From 8d753db5c227d1f403c4bc9cae4ae02c862413cd Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 8 Sep 2021 21:55:56 +0200 Subject: misc: genwqe: Fixes DMA mask setting Commit 505b08777d78 ("misc: genwqe: Use dma_set_mask_and_coherent to simplify code") changed the logic in the code. Instead of a ||, a && should have been used to keep the code the same. Fixes: 505b08777d78 ("misc: genwqe: Use dma_set_mask_and_coherent to simplify code") Cc: stable Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/be49835baa8ba6daba5813b399edf6300f7fdbda.1631130862.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- drivers/misc/genwqe/card_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/misc') diff --git a/drivers/misc/genwqe/card_base.c b/drivers/misc/genwqe/card_base.c index 2e1befbd1ad9..693981891870 100644 --- a/drivers/misc/genwqe/card_base.c +++ b/drivers/misc/genwqe/card_base.c @@ -1090,7 +1090,7 @@ static int genwqe_pci_setup(struct genwqe_dev *cd) /* check for 64-bit DMA address supported (DAC) */ /* check for 32-bit DMA address supported (SAC) */ - if (dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64)) || + if (dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64)) && dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32))) { dev_err(&pci_dev->dev, "err: neither DMA32 nor DMA64 supported\n"); -- cgit v1.2.3 From d53c66594dc7606b191bb2976901a691d291a316 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Mon, 30 Aug 2021 15:02:09 +0300 Subject: habanalabs: fix potential race in interrupt wait ioctl We have a potential race where a user interrupt can be received in between user thread value comparison and before request was added to wait list. This means that if no consecutive interrupt will be received, user thread will timeout and fail. The solution is to add the request to wait list before we perform the comparison. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- .../misc/habanalabs/common/command_submission.c | 35 +++++++++++++--------- 1 file changed, 21 insertions(+), 14 deletions(-) (limited to 'drivers/misc') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 7b0516cf808b..9a8b9191c28c 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -2740,10 +2740,20 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx, else interrupt = &hdev->user_interrupt[interrupt_offset]; + /* Add pending user interrupt to relevant list for the interrupt + * handler to monitor + */ + spin_lock_irqsave(&interrupt->wait_list_lock, flags); + list_add_tail(&pend->wait_list_node, &interrupt->wait_list_head); + spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); + + /* We check for completion value as interrupt could have been received + * before we added the node to the wait list + */ if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 4)) { dev_err(hdev->dev, "Failed to copy completion value from user\n"); rc = -EFAULT; - goto free_fence; + goto remove_pending_user_interrupt; } if (completion_value >= target_value) @@ -2752,14 +2762,7 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx, *status = CS_WAIT_STATUS_BUSY; if (!timeout_us || (*status == CS_WAIT_STATUS_COMPLETED)) - goto free_fence; - - /* Add pending user interrupt to relevant list for the interrupt - * handler to monitor - */ - spin_lock_irqsave(&interrupt->wait_list_lock, flags); - list_add_tail(&pend->wait_list_node, &interrupt->wait_list_head); - spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); + goto remove_pending_user_interrupt; wait_again: /* Wait for interrupt handler to signal completion */ @@ -2770,6 +2773,15 @@ wait_again: * If comparison fails, keep waiting until timeout expires */ if (completion_rc > 0) { + spin_lock_irqsave(&interrupt->wait_list_lock, flags); + /* reinit_completion must be called before we check for user + * completion value, otherwise, if interrupt is received after + * the comparison and before the next wait_for_completion, + * we will reach timeout and fail + */ + reinit_completion(&pend->fence.completion); + spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); + if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 4)) { dev_err(hdev->dev, "Failed to copy completion value from user\n"); rc = -EFAULT; @@ -2780,11 +2792,7 @@ wait_again: if (completion_value >= target_value) { *status = CS_WAIT_STATUS_COMPLETED; } else { - spin_lock_irqsave(&interrupt->wait_list_lock, flags); - reinit_completion(&pend->fence.completion); timeout = completion_rc; - - spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); goto wait_again; } } else if (completion_rc == -ERESTARTSYS) { @@ -2802,7 +2810,6 @@ remove_pending_user_interrupt: list_del(&pend->wait_list_node); spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); -free_fence: kfree(pend); hl_ctx_put(ctx); -- cgit v1.2.3 From beb71ee36e4de93c2b21d916fb94558333d99974 Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Wed, 1 Sep 2021 15:48:04 +0300 Subject: habanalabs: fix kernel OOPs related to staged cs In case of single staged cs with both first/last indications set, we reach a scenario where in cs_release function flow we don't cancel the TDR work before freeing the cs memory, this lead to kernel OOPs since when the timer expires the work pointer will be freed already. In addition treat wait encaps cs "not found" handle as "OK" for the user in order to keep the user interface for both legacy and encpas signal/wait features the same. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/command_submission.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'drivers/misc') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 9a8b9191c28c..deb080830ecb 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -405,7 +405,7 @@ static void staged_cs_put(struct hl_device *hdev, struct hl_cs *cs) static void cs_handle_tdr(struct hl_device *hdev, struct hl_cs *cs) { bool next_entry_found = false; - struct hl_cs *next; + struct hl_cs *next, *first_cs; if (!cs_needs_timeout(cs)) return; @@ -415,9 +415,16 @@ static void cs_handle_tdr(struct hl_device *hdev, struct hl_cs *cs) /* We need to handle tdr only once for the complete staged submission. * Hence, we choose the CS that reaches this function first which is * the CS marked as 'staged_last'. + * In case single staged cs was submitted which has both first and last + * indications, then "cs_find_first" below will return NULL, since we + * removed the cs node from the list before getting here, + * in such cases just continue with the cs to cancel it's TDR work. */ - if (cs->staged_cs && cs->staged_last) - cs = hl_staged_cs_find_first(hdev, cs->staged_sequence); + if (cs->staged_cs && cs->staged_last) { + first_cs = hl_staged_cs_find_first(hdev, cs->staged_sequence); + if (first_cs) + cs = first_cs; + } spin_unlock(&hdev->cs_mirror_lock); @@ -2026,9 +2033,10 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, spin_unlock(&ctx->sig_mgr.lock); if (!handle_found) { - dev_err(hdev->dev, "Cannot find encapsulated signals handle for seq 0x%llx\n", + /* treat as signal CS already finished */ + dev_dbg(hdev->dev, "Cannot find encapsulated signals handle for seq 0x%llx\n", signal_seq); - rc = -EINVAL; + rc = 0; goto free_cs_chunk_array; } -- cgit v1.2.3 From 3e08f157c2587fc7ada93abed41aae19bcbf8a6b Mon Sep 17 00:00:00 2001 From: Omer Shpigelman Date: Wed, 30 Dec 2020 08:05:18 +0200 Subject: habanalabs/gaudi: use direct MSI in single mode Due to FLR scenario when running inside a VM, we must not use indirect MSI because it might cause some issues on VM destroy. In a VM we use single MSI mode in contrary to multi MSI mode which is used in bare-metal. Hence direct MSI should be used in single MSI mode only. Signed-off-by: Omer Shpigelman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/gaudi/gaudi.c | 9 ++++++--- drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h | 2 ++ 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'drivers/misc') diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 383865be3c2c..5249f8fd4d59 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -5802,6 +5802,7 @@ static void gaudi_add_end_of_cb_packets(struct hl_device *hdev, { struct gaudi_device *gaudi = hdev->asic_specific; struct packet_msg_prot *cq_pkt; + u64 msi_addr; u32 tmp; cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2); @@ -5823,10 +5824,12 @@ static void gaudi_add_end_of_cb_packets(struct hl_device *hdev, cq_pkt->ctl = cpu_to_le32(tmp); cq_pkt->value = cpu_to_le32(1); - if (!gaudi->multi_msi_mode) - msi_vec = 0; + if (gaudi->multi_msi_mode) + msi_addr = mmPCIE_MSI_INTR_0 + msi_vec * 4; + else + msi_addr = mmPCIE_CORE_MSI_REQ; - cq_pkt->addr = cpu_to_le64(CFG_BASE + mmPCIE_MSI_INTR_0 + msi_vec * 4); + cq_pkt->addr = cpu_to_le64(CFG_BASE + msi_addr); } static void gaudi_update_eq_ci(struct hl_device *hdev, u32 val) diff --git a/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h b/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h index ffdfbd9b3220..1a6576666794 100644 --- a/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h +++ b/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h @@ -308,6 +308,8 @@ #define mmPCIE_AUX_FLR_CTRL 0xC07394 #define mmPCIE_AUX_DBI 0xC07490 +#define mmPCIE_CORE_MSI_REQ 0xC04100 + #define mmPSOC_PCI_PLL_NR 0xC72100 #define mmSRAM_W_PLL_NR 0x4C8100 #define mmPSOC_HBM_PLL_NR 0xC74100 -- cgit v1.2.3 From d09ff62c820b5950ab9958e77620a8498efe9386 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Thu, 2 Sep 2021 09:47:53 +0300 Subject: habanalabs: fail collective wait when not supported As collective wait operation is required only when NIC ports are available, we disable the option to submit a CS in case all the ports are disabled, which is the current situation in the upstream driver. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/command_submission.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'drivers/misc') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index deb080830ecb..5b7de857fbc1 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -1995,6 +1995,15 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, goto free_cs_chunk_array; } + if (!hdev->nic_ports_mask) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); + dev_err(hdev->dev, + "Collective operations not supported when NIC ports are disabled"); + rc = -EINVAL; + goto free_cs_chunk_array; + } + collective_engine_id = chunk->collective_engine_id; } -- cgit v1.2.3 From fcffb759f7d53b8e6c6e91804eec994205099dd3 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 3 Sep 2021 09:02:03 +0100 Subject: habanalabs: Fix spelling mistake "FEADBACK" -> "FEEDBACK" There is a spelling mistake in a literal string. Fix it. Signed-off-by: Colin Ian King Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/gaudi/gaudi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/misc') diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 5249f8fd4d59..14da87b38e83 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -395,7 +395,7 @@ static struct hl_hw_obj_name_entry gaudi_so_id_to_str[] = { static struct hl_hw_obj_name_entry gaudi_monitor_id_to_str[] = { { .id = 200, .name = "MON_OBJ_DMA_DOWN_FEEDBACK_RESET" }, - { .id = 201, .name = "MON_OBJ_DMA_UP_FEADBACK_RESET" }, + { .id = 201, .name = "MON_OBJ_DMA_UP_FEEDBACK_RESET" }, { .id = 203, .name = "MON_OBJ_DRAM_TO_SRAM_QUEUE_FENCE" }, { .id = 204, .name = "MON_OBJ_TPC_0_CLK_GATE" }, { .id = 205, .name = "MON_OBJ_TPC_1_CLK_GATE" }, -- cgit v1.2.3 From 0a5ff77bf0a94468d541735f919a633f167787e9 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 12 Sep 2021 10:25:49 +0300 Subject: habanalabs/gaudi: fix LBW RR configuration Couple of fixes to the LBW RR configuration: 1. Add missing configuration of the SM RR registers in the DMA_IF. 2. Remove HBW range that doesn't belong. 3. Add entire gap + DBG area, from end of TPC7 to end of entire DBG space. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/gaudi/gaudi_security.c | 115 ++++++++++++++----------- 1 file changed, 67 insertions(+), 48 deletions(-) (limited to 'drivers/misc') diff --git a/drivers/misc/habanalabs/gaudi/gaudi_security.c b/drivers/misc/habanalabs/gaudi/gaudi_security.c index cb265c00cf73..25ac87cebd45 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi_security.c +++ b/drivers/misc/habanalabs/gaudi/gaudi_security.c @@ -8,16 +8,21 @@ #include "gaudiP.h" #include "../include/gaudi/asic_reg/gaudi_regs.h" -#define GAUDI_NUMBER_OF_RR_REGS 24 -#define GAUDI_NUMBER_OF_LBW_RANGES 12 +#define GAUDI_NUMBER_OF_LBW_RR_REGS 28 +#define GAUDI_NUMBER_OF_HBW_RR_REGS 24 +#define GAUDI_NUMBER_OF_LBW_RANGES 10 -static u64 gaudi_rr_lbw_hit_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_hit_aw_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_HIT_WPROT, mmDMA_IF_W_S_DMA0_HIT_WPROT, mmDMA_IF_W_S_DMA1_HIT_WPROT, + mmDMA_IF_E_S_SOB_HIT_WPROT, mmDMA_IF_E_S_DMA0_HIT_WPROT, mmDMA_IF_E_S_DMA1_HIT_WPROT, + mmDMA_IF_W_N_SOB_HIT_WPROT, mmDMA_IF_W_N_DMA0_HIT_WPROT, mmDMA_IF_W_N_DMA1_HIT_WPROT, + mmDMA_IF_E_N_SOB_HIT_WPROT, mmDMA_IF_E_N_DMA0_HIT_WPROT, mmDMA_IF_E_N_DMA1_HIT_WPROT, mmSIF_RTR_0_LBW_RANGE_PROT_HIT_AW, @@ -38,13 +43,17 @@ static u64 gaudi_rr_lbw_hit_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_HIT_AW, }; -static u64 gaudi_rr_lbw_hit_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_hit_ar_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_HIT_RPROT, mmDMA_IF_W_S_DMA0_HIT_RPROT, mmDMA_IF_W_S_DMA1_HIT_RPROT, + mmDMA_IF_E_S_SOB_HIT_RPROT, mmDMA_IF_E_S_DMA0_HIT_RPROT, mmDMA_IF_E_S_DMA1_HIT_RPROT, + mmDMA_IF_W_N_SOB_HIT_RPROT, mmDMA_IF_W_N_DMA0_HIT_RPROT, mmDMA_IF_W_N_DMA1_HIT_RPROT, + mmDMA_IF_E_N_SOB_HIT_RPROT, mmDMA_IF_E_N_DMA0_HIT_RPROT, mmDMA_IF_E_N_DMA1_HIT_RPROT, mmSIF_RTR_0_LBW_RANGE_PROT_HIT_AR, @@ -65,13 +74,17 @@ static u64 gaudi_rr_lbw_hit_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_HIT_AR, }; -static u64 gaudi_rr_lbw_min_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_min_aw_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_MIN_WPROT_0, mmDMA_IF_W_S_DMA0_MIN_WPROT_0, mmDMA_IF_W_S_DMA1_MIN_WPROT_0, + mmDMA_IF_E_S_SOB_MIN_WPROT_0, mmDMA_IF_E_S_DMA0_MIN_WPROT_0, mmDMA_IF_E_S_DMA1_MIN_WPROT_0, + mmDMA_IF_W_N_SOB_MIN_WPROT_0, mmDMA_IF_W_N_DMA0_MIN_WPROT_0, mmDMA_IF_W_N_DMA1_MIN_WPROT_0, + mmDMA_IF_E_N_SOB_MIN_WPROT_0, mmDMA_IF_E_N_DMA0_MIN_WPROT_0, mmDMA_IF_E_N_DMA1_MIN_WPROT_0, mmSIF_RTR_0_LBW_RANGE_PROT_MIN_AW_0, @@ -92,13 +105,17 @@ static u64 gaudi_rr_lbw_min_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_MIN_AW_0, }; -static u64 gaudi_rr_lbw_max_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_max_aw_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_MAX_WPROT_0, mmDMA_IF_W_S_DMA0_MAX_WPROT_0, mmDMA_IF_W_S_DMA1_MAX_WPROT_0, + mmDMA_IF_E_S_SOB_MAX_WPROT_0, mmDMA_IF_E_S_DMA0_MAX_WPROT_0, mmDMA_IF_E_S_DMA1_MAX_WPROT_0, + mmDMA_IF_W_N_SOB_MAX_WPROT_0, mmDMA_IF_W_N_DMA0_MAX_WPROT_0, mmDMA_IF_W_N_DMA1_MAX_WPROT_0, + mmDMA_IF_E_N_SOB_MAX_WPROT_0, mmDMA_IF_E_N_DMA0_MAX_WPROT_0, mmDMA_IF_E_N_DMA1_MAX_WPROT_0, mmSIF_RTR_0_LBW_RANGE_PROT_MAX_AW_0, @@ -119,13 +136,17 @@ static u64 gaudi_rr_lbw_max_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_MAX_AW_0, }; -static u64 gaudi_rr_lbw_min_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_min_ar_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_MIN_RPROT_0, mmDMA_IF_W_S_DMA0_MIN_RPROT_0, mmDMA_IF_W_S_DMA1_MIN_RPROT_0, + mmDMA_IF_E_S_SOB_MIN_RPROT_0, mmDMA_IF_E_S_DMA0_MIN_RPROT_0, mmDMA_IF_E_S_DMA1_MIN_RPROT_0, + mmDMA_IF_W_N_SOB_MIN_RPROT_0, mmDMA_IF_W_N_DMA0_MIN_RPROT_0, mmDMA_IF_W_N_DMA1_MIN_RPROT_0, + mmDMA_IF_E_N_SOB_MIN_RPROT_0, mmDMA_IF_E_N_DMA0_MIN_RPROT_0, mmDMA_IF_E_N_DMA1_MIN_RPROT_0, mmSIF_RTR_0_LBW_RANGE_PROT_MIN_AR_0, @@ -146,13 +167,17 @@ static u64 gaudi_rr_lbw_min_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_MIN_AR_0, }; -static u64 gaudi_rr_lbw_max_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_max_ar_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_MAX_RPROT_0, mmDMA_IF_W_S_DMA0_MAX_RPROT_0, mmDMA_IF_W_S_DMA1_MAX_RPROT_0, + mmDMA_IF_E_S_SOB_MAX_RPROT_0, mmDMA_IF_E_S_DMA0_MAX_RPROT_0, mmDMA_IF_E_S_DMA1_MAX_RPROT_0, + mmDMA_IF_W_N_SOB_MAX_RPROT_0, mmDMA_IF_W_N_DMA0_MAX_RPROT_0, mmDMA_IF_W_N_DMA1_MAX_RPROT_0, + mmDMA_IF_E_N_SOB_MAX_RPROT_0, mmDMA_IF_E_N_DMA0_MAX_RPROT_0, mmDMA_IF_E_N_DMA1_MAX_RPROT_0, mmSIF_RTR_0_LBW_RANGE_PROT_MAX_AR_0, @@ -173,7 +198,7 @@ static u64 gaudi_rr_lbw_max_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_MAX_AR_0, }; -static u64 gaudi_rr_hbw_hit_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_hit_aw_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_HIT_AW, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_HIT_AW, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_HIT_AW, @@ -200,7 +225,7 @@ static u64 gaudi_rr_hbw_hit_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_HIT_AW }; -static u64 gaudi_rr_hbw_hit_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_hit_ar_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_HIT_AR, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_HIT_AR, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_HIT_AR, @@ -227,7 +252,7 @@ static u64 gaudi_rr_hbw_hit_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_HIT_AR }; -static u64 gaudi_rr_hbw_base_low_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_base_low_aw_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_BASE_LOW_AW_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_BASE_LOW_AW_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_BASE_LOW_AW_0, @@ -254,7 +279,7 @@ static u64 gaudi_rr_hbw_base_low_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_BASE_LOW_AW_0 }; -static u64 gaudi_rr_hbw_base_high_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_base_high_aw_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_BASE_HIGH_AW_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_BASE_HIGH_AW_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_BASE_HIGH_AW_0, @@ -281,7 +306,7 @@ static u64 gaudi_rr_hbw_base_high_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_BASE_HIGH_AW_0 }; -static u64 gaudi_rr_hbw_mask_low_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_mask_low_aw_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_MASK_LOW_AW_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_MASK_LOW_AW_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_MASK_LOW_AW_0, @@ -308,7 +333,7 @@ static u64 gaudi_rr_hbw_mask_low_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_MASK_LOW_AW_0 }; -static u64 gaudi_rr_hbw_mask_high_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_mask_high_aw_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_MASK_HIGH_AW_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_MASK_HIGH_AW_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_MASK_HIGH_AW_0, @@ -335,7 +360,7 @@ static u64 gaudi_rr_hbw_mask_high_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_MASK_HIGH_AW_0 }; -static u64 gaudi_rr_hbw_base_low_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_base_low_ar_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_BASE_LOW_AR_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_BASE_LOW_AR_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_BASE_LOW_AR_0, @@ -362,7 +387,7 @@ static u64 gaudi_rr_hbw_base_low_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_BASE_LOW_AR_0 }; -static u64 gaudi_rr_hbw_base_high_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_base_high_ar_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_BASE_HIGH_AR_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_BASE_HIGH_AR_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_BASE_HIGH_AR_0, @@ -389,7 +414,7 @@ static u64 gaudi_rr_hbw_base_high_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_BASE_HIGH_AR_0 }; -static u64 gaudi_rr_hbw_mask_low_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_mask_low_ar_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_MASK_LOW_AR_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_MASK_LOW_AR_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_MASK_LOW_AR_0, @@ -416,7 +441,7 @@ static u64 gaudi_rr_hbw_mask_low_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_MASK_LOW_AR_0 }; -static u64 gaudi_rr_hbw_mask_high_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_mask_high_ar_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_MASK_HIGH_AR_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_MASK_HIGH_AR_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_MASK_HIGH_AR_0, @@ -12849,50 +12874,44 @@ static void gaudi_init_range_registers_lbw(struct hl_device *hdev) u32 lbw_rng_end[GAUDI_NUMBER_OF_LBW_RANGES]; int i, j; - lbw_rng_start[0] = (0xFBFE0000 & 0x3FFFFFF) - 1; - lbw_rng_end[0] = (0xFBFFF000 & 0x3FFFFFF) + 1; + lbw_rng_start[0] = (0xFC0E8000 & 0x3FFFFFF) - 1; /* 0x000E7FFF */ + lbw_rng_end[0] = (0xFC11FFFF & 0x3FFFFFF) + 1; /* 0x00120000 */ - lbw_rng_start[1] = (0xFC0E8000 & 0x3FFFFFF) - 1; - lbw_rng_end[1] = (0xFC120000 & 0x3FFFFFF) + 1; + lbw_rng_start[1] = (0xFC1E8000 & 0x3FFFFFF) - 1; /* 0x001E7FFF */ + lbw_rng_end[1] = (0xFC48FFFF & 0x3FFFFFF) + 1; /* 0x00490000 */ - lbw_rng_start[2] = (0xFC1E8000 & 0x3FFFFFF) - 1; - lbw_rng_end[2] = (0xFC48FFFF & 0x3FFFFFF) + 1; + lbw_rng_start[2] = (0xFC600000 & 0x3FFFFFF) - 1; /* 0x005FFFFF */ + lbw_rng_end[2] = (0xFCC48FFF & 0x3FFFFFF) + 1; /* 0x00C49000 */ - lbw_rng_start[3] = (0xFC600000 & 0x3FFFFFF) - 1; - lbw_rng_end[3] = (0xFCC48FFF & 0x3FFFFFF) + 1; + lbw_rng_start[3] = (0xFCC4A000 & 0x3FFFFFF) - 1; /* 0x00C49FFF */ + lbw_rng_end[3] = (0xFCCDFFFF & 0x3FFFFFF) + 1; /* 0x00CE0000 */ - lbw_rng_start[4] = (0xFCC4A000 & 0x3FFFFFF) - 1; - lbw_rng_end[4] = (0xFCCDFFFF & 0x3FFFFFF) + 1; + lbw_rng_start[4] = (0xFCCE4000 & 0x3FFFFFF) - 1; /* 0x00CE3FFF */ + lbw_rng_end[4] = (0xFCD1FFFF & 0x3FFFFFF) + 1; /* 0x00D20000 */ - lbw_rng_start[5] = (0xFCCE4000 & 0x3FFFFFF) - 1; - lbw_rng_end[5] = (0xFCD1FFFF & 0x3FFFFFF) + 1; + lbw_rng_start[5] = (0xFCD24000 & 0x3FFFFFF) - 1; /* 0x00D23FFF */ + lbw_rng_end[5] = (0xFCD5FFFF & 0x3FFFFFF) + 1; /* 0x00D60000 */ - lbw_rng_start[6] = (0xFCD24000 & 0x3FFFFFF) - 1; - lbw_rng_end[6] = (0xFCD5FFFF & 0x3FFFFFF) + 1; + lbw_rng_start[6] = (0xFCD64000 & 0x3FFFFFF) - 1; /* 0x00D63FFF */ + lbw_rng_end[6] = (0xFCD9FFFF & 0x3FFFFFF) + 1; /* 0x00DA0000 */ - lbw_rng_start[7] = (0xFCD64000 & 0x3FFFFFF) - 1; - lbw_rng_end[7] = (0xFCD9FFFF & 0x3FFFFFF) + 1; + lbw_rng_start[7] = (0xFCDA4000 & 0x3FFFFFF) - 1; /* 0x00DA3FFF */ + lbw_rng_end[7] = (0xFCDDFFFF & 0x3FFFFFF) + 1; /* 0x00DE0000 */ - lbw_rng_start[8] = (0xFCDA4000 & 0x3FFFFFF) - 1; - lbw_rng_end[8] = (0xFCDDFFFF & 0x3FFFFFF) + 1; + lbw_rng_start[8] = (0xFCDE4000 & 0x3FFFFFF) - 1; /* 0x00DE3FFF */ + lbw_rng_end[8] = (0xFCE05FFF & 0x3FFFFFF) + 1; /* 0x00E06000 */ - lbw_rng_start[9] = (0xFCDE4000 & 0x3FFFFFF) - 1; - lbw_rng_end[9] = (0xFCE05FFF & 0x3FFFFFF) + 1; + lbw_rng_start[9] = (0xFCFC9000 & 0x3FFFFFF) - 1; /* 0x00FC8FFF */ + lbw_rng_end[9] = (0xFFFFFFFE & 0x3FFFFFF) + 1; /* 0x03FFFFFF */ - lbw_rng_start[10] = (0xFEC43000 & 0x3FFFFFF) - 1; - lbw_rng_end[10] = (0xFEC43FFF & 0x3FFFFFF) + 1; - - lbw_rng_start[11] = (0xFE484000 & 0x3FFFFFF) - 1; - lbw_rng_end[11] = (0xFE484FFF & 0x3FFFFFF) + 1; - - for (i = 0 ; i < GAUDI_NUMBER_OF_RR_REGS ; i++) { + for (i = 0 ; i < GAUDI_NUMBER_OF_LBW_RR_REGS ; i++) { WREG32(gaudi_rr_lbw_hit_aw_regs[i], (1 << GAUDI_NUMBER_OF_LBW_RANGES) - 1); WREG32(gaudi_rr_lbw_hit_ar_regs[i], (1 << GAUDI_NUMBER_OF_LBW_RANGES) - 1); } - for (i = 0 ; i < GAUDI_NUMBER_OF_RR_REGS ; i++) + for (i = 0 ; i < GAUDI_NUMBER_OF_LBW_RR_REGS ; i++) for (j = 0 ; j < GAUDI_NUMBER_OF_LBW_RANGES ; j++) { WREG32(gaudi_rr_lbw_min_aw_regs[i] + (j << 2), lbw_rng_start[j]); @@ -12939,12 +12958,12 @@ static void gaudi_init_range_registers_hbw(struct hl_device *hdev) * 6th range is the host */ - for (i = 0 ; i < GAUDI_NUMBER_OF_RR_REGS ; i++) { + for (i = 0 ; i < GAUDI_NUMBER_OF_HBW_RR_REGS ; i++) { WREG32(gaudi_rr_hbw_hit_aw_regs[i], 0x1F); WREG32(gaudi_rr_hbw_hit_ar_regs[i], 0x1D); } - for (i = 0 ; i < GAUDI_NUMBER_OF_RR_REGS ; i++) { + for (i = 0 ; i < GAUDI_NUMBER_OF_HBW_RR_REGS ; i++) { WREG32(gaudi_rr_hbw_base_low_aw_regs[i], dram_addr_lo); WREG32(gaudi_rr_hbw_base_low_ar_regs[i], dram_addr_lo); -- cgit v1.2.3 From 3d3200ae167ba048a29e0c815987a3fdc90fc8d2 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Thu, 9 Sep 2021 09:56:37 +0300 Subject: habanalabs: rate limit multi CS completion errors As user can send wrong arguments to multi CS API, we rate limit the amount of errors dumped to dmesg, in addition we change the severity to warning. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/command_submission.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/misc') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 5b7de857fbc1..a4ed91ed991d 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -2630,7 +2630,8 @@ static int hl_multi_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data) * completed after the poll function. */ if (!mcs_data.completion_bitmap) { - dev_err(hdev->dev, "Multi-CS got completion on wait but no CS completed\n"); + dev_warn_ratelimited(hdev->dev, + "Multi-CS got completion on wait but no CS completed\n"); rc = -EFAULT; } } -- cgit v1.2.3 From 42254c2a4991b98ca3f86040a1a7b7b32a0c8c4a Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Sun, 12 Sep 2021 14:30:35 +0300 Subject: habanalabs: fix wait offset handling Add handling for case where the user doesn't set wait offset, and keeps it as 0. In such a case the driver will decrement one from this zero value which will cause the code to wait for wrong number of signals. The solution is to treat this case as in legacy wait cs, and wait for the next signal. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/hw_queue.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'drivers/misc') diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c index 76b7de8f1406..0743319b10c7 100644 --- a/drivers/misc/habanalabs/common/hw_queue.c +++ b/drivers/misc/habanalabs/common/hw_queue.c @@ -437,6 +437,7 @@ void hl_hw_queue_encaps_sig_set_sob_info(struct hl_device *hdev, struct hl_cs_compl *cs_cmpl) { struct hl_cs_encaps_sig_handle *handle = cs->encaps_sig_hdl; + u32 offset = 0; cs_cmpl->hw_sob = handle->hw_sob; @@ -446,9 +447,13 @@ void hl_hw_queue_encaps_sig_set_sob_info(struct hl_device *hdev, * set offset 1 for example he mean to wait only for the first * signal only, which will be pre_sob_val, and if he set offset 2 * then the value required is (pre_sob_val + 1) and so on... + * if user set wait offset to 0, then treat it as legacy wait cs, + * wait for the next signal. */ - cs_cmpl->sob_val = handle->pre_sob_val + - (job->encaps_sig_wait_offset - 1); + if (job->encaps_sig_wait_offset) + offset = job->encaps_sig_wait_offset - 1; + + cs_cmpl->sob_val = handle->pre_sob_val + offset; } static int init_wait_cs(struct hl_device *hdev, struct hl_cs *cs, -- cgit v1.2.3 From c8fee41957f036cbc8e840bd91e2087731df7f7e Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Sun, 12 Sep 2021 15:49:00 +0300 Subject: habanalabs: expose a single cs seq in staged submissions Staged submission consists of multiple command submissions. In order to be explicit, driver should return a single cs sequence for every cs in the submission, or else user may try to wait on an internal CS rather than waiting for the whole submission. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/command_submission.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/misc') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index a4ed91ed991d..91b57544f7c6 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -1295,6 +1295,12 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, if (rc) goto free_cs_object; + /* If this is a staged submission we must return the staged sequence + * rather than the internal CS sequence + */ + if (cs->staged_cs) + *cs_seq = cs->staged_sequence; + /* Validate ALL the CS chunks before submitting the CS */ for (i = 0 ; i < num_chunks ; i++) { struct hl_cs_chunk *chunk = &cs_chunk_array[i]; -- cgit v1.2.3 From d9d1232b48344c6c72dbdf89fae1e7638e5df757 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 17 Sep 2021 13:57:36 +0200 Subject: misc: bcm-vk: fix tty registration race Make sure to set the tty class-device driver data before registering the tty to avoid having a racing open() dereference a NULL pointer. Fixes: 91ca10d6fa07 ("misc: bcm-vk: add ttyVK support") Cc: stable@vger.kernel.org # 5.12 Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210917115736.5816-1-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/bcm-vk/bcm_vk_tty.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/misc') diff --git a/drivers/misc/bcm-vk/bcm_vk_tty.c b/drivers/misc/bcm-vk/bcm_vk_tty.c index 1b6076a89ca6..6669625ba4c8 100644 --- a/drivers/misc/bcm-vk/bcm_vk_tty.c +++ b/drivers/misc/bcm-vk/bcm_vk_tty.c @@ -267,13 +267,13 @@ int bcm_vk_tty_init(struct bcm_vk *vk, char *name) struct device *tty_dev; tty_port_init(&vk->tty[i].port); - tty_dev = tty_port_register_device(&vk->tty[i].port, tty_drv, - i, dev); + tty_dev = tty_port_register_device_attr(&vk->tty[i].port, + tty_drv, i, dev, vk, + NULL); if (IS_ERR(tty_dev)) { err = PTR_ERR(tty_dev); goto unwind; } - dev_set_drvdata(tty_dev, vk); vk->tty[i].is_opened = false; } -- cgit v1.2.3 From 4ca57d5139a0be3cf76c1667a4c0afb16d4a3b02 Mon Sep 17 00:00:00 2001 From: Rajaravi Krishna Katta Date: Tue, 14 Sep 2021 18:28:48 +0300 Subject: habanalabs: fix resetting args in wait for CS IOCTL In wait for CS IOCTL code, the driver resets the incoming args structure before returning to the user, regardless of the return value of the IOCTL. In case the IOCTL returns EINTR, resetting the args will result in error in case the userspace will repeat the ioctl call immediately (which is the behavior in the hl-thunk userspace library). The solution is to reset the args only if the driver returns success (0) as a return value for the IOCTL. Signed-off-by: Rajaravi Krishna Katta Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- .../misc/habanalabs/common/command_submission.c | 33 +++++++++++++--------- include/uapi/misc/habanalabs.h | 6 ++-- 2 files changed, 21 insertions(+), 18 