ida_remove: + ida_simple_remove(&nvmet_tcp_queue_ida, queue->idx); +out_free_queue: + kfree(queue); + return ret; +} + +static void nvmet_tcp_accept_work(struct work_struct *w) +{ + struct nvmet_tcp_port *port = + container_of(w, struct nvmet_tcp_port, accept_work); + struct socket *newsock; + int ret; + + while (true) { + ret = kernel_accept(port->sock, &newsock, O_NONBLOCK); + if (ret < 0) { + if (ret != -EAGAIN) + pr_warn("failed to accept err=%d\n", ret); + return; + } + ret = nvmet_tcp_alloc_queue(port, newsock); + if (ret) { + pr_err("failed to allocate queue\n"); + sock_release(newsock); + } + } +} + +static void nvmet_tcp_listen_data_ready(struct sock *sk) +{ + struct nvmet_tcp_port *port; + + read_lock_bh(&sk->sk_callback_lock); + port = sk->sk_user_data; + if (!port) + goto out; + + if (sk->sk_state == TCP_LISTEN) + schedule_work(&port->accept_work); +out: + read_unlock_bh(&sk->sk_callback_lock); +} + +static int nvmet_tcp_add_port(struct nvmet_port *nport) +{ + struct nvmet_tcp_port *port; + __kernel_sa_family_t af; + int opt, ret; + + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + switch (nport->disc_addr.adrfam) { + case NVMF_ADDR_FAMILY_IP4: + af = AF_INET; + break; + case NVMF_ADDR_FAMILY_IP6: + af = AF_INET6; + break; + default: + pr_err("address family %d not supported\n", + nport->disc_addr.adrfam); + ret = -EINVAL; + goto err_port; + } + + ret = inet_pton_with_scope(&init_net, af, nport->disc_addr.traddr, + nport->disc_addr.trsvcid, &port->addr); + if (ret) { + pr_err("malformed ip/port passed: %s:%s\n", + nport->disc_addr.traddr, nport->disc_addr.trsvcid); + goto err_port; + } + + port->nport = nport; + port->last_cpu = -1; + INIT_WORK(&port->accept_work, nvmet_tcp_accept_work); + if (port->nport->inline_data_size < 0) + port->nport->inline_data_size = NVMET_TCP_DEF_INLINE_DATA_SIZE; + + ret = sock_create(port->addr.ss_family, SOCK_STREAM, + IPPROTO_TCP, &port->sock); + if (ret) { + pr_err("failed to create a socket\n"); + goto err_port; + } + + port->sock->sk->sk_user_data = port; + port->data_ready = port->sock->sk->sk_data_ready; + port->sock->sk->sk_data_ready = nvmet_tcp_listen_data_ready; + + opt = 1; + ret = kernel_setsockopt(port->sock, IPPROTO_TCP, + TCP_NODELAY, (char *)&opt, sizeof(opt)); + if (ret) { + pr_err("failed to set TCP_NODELAY sock opt %d\n", ret); + goto err_sock; + } + + ret = kernel_setsockopt(port->sock, SOL_SOCKET, SO_REUSEADDR, + (char *)&opt, sizeof(opt)); + if (ret) { + pr_err("failed to set SO_REUSEADDR sock opt %d\n", ret); + goto err_sock; + } + + ret = kernel_bind(port->sock, (struct sockaddr *)&port->addr, + sizeof(port->addr)); + if (ret) { + pr_err("failed to bind port socket %d\n", ret); + goto err_sock; + } + + ret = kernel_listen(port->sock, 128); + if (ret) { + pr_err("failed to listen %d on port sock\n", ret); + goto err_sock; + } + + nport->priv = port; + pr_info("enabling port %d (%pISpc)\n", + le16_to_cpu(nport->disc_addr.portid), &port->addr); + + return 0; + +err_sock: + sock_release(port->sock); +err_port: + kfree(port); + return ret; +} + +static void nvmet_tcp_remove_port(struct nvmet_port *nport) +{ + struct nvmet_tcp_port *port = nport->priv; + + write_lock_bh(&port->sock->sk->sk_callback_lock); + port->sock->sk->sk_data_ready = port->data_ready; + port->sock->sk->sk_user_data = NULL; + write_unlock_bh(&port->sock->sk->sk_callback_lock); + cancel_work_sync(&port->accept_work); + + sock_release(port->sock); + kfree(port); +} + +static void nvmet_tcp_delete_ctrl(struct nvmet_ctrl *ctrl) +{ + struct nvmet_tcp_queue *queue; + + mutex_lock(&nvmet_tcp_queue_mutex); + list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list) + if (queue->nvme_sq.ctrl == ctrl) + kernel_sock_shutdown(queue->sock, SHUT_RDWR); + mutex_unlock(&nvmet_tcp_queue_mutex); +} + +static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq) +{ + struct nvmet_tcp_queue *queue = + container_of(sq, struct nvmet_tcp_queue, nvme_sq); + + if (sq->qid == 0) { + /* Let inflight controller teardown complete */ + flush_scheduled_work(); + } + + queue->nr_cmds = sq->size * 2; + if (nvmet_tcp_alloc_cmds(queue)) + return NVME_SC_INTERNAL; + return 0; +} + +static void nvmet_tcp_disc_port_addr(struct nvmet_req *req, + struct nvmet_port *nport, char *traddr) +{ + struct nvmet_tcp_port *port = nport->priv; + + if (inet_addr_is_any((struct sockaddr *)&port->addr)) { + struct nvmet_tcp_cmd *cmd = + container_of(req, struct nvmet_tcp_cmd, req); + struct nvmet_tcp_queue *queue = cmd->queue; + + sprintf(traddr, "%pISc", (struct sockaddr *)&queue->sockaddr); + } else { + memcpy(traddr, nport->disc_addr.traddr, NVMF_TRADDR_SIZE); + } +} + +static struct nvmet_fabrics_ops nvmet_tcp_ops = { + .owner = THIS_MODULE, + .type = NVMF_TRTYPE_TCP, + .msdbd = 1, + .has_keyed_sgls = 0, + .add_port = nvmet_tcp_add_port, + .remove_port = nvmet_tcp_remove_port, + .queue_response = nvmet_tcp_queue_response, + .delete_ctrl = nvmet_tcp_delete_ctrl, + .install_queue = nvmet_tcp_install_queue, + .disc_traddr = nvmet_tcp_disc_port_addr, +}; + +static int __init nvmet_tcp_init(void) +{ + int ret; + + nvmet_tcp_wq = alloc_workqueue("nvmet_tcp_wq", WQ_HIGHPRI, 0); + if (!nvmet_tcp_wq) + return -ENOMEM; + + ret = nvmet_register_transport(&nvmet_tcp_ops); + if (ret) + goto err; + + return 0; +err: + destroy_workqueue(nvmet_tcp_wq); + return ret; +} + +static void __exit nvmet_tcp_exit(void) +{ + struct nvmet_tcp_queue *queue; + + nvmet_unregister_transport(&nvmet_tcp_ops); + + flush_scheduled_work(); + mutex_lock(&nvmet_tcp_queue_mutex); + list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list) + kernel_sock_shutdown(queue->sock, SHUT_RDWR); + mutex_unlock(&nvmet_tcp_queue_mutex); + flush_scheduled_work(); + + destroy_workqueue(nvmet_tcp_wq); +} + +module_init(nvmet_tcp_init); +module_exit(nvmet_tcp_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("nvmet-transport-3"); /* 3 == NVMF_TRTYPE_TCP */ From ad4f530e95a7b88a332035b9e0c5384441356576 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:16 -0800 Subject: [PATCH 12/33] nvmet: allow configfs tcp trtype configuration Reviewed-by: Max Gurtovoy Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/configfs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index db2cb64be7ba..618bbd006544 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -34,6 +34,7 @@ static const struct nvmet_transport_name { } nvmet_transport_names[] = { { NVMF_TRTYPE_RDMA, "rdma" }, { NVMF_TRTYPE_FC, "fc" }, + { NVMF_TRTYPE_TCP, "tcp" }, { NVMF_TRTYPE_LOOP, "loop" }, }; From 3f2304f8c6d6ed97849057bd16fee99e434ca796 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 3 Dec 2018 17:52:17 -0800 Subject: [PATCH 13/33] nvme-tcp: add NVMe over TCP host driver This patch implements the NVMe over TCP host driver. It can be used to connect to remote NVMe over Fabrics subsystems over good old TCP/IP. The driver implements the TP 8000 of how nvme over fabrics capsules and data are encapsulated in nvme-tcp pdus and exchaged on top of a TCP byte stream. nvme-tcp header and data digest are supported as well. To connect to all NVMe over Fabrics controllers reachable on a given taget port over TCP use the following command: nvme connect-all -t tcp -a $IPADDR This requires the latest version of nvme-cli with TCP support. Signed-off-by: Sagi Grimberg Signed-off-by: Roy Shterman Signed-off-by: Solganik Alexander Signed-off-by: Christoph Hellwig --- drivers/nvme/host/Kconfig | 15 + drivers/nvme/host/Makefile | 3 + drivers/nvme/host/tcp.c | 2242 ++++++++++++++++++++++++++++++++++++ 3 files changed, 2260 insertions(+) create mode 100644 drivers/nvme/host/tcp.c diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 88a8b5916624..0f345e207675 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -57,3 +57,18 @@ config NVME_FC from https://github.com/linux-nvme/nvme-cli. If unsure, say N. + +config NVME_TCP + tristate "NVM Express over Fabrics TCP host driver" + depends on INET + depends on BLK_DEV_NVME + select NVME_FABRICS + help + This provides support for the NVMe over Fabrics protocol using + the TCP transport. This allows you to use remote block devices + exported using the NVMe protocol set. + + To configure a NVMe over Fabrics controller use the nvme-cli tool + from https://github.com/linux-nvme/nvme-cli. + + If unsure, say N. diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile index aea459c65ae1..8a4b671c5f0c 100644 --- a/drivers/nvme/host/Makefile +++ b/drivers/nvme/host/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_BLK_DEV_NVME) += nvme.o obj-$(CONFIG_NVME_FABRICS) += nvme-fabrics.o obj-$(CONFIG_NVME_RDMA) += nvme-rdma.o obj-$(CONFIG_NVME_FC) += nvme-fc.o +obj-$(CONFIG_NVME_TCP) += nvme-tcp.o nvme-core-y := core.o nvme-core-$(CONFIG_TRACING) += trace.o @@ -21,3 +22,5 @@ nvme-fabrics-y += fabrics.o nvme-rdma-y += rdma.o nvme-fc-y += fc.o + +nvme-tcp-y += tcp.o diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c new file mode 100644 index 000000000000..15543358e245 --- /dev/null +++ b/drivers/nvme/host/tcp.c @@ -0,0 +1,2242 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVMe over Fabrics TCP host. + * Copyright (c) 2018 Lightbits Labs. All rights reserved. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "nvme.h" +#include "fabrics.h" + +struct nvme_tcp_queue; + +enum nvme_tcp_send_state { + NVME_TCP_SEND_CMD_PDU = 0, + NVME_TCP_SEND_H2C_PDU, + NVME_TCP_SEND_DATA, + NVME_TCP_SEND_DDGST, +}; + +struct nvme_tcp_request { + struct nvme_request req; + void *pdu; + struct nvme_tcp_queue *queue; + u32 data_len; + u32 pdu_len; + u32 pdu_sent; + u16 ttag; + struct list_head entry; + u32 ddgst; + + struct bio *curr_bio; + struct iov_iter iter; + + /* send state */ + size_t offset; + size_t data_sent; + enum nvme_tcp_send_state state; +}; + +enum nvme_tcp_queue_flags { + NVME_TCP_Q_ALLOCATED = 0, + NVME_TCP_Q_LIVE = 1, +}; + +enum nvme_tcp_recv_state { + NVME_TCP_RECV_PDU = 0, + NVME_TCP_RECV_DATA, + NVME_TCP_RECV_DDGST, +}; + +struct nvme_tcp_ctrl; +struct nvme_tcp_queue { + struct socket *sock; + struct work_struct io_work; + int io_cpu; + + spinlock_t lock; + struct list_head send_list; + + /* recv state */ + void *pdu; + int pdu_remaining; + int pdu_offset; + size_t data_remaining; + size_t ddgst_remaining; + + /* send state */ + struct nvme_tcp_request *request; + + int queue_size; + size_t cmnd_capsule_len; + struct nvme_tcp_ctrl *ctrl; + unsigned long flags; + bool rd_enabled; + + bool hdr_digest; + bool data_digest; + struct ahash_request *rcv_hash; + struct ahash_request *snd_hash; + __le32 exp_ddgst; + __le32 recv_ddgst; + + struct page_frag_cache pf_cache; + + void (*state_change)(struct sock *); + void (*data_ready)(struct sock *); + void (*write_space)(struct sock *); +}; + +struct nvme_tcp_ctrl { + /* read only in the hot path */ + struct nvme_tcp_queue *queues; + struct blk_mq_tag_set tag_set; + + /* other member variables */ + struct list_head list; + struct blk_mq_tag_set admin_tag_set; + struct sockaddr_storage addr; + struct sockaddr_storage src_addr; + struct nvme_ctrl ctrl; + + struct work_struct err_work; + struct delayed_work connect_work; + struct nvme_tcp_request async_req; +}; + +static LIST_HEAD(nvme_tcp_ctrl_list); +static DEFINE_MUTEX(nvme_tcp_ctrl_mutex); +static struct workqueue_struct *nvme_tcp_wq; +static struct blk_mq_ops nvme_tcp_mq_ops; +static struct blk_mq_ops nvme_tcp_admin_mq_ops; + +static inline struct nvme_tcp_ctrl *to_tcp_ctrl(struct nvme_ctrl *ctrl) +{ + return container_of(ctrl, struct nvme_tcp_ctrl, ctrl); +} + +static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue) +{ + return queue - queue->ctrl->queues; +} + +static inline struct blk_mq_tags *nvme_tcp_tagset(struct nvme_tcp_queue *queue) +{ + u32 queue_idx = nvme_tcp_queue_id(queue); + + if (queue_idx == 0) + return queue->ctrl->admin_tag_set.tags[queue_idx]; + return queue->ctrl->tag_set.tags[queue_idx - 1]; +} + +static inline u8 nvme_tcp_hdgst_len(struct nvme_tcp_queue *queue) +{ + return queue->hdr_digest ? NVME_TCP_DIGEST_LENGTH : 0; +} + +static inline u8 nvme_tcp_ddgst_len(struct nvme_tcp_queue *queue) +{ + return queue->data_digest ? NVME_TCP_DIGEST_LENGTH : 0; +} + +static inline size_t nvme_tcp_inline_data_size(struct nvme_tcp_queue *queue) +{ + return queue->cmnd_capsule_len - sizeof(struct nvme_command); +} + +static inline bool nvme_tcp_async_req(struct nvme_tcp_request *req) +{ + return req == &req->queue->ctrl->async_req; +} + +static inline bool nvme_tcp_has_inline_data(struct nvme_tcp_request *req) +{ + struct request *rq; + unsigned int bytes; + + if (unlikely(nvme_tcp_async_req(req))) + return false; /* async events don't have a request */ + + rq = blk_mq_rq_from_pdu(req); + bytes = blk_rq_payload_bytes(rq); + + return rq_data_dir(rq) == WRITE && bytes && + bytes <= nvme_tcp_inline_data_size(req->queue); +} + +static inline struct page *nvme_tcp_req_cur_page(struct nvme_tcp_request *req) +{ + return req->iter.bvec->bv_page; +} + +static inline size_t nvme_tcp_req_cur_offset(struct nvme_tcp_request *req) +{ + return req->iter.bvec->bv_offset + req->iter.iov_offset; +} + +static inline size_t nvme_tcp_req_cur_length(struct nvme_tcp_request *req) +{ + return min_t(size_t, req->iter.bvec->bv_len - req->iter.iov_offset, + req->pdu_len - req->pdu_sent); +} + +static inline size_t nvme_tcp_req_offset(struct nvme_tcp_request *req) +{ + return req->iter.iov_offset; +} + +static inline size_t nvme_tcp_pdu_data_left(struct nvme_tcp_request *req) +{ + return rq_data_dir(blk_mq_rq_from_pdu(req)) == WRITE ? + req->pdu_len - req->pdu_sent : 0; +} + +static inline size_t nvme_tcp_pdu_last_send(struct nvme_tcp_request *req, + int len) +{ + return nvme_tcp_pdu_data_left(req) <= len; +} + +static void nvme_tcp_init_iter(struct nvme_tcp_request *req, + unsigned int dir) +{ + struct request *rq = blk_mq_rq_from_pdu(req); + struct bio_vec *vec; + unsigned int size; + int nsegs; + size_t offset; + + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) { + vec = &rq->special_vec; + nsegs = 1; + size = blk_rq_payload_bytes(rq); + offset = 0; + } else { + struct bio *bio = req->curr_bio; + + vec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); + nsegs = bio_segments(bio); + size = bio->bi_iter.bi_size; + offset = bio->bi_iter.bi_bvec_done; + } + + iov_iter_bvec(&req->iter, dir, vec, nsegs, size); + req->iter.iov_offset = offset; +} + +static inline void nvme_tcp_advance_req(struct nvme_tcp_request *req, + int len) +{ + req->data_sent += len; + req->pdu_sent += len; + iov_iter_advance(&req->iter, len); + if (!iov_iter_count(&req->iter) && + req->data_sent < req->data_len) { + req->curr_bio = req->curr_bio->bi_next; + nvme_tcp_init_iter(req, WRITE); + } +} + +static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req) +{ + struct nvme_tcp_queue *queue = req->queue; + + spin_lock(&queue->lock); + list_add_tail(&req->entry, &queue->send_list); + spin_unlock(&queue->lock); + + queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); +} + +static inline struct nvme_tcp_request * +nvme_tcp_fetch_request(struct nvme_tcp_queue *queue) +{ + struct nvme_tcp_request *req; + + spin_lock(&queue->lock); + req = list_first_entry_or_null(&queue->send_list, + struct nvme_tcp_request, entry); + if (req) + list_del(&req->entry); + spin_unlock(&queue->lock); + + return req; +} + +static inline void nvme_tcp_ddgst_final(struct ahash_request *hash, u32 *dgst) +{ + ahash_request_set_crypt(hash, NULL, (u8 *)dgst, 0); + crypto_ahash_final(hash); +} + +static inline void nvme_tcp_ddgst_update(struct ahash_request *hash, + struct page *page, off_t off, size_t len) +{ + struct scatterlist sg; + + sg_init_marker(&sg, 1); + sg_set_page(&sg, page, len, off); + ahash_request_set_crypt(hash, &sg, NULL, len); + crypto_ahash_update(hash); +} + +static inline void nvme_tcp_hdgst(struct ahash_request *hash, + void *pdu, size_t len) +{ + struct scatterlist sg; + + sg_init_one(&sg, pdu, len); + ahash_request_set_crypt(hash, &sg, pdu + len, len); + crypto_ahash_digest(hash); +} + +static int nvme_tcp_verify_hdgst(struct nvme_tcp_queue *queue, + void *pdu, size_t pdu_len) +{ + struct nvme_tcp_hdr *hdr = pdu; + __le32 recv_digest; + __le32 exp_digest; + + if (unlikely(!