From: Oded Gabbay <ogabbay@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Koby Elbaz <kelbaz@habana.ai>
Subject: [PATCH 2/3] habanalabs: clear msg_to_cpu_reg to avoid misread after reset
Date: Thu, 22 Jul 2021 14:16:42 +0300 [thread overview]
Message-ID: <20210722111643.17568-2-ogabbay@kernel.org> (raw)
In-Reply-To: <20210722111643.17568-1-ogabbay@kernel.org>
From: Koby Elbaz <kelbaz@habana.ai>
For some ASICs, the f/w reads the msg_to_cpu_reg value after
reset, and for some it doesn't.
Therefore, to be sure f/w doesn't read a wrong value after reset, we
need to clear this register before the reset occurs.
Signed-off-by: Koby Elbaz <kelbaz@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/misc/habanalabs/common/firmware_if.c | 28 +++++++++-----------
1 file changed, 12 insertions(+), 16 deletions(-)
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 0be3f5414f0b..c232d197b57a 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -667,17 +667,15 @@ int hl_fw_cpucp_info_get(struct hl_device *hdev,
hdev->event_queue.check_eqe_index = false;
/* Read FW application security bits again */
- if (hdev->asic_prop.fw_cpu_boot_dev_sts0_valid) {
- hdev->asic_prop.fw_app_cpu_boot_dev_sts0 =
- RREG32(sts_boot_dev_sts0_reg);
- if (hdev->asic_prop.fw_app_cpu_boot_dev_sts0 &
+ if (prop->fw_cpu_boot_dev_sts0_valid) {
+ prop->fw_app_cpu_boot_dev_sts0 = RREG32(sts_boot_dev_sts0_reg);
+ if (prop->fw_app_cpu_boot_dev_sts0 &
CPU_BOOT_DEV_STS0_EQ_INDEX_EN)
hdev->event_queue.check_eqe_index = true;
}
- if (hdev->asic_prop.fw_cpu_boot_dev_sts1_valid)
- hdev->asic_prop.fw_app_cpu_boot_dev_sts1 =
- RREG32(sts_boot_dev_sts1_reg);
+ if (prop->fw_cpu_boot_dev_sts1_valid)
+ prop->fw_app_cpu_boot_dev_sts1 = RREG32(sts_boot_dev_sts1_reg);
out:
hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
@@ -1012,6 +1010,11 @@ void hl_fw_ask_halt_machine_without_linux(struct hl_device *hdev)
} else {
WREG32(static_loader->kmd_msg_to_cpu_reg, KMD_MSG_GOTO_WFE);
msleep(static_loader->cpu_reset_wait_msec);
+
+ /* Must clear this register in order to prevent preboot
+ * from reading WFE after reboot
+ */
+ WREG32(static_loader->kmd_msg_to_cpu_reg, KMD_MSG_NA);
}
hdev->device_cpu_is_halted = true;
@@ -1242,11 +1245,6 @@ static void hl_fw_preboot_update_state(struct hl_device *hdev)
* b. Check whether hard reset is done by boot cpu
* 3. FW application - a. Fetch fw application security status
* b. Check whether hard reset is done by fw app
- *
- * Preboot:
- * Check security status bit (CPU_BOOT_DEV_STS0_ENABLED). If set, then-
- * check security enabled bit (CPU_BOOT_DEV_STS0_SECURITY_EN)
- * If set, then mark GIC controller to be disabled.
*/
prop->hard_reset_done_by_fw =
!!(cpu_boot_dev_sts0 & CPU_BOOT_DEV_STS0_FW_HARD_RST_EN);
@@ -2126,8 +2124,7 @@ static void hl_fw_linux_update_state(struct hl_device *hdev,
/* Read FW application security bits */
if (prop->fw_cpu_boot_dev_sts0_valid) {
- prop->fw_app_cpu_boot_dev_sts0 =
- RREG32(cpu_boot_dev_sts0_reg);
+ prop->fw_app_cpu_boot_dev_sts0 = RREG32(cpu_boot_dev_sts0_reg);
if (prop->fw_app_cpu_boot_dev_sts0 &
CPU_BOOT_DEV_STS0_FW_HARD_RST_EN)
@@ -2147,8 +2144,7 @@ static void hl_fw_linux_update_state(struct hl_device *hdev,
}
if (prop->fw_cpu_boot_dev_sts1_valid) {
- prop->fw_app_cpu_boot_dev_sts1 =
- RREG32(cpu_boot_dev_sts1_reg);
+ prop->fw_app_cpu_boot_dev_sts1 = RREG32(cpu_boot_dev_sts1_reg);
dev_dbg(hdev->dev,
"Firmware application CPU status1 %#x\n",
--
2.25.1
next prev parent reply other threads:[~2021-07-22 11:16 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-22 11:16 [PATCH 1/3] habanalabs: make set_pci_regions asic function Oded Gabbay
2021-07-22 11:16 ` Oded Gabbay [this message]
2021-07-22 11:16 ` [PATCH 3/3] habanalabs: add validity check for event ID received from F/W Oded Gabbay
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210722111643.17568-2-ogabbay@kernel.org \
--to=ogabbay@kernel.org \
--cc=kelbaz@habana.ai \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.