From e747d01199503a97d9b3f477f1cded54d194cfb9 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Wed, 26 Feb 2020 10:56:57 -0800
Subject: drm/i915/ggtt: do not set bits 1-11 in gen12 ptes
Git-commit: 69edc390a54268d41e45089cb972bf71510f5f07
Patch-mainline: v5.7-rc1
References: jsc#SLE-12680, jsc#SLE-12880, jsc#SLE-12882, jsc#SLE-12883, jsc#SLE-13496, jsc#SLE-15322
On TGL, bits 2-4 in the GGTT PTE are not ignored anymore and are
instead used for some extra VT-d capabilities. We don't (yet?) have
support for those capabilities, but, given that we shared the pte_encode
function betweed GGTT and PPGTT, we still set those bits to the PPGTT
PPAT values. The DMA engine gets very confused when those bits are
set while the iommu is enabled, leading to errors. E.g. when loading
the GuC we get:
[ 9.796218] DMAR: DRHD: handling fault status reg 2
[ 9.796235] DMAR: [DMA Write] Request device [00:02.0] PASID ffffffff fault addr 0 [fault reason 02] Present bit in context entry is clear
[ 9.899215] [drm:intel_guc_fw_upload [i915]] *ERROR* GuC firmware signature verification failed
To fix this, just have dedicated gen8_pte_encode function per type of
gtt. Also, explicitly set vm->pte_encode for gen8_ppgtt, even if we
don't use it, to make sure we don't accidentally assign it to the GGTT
one, like we do for gen6_ppgtt, in case we need it in the future.
Reported-by: "Sodhi, Vunny" <vunny.sodhi@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200226185657.26445-1-daniele.ceraolospurio@intel.com
Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 26 ++++++++++++++++++++++++++
drivers/gpu/drm/i915/gt/intel_ggtt.c | 13 ++++++++++---
drivers/gpu/drm/i915/gt/intel_gtt.c | 24 ------------------------
drivers/gpu/drm/i915/gt/intel_gtt.h | 4 ----
4 files changed, 36 insertions(+), 31 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 4d1de2d97d5c..9aabc5815d38 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -25,6 +25,30 @@ static u64 gen8_pde_encode(const dma_addr_t addr,
return pde;
}
+static u64 gen8_pte_encode(dma_addr_t addr,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW;
+
+ if (unlikely(flags & PTE_READ_ONLY))
+ pte &= ~_PAGE_RW;
+
+ switch (level) {
+ case I915_CACHE_NONE:
+ pte |= PPAT_UNCACHED;
+ break;
+ case I915_CACHE_WT:
+ pte |= PPAT_DISPLAY_ELLC;
+ break;
+ default:
+ pte |= PPAT_CACHED;
+ break;
+ }
+
+ return pte;
+}
+
static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
{
struct drm_i915_private *i915 = ppgtt->vm.i915;
@@ -706,6 +730,8 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt)
ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc;
ppgtt->vm.clear_range = gen8_ppgtt_clear;
+ ppgtt->vm.pte_encode = gen8_pte_encode;
+
if (intel_vgpu_active(gt->i915))
gen8_ppgtt_notify_vgt(ppgtt, true);
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 322de1577d9c..aed498a0d032 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -159,6 +159,13 @@ static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt)
intel_gtt_chipset_flush();
}
+static u64 gen8_ggtt_pte_encode(dma_addr_t addr,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ return addr | _PAGE_PRESENT;
+}
+
static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
{
writeq(pte, addr);
@@ -174,7 +181,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
gen8_pte_t __iomem *pte =
(gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
- gen8_set_pte(pte, gen8_pte_encode(addr, level, 0));
+ gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, 0));
ggtt->invalidate(ggtt);
}
@@ -187,7 +194,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
struct sgt_iter sgt_iter;
gen8_pte_t __iomem *gtt_entries;
- const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0);
+ const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, 0);
dma_addr_t addr;
/*
@@ -859,7 +866,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
ggtt->vm.vma_ops.set_pages = ggtt_set_pages;
ggtt->vm.vma_ops.clear_pages = clear_pages;
- ggtt->vm.pte_encode = gen8_pte_encode;
+ ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
setup_private_pat(ggtt->vm.gt->uncore);
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index bb9a6e638175..c8db4f95c1b7 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -484,30 +484,6 @@ void gtt_write_workarounds(struct intel_gt *gt)
}
}
-u64 gen8_pte_encode(dma_addr_t addr,
- enum i915_cache_level level,
- u32 flags)
-{
- gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW;
-
- if (unlikely(flags & PTE_READ_ONLY))
- pte &= ~_PAGE_RW;
-
- switch (level) {
- case I915_CACHE_NONE:
- pte |= PPAT_UNCACHED;
- break;
- case I915_CACHE_WT:
- pte |= PPAT_DISPLAY_ELLC;
- break;
- default:
- pte |= PPAT_CACHED;
- break;
- }
-
- return pte;
-}
-
static void tgl_setup_private_ppat(struct intel_uncore *uncore)
{
/* TGL doesn't support LLC or AGE settings */
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index 23004445806a..9a185f4537e1 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -515,10 +515,6 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt);
void i915_ggtt_suspend(struct i915_ggtt *gtt);
void i915_ggtt_resume(struct i915_ggtt *ggtt);
-u64 gen8_pte_encode(dma_addr_t addr,
- enum i915_cache_level level,
- u32 flags);
-
int setup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p);
void cleanup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p);
--
2.28.0