deletions(-) (limited to 'drivers/misc') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 91b57544f7c6..6dafff375f1c 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -2649,11 +2649,18 @@ put_ctx: free_seq_arr: kfree(cs_seq_arr); - /* update output args */ - memset(args, 0, sizeof(*args)); if (rc) return rc; + if (mcs_data.wait_status == -ERESTARTSYS) { + dev_err_ratelimited(hdev->dev, + "user process got signal while waiting for Multi-CS\n"); + return -EINTR; + } + + /* update output args */ + memset(args, 0, sizeof(*args)); + if (mcs_data.completion_bitmap) { args->out.status = HL_WAIT_CS_STATUS_COMPLETED; args->out.cs_completion_map = mcs_data.completion_bitmap; @@ -2667,8 +2674,6 @@ free_seq_arr: /* update if some CS was gone */ if (mcs_data.timestamp) args->out.flags |= HL_WAIT_CS_STATUS_FLAG_GONE; - } else if (mcs_data.wait_status == -ERESTARTSYS) { - args->out.status = HL_WAIT_CS_STATUS_INTERRUPTED; } else { args->out.status = HL_WAIT_CS_STATUS_BUSY; } @@ -2688,16 +2693,17 @@ static int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data) rc = _hl_cs_wait_ioctl(hdev, hpriv->ctx, args->in.timeout_us, seq, &status, ×tamp); + if (rc == -ERESTARTSYS) { + dev_err_ratelimited(hdev->dev, + "user process got signal while waiting for CS handle %llu\n", + seq); + return -EINTR; + } + memset(args, 0, sizeof(*args)); if (rc) { - if (rc == -ERESTARTSYS) { - dev_err_ratelimited(hdev->dev, - "user process got signal while waiting for CS handle %llu\n", - seq); - args->out.status = HL_WAIT_CS_STATUS_INTERRUPTED; - rc = -EINTR; - } else if (rc == -ETIMEDOUT) { + if (rc == -ETIMEDOUT) { dev_err_ratelimited(hdev->dev, "CS %llu has timed-out while user process is waiting for it\n", seq); @@ -2823,7 +2829,6 @@ wait_again: dev_err_ratelimited(hdev->dev, "user process got signal while waiting for interrupt ID %d\n", interrupt->interrupt_id); - *status = HL_WAIT_CS_STATUS_INTERRUPTED; rc = -EINTR; } else { *status = CS_WAIT_STATUS_BUSY; @@ -2878,8 +2883,6 @@ static int hl_interrupt_wait_ioctl(struct hl_fpriv *hpriv, void *data) args->in.interrupt_timeout_us, args->in.addr, args->in.target, interrupt_offset, &status); - memset(args, 0, sizeof(*args)); - if (rc) { if (rc != -EINTR) dev_err_ratelimited(hdev->dev, @@ -2888,6 +2891,8 @@ static int hl_interrupt_wait_ioctl(struct hl_fpriv *hpriv, void *data) return rc; } + memset(args, 0, sizeof(*args)); + switch (status) { case CS_WAIT_STATUS_COMPLETED: args->out.status = HL_WAIT_CS_STATUS_COMPLETED; diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 7cc2a0f3f2f5..d13bb8c1b450 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -917,7 +917,6 @@ struct hl_wait_cs_in { #define HL_WAIT_CS_STATUS_BUSY 1 #define HL_WAIT_CS_STATUS_TIMEDOUT 2 #define HL_WAIT_CS_STATUS_ABORTED 3 -#define HL_WAIT_CS_STATUS_INTERRUPTED 4 #define HL_WAIT_CS_STATUS_FLAG_GONE 0x1 #define HL_WAIT_CS_STATUS_FLAG_TIMESTAMP_VLD 0x2 @@ -1286,7 +1285,8 @@ struct hl_debug_args { * EIO - The CS was aborted (usually because the device was reset) * ENODEV - The device wants to do hard-reset (so user need to close FD) * - * The driver also returns a custom define inside the IOCTL which can be: + * The driver also returns a custom define in case the IOCTL call returned 0. + * The define can be one of the following: * * HL_WAIT_CS_STATUS_COMPLETED - The CS has been completed successfully (0) * HL_WAIT_CS_STATUS_BUSY - The CS is still executing (0) @@ -1294,8 +1294,6 @@ struct hl_debug_args { * (ETIMEDOUT) * HL_WAIT_CS_STATUS_ABORTED - The CS was aborted, usually because the * device was reset (EIO) - * HL_WAIT_CS_STATUS_INTERRUPTED - Waiting for the CS was interrupted (EINTR) - * */ #define HL_IOCTL_WAIT_CS \ -- cgit v1.2.3 From a3e16937319aea285c64ab5bf8464470afac8dd3 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 23 Sep 2021 20:46:09 +0100 Subject: misc: gehc: Add SPI ID table Currently autoloading for SPI devices does not use the DT ID table, it uses SPI modalises. Supporting OF modalises is going to be difficult if not impractical, an attempt was made but has been reverted, so ensure that module autoloading works for this driver by adding a SPI ID table entry for the device name part of the compatible - currently only the full compatible is listed which isn't very idiomatic and won't match the modalias that is generated. Fixes: 96c8395e2166 ("spi: Revert modalias changes") Cc: stable Tested-by: Martyn Welch Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20210923194609.52647-1-broonie@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/gehc-achc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/misc') diff --git a/drivers/misc/gehc-achc.c b/drivers/misc/gehc-achc.c index 02f33bc60c56..4c9c5394da6f 100644 --- a/drivers/misc/gehc-achc.c +++ b/drivers/misc/gehc-achc.c @@ -539,6 +539,7 @@ static int gehc_achc_probe(struct spi_device *spi) static const struct spi_device_id gehc_achc_id[] = { { "ge,achc", 0 }, + { "achc", 0 }, { } }; MODULE_DEVICE_TABLE(spi, gehc_achc_id); -- cgit v1.2.3 From 42641042c10c757fe10cc09088cf3f436cec5007 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 27 Sep 2021 14:13:57 +0200 Subject: cb710: avoid NULL pointer subtraction clang-14 complains about an unusual way of converting a pointer to an integer: drivers/misc/cb710/sgbuf2.c:50:15: error: performing pointer subtraction with a null pointer has undefined behavior [-Werror,-Wnull-pointer-subtraction] return ((ptr - NULL) & 3) != 0; Replace this with a normal cast to uintptr_t. Fixes: 5f5bac8272be ("mmc: Driver for CB710/720 memory card reader (MMC part)") Cc: stable Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210927121408.939246-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cb710/sgbuf2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/misc') diff --git a/drivers/misc/cb710/sgbuf2.c b/drivers/misc/cb710/sgbuf2.c index e5a4ed3701eb..a798fad5f03c 100644 --- a/drivers/misc/cb710/sgbuf2.c +++ b/drivers/misc/cb710/sgbuf2.c @@ -47,7 +47,7 @@ static inline bool needs_unaligned_copy(const void *ptr) #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS return false; #else - return ((ptr - NULL) & 3) != 0; + return ((uintptr_t)ptr & 3) != 0; #endif } -- cgit v1.2.3 From f9a470db2736b01538ad193c316eb3f26be37d58 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Wed, 22 Sep 2021 16:43:26 +0100 Subject: misc: fastrpc: Add missing lock before accessing find_vma() fastrpc driver is using find_vma() without any protection, as a result we see below warning due to recent patch 5b78ed24e8ec ("mm/pagemap: add mmap_assert_locked() annotations to find_vma*()") which added mmap_assert_locked() in find_vma() function. This bug went un-noticed in previous versions. Fix this issue by adding required protection while calling find_vma(). CPU: 0 PID: 209746 Comm: benchmark_model Not tainted 5.15.0-rc2-00445-ge14fe2bf817a-dirty #969 Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT) pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : find_vma+0x64/0xd0 lr : find_vma+0x60/0xd0 sp : ffff8000158ebc40 ... Call trace: find_vma+0x64/0xd0 fastrpc_internal_invoke+0x570/0xda8 fastrpc_device_ioctl+0x3e0/0x928 __arm64_sys_ioctl+0xac/0xf0 invoke_syscall+0x44/0x100 el0_svc_common.constprop.3+0x70/0xf8 do_el0_svc+0x24/0x88 el0_svc+0x3c/0x138 el0t_64_sync_handler+0x90/0xb8 el0t_64_sync+0x180/0x184 Fixes: 80f3afd72bd4 ("misc: fastrpc: consider address offset before sending to DSP") Cc: stable@vger.kernel.org Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20210922154326.8927-1-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/misc') diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index beda610e6b30..ad6ced454655 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -814,10 +814,12 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) rpra[i].pv = (u64) ctx->args[i].ptr; pages[i].addr = ctx->maps[i]->phys; + mmap_read_lock(current->mm); vma = find_vma(current->mm, ctx->args[i].ptr); if (vma) pages[i].addr += ctx->args[i].ptr - vma->vm_start; + mmap_read_unlock(current->mm); pg_start = (ctx->args[i].ptr & PAGE_MASK) >> PAGE_SHIFT; pg_end = ((ctx->args[i].ptr + len - 1) & PAGE_MASK) >> -- cgit v1.2.3 From 97d8ebead87b7457ba5c4f4e7860b8fc8cf013fd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 3 Oct 2021 17:16:41 -0700 Subject: misc: HI6421V600_IRQ should depend on HAS_IOMEM MFD_CORE depends on HAS_IOMEM so anything that selects MFD_CORE should also depend on HAS_IOMEM since 'select' does not check any dependencies of the symbol that is being selected. Prevents this kconfig warning: WARNING: unmet direct dependencies detected for MFD_CORE Depends on [n]: HAS_IOMEM [=n] Selected by [m]: - HI6421V600_IRQ [=m] && OF [=y] && SPMI [=m] Fixes: bb3b6552a5b0 ("staging: hikey9xx: split hi6421v600 irq into a separate driver") Cc: Mauro Carvalho Chehab Cc: Greg Kroah-Hartman Cc: Arnd Bergmann Signed-off-by: Randy Dunlap Link: https://lore.kernel.org/r/20211004001641.23180-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/misc') diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 85ba901bc11b..0f5a49fc7c9e 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -224,6 +224,7 @@ config HI6421V600_IRQ tristate "HiSilicon Hi6421v600 IRQ and powerkey" depends on OF depends on SPMI + depends on HAS_IOMEM select MFD_CORE select REGMAP_SPMI help -- cgit v1.2.3 From 9e2cd444909b3c93f5cc83463d12291e3e0f990b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 23 Sep 2021 18:24:53 +0100 Subject: eeprom: at25: Add SPI ID table Currently autoloading for SPI devices does not use the DT ID table, it uses SPI modalises. Supporting OF modalises is going to be difficult if not impractical, an attempt was made but has been reverted, so ensure that module autoloading works for this driver by adding an id_table listing the SPI IDs for everything. Fixes: 96c8395e2166 ("spi: Revert modalias changes") Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20210923172453.4921-1-broonie@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/eeprom/at25.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'drivers/misc') diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index 4d09b672ac3c..632325474233 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -366,6 +366,13 @@ static const struct of_device_id at25_of_match[] = { }; MODULE_DEVICE_TABLE(of, at25_of_match); +static const struct spi_device_id at25_spi_ids[] = { + { .name = "at25",}, + { .name = "fm25",}, + { } +}; +MODULE_DEVICE_TABLE(spi, at25_spi_ids); + static int at25_probe(struct spi_device *spi) { struct at25_data *at25 = NULL; @@ -491,6 +498,7 @@ static struct spi_driver at25_driver = { .dev_groups = sernum_groups, }, .probe = at25_probe, + .id_table = at25_spi_ids, }; module_spi_driver(at25_driver); -- cgit v1.2.3 From 137879f7ff23c635d2c6b2e43f4b39e2d305c3e2 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 22 Sep 2021 19:40:48 +0100 Subject: eeprom: 93xx46: Add SPI device ID table Currently autoloading for SPI devices does not use the DT ID table, it uses SPI modalises. Supporting OF modalises is going to be difficult if not impractical, an attempt was made but has been reverted, so ensure that module autoloading works for this driver by adding a SPI device ID table. Fixes: 96c8395e2166 ("spi: Revert modalias changes") Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20210922184048.34770-1-broonie@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/eeprom/eeprom_93xx46.