leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

habanalabs: reset device upon FD close if not idle

Browse Source 
If device is not idle after user closes the FD we must reset device
as next user that will try to open FD will encounter a non-functional
device.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This commit is contained in:
Ofir Bitton 2021-05-20 13:30:31 +03:00 committed by Oded Gabbay
parent 8e8125f192
commit 84586de496
4 changed files with 19 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
drivers/misc/habanalabs/common/context.c
View File

@ -12,7 +12,6 @@
static void hl_ctx_fini(struct hl_ctx *ctx)
{
struct hl_device *hdev = ctx->hdev;
u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0};
int i;
/* Release all allocated pending cb's, those cb's were never
@ -57,14 +56,6 @@ static void hl_ctx_fini(struct hl_ctx *ctx)
/* Scrub both SRAM and DRAM */
hdev->asic_funcs->scrub_device_mem(hdev, 0, 0);
if ((!hdev->pldm) && (hdev->pdev) &&
(!hdev->asic_funcs->is_device_idle(hdev,
idle_mask,
HL_BUSY_ENGINES_MASK_EXT_SIZE, NULL)))
dev_notice(hdev->dev,
"device not idle after user context is closed (0x%llx, 0x%llx)\n",
idle_mask[0], idle_mask[1]);
} else {
dev_dbg(hdev->dev, "closing kernel context\n");
hdev->asic_funcs->ctx_fini(ctx);

20
drivers/misc/habanalabs/common/device.c
View File

@ -51,6 +51,8 @@ bool hl_device_operational(struct hl_device *hdev,
static void hpriv_release(struct kref *ref)
{
u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0};
bool device_is_idle = true;
struct hl_fpriv *hpriv;
struct hl_device *hdev;
@ -71,7 +73,19 @@ static void hpriv_release(struct kref *ref)
kfree(hpriv);
if (hdev->reset_upon_device_release)
if ((!hdev->pldm) && (hdev->pdev) &&
(!hdev->asic_funcs->is_device_idle(hdev,
idle_mask,
HL_BUSY_ENGINES_MASK_EXT_SIZE, NULL))) {
dev_err(hdev->dev,
"device not idle after user context is closed (0x%llx_%llx)\n",
idle_mask[1], idle_mask[0]);
device_is_idle = false;
}
if ((hdev->reset_if_device_not_idle && !device_is_idle)
|| hdev->reset_upon_device_release)
hl_device_reset(hdev, 0);
}
@ -1108,8 +1122,8 @@ kill_processes:
if (!hdev->asic_funcs->is_device_idle(hdev, idle_mask,
HL_BUSY_ENGINES_MASK_EXT_SIZE, NULL)) {
dev_err(hdev->dev,
"device is not idle (mask %#llx %#llx) after reset\n",
idle_mask[0], idle_mask[1]);
"device is not idle (mask 0x%llx_%llx) after reset\n",
idle_mask[1], idle_mask[0]);
rc = -EIO;
goto out_err;
}

1
drivers/misc/habanalabs/common/habanalabs.h
View File

@ -2311,6 +2311,7 @@ struct hl_device {
u8 rl_enable;
u8 reset_on_preboot_fail;
u8 reset_upon_device_release;
u8 reset_if_device_not_idle;
};

1
drivers/misc/habanalabs/common/habanalabs_drv.c
View File

@ -264,6 +264,7 @@ static void set_driver_behavior_per_device(struct hl_device *hdev)
hdev->bmc_enable = 1;
hdev->hard_reset_on_fw_events = 1;
hdev->reset_on_preboot_fail = 1;
hdev->reset_if_device_not_idle = 1;
hdev->reset_pcilink = 0;
hdev->axi_drain = 0;