| Message ID | 20220412102753.670867-1-poros@redhat.com (mailing list archive) |
|---|---|
| State | Awaiting Upstream |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | ice: wait for EMP reset after firmware flash | expand |
[Cc: +Jakob, +regressions@lists.linux.dev] Dear Petr, Thank you for your patch for the regression. #regzbot ^introduced 399e27dbbd9e94 Am 12.04.22 um 12:27 schrieb Petr Oros: Please mention the time in the commit message summary: ice: Wait 5 s for EMP reset after firmware flash > We need to wait for EMP reset after firmware flash. > Code was extracted from OOT driver and without this wait fw_activate let Which OOT driver exactly? > card in inconsistent state recoverable only by second flash/activate Please reflow for 75 characters per line, and add a dot/period to the end of sentences. > Reproducer: > [root@host ~]# devlink dev flash pci/0000:ca:00.0 file E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bin > Preparing to flash > [fw.mgmt] Erasing > [fw.mgmt] Erasing done > [fw.mgmt] Flashing 100% > [fw.mgmt] Flashing done 100% > [fw.undi] Erasing > [fw.undi] Erasing done > [fw.undi] Flashing 100% > [fw.undi] Flashing done 100% > [fw.netlist] Erasing > [fw.netlist] Erasing done > [fw.netlist] Flashing 100% > [fw.netlist] Flashing done 100% > Activate new firmware by devlink reload > [root@host ~]# devlink dev reload pci/0000:ca:00.0 action fw_activate > reload_actions_performed: > fw_activate > [root@host ~]# ip link show ens7f0 > 71: ens7f0: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc mq state DOWN mode DEFAULT group default qlen 1000 > link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff > altname enp202s0f0 > > dmesg after flash: > [ 55.120788] ice: Copyright (c) 2018, Intel Corporation. > [ 55.274734] ice 0000:ca:00.0: Get PHY capabilities failed status = -5, continuing anyway > [ 55.569797] ice 0000:ca:00.0: The DDP package was successfully loaded: ICE OS Default Package version 1.3.28.0 > [ 55.603629] ice 0000:ca:00.0: Get PHY capability failed. > [ 55.608951] ice 0000:ca:00.0: ice_init_nvm_phy_type failed: -5 > [ 55.647348] ice 0000:ca:00.0: PTP init successful > [ 55.675536] ice 0000:ca:00.0: DCB is enabled in the hardware, max number of TCs supported on this port are 8 > [ 55.685365] ice 0000:ca:00.0: FW LLDP is disabled, DCBx/LLDP in SW mode. > [ 55.692179] ice 0000:ca:00.0: Commit DCB Configuration to the hardware > [ 55.701382] ice 0000:ca:00.0: 126.024 Gb/s available PCIe bandwidth, limited by 16.0 GT/s PCIe x8 link at 0000:c9:02.0 (capable of 252.048 Gb/s with 16.0 GT/s PCIe x16 link) So, what is the error? `Get PHY capabilities failed status = -5`? What firmware version did the network card have before and after the update? > Reboot don't help, only second flash/activate with OOT or patched driver put card back in consistent state s/don't/doesn’t/ > After patch: > [root@host ~]# devlink dev flash pci/0000:ca:00.0 file E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bin > Preparing to flash > [fw.mgmt] Erasing > [fw.mgmt] Erasing done > [fw.mgmt] Flashing 100% > [fw.mgmt] Flashing done 100% > [fw.undi] Erasing > [fw.undi] Erasing done > [fw.undi] Flashing 100% > [fw.undi] Flashing done 100% > [fw.netlist] Erasing > [fw.netlist] Erasing done > [fw.netlist] Flashing 100% > [fw.netlist] Flashing done 100% > Activate new firmware by devlink reload > [root@host ~]# devlink dev reload pci/0000:ca:00.0 action fw_activate > reload_actions_performed: > fw_activate > [root@host ~]# ip link show ens7f0 > 19: ens7f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000 > link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff > altname enp202s0f0 Did you try anything less than five seconds? i40e uses one second, cf. commit 9b13bd53134c (i40e: Increase delay to 1 s after global EMP reset). > Fixes: 399e27dbbd9e94 ("ice: support immediate firmware activation via devlink reload") > Signed-off-by: Petr Oros <poros@redhat.com> > --- > 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 d768925785ca79..90ea2203cdc763 100644 > --- a/drivers/net/ethernet/intel/ice/ice_main.c > +++ b/drivers/net/ethernet/intel/ice/ice_main.c > @@ -6931,12 +6931,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) > > dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); > > +#define ICE_EMP_RESET_SLEEP 5000 Please append the unit to the macro name. > if (reset_type == ICE_RESET_EMPR) { > /* If an EMP reset has occurred, any previously pending flash > * update will have completed. We no longer know whether or > * not the NVM update EMP reset is restricted. > */ > pf->fw_emp_reset_disabled = false; > + > + msleep(ICE_EMP_RESET_SLEEP); > } > > err = ice_init_all_ctrlq(hw); Kind regards, Paul
From: Petr Oros <poros@redhat.com> Date: Tue, 12 Apr 2022 12:27:53 +0200 > We need to wait for EMP reset after firmware flash. > Code was extracted from OOT driver and without this wait fw_activate let > card in inconsistent state recoverable only by second flash/activate > > Reproducer: > [root@host ~]# devlink dev flash pci/0000:ca:00.0 file E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bin > Preparing to flash > [fw.mgmt] Erasing > [fw.mgmt] Erasing done > [fw.mgmt] Flashing 100% > [fw.mgmt] Flashing done 100% > [fw.undi] Erasing > [fw.undi] Erasing done > [fw.undi] Flashing 100% > [fw.undi] Flashing done 100% > [fw.netlist] Erasing > [fw.netlist] Erasing done > [fw.netlist] Flashing 100% > [fw.netlist] Flashing done 100% > Activate new firmware by devlink reload > [root@host ~]# devlink dev reload pci/0000:ca:00.0 action fw_activate > reload_actions_performed: > fw_activate > [root@host ~]# ip link show ens7f0 > 71: ens7f0: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc mq state DOWN mode DEFAULT group default qlen 1000 > link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff > altname enp202s0f0 > > dmesg after flash: > [ 55.120788] ice: Copyright (c) 2018, Intel Corporation. > [ 55.274734] ice 0000:ca:00.0: Get PHY capabilities failed status = -5, continuing anyway > [ 55.569797] ice 0000:ca:00.0: The DDP package was successfully loaded: ICE OS Default Package version 1.3.28.0 > [ 55.603629] ice 0000:ca:00.0: Get PHY capability failed. > [ 55.608951] ice 0000:ca:00.0: ice_init_nvm_phy_type failed: -5 > [ 55.647348] ice 0000:ca:00.0: PTP init successful > [ 55.675536] ice 0000:ca:00.0: DCB is enabled in the hardware, max number of TCs supported on this port are 8 > [ 55.685365] ice 0000:ca:00.0: FW LLDP is disabled, DCBx/LLDP in SW mode. > [ 55.692179] ice 0000:ca:00.0: Commit DCB Configuration to the hardware > [ 55.701382] ice 0000:ca:00.0: 126.024 Gb/s available PCIe bandwidth, limited by 16.0 GT/s PCIe x8 link at 0000:c9:02.0 (capable of 252.048 Gb/s with 16.0 GT/s PCIe x16 link) > Reboot don't help, only second flash/activate with OOT or patched driver put card back in consistent state > > After patch: > [root@host ~]# devlink dev flash pci/0000:ca:00.0 file E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bin > Preparing to flash > [fw.mgmt] Erasing > [fw.mgmt] Erasing done > [fw.mgmt] Flashing 100% > [fw.mgmt] Flashing done 100% > [fw.undi] Erasing > [fw.undi] Erasing done > [fw.undi] Flashing 100% > [fw.undi] Flashing done 100% > [fw.netlist] Erasing > [fw.netlist] Erasing done > [fw.netlist] Flashing 100% > [fw.netlist] Flashing done 100% > Activate new firmware by devlink reload > [root@host ~]# devlink dev reload pci/0000:ca:00.0 action fw_activate > reload_actions_performed: > fw_activate > [root@host ~]# ip link show ens7f0 > 19: ens7f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000 > link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff > altname enp202s0f0 > > Fixes: 399e27dbbd9e94 ("ice: support immediate firmware activation via devlink reload") > Signed-off-by: Petr Oros <poros@redhat.com> > --- > 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 d768925785ca79..90ea2203cdc763 100644 > --- a/drivers/net/ethernet/intel/ice/ice_main.c > +++ b/drivers/net/ethernet/intel/ice/ice_main.c > @@ -6931,12 +6931,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) > > dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); > > +#define ICE_EMP_RESET_SLEEP 5000 Ooof, 5 sec is a lot! Is there any way to poll the device readiness? Does it really need the whole 5 sec? > if (reset_type == ICE_RESET_EMPR) { > /* If an EMP reset has occurred, any previously pending flash > * update will have completed. We no longer know whether or > * not the NVM update EMP reset is restricted. > */ > pf->fw_emp_reset_disabled = false; > + > + msleep(ICE_EMP_RESET_SLEEP); > } > > err = ice_init_all_ctrlq(hw); > -- > 2.35.1 Thanks, Al
On 4/12/2022 3:27 AM, Petr Oros wrote: > We need to wait for EMP reset after firmware flash. > Code was extracted from OOT driver and without this wait fw_activate let > card in inconsistent state recoverable only by second flash/activate > > Reproducer: > [root@host ~]# devlink dev flash pci/0000:ca:00.0 file E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bin > Preparing to flash > [fw.mgmt] Erasing > [fw.mgmt] Erasing done > [fw.mgmt] Flashing 100% > [fw.mgmt] Flashing done 100% > [fw.undi] Erasing > [fw.undi] Erasing done > [fw.undi] Flashing 100% > [fw.undi] Flashing done 100% > [fw.netlist] Erasing > [fw.netlist] Erasing done > [fw.netlist] Flashing 100% > [fw.netlist] Flashing done 100% > Activate new firmware by devlink reload > [root@host ~]# devlink dev reload pci/0000:ca:00.0 action fw_activate > reload_actions_performed: > fw_activate > [root@host ~]# ip link show ens7f0 > 71: ens7f0: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc mq state DOWN mode DEFAULT group default qlen 1000 > link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff > altname enp202s0f0 > > dmesg after flash: > [ 55.120788] ice: Copyright (c) 2018, Intel Corporation. > [ 55.274734] ice 0000:ca:00.0: Get PHY capabilities failed status = -5, continuing anyway > [ 55.569797] ice 0000:ca:00.0: The DDP package was successfully loaded: ICE OS Default Package version 1.3.28.0 > [ 55.603629] ice 0000:ca:00.0: Get PHY capability failed. > [ 55.608951] ice 0000:ca:00.0: ice_init_nvm_phy_type failed: -5 > [ 55.647348] ice 0000:ca:00.0: PTP init successful > [ 55.675536] ice 0000:ca:00.0: DCB is enabled in the hardware, max number of TCs supported on this port are 8 > [ 55.685365] ice 0000:ca:00.0: FW LLDP is disabled, DCBx/LLDP in SW mode. > [ 55.692179] ice 0000:ca:00.0: Commit DCB Configuration to the hardware > [ 55.701382] ice 0000:ca:00.0: 126.024 Gb/s available PCIe bandwidth, limited by 16.0 GT/s PCIe x8 link at 0000:c9:02.0 (capable of 252.048 Gb/s with 16.0 GT/s PCIe x16 link) > Reboot don't help, only second flash/activate with OOT or patched driver put card back in consistent state > > After patch: > [root@host ~]# devlink dev flash pci/0000:ca:00.0 file E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bin > Preparing to flash > [fw.mgmt] Erasing > [fw.mgmt] Erasing done > [fw.mgmt] Flashing 100% > [fw.mgmt] Flashing done 100% > [fw.undi] Erasing > [fw.undi] Erasing done > [fw.undi] Flashing 100% > [fw.undi] Flashing done 100% > [fw.netlist] Erasing > [fw.netlist] Erasing done > [fw.netlist] Flashing 100% > [fw.netlist] Flashing done 100% > Activate new firmware by devlink reload > [root@host ~]# devlink dev reload pci/0000:ca:00.0 action fw_activate > reload_actions_performed: > fw_activate > [root@host ~]# ip link show ens7f0 > 19: ens7f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000 > link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff > altname enp202s0f0 > Ahh.. good find. I checked a bunch of places, but didn't check here for differences. :( For what its worth, I checked the source history of the out-of-tree driver this came from. It appears to be a workaround added for fixing a similar issue. I haven't been able to dig up the full details yet. It appeares to be a collision with firmware finalizing recovery after the EMP reset. Still trying to dig for any more information I can find. > Fixes: 399e27dbbd9e94 ("ice: support immediate firmware activation via devlink reload") > Signed-off-by: Petr Oros <poros@redhat.com> > --- > 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 d768925785ca79..90ea2203cdc763 100644 > --- a/drivers/net/ethernet/intel/ice/ice_main.c > +++ b/drivers/net/ethernet/intel/ice/ice_main.c > @@ -6931,12 +6931,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) > > dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); > > +#define ICE_EMP_RESET_SLEEP 5000 > if (reset_type == ICE_RESET_EMPR) { > /* If an EMP reset has occurred, any previously pending flash > * update will have completed. We no longer know whether or > * not the NVM update EMP reset is restricted. > */ > pf->fw_emp_reset_disabled = false; > + > + msleep(ICE_EMP_RESET_SLEEP); > } > > err = ice_init_all_ctrlq(hw);
On 4/12/2022 9:08 AM, Alexander Lobakin wrote: >> +#define ICE_EMP_RESET_SLEEP 5000 > > Ooof, 5 sec is a lot! Is there any way to poll the device readiness? > Does it really need the whole 5 sec? The problem with resets is usually you don't want to disturb the hardware with PCIe pokes while it's resetting. In this case, this code only runs if it was indicated by the update status that the firmware could internally reset itself to pick up new updates, avoiding a reboot. Yes the five seconds is less than ideal, but it was the value we found that offered the most stability / likelihood of reset completing. In this case the 5 seconds is a tradeoff vs a reboot. Thank you Ivan for chasing down this bug!
Jacob Keller píše v Út 12. 04. 2022 v 09:58 -0700: > > > On 4/12/2022 3:27 AM, Petr Oros wrote: > > We need to wait for EMP reset after firmware flash. > > Code was extracted from OOT driver and without this wait > > fw_activate let > > card in inconsistent state recoverable only by second > > flash/activate > > > > Reproducer: > > [root@host ~]# devlink dev flash pci/0000:ca:00.0 file > > E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bi > > n > > Preparing to flash > > [fw.mgmt] Erasing > > [fw.mgmt] Erasing done > > [fw.mgmt] Flashing 100% > > [fw.mgmt] Flashing done 100% > > [fw.undi] Erasing > > [fw.undi] Erasing done > > [fw.undi] Flashing 100% > > [fw.undi] Flashing done 100% > > [fw.netlist] Erasing > > [fw.netlist] Erasing done > > [fw.netlist] Flashing 100% > > [fw.netlist] Flashing done 100% > > Activate new firmware by devlink reload > > [root@host ~]# devlink dev reload pci/0000:ca:00.0 action > > fw_activate > > reload_actions_performed: > > fw_activate > > [root@host ~]# ip link show ens7f0 > > 71: ens7f0: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc mq > > state DOWN mode DEFAULT group default qlen 1000 > > link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff > > altname enp202s0f0 > > > > dmesg after flash: > > [ 55.120788] ice: Copyright (c) 2018, Intel Corporation. > > [ 55.274734] ice 0000:ca:00.0: Get PHY capabilities failed status > > = -5, continuing anyway > > [ 55.569797] ice 0000:ca:00.0: The DDP package was successfully > > loaded: ICE OS Default Package version 1.3.28.0 > > [ 55.603629] ice 0000:ca:00.0: Get PHY capability failed. > > [ 55.608951] ice 0000:ca:00.0: ice_init_nvm_phy_type failed: -5 > > [ 55.647348] ice 0000:ca:00.0: PTP init successful > > [ 55.675536] ice 0000:ca:00.0: DCB is enabled in the hardware, > > max number