Merge tag 'amd-drm-next-6.2-2022-11-18' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.2-2022-11-18:

amdgpu:
- SR-IOV fixes
- Clean up DC checks
- DCN 3.2.x fixes
- DCN 3.1.x fixes
- Don't enable degamma on asics which don't support it
- IP discovery fixes
- BACO fixes
- Fix vbios allocation handling when vkms is enabled
- Drop buggy tdr advanced mode GPU reset handling
- Fix the build when DCN is not set in kconfig
- MST DSC fixes
- Userptr fixes
- FRU and RAS EEPROM fixes
- VCN 4.x RAS support
- Aldrebaran CU occupancy reporting fix
- PSP ring cleanup

amdkfd:
- Memory limit fix
- Enable cooperative launch on gfx 10.3

amd-drm-next-6.2-2022-11-11:

amdgpu:
- SMU 13.x updates
- GPUVM TLB race fix
- DCN 3.1.4 updates
- DCN 3.2.x updates
- PSR fixes
- Kerneldoc fix
- Vega10 fan fix
- GPUVM locking fixes in error pathes
- BACO fix for Beige Goby
- EEPROM I2C address cleanup
- GFXOFF fix
- Fix DC memory leak in error pathes
- Flexible array updates
- Mtype fix for GPUVM PTEs
- Move Kconfig into amdgpu directory
- SR-IOV updates
- Fix possible memory leak in CS IOCTL error path

amdkfd:
- Fix possible memory overrun
- CRIU fixes

radeon:
- ACPI ref count fix
- HDA audio notifier support
- Move Kconfig into radeon directory

UAPI:
- Add new GEM_CREATE flags to help to transition more KFD functionality to the DRM UAPI.
  These are used internally in the driver to align location based memory coherency
  requirements from memory allocated in the KFD with how we manage GPUVM PTEs.  They
  are currently blocked in the GEM_CREATE IOCTL as we don't have a user right now.
  They are just used internally in the kernel driver for now for existing KFD memory
  allocations. So a change to the UAPI header, but no functional change in the UAPI.

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221118170807.6505-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 35 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 7268ae65c140..2d9f3f4cd79e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -33,12 +33,29 @@
 
 #include "amdgpu_reset.h"
 
-#define EEPROM_I2C_MADDR_VEGA20         0x0
-#define EEPROM_I2C_MADDR_ARCTURUS       0x40000
-#define EEPROM_I2C_MADDR_ARCTURUS_D342  0x0
-#define EEPROM_I2C_MADDR_SIENNA_CICHLID 0x0
-#define EEPROM_I2C_MADDR_ALDEBARAN      0x0
-#define EEPROM_I2C_MADDR_54H            (0x54UL << 16)
+/* These are memory addresses as would be seen by one or more EEPROM
+ * chips strung on the I2C bus, usually by manipulating pins 1-3 of a
+ * set of EEPROM devices. They form a continuous memory space.
+ *
+ * The I2C device address includes the device type identifier, 1010b,
+ * which is a reserved value and indicates that this is an I2C EEPROM
+ * device. It also includes the top 3 bits of the 19 bit EEPROM memory
+ * address, namely bits 18, 17, and 16. This makes up the 7 bit
+ * address sent on the I2C bus with bit 0 being the direction bit,
+ * which is not represented here, and sent by the hardware directly.
+ *
+ * For instance,
+ *   50h = 1010000b => device type identifier 1010b, bits 18:16 = 000b, address 0.
+ *   54h = 1010100b => --"--, bits 18:16 = 100b, address 40000h.
+ *   56h = 1010110b => --"--, bits 18:16 = 110b, address 60000h.
+ * Depending on the size of the I2C EEPROM device(s), bits 18:16 may
+ * address memory in a device or a device on the I2C bus, depending on
+ * the status of pins 1-3. See top of amdgpu_eeprom.c.
+ *
+ * The RAS table lives either at address 0 or address 40000h of EEPROM.
+ */
+#define EEPROM_I2C_MADDR_0      0x0
+#define EEPROM_I2C_MADDR_4      0x40000
 
 /*
  * The 2 macros bellow represent the actual size in bytes that
@@ -117,9 +134,9 @@ static bool __get_eeprom_i2c_addr_arct(struct amdgpu_device *adev,
 	if (strnstr(atom_ctx->vbios_version,
 	            "D342",
 		    sizeof(atom_ctx->vbios_version)))
-		control->i2c_address = EEPROM_I2C_MADDR_ARCTURUS_D342;
+		control->i2c_address = EEPROM_I2C_MADDR_0;
 	else
-		control->i2c_address = EEPROM_I2C_MADDR_ARCTURUS;
+		control->i2c_address = EEPROM_I2C_MADDR_4;
 
 	return true;
 }
@@ -130,7 +147,7 @@ static bool __get_eeprom_i2c_addr_ip_discovery(struct amdgpu_device *adev,
 	switch (adev->ip_versions[MP1_HWIP][0]) {
 	case IP_VERSION(13, 0, 0):
 	case IP_VERSION(13, 0, 10):
-		control->i2c_address = EEPROM_I2C_MADDR_54H;
+		control->i2c_address = EEPROM_I2C_MADDR_4;
 		return true;
 	default:
 		return false;
@@ -140,6 +157,7 @@ static bool __get_eeprom_i2c_addr_ip_discovery(struct amdgpu_device *adev,
 static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 				  struct amdgpu_ras_eeprom_control *control)
 {
+	struct atom_context *atom_ctx = adev->mode_info.atom_context;
 	u8 i2c_addr;
 
 	if (!control)
@@ -162,18 +180,22 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
-		control->i2c_address = EEPROM_I2C_MADDR_VEGA20;
+		control->i2c_address = EEPROM_I2C_MADDR_0;
 		break;
 
 	case CHIP_ARCTURUS:
 		return __get_eeprom_i2c_addr_arct(adev, control);
 
 	case CHIP_SIENNA_CICHLID:
-		control->i2c_address = EEPROM_I2C_MADDR_SIENNA_CICHLID;
+		control->i2c_address = EEPROM_I2C_MADDR_0;
 		break;
 
 	case CHIP_ALDEBARAN:
-		control->i2c_address = EEPROM_I2C_MADDR_ALDEBARAN;
+		if (strnstr(atom_ctx->vbios_version, "D673",
+			    sizeof(atom_ctx->vbios_version)))
+			control->i2c_address = EEPROM_I2C_MADDR_4;
+		else
+			control->i2c_address = EEPROM_I2C_MADDR_0;
 		break;
 
 	case CHIP_IP_DISCOVERY:
@@ -185,7 +207,7 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 
 	switch (adev->ip_versions[MP1_HWIP][0]) {
 	case IP_VERSION(13, 0, 0):
-		control->i2c_address = EEPROM_I2C_MADDR_54H;
+		control->i2c_address = EEPROM_I2C_MADDR_4;
 		break;
 
 	default: