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.c1822
1 files changed, 901 insertions, 921 deletions
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 333cde9d4e7..1544efcf1c3 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -27,9 +27,8 @@
*/
#include <linux/seq_file.h>
#include <linux/slab.h>
-#include "drmP.h"
-#include "drm.h"
-#include "radeon_drm.h"
+#include <drm/drmP.h>
+#include <drm/radeon_drm.h>
#include "radeon_reg.h"
#include "radeon.h"
#include "radeon_asic.h"
@@ -40,7 +39,6 @@
#include "atom.h"
#include <linux/firmware.h>
-#include <linux/platform_device.h>
#include <linux/module.h>
#include "r100_reg_safe.h"
@@ -67,123 +65,95 @@ MODULE_FIRMWARE(FIRMWARE_R520);
/* This files gather functions specifics to:
* r100,rv100,rs100,rv200,rs200,r200,rv250,rs300,rv280
+ * and others in some cases.
*/
-int r100_reloc_pitch_offset(struct radeon_cs_parser *p,
- struct radeon_cs_packet *pkt,
- unsigned idx,
- unsigned reg)
+static bool r100_is_in_vblank(struct radeon_device *rdev, int crtc)
{
- int r;
- u32 tile_flags = 0;
- u32 tmp;
- struct radeon_cs_reloc *reloc;
- u32 value;
-
- r = r100_cs_packet_next_reloc(p, &reloc);
- if (r) {
- DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
- idx, reg);
- r100_cs_dump_packet(p, pkt);
- return r;
- }
- value = radeon_get_ib_value(p, idx);
- tmp = value & 0x003fffff;
- tmp += (((u32)reloc->lobj.gpu_offset) >> 10);
-
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
- tile_flags |= RADEON_DST_TILE_MACRO;
- if (reloc->lobj.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);
- return -EINVAL;
- }
- tile_flags |= RADEON_DST_TILE_MICRO;
+ 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;
}
+}
- tmp |= tile_flags;
- p->ib->ptr[idx] = (value & 0x3fc00000) | tmp;
- return 0;
+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;
}
-int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
- struct radeon_cs_packet *pkt,
- int idx)
+/**
+ * r100_wait_for_vblank - vblank wait asic callback.
+ *
+ * @rdev: radeon_device pointer
+ * @crtc: crtc to wait for vblank on
+ *
+ * Wait for vblank on the requested crtc (r1xx-r4xx).
+ */
+void r100_wait_for_vblank(struct radeon_device *rdev, int crtc)
{
- unsigned c, i;
- struct radeon_cs_reloc *reloc;
- struct r100_cs_track *track;
- int r = 0;
- volatile uint32_t *ib;
- u32 idx_value;
+ unsigned i = 0;
- ib = p->ib->ptr;
- track = (struct r100_cs_track *)p->track;
- c = radeon_get_ib_value(p, idx++) & 0x1F;
- if (c > 16) {
- DRM_ERROR("Only 16 vertex buffers are allowed %d\n",
- pkt->opcode);
- r100_cs_dump_packet(p, pkt);
- return -EINVAL;
+ if (crtc >= rdev->num_crtc)
+ return;
+
+ if (crtc == 0) {
+ if (!(RREG32(RADEON_CRTC_GEN_CNTL) & RADEON_CRTC_EN))
+ return;
+ } else {
+ if (!(RREG32(RADEON_CRTC2_GEN_CNTL) & RADEON_CRTC2_EN))
+ return;
}
- track->num_arrays = c;
- for (i = 0; i < (c - 1); i+=2, idx+=3) {
- r = r100_cs_packet_next_reloc(p, &reloc);
- if (r) {
- DRM_ERROR("No reloc for packet3 %d\n",
- pkt->opcode);
- r100_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);
- 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);
- if (r) {
- DRM_ERROR("No reloc for packet3 %d\n",
- pkt->opcode);
- r100_cs_dump_packet(p, pkt);
- return r;
+ /* 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;
}
- ib[idx+2] = radeon_get_ib_value(p, idx + 2) + ((u32)reloc->lobj.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);
- if (r) {
- DRM_ERROR("No reloc for packet3 %d\n",
- pkt->opcode);
- r100_cs_dump_packet(p, pkt);
- return r;
+
+ while (!r100_is_in_vblank(rdev, crtc)) {
+ if (i++ % 100 == 0) {
+ if (!r100_is_counter_moving(rdev, crtc))
+ break;
}
- idx_value = radeon_get_ib_value(p, idx);
- ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->lobj.gpu_offset);
- track->arrays[i + 0].robj = reloc->robj;
- track->arrays[i + 0].esize = idx_value >> 8;
- track->arrays[i + 0].esize &= 0x7F;
}
- return r;
-}
-
-void r100_pre_page_flip(struct radeon_device *rdev, int crtc)
-{
- /* enable the pflip int */
- radeon_irq_kms_pflip_irq_get(rdev, crtc);
-}
-
-void r100_post_page_flip(struct radeon_device *rdev, int crtc)
-{
- /* disable the pflip int */
- radeon_irq_kms_pflip_irq_put(rdev, crtc);
}
-u32 r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
+/**
+ * r100_page_flip - pageflip callback.
+ *
+ * @rdev: radeon_device pointer
+ * @crtc_id: crtc to cleanup pageflip on
+ * @crtc_base: new address of the crtc (GPU MC address)
+ *
+ * Does the actual pageflip (r1xx-r4xx).
+ * 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.
+ */
+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;
@@ -205,10 +175,35 @@ 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);
}
+/**
+ * r100_pm_get_dynpm_state - look up dynpm power state callback.
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Look up the optimal power state based on the
+ * current state of the GPU (r1xx-r5xx).
+ * Used for dynpm only.
+ */
void r100_pm_get_dynpm_state(struct radeon_device *rdev)
{
int i;
@@ -291,6 +286,15 @@ void r100_pm_get_dynpm_state(struct radeon_device *rdev)
pcie_lanes);
}
+/**
+ * r100_pm_init_profile - Initialize power profiles callback.
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Initialize the power states used in profile mode
+ * (r1xx-r3xx).
+ * Used for profile mode only.
+ */
void r100_pm_init_profile(struct radeon_device *rdev)
{
/* default */
@@ -330,6 +334,14 @@ void r100_pm_init_profile(struct radeon_device *rdev)
rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_on_cm_idx = 0;
}
+/**
+ * r100_pm_misc - set additional pm hw parameters callback.
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Set non-clock parameters associated with a power state
+ * (voltage, pcie lanes, etc.) (r1xx-r4xx).
+ */
void r100_pm_misc(struct radeon_device *rdev)
{
int requested_index = rdev->pm.requested_power_state_index;
@@ -412,7 +424,7 @@ void r100_pm_misc(struct radeon_device *rdev)
/* set pcie lanes */
if ((rdev->flags & RADEON_IS_PCIE) &&
!(rdev->flags & RADEON_IS_IGP) &&
- rdev->asic->set_pcie_lanes &&
+ rdev->asic->pm.set_pcie_lanes &&
(ps->pcie_lanes !=
rdev->pm.power_state[rdev->pm.current_power_state_index].pcie_lanes)) {
radeon_set_pcie_lanes(rdev,
@@ -421,6 +433,13 @@ void r100_pm_misc(struct radeon_device *rdev)
}
}
+/**
+ * r100_pm_prepare - pre-power state change callback.
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Prepare for a power state change (r1xx-r4xx).
+ */
void r100_pm_prepare(struct radeon_device *rdev)
{
struct drm_device *ddev = rdev->ddev;
@@ -445,6 +464,13 @@ void r100_pm_prepare(struct radeon_device *rdev)
}
}
+/**
+ * r100_pm_finish - post-power state change callback.
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Clean up after a power state change (r1xx-r4xx).
+ */
void r100_pm_finish(struct radeon_device *rdev)
{
struct drm_device *ddev = rdev->ddev;
@@ -469,6 +495,14 @@ void r100_pm_finish(struct radeon_device *rdev)
}
}
+/**
+ * r100_gui_idle - gui idle callback.
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Check of the GUI (2D/3D engines) are idle (r1xx-r5xx).
+ * Returns true if idle, false if not.
+ */
bool r100_gui_idle(struct radeon_device *rdev)
{
if (RREG32(RADEON_RBBM_STATUS) & RADEON_RBBM_ACTIVE)
@@ -478,6 +512,15 @@ bool r100_gui_idle(struct radeon_device *rdev)
}
/* hpd for digital panel detect/disconnect */
+/**
+ * r100_hpd_sense - hpd sense callback.
+ *
+ * @rdev: radeon_device pointer
+ * @hpd: hpd (hotplug detect) pin
+ *
+ * Checks if a digital monitor is connected (r1xx-r4xx).
+ * Returns true if connected, false if not connected.
+ */
bool r100_hpd_sense(struct radeon_device *rdev, enum radeon_hpd_id hpd)
{
bool connected = false;
@@ -497,6 +540,14 @@ bool r100_hpd_sense(struct radeon_device *rdev, enum radeon_hpd_id hpd)
return connected;
}
+/**
+ * r100_hpd_set_polarity - hpd set polarity callback.
+ *
+ * @rdev: radeon_device pointer
+ * @hpd: hpd (hotplug detect) pin
+ *
+ * Set the polarity of the hpd pin (r1xx-r4xx).
+ */
void r100_hpd_set_polarity(struct radeon_device *rdev,
enum radeon_hpd_id hpd)
{
@@ -525,47 +576,47 @@ void r100_hpd_set_polarity(struct radeon_device *rdev,
}
}
+/**
+ * r100_hpd_init - hpd setup callback.
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Setup the hpd pins used by the card (r1xx-r4xx).
+ * Set the polarity, and enable the hpd interrupts.
+ */
void r100_hpd_init(struct radeon_device *rdev)
{
struct drm_device *dev = rdev->ddev;
struct drm_connector *connector;
+ unsigned enable = 0;
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
struct radeon_connector *radeon_connector = to_radeon_connector(connector);
- switch (radeon_connector->hpd.hpd) {
- case RADEON_HPD_1:
- rdev->irq.hpd[0] = true;
- break;
- case RADEON_HPD_2:
- rdev->irq.hpd[1] = true;
- break;
- default:
- break;
- }
+ enable |= 1 << radeon_connector->hpd.hpd;
radeon_hpd_set_polarity(rdev, radeon_connector->hpd.hpd);
}
- if (rdev->irq.installed)
- r100_irq_set(rdev);
+ radeon_irq_kms_enable_hpd(rdev, enable);
}
+/**
+ * r100_hpd_fini - hpd tear down callback.
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Tear down the hpd pins used by the card (r1xx-r4xx).
+ * Disable the hpd interrupts.
+ */
void r100_hpd_fini(struct radeon_device *rdev)
{
struct drm_device *dev = rdev->ddev;
struct drm_connector *connector;
+ unsigned disable = 0;
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
struct radeon_connector *radeon_connector = to_radeon_connector(connector);
- switch (radeon_connector->hpd.hpd) {
- case RADEON_HPD_1:
- rdev->irq.hpd[0] = false;
- break;
- case RADEON_HPD_2:
- rdev->irq.hpd[1] = false;
- break;
- default:
- break;
- }
+ disable |= 1 << radeon_connector->hpd.hpd;
}
+ radeon_irq_kms_disable_hpd(rdev, disable);
}
/*
@@ -592,20 +643,11 @@ int r100_pci_gart_init(struct radeon_device *rdev)
if (r)
return r;
rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
- rdev->asic->gart_tlb_flush = &r100_pci_gart_tlb_flush;
- rdev->asic->gart_set_page = &r100_pci_gart_set_page;
+ rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush;
+ rdev->asic->gart.set_page = &r100_pci_gart_set_page;
return radeon_gart_table_ram_alloc(rdev);
}
-/* required on r1xx, r2xx, r300, r(v)350, r420/r481, rs400/rs480 */
-void r100_enable_bm(struct radeon_device *rdev)
-{
- uint32_t tmp;
- /* Enable bus mastering */
- tmp = RREG32(RADEON_BUS_CNTL) & ~RADEON_BUS_MASTER_DIS;
- WREG32(RADEON_BUS_CNTL, tmp);
-}
-
int r100_pci_gart_enable(struct radeon_device *rdev)
{
uint32_t tmp;
@@ -622,7 +664,7 @@ int r100_pci_gart_enable(struct radeon_device *rdev)
tmp = RREG32(RADEON_AIC_CNTL) | RADEON_PCIGART_TRANSLATE_EN;
WREG32(RADEON_AIC_CNTL, tmp);
r100_pci_gart_tlb_flush(rdev);
- DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
+ DRM_INFO("PCI GART of %uM enabled (table at 0x%016llX).\n",
(unsigned)(rdev->mc.gtt_size >> 20),
(unsigned long long)rdev->gart.table_addr);
rdev->gart.ready = true;
@@ -640,15 +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)
@@ -667,18 +705,15 @@ int r100_irq_set(struct radeon_device *rdev)
WREG32(R_000040_GEN_INT_CNTL, 0);
return -EINVAL;
}
- if (rdev->irq.sw_int[RADEON_RING_TYPE_GFX_INDEX]) {
+ if (atomic_read(&rdev->irq.ring_int[RADEON_RING_TYPE_GFX_INDEX])) {
tmp |= RADEON_SW_INT_ENABLE;
}
- if (rdev->irq.gui_idle) {
- tmp |= RADEON_GUI_IDLE_MASK;
- }
if (rdev->irq.crtc_vblank_int[0] ||
- rdev->irq.pflip[0]) {
+ atomic_read(&rdev->irq.pflip[0])) {
tmp |= RADEON_CRTC_VBLANK_MASK;
}
if (rdev->irq.crtc_vblank_int[1] ||
- rdev->irq.pflip[1]) {
+ atomic_read(&rdev->irq.pflip[1])) {
tmp |= RADEON_CRTC2_VBLANK_MASK;
}
if (rdev->irq.hpd[0]) {
@@ -709,12 +744,6 @@ static uint32_t r100_irq_ack(struct radeon_device *rdev)
RADEON_CRTC_VBLANK_STAT | RADEON_CRTC2_VBLANK_STAT |
RADEON_FP_DETECT_STAT | RADEON_FP2_DETECT_STAT;
- /* the interrupt works, but the status bit is permanently asserted */
- if (rdev->irq.gui_idle && radeon_gui_idle(rdev)) {
- if (!rdev->irq.gui_idle_acked)
- irq_mask |= RADEON_GUI_IDLE_STAT;
- }
-
if (irqs) {
WREG32(RADEON_GEN_INT_STATUS, irqs);
}
@@ -726,9 +755,6 @@ int r100_irq_process(struct radeon_device *rdev)
uint32_t status, msi_rearm;
bool queue_hotplug = false;
- /* reset gui idle ack. the status bit is broken */
- rdev->irq.gui_idle_acked = false;
-
status = r100_irq_ack(rdev);
if (!status) {
return IRQ_NONE;
@@ -741,12 +767,6 @@ int r100_irq_process(struct radeon_device *rdev)
if (status & RADEON_SW_INT_TEST) {
radeon_fence_process(rdev, RADEON_RING_TYPE_GFX_INDEX);
}
- /* gui idle interrupt */
- if (status & RADEON_GUI_IDLE_STAT) {
- rdev->irq.gui_idle_acked = true;
- rdev->pm.gui_idle = true;
- wake_up(&rdev->irq.idle_queue);
- }
/* Vertical blank interrupts */
if (status & RADEON_CRTC_VBLANK_STAT) {
if (rdev->irq.crtc_vblank_int[0]) {
@@ -754,8 +774,8 @@ int r100_irq_process(struct radeon_device *rdev)
rdev->pm.vblank_sync = true;
wake_up(&rdev->irq.vblank_queue);
}
- if (rdev->irq.pflip[0])
- radeon_crtc_handle_flip(rdev, 0);
+ if (atomic_read(&rdev->irq.pflip[0]))
+ radeon_crtc_handle_vblank(rdev, 0);
}
if (status & RADEON_CRTC2_VBLANK_STAT) {
if (rdev->irq.crtc_vblank_int[1]) {
@@ -763,8 +783,8 @@ int r100_irq_process(struct radeon_device *rdev)
rdev->pm.vblank_sync = true;
wake_up(&rdev->irq.vblank_queue);
}
- if (rdev->irq.pflip[1])
- radeon_crtc_handle_flip(rdev, 1);
+ if (atomic_read(&rdev->irq.pflip[1]))
+ radeon_crtc_handle_vblank(rdev, 1);
}
if (status & RADEON_FP_DETECT_STAT) {
queue_hotplug = true;
@@ -776,8 +796,6 @@ int r100_irq_process(struct radeon_device *rdev)
}
status = r100_irq_ack(rdev);
}
- /* reset gui idle ack. the status bit is broken */
- rdev->irq.gui_idle_acked = false;
if (queue_hotplug)
schedule_work(&rdev->hotplug_work);
if (rdev->msi_enabled) {
@@ -832,20 +850,21 @@ 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,
uint64_t src_offset,
uint64_t dst_offset,
unsigned num_gpu_pages,
- struct radeon_fence *fence)
+ struct radeon_fence **fence)
{
struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
uint32_t cur_pages;
@@ -909,7 +928,7 @@ int r100_copy_blit(struct radeon_device *rdev,
RADEON_WAIT_HOST_IDLECLEAN |
RADEON_WAIT_DMA_GUI_IDLE);
if (fence) {
- r = radeon_fence_emit(rdev, fence);
+ r = radeon_fence_emit(rdev, fence, RADEON_RING_TYPE_GFX_INDEX);
}
radeon_ring_unlock_commit(rdev, ring);
return r;
@@ -930,9 +949,8 @@ static int r100_cp_wait_for_idle(struct radeon_device *rdev)
return -1;
}
-void r100_ring_start(struct radeon_device *rdev)
+void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring)
{
- struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
int r;
r = radeon_ring_lock(rdev, ring, 2);
@@ -952,18 +970,11 @@ void r100_ring_start(struct radeon_device *rdev)
/* 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)) {
@@ -1005,8 +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);
@@ -1021,6 +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;
@@ -1069,12 +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;
}
@@ -1135,7 +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) |
@@ -1143,14 +1181,27 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
WREG32(RADEON_CP_RB_WPTR_DELAY, 0);
WREG32(RADEON_CP_CSQ_MODE, 0x00004D4D);
WREG32(RADEON_CP_CSQ_CNTL, RADEON_CSQ_PRIBM_INDBM);
- radeon_ring_start(rdev);
- r = radeon_ring_test(rdev, ring);
+
+ /* at this point everything should be setup correctly to enable master */
+ pci_set_master(rdev->pdev);
+
+ radeon_ring_start(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
+ r = radeon_ring_test(rdev, RADEON_RING_TYPE_GFX_INDEX, ring);
if (r) {
DRM_ERROR("radeon: cp isn't working (%d).\n", r);
return r;
}
ring->ready = true;
radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
+
+ if (!ring->rptr_save_reg /* not resuming from suspend */
+ && radeon_ring_supports_scratch_reg(rdev, ring)) {
+ r = radeon_scratch_get(rdev, &ring->rptr_save_reg);
+ if (r) {
+ DRM_ERROR("failed to get scratch reg for rptr save (%d).\n", r);
+ ring->rptr_save_reg = 0;
+ }
+ }
return 0;
}
@@ -1161,6 +1212,7 @@ void r100_cp_fini(struct radeon_device *rdev)
}
/* Disable ring */
r100_cp_disable(rdev);
+ radeon_scratch_free(rdev, rdev->ring[RADEON_RING_TYPE_GFX_INDEX].rptr_save_reg);
radeon_ring_fini(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
DRM_INFO("radeon: cp finalized\n");
}
@@ -1182,6 +1234,112 @@ void r100_cp_disable(struct radeon_device *rdev)
/*
* CS functions
*/
+int r100_reloc_pitch_offset(struct radeon_cs_parser *p,
+ struct radeon_cs_packet *pkt,
+ unsigned idx,
+ unsigned reg)
+{
+ int r;
+ u32 tile_flags = 0;
+ u32 tmp;
+ struct radeon_cs_reloc *reloc;
+ u32 value;
+
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
+ if (r) {
+ DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
+ idx, reg);
+ radeon_cs_dump_packet(p, pkt);
+ return r;
+ }
+
+ value = radeon_get_ib_value(p, idx);
+ tmp = value & 0x003fffff;
+ tmp += (((u32)reloc->gpu_offset) >> 10);
+
+ if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
+ if (reloc->tiling_flags & RADEON_TILING_MACRO)
+ tile_flags |= RADEON_DST_TILE_MACRO;
+ if (reloc->tiling_flags & RADEON_TILING_MICRO) {
+ if (reg == RADEON_SRC_PITCH_OFFSET) {
+ DRM_ERROR("Cannot src blit from microtiled surface\n");
+ radeon_cs_dump_packet(p, pkt);
+ return -EINVAL;
+ }
+ tile_flags |= RADEON_DST_TILE_MICRO;
+ }
+
+ tmp |= tile_flags;
+ p->ib.ptr[idx] = (value & 0x3fc00000) | tmp;
+ } else
+ p->ib.ptr[idx] = (value & 0xffc00000) | tmp;
+ return 0;
+}
+
+int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
+ struct radeon_cs_packet *pkt,
+ int idx)
+{
+ unsigned c, i;
+ struct radeon_cs_reloc *reloc;
+ struct r100_cs_track *track;
+ int r = 0;
+ volatile uint32_t *ib;
+ u32 idx_value;
+
+ ib = p->ib.ptr;
+ track = (struct r100_cs_track *)p->track;
+ c = radeon_get_ib_value(p, idx++) & 0x1F;
+ if (c > 16) {
+ DRM_ERROR("Only 16 vertex buffers are allowed %d\n",
+ pkt->opcode);
+ radeon_cs_dump_packet(p, pkt);
+ return -EINVAL;
+ }
+ track->num_arrays = c;
+ for (i = 0; i < (c - 1); i+=2, idx+=3) {
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
+ if (r) {
+ DRM_ERROR("No reloc for packet3 %d\n",
+ pkt->opcode);
+ 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->gpu_offset);
+
+ track->arrays[i + 0].esize = idx_value >> 8;
+ track->arrays[i + 0].robj = reloc->robj;
+ track->arrays[i + 0].esize &= 0x7F;
+ r = radeon_cs_packet_next_reloc(p, &reloc, 0);
+ if (r) {
+ DRM_ERROR("No reloc for packet3 %d\n",
+ pkt->opcode);
+ radeon_cs_dump_packet(p, pkt);
+ return r;
+ }
+ 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 = radeon_cs_packet_next_reloc(p, &reloc, 0);
+ if (r) {
+ DRM_ERROR("No reloc for packet3 %d\n",
+ pkt->opcode);
+ 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->gpu_offset);
+ track->arrays[i + 0].robj = reloc->robj;
+ track->arrays[i + 0].esize = idx_value >> 8;
+ track->arrays[i + 0].esize &= 0x7F;
+ }
+ return r;
+}
+
int r100_cs_parse_packet0(struct radeon_cs_parser *p,
struct radeon_cs_packet *pkt,
const unsigned *auth, unsigned n,
@@ -1227,67 +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.
