From d7e3fa7d06bf7fcaac186d3c4d635caac166d36c Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Thu, 30 Jul 2026 21:28:19 +0530 Subject: [PATCH] scsi: qla2xxx: Fix soft lockup polling continuation IOCB signature qla27xx_copy_multiple_pkt() and qla27xx_copy_fpin_pkt() poll rsp_q->ring_ptr->signature for RESPONSE_PROCESSED (0xDEADDEAD) to decide whether the next continuation IOCB has arrived, spinning on cpu_relax() without advancing the ring or decrementing the entry count while it has not. response_t::signature lives at byte offset 60, but a continuation IOCB (sts_cont_entry_t / struct sts_cont_entry_ext) carries raw FC frame payload at that offset (data[56..59]). A received frame whose payload bytes happen to equal 0xDEADDEAD is therefore misread as "not yet arrived", and the loop spins forever in interrupt/DPC context, causing a CPU soft lockup. The poll is also unnecessary: callers of qla27xx_copy_multiple_pkt() (PT_LS4_UNSOL and the NVMe purls path) already gate on qla_chk_cont_iocb_avail(), which guarantees all entry_count IOCBs are present before copying begins. The sibling helper __qla_copy_purex_to_buffer() already drops the signature poll and relies on the entry_type == STATUS_CONT_TYPE guard instead. Remove the signature busy-wait from both helpers, keeping the entry_type guard, and gate the FPIN path with qla_chk_cont_iocb_avail() so it defers and re-processes on the next interrupt once all continuation IOCBs have arrived, mirroring the ELS_AUTH_ELS and PT_LS4_UNSOL arms. With this the signature field is never read on a continuation IOCB, eliminating the payload-aliasing lockup. Fixes: 9f2475fe7406 ("scsi: qla2xxx: SAN congestion management implementation") Cc: stable@vger.kernel.org Reported-by: Sashiko Signed-off-by: Nilesh Javali Link: https://patch.msgid.link/20260730155838.2119230-15-njavali@marvell.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/qla2xxx/qla_isr.c | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 6375c18fe392..d9019f2b059c 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1002,14 +1002,6 @@ qla27xx_copy_multiple_pkt(struct scsi_qla_host *vha, void **pkt, do { while ((total_bytes > 0) && (entry_count_remaining > 0)) { - if (rsp_q->ring_ptr->signature == RESPONSE_PROCESSED) { - ql_dbg(ql_dbg_async, vha, 0x5084, - "Ran out of IOCBs, partial data 0x%x\n", - buffer_copy_offset); - cpu_relax(); - continue; - } - *pkt = rsp_q->ring_ptr; data = ((sts_cont_entry_t *)*pkt)->data; data_sz = qla_sts_cont_data_size(ha); @@ -1299,14 +1291,6 @@ qla27xx_copy_fpin_pkt(struct scsi_qla_host *vha, void **pkt, do { while ((total_bytes > 0) && (entry_count_remaining > 0)) { - if (rsp_q->ring_ptr->signature == RESPONSE_PROCESSED) { - ql_dbg(ql_dbg_async, vha, 0x5084, - "Ran out of IOCBs, partial data 0x%x\n", - buffer_copy_offset); - cpu_relax(); - continue; - } - *pkt = rsp_q->ring_ptr; data = ((sts_cont_entry_t *)*pkt)->data; data_sz = qla_sts_cont_data_size(ha); @@ -4272,9 +4256,24 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha, "SCM not active for this port\n"); break; } + if (qla_chk_cont_iocb_avail(vha, rsp, + (response_t *)pkt, rsp_in)) { + /* + * ring_ptr and ring_index were + * pre-incremented above. Reset them + * back to current. Wait for next + * interrupt with all IOCBs to arrive + * and re-process. + */ + qla_rsp_ring_rewind_to(rsp, + (response_t *)pkt, cur_ring_index); + + ql_dbg(ql_dbg_init, vha, 0x5095, + "Defer processing FPIN...\n"); + return; + } pure_item = qla27xx_copy_fpin_pkt(vha, (void **)&pkt, &rsp); - __update_rsp_in(is_shadow_hba, rsp, rsp_in); if (!pure_item) break; qla24xx_queue_purex_item(vha, pure_item,