[PATCHv5 0/6] System Cache support for GPU and required SMMU support

[PATCHv5 0/6] System Cache support for GPU and required SMMU support

[Sai Prakash Ranjan]

Some hardware variants contain a system cache or the last level
cache(llc). This cache is typically a large block which is shared
by multiple clients on the SOC. GPU uses the system cache to cache
both the GPU data buffers(like textures) as well the SMMU pagetables.
This helps with improved render performance as well as lower power
consumption by reducing the bus traffic to the system memory.

The system cache architecture allows the cache to be split into slices
which then be used by multiple SOC clients. This patch series is an
effort to enable and use two of those slices perallocated for the GPU,
one for the GPU data buffers and another for the GPU SMMU hardware
pagetables.

Patch 1 - Patch 4 adds system cache support in SMMU and GPU driver.
Patch 5 and 6 are minor cleanups for arm-smmu impl.

The series is based on top of https://gitlab.freedesktop.org/drm/msm/-/tree/msm-next-pgtables

Changes in v5:
 * Drop cleanup of blank lines since it was intentional (Robin)
 * Rebase again on top of msm-next-pgtables as it moves pretty fast

Changes in v4:
 * Drop IOMMU_SYS_CACHE prot flag
 * Rebase on top of https://gitlab.freedesktop.org/drm/msm/-/tree/msm-next-pgtables

Changes in v3:
 * Fix domain attribute setting to before iommu_attach_device()
 * Fix few code style and checkpatch warnings
 * Rebase on top of Jordan's latest split pagetables and per-instance
   pagetables support

Changes in v2:
 * Addressed review comments and rebased on top of Jordan's split
   pagetables series

Sai Prakash Ranjan (4):
  iommu/io-pgtable-arm: Add support to use system cache
  iommu/arm-smmu: Add domain attribute for system cache
  iommu: arm-smmu-impl: Use table to list QCOM implementations
  iommu: arm-smmu-impl: Add a space before open parenthesis

Sharat Masetty (2):
  drm/msm: rearrange the gpu_rmw() function
  drm/msm/a6xx: Add support for using system cache(LLC)

 drivers/gpu/drm/msm/adreno/a6xx_gpu.c      | 83 ++++++++++++++++++++++
 drivers/gpu/drm/msm/adreno/a6xx_gpu.h      |  4 ++
 drivers/gpu/drm/msm/adreno/adreno_gpu.c    | 17 +++++
 drivers/gpu/drm/msm/msm_drv.c              |  8 +++
 drivers/gpu/drm/msm/msm_drv.h              |  1 +
 drivers/gpu/drm/msm/msm_gpu.h              |  5 +-
 drivers/iommu/arm/arm-smmu/arm-smmu-impl.c | 14 ++--
 drivers/iommu/arm/arm-smmu/arm-smmu.c      | 17 +++++
 drivers/iommu/arm/arm-smmu/arm-smmu.h      |  1 +
 drivers/iommu/io-pgtable-arm.c             |  7 +-
 include/linux/io-pgtable.h                 |  4 ++
 include/linux/iommu.h                      |  1 +
 12 files changed, 152 insertions(+), 10 deletions(-)


base-commit: 115b1aca7a2a9c0649b1f5f6cffee6873c7efd89
-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation

[PATCHv5 1/6] iommu/io-pgtable-arm: Add support to use system cache

[Sai Prakash Ranjan]

Add a quirk IO_PGTABLE_QUIRK_SYS_CACHE to override the
attributes set in TCR for the page table walker when
using system cache.

Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
---
 drivers/iommu/io-pgtable-arm.c | 7 ++++++-
 include/linux/io-pgtable.h     | 4 ++++
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index dc7bcf858b6d..828426c16fa9 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -789,7 +789,8 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NON_STRICT |
-			    IO_PGTABLE_QUIRK_ARM_TTBR1))
+			    IO_PGTABLE_QUIRK_ARM_TTBR1 |
+			    IO_PGTABLE_QUIRK_SYS_CACHE))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
@@ -801,6 +802,10 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 		tcr->sh = ARM_LPAE_TCR_SH_IS;
 		tcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
 		tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
+	} else if (cfg->quirks & IO_PGTABLE_QUIRK_SYS_CACHE) {
+		tcr->sh = ARM_LPAE_TCR_SH_OS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_NC;
+		tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
 	} else {
 		tcr->sh = ARM_LPAE_TCR_SH_OS;
 		tcr->irgn = ARM_LPAE_TCR_RGN_NC;
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 23285ba645db..ecc9d2248b84 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -86,6 +86,9 @@ struct io_pgtable_cfg {
 	 *
 	 * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table
 	 *	for use in the upper half of a split address space.
+	 *
+	 * IO_PGTABLE_QUIRK_SYS_CACHE: Override the attributes set in TCR for
+	 *	the page table walker when using system cache.
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
@@ -93,6 +96,7 @@ struct io_pgtable_cfg {
 	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT	BIT(3)
 	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(4)
 	#define IO_PGTABLE_QUIRK_ARM_TTBR1	BIT(5)
+	#define IO_PGTABLE_QUIRK_SYS_CACHE	BIT(6)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;
-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation

[PATCHv5 2/6] iommu/arm-smmu: Add domain attribute for system cache

[Sai Prakash Ranjan]

Add iommu domain attribute for using system cache aka last level
cache by client drivers like GPU to set right attributes for caching
the hardware pagetables into the system cache.

Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu.c | 17 +++++++++++++++++
 drivers/iommu/arm/arm-smmu/arm-smmu.h |  1 +
 include/linux/iommu.h                 |  1 +
 3 files changed, 19 insertions(+)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 1f06ab219819..d449c895ba16 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -789,6 +789,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (smmu_domain->non_strict)
 		pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
 
+	if (smmu_domain->sys_cache)
+		pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_SYS_CACHE;
+
 	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
 	if (!pgtbl_ops) {
 		ret = -ENOMEM;
@@ -1513,6 +1516,9 @@ static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
 		case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
 			*(int *)data = smmu_domain->non_strict;
 			return 0;
+		case DOMAIN_ATTR_SYS_CACHE:
+			*((int *)data) = smmu_domain->sys_cache;
+			return 0;
 		default:
 			return -ENODEV;
 		}
@@ -1544,6 +1550,17 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
 			else
 				smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
 			break;
+		case DOMAIN_ATTR_SYS_CACHE:
+			if (smmu_domain->smmu) {
+				ret = -EPERM;
+				goto out_unlock;
+			}
+
+			if (*((int *)data))
+				smmu_domain->sys_cache = true;
+			else
+				smmu_domain->sys_cache = false;
+			break;
 		default:
 			ret = -ENODEV;
 		}
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index ddf2ca4c923d..93593e164e44 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -373,6 +373,7 @@ struct arm_smmu_domain {
 	struct mutex			init_mutex; /* Protects smmu pointer */
 	spinlock_t			cb_lock; /* Serialises ATS1* ops and TLB syncs */
 	struct iommu_domain		domain;
+	bool				sys_cache;
 };
 
 struct arm_smmu_master_cfg {
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index fee209efb756..a580dfe9c68d 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -118,6 +118,7 @@ enum iommu_attr {
 	DOMAIN_ATTR_FSL_PAMUV1,
 	DOMAIN_ATTR_NESTING,	/* two stages of translation */
 	DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
+	DOMAIN_ATTR_SYS_CACHE,
 	DOMAIN_ATTR_MAX,
 };
 
-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation

[PATCHv5 3/6] drm/msm: rearrange the gpu_rmw() function

[Sai Prakash Ranjan]

From: Sharat Masetty <smasetty@codeaurora.org>

The register read-modify-write construct is generic enough
that it can be used by other subsystems as needed, create
a more generic rmw() function and have the gpu_rmw() use
this new function.

Signed-off-by: Sharat Masetty <smasetty@codeaurora.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
---
 drivers/gpu/drm/msm/msm_drv.c | 8 ++++++++
 drivers/gpu/drm/msm/msm_drv.h | 1 +
 drivers/gpu/drm/msm/msm_gpu.h | 5 +----
 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 49685571dc0e..a1e22b974b77 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -180,6 +180,14 @@ u32 msm_readl(const void __iomem *addr)
 	return val;
 }
 
+void msm_rmw(void __iomem *addr, u32 mask, u32 or)
+{
+	u32 val = msm_readl(addr);
+
+	val &= ~mask;
+	msm_writel(val | or, addr);
+}
+
 struct msm_vblank_work {
 	struct work_struct work;
 	int crtc_id;
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 319327462b29..079e33680a6c 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -474,6 +474,7 @@ void __iomem *msm_ioremap_quiet(struct platform_device *pdev, const char *name,
 		const char *dbgname);
 void msm_writel(u32 data, void __iomem *addr);
 u32 msm_readl(const void __iomem *addr);
+void msm_rmw(void __iomem *addr, u32 mask, u32 or);
 
 struct msm_gpu_submitqueue;
 int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 6c9e1fdc1a76..b2b419277953 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -246,10 +246,7 @@ static inline u32 gpu_read(struct msm_gpu *gpu, u32 reg)
 
 static inline void gpu_rmw(struct msm_gpu *gpu, u32 reg, u32 mask, u32 or)
 {
-	uint32_t val = gpu_read(gpu, reg);
-
-	val &= ~mask;
-	gpu_write(gpu, reg, val | or);
+	msm_rmw(gpu->mmio + (reg << 2), mask, or);
 }
 
 static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi)
-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation

[PATCHv5 4/6] drm/msm/a6xx: Add support for using system cache(LLC)

[Sai Prakash Ranjan]

From: Sharat Masetty <smasetty@codeaurora.org>

The last level system cache can be partitioned to 32 different
slices of which GPU has two slices preallocated. One slice is
used for caching GPU buffers and the other slice is used for
caching the GPU SMMU pagetables. This talks to the core system
cache driver to acquire the slice handles, configure the SCID's
to those slices and activates and deactivates the slices upon
GPU power collapse and restore.

Some support from the IOMMU driver is also needed to make use
of the system cache to set the right TCR attributes. GPU then
has the ability to override a few cacheability parameters which
it does to override write-allocate to write-no-allocate as the
GPU hardware does not benefit much from it.

DOMAIN_ATTR_SYS_CACHE is another domain level attribute used by the
IOMMU driver to set the right attributes to cache the hardware
pagetables into the system cache.

Signed-off-by: Sharat Masetty <smasetty@codeaurora.org>
[saiprakash.ranjan: fix to set attr before device attach to iommu and rebase]
Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c   | 83 +++++++++++++++++++++++++
 drivers/gpu/drm/msm/adreno/a6xx_gpu.h   |  4 ++
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 17 +++++
 3 files changed, 104 insertions(+)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 8915882e4444..151190ff62f7 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -8,7 +8,9 @@
 #include "a6xx_gpu.h"
 #include "a6xx_gmu.xml.h"
 
+#include <linux/bitfield.h>
 #include <linux/devfreq.h>
+#include <linux/soc/qcom/llcc-qcom.h>
 
 #define GPU_PAS_ID 13
 
@@ -1022,6 +1024,79 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu)
 	return IRQ_HANDLED;
 }
 
+static void a6xx_llc_rmw(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 mask, u32 or)
+{
+	return msm_rmw(a6xx_gpu->llc_mmio + (reg << 2), mask, or);
+}
+
+static void a6xx_llc_write(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 value)
+{
+	return msm_writel(value, a6xx_gpu->llc_mmio + (reg << 2));
+}
+
+static void a6xx_llc_deactivate(struct a6xx_gpu *a6xx_gpu)
+{
+	llcc_slice_deactivate(a6xx_gpu->llc_slice);
+	llcc_slice_deactivate(a6xx_gpu->htw_llc_slice);
+}
+
+static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
+{
+	u32 cntl1_regval = 0;
+
+	if (IS_ERR(a6xx_gpu->llc_mmio))
+		return;
+
+	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
+		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
+
+		gpu_scid &= 0x1f;
+		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
+			       (gpu_scid << 15) | (gpu_scid << 20);
+	}
+
+	if (!llcc_slice_activate(a6xx_gpu->htw_llc_slice)) {
+		u32 gpuhtw_scid = llcc_get_slice_id(a6xx_gpu->htw_llc_slice);
+
+		gpuhtw_scid &= 0x1f;
+		cntl1_regval |= FIELD_PREP(GENMASK(29, 25), gpuhtw_scid);
+	}
+
+	if (cntl1_regval) {
+		/*
+		 * Program the slice IDs for the various GPU blocks and GPU MMU
+		 * pagetables
+		 */
+		a6xx_llc_write(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
+
+		/*
+		 * Program cacheability overrides to not allocate cache lines on
+		 * a write miss
+		 */
+		a6xx_llc_rmw(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
+	}
+}
+
+static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
+{
+	llcc_slice_putd(a6xx_gpu->llc_slice);
+	llcc_slice_putd(a6xx_gpu->htw_llc_slice);
+}
+
+static void a6xx_llc_slices_init(struct platform_device *pdev,
+		struct a6xx_gpu *a6xx_gpu)
+{
+	a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx");
+	if (IS_ERR(a6xx_gpu->llc_mmio))
+		return;
+
+	a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU);
+	a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW);
+
+	if (IS_ERR(a6xx_gpu->llc_slice) && IS_ERR(a6xx_gpu->htw_llc_slice))
+		a6xx_gpu->llc_mmio = ERR_PTR(-EINVAL);
+}
+
 static int a6xx_pm_resume(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -1038,6 +1113,8 @@ static int a6xx_pm_resume(struct msm_gpu *gpu)
 
 	msm_gpu_resume_devfreq(gpu);
 
+	a6xx_llc_activate(a6xx_gpu);
+
 	return 0;
 }
 
@@ -1048,6 +1125,8 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	trace_msm_gpu_suspend(0);
 
+	a6xx_llc_deactivate(a6xx_gpu);
+
 	devfreq_suspend_device(gpu->devfreq.devfreq);
 
 	return a6xx_gmu_stop(a6xx_gpu);
@@ -1091,6 +1170,8 @@ static void a6xx_destroy(struct msm_gpu *gpu)
 		drm_gem_object_put(a6xx_gpu->shadow_bo);
 	}
 
+	a6xx_llc_slices_destroy(a6xx_gpu);
+
 	a6xx_gmu_remove(a6xx_gpu);
 
 	adreno_gpu_cleanup(adreno_gpu);
@@ -1209,6 +1290,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	if (info && info->revn == 650)
 		adreno_gpu->base.hw_apriv = true;
 
+	a6xx_llc_slices_init(pdev, a6xx_gpu);
+
 	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
 	if (ret) {
 		a6xx_destroy(&(a6xx_gpu->base.base));
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index 3eeebf6a754b..9e6079af679c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -28,6 +28,10 @@ struct a6xx_gpu {
 	uint32_t *shadow;
 
 	bool has_whereami;
+
+	void __iomem *llc_mmio;
+	void *llc_slice;
+	void *htw_llc_slice;
 };
 
 #define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index fd8f491f2e48..86c4fe667225 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -16,6 +16,7 @@
 #include <linux/soc/qcom/mdt_loader.h>
 #include <soc/qcom/ocmem.h>
 #include "adreno_gpu.h"
+#include "a6xx_gpu.h"
 #include "msm_gem.h"
 #include "msm_mmu.h"
 
@@ -189,6 +190,8 @@ struct msm_gem_address_space *
 adreno_iommu_create_address_space(struct msm_gpu *gpu,
 		struct platform_device *pdev)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	struct iommu_domain *iommu;
 	struct msm_mmu *mmu;
 	struct msm_gem_address_space *aspace;
@@ -198,7 +201,21 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu,
 	if (!iommu)
 		return NULL;
 
+	/*
+	 * This allows GPU to set the bus attributes required to use system
+	 * cache on behalf of the iommu page table walker.
+	 */
+	if (!IS_ERR(a6xx_gpu->htw_llc_slice)) {
+		int gpu_htw_llc = 1;
+
+		iommu_domain_set_attr(iommu, DOMAIN_ATTR_SYS_CACHE, &gpu_htw_llc);
+	}
+
 	mmu = msm_iommu_new(&pdev->dev, iommu);
+	if (IS_ERR(mmu)) {
+		iommu_domain_free(iommu);
+		return ERR_CAST(mmu);
+	}
 
 	/*
 	 * Use the aperture start or SZ_16M, whichever is greater. This will
-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation

Re: [PATCHv5 4/6] drm/msm/a6xx: Add support for using system cache(LLC)

[Jordan Crouse]

On Tue, Sep 22, 2020 at 11:48:17AM +0530, Sai Prakash Ranjan wrote:
> From: Sharat Masetty <smasetty@codeaurora.org>
> 
> The last level system cache can be partitioned to 32 different
> slices of which GPU has two slices preallocated. One slice is
> used for caching GPU buffers and the other slice is used for
> caching the GPU SMMU pagetables. This talks to the core system
> cache driver to acquire the slice handles, configure the SCID's
> to those slices and activates and deactivates the slices upon
> GPU power collapse and restore.
> 
> Some support from the IOMMU driver is also needed to make use
> of the system cache to set the right TCR attributes. GPU then
> has the ability to override a few cacheability parameters which
> it does to override write-allocate to write-no-allocate as the
> GPU hardware does not benefit much from it.
> 
> DOMAIN_ATTR_SYS_CACHE is another domain level attribute used by the
> IOMMU driver to set the right attributes to cache the hardware
> pagetables into the system cache.
> 
> Signed-off-by: Sharat Masetty <smasetty@codeaurora.org>
> [saiprakash.ranjan: fix to set attr before device attach to iommu and rebase]
> Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
> ---
>  drivers/gpu/drm/msm/adreno/a6xx_gpu.c   | 83 +++++++++++++++++++++++++
>  drivers/gpu/drm/msm/adreno/a6xx_gpu.h   |  4 ++
>  drivers/gpu/drm/msm/adreno/adreno_gpu.c | 17 +++++
>  3 files changed, 104 insertions(+)
> 
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> index 8915882e4444..151190ff62f7 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> @@ -8,7 +8,9 @@
>  #include "a6xx_gpu.h"
>  #include "a6xx_gmu.xml.h"
>  
> +#include <linux/bitfield.h>
>  #include <linux/devfreq.h>
> +#include <linux/soc/qcom/llcc-qcom.h>
>  
>  #define GPU_PAS_ID 13
>  
> @@ -1022,6 +1024,79 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu)
>  	return IRQ_HANDLED;
>  }
>  
> +static void a6xx_llc_rmw(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 mask, u32 or)
> +{
> +	return msm_rmw(a6xx_gpu->llc_mmio + (reg << 2), mask, or);
> +}
> +
> +static void a6xx_llc_write(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 value)
> +{
> +	return msm_writel(value, a6xx_gpu->llc_mmio + (reg << 2));
> +}
> +
> +static void a6xx_llc_deactivate(struct a6xx_gpu *a6xx_gpu)
> +{
> +	llcc_slice_deactivate(a6xx_gpu->llc_slice);
> +	llcc_slice_deactivate(a6xx_gpu->htw_llc_slice);
> +}
> +
> +static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
> +{
> +	u32 cntl1_regval = 0;
> +
> +	if (IS_ERR(a6xx_gpu->llc_mmio))
> +		return;
> +
> +	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
> +		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
> +
> +		gpu_scid &= 0x1f;
> +		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
> +			       (gpu_scid << 15) | (gpu_scid << 20);
> +	}
> +
> +	if (!llcc_slice_activate(a6xx_gpu->htw_llc_slice)) {
> +		u32 gpuhtw_scid = llcc_get_slice_id(a6xx_gpu->htw_llc_slice);
> +
> +		gpuhtw_scid &= 0x1f;
> +		cntl1_regval |= FIELD_PREP(GENMASK(29, 25), gpuhtw_scid);
> +	}
> +
> +	if (cntl1_regval) {
> +		/*
> +		 * Program the slice IDs for the various GPU blocks and GPU MMU
> +		 * pagetables
> +		 */
> +		a6xx_llc_write(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
> +
> +		/*
> +		 * Program cacheability overrides to not allocate cache lines on
> +		 * a write miss
> +		 */
> +		a6xx_llc_rmw(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
> +	}
> +}

This code has been around long enough that it pre-dates a650. On a650 and other
MMU-500 targets the htw_llc is configured by the firmware and the llc_slice is
configured in a different register.

I don't think we need to pause everything and add support for the MMU-500 path,
but we do need a way to disallow LLCC on affected targets until such time that
we can get it fixed up.

Jordan

> +
> +static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
> +{
> +	llcc_slice_putd(a6xx_gpu->llc_slice);
> +	llcc_slice_putd(a6xx_gpu->htw_llc_slice);
> +}
> +
> +static void a6xx_llc_slices_init(struct platform_device *pdev,
> +		struct a6xx_gpu *a6xx_gpu)
> +{
> +	a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx");
> +	if (IS_ERR(a6xx_gpu->llc_mmio))
> +		return;
> +
> +	a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU);
> +	a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW);
> +
> +	if (IS_ERR(a6xx_gpu->llc_slice) && IS_ERR(a6xx_gpu->htw_llc_slice))
> +		a6xx_gpu->llc_mmio = ERR_PTR(-EINVAL);
> +}
> +
>  static int a6xx_pm_resume(struct msm_gpu *gpu)
>  {
>  	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
> @@ -1038,6 +1113,8 @@ static int a6xx_pm_resume(struct msm_gpu *gpu)
>  
>  	msm_gpu_resume_devfreq(gpu);
>  
> +	a6xx_llc_activate(a6xx_gpu);
> +
>  	return 0;
>  }
>  
> @@ -1048,6 +1125,8 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
>  
>  	trace_msm_gpu_suspend(0);
>  
> +	a6xx_llc_deactivate(a6xx_gpu);
> +
>  	devfreq_suspend_device(gpu->devfreq.devfreq);
>  
>  	return a6xx_gmu_stop(a6xx_gpu);
> @@ -1091,6 +1170,8 @@ static void a6xx_destroy(struct msm_gpu *gpu)
>  		drm_gem_object_put(a6xx_gpu->shadow_bo);
>  	}
>  
> +	a6xx_llc_slices_destroy(a6xx_gpu);
> +
>  	a6xx_gmu_remove(a6xx_gpu);
>  
>  	adreno_gpu_cleanup(adreno_gpu);
> @@ -1209,6 +1290,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
>  	if (info && info->revn == 650)
>  		adreno_gpu->base.hw_apriv = true;
>  
> +	a6xx_llc_slices_init(pdev, a6xx_gpu);
> +
>  	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
>  	if (ret) {
>  		a6xx_destroy(&(a6xx_gpu->base.base));
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> index 3eeebf6a754b..9e6079af679c 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> @@ -28,6 +28,10 @@ struct a6xx_gpu {
>  	uint32_t *shadow;
>  
>  	bool has_whereami;
> +
> +	void __iomem *llc_mmio;
> +	void *llc_slice;
> +	void *htw_llc_slice;
>  };
>  
>  #define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base)
> diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> index fd8f491f2e48..86c4fe667225 100644
> --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> @@ -16,6 +16,7 @@
>  #include <linux/soc/qcom/mdt_loader.h>
>  #include <soc/qcom/ocmem.h>
>  #include "adreno_gpu.h"
> +#include "a6xx_gpu.h"
>  #include "msm_gem.h"
>  #include "msm_mmu.h"
>  
> @@ -189,6 +190,8 @@ struct msm_gem_address_space *
>  adreno_iommu_create_address_space(struct msm_gpu *gpu,
>  		struct platform_device *pdev)
>  {
> +	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
> +	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
>  	struct iommu_domain *iommu;
>  	struct msm_mmu *mmu;
>  	struct msm_gem_address_space *aspace;
> @@ -198,7 +201,21 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu,
>  	if (!iommu)
>  		return NULL;
>  
> +	/*
> +	 * This allows GPU to set the bus attributes required to use system
> +	 * cache on behalf of the iommu page table walker.
> +	 */
> +	if (!IS_ERR(a6xx_gpu->htw_llc_slice)) {
> +		int gpu_htw_llc = 1;
> +
> +		iommu_domain_set_attr(iommu, DOMAIN_ATTR_SYS_CACHE, &gpu_htw_llc);
> +	}
> +
>  	mmu = msm_iommu_new(&pdev->dev, iommu);
> +	if (IS_ERR(mmu)) {
> +		iommu_domain_free(iommu);
> +		return ERR_CAST(mmu);
> +	}
>  
>  	/*
>  	 * Use the aperture start or SZ_16M, whichever is greater. This will
> -- 
> QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
> of Code Aurora Forum, hosted by The Linux Foundation
> 

