From: Brian King Date: Fri, 24 Aug 2012 21:51:01 +0000 (-0500) Subject: [SCSI] ibmvfc: Ignore fabric RSCNs when link is dead X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=5cdf162654123c53f14524bb23546f4d11bfde28;p=GitHub%2Fmoto-9609%2Fandroid_kernel_motorola_exynos9610.git [SCSI] ibmvfc: Ignore fabric RSCNs when link is dead This fixes an issues seen where a Fabric RSCN event was received while the link was down, which resulted in repeated attempts to log back into the fabric, which then failed, resulting in the ibmvfc driver taking the host offline. Fix this by delaying taking any action regarding the fabric RSCN until the link comes back up. Signed-off-by: Brian King Signed-off-by: James Bottomley --- diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 4f73daccc9f1..5e8d51bd03de 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -2625,8 +2625,10 @@ static void ibmvfc_handle_async(struct ibmvfc_async_crq *crq, case IBMVFC_AE_SCN_FABRIC: case IBMVFC_AE_SCN_DOMAIN: vhost->events_to_log |= IBMVFC_AE_RSCN; - vhost->delay_init = 1; - __ibmvfc_reset_host(vhost); + if (vhost->state < IBMVFC_HALTED) { + vhost->delay_init = 1; + __ibmvfc_reset_host(vhost); + } break; case IBMVFC_AE_SCN_NPORT: case IBMVFC_AE_SCN_GROUP: