From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB
---
kernel/drivers/gpu/drm/i915/intel_pm.c | 7436 +++++++++++++++++++++--------------------------------------
1 files changed, 2,656 insertions(+), 4,780 deletions(-)
diff --git a/kernel/drivers/gpu/drm/i915/intel_pm.c b/kernel/drivers/gpu/drm/i915/intel_pm.c
index 1847faa..1b5e8d3 100644
--- a/kernel/drivers/gpu/drm/i915/intel_pm.c
+++ b/kernel/drivers/gpu/drm/i915/intel_pm.c
@@ -25,33 +25,51 @@
*
*/
-#include <linux/cpufreq.h>
-#include <drm/drm_plane_helper.h>
-#include "i915_drv.h"
-#include "intel_drv.h"
-#include "../../../platform/x86/intel_ips.h"
#include <linux/module.h>
-#include <drm/drm_atomic_helper.h>
+#include <linux/pm_runtime.h>
-/**
- * DOC: RC6
- *
- * RC6 is a special power stage which allows the GPU to enter an very
- * low-voltage mode when idle, using down to 0V while at this stage. This
- * stage is entered automatically when the GPU is idle when RC6 support is
- * enabled, and as soon as new workload arises GPU wakes up automatically as well.
- *
- * There are different RC6 modes available in Intel GPU, which differentiate
- * among each other with the latency required to enter and leave RC6 and
- * voltage consumed by the GPU in different states.
- *
- * The combination of the following flags define which states GPU is allowed
- * to enter, while RC6 is the normal RC6 state, RC6p is the deep RC6, and
- * RC6pp is deepest RC6. Their support by hardware varies according to the
- * GPU, BIOS, chipset and platform. RC6 is usually the safest one and the one
- * which brings the most power savings; deeper states save more power, but
- * require higher latency to switch to and wake up.
- */
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_plane_helper.h>
+
+#include "display/intel_atomic.h"
+#include "display/intel_bw.h"
+#include "display/intel_display_types.h"
+#include "display/intel_fbc.h"
+#include "display/intel_sprite.h"
+
+#include "gt/intel_llc.h"
+
+#include "i915_drv.h"
+#include "i915_fixed.h"
+#include "i915_irq.h"
+#include "i915_trace.h"
+#include "intel_pm.h"
+#include "intel_sideband.h"
+#include "../../../platform/x86/intel_ips.h"
+
+/* Stores plane specific WM parameters */
+struct skl_wm_params {
+ bool x_tiled, y_tiled;
+ bool rc_surface;
+ bool is_planar;
+ u32 width;
+ u8 cpp;
+ u32 plane_pixel_rate;
+ u32 y_min_scanlines;
+ u32 plane_bytes_per_line;
+ uint_fixed_16_16_t plane_blocks_per_line;
+ uint_fixed_16_16_t y_tile_minimum;
+ u32 linetime_us;
+ u32 dbuf_block_size;
+};
+
+/* used in computing the new watermarks state */
+struct intel_wm_config {
+ unsigned int num_pipes_active;
+ bool sprites_enabled;
+ bool sprites_scaled;
+};
static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
{
@@ -76,21 +94,12 @@
I915_WRITE(GEN8_CHICKEN_DCPR_1,
I915_READ(GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM);
- /* WaFbcTurnOffFbcWatermark:skl,bxt,kbl,cfl */
- /* WaFbcWakeMemOn:skl,bxt,kbl,glk,cfl */
+ /*
+ * WaFbcWakeMemOn:skl,bxt,kbl,glk,cfl
+ * Display WA #0859: skl,bxt,kbl,glk,cfl
+ */
I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
- DISP_FBC_WM_DIS |
DISP_FBC_MEMORY_WAKE);
-
- /* WaFbcHighMemBwCorruptionAvoidance:skl,bxt,kbl,cfl */
- I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
- ILK_DPFC_DISABLE_DUMMY0);
-
- if (IS_SKYLAKE(dev_priv)) {
- /* WaDisableDopClockGating */
- I915_WRITE(GEN7_MISCCPCTL, I915_READ(GEN7_MISCCPCTL)
- & ~GEN7_DOP_CLOCK_GATE_ENABLE);
- }
}
static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -122,6 +131,20 @@
* application, using batch buffers or any other means.
*/
I915_WRITE(RM_TIMEOUT, MMIO_TIMEOUT_US(950));
+
+ /*
+ * WaFbcTurnOffFbcWatermark:bxt
+ * Display WA #0562: bxt
+ */
+ I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
+ DISP_FBC_WM_DIS);
+
+ /*
+ * WaFbcHighMemBwCorruptionAvoidance:bxt
+ * Display WA #0883: bxt
+ */
+ I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
+ ILK_DPFC_DISABLE_DUMMY0);
}
static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -135,19 +158,9 @@
*/
I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
PWM1_GATING_DIS | PWM2_GATING_DIS);
-
- /* WaDDIIOTimeout:glk */
- if (IS_GLK_REVID(dev_priv, 0, GLK_REVID_A1)) {
- u32 val = I915_READ(CHICKEN_MISC_2);
- val &= ~(GLK_CL0_PWR_DOWN |
- GLK_CL1_PWR_DOWN |
- GLK_CL2_PWR_DOWN);
- I915_WRITE(CHICKEN_MISC_2, val);
- }
-
}
-static void i915_pineview_get_mem_freq(struct drm_i915_private *dev_priv)
+static void pnv_get_mem_freq(struct drm_i915_private *dev_priv)
{
u32 tmp;
@@ -185,12 +198,12 @@
dev_priv->is_ddr3 = (tmp & CSHRDDR3CTL_DDR3) ? 1 : 0;
}
-static void i915_ironlake_get_mem_freq(struct drm_i915_private *dev_priv)
+static void ilk_get_mem_freq(struct drm_i915_private *dev_priv)
{
u16 ddrpll, csipll;
- ddrpll = I915_READ16(DDRMPLL1);
- csipll = I915_READ16(CSIPLL0);
+ ddrpll = intel_uncore_read16(&dev_priv->uncore, DDRMPLL1);
+ csipll = intel_uncore_read16(&dev_priv->uncore, CSIPLL0);
switch (ddrpll & 0xff) {
case 0xc:
@@ -206,13 +219,11 @@
dev_priv->mem_freq = 1600;
break;
default:
- DRM_DEBUG_DRIVER("unknown memory frequency 0x%02x\n",
- ddrpll & 0xff);
+ drm_dbg(&dev_priv->drm, "unknown memory frequency 0x%02x\n",
+ ddrpll & 0xff);
dev_priv->mem_freq = 0;
break;
}
-
- dev_priv->ips.r_t = dev_priv->mem_freq;
switch (csipll & 0x3ff) {
case 0x00c:
@@ -237,18 +248,10 @@
dev_priv->fsb_freq = 6400;
break;
default:
- DRM_DEBUG_DRIVER("unknown fsb frequency 0x%04x\n",
- csipll & 0x3ff);
+ drm_dbg(&dev_priv->drm, "unknown fsb frequency 0x%04x\n",
+ csipll & 0x3ff);
dev_priv->fsb_freq = 0;
break;
- }
-
- if (dev_priv->fsb_freq == 3200) {
- dev_priv->ips.c_m = 0;
- } else if (dev_priv->fsb_freq > 3200 && dev_priv->fsb_freq <= 4800) {
- dev_priv->ips.c_m = 1;
- } else {
- dev_priv->ips.c_m = 2;
}
}
@@ -318,7 +321,7 @@
{
u32 val;
- mutex_lock(&dev_priv->pcu_lock);
+ vlv_punit_get(dev_priv);
val = vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2);
if (enable)
@@ -331,25 +334,26 @@
if (wait_for((vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2) &
FORCE_DDR_FREQ_REQ_ACK) == 0, 3))
- DRM_ERROR("timed out waiting for Punit DDR DVFS request\n");
+ drm_err(&dev_priv->drm,
+ "timed out waiting for Punit DDR DVFS request\n");
- mutex_unlock(&dev_priv->pcu_lock);
+ vlv_punit_put(dev_priv);
}
static void chv_set_memory_pm5(struct drm_i915_private *dev_priv, bool enable)
{
u32 val;
- mutex_lock(&dev_priv->pcu_lock);
+ vlv_punit_get(dev_priv);
- val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
+ val = vlv_punit_read(dev_priv, PUNIT_REG_DSPSSPM);
if (enable)
val |= DSP_MAXFIFO_PM5_ENABLE;
else
val &= ~DSP_MAXFIFO_PM5_ENABLE;
- vlv_punit_write(dev_priv, PUNIT_REG_DSPFREQ, val);
+ vlv_punit_write(dev_priv, PUNIT_REG_DSPSSPM, val);
- mutex_unlock(&dev_priv->pcu_lock);
+ vlv_punit_put(dev_priv);
}
#define FW_WM(value, plane) \
@@ -400,9 +404,9 @@
trace_intel_memory_cxsr(dev_priv, was_enabled, enable);
- DRM_DEBUG_KMS("memory self-refresh is %s (was %s)\n",
- enableddisabled(enable),
- enableddisabled(was_enabled));
+ drm_dbg_kms(&dev_priv->drm, "memory self-refresh is %s (was %s)\n",
+ enableddisabled(enable),
+ enableddisabled(was_enabled));
return was_enabled;
}
@@ -480,14 +484,14 @@
static void vlv_get_fifo_size(struct intel_crtc_state *crtc_state)
{
- struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state;
enum pipe pipe = crtc->pipe;
int sprite0_start, sprite1_start;
+ u32 dsparb, dsparb2, dsparb3;
switch (pipe) {
- uint32_t dsparb, dsparb2, dsparb3;
case PIPE_A:
dsparb = I915_READ(DSPARB);
dsparb2 = I915_READ(DSPARB2);
@@ -520,15 +524,15 @@
static int i9xx_get_fifo_size(struct drm_i915_private *dev_priv,
enum i9xx_plane_id i9xx_plane)
{
- uint32_t dsparb = I915_READ(DSPARB);
+ u32 dsparb = I915_READ(DSPARB);
int size;
size = dsparb & 0x7f;
if (i9xx_plane == PLANE_B)
size = ((dsparb >> DSPARB_CSTART_SHIFT) & 0x7f) - size;
- DRM_DEBUG_KMS("FIFO size - (0x%08x) %c: %d\n",
- dsparb, plane_name(i9xx_plane), size);
+ drm_dbg_kms(&dev_priv->drm, "FIFO size - (0x%08x) %c: %d\n",
+ dsparb, plane_name(i9xx_plane), size);
return size;
}
@@ -536,7 +540,7 @@
static int i830_get_fifo_size(struct drm_i915_private *dev_priv,
enum i9xx_plane_id i9xx_plane)
{
- uint32_t dsparb = I915_READ(DSPARB);
+ u32 dsparb = I915_READ(DSPARB);
int size;
size = dsparb & 0x1ff;
@@ -544,8 +548,8 @@
size = ((dsparb >> DSPARB_BEND_SHIFT) & 0x1ff) - size;
size >>= 1; /* Convert to cachelines */
- DRM_DEBUG_KMS("FIFO size - (0x%08x) %c: %d\n",
- dsparb, plane_name(i9xx_plane), size);
+ drm_dbg_kms(&dev_priv->drm, "FIFO size - (0x%08x) %c: %d\n",
+ dsparb, plane_name(i9xx_plane), size);
return size;
}
@@ -553,47 +557,51 @@
static int i845_get_fifo_size(struct drm_i915_private *dev_priv,
enum i9xx_plane_id i9xx_plane)
{
- uint32_t dsparb = I915_READ(DSPARB);
+ u32 dsparb = I915_READ(DSPARB);
int size;
size = dsparb & 0x7f;
size >>= 2; /* Convert to cachelines */
- DRM_DEBUG_KMS("FIFO size - (0x%08x) %c: %d\n",
- dsparb, plane_name(i9xx_plane), size);
+ drm_dbg_kms(&dev_priv->drm, "FIFO size - (0x%08x) %c: %d\n",
+ dsparb, plane_name(i9xx_plane), size);
return size;
}
/* Pineview has different values for various configs */
-static const struct intel_watermark_params pineview_display_wm = {
+static const struct intel_watermark_params pnv_display_wm = {
.fifo_size = PINEVIEW_DISPLAY_FIFO,
.max_wm = PINEVIEW_MAX_WM,
.default_wm = PINEVIEW_DFT_WM,
.guard_size = PINEVIEW_GUARD_WM,
.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
};
-static const struct intel_watermark_params pineview_display_hplloff_wm = {
+
+static const struct intel_watermark_params pnv_display_hplloff_wm = {
.fifo_size = PINEVIEW_DISPLAY_FIFO,
.max_wm = PINEVIEW_MAX_WM,
.default_wm = PINEVIEW_DFT_HPLLOFF_WM,
.guard_size = PINEVIEW_GUARD_WM,
.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
};
-static const struct intel_watermark_params pineview_cursor_wm = {
+
+static const struct intel_watermark_params pnv_cursor_wm = {
.fifo_size = PINEVIEW_CURSOR_FIFO,
.max_wm = PINEVIEW_CURSOR_MAX_WM,
.default_wm = PINEVIEW_CURSOR_DFT_WM,
.guard_size = PINEVIEW_CURSOR_GUARD_WM,
.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
};
-static const struct intel_watermark_params pineview_cursor_hplloff_wm = {
+
+static const struct intel_watermark_params pnv_cursor_hplloff_wm = {
.fifo_size = PINEVIEW_CURSOR_FIFO,
.max_wm = PINEVIEW_CURSOR_MAX_WM,
.default_wm = PINEVIEW_CURSOR_DFT_WM,
.guard_size = PINEVIEW_CURSOR_GUARD_WM,
.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
};
+
static const struct intel_watermark_params i965_cursor_wm_info = {
.fifo_size = I965_CURSOR_FIFO,
.max_wm = I965_CURSOR_MAX_WM,
@@ -601,6 +609,7 @@
.guard_size = 2,
.cacheline_size = I915_FIFO_LINE_SIZE,
};
+
static const struct intel_watermark_params i945_wm_info = {
.fifo_size = I945_FIFO_SIZE,
.max_wm = I915_MAX_WM,
@@ -608,6 +617,7 @@
.guard_size = 2,
.cacheline_size = I915_FIFO_LINE_SIZE,
};
+
static const struct intel_watermark_params i915_wm_info = {
.fifo_size = I915_FIFO_SIZE,
.max_wm = I915_MAX_WM,
@@ -615,6 +625,7 @@
.guard_size = 2,
.cacheline_size = I915_FIFO_LINE_SIZE,
};
+
static const struct intel_watermark_params i830_a_wm_info = {
.fifo_size = I855GM_FIFO_SIZE,
.max_wm = I915_MAX_WM,
@@ -622,6 +633,7 @@
.guard_size = 2,
.cacheline_size = I830_FIFO_LINE_SIZE,
};
+
static const struct intel_watermark_params i830_bc_wm_info = {
.fifo_size = I855GM_FIFO_SIZE,
.max_wm = I915_MAX_WM/2,
@@ -629,6 +641,7 @@
.guard_size = 2,
.cacheline_size = I830_FIFO_LINE_SIZE,
};
+
static const struct intel_watermark_params i845_wm_info = {
.fifo_size = I830_FIFO_SIZE,
.max_wm = I915_MAX_WM,
@@ -674,9 +687,9 @@
unsigned int cpp,
unsigned int latency)
{
- uint64_t ret;
+ u64 ret;
- ret = (uint64_t) pixel_rate * cpp * latency;
+ ret = mul_u32_u32(pixel_rate, cpp * latency);
ret = DIV_ROUND_UP_ULL(ret, 10000);
return ret;
@@ -811,10 +824,10 @@
static bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state,
const struct intel_plane_state *plane_state)
{
- struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+ struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
/* FIXME check the 'enable' instead */
- if (!crtc_state->base.active)
+ if (!crtc_state->hw.active)
return false;
/*
@@ -826,9 +839,28 @@
* around this problem with the watermark code.
*/
if (plane->id == PLANE_CURSOR)
- return plane_state->base.fb != NULL;
+ return plane_state->hw.fb != NULL;
else
- return plane_state->base.visible;
+ return plane_state->uapi.visible;
+}
+
+static bool intel_crtc_active(struct intel_crtc *crtc)
+{
+ /* Be paranoid as we can arrive here with only partial
+ * state retrieved from the hardware during setup.
+ *
+ * We can ditch the adjusted_mode.crtc_clock check as soon
+ * as Haswell has gained clock readout/fastboot support.
+ *
+ * We can ditch the crtc->primary->state->fb check as soon as we can
+ * properly reconstruct framebuffers.
+ *
+ * FIXME: The intel_crtc->active here should be switched to
+ * crtc->state->active once we have proper CRTC states wired up
+ * for atomic.
+ */
+ return crtc->active && crtc->base.primary->state->fb &&
+ crtc->config->hw.adjusted_mode.crtc_clock;
}
static struct intel_crtc *single_enabled_crtc(struct drm_i915_private *dev_priv)
@@ -846,7 +878,7 @@
return enabled;
}
-static void pineview_update_wm(struct intel_crtc *unused_crtc)
+static void pnv_update_wm(struct intel_crtc *unused_crtc)
{
struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev);
struct intel_crtc *crtc;
@@ -854,12 +886,13 @@
u32 reg;
unsigned int wm;
- latency = intel_get_cxsr_latency(IS_PINEVIEW_G(dev_priv),
+ latency = intel_get_cxsr_latency(!IS_MOBILE(dev_priv),
dev_priv->is_ddr3,
dev_priv->fsb_freq,
dev_priv->mem_freq);
if (!latency) {
- DRM_DEBUG_KMS("Unknown FSB/MEM found, disable CxSR\n");
+ drm_dbg_kms(&dev_priv->drm,
+ "Unknown FSB/MEM found, disable CxSR\n");
intel_set_memory_cxsr(dev_priv, false);
return;
}
@@ -867,25 +900,25 @@
crtc = single_enabled_crtc(dev_priv);
if (crtc) {
const struct drm_display_mode *adjusted_mode =
- &crtc->config->base.adjusted_mode;
+ &crtc->config->hw.adjusted_mode;
const struct drm_framebuffer *fb =
crtc->base.primary->state->fb;
int cpp = fb->format->cpp[0];
int clock = adjusted_mode->crtc_clock;
/* Display SR */
- wm = intel_calculate_wm(clock, &pineview_display_wm,
- pineview_display_wm.fifo_size,
+ wm = intel_calculate_wm(clock, &pnv_display_wm,
+ pnv_display_wm.fifo_size,
cpp, latency->display_sr);
reg = I915_READ(DSPFW1);
reg &= ~DSPFW_SR_MASK;
reg |= FW_WM(wm, SR);
I915_WRITE(DSPFW1, reg);
- DRM_DEBUG_KMS("DSPFW1 register is %x\n", reg);
+ drm_dbg_kms(&dev_priv->drm, "DSPFW1 register is %x\n", reg);
/* cursor SR */
- wm = intel_calculate_wm(clock, &pineview_cursor_wm,
- pineview_display_wm.fifo_size,
+ wm = intel_calculate_wm(clock, &pnv_cursor_wm,
+ pnv_display_wm.fifo_size,
4, latency->cursor_sr);
reg = I915_READ(DSPFW3);
reg &= ~DSPFW_CURSOR_SR_MASK;
@@ -893,8 +926,8 @@
I915_WRITE(DSPFW3, reg);
/* Display HPLL off SR */
- wm = intel_calculate_wm(clock, &pineview_display_hplloff_wm,
- pineview_display_hplloff_wm.fifo_size,
+ wm = intel_calculate_wm(clock, &pnv_display_hplloff_wm,
+ pnv_display_hplloff_wm.fifo_size,
cpp, latency->display_hpll_disable);
reg = I915_READ(DSPFW3);
reg &= ~DSPFW_HPLL_SR_MASK;
@@ -902,14 +935,14 @@
I915_WRITE(DSPFW3, reg);
/* cursor HPLL off SR */
- wm = intel_calculate_wm(clock, &pineview_cursor_hplloff_wm,
- pineview_display_hplloff_wm.fifo_size,
+ wm = intel_calculate_wm(clock, &pnv_cursor_hplloff_wm,
+ pnv_display_hplloff_wm.fifo_size,
4, latency->cursor_hpll_disable);
reg = I915_READ(DSPFW3);
reg &= ~DSPFW_HPLL_CURSOR_MASK;
reg |= FW_WM(wm, HPLL_CURSOR);
I915_WRITE(DSPFW3, reg);
- DRM_DEBUG_KMS("DSPFW3 register is %x\n", reg);
+ drm_dbg_kms(&dev_priv->drm, "DSPFW3 register is %x\n", reg);
intel_set_memory_cxsr(dev_priv, true);
} else {
@@ -1096,14 +1129,14 @@
}
}
-static uint16_t g4x_compute_wm(const struct intel_crtc_state *crtc_state,
- const struct intel_plane_state *plane_state,
- int level)
+static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ int level)
{
- struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+ struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
const struct drm_display_mode *adjusted_mode =
- &crtc_state->base.adjusted_mode;
+ &crtc_state->hw.adjusted_mode;
unsigned int latency = dev_priv->wm.pri_latency[level] * 10;
unsigned int clock, htotal, cpp, width, wm;
@@ -1112,6 +1145,8 @@
if (!intel_wm_plane_visible(crtc_state, plane_state))
return 0;
+
+ cpp = plane_state->hw.fb->format->cpp[0];
/*
* Not 100% sure which way ELK should go here as the
@@ -1126,17 +1161,12 @@
*/
if (IS_GM45(dev_priv) && plane->id == PLANE_PRIMARY &&
level != G4X_WM_LEVEL_NORMAL)
- cpp = 4;
- else
- cpp = plane_state->base.fb->format->cpp[0];
+ cpp = max(cpp, 4u);
clock = adjusted_mode->crtc_clock;
htotal = adjusted_mode->crtc_htotal;
- if (plane->id == PLANE_CURSOR)
- width = plane_state->base.crtc_w;
- else
- width = drm_rect_width(&plane_state->base.dst);
+ width = drm_rect_width(&plane_state->uapi.dst);
if (plane->id == PLANE_CURSOR) {
wm = intel_wm_method2(clock, htotal, width, cpp, latency);
@@ -1163,7 +1193,7 @@
static bool g4x_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
int level, enum plane_id plane_id, u16 value)
{
- struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
bool dirty = false;
for (; level < intel_wm_num_levels(dev_priv); level++) {
@@ -1179,7 +1209,7 @@
static bool g4x_raw_fbc_wm_set(struct intel_crtc_state *crtc_state,
int level, u16 value)
{
- struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
bool dirty = false;
/* NORMAL level doesn't have an FBC watermark */
@@ -1195,14 +1225,15 @@
return dirty;
}
-static uint32_t ilk_compute_fbc_wm(const struct intel_crtc_state *cstate,
- const struct intel_plane_state *pstate,
- uint32_t pri_val);
+static u32 ilk_compute_fbc_wm(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ u32 pri_val);
static bool g4x_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
const struct intel_plane_state *plane_state)
{
- struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+ struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
int num_levels = intel_wm_num_levels(to_i915(plane->base.dev));
enum plane_id plane_id = plane->id;
bool dirty = false;
@@ -1255,16 +1286,18 @@
out:
if (dirty) {
- DRM_DEBUG_KMS("%s watermarks: normal=%d, SR=%d, HPLL=%d\n",
- plane->base.name,
- crtc_state->wm.g4x.raw[G4X_WM_LEVEL_NORMAL].plane[plane_id],
- crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].plane[plane_id],
- crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].plane[plane_id]);
+ drm_dbg_kms(&dev_priv->drm,
+ "%s watermarks: normal=%d, SR=%d, HPLL=%d\n",
+ plane->base.name,
+ crtc_state->wm.g4x.raw[G4X_WM_LEVEL_NORMAL].plane[plane_id],
+ crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].plane[plane_id],
+ crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].plane[plane_id]);
if (plane_id == PLANE_PRIMARY)
- DRM_DEBUG_KMS("FBC watermarks: SR=%d, HPLL=%d\n",
- crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].fbc,
- crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].fbc);
+ drm_dbg_kms(&dev_priv->drm,
+ "FBC watermarks: SR=%d, HPLL=%d\n",
+ crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].fbc,
+ crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].fbc);
}
return dirty;
@@ -1281,7 +1314,7 @@
static bool g4x_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state,
int level)
{
- struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
if (level > dev_priv->wm.max_level)
return false;
@@ -1317,14 +1350,31 @@
}
}
+static bool g4x_compute_fbc_en(const struct g4x_wm_state *wm_state,
+ int level)
+{
+ if (level < G4X_WM_LEVEL_SR)
+ return false;
+
+ if (level >= G4X_WM_LEVEL_SR &&
+ wm_state->sr.fbc > g4x_fbc_fifo_size(G4X_WM_LEVEL_SR))
+ return false;
+
+ if (level >= G4X_WM_LEVEL_HPLL &&
+ wm_state->hpll.fbc > g4x_fbc_fifo_size(G4X_WM_LEVEL_HPLL))
+ return false;
+
+ return true;
+}
+
static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
{
- struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
struct intel_atomic_state *state =
- to_intel_atomic_state(crtc_state->base.state);
+ to_intel_atomic_state(crtc_state->uapi.state);
struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal;
- int num_active_planes = hweight32(crtc_state->active_planes &
- ~BIT(PLANE_CURSOR));
+ int num_active_planes = hweight8(crtc_state->active_planes &
+ ~BIT(PLANE_CURSOR));
const struct g4x_pipe_wm *raw;
const struct intel_plane_state *old_plane_state;
const struct intel_plane_state *new_plane_state;
@@ -1336,8 +1386,8 @@
for_each_oldnew_intel_plane_in_state(state, plane,
old_plane_state,
new_plane_state, i) {
- if (new_plane_state->base.crtc != &crtc->base &&
- old_plane_state->base.crtc != &crtc->base)
+ if (new_plane_state->hw.crtc != &crtc->base &&
+ old_plane_state->hw.crtc != &crtc->base)
continue;
if (g4x_raw_plane_wm_compute(crtc_state, new_plane_state))
@@ -1356,7 +1406,6 @@
wm_state->wm.plane[plane_id] = raw->plane[plane_id];
level = G4X_WM_LEVEL_SR;
-
if (!g4x_raw_crtc_wm_is_valid(crtc_state, level))
goto out;
@@ -1368,7 +1417,6 @@
wm_state->cxsr = num_active_planes == BIT(PLANE_PRIMARY);
level = G4X_WM_LEVEL_HPLL;
-
if (!g4x_raw_crtc_wm_is_valid(crtc_state, level))
goto out;
@@ -1391,35 +1439,29 @@
/*
* Determine if the FBC watermark(s) can be used. IF
* this isn't the case we prefer to disable the FBC
- ( watermark(s) rather than disable the SR/HPLL
- * level(s) entirely.