-- 
The Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
a Linux Foundation Collaborative Project

Re: [PATCHv5 4/6] drm/msm/a6xx: Add support for using system cache(LLC)

[Sai Prakash Ranjan]

Hi Jordan,

On 2020-09-23 20:33, Jordan Crouse wrote:
> On Tue, Sep 22, 2020 at 11:48:17AM +0530, Sai Prakash Ranjan wrote:
>> From: Sharat Masetty <smasetty@codeaurora.org>
>> 
>> The last level system cache can be partitioned to 32 different
>> slices of which GPU has two slices preallocated. One slice is
>> used for caching GPU buffers and the other slice is used for
>> caching the GPU SMMU pagetables. This talks to the core system
>> cache driver to acquire the slice handles, configure the SCID's
>> to those slices and activates and deactivates the slices upon
>> GPU power collapse and restore.
>> 
>> Some support from the IOMMU driver is also needed to make use
>> of the system cache to set the right TCR attributes. GPU then
>> has the ability to override a few cacheability parameters which
>> it does to override write-allocate to write-no-allocate as the
>> GPU hardware does not benefit much from it.
>> 
>> DOMAIN_ATTR_SYS_CACHE is another domain level attribute used by the
>> IOMMU driver to set the right attributes to cache the hardware
>> pagetables into the system cache.
>> 
>> Signed-off-by: Sharat Masetty <smasetty@codeaurora.org>
>> [saiprakash.ranjan: fix to set attr before device attach to iommu and 
>> rebase]
>> Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
>> ---
>>  drivers/gpu/drm/msm/adreno/a6xx_gpu.c   | 83 
>> +++++++++++++++++++++++++
>>  drivers/gpu/drm/msm/adreno/a6xx_gpu.h   |  4 ++
>>  drivers/gpu/drm/msm/adreno/adreno_gpu.c | 17 +++++
>>  3 files changed, 104 insertions(+)
>> 
>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c 
>> b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> index 8915882e4444..151190ff62f7 100644
>> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> @@ -8,7 +8,9 @@
>>  #include "a6xx_gpu.h"
>>  #include "a6xx_gmu.xml.h"
>> 
>> +#include <linux/bitfield.h>
>>  #include <linux/devfreq.h>
>> +#include <linux/soc/qcom/llcc-qcom.h>
>> 
>>  #define GPU_PAS_ID 13
>> 
>> @@ -1022,6 +1024,79 @@ static irqreturn_t a6xx_irq(struct msm_gpu 
>> *gpu)
>>  	return IRQ_HANDLED;
>>  }
>> 
>> +static void a6xx_llc_rmw(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 
>> mask, u32 or)
>> +{
>> +	return msm_rmw(a6xx_gpu->llc_mmio + (reg << 2), mask, or);
>> +}
>> +
>> +static void a6xx_llc_write(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 
>> value)
>> +{
>> +	return msm_writel(value, a6xx_gpu->llc_mmio + (reg << 2));
>> +}
>> +
>> +static void a6xx_llc_deactivate(struct a6xx_gpu *a6xx_gpu)
>> +{
>> +	llcc_slice_deactivate(a6xx_gpu->llc_slice);
>> +	llcc_slice_deactivate(a6xx_gpu->htw_llc_slice);
>> +}
>> +
>> +static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
>> +{
>> +	u32 cntl1_regval = 0;
>> +
>> +	if (IS_ERR(a6xx_gpu->llc_mmio))
>> +		return;
>> +
>> +	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
>> +		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
>> +
>> +		gpu_scid &= 0x1f;
>> +		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) 
>> |
>> +			       (gpu_scid << 15) | (gpu_scid << 20);
>> +	}
>> +
>> +	if (!llcc_slice_activate(a6xx_gpu->htw_llc_slice)) {
>> +		u32 gpuhtw_scid = llcc_get_slice_id(a6xx_gpu->htw_llc_slice);
>> +
>> +		gpuhtw_scid &= 0x1f;
>> +		cntl1_regval |= FIELD_PREP(GENMASK(29, 25), gpuhtw_scid);
>> +	}
>> +
>> +	if (cntl1_regval) {
>> +		/*
>> +		 * Program the slice IDs for the various GPU blocks and GPU MMU
>> +		 * pagetables
>> +		 */
>> +		a6xx_llc_write(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, 
>> cntl1_regval);
>> +
>> +		/*
>> +		 * Program cacheability overrides to not allocate cache lines on
>> +		 * a write miss
>> +		 */
>> +		a6xx_llc_rmw(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 
>> 0x03);
>> +	}
>> +}
> 
> This code has been around long enough that it pre-dates a650. On a650 
> and other
> MMU-500 targets the htw_llc is configured by the firmware and the 
> llc_slice is
> configured in a different register.
> 
> I don't think we need to pause everything and add support for the 
> MMU-500 path,
> but we do need a way to disallow LLCC on affected targets until such 
> time that
> we can get it fixed up.
> 

Thanks for taking a close look, does something like below look ok or 
something
else is needed here?

+         /* Till the time we get in LLCC support for A650 */
+         if (!(info && info->revn == 650))
+                 a6xx_llc_slices_init(pdev, a6xx_gpu);

Thanks,
Sai

-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a 
member
of Code Aurora Forum, hosted by The Linux Foundation

Re: [PATCHv5 4/6] drm/msm/a6xx: Add support for using system cache(LLC)

[Jordan Crouse]

On Mon, Sep 28, 2020 at 05:56:55PM +0530, Sai Prakash Ranjan wrote:
> Hi Jordan,
> 
> On 2020-09-23 20:33, Jordan Crouse wrote:
> >On Tue, Sep 22, 2020 at 11:48:17AM +0530, Sai Prakash Ranjan wrote:
> >>From: Sharat Masetty <smasetty@codeaurora.org>
> >>
> >>The last level system cache can be partitioned to 32 different
> >>slices of which GPU has two slices preallocated. One slice is
> >>used for caching GPU buffers and the other slice is used for
> >>caching the GPU SMMU pagetables. This talks to the core system
> >>cache driver to acquire the slice handles, configure the SCID's
> >>to those slices and activates and deactivates the slices upon
> >>GPU power collapse and restore.
> >>
> >>Some support from the IOMMU driver is also needed to make use
> >>of the system cache to set the right TCR attributes. GPU then
> >>has the ability to override a few cacheability parameters which
> >>it does to override write-allocate to write-no-allocate as the
> >>GPU hardware does not benefit much from it.
> >>
> >>DOMAIN_ATTR_SYS_CACHE is another domain level attribute used by the
> >>IOMMU driver to set the right attributes to cache the hardware
> >>pagetables into the system cache.
> >>
> >>Signed-off-by: Sharat Masetty <smasetty@codeaurora.org>
> >>[saiprakash.ranjan: fix to set attr before device attach to iommu and
> >>rebase]
> >>Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
> >>---
> >> drivers/gpu/drm/msm/adreno/a6xx_gpu.c   | 83 +++++++++++++++++++++++++
> >> drivers/gpu/drm/msm/adreno/a6xx_gpu.h   |  4 ++
> >> drivers/gpu/drm/msm/adreno/adreno_gpu.c | 17 +++++
> >> 3 files changed, 104 insertions(+)
> >>
> >>diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> >>b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> >>index 8915882e4444..151190ff62f7 100644
> >>--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> >>+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> >>@@ -8,7 +8,9 @@
> >> #include "a6xx_gpu.h"
> >> #include "a6xx_gmu.xml.h"
> >>
> >>+#include <linux/bitfield.h>
> >> #include <linux/devfreq.h>
> >>+#include <linux/soc/qcom/llcc-qcom.h>
> >>
> >> #define GPU_PAS_ID 13
> >>
> >>@@ -1022,6 +1024,79 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu)
> >> 	return IRQ_HANDLED;
> >> }
> >>
> >>+static void a6xx_llc_rmw(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 mask,
> >>u32 or)
> >>+{
> >>+	return msm_rmw(a6xx_gpu->llc_mmio + (reg << 2), mask, or);
> >>+}
> >>+
> >>+static void a6xx_llc_write(struct a6xx_gpu *a6xx_gpu, u32 reg, u32
> >>value)
> >>+{
> >>+	return msm_writel(value, a6xx_gpu->llc_mmio + (reg << 2));
> >>+}
> >>+
> >>+static void a6xx_llc_deactivate(struct a6xx_gpu *a6xx_gpu)
> >>+{
> >>+	llcc_slice_deactivate(a6xx_gpu->llc_slice);
> >>+	llcc_slice_deactivate(a6xx_gpu->htw_llc_slice);
> >>+}
> >>+
> >>+static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
> >>+{
> >>+	u32 cntl1_regval = 0;
> >>+
> >>+	if (IS_ERR(a6xx_gpu->llc_mmio))
> >>+		return;
> >>+
> >>+	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
> >>+		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
> >>+
> >>+		gpu_scid &= 0x1f;
> >>+		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
> >>+			       (gpu_scid << 15) | (gpu_scid << 20);
> >>+	}
> >>+
> >>+	if (!llcc_slice_activate(a6xx_gpu->htw_llc_slice)) {
> >>+		u32 gpuhtw_scid = llcc_get_slice_id(a6xx_gpu->htw_llc_slice);
> >>+
> >>+		gpuhtw_scid &= 0x1f;
> >>+		cntl1_regval |= FIELD_PREP(GENMASK(29, 25), gpuhtw_scid);
> >>+	}
> >>+
> >>+	if (cntl1_regval) {
> >>+		/*
> >>+		 * Program the slice IDs for the various GPU blocks and GPU MMU
> >>+		 * pagetables
> >>+		 */
> >>+		a6xx_llc_write(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1,
> >>cntl1_regval);
> >>+
> >>+		/*
> >>+		 * Program cacheability overrides to not allocate cache lines on
> >>+		 * a write miss
> >>+		 */
> >>+		a6xx_llc_rmw(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF,
> >>0x03);
> >>+	}
> >>+}
> >
> >This code has been around long enough that it pre-dates a650. On a650 and
> >other
> >MMU-500 targets the htw_llc is configured by the firmware and the
> >llc_slice is
> >configured in a different register.
> >
> >I don't think we need to pause everything and add support for the MMU-500
> >path,
> >but we do need a way to disallow LLCC on affected targets until such time
> >that
> >we can get it fixed up.
> >
> 
> Thanks for taking a close look, does something like below look ok or
> something
> else is needed here?
> 
> +         /* Till the time we get in LLCC support for A650 */
> +         if (!(info && info->revn == 650))
> +                 a6xx_llc_slices_init(pdev, a6xx_gpu);

It doesn't look like Rob picked this up for 5.10, so we have some time to do it
right.  Would you like me to give you an add-on patch for mmu-500 targets?

