[PATCH] amdgpu: fix asic initialization for virtualized environments

[Andres Rodriguez]

When executing in a PCI passthrough based virtuzliation environemnt, the
hypervisor will usually attempt to send a PCIe bus reset signal to the
ASIC when the VM reboots. In this scenario, the card is not correctly
initialized, but we still consider it to be posted. Therefore, in a
passthrough based environemnt we should always post the card to guarantee
it is in a good state for driver initialization.

However, if we are operating in SR-IOV mode it is up to the GIM driver
to manage the asic state, therefore we should not post the card (and
shouldn't be able to do it either).

Signed-off-by: Andres Rodriguez <andres.rodriguez at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  7 +++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 16 +++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/cik.c           |  7 +++++++
 drivers/gpu/drm/amd/amdgpu/vi.c            | 15 +++++++++++++++
 4 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 26fe670..fe71dea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1835,6 +1835,8 @@ struct amdgpu_asic_funcs {
 	/* MM block clocks */
 	int (*set_uvd_clocks)(struct amdgpu_device *adev, u32 vclk, u32 dclk);
 	int (*set_vce_clocks)(struct amdgpu_device *adev, u32 evclk, u32 ecclk);
+	/* query virtual capabilities */
+	u32 (*get_virtual_caps)(struct amdgpu_device *adev);
 };
 
 /*
@@ -1932,8 +1934,12 @@ void amdgpu_cgs_destroy_device(struct cgs_device *cgs_device);
 
 
 /* GPU virtualization */
+#define AMDGPU_VIRT_CAPS_SRIOV_EN       (1 << 0)
+#define AMDGPU_VIRT_CAPS_IS_VF          (1 << 1)
 struct amdgpu_virtualization {
 	bool supports_sr_iov;
+	bool is_virtual;
+	u32 caps;
 };
 
 /*
@@ -2226,6 +2232,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev))
 #define amdgpu_asic_set_uvd_clocks(adev, v, d) (adev)->asic_funcs->set_uvd_clocks((adev), (v), (d))
 #define amdgpu_asic_set_vce_clocks(adev, ev, ec) (adev)->asic_funcs->set_vce_clocks((adev), (ev), (ec))
+#define amdgpu_asic_get_virtual_caps(adev) ((adev)->asic_funcs->get_virtual_caps((adev)))
 #define amdgpu_asic_get_gpu_clock_counter(adev) (adev)->asic_funcs->get_gpu_clock_counter((adev))
 #define amdgpu_asic_read_disabled_bios(adev) (adev)->asic_funcs->read_disabled_bios((adev))
 #define amdgpu_asic_read_bios_from_rom(adev, b, l) (adev)->asic_funcs->read_bios_from_rom((adev), (b), (l))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b494212..629e4e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1392,6 +1392,14 @@ static int amdgpu_resume(struct amdgpu_device *adev)
 	return 0;
 }
 
+static bool amdgpu_device_is_virtual(void)
+{
+#ifdef CONFIG_X86
+	return boot_cpu_has(X86_FEATURE_HYPERVISOR);
+#else
+	return false
+#endif
+}
 
 /**
  * amdgpu_device_has_dal_support - check if dal is supported
@@ -1560,8 +1568,14 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	adev->virtualization.supports_sr_iov =
 		amdgpu_atombios_has_gpu_virtualization_table(adev);
 
+	/* Check if we are executing in a virtualized environment */
+	adev->virtualization.is_virtual = amdgpu_device_is_virtual();
+	adev->virtualization.caps = amdgpu_asic_get_virtual_caps(adev);
+
 	/* Post card if necessary */
-	if (!amdgpu_card_posted(adev)) {
+	if (!amdgpu_card_posted(adev) ||
+	    (adev->virtualization.is_virtual &&
+	     !adev->virtualization.caps & AMDGPU_VIRT_CAPS_SRIOV_EN)) {
 		if (!adev->bios) {
 			dev_err(adev->dev, "Card not posted and no BIOS - ignoring\n");
 			return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 40f4fda..907bb28 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -963,6 +963,12 @@ static bool cik_read_bios_from_rom(struct amdgpu_device *adev,
 	return true;
 }
 
+static u32 cik_get_virtual_caps(struct amdgpu_device *adev)
+{
+	/* CIK does not support SR-IOV */
+	return 0;
+}
+
 static const struct amdgpu_allowed_register_entry cik_allowed_read_registers[] = {
 	{mmGRBM_STATUS, false},
 	{mmGB_ADDR_CONFIG, false},
@@ -2176,6 +2182,7 @@ static const struct amdgpu_asic_funcs cik_asic_funcs =
 	.get_xclk = &cik_get_xclk,
 	.set_uvd_clocks = &cik_set_uvd_clocks,
 	.set_vce_clocks = &cik_set_vce_clocks,
+	.get_virtual_caps = &cik_get_virtual_caps,
 	/* these should be moved to their own ip modules */
 	.get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter,
 	.wait_for_mc_idle = &gmc_v7_0_mc_wait_for_idle,
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 1ac0c91..6a7d531 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -422,6 +422,20 @@ static bool vi_read_bios_from_rom(struct amdgpu_device *adev,
 	return true;
 }
 
+static u32 vi_get_virtual_caps(struct amdgpu_device *adev)
+{
+	u32 caps = 0;
+	u32 reg = RREG32(mmBIF_IOV_FUNC_IDENTIFIER);
+
+	if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, IOV_ENABLE))
+		caps |= AMDGPU_VIRT_CAPS_SRIOV_EN;
+
+	if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, FUNC_IDENTIFIER))
+		caps |= AMDGPU_VIRT_CAPS_IS_VF;
+
+	return caps;
+}
+
 static const struct amdgpu_allowed_register_entry tonga_allowed_read_registers[] = {
 	{mmGB_MACROTILE_MODE7, true},
 };
@@ -1452,6 +1466,7 @@ static const struct amdgpu_asic_funcs vi_asic_funcs =
 	.get_xclk = &vi_get_xclk,
 	.set_uvd_clocks = &vi_set_uvd_clocks,
 	.set_vce_clocks = &vi_set_vce_clocks,
+	.get_virtual_caps = &vi_get_virtual_caps,
 	/* these should be moved to their own ip modules */
 	.get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter,
 	.wait_for_mc_idle = &gmc_v8_0_mc_wait_for_idle,
-- 
2.8.4