* [PATCH 1/4] fc_els: use 'union fc_tlv_desc'
2025-04-28 6:36 [PATCHv3 0/4] nvme-fc: FPIN link integrity handling hare
@ 2025-04-28 6:36 ` hare
2025-04-29 0:32 ` Justin Tee
2025-04-28 6:36 ` [PATCH 2/4] nvme-fc: marginal path handling hare
` (2 subsequent siblings)
3 siblings, 1 reply; 10+ messages in thread
From: hare @ 2025-04-28 6:36 UTC (permalink / raw)
To: Christoph Hellwig; +Cc: Keith Busch, Sagi Grimberg, linux-nvme, Hannes Reinecke
From: Hannes Reinecke <hare@kernel.org>
Introduce 'union fc_tlv_desc' to have a common structure for all FC
ELS TLV structures and avoid type casts.
Signed-off-by: Hannes Reinecke <hare@kernel.org>
---
drivers/scsi/lpfc/lpfc_els.c | 67 ++++++-------
drivers/scsi/scsi_transport_fc.c | 27 +++--
include/uapi/scsi/fc/fc_els.h | 165 +++++++++++++++++--------------
3 files changed, 131 insertions(+), 128 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 375a879c31f1..4748c00f0f32 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -33,6 +33,7 @@
#include <scsi/scsi_transport_fc.h>
#include <uapi/scsi/fc/fc_fs.h>
#include <uapi/scsi/fc/fc_els.h>
+#include <linux/nvme-fc-driver.h>
#include "lpfc_hw4.h"
#include "lpfc_hw.h"
@@ -3937,7 +3938,7 @@ lpfc_cmpl_els_edc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
{
IOCB_t *irsp_iocb;
struct fc_els_edc_resp *edc_rsp;
- struct fc_tlv_desc *tlv;
+ union fc_tlv_desc *tlv;
struct fc_diag_cg_sig_desc *pcgd;
struct fc_diag_lnkflt_desc *plnkflt;
struct lpfc_dmabuf *pcmd, *prsp;
@@ -4028,7 +4029,7 @@ lpfc_cmpl_els_edc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
goto out;
}
- dtag = be32_to_cpu(tlv->desc_tag);
+ dtag = be32_to_cpu(tlv->hdr.desc_tag);
switch (dtag) {
case ELS_DTAG_LNK_FAULT_CAP:
if (bytes_remain < FC_TLV_DESC_SZ_FROM_LENGTH(tlv) ||
@@ -4043,7 +4044,7 @@ lpfc_cmpl_els_edc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
sizeof(struct fc_diag_lnkflt_desc));
goto out;
}
- plnkflt = (struct fc_diag_lnkflt_desc *)tlv;
+ plnkflt = &tlv->lnkflt;
lpfc_printf_log(phba, KERN_INFO,
LOG_ELS | LOG_LDS_EVENT,
"4617 Link Fault Desc Data: 0x%08x 0x%08x "
@@ -4070,7 +4071,7 @@ lpfc_cmpl_els_edc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
goto out;
}
- pcgd = (struct fc_diag_cg_sig_desc *)tlv;
+ pcgd = &tlv->cg_sig;
lpfc_printf_log(
phba, KERN_INFO, LOG_ELS | LOG_CGN_MGMT,
"4616 CGN Desc Data: 0x%08x 0x%08x "
@@ -4125,10 +4126,8 @@ lpfc_cmpl_els_edc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
}
static void
-lpfc_format_edc_lft_desc(struct lpfc_hba *phba, struct fc_tlv_desc *tlv)
+lpfc_format_edc_lft_desc(struct lpfc_hba *phba, struct fc_diag_lnkflt_desc *lft)
{
- struct fc_diag_lnkflt_desc *lft = (struct fc_diag_lnkflt_desc *)tlv;
-
lft->desc_tag = cpu_to_be32(ELS_DTAG_LNK_FAULT_CAP);
lft->desc_len = cpu_to_be32(
FC_TLV_DESC_LENGTH_FROM_SZ(struct fc_diag_lnkflt_desc));
@@ -4141,10 +4140,8 @@ lpfc_format_edc_lft_desc(struct lpfc_hba *phba, struct fc_tlv_desc *tlv)
}
static void
-lpfc_format_edc_cgn_desc(struct lpfc_hba *phba, struct fc_tlv_desc *tlv)
+lpfc_format_edc_cgn_desc(struct lpfc_hba *phba, struct fc_diag_cg_sig_desc *cgd)
{
- struct fc_diag_cg_sig_desc *cgd = (struct fc_diag_cg_sig_desc *)tlv;
-
/* We are assuming cgd was zero'ed before calling this routine */
/* Configure the congestion detection capability */
@@ -4233,7 +4230,7 @@ lpfc_issue_els_edc(struct lpfc_vport *vport, uint8_t retry)
