On 1/16/2024 8:56 AM, Ville Syrjala
wrote:
From: Ville Syrjälä <ville.syrjala@xxxxxxxxxxxxxxx> On MTL accessing stolen memory via the BARs is somehow borked, and it can hang the machine. As a workaround let's bypass the BARs and just go straight to DSMBASE/GSMBASE instead. Note that on every other platform this itself would hang the machine, but on MTL the system firmware is expected to relax the access permission guarding stolen memory to enable this workaround, and thus direct CPU accesses should be fine. The raw stolen memory areas won't be passed to VMs so we'll need to risk using the BAR there for the initial setup. Once command submission is up we should switch to MI_UPDATE_GTT which at least shouldn't hang the whole machine. v2: Don't use direct GSM/DSM access on guests Add w/a number Cc: Paz Zcharya <pazz@xxxxxxxxxxxx> Cc: Nirmoy Das <nirmoy.das@xxxxxxxxx> Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx> Reviewed-by: Andrzej Hajda <andrzej.hajda@xxxxxxxxx> Reviewed-by: Radhakrishna Sripada <radhakrishna.sripada@xxxxxxxxx> Signed-off-by: Ville Syrjälä <ville.syrjala@xxxxxxxxxxxxxxx>
I think i915_run_as_guest() should work.
Reviewed-by: Nirmoy Das <nirmoy.das@xxxxxxxxx>
---
drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 14 +++++++++++++-
drivers/gpu/drm/i915/gt/intel_ggtt.c | 16 +++++++++++++++-
2 files changed, 28 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index ee237043c302..0b429f1ecd99 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -941,7 +941,19 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
dsm_size = ALIGN_DOWN(lmem_size - dsm_base, SZ_1M);
}
- if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) {
+ if (IS_METEORLAKE(i915) && !i915_run_as_guest()) {
+ /*
+ * Wa_22018444074
+ *
+ * Access via BAR can hang MTL, go directly to DSM,
+ * except for VM guests which won't have access to it.
+ *
+ * Normally this would not work but on MTL the system firmware
+ * should have relaxed the access permissions sufficiently.
+ */
+ io_start = intel_uncore_read64(uncore, GEN12_DSMBASE) & GEN12_BDSM_MASK;
+ io_size = dsm_size;
+ } else if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) {
io_start = 0;
io_size = 0;
} else {
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 21a7e3191c18..7a716ff16070 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -24,6 +24,7 @@
#include "intel_ring.h"
#include "i915_drv.h"
#include "i915_pci.h"
+#include "i915_reg.h"
#include "i915_request.h"
#include "i915_scatterlist.h"
#include "i915_utils.h"
@@ -1152,13 +1153,26 @@ static unsigned int gen6_gttadr_offset(struct drm_i915_private *i915)
static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
{
struct drm_i915_private *i915 = ggtt->vm.i915;
+ struct intel_uncore *uncore = ggtt->vm.gt->uncore;
struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
phys_addr_t phys_addr;
u32 pte_flags;
int ret;
GEM_WARN_ON(pci_resource_len(pdev, GEN4_GTTMMADR_BAR) != gen6_gttmmadr_size(i915));
- phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915);
+ /*
+ * Wa_22018444074
+ *
+ * Access via BAR can hang MTL, go directly to GSM,
+ * except for VM guests which won't have access to it.
+ *
+ * Normally this would not work but on MTL the system firmware
+ * should have relaxed the access permissions sufficiently.
+ */
+ if (IS_METEORLAKE(i915) && !i915_run_as_guest())
+ phys_addr = intel_uncore_read64(uncore, GEN12_GSMBASE) & GEN12_BDSM_MASK;
+ else
+ phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915);
if (needs_wc_ggtt_mapping(i915))
ggtt->gsm = ioremap_wc(phys_addr, size);
