summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/radeon/cik.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/radeon/cik.c')
-rw-r--r--drivers/gpu/drm/radeon/cik.c179
1 files changed, 77 insertions, 102 deletions
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 5c42877fd6fb..51a3e0fc2f56 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -30,13 +30,18 @@
#include <drm/drm_vblank.h>
#include "atom.h"
+#include "evergreen.h"
#include "cik_blit_shaders.h"
+#include "cik.h"
#include "cikd.h"
#include "clearstate_ci.h"
+#include "r600.h"
#include "radeon.h"
#include "radeon_asic.h"
#include "radeon_audio.h"
#include "radeon_ucode.h"
+#include "si.h"
+#include "vce.h"
#define SH_MEM_CONFIG_GFX_DEFAULT \
ALIGNMENT_MODE(SH_MEM_ALIGNMENT_MODE_UNALIGNED)
@@ -124,21 +129,7 @@ MODULE_FIRMWARE("radeon/mullins_mec.bin");
MODULE_FIRMWARE("radeon/mullins_rlc.bin");
MODULE_FIRMWARE("radeon/mullins_sdma.bin");
-extern int r600_ih_ring_alloc(struct radeon_device *rdev);
-extern void r600_ih_ring_fini(struct radeon_device *rdev);
-extern void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save);
-extern void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save);
-extern bool evergreen_is_display_hung(struct radeon_device *rdev);
-extern void sumo_rlc_fini(struct radeon_device *rdev);
-extern int sumo_rlc_init(struct radeon_device *rdev);
-extern void si_vram_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
-extern void si_rlc_reset(struct radeon_device *rdev);
-extern void si_init_uvd_internal_cg(struct radeon_device *rdev);
static u32 cik_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh);
-extern int cik_sdma_resume(struct radeon_device *rdev);
-extern void cik_sdma_enable(struct radeon_device *rdev, bool enable);
-extern void cik_sdma_fini(struct radeon_device *rdev);
-extern void vce_v2_0_enable_mgcg(struct radeon_device *rdev, bool enable);
static void cik_rlc_stop(struct radeon_device *rdev);
static void cik_pcie_gen3_enable(struct radeon_device *rdev);
static void cik_program_aspm(struct radeon_device *rdev);
@@ -3071,8 +3062,7 @@ static u32 cik_create_bitmask(u32 bit_width)
* cik_get_rb_disabled - computes the mask of disabled RBs
*
* @rdev: radeon_device pointer
- * @max_rb_num: max RBs (render backends) for the asic
- * @se_num: number of SEs (shader engines) for the asic
+ * @max_rb_num_per_se: max RBs (render backends) per SE (shader engine) for the asic
* @sh_per_se: number of SH blocks per SE for the asic
*
* Calculates the bitmask of disabled RBs (CIK).
@@ -3104,7 +3094,7 @@ static u32 cik_get_rb_disabled(struct radeon_device *rdev,
* @rdev: radeon_device pointer
* @se_num: number of SEs (shader engines) for the asic
* @sh_per_se: number of SH blocks per SE for the asic
- * @max_rb_num: max RBs (render backends) for the asic
+ * @max_rb_num_per_se: max RBs (render backends) per SE for the asic
*
* Configures per-SE/SH RB registers (CIK).
*/
@@ -3178,7 +3168,7 @@ static void cik_setup_rb(struct radeon_device *rdev,
static void cik_gpu_init(struct radeon_device *rdev)
{
u32 gb_addr_config = RREG32(GB_ADDR_CONFIG);
- u32 mc_shared_chmap, mc_arb_ramcfg;
+ u32 mc_arb_ramcfg;
u32 hdp_host_path_cntl;
u32 tmp;
int i, j;
@@ -3271,7 +3261,7 @@ static void cik_gpu_init(struct radeon_device *rdev)
WREG32(BIF_FB_EN, FB_READ_EN | FB_WRITE_EN);
- mc_shared_chmap = RREG32(MC_SHARED_CHMAP);
+ RREG32(MC_SHARED_CHMAP);
mc_arb_ramcfg = RREG32(MC_ARB_RAMCFG);
rdev->config.cik.num_tile_pipes = rdev->config.cik.max_tile_pipes;
@@ -3613,7 +3603,7 @@ void cik_fence_compute_ring_emit(struct radeon_device *rdev,
* @rdev: radeon_device pointer
* @ring: radeon ring buffer object
* @semaphore: radeon semaphore object
- * @emit_wait: Is this a sempahore wait?
+ * @emit_wait: Is this a semaphore wait?
*
* Emits a semaphore signal/wait packet to the CP ring and prevents the PFP
* from running ahead of semaphore waits.
@@ -5654,6 +5644,7 @@ void cik_vm_fini(struct radeon_device *rdev)
* @rdev: radeon_device pointer
* @status: VM_CONTEXT1_PROTECTION_FAULT_STATUS register value
* @addr: VM_CONTEXT1_PROTECTION_FAULT_ADDR register value
+ * @mc_client: VM_CONTEXT1_PROTECTION_FAULT_MCCLIENT register value
*
* Print human readable fault information (CIK).
*/
@@ -5677,11 +5668,9 @@ static void cik_vm_decode_fault(struct radeon_device *rdev,
block, mc_client, mc_id);
}
-/**
+/*
* cik_vm_flush - cik vm flush using the CP
*
- * @rdev: radeon_device pointer
- *
* Update the page table base and flush the VM TLB
* using the CP (CIK).
*/
@@ -7450,7 +7439,7 @@ static void cik_irq_disable(struct radeon_device *rdev)
}
/**
- * cik_irq_disable - disable interrupts for suspend
+ * cik_irq_suspend - disable interrupts for suspend
*
* @rdev: radeon_device pointer
*
@@ -7596,7 +7585,7 @@ restart_ih:
DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
if (rdev->irq.crtc_vblank_int[0]) {
- drm_handle_vblank(rdev->ddev, 0);
+ drm_handle_vblank(rdev_to_drm(rdev), 0);
rdev->pm.vblank_sync = true;
wake_up(&rdev->irq.vblank_queue);
}
@@ -7626,7 +7615,7 @@ restart_ih:
DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
if (rdev->irq.crtc_vblank_int[1]) {
- drm_handle_vblank(rdev->ddev, 1);
+ drm_handle_vblank(rdev_to_drm(rdev), 1);
rdev->pm.vblank_sync = true;
wake_up(&rdev->irq.vblank_queue);
}
@@ -7656,7 +7645,7 @@ restart_ih:
DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
if (rdev->irq.crtc_vblank_int[2]) {
- drm_handle_vblank(rdev->ddev, 2);
+ drm_handle_vblank(rdev_to_drm(rdev), 2);
rdev->pm.vblank_sync = true;
wake_up(&rdev->irq.vblank_queue);
}
@@ -7686,7 +7675,7 @@ restart_ih:
DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
if (rdev->irq.crtc_vblank_int[3]) {
- drm_handle_vblank(rdev->ddev, 3);
+ drm_handle_vblank(rdev_to_drm(rdev), 3);
rdev->pm.vblank_sync = true;
wake_up(&rdev->irq.vblank_queue);
}
@@ -7716,7 +7705,7 @@ restart_ih:
DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
if (rdev->irq.crtc_vblank_int[4]) {
- drm_handle_vblank(rdev->ddev, 4);
+ drm_handle_vblank(rdev_to_drm(rdev), 4);
rdev->pm.vblank_sync = true;
wake_up(&rdev->irq.vblank_queue);
}
@@ -7746,7 +7735,7 @@ restart_ih:
DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
if (rdev->irq.crtc_vblank_int[5]) {
- drm_handle_vblank(rdev->ddev, 5);
+ drm_handle_vblank(rdev_to_drm(rdev), 5);