+ * watermark(s) rather than disable the SR/HPLL
+ * level(s) entirely. 'level-1' is the highest valid
+ * level here.
*/
- wm_state->fbc_en = level > G4X_WM_LEVEL_NORMAL;
-
- if (level >= G4X_WM_LEVEL_SR &&
- wm_state->sr.fbc > g4x_fbc_fifo_size(G4X_WM_LEVEL_SR))
- wm_state->fbc_en = false;
- else if (level >= G4X_WM_LEVEL_HPLL &&
- wm_state->hpll.fbc > g4x_fbc_fifo_size(G4X_WM_LEVEL_HPLL))
- wm_state->fbc_en = false;
+ wm_state->fbc_en = g4x_compute_fbc_en(wm_state, level - 1);
return 0;
}
-static int g4x_compute_intermediate_wm(struct drm_device *dev,
- struct intel_crtc *crtc,
- struct intel_crtc_state *new_crtc_state)
+static int g4x_compute_intermediate_wm(struct intel_crtc_state *new_crtc_state)
{
+ struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
struct g4x_wm_state *intermediate = &new_crtc_state->wm.g4x.intermediate;
const struct g4x_wm_state *optimal = &new_crtc_state->wm.g4x.optimal;
struct intel_atomic_state *intel_state =
- to_intel_atomic_state(new_crtc_state->base.state);
+ to_intel_atomic_state(new_crtc_state->uapi.state);
const struct intel_crtc_state *old_crtc_state =
intel_atomic_get_old_crtc_state(intel_state, crtc);
const struct g4x_wm_state *active = &old_crtc_state->wm.g4x.optimal;
enum plane_id plane_id;
- if (!new_crtc_state->base.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->base)) {
+ if (!new_crtc_state->hw.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) {
*intermediate = *optimal;
intermediate->cxsr = false;
@@ -1438,8 +1480,8 @@
max(optimal->wm.plane[plane_id],
active->wm.plane[plane_id]);
- WARN_ON(intermediate->wm.plane[plane_id] >
- g4x_plane_fifo_size(plane_id, G4X_WM_LEVEL_NORMAL));
+ drm_WARN_ON(&dev_priv->drm, intermediate->wm.plane[plane_id] >
+ g4x_plane_fifo_size(plane_id, G4X_WM_LEVEL_NORMAL));
}
intermediate->sr.plane = max(optimal->sr.plane,
@@ -1456,21 +1498,25 @@
intermediate->hpll.fbc = max(optimal->hpll.fbc,
active->hpll.fbc);
- WARN_ON((intermediate->sr.plane >
- g4x_plane_fifo_size(PLANE_PRIMARY, G4X_WM_LEVEL_SR) ||
- intermediate->sr.cursor >
- g4x_plane_fifo_size(PLANE_CURSOR, G4X_WM_LEVEL_SR)) &&
- intermediate->cxsr);
- WARN_ON((intermediate->sr.plane >
- g4x_plane_fifo_size(PLANE_PRIMARY, G4X_WM_LEVEL_HPLL) ||
- intermediate->sr.cursor >
- g4x_plane_fifo_size(PLANE_CURSOR, G4X_WM_LEVEL_HPLL)) &&
- intermediate->hpll_en);
+ drm_WARN_ON(&dev_priv->drm,
+ (intermediate->sr.plane >
+ g4x_plane_fifo_size(PLANE_PRIMARY, G4X_WM_LEVEL_SR) ||
+ intermediate->sr.cursor >
+ g4x_plane_fifo_size(PLANE_CURSOR, G4X_WM_LEVEL_SR)) &&
+ intermediate->cxsr);
+ drm_WARN_ON(&dev_priv->drm,
+ (intermediate->sr.plane >
+ g4x_plane_fifo_size(PLANE_PRIMARY, G4X_WM_LEVEL_HPLL) ||
+ intermediate->sr.cursor >
+ g4x_plane_fifo_size(PLANE_CURSOR, G4X_WM_LEVEL_HPLL)) &&
+ intermediate->hpll_en);
- WARN_ON(intermediate->sr.fbc > g4x_fbc_fifo_size(1) &&
- intermediate->fbc_en && intermediate->cxsr);
- WARN_ON(intermediate->hpll.fbc > g4x_fbc_fifo_size(2) &&
- intermediate->fbc_en && intermediate->hpll_en);
+ drm_WARN_ON(&dev_priv->drm,
+ intermediate->sr.fbc > g4x_fbc_fifo_size(1) &&
+ intermediate->fbc_en && intermediate->cxsr);
+ drm_WARN_ON(&dev_priv->drm,
+ intermediate->hpll.fbc > g4x_fbc_fifo_size(2) &&
+ intermediate->fbc_en && intermediate->hpll_en);
out:
/*
@@ -1487,7 +1533,7 @@
struct g4x_wm_values *wm)
{
struct intel_crtc *crtc;
- int num_active_crtcs = 0;
+ int num_active_pipes = 0;
wm->cxsr = true;
wm->hpll_en = true;
@@ -1506,10 +1552,10 @@
if (!wm_state->fbc_en)
wm->fbc_en = false;
- num_active_crtcs++;
+ num_active_pipes++;
}
- if (num_active_crtcs != 1) {
+ if (num_active_pipes != 1) {
wm->cxsr = false;
wm->hpll_en = false;
wm->fbc_en = false;
@@ -1549,10 +1595,11 @@
}
static void g4x_initial_watermarks(struct intel_atomic_state *state,
- struct intel_crtc_state *crtc_state)
+ struct intel_crtc *crtc)
{
- struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
- struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ const struct intel_crtc_state *crtc_state =
+ intel_atomic_get_new_crtc_state(state, crtc);
mutex_lock(&dev_priv->wm.wm_mutex);
crtc->wm.active.g4x = crtc_state->wm.g4x.intermediate;
@@ -1561,16 +1608,17 @@
}
static void g4x_optimize_watermarks(struct intel_atomic_state *state,
- struct intel_crtc_state *crtc_state)
+ struct intel_crtc *crtc)
{
- struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ const struct intel_crtc_state *crtc_state =
+ intel_atomic_get_new_crtc_state(state, crtc);
if (!crtc_state->wm.need_postvbl_update)
return;
mutex_lock(&dev_priv->wm.wm_mutex);
- intel_crtc->wm.active.g4x = crtc_state->wm.g4x.optimal;
+ crtc->wm.active.g4x = crtc_state->wm.g4x.optimal;
g4x_program_watermarks(dev_priv);
mutex_unlock(&dev_priv->wm.wm_mutex);
}
@@ -1606,14 +1654,14 @@
}
}
-static uint16_t vlv_compute_wm_level(const struct intel_crtc_state *crtc_state,
- const struct intel_plane_state *plane_state,
- int level)
+static u16 vlv_compute_wm_level(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ int level)
{
- struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+ struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
const struct drm_display_mode *adjusted_mode =
- &crtc_state->base.adjusted_mode;
+ &crtc_state->hw.adjusted_mode;
unsigned int clock, htotal, cpp, width, wm;
if (dev_priv->wm.pri_latency[level] == 0)
@@ -1622,7 +1670,7 @@
if (!intel_wm_plane_visible(crtc_state, plane_state))
return 0;
- cpp = plane_state->base.fb->format->cpp[0];
+ cpp = plane_state->hw.fb->format->cpp[0];
clock = adjusted_mode->crtc_clock;
htotal = adjusted_mode->crtc_htotal;
width = crtc_state->pipe_src_w;
@@ -1651,12 +1699,13 @@
static int vlv_compute_fifo(struct intel_crtc_state *crtc_state)
{
- struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
const struct g4x_pipe_wm *raw =
&crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2];
struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state;
unsigned int active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
- int num_active_planes = hweight32(active_planes);
+ int num_active_planes = hweight8(active_planes);
const int fifo_size = 511;
int fifo_extra, fifo_left = fifo_size;
int sprite0_fifo_extra = 0;
@@ -1720,11 +1769,11 @@
fifo_left -= plane_extra;
}
- WARN_ON(active_planes != 0 && fifo_left != 0);
+ drm_WARN_ON(&dev_priv->drm, active_planes != 0 && fifo_left != 0);
/* give it all to the first plane if none are active */
if (active_planes == 0) {
- WARN_ON(fifo_left != fifo_size);
+ drm_WARN_ON(&dev_priv->drm, fifo_left != fifo_size);
fifo_state->plane[PLANE_PRIMARY] = fifo_left;
}
@@ -1763,7 +1812,7 @@
static bool vlv_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
int level, enum plane_id plane_id, u16 value)
{
- struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
int num_levels = intel_wm_num_levels(dev_priv);
bool dirty = false;
@@ -1780,7 +1829,8 @@
static bool vlv_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
const struct intel_plane_state *plane_state)
{
- struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+ struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
enum plane_id plane_id = plane->id;
int num_levels = intel_wm_num_levels(to_i915(plane->base.dev));
int level;
@@ -1808,11 +1858,12 @@
out:
if (dirty)
- DRM_DEBUG_KMS("%s watermarks: PM2=%d, PM5=%d, DDR DVFS=%d\n",
- plane->base.name,
- crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2].plane[plane_id],
- crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM5].plane[plane_id],
- crtc_state->wm.vlv.raw[VLV_WM_LEVEL_DDR_DVFS].plane[plane_id]);
+ drm_dbg_kms(&dev_priv->drm,
+ "%s watermarks: PM2=%d, PM5=%d, DDR DVFS=%d\n",
+ plane->base.name,
+ crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2].plane[plane_id],
+ crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM5].plane[plane_id],
+ crtc_state->wm.vlv.raw[VLV_WM_LEVEL_DDR_DVFS].plane[plane_id]);
return dirty;
}
@@ -1838,16 +1889,16 @@
static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
{
- struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
struct intel_atomic_state *state =
- to_intel_atomic_state(crtc_state->base.state);
+ to_intel_atomic_state(crtc_state->uapi.state);
struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal;
const struct vlv_fifo_state *fifo_state =
&crtc_state->wm.vlv.fifo_state;
- int num_active_planes = hweight32(crtc_state->active_planes &
- ~BIT(PLANE_CURSOR));
- bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->base);
+ int num_active_planes = hweight8(crtc_state->active_planes &
+ ~BIT(PLANE_CURSOR));
+ bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->uapi);
const struct intel_plane_state *old_plane_state;
const struct intel_plane_state *new_plane_state;
struct intel_plane *plane;
@@ -1858,8 +1909,8 @@
for_each_oldnew_intel_plane_in_state(state, plane,
old_plane_state,
new_plane_state, i) {
- if (new_plane_state->base.crtc != &crtc->base &&
- old_plane_state->base.crtc != &crtc->base)
+ if (new_plane_state->hw.crtc != &crtc->base &&
+ old_plane_state->hw.crtc != &crtc->base)
continue;
if (vlv_raw_plane_wm_compute(crtc_state, new_plane_state))
@@ -1906,7 +1957,7 @@
for (level = 0; level < wm_state->num_levels; level++) {
const struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level];
- const int sr_fifo_size = INTEL_INFO(dev_priv)->num_pipes * 512 - 1;
+ const int sr_fifo_size = INTEL_NUM_PIPES(dev_priv) * 512 - 1;
if (!vlv_raw_crtc_wm_is_valid(crtc_state, level))
break;
@@ -1944,13 +1995,16 @@
(((value) << DSPARB_ ## plane ## _SHIFT_VLV) & DSPARB_ ## plane ## _MASK_VLV)
static void vlv_atomic_update_fifo(struct intel_atomic_state *state,
- struct intel_crtc_state *crtc_state)
+ struct intel_crtc *crtc)
{
- struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ struct intel_uncore *uncore = &dev_priv->uncore;
+ const struct intel_crtc_state *crtc_state =
+ intel_atomic_get_new_crtc_state(state, crtc);
const struct vlv_fifo_state *fifo_state =
&crtc_state->wm.vlv.fifo_state;
int sprite0_start, sprite1_start, fifo_size;
+ u32 dsparb, dsparb2, dsparb3;
if (!crtc_state->fifo_changed)
return;
@@ -1959,8 +2013,8 @@
sprite1_start = fifo_state->plane[PLANE_SPRITE0] + sprite0_start;
fifo_size = fifo_state->plane[PLANE_SPRITE1] + sprite1_start;
- WARN_ON(fifo_state->plane[PLANE_CURSOR] != 63);
- WARN_ON(fifo_size != 511);
+ drm_WARN_ON(&dev_priv->drm, fifo_state->plane[PLANE_CURSOR] != 63);
+ drm_WARN_ON(&dev_priv->drm, fifo_size != 511);
trace_vlv_fifo_size(crtc, sprite0_start, sprite1_start, fifo_size);
@@ -1973,13 +2027,12 @@
* intel_pipe_update_start() has already disabled interrupts
* for us, so a plain spin_lock() is sufficient here.
*/
- spin_lock(&dev_priv->uncore.lock);
+ spin_lock(&uncore->lock);
switch (crtc->pipe) {
- uint32_t dsparb, dsparb2, dsparb3;
case PIPE_A:
- dsparb = I915_READ_FW(DSPARB);
- dsparb2 = I915_READ_FW(DSPARB2);
+ dsparb = intel_uncore_read_fw(uncore, DSPARB);
+ dsparb2 = intel_uncore_read_fw(uncore, DSPARB2);
dsparb &= ~(VLV_FIFO(SPRITEA, 0xff) |
VLV_FIFO(SPRITEB, 0xff));
@@ -1991,12 +2044,12 @@
dsparb2 |= (VLV_FIFO(SPRITEA_HI, sprite0_start >> 8) |
VLV_FIFO(SPRITEB_HI, sprite1_start >> 8));
- I915_WRITE_FW(DSPARB, dsparb);
- I915_WRITE_FW(DSPARB2, dsparb2);
+ intel_uncore_write_fw(uncore, DSPARB, dsparb);
+ intel_uncore_write_fw(uncore, DSPARB2, dsparb2);
break;
case PIPE_B:
- dsparb = I915_READ_FW(DSPARB);
- dsparb2 = I915_READ_FW(DSPARB2);
+ dsparb = intel_uncore_read_fw(uncore, DSPARB);
+ dsparb2 = intel_uncore_read_fw(uncore, DSPARB2);
dsparb &= ~(VLV_FIFO(SPRITEC, 0xff) |
VLV_FIFO(SPRITED, 0xff));
@@ -2008,12 +2061,12 @@
dsparb2 |= (VLV_FIFO(SPRITEC_HI, sprite0_start >> 8) |
VLV_FIFO(SPRITED_HI, sprite1_start >> 8));
- I915_WRITE_FW(DSPARB, dsparb);
- I915_WRITE_FW(DSPARB2, dsparb2);
+ intel_uncore_write_fw(uncore, DSPARB, dsparb);
+ intel_uncore_write_fw(uncore, DSPARB2, dsparb2);
break;
case PIPE_C:
- dsparb3 = I915_READ_FW(DSPARB3);
- dsparb2 = I915_READ_FW(DSPARB2);
+ dsparb3 = intel_uncore_read_fw(uncore, DSPARB3);
+ dsparb2 = intel_uncore_read_fw(uncore, DSPARB2);
dsparb3 &= ~(VLV_FIFO(SPRITEE, 0xff) |
VLV_FIFO(SPRITEF, 0xff));
@@ -2025,34 +2078,33 @@
dsparb2 |= (VLV_FIFO(SPRITEE_HI, sprite0_start >> 8) |
VLV_FIFO(SPRITEF_HI, sprite1_start >> 8));
- I915_WRITE_FW(DSPARB3, dsparb3);
- I915_WRITE_FW(DSPARB2, dsparb2);
+ intel_uncore_write_fw(uncore, DSPARB3, dsparb3);
+ intel_uncore_write_fw(uncore, DSPARB2, dsparb2);
break;
default:
break;
}
- POSTING_READ_FW(DSPARB);
+ intel_uncore_posting_read_fw(uncore, DSPARB);
- spin_unlock(&dev_priv->uncore.lock);
+ spin_unlock(&uncore->lock);
}
#undef VLV_FIFO
-static int vlv_compute_intermediate_wm(struct drm_device *dev,
- struct intel_crtc *crtc,
- struct intel_crtc_state *new_crtc_state)
+static int vlv_compute_intermediate_wm(struct intel_crtc_state *new_crtc_state)
{
+ struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
struct vlv_wm_state *intermediate = &new_crtc_state->wm.vlv.intermediate;
const struct vlv_wm_state *optimal = &new_crtc_state->wm.vlv.optimal;
struct intel_atomic_state *intel_state =
- to_intel_atomic_state(new_crtc_state->base.state);
+ to_intel_atomic_state(new_crtc_state->uapi.state);
const struct intel_crtc_state *old_crtc_state =
intel_atomic_get_old_crtc_state(intel_state, crtc);
const struct vlv_wm_state *active = &old_crtc_state->wm.vlv.optimal;
int level;
- if (!new_crtc_state->base.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->base)) {
+ if (!new_crtc_state->hw.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) {
*intermediate = *optimal;
intermediate->cxsr = false;
@@ -2095,7 +2147,7 @@
struct vlv_wm_values *wm)
{
struct intel_crtc *crtc;
- int num_active_crtcs = 0;
+ int num_active_pipes = 0;
wm->level = dev_priv->wm.max_level;
wm->cxsr = true;
@@ -2109,14 +2161,14 @@
if (!wm_state->cxsr)
wm->cxsr = false;
- num_active_crtcs++;
+ num_active_pipes++;
wm->level = min_t(int, wm->level, wm_state->num_levels - 1);
}
- if (num_active_crtcs != 1)
+ if (num_active_pipes != 1)
wm->cxsr = false;
- if (num_active_crtcs > 1)
+ if (num_active_pipes > 1)
wm->level = VLV_WM_LEVEL_PM2;
for_each_intel_crtc(&dev_priv->drm, crtc) {
@@ -2168,10 +2220,11 @@
}
static void vlv_initial_watermarks(struct intel_atomic_state *state,
- struct intel_crtc_state *crtc_state)
+ struct intel_crtc *crtc)
{
- struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
- struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ const struct intel_crtc_state *crtc_state =
+ intel_atomic_get_new_crtc_state(state, crtc);
mutex_lock(&dev_priv->wm.wm_mutex);
crtc->wm.active.vlv = crtc_state->wm.vlv.intermediate;
@@ -2180,16 +2233,17 @@
}
static void vlv_optimize_watermarks(struct intel_atomic_state *state,
- struct intel_crtc_state *crtc_state)
+ struct intel_crtc *crtc)
{
- struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ const struct intel_crtc_state *crtc_state =
+ intel_atomic_get_new_crtc_state(state, crtc);
if (!crtc_state->wm.need_postvbl_update)
return;
mutex_lock(&dev_priv->wm.wm_mutex);
- intel_crtc->wm.active.vlv = crtc_state->wm.vlv.optimal;
+ crtc->wm.active.vlv = crtc_state->wm.vlv.optimal;
vlv_program_watermarks(dev_priv);
mutex_unlock(&dev_priv->wm.wm_mutex);
}
@@ -2208,7 +2262,7 @@
/* self-refresh has much higher latency */
static const int sr_latency_ns = 12000;
const struct drm_display_mode *adjusted_mode =
- &crtc->config->base.adjusted_mode;
+ &crtc->config->hw.adjusted_mode;
const struct drm_framebuffer *fb =
crtc->base.primary->state->fb;
int clock = adjusted_mode->crtc_clock;
@@ -2224,8 +2278,9 @@
if (srwm < 0)
srwm = 1;
srwm &= 0x1ff;
- DRM_DEBUG_KMS("self-refresh entries: %d, wm: %d\n",
- entries, srwm);
+ drm_dbg_kms(&dev_priv->drm,
+ "self-refresh entries: %d, wm: %d\n",
+ entries, srwm);
entries = intel_wm_method2(clock, htotal,
crtc->base.cursor->state->crtc_w, 4,
@@ -2238,8 +2293,9 @@
if (cursor_sr > i965_cursor_wm_info.max_wm)
cursor_sr = i965_cursor_wm_info.max_wm;
- DRM_DEBUG_KMS("self-refresh watermark: display plane %d "
- "cursor %d\n", srwm, cursor_sr);
+ drm_dbg_kms(&dev_priv->drm,
+ "self-refresh watermark: display plane %d "
+ "cursor %d\n", srwm, cursor_sr);
cxsr_enabled = true;
} else {
@@ -2248,8 +2304,9 @@
intel_set_memory_cxsr(dev_priv, false);
}
- DRM_DEBUG_KMS("Setting FIFO watermarks - A: 8, B: 8, C: 8, SR %d\n",
- srwm);
+ drm_dbg_kms(&dev_priv->drm,
+ "Setting FIFO watermarks - A: 8, B: 8, C: 8, SR %d\n",
+ srwm);
/* 965 has limitations... */
I915_WRITE(DSPFW1, FW_WM(srwm, SR) |
@@ -2271,8 +2328,8 @@
{
struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev);
const struct intel_watermark_params *wm_info;
- uint32_t fwater_lo;
- uint32_t fwater_hi;
+ u32 fwater_lo;
+ u32 fwater_hi;
int cwm, srwm = 1;
int fifo_size;
int planea_wm, planeb_wm;
@@ -2280,7 +2337,7 @@
if (IS_I945GM(dev_priv))
wm_info = &i945_wm_info;
- else if (!IS_GEN2(dev_priv))
+ else if (!IS_GEN(dev_priv, 2))
wm_info = &i915_wm_info;
else
wm_info = &i830_a_wm_info;
@@ -2289,12 +2346,12 @@
crtc = intel_get_crtc_for_plane(dev_priv, PLANE_A);
if (intel_crtc_active(crtc)) {
const struct drm_display_mode *adjusted_mode =
- &crtc->config->base.adjusted_mode;
+ &crtc->config->hw.adjusted_mode;
const struct drm_framebuffer *fb =
crtc->base.primary->state->fb;
int cpp;
- if (IS_GEN2(dev_priv))
+ if (IS_GEN(dev_priv, 2))
cpp = 4;
else
cpp = fb->format->cpp[0];
@@ -2309,19 +2366,19 @@
planea_wm = wm_info->max_wm;
}
- if (IS_GEN2(dev_priv))
+ if (IS_GEN(dev_priv, 2))
wm_info = &i830_bc_wm_info;
fifo_size = dev_priv->display.get_fifo_size(dev_priv, PLANE_B);
crtc = intel_get_crtc_for_plane(dev_priv, PLANE_B);
if (intel_crtc_active(crtc)) {
const struct drm_display_mode *adjusted_mode =
- &crtc->config->base.adjusted_mode;
+ &crtc->config->hw.adjusted_mode;
const struct drm_framebuffer *fb =
crtc->base.primary->state->fb;
int cpp;
- if (IS_GEN2(dev_priv))
+ if (IS_GEN(dev_priv, 2))
cpp = 4;
else
cpp = fb->format->cpp[0];
@@ -2339,7 +2396,8 @@
planeb_wm = wm_info->max_wm;
}
- DRM_DEBUG_KMS("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);
+ drm_dbg_kms(&dev_priv->drm,
+ "FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);
if (IS_I915GM(dev_priv) && enabled) {
struct drm_i915_gem_object *obj;
@@ -2364,7 +2422,7 @@
/* self-refresh has much higher latency */
static const int sr_latency_ns = 6000;
const struct drm_display_mode *adjusted_mode =
- &enabled->config->base.adjusted_mode;
+ &enabled->config->hw.adjusted_mode;
const struct drm_framebuffer *fb =
enabled->base.primary->state->fb;
int clock = adjusted_mode->crtc_clock;
@@ -2381,7 +2439,8 @@
entries = intel_wm_method2(clock, htotal, hdisplay, cpp,
sr_latency_ns / 100);
entries = DIV_ROUND_UP(entries, wm_info->cacheline_size);
- DRM_DEBUG_KMS("self-refresh entries: %d\n", entries);
+ drm_dbg_kms(&dev_priv->drm,
+ "self-refresh entries: %d\n", entries);
srwm = wm_info->fifo_size - entries;
if (srwm < 0)
srwm = 1;
@@ -2393,8 +2452,9 @@
I915_WRITE(FW_BLC_SELF, srwm & 0x3f);
}
- DRM_DEBUG_KMS("Setting FIFO watermarks - A: %d, B: %d, C: %d, SR %d\n",
- planea_wm, planeb_wm, cwm, srwm);
+ drm_dbg_kms(&dev_priv->drm,
+ "Setting FIFO watermarks - A: %d, B: %d, C: %d, SR %d\n",
+ planea_wm, planeb_wm, cwm, srwm);
fwater_lo = ((planeb_wm & 0x3f) << 16) | (planea_wm & 0x3f);
fwater_hi = (cwm & 0x1f);
@@ -2415,14 +2475,14 @@
struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev);
struct intel_crtc *crtc;
const struct drm_display_mode *adjusted_mode;
- uint32_t fwater_lo;
+ u32 fwater_lo;
int planea_wm;
crtc = single_enabled_crtc(dev_priv);
if (crtc == NULL)
return;
- adjusted_mode = &crtc->config->base.adjusted_mode;
+ adjusted_mode = &crtc->config->hw.adjusted_mode;
planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
&i845_wm_info,
dev_priv->display.get_fifo_size(dev_priv, PLANE_A),
@@ -2430,7 +2490,8 @@
fwater_lo = I915_READ(FW_BLC) & ~0xfff;
fwater_lo |= (3<<8) | planea_wm;
- DRM_DEBUG_KMS("Setting FIFO watermarks - A: %d\n", planea_wm);
+ drm_dbg_kms(&dev_priv->drm,
+ "Setting FIFO watermarks - A: %d\n", planea_wm);
I915_WRITE(FW_BLC, fwater_lo);
}
@@ -2464,8 +2525,7 @@
return ret;
}
-static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
- uint8_t cpp)
+static u32 ilk_wm_fbc(u32 pri_val, u32 horiz_pixels, u8 cpp)
{
/*
* Neither of these should be possible since this function shouldn't be
@@ -2482,40 +2542,39 @@
}
struct ilk_wm_maximums {
- uint16_t pri;
- uint16_t spr;
- uint16_t cur;
- uint16_t fbc;
+ u16 pri;
+ u16 spr;
+ u16 cur;
+ u16 fbc;
};
/*
* For both WM_PIPE and WM_LP.
* mem_value must be in 0.1us units.
*/
-static uint32_t ilk_compute_pri_wm(const struct intel_crtc_state *cstate,
- const struct intel_plane_state *pstate,
- uint32_t mem_value,
- bool is_lp)
+static u32 ilk_compute_pri_wm(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ u32 mem_value, bool is_lp)
{
- uint32_t method1, method2;
+ u32 method1, method2;
int cpp;
if (mem_value == 0)
return U32_MAX;
- if (!intel_wm_plane_visible(cstate, pstate))
+ if (!intel_wm_plane_visible(crtc_state, plane_state))
return 0;
- cpp = pstate->base.fb->format->cpp[0];
+ cpp = plane_state->hw.fb->format->cpp[0];
- method1 = ilk_wm_method1(cstate->pixel_rate, cpp, mem_value);
+ method1 = ilk_wm_method1(crtc_state->pixel_rate, cpp, mem_value);
if (!is_lp)
return method1;
- method2 = ilk_wm_method2(cstate->pixel_rate,
- cstate->base.adjusted_mode.crtc_htotal,
- drm_rect_width(&pstate->base.dst),
+ method2 = ilk_wm_method2(crtc_state->pixel_rate,
+ crtc_state->hw.adjusted_mode.crtc_htotal,
+ drm_rect_width(&plane_state->uapi.dst),
cpp, mem_value);
return min(method1, method2);
@@ -2525,25 +2584,25 @@
* For both WM_PIPE and WM_LP.
* mem_value must be in 0.1us units.
*/
-static uint32_t ilk_compute_spr_wm(const struct intel_crtc_state *cstate,
- const struct intel_plane_state *pstate,
- uint32_t mem_value)
+static u32 ilk_compute_spr_wm(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ u32 mem_value)
{
- uint32_t method1, method2;
+ u32 method1, method2;
int cpp;
if (mem_value == 0)
return U32_MAX;
- if (!intel_wm_plane_visible(cstate, pstate))
+ if (!intel_wm_plane_visible(crtc_state, plane_state))
return 0;
- cpp = pstate->base.fb->format->cpp[0];
+ cpp = plane_state->hw.fb->format->cpp[0];
- method1 = ilk_wm_method1(cstate->pixel_rate, cpp, mem_value);
- method2 = ilk_wm_method2(cstate->pixel_rate,
- cstate->base.adjusted_mode.crtc_htotal,
- drm_rect_width(&pstate->base.dst),
+ method1 = ilk_wm_method1(crtc_state->pixel_rate, cpp, mem_value);
+ method2 = ilk_wm_method2(crtc_state->pixel_rate,
+ crtc_state->hw.adjusted_mode.crtc_htotal,
+ drm_rect_width(&plane_state->uapi.dst),
cpp, mem_value);
return min(method1, method2);
}
@@ -2552,38 +2611,40 @@
* For both WM_PIPE and WM_LP.
* mem_value must be in 0.1us units.
*/
-static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate,
- const struct intel_plane_state *pstate,
- uint32_t mem_value)
+static u32 ilk_compute_cur_wm(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ u32 mem_value)
{
int cpp;
if (mem_value == 0)
return U32_MAX;
- if (!intel_wm_plane_visible(cstate, pstate))
+ if (!intel_wm_plane_visible(crtc_state, plane_state))
return 0;
- cpp = pstate->base.fb->format->cpp[0];
+ cpp = plane_state->hw.fb->format->cpp[0];
- return ilk_wm_method2(cstate->pixel_rate,
- cstate->base.adjusted_mode.crtc_htotal,
- pstate->base.crtc_w, cpp, mem_value);
+ return ilk_wm_method2(crtc_state->pixel_rate,
+ crtc_state->hw.adjusted_mode.crtc_htotal,
+ drm_rect_width(&plane_state->uapi.dst),
+ cpp, mem_value);
}
/* Only for WM_LP. */
-static uint32_t ilk_compute_fbc_wm(const struct intel_crtc_state *cstate,
- const struct intel_plane_state *pstate,
- uint32_t pri_val)
+static u32 ilk_compute_fbc_wm(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ u32 pri_val)
{
int cpp;
- if (!intel_wm_plane_visible(cstate, pstate))
+ if (!intel_wm_plane_visible(crtc_state, plane_state))
return 0;
- cpp = pstate->base.fb->format->cpp[0];
+ cpp = plane_state->hw.fb->format->cpp[0];
- return ilk_wm_fbc(pri_val, drm_rect_width(&pstate->base.dst), cpp);
+ return ilk_wm_fbc(pri_val, drm_rect_width(&plane_state->uapi.dst),
+ cpp);
}
static unsigned int
@@ -2633,13 +2694,12 @@
}
/* Calculate the maximum primary/sprite plane watermark */
-static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
+static unsigned int ilk_plane_wm_max(const struct drm_i915_private *dev_priv,
int level,
const struct intel_wm_config *config,
enum intel_ddb_partitioning ddb_partitioning,
bool is_sprite)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
unsigned int fifo_size = ilk_display_fifo_size(dev_priv);
/* if sprites aren't enabled, sprites get nothing */
@@ -2648,7 +2708,7 @@
/* HSW allows LP1+ watermarks even with multiple pipes */
if (level == 0 || config->num_pipes_active > 1) {
- fifo_size /= INTEL_INFO(dev_priv)->num_pipes;
+ fifo_size /= INTEL_NUM_PIPES(dev_priv);
/*
* For some reason the non self refresh
@@ -2675,7 +2735,7 @@
}
/* Calculate the maximum cursor plane watermark */
-static unsigned int ilk_cursor_wm_max(const struct drm_device *dev,
+static unsigned int ilk_cursor_wm_max(const struct drm_i915_private *dev_priv,
int level,
const struct intel_wm_config *config)
{
@@ -2684,19 +2744,19 @@
return 64;
/* otherwise just report max that registers can hold */
- return ilk_cursor_wm_reg_max(to_i915(dev), level);
+ return ilk_cursor_wm_reg_max(dev_priv, level);
}
-static void ilk_compute_wm_maximums(const struct drm_device *dev,
+static void ilk_compute_wm_maximums(const struct drm_i915_private *dev_priv,
int level,
const struct intel_wm_config *config,
enum intel_ddb_partitioning ddb_partitioning,
struct ilk_wm_maximums *max)
{
- max->pri = ilk_plane_wm_max(dev, level, config, ddb_partitioning, false);
- max->spr = ilk_plane_wm_max(dev, level, config, ddb_partitioning, true);
- max->cur = ilk_cursor_wm_max(dev, level, config);
- max->fbc = ilk_fbc_wm_reg_max(to_i915(dev));
+ max->pri = ilk_plane_wm_max(dev_priv, level, config, ddb_partitioning, false);
+ max->spr = ilk_plane_wm_max(dev_priv, level, config, ddb_partitioning, true);
+ max->cur = ilk_cursor_wm_max(dev_priv, level, config);
+ max->fbc = ilk_fbc_wm_reg_max(dev_priv);
}
static void ilk_compute_wm_reg_maximums(const struct drm_i915_private *dev_priv,
@@ -2741,9 +2801,9 @@
DRM_DEBUG_KMS("Cursor WM%d too large %u (max %u)\n",
level, result->cur_val, max->cur);
- result->pri_val = min_t(uint32_t, result->pri_val, max->pri);
- result->spr_val = min_t(uint32_t, result->spr_val, max->spr);
- result->cur_val = min_t(uint32_t, result->cur_val, max->cur);
+ result->pri_val = min_t(u32, result->pri_val, max->pri);
+ result->spr_val = min_t(u32, result->spr_val, max->spr);
+ result->cur_val = min_t(u32, result->cur_val, max->cur);
result->enable = true;
}
@@ -2751,17 +2811,17 @@
}
static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv,
- const struct intel_crtc *intel_crtc,
+ const struct intel_crtc *crtc,
int level,
- struct intel_crtc_state *cstate,
+ struct intel_crtc_state *crtc_state,
const struct intel_plane_state *pristate,
const struct intel_plane_state *sprstate,
const struct intel_plane_state *curstate,
struct intel_wm_level *result)
{
- uint16_t pri_latency = dev_priv->wm.pri_latency[level];
- uint16_t spr_latency = dev_priv->wm.spr_latency[level];
- uint16_t cur_latency = dev_priv->wm.cur_latency[level];
+ u16 pri_latency = dev_priv->wm.pri_latency[level];
+ u16 spr_latency = dev_priv->wm.spr_latency[level];
+ u16 cur_latency = dev_priv->wm.cur_latency[level];
/* WM1+ latency values stored in 0.5us units */
if (level > 0) {
@@ -2771,66 +2831,39 @@
}
if (pristate) {
- result->pri_val = ilk_compute_pri_wm(cstate, pristate,
+ result->pri_val = ilk_compute_pri_wm(crtc_state, pristate,
pri_latency, level);
- result->fbc_val = ilk_compute_fbc_wm(cstate, pristate, result->pri_val);
+ result->fbc_val = ilk_compute_fbc_wm(crtc_state, pristate, result->pri_val);
}
if (sprstate)
- result->spr_val = ilk_compute_spr_wm(cstate, sprstate, spr_latency);
+ result->spr_val = ilk_compute_spr_wm(crtc_state, sprstate, spr_latency);
if (curstate)
- result->cur_val = ilk_compute_cur_wm(cstate, curstate, cur_latency);
+ result->cur_val = ilk_compute_cur_wm(crtc_state, curstate, cur_latency);
result->enable = true;
}
-static uint32_t
-hsw_compute_linetime_wm(const struct intel_crtc_state *cstate)
-{
- const struct intel_atomic_state *intel_state =
- to_intel_atomic_state(cstate->base.state);
- const struct drm_display_mode *adjusted_mode =
- &cstate->base.adjusted_mode;
- u32 linetime, ips_linetime;
-
- if (!cstate->base.active)
- return 0;
- if (WARN_ON(adjusted_mode->crtc_clock == 0))
- return 0;
- if (WARN_ON(intel_state->cdclk.logical.cdclk == 0))
- return 0;
-
- /* The WM are computed with base on how long it takes to fill a single
- * row at the given clock rate, multiplied by 8.
- * */
- linetime = DIV_ROUND_CLOSEST(adjusted_mode->crtc_htotal * 1000 * 8,
- adjusted_mode->crtc_clock);
- ips_linetime = DIV_ROUND_CLOSEST(adjusted_mode->crtc_htotal * 1000 * 8,
- intel_state->cdclk.logical.cdclk);
-
- return PIPE_WM_LINETIME_IPS_LINETIME(ips_linetime) |
- PIPE_WM_LINETIME_TIME(linetime);
-}
-
static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
- uint16_t wm[8])
+ u16 wm[])
{
+ struct intel_uncore *uncore = &dev_priv->uncore;
+
if (INTEL_GEN(dev_priv) >= 9) {
- uint32_t val;
+ u32 val;
int ret, i;
int level, max_level = ilk_wm_max_level(dev_priv);
/* read the first set of memory latencies[0:3] */
val = 0; /* data0 to be programmed to 0 for first set */
- mutex_lock(&dev_priv->pcu_lock);
ret = sandybridge_pcode_read(dev_priv,
GEN9_PCODE_READ_MEM_LATENCY,
- &val);
- mutex_unlock(&dev_priv->pcu_lock);
+ &val, NULL);
if (ret) {
- DRM_ERROR("SKL Mailbox read error = %d\n", ret);
+ drm_err(&dev_priv->drm,
+ "SKL Mailbox read error = %d\n", ret);
return;
}
@@ -2844,13 +2877,12 @@
/* read the second set of memory latencies[4:7] */
val = 1; /* data0 to be programmed to 1 for second set */
- mutex_lock(&dev_priv->pcu_lock);
ret = sandybridge_pcode_read(dev_priv,
GEN9_PCODE_READ_MEM_LATENCY,
- &val);
- mutex_unlock(&dev_priv->pcu_lock);
+ &val, NULL);
if (ret) {
- DRM_ERROR("SKL Mailbox read error = %d\n", ret);
+ drm_err(&dev_priv->drm,
+ "SKL Mailbox read error = %d\n", ret);
return;
}
@@ -2891,8 +2923,17 @@
}
}
+ /*
+ * WA Level-0 adjustment for 16GB DIMMs: SKL+
+ * If we could not get dimm info enable this WA to prevent from
+ * any underrun. If not able to get Dimm info assume 16GB dimm
+ * to avoid any underrun.
+ */
+ if (dev_priv->dram_info.is_16gb_dimm)
+ wm[0] += 1;
+
} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
- uint64_t sskpd = I915_READ64(MCH_SSKPD);
+ u64 sskpd = intel_uncore_read64(uncore, MCH_SSKPD);
wm[0] = (sskpd >> 56) & 0xFF;
if (wm[0] == 0)
@@ -2902,14 +2943,14 @@
wm[3] = (sskpd >> 20) & 0x1FF;
wm[4] = (sskpd >> 32) & 0x1FF;
} else if (INTEL_GEN(dev_priv) >= 6) {
- uint32_t sskpd = I915_READ(MCH_SSKPD);
+ u32 sskpd = intel_uncore_read(uncore, MCH_SSKPD);
wm[0] = (sskpd >> SSKPD_WM0_SHIFT) & SSKPD_WM_MASK;
wm[1] = (sskpd >> SSKPD_WM1_SHIFT) & SSKPD_WM_MASK;
wm[2] = (sskpd >> SSKPD_WM2_SHIFT) & SSKPD_WM_MASK;
wm[3] = (sskpd >> SSKPD_WM3_SHIFT) & SSKPD_WM_MASK;
} else if (INTEL_GEN(dev_priv) >= 5) {
- uint32_t mltr = I915_READ(MLTR_ILK);
+ u32 mltr = intel_uncore_read(uncore, MLTR_ILK);
/* ILK primary LP0 latency is 700 ns */
wm[0] = 7;
@@ -2921,18 +2962,18 @@
}
static void intel_fixup_spr_wm_latency(struct drm_i915_private *dev_priv,
- uint16_t wm[5])
+ u16 wm[5])
{
/* ILK sprite LP0 latency is 1300 ns */
- if (IS_GEN5(dev_priv))
+ if (IS_GEN(dev_priv, 5))
wm[0] = 13;
}
static void intel_fixup_cur_wm_latency(struct drm_i915_private *dev_priv,
- uint16_t wm[5])
+ u16 wm[5])
{
/* ILK cursor LP0 latency is 1300 ns */
- if (IS_GEN5(dev_priv))
+ if (IS_GEN(dev_priv, 5))
wm[0] = 13;
}
@@ -2951,7 +2992,7 @@
static void intel_print_wm_latency(struct drm_i915_private *dev_priv,
const char *name,
- const uint16_t wm[])
+ const u16 wm[])
{
int level, max_level = ilk_wm_max_level(dev_priv);
@@ -2959,8 +3000,9 @@
unsigned int latency = wm[level];
if (latency == 0) {
- DRM_DEBUG_KMS("%s WM%d latency not provided\n",
- name, level);
+ drm_dbg_kms(&dev_priv->drm,
+ "%s WM%d latency not provided\n",
+ name, level);
continue;
}
@@ -2973,14 +3015,14 @@
else if (level > 0)
latency *= 5;
- DRM_DEBUG_KMS("%s WM%d latency %u (%u.%u usec)\n",
- name, level, wm[level],
- latency / 10, latency % 10);
+ drm_dbg_kms(&dev_priv->drm,
+ "%s WM%d latency %u (%u.%u usec)\n", name, level,
+ wm[level], latency / 10, latency % 10);
}
}
static bool ilk_increase_wm_latency(struct drm_i915_private *dev_priv,
- uint16_t wm[5], uint16_t min)
+ u16 wm[5], u16 min)
{
int level, max_level = ilk_wm_max_level(dev_priv);
@@ -2989,7 +3031,7 @@
wm[0] = max(wm[0], min);
for (level = 1; level <= max_level; level++)
- wm[level] = max_t(uint16_t, wm[level], DIV_ROUND_UP(min, 5));
+ wm[level] = max_t(u16, wm[level], DIV_ROUND_UP(min, 5));
return true;
}
@@ -3009,7 +3051,8 @@
if (!changed)
return;
- DRM_DEBUG_KMS("WM latency values increased to avoid potential underruns\n");
+ drm_dbg_kms(&dev_priv->drm,
+ "WM latency values increased to avoid potential underruns\n");
intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency);
intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency);
intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency);
@@ -3037,7 +3080,8 @@
dev_priv->wm.spr_latency[3] = 0;
dev_priv->wm.cur_latency[3] = 0;
- DRM_DEBUG_KMS("LP3 watermarks disabled due to potential for lost interrupts\n");
+ drm_dbg_kms(&dev_priv->drm,
+ "LP3 watermarks disabled due to potential for lost interrupts\n");
intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency);
intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency);
intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency);
@@ -3059,7 +3103,7 @@
intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency);
intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency);
- if (IS_GEN6(dev_priv)) {
+ if (IS_GEN(dev_priv, 6)) {
snb_wm_latency_quirk(dev_priv);
snb_wm_lp3_irq_quirk(dev_priv);
}
@@ -3071,7 +3115,7 @@
intel_print_wm_latency(dev_priv, "Gen9 Plane", dev_priv->wm.skl_latency);
}
-static bool ilk_validate_pipe_wm(struct drm_device *dev,
+static bool ilk_validate_pipe_wm(const struct drm_i915_private *dev_priv,
struct intel_pipe_wm *pipe_wm)
{
/* LP0 watermark maximums depend on this pipe alone */
@@ -3083,11 +3127,11 @@
struct ilk_wm_maximums max;
/* LP0 watermarks always use 1/2 DDB partitioning */
- ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max);
+ ilk_compute_wm_maximums(dev_priv, 0, &config, INTEL_DDB_PART_1_2, &max);
/* At least LP0 must be valid */
if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) {
- DRM_DEBUG_KMS("LP0 watermark invalid\n");
+ drm_dbg_kms(&dev_priv->drm, "LP0 watermark invalid\n");
return false;
}
@@ -3095,40 +3139,36 @@
}
/* Compute new watermarks for the pipe */
-static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
+static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
{
- struct drm_atomic_state *state = cstate->base.state;
- struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
struct intel_pipe_wm *pipe_wm;
- struct drm_device *dev = state->dev;
- const struct drm_i915_private *dev_priv = to_i915(dev);
- struct drm_plane *plane;
- const struct drm_plane_state *plane_state;
+ struct intel_plane *plane;
+ const struct intel_plane_state *plane_state;
const struct intel_plane_state *pristate = NULL;
const struct intel_plane_state *sprstate = NULL;
const struct intel_plane_state *curstate = NULL;
int level, max_level = ilk_wm_max_level(dev_priv), usable_level;
struct ilk_wm_maximums max;
- pipe_wm = &cstate->wm.ilk.optimal;
+ pipe_wm = &crtc_state->wm.ilk.optimal;
- drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, &cstate->base) {
- const struct intel_plane_state *ps = to_intel_plane_state(plane_state);
-
- if (plane->type == DRM_PLANE_TYPE_PRIMARY)
- pristate = ps;
- else if (plane->type == DRM_PLANE_TYPE_OVERLAY)
- sprstate = ps;
- else if (plane->type == DRM_PLANE_TYPE_CURSOR)
- curstate = ps;
+ intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
+ if (plane->base.type == DRM_PLANE_TYPE_PRIMARY)
+ pristate = plane_state;
+ else if (plane->base.type == DRM_PLANE_TYPE_OVERLAY)
+ sprstate = plane_state;
+ else if (plane->base.type == DRM_PLANE_TYPE_CURSOR)
+ curstate = plane_state;
}
- pipe_wm->pipe_enabled = cstate->base.active;
+ pipe_wm->pipe_enabled = crtc_state->hw.active;
if (sprstate) {
- pipe_wm->sprites_enabled = sprstate->base.visible;
- pipe_wm->sprites_scaled = sprstate->base.visible &&
- (drm_rect_width(&sprstate->base.dst) != drm_rect_width(&sprstate->base.src) >> 16 ||
- drm_rect_height(&sprstate->base.dst) != drm_rect_height(&sprstate->base.src) >> 16);
+ pipe_wm->sprites_enabled = sprstate->uapi.visible;
+ pipe_wm->sprites_scaled = sprstate->uapi.visible &&
+ (drm_rect_width(&sprstate->uapi.dst) != drm_rect_width(&sprstate->uapi.src) >> 16 ||
+ drm_rect_height(&sprstate->uapi.dst) != drm_rect_height(&sprstate->uapi.src) >> 16);
}
usable_level = max_level;
@@ -3142,13 +3182,10 @@
usable_level = 0;
memset(&pipe_wm->wm, 0, sizeof(pipe_wm->wm));
- ilk_compute_wm_level(dev_priv, intel_crtc, 0, cstate,
+ ilk_compute_wm_level(dev_priv, crtc, 0, crtc_state,
pristate, sprstate, curstate, &pipe_wm->wm[0]);
- if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
- pipe_wm->linetime = hsw_compute_linetime_wm(cstate);
-
- if (!ilk_validate_pipe_wm(dev, pipe_wm))
+ if (!ilk_validate_pipe_wm(dev_priv, pipe_wm))
return -EINVAL;
ilk_compute_wm_reg_maximums(dev_priv, 1, &max);
@@ -3156,7 +3193,7 @@
for (level = 1; level <= usable_level; level++) {
struct intel_wm_level *wm = &pipe_wm->wm[level];
- ilk_compute_wm_level(dev_priv, intel_crtc, level, cstate,
+ ilk_compute_wm_level(dev_priv, crtc, level, crtc_state,
pristate, sprstate, curstate, wm);
/*
@@ -3178,17 +3215,17 @@
* state and the new state. These can be programmed to the hardware
* immediately.
*/
-static int ilk_compute_intermediate_wm(struct drm_device *dev,
- struct intel_crtc *intel_crtc,
- struct intel_crtc_state *newstate)
+static int ilk_compute_intermediate_wm(struct intel_crtc_state *newstate)
{
+ struct intel_crtc *intel_crtc = to_intel_crtc(newstate->uapi.crtc);
+ struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
struct intel_pipe_wm *a = &newstate->wm.ilk.intermediate;
struct intel_atomic_state *intel_state =
- to_intel_atomic_state(newstate->base.state);
+ to_intel_atomic_state(newstate->uapi.state);
const struct intel_crtc_state *oldstate =
intel_atomic_get_old_crtc_state(intel_state, intel_crtc);
const struct intel_pipe_wm *b = &oldstate->wm.ilk.optimal;
- int level, max_level = ilk_wm_max_level(to_i915(dev));
+ int level, max_level = ilk_wm_max_level(dev_priv);
/*
* Start with the final, target watermarks, then combine with the
@@ -3196,7 +3233,8 @@
* and after the vblank.
*/
*a = newstate->wm.ilk.optimal;
- if (!newstate->base.active || drm_atomic_crtc_needs_modeset(&newstate->base))
+ if (!newstate->hw.active || drm_atomic_crtc_needs_modeset(&newstate->uapi) ||
+ intel_state->skip_intermediate_wm)
return 0;
a->pipe_enabled |= b->pipe_enabled;
@@ -3220,7 +3258,7 @@
* there's no safe way to transition from the old state to
* the new state, so we need to fail the atomic transaction.
*/
- if (!ilk_validate_pipe_wm(dev, a))
+ if (!ilk_validate_pipe_wm(dev_priv, a))
return -EINVAL;
/*
@@ -3236,7 +3274,7 @@
/*
* Merge the watermarks from all active pipes for a specific level.
*/
-static void ilk_merge_wm_level(struct drm_device *dev,
+static void ilk_merge_wm_level(struct drm_i915_private *dev_priv,
int level,
struct intel_wm_level *ret_wm)
{
@@ -3244,7 +3282,7 @@
ret_wm->enable = true;
- for_each_intel_crtc(dev, intel_crtc) {
+ for_each_intel_crtc(&dev_priv->drm, intel_crtc) {
const struct intel_pipe_wm *active = &intel_crtc->wm.active.ilk;
const struct intel_wm_level *wm = &active->wm[level];
@@ -3269,12 +3307,11 @@
/*
* Merge all low power watermarks for all active pipes.
*/
-static void ilk_wm_merge(struct drm_device *dev,
+static void ilk_wm_merge(struct drm_i915_private *dev_priv,
const struct intel_wm_config *config,
const struct ilk_wm_maximums *max,
struct intel_pipe_wm *merged)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
int level, max_level = ilk_wm_max_level(dev_priv);
int last_enabled_level = max_level;
@@ -3290,7 +3327,7 @@
for (level = 1; level <= max_level; level++) {
struct intel_wm_level *wm = &merged->wm[level];
- ilk_merge_wm_level(dev, level, wm);
+ ilk_merge_wm_level(dev_priv, level, wm);
if (level > last_enabled_level)
wm->enable = false;
@@ -3315,7 +3352,7 @@
* What we should check here is whether FBC can be
* enabled sometime later.
*/
- if (IS_GEN5(dev_priv) && !merged->fbc_wm_enabled &&
+ if (IS_GEN(dev_priv, 5) && !merged->fbc_wm_enabled &&
intel_fbc_is_active(dev_priv)) {
for (level = 2; level <= max_level; level++) {
struct intel_wm_level *wm = &merged->wm[level];
@@ -3332,22 +3369,20 @@
}
/* The value we need to program into the WM_LPx latency field */
-static unsigned int ilk_wm_lp_latency(struct drm_device *dev, int level)
+static unsigned int ilk_wm_lp_latency(struct drm_i915_private *dev_priv,
+ int level)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
-
if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
return 2 * level;
else
return dev_priv->wm.pri_latency[level];
}
-static void ilk_compute_wm_results(struct drm_device *dev,
+static void ilk_compute_wm_results(struct drm_i915_private *dev_priv,
const struct intel_pipe_wm *merged,
enum intel_ddb_partitioning partitioning,
struct ilk_wm_values *results)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
struct intel_crtc *intel_crtc;
int level, wm_lp;
@@ -3367,7 +3402,7 @@
* disabled. Doing otherwise could cause underruns.
*/
results->wm_lp[wm_lp - 1] =
- (ilk_wm_lp_latency(dev, level) << WM1_LP_LATENCY_SHIFT) |
+ (ilk_wm_lp_latency(dev_priv, level) << WM1_LP_LATENCY_SHIFT) |
(r->pri_val << WM1_LP_SR_SHIFT) |
r->cur_val;
@@ -3386,22 +3421,20 @@
* level is disabled. Doing otherwise could cause underruns.
*/
if (INTEL_GEN(dev_priv) <= 6 && r->spr_val) {
- WARN_ON(wm_lp != 1);
+ drm_WARN_ON(&dev_priv->drm, wm_lp != 1);
results->wm_lp_spr[wm_lp - 1] = WM1S_LP_EN | r->spr_val;
} else
results->wm_lp_spr[wm_lp - 1] = r->spr_val;
}
/* LP0 register values */
- for_each_intel_crtc(dev, intel_crtc) {
+ for_each_intel_crtc(&dev_priv->drm, intel_crtc) {
enum pipe pipe = intel_crtc->pipe;
- const struct intel_wm_level *r =
- &intel_crtc->wm.active.ilk.wm[0];
+ const struct intel_pipe_wm *pipe_wm = &intel_crtc->wm.active.ilk;
+ const struct intel_wm_level *r = &pipe_wm->wm[0];
- if (WARN_ON(!r->enable))
+ if (drm_WARN_ON(&dev_priv->drm, !r->enable))
continue;
-
- results->wm_linetime[pipe] = intel_crtc->wm.active.ilk.linetime;
results->wm_pipe[pipe] =
(r->pri_val << WM0_PIPE_PLANE_SHIFT) |
@@ -3412,11 +3445,12 @@
/* Find the result with the highest level enabled. Check for enable_fbc_wm in
* case both are at the same level. Prefer r1 in case they're the same. */
-static struct intel_pipe_wm *ilk_find_best_result(struct drm_device *dev,
- struct intel_pipe_wm *r1,
- struct intel_pipe_wm *r2)
+static struct intel_pipe_wm *
+ilk_find_best_result(struct drm_i915_private *dev_priv,
+ struct intel_pipe_wm *r1,
+ struct intel_pipe_wm *r2)
{
- int level, max_level = ilk_wm_max_level(to_i915(dev));
+ int level, max_level = ilk_wm_max_level(dev_priv);
int level1 = 0, level2 = 0;
for (level = 1; level <= max_level; level++) {
@@ -3440,7 +3474,6 @@
/* dirty bits used to track which watermarks need changes */
#define WM_DIRTY_PIPE(pipe) (1 << (pipe))
-#define WM_DIRTY_LINETIME(pipe) (1 << (8 + (pipe)))
#define WM_DIRTY_LP(wm_lp) (1 << (15 + (wm_lp)))
#define WM_DIRTY_LP_ALL (WM_DIRTY_LP(1) | WM_DIRTY_LP(2) | WM_DIRTY_LP(3))
#define WM_DIRTY_FBC (1 << 24)
@@ -3455,12 +3488,6 @@
int wm_lp;
for_each_pipe(dev_priv, pipe) {
- if (old->wm_linetime[pipe] != new->wm_linetime[pipe]) {
- dirty |= WM_DIRTY_LINETIME(pipe);
- /* Must disable LP1+ watermarks too */
- dirty |= WM_DIRTY_LP_ALL;
- }
-
if (old->wm_pipe[pipe] != new->wm_pipe[pipe]) {
dirty |= WM_DIRTY_PIPE(pipe);
/* Must disable LP1+ watermarks too */
@@ -3537,7 +3564,7 @@
{
struct ilk_wm_values *previous = &dev_priv->wm.hw;
unsigned int dirty;
- uint32_t val;
+ u32 val;
dirty = ilk_compute_wm_dirty(dev_priv, previous, results);
if (!dirty)
@@ -3551,13 +3578,6 @@
I915_WRITE(WM0_PIPEB_ILK, results->wm_pipe[1]);
if (dirty & WM_DIRTY_PIPE(PIPE_C))
I915_WRITE(WM0_PIPEC_IVB, results->wm_pipe[2]);
-
- if (dirty & WM_DIRTY_LINETIME(PIPE_A))
- I915_WRITE(PIPE_WM_LINETIME(PIPE_A), results->wm_linetime[0]);
- if (dirty & WM_DIRTY_LINETIME(PIPE_B))
- I915_WRITE(PIPE_WM_LINETIME(PIPE_B), results->wm_linetime[1]);
- if (dirty & WM_DIRTY_LINETIME(PIPE_C))
- I915_WRITE(PIPE_WM_LINETIME(PIPE_C), results->wm_linetime[2]);
if (dirty & WM_DIRTY_DDB) {
if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
@@ -3607,56 +3627,72 @@
dev_priv->wm.hw = *results;
}
-bool ilk_disable_lp_wm(struct drm_device *dev)
+bool ilk_disable_lp_wm(struct drm_i915_private *dev_priv)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
-
return _ilk_disable_lp_wm(dev_priv, WM_DIRTY_LP_ALL);
}
-static u8 intel_enabled_dbuf_slices_num(struct drm_i915_private *dev_priv)
+u8 intel_enabled_dbuf_slices_mask(struct drm_i915_private *dev_priv)
{
- u8 enabled_slices;
+ int i;
+ int max_slices = INTEL_INFO(dev_priv)->num_supported_dbuf_slices;
+ u8 enabled_slices_mask = 0;
- /* Slice 1 will always be enabled */
- enabled_slices = 1;
+ for (i = 0; i < max_slices; i++) {
+ if (I915_READ(DBUF_CTL_S(i)) & DBUF_POWER_STATE)
+ enabled_slices_mask |= BIT(i);
+ }
- /* Gen prior to GEN11 have only one DBuf slice */
- if (INTEL_GEN(dev_priv) < 11)
- return enabled_slices;
-
- if (I915_READ(DBUF_CTL_S2) & DBUF_POWER_STATE)
- enabled_slices++;
-
- return enabled_slices;
+ return enabled_slices_mask;
}
/*
* FIXME: We still don't have the proper code detect if we need to apply the WA,
* so assume we'll always need it in order to avoid underruns.
*/
-static bool skl_needs_memory_bw_wa(struct intel_atomic_state *state)
+static bool skl_needs_memory_bw_wa(struct drm_i915_private *dev_priv)
{
- struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-
- if (IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv))
- return true;
-
- return false;
+ return IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv);
}
static bool
intel_has_sagv(struct drm_i915_private *dev_priv)
{
- if (IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv) ||
- IS_CANNONLAKE(dev_priv))
- return true;
+ return (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) &&
+ dev_priv->sagv_status != I915_SAGV_NOT_CONTROLLED;
+}
- if (IS_SKYLAKE(dev_priv) &&
- dev_priv->sagv_status != I915_SAGV_NOT_CONTROLLED)
- return true;
+static void
+skl_setup_sagv_block_time(struct drm_i915_private *dev_priv)
+{
+ if (INTEL_GEN(dev_priv) >= 12) {
+ u32 val = 0;
+ int ret;
- return false;
+ ret = sandybridge_pcode_read(dev_priv,
+ GEN12_PCODE_READ_SAGV_BLOCK_TIME_US,
+ &val, NULL);
+ if (!ret) {
+ dev_priv->sagv_block_time_us = val;
+ return;
+ }
+
+ drm_dbg(&dev_priv->drm, "Couldn't read SAGV block time!\n");
+ } else if (IS_GEN(dev_priv, 11)) {
+ dev_priv->sagv_block_time_us = 10;
+ return;
+ } else if (IS_GEN(dev_priv, 10)) {
+ dev_priv->sagv_block_time_us = 20;
+ return;
+ } else if (IS_GEN(dev_priv, 9)) {
+ dev_priv->sagv_block_time_us = 30;
+ return;
+ } else {
+ MISSING_CASE(INTEL_GEN(dev_priv));
+ }
+
+ /* Default to an unusable block time */
+ dev_priv->sagv_block_time_us = -1;
}
/*
@@ -3681,25 +3717,22 @@
if (dev_priv->sagv_status == I915_SAGV_ENABLED)
return 0;
- DRM_DEBUG_KMS("Enabling the SAGV\n");
- mutex_lock(&dev_priv->pcu_lock);
-
+ drm_dbg_kms(&dev_priv->drm, "Enabling SAGV\n");
ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
GEN9_SAGV_ENABLE);
- /* We don't need to wait for the SAGV when enabling */
- mutex_unlock(&dev_priv->pcu_lock);
+ /* We don't need to wait for SAGV when enabling */
/*
* Some skl systems, pre-release machines in particular,
- * don't actually have an SAGV.
+ * don't actually have SAGV.
*/
if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
- DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+ drm_dbg(&dev_priv->drm, "No SAGV found on system, ignoring\n");
dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
return 0;
} else if (ret < 0) {
- DRM_ERROR("Failed to enable the SAGV\n");
+ drm_err(&dev_priv->drm, "Failed to enable SAGV\n");
return ret;
}
@@ -3718,26 +3751,22 @@
if (dev_priv->sagv_status == I915_SAGV_DISABLED)
return 0;
- DRM_DEBUG_KMS("Disabling the SAGV\n");
- mutex_lock(&dev_priv->pcu_lock);
-
+ drm_dbg_kms(&dev_priv->drm, "Disabling SAGV\n");
/* bspec says to keep retrying for at least 1 ms */
ret = skl_pcode_request(dev_priv, GEN9_PCODE_SAGV_CONTROL,
GEN9_SAGV_DISABLE,
GEN9_SAGV_IS_DISABLED, GEN9_SAGV_IS_DISABLED,
1);
- mutex_unlock(&dev_priv->pcu_lock);
-
/*
* Some skl systems, pre-release machines in particular,
- * don't actually have an SAGV.