@@ -1313,10 +1410,10 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
uint32_t header, h_idx, reg;
volatile uint32_t *ib;
- ib = p->ib->ptr;
+ 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;
@@ -1333,7 +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;
@@ -1343,11 +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);
@@ -1378,54 +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;
@@ -1492,7 +1541,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
u32 tile_flags = 0;
u32 idx_value;
- ib = p->ib->ptr;
+ ib = p->ib.ptr;
track = (struct r100_cs_track *)p->track;
idx_value = radeon_get_ib_value(p, idx);
@@ -1503,7 +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;
@@ -1516,43 +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;
}
- ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+ if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
+ if (reloc->tiling_flags & RADEON_TILING_MACRO)
+ tile_flags |= RADEON_TXO_MACRO_TILE;
+ 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->gpu_offset);
+ } else
+ ib[idx] = idx_value + ((u32)reloc->gpu_offset);
track->textures[i].robj = reloc->robj;
track->tex_dirty = true;
break;
@@ -1562,15 +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;
@@ -1580,15 +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;
@@ -1598,15 +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;
@@ -1616,22 +1675,24 @@ 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 (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
- tile_flags |= RADEON_COLOR_TILE_ENABLE;
- if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
- tile_flags |= RADEON_COLOR_MICROTILE_ENABLE;
-
- tmp = idx_value & ~(0x7 << 16);
- tmp |= tile_flags;
- ib[idx] = tmp;
+ if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
+ if (reloc->tiling_flags & RADEON_TILING_MACRO)
+ tile_flags |= RADEON_COLOR_TILE_ENABLE;
+ if (reloc->tiling_flags & RADEON_TILING_MICRO)
+ tile_flags |= RADEON_COLOR_MICROTILE_ENABLE;
+
+ tmp = idx_value & ~(0x7 << 16);
+ tmp |= tile_flags;
+ ib[idx] = tmp;
+ } else
+ ib[idx] = idx_value;
track->cb[0].pitch = idx_value & RADEON_COLORPITCH_MASK;
track->cb_dirty = true;
@@ -1685,14 +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:
{
@@ -1836,7 +1897,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
volatile uint32_t *ib;
int r;
- ib = p->ib->ptr;
+ ib = p->ib.ptr;
idx = pkt->idx + 1;
track = (struct r100_cs_track *)p->track;
switch (pkt->opcode) {
@@ -1846,13 +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;
@@ -1860,13 +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));
@@ -1955,108 +2016,438 @@ int r100_cs_parse(struct radeon_cs_parser *p)
int r;
track = kzalloc(sizeof(*track), GFP_KERNEL);
+ if (!track)
+ return -ENOMEM;
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;
}
+static void r100_cs_track_texture_print(struct r100_cs_track_texture *t)
+{
+ DRM_ERROR("pitch %d\n", t->pitch);
+ DRM_ERROR("use_pitch %d\n", t->use_pitch);
+ DRM_ERROR("width %d\n", t->width);
+ DRM_ERROR("width_11 %d\n", t->width_11);
+ DRM_ERROR("height %d\n", t->height);
+ DRM_ERROR("height_11 %d\n", t->height_11);
+ DRM_ERROR("num levels %d\n", t->num_levels);
+ DRM_ERROR("depth %d\n", t->txdepth);
+ DRM_ERROR("bpp %d\n", t->cpp);
+ DRM_ERROR("coordinate type %d\n", t->tex_coord_type);
+ DRM_ERROR("width round to power of 2 %d\n", t->roundup_w);
+ DRM_ERROR("height round to power of 2 %d\n", t->roundup_h);
+ DRM_ERROR("compress format %d\n", t->compress_format);
+}
-/*
- * Global GPU functions
- */
-void r100_errata(struct radeon_device *rdev)
+static int r100_track_compress_size(int compress_format, int w, int h)
{
- rdev->pll_errata = 0;
+ int block_width, block_height, block_bytes;
+ int wblocks, hblocks;
+ int min_wblocks;
+ int sz;
- if (rdev->family == CHIP_RV200 || rdev->family == CHIP_RS200) {
- rdev->pll_errata |= CHIP_ERRATA_PLL_DUMMYREADS;
+ block_width = 4;
+ block_height = 4;
+
+ switch (compress_format) {
+ case R100_TRACK_COMP_DXT1:
+ block_bytes = 8;
+ min_wblocks = 4;
+ break;
+ default:
+ case R100_TRACK_COMP_DXT35:
+ block_bytes = 16;
+ min_wblocks = 2;
+ break;
}
- if (rdev->family == CHIP_RV100 ||
- rdev->family == CHIP_RS100 ||
- rdev->family == CHIP_RS200) {
- rdev->pll_errata |= CHIP_ERRATA_PLL_DELAY;
+ hblocks = (h + block_height - 1) / block_height;
+ wblocks = (w + block_width - 1) / block_width;
+ if (wblocks < min_wblocks)
+ wblocks = min_wblocks;
+ sz = wblocks * hblocks * block_bytes;
+ return sz;
+}
+
+static int r100_cs_track_cube(struct radeon_device *rdev,
+ struct r100_cs_track *track, unsigned idx)
+{
+ unsigned face, w, h;
+ struct radeon_bo *cube_robj;
+ unsigned long size;
+ unsigned compress_format = track->textures[idx].compress_format;
+
+ for (face = 0; face < 5; face++) {
+ cube_robj = track->textures[idx].cube_info[face].robj;
+ w = track->textures[idx].cube_info[face].width;
+ h = track->textures[idx].cube_info[face].height;
+
+ if (compress_format) {
+ size = r100_track_compress_size(compress_format, w, h);
+ } else
+ size = w * h;
+ size *= track->textures[idx].cpp;
+
+ size += track->textures[idx].cube_info[face].offset;
+
+ if (size > radeon_bo_size(cube_robj)) {
+ DRM_ERROR("Cube texture offset greater than object size %lu %lu\n",
+ size, radeon_bo_size(cube_robj));
+ r100_cs_track_texture_print(&track->textures[idx]);
+ return -1;
+ }
}
+ return 0;
}
-/* Wait for vertical sync on primary CRTC */
-void r100_gpu_wait_for_vsync(struct radeon_device *rdev)
+static int r100_cs_track_texture_check(struct radeon_device *rdev,
+ struct r100_cs_track *track)
{
- uint32_t crtc_gen_cntl, tmp;
- int i;
+ struct radeon_bo *robj;
+ unsigned long size;
+ unsigned u, i, w, h, d;
+ int ret;
- crtc_gen_cntl = RREG32(RADEON_CRTC_GEN_CNTL);
- if ((crtc_gen_cntl & RADEON_CRTC_DISP_REQ_EN_B) ||
- !(crtc_gen_cntl & RADEON_CRTC_EN)) {
- return;
+ for (u = 0; u < track->num_texture; u++) {
+ if (!track->textures[u].enabled)
+ continue;
+ if (track->textures[u].lookup_disable)
+ continue;
+ robj = track->textures[u].robj;
+ if (robj == NULL) {
+ DRM_ERROR("No texture bound to unit %u\n", u);
+ return -EINVAL;
+ }
+ size = 0;
+ for (i = 0; i <= track->textures[u].num_levels; i++) {
+ if (track->textures[u].use_pitch) {
+ if (rdev->family < CHIP_R300)
+ w = (track->textures[u].pitch / track->textures[u].cpp) / (1 << i);
+ else
+ w = track->textures[u].pitch / (1 << i);
+ } else {
+ w = track->textures[u].width;
+ if (rdev->family >= CHIP_RV515)
+ w |= track->textures[u].width_11;
+ w = w / (1 << i);
+ if (track->textures[u].roundup_w)
+ w = roundup_pow_of_two(w);
+ }
+ h = track->textures[u].height;
+ if (rdev->family >= CHIP_RV515)
+ h |= track->textures[u].height_11;
+ h = h / (1 << i);
+ if (track->textures[u].roundup_h)
+ h = roundup_pow_of_two(h);
+ if (track->textures[u].tex_coord_type == 1) {
+ d = (1 << track->textures[u].txdepth) / (1 << i);
+ if (!d)
+ d = 1;
+ } else {
+ d = 1;
+ }
+ if (track->textures[u].compress_format) {
+
+ size += r100_track_compress_size(track->textures[u].compress_format, w, h) * d;
+ /* compressed textures are block based */
+ } else
+ size += w * h * d;
+ }
+ size *= track->textures[u].cpp;
+
+ switch (track->textures[u].tex_coord_type) {
+ case 0:
+ case 1:
+ break;
+ case 2:
+ if (track->separate_cube) {
+ ret = r100_cs_track_cube(rdev, track, u);
+ if (ret)
+ return ret;
+ } else
+ size *= 6;
+ break;
+ default:
+ DRM_ERROR("Invalid texture coordinate type %u for unit "
+ "%u\n", track->textures[u].tex_coord_type, u);
+ return -EINVAL;
+ }
+ if (size > radeon_bo_size(robj)) {
+ DRM_ERROR("Texture of unit %u needs %lu bytes but is "
+ "%lu\n", u, size, radeon_bo_size(robj));
+ r100_cs_track_texture_print(&track->textures[u]);
+ return -EINVAL;
+ }
}
- /* Clear the CRTC_VBLANK_SAVE bit */
- WREG32(RADEON_CRTC_STATUS, RADEON_CRTC_VBLANK_SAVE_CLEAR);
- for (i = 0; i < rdev->usec_timeout; i++) {
- tmp = RREG32(RADEON_CRTC_STATUS);
- if (tmp & RADEON_CRTC_VBLANK_SAVE) {
- return;
+ return 0;
+}
+
+int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track)
+{
+ unsigned i;
+ unsigned long size;
+ unsigned prim_walk;
+ unsigned nverts;
+ unsigned num_cb = track->cb_dirty ? track->num_cb : 0;
+
+ if (num_cb && !track->zb_cb_clear && !track->color_channel_mask &&
+ !track->blend_read_enable)
+ num_cb = 0;
+
+ for (i = 0; i < num_cb; i++) {
+ if (track->cb[i].robj == NULL) {
+ DRM_ERROR("[drm] No buffer for color buffer %d !\n", i);
+ return -EINVAL;
}
- DRM_UDELAY(1);
+ size = track->cb[i].pitch * track->cb[i].cpp * track->maxy;
+ size += track->cb[i].offset;
+ if (size > radeon_bo_size(track->cb[i].robj)) {
+ DRM_ERROR("[drm] Buffer too small for color buffer %d "
+ "(need %lu have %lu) !\n", i, size,
+ radeon_bo_size(track->cb[i].robj));
+ DRM_ERROR("[drm] color buffer %d (%u %u %u %u)\n",
+ i, track->cb[i].pitch, track->cb[i].cpp,
+ track->cb[i].offset, track->maxy);
+ return -EINVAL;
+ }
+ }
+ track->cb_dirty = false;
+
+ if (track->zb_dirty && track->z_enabled) {
+ if (track->zb.robj == NULL) {
+ DRM_ERROR("[drm] No buffer for z buffer !\n");
+ return -EINVAL;
+ }
+ size = track->zb.pitch * track->zb.cpp * track->maxy;
+ size += track->zb.offset;
+ if (size > radeon_bo_size(track->zb.robj)) {
+ DRM_ERROR("[drm] Buffer too small for z buffer "
+ "(need %lu have %lu) !\n", size,
+ radeon_bo_size(track->zb.robj));
+ DRM_ERROR("[drm] zbuffer (%u %u %u %u)\n",
+ track->zb.pitch, track->zb.cpp,
+ track->zb.offset, track->maxy);
+ return -EINVAL;
+ }
+ }
+ track->zb_dirty = false;
+
+ if (track->aa_dirty && track->aaresolve) {
+ if (track->aa.robj == NULL) {
+ DRM_ERROR("[drm] No buffer for AA resolve buffer %d !\n", i);
+ return -EINVAL;
+ }
+ /* I believe the format comes from colorbuffer0. */
+ size = track->aa.pitch * track->cb[0].cpp * track->maxy;
+ size += track->aa.offset;
+ if (size > radeon_bo_size(track->aa.robj)) {
+ DRM_ERROR("[drm] Buffer too small for AA resolve buffer %d "
+ "(need %lu have %lu) !\n", i, size,
+ radeon_bo_size(track->aa.robj));
+ DRM_ERROR("[drm] AA resolve buffer %d (%u %u %u %u)\n",
+ i, track->aa.pitch, track->cb[0].cpp,
+ track->aa.offset, track->maxy);
+ return -EINVAL;
+ }
+ }
+ track->aa_dirty = false;
+
+ prim_walk = (track->vap_vf_cntl >> 4) & 0x3;
+ if (track->vap_vf_cntl & (1 << 14)) {
+ nverts = track->vap_alt_nverts;
+ } else {
+ nverts = (track->vap_vf_cntl >> 16) & 0xFFFF;
+ }
+ switch (prim_walk) {
+ case 1:
+ for (i = 0; i < track->num_arrays; i++) {
+ size = track->arrays[i].esize * track->max_indx * 4;
+ if (track->arrays[i].robj == NULL) {
+ DRM_ERROR("(PW %u) Vertex array %u no buffer "
+ "bound\n", prim_walk, i);
+ return -EINVAL;
+ }
+ if (size > radeon_bo_size(track->arrays[i].robj)) {
+ dev_err(rdev->dev, "(PW %u) Vertex array %u "
+ "need %lu dwords have %lu dwords\n",
+ prim_walk, i, size >> 2,
+ radeon_bo_size(track->arrays[i].robj)
+ >> 2);
+ DRM_ERROR("Max indices %u\n", track->max_indx);
+ return -EINVAL;
+ }
+ }
+ break;
+ case 2:
+ for (i = 0; i < track->num_arrays; i++) {
+ size = track->arrays[i].esize * (nverts - 1) * 4;
+ if (track->arrays[i].robj == NULL) {
+ DRM_ERROR("(PW %u) Vertex array %u no buffer "
+ "bound\n", prim_walk, i);
+ return -EINVAL;
+ }
+ if (size > radeon_bo_size(track->arrays[i].robj)) {
+ dev_err(rdev->dev, "(PW %u) Vertex array %u "
+ "need %lu dwords have %lu dwords\n",
+ prim_walk, i, size >> 2,
+ radeon_bo_size(track->arrays[i].robj)
+ >> 2);
+ return -EINVAL;
+ }
+ }
+ break;
+ case 3:
+ size = track->vtx_size * nverts;
+ if (size != track->immd_dwords) {
+ DRM_ERROR("IMMD draw %u dwors but needs %lu dwords\n",
+ track->immd_dwords, size);
+ DRM_ERROR("VAP_VF_CNTL.NUM_VERTICES %u, VTX_SIZE %u\n",
+ nverts, track->vtx_size);
+ return -EINVAL;
+ }
+ break;
+ default:
+ DRM_ERROR("[drm] Invalid primitive walk %d for VAP_VF_CNTL\n",
+ prim_walk);
+ return -EINVAL;
}
+
+ if (track->tex_dirty) {
+ track->tex_dirty = false;
+ return r100_cs_track_texture_check(rdev, track);
+ }
+ return 0;
}
-/* Wait for vertical sync on secondary CRTC */
-void r100_gpu_wait_for_vsync2(struct radeon_device *rdev)
+void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track)
{
- uint32_t crtc2_gen_cntl, tmp;
- int i;
+ unsigned i, face;
- crtc2_gen_cntl = RREG32(RADEON_CRTC2_GEN_CNTL);
- if ((crtc2_gen_cntl & RADEON_CRTC2_DISP_REQ_EN_B) ||
- !(crtc2_gen_cntl & RADEON_CRTC2_EN))
- return;
+ track->cb_dirty = true;
+ track->zb_dirty = true;
+ track->tex_dirty = true;
+ track->aa_dirty = true;
- /* Clear the CRTC_VBLANK_SAVE bit */
- WREG32(RADEON_CRTC2_STATUS, RADEON_CRTC2_VBLANK_SAVE_CLEAR);
- for (i = 0; i < rdev->usec_timeout; i++) {
- tmp = RREG32(RADEON_CRTC2_STATUS);
- if (tmp & RADEON_CRTC2_VBLANK_SAVE) {
- return;
+ if (rdev->family < CHIP_R300) {
+ track->num_cb = 1;
+ if (rdev->family <= CHIP_RS200)
+ track->num_texture = 3;
+ else
+ track->num_texture = 6;
+ track->maxy = 2048;
+ track->separate_cube = 1;
+ } else {
+ track->num_cb = 4;
+ track->num_texture = 16;
+ track->maxy = 4096;
+ track->separate_cube = 0;
+ track->aaresolve = false;
+ track->aa.robj = NULL;
+ }
+
+ for (i = 0; i < track->num_cb; i++) {
+ track->cb[i].robj = NULL;
+ track->cb[i].pitch = 8192;
+ track->cb[i].cpp = 16;
+ track->cb[i].offset = 0;
+ }
+ track->z_enabled = true;
+ track->zb.robj = NULL;
+ track->zb.pitch = 8192;
+ track->zb.cpp = 4;
+ track->zb.offset = 0;
+ track->vtx_size = 0x7F;
+ track->immd_dwords = 0xFFFFFFFFUL;
+ track->num_arrays = 11;
+ track->max_indx = 0x00FFFFFFUL;
+ for (i = 0; i < track->num_arrays; i++) {
+ track->arrays[i].robj = NULL;
+ track->arrays[i].esize = 0x7F;
+ }
+ for (i = 0; i < track->num_texture; i++) {
+ track->textures[i].compress_format = R100_TRACK_COMP_NONE;
+ track->textures[i].pitch = 16536;
+ track->textures[i].width = 16536;
+ track->textures[i].height = 16536;
+ track->textures[i].width_11 = 1 << 11;
+ track->textures[i].height_11 = 1 << 11;
+ track->textures[i].num_levels = 12;
+ if (rdev->family <= CHIP_RS200) {
+ track->textures[i].tex_coord_type = 0;
+ track->textures[i].txdepth = 0;
+ } else {
+ track->textures[i].txdepth = 16;
+ track->textures[i].tex_coord_type = 1;
}
- DRM_UDELAY(1);
+ track->textures[i].cpp = 64;
+ track->textures[i].robj = NULL;
+ /* CS IB emission code makes sure texture unit are disabled */
+ track->textures[i].enabled = false;
+ track->textures[i].lookup_disable = false;
+ track->textures[i].roundup_w = true;
+ track->textures[i].roundup_h = true;
+ if (track->separate_cube)
+ for (face = 0; face < 5; face++) {
+ track->textures[i].cube_info[face].robj = NULL;
+ track->textures[i].cube_info[face].width = 16536;
+ track->textures[i].cube_info[face].height = 16536;
+ track->textures[i].cube_info[face].offset = 0;
+ }
}
}
-int r100_rbbm_fifo_wait_for_entry(struct radeon_device *rdev, unsigned n)
+/*
+ * Global GPU functions
+ */
+static void r100_errata(struct radeon_device *rdev)
+{
+ rdev->pll_errata = 0;
+
+ if (rdev->family == CHIP_RV200 || rdev->family == CHIP_RS200) {
+ rdev->pll_errata |= CHIP_ERRATA_PLL_DUMMYREADS;
+ }
+
+ if (rdev->family == CHIP_RV100 ||
+ rdev->family == CHIP_RS100 ||
+ rdev->family == CHIP_RS200) {
+ rdev->pll_errata |= CHIP_ERRATA_PLL_DELAY;
+ }
+}
+
+static int r100_rbbm_fifo_wait_for_entry(struct radeon_device *rdev, unsigned n)
{
unsigned i;
uint32_t tmp;
@@ -2106,79 +2497,25 @@ int r100_mc_wait_for_idle(struct radeon_device *rdev)
return -1;
}
-void r100_gpu_lockup_update(struct r100_gpu_lockup *lockup, struct radeon_ring *ring)
-{
- lockup->last_cp_rptr = ring->rptr;
- lockup->last_jiffies = jiffies;
-}
-
-/**
- * r100_gpu_cp_is_lockup() - check if CP is lockup by recording information
- * @rdev: radeon device structure
- * @lockup: r100_gpu_lockup structure holding CP lockup tracking informations
- * @cp: radeon_cp structure holding CP information
- *
- * We don't need to initialize the lockup tracking information as we will either
- * have CP rptr to a different value of jiffies wrap around which will force
- * initialization of the lockup tracking informations.
- *
- * A possible false positivie is if we get call after while and last_cp_rptr ==
- * the current CP rptr, even if it's unlikely it might happen. To avoid this
- * if the elapsed time since last call is bigger than 2 second than we return
- * false and update the tracking information. Due to this the caller must call
- * r100_gpu_cp_is_lockup several time in less than 2sec for lockup to be reported
- * the fencing code should be cautious about that.
- *
- * Caller should write to the ring to force CP to do something so we don't get
- * false positive when CP is just gived nothing to do.
- *
- **/
-bool r100_gpu_cp_is_lockup(struct radeon_device *rdev, struct r100_gpu_lockup *lockup, struct radeon_ring *ring)
-{
- unsigned long cjiffies, elapsed;
-
- cjiffies = jiffies;
- if (!time_after(cjiffies, lockup->last_jiffies)) {
- /* likely a wrap around */
- lockup->last_cp_rptr = ring->rptr;
- lockup->last_jiffies = jiffies;
- return false;
- }
- if (ring->rptr != lockup->last_cp_rptr) {
- /* CP is still working no lockup */
- lockup->last_cp_rptr = ring->rptr;
- lockup->last_jiffies = jiffies;
- return false;
- }
- elapsed = jiffies_to_msecs(cjiffies - lockup->last_jiffies);
- if (elapsed >= 10000) {
- dev_err(rdev->dev, "GPU lockup CP stall for more than %lumsec\n", elapsed);
- return true;
- }
- /* give a chance to the GPU ... */
- return false;
-}
-
bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
{
u32 rbbm_status;
- int r;
rbbm_status = RREG32(R_000E40_RBBM_STATUS);
if (!G_000E40_GUI_ACTIVE(rbbm_status)) {
- r100_gpu_lockup_update(&rdev->config.r100.lockup, ring);
+ radeon_ring_lockup_update(rdev, ring);
return false;
}
- /* force CP activities */
- r = radeon_ring_lock(rdev, ring, 2);
- if (!r) {
- /* PACKET2 NOP */
- radeon_ring_write(ring, 0x80000000);
- radeon_ring_write(ring, 0x80000000);
- radeon_ring_unlock_commit(rdev, ring);
- }
- ring->rptr = RREG32(ring->rptr_reg);
- return r100_gpu_cp_is_lockup(rdev, &rdev->config.r100.lockup, ring);
+ return radeon_ring_test_lockup(rdev, ring);
+}
+
+/* required on r1xx, r2xx, r300, r(v)350, r420/r481, rs400/rs480 */
+void r100_enable_bm(struct radeon_device *rdev)
+{
+ uint32_t tmp;
+ /* Enable bus mastering */
+ tmp = RREG32(RADEON_BUS_CNTL) & ~RADEON_BUS_MASTER_DIS;
+ WREG32(RADEON_BUS_CNTL, tmp);
}
void r100_bm_disable(struct radeon_device *rdev)
@@ -2247,7 +2584,6 @@ int r100_asic_reset(struct radeon_device *rdev)
if (G_000E40_SE_BUSY(status) || G_000E40_RE_BUSY(status) ||
G_000E40_TAM_BUSY(status) || G_000E40_PB_BUSY(status)) {
dev_err(rdev->dev, "failed to reset GPU\n");
- rdev->gpu_lockup = true;
ret = -1;
} else
dev_info(rdev->dev, "GPU reset succeed\n");
@@ -2470,7 +2806,7 @@ void r100_vga_set_state(struct radeon_device *rdev, bool state)
WREG32(RADEON_CONFIG_CNTL, temp);
}
-void r100_mc_init(struct radeon_device *rdev)
+static void r100_mc_init(struct radeon_device *rdev)
{
u64 base;
@@ -2504,7 +2840,7 @@ static void r100_pll_errata_after_data(struct radeon_device *rdev)
* or the chip could hang on a subsequent access
*/
if (rdev->pll_errata & CHIP_ERRATA_PLL_DELAY) {
- udelay(5000);
+ mdelay(5);
}
/* This function is required to workaround a hardware bug in some (all?)
@@ -2525,24 +2861,31 @@ 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);
}
-void r100_set_safe_registers(struct radeon_device *rdev)
+static void r100_set_safe_registers(struct radeon_device *rdev)
{
if (ASIC_IS_RN50(rdev)) {
rdev->config.r100.reg_safe_bm = rn50_reg_safe_bm;
@@ -2598,9 +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;
}
@@ -2740,6 +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;
@@ -2757,13 +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;
@@ -2859,12 +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;
}
}
@@ -3268,380 +3610,6 @@ void r100_bandwidth_update(struct radeon_device *rdev)
}
}
-static void r100_cs_track_texture_print(struct r100_cs_track_texture *t)
-{
- DRM_ERROR("pitch %d\n", t->pitch);
- DRM_ERROR("use_pitch %d\n", t->use_pitch);
- DRM_ERROR("width %d\n", t->width);
- DRM_ERROR("width_11 %d\n", t->width_11);
- DRM_ERROR("height %d\n", t->height);
- DRM_ERROR("height_11 %d\n", t->height_11);
- DRM_ERROR("num levels %d\n", t->num_levels);
- DRM_ERROR("depth %d\n", t->txdepth);
- DRM_ERROR("bpp %d\n", t->cpp);
- DRM_ERROR("coordinate type %d\n", t->tex_coord_type);
- DRM_ERROR("width round to power of 2 %d\n", t->roundup_w);
- DRM_ERROR("height round to power of 2 %d\n", t->roundup_h);
- DRM_ERROR("compress format %d\n", t->compress_format);
-}
-
-static int r100_track_compress_size(int compress_format, int w, int h)
-{
- int block_width, block_height, block_bytes;
- int wblocks, hblocks;
- int min_wblocks;
- int sz;
-
- block_width = 4;
- block_height = 4;
-
- switch (compress_format) {
- case R100_TRACK_COMP_DXT1:
- block_bytes = 8;
- min_wblocks = 4;
- break;
- default:
- case R100_TRACK_COMP_DXT35:
- block_bytes = 16;
- min_wblocks = 2;
- break;
- }
-
- hblocks = (h + block_height - 1) / block_height;
- wblocks = (w + block_width - 1) / block_width;
- if (wblocks < min_wblocks)
- wblocks = min_wblocks;
- sz = wblocks * hblocks * block_bytes;
- return sz;
-}
-
-static int r100_cs_track_cube(struct radeon_device *rdev,
- struct r100_cs_track *track, unsigned idx)
-{
- unsigned face, w, h;
- struct radeon_bo *cube_robj;
- unsigned long size;
- unsigned compress_format = track->textures[idx].compress_format;
-
- for (face = 0; face < 5; face++) {
- cube_robj = track->textures[idx].cube_info[face].robj;
- w = track->textures[idx].cube_info[face].width;
- h = track->textures[idx].cube_info[face].height;
-
- if (compress_format) {
- size = r100_track_compress_size(compress_format, w, h);
- } else
- size = w * h;
- size *= track->textures[idx].cpp;
-
- size += track->textures[idx].cube_info[face].offset;
-
- if (size > radeon_bo_size(cube_robj)) {
- DRM_ERROR("Cube texture offset greater than object size %lu %lu\n",
- size, radeon_bo_size(cube_robj));
- r100_cs_track_texture_print(&track->textures[idx]);
- return -1;
- }
- }
- return 0;
-}
-
-static int r100_cs_track_texture_check(struct radeon_device *rdev,
- struct r100_cs_track *track)
-{
- struct radeon_bo *robj;
- unsigned long size;
- unsigned u, i, w, h, d;
- int ret;
-
- for (u = 0; u < track->num_texture; u++) {
- if (!track->textures[u].enabled)
- continue;
- if (track->textures[u].lookup_disable)
- continue;
- robj = track->textures[u].robj;
- if (robj == NULL) {
- DRM_ERROR("No texture bound to unit %u\n", u);
- return -EINVAL;
- }
- size = 0;
- for (i = 0; i <= track->textures[u].num_levels; i++) {
- if (track->textures[u].use_pitch) {
- if (rdev->family < CHIP_R300)
- w = (track->textures[u].pitch / track->textures[u].cpp) / (1 << i);
- else
- w = track->textures[u].pitch / (1 << i);
- } else {
- w = track->textures[u].width;
- if (rdev->family >= CHIP_RV515)
- w |= track->textures[u].width_11;
- w = w / (1 << i);
- if (track->textures[u].roundup_w)
- w = roundup_pow_of_two(w);
- }
- h = track->textures[u].height;
- if (rdev->family >= CHIP_RV515)
- h |= track->textures[u].height_11;
- h = h / (1 << i);
- if (track->textures[u].roundup_h)
- h = roundup_pow_of_two(h);
- if (track->textures[u].tex_coord_type == 1) {
- d = (1 << track->textures[u].txdepth) / (1 << i);
- if (!d)
- d = 1;
- } else {
- d = 1;
- }
- if (track->textures[u].compress_format) {
-
- size += r100_track_compress_size(track->textures[u].compress_format, w, h) * d;
- /* compressed textures are block based */
- } else
- size += w * h * d;
- }
- size *= track->textures[u].cpp;
-
- switch (track->textures[u].tex_coord_type) {
- case 0:
- case 1:
- break;
- case 2:
- if (track->separate_cube) {
- ret = r100_cs_track_cube(rdev, track, u);
- if (ret)
- return ret;
- } else
- size *= 6;
- break;
- default:
- DRM_ERROR("Invalid texture coordinate type %u for unit "
- "%u\n", track->textures[u].tex_coord_type, u);
- return -EINVAL;
- }
- if (size > radeon_bo_size(robj)) {
- DRM_ERROR("Texture of unit %u needs %lu bytes but is "
- "%lu\n", u, size, radeon_bo_size(robj));
- r100_cs_track_texture_print(&track->textures[u]);
- return -EINVAL;
- }
- }
- return 0;
-}
-
-int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track)
-{
- unsigned i;
- unsigned long size;
- unsigned prim_walk;
- unsigned nverts;
- unsigned num_cb = track->cb_dirty ? track->num_cb : 0;
-
- if (num_cb && !track->zb_cb_clear && !track->color_channel_mask &&
- !track->blend_read_enable)
- num_cb = 0;
-
- for (i = 0; i < num_cb; i++) {
- if (track->cb[i].robj == NULL) {
- DRM_ERROR("[drm] No buffer for color buffer %d !\n", i);
- return -EINVAL;
- }
- size = track->cb[i].pitch * track->cb[i].cpp * track->maxy;
- size += track->cb[i].offset;
- if (size > radeon_bo_size(track->cb[i].robj)) {
- DRM_ERROR("[drm] Buffer too small for color buffer %d "
- "(need %lu have %lu) !\n", i, size,
- radeon_bo_size(track->cb[i].robj));
- DRM_ERROR("[drm] color buffer %d (%u %u %u %u)\n",
- i, track->cb[i].pitch, track->cb[i].cpp,
- track->cb[i].offset, track->maxy);
- return -EINVAL;
- }
- }
- track->cb_dirty = false;
-
- if (track->zb_dirty && track->z_enabled) {
- if (track->zb.robj == NULL) {
- DRM_ERROR("[drm] No buffer for z buffer !\n");
- return -EINVAL;
- }
- size = track->zb.pitch * track->zb.cpp * track->maxy;
- size += track->zb.offset;
- if (size > radeon_bo_size(track->zb.robj)) {
- DRM_ERROR("[drm] Buffer too small for z buffer "
- "(need %lu have %lu) !\n", size,
- radeon_bo_size(track->zb.robj));
- DRM_ERROR("[drm] zbuffer (%u %u %u %u)\n",
- track->zb.pitch, track->zb.cpp,
- track->zb.offset, track->maxy);
- return -EINVAL;
- }
- }
- track->zb_dirty = false;
-
- if (track->aa_dirty && track->aaresolve) {
- if (track->aa.robj == NULL) {
- DRM_ERROR("[drm] No buffer for AA resolve buffer %d !\n", i);
- return -EINVAL;
- }
- /* I believe the format comes from colorbuffer0. */
- size = track->aa.pitch * track->cb[0].cpp * track->maxy;
- size += track->aa.offset;
- if (size > radeon_bo_size(track->aa.robj)) {
- DRM_ERROR("[drm] Buffer too small for AA resolve buffer %d "
- "(need %lu have %lu) !\n", i, size,
- radeon_bo_size(track->aa.robj));
- DRM_ERROR("[drm] AA resolve buffer %d (%u %u %u %u)\n",
- i, track->aa.pitch, track->cb[0].cpp,
- track->aa.offset, track->maxy);
- return -EINVAL;
- }
- }
- track->aa_dirty = false;
-
- prim_walk = (track->vap_vf_cntl >> 4) & 0x3;
- if (track->vap_vf_cntl & (1 << 14)) {
- nverts = track->vap_alt_nverts;
- } else {
- nverts = (track->vap_vf_cntl >> 16) & 0xFFFF;
- }
- switch (prim_walk) {
- case 1:
- for (i = 0; i < track->num_arrays; i++) {
- size = track->arrays[i].esize * track->max_indx * 4;
- if (track->arrays[i].robj == NULL) {
- DRM_ERROR("(PW %u) Vertex array %u no buffer "
- "bound\n", prim_walk, i);
- return -EINVAL;
- }
- if (size > radeon_bo_size(track->arrays[i].robj)) {
- dev_err(rdev->dev, "(PW %u) Vertex array %u "
- "need %lu dwords have %lu dwords\n",
- prim_walk, i, size >> 2,
- radeon_bo_size(track->arrays[i].robj)
- >> 2);
- DRM_ERROR("Max indices %u\n", track->max_indx);
- return -EINVAL;
- }
- }
- break;
- case 2:
- for (i = 0; i < track->num_arrays; i++) {
- size = track->arrays[i].esize * (nverts - 1) * 4;
- if (track->arrays[i].robj == NULL) {
- DRM_ERROR("(PW %u) Vertex array %u no buffer "
- "bound\n", prim_walk, i);
- return -EINVAL;
- }
- if (size > radeon_bo_size(track->arrays[i].robj)) {
- dev_err(rdev->dev, "(PW %u) Vertex array %u "
- "need %lu dwords have %lu dwords\n",
- prim_walk, i, size >> 2,
- radeon_bo_size(track->arrays[i].robj)
- >> 2);
- return -EINVAL;
- }
- }
- break;
- case 3:
- size = track->vtx_size * nverts;
- if (size != track->immd_dwords) {
- DRM_ERROR("IMMD draw %u dwors but needs %lu dwords\n",
- track->immd_dwords, size);
- DRM_ERROR("VAP_VF_CNTL.NUM_VERTICES %u, VTX_SIZE %u\n",
- nverts, track->vtx_size);
- return -EINVAL;
- }
- break;
- default:
- DRM_ERROR("[drm] Invalid primitive walk %d for VAP_VF_CNTL\n",
- prim_walk);
- return -EINVAL;
- }
-
- if (track->tex_dirty) {
- track->tex_dirty = false;
- return r100_cs_track_texture_check(rdev, track);
- }
- return 0;
-}
-
-void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track)
-{
- unsigned i, face;
-
- track->cb_dirty = true;
- track->zb_dirty = true;
- track->tex_dirty = true;
- track->aa_dirty = true;
-
- if (rdev->family < CHIP_R300) {
- track->num_cb = 1;
- if (rdev->family <= CHIP_RS200)
- track->num_texture = 3;
- else
- track->num_texture = 6;
- track->maxy = 2048;
- track->separate_cube = 1;
- } else {
- track->num_cb = 4;
- track->num_texture = 16;
- track->maxy = 4096;
- track->separate_cube = 0;
- track->aaresolve = false;
- track->aa.robj = NULL;
- }
-
- for (i = 0; i < track->num_cb; i++) {
- track->cb[i].robj = NULL;
- track->cb[i].pitch = 8192;
- track->cb[i].cpp = 16;
- track->cb[i].offset = 0;
- }
- track->z_enabled = true;
- track->zb.robj = NULL;
- track->zb.pitch = 8192;
- track->zb.cpp = 4;
- track->zb.offset = 0;
- track->vtx_size = 0x7F;
- track->immd_dwords = 0xFFFFFFFFUL;
- track->num_arrays = 11;
- track->max_indx = 0x00FFFFFFUL;
- for (i = 0; i < track->num_arrays; i++) {
- track->arrays[i].robj = NULL;
- track->arrays[i].esize = 0x7F;
- }
- for (i = 0; i < track->num_texture; i++) {
- track->textures[i].compress_format = R100_TRACK_COMP_NONE;
- track->textures[i].pitch = 16536;
- track->textures[i].width = 16536;
- track->textures[i].height = 16536;
- track->textures[i].width_11 = 1 << 11;
- track->textures[i].height_11 = 1 << 11;
- track->textures[i].num_levels = 12;
- if (rdev->family <= CHIP_RS200) {
- track->textures[i].tex_coord_type = 0;
- track->textures[i].txdepth = 0;
- } else {
- track->textures[i].txdepth = 16;
- track->textures[i].tex_coord_type = 1;
- }
- track->textures[i].cpp = 64;
- track->textures[i].robj = NULL;
- /* CS IB emission code makes sure texture unit are disabled */
- track->textures[i].enabled = false;
- track->textures[i].lookup_disable = false;
- track->textures[i].roundup_w = true;
- track->textures[i].roundup_h = true;
- if (track->separate_cube)
- for (face = 0; face < 5; face++) {
- track->textures[i].cube_info[face].robj = NULL;
- track->textures[i].cube_info[face].width = 16536;
- track->textures[i].cube_info[face].height = 16536;
- track->textures[i].cube_info[face].offset = 0;
- }
- }
-}
-
int r100_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
{
uint32_t scratch;
@@ -3686,14 +3654,20 @@ void r100_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
{
struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
+ if (ring->rptr_save_reg) {
+ u32 next_rptr = ring->wptr + 2 + 3;
+ radeon_ring_write(ring, PACKET0(ring->rptr_save_reg, 0));
+ radeon_ring_write(ring, next_rptr);
+ }
+
radeon_ring_write(ring, PACKET0(RADEON_CP_IB_BASE, 1));
radeon_ring_write(ring, ib->gpu_addr);
radeon_ring_write(ring, ib->length_dw);
}
-int r100_ib_test(struct radeon_device *rdev)
+int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
{
- struct radeon_ib *ib;
+ struct radeon_ib ib;
uint32_t scratch;
uint32_t tmp = 0;
unsigned i;
@@ -3705,28 +3679,29 @@ int r100_ib_test(struct radeon_device *rdev)
return r;
}
WREG32(scratch, 0xCAFEDEAD);
- r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &ib, 256);
+ r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &ib, NULL, 256);
if (r) {
- return r;
- }
- ib->ptr[0] = PACKET0(scratch, 0);
- ib->ptr[1] = 0xDEADBEEF;
- ib->ptr[2] = PACKET2(0);
- ib->ptr[3] = PACKET2(0);
- ib->ptr[4] = PACKET2(0);
- ib->ptr[5] = PACKET2(0);
- ib->ptr[6] = PACKET2(0);
- ib->ptr[7] = PACKET2(0);
- ib->length_dw = 8;
- r = radeon_ib_schedule(rdev, ib);
+ DRM_ERROR("radeon: failed to get ib (%d).\n", r);
+ goto free_scratch;
+ }
+ ib.ptr[0] = PACKET0(scratch, 0);
+ ib.ptr[1] = 0xDEADBEEF;
+ ib.ptr[2] = PACKET2(0);
+ ib.ptr[3] = PACKET2(0);
+ ib.ptr[4] = PACKET2(0);
+ ib.ptr[5] = PACKET2(0);
+ ib.ptr[6] = PACKET2(0);
+ ib.ptr[7] = PACKET2(0);
+ ib.length_dw = 8;
+ r = radeon_ib_schedule(rdev, &ib, NULL);
if (r) {
- radeon_scratch_free(rdev, scratch);
- radeon_ib_free(rdev, &ib);
- return r;
+ DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
+ goto free_ib;
}
- r = radeon_fence_wait(ib->fence, false);
+ r = radeon_fence_wait(ib.fence, false);
if (r) {
- return r;
+ DRM_ERROR("radeon: fence wait failed (%d).\n", r);
+ goto free_ib;
}
for (i = 0; i < rdev->usec_timeout; i++) {
tmp = RREG32(scratch);
@@ -3742,17 +3717,13 @@ int r100_ib_test(struct radeon_device *rdev)
scratch, tmp);
r = -EINVAL;
}
- radeon_scratch_free(rdev, scratch);
+free_ib:
radeon_ib_free(rdev, &ib);
+free_scratch:
+ radeon_scratch_free(rdev, scratch);
return r;
}
-void r100_ib_fini(struct radeon_device *rdev)
-{
- radeon_ib_pool_suspend(rdev);
- radeon_ib_pool_fini(rdev);
-}
-
void r100_mc_stop(struct radeon_device *rdev, struct r100_mc_save *save)
{
/* Shutdown CP we shouldn't need to do that but better be safe than
@@ -3858,7 +3829,7 @@ static void r100_mc_program(struct radeon_device *rdev)
r100_mc_resume(rdev, &save);
}
-void r100_clock_startup(struct radeon_device *rdev)
+static void r100_clock_startup(struct radeon_device *rdev)
{
u32 tmp;
@@ -3903,6 +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 */
@@ -3912,14 +3889,9 @@ static int r100_startup(struct radeon_device *rdev)
return r;
}
- r = radeon_ib_pool_start(rdev);
- if (r)
- return r;
-
- r = r100_ib_test(rdev);
+ r = radeon_ib_pool_init(rdev);
if (r) {
- dev_err(rdev->dev, "failed testing IB (%d).\n", r);
- rdev->accel_working = false;
+ dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
return r;
}
@@ -3958,7 +3930,7 @@ int r100_resume(struct radeon_device *rdev)
int r100_suspend(struct radeon_device *rdev)
{
- radeon_ib_pool_suspend(rdev);
+ radeon_pm_suspend(rdev);
r100_cp_disable(rdev);
radeon_wb_disable(rdev);
r100_irq_disable(rdev);
@@ -3969,9 +3941,10 @@ 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);
- r100_ib_fini(rdev);
+ radeon_ib_pool_fini(rdev);
radeon_gem_fini(rdev);
if (rdev->flags & RADEON_IS_PCI)
r100_pci_gart_fini(rdev);
@@ -4064,9 +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)
@@ -4078,20 +4048,17 @@ int r100_init(struct radeon_device *rdev)
}
r100_set_safe_registers(rdev);
- r = radeon_ib_pool_init(rdev);
- rdev->accel_working = true;
- if (r) {
- dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
- rdev->accel_working = false;
- }
+ /* Initialize power management */
+ radeon_pm_init(rdev);
+ rdev->accel_working = true;
r = r100_startup(rdev);
if (r) {
/* Somethings want wront with the accel init stop accel */
dev_err(rdev->dev, "Disabling GPU acceleration\n");
r100_cp_fini(rdev);
radeon_wb_fini(rdev);
- r100_ib_fini(rdev);
+ radeon_ib_pool_fini(rdev);
radeon_irq_kms_fini(rdev);
if (rdev->flags & RADEON_IS_PCI)
r100_pci_gart_fini(rdev);
@@ -4100,23 +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 08:22:22 +0000