of TCs supported on this port are 8 > > [ 55.685365] ice 0000:ca:00.0: FW LLDP is disabled, DCBx/LLDP in > > SW mode. > > [ 55.692179] ice 0000:ca:00.0: Commit DCB Configuration to the > > hardware > > [ 55.701382] ice 0000:ca:00.0: 126.024 Gb/s available PCIe > > bandwidth, limited by 16.0 GT/s PCIe x8 link at 0000:c9:02.0 > > (capable of 252.048 Gb/s with 16.0 GT/s PCIe x16 link) > > Reboot don't help, only second flash/activate with OOT or patched > > driver put card back in consistent state > > > > After patch: > > [root@host ~]# devlink dev flash pci/0000:ca:00.0 file > > E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bi > > n > > Preparing to flash > > [fw.mgmt] Erasing > > [fw.mgmt] Erasing done > > [fw.mgmt] Flashing 100% > > [fw.mgmt] Flashing done 100% > > [fw.undi] Erasing > > [fw.undi] Erasing done > > [fw.undi] Flashing 100% > > [fw.undi] Flashing done 100% > > [fw.netlist] Erasing > > [fw.netlist] Erasing done > > [fw.netlist] Flashing 100% > > [fw.netlist] Flashing done 100% > > Activate new firmware by devlink reload > > [root@host ~]# devlink dev reload pci/0000:ca:00.0 action > > fw_activate > > reload_actions_performed: > > fw_activate > > [root@host ~]# ip link show ens7f0 > > 19: ens7f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq > > state UP mode DEFAULT group default qlen 1000 > > link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff > > altname enp202s0f0 > > > > Ahh.. good find. I checked a bunch of places, but didn't check here > for > differences. :( > > For what its worth, I checked the source history of the out-of-tree > driver this came from. It appears to be a workaround added for fixing > a > similar issue. > > I haven't been able to dig up the full details yet. It appeares to be > a > collision with firmware finalizing recovery after the EMP reset. > > Still trying to dig for any more information I can find. Interesting time frame could be around this commit: 08771bce330036 ("ice: Continue probe on link/PHY errors") Petr > > > Fixes: 399e27dbbd9e94 ("ice: support immediate firmware activation > > via devlink reload") > > Signed-off-by: Petr Oros <poros@redhat.com> > > --- > > 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 d768925785ca79..90ea2203cdc763 100644 > > --- a/drivers/net/ethernet/intel/ice/ice_main.c > > +++ b/drivers/net/ethernet/intel/ice/ice_main.c > > @@ -6931,12 +6931,15 @@ static void ice_rebuild(struct ice_pf *pf, > > enum ice_reset_req reset_type) > > > > dev_dbg(dev, "rebuilding PF after reset_type=%d\n", > > reset_type); > > > > +#define ICE_EMP_RESET_SLEEP 5000 > > if (reset_type == ICE_RESET_EMPR) { > > /* If an EMP reset has occurred, any previously > > pending flash > > * update will have completed. We no longer know > > whether or > > * not the NVM update EMP reset is restricted. > > */ > > pf->fw_emp_reset_disabled = false; > > + > > + msleep(ICE_EMP_RESET_SLEEP); > > } > > > > err = ice_init_all_ctrlq(hw); >
TWIMC: this mail is primarily send for documentation purposes and for regzbot, my Linux kernel regression tracking bot. These mails usually contain '#forregzbot' in the subject, to make them easy to spot and filter. #regzbot fixed-by: b537752e6cbf0e On 12.04.22 15:28, Paul Menzel wrote: > [Cc: +Jakob, +regressions@lists.linux.dev] > > > Dear Petr, > > > Thank you for your patch for the regression. > > #regzbot ^introduced 399e27dbbd9e94 > > > Am 12.04.22 um 12:27 schrieb Petr Oros: > > Please mention the time in the commit message summary: > > ice: Wait 5 s for EMP reset after firmware flash > >> We need to wait for EMP reset after firmware flash. >> Code was extracted from OOT driver and without this wait fw_activate let > > Which OOT driver exactly? > >> card in inconsistent state recoverable only by second flash/activate > > Please reflow for 75 characters per line, and add a dot/period to the > end of sentences. > >> Reproducer: >> [root@host ~]# devlink dev flash pci/0000:ca:00.0 file >> E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bin >> Preparing to flash >> [fw.mgmt] Erasing >> [fw.mgmt] Erasing done >> [fw.mgmt] Flashing 100% >> [fw.mgmt] Flashing done 100% >> [fw.undi] Erasing >> [fw.undi] Erasing done >> [fw.undi] Flashing 100% >> [fw.undi] Flashing done 100% >> [fw.netlist] Erasing >> [fw.netlist] Erasing done >> [fw.netlist] Flashing 100% >> [fw.netlist] Flashing done 100% >> Activate new firmware by devlink reload >> [root@host ~]# devlink dev reload pci/0000:ca:00.0 action fw_activate >> reload_actions_performed: >> fw_activate >> [root@host ~]# ip link show ens7f0 >> 71: ens7f0: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc mq >> state DOWN mode DEFAULT group default qlen 1000 >> link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff >> altname enp202s0f0 >> >> dmesg after flash: >> [ 55.120788] ice: Copyright (c) 2018, Intel Corporation. >> [ 55.274734] ice 0000:ca:00.0: Get PHY capabilities failed status = >> -5, continuing anyway >> [ 55.569797] ice 0000:ca:00.0: The DDP package was successfully >> loaded: ICE OS Default Package version 1.3.28.0 >> [ 55.603629] ice 0000:ca:00.0: Get PHY capability failed. >> [ 55.608951] ice 0000:ca:00.0: ice_init_nvm_phy_type failed: -5 >> [ 55.647348] ice 0000:ca:00.0: PTP init successful >> [ 55.675536] ice 0000:ca:00.0: DCB is enabled in the hardware, max >> number of TCs supported on this port are 8 >> [ 55.685365] ice 0000:ca:00.0: FW LLDP is disabled, DCBx/LLDP in SW >> mode. >> [ 55.692179] ice 0000:ca:00.0: Commit DCB Configuration to the hardware >> [ 55.701382] ice 0000:ca:00.0: 126.024 Gb/s available PCIe >> bandwidth, limited by 16.0 GT/s PCIe x8 link at 0000:c9:02.0 (capable >> of 252.048 Gb/s with 16.0 GT/s PCIe x16 link) > > So, what is the error? `Get PHY capabilities failed status = -5`? > > What firmware version did the network card have before and after the > update? > >> Reboot don't help, only second flash/activate with OOT or patched >> driver put card back in consistent state > > s/don't/doesn’t/ > >> After patch: >> [root@host ~]# devlink dev flash pci/0000:ca:00.0 file >> E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bin >> Preparing to flash >> [fw.mgmt] Erasing >> [fw.mgmt] Erasing done >> [fw.mgmt] Flashing 100% >> [fw.mgmt] Flashing done 100% >> [fw.undi] Erasing >> [fw.undi] Erasing done >> [fw.undi] Flashing 100% >> [fw.undi] Flashing done 100% >> [fw.netlist] Erasing >> [fw.netlist] Erasing done >> [fw.netlist] Flashing 100% >> [fw.netlist] Flashing done 100% >> Activate new firmware by devlink reload >> [root@host ~]# devlink dev reload pci/0000:ca:00.0 action fw_activate >> reload_actions_performed: >> fw_activate >> [root@host ~]# ip link show ens7f0 >> 19: ens7f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state >> UP mode DEFAULT group default qlen 1000 >> link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff >> altname enp202s0f0 > > Did you try anything less than five seconds? i40e uses one second, cf. > commit 9b13bd53134c (i40e: Increase delay to 1 s after global EMP reset). > >> Fixes: 399e27dbbd9e94 ("ice: support immediate firmware activation via >> devlink reload") >> Signed-off-by: Petr Oros <poros@redhat.com> >> --- >> 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 d768925785ca79..90ea2203cdc763 100644 >> --- a/drivers/net/ethernet/intel/ice/ice_main.c >> +++ b/drivers/net/ethernet/intel/ice/ice_main.c >> @@ -6931,12 +6931,15 @@ static void ice_rebuild(struct ice_pf *pf, >> enum ice_reset_req reset_type) >> dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); >> +#define ICE_EMP_RESET_SLEEP 5000 > > Please append the unit to the macro name. > >> if (reset_type == ICE_RESET_EMPR) { >> /* If an EMP reset has occurred, any previously pending flash >> * update will have completed. We no longer know whether or >> * not the NVM update EMP reset is restricted. >> */ >> pf->fw_emp_reset_disabled = false; >> + >> + msleep(ICE_EMP_RESET_SLEEP); >> } >> err = ice_init_all_ctrlq(hw); > > > Kind regards, > > Paul > >
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index d768925785ca79..90ea2203cdc763 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -6931,12 +6931,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); +#define ICE_EMP_RESET_SLEEP 5000 if (reset_type == ICE_RESET_EMPR) { /* If an EMP reset has occurred, any previously pending flash * update will have completed. We no longer know whether or * not the NVM update EMP reset is restricted. */ pf->fw_emp_reset_disabled = false; + + msleep(ICE_EMP_RESET_SLEEP); } err = ice_init_all_ctrlq(hw);
We need to wait for EMP reset after firmware flash. Code was extracted from OOT driver and without this wait fw_activate let card in inconsistent state recoverable only by second flash/activate Reproducer: [root@host ~]# devlink dev flash pci/0000:ca:00.0 file E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bin Preparing to flash [fw.mgmt] Erasing [fw.mgmt] Erasing done [fw.mgmt] Flashing 100% [fw.mgmt] Flashing done 100% [fw.undi] Erasing [fw.undi] Erasing done [fw.undi] Flashing 100% [fw.undi] Flashing done 100% [fw.netlist] Erasing [fw.netlist] Erasing done [fw.netlist] Flashing 100% [fw.netlist] Flashing done 100% Activate new firmware by devlink reload [root@host ~]# devlink dev reload pci/0000:ca:00.0 action fw_activate reload_actions_performed: fw_activate [root@host ~]# ip link show ens7f0 71: ens7f0: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc mq state DOWN mode DEFAULT group default qlen 1000 link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff altname enp202s0f0 dmesg after flash: [ 55.120788] ice: Copyright (c) 2018, Intel Corporation. [ 55.274734] ice 0000:ca:00.0: Get PHY capabilities failed status = -5, continuing anyway [ 55.569797] ice 0000:ca:00.0: The DDP package was successfully loaded: ICE OS Default Package version 1.3.28.0 [ 55.603629] ice 0000:ca:00.0: Get PHY capability failed. [ 55.608951] ice 0000:ca:00.0: ice_init_nvm_phy_type failed: -5 [ 55.647348] ice 0000:ca:00.0: PTP init successful [ 55.675536] ice 0000:ca:00.0: DCB is enabled in the hardware, max number of TCs supported on this port are 8 [ 55.685365] ice 0000:ca:00.0: FW LLDP is disabled, DCBx/LLDP in SW mode. [ 55.692179] ice 0000:ca:00.0: Commit DCB Configuration to the hardware [ 55.701382] ice 0000:ca:00.0: 126.024 Gb/s available PCIe bandwidth, limited by 16.0 GT/s PCIe x8 link at 0000:c9:02.0 (capable of 252.048 Gb/s with 16.0 GT/s PCIe x16 link) Reboot don't help, only second flash/activate with OOT or patched driver put card back in consistent state After patch: [root@host ~]# devlink dev flash pci/0000:ca:00.0 file E810_XXVDA4_FH_O_SEC_FW_1p6p1p9_NVM_3p10_PLDMoMCTP_0.11_8000AD7B.bin Preparing to flash [fw.mgmt] Erasing [fw.mgmt] Erasing done [fw.mgmt] Flashing 100% [fw.mgmt] Flashing done 100% [fw.undi] Erasing [fw.undi] Erasing done [fw.undi] Flashing 100% [fw.undi] Flashing done 100% [fw.netlist] Erasing [fw.netlist] Erasing done [fw.netlist] Flashing 100% [fw.netlist] Flashing done 100% Activate new firmware by devlink reload [root@host ~]# devlink dev reload pci/0000:ca:00.0 action fw_activate reload_actions_performed: fw_activate [root@host ~]# ip link show ens7f0 19: ens7f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000 link/ether b4:96:91:dc:72:e0 brd ff:ff:ff:ff:ff:ff altname enp202s0f0 Fixes: 399e27dbbd9e94 ("ice: support immediate firmware activation via devlink reload") Signed-off-by: Petr Oros <poros@redhat.com> --- drivers/net/ethernet/intel/ice/ice_main.c | 3 +++ 1 file changed, 3 insertions(+)