struct lpfc_hba *phba = vport->phba;
struct lpfc_iocbq *elsiocb;
struct fc_els_edc *edc_req;
- struct fc_tlv_desc *tlv;
+ union fc_tlv_desc *tlv;
u16 cmdsize;
struct lpfc_nodelist *ndlp;
u8 *pcmd = NULL;
@@ -4272,13 +4269,13 @@ lpfc_issue_els_edc(struct lpfc_vport *vport, uint8_t retry)
tlv = edc_req->desc;
if (cgn_desc_size) {
- lpfc_format_edc_cgn_desc(phba, tlv);
+ lpfc_format_edc_cgn_desc(phba, &tlv->cg_sig);
phba->cgn_sig_freq = lpfc_fabric_cgn_frequency;
tlv = fc_tlv_next_desc(tlv);
}
if (lft_desc_size)
- lpfc_format_edc_lft_desc(phba, tlv);
+ lpfc_format_edc_lft_desc(phba, &tlv->lnkflt);
lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS | LOG_CGN_MGMT,
"4623 Xmit EDC to remote "
@@ -5823,7 +5820,7 @@ lpfc_issue_els_edc_rsp(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
{
struct lpfc_hba *phba = vport->phba;
struct fc_els_edc_resp *edc_rsp;
- struct fc_tlv_desc *tlv;
+ union fc_tlv_desc *tlv;
struct lpfc_iocbq *elsiocb;
IOCB_t *icmd, *cmd;
union lpfc_wqe128 *wqe;
@@ -5867,10 +5864,10 @@ lpfc_issue_els_edc_rsp(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
FC_TLV_DESC_LENGTH_FROM_SZ(struct fc_els_lsri_desc));
edc_rsp->lsri.rqst_w0.cmd = ELS_EDC;
tlv = edc_rsp->desc;
- lpfc_format_edc_cgn_desc(phba, tlv);
+ lpfc_format_edc_cgn_desc(phba, &tlv->cg_sig);
tlv = fc_tlv_next_desc(tlv);
if (lft_desc_size)
- lpfc_format_edc_lft_desc(phba, tlv);
+ lpfc_format_edc_lft_desc(phba, &tlv->lnkflt);
lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
"Issue EDC ACC: did:x%x flg:x%lx refcnt %d",
@@ -9255,7 +9252,7 @@ lpfc_els_rcv_edc(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
{
struct lpfc_hba *phba = vport->phba;
struct fc_els_edc *edc_req;
- struct fc_tlv_desc *tlv;
+ union fc_tlv_desc *tlv;
uint8_t *payload;
uint32_t *ptr, dtag;
const char *dtag_nm;
@@ -9298,7 +9295,7 @@ lpfc_els_rcv_edc(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
goto out;
}
- dtag = be32_to_cpu(tlv->desc_tag);
+ dtag = be32_to_cpu(tlv->hdr.desc_tag);
switch (dtag) {
case ELS_DTAG_LNK_FAULT_CAP:
if (bytes_remain < FC_TLV_DESC_SZ_FROM_LENGTH(tlv) ||
@@ -9313,7 +9310,7 @@ lpfc_els_rcv_edc(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
sizeof(struct fc_diag_lnkflt_desc));
goto out;
}
- plnkflt = (struct fc_diag_lnkflt_desc *)tlv;
+ plnkflt = &tlv->lnkflt;
lpfc_printf_log(phba, KERN_INFO,
LOG_ELS | LOG_LDS_EVENT,
"4626 Link Fault Desc Data: x%08x len x%x "
@@ -9350,7 +9347,7 @@ lpfc_els_rcv_edc(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
phba->cgn_sig_freq = lpfc_fabric_cgn_frequency;
lpfc_least_capable_settings(
- phba, (struct fc_diag_cg_sig_desc *)tlv);
+ phba, &tlv->cg_sig);
break;
default:
dtag_nm = lpfc_get_tlv_dtag_nm(dtag);
@@ -9946,9 +9943,8 @@ lpfc_display_fpin_wwpn(struct lpfc_hba *phba, __be64 *wwnlist, u32 cnt)
* This function processes a Link Integrity FPIN event by logging a message.
**/
static void
-lpfc_els_rcv_fpin_li(struct lpfc_hba *phba, struct fc_tlv_desc *tlv)
+lpfc_els_rcv_fpin_li(struct lpfc_hba *phba, struct fc_fn_li_desc *li)
{
- struct fc_fn_li_desc *li = (struct fc_fn_li_desc *)tlv;
const char *li_evt_str;
u32 li_evt, cnt;
@@ -9977,9 +9973,8 @@ lpfc_els_rcv_fpin_li(struct lpfc_hba *phba, struct fc_tlv_desc *tlv)
* This function processes a Delivery FPIN event by logging a message.
**/
static void
-lpfc_els_rcv_fpin_del(struct lpfc_hba *phba, struct fc_tlv_desc *tlv)
+lpfc_els_rcv_fpin_del(struct lpfc_hba *phba, struct fc_fn_deli_desc *del)
{
- struct fc_fn_deli_desc *del = (struct fc_fn_deli_desc *)tlv;
const char *del_rsn_str;
u32 del_rsn;
__be32 *frame;
@@ -10015,9 +10010,8 @@ lpfc_els_rcv_fpin_del(struct lpfc_hba *phba, struct fc_tlv_desc *tlv)
* This function processes a Peer Congestion FPIN event by logging a message.
**/
static void
-lpfc_els_rcv_fpin_peer_cgn(struct lpfc_hba *phba, struct fc_tlv_desc *tlv)
+lpfc_els_rcv_fpin_peer_cgn(struct lpfc_hba *phba, struct fc_fn_peer_congn_desc *pc)
{
- struct fc_fn_peer_congn_desc *pc = (struct fc_fn_peer_congn_desc *)tlv;
const char *pc_evt_str;
u32 pc_evt, cnt;
@@ -10054,10 +10048,9 @@ lpfc_els_rcv_fpin_peer_cgn(struct lpfc_hba *phba, struct fc_tlv_desc *tlv)
* to the upper layer or 0 to indicate don't deliver it.
**/
static int
-lpfc_els_rcv_fpin_cgn(struct lpfc_hba *phba, struct fc_tlv_desc *tlv)
+lpfc_els_rcv_fpin_cgn(struct lpfc_hba *phba, struct fc_fn_congn_desc *cgn)
{
struct lpfc_cgn_info *cp;
- struct fc_fn_congn_desc *cgn = (struct fc_fn_congn_desc *)tlv;
const char *cgn_evt_str;
u32 cgn_evt;
const char *cgn_sev_str;
@@ -10160,7 +10153,7 @@ lpfc_els_rcv_fpin(struct lpfc_vport *vport, void *p, u32 fpin_length)
{
struct lpfc_hba *phba = vport->phba;
struct fc_els_fpin *fpin = (struct fc_els_fpin *)p;
- struct fc_tlv_desc *tlv, *first_tlv, *current_tlv;
+ union fc_tlv_desc *tlv, *first_tlv, *current_tlv;
const char *dtag_nm;
int desc_cnt = 0, bytes_remain, cnt;
u32 dtag, deliver = 0;
@@ -10185,7 +10178,7 @@ lpfc_els_rcv_fpin(struct lpfc_vport *vport, void *p, u32 fpin_length)
return;
}
- tlv = (struct fc_tlv_desc *)&fpin->fpin_desc[0];
+ tlv = &fpin->fpin_desc[0];
first_tlv = tlv;
bytes_remain = fpin_length - offsetof(struct fc_els_fpin, fpin_desc);
bytes_remain = min_t(u32, bytes_remain, be32_to_cpu(fpin->desc_len));
@@ -10193,22 +10186,22 @@ lpfc_els_rcv_fpin(struct lpfc_vport *vport, void *p, u32 fpin_length)
/* process each descriptor separately */
while (bytes_remain >= FC_TLV_DESC_HDR_SZ &&
bytes_remain >= FC_TLV_DESC_SZ_FROM_LENGTH(tlv)) {
- dtag = be32_to_cpu(tlv->desc_tag);
+ dtag = be32_to_cpu(tlv->hdr.desc_tag);
switch (dtag) {
case ELS_DTAG_LNK_INTEGRITY:
- lpfc_els_rcv_fpin_li(phba, tlv);
+ lpfc_els_rcv_fpin_li(phba, &tlv->li);
deliver = 1;
break;
case ELS_DTAG_DELIVERY:
- lpfc_els_rcv_fpin_del(phba, tlv);
+ lpfc_els_rcv_fpin_del(phba, &tlv->deli);
deliver = 1;
break;
case ELS_DTAG_PEER_CONGEST:
- lpfc_els_rcv_fpin_peer_cgn(phba, tlv);
+ lpfc_els_rcv_fpin_peer_cgn(phba, &tlv->peer_congn);
deliver = 1;
break;
case ELS_DTAG_CONGESTION:
- deliver = lpfc_els_rcv_fpin_cgn(phba, tlv);
+ deliver = lpfc_els_rcv_fpin_cgn(phba, &tlv->congn);
break;
default:
dtag_nm = lpfc_get_tlv_dtag_nm(dtag);
@@ -10221,12 +10214,12 @@ lpfc_els_rcv_fpin(struct lpfc_vport *vport, void *p, u32 fpin_length)
return;
}
lpfc_cgn_update_stat(phba, dtag);
- cnt = be32_to_cpu(tlv->desc_len);
+ cnt = be32_to_cpu(tlv->hdr.desc_len);
/* Sanity check descriptor length. The desc_len value does not
* include space for the desc_tag and the desc_len fields.
