aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/radeon/r100.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/radeon/r100.c')
-rw-r--r--drivers/gpu/drm/radeon/r100.c525
1 files changed, 235 insertions, 290 deletions
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 376884f1bcd..1544efcf1c3 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -39,7 +39,6 @@
#include "atom.h"
#include <linux/firmware.h>
-#include <linux/platform_device.h>
#include <linux/module.h>
#include "r100_reg_safe.h"
@@ -69,6 +68,38 @@ MODULE_FIRMWARE(FIRMWARE_R520);
* and others in some cases.
*/
+static bool r100_is_in_vblank(struct radeon_device *rdev, int crtc)
+{
+ if (crtc == 0) {
+ if (RREG32(RADEON_CRTC_STATUS) & RADEON_CRTC_VBLANK_CUR)
+ return true;
+ else
+ return false;
+ } else {
+ if (RREG32(RADEON_CRTC2_STATUS) & RADEON_CRTC2_VBLANK_CUR)
+ return true;
+ else
+ return false;
+ }
+}
+
+static bool r100_is_counter_moving(struct radeon_device *rdev, int crtc)
+{
+ u32 vline1, vline2;
+
+ if (crtc == 0) {
+ vline1 = (RREG32(RADEON_CRTC_VLINE_CRNT_VLINE) >> 16) & RADEON_CRTC_V_TOTAL;
+ vline2 = (RREG32(RADEON_CRTC_VLINE_CRNT_VLINE) >> 16) & RADEON_CRTC_V_TOTAL;
+ } else {
+ vline1 = (RREG32(RADEON_CRTC2_VLINE_CRNT_VLINE) >> 16) & RADEON_CRTC_V_TOTAL;
+ vline2 = (RREG32(RADEON_CRTC2_VLINE_CRNT_VLINE) >> 16) & RADEON_CRTC_V_TOTAL;
+ }
+ if (vline1 != vline2)
+ return true;
+ else
+ return false;
+}
+
/**
* r100_wait_for_vblank - vblank wait asic callback.
*
@@ -79,68 +110,35 @@ MODULE_FIRMWARE(FIRMWARE_R520);
*/
void r100_wait_for_vblank(struct radeon_device *rdev, int crtc)
{
- int i;
+ unsigned i = 0;
if (crtc >= rdev->num_crtc)
return;
if (crtc == 0) {
- if (RREG32(RADEON_CRTC_GEN_CNTL) & RADEON_CRTC_EN) {
- for (i = 0; i < rdev->usec_timeout; i++) {
- if (!(RREG32(RADEON_CRTC_STATUS) & RADEON_CRTC_VBLANK_CUR))
- break;
- udelay(1);
- }
- for (i = 0; i < rdev->usec_timeout; i++) {
- if (RREG32(RADEON_CRTC_STATUS) & RADEON_CRTC_VBLANK_CUR)
- break;
- udelay(1);
- }
- }
+ if (!(RREG32(RADEON_CRTC_GEN_CNTL) & RADEON_CRTC_EN))
+ return;
} else {
- if (RREG32(RADEON_CRTC2_GEN_CNTL) & RADEON_CRTC2_EN) {
- for (i = 0; i < rdev->usec_timeout; i++) {
- if (!(RREG32(RADEON_CRTC2_STATUS) & RADEON_CRTC2_VBLANK_CUR))
- break;
- udelay(1);
- }
- for (i = 0; i < rdev->usec_timeout; i++) {
- if (RREG32(RADEON_CRTC2_STATUS) & RADEON_CRTC2_VBLANK_CUR)
- break;
- udelay(1);
- }
- }
+ if (!(RREG32(RADEON_CRTC2_GEN_CNTL) & RADEON_CRTC2_EN))
+ return;
}
-}
-/**
- * r100_pre_page_flip - pre-pageflip callback.
- *
- * @rdev: radeon_device pointer
- * @crtc: crtc to prepare for pageflip on
- *
- * Pre-pageflip callback (r1xx-r4xx).
- * Enables the pageflip irq (vblank irq).
- */
-void r100_pre_page_flip(struct radeon_device *rdev, int crtc)
-{
- /* enable the pflip int */
- radeon_irq_kms_pflip_irq_get(rdev, crtc);
-}
+ /* depending on when we hit vblank, we may be close to active; if so,
+ * wait for another frame.
+ */
+ while (r100_is_in_vblank(rdev, crtc)) {
+ if (i++ % 100 == 0) {
+ if (!r100_is_counter_moving(rdev, crtc))
+ break;
+ }
+ }
-/**
- * r100_post_page_flip - pos-pageflip callback.
- *
- * @rdev: radeon_device pointer
- * @crtc: crtc to cleanup pageflip on
- *
- * Post-pageflip callback (r1xx-r4xx).
- * Disables the pageflip irq (vblank irq).
- */
-void r100_post_page_flip(struct radeon_device *rdev, int crtc)
-{
- /* disable the pflip int */
- radeon_irq_kms_pflip_irq_put(rdev, crtc);
+ while (!r100_is_in_vblank(rdev, crtc)) {
+ if (i++ % 100 == 0) {
+ if (!r100_is_counter_moving(rdev, crtc))
+ break;
+ }
+ }
}
/**
@@ -154,9 +152,8 @@ void r100_post_page_flip(struct radeon_device *rdev, int crtc)
* During vblank we take the crtc lock and wait for the update_pending
* bit to go high, when it does, we release the lock, and allow the
* double buffered update to take place.
- * Returns the current update pending status.
*/
-u32 r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
+void r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
{
struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
u32 tmp = ((u32)crtc_base) | RADEON_CRTC_OFFSET__OFFSET_LOCK;
@@ -178,8 +175,24 @@ u32 r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
tmp &= ~RADEON_CRTC_OFFSET__OFFSET_LOCK;
WREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset, tmp);
+}
+
+/**
+ * r100_page_flip_pending - check if page flip is still pending
+ *
+ * @rdev: radeon_device pointer
+ * @crtc_id: crtc to check
+ *
+ * Check if the last pagefilp is still pending (r1xx-r4xx).
+ * Returns the current update pending status.
+ */
+bool r100_page_flip_pending(struct radeon_device *rdev, int crtc_id)
+{
+ struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+
/* Return current update_pending status: */
- return RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) & RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET;
+ return !!(RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) &
+ RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET);
}
/**
@@ -669,15 +682,11 @@ void r100_pci_gart_disable(struct radeon_device *rdev)
WREG32(RADEON_AIC_HI_ADDR, 0);
}
-int r100_pci_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
+void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
+ uint64_t addr)
{
u32 *gtt = rdev->gart.ptr;
-
- if (i < 0 || i > rdev->gart.num_gpu_pages) {
- return -EINVAL;
- }
gtt[i] = cpu_to_le32(lower_32_bits(addr));
- return 0;
}
void r100_pci_gart_fini(struct radeon_device *rdev)
@@ -766,7 +775,7 @@ int r100_irq_process(struct radeon_device *rdev)
wake_up(&rdev->irq.vblank_queue);
}
if (atomic_read(&rdev->irq.pflip[0]))
- radeon_crtc_handle_flip(rdev, 0);
+ radeon_crtc_handle_vblank(rdev, 0);
}
if (status & RADEON_CRTC2_VBLANK_STAT) {
if (rdev->irq.crtc_vblank_int[1]) {
@@ -775,7 +784,7 @@ int r100_irq_process(struct radeon_device *rdev)
wake_up(&rdev->irq.vblank_queue);
}
if (atomic_read(&rdev->irq.pflip[1]))
- radeon_crtc_handle_flip(rdev, 1);
+ radeon_crtc_handle_vblank(rdev, 1);
}
if (status & RADEON_FP_DETECT_STAT) {
queue_hotplug = true;
@@ -841,13 +850,14 @@ void r100_fence_ring_emit(struct radeon_device *rdev,
radeon_ring_write(ring, RADEON_SW_INT_FIRE);
}
-void r100_semaphore_ring_emit(struct radeon_device *rdev,
+bool r100_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait)
{
/* Unused on older asics, since we don't have semaphores or multiple rings */
BUG();
+ return false;
}
int r100_copy_blit(struct radeon_device *rdev,
@@ -960,18 +970,11 @@ void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring)
/* Load the microcode for the CP */
static int r100_cp_init_microcode(struct radeon_device *rdev)
{
- struct platform_device *pdev;
const char *fw_name = NULL;
int err;
DRM_DEBUG_KMS("\n");
- pdev = platform_device_register_simple("radeon_cp", 0, NULL, 0);
- err = IS_ERR(pdev);
- if (err) {
- printk(KERN_ERR "radeon_cp: Failed to register firmware\n");
- return -EINVAL;
- }
if ((rdev->family == CHIP_R100) || (rdev->family == CHIP_RV100) ||
(rdev->family == CHIP_RV200) || (rdev->family == CHIP_RS100) ||
(rdev->family == CHIP_RS200)) {
@@ -1013,8 +1016,7 @@ static int r100_cp_init_microcode(struct radeon_device *rdev)
fw_name = FIRMWARE_R520;
}
- err = request_firmware(&rdev->me_fw, fw_name, &pdev->dev);
- platform_device_unregister(pdev);
+ err = request_firmware(&rdev->me_fw, fw_name, rdev->dev);
if (err) {
printk(KERN_ERR "radeon_cp: Failed to load firmware \"%s\"\n",
fw_name);
@@ -1029,6 +1031,36 @@ static int r100_cp_init_microcode(struct radeon_device *rdev)
return err;
}
+u32 r100_gfx_get_rptr(struct radeon_device *rdev,
+ struct radeon_ring *ring)
+{
+ u32 rptr;
+
+ if (rdev->wb.enabled)
+ rptr = le32_to_cpu(rdev->wb.wb[ring->rptr_offs/4]);
+ else
+ rptr = RREG32(RADEON_CP_RB_RPTR);
+
+ return rptr;
+}
+
+u32 r100_gfx_get_wptr(struct radeon_device *rdev,
+ struct radeon_ring *ring)
+{
+ u32 wptr;
+
+ wptr = RREG32(RADEON_CP_RB_WPTR);
+
+ return wptr;
+}
+
+void r100_gfx_set_wptr(struct radeon_device *rdev,
+ struct radeon_ring *ring)
+{
+ WREG32(RADEON_CP_RB_WPTR, ring->wptr);
+ (void)RREG32(RADEON_CP_RB_WPTR);
+}
+
static void r100_cp_load_microcode(struct radeon_device *rdev)
{
const __be32 *fw_data;
@@ -1077,12 +1109,11 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
}
/* Align ring size */
- rb_bufsz = drm_order(ring_size / 8);
+ rb_bufsz = order_base_2(ring_size / 8);
ring_size = (1 << (rb_bufsz + 1)) * 4;
r100_cp_load_microcode(rdev);
r = radeon_ring_init(rdev, ring, ring_size, RADEON_WB_CP_RPTR_OFFSET,
- RADEON_CP_RB_RPTR, RADEON_CP_RB_WPTR,
- 0, 0x7fffff, RADEON_CP_PACKET2);
+ RADEON_CP_PACKET2);
if (r) {
return r;
}
@@ -1143,7 +1174,6 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
WREG32(RADEON_CP_RB_CNTL, tmp);
udelay(10);
- ring->rptr = RREG32(RADEON_CP_RB_RPTR);
/* Set cp mode to bus mastering & enable cp*/
WREG32(RADEON_CP_CSQ_MODE,
REG_SET(RADEON_INDIRECT2_START, indirect2_start) |
@@ -1215,25 +1245,25 @@ int r100_reloc_pitch_offset(struct radeon_cs_parser *p,
struct radeon_cs_reloc *reloc;
u32 value;
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
idx, reg);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
value = radeon_get_ib_value(p, idx);
tmp = value & 0x003fffff;
- tmp += (((u32)reloc->lobj.gpu_offset) >> 10);
+ tmp += (((u32)reloc->gpu_offset) >> 10);
if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+ if (reloc->tiling_flags & RADEON_TILING_MACRO)
tile_flags |= RADEON_DST_TILE_MACRO;
- if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
+ if (reloc->tiling_flags & RADEON_TILING_MICRO) {
if (reg == RADEON_SRC_PITCH_OFFSET) {
DRM_ERROR("Cannot src blit from microtiled surface\n");
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return -EINVAL;
}
tile_flags |= RADEON_DST_TILE_MICRO;
@@ -1263,46 +1293,46 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
if (c > 16) {
DRM_ERROR("Only 16 vertex buffers are allowed %d\n",
pkt->opcode);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return -EINVAL;
}
track->num_arrays = c;
for (i = 0; i < (c - 1); i+=2, idx+=3) {
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for packet3 %d\n",
pkt->opcode);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
idx_value = radeon_get_ib_value(p, idx);
- ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->lobj.gpu_offset);
+ ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->gpu_offset);
track->arrays[i + 0].esize = idx_value >> 8;
track->arrays[i + 0].robj = reloc->robj;
track->arrays[i + 0].esize &= 0x7F;
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for packet3 %d\n",
pkt->opcode);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
