linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v3 0/3] Initial Panfrost driver
@ 2019-04-09 20:54 Rob Herring
  2019-04-09 20:54 ` [PATCH v3 1/3] iommu: io-pgtable: Add ARM Mali midgard MMU page table format Rob Herring
  0 siblings, 1 reply; 2+ messages in thread
From: Rob Herring @ 2019-04-09 20:54 UTC (permalink / raw)
  To: dri-devel
  Cc: Sean Paul, Lyude Paul, Eric Anholt, Maxime Ripard,
	Maarten Lankhorst, Joerg Roedel, Neil Armstrong, Will Deacon,
	linux-kernel, Steven Price, David Airlie, iommu, Boris Brezillon,
	Alyssa Rosenzweig, Daniel Vetter, Robin Murphy, linux-arm-kernel

Here's v3 of the panfrost driver. Lot's of changes from review comments
and further testing. Details are in each patch. Of note, a problem with
MMU page faults has been addressed improving the stability. In the
process, the TLB invalidate has been optimized which Tomeu says has
improved the performance some.

Several dependencies have been applied already, but the first 2 patches
are the remaining dependencies. We need to take the iommu change via
drm-misc or we need a stable branch.

I'm hoping this is the last version. I'm hoping to apply this to drm-misc
this week before -rc5 cutoff.

A git branch is here[1].

Rob

[1] git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git panfrost-rebase-v3


Rob Herring (3):
  iommu: io-pgtable: Add ARM Mali midgard MMU page table format
  drm: Add a drm_gem_objects_lookup helper
  drm/panfrost: Add initial panfrost driver

 MAINTAINERS                                  |   9 +
 drivers/gpu/drm/Kconfig                      |   2 +
 drivers/gpu/drm/Makefile                     |   1 +
 drivers/gpu/drm/drm_gem.c                    |  93 ++-
 drivers/gpu/drm/panfrost/Kconfig             |  14 +
 drivers/gpu/drm/panfrost/Makefile            |  12 +
 drivers/gpu/drm/panfrost/TODO                |  27 +
 drivers/gpu/drm/panfrost/panfrost_devfreq.c  | 218 ++++++++
 drivers/gpu/drm/panfrost/panfrost_devfreq.h  |  14 +
 drivers/gpu/drm/panfrost/panfrost_device.c   | 252 +++++++++
 drivers/gpu/drm/panfrost/panfrost_device.h   | 124 ++++
 drivers/gpu/drm/panfrost/panfrost_drv.c      | 460 +++++++++++++++
 drivers/gpu/drm/panfrost/panfrost_features.h | 309 ++++++++++
 drivers/gpu/drm/panfrost/panfrost_gem.c      |  95 ++++
 drivers/gpu/drm/panfrost/panfrost_gem.h      |  29 +
 drivers/gpu/drm/panfrost/panfrost_gpu.c      | 362 ++++++++++++
 drivers/gpu/drm/panfrost/panfrost_gpu.h      |  19 +
 drivers/gpu/drm/panfrost/panfrost_issues.h   | 176 ++++++
 drivers/gpu/drm/panfrost/panfrost_job.c      | 560 +++++++++++++++++++
 drivers/gpu/drm/panfrost/panfrost_job.h      |  51 ++
 drivers/gpu/drm/panfrost/panfrost_mmu.c      | 369 ++++++++++++
 drivers/gpu/drm/panfrost/panfrost_mmu.h      |  17 +
 drivers/gpu/drm/panfrost/panfrost_regs.h     | 298 ++++++++++
 drivers/iommu/io-pgtable-arm.c               |  91 ++-
 drivers/iommu/io-pgtable.c                   |   1 +
 include/drm/drm_gem.h                        |   2 +
 include/linux/io-pgtable.h                   |   7 +
 include/uapi/drm/panfrost_drm.h              | 142 +++++
 28 files changed, 3722 insertions(+), 32 deletions(-)
 create mode 100644 drivers/gpu/drm/panfrost/Kconfig
 create mode 100644 drivers/gpu/drm/panfrost/Makefile
 create mode 100644 drivers/gpu/drm/panfrost/TODO
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_devfreq.c
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_devfreq.h
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_device.c
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_device.h
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_drv.c
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_features.h
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_gem.c
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_gem.h
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_gpu.c
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_gpu.h
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_issues.h
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_job.c
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_job.h
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_mmu.c
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_mmu.h
 create mode 100644 drivers/gpu/drm/panfrost/panfrost_regs.h
 create mode 100644 include/uapi/drm/panfrost_drm.h