*/
- len -= (cnt + sizeof(struct fc_tlv_desc));
+ len -= (cnt + sizeof(struct fc_tlv_desc_hdr));
if (len < 0) {
dtag_nm = lpfc_get_tlv_dtag_nm(dtag);
lpfc_printf_log(phba, KERN_WARNING, LOG_CGN_MGMT,
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 082f76e76721..a62636c6f708 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -750,13 +750,12 @@ fc_cn_stats_update(u16 event_type, struct fc_fpin_stats *stats)
*
*/
static void
-fc_fpin_li_stats_update(struct Scsi_Host *shost, struct fc_tlv_desc *tlv)
+fc_fpin_li_stats_update(struct Scsi_Host *shost, struct fc_fn_li_desc *li_desc)
{
u8 i;
struct fc_rport *rport = NULL;
struct fc_rport *attach_rport = NULL;
struct fc_host_attrs *fc_host = shost_to_fc_host(shost);
- struct fc_fn_li_desc *li_desc = (struct fc_fn_li_desc *)tlv;
u16 event_type = be16_to_cpu(li_desc->event_type);
u64 wwpn;
@@ -799,12 +798,11 @@ fc_fpin_li_stats_update(struct Scsi_Host *shost, struct fc_tlv_desc *tlv)
*/
static void
fc_fpin_delivery_stats_update(struct Scsi_Host *shost,
- struct fc_tlv_desc *tlv)
+ struct fc_fn_deli_desc *dn_desc)
{
struct fc_rport *rport = NULL;
struct fc_rport *attach_rport = NULL;
struct fc_host_attrs *fc_host = shost_to_fc_host(shost);
- struct fc_fn_deli_desc *dn_desc = (struct fc_fn_deli_desc *)tlv;
u32 reason_code = be32_to_cpu(dn_desc->deli_reason_code);
rport = fc_find_rport_by_wwpn(shost,
@@ -830,13 +828,11 @@ fc_fpin_delivery_stats_update(struct Scsi_Host *shost,
*/
static void
fc_fpin_peer_congn_stats_update(struct Scsi_Host *shost,
- struct fc_tlv_desc *tlv)
+ struct fc_fn_peer_congn_desc *pc_desc)
{
u8 i;
struct fc_rport *rport = NULL;
struct fc_rport *attach_rport = NULL;
- struct fc_fn_peer_congn_desc *pc_desc =
- (struct fc_fn_peer_congn_desc *)tlv;
u16 event_type = be16_to_cpu(pc_desc->event_type);
u64 wwpn;
@@ -876,10 +872,9 @@ fc_fpin_peer_congn_stats_update(struct Scsi_Host *shost,
*/
static void
fc_fpin_congn_stats_update(struct Scsi_Host *shost,
- struct fc_tlv_desc *tlv)
+ struct fc_fn_congn_desc *congn)
{
struct fc_host_attrs *fc_host = shost_to_fc_host(shost);
- struct fc_fn_congn_desc *congn = (struct fc_fn_congn_desc *)tlv;
fc_cn_stats_update(be16_to_cpu(congn->event_type),
&fc_host->fpin_stats);
@@ -899,32 +894,32 @@ fc_host_fpin_rcv(struct Scsi_Host *shost, u32 fpin_len, char *fpin_buf,
u8 event_acknowledge)
{
struct fc_els_fpin *fpin = (struct fc_els_fpin *)fpin_buf;
- struct fc_tlv_desc *tlv;
+ union fc_tlv_desc *tlv;
u32 bytes_remain;
u32 dtag;
enum fc_host_event_code event_code =
event_acknowledge ? FCH_EVT_LINK_FPIN_ACK : FCH_EVT_LINK_FPIN;
/* Update Statistics */
- tlv = (struct fc_tlv_desc *)&fpin->fpin_desc[0];
+ tlv = &fpin->fpin_desc[0];
bytes_remain = fpin_len - offsetof(struct fc_els_fpin, fpin_desc);
bytes_remain = min_t(u32, bytes_remain, be32_to_cpu(fpin->desc_len));
while (bytes_remain >= FC_TLV_DESC_HDR_SZ &&
bytes_remain >= FC_TLV_DESC_SZ_FROM_LENGTH(tlv)) {
- dtag = be32_to_cpu(tlv->desc_tag);
+ dtag = be32_to_cpu(tlv->hdr.desc_tag);
switch (dtag) {
case ELS_DTAG_LNK_INTEGRITY:
- fc_fpin_li_stats_update(shost, tlv);
+ fc_fpin_li_stats_update(shost, &tlv->li);
break;
case ELS_DTAG_DELIVERY:
- fc_fpin_delivery_stats_update(shost, tlv);
+ fc_fpin_delivery_stats_update(shost, &tlv->deli);
break;
case ELS_DTAG_PEER_CONGEST:
- fc_fpin_peer_congn_stats_update(shost, tlv);
+ fc_fpin_peer_congn_stats_update(shost, &tlv->peer_congn);
break;
case ELS_DTAG_CONGESTION:
- fc_fpin_congn_stats_update(shost, tlv);
+ fc_fpin_congn_stats_update(shost, &tlv->congn);
}
bytes_remain -= FC_TLV_DESC_SZ_FROM_LENGTH(tlv);
diff --git a/include/uapi/scsi/fc/fc_els.h b/include/uapi/scsi/fc/fc_els.h
index 16782c360de3..aceabd31ee88 100644
--- a/include/uapi/scsi/fc/fc_els.h
+++ b/include/uapi/scsi/fc/fc_els.h
@@ -253,12 +253,12 @@ enum fc_ls_tlv_dtag {
/*
- * Generic Link Service TLV Descriptor format
+ * Generic Link Service TLV Descriptor header
*
* This structure, as it defines no payload, will also be referred to
* as the "tlv header" - which contains the tag and len fields.
*/
-struct fc_tlv_desc {
+struct fc_tlv_desc_hdr {
__be32 desc_tag; /* Notification Descriptor Tag */
__be32 desc_len; /* Length of Descriptor (in bytes).
* Size of descriptor excluding
@@ -267,36 +267,6 @@ struct fc_tlv_desc {
__u8 desc_value[]; /* Descriptor Value */
};
-/* Descriptor tag and len fields are considered the mandatory header
- * for a descriptor
- */
-#define FC_TLV_DESC_HDR_SZ sizeof(struct fc_tlv_desc)
-
-/*
- * Macro, used when initializing payloads, to return the descriptor length.
- * Length is size of descriptor minus the tag and len fields.
- */
-#define FC_TLV_DESC_LENGTH_FROM_SZ(desc) \
- (sizeof(desc) - FC_TLV_DESC_HDR_SZ)
-
-/* Macro, used on received payloads, to return the descriptor length */
-#define FC_TLV_DESC_SZ_FROM_LENGTH(tlv) \
- (__be32_to_cpu((tlv)->desc_len) + FC_TLV_DESC_HDR_SZ)
-
-/*
- * This helper is used to walk descriptors in a descriptor list.
- * Given the address of the current descriptor, which minimally contains a
- * tag and len field, calculate the address of the next descriptor based
- * on the len field.
- */
-static inline void *fc_tlv_next_desc(void *desc)
-{
- struct fc_tlv_desc *tlv = desc;
-
- return (desc + FC_TLV_DESC_SZ_FROM_LENGTH(tlv));
-}
-
-
/*
* Link Service Request Information Descriptor
*/
@@ -1094,19 +1064,6 @@ struct fc_fn_congn_desc {
__u8 resv[3]; /* reserved - must be zero */
};
-/*
- * ELS_FPIN - Fabric Performance Impact Notification
- */
-struct fc_els_fpin {
- __u8 fpin_cmd; /* command (0x16) */
- __u8 fpin_zero[3]; /* specified as zero - part of cmd */
- __be32 desc_len; /* Length of Descriptor List (in bytes).
- * Size of ELS excluding fpin_cmd,
- * fpin_zero and desc_len fields.
- */
- struct fc_tlv_desc fpin_desc[]; /* Descriptor list */
-};
-
/* Diagnostic Function Descriptor - FPIN Registration */
struct fc_df_desc_fpin_reg {
__be32 desc_tag; /* FPIN Registration (0x00030001) */
@@ -1125,33 +1082,6 @@ struct fc_df_desc_fpin_reg {
*/
};
-/*
- * ELS_RDF - Register Diagnostic Functions
- */
-struct fc_els_rdf {
- __u8 fpin_cmd; /* command (0x19) */
- __u8 fpin_zero[3]; /* specified as zero - part of cmd */
- __be32 desc_len; /* Length of Descriptor List (in bytes).
- * Size of ELS excluding fpin_cmd,
- * fpin_zero and desc_len fields.
- */
- struct fc_tlv_desc desc[]; /* Descriptor list */
-};
-
-/*
- * ELS RDF LS_ACC Response.
- */
-struct fc_els_rdf_resp {
- struct fc_els_ls_acc acc_hdr;
- __be32 desc_list_len; /* Length of response (in
- * bytes). Excludes acc_hdr
- * and desc_list_len fields.