rdev->pm.vblank_sync = true;
wake_up(&rdev->irq.vblank_queue);
}
@@ -7959,8 +7948,6 @@ restart_ih:
DRM_ERROR("Illegal register access in command stream\n");
/* XXX check the bitfield order! */
me_id = (ring_id & 0x60) >> 5;
- pipe_id = (ring_id & 0x18) >> 3;
- queue_id = (ring_id & 0x7) >> 0;
switch (me_id) {
case 0:
/* This results in a full GPU reset, but all we need to do is soft
@@ -7982,8 +7969,6 @@ restart_ih:
DRM_ERROR("Illegal instruction in command stream\n");
/* XXX check the bitfield order! */
me_id = (ring_id & 0x60) >> 5;
- pipe_id = (ring_id & 0x18) >> 3;
- queue_id = (ring_id & 0x7) >> 0;
switch (me_id) {
case 0:
/* This results in a full GPU reset, but all we need to do is soft
@@ -8532,8 +8517,8 @@ int cik_suspend(struct radeon_device *rdev)
cik_cp_enable(rdev, false);
cik_sdma_enable(rdev, false);
if (rdev->has_uvd) {
- uvd_v1_0_fini(rdev);
radeon_uvd_suspend(rdev);
+ uvd_v1_0_fini(rdev);
}
if (rdev->has_vce)
radeon_vce_suspend(rdev);
@@ -8563,7 +8548,7 @@ int cik_suspend(struct radeon_device *rdev)
*/
int cik_init(struct radeon_device *rdev)
{
- struct radeon_ring *ring;
+ struct radeon_ring *ring, *ring_cp1, *ring_cp2;
int r;
/* Read BIOS */
@@ -8596,12 +8581,10 @@ int cik_init(struct radeon_device *rdev)
/* Initialize surface registers */
radeon_surface_init(rdev);
/* Initialize clocks */
- radeon_get_clock_info(rdev->ddev);
+ radeon_get_clock_info(rdev_to_drm(rdev));
/* Fence driver */
- r = radeon_fence_driver_init(rdev);
- if (r)
- return r;
+ radeon_fence_driver_init(rdev);
/* initialize memory controller */
r = cik_mc_init(rdev);
@@ -8640,19 +8623,22 @@ int cik_init(struct radeon_device *rdev)
ring->ring_obj = NULL;
r600_ring_init(rdev, ring, 1024 * 1024);
- ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
- ring->ring_obj = NULL;
- r600_ring_init(rdev, ring, 1024 * 1024);
- r = radeon_doorbell_get(rdev, &ring->doorbell_index);
+ ring_cp1 = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
+ ring_cp2 = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
+ ring_cp1->ring_obj = NULL;
+ ring_cp2->ring_obj = NULL;
+ ring_cp1->doorbell_index = RADEON_MAX_DOORBELLS;
+ ring_cp2->doorbell_index = RADEON_MAX_DOORBELLS;
+
+ r600_ring_init(rdev, ring_cp1, 1024 * 1024);
+ r = radeon_doorbell_get(rdev, &ring_cp1->doorbell_index);
if (r)
return r;
- ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
- ring->ring_obj = NULL;
- r600_ring_init(rdev, ring, 1024 * 1024);
- r = radeon_doorbell_get(rdev, &ring->doorbell_index);
+ r600_ring_init(rdev, ring_cp2, 1024 * 1024);
+ r = radeon_doorbell_get(rdev, &ring_cp2->doorbell_index);
if (r)
- return r;
+ goto out;
ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
ring->ring_obj = NULL;
@@ -8670,12 +8656,16 @@ int cik_init(struct radeon_device *rdev)
r = r600_pcie_gart_init(rdev);
if (r)
- return r;
+ goto out;
rdev->accel_working = true;
r = cik_startup(rdev);
if (r) {
dev_err(rdev->dev, "disabling GPU acceleration\n");
+ radeon_doorbell_free(rdev, ring_cp1->doorbell_index);
+ radeon_doorbell_free(rdev, ring_cp2->doorbell_index);
+ ring_cp1->doorbell_index = RADEON_MAX_DOORBELLS;
+ ring_cp2->doorbell_index = RADEON_MAX_DOORBELLS;
cik_cp_fini(rdev);
cik_sdma_fini(rdev);
cik_irq_fini(rdev);
@@ -8695,10 +8685,16 @@ int cik_init(struct radeon_device *rdev)
*/
if (!rdev->mc_fw && !(rdev->flags & RADEON_IS_IGP)) {
DRM_ERROR("radeon: MC ucode required for NI+.\n");
- return -EINVAL;
+ r = -EINVAL;
+ goto out;
}
return 0;
+
+out:
+ radeon_doorbell_free(rdev, ring_cp1->doorbell_index);
+ radeon_doorbell_free(rdev, ring_cp2->doorbell_index);
+ return r;
}
/**
@@ -8712,6 +8708,7 @@ int cik_init(struct radeon_device *rdev)
*/
void cik_fini(struct radeon_device *rdev)
{
+ struct radeon_ring *ring;
radeon_pm_fini(rdev);
cik_cp_fini(rdev);
cik_sdma_fini(rdev);
@@ -8725,6 +8722,10 @@ void cik_fini(struct radeon_device *rdev)
radeon_ib_pool_fini(rdev);
radeon_irq_kms_fini(rdev);
uvd_v1_0_fini(rdev);
+ ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
+ radeon_doorbell_free(rdev, ring->doorbell_index);
+ ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
+ radeon_doorbell_free(rdev, ring->doorbell_index);
radeon_uvd_fini(rdev);
radeon_vce_fini(rdev);
cik_pcie_gart_fini(rdev);
@@ -9551,17 +9552,8 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
u16 bridge_cfg2, gpu_cfg2;
u32 max_lw, current_lw, tmp;
- pcie_capability_read_word(root, PCI_EXP_LNKCTL,
- &bridge_cfg);
- pcie_capability_read_word(rdev->pdev, PCI_EXP_LNKCTL,
- &gpu_cfg);
-
- tmp16 = bridge_cfg | PCI_EXP_LNKCTL_HAWD;
- pcie_capability_write_word(root, PCI_EXP_LNKCTL, tmp16);
-
- tmp16 = gpu_cfg | PCI_EXP_LNKCTL_HAWD;
- pcie_capability_write_word(rdev->pdev, PCI_EXP_LNKCTL,
- tmp16);
+ pcie_capability_set_word(root, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_HAWD);
+ pcie_capability_set_word(rdev->pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_HAWD);
tmp = RREG32_PCIE_PORT(PCIE_LC_STATUS1);
max_lw = (tmp & LC_DETECTED_LINK_WIDTH_MASK) >> LC_DETECTED_LINK_WIDTH_SHIFT;
@@ -9608,45 +9600,28 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
msleep(100);
/* linkctl */
- pcie_capability_read_word(root, PCI_EXP_LNKCTL,
- &tmp16);
- tmp16 &= ~PCI_EXP_LNKCTL_HAWD;
- tmp16 |= (bridge_cfg & PCI_EXP_LNKCTL_HAWD);
- pcie_capability_write_word(root, PCI_EXP_LNKCTL,
- tmp16);
-
- pcie_capability_read_word(rdev->pdev,
- PCI_EXP_LNKCTL,
- &tmp16);
- tmp16 &= ~PCI_EXP_LNKCTL_HAWD;
- tmp16 |= (gpu_cfg & PCI_EXP_LNKCTL_HAWD);
- pcie_capability_write_word(rdev->pdev,
- PCI_EXP_LNKCTL,
- tmp16);
+ pcie_capability_clear_and_set_word(root, PCI_EXP_LNKCTL,
+ PCI_EXP_LNKCTL_HAWD,
+ bridge_cfg &
+ PCI_EXP_LNKCTL_HAWD);
+ pcie_capability_clear_and_set_word(rdev->pdev, PCI_EXP_LNKCTL,
+ PCI_EXP_LNKCTL_HAWD,
+ gpu_cfg &
+ PCI_EXP_LNKCTL_HAWD);
/* linkctl2 */
- pcie_capability_read_word(root, PCI_EXP_LNKCTL2,
- &tmp16);
- tmp16 &= ~(PCI_EXP_LNKCTL2_ENTER_COMP |
- PCI_EXP_LNKCTL2_TX_MARGIN);
- tmp16 |= (bridge_cfg2 &
- (PCI_EXP_LNKCTL2_ENTER_COMP |
- PCI_EXP_LNKCTL2_TX_MARGIN));
- pcie_capability_write_word(root,
- PCI_EXP_LNKCTL2,
- tmp16);
-
- pcie_capability_read_word(rdev->pdev,
- PCI_EXP_LNKCTL2,
- &tmp16);
- tmp16 &= ~(PCI_EXP_LNKCTL2_ENTER_COMP |
- PCI_EXP_LNKCTL2_TX_MARGIN);
- tmp16 |= (gpu_cfg2 &
- (PCI_EXP_LNKCTL2_ENTER_COMP |
- PCI_EXP_LNKCTL2_TX_MARGIN));
- pcie_capability_write_word(rdev->pdev,
- PCI_EXP_LNKCTL2,
- tmp16);
+ pcie_capability_clear_and_set_word(root, PCI_EXP_LNKCTL2,
+ PCI_EXP_LNKCTL2_ENTER_COMP |
+ PCI_EXP_LNKCTL2_TX_MARGIN,
+ bridge_cfg2 |
+ (PCI_EXP_LNKCTL2_ENTER_COMP |
+ PCI_EXP_LNKCTL2_TX_MARGIN));
+ pcie_capability_clear_and_set_word(rdev->pdev, PCI_EXP_LNKCTL2,
+ PCI_EXP_LNKCTL2_ENTER_COMP |
+ PCI_EXP_LNKCTL2_TX_MARGIN,
+ gpu_cfg2 |
+ (PCI_EXP_LNKCTL2_ENTER_COMP |
+ PCI_EXP_LNKCTL2_TX_MARGIN));
tmp = RREG32_PCIE_PORT(PCIE_LC_CNTL4);
tmp &= ~LC_SET_QUIESCE;
@@ -9660,15 +9635,15 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
speed_cntl &= ~LC_FORCE_DIS_SW_SPEED_CHANGE;
WREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL, speed_cntl);
- pcie_capability_read_word(rdev->pdev, PCI_EXP_LNKCTL2, &tmp16);
- tmp16 &= ~PCI_EXP_LNKCTL2_TLS;
+ tmp16 = 0;
if (speed_cap == PCIE_SPEED_8_0GT)
tmp16 |= PCI_EXP_LNKCTL2_TLS_8_0GT; /* gen3 */
else if (speed_cap == PCIE_SPEED_5_0GT)
tmp16 |= PCI_EXP_LNKCTL2_TLS_5_0GT; /* gen2 */
else
tmp16 |= PCI_EXP_LNKCTL2_TLS_2_5GT; /* gen1 */
- pcie_capability_write_word(rdev->pdev, PCI_EXP_LNKCTL2, tmp16);
+ pcie_capability_clear_and_set_word(rdev->pdev, PCI_EXP_LNKCTL2,
+ PCI_EXP_LNKCTL2_TLS, tmp16);
speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
speed_cntl |= LC_INITIATE_LINK_SPEED_CHANGE;
generated by cgit (git 2.34.1) at 2025-12-25 20:13:03 +0000