--
2.19.1

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply	[flat|nested] 2+ messages in thread

* [PATCH v3 1/3] iommu: io-pgtable: Add ARM Mali midgard MMU page table format
  2019-04-09 20:54 [PATCH v3 0/3] Initial Panfrost driver Rob Herring
@ 2019-04-09 20:54 ` Rob Herring
  0 siblings, 0 replies; 2+ messages in thread
From: Rob Herring @ 2019-04-09 20:54 UTC (permalink / raw)
  To: dri-devel
  Cc: Joerg Roedel, Will Deacon, linux-kernel, iommu, Alyssa Rosenzweig,
	Robin Murphy, linux-arm-kernel

ARM Mali midgard GPU is similar to standard 64-bit stage 1 page tables, but
have a few differences. Add a new format type to represent the format. The
input address size is 48-bits and the output address size is 40-bits (and
possibly less?). Note that the later bifrost GPUs follow the standard
64-bit stage 1 format.

The differences in the format compared to 64-bit stage 1 format are:

The 3rd level page entry bits are 0x1 instead of 0x3 for page entries.

The access flags are not read-only and unprivileged, but read and write.
This is similar to stage 2 entries, but the memory attributes field matches
stage 1 being an index.

The nG bit is not set by the vendor driver. This one didn't seem to matter,
but we'll keep it aligned to the vendor driver.

Cc: Will Deacon <will.deacon@arm.com>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: iommu@lists.linux-foundation.org
Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Rob Herring <robh@kernel.org>
---
This is really v4 of the patch. v3 is the series version.

Joerg, please ack so we can take this via the drm tree.

v3:
- Incorporated refactoring from Robin

 drivers/iommu/io-pgtable-arm.c | 91 ++++++++++++++++++++++++++--------
 drivers/iommu/io-pgtable.c     |  1 +
 include/linux/io-pgtable.h     |  7 +++
 3 files changed, 77 insertions(+), 22 deletions(-)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index d3700ec15cbd..4e21efbc4459 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -172,6 +172,10 @@
 #define ARM_LPAE_MAIR_ATTR_IDX_CACHE	1
 #define ARM_LPAE_MAIR_ATTR_IDX_DEV	2

+#define ARM_MALI_LPAE_TTBR_ADRMODE_TABLE (3u << 0)
+#define ARM_MALI_LPAE_TTBR_READ_INNER	BIT(2)
+#define ARM_MALI_LPAE_TTBR_SHARE_OUTER	BIT(4)
+
 /* IOPTE accessors */
 #define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d))

@@ -180,11 +184,6 @@

 #define iopte_prot(pte)	((pte) & ARM_LPAE_PTE_ATTR_MASK)

-#define iopte_leaf(pte,l)					\
-	(l == (ARM_LPAE_MAX_LEVELS - 1) ?			\
-		(iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_PAGE) :	\
-		(iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_BLOCK))
-
 struct arm_lpae_io_pgtable {
 	struct io_pgtable	iop;

@@ -198,6 +197,15 @@ struct arm_lpae_io_pgtable {

 typedef u64 arm_lpae_iopte;

+static inline bool iopte_leaf(arm_lpae_iopte pte, int lvl,
+			      enum io_pgtable_fmt fmt)
+{
+	if (lvl == (ARM_LPAE_MAX_LEVELS - 1) && fmt != ARM_MALI_LPAE)
+		return iopte_type(pte, lvl) == ARM_LPAE_PTE_TYPE_PAGE;
+
+	return iopte_type(pte, lvl) == ARM_LPAE_PTE_TYPE_BLOCK;
+}
+
 static arm_lpae_iopte paddr_to_iopte(phys_addr_t paddr,
 				     struct arm_lpae_io_pgtable *data)
 {
@@ -303,12 +311,14 @@ static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
 	if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
 		pte |= ARM_LPAE_PTE_NS;