- */
- struct fc_els_lsri_desc lsri;
- struct fc_tlv_desc desc[]; /* Supported Descriptor list */
-};
-
-
/*
* Diagnostic Capability Descriptors for EDC ELS
*/
@@ -1221,6 +1151,65 @@ struct fc_diag_cg_sig_desc {
struct fc_diag_cg_sig_freq rcv_signal_frequency;
};
+/*
+ * Generic Link Service TLV Descriptor format
+ *
+ * This structure, as it defines no payload, will also be referred to
+ * as the "tlv header" - which contains the tag and len fields.
+ */
+union fc_tlv_desc {
+ struct fc_tlv_desc_hdr hdr;
+ struct fc_els_lsri_desc lsri;
+ struct fc_fn_li_desc li;
+ struct fc_fn_deli_desc deli;
+ struct fc_fn_peer_congn_desc peer_congn;
+ struct fc_fn_congn_desc congn;
+ struct fc_df_desc_fpin_reg fpin_reg;
+ struct fc_diag_lnkflt_desc lnkflt;
+ struct fc_diag_cg_sig_desc cg_sig;
+};
+
+/* Descriptor tag and len fields are considered the mandatory header
+ * for a descriptor
+ */
+#define FC_TLV_DESC_HDR_SZ sizeof(struct fc_tlv_desc_hdr)
+
+/*
+ * Macro, used when initializing payloads, to return the descriptor length.
+ * Length is size of descriptor minus the tag and len fields.
+ */
+#define FC_TLV_DESC_LENGTH_FROM_SZ(desc) \
+ (sizeof(desc) - FC_TLV_DESC_HDR_SZ)
+
+/* Macro, used on received payloads, to return the descriptor length */
+#define FC_TLV_DESC_SZ_FROM_LENGTH(tlv) \
+ (__be32_to_cpu((tlv)->hdr.desc_len) + FC_TLV_DESC_HDR_SZ)
+
+/*
+ * This helper is used to walk descriptors in a descriptor list.
+ * Given the address of the current descriptor, which minimally contains a
+ * tag and len field, calculate the address of the next descriptor based
+ * on the len field.
+ */
+static inline union fc_tlv_desc *fc_tlv_next_desc(union fc_tlv_desc *desc)
+{
+ return (union fc_tlv_desc *)((u8 *)desc + FC_TLV_DESC_SZ_FROM_LENGTH(desc));
+}
+
+
+/*
+ * ELS_FPIN - Fabric Performance Impact Notification
+ */
+struct fc_els_fpin {
+ __u8 fpin_cmd; /* command (0x16) */
+ __u8 fpin_zero[3]; /* specified as zero - part of cmd */
+ __be32 desc_len; /* Length of Descriptor List (in bytes).
+ * Size of ELS excluding fpin_cmd,
+ * fpin_zero and desc_len fields.
+ */
+ union fc_tlv_desc fpin_desc[]; /* Descriptor list */
+};
+
/*
* ELS_EDC - Exchange Diagnostic Capabilities
*/
@@ -1231,10 +1220,37 @@ struct fc_els_edc {
* Size of ELS excluding edc_cmd,
* edc_zero and desc_len fields.
*/
- struct fc_tlv_desc desc[];
+ union fc_tlv_desc desc[];
/* Diagnostic Descriptor list */
};
+/*
+ * ELS_RDF - Register Diagnostic Functions
+ */
+struct fc_els_rdf {
+ __u8 fpin_cmd; /* command (0x19) */
+ __u8 fpin_zero[3]; /* specified as zero - part of cmd */
+ __be32 desc_len; /* Length of Descriptor List (in bytes).
+ * Size of ELS excluding fpin_cmd,
+ * fpin_zero and desc_len fields.
+ */
+ union fc_tlv_desc desc[]; /* Descriptor list */
+};
+
+/*
+ * ELS RDF LS_ACC Response.
+ */
+struct fc_els_rdf_resp {
+ struct fc_els_ls_acc acc_hdr;
+ __be32 desc_list_len; /* Length of response (in
+ * bytes). Excludes acc_hdr
+ * and desc_list_len fields.
+ */
+ struct fc_els_lsri_desc lsri;
+ union fc_tlv_desc desc[]; /* Supported Descriptor list */
+};
+
+
/*
* ELS EDC LS_ACC Response.
*/
@@ -1245,9 +1261,8 @@ struct fc_els_edc_resp {
* and desc_list_len fields.
