From 018e0e3594f7dcd029d258e368c485e742fa9cdb Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Tue, 3 Dec 2019 10:12:10 +0200 Subject: habanalabs: rate limit error msg on waiting for CS In case a user submits a CS, and the submission fails, and the user doesn't check the return value and instead use the error return value as a valid sequence number of a CS and ask to wait on it, the driver will print an error and return an error code for that wait. The real problem happens if now the user ignores the error of the wait, and try to wait again and again. This can lead to a flood of error messages from the driver and even soft lockup event. Signed-off-by: Oded Gabbay Reviewed-by: Tomer Tayar --- drivers/misc/habanalabs/command_submission.c | 5 +++-- drivers/misc/habanalabs/context.c | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index 8850f475a413..0bf08678431b 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -824,8 +824,9 @@ int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data) memset(args, 0, sizeof(*args)); if (rc < 0) { - dev_err(hdev->dev, "Error %ld on waiting for CS handle %llu\n", - rc, seq); + dev_err_ratelimited(hdev->dev, + "Error %ld on waiting for CS handle %llu\n", + rc, seq); if (rc == -ERESTARTSYS) { args->out.status = HL_WAIT_CS_STATUS_INTERRUPTED; rc = -EINTR; diff --git a/drivers/misc/habanalabs/context.c b/drivers/misc/habanalabs/context.c index 17db7b3dfb4c..2df6fb87e7ff 100644 --- a/drivers/misc/habanalabs/context.c +++ b/drivers/misc/habanalabs/context.c @@ -176,7 +176,7 @@ struct dma_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq) spin_lock(&ctx->cs_lock); if (seq >= ctx->cs_sequence) { - dev_notice(hdev->dev, + dev_notice_ratelimited(hdev->dev, "Can't wait on seq %llu because current CS is at seq %llu\n", seq, ctx->cs_sequence); spin_unlock(&ctx->cs_lock); -- cgit From 68a1fdf2451f38b4ada0607eb6e1303f8a02e0b7 Mon Sep 17 00:00:00 2001 From: Chen Wandun Date: Tue, 10 Dec 2019 19:06:56 +0800 Subject: habanalabs: remove variable 'val' set but not used Fixes gcc '-Wunused-but-set-variable' warning: drivers/misc/habanalabs/goya/goya.c: In function goya_pldm_init_cpu: drivers/misc/habanalabs/goya/goya.c:2195:6: warning: variable val set but not used [-Wunused-but-set-variable] drivers/misc/habanalabs/goya/goya.c: In function goya_hw_init: drivers/misc/habanalabs/goya/goya.c:2505:6: warning: variable val set but not used [-Wunused-but-set-variable] Fixes: 9494a8dd8d22 ("habanalabs: add h/w queues module") Signed-off-by: Chen Wandun Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index c8d16aa4382c..7344e8a222ae 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2192,7 +2192,7 @@ static int goya_push_linux_to_device(struct hl_device *hdev) static int goya_pldm_init_cpu(struct hl_device *hdev) { - u32 val, unit_rst_val; + u32 unit_rst_val; int rc; /* Must initialize SRAM scrambler before pushing u-boot to SRAM */ @@ -2200,14 +2200,14 @@ static int goya_pldm_init_cpu(struct hl_device *hdev) /* Put ARM cores into reset */ WREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL, CPU_RESET_ASSERT); - val = RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); + RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); /* Reset the CA53 MACRO */ unit_rst_val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); WREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N, CA53_RESET); - val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); + RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); WREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N, unit_rst_val); - val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); + RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); rc = goya_push_uboot_to_device(hdev); if (rc) @@ -2228,7 +2228,7 @@ static int goya_pldm_init_cpu(struct hl_device *hdev) /* Release ARM core 0 from reset */ WREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL, CPU_RESET_CORE0_DEASSERT); - val = RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); + RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); return 0; } @@ -2502,13 +2502,12 @@ err: static int goya_hw_init(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; - u32 val; int rc; dev_info(hdev->dev, "Starting initialization of H/W\n"); /* Perform read from the device to make sure device is up */ - val = RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); + RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); /* * Let's mark in the H/W that we have reached this point. We check @@ -2560,7 +2559,7 @@ static int goya_hw_init(struct hl_device *hdev) goto disable_queues; /* Perform read from the device to flush all MSI-X configuration */ - val = RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); + RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); return 0; -- cgit