renegade-project/linux-snapdragon
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

habanalabs: add "in device creation" status

Browse Source 
[ Upstream commit 71731090ab17a208a58020e4b342fdfee280458a ]

On init, the disabled state is cleared right before hw_init and that
causes the device to report on "Operational" state before the device
initialization is finished. Although the char device is not yet exposed
to the user at this stage, the sysfs entries are exposed.

This can cause errors in monitoring applications that use the sysfs
entries.

In order to avoid this, a new state "in device creation" is introduced
to ne reported when the device is not disabled but is still in init
flow.

Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Omer Shpigelman 2021-08-16 13:27:12 +03:00 committed by Greg Kroah-Hartman
parent 836c080650
commit f621eeead8
5 changed files with 20 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
drivers/misc/habanalabs/common/device.c
View File

@ -23,6 +23,8 @@ enum hl_device_status hl_device_status(struct hl_device *hdev)
status = HL_DEVICE_STATUS_NEEDS_RESET;
else if (hdev->disabled)
status = HL_DEVICE_STATUS_MALFUNCTION;
else if (!hdev->init_done)
status = HL_DEVICE_STATUS_IN_DEVICE_CREATION;
else
status = HL_DEVICE_STATUS_OPERATIONAL;
@ -44,6 +46,7 @@ bool hl_device_operational(struct hl_device *hdev,
case HL_DEVICE_STATUS_NEEDS_RESET:
return false;
case HL_DEVICE_STATUS_OPERATIONAL:
case HL_DEVICE_STATUS_IN_DEVICE_CREATION:
default:
return true;
}

2
drivers/misc/habanalabs/common/habanalabs.h
View File

@ -1798,7 +1798,7 @@ struct hl_dbg_device_entry {
#define HL_STR_MAX 32
#define HL_DEV_STS_MAX (HL_DEVICE_STATUS_NEEDS_RESET + 1)
#define HL_DEV_STS_MAX (HL_DEVICE_STATUS_LAST + 1)
/* Theoretical limit only. A single host can only contain up to 4 or 8 PCIe
* x16 cards. In extreme cases, there are hosts that can accommodate 16 cards.

8
drivers/misc/habanalabs/common/habanalabs_drv.c
View File

@ -318,12 +318,16 @@ int create_hdev(struct hl_device **dev, struct pci_dev *pdev,
hdev->asic_prop.fw_security_enabled = false;
/* Assign status description string */
strncpy(hdev->status[HL_DEVICE_STATUS_MALFUNCTION],
"disabled", HL_STR_MAX);
strncpy(hdev->status[HL_DEVICE_STATUS_OPERATIONAL],
"operational", HL_STR_MAX);
strncpy(hdev->status[HL_DEVICE_STATUS_IN_RESET],
"in reset", HL_STR_MAX);
strncpy(hdev->status[HL_DEVICE_STATUS_MALFUNCTION],
"disabled", HL_STR_MAX);
strncpy(hdev->status[HL_DEVICE_STATUS_NEEDS_RESET],
"needs reset", HL_STR_MAX);
strncpy(hdev->status[HL_DEVICE_STATUS_IN_DEVICE_CREATION],
"in device creation", HL_STR_MAX);
hdev->major = hl_major;
hdev->reset_on_lockup = reset_on_lockup;

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

@ -9,8 +9,7 @@
#include <linux/pci.h>
long hl_get_frequency(struct hl_device *hdev, u32 pll_index,
bool curr)
long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr)
{
struct cpucp_packet pkt;
u32 used_pll_idx;
@ -44,8 +43,7 @@ long hl_get_frequency(struct hl_device *hdev, u32 pll_index,
return (long) result;
}
void hl_set_frequency(struct hl_device *hdev, u32 pll_index,
u64 freq)
void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq)
{
struct cpucp_packet pkt;
u32 used_pll_idx;
@ -285,16 +283,12 @@ static ssize_t status_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct hl_device *hdev = dev_get_drvdata(dev);
char *str;
char str[HL_STR_MAX];
if (atomic_read(&hdev->in_reset))
str = "In reset";
else if (hdev->disabled)
str = "Malfunction";
else if (hdev->needs_reset)
str = "Needs Reset";
else
str = "Operational";
strscpy(str, hdev->status[hl_device_status(hdev)], HL_STR_MAX);
/* use uppercase for backward compatibility */
str[0] = 'A' + (str[0] - 'a');
return sprintf(buf, "%s\n", str);
}

4
include/uapi/misc/habanalabs.h
View File

@ -276,7 +276,9 @@ enum hl_device_status {
HL_DEVICE_STATUS_OPERATIONAL,
HL_DEVICE_STATUS_IN_RESET,
HL_DEVICE_STATUS_MALFUNCTION,
HL_DEVICE_STATUS_NEEDS_RESET
HL_DEVICE_STATUS_NEEDS_RESET,
HL_DEVICE_STATUS_IN_DEVICE_CREATION,
HL_DEVICE_STATUS_LAST = HL_DEVICE_STATUS_IN_DEVICE_CREATION
};
/* Opcode for management ioctl