*/
struct fc_els_lsri_desc lsri;
- struct fc_tlv_desc desc[];
+ union fc_tlv_desc desc[];
/* Supported Diagnostic Descriptor list */
};
-
#endif /* _FC_ELS_H_ */
--
2.35.3
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 2/4] nvme-fc: marginal path handling
2025-04-28 6:36 [PATCHv3 0/4] nvme-fc: FPIN link integrity handling hare
2025-04-28 6:36 ` [PATCH 1/4] fc_els: use 'union fc_tlv_desc' hare
@ 2025-04-28 6:36 ` hare
2025-04-28 6:36 ` [PATCH 3/4] lpfc: enable FPIN notification for NVMe hare
2025-04-28 6:36 ` [PATCH 4/4] qla2xxx: " hare
3 siblings, 0 replies; 10+ messages in thread
From: hare @ 2025-04-28 6:36 UTC (permalink / raw)
To: Christoph Hellwig; +Cc: Keith Busch, Sagi Grimberg, linux-nvme, Hannes Reinecke
From: Hannes Reinecke <hare@kernel.org>
FPIN LI (link integrity) messages are received when the attached
fabric detects hardware errors. In response to these messages I/O
should be directed away from the affected ports, and only used
if the 'optimized' paths are unavailable.
To handle this a new controller flag 'NVME_CTRL_MARGINAL' is added
which will cause the multipath scheduler to skip these paths when
checking for 'optimized' paths. They are, however, still eligible
for non-optimized path selected. The flag is cleared upon reset as then the
faulty hardware might be replaced.
Signed-off-by: Hannes Reinecke <hare@kernel.org>
---
drivers/nvme/host/core.c | 1 +
drivers/nvme/host/fc.c | 99 ++++++++++++++++++++++++++++++++++
drivers/nvme/host/multipath.c | 17 +++---
drivers/nvme/host/nvme.h | 6 +++
include/linux/nvme-fc-driver.h | 3 ++
5 files changed, 120 insertions(+), 6 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index eb6ea8acb3cc..ab851df98079 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4833,6 +4833,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
WRITE_ONCE(ctrl->state, NVME_CTRL_NEW);
ctrl->passthru_err_log_enabled = false;
clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
+ clear_bit(NVME_CTRL_MARGINAL, &ctrl->flags);
spin_lock_init(&ctrl->lock);
mutex_init(&ctrl->namespaces_lock);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 2257c3c96dd2..475a636d1f7d 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -786,6 +786,10 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
"Reconnect", ctrl->cnum);
set_bit(ASSOC_FAILED, &ctrl->flags);
+
+ /* clear 'marginal' flag as controller will be reset */
+ clear_bit(NVME_CTRL_MARGINAL, &ctrl->flags);
+
nvme_reset_ctrl(&ctrl->ctrl);
}
@@ -3713,6 +3717,101 @@ static struct nvmf_transport_ops nvme_fc_transport = {
.create_ctrl = nvme_fc_create_ctrl,
};
+static struct nvme_fc_rport *nvme_fc_rport_from_wwpn(struct nvme_fc_lport *lport,
+ u64 rport_wwpn)
+{
+ struct nvme_fc_rport *rport;
+
+ list_for_each_entry(rport, &lport->endp_list, endp_list) {
+ if (!nvme_fc_rport_get(rport))
+ continue;
+ if (rport->remoteport.port_name == rport_wwpn &&
+ rport->remoteport.port_role & FC_PORT_ROLE_NVME_TARGET)
+ return rport;
+ nvme_fc_rport_put(rport);
+ }
+ return NULL;
+}
+
+static void
+nvme_fc_fpin_li_lport_update(struct nvme_fc_lport *lport, struct fc_fn_li_desc *li)
+{
+ unsigned int i, pname_count = be32_to_cpu(li->pname_count);
+ u64 attached_wwpn = be64_to_cpu(li->attached_wwpn);
+ struct nvme_fc_rport *attached_rport;
+
+ for (i = 0; i < pname_count; i++) {
+ struct nvme_fc_rport *rport;
+ u64 wwpn = be64_to_cpu(li->pname_list[i]);
+
+ rport = nvme_fc_rport_from_wwpn(lport, wwpn);
+ if (!rport)
+ continue;
+ if (wwpn != attached_wwpn) {
+ struct nvme_fc_ctrl *ctrl;
+
+ spin_lock_irq(&rport->lock);
+ list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list)
+ set_bit(NVME_CTRL_MARGINAL, &ctrl->ctrl.flags);
+ spin_unlock_irq(&rport->lock);
+ }
+ nvme_fc_rport_put(rport);
+ }
+
+ attached_rport = nvme_fc_rport_from_wwpn(lport, attached_wwpn);
+ if (attached_rport) {
+ struct nvme_fc_ctrl *ctrl;
+
+ spin_lock_irq(&attached_rport->lock);
+ list_for_each_entry(ctrl, &attached_rport->ctrl_list, ctrl_list)
+ set_bit(NVME_CTRL_MARGINAL, &ctrl->ctrl.flags);
+ spin_unlock_irq(&attached_rport->lock);
+ nvme_fc_rport_put(attached_rport);
+ }
+}
+
+/**
+ * fc_host_fpin_rcv() - Process a received FPIN.