(hdr->flags & NVME_TCP_F_HDGST))) { + dev_err(queue->ctrl->ctrl.device, + "queue %d: header digest flag is cleared\n", + nvme_tcp_queue_id(queue)); + return -EPROTO; + } + + recv_digest = *(__le32 *)(pdu + hdr->hlen); + nvme_tcp_hdgst(queue->rcv_hash, pdu, pdu_len); + exp_digest = *(__le32 *)(pdu + hdr->hlen); + if (recv_digest != exp_digest) { + dev_err(queue->ctrl->ctrl.device, + "header digest error: recv %#x expected %#x\n", + le32_to_cpu(recv_digest), le32_to_cpu(exp_digest)); + return -EIO; + } + + return 0; +} + +static int nvme_tcp_check_ddgst(struct nvme_tcp_queue *queue, void *pdu) +{ + struct nvme_tcp_hdr *hdr = pdu; + u8 digest_len = nvme_tcp_hdgst_len(queue); + u32 len; + + len = le32_to_cpu(hdr->plen) - hdr->hlen - + ((hdr->flags & NVME_TCP_F_HDGST) ? digest_len : 0); + + if (unlikely(len && !(hdr->flags & NVME_TCP_F_DDGST))) { + dev_err(queue->ctrl->ctrl.device, + "queue %d: data digest flag is cleared\n", + nvme_tcp_queue_id(queue)); + return -EPROTO; + } + crypto_ahash_init(queue->rcv_hash); + + return 0; +} + +static void nvme_tcp_exit_request(struct blk_mq_tag_set *set, + struct request *rq, unsigned int hctx_idx) +{ + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + + page_frag_free(req->pdu); +} + +static int nvme_tcp_init_request(struct blk_mq_tag_set *set, + struct request *rq, unsigned int hctx_idx, + unsigned int numa_node) +{ + struct nvme_tcp_ctrl *ctrl = set->driver_data; + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0; + struct nvme_tcp_queue *queue = &ctrl->queues[queue_idx]; + u8 hdgst = nvme_tcp_hdgst_len(queue); + + req->pdu = page_frag_alloc(&queue->pf_cache, + sizeof(struct nvme_tcp_cmd_pdu) + hdgst, + GFP_KERNEL | __GFP_ZERO); + if (!req->pdu) + return -ENOMEM; + + req->queue = queue; + nvme_req(rq)->ctrl = &ctrl->ctrl; + + return 0; +} + +static int nvme_tcp_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int hctx_idx) +{ + struct nvme_tcp_ctrl *ctrl = data; + struct nvme_tcp_queue *queue = &ctrl->queues[hctx_idx + 1]; + + hctx->driver_data = queue; + return 0; +} + +static int nvme_tcp_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int hctx_idx) +{ + struct nvme_tcp_ctrl *ctrl = data; + struct nvme_tcp_queue *queue = &ctrl->queues[0]; + + hctx->driver_data = queue; + return 0; +} + +static enum nvme_tcp_recv_state +nvme_tcp_recv_state(struct nvme_tcp_queue *queue) +{ + return (queue->pdu_remaining) ? NVME_TCP_RECV_PDU : + (queue->ddgst_remaining) ? NVME_TCP_RECV_DDGST : + NVME_TCP_RECV_DATA; +} + +static void nvme_tcp_init_recv_ctx(struct nvme_tcp_queue *queue) +{ + queue->pdu_remaining = sizeof(struct nvme_tcp_rsp_pdu) + + nvme_tcp_hdgst_len(queue); + queue->pdu_offset = 0; + queue->data_remaining = -1; + queue->ddgst_remaining = 0; +} + +static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl) +{ + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) + return; + + queue_work(nvme_wq, &to_tcp_ctrl(ctrl)->err_work); +} + +static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, + struct nvme_completion *cqe) +{ + struct request *rq; + + rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), cqe->command_id); + if (!rq) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag 0x%x not found\n", + nvme_tcp_queue_id(queue), cqe->command_id); + nvme_tcp_error_recovery(&queue->ctrl->ctrl); + return -EINVAL; + } + + nvme_end_request(rq, cqe->status, cqe->result); + + return 0; +} + +static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue, + struct nvme_tcp_data_pdu *pdu) +{ + struct request *rq; + + rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id); + if (!rq) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x not found\n", + nvme_tcp_queue_id(queue), pdu->command_id); + return -ENOENT; + } + + if (!blk_rq_payload_bytes(rq)) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x unexpected data\n", + nvme_tcp_queue_id(queue), rq->tag); + return -EIO; + } + + queue->data_remaining = le32_to_cpu(pdu->data_length); + + return 0; + +} + +static int nvme_tcp_handle_comp(struct nvme_tcp_queue *queue, + struct nvme_tcp_rsp_pdu *pdu) +{ + struct nvme_completion *cqe = &pdu->cqe; + int ret = 0; + + /* + * AEN requests are special as they don't time out and can + * survive any kind of queue freeze and often don't respond to + * aborts. We don't even bother to allocate a struct request + * for them but rather special case them here. + */ + if (unlikely(nvme_tcp_queue_id(queue) == 0 && + cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) + nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, + &cqe->result); + else + ret = nvme_tcp_process_nvme_cqe(queue, cqe); + + return ret; +} + +static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req, + struct nvme_tcp_r2t_pdu *pdu) +{ + struct nvme_tcp_data_pdu *data = req->pdu; + struct nvme_tcp_queue *queue = req->queue; + struct request *rq = blk_mq_rq_from_pdu(req); + u8 hdgst = nvme_tcp_hdgst_len(queue); + u8 ddgst = nvme_tcp_ddgst_len(queue); + + req->pdu_len = le32_to_cpu(pdu->r2t_length); + req->pdu_sent = 0; + + if (unlikely(req->data_sent + req->pdu_len > req->data_len)) { + dev_err(queue->ctrl->ctrl.device, + "req %d r2t len %u exceeded data len %u (%zu sent)\n", + rq->tag, req->pdu_len, req->data_len, + req->data_sent); + return -EPROTO; + } + + if (unlikely(le32_to_cpu(pdu->r2t_offset) < req->data_sent)) { + dev_err(queue->ctrl->ctrl.device, + "req %d unexpected r2t offset %u (expected %zu)\n", + rq->tag, le32_to_cpu(pdu->r2t_offset), + req->data_sent); + return -EPROTO; + } + + memset(data, 0, sizeof(*data)); + data->hdr.type = nvme_tcp_h2c_data; + data->hdr.flags = NVME_TCP_F_DATA_LAST; + if (queue->hdr_digest) + data->hdr.flags |= NVME_TCP_F_HDGST; + if (queue->data_digest) + data->hdr.flags |= NVME_TCP_F_DDGST; + data->hdr.hlen = sizeof(*data); + data->hdr.pdo = data->hdr.hlen + hdgst; + data->hdr.plen = + cpu_to_le32(data->hdr.hlen + hdgst + req->pdu_len + ddgst); + data->ttag = pdu->ttag; + data->command_id = rq->tag; + data->data_offset = cpu_to_le32(req->data_sent); + data->data_length = cpu_to_le32(req->pdu_len); + return 0; +} + +static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue, + struct nvme_tcp_r2t_pdu *pdu) +{ + struct nvme_tcp_request *req; + struct request *rq; + int ret; + + rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id); + if (!rq) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x not found\n", + nvme_tcp_queue_id(queue), pdu->command_id); + return -ENOENT; + } + req = blk_mq_rq_to_pdu(rq); + + ret = nvme_tcp_setup_h2c_data_pdu(req, pdu); + if (unlikely(ret)) + return ret; + + req->state = NVME_TCP_SEND_H2C_PDU; + req->offset = 0; + + nvme_tcp_queue_request(req); + + return 0; +} + +static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb, + unsigned int *offset, size_t *len) +{ + struct nvme_tcp_hdr *hdr; + char *pdu = queue->pdu; + size_t rcv_len = min_t(size_t, *len, queue->pdu_remaining); + int ret; + + ret = skb_copy_bits(skb, *offset, + &pdu[queue->pdu_offset], rcv_len); + if (unlikely(ret)) + return ret; + + queue->pdu_remaining -= rcv_len; + queue->pdu_offset += rcv_len; + *offset += rcv_len; + *len -= rcv_len; + if (queue->pdu_remaining) + return 0; + + hdr = queue->pdu; + if (queue->hdr_digest) { + ret = nvme_tcp_verify_hdgst(queue, queue->pdu, hdr->hlen); + if (unlikely(ret)) + return ret; + } + + + if (queue->data_digest) { + ret = nvme_tcp_check_ddgst(queue, queue->pdu); + if (unlikely(ret)) + return ret; + } + + switch (hdr->type) { + case nvme_tcp_c2h_data: + ret = nvme_tcp_handle_c2h_data(queue, (void *)queue->pdu); + break; + case nvme_tcp_rsp: + nvme_tcp_init_recv_ctx(queue); + ret = nvme_tcp_handle_comp(queue, (void *)queue->pdu); + break; + case nvme_tcp_r2t: + nvme_tcp_init_recv_ctx(queue); + ret = nvme_tcp_handle_r2t(queue, (void *)queue->pdu); + break; + default: + dev_err(queue->ctrl->ctrl.device, + "unsupported pdu type (%d)\n", hdr->type); + return -EINVAL; + } + + return ret; +} + +static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb, + unsigned int *offset, size_t *len) +{ + struct nvme_tcp_data_pdu *pdu = (void *)queue->pdu; + struct nvme_tcp_request *req; + struct request *rq; + + rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id); + if (!rq) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x not found\n", + nvme_tcp_queue_id(queue), pdu->command_id); + return -ENOENT; + } + req = blk_mq_rq_to_pdu(rq); + + while (true) { + int recv_len, ret; + + recv_len = min_t(size_t, *len, queue->data_remaining); + if (!recv_len) + break; + + if (!iov_iter_count(&req->iter)) { + req->curr_bio = req->curr_bio->bi_next; + + /* + * If we don`t have any bios it means that controller + * sent more data than we requested, hence error + */ + if (!req->curr_bio) { + dev_err(queue->ctrl->ctrl.device, + "queue %d no space in request %#x", + nvme_tcp_queue_id(queue), rq->tag); + nvme_tcp_init_recv_ctx(queue); + return -EIO; + } + nvme_tcp_init_iter(req, READ); + } + + /* we can read only from what is left in this bio */ + recv_len = min_t(size_t, recv_len, + iov_iter_count(&req->iter)); + + if (queue->data_digest) + ret = skb_copy_and_hash_datagram_iter(skb, *offset, + &req->iter, recv_len, queue->rcv_hash); + else + ret = skb_copy_datagram_iter(skb, *offset, + &req->iter, recv_len); + if (ret) { + dev_err(queue->ctrl->ctrl.device, + "queue %d failed to copy request %#x data", + nvme_tcp_queue_id(queue), rq->tag); + return ret; + } + + *len -= recv_len; + *offset += recv_len; + queue->data_remaining -= recv_len; + } + + if (!queue->data_remaining) { + if (queue->data_digest) { + nvme_tcp_ddgst_final(queue->rcv_hash, &queue->exp_ddgst); + queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH; + } else { + nvme_tcp_init_recv_ctx(queue); + } + } + + return 0; +} + +static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue, + struct sk_buff *skb, unsigned int *offset, size_t *len) +{ + char *ddgst = (char *)&queue->recv_ddgst; + size_t recv_len = min_t(size_t, *len, queue->ddgst_remaining); + off_t off = NVME_TCP_DIGEST_LENGTH - queue->ddgst_remaining; + int ret; + + ret = skb_copy_bits(skb, *offset, &ddgst[off], recv_len); + if (unlikely(ret)) + return ret; + + queue->ddgst_remaining -= recv_len; + *offset += recv_len; + *len -= recv_len; + if (queue->ddgst_remaining) + return 0; + + if (queue->recv_ddgst != queue->exp_ddgst) { + dev_err(queue->ctrl->ctrl.device, + "data digest error: recv %#x expected %#x\n", + le32_to_cpu(queue->recv_ddgst), + le32_to_cpu(queue->exp_ddgst)); + return -EIO; + } + + nvme_tcp_init_recv_ctx(queue); + return 0; +} + +static int nvme_tcp_recv_skb(read_descriptor_t *desc, struct sk_buff *skb, + unsigned int offset, size_t len) +{ + struct nvme_tcp_queue *queue = desc->arg.data; + size_t consumed = len; + int result; + + while (len) { + switch (nvme_tcp_recv_state(queue)) { + case NVME_TCP_RECV_PDU: + result = nvme_tcp_recv_pdu(queue, skb, &offset, &len); + break; + case NVME_TCP_RECV_DATA: + result = nvme_tcp_recv_data(queue, skb, &offset, &len); + break; + case NVME_TCP_RECV_DDGST: + result = nvme_tcp_recv_ddgst(queue, skb, &offset, &len); + break; + default: + result = -EFAULT; + } + if (result) { + dev_err(queue->ctrl->ctrl.device, + "receive failed: %d\n", result); + queue->rd_enabled = false; + nvme_tcp_error_recovery(&queue->ctrl->ctrl); + return result; + } + } + + return consumed; +} + +static void nvme_tcp_data_ready(struct sock *sk) +{ + struct nvme_tcp_queue *queue; + + read_lock(&sk->sk_callback_lock); + queue = sk->sk_user_data; + if (likely(queue && queue->rd_enabled)) + queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); + read_unlock(&sk->sk_callback_lock); +} + +static void nvme_tcp_write_space(struct sock *sk) +{ + struct nvme_tcp_queue *queue; + + read_lock_bh(&sk->sk_callback_lock); + queue = sk->sk_user_data; + if (likely(queue && sk_stream_is_writeable(sk))) { + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); + } + read_unlock_bh(&sk->sk_callback_lock); +} + +static void nvme_tcp_state_change(struct sock *sk) +{ + struct nvme_tcp_queue *queue; + + read_lock(&sk->sk_callback_lock); + queue = sk->sk_user_data; + if (!queue) + goto done; + + switch (sk->sk_state) { + case TCP_CLOSE: + case TCP_CLOSE_WAIT: + case TCP_LAST_ACK: + case TCP_FIN_WAIT1: + case TCP_FIN_WAIT2: + /* fallthrough */ + nvme_tcp_error_recovery(&queue->ctrl->ctrl); + break; + default: + dev_info(queue->ctrl->ctrl.device, + "queue %d socket state %d\n", + nvme_tcp_queue_id(queue), sk->sk_state); + } + + queue->state_change(sk); +done: + read_unlock(&sk->sk_callback_lock); +} + +static inline void nvme_tcp_done_send_req(struct nvme_tcp_queue *queue) +{ + queue->request = NULL; +} + +static void nvme_tcp_fail_request(struct nvme_tcp_request *req) +{ + union nvme_result res = {}; + + nvme_end_request(blk_mq_rq_from_pdu(req), + NVME_SC_DATA_XFER_ERROR, res); +} + +static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) +{ + struct nvme_tcp_queue *queue = req->queue; + + while (true) { + struct page *page = nvme_tcp_req_cur_page(req); + size_t offset = nvme_tcp_req_cur_offset(req); + size_t len = nvme_tcp_req_cur_length(req); + bool last = nvme_tcp_pdu_last_send(req, len); + int ret, flags = MSG_DONTWAIT; + + if (last && !queue->data_digest) + flags |= MSG_EOR; + else + flags |= MSG_MORE; + + ret = kernel_sendpage(queue->sock, page, offset, len, flags); + if (ret <= 0) + return ret; + + nvme_tcp_advance_req(req, ret); + if (queue->data_digest) + nvme_tcp_ddgst_update(queue->snd_hash, page, + offset, ret); + + /* fully successful last write*/ + if (last && ret == len) { + if (queue->data_digest) { + nvme_tcp_ddgst_final(queue->snd_hash, + &req->ddgst); + req->state = NVME_TCP_SEND_DDGST; + req->offset = 0; + } else { + nvme_tcp_done_send_req(queue); + } + return 1; + } + } + return -EAGAIN; +} + +static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req) +{ + struct nvme_tcp_queue *queue = req->queue; + struct nvme_tcp_cmd_pdu *pdu = req->pdu; + bool inline_data = nvme_tcp_has_inline_data(req); + int flags = MSG_DONTWAIT | (inline_data ? MSG_MORE : MSG_EOR); + u8 hdgst = nvme_tcp_hdgst_len(queue); + int len = sizeof(*pdu) + hdgst - req->offset; + int ret; + + if (queue->hdr_digest && !req->offset) + nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu)); + + ret = kernel_sendpage(queue->sock, virt_to_page(pdu), + offset_in_page(pdu) + req->offset, len, flags); + if (unlikely(ret <= 0)) + return ret; + + len -= ret; + if (!len) { + if (inline_data) { + req->state = NVME_TCP_SEND_DATA; + if (queue->data_digest) + crypto_ahash_init(queue->snd_hash); + nvme_tcp_init_iter(req, WRITE); + } else { + nvme_tcp_done_send_req(queue); + } + return 1; + } + req->offset += ret; + + return -EAGAIN; +} + +static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req) +{ + struct nvme_tcp_queue *queue = req->queue; + struct nvme_tcp_data_pdu *pdu = req->pdu; + u8 hdgst = nvme_tcp_hdgst_len(queue); + int len = sizeof(*pdu) - req->offset + hdgst; + int ret; + + if (queue->hdr_digest && !req->offset) + nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu)); + + ret = kernel_sendpage(queue->sock, virt_to_page(pdu), + offset_in_page(pdu) + req->offset, len, + MSG_DONTWAIT | MSG_MORE); + if (unlikely(ret <= 0)) + return ret; + + len -= ret; + if (!len) { + req->state = NVME_TCP_SEND_DATA; + if (queue->data_digest) + crypto_ahash_init(queue->snd_hash); + if (!req->data_sent) + nvme_tcp_init_iter(req, WRITE); + return 1; + } + req->offset += ret; + + return -EAGAIN; +} + +static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req) +{ + struct nvme_tcp_queue *queue = req->queue; + int ret; + struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_EOR }; + struct kvec iov = { + .iov_base = &req->ddgst + req->offset, + .iov_len = NVME_TCP_DIGEST_LENGTH - req->offset + }; + + ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); + if (unlikely(ret <= 0)) + return ret; + + if (req->offset + ret == NVME_TCP_DIGEST_LENGTH) { + nvme_tcp_done_send_req(queue); + return 1; + } + + req->offset += ret; + return -EAGAIN; +} + +static int nvme_tcp_try_send(struct nvme_tcp_queue *queue) +{ + struct nvme_tcp_request *req; + int ret = 1; + + if (!queue->request) { + queue->request = nvme_tcp_fetch_request(queue); + if (!queue->request) + return 0; + } + req = queue->request; + + if (req->state == NVME_TCP_SEND_CMD_PDU) { + ret = nvme_tcp_try_send_cmd_pdu(req); + if (ret <= 0) + goto done; + if (!nvme_tcp_has_inline_data(req)) + return ret; + } + + if (req->state == NVME_TCP_SEND_H2C_PDU) { + ret = nvme_tcp_try_send_data_pdu(req); + if (ret <= 0) + goto done; + } + + if (req->state == NVME_TCP_SEND_DATA) { + ret = nvme_tcp_try_send_data(req); + if (ret <= 0) + goto done; + } + + if (req->state == NVME_TCP_SEND_DDGST) + ret = nvme_tcp_try_send_ddgst(req); +done: + if (ret == -EAGAIN) + ret = 0; + return ret; +} + +static int nvme_tcp_try_recv(struct nvme_tcp_queue *queue) +{ + struct sock *sk = queue->sock->sk; + read_descriptor_t rd_desc; + int consumed; + + rd_desc.arg.data = queue; + rd_desc.count = 1; + lock_sock(sk); + consumed = tcp_read_sock(sk, &rd_desc, nvme_tcp_recv_skb); + release_sock(sk); + return consumed; +} + +static void nvme_tcp_io_work(struct work_struct *w) +{ + struct nvme_tcp_queue *queue = + container_of(w, struct nvme_tcp_queue, io_work); + unsigned long start = jiffies + msecs_to_jiffies(1); + + do { + bool pending = false; + int result; + + result = nvme_tcp_try_send(queue); + if (result > 0) { + pending = true; + } else if (unlikely(result < 0)) { + dev_err(queue->ctrl->ctrl.device, + "failed to send request %d\n", result); + if (result != -EPIPE) + nvme_tcp_fail_request(queue->request); + nvme_tcp_done_send_req(queue); + return; + } + + result = nvme_tcp_try_recv(queue); + if (result > 0) + pending = true; + + if (!pending) + return; + + } while (time_after(jiffies, start)); /* quota is exhausted */ + + queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); +} + +static void nvme_tcp_free_crypto(struct nvme_tcp_queue *queue) +{ + struct crypto_ahash *tfm = crypto_ahash_reqtfm(queue->rcv_hash); + + ahash_request_free(queue->rcv_hash); + ahash_request_free(queue->snd_hash); + crypto_free_ahash(tfm); +} + +static int nvme_tcp_alloc_crypto(struct nvme_tcp_queue *queue) +{ + struct crypto_ahash *tfm; + + tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + queue->snd_hash = ahash_request_alloc(tfm, GFP_KERNEL); + if (!queue->snd_hash) + goto free_tfm; + ahash_request_set_callback(queue->snd_hash, 0, NULL, NULL); + + queue->rcv_hash = ahash_request_alloc(tfm, GFP_KERNEL); + if (!queue->rcv_hash) + goto free_snd_hash; + ahash_request_set_callback(queue->rcv_hash, 0, NULL, NULL); + + return 0; +free_snd_hash: + ahash_request_free(queue->snd_hash); +free_tfm: + crypto_free_ahash(tfm); + return -ENOMEM; +} + +static void nvme_tcp_free_async_req(struct nvme_tcp_ctrl *ctrl) +{ + struct nvme_tcp_request *async = &ctrl->async_req; + + page_frag_free(async->pdu); +} + +static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl) +{ + struct nvme_tcp_queue *queue = &ctrl->queues[0]; + struct nvme_tcp_request *async = &ctrl->async_req; + u8 hdgst = nvme_tcp_hdgst_len(queue); + + async->pdu = page_frag_alloc(&queue->pf_cache, + sizeof(struct nvme_tcp_cmd_pdu) + hdgst, + GFP_KERNEL | __GFP_ZERO); + if (!async->pdu) + return -ENOMEM; + + async->queue = &ctrl->queues[0]; + return 0; +} + +static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct nvme_tcp_queue *queue = &ctrl->queues[qid]; + + if (!test_and_clear_bit(NVME_TCP_Q_ALLOCATED, &queue->flags)) + return; + + if (queue->hdr_digest || queue->data_digest) + nvme_tcp_free_crypto(queue); + + sock_release(queue->sock); + kfree(queue->pdu); +} + +static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) +{ + struct nvme_tcp_icreq_pdu *icreq; + struct nvme_tcp_icresp_pdu *icresp; + struct msghdr msg = {}; + struct kvec iov; + bool ctrl_hdgst, ctrl_ddgst; + int ret; + + icreq = kzalloc(sizeof(*icreq), GFP_KERNEL); + if (!icreq) + return -ENOMEM; + + icresp = kzalloc(sizeof(*icresp), GFP_KERNEL); + if (!icresp) { + ret = -ENOMEM; + goto free_icreq; + } + + icreq->hdr.type = nvme_tcp_icreq; + icreq->hdr.hlen = sizeof(*icreq); + icreq->hdr.pdo = 0; + icreq->hdr.plen = cpu_to_le32(icreq->hdr.hlen); + icreq->pfv = cpu_to_le16(NVME_TCP_PFV_1_0); + icreq->maxr2t = 0; /* single inflight r2t supported */ + icreq->hpda = 0; /* no alignment constraint */ + if (queue->hdr_digest) + icreq->digest |= NVME_TCP_HDR_DIGEST_ENABLE; + if (queue->data_digest) + icreq->digest |= NVME_TCP_DATA_DIGEST_ENABLE; + + iov.iov_base = icreq; + iov.iov_len = sizeof(*icreq); + ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); + if (ret < 0) + goto free_icresp; + + memset(&msg, 0, sizeof(msg)); + iov.iov_base = icresp; + iov.iov_len = sizeof(*icresp); + ret = kernel_recvmsg(queue->sock, &msg, &iov, 1, + iov.iov_len, msg.msg_flags); + if (ret < 0) + goto free_icresp; + + ret = -EINVAL; + if (icresp->hdr.type != nvme_tcp_icresp) { + pr_err("queue %d: bad type returned %d\n", + nvme_tcp_queue_id(queue), icresp->hdr.type); + goto free_icresp; + } + + if (le32_to_cpu(icresp->hdr.plen) != sizeof(*icresp)) { + pr_err("queue %d: bad pdu length returned %d\n", + nvme_tcp_queue_id(queue), icresp->hdr.plen); + goto free_icresp; + } + + if (icresp->pfv != NVME_TCP_PFV_1_0) { + pr_err("queue %d: bad pfv returned %d\n", + nvme_tcp_queue_id(queue), icresp->pfv); + goto free_icresp; + } + + ctrl_ddgst = !!(icresp->digest & NVME_TCP_DATA_DIGEST_ENABLE); + if ((queue->data_digest && !ctrl_ddgst) || + (!queue->data_digest && ctrl_ddgst)) { + pr_err("queue %d: data digest mismatch host: %s ctrl: %s\n", + nvme_tcp_queue_id(queue), + queue->data_digest ? "enabled" : "disabled", + ctrl_ddgst ? "enabled" : "disabled"); + goto free_icresp; + } + + ctrl_hdgst = !!(icresp->digest & NVME_TCP_HDR_DIGEST_ENABLE); + if ((queue->hdr_digest && !ctrl_hdgst) || + (!queue->hdr_digest && ctrl_hdgst)) { + pr_err("queue %d: header digest mismatch host: %s ctrl: %s\n", + nvme_tcp_queue_id(queue), + queue->hdr_digest ? "enabled" : "disabled", + ctrl_hdgst ? "enabled" : "disabled"); + goto free_icresp; + } + + if (icresp->cpda != 0) { + pr_err("queue %d: unsupported cpda returned %d\n", + nvme_tcp_queue_id(queue), icresp->cpda); + goto free_icresp; + } + + ret = 0; +free_icresp: + kfree(icresp); +free_icreq: + kfree(icreq); + return ret; +} + +static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, + int qid, size_t queue_size) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct nvme_tcp_queue *queue = &ctrl->queues[qid]; + struct linger sol = { .l_onoff = 1, .l_linger = 0 }; + int ret, opt, rcv_pdu_size; + + queue->ctrl = ctrl; + INIT_LIST_HEAD(&queue->send_list); + spin_lock_init(&queue->lock); + INIT_WORK(&queue->io_work, nvme_tcp_io_work); + queue->queue_size = queue_size; + + if (qid > 0) + queue->cmnd_capsule_len = ctrl->ctrl.ioccsz * 16; + else + queue->cmnd_capsule_len = sizeof(struct nvme_command) + + NVME_TCP_ADMIN_CCSZ; + + ret = sock_create(ctrl->addr.ss_family, SOCK_STREAM, + IPPROTO_TCP, &queue->sock); + if (ret) { + dev_err(ctrl->ctrl.device, + "failed to create socket: %d\n", ret); + return ret; + } + + /* Single syn retry */ + opt = 1; + ret = kernel_setsockopt(queue->sock, IPPROTO_TCP, TCP_SYNCNT, + (char *)&opt, sizeof(opt)); + if (ret) { + dev_err(ctrl->ctrl.device, + "failed to set TCP_SYNCNT sock opt %d\n", ret); + goto err_sock; + } + + /* Set TCP no delay */ + opt = 1; + ret = kernel_setsockopt(queue->sock, IPPROTO_TCP, + TCP_NODELAY, (char *)&opt, sizeof(opt)); + if (ret) { + dev_err(ctrl->ctrl.device, + "failed to set TCP_NODELAY sock opt %d\n", ret); + goto err_sock; + } + + /* + * Cleanup whatever is sitting in the TCP transmit queue on socket + * close. This is done to prevent stale data from being sent should + * the network connection be restored before TCP times out. + */ + ret = kernel_setsockopt(queue->sock, SOL_SOCKET, SO_LINGER, + (char *)&sol, sizeof(sol)); + if (ret) { + dev_err(ctrl->ctrl.device, + "failed to set SO_LINGER sock opt %d\n", ret); + goto err_sock; + } + + queue->sock->sk->sk_allocation = GFP_ATOMIC; + queue->io_cpu = (qid == 0) ? 0 : qid - 1; + queue->request = NULL; + queue->data_remaining = 0; + queue->ddgst_remaining = 0; + queue->pdu_remaining = 0; + queue->pdu_offset = 0; + sk_set_memalloc(queue->sock->sk); + + if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR) { + ret = kernel_bind(queue->sock, (struct sockaddr *)&ctrl->src_addr, + sizeof(ctrl->src_addr)); + if (ret) { + dev_err(ctrl->ctrl.device, + "failed to bind queue %d socket %d\n", + qid, ret); + goto err_sock; + } + } + + queue->hdr_digest = nctrl->opts->hdr_digest; + queue->data_digest = nctrl->opts->data_digest; + if (queue->hdr_digest || queue->data_digest) { + ret = nvme_tcp_alloc_crypto(queue); + if (ret) { + dev_err(ctrl->ctrl.device, + "failed to allocate queue %d crypto\n", qid); + goto err_sock; + } + } + + rcv_pdu_size = sizeof(struct nvme_tcp_rsp_pdu) + + nvme_tcp_hdgst_len(queue); + queue->pdu = kmalloc(rcv_pdu_size, GFP_KERNEL); + if (!queue->pdu) { + ret = -ENOMEM; + goto err_crypto; + } + + dev_dbg(ctrl->ctrl.device, "connecting queue %d\n", + nvme_tcp_queue_id(queue)); + + ret = kernel_connect(queue->sock, (struct sockaddr *)&ctrl->addr, + sizeof(ctrl->addr), 0); + if (ret) { + dev_err(ctrl->ctrl.device, + "failed to connect socket: %d\n", ret); + goto err_rcv_pdu; + } + + ret = nvme_tcp_init_connection(queue); + if (ret) + goto err_init_connect; + + queue->rd_enabled = true; + set_bit(NVME_TCP_Q_ALLOCATED, &queue->flags); + nvme_tcp_init_recv_ctx(queue); + + write_lock_bh(&queue->sock->sk->sk_callback_lock); + queue->sock->sk->sk_user_data = queue; + queue->state_change = queue->sock->sk->sk_state_change; + queue->data_ready = queue->sock->sk->sk_data_ready; + queue->write_space = queue->sock->sk->sk_write_space; + queue->sock->sk->sk_data_ready = nvme_tcp_data_ready; + queue->sock->sk->sk_state_change = nvme_tcp_state_change; + queue->sock->sk->sk_write_space = nvme_tcp_write_space; + write_unlock_bh(&queue->sock->sk->sk_callback_lock); + + return 0; + +err_init_connect: + kernel_sock_shutdown(queue->sock, SHUT_RDWR); +err_rcv_pdu: + kfree(queue->pdu); +err_crypto: + if (queue->hdr_digest || queue->data_digest) + nvme_tcp_free_crypto(queue); +err_sock: + sock_release(queue->sock); + queue->sock = NULL; + return ret; +} + +static void nvme_tcp_restore_sock_calls(struct nvme_tcp_queue *queue) +{ + struct socket *sock = queue->sock; + + write_lock_bh(&sock->sk->sk_callback_lock); + sock->sk->sk_user_data = NULL; + sock->sk->sk_data_ready = queue->data_ready; + sock->sk->sk_state_change = queue->state_change; + sock->sk->sk_write_space = queue->write_space; + write_unlock_bh(&sock->sk->sk_callback_lock); +} + +static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue) +{ + kernel_sock_shutdown(queue->sock, SHUT_RDWR); + nvme_tcp_restore_sock_calls(queue); + cancel_work_sync(&queue->io_work); +} + +static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct nvme_tcp_queue *queue = &ctrl->queues[qid]; + + if (!test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags)) + return; + + __nvme_tcp_stop_queue(queue); +} + +static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + int ret; + + if (idx) + ret = nvmf_connect_io_queue(nctrl, idx); + else + ret = nvmf_connect_admin_queue(nctrl); + + if (!ret) { + set_bit(NVME_TCP_Q_LIVE, &ctrl->queues[idx].flags); + } else { + __nvme_tcp_stop_queue(&ctrl->queues[idx]); + dev_err(nctrl->device, + "failed to connect queue: %d ret=%d\n", idx, ret); + } + return ret; +} + +static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, + bool admin) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct blk_mq_tag_set *set; + int ret; + + if (admin) { + set = &ctrl->admin_tag_set; + memset(set, 0, sizeof(*set)); + set->ops = &nvme_tcp_admin_mq_ops; + set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; + set->reserved_tags = 2; /* connect + keep-alive */ + set->numa_node = NUMA_NO_NODE; + set->cmd_size = sizeof(struct nvme_tcp_request); + set->driver_data = ctrl; + set->nr_hw_queues = 1; + set->timeout = ADMIN_TIMEOUT; + } else { + set = &ctrl->tag_set; + memset(set, 0, sizeof(*set)); + set->ops = &nvme_tcp_mq_ops; + set->queue_depth = nctrl->sqsize + 1; + set->reserved_tags = 1; /* fabric connect */ + set->numa_node = NUMA_NO_NODE; + set->flags = BLK_MQ_F_SHOULD_MERGE; + set->cmd_size = sizeof(struct nvme_tcp_request); + set->driver_data = ctrl; + set->nr_hw_queues = nctrl->queue_count - 1; + set->timeout = NVME_IO_TIMEOUT; + } + + ret = blk_mq_alloc_tag_set(set); + if (ret) + return ERR_PTR(ret); + + return set; +} + +static void nvme_tcp_free_admin_queue(struct nvme_ctrl *ctrl) +{ + if (to_tcp_ctrl(ctrl)->async_req.pdu) { + nvme_tcp_free_async_req(to_tcp_ctrl(ctrl)); + to_tcp_ctrl(ctrl)->async_req.pdu = NULL; + } + + nvme_tcp_free_queue(ctrl, 0); +} + +static void nvme_tcp_free_io_queues(struct nvme_ctrl *ctrl) +{ + int i; + + for (i = 1; i < ctrl->queue_count; i++) + nvme_tcp_free_queue(ctrl, i); +} + +static void nvme_tcp_stop_io_queues(struct nvme_ctrl *ctrl) +{ + int i; + + for (i = 1; i < ctrl->queue_count; i++) + nvme_tcp_stop_queue(ctrl, i); +} + +static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl) +{ + int i, ret = 0; + + for (i = 1; i < ctrl->queue_count; i++) { + ret = nvme_tcp_start_queue(ctrl, i); + if (ret) + goto out_stop_queues; + } + + return 0; + +out_stop_queues: + for (i--; i >= 1; i--) + nvme_tcp_stop_queue(ctrl, i); + return ret; +} + +static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl) +{ + int ret; + + ret = nvme_tcp_alloc_queue(ctrl, 0, NVME_AQ_DEPTH); + if (ret) + return ret; + + ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl)); + if (ret) + goto out_free_queue; + + return 0; + +out_free_queue: + nvme_tcp_free_queue(ctrl, 0); + return ret; +} + +static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) +{ + int i, ret; + + for (i = 1; i < ctrl->queue_count; i++) { + ret = nvme_tcp_alloc_queue(ctrl, i, + ctrl->sqsize + 1); + if (ret) + goto out_free_queues; + } + + return 0; + +out_free_queues: + for (i--; i >= 1; i--) + nvme_tcp_free_queue(ctrl, i); + + return ret; +} + +static unsigned int nvme_tcp_nr_io_queues(struct nvme_ctrl *ctrl) +{ + return min(ctrl->queue_count - 1, num_online_cpus()); +} + +static int nvme_alloc_io_queues(struct nvme_ctrl *ctrl) +{ + unsigned int nr_io_queues; + int ret; + + nr_io_queues = nvme_tcp_nr_io_queues(ctrl); + ret = nvme_set_queue_count(ctrl, &nr_io_queues); + if (ret) + return ret; + + ctrl->queue_count = nr_io_queues + 1; + if (ctrl->queue_count < 2) + return 0; + + dev_info(ctrl->device, + "creating %d I/O queues.\n", nr_io_queues); + + return nvme_tcp_alloc_io_queues(ctrl); +} + +static void nvme_tcp_destroy_io_queues(struct nvme_ctrl *ctrl, bool remove) +{ + nvme_tcp_stop_io_queues(ctrl); + if (remove) { + if (ctrl->ops->flags & NVME_F_FABRICS) + blk_cleanup_queue(ctrl->connect_q); + blk_mq_free_tag_set(ctrl->tagset); + } + nvme_tcp_free_io_queues(ctrl); +} + +static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) +{ + int ret; + + ret = nvme_alloc_io_queues(ctrl); + if (ret) + return ret; + + if (new) { + ctrl->tagset = nvme_tcp_alloc_tagset(ctrl, false); + if (IS_ERR(ctrl->tagset)) { + ret = PTR_ERR(ctrl->tagset); + goto out_free_io_queues; + } + + if (ctrl->ops->flags & NVME_F_FABRICS) { + ctrl->connect_q = blk_mq_init_queue(ctrl->tagset); + if (IS_ERR(ctrl->connect_q)) { + ret = PTR_ERR(ctrl->connect_q); + goto out_free_tag_set; + } + } + } else { + blk_mq_update_nr_hw_queues(ctrl->tagset, + ctrl->queue_count - 1); + } + + ret = nvme_tcp_start_io_queues(ctrl); + if (ret) + goto out_cleanup_connect_q; + + return 0; + +out_cleanup_connect_q: + if (new && (ctrl->ops->flags & NVME_F_FABRICS)) + blk_cleanup_queue(ctrl->connect_q); +out_free_tag_set: + if (new) + blk_mq_free_tag_set(ctrl->tagset); +out_free_io_queues: + nvme_tcp_free_io_queues(ctrl); + return ret; +} + +static void nvme_tcp_destroy_admin_queue(struct nvme_ctrl *ctrl, bool remove) +{ + nvme_tcp_stop_queue(ctrl, 0); + if (remove) { + free_opal_dev(ctrl->opal_dev); + blk_cleanup_queue(ctrl->admin_q); + blk_mq_free_tag_set(ctrl->admin_tagset); + } + nvme_tcp_free_admin_queue(ctrl); +} + +static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new) +{ + int error; + + error = nvme_tcp_alloc_admin_queue(ctrl); + if (error) + return error; + + if (new) { + ctrl->admin_tagset = nvme_tcp_alloc_tagset(ctrl, true); + if (IS_ERR(ctrl->admin_tagset)) { + error = PTR_ERR(ctrl->admin_tagset); + goto out_free_queue; + } + + ctrl->admin_q = blk_mq_init_queue(ctrl->admin_tagset); + if (IS_ERR(ctrl->admin_q)) { + error = PTR_ERR(ctrl->admin_q); + goto out_free_tagset; + } + } + + error = nvme_tcp_start_queue(ctrl, 0); + if (error) + goto out_cleanup_queue; + + error = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap); + if (error) { + dev_err(ctrl->device, + "prop_get NVME_REG_CAP failed\n"); + goto out_stop_queue; + } + + ctrl->sqsize = min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize); + + error = nvme_enable_ctrl(ctrl, ctrl->cap); + if (error) + goto out_stop_queue; + + error = nvme_init_identify(ctrl); + if (error) + goto out_stop_queue; + + return 0; + +out_stop_queue: + nvme_tcp_stop_queue(ctrl, 0); +out_cleanup_queue: + if (new) + blk_cleanup_queue(ctrl->admin_q); +out_free_tagset: + if (new) + blk_mq_free_tag_set(ctrl->admin_tagset); +out_free_queue: + nvme_tcp_free_admin_queue(ctrl); + return error; +} + +static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl, + bool remove) +{ + blk_mq_quiesce_queue(ctrl->admin_q); + nvme_tcp_stop_queue(ctrl, 0); + blk_mq_tagset_busy_iter(ctrl->admin_tagset, nvme_cancel_request, ctrl); + blk_mq_unquiesce_queue(ctrl->admin_q); + nvme_tcp_destroy_admin_queue(ctrl, remove); +} + +static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, + bool remove) +{ + if (ctrl->queue_count <= 1) + return; + nvme_stop_queues(ctrl); + nvme_tcp_stop_io_queues(ctrl); + blk_mq_tagset_busy_iter(ctrl->tagset, nvme_cancel_request, ctrl); + if (remove) + nvme_start_queues(ctrl); + nvme_tcp_destroy_io_queues(ctrl, remove); +} + +static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl) +{ + /* If we are resetting/deleting then do nothing */ + if (ctrl->state != NVME_CTRL_CONNECTING) { + WARN_ON_ONCE(ctrl->state == NVME_CTRL_NEW || + ctrl->state == NVME_CTRL_LIVE); + return; + } + + if (nvmf_should_reconnect(ctrl)) { + dev_info(ctrl->device, "Reconnecting in %d seconds...\n", + ctrl->opts->reconnect_delay); + queue_delayed_work(nvme_wq, &to_tcp_ctrl(ctrl)->connect_work, + ctrl->opts->reconnect_delay * HZ); + } else { + dev_info(ctrl->device, "Removing controller...\n"); + nvme_delete_ctrl(ctrl); + } +} + +static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new) +{ + struct nvmf_ctrl_options *opts = ctrl->opts; + int ret = -EINVAL; + + ret = nvme_tcp_configure_admin_queue(ctrl, new); + if (ret) + return ret; + + if (ctrl->icdoff) { + dev_err(ctrl->device, "icdoff is not supported!\n"); + goto destroy_admin; + } + + if (opts->queue_size > ctrl->sqsize + 1) + dev_warn(ctrl->device, + "queue_size %zu > ctrl sqsize %u, clamping down\n", + opts->queue_size, ctrl->sqsize + 1); + + if (ctrl->sqsize + 1 > ctrl->maxcmd) { + dev_warn(ctrl->device, + "sqsize %u > ctrl maxcmd %u, clamping down\n", + ctrl->sqsize + 1, ctrl->maxcmd); + ctrl->sqsize = ctrl->maxcmd - 1; + } + + if (ctrl->queue_count > 1) { + ret = nvme_tcp_configure_io_queues(ctrl, new); + if (ret) + goto destroy_admin; + } + + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) { + /* state change failure is ok if we're in DELETING state */ + WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING); + ret = -EINVAL; + goto destroy_io; + } + + nvme_start_ctrl(ctrl); + return 0; + +destroy_io: + if (ctrl->queue_count > 1) + nvme_tcp_destroy_io_queues(ctrl, new); +destroy_admin: + nvme_tcp_stop_queue(ctrl, 0); + nvme_tcp_destroy_admin_queue(ctrl, new); + return ret; +} + +static void nvme_tcp_reconnect_ctrl_work(struct work_struct *work) +{ + struct nvme_tcp_ctrl *tcp_ctrl = container_of(to_delayed_work(work), + struct nvme_tcp_ctrl, connect_work); + struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl; + + ++ctrl->nr_reconnects; + + if (nvme_tcp_setup_ctrl(ctrl, false)) + goto requeue; + + dev_info(ctrl->device, "Successfully reconnected (%d attepmpt)\n", + ctrl->nr_reconnects); + + ctrl->nr_reconnects = 0; + + return; + +requeue: + dev_info(ctrl->device, "Failed reconnect attempt %d\n", + ctrl->nr_reconnects); + nvme_tcp_reconnect_or_remove(ctrl); +} + +static void nvme_tcp_error_recovery_work(struct work_struct *work) +{ + struct nvme_tcp_ctrl *tcp_ctrl = container_of(work, + struct nvme_tcp_ctrl, err_work); + struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl; + + nvme_stop_keep_alive(ctrl); + nvme_tcp_teardown_io_queues(ctrl, false); + /* unquiesce to fail fast pending requests */ + nvme_start_queues(ctrl); + nvme_tcp_teardown_admin_queue(ctrl, false); + + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) { + /* state change failure is ok if we're in DELETING state */ + WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING); + return; + } + + nvme_tcp_reconnect_or_remove(ctrl); +} + +static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown) +{ + nvme_tcp_teardown_io_queues(ctrl, shutdown); + if (shutdown) + nvme_shutdown_ctrl(ctrl); + else + nvme_disable_ctrl(ctrl, ctrl->cap); + nvme_tcp_teardown_admin_queue(ctrl, shutdown); +} + +static void nvme_tcp_delete_ctrl(struct nvme_ctrl *ctrl) +{ + nvme_tcp_teardown_ctrl(ctrl, true); +} + +static void nvme_reset_ctrl_work(struct work_struct *work) +{ + struct nvme_ctrl *ctrl = + container_of(work, struct nvme_ctrl, reset_work); + + nvme_stop_ctrl(ctrl); + nvme_tcp_teardown_ctrl(ctrl, false); + + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) { + /* state change failure is ok if we're in DELETING state */ + WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING); + return; + } + + if (nvme_tcp_setup_ctrl(ctrl, false)) + goto out_fail; + + return; + +out_fail: + ++ctrl->nr_reconnects; + nvme_tcp_reconnect_or_remove(ctrl); +} + +static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl) +{ + cancel_work_sync(&to_tcp_ctrl(ctrl)->err_work); + cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work); +} + +static void nvme_tcp_free_ctrl(struct nvme_ctrl *nctrl) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + + if (list_empty(&ctrl->list)) + goto free_ctrl; + + mutex_lock(&nvme_tcp_ctrl_mutex); + list_del(&ctrl->list); + mutex_unlock(&nvme_tcp_ctrl_mutex); + + nvmf_free_options(nctrl->opts); +free_ctrl: + kfree(ctrl->queues); + kfree(ctrl); +} + +static void nvme_tcp_set_sg_null(struct nvme_command *c) +{ + struct nvme_sgl_desc *sg = &c->common.dptr.sgl; + + sg->addr = 0; + sg->length = 0; + sg->type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) | + NVME_SGL_FMT_TRANSPORT_A; +} + +static void nvme_tcp_set_sg_inline(struct nvme_tcp_queue *queue, + struct nvme_command *c, u32 data_len) +{ + struct nvme_sgl_desc *sg = &c->common.dptr.sgl; + + sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff); + sg->length = cpu_to_le32(data_len); + sg->type = (NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET; +} + +static void nvme_tcp_set_sg_host_data(struct nvme_command *c, + u32 data_len) +{ + struct nvme_sgl_desc *sg = &c->common.dptr.sgl; + + sg->addr = 0; + sg->length = cpu_to_le32(data_len); + sg->type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) | + NVME_SGL_FMT_TRANSPORT_A; +} + +static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(arg); + struct nvme_tcp_queue *queue = &ctrl->queues[0]; + struct nvme_tcp_cmd_pdu *pdu = ctrl->async_req.pdu; + struct nvme_command *cmd = &pdu->cmd; + u8 hdgst = nvme_tcp_hdgst_len(queue); + + memset(pdu, 0, sizeof(*pdu)); + pdu->hdr.type = nvme_tcp_cmd; + if (queue->hdr_digest) + pdu->hdr.flags |= NVME_TCP_F_HDGST; + pdu->hdr.hlen = sizeof(*pdu); + pdu->hdr.plen = cpu_to_le32(pdu->hdr.hlen + hdgst); + + cmd->common.opcode = nvme_admin_async_event; + cmd->common.command_id = NVME_AQ_BLK_MQ_DEPTH; + cmd->common.flags |= NVME_CMD_SGL_METABUF; + nvme_tcp_set_sg_null(cmd); + + ctrl->async_req.state = NVME_TCP_SEND_CMD_PDU; + ctrl->async_req.offset = 0; + ctrl->async_req.curr_bio = NULL; + ctrl->async_req.data_len = 0; + + nvme_tcp_queue_request(&ctrl->async_req); +} + +static enum blk_eh_timer_return +nvme_tcp_timeout(struct request *rq, bool reserved) +{ + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_tcp_ctrl *ctrl = req->queue->ctrl; + struct nvme_tcp_cmd_pdu *pdu = req->pdu; + + dev_dbg(ctrl->ctrl.device, + "queue %d: timeout request %#x type %d\n", + nvme_tcp_queue_id(req->queue), rq->tag, + pdu->hdr.type); + + if (ctrl->ctrl.state != NVME_CTRL_LIVE) { + union nvme_result res = {}; + + nvme_req(rq)->flags |= NVME_REQ_CANCELLED; + nvme_end_request(rq, NVME_SC_ABORT_REQ, res); + return BLK_EH_DONE; + } + + /* queue error recovery */ + nvme_tcp_error_recovery(&ctrl->ctrl); + + return BLK_EH_RESET_TIMER; +} + +static blk_status_t nvme_tcp_map_data(struct nvme_tcp_queue *queue, + struct request *rq) +{ + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_tcp_cmd_pdu *pdu = req->pdu; + struct nvme_command *c = &pdu->cmd; + + c->common.flags |= NVME_CMD_SGL_METABUF; + + if (rq_data_dir(rq) == WRITE && req->data_len && + req->data_len <= nvme_tcp_inline_data_size(queue)) + nvme_tcp_set_sg_inline(queue, c, req->data_len); + else + nvme_tcp_set_sg_host_data(c, req->data_len); + + return 0; +} + +static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns, + struct request *rq) +{ + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_tcp_cmd_pdu *pdu = req->pdu; + struct nvme_tcp_queue *queue = req->queue; + u8 hdgst = nvme_tcp_hdgst_len(queue), ddgst = 0; + blk_status_t ret; + + ret = nvme_setup_cmd(ns, rq, &pdu->cmd); + if (ret) + return ret; + + req->state = NVME_TCP_SEND_CMD_PDU; + req->offset = 0; + req->data_sent = 0; + req->pdu_len = 0; + req->pdu_sent = 0; + req->data_len = blk_rq_payload_bytes(rq); + req->curr_bio = rq->bio; + + if (rq_data_dir(rq) == WRITE && + req->data_len <= nvme_tcp_inline_data_size(queue)) + req->pdu_len = req->data_len; + else if (req->curr_bio) + nvme_tcp_init_iter(req, READ); + + pdu->hdr.type = nvme_tcp_cmd; + pdu->hdr.flags = 0; + if (queue->hdr_digest) + pdu->hdr.flags |= NVME_TCP_F_HDGST; + if (queue->data_digest && req->pdu_len) { + pdu->hdr.flags |= NVME_TCP_F_DDGST; + ddgst = nvme_tcp_ddgst_len(queue); + } + pdu->hdr.hlen = sizeof(*pdu); + pdu->hdr.pdo = req->pdu_len ? pdu->hdr.hlen + hdgst : 0; + pdu->hdr.plen = + cpu_to_le32(pdu->hdr.hlen + hdgst + req->pdu_len + ddgst); + + ret = nvme_tcp_map_data(queue, rq); + if (unlikely(ret)) { + dev_err(queue->ctrl->ctrl.device, + "Failed to map data (%d)\n", ret); + return ret; + } + + return 0; +} + +static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + struct nvme_ns *ns = hctx->queue->queuedata; + struct nvme_tcp_queue *queue = hctx->driver_data; + struct request *rq = bd->rq; + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + bool queue_ready = test_bit(NVME_TCP_Q_LIVE, &queue->flags); + blk_status_t ret; + + if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready)) + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq); + + ret = nvme_tcp_setup_cmd_pdu(ns, rq); + if (unlikely(ret)) + return ret; + + blk_mq_start_request(rq); + + nvme_tcp_queue_request(req); + + return BLK_STS_OK; +} + +static struct blk_mq_ops nvme_tcp_mq_ops = { + .queue_rq = nvme_tcp_queue_rq, + .complete = nvme_complete_rq, + .init_request = nvme_tcp_init_request, + .exit_request = nvme_tcp_exit_request, + .init_hctx = nvme_tcp_init_hctx, + .timeout = nvme_tcp_timeout, +}; + +static struct blk_mq_ops nvme_tcp_admin_mq_ops = { + .queue_rq = nvme_tcp_queue_rq, + .complete = nvme_complete_rq, + .init_request = nvme_tcp_init_request, + .exit_request = nvme_tcp_exit_request, + .init_hctx = nvme_tcp_init_admin_hctx, + .timeout = nvme_tcp_timeout, +}; + +static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = { + .name = "tcp", + .module = THIS_MODULE, + .flags = NVME_F_FABRICS, + .reg_read32 = nvmf_reg_read32, + .reg_read64 = nvmf_reg_read64, + .reg_write32 = nvmf_reg_write32, + .free_ctrl = nvme_tcp_free_ctrl, + .submit_async_event = nvme_tcp_submit_async_event, + .delete_ctrl = nvme_tcp_delete_ctrl, + .get_address = nvmf_get_address, + .stop_ctrl = nvme_tcp_stop_ctrl, +}; + +static bool +nvme_tcp_existing_controller(struct nvmf_ctrl_options *opts) +{ + struct nvme_tcp_ctrl *ctrl; + bool found = false; + + mutex_lock(&nvme_tcp_ctrl_mutex); + list_for_each_entry(ctrl, &nvme_tcp_ctrl_list, list) { + found = nvmf_ip_options_match(&ctrl->ctrl, opts); + if (found) + break; + } + mutex_unlock(&nvme_tcp_ctrl_mutex); + + return found; +} + +static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, + struct nvmf_ctrl_options *opts) +{ + struct nvme_tcp_ctrl *ctrl; + int ret; + + ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); + if (!ctrl) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&ctrl->list); + ctrl->ctrl.opts = opts; + ctrl->ctrl.queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */ + ctrl->ctrl.sqsize = opts->queue_size - 1; + ctrl->ctrl.kato = opts->kato; + + INIT_DELAYED_WORK(&ctrl->connect_work, + nvme_tcp_reconnect_ctrl_work); + INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work); + INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work); + + if (!(opts->mask & NVMF_OPT_TRSVCID)) { + opts->trsvcid = + kstrdup(__stringify(NVME_TCP_DISC_PORT), GFP_KERNEL); + if (!opts->trsvcid) { + ret = -ENOMEM; + goto out_free_ctrl; + } + opts->mask |= NVMF_OPT_TRSVCID; + } + + ret = inet_pton_with_scope(&init_net, AF_UNSPEC, + opts->traddr, opts->trsvcid, &ctrl->addr); + if (ret) { + pr_err("malformed address passed: %s:%s\n", + opts->traddr, opts->trsvcid); + goto out_free_ctrl; + } + + if (opts->mask & NVMF_OPT_HOST_TRADDR) { + ret = inet_pton_with_scope(&init_net, AF_UNSPEC, + opts->host_traddr, NULL, &ctrl->src_addr); + if (ret) { + pr_err("malformed src address passed: %s\n", + opts->host_traddr); + goto out_free_ctrl; + } + } + + if (!opts->duplicate_connect && nvme_tcp_existing_controller(opts)) { + ret = -EALREADY; + goto out_free_ctrl; + } + + ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues), + GFP_KERNEL); + if (!ctrl->queues) { + ret = -ENOMEM; + goto out_free_ctrl; + } + + ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_tcp_ctrl_ops, 0); + if (ret) + goto out_kfree_queues; + + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { + WARN_ON_ONCE(1); + ret = -EINTR; + goto out_uninit_ctrl; + } + + ret = nvme_tcp_setup_ctrl(&ctrl->ctrl, true); + if (ret) + goto out_uninit_ctrl; + + dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n", + ctrl->ctrl.opts->subsysnqn, &ctrl->addr); + + nvme_get_ctrl(&ctrl->ctrl); + + mutex_lock(&nvme_tcp_ctrl_mutex); + list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list); + mutex_unlock(&nvme_tcp_ctrl_mutex); + + return &ctrl->ctrl; + +out_uninit_ctrl: + nvme_uninit_ctrl(&ctrl->ctrl); + nvme_put_ctrl(&ctrl->ctrl); + if (ret > 0) + ret = -EIO; + return ERR_PTR(ret); +out_kfree_queues: + kfree(ctrl->queues); +out_free_ctrl: + kfree(ctrl); + return ERR_PTR(ret); +} + +static struct nvmf_transport_ops nvme_tcp_transport = { + .name = "tcp", + .module = THIS_MODULE, + .required_opts = NVMF_OPT_TRADDR, + .allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY | + NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO | + NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST, + .create_ctrl = nvme_tcp_create_ctrl, +}; + +static int __init nvme_tcp_init_module(void) +{ + nvme_tcp_wq = alloc_workqueue("nvme_tcp_wq", + WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); + if (!nvme_tcp_wq) + return -ENOMEM; + + nvmf_register_transport(&nvme_tcp_transport); + return 0; +} + +static void __exit nvme_tcp_cleanup_module(void) +{ + struct nvme_tcp_ctrl *ctrl; + + nvmf_unregister_transport(&nvme_tcp_transport); + + mutex_lock(&nvme_tcp_ctrl_mutex); + list_for_each_entry(ctrl, &nvme_tcp_ctrl_list, list) + nvme_delete_ctrl(&ctrl->ctrl); + mutex_unlock(&nvme_tcp_ctrl_mutex); + flush_workqueue(nvme_delete_wq); + + destroy_workqueue(nvme_tcp_wq); +} + +module_init(nvme_tcp_init_module); +module_exit(nvme_tcp_cleanup_module); + +MODULE_LICENSE("GPL v2"); From 8eb5d89f483141dd076529bf5f6aa235b425886e Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Tue, 11 Dec 2018 07:24:34 +0800 Subject: [PATCH 14/33] nvme: add __exit annotation Add __exit annotation to cleanup helper which is only called once in the module. Signed-off-by: Chengguang Xu Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 2 +- drivers/nvme/host/nvme.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c71e879821ad..3043cedb24e1 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3802,7 +3802,7 @@ out: return result; } -void nvme_core_exit(void) +void __exit nvme_core_exit(void) { ida_destroy(&nvme_subsystems_ida); class_destroy(nvme_subsys_class); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index e20e737ac10c..c78a9dc7fdcf 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -565,6 +565,6 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) } int __init nvme_core_init(void); -void nvme_core_exit(void); +void __exit nvme_core_exit(void); #endif /* _NVME_H */ From cb5b7262b011cfb793519bf97e54dff5282da23c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 12 Dec 2018 09:18:11 -0700 Subject: [PATCH 15/33] nvme: provide fallback for discard alloc failure When boxes are run near (or to) OOM, we have a problem with the discard page allocation in nvme. If we fail allocating the special page, we return busy, and it'll get retried. But since ordering is honored for dispatch requests, we can keep retrying this same IO and failing. Behind that IO could be requests that want to free memory, but they never get the chance. Allocate a fixed discard page per controller for a safe fallback, and use that if the initial allocation fails. Signed-off-by: Jens Axboe Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 41 ++++++++++++++++++++++++++++++++++------ drivers/nvme/host/nvme.h | 3 +++ 2 files changed, 38 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 3043cedb24e1..168f2c1eaf60 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -564,9 +564,19 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, struct nvme_dsm_range *range; struct bio *bio; - range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC); - if (!range) - return BLK_STS_RESOURCE; + range = kmalloc_array(segments, sizeof(*range), + GFP_ATOMIC | __GFP_NOWARN); + if (!range) { + /* + * If we fail allocation our range, fallback to the controller + * discard page. If that's also busy, it's safe to return + * busy, as we know we can make progress once that's freed. + */ + if (test_and_set_bit_lock(0, &ns->ctrl->discard_page_busy)) + return BLK_STS_RESOURCE; + + range = page_address(ns->ctrl->discard_page); + } __rq_for_each_bio(bio, req) { u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector); @@ -581,7 +591,10 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, } if (WARN_ON_ONCE(n != segments)) { - kfree(range); + if (virt_to_page(range) == ns->ctrl->discard_page) + clear_bit_unlock(0, &ns->ctrl->discard_page_busy); + else + kfree(range); return BLK_STS_IOERR; } @@ -664,8 +677,13 @@ void nvme_cleanup_cmd(struct request *req) blk_rq_bytes(req) >> ns->lba_shift); } if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { - kfree(page_address(req->special_vec.bv_page) + - req->special_vec.bv_offset); + struct nvme_ns *ns = req->rq_disk->private_data; + struct page *page = req->special_vec.bv_page; + + if (page == ns->ctrl->discard_page) + clear_bit_unlock(0, &ns->ctrl->discard_page_busy); + else + kfree(page_address(page) + req->special_vec.bv_offset); } } EXPORT_SYMBOL_GPL(nvme_cleanup_cmd); @@ -3578,6 +3596,7 @@ static void nvme_free_ctrl(struct device *dev) ida_simple_remove(&nvme_instance_ida, ctrl->instance); kfree(ctrl->effects); nvme_mpath_uninit(ctrl); + kfree(ctrl->discard_page); if (subsys) { mutex_lock(&subsys->lock); @@ -3618,6 +3637,14 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd)); ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive; + BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) > + PAGE_SIZE); + ctrl->discard_page = alloc_page(GFP_KERNEL); + if (!ctrl->discard_page) { + ret = -ENOMEM; + goto out; + } + ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL); if (ret < 0) goto out; @@ -3655,6 +3682,8 @@ out_free_name: out_release_instance: ida_simple_remove(&nvme_instance_ida, ctrl->instance); out: + if (ctrl->discard_page) + __free_page(ctrl->discard_page); return ret; } EXPORT_SYMBOL_GPL(nvme_init_ctrl); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index c78a9dc7fdcf..39b52f4d9b24 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -241,6 +241,9 @@ struct nvme_ctrl { u16 maxcmd; int nr_reconnects; struct nvmf_ctrl_options *opts; + + struct page *discard_page; + unsigned long discard_page_busy; }; struct nvme_subsystem { From 16d3a280d4d73eae786ebf2576cd597a031bc9df Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 12 Dec 2018 23:01:54 -0800 Subject: [PATCH 16/33] nvmet: remove unused variable Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/io-cmd-bdev.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index c1cb2ed5531c..e0831230ca27 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -61,7 +61,6 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) struct bio *bio; struct scatterlist *sg; sector_t sector; - blk_qc_t cookie; int op, op_flags = 0, i; if (!req->sg_cnt) { @@ -114,7 +113,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) sg_cnt--; } - cookie = submit_bio(bio); + submit_bio(bio); } static void nvmet_bdev_execute_flush(struct nvmet_req *req) From b7c8f3663d0e0773aca3324c26bce3ca8343ec14 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:37 -0800 Subject: [PATCH 17/33] nvme: remove nvme_common command cdw10 array This is a preparation patch which removes the nvme common command cdw10 array and replace with individual fields. This is needed for the nvmet error log page implementation make is error log page entry offset assignment easier. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 18 +++++++++--------- drivers/nvme/host/lightnvm.c | 6 +++--- drivers/nvme/host/trace.h | 4 ++-- drivers/nvme/target/admin-cmd.c | 12 ++++++------ drivers/nvme/target/discovery.c | 4 ++-- drivers/nvme/target/nvmet.h | 2 +- include/linux/nvme.h | 7 ++++++- 7 files changed, 29 insertions(+), 24 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 168f2c1eaf60..4d8ee7186268 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1283,12 +1283,12 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, c.common.nsid = cpu_to_le32(cmd.nsid); c.common.cdw2[0] = cpu_to_le32(cmd.cdw2); c.common.cdw2[1] = cpu_to_le32(cmd.cdw3); - c.common.cdw10[0] = cpu_to_le32(cmd.cdw10); - c.common.cdw10[1] = cpu_to_le32(cmd.cdw11); - c.common.cdw10[2] = cpu_to_le32(cmd.cdw12); - c.common.cdw10[3] = cpu_to_le32(cmd.cdw13); - c.common.cdw10[4] = cpu_to_le32(cmd.cdw14); - c.common.cdw10[5] = cpu_to_le32(cmd.cdw15); + c.common.cdw10 = cpu_to_le32(cmd.cdw10); + c.common.cdw11 = cpu_to_le32(cmd.cdw11); + c.common.cdw12 = cpu_to_le32(cmd.cdw12); + c.common.cdw13 = cpu_to_le32(cmd.cdw13); + c.common.cdw14 = cpu_to_le32(cmd.cdw14); + c.common.cdw15 = cpu_to_le32(cmd.cdw15); if (cmd.timeout_ms) timeout = msecs_to_jiffies(cmd.timeout_ms); @@ -1649,7 +1649,7 @@ static int nvme_pr_command(struct block_device *bdev, u32 cdw10, memset(&c, 0, sizeof(c)); c.common.opcode = op; c.common.nsid = cpu_to_le32(ns->head->ns_id); - c.common.cdw10[0] = cpu_to_le32(cdw10); + c.common.cdw10 = cpu_to_le32(cdw10); ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16); nvme_put_ns_from_disk(head, srcu_idx); @@ -1723,8 +1723,8 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len, else cmd.common.opcode = nvme_admin_security_recv; cmd.common.nsid = 0; - cmd.common.cdw10[0] = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8); - cmd.common.cdw10[1] = cpu_to_le32(len); + cmd.common.cdw10 = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8); + cmd.common.cdw11 = cpu_to_le32(len); return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len, ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0); diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c index f145fc0220d6..b759c25c89c8 100644 --- a/drivers/nvme/host/lightnvm.c +++ b/drivers/nvme/host/lightnvm.c @@ -937,9 +937,9 @@ static int nvme_nvm_user_vcmd(struct nvme_ns *ns, int admin, /* cdw11-12 */ c.ph_rw.length = cpu_to_le16(vcmd.nppas); c.ph_rw.control = cpu_to_le16(vcmd.control); - c.common.cdw10[3] = cpu_to_le32(vcmd.cdw13); - c.common.cdw10[4] = cpu_to_le32(vcmd.cdw14); - c.common.cdw10[5] = cpu_to_le32(vcmd.cdw15); + c.common.cdw13 = cpu_to_le32(vcmd.cdw13); + c.common.cdw14 = cpu_to_le32(vcmd.cdw14); + c.common.cdw15 = cpu_to_le32(vcmd.cdw15); if (vcmd.timeout_ms) timeout = msecs_to_jiffies(vcmd.timeout_ms); diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h index 196d5bd56718..1978deb6fcc7 100644 --- a/drivers/nvme/host/trace.h +++ b/drivers/nvme/host/trace.h @@ -115,8 +115,8 @@ TRACE_EVENT(nvme_setup_cmd, __entry->nsid = le32_to_cpu(cmd->common.nsid); __entry->metadata = le64_to_cpu(cmd->common.metadata); __assign_disk_name(__entry->disk, req->rq_disk); - memcpy(__entry->cdw10, cmd->common.cdw10, - sizeof(__entry->cdw10)); + memcpy(__entry->cdw10, &cmd->common.cdw10, + 6 * sizeof(__entry->cdw10)); ), TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)", __entry->ctrl_id, __print_disk_name(__entry->disk), diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 753515fc8028..721b041a6b3b 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -557,7 +557,7 @@ static u16 nvmet_write_protect_flush_sync(struct nvmet_req *req) static u16 nvmet_set_feat_write_protect(struct nvmet_req *req) { - u32 write_protect = le32_to_cpu(req->cmd->common.cdw10[1]); + u32 write_protect = le32_to_cpu(req->cmd->common.cdw11); struct nvmet_subsys *subsys = req->sq->ctrl->subsys; u16 status = NVME_SC_FEATURE_NOT_CHANGEABLE; @@ -589,7 +589,7 @@ static u16 nvmet_set_feat_write_protect(struct nvmet_req *req) u16 nvmet_set_feat_kato(struct nvmet_req *req) { - u32 val32 = le32_to_cpu(req->cmd->common.cdw10[1]); + u32 val32 = le32_to_cpu(req->cmd->common.cdw11); req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000); @@ -600,7 +600,7 @@ u16 nvmet_set_feat_kato(struct nvmet_req *req) u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask) { - u32 val32 = le32_to_cpu(req->cmd->common.cdw10[1]); + u32 val32 = le32_to_cpu(req->cmd->common.cdw11); if (val32 & ~mask) return NVME_SC_INVALID_FIELD | NVME_SC_DNR; @@ -614,7 +614,7 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask) static void nvmet_execute_set_features(struct nvmet_req *req) { struct nvmet_subsys *subsys = req->sq->ctrl->subsys; - u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]); + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 status = 0; switch (cdw10 & 0xff) { @@ -675,7 +675,7 @@ void nvmet_get_feat_async_event(struct nvmet_req *req) static void nvmet_execute_get_features(struct nvmet_req *req) { struct nvmet_subsys *subsys = req->sq->ctrl->subsys; - u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]); + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 status = 0; switch (cdw10 & 0xff) { @@ -715,7 +715,7 @@ static void nvmet_execute_get_features(struct nvmet_req *req) break; case NVME_FEAT_HOST_ID: /* need 128-bit host identifier flag */ - if (!(req->cmd->common.cdw10[1] & cpu_to_le32(1 << 0))) { + if (!(req->cmd->common.cdw11 & cpu_to_le32(1 << 0))) { status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; break; } diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 4d8757ae8210..e1bb254671de 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -247,7 +247,7 @@ out: static void nvmet_execute_disc_set_features(struct nvmet_req *req) { - u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]); + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 stat; switch (cdw10 & 0xff) { @@ -268,7 +268,7 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req) static void nvmet_execute_disc_get_features(struct nvmet_req *req) { - u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]); + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 stat = 0; switch (cdw10 & 0xff) { diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 89df51ee5bdf..dafee1af4829 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -349,7 +349,7 @@ struct nvmet_async_event { static inline void nvmet_clear_aen_bit(struct nvmet_req *req, u32 bn) { - int rae = le32_to_cpu(req->cmd->common.cdw10[0]) & 1 << 15; + int rae = le32_to_cpu(req->cmd->common.cdw10) & 1 << 15; if (!rae) clear_bit(bn, &req->sq->ctrl->aen_masked); diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4d7907e3771e..b94fe8fadc4f 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -662,7 +662,12 @@ struct nvme_common_command { __le32 cdw2[2]; __le64 metadata; union nvme_data_ptr dptr; - __le32 cdw10[6]; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; }; struct nvme_rw_command { From b34de7cee0a65f2557bb05447fbe2cc7a9c46750 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:38 -0800 Subject: [PATCH 18/33] nvme: add error log page slot definition This patch adds the NVMe error slot definition from the spec. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/include/linux/nvme.h b/include/linux/nvme.h index b94fe8fadc4f..bbcc83886899 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1168,6 +1168,20 @@ struct nvme_command { }; }; +struct nvme_error_slot { + __le64 error_count; + __le16 sqid; + __le16 cmdid; + __le16 status_field; + __le16 param_error_location; + __le64 lba; + __le32 nsid; + __u8 vs; + __u8 resv[3]; + __le64 cs; + __u8 resv2[24]; +}; + static inline bool nvme_is_write(struct nvme_command *cmd) { /* From e4a976254ec5ebdcdb3e1e1b40e795b3db6b6dab Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:39 -0800 Subject: [PATCH 19/33] nvmet: add error-log definitions This patch adds necessary fields in the target data structures to support error log page. For a target controller, we add a new error log field to maintain the error log, at any given point we maintain error entries equal to NVMET_ERROR_LOG_SLOTS for each controller. In the following patch, we also update the error log page entry in the I/O completion path so we introduce a spinlock for synchronization of the log. For nvmet_req, we add a new field error_loc to hold the location of the error in the command when the actual error occurs for each request and a starting LBA if applicable. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/core.c | 5 +++++ drivers/nvme/target/nvmet.h | 6 ++++++ 2 files changed, 11 insertions(+) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index e468100b9211..32dca1b50c21 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -769,6 +769,8 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, req->rsp->status = 0; req->rsp->sq_head = 0; req->ns = NULL; + req->error_loc = -1; + req->error_slba = 0; /* no support for fused commands yet */ if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) { @@ -1174,6 +1176,9 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, /* keep-alive timeout in seconds */ ctrl->kato = DIV_ROUND_UP(kato, 1000); + ctrl->err_counter = 0; + spin_lock_init(&ctrl->error_lock); + nvmet_start_keep_alive_timer(ctrl); mutex_lock(&subsys->lock); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index dafee1af4829..61b3cc415905 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -202,6 +202,10 @@ struct nvmet_ctrl { struct device *p2p_client; struct radix_tree_root p2p_ns_map; + + spinlock_t error_lock; + u64 err_counter; + struct nvme_error_slot slots[NVMET_ERROR_LOG_SLOTS]; }; struct nvmet_subsys { @@ -317,6 +321,8 @@ struct nvmet_req { struct pci_dev *p2p_dev; struct device *p2p_client; + u16 error_loc; + u64 error_slba; }; extern struct workqueue_struct *buffered_io_wq; From 76574f37bf4caa7150ea1559cd98e3017b9752d2 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:40 -0800 Subject: [PATCH 20/33] nvmet: add interface to update error-log page This patch adds nvmet_req based interface to the nvmet-core so that we can update the error log page. We update error log page in the request completion path when status is not set to NVME_SC_SUCCESS. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/core.c | 32 +++++++++++++++++++++++++++++++- drivers/nvme/target/nvmet.h | 5 ----- 2 files changed, 31 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 32dca1b50c21..c7753ecdaaa5 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -611,14 +611,44 @@ static void nvmet_update_sq_head(struct nvmet_req *req) req->rsp->sq_head = cpu_to_le16(req->sq->sqhd & 0x0000FFFF); } +static void nvmet_set_error(struct nvmet_req *req, u16 status) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvme_error_slot *new_error_slot; + unsigned long flags; + + req->rsp->status = cpu_to_le16(status << 1); + + if (!ctrl || req->error_loc == -1) + return; + + spin_lock_irqsave(&ctrl->error_lock, flags); + ctrl->err_counter++; + new_error_slot = + &ctrl->slots[ctrl->err_counter % NVMET_ERROR_LOG_SLOTS]; + + new_error_slot->error_count = cpu_to_le64(ctrl->err_counter); + new_error_slot->sqid = cpu_to_le16(req->sq->qid); + new_error_slot->cmdid = cpu_to_le16(req->cmd->common.command_id); + new_error_slot->status_field = cpu_to_le16(status << 1); + new_error_slot->param_error_location = cpu_to_le16(req->error_loc); + new_error_slot->lba = cpu_to_le64(req->error_slba); + new_error_slot->nsid = req->cmd->common.nsid; + spin_unlock_irqrestore(&ctrl->error_lock, flags); + + /* set the more bit for this request */ + req->rsp->status |= cpu_to_le16(1 << 14); +} + static void __nvmet_req_complete(struct nvmet_req *req, u16 status) { if (!req->sq->sqhd_disabled) nvmet_update_sq_head(req); req->rsp->sq_id = cpu_to_le16(req->sq->qid); req->rsp->command_id = req->cmd->common.command_id; + if (unlikely(status)) - nvmet_set_status(req, status); + nvmet_set_error(req, status); if (req->ns) nvmet_put_namespace(req->ns); req->ops->queue_response(req); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 61b3cc415905..a2a7fd69b66a 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -327,11 +327,6 @@ struct nvmet_req { extern struct workqueue_struct *buffered_io_wq; -static inline void nvmet_set_status(struct nvmet_req *req, u16 status) -{ - req->rsp->status = cpu_to_le16(status << 1); -} - static inline void nvmet_set_result(struct nvmet_req *req, u32 result) { req->rsp->result.u32 = cpu_to_le32(result); From e81446afc7f5ee45fd90b1b5a22ffa247dca5b15 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:41 -0800 Subject: [PATCH 21/33] nvmet: add error log support in the core This patch adds the support to maintain error log page for the nvmet-core. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/core.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index c7753ecdaaa5..0b969977e361 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -51,22 +51,28 @@ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port, u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf, size_t len) { - if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len) + if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len) { + req->error_loc = offsetof(struct nvme_common_command, dptr); return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR; + } return 0; } u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len) { - if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len) + if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len) { + req->error_loc = offsetof(struct nvme_common_command, dptr); return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR; + } return 0; } u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len) { - if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len) + if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len) { + req->error_loc = offsetof(struct nvme_common_command, dptr); return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR; + } return 0; } @@ -769,14 +775,20 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req) return ret; req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid); - if (unlikely(!req->ns)) + if (unlikely(!req->ns)) { + req->error_loc = offsetof(struct nvme_common_command, nsid); return NVME_SC_INVALID_NS | NVME_SC_DNR; + } ret = nvmet_check_ana_state(req->port, req->ns); - if (unlikely(ret)) + if (unlikely(ret)) { + req->error_loc = offsetof(struct nvme_common_command, nsid); return ret; + } ret = nvmet_io_cmd_check_access(req); - if (unlikely(ret)) + if (unlikely(ret)) { + req->error_loc = offsetof(struct nvme_common_command, nsid); return ret; + } if (req->ns->file) return nvmet_file_parse_io_cmd(req); @@ -804,6 +816,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, /* no support for fused commands yet */ if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) { + req->error_loc = offsetof(struct nvme_common_command, flags); status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; goto fail; } @@ -814,6 +827,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, * byte aligned. */ if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) { + req->error_loc = offsetof(struct nvme_common_command, flags); status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; goto fail; } @@ -859,9 +873,10 @@ EXPORT_SYMBOL_GPL(nvmet_req_uninit); void nvmet_req_execute(struct nvmet_req *req) { - if (unlikely(req->data_len != req->transfer_len)) + if (unlikely(req->data_len != req->transfer_len)) { + req->error_loc = offsetof(struct nvme_common_command, dptr); nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR); - else + } else req->execute(req); } EXPORT_SYMBOL_GPL(nvmet_req_execute); From 84faf42b8aff3be95d96249da4152c77d81e1469 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:44 -0800 Subject: [PATCH 22/33] nvmet: add error log support for fabrics-cmd This patch adds the support to maintain error log page for the fabrics prop get, prop set, and admin connect commands. Here we also update the discovery.c and add update set/get features and parse functions to support error log page. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/discovery.c | 10 +++++++ drivers/nvme/target/fabrics-cmd.c | 48 ++++++++++++++++++++++--------- 2 files changed, 45 insertions(+), 13 deletions(-) diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index e1bb254671de..d2cb71a0b419 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -259,6 +259,8 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req) NVMET_DISC_AEN_CFG_OPTIONAL); break; default: + req->error_loc = + offsetof(struct nvme_common_command, cdw10); stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR; break; } @@ -279,6 +281,8 @@ static void nvmet_execute_disc_get_features(struct nvmet_req *req) nvmet_get_feat_async_event(req); break; default: + req->error_loc = + offsetof(struct nvme_common_command, cdw10); stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR; break; } @@ -293,6 +297,8 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) { pr_err("got cmd %d while not ready\n", cmd->common.opcode); + req->error_loc = + offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } @@ -323,6 +329,8 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) default: pr_err("unsupported get_log_page lid %d\n", cmd->get_log_page.lid); + req->error_loc = + offsetof(struct nvme_get_log_page_command, lid); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } case nvme_admin_identify: @@ -335,10 +343,12 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) default: pr_err("unsupported identify cns %d\n", cmd->identify.cns); + req->error_loc = offsetof(struct nvme_identify, cns); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } default: pr_err("unhandled cmd %d\n", cmd->common.opcode); + req->error_loc = offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index ee7d84621d65..6cf1fd9eb32e 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -17,23 +17,26 @@ static void nvmet_execute_prop_set(struct nvmet_req *req) { + u64 val = le64_to_cpu(req->cmd->prop_set.value); u16 status = 0; - if (!(req->cmd->prop_set.attrib & 1)) { - u64 val = le64_to_cpu(req->cmd->prop_set.value); - - switch (le32_to_cpu(req->cmd->prop_set.offset)) { - case NVME_REG_CC: - nvmet_update_cc(req->sq->ctrl, val); - break; - default: - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; - break; - } - } else { + if (req->cmd->prop_set.attrib & 1) { + req->error_loc = + offsetof(struct nvmf_property_set_command, attrib); status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + goto out; } + switch (le32_to_cpu(req->cmd->prop_set.offset)) { + case NVME_REG_CC: + nvmet_update_cc(req->sq->ctrl, val); + break; + default: + req->error_loc = + offsetof(struct nvmf_property_set_command, offset); + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + } +out: nvmet_req_complete(req, status); } @@ -69,6 +72,14 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) } } + if (status && req->cmd->prop_get.attrib & 1) { + req->error_loc = + offsetof(struct nvmf_property_get_command, offset); + } else { + req->error_loc = + offsetof(struct nvmf_property_get_command, attrib); + } + req->rsp->result.u64 = cpu_to_le64(val); nvmet_req_complete(req, status); } @@ -89,6 +100,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req) default: pr_err("received unknown capsule type 0x%x\n", cmd->fabrics.fctype); + req->error_loc = offsetof(struct nvmf_common_command, fctype); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } @@ -105,10 +117,12 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req) old = cmpxchg(&req->sq->ctrl, NULL, ctrl); if (old) { pr_warn("queue already connected!\n"); + req->error_loc = offsetof(struct nvmf_connect_command, opcode); return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR; } if (!sqsize) { pr_warn("queue size zero!\n"); + req->error_loc = offsetof(struct nvmf_connect_command, sqsize); return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; } @@ -157,6 +171,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) if (c->recfmt != 0) { pr_warn("invalid connect version (%d).\n", le16_to_cpu(c->recfmt)); + req->error_loc = offsetof(struct nvmf_connect_command, recfmt); status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR; goto out; } @@ -171,8 +186,13 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req, le32_to_cpu(c->kato), &ctrl); - if (status) + if (status) { + if (status == (NVME_SC_INVALID_FIELD | NVME_SC_DNR)) + req->error_loc = + offsetof(struct nvme_common_command, opcode); goto out; + } + uuid_copy(&ctrl->hostid, &d->hostid); status = nvmet_install_queue(ctrl, req); @@ -259,11 +279,13 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req) if (cmd->common.opcode != nvme_fabrics_command) { pr_err("invalid command 0x%x on unconnected queue.\n", cmd->fabrics.opcode); + req->error_loc = offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } if (cmd->fabrics.fctype != nvme_fabrics_type_connect) { pr_err("invalid capsule type 0x%x on unconnected queue.\n", cmd->fabrics.fctype); + req->error_loc = offsetof(struct nvmf_common_command, fctype); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } From 762a11dfee10783a2fe4c467a68bac601e5acf1c Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:45 -0800 Subject: [PATCH 23/33] nvmet: add error log support for rdma backend This patch adds the support to maintain the error log page for rdma transport, we mainly focus here on the NVME_INVALID_FIELD errors. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/rdma.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index fb84caddd94b..a8d23eb80192 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -630,8 +630,11 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp) u64 off = le64_to_cpu(sgl->addr); u32 len = le32_to_cpu(sgl->length); - if (!nvme_is_write(rsp->req.cmd)) + if (!nvme_is_write(rsp->req.cmd)) { + rsp->req.error_loc = + offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + } if (off + len > rsp->queue->dev->inline_data_size) { pr_err("invalid inline data offset!\n"); @@ -696,6 +699,8 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp) return nvmet_rdma_map_sgl_inline(rsp); default: pr_err("invalid SGL subtype: %#x\n", sgl->type); + rsp->req.error_loc = + offsetof(struct nvme_common_command, dptr); return NVME_SC_INVALID_FIELD | NVME_SC_DNR; } case NVME_KEY_SGL_FMT_DATA_DESC: @@ -706,10 +711,13 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp) return nvmet_rdma_map_sgl_keyed(rsp, sgl, false); default: pr_err("invalid SGL subtype: %#x\n", sgl->type); + rsp->req.error_loc = + offsetof(struct nvme_common_command, dptr); return NVME_SC_INVALID_FIELD | NVME_SC_DNR; } default: pr_err("invalid SGL type: %#x\n", sgl->type); + rsp->req.error_loc = offsetof(struct nvme_common_command, dptr); return NVME_SC_SGL_INVALID_TYPE | NVME_SC_DNR; } } From 2da6e00580f5bc13ed0ba0acaa9d7ce0df226e7e Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:46 -0800 Subject: [PATCH 24/33] nvmet: add error log support for admin-cmd This patch adds the support to maintain the error log page for admin commands. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/admin-cmd.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 721b041a6b3b..fa62db7a5e9e 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -47,6 +47,7 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req, if (!ns) { pr_err("Could not find namespace id : %d\n", le32_to_cpu(req->cmd->get_log_page.nsid)); + req->error_loc = offsetof(struct nvme_rw_command, nsid); return NVME_SC_INVALID_NS; } @@ -380,6 +381,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) u16 status = 0; if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) { + req->error_loc = offsetof(struct nvme_identify, nsid); status = NVME_SC_INVALID_NS | NVME_SC_DNR; goto out; } @@ -500,6 +502,7 @@ static void nvmet_execute_identify_desclist(struct nvmet_req *req) ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->identify.nsid); if (!ns) { + req->error_loc = offsetof(struct nvme_identify, nsid); status = NVME_SC_INVALID_NS | NVME_SC_DNR; goto out; } @@ -562,8 +565,10 @@ static u16 nvmet_set_feat_write_protect(struct nvmet_req *req) u16 status = NVME_SC_FEATURE_NOT_CHANGEABLE; req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->rw.nsid); - if (unlikely(!req->ns)) + if (unlikely(!req->ns)) { + req->error_loc = offsetof(struct nvme_common_command, nsid); return status; + } mutex_lock(&subsys->lock); switch (write_protect) { @@ -602,8 +607,10 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask) { u32 val32 = le32_to_cpu(req->cmd->common.cdw11); - if (val32 & ~mask) + if (val32 & ~mask) { + req->error_loc = offsetof(struct nvme_common_command, cdw11); return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + } WRITE_ONCE(req->sq->ctrl->aen_enabled, val32); nvmet_set_result(req, val32); @@ -635,6 +642,7 @@ static void nvmet_execute_set_features(struct nvmet_req *req) status = nvmet_set_feat_write_protect(req); break; default: + req->error_loc = offsetof(struct nvme_common_command, cdw10); status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; break; } @@ -648,9 +656,10 @@ static u16 nvmet_get_feat_write_protect(struct nvmet_req *req) u32 result; req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->common.nsid); - if (!req->ns) + if (!req->ns) { + req->error_loc = offsetof(struct nvme_common_command, nsid); return NVME_SC_INVALID_NS | NVME_SC_DNR; - + } mutex_lock(&subsys->lock); if (req->ns->readonly == true) result = NVME_NS_WRITE_PROTECT; @@ -716,6 +725,8 @@ static void nvmet_execute_get_features(struct nvmet_req *req) case NVME_FEAT_HOST_ID: /* need 128-bit host identifier flag */ if (!(req->cmd->common.cdw11 & cpu_to_le32(1 << 0))) { + req->error_loc = + offsetof(struct nvme_common_command, cdw11); status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; break; } @@ -727,6 +738,8 @@ static void nvmet_execute_get_features(struct nvmet_req *req) status = nvmet_get_feat_write_protect(req); break; default: + req->error_loc = + offsetof(struct nvme_common_command, cdw10); status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; break; } @@ -848,5 +861,6 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode, req->sq->qid); + req->error_loc = offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } From 3b031d15995f3e4c43e38159072f07efe3fa35d9 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:42 -0800 Subject: [PATCH 25/33] nvmet: add error log support for bdev backend This patch adds the support for the block device backend to populate the error log entries. Here we map the blk_status_t to the NVMe status. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/io-cmd-bdev.c | 84 ++++++++++++++++++++++++++----- 1 file changed, 72 insertions(+), 12 deletions(-) diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index e0831230ca27..b6d030d3259f 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -44,13 +44,69 @@ void nvmet_bdev_ns_disable(struct nvmet_ns *ns) } } +static u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts) +{ + u16 status = NVME_SC_SUCCESS; + + if (likely(blk_sts == BLK_STS_OK)) + return status; + /* + * Right now there exists M : 1 mapping between block layer error + * to the NVMe status code (see nvme_error_status()). For consistency, + * when we reverse map we use most appropriate NVMe Status code from + * the group of the NVMe staus codes used in the nvme_error_status(). + */ + switch (blk_sts) { + case BLK_STS_NOSPC: + status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR; + req->error_loc = offsetof(struct nvme_rw_command, length); + break; + case BLK_STS_TARGET: + status = NVME_SC_LBA_RANGE | NVME_SC_DNR; + req->error_loc = offsetof(struct nvme_rw_command, slba); + break; + case BLK_STS_NOTSUPP: + req->error_loc = offsetof(struct nvme_common_command, opcode); + switch (req->cmd->common.opcode) { + case nvme_cmd_dsm: + case nvme_cmd_write_zeroes: + status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR; + break; + default: + status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + } + break; + case BLK_STS_MEDIUM: + status = NVME_SC_ACCESS_DENIED; + req->error_loc = offsetof(struct nvme_rw_command, nsid); + break; + case BLK_STS_IOERR: + /* fallthru */ + default: + status = NVME_SC_INTERNAL | NVME_SC_DNR; + req->error_loc = offsetof(struct nvme_common_command, opcode); + } + + switch (req->cmd->common.opcode) { + case nvme_cmd_read: + case nvme_cmd_write: + req->error_slba = le64_to_cpu(req->cmd->rw.slba); + break; + case nvme_cmd_write_zeroes: + req->error_slba = + le64_to_cpu(req->cmd->write_zeroes.slba); + break; + default: + req->error_slba = 0; + } + return status; +} + static void nvmet_bio_done(struct bio *bio) { struct nvmet_req *req = bio->bi_private; - nvmet_req_complete(req, - bio->bi_status ? NVME_SC_INTERNAL | NVME_SC_DNR : 0); - + nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status)); if (bio != &req->b.inline_bio) bio_put(bio); } @@ -136,18 +192,21 @@ u16 nvmet_bdev_flush(struct nvmet_req *req) return 0; } -static u16 nvmet_bdev_discard_range(struct nvmet_ns *ns, +static u16 nvmet_bdev_discard_range(struct nvmet_req *req, struct nvme_dsm_range *range, struct bio **bio) { + struct nvmet_ns *ns = req->ns; int ret; ret = __blkdev_issue_discard(ns->bdev, le64_to_cpu(range->slba) << (ns->blksize_shift - 9), le32_to_cpu(range->nlb) << (ns->blksize_shift - 9), GFP_KERNEL, 0, bio); - if (ret && ret != -EOPNOTSUPP) - return NVME_SC_INTERNAL | NVME_SC_DNR; - return 0; + + if (ret) + req->error_slba = le64_to_cpu(range->slba); + + return blk_to_nvme_status(req, errno_to_blk_status(ret)); } static void nvmet_bdev_execute_discard(struct nvmet_req *req) @@ -163,7 +222,7 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req) if (status) break; - status = nvmet_bdev_discard_range(req->ns, &range, &bio); + status = nvmet_bdev_discard_range(req, &range, &bio); if (status) break; } @@ -204,16 +263,16 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req) u16 status = NVME_SC_SUCCESS; sector_t sector; sector_t nr_sector; + int ret; sector = le64_to_cpu(write_zeroes->slba) << (req->ns->blksize_shift - 9); nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) << (req->ns->blksize_shift - 9)); - if (__blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector, - GFP_KERNEL, &bio, 0)) - status = NVME_SC_INTERNAL | NVME_SC_DNR; - + ret = __blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector, + GFP_KERNEL, &bio, 0); + status = blk_to_nvme_status(req, errno_to_blk_status(ret)); if (bio) { bio->bi_private = req; bio->bi_end_io = nvmet_bio_done; @@ -248,6 +307,7 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req) default: pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode, req->sq->qid); + req->error_loc = offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } } From c6aa3542e01026a94d24713ee2c0dce517e9b6de Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:43 -0800 Subject: [PATCH 26/33] nvmet: add error log support for file backend This patch adds support for the file backend to populate the error log entries. Here we map the errno to the NVMe status codes. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/core.c | 38 +++++++++++++++++++++++++++++++ drivers/nvme/target/io-cmd-file.c | 35 ++++++++++++++++------------ drivers/nvme/target/nvmet.h | 2 ++ 3 files changed, 60 insertions(+), 15 deletions(-) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 0b969977e361..cc81d0231587 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -45,6 +45,44 @@ u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1]; u64 nvmet_ana_chgcnt; DECLARE_RWSEM(nvmet_ana_sem); +inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno) +{ + u16 status; + + switch (errno) { + case -ENOSPC: + req->error_loc = offsetof(struct nvme_rw_command, length); + status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR; + break; + case -EREMOTEIO: + req->error_loc = offsetof(struct nvme_rw_command, slba); + status = NVME_SC_LBA_RANGE | NVME_SC_DNR; + break; + case -EOPNOTSUPP: + req->error_loc = offsetof(struct nvme_common_command, opcode); + switch (req->cmd->common.opcode) { + case nvme_cmd_dsm: + case nvme_cmd_write_zeroes: + status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR; + break; + default: + status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + } + break; + case -ENODATA: + req->error_loc = offsetof(struct nvme_rw_command, nsid); + status = NVME_SC_ACCESS_DENIED; + break; + case -EIO: + /* FALLTHRU */ + default: + req->error_loc = offsetof(struct nvme_common_command, opcode); + status = NVME_SC_INTERNAL | NVME_SC_DNR; + } + + return status; +} + static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port, const char *subsysnqn); diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 12eaa8ddc248..517522305e5c 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -112,6 +112,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos, static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2) { struct nvmet_req *req = container_of(iocb, struct nvmet_req, f.iocb); + u16 status = NVME_SC_SUCCESS; if (req->f.bvec != req->inline_bvec) { if (likely(req->f.mpool_alloc == false)) @@ -120,8 +121,9 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2) mempool_free(req->f.bvec, req->ns->bvec_pool); } - nvmet_req_complete(req, ret != req->data_len ? - NVME_SC_INTERNAL | NVME_SC_DNR : 0); + if (unlikely(ret != req->data_len)) + status = errno_to_nvme_status(req, ret); + nvmet_req_complete(req, status); } static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) @@ -140,7 +142,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift; if (unlikely(pos + req->data_len > req->ns->size)) { - nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR); + nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC)); return true; } @@ -254,9 +256,7 @@ static void nvmet_file_execute_rw(struct nvmet_req *req) u16 nvmet_file_flush(struct nvmet_req *req) { - if (vfs_fsync(req->ns->file, 1) < 0) - return NVME_SC_INTERNAL | NVME_SC_DNR; - return 0; + return errno_to_nvme_status(req, vfs_fsync(req->ns->file, 1)); } static void nvmet_file_flush_work(struct work_struct *w) @@ -277,30 +277,34 @@ static void nvmet_file_execute_discard(struct nvmet_req *req) int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE; struct nvme_dsm_range range; loff_t offset, len; - u16 ret; + u16 status = 0; + int ret; int i; for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) { - ret = nvmet_copy_from_sgl(req, i * sizeof(range), &range, + status = nvmet_copy_from_sgl(req, i * sizeof(range), &range, sizeof(range)); - if (ret) + if (status) break; offset = le64_to_cpu(range.slba) << req->ns->blksize_shift; len = le32_to_cpu(range.nlb); len <<= req->ns->blksize_shift; if (offset + len > req->ns->size) { - ret = NVME_SC_LBA_RANGE | NVME_SC_DNR; + req->error_slba = le64_to_cpu(range.slba); + status = errno_to_nvme_status(req, -ENOSPC); break; } - if (vfs_fallocate(req->ns->file, mode, offset, len)) { - ret = NVME_SC_INTERNAL | NVME_SC_DNR; + ret = vfs_fallocate(req->ns->file, mode, offset, len); + if (ret) { + req->error_slba = le64_to_cpu(range.slba); + status = errno_to_nvme_status(req, ret); break; } } - nvmet_req_complete(req, ret); + nvmet_req_complete(req, status); } static void nvmet_file_dsm_work(struct work_struct *w) @@ -340,12 +344,12 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w) req->ns->blksize_shift); if (unlikely(offset + len > req->ns->size)) { - nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR); + nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC)); return; } ret = vfs_fallocate(req->ns->file, mode, offset, len); - nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0); + nvmet_req_complete(req, ret < 0 ? errno_to_nvme_status(req, ret) : 0); } static void nvmet_file_execute_write_zeroes(struct nvmet_req *req) @@ -380,6 +384,7 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req) default: pr_err("unhandled cmd for file ns %d on qid %d\n", cmd->common.opcode, req->sq->qid); + req->error_loc = offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index a2a7fd69b66a..3b5f0bcaf3e8 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -494,4 +494,6 @@ static inline u32 nvmet_rw_len(struct nvmet_req *req) return ((u32)le16_to_cpu(req->cmd->rw.length) + 1) << req->ns->blksize_shift; } + +u16 errno_to_nvme_status(struct nvmet_req *req, int errno); #endif /* _NVMET_H */ From 11ad507784ed5113af97903af1b0c4aea6b90690 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:47 -0800 Subject: [PATCH 27/33] nvmet: add error log page cmd handler Now that we have support for all the major parts of the target we add a NVMe error log page handler so that host can read the log page. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/admin-cmd.c | 36 ++++++++++++++++++++++++++------- 1 file changed, 29 insertions(+), 7 deletions(-) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index fa62db7a5e9e..00956b4106a8 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -37,6 +37,34 @@ static void nvmet_execute_get_log_page_noop(struct nvmet_req *req) nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len)); } +static void nvmet_execute_get_log_page_error(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u16 status = NVME_SC_SUCCESS; + unsigned long flags; + off_t offset = 0; + u64 slot; + u64 i; + + spin_lock_irqsave(&ctrl->error_lock, flags); + slot = ctrl->err_counter % NVMET_ERROR_LOG_SLOTS; + + for (i = 0; i < NVMET_ERROR_LOG_SLOTS; i++) { + status = nvmet_copy_to_sgl(req, offset, &ctrl->slots[slot], + sizeof(struct nvme_error_slot)); + if (status) + break; + + if (slot == 0) + slot = NVMET_ERROR_LOG_SLOTS - 1; + else + slot--; + offset += sizeof(struct nvme_error_slot); + } + spin_unlock_irqrestore(&ctrl->error_lock, flags); + nvmet_req_complete(req, status); +} + static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req, struct nvme_smart_log *slog) { @@ -789,13 +817,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) switch (cmd->get_log_page.lid) { case NVME_LOG_ERROR: - /* - * We currently never set the More bit in the status - * field, so all error log entries are invalid and can - * be zeroed out. This is called a minum viable - * implementation (TM) of this mandatory log page. - */ - req->execute = nvmet_execute_get_log_page_noop; + req->execute = nvmet_execute_get_log_page_error; return 0; case NVME_LOG_SMART: req->execute = nvmet_execute_get_log_page_smart; From 23454d59cc16ddddf4b2290bbe60d2d9581dfd9a Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 12 Dec 2018 15:11:48 -0800 Subject: [PATCH 28/33] nvmet: update smart log with num err log entries Now that we have error log page implementation update smart log command handler to provide number of error log entries in the lifetime of the controller field. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/admin-cmd.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 00956b4106a8..11baeb14c388 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -135,6 +135,7 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req) { struct nvme_smart_log *log; u16 status = NVME_SC_INTERNAL; + unsigned long flags; if (req->data_len != sizeof(*log)) goto out; @@ -150,6 +151,11 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req) if (status) goto out_free_log; + spin_lock_irqsave(&req->sq->ctrl->error_lock, flags); + put_unaligned_le64(req->sq->ctrl->err_counter, + &log->num_err_log_entries); + spin_unlock_irqrestore(&req->sq->ctrl->error_lock, flags); + status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log)); out_free_log: kfree(log); From e42b3867de4bd5ee3a1849afb68a1fa8627f7282 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 11 Dec 2018 23:38:54 -0800 Subject: [PATCH 29/33] blk-mq-rdma: pass in queue map to blk_mq_rdma_map_queues Will be used by nvme-rdma for queue map separation support. Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- block/blk-mq-rdma.c | 8 ++++---- drivers/nvme/host/rdma.c | 2 +- include/linux/blk-mq-rdma.h | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/block/blk-mq-rdma.c b/block/blk-mq-rdma.c index a71576aff3a5..45030a81a1ed 100644 --- a/block/blk-mq-rdma.c +++ b/block/blk-mq-rdma.c @@ -29,24 +29,24 @@ * @set->nr_hw_queues, or @dev does not provide an affinity mask for a * vector, we fallback to the naive mapping. */ -int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set, +int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, struct ib_device *dev, int first_vec) { const struct cpumask *mask; unsigned int queue, cpu; - for (queue = 0; queue < set->nr_hw_queues; queue++) { + for (queue = 0; queue < map->nr_queues; queue++) { mask = ib_get_vector_affinity(dev, first_vec + queue); if (!mask) goto fallback; for_each_cpu(cpu, mask) - set->map[0].mq_map[cpu] = queue; + map->mq_map[cpu] = map->queue_offset + queue; } return 0; fallback: - return blk_mq_map_queues(&set->map[0]); + return blk_mq_map_queues(map); } EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index f2db848f6985..5057d5ab5aaa 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1751,7 +1751,7 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) { struct nvme_rdma_ctrl *ctrl = set->driver_data; - return blk_mq_rdma_map_queues(set, ctrl->device->dev, 0); + return blk_mq_rdma_map_queues(&set->map[0], ctrl->device->dev, 0); } static const struct blk_mq_ops nvme_rdma_mq_ops = { diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h index b4ade198007d..7b6ecf9ac4c3 100644 --- a/include/linux/blk-mq-rdma.h +++ b/include/linux/blk-mq-rdma.h @@ -4,7 +4,7 @@ struct blk_mq_tag_set; struct ib_device; -int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set, +int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, struct ib_device *dev, int first_vec); #endif /* _LINUX_BLK_MQ_RDMA_H */ From fa9a1811e094658e53b0c82b6ce0431c4c54fc1b Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 11 Dec 2018 23:38:55 -0800 Subject: [PATCH 30/33] nvme-fabrics: add missing nvmf_ctrl_options documentation Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fabrics.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 524a02a67817..28dc916ef26b 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -88,6 +88,9 @@ enum { * @max_reconnects: maximum number of allowed reconnect attempts before removing * the controller, (-1) means reconnect forever, zero means remove * immediately; + * @disable_sqflow: disable controller sq flow control + * @hdr_digest: generate/verify header digest (TCP) + * @data_digest: generate/verify data digest (TCP) */ struct nvmf_ctrl_options { unsigned mask; From 330f6b8a70771f0b059b7bcbc9a28d8023235b55 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 11 Dec 2018 23:38:56 -0800 Subject: [PATCH 31/33] nvme-fabrics: allow user to set nr_write_queues for separate queue maps This argument will specify how many I/O queues will be connected in create_ctrl in addition to nr_io_queues. With this configuration, I/O that carries payload from the host to the target, will use the default hctx queue map, and I/O that involves target to host transfers will use the read hctx queue map. Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fabrics.c | 13 +++++++++++++ drivers/nvme/host/fabrics.h | 3 +++ 2 files changed, 16 insertions(+) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 9c62c6838b76..19ff0eae4582 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -616,6 +616,7 @@ static const match_table_t opt_tokens = { { NVMF_OPT_DISABLE_SQFLOW, "disable_sqflow" }, { NVMF_OPT_HDR_DIGEST, "hdr_digest" }, { NVMF_OPT_DATA_DIGEST, "data_digest" }, + { NVMF_OPT_NR_WRITE_QUEUES, "nr_write_queues=%d" }, { NVMF_OPT_ERR, NULL } }; @@ -837,6 +838,18 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, case NVMF_OPT_DATA_DIGEST: opts->data_digest = true; break; + case NVMF_OPT_NR_WRITE_QUEUES: + if (match_int(args, &token)) { + ret = -EINVAL; + goto out; + } + if (token <= 0) { + pr_err("Invalid nr_write_queues %d\n", token); + ret = -EINVAL; + goto out; + } + opts->nr_write_queues = token; + break; default: pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", p); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 28dc916ef26b..81b8fd1c0c5d 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -61,6 +61,7 @@ enum { NVMF_OPT_DISABLE_SQFLOW = 1 << 14, NVMF_OPT_HDR_DIGEST = 1 << 15, NVMF_OPT_DATA_DIGEST = 1 << 16, + NVMF_OPT_NR_WRITE_QUEUES = 1 << 17, }; /** @@ -91,6 +92,7 @@ enum { * @disable_sqflow: disable controller sq flow control * @hdr_digest: generate/verify header digest (TCP) * @data_digest: generate/verify data digest (TCP) + * @nr_write_queues: number of queues for write I/O */ struct nvmf_ctrl_options { unsigned mask; @@ -110,6 +112,7 @@ struct nvmf_ctrl_options { bool disable_sqflow; bool hdr_digest; bool data_digest; + unsigned int nr_write_queues; }; /* From 873946f4b957bf6e6a0351dd5282c73e0c870be9 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 11 Dec 2018 23:38:57 -0800 Subject: [PATCH 32/33] nvme-tcp: support separate queue maps for read and write Allow NVMF_OPT_NR_WRITE_QUEUES to describe additional write queues. In addition, implement .map_queues that will apply 2 queue maps for read and write queue sets. Note that with the separate queue map, HCTX_TYPE_READ will always use nr_io_queues and HCTX_TYPE_DEFAULT will use nr_write_queues. Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/tcp.c | 47 +++++++++++++++++++++++++++++++++++------ 1 file changed, 41 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 15543358e245..51826479a41e 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1215,7 +1215,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; struct linger sol = { .l_onoff = 1, .l_linger = 0 }; - int ret, opt, rcv_pdu_size; + int ret, opt, rcv_pdu_size, n; queue->ctrl = ctrl; INIT_LIST_HEAD(&queue->send_list); @@ -1271,7 +1271,11 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, } queue->sock->sk->sk_allocation = GFP_ATOMIC; - queue->io_cpu = (qid == 0) ? 0 : qid - 1; + if (!qid) + n = 0; + else + n = (qid - 1) % num_online_cpus(); + queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false); queue->request = NULL; queue->data_remaining = 0; queue->ddgst_remaining = 0; @@ -1433,6 +1437,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, set->driver_data = ctrl; set->nr_hw_queues = nctrl->queue_count - 1; set->timeout = NVME_IO_TIMEOUT; + set->nr_maps = 2 /* default + read */; } ret = blk_mq_alloc_tag_set(set); @@ -1527,7 +1532,12 @@ out_free_queues: static unsigned int nvme_tcp_nr_io_queues(struct nvme_ctrl *ctrl) { - return min(ctrl->queue_count - 1, num_online_cpus()); + unsigned int nr_io_queues; + + nr_io_queues = min(ctrl->opts->nr_io_queues, num_online_cpus()); + nr_io_queues += min(ctrl->opts->nr_write_queues, num_online_cpus()); + + return nr_io_queues; } static int nvme_alloc_io_queues(struct nvme_ctrl *ctrl) @@ -2052,6 +2062,29 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } +static int nvme_tcp_map_queues(struct blk_mq_tag_set *set) +{ + struct nvme_tcp_ctrl *ctrl = set->driver_data; + + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; + set->map[HCTX_TYPE_READ].nr_queues = ctrl->ctrl.opts->nr_io_queues; + if (ctrl->ctrl.opts->nr_write_queues) { + /* separate read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = + ctrl->ctrl.opts->nr_write_queues; + set->map[HCTX_TYPE_READ].queue_offset = + ctrl->ctrl.opts->nr_write_queues; + } else { + /* mixed read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = + ctrl->ctrl.opts->nr_io_queues; + set->map[HCTX_TYPE_READ].queue_offset = 0; + } + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); + blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); + return 0; +} + static struct blk_mq_ops nvme_tcp_mq_ops = { .queue_rq = nvme_tcp_queue_rq, .complete = nvme_complete_rq, @@ -2059,6 +2092,7 @@ static struct blk_mq_ops nvme_tcp_mq_ops = { .exit_request = nvme_tcp_exit_request, .init_hctx = nvme_tcp_init_hctx, .timeout = nvme_tcp_timeout, + .map_queues = nvme_tcp_map_queues, }; static struct blk_mq_ops nvme_tcp_admin_mq_ops = { @@ -2113,7 +2147,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, INIT_LIST_HEAD(&ctrl->list); ctrl->ctrl.opts = opts; - ctrl->ctrl.queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */ + ctrl->ctrl.queue_count = opts->nr_io_queues + opts->nr_write_queues + 1; ctrl->ctrl.sqsize = opts->queue_size - 1; ctrl->ctrl.kato = opts->kato; @@ -2155,7 +2189,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, goto out_free_ctrl; } - ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues), + ctrl->queues = kcalloc(ctrl->ctrl.queue_count, sizeof(*ctrl->queues), GFP_KERNEL); if (!ctrl->queues) { ret = -ENOMEM; @@ -2206,7 +2240,8 @@ static struct nvmf_transport_ops nvme_tcp_transport = { .required_opts = NVMF_OPT_TRADDR, .allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY | NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO | - NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST, + NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST | + NVMF_OPT_NR_WRITE_QUEUES, .create_ctrl = nvme_tcp_create_ctrl, }; From b65bb777ef2237030f2802f2263ae9a0108f7acf Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 11 Dec 2018 23:38:58 -0800 Subject: [PATCH 33/33] nvme-rdma: support separate queue maps for read and write llow NVMF_OPT_NR_WRITE_QUEUES to describe additional write queues. In addition, implement .map_queues that will apply 2 queue maps for read and write queue sets. Note that with the separate queue map, HCTX_TYPE_READ will always use nr_io_queues and HCTX_TYPE_DEFAULT will use nr_write_queues. Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/rdma.c | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 5057d5ab5aaa..ed726da77b5b 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -645,6 +645,8 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) nr_io_queues = min_t(unsigned int, nr_io_queues, ibdev->num_comp_vectors); + nr_io_queues += min(opts->nr_write_queues, num_online_cpus()); + ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues); if (ret) return ret; @@ -714,6 +716,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, set->driver_data = ctrl; set->nr_hw_queues = nctrl->queue_count - 1; set->timeout = NVME_IO_TIMEOUT; + set->nr_maps = 2 /* default + read */; } ret = blk_mq_alloc_tag_set(set); @@ -1751,7 +1754,25 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) { struct nvme_rdma_ctrl *ctrl = set->driver_data; - return blk_mq_rdma_map_queues(&set->map[0], ctrl->device->dev, 0); + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; + set->map[HCTX_TYPE_READ].nr_queues = ctrl->ctrl.opts->nr_io_queues; + if (ctrl->ctrl.opts->nr_write_queues) { + /* separate read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = + ctrl->ctrl.opts->nr_write_queues; + set->map[HCTX_TYPE_READ].queue_offset = + ctrl->ctrl.opts->nr_write_queues; + } else { + /* mixed read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = + ctrl->ctrl.opts->nr_io_queues; + set->map[HCTX_TYPE_READ].queue_offset = 0; + } + blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_DEFAULT], + ctrl->device->dev, 0); + blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_READ], + ctrl->device->dev, 0); + return 0; } static const struct blk_mq_ops nvme_rdma_mq_ops = { @@ -1906,7 +1927,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work); INIT_WORK(&ctrl->ctrl.reset_work, nvme_rdma_reset_ctrl_work); - ctrl->ctrl.queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */ + ctrl->ctrl.queue_count = opts->nr_io_queues + opts->nr_write_queues + 1; ctrl->ctrl.sqsize = opts->queue_size - 1; ctrl->ctrl.kato = opts->kato; @@ -1957,7 +1978,8 @@ static struct nvmf_transport_ops nvme_rdma_transport = { .module = THIS_MODULE, .required_opts = NVMF_OPT_TRADDR, .allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY | - NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO, + NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO | + NVMF_OPT_NR_WRITE_QUEUES, .create_ctrl = nvme_rdma_create_ctrl, };