From: Oded Gabbay <ogabbay@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: SW_Drivers@habana.ai, Moti Haimovski <mhaimovski@habana.ai>
Subject: [PATCH] habanalabs: share a single ctx-mutex between all MMUs
Date: Sat, 14 Nov 2020 11:24:13 +0200 [thread overview]
Message-ID: <20201114092414.12244-3-ogabbay@kernel.org> (raw)
In-Reply-To: <20201114092414.12244-1-ogabbay@kernel.org>
From: Moti Haimovski <mhaimovski@habana.ai>
Multiple locks are usually a source of problems, which in the MMU
case can be avoided since it is relatively rare that both MMU
tables are updated at the same time.
Therefore, use a single shared lock instead of two separate ones.
Signed-off-by: Moti Haimovski <mhaimovski@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/misc/habanalabs/common/mmu.c | 4 ++++
drivers/misc/habanalabs/common/mmu_v1.c | 4 ----
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/misc/habanalabs/common/mmu.c b/drivers/misc/habanalabs/common/mmu.c
index 6f535c81478d..f4b3d02fe0d8 100644
--- a/drivers/misc/habanalabs/common/mmu.c
+++ b/drivers/misc/habanalabs/common/mmu.c
@@ -81,6 +81,8 @@ int hl_mmu_ctx_init(struct hl_ctx *ctx)
if (!hdev->mmu_enable)
return 0;
+ mutex_init(&ctx->mmu_lock);
+
if (hdev->mmu_func[MMU_DR_PGT].ctx_init != NULL) {
rc = hdev->mmu_func[MMU_DR_PGT].ctx_init(ctx);
if (rc)
@@ -115,6 +117,8 @@ void hl_mmu_ctx_fini(struct hl_ctx *ctx)
if (hdev->mmu_func[MMU_HR_PGT].ctx_fini != NULL)
hdev->mmu_func[MMU_HR_PGT].ctx_fini(ctx);
+
+ mutex_destroy(&ctx->mmu_lock);
}
/*
diff --git a/drivers/misc/habanalabs/common/mmu_v1.c b/drivers/misc/habanalabs/common/mmu_v1.c
index 5f62cb158eef..92b22298bb5c 100644
--- a/drivers/misc/habanalabs/common/mmu_v1.c
+++ b/drivers/misc/habanalabs/common/mmu_v1.c
@@ -481,9 +481,7 @@ static void hl_mmu_v1_fini(struct hl_device *hdev)
*/
static int hl_mmu_v1_ctx_init(struct hl_ctx *ctx)
{
- mutex_init(&ctx->mmu_lock);
hash_init(ctx->mmu_shadow_hash);
-
return dram_default_mapping_init(ctx);
}
@@ -516,8 +514,6 @@ static void hl_mmu_v1_ctx_fini(struct hl_ctx *ctx)
pgt_info->phys_addr, ctx->asid, pgt_info->num_of_ptes);
_free_hop(ctx, pgt_info);
}
-
- mutex_destroy(&ctx->mmu_lock);
}
static int _hl_mmu_v1_unmap(struct hl_ctx *ctx,
--
2.17.1
next prev parent reply other threads:[~2020-11-14 9:25 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-14 9:24 [PATCH] habanalabs: add boot errors prints Oded Gabbay
2020-11-14 9:24 ` [PATCH] habanalabs: fix MMU debugfs operations Oded Gabbay
2020-11-14 9:24 ` Oded Gabbay [this message]
2020-11-14 9:24 ` [PATCH] habanalabs: support reserving aligned va block 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=20201114092414.12244-3-ogabbay@kernel.org \
--to=ogabbay@kernel.org \
--cc=SW_Drivers@habana.ai \
--cc=linux-kernel@vger.kernel.org \
--cc=mhaimovski@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