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'drivers/misc') diff --git a/drivers/misc/eeprom/eeprom_93xx46.c b/drivers/misc/eeprom/eeprom_93xx46.c index 29d8971ec558..660ee924f8b1 100644 --- a/drivers/misc/eeprom/eeprom_93xx46.c +++ b/drivers/misc/eeprom/eeprom_93xx46.c @@ -406,6 +406,23 @@ static const struct of_device_id eeprom_93xx46_of_table[] = { }; MODULE_DEVICE_TABLE(of, eeprom_93xx46_of_table); +static const struct spi_device_id eeprom_93xx46_spi_ids[] = { + { .name = "eeprom-93xx46", + .driver_data = (kernel_ulong_t)&at93c46_data, }, + { .name = "at93c46", + .driver_data = (kernel_ulong_t)&at93c46_data, }, + { .name = "at93c46d", + .driver_data = (kernel_ulong_t)&atmel_at93c46d_data, }, + { .name = "at93c56", + .driver_data = (kernel_ulong_t)&at93c56_data, }, + { .name = "at93c66", + .driver_data = (kernel_ulong_t)&at93c66_data, }, + { .name = "93lc46b", + .driver_data = (kernel_ulong_t)µchip_93lc46b_data, }, + {} +}; +MODULE_DEVICE_TABLE(of, eeprom_93xx46_of_table); + static int eeprom_93xx46_probe_dt(struct spi_device *spi) { const struct of_device_id *of_id = @@ -555,6 +572,7 @@ static struct spi_driver eeprom_93xx46_driver = { }, .probe = eeprom_93xx46_probe, .remove = eeprom_93xx46_remove, + .id_table = eeprom_93xx46_spi_ids, }; module_spi_driver(eeprom_93xx46_driver); -- cgit v1.2.3 From 75c10c5e7a715550afdd51ef8cfd1d975f48f9e1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Oct 2021 20:36:44 +0300 Subject: mei: me: add Ice Lake-N device id. Add Ice Lake-N device ID. The device can be found on MacBookPro16,2 [1]. [1]: https://linux-hardware.org/?probe=f1c5cf0c43 Signed-off-by: Andy Shevchenko Cc: stable Link: https://lore.kernel.org/r/20211001173644.16068-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/hw-me-regs.h | 1 + drivers/misc/mei/pci-me.c | 1 + 2 files changed, 2 insertions(+) (limited to 'drivers/misc') diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index cb34925e10f1..67bb6a25fd0a 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -92,6 +92,7 @@ #define MEI_DEV_ID_CDF 0x18D3 /* Cedar Fork */ #define MEI_DEV_ID_ICP_LP 0x34E0 /* Ice Lake Point LP */ +#define MEI_DEV_ID_ICP_N 0x38E0 /* Ice Lake Point N */ #define MEI_DEV_ID_JSP_N 0x4DE0 /* Jasper Lake Point N */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index c3393b383e59..3a45aaf002ac 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -96,6 +96,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_CMP_H_3, MEI_ME_PCH8_ITOUCH_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICP_N, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_TGP_LP, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_TGP_H, MEI_ME_PCH15_SPS_CFG)}, -- cgit v1.2.3 From 6d7163f2c49fda5658e43105a96b555c89a4548d Mon Sep 17 00:00:00 2001 From: Alexander Usyskin Date: Wed, 13 Oct 2021 10:45:52 +0300 Subject: mei: hbm: drop hbm responses on early shutdown Drop HBM responses also in the early shutdown phase where the usual traffic is allowed. Extend the rule that drop HBM responses received during the shutdown phase by also in MEI_DEV_POWERING_DOWN state. This resolves the stall if the driver is stopping in the middle of the link init or link reset. Fixes: da3eb47c90d4 ("mei: hbm: drop hbm responses on shutdown") Fixes: 36edb1407c3c ("mei: allow clients on bus to communicate in remove callback") Cc: # v5.12+ Signed-off-by: Alexander Usyskin Signed-off-by: Tomas Winkler Link: https://lore.kernel.org/r/20211013074552.2278419-1-tomas.winkler@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/hbm.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'drivers/misc') diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c index 99b5c1ecc444..be41843df75b 100644 --- a/drivers/misc/mei/hbm.c +++ b/drivers/misc/mei/hbm.c @@ -1298,7 +1298,8 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) if (dev->dev_state != MEI_DEV_INIT_CLIENTS || dev->hbm_state != MEI_HBM_STARTING) { - if (dev->dev_state == MEI_DEV_POWER_DOWN) { + if (dev->dev_state == MEI_DEV_POWER_DOWN || + dev->dev_state == MEI_DEV_POWERING_DOWN) { dev_dbg(dev->dev, "hbm: start: on shutdown, ignoring\n"); return 0; } @@ -1381,7 +1382,8 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) if (dev->dev_state != MEI_DEV_INIT_CLIENTS || dev->hbm_state != MEI_HBM_DR_SETUP) { - if (dev->dev_state == MEI_DEV_POWER_DOWN) { + if (dev->dev_state == MEI_DEV_POWER_DOWN || + dev->dev_state == MEI_DEV_POWERING_DOWN) { dev_dbg(dev->dev, "hbm: dma setup response: on shutdown, ignoring\n"); return 0; } @@ -1448,7 +1450,8 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) if (dev->dev_state != MEI_DEV_INIT_CLIENTS || dev->hbm_state != MEI_HBM_CLIENT_PROPERTIES) { - if (dev->dev_state == MEI_DEV_POWER_DOWN) { + if (dev->dev_state == MEI_DEV_POWER_DOWN || + dev->dev_state == MEI_DEV_POWERING_DOWN) { dev_dbg(dev->dev, "hbm: properties response: on shutdown, ignoring\n"); return 0; } @@ -1490,7 +1493,8 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) if (dev->dev_state != MEI_DEV_INIT_CLIENTS || dev->hbm_state != MEI_HBM_ENUM_CLIENTS) { - if (dev->dev_state == MEI_DEV_POWER_DOWN) { + if (dev->dev_state == MEI_DEV_POWER_DOWN || + dev->dev_state == MEI_DEV_POWERING_DOWN) { dev_dbg(dev->dev, "hbm: enumeration response: on shutdown, ignoring\n"); return 0; } -- cgit v1.2.3 From f42752729e2068a92c7d8b576d0dbbc9c1464149 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 14 Oct 2021 17:37:18 +0200 Subject: eeprom: 93xx46: fix MODULE_DEVICE_TABLE The newly added SPI device ID table does not work because the entry is incorrectly copied from the OF device table. During build testing, this shows as a compile failure when building it as a loadable module: drivers/misc/eeprom/eeprom_93xx46.c:424:1: error: redefinition of '__mod_of__eeprom_93xx46_of_table_device_table' MODULE_DEVICE_TABLE(of, eeprom_93xx46_of_table); Change the entry to refer to the correct symbol. Fixes: 137879f7ff23 ("eeprom: 93xx46: Add SPI device ID table") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20211014153730.3821376-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/eeprom/eeprom_93xx46.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/misc') diff --git a/drivers/misc/eeprom/eeprom_93xx46.c b/drivers/misc/eeprom/eeprom_93xx46.c index 660ee924f8b1..1f15399e5cb4 100644 --- a/drivers/misc/eeprom/eeprom_93xx46.c +++ b/drivers/misc/eeprom/eeprom_93xx46.c @@ -421,7 +421,7 @@ static const struct spi_device_id eeprom_93xx46_spi_ids[] = { .driver_data = (kernel_ulong_t)µchip_93lc46b_data, }, {} }; -MODULE_DEVICE_TABLE(of, eeprom_93xx46_of_table); +MODULE_DEVICE_TABLE(spi, eeprom_93xx46_spi_ids); static int eeprom_93xx46_probe_dt(struct spi_device *spi) { -- cgit v1.2.3