From bc69ad74867dba1377abe14356c94a946d9837a3 Mon Sep 17 00:00:00 2001 From: En-Wei Wu Date: Thu, 30 May 2024 22:21:31 +0800 Subject: [PATCH 1/3] ice: avoid IRQ collision to fix init failure on ACPI S3 resume A bug in https://bugzilla.kernel.org/show_bug.cgi?id=218906 describes that irdma would break and report hardware initialization failed after suspend/resume with Intel E810 NIC (tested on 6.9.0-rc5). The problem is caused due to the collision between the irq numbers requested in irdma and the irq numbers requested in other drivers after suspend/resume. The irq numbers used by irdma are derived from ice's ice_pf->msix_entries which stores mappings between MSI-X index and Linux interrupt number. It's supposed to be cleaned up when suspend and rebuilt in resume but it's not, causing irdma using the old irq numbers stored in the old ice_pf->msix_entries to request_irq() when resume. And eventually collide with other drivers. This patch fixes this problem. On suspend, we call ice_deinit_rdma() to clean up the ice_pf->msix_entries (and free the MSI-X vectors used by irdma if we've dynamically allocated them). On resume, we call ice_init_rdma() to rebuild the ice_pf->msix_entries (and allocate the MSI-X vectors if we would like to dynamically allocate them). Fixes: f9f5301e7e2d ("ice: Register auxiliary device to provide RDMA") Tested-by: Cyrus Lien Signed-off-by: En-Wei Wu Reviewed-by: Wojciech Drewek Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 1b61ca3a6eb6..45d850514f4c 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5564,7 +5564,7 @@ static int ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); - ice_unplug_aux_dev(pf); + ice_deinit_rdma(pf); /* Already suspended?, then there is nothing to do */ if (test_and_set_bit(ICE_SUSPENDED, pf->state)) { @@ -5644,6 +5644,11 @@ static int ice_resume(struct device *dev) if (ret) dev_err(dev, "Cannot restore interrupt scheme: %d\n", ret); + ret = ice_init_rdma(pf); + if (ret) + dev_err(dev, "Reinitialize RDMA during resume failed: %d\n", + ret); + clear_bit(ICE_DOWN, pf->state); /* Now perform PF reset and rebuild */ reset_type = ICE_RESET_PFR; From aeccadb24d9dacdde673a0f68f0a9135c6be4993 Mon Sep 17 00:00:00 2001 From: Paul Greenwalt Date: Thu, 30 May 2024 13:06:17 -0400 Subject: [PATCH 2/3] ice: fix 200G link speed message log Commit 24407a01e57c ("ice: Add 200G speed/phy type use") added support for 200G PHY speeds, but did not include 200G link speed message support. As a result the driver incorrectly reports Unknown for 200G link speed. Fix this by adding 200G support to ice_print_link_msg(). Fixes: 24407a01e57c ("ice: Add 200G speed/phy type use") Reviewed-by: Michal Swiatkowski Signed-off-by: Paul Greenwalt Reviewed-by: Jesse Brandeburg Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 45d850514f4c..1766230abfff 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -805,6 +805,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) } switch (vsi->port_info->phy.link_info.link_speed) { + case ICE_AQ_LINK_SPEED_200GB: + speed = "200 G"; + break; case ICE_AQ_LINK_SPEED_100GB: speed = "100 G"; break; From a27f6ac9d404ea84196639dcc456f969ef813c0f Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Tue, 4 Jun 2024 14:55:14 +0200 Subject: [PATCH 3/3] ice: implement AQ download pkg retry ice_aqc_opc_download_pkg (0x0C40) AQ sporadically returns error due to FW issue. Fix this by retrying five times before moving to Safe Mode. Sleep for 20 ms before retrying. This was tested with the 4.40 firmware. Fixes: c76488109616 ("ice: Implement Dynamic Device Personalization (DDP) download") Reviewed-by: Michal Swiatkowski Signed-off-by: Wojciech Drewek Reviewed-by: Brett Creeley Reviewed-by: Przemek Kitszel Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ddp.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index ce5034ed2b24..f182179529b7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -1339,6 +1339,7 @@ ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start, for (i = 0; i < count; i++) { bool last = false; + int try_cnt = 0; int status; bh = (struct ice_buf_hdr *)(bufs + start + i); @@ -1346,8 +1347,26 @@ ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start, if (indicate_last) last = ice_is_last_download_buffer(bh, i, count); - status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last, - &offset, &info, NULL); + while (1) { + status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, + last, &offset, &info, + NULL); + if (hw->adminq.sq_last_status != ICE_AQ_RC_ENOSEC && + hw->adminq.sq_last_status != ICE_AQ_RC_EBADSIG) + break; + + try_cnt++; + + if (try_cnt == 5) + break; + + msleep(20); + } + + if (try_cnt) + dev_dbg(ice_hw_to_dev(hw), + "ice_aq_download_pkg number of retries: %d\n", + try_cnt); /* Save AQ status from download package */ if (status) {