- ib[idx+2] = radeon_get_ib_value(p, idx + 2) + ((u32)reloc->lobj.gpu_offset);
+ ib[idx+2] = radeon_get_ib_value(p, idx + 2) + ((u32)reloc->gpu_offset);
track->arrays[i + 1].robj = reloc->robj;
track->arrays[i + 1].esize = idx_value >> 24;
track->arrays[i + 1].esize &= 0x7F;
}
if (c & 1) {
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for packet3 %d\n",
pkt->opcode);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
idx_value = radeon_get_ib_value(p, idx);
- ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->lobj.gpu_offset);
+ ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->gpu_offset);
track->arrays[i + 0].robj = reloc->robj;
track->arrays[i + 0].esize = idx_value >> 8;
track->arrays[i + 0].esize &= 0x7F;
@@ -1355,67 +1385,6 @@ int r100_cs_parse_packet0(struct radeon_cs_parser *p,
return 0;
}
-void r100_cs_dump_packet(struct radeon_cs_parser *p,
- struct radeon_cs_packet *pkt)
-{
- volatile uint32_t *ib;
- unsigned i;
- unsigned idx;
-
- ib = p->ib.ptr;
- idx = pkt->idx;
- for (i = 0; i <= (pkt->count + 1); i++, idx++) {
- DRM_INFO("ib[%d]=0x%08X\n", idx, ib[idx]);
- }
-}
-
-/**
- * r100_cs_packet_parse() - parse cp packet and point ib index to next packet
- * @parser: parser structure holding parsing context.
- * @pkt: where to store packet informations
- *
- * Assume that chunk_ib_index is properly set. Will return -EINVAL
- * if packet is bigger than remaining ib size. or if packets is unknown.
- **/
-int r100_cs_packet_parse(struct radeon_cs_parser *p,
- struct radeon_cs_packet *pkt,
- unsigned idx)
-{
- struct radeon_cs_chunk *ib_chunk = &p->chunks[p->chunk_ib_idx];
- uint32_t header;
-
- if (idx >= ib_chunk->length_dw) {
- DRM_ERROR("Can not parse packet at %d after CS end %d !\n",
- idx, ib_chunk->length_dw);
- return -EINVAL;
- }
- header = radeon_get_ib_value(p, idx);
- pkt->idx = idx;
- pkt->type = CP_PACKET_GET_TYPE(header);
- pkt->count = CP_PACKET_GET_COUNT(header);
- switch (pkt->type) {
- case PACKET_TYPE0:
- pkt->reg = CP_PACKET0_GET_REG(header);
- pkt->one_reg_wr = CP_PACKET0_GET_ONE_REG_WR(header);
- break;
- case PACKET_TYPE3:
- pkt->opcode = CP_PACKET3_GET_OPCODE(header);
- break;
- case PACKET_TYPE2:
- pkt->count = -1;
- break;
- default:
- DRM_ERROR("Unknown packet type %d at %d !\n", pkt->type, idx);
- return -EINVAL;
- }
- if ((pkt->count + 1 + pkt->idx) >= ib_chunk->length_dw) {
- DRM_ERROR("Packet (%d:%d:%d) end after CS buffer (%d) !\n",
- pkt->idx, pkt->type, pkt->count, ib_chunk->length_dw);
- return -EINVAL;
- }
- return 0;
-}
-
/**
* r100_cs_packet_next_vline() - parse userspace VLINE packet
* @parser: parser structure holding parsing context.
@@ -1444,7 +1413,7 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
ib = p->ib.ptr;
/* parse the wait until */
- r = r100_cs_packet_parse(p, &waitreloc, p->idx);
+ r = radeon_cs_packet_parse(p, &waitreloc, p->idx);
if (r)
return r;
@@ -1461,7 +1430,7 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
}
/* jump over the NOP */
- r = r100_cs_packet_parse(p, &p3reloc, p->idx + waitreloc.count + 2);
+ r = radeon_cs_packet_parse(p, &p3reloc, p->idx + waitreloc.count + 2);
if (r)
return r;
@@ -1471,11 +1440,11 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
header = radeon_get_ib_value(p, h_idx);
crtc_id = radeon_get_ib_value(p, h_idx + 5);
- reg = CP_PACKET0_GET_REG(header);
+ reg = R100_CP_PACKET0_GET_REG(header);
obj = drm_mode_object_find(p->rdev->ddev, crtc_id, DRM_MODE_OBJECT_CRTC);
if (!obj) {
DRM_ERROR("cannot find crtc %d\n", crtc_id);
- return -EINVAL;
+ return -ENOENT;
}
crtc = obj_to_crtc(obj);
radeon_crtc = to_radeon_crtc(crtc);
@@ -1506,54 +1475,6 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
return 0;
}
-/**
- * r100_cs_packet_next_reloc() - parse next packet which should be reloc packet3
- * @parser: parser structure holding parsing context.
- * @data: pointer to relocation data
- * @offset_start: starting offset
- * @offset_mask: offset mask (to align start offset on)
- * @reloc: reloc informations
- *
- * Check next packet is relocation packet3, do bo validation and compute
- * GPU offset using the provided start.
- **/
-int r100_cs_packet_next_reloc(struct radeon_cs_parser *p,
- struct radeon_cs_reloc **cs_reloc)
-{
- struct radeon_cs_chunk *relocs_chunk;
- struct radeon_cs_packet p3reloc;
- unsigned idx;
- int r;
-
- if (p->chunk_relocs_idx == -1) {
- DRM_ERROR("No relocation chunk !\n");
- return -EINVAL;
- }
- *cs_reloc = NULL;
- relocs_chunk = &p->chunks[p->chunk_relocs_idx];
- r = r100_cs_packet_parse(p, &p3reloc, p->idx);
- if (r) {
- return r;
- }
- p->idx += p3reloc.count + 2;
- if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
- DRM_ERROR("No packet3 for relocation for packet at %d.\n",
- p3reloc.idx);
- r100_cs_dump_packet(p, &p3reloc);
- return -EINVAL;
- }
- idx = radeon_get_ib_value(p, p3reloc.idx + 1);
- if (idx >= relocs_chunk->length_dw) {
- DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
- idx, relocs_chunk->length_dw);
- r100_cs_dump_packet(p, &p3reloc);
- return -EINVAL;
- }
- /* FIXME: we assume reloc size is 4 dwords */
- *cs_reloc = p->relocs_ptr[(idx / 4)];
- return 0;
-}
-
static int r100_get_vtx_size(uint32_t vtx_fmt)
{
int vtx_size;
@@ -1631,7 +1552,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
if (r) {
DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
idx, reg);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
break;
@@ -1644,53 +1565,53 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
return r;
break;
case RADEON_RB3D_DEPTHOFFSET:
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
idx, reg);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
track->zb.robj = reloc->robj;
track->zb.offset = idx_value;
track->zb_dirty = true;
- ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+ ib[idx] = idx_value + ((u32)reloc->gpu_offset);
break;
case RADEON_RB3D_COLOROFFSET:
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
idx, reg);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
track->cb[0].robj = reloc->robj;
track->cb[0].offset = idx_value;
track->cb_dirty = true;
- ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+ ib[idx] = idx_value + ((u32)reloc->gpu_offset);
break;
case RADEON_PP_TXOFFSET_0:
case RADEON_PP_TXOFFSET_1:
case RADEON_PP_TXOFFSET_2:
i = (reg - RADEON_PP_TXOFFSET_0) / 24;
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
idx, reg);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+ if (reloc->tiling_flags & RADEON_TILING_MACRO)
tile_flags |= RADEON_TXO_MACRO_TILE;
- if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+ if (reloc->tiling_flags & RADEON_TILING_MICRO)
tile_flags |= RADEON_TXO_MICRO_TILE_X2;
tmp = idx_value & ~(0x7 << 2);
tmp |= tile_flags;
- ib[idx] = tmp + ((u32)reloc->lobj.gpu_offset);
+ ib[idx] = tmp + ((u32)reloc->gpu_offset);
} else
- ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+ ib[idx] = idx_value + ((u32)reloc->gpu_offset);
track->textures[i].robj = reloc->robj;
track->tex_dirty = true;
break;
@@ -1700,15 +1621,15 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
case RADEON_PP_CUBIC_OFFSET_T0_3:
case RADEON_PP_CUBIC_OFFSET_T0_4:
i = (reg - RADEON_PP_CUBIC_OFFSET_T0_0) / 4;
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
idx, reg);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
track->textures[0].cube_info[i].offset = idx_value;
- ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+ ib[idx] = idx_value + ((u32)reloc->gpu_offset);
track->textures[0].cube_info[i].robj = reloc->robj;
track->tex_dirty = true;
break;
@@ -1718,15 +1639,15 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
case RADEON_PP_CUBIC_OFFSET_T1_3:
case RADEON_PP_CUBIC_OFFSET_T1_4:
i = (reg - RADEON_PP_CUBIC_OFFSET_T1_0) / 4;
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
idx, reg);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
track->textures[1].cube_info[i].offset = idx_value;
- ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+ ib[idx] = idx_value + ((u32)reloc->gpu_offset);
track->textures[1].cube_info[i].robj = reloc->robj;
track->tex_dirty = true;
break;
@@ -1736,15 +1657,15 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
case RADEON_PP_CUBIC_OFFSET_T2_3:
case RADEON_PP_CUBIC_OFFSET_T2_4:
i = (reg - RADEON_PP_CUBIC_OFFSET_T2_0) / 4;
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
idx, reg);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
track->textures[2].cube_info[i].offset = idx_value;
- ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+ ib[idx] = idx_value + ((u32)reloc->gpu_offset);
track->textures[2].cube_info[i].robj = reloc->robj;
track->tex_dirty = true;
break;
@@ -1754,17 +1675,17 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
track->zb_dirty = true;
break;
case RADEON_RB3D_COLORPITCH:
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
idx, reg);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+ if (reloc->tiling_flags & RADEON_TILING_MACRO)
tile_flags |= RADEON_COLOR_TILE_ENABLE;
- if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+ if (reloc->tiling_flags & RADEON_TILING_MICRO)
tile_flags |= RADEON_COLOR_MICROTILE_ENABLE;
tmp = idx_value & ~(0x7 << 16);
@@ -1825,14 +1746,14 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
track->zb_dirty = true;
break;
case RADEON_RB3D_ZPASS_ADDR:
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
idx, reg);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
- ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+ ib[idx] = idx_value + ((u32)reloc->gpu_offset);
break;
case RADEON_PP_CNTL:
{
@@ -1986,13 +1907,13 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
return r;
break;
case PACKET3_INDX_BUFFER:
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
- ib[idx+1] = radeon_get_ib_value(p, idx+1) + ((u32)reloc->lobj.gpu_offset);
+ ib[idx+1] = radeon_get_ib_value(p, idx+1) + ((u32)reloc->gpu_offset);
r = r100_cs_track_check_pkt3_indx_buffer(p, pkt, reloc->robj);
if (r) {
return r;
@@ -2000,13 +1921,13 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
break;
case 0x23:
/* 3D_RNDR_GEN_INDX_PRIM on r100/r200 */
- r = r100_cs_packet_next_reloc(p, &reloc);
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
if (r) {
DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
- r100_cs_dump_packet(p, pkt);
+ radeon_cs_dump_packet(p, pkt);
return r;
}
- ib[idx] = radeon_get_ib_value(p, idx) + ((u32)reloc->lobj.gpu_offset);
+ ib[idx] = radeon_get_ib_value(p, idx) + ((u32)reloc->gpu_offset);
track->num_arrays = 1;
track->vtx_size = r100_get_vtx_size(radeon_get_ib_value(p, idx + 2));
@@ -2100,37 +2021,36 @@ int r100_cs_parse(struct radeon_cs_parser *p)
r100_cs_track_clear(p->rdev, track);
p->track = track;
do {
- r = r100_cs_packet_parse(p, &pkt, p->idx);
+ r = radeon_cs_packet_parse(p, &pkt, p->idx);
if (r) {
return r;
}
p->idx += pkt.count + 2;
switch (pkt.type) {
- case PACKET_TYPE0:
- if (p->rdev->family >= CHIP_R200)
- r = r100_cs_parse_packet0(p, &pkt,
- p->rdev->config.r100.reg_safe_bm,
- p->rdev->config.r100.reg_safe_bm_size,
- &r200_packet0_check);
- else
- r = r100_cs_parse_packet0(p, &pkt,
- p->rdev->config.r100.reg_safe_bm,
- p->rdev->config.r100.reg_safe_bm_size,
- &r100_packet0_check);
- break;
- case PACKET_TYPE2:
- break;
- case PACKET_TYPE3:
- r = r100_packet3_check(p, &pkt);
- break;
- default:
- DRM_ERROR("Unknown packet type %d !\n",
- pkt.type);
- return -EINVAL;
+ case RADEON_PACKET_TYPE0:
+ if (p->rdev->family >= CHIP_R200)
+ r = r100_cs_parse_packet0(p, &pkt,
+ p->rdev->config.r100.reg_safe_bm,
+ p->rdev->config.r100.reg_safe_bm_size,
+ &r200_packet0_check);
+ else
+ r = r100_cs_parse_packet0(p, &pkt,
+ p->rdev->config.r100.reg_safe_bm,
+ p->rdev->config.r100.reg_safe_bm_size,
+ &r100_packet0_check);
+ break;
+ case RADEON_PACKET_TYPE2:
+ break;
+ case RADEON_PACKET_TYPE3:
+ r = r100_packet3_check(p, &pkt);
+ break;
+ default:
+ DRM_ERROR("Unknown packet type %d !\n",
+ pkt.type);
+ return -EINVAL;
}
- if (r) {
+ if (r)
return r;
- }
} while (p->idx < p->chunks[p->chunk_ib_idx].length_dw);
return 0;
}
@@ -2583,11 +2503,9 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
rbbm_status = RREG32(R_000E40_RBBM_STATUS);
if (!G_000E40_GUI_ACTIVE(rbbm_status)) {
- radeon_ring_lockup_update(ring);
+ radeon_ring_lockup_update(rdev, ring);
return false;
}
- /* force CP activities */
- radeon_ring_force_activity(rdev, ring);
return radeon_ring_test_lockup(rdev, ring);
}
@@ -2943,21 +2861,28 @@ static void r100_pll_errata_after_data(struct radeon_device *rdev)
uint32_t r100_pll_rreg(struct radeon_device *rdev, uint32_t reg)
{
+ unsigned long flags;
uint32_t data;
+ spin_lock_irqsave(&rdev->pll_idx_lock, flags);
WREG8(RADEON_CLOCK_CNTL_INDEX, reg & 0x3f);
r100_pll_errata_after_index(rdev);
data = RREG32(RADEON_CLOCK_CNTL_DATA);
r100_pll_errata_after_data(rdev);
+ spin_unlock_irqrestore(&rdev->pll_idx_lock, flags);
return data;
}
void r100_pll_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
{
+ unsigned long flags;
+
+ spin_lock_irqsave(&rdev->pll_idx_lock, flags);
WREG8(RADEON_CLOCK_CNTL_INDEX, ((reg & 0x3f) | RADEON_PLL_WR_EN));
r100_pll_errata_after_index(rdev);
WREG32(RADEON_CLOCK_CNTL_DATA, v);
r100_pll_errata_after_data(rdev);
+ spin_unlock_irqrestore(&rdev->pll_idx_lock, flags);
}
static void r100_set_safe_registers(struct radeon_device *rdev)
@@ -3016,9 +2941,11 @@ static int r100_debugfs_cp_ring_info(struct seq_file *m, void *data)
seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp);
seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
seq_printf(m, "%u dwords in ring\n", count);
- for (j = 0; j <= count; j++) {
- i = (rdp + j) & ring->ptr_mask;
- seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+ if (ring->ready) {
+ for (j = 0; j <= count; j++) {
+ i = (rdp + j) & ring->ptr_mask;
+ seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+ }
}
return 0;
}
@@ -3158,6 +3085,10 @@ int r100_set_surface_reg(struct radeon_device *rdev, int reg,
flags |= RADEON_SURF_TILE_COLOR_BOTH;
if (tiling_flags & RADEON_TILING_MACRO)
flags |= RADEON_SURF_TILE_COLOR_MACRO;
+ /* setting pitch to 0 disables tiling */
+ if ((tiling_flags & (RADEON_TILING_MACRO|RADEON_TILING_MICRO))
+ == 0)
+ pitch = 0;
} else if (rdev->family <= CHIP_RV280) {
if (tiling_flags & (RADEON_TILING_MACRO))
flags |= R200_SURF_TILE_COLOR_MACRO;
@@ -3175,13 +3106,6 @@ int r100_set_surface_reg(struct radeon_device *rdev, int reg,
if (tiling_flags & RADEON_TILING_SWAP_32BIT)
flags |= RADEON_SURF_AP0_SWP_32BPP | RADEON_SURF_AP1_SWP_32BPP;
- /* when we aren't tiling the pitch seems to needs to be furtherdivided down. - tested on power5 + rn50 server */
- if (tiling_flags & (RADEON_TILING_SWAP_16BIT | RADEON_TILING_SWAP_32BIT)) {
- if (!(tiling_flags & (RADEON_TILING_MACRO | RADEON_TILING_MICRO)))
- if (ASIC_IS_RN50(rdev))
- pitch /= 16;
- }
-
/* r100/r200 divide by 16 */
if (rdev->family < CHIP_R300)
flags |= pitch / 16;
@@ -3277,12 +3201,12 @@ void r100_bandwidth_update(struct radeon_device *rdev)
if (rdev->mode_info.crtcs[0]->base.enabled) {
mode1 = &rdev->mode_info.crtcs[0]->base.mode;
- pixel_bytes1 = rdev->mode_info.crtcs[0]->base.fb->bits_per_pixel / 8;
+ pixel_bytes1 = rdev->mode_info.crtcs[0]->base.primary->fb->bits_per_pixel / 8;
}
if (!(rdev->flags & RADEON_SINGLE_CRTC)) {
if (rdev->mode_info.crtcs[1]->base.enabled) {
mode2 = &rdev->mode_info.crtcs[1]->base.mode;
- pixel_bytes2 = rdev->mode_info.crtcs[1]->base.fb->bits_per_pixel / 8;
+ pixel_bytes2 = rdev->mode_info.crtcs[1]->base.primary->fb->bits_per_pixel / 8;
}
}
@@ -3950,6 +3874,12 @@ static int r100_startup(struct radeon_device *rdev)
}
/* Enable IRQ */
+ if (!rdev->irq.installed) {
+ r = radeon_irq_kms_init(rdev);
+ if (r)
+ return r;
+ }
+
r100_irq_set(rdev);
rdev->config.r100.hdp_cntl = RREG32(RADEON_HOST_PATH_CNTL);
/* 1M ring buffer */
@@ -4000,6 +3930,7 @@ int r100_resume(struct radeon_device *rdev)
int r100_suspend(struct radeon_device *rdev)
{
+ radeon_pm_suspend(rdev);
r100_cp_disable(rdev);
radeon_wb_disable(rdev);
r100_irq_disable(rdev);
@@ -4010,6 +3941,7 @@ int r100_suspend(struct radeon_device *rdev)
void r100_fini(struct radeon_device *rdev)
{
+ radeon_pm_fini(rdev);
r100_cp_fini(rdev);
radeon_wb_fini(rdev);
radeon_ib_pool_fini(rdev);
@@ -4105,9 +4037,6 @@ int r100_init(struct radeon_device *rdev)
r = radeon_fence_driver_init(rdev);
if (r)
return r;
- r = radeon_irq_kms_init(rdev);
- if (r)
- return r;
/* Memory manager */
r = radeon_bo_init(rdev);
if (r)
@@ -4119,6 +4048,9 @@ int r100_init(struct radeon_device *rdev)
}
r100_set_safe_registers(rdev);
+ /* Initialize power management */
+ radeon_pm_init(rdev);
+
rdev->accel_working = true;
r = r100_startup(rdev);
if (r) {
@@ -4135,23 +4067,36 @@ int r100_init(struct radeon_device *rdev)
return 0;
}
-uint32_t r100_mm_rreg(struct radeon_device *rdev, uint32_t reg)
+uint32_t r100_mm_rreg(struct radeon_device *rdev, uint32_t reg,
+ bool always_indirect)
{
- if (reg < rdev->rmmio_size)
+ if (reg < rdev->rmmio_size && !always_indirect)
return readl(((void __iomem *)rdev->rmmio) + reg);
else {
+ unsigned long flags;
+ uint32_t ret;
+
+ spin_lock_irqsave(&rdev->mmio_idx_lock, flags);
writel(reg, ((void __iomem *)rdev->rmmio) + RADEON_MM_INDEX);
- return readl(((void __iomem *)rdev->rmmio) + RADEON_MM_DATA);
+ ret = readl(((void __iomem *)rdev->rmmio) + RADEON_MM_DATA);
+ spin_unlock_irqrestore(&rdev->mmio_idx_lock, flags);
+
+ return ret;
}
}
-void r100_mm_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
+void r100_mm_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v,
+ bool always_indirect)
{
- if (reg < rdev->rmmio_size)
+ if (reg < rdev->rmmio_size && !always_indirect)
writel(v, ((void __iomem *)rdev->rmmio) + reg);
else {
+ unsigned long flags;
+
+ spin_lock_irqsave(&rdev->mmio_idx_lock, flags);
writel(reg, ((void __iomem *)rdev->rmmio) + RADEON_MM_INDEX);
writel(v, ((void __iomem *)rdev->rmmio) + RADEON_MM_DATA);
+ spin_unlock_irqrestore(&rdev->mmio_idx_lock, flags);
}
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 16:24:03 +0000