Jordan

> Thanks,
> Sai
> 
> -- 
> QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
> of Code Aurora Forum, hosted by The Linux Foundation

-- 
The Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
a Linux Foundation Collaborative Project

Re: [PATCHv5 4/6] drm/msm/a6xx: Add support for using system cache(LLC)

[Sai Prakash Ranjan]

On 2020-09-28 21:41, Jordan Crouse wrote:
> On Mon, Sep 28, 2020 at 05:56:55PM +0530, Sai Prakash Ranjan wrote:
>> Hi Jordan,
>> 
>> On 2020-09-23 20:33, Jordan Crouse wrote:
>> >On Tue, Sep 22, 2020 at 11:48:17AM +0530, Sai Prakash Ranjan wrote:
>> >>From: Sharat Masetty <smasetty@codeaurora.org>
>> >>
>> >>The last level system cache can be partitioned to 32 different
>> >>slices of which GPU has two slices preallocated. One slice is
>> >>used for caching GPU buffers and the other slice is used for
>> >>caching the GPU SMMU pagetables. This talks to the core system
>> >>cache driver to acquire the slice handles, configure the SCID's
>> >>to those slices and activates and deactivates the slices upon
>> >>GPU power collapse and restore.
>> >>
>> >>Some support from the IOMMU driver is also needed to make use
>> >>of the system cache to set the right TCR attributes. GPU then
>> >>has the ability to override a few cacheability parameters which
>> >>it does to override write-allocate to write-no-allocate as the
>> >>GPU hardware does not benefit much from it.
>> >>
>> >>DOMAIN_ATTR_SYS_CACHE is another domain level attribute used by the
>> >>IOMMU driver to set the right attributes to cache the hardware
>> >>pagetables into the system cache.
>> >>
>> >>Signed-off-by: Sharat Masetty <smasetty@codeaurora.org>
>> >>[saiprakash.ranjan: fix to set attr before device attach to iommu and
>> >>rebase]
>> >>Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
>> >>---
>> >> drivers/gpu/drm/msm/adreno/a6xx_gpu.c   | 83 +++++++++++++++++++++++++
>> >> drivers/gpu/drm/msm/adreno/a6xx_gpu.h   |  4 ++
>> >> drivers/gpu/drm/msm/adreno/adreno_gpu.c | 17 +++++
>> >> 3 files changed, 104 insertions(+)
>> >>
>> >>diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> >>b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> >>index 8915882e4444..151190ff62f7 100644
>> >>--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> >>+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> >>@@ -8,7 +8,9 @@
>> >> #include "a6xx_gpu.h"
>> >> #include "a6xx_gmu.xml.h"
>> >>
>> >>+#include <linux/bitfield.h>
>> >> #include <linux/devfreq.h>
>> >>+#include <linux/soc/qcom/llcc-qcom.h>
>> >>
>> >> #define GPU_PAS_ID 13
>> >>
>> >>@@ -1022,6 +1024,79 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu)
>> >> 	return IRQ_HANDLED;
>> >> }
>> >>
>> >>+static void a6xx_llc_rmw(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 mask,
>> >>u32 or)
>> >>+{
>> >>+	return msm_rmw(a6xx_gpu->llc_mmio + (reg << 2), mask, or);
>> >>+}
>> >>+
>> >>+static void a6xx_llc_write(struct a6xx_gpu *a6xx_gpu, u32 reg, u32
>> >>value)
>> >>+{
>> >>+	return msm_writel(value, a6xx_gpu->llc_mmio + (reg << 2));
>> >>+}
>> >>+
>> >>+static void a6xx_llc_deactivate(struct a6xx_gpu *a6xx_gpu)
>> >>+{
>> >>+	llcc_slice_deactivate(a6xx_gpu->llc_slice);
>> >>+	llcc_slice_deactivate(a6xx_gpu->htw_llc_slice);
>> >>+}
>> >>+
>> >>+static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
>> >>+{
>> >>+	u32 cntl1_regval = 0;
>> >>+
>> >>+	if (IS_ERR(a6xx_gpu->llc_mmio))
>> >>+		return;
>> >>+
>> >>+	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
>> >>+		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
>> >>+
>> >>+		gpu_scid &= 0x1f;
>> >>+		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
>> >>+			       (gpu_scid << 15) | (gpu_scid << 20);
>> >>+	}
>> >>+
>> >>+	if (!llcc_slice_activate(a6xx_gpu->htw_llc_slice)) {
>> >>+		u32 gpuhtw_scid = llcc_get_slice_id(a6xx_gpu->htw_llc_slice);
>> >>+
>> >>+		gpuhtw_scid &= 0x1f;
>> >>+		cntl1_regval |= FIELD_PREP(GENMASK(29, 25), gpuhtw_scid);
>> >>+	}
>> >>+
>> >>+	if (cntl1_regval) {
>> >>+		/*
>> >>+		 * Program the slice IDs for the various GPU blocks and GPU MMU
>> >>+		 * pagetables
>> >>+		 */
>> >>+		a6xx_llc_write(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1,
>> >>cntl1_regval);
>> >>+
>> >>+		/*
>> >>+		 * Program cacheability overrides to not allocate cache lines on
>> >>+		 * a write miss
>> >>+		 */
>> >>+		a6xx_llc_rmw(a6xx_gpu, REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF,
>> >>0x03);
>> >>+	}
>> >>+}
>> >
>> >This code has been around long enough that it pre-dates a650. On a650 and
>> >other
>> >MMU-500 targets the htw_llc is configured by the firmware and the
>> >llc_slice is
>> >configured in a different register.
>> >
>> >I don't think we need to pause everything and add support for the MMU-500
>> >path,
>> >but we do need a way to disallow LLCC on affected targets until such time
>> >that
>> >we can get it fixed up.
>> >
>> 
>> Thanks for taking a close look, does something like below look ok or
>> something
>> else is needed here?
>> 
>> +         /* Till the time we get in LLCC support for A650 */
>> +         if (!(info && info->revn == 650))
>> +                 a6xx_llc_slices_init(pdev, a6xx_gpu);
> 
> It doesn't look like Rob picked this up for 5.10, so we have some time 
> to do it
> right.  Would you like me to give you an add-on patch for mmu-500 
> targets?
> 

Yes that will be great.

Thanks,
Sai

-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a 
member
of Code Aurora Forum, hosted by The Linux Foundation

[PATCHv5 5/6] iommu: arm-smmu-impl: Use table to list QCOM implementations

[Sai Prakash Ranjan]

Use table and of_match_node() to match qcom implementation
instead of multiple of_device_compatible() calls for each
QCOM SMMU implementation.

Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-impl.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
index d199b4bff15d..ce78295cfa78 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
@@ -9,6 +9,13 @@
 
 #include "arm-smmu.h"
 
+static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
+	{ .compatible = "qcom,sc7180-smmu-500" },
+	{ .compatible = "qcom,sdm845-smmu-500" },
+	{ .compatible = "qcom,sm8150-smmu-500" },
+	{ .compatible = "qcom,sm8250-smmu-500" },
+	{ }
+};
 
 static int arm_smmu_gr0_ns(int offset)
 {
@@ -217,10 +224,7 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 	if (of_device_is_compatible(np, "nvidia,tegra194-smmu"))
 		return nvidia_smmu_impl_init(smmu);
 
-	if (of_device_is_compatible(np, "qcom,sdm845-smmu-500") ||
-	    of_device_is_compatible(np, "qcom,sc7180-smmu-500") ||
-	    of_device_is_compatible(np, "qcom,sm8150-smmu-500") ||
-	    of_device_is_compatible(np, "qcom,sm8250-smmu-500"))
+	if (of_match_node(qcom_smmu_impl_of_match, np))
 		return qcom_smmu_impl_init(smmu);
 
 	if (of_device_is_compatible(smmu->dev->of_node, "qcom,adreno-smmu"))
-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation

Re: [PATCHv5 5/6] iommu: arm-smmu-impl: Use table to list QCOM implementations

[Robin Murphy]

On 2020-09-22 07:18, Sai Prakash Ranjan wrote:
> Use table and of_match_node() to match qcom implementation
> instead of multiple of_device_compatible() calls for each
> QCOM SMMU implementation.
> 
> Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
> ---
>   drivers/iommu/arm/arm-smmu/arm-smmu-impl.c | 12 ++++++++----
>   1 file changed, 8 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
> index d199b4bff15d..ce78295cfa78 100644
> --- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
> +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
> @@ -9,6 +9,13 @@
>   
>   #include "arm-smmu.h"
>   
> +static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
> +	{ .compatible = "qcom,sc7180-smmu-500" },
> +	{ .compatible = "qcom,sdm845-smmu-500" },
> +	{ .compatible = "qcom,sm8150-smmu-500" },
> +	{ .compatible = "qcom,sm8250-smmu-500" },
> +	{ }
> +};

Can you push the table itself into arm-smmu-qcom? That way you'll be 
free to add new SoCs willy-nilly without any possibility of conflicting 
with anything else.

Bonus points if you can fold in the Adreno variant and keep everything 
together ;)

Robin.

>   static int arm_smmu_gr0_ns(int offset)
>   {
> @@ -217,10 +224,7 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
>   	if (of_device_is_compatible(np, "nvidia,tegra194-smmu"))
>   		return nvidia_smmu_impl_init(smmu);
>   
> -	if (of_device_is_compatible(np, "qcom,sdm845-smmu-500") ||
> -	    of_device_is_compatible(np, "qcom,sc7180-smmu-500") ||
> -	    of_device_is_compatible(np, "qcom,sm8150-smmu-500") ||
> -	    of_device_is_compatible(np, "qcom,sm8250-smmu-500"))
> +	if (of_match_node(qcom_smmu_impl_of_match, np))
>   		return qcom_smmu_impl_init(smmu);
>   
>   	if (of_device_is_compatible(smmu->dev->of_node, "qcom,adreno-smmu"))
> 

Re: [PATCHv5 5/6] iommu: arm-smmu-impl: Use table to list QCOM implementations

[Sai Prakash Ranjan]

On 2020-09-23 20:54, Robin Murphy wrote:
> On 2020-09-22 07:18, Sai Prakash Ranjan wrote:
>> Use table and of_match_node() to match qcom implementation
>> instead of multiple of_device_compatible() calls for each
>> QCOM SMMU implementation.
>> 
>> Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
>> ---
>>   drivers/iommu/arm/arm-smmu/arm-smmu-impl.c | 12 ++++++++----
>>   1 file changed, 8 insertions(+), 4 deletions(-)
>> 
>> diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c 
>> b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
>> index d199b4bff15d..ce78295cfa78 100644
>> --- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
>> +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
>> @@ -9,6 +9,13 @@
>>     #include "arm-smmu.h"
>>   +static const struct of_device_id __maybe_unused 
>> qcom_smmu_impl_of_match[] = {
>> +	{ .compatible = "qcom,sc7180-smmu-500" },
>> +	{ .compatible = "qcom,sdm845-smmu-500" },
>> +	{ .compatible = "qcom,sm8150-smmu-500" },
>> +	{ .compatible = "qcom,sm8250-smmu-500" },
>> +	{ }
>> +};
> 
> Can you push the table itself into arm-smmu-qcom? That way you'll be
> free to add new SoCs willy-nilly without any possibility of
> conflicting with anything else.
> 
> Bonus points if you can fold in the Adreno variant and keep everything
> together ;)
> 

Sure I can get bonus points :)

Thanks,
Sai

-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a 
member
of Code Aurora Forum, hosted by The Linux Foundation

[PATCHv5 6/6] iommu: arm-smmu-impl: Add a space before open parenthesis

[Sai Prakash Ranjan]

Fix the checkpatch warning for space required before the open
parenthesis.

Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-impl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
index ce78295cfa78..eda852111706 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
@@ -19,7 +19,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 
 static int arm_smmu_gr0_ns(int offset)
 {
-	switch(offset) {
+	switch (offset) {
 	case ARM_SMMU_GR0_sCR0:
 	case ARM_SMMU_GR0_sACR:
 	case ARM_SMMU_GR0_sGFSR:
-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation