mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Oded Gabbay <ogabbay@kernel.org>
To: dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org
Cc: Tomer Tayar <ttayar@habana.ai>
Subject: [PATCH 12/13] accel/habanalabs: keep explicit size of reserved memory for FW
Date: Tue, 20 Feb 2024 18:01:28 +0200	[thread overview]
Message-ID: <20240220160129.909714-12-ogabbay@kernel.org> (raw)
In-Reply-To: <20240220160129.909714-1-ogabbay@kernel.org>

From: Tomer Tayar <ttayar@habana.ai>

The reserved memory for FW is currently saved in an ASIC property in
units of MB, just like the value that comes from FW.
Except the fact that it is not clear from the property's name, it means
also that a calculation to actual size is required everywhere that it is
used.
Modify the property to hold the size in bytes.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/firmware_if.c | 2 +-
 drivers/accel/habanalabs/common/habanalabs.h  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/accel/habanalabs/common/firmware_if.c b/drivers/accel/habanalabs/common/firmware_if.c
index 4246162b6807..348418643709 100644
--- a/drivers/accel/habanalabs/common/firmware_if.c
+++ b/drivers/accel/habanalabs/common/firmware_if.c
@@ -2749,7 +2749,7 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
 
 	if (hdev->asic_prop.support_dynamic_resereved_fw_size)
 		hdev->asic_prop.reserved_fw_mem_size =
-				le32_to_cpu(fw_loader->dynamic_loader.comm_desc.rsvd_mem_size_mb);
+			le32_to_cpu(fw_loader->dynamic_loader.comm_desc.rsvd_mem_size_mb) * SZ_1M;
 
 	if (!(hdev->fw_components & FW_TYPE_BOOT_CPU)) {
 		struct lkd_fw_binning_info *binning_info;
diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h
index 40107a4eba93..55495861f432 100644
--- a/drivers/accel/habanalabs/common/habanalabs.h
+++ b/drivers/accel/habanalabs/common/habanalabs.h
@@ -650,7 +650,7 @@ struct hl_hints_range {
  * @glbl_err_max_cause_num: global err max cause number.
  * @hbw_flush_reg: register to read to generate HBW flush. value of 0 means HBW flush is
  *                 not supported.
- * @reserved_fw_mem_size: size in MB of dram memory reserved for FW.
+ * @reserved_fw_mem_size: size of dram memory reserved for FW.
  * @collective_first_sob: first sync object available for collective use
  * @collective_first_mon: first monitor available for collective use
  * @sync_stream_first_sob: first sync object available for sync stream use
-- 
2.34.1


  parent reply	other threads:[~2024-02-20 16:01 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-20 16:01 [PATCH 01/13] accel/habanalabs/gaudi2: use single function to compare FW versions Oded Gabbay
2024-02-20 16:01 ` [PATCH 02/13] accel/habanalabs: remove hop size from asic properties Oded Gabbay
2024-02-23 22:42   ` Carl Vanderlip
2024-02-20 16:01 ` [PATCH 03/13] accel/habanalabs: modify print for skip loading linux FW to debug log Oded Gabbay
2024-02-23 22:45   ` Carl Vanderlip
2024-02-20 16:01 ` [PATCH 04/13] accel/habanalabs/gaudi2: check extended errors according to PCIe addr_dec interrupt info Oded Gabbay
2024-02-23 22:49   ` Carl Vanderlip
2024-02-20 16:01 ` [PATCH 05/13] accel/habanalabs: fix glbl error cause handling Oded Gabbay
2024-02-23 23:01   ` Carl Vanderlip
2024-02-20 16:01 ` [PATCH 06/13] accel/habanalabs: fix debugfs files permissions Oded Gabbay
2024-02-23 23:10   ` Carl Vanderlip
2024-02-20 16:01 ` [PATCH 07/13] accel/habanalabs: initialize maybe-uninitialized variables Oded Gabbay
2024-02-23 23:12   ` Carl Vanderlip
2024-02-20 16:01 ` [PATCH 08/13] accel/habanalabs: fix error print Oded Gabbay
2024-02-23 23:15   ` Carl Vanderlip
2024-02-20 16:01 ` [PATCH 09/13] accel/habanalabs/gaudi2: drain event lacks rd/wr indication Oded Gabbay
2024-02-23 23:17   ` Carl Vanderlip
2024-02-20 16:01 ` [PATCH 10/13] accel/habanalabs/hwmon: rate limit errors user can generate Oded Gabbay
2024-02-23 23:21   ` Carl Vanderlip
2024-02-20 16:01 ` [PATCH 11/13] accel/habanalabs: handle reserved memory request when working with full FW Oded Gabbay
2024-02-23 23:24   ` Carl Vanderlip
2024-02-20 16:01 ` Oded Gabbay [this message]
2024-02-23 23:26   ` [PATCH 12/13] accel/habanalabs: keep explicit size of reserved memory for FW Carl Vanderlip
2024-02-20 16:01 ` [PATCH 13/13] accel/habanalabs: modify pci health check Oded Gabbay
2024-02-23 23:32   ` Carl Vanderlip
2024-02-24 19:20     ` Ofir Bitton
2024-02-23 22:38 ` [PATCH 01/13] accel/habanalabs/gaudi2: use single function to compare FW versions Carl Vanderlip
2024-02-25 10:36   ` Ohad Sharabi

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=20240220160129.909714-12-ogabbay@kernel.org \
    --to=ogabbay@kernel.org \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ttayar@habana.ai \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome