From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
To: dri-devel@lists.freedesktop.org
Cc: oded.gabbay@gmail.com, quic_jhugo@quicinc.com, "Wachowski,
Karol" <karol.wachowski@intel.com>,
Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Subject: [PATCH 09/12] accel/ivpu: Add force snoop module parameter
Date: Wed, 8 May 2024 15:21:06 +0200 [thread overview]
Message-ID: <20240508132106.2387464-10-jacek.lawrynowicz@linux.intel.com> (raw)
In-Reply-To: <20240508132106.2387464-1-jacek.lawrynowicz@linux.intel.com>
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Add module parameter that enforces snooping for all NPU accesses,
both through MMU PTEs mappings and through TCU page table walk
override register bits for MMU page walks / configuration access.
Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
---
drivers/accel/ivpu/ivpu_drv.c | 4 ++++
drivers/accel/ivpu/ivpu_drv.h | 6 ++++++
drivers/accel/ivpu/ivpu_gem.h | 11 +++++++----
drivers/accel/ivpu/ivpu_hw_37xx.c | 6 +++++-
drivers/accel/ivpu/ivpu_hw_40xx.c | 6 +++++-
drivers/accel/ivpu/ivpu_mmu.c | 12 ++++++++----
6 files changed, 35 insertions(+), 10 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index ece6b212aaf8..87c48fa8d719 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -60,6 +60,10 @@ bool ivpu_disable_mmu_cont_pages;
module_param_named(disable_mmu_cont_pages, ivpu_disable_mmu_cont_pages, bool, 0644);
MODULE_PARM_DESC(disable_mmu_cont_pages, "Disable MMU contiguous pages optimization");
+bool ivpu_force_snoop;
+module_param_named(force_snoop, ivpu_force_snoop, bool, 0644);
+MODULE_PARM_DESC(force_snoop, "Force snooping for NPU host memory access");
+
struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv)
{
struct ivpu_device *vdev = file_priv->vdev;
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 0f42a3a9e59c..d55f0bdffd71 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -167,6 +167,7 @@ extern u8 ivpu_pll_min_ratio;
extern u8 ivpu_pll_max_ratio;
extern bool ivpu_sched_mode;
extern bool ivpu_disable_mmu_cont_pages;
+extern bool ivpu_force_snoop;
#define IVPU_TEST_MODE_FW_TEST BIT(0)
#define IVPU_TEST_MODE_NULL_HW BIT(1)
@@ -241,4 +242,9 @@ static inline bool ivpu_is_fpga(struct ivpu_device *vdev)
return ivpu_get_platform(vdev) == IVPU_PLATFORM_FPGA;
}
+static inline bool ivpu_is_force_snoop_enabled(struct ivpu_device *vdev)
+{
+ return ivpu_force_snoop;
+}
+
#endif /* __IVPU_DRV_H__ */
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index fb7117c13eec..d975000abd78 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -60,14 +60,17 @@ static inline u32 ivpu_bo_cache_mode(struct ivpu_bo *bo)
return bo->flags & DRM_IVPU_BO_CACHE_MASK;
}
-static inline bool ivpu_bo_is_snooped(struct ivpu_bo *bo)
+static inline struct ivpu_device *ivpu_bo_to_vdev(struct ivpu_bo *bo)
{
- return ivpu_bo_cache_mode(bo) == DRM_IVPU_BO_CACHED;
+ return to_ivpu_device(bo->base.base.dev);
}
-static inline struct ivpu_device *ivpu_bo_to_vdev(struct ivpu_bo *bo)
+static inline bool ivpu_bo_is_snooped(struct ivpu_bo *bo)
{
- return to_ivpu_device(bo->base.base.dev);
+ if (ivpu_is_force_snoop_enabled(ivpu_bo_to_vdev(bo)))
+ return true;
+
+ return ivpu_bo_cache_mode(bo) == DRM_IVPU_BO_CACHED;
}
static inline void *ivpu_to_cpu_addr(struct ivpu_bo *bo, u32 vpu_addr)
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index ce664b6515aa..250291cc1f3a 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -514,7 +514,11 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val);
val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
- val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
+
+ if (ivpu_is_force_snoop_enabled(vdev))
+ val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
+ else
+ val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val);
}
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 186cd87079c2..e64ee705d00c 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -531,7 +531,11 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val);
val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
- val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
+
+ if (ivpu_is_force_snoop_enabled(vdev))
+ val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
+ else
+ val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val);
}
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 2e46b322c450..8682e6145520 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -519,7 +519,8 @@ static int ivpu_mmu_cmdq_sync(struct ivpu_device *vdev)
if (ret)
return ret;
- clflush_cache_range(q->base, IVPU_MMU_CMDQ_SIZE);
+ if (!ivpu_is_force_snoop_enabled(vdev))
+ clflush_cache_range(q->base, IVPU_MMU_CMDQ_SIZE);
REGV_WR32(IVPU_MMU_REG_CMDQ_PROD, q->prod);
ret = ivpu_mmu_cmdq_wait_for_cons(vdev);
@@ -567,7 +568,8 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
int ret;
memset(mmu->cmdq.base, 0, IVPU_MMU_CMDQ_SIZE);
- clflush_cache_range(mmu->cmdq.base, IVPU_MMU_CMDQ_SIZE);
+ if (!ivpu_is_force_snoop_enabled(vdev))
+ clflush_cache_range(mmu->cmdq.base, IVPU_MMU_CMDQ_SIZE);
mmu->cmdq.prod = 0;
mmu->cmdq.cons = 0;
@@ -661,7 +663,8 @@ static void ivpu_mmu_strtab_link_cd(struct ivpu_device *vdev, u32 sid)
WRITE_ONCE(entry[1], str[1]);
WRITE_ONCE(entry[0], str[0]);
- clflush_cache_range(entry, IVPU_MMU_STRTAB_ENT_SIZE);
+ if (!ivpu_is_force_snoop_enabled(vdev))
+ clflush_cache_range(entry, IVPU_MMU_STRTAB_ENT_SIZE);
ivpu_dbg(vdev, MMU, "STRTAB write entry (SSID=%u): 0x%llx, 0x%llx\n", sid, str[0], str[1]);
}
@@ -735,7 +738,8 @@ static int ivpu_mmu_cd_add(struct ivpu_device *vdev, u32 ssid, u64 cd_dma)
WRITE_ONCE(entry[3], cd[3]);
WRITE_ONCE(entry[0], cd[0]);
- clflush_cache_range(entry, IVPU_MMU_CDTAB_ENT_SIZE);
+ if (!ivpu_is_force_snoop_enabled(vdev))
+ clflush_cache_range(entry, IVPU_MMU_CDTAB_ENT_SIZE);
ivpu_dbg(vdev, MMU, "CDTAB %s entry (SSID=%u, dma=%pad): 0x%llx, 0x%llx, 0x%llx, 0x%llx\n",
cd_dma ? "write" : "clear", ssid, &cd_dma, cd[0], cd[1], cd[2], cd[3]);
--
2.43.2
next prev parent reply other threads:[~2024-05-08 13:21 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-08 13:20 [PATCH 00/12] accel/ivpu: Changes for 6.10 Jacek Lawrynowicz
2024-05-08 13:20 ` [PATCH 01/12] accel/ivpu: Update VPU FW API headers Jacek Lawrynowicz
2024-05-10 16:27 ` Jeffrey Hugo
2024-05-08 13:20 ` [PATCH 02/12] accel/ivpu: Add sched_mode module param Jacek Lawrynowicz
2024-05-10 16:30 ` Jeffrey Hugo
2024-05-13 10:08 ` Jacek Lawrynowicz
2024-05-08 13:21 ` [PATCH 03/12] accel/ivpu: Create priority based command queues Jacek Lawrynowicz
2024-05-10 16:32 ` Jeffrey Hugo
2024-05-08 13:21 ` [PATCH 04/12] accel/ivpu: Implement support for preemption buffers Jacek Lawrynowicz
2024-05-10 16:36 ` Jeffrey Hugo
2024-05-08 13:21 ` [PATCH 05/12] accel/ivpu: Add HWS JSM messages Jacek Lawrynowicz
2024-05-10 16:38 ` Jeffrey Hugo
2024-05-08 13:21 ` [PATCH 06/12] accel/ivpu: Implement support for hardware scheduler Jacek Lawrynowicz
2024-05-10 16:41 ` Jeffrey Hugo
2024-05-13 10:10 ` Jacek Lawrynowicz
2024-05-08 13:21 ` [PATCH 07/12] accel/ivpu: Add resume engine support Jacek Lawrynowicz
2024-05-10 16:42 ` Jeffrey Hugo
2024-05-13 10:11 ` Jacek Lawrynowicz
2024-05-08 13:21 ` [PATCH 08/12] accel/ivpu: Add NPU profiling support Jacek Lawrynowicz
2024-05-10 16:46 ` Jeffrey Hugo
2024-05-13 10:12 ` Jacek Lawrynowicz
2024-05-08 13:21 ` Jacek Lawrynowicz [this message]
2024-05-10 16:47 ` [PATCH 09/12] accel/ivpu: Add force snoop module parameter Jeffrey Hugo
2024-05-08 13:28 ` [PATCH 10/12] accel/ivpu: Configure fw logging using debugfs Jacek Lawrynowicz
2024-05-08 13:29 ` [PATCH 11/12] accel/ivpu: Increase reset counter when warm boot fails Jacek Lawrynowicz
2024-05-10 16:49 ` Jeffrey Hugo
2024-05-08 13:29 ` [PATCH 12/12] accel/ivpu: Share NPU busy time in sysfs Jacek Lawrynowicz
2024-05-10 16:55 ` Jeffrey Hugo
2024-05-13 10:22 ` Jacek Lawrynowicz
2024-05-13 10:45 ` Tvrtko Ursulin
2024-05-13 11:39 ` Jacek Lawrynowicz
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=20240508132106.2387464-10-jacek.lawrynowicz@linux.intel.com \
--to=jacek.lawrynowicz@linux.intel.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=karol.wachowski@intel.com \
--cc=oded.gabbay@gmail.com \
--cc=quic_jhugo@quicinc.com \
/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;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).