From 1a323bd071dd81c9c136c06fad9e02c403b48aca Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Thu, 14 Oct 2021 14:18:55 +0000 Subject: [PATCH 1/5] PCI/switchtec: Error out MRPC execution when MMIO reads fail A firmware hard reset may be initiated by various mechanisms including a UART interface, TWI sideband interface from BMC, MRPC command from userspace, etc. The switchtec management driver is unaware of these resets. The reset clears PCI state including the BARs and Memory Space Enable bits, so the device no longer responds to the MMIO accesses the driver uses to operate it. MMIO reads to the device will fail with a PCIe error. When the root complex handles that error, it typically fabricates ~0 data to complete the CPU read. Check for this sort of error by reading the device ID from MMIO space. This ID can never be ~0, so if we see that value, it probably means the PCIe Memory Read failed and we should return an error indication to the application using the switchtec driver. Link: https://lore.kernel.org/r/20211014141859.11444-2-kelvin.cao@microchip.com Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 67 ++++++++++++++++++++++++++++++---- 1 file changed, 60 insertions(+), 7 deletions(-) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 0b301f8be9ed..e5bb2ac0e7bb 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -45,6 +45,7 @@ enum mrpc_state { MRPC_QUEUED, MRPC_RUNNING, MRPC_DONE, + MRPC_IO_ERROR, }; struct switchtec_user { @@ -66,6 +67,19 @@ struct switchtec_user { int event_cnt; }; +/* + * The MMIO reads to the device_id register should always return the device ID + * of the device, otherwise the firmware is probably stuck or unreachable + * due to a firmware reset which clears PCI state including the BARs and Memory + * Space Enable bits. + */ +static int is_firmware_running(struct switchtec_dev *stdev) +{ + u32 device = ioread32(&stdev->mmio_sys_info->device_id); + + return stdev->pdev->device == device; +} + static struct switchtec_user *stuser_create(struct switchtec_dev *stdev) { struct switchtec_user *stuser; @@ -113,6 +127,7 @@ static void stuser_set_state(struct switchtec_user *stuser, [MRPC_QUEUED] = "QUEUED", [MRPC_RUNNING] = "RUNNING", [MRPC_DONE] = "DONE", + [MRPC_IO_ERROR] = "IO_ERROR", }; stuser->state = state; @@ -184,9 +199,26 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser) return 0; } +static void mrpc_cleanup_cmd(struct switchtec_dev *stdev) +{ + /* requires the mrpc_mutex to already be held when called */ + + struct switchtec_user *stuser = list_entry(stdev->mrpc_queue.next, + struct switchtec_user, list); + + stuser->cmd_done = true; + wake_up_interruptible(&stuser->cmd_comp); + list_del_init(&stuser->list); + stuser_put(stuser); + stdev->mrpc_busy = 0; + + mrpc_cmd_submit(stdev); +} + static void mrpc_complete_cmd(struct switchtec_dev *stdev) { /* requires the mrpc_mutex to already be held when called */ + struct switchtec_user *stuser; if (list_empty(&stdev->mrpc_queue)) @@ -223,13 +255,7 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev) memcpy_fromio(stuser->data, &stdev->mmio_mrpc->output_data, stuser->read_len); out: - stuser->cmd_done = true; - wake_up_interruptible(&stuser->cmd_comp); - list_del_init(&stuser->list); - stuser_put(stuser); - stdev->mrpc_busy = 0; - - mrpc_cmd_submit(stdev); + mrpc_cleanup_cmd(stdev); } static void mrpc_event_work(struct work_struct *work) @@ -246,6 +272,23 @@ static void mrpc_event_work(struct work_struct *work) mutex_unlock(&stdev->mrpc_mutex); } +static void mrpc_error_complete_cmd(struct switchtec_dev *stdev) +{ + /* requires the mrpc_mutex to already be held when called */ + + struct switchtec_user *stuser; + + if (list_empty(&stdev->mrpc_queue)) + return; + + stuser = list_entry(stdev->mrpc_queue.next, + struct switchtec_user, list); + + stuser_set_state(stuser, MRPC_IO_ERROR); + + mrpc_cleanup_cmd(stdev); +} + static void mrpc_timeout_work(struct work_struct *work) { struct switchtec_dev *stdev; @@ -257,6 +300,11 @@ static void mrpc_timeout_work(struct work_struct *work) mutex_lock(&stdev->mrpc_mutex); + if (!is_firmware_running(stdev)) { + mrpc_error_complete_cmd(stdev); + goto out; + } + if (stdev->dma_mrpc) status = stdev->dma_mrpc->status; else @@ -544,6 +592,11 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data, if (rc) return rc; + if (stuser->state == MRPC_IO_ERROR) { + mutex_unlock(&stdev->mrpc_mutex); + return -EIO; + } + if (stuser->state != MRPC_DONE) { mutex_unlock(&stdev->mrpc_mutex); return -EBADE; From 551ec658b69807318aeef5506da886cf9587b251 Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Thu, 14 Oct 2021 14:18:56 +0000 Subject: [PATCH 2/5] PCI/switchtec: Fix a MRPC error status handling issue If an error is encountered when executing a MRPC command, the firmware will set the status register to SWITCHTEC_MRPC_STATUS_ERROR and return the error code in the return value register. Add handling of SWITCHTEC_MRPC_STATUS_ERROR on status register when completing a MRPC command. Link: https://lore.kernel.org/r/20211014141859.11444-3-kelvin.cao@microchip.com Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index e5bb2ac0e7bb..5c300ff3921d 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -238,7 +238,8 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev) stuser_set_state(stuser, MRPC_DONE); stuser->return_code = 0; - if (stuser->status != SWITCHTEC_MRPC_STATUS_DONE) + if (stuser->status != SWITCHTEC_MRPC_STATUS_DONE && + stuser->status != SWITCHTEC_MRPC_STATUS_ERROR) goto out; if (stdev->dma_mrpc) @@ -622,7 +623,8 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data, out: mutex_unlock(&stdev->mrpc_mutex); - if (stuser->status == SWITCHTEC_MRPC_STATUS_DONE) + if (stuser->status == SWITCHTEC_MRPC_STATUS_DONE || + stuser->status == SWITCHTEC_MRPC_STATUS_ERROR) return size; else if (stuser->status == SWITCHTEC_MRPC_STATUS_INTERRUPTED) return -ENXIO; From 1420ac218abcc1df809eedfb0f7351941b01c785 Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Thu, 14 Oct 2021 14:18:57 +0000 Subject: [PATCH 3/5] PCI/switchtec: Update the way of getting management VEP instance ID Gen4 firmware adds DMA VEP and NVMe VEP support in VEP (virtual EP) instance ID register in addtion to management EP, update the way of getting management VEP instance ID. Link: https://lore.kernel.org/r/20211014141859.11444-4-kelvin.cao@microchip.com Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 5c300ff3921d..97a93c9b4629 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -1133,7 +1133,7 @@ static int ioctl_pff_to_port(struct switchtec_dev *stdev, break; } - reg = ioread32(&pcfg->vep_pff_inst_id); + reg = ioread32(&pcfg->vep_pff_inst_id) & 0xFF; if (reg == p.pff) { p.port = SWITCHTEC_IOCTL_PFF_VEP; break; @@ -1179,7 +1179,7 @@ static int ioctl_port_to_pff(struct switchtec_dev *stdev, p.pff = ioread32(&pcfg->usp_pff_inst_id); break; case SWITCHTEC_IOCTL_PFF_VEP: - p.pff = ioread32(&pcfg->vep_pff_inst_id); + p.pff = ioread32(&pcfg->vep_pff_inst_id) & 0xFF; break; default: if (p.port > ARRAY_SIZE(pcfg->dsp_pff_inst_id)) @@ -1553,7 +1553,7 @@ static void init_pff(struct switchtec_dev *stdev) if (reg < stdev->pff_csr_count) stdev->pff_local[reg] = 1; - reg = ioread32(&pcfg->vep_pff_inst_id); + reg = ioread32(&pcfg->vep_pff_inst_id) & 0xFF; if (reg < stdev->pff_csr_count) stdev->pff_local[reg] = 1; From 67116444cf55e1d070ee2060ffe4d1c72917ec31 Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Thu, 14 Oct 2021 14:18:58 +0000 Subject: [PATCH 4/5] PCI/switchtec: Replace ENOTSUPP with EOPNOTSUPP ENOTSUPP is not a SUSV4 error code, and the following checkpatch.pl warning will be given for new patches which still use ENOTSUPP. WARNING: ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP See the link below for the discussion. https://lore.kernel.org/netdev/20200511165319.2251678-1-kuba@kernel.org/ Replace ENOTSUPP with EOPNOTSUPP to align with future patches which will be using EOPNOTSUPP. Link: https://lore.kernel.org/r/20211014141859.11444-5-kelvin.cao@microchip.com Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 97a93c9b4629..236cb40cc7c5 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -376,7 +376,7 @@ static ssize_t field ## _show(struct device *dev, \ return io_string_show(buf, &si->gen4.field, \ sizeof(si->gen4.field)); \ else \ - return -ENOTSUPP; \ + return -EOPNOTSUPP; \ } \ \ static DEVICE_ATTR_RO(field) @@ -668,7 +668,7 @@ static int ioctl_flash_info(struct switchtec_dev *stdev, info.flash_length = ioread32(&fi->gen4.flash_length); info.num_partitions = SWITCHTEC_NUM_PARTITIONS_GEN4; } else { - return -ENOTSUPP; + return -EOPNOTSUPP; } if (copy_to_user(uinfo, &info, sizeof(info))) @@ -876,7 +876,7 @@ static int ioctl_flash_part_info(struct switchtec_dev *stdev, if (ret) return ret; } else { - return -ENOTSUPP; + return -EOPNOTSUPP; } if (copy_to_user(uinfo, &info, sizeof(info))) @@ -1611,7 +1611,7 @@ static int switchtec_init_pci(struct switchtec_dev *stdev, else if (stdev->gen == SWITCHTEC_GEN4) part_id = &stdev->mmio_sys_info->gen4.partition_id; else - return -ENOTSUPP; + return -EOPNOTSUPP; stdev->partition = ioread8(part_id); stdev->partition_count = ioread8(&stdev->mmio_ntb->partition_count); From 9f37ab0412eba537377c38b1dde1a04fbd7b5264 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 14 Oct 2021 14:18:59 +0000 Subject: [PATCH 5/5] PCI/switchtec: Add check of event support Not all events are supported by every gen/variant of the Switchtec firmware. To solve this, since Gen4, a new bit in each event header is introduced to indicate if an event is supported by the firmware. Link: https://lore.kernel.org/r/20211014141859.11444-6-kelvin.cao@microchip.com Signed-off-by: Logan Gunthorpe Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 8 +++++++- include/linux/switchtec.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 236cb40cc7c5..38c2b036fb8e 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -1024,6 +1024,9 @@ static int event_ctl(struct switchtec_dev *stdev, return PTR_ERR(reg); hdr = ioread32(reg); + if (hdr & SWITCHTEC_EVENT_NOT_SUPP) + return -EOPNOTSUPP; + for (i = 0; i < ARRAY_SIZE(ctl->data); i++) ctl->data[i] = ioread32(®[i + 1]); @@ -1096,7 +1099,7 @@ static int ioctl_event_ctl(struct switchtec_dev *stdev, for (ctl.index = 0; ctl.index < nr_idxs; ctl.index++) { ctl.flags = event_flags; ret = event_ctl(stdev, &ctl); - if (ret < 0) + if (ret < 0 && ret != -EOPNOTSUPP) return ret; } } else { @@ -1403,6 +1406,9 @@ static int mask_event(struct switchtec_dev *stdev, int eid, int idx) hdr_reg = event_regs[eid].map_reg(stdev, off, idx); hdr = ioread32(hdr_reg); + if (hdr & SWITCHTEC_EVENT_NOT_SUPP) + return 0; + if (!(hdr & SWITCHTEC_EVENT_OCCURRED && hdr & SWITCHTEC_EVENT_EN_IRQ)) return 0; diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index 082f1d51957a..be24056ac00f 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -19,6 +19,7 @@ #define SWITCHTEC_EVENT_EN_CLI BIT(2) #define SWITCHTEC_EVENT_EN_IRQ BIT(3) #define SWITCHTEC_EVENT_FATAL BIT(4) +#define SWITCHTEC_EVENT_NOT_SUPP BIT(31) #define SWITCHTEC_DMA_MRPC_EN BIT(0)