-	if (lvl == ARM_LPAE_MAX_LEVELS - 1)
+	if (data->iop.fmt != ARM_MALI_LPAE && lvl == ARM_LPAE_MAX_LEVELS - 1)
 		pte |= ARM_LPAE_PTE_TYPE_PAGE;
 	else
 		pte |= ARM_LPAE_PTE_TYPE_BLOCK;

-	pte |= ARM_LPAE_PTE_AF | ARM_LPAE_PTE_SH_IS;
+	if (data->iop.fmt != ARM_MALI_LPAE)
+		pte |= ARM_LPAE_PTE_AF;
+	pte |= ARM_LPAE_PTE_SH_IS;
 	pte |= paddr_to_iopte(paddr, data);

 	__arm_lpae_set_pte(ptep, pte, &data->iop.cfg);
@@ -321,7 +331,7 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
 {
 	arm_lpae_iopte pte = *ptep;

-	if (iopte_leaf(pte, lvl)) {
+	if (iopte_leaf(pte, lvl, data->iop.fmt)) {
 		/* We require an unmap first */
 		WARN_ON(!selftest_running);
 		return -EEXIST;
@@ -409,7 +419,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 		__arm_lpae_sync_pte(ptep, cfg);
 	}

-	if (pte && !iopte_leaf(pte, lvl)) {
+	if (pte && !iopte_leaf(pte, lvl, data->iop.fmt)) {
 		cptep = iopte_deref(pte, data);
 	} else if (pte) {
 		/* We require an unmap first */
@@ -429,31 +439,37 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 	if (data->iop.fmt == ARM_64_LPAE_S1 ||
 	    data->iop.fmt == ARM_32_LPAE_S1) {
 		pte = ARM_LPAE_PTE_nG;
-
 		if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ))
 			pte |= ARM_LPAE_PTE_AP_RDONLY;
-
 		if (!(prot & IOMMU_PRIV))
 			pte |= ARM_LPAE_PTE_AP_UNPRIV;
-
-		if (prot & IOMMU_MMIO)
-			pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV
-				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
-		else if (prot & IOMMU_CACHE)
-			pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
-				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	} else {
 		pte = ARM_LPAE_PTE_HAP_FAULT;
 		if (prot & IOMMU_READ)
 			pte |= ARM_LPAE_PTE_HAP_READ;
 		if (prot & IOMMU_WRITE)
 			pte |= ARM_LPAE_PTE_HAP_WRITE;
+	}
+
+	/*
+	 * Note that this logic is structured to accommodate Mali LPAE
+	 * having stage-1-like attributes but stage-2-like permissions.
+	 */
+	if (data->iop.fmt == ARM_64_LPAE_S2 ||
+	    data->iop.fmt == ARM_32_LPAE_S2) {
 		if (prot & IOMMU_MMIO)
 			pte |= ARM_LPAE_PTE_MEMATTR_DEV;
 		else if (prot & IOMMU_CACHE)
 			pte |= ARM_LPAE_PTE_MEMATTR_OIWB;
 		else
 			pte |= ARM_LPAE_PTE_MEMATTR_NC;
+	} else {
+		if (prot & IOMMU_MMIO)
+			pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV
+				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
+		else if (prot & IOMMU_CACHE)
+			pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
+				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	}

 	if (prot & IOMMU_NOEXEC)
@@ -511,7 +527,7 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl,
 	while (ptep != end) {
 		arm_lpae_iopte pte = *ptep++;

-		if (!pte || iopte_leaf(pte, lvl))
+		if (!pte || iopte_leaf(pte, lvl, data->iop.fmt))
 			continue;

 		__arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data));
@@ -602,7 +618,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 	if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) {
 		__arm_lpae_set_pte(ptep, 0, &iop->cfg);

-		if (!iopte_leaf(pte, lvl)) {
+		if (!iopte_leaf(pte, lvl, iop->fmt)) {
 			/* Also flush any partial walks */
 			io_pgtable_tlb_add_flush(iop, iova, size,
 						ARM_LPAE_GRANULE(data), false);
@@ -621,7 +637,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 		}

 		return size;
-	} else if (iopte_leaf(pte, lvl)) {
+	} else if (iopte_leaf(pte, lvl, iop->fmt)) {
 		/*
 		 * Insert a table at the next level to map the old region,
 		 * minus the part we want to unmap
@@ -669,7 +685,7 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
 			return 0;

 		/* Leaf entry? */
-		if (iopte_leaf(pte,lvl))
+		if (iopte_leaf(pte, lvl, data->iop.fmt))
 			goto found_translation;

 		/* Take it to the next level */
@@ -995,6 +1011,32 @@ arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	return iop;
 }

+static struct io_pgtable *
+arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct io_pgtable *iop;
+
+	if (cfg->ias != 48 || cfg->oas > 40)
+		return NULL;
+
+	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
+	if (iop) {
+		u64 mair, ttbr;
+
+		/* Copy values as union fields overlap */
+		mair = cfg->arm_lpae_s1_cfg.mair[0];
+		ttbr = cfg->arm_lpae_s1_cfg.ttbr[0];
+
+		cfg->arm_mali_lpae_cfg.memattr = mair;
+		cfg->arm_mali_lpae_cfg.transtab = ttbr |
+			ARM_MALI_LPAE_TTBR_READ_INNER |
+			ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	}
+
+	return iop;
+}
+
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
 	.alloc	= arm_64_lpae_alloc_pgtable_s1,
 	.free	= arm_lpae_free_pgtable,
@@ -1015,6 +1057,11 @@ struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns = {
 	.free	= arm_lpae_free_pgtable,
 };

+struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = {
+	.alloc	= arm_mali_lpae_alloc_pgtable,
+	.free	= arm_lpae_free_pgtable,
+};
+
 #ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST

 static struct io_pgtable_cfg *cfg_cookie;
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index 93f2880be6c6..5227cfdbb65b 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -30,6 +30,7 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
 	[ARM_32_LPAE_S2] = &io_pgtable_arm_32_lpae_s2_init_fns,
 	[ARM_64_LPAE_S1] = &io_pgtable_arm_64_lpae_s1_init_fns,
 	[ARM_64_LPAE_S2] = &io_pgtable_arm_64_lpae_s2_init_fns,
+	[ARM_MALI_LPAE] = &io_pgtable_arm_mali_lpae_init_fns,
 #endif
 #ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S
 	[ARM_V7S] = &io_pgtable_arm_v7s_init_fns,
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 47d5ae559329..76969a564831 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -12,6 +12,7 @@ enum io_pgtable_fmt {
 	ARM_64_LPAE_S1,
 	ARM_64_LPAE_S2,
 	ARM_V7S,
+	ARM_MALI_LPAE,
 	IO_PGTABLE_NUM_FMTS,
 };

@@ -108,6 +109,11 @@ struct io_pgtable_cfg {
 			u32	nmrr;
 			u32	prrr;
 		} arm_v7s_cfg;
+
+		struct {
+			u64	transtab;
+			u64	memattr;
+		} arm_mali_lpae_cfg;
 	};
 };

@@ -209,5 +215,6 @@ extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns;
 extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns;
 extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns;
 extern struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns;

 #endif /* __IO_PGTABLE_H */
--
2.19.1

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2019-04-09 20:54 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2019-04-09 20:54 [PATCH v3 0/3] Initial Panfrost driver Rob Herring
2019-04-09 20:54 ` [PATCH v3 1/3] iommu: io-pgtable: Add ARM Mali midgard MMU page table format Rob Herring

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 NNTP newsgroup(s).