Although the possible values for CB's ID are only 32 bits, there are a few
places in the code where this field is shifted and passed into a function
which expects 64 bits.
Reported-by: kernel test robot <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
---
drivers/misc/habanalabs/common/command_buffer.c | 2 +-
drivers/misc/habanalabs/common/debugfs.c | 2 +-
drivers/misc/habanalabs/common/habanalabs.h | 4 ++--
3 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index 7c38c4f7f9c0..33aee64f37aa 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -173,7 +173,7 @@ int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
goto release_cb;
}
- cb->id = rc;
+ cb->id = (u64) rc;
kref_init(&cb->refcount);
spin_lock_init(&cb->lock);
diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
index c50c6fc9e905..25775b12139b 100644
--- a/drivers/misc/habanalabs/common/debugfs.c
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -110,7 +110,7 @@ static int command_buffers_show(struct seq_file *s, void *data)
seq_puts(s, "---------------------------------------------------------------\n");
}
seq_printf(s,
- " %03d %d 0x%08x %d %d %d\n",
+ " %03llu %d 0x%08x %d %d %d\n",
cb->id, cb->ctx_id, cb->size,
kref_read(&cb->refcount),
cb->mmap, cb->cs_cnt);
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 52a07c8d7d7c..2decf7be3e08 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -401,11 +401,11 @@ struct hl_cb_mgr {
* @lock: spinlock to protect mmap/cs flows.
* @debugfs_list: node in debugfs list of command buffers.
* @pool_list: node in pool list of command buffers.
+ * @id: the CB's ID.
* @kernel_address: Holds the CB's kernel virtual address.
* @bus_address: Holds the CB's DMA address.
* @mmap_size: Holds the CB's size that was mmaped.
* @size: holds the CB's size.
- * @id: the CB's ID.
* @cs_cnt: holds number of CS that this CB participates in.
* @ctx_id: holds the ID of the owner's context.
* @mmap: true if the CB is currently mmaped to user.
@@ -418,11 +418,11 @@ struct hl_cb {
spinlock_t lock;
struct list_head debugfs_list;
struct list_head pool_list;
+ u64 id;
u64 kernel_address;
dma_addr_t bus_address;
u32 mmap_size;
u32 size;
- u32 id;
u32 cs_cnt;
u32 ctx_id;
u8 mmap;
--
2.17.1
From: farah kassabri <[email protected]>
change busy engines bitmask to 64 bits in order to represent
more engines, needed for future ASIC support.
Signed-off-by: farah kassabri <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
---
drivers/misc/habanalabs/common/habanalabs.h | 2 +-
drivers/misc/habanalabs/common/habanalabs_ioctl.c | 2 +-
drivers/misc/habanalabs/gaudi/gaudi.c | 2 +-
drivers/misc/habanalabs/goya/goya.c | 2 +-
include/uapi/misc/habanalabs.h | 6 ++++++
5 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 2decf7be3e08..dbf214421ae1 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -754,7 +754,7 @@ struct hl_asic_funcs {
void (*set_clock_gating)(struct hl_device *hdev);
void (*disable_clock_gating)(struct hl_device *hdev);
int (*debug_coresight)(struct hl_device *hdev, void *data);
- bool (*is_device_idle)(struct hl_device *hdev, u32 *mask,
+ bool (*is_device_idle)(struct hl_device *hdev, u64 *mask,
struct seq_file *s);
int (*soft_reset_late_init)(struct hl_device *hdev);
void (*hw_queues_lock)(struct hl_device *hdev);
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index fe6c5534d378..a94800014243 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -132,7 +132,7 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args)
return -EINVAL;
hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev,
- &hw_idle.busy_engines_mask, NULL);
+ &hw_idle.busy_engines_mask_ext, NULL);
return copy_to_user(out, &hw_idle,
min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0;
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 3360c3c207a9..e56f95e6c741 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -6041,7 +6041,7 @@ static int gaudi_armcp_info_get(struct hl_device *hdev)
return 0;
}
-static bool gaudi_is_device_idle(struct hl_device *hdev, u32 *mask,
+static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask,
struct seq_file *s)
{
struct gaudi_device *gaudi = hdev->asic_specific;
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 77a5963a4d10..021cd26fb018 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -5117,7 +5117,7 @@ static void goya_disable_clock_gating(struct hl_device *hdev)
/* clock gating not supported in Goya */
}
-static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask,
+static bool goya_is_device_idle(struct hl_device *hdev, u64 *mask,
struct seq_file *s)
{
const char *fmt = "%-5d%-9s%#-14x%#-16x%#x\n";
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index ca6dc1fc250e..693081728ef3 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -319,6 +319,12 @@ struct hl_info_hw_idle {
* Bits definition is according to `enum <chip>_enging_id'.
*/
__u32 busy_engines_mask;
+
+ /*
+ * Extended Bitmask of busy engines.
+ * Bits definition is according to `enum <chip>_enging_id'.
+ */
+ __u64 busy_engines_mask_ext;
};
struct hl_info_device_status {
--
2.17.1
The driver waits for the TPC vector pipe to be empty before checking if the
TPC kernel has finished executing, but the code doesn't validate that the
pipe was indeed empty, it just wait for it without checking the return
value.
Reported-by: kernel test robot <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
---
drivers/misc/habanalabs/gaudi/gaudi.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index ffd0849e8f2d..3360c3c207a9 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -6262,6 +6262,15 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel,
1000,
kernel_timeout);
+ if (rc) {
+ dev_err(hdev->dev,
+ "Timeout while waiting for TPC%d vector pipe\n",
+ tpc_id);
+ hdev->asic_funcs->set_clock_gating(hdev);
+ mutex_unlock(&gaudi->clk_gate_mutex);
+ return -EIO;
+ }
+
rc = hl_poll_timeout(
hdev,
mmTPC0_CFG_WQ_INFLIGHT_CNTR + offset,
--
2.17.1
new_dma_pkt->ctl is assigned a value and then is reassigned a new value
without the first value ever being used.
Reported-by: kernel test robot <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
---
drivers/misc/habanalabs/gaudi/gaudi.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index ed289a6ed622..ffd0849e8f2d 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -3944,8 +3944,6 @@ static int gaudi_patch_dma_packet(struct hl_device *hdev,
}
}
- new_dma_pkt->ctl = user_dma_pkt->ctl;
-
ctl = le32_to_cpu(user_dma_pkt->ctl);
if (likely(dma_desc_cnt))
ctl &= ~GAUDI_PKT_CTL_EB_MASK;
--
2.17.1
On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <[email protected]> wrote:
> Although the possible values for CB's ID are only 32 bits, there are a few
> places in the code where this field is shifted and passed into a function
> which expects 64 bits.
>
> Reported-by: kernel test robot <[email protected]>
> Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Tomer Tayar <[email protected]>
On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <[email protected]> wrote:
> new_dma_pkt->ctl is assigned a value and then is reassigned a new value
> without the first value ever being used.
>
> Reported-by: kernel test robot <[email protected]>
> Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Tomer Tayar <[email protected]>
On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <[email protected]> wrote:
> The driver waits for the TPC vector pipe to be empty before checking if the
> TPC kernel has finished executing, but the code doesn't validate that the
> pipe was indeed empty, it just wait for it without checking the return
> value.
>
> Reported-by: kernel test robot <[email protected]>
> Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Tomer Tayar <[email protected]>