[rocky8_10] History Rebuild through kernel-4.18.0-553.97.1.el8_10

Makefile.rhelver

@@ -12,7 +12,7 @@ RHEL_MINOR = 10
 #
 # Use this spot to avoid future merge conflicts.
 # Do not trim this comment.
-RHEL_RELEASE = 553.94.1
+RHEL_RELEASE = 553.97.1
 
 #
 # ZSTREAM

arch/x86/xen/smp_hvm.c

@@ -19,6 +19,12 @@ static void __init xen_hvm_smp_prepare_boot_cpu(void)
 	 */
 	xen_vcpu_setup(0);
 
+	/*
+	 * Called again in case the kernel boots on vcpu >= MAX_VIRT_CPUS.
+	 * Refer to comments in xen_hvm_init_time_ops().
+	 */
+	xen_hvm_init_time_ops();
+
 	/*
 	 * The alternative logic (which patches the unlock/lock) runs before
 	 * the smp bootup up code is activated. Hence we need to set this up

arch/x86/xen/time.c

@@ -31,6 +31,8 @@
 /* Xen may fire a timer up to this many ns early */
 #define TIMER_SLOP	100000
 
+static u64 xen_sched_clock_offset __read_mostly;
+
 /* Get the TSC speed from Xen */
 static unsigned long xen_tsc_khz(void)
 {
@@ -57,6 +59,11 @@ static u64 xen_clocksource_get_cycles(struct clocksource *cs)
 	return xen_clocksource_read();
 }
 
+static u64 xen_sched_clock(void)
+{
+	return xen_clocksource_read() - xen_sched_clock_offset;
+}
+
 static void xen_read_wallclock(struct timespec64 *ts)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
@@ -361,8 +368,6 @@ void xen_timer_resume(void)
 {
 	int cpu;
 
-	pvclock_resume();
-
 	if (xen_clockevent != &xen_vcpuop_clockevent)
 		return;
 
@@ -374,17 +379,20 @@ void xen_timer_resume(void)
 }
 
 static const struct pv_time_ops xen_time_ops __initconst = {
-	.sched_clock = xen_clocksource_read,
+	.sched_clock = xen_sched_clock,
 	.steal_clock = xen_steal_clock,
 };
 
 static struct pvclock_vsyscall_time_info *xen_clock __read_mostly;
+static u64 xen_clock_value_saved;
 
 void xen_save_time_memory_area(void)
 {
 	struct vcpu_register_time_memory_area t;
 	int ret;
 
+	xen_clock_value_saved = xen_clocksource_read() - xen_sched_clock_offset;
+
 	if (!xen_clock)
 		return;
 
@@ -404,7 +412,7 @@ void xen_restore_time_memory_area(void)
 	int ret;
 
 	if (!xen_clock)
-		return;
+		goto out;
 
 	t.addr.v = &xen_clock->pvti;
 
@@ -422,6 +430,11 @@ void xen_restore_time_memory_area(void)
 	if (ret != 0)
 		pr_notice("Cannot restore secondary vcpu_time_info (err %d)",
 			  ret);
+
+out:
+	/* Need pvclock_resume() before using xen_clocksource_read(). */
+	pvclock_resume();
+	xen_sched_clock_offset = xen_clocksource_read() - xen_clock_value_saved;
 }
 
 static void xen_setup_vsyscall_time_info(void)
@@ -513,6 +526,7 @@ static void __init xen_time_init(void)
 
 void __ref xen_init_time_ops(void)
 {
+	xen_sched_clock_offset = xen_clocksource_read();
 	pv_time_ops = xen_time_ops;
 
 	x86_init.timers.timer_init = xen_time_init;
@@ -541,6 +555,11 @@ static void xen_hvm_setup_cpu_clockevents(void)
 
 void __init xen_hvm_init_time_ops(void)
 {
+	static bool hvm_time_initialized;
+
+	if (hvm_time_initialized)
+		return;
+
 	/*
 	 * vector callback is needed otherwise we cannot receive interrupts
 	 * on cpu > 0 and at this point we don't know how many cpus are
@@ -550,17 +569,34 @@ void __init xen_hvm_init_time_ops(void)
 		return;
 
 	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
-		printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
-				"disable pv timer\n");
+		pr_info_once("Xen doesn't support pvclock on HVM, disable pv timer");
 		return;
 	}
 
+	/*
+	 * Only MAX_VIRT_CPUS 'vcpu_info' are embedded inside 'shared_info'.
+	 * The __this_cpu_read(xen_vcpu) is still NULL when Xen HVM guest
+	 * boots on vcpu >= MAX_VIRT_CPUS (e.g., kexec), To access
+	 * __this_cpu_read(xen_vcpu) via xen_clocksource_read() will panic.
+	 *
+	 * The xen_hvm_init_time_ops() should be called again later after
+	 * __this_cpu_read(xen_vcpu) is available.
+	 */
+	if (!__this_cpu_read(xen_vcpu)) {
+		pr_info("Delay xen_init_time_common() as kernel is running on vcpu=%d\n",
+			xen_vcpu_nr(0));
+		return;
+	}
+
+	xen_sched_clock_offset = xen_clocksource_read();
 	pv_time_ops = xen_time_ops;
 	x86_init.timers.setup_percpu_clockev = xen_time_init;
 	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
 
 	x86_platform.calibrate_tsc = xen_tsc_khz;
 	x86_platform.get_wallclock = xen_get_wallclock;
 	x86_platform.set_wallclock = xen_set_wallclock;
+
+	hvm_time_initialized = true;
 }
 #endif

ciq/ciq_backports/kernel-4.18.0-553.97.1.el8_10/05ae6c9c.failed

@@ -0,0 +1,63 @@
+scsi: lpfc: Fix lpfc_check_sli_ndlp() handling for GEN_REQUEST64 commands
+
+jira KERNEL-548
+Rebuild_History Non-Buildable kernel-4.18.0-553.97.1.el8_10
+commit-author Justin Tee <justin.tee@broadcom.com>
+commit 05ae6c9c7315d844fbc15afe393f5ba5e5771126
+Empty-Commit: Cherry-Pick Conflicts during history rebuild.
+Will be included in final tarball splat. Ref for failed cherry-pick at:
+ciq/ciq_backports/kernel-4.18.0-553.97.1.el8_10/05ae6c9c.failed
+
+In lpfc_check_sli_ndlp(), the get_job_els_rsp64_did remote_id assignment
+does not apply for GEN_REQUEST64 commands as it only has meaning for a
+ELS_REQUEST64 command.  So, if (iocb->ndlp == ndlp) is false, we could
+erroneously return the wrong value.  Fix by replacing the fallthrough
+statement with a break statement before the remote_id check.
+
+	Signed-off-by: Justin Tee <justin.tee@broadcom.com>
+Link: https://lore.kernel.org/r/20250425194806.3585-2-justintee8345@gmail.com
+	Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+(cherry picked from commit 05ae6c9c7315d844fbc15afe393f5ba5e5771126)
+	Signed-off-by: Jonathan Maple <jmaple@ciq.com>
+
+# Conflicts:
+#	drivers/scsi/lpfc/lpfc_hbadisc.c
+diff --cc drivers/scsi/lpfc/lpfc_hbadisc.c
+index 0c20ab745390,b5273cb1adbd..000000000000
+--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
++++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
+@@@ -5211,20 -5044,23 +5211,24 @@@ lpfc_check_sli_ndlp(struct lpfc_hba *ph
+  	if (iocb->vport != vport)
+  		return 0;
+
+ -	ulp_command = get_job_cmnd(phba, iocb);
+ -	ulp_context = get_job_ulpcontext(phba, iocb);
+ -	remote_id = get_job_els_rsp64_did(phba, iocb);
+ -
+  	if (pring->ringno == LPFC_ELS_RING) {
+ -		switch (ulp_command) {
+ +		switch (icmd->ulpCommand) {
+  		case CMD_GEN_REQUEST64_CR:
+ -			if (iocb->ndlp == ndlp)
+ +			if (iocb->context_un.ndlp == ndlp)
+  				return 1;
+++<<<<<<< HEAD
+ +			/* fall through */
+++=======
++ 			break;
+++>>>>>>> 05ae6c9c7315 (scsi: lpfc: Fix lpfc_check_sli_ndlp() handling for GEN_REQUEST64 commands)
+  		case CMD_ELS_REQUEST64_CR:
+ -			if (remote_id == ndlp->nlp_DID)
+ +			if (icmd->un.elsreq64.remoteID == ndlp->nlp_DID)
+  				return 1;
+ -			fallthrough;
+ +			/* fall through */
+  		case CMD_XMIT_ELS_RSP64_CX:
+ -			if (iocb->ndlp == ndlp)
+ +			if (iocb->context1 == (uint8_t *) ndlp)
+  				return 1;
+ +			/* fall through */
+  		}
+  	} else if (pring->ringno == LPFC_FCP_RING) {
+  		/* Skip match check if waiting to relogin to FCP target */
+* Unmerged path drivers/scsi/lpfc/lpfc_hbadisc.c

ciq/ciq_backports/kernel-4.18.0-553.97.1.el8_10/07caedc6.failed

@@ -0,0 +1,135 @@
+scsi: lpfc: Fix reusing an ndlp that is marked NLP_DROPPED during FLOGI
+
+jira KERNEL-548
+Rebuild_History Non-Buildable kernel-4.18.0-553.97.1.el8_10
+commit-author Justin Tee <justin.tee@broadcom.com>
+commit 07caedc6a3887938813727beafea40f07c497705
+Empty-Commit: Cherry-Pick Conflicts during history rebuild.
+Will be included in final tarball splat. Ref for failed cherry-pick at:
+ciq/ciq_backports/kernel-4.18.0-553.97.1.el8_10/07caedc6.failed
+
+It's possible for an unstable link to repeatedly bounce allowing a FLOGI
+retry, but then bounce again forcing an abort of the FLOGI.  Ensure that
+the initial reference count on the FLOGI ndlp is restored in this faulty
+link scenario.
+
+	Signed-off-by: Justin Tee <justin.tee@broadcom.com>
+Link: https://patch.msgid.link/20251106224639.139176-8-justintee8345@gmail.com
+	Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+(cherry picked from commit 07caedc6a3887938813727beafea40f07c497705)
+	Signed-off-by: Jonathan Maple <jmaple@ciq.com>
+
+# Conflicts:
+#	drivers/scsi/lpfc/lpfc_els.c
+#	drivers/scsi/lpfc/lpfc_hbadisc.c
+diff --cc drivers/scsi/lpfc/lpfc_els.c
+index 5c9369b9b870,0045c1e29619..000000000000
+--- a/drivers/scsi/lpfc/lpfc_els.c
++++ b/drivers/scsi/lpfc/lpfc_els.c
+@@@ -1061,15 -995,15 +1066,24 @@@ lpfc_cmpl_els_flogi(struct lpfc_hba *ph
+
+  stop_rr_fcf_flogi:
+  		/* FLOGI failure */
+ -		if (!(ulp_status == IOSTAT_LOCAL_REJECT &&
+ -		      ((ulp_word4 & IOERR_PARAM_MASK) ==
+ +		if (!(irsp->ulpStatus == IOSTAT_LOCAL_REJECT &&
+ +		      ((irsp->un.ulpWord[4] & IOERR_PARAM_MASK) ==
+  					IOERR_LOOP_OPEN_FAILURE)))
+++<<<<<<< HEAD
+ +			lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
+ +					 "2858 FLOGI failure Status:x%x/x%x TMO"
+ +					 ":x%x Data x%x x%x\n",
+ +					 irsp->ulpStatus, irsp->un.ulpWord[4],
+ +					 irsp->ulpTimeout, phba->hba_flag,
+ +					 phba->fcf.fcf_flag);
+++=======
++ 			lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS,
++ 				      "2858 FLOGI Status:x%x/x%x TMO"
++ 				      ":x%x Data x%lx x%x x%lx x%x\n",
++ 				      ulp_status, ulp_word4, tmo,
++ 				      phba->hba_flag, phba->fcf.fcf_flag,
++ 				      ndlp->nlp_flag, ndlp->fc4_xpt_flags);
+++>>>>>>> 07caedc6a388 (scsi: lpfc: Fix reusing an ndlp that is marked NLP_DROPPED during FLOGI)
+
+  		/* Check for retry */
+  		if (lpfc_els_retry(phba, cmdiocb, rspiocb)) {
+@@@ -1086,28 -1020,35 +1100,43 @@@
+  		 * registered with the SCSI transport, remove the initial
+  		 * reference to trigger node release.
+  		 */
+++<<<<<<< HEAD
+ +		if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS) &&
+ +		    !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD))
+++=======
++ 		if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag) &&
++ 		    !test_bit(NLP_DROPPED, &ndlp->nlp_flag) &&
++ 		    !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD)) {
++ 			set_bit(NLP_DROPPED, &ndlp->nlp_flag);
+++>>>>>>> 07caedc6a388 (scsi: lpfc: Fix reusing an ndlp that is marked NLP_DROPPED during FLOGI)
+  			lpfc_nlp_put(ndlp);
++ 		}
+
+  		lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS,
+++<<<<<<< HEAD
+ +				 "0150 FLOGI failure Status:x%x/x%x "
+ +				 "xri x%x TMO:x%x refcnt %d\n",
+ +				 irsp->ulpStatus, irsp->un.ulpWord[4],
+ +				 cmdiocb->sli4_xritag, irsp->ulpTimeout,
+ +				 kref_read(&ndlp->kref));
+++=======
++ 				 "0150 FLOGI Status:x%x/x%x "
++ 				 "xri x%x iotag x%x TMO:x%x refcnt %d\n",
++ 				 ulp_status, ulp_word4, cmdiocb->sli4_xritag,
++ 				 cmdiocb->iotag, tmo, kref_read(&ndlp->kref));
+++>>>>>>> 07caedc6a388 (scsi: lpfc: Fix reusing an ndlp that is marked NLP_DROPPED during FLOGI)
+
+  		/* If this is not a loop open failure, bail out */
+ -		if (!(ulp_status == IOSTAT_LOCAL_REJECT &&
+ -		      ((ulp_word4 & IOERR_PARAM_MASK) ==
+ -					IOERR_LOOP_OPEN_FAILURE))) {
+ -			/* Warn FLOGI status */
+ -			lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS,
+ -				      "0100 FLOGI Status:x%x/x%x "
+ -				      "TMO:x%x\n",
+ -				      ulp_status, ulp_word4, tmo);
+ +		if (!(irsp->ulpStatus == IOSTAT_LOCAL_REJECT &&
+ +		      ((irsp->un.ulpWord[4] & IOERR_PARAM_MASK) ==
+ +					IOERR_LOOP_OPEN_FAILURE)))
+  			goto flogifail;
+ -		}
+
+  		/* FLOGI failed, so there is no fabric */
+ -		clear_bit(FC_FABRIC, &vport->fc_flag);
+ -		clear_bit(FC_PUBLIC_LOOP, &vport->fc_flag);
+ -		clear_bit(FC_PT2PT_NO_NVME, &vport->fc_flag);
+ +		spin_lock_irq(shost->host_lock);
+ +		vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP |
+ +				    FC_PT2PT_NO_NVME);
+ +		spin_unlock_irq(shost->host_lock);
+
+  		/* If private loop, then allow max outstanding els to be
+  		 * LPFC_MAX_DISC_THREADS (32). Scanning in the case of no
+diff --cc drivers/scsi/lpfc/lpfc_hbadisc.c
+index 2be2e893f962,717ae56c8e4b..000000000000
+--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
++++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
+@@@ -415,12 -423,8 +415,17 @@@ voi
+  lpfc_check_nlp_post_devloss(struct lpfc_vport *vport,
+  			    struct lpfc_nodelist *ndlp)
+  {
+++<<<<<<< HEAD
+ +	unsigned long iflags;
+ +
+ +	spin_lock_irqsave(&ndlp->lock, iflags);
+ +	if (ndlp->save_flags & NLP_IN_RECOV_POST_DEV_LOSS) {
+ +		ndlp->save_flags &= ~NLP_IN_RECOV_POST_DEV_LOSS;
+ +		spin_unlock_irqrestore(&ndlp->lock, iflags);
+++=======
++ 	if (test_and_clear_bit(NLP_IN_RECOV_POST_DEV_LOSS, &ndlp->save_flags)) {
++ 		clear_bit(NLP_DROPPED, &ndlp->nlp_flag);
+++>>>>>>> 07caedc6a388 (scsi: lpfc: Fix reusing an ndlp that is marked NLP_DROPPED during FLOGI)
+  		lpfc_nlp_get(ndlp);
+  		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY | LOG_NODE,
+  				 "8438 Devloss timeout reversed on DID x%x "
+* Unmerged path drivers/scsi/lpfc/lpfc_els.c
+* Unmerged path drivers/scsi/lpfc/lpfc_hbadisc.c