+ * @localport: local port the FPIN was received on
+ * @fpin_len: length of FPIN payload, in bytes
+ * @fpin_buf: pointer to FPIN payload
+ * Notes:
+ * This routine assumes no locks are held on entry.
+ */
+void
+nvme_fc_fpin_rcv(struct nvme_fc_local_port *localport,
+ u32 fpin_len, char *fpin_buf)
+{
+ struct nvme_fc_lport *lport;
+ struct fc_els_fpin *fpin = (struct fc_els_fpin *)fpin_buf;
+ union fc_tlv_desc *tlv;
+ u32 bytes_remain;
+ u32 dtag;
+
+ if (!localport)
+ return;
+ lport = localport_to_lport(localport);
+ tlv = &fpin->fpin_desc[0];
+ bytes_remain = fpin_len - offsetof(struct fc_els_fpin, fpin_desc);
+ bytes_remain = min_t(u32, bytes_remain, be32_to_cpu(fpin->desc_len));
+
+ while (bytes_remain >= FC_TLV_DESC_HDR_SZ &&
+ bytes_remain >= FC_TLV_DESC_SZ_FROM_LENGTH(tlv)) {
+ dtag = be32_to_cpu(tlv->hdr.desc_tag);
+ switch (dtag) {
+ case ELS_DTAG_LNK_INTEGRITY:
+ nvme_fc_fpin_li_lport_update(lport, &tlv->li);
+ break;
+ default:
+ break;
+ }
+
+ bytes_remain -= FC_TLV_DESC_SZ_FROM_LENGTH(tlv);
+ tlv = fc_tlv_next_desc(tlv);
+ }
+}
+EXPORT_SYMBOL(nvme_fc_fpin_rcv);
+
/* Arbitrary successive failures max. With lots of subsystems could be high */
#define DISCOVERY_MAX_FAIL 20
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 250f3da67cc9..6d7425d34dfc 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -273,11 +273,14 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
switch (ns->ana_state) {
case NVME_ANA_OPTIMIZED:
- if (distance < found_distance) {
- found_distance = distance;
- found = ns;
+ if (!nvme_ctrl_is_marginal(ns->ctrl)) {
+ if (distance < found_distance) {
+ found_distance = distance;
+ found = ns;
+ }
+ break;
}
- break;
+ fallthrough;
case NVME_ANA_NONOPTIMIZED:
if (distance < fallback_distance) {
fallback_distance = distance;
@@ -330,7 +333,8 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head)
if (ns->ana_state == NVME_ANA_OPTIMIZED) {
found = ns;
- goto out;
+ if (!nvme_ctrl_is_marginal(ns->ctrl))
+ goto out;
}
if (ns->ana_state == NVME_ANA_NONOPTIMIZED)
found = ns;
@@ -394,7 +398,8 @@ static struct nvme_ns *nvme_queue_depth_path(struct nvme_ns_head *head)
static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
{
return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
- ns->ana_state == NVME_ANA_OPTIMIZED;
+ ns->ana_state == NVME_ANA_OPTIMIZED &&
+ !nvme_ctrl_is_marginal(ns->ctrl);
}
static struct nvme_ns *nvme_numa_path(struct nvme_ns_head *head)
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index c1b4ef6c5233..503df5dc2934 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -275,6 +275,7 @@ enum nvme_ctrl_flags {
NVME_CTRL_SKIP_ID_CNS_CS = 4,
NVME_CTRL_DIRTY_CAPABILITY = 5,
NVME_CTRL_FROZEN = 6,
+ NVME_CTRL_MARGINAL = 7,
};
struct nvme_ctrl {
@@ -419,6 +420,11 @@ static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
return READ_ONCE(ctrl->state);
}
+static inline bool nvme_ctrl_is_marginal(struct nvme_ctrl *ctrl)
+{
+ return test_bit(NVME_CTRL_MARGINAL, &ctrl->flags);
+}
+
enum nvme_iopolicy {
NVME_IOPOLICY_NUMA,
NVME_IOPOLICY_RR,
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index 9f6acadfe0c8..bcd3b1e5a256 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -536,6 +536,9 @@ void nvme_fc_rescan_remoteport(struct nvme_fc_remote_port *remoteport);
int nvme_fc_set_remoteport_devloss(struct nvme_fc_remote_port *remoteport,
u32 dev_loss_tmo);
+void nvme_fc_fpin_rcv(struct nvme_fc_local_port *localport,
+ u32 fpin_len, char *fpin_buf);
+
/*
* Routine called to pass a NVME-FC LS request, received by the lldd,
* to the nvme-fc transport.
--
2.35.3
^ permalink raw reply related [flat|nested] 10+ messages in thread