+ * don't actually have SAGV.
*/
if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
- DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+ drm_dbg(&dev_priv->drm, "No SAGV found on system, ignoring\n");
dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
return 0;
} else if (ret < 0) {
- DRM_ERROR("Failed to disable the SAGV (%d)\n", ret);
+ drm_err(&dev_priv->drm, "Failed to disable SAGV (%d)\n", ret);
return ret;
}
@@ -3745,50 +3774,121 @@
return 0;
}
-bool intel_can_enable_sagv(struct drm_atomic_state *state)
+void intel_sagv_pre_plane_update(struct intel_atomic_state *state)
{
- struct drm_device *dev = state->dev;
- struct drm_i915_private *dev_priv = to_i915(dev);
- struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
- struct intel_crtc *crtc;
+ struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+ const struct intel_bw_state *new_bw_state;
+ const struct intel_bw_state *old_bw_state;
+ u32 new_mask = 0;
+
+ /*
+ * Just return if we can't control SAGV or don't have it.
+ * This is different from situation when we have SAGV but just can't
+ * afford it due to DBuf limitation - in case if SAGV is completely
+ * disabled in a BIOS, we are not even allowed to send a PCode request,
+ * as it will throw an error. So have to check it here.
+ */
+ if (!intel_has_sagv(dev_priv))
+ return;
+
+ new_bw_state = intel_atomic_get_new_bw_state(state);
+ if (!new_bw_state)
+ return;
+
+ if (INTEL_GEN(dev_priv) < 11 && !intel_can_enable_sagv(dev_priv, new_bw_state)) {
+ intel_disable_sagv(dev_priv);
+ return;
+ }
+
+ old_bw_state = intel_atomic_get_old_bw_state(state);
+ /*
+ * Nothing to mask
+ */
+ if (new_bw_state->qgv_points_mask == old_bw_state->qgv_points_mask)
+ return;
+
+ new_mask = old_bw_state->qgv_points_mask | new_bw_state->qgv_points_mask;
+
+ /*
+ * If new mask is zero - means there is nothing to mask,
+ * we can only unmask, which should be done in unmask.
+ */
+ if (!new_mask)
+ return;
+
+ /*
+ * Restrict required qgv points before updating the configuration.
+ * According to BSpec we can't mask and unmask qgv points at the same
+ * time. Also masking should be done before updating the configuration
+ * and unmasking afterwards.
+ */
+ icl_pcode_restrict_qgv_points(dev_priv, new_mask);
+}
+
+void intel_sagv_post_plane_update(struct intel_atomic_state *state)
+{
+ struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+ const struct intel_bw_state *new_bw_state;
+ const struct intel_bw_state *old_bw_state;
+ u32 new_mask = 0;
+
+ /*
+ * Just return if we can't control SAGV or don't have it.
+ * This is different from situation when we have SAGV but just can't
+ * afford it due to DBuf limitation - in case if SAGV is completely
+ * disabled in a BIOS, we are not even allowed to send a PCode request,
+ * as it will throw an error. So have to check it here.
+ */
+ if (!intel_has_sagv(dev_priv))
+ return;
+
+ new_bw_state = intel_atomic_get_new_bw_state(state);
+ if (!new_bw_state)
+ return;
+
+ if (INTEL_GEN(dev_priv) < 11 && intel_can_enable_sagv(dev_priv, new_bw_state)) {
+ intel_enable_sagv(dev_priv);
+ return;
+ }
+
+ old_bw_state = intel_atomic_get_old_bw_state(state);
+ /*
+ * Nothing to unmask
+ */
+ if (new_bw_state->qgv_points_mask == old_bw_state->qgv_points_mask)
+ return;
+
+ new_mask = new_bw_state->qgv_points_mask;
+
+ /*
+ * Allow required qgv points after updating the configuration.
+ * According to BSpec we can't mask and unmask qgv points at the same
+ * time. Also masking should be done before updating the configuration
+ * and unmasking afterwards.
+ */
+ icl_pcode_restrict_qgv_points(dev_priv, new_mask);
+}
+
+static bool skl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state)
+{
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
struct intel_plane *plane;
- struct intel_crtc_state *cstate;
- enum pipe pipe;
+ const struct intel_plane_state *plane_state;
int level, latency;
- int sagv_block_time_us;
if (!intel_has_sagv(dev_priv))
return false;
- if (IS_GEN9(dev_priv))
- sagv_block_time_us = 30;
- else if (IS_GEN10(dev_priv))
- sagv_block_time_us = 20;
- else
- sagv_block_time_us = 10;
-
- /*
- * SKL+ workaround: bspec recommends we disable the SAGV when we have
- * more then one pipe enabled
- *
- * If there are no active CRTCs, no additional checks need be performed
- */
- if (hweight32(intel_state->active_crtcs) == 0)
+ if (!crtc_state->hw.active)
return true;
- else if (hweight32(intel_state->active_crtcs) > 1)
+
+ if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
return false;
- /* Since we're now guaranteed to only have one active CRTC... */
- pipe = ffs(intel_state->active_crtcs) - 1;
- crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
- cstate = to_intel_crtc_state(crtc->base.state);
-
- if (crtc->base.state->adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
- return false;
-
- for_each_intel_plane_on_crtc(dev, crtc, plane) {
- struct skl_plane_wm *wm =
- &cstate->wm.skl.optimal.planes[plane->id];
+ intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
+ const struct skl_plane_wm *wm =
+ &crtc_state->wm.skl.optimal.planes[plane->id];
/* Skip this plane if it's not enabled */
if (!wm->wm[0].plane_en)
@@ -3801,127 +3901,395 @@
latency = dev_priv->wm.skl_latency[level];
- if (skl_needs_memory_bw_wa(intel_state) &&
- plane->base.state->fb->modifier ==
+ if (skl_needs_memory_bw_wa(dev_priv) &&
+ plane_state->uapi.fb->modifier ==
I915_FORMAT_MOD_X_TILED)
latency += 15;
/*
* If any of the planes on this pipe don't enable wm levels that
* incur memory latencies higher than sagv_block_time_us we
- * can't enable the SAGV.
+ * can't enable SAGV.
*/
- if (latency < sagv_block_time_us)
+ if (latency < dev_priv->sagv_block_time_us)
return false;
}
return true;
}
-static unsigned int intel_get_ddb_size(struct drm_i915_private *dev_priv,
- const struct intel_crtc_state *cstate,
- const unsigned int total_data_rate,
- const int num_active,
- struct skl_ddb_allocation *ddb)
+static bool tgl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state)
{
- const struct drm_display_mode *adjusted_mode;
- u64 total_data_bw;
- u16 ddb_size = INTEL_INFO(dev_priv)->ddb_size;
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+ enum plane_id plane_id;
- WARN_ON(ddb_size == 0);
+ if (!crtc_state->hw.active)
+ return true;
+
+ for_each_plane_id_on_crtc(crtc, plane_id) {
+ const struct skl_ddb_entry *plane_alloc =
+ &crtc_state->wm.skl.plane_ddb_y[plane_id];
+ const struct skl_plane_wm *wm =
+ &crtc_state->wm.skl.optimal.planes[plane_id];
+
+ if (skl_ddb_entry_size(plane_alloc) < wm->sagv_wm0.min_ddb_alloc)
+ return false;
+ }
+
+ return true;
+}
+
+static bool intel_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state)
+{
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
+ if (INTEL_GEN(dev_priv) >= 12)
+ return tgl_crtc_can_enable_sagv(crtc_state);
+ else
+ return skl_crtc_can_enable_sagv(crtc_state);
+}
+
+bool intel_can_enable_sagv(struct drm_i915_private *dev_priv,
+ const struct intel_bw_state *bw_state)
+{
+ if (INTEL_GEN(dev_priv) < 11 &&
+ bw_state->active_pipes && !is_power_of_2(bw_state->active_pipes))
+ return false;
+
+ return bw_state->pipe_sagv_reject == 0;
+}
+
+static int intel_compute_sagv_mask(struct intel_atomic_state *state)
+{
+ struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+ int ret;
+ struct intel_crtc *crtc;
+ struct intel_crtc_state *new_crtc_state;
+ struct intel_bw_state *new_bw_state = NULL;
+ const struct intel_bw_state *old_bw_state = NULL;
+ int i;
+
+ for_each_new_intel_crtc_in_state(state, crtc,
+ new_crtc_state, i) {
+ new_bw_state = intel_atomic_get_bw_state(state);
+ if (IS_ERR(new_bw_state))
+ return PTR_ERR(new_bw_state);
+
+ old_bw_state = intel_atomic_get_old_bw_state(state);
+
+ if (intel_crtc_can_enable_sagv(new_crtc_state))
+ new_bw_state->pipe_sagv_reject &= ~BIT(crtc->pipe);
+ else
+ new_bw_state->pipe_sagv_reject |= BIT(crtc->pipe);
+ }
+
+ if (!new_bw_state)
+ return 0;
+
+ new_bw_state->active_pipes =
+ intel_calc_active_pipes(state, old_bw_state->active_pipes);
+
+ if (new_bw_state->active_pipes != old_bw_state->active_pipes) {
+ ret = intel_atomic_lock_global_state(&new_bw_state->base);
+ if (ret)
+ return ret;
+ }
+
+ if (intel_can_enable_sagv(dev_priv, new_bw_state) !=
+ intel_can_enable_sagv(dev_priv, old_bw_state)) {
+ ret = intel_atomic_serialize_global_state(&new_bw_state->base);
+ if (ret)
+ return ret;
+ } else if (new_bw_state->pipe_sagv_reject != old_bw_state->pipe_sagv_reject) {
+ ret = intel_atomic_lock_global_state(&new_bw_state->base);
+ if (ret)
+ return ret;
+ }
+
+ for_each_new_intel_crtc_in_state(state, crtc,
+ new_crtc_state, i) {
+ struct skl_pipe_wm *pipe_wm = &new_crtc_state->wm.skl.optimal;
+
+ /*
+ * We store use_sagv_wm in the crtc state rather than relying on
+ * that bw state since we have no convenient way to get at the
+ * latter from the plane commit hooks (especially in the legacy
+ * cursor case)
+ */
+ pipe_wm->use_sagv_wm = INTEL_GEN(dev_priv) >= 12 &&
+ intel_can_enable_sagv(dev_priv, new_bw_state);
+ }
+
+ return 0;
+}
+
+/*
+ * Calculate initial DBuf slice offset, based on slice size
+ * and mask(i.e if slice size is 1024 and second slice is enabled
+ * offset would be 1024)
+ */
+static unsigned int
+icl_get_first_dbuf_slice_offset(u32 dbuf_slice_mask,
+ u32 slice_size,
+ u32 ddb_size)
+{
+ unsigned int offset = 0;
+
+ if (!dbuf_slice_mask)
+ return 0;
+
+ offset = (ffs(dbuf_slice_mask) - 1) * slice_size;
+
+ WARN_ON(offset >= ddb_size);
+ return offset;
+}
+
+u16 intel_get_ddb_size(struct drm_i915_private *dev_priv)
+{
+ u16 ddb_size = INTEL_INFO(dev_priv)->ddb_size;
+ drm_WARN_ON(&dev_priv->drm, ddb_size == 0);
if (INTEL_GEN(dev_priv) < 11)
return ddb_size - 4; /* 4 blocks for bypass path allocation */
- adjusted_mode = &cstate->base.adjusted_mode;
- total_data_bw = (u64)total_data_rate * drm_mode_vrefresh(adjusted_mode);
-
- /*
- * 12GB/s is maximum BW supported by single DBuf slice.
- */
- if (total_data_bw >= GBps(12) || num_active > 1) {
- ddb->enabled_slices = 2;
- } else {
- ddb->enabled_slices = 1;
- ddb_size /= 2;
- }
-
return ddb_size;
}
-static void
-skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
- const struct intel_crtc_state *cstate,
- const unsigned int total_data_rate,
- struct skl_ddb_allocation *ddb,
+u32 skl_ddb_dbuf_slice_mask(struct drm_i915_private *dev_priv,
+ const struct skl_ddb_entry *entry)
+{
+ u32 slice_mask = 0;
+ u16 ddb_size = intel_get_ddb_size(dev_priv);
+ u16 num_supported_slices = INTEL_INFO(dev_priv)->num_supported_dbuf_slices;
+ u16 slice_size = ddb_size / num_supported_slices;
+ u16 start_slice;
+ u16 end_slice;
+
+ if (!skl_ddb_entry_size(entry))
+ return 0;
+
+ start_slice = entry->start / slice_size;
+ end_slice = (entry->end - 1) / slice_size;
+
+ /*
+ * Per plane DDB entry can in a really worst case be on multiple slices
+ * but single entry is anyway contigious.
+ */
+ while (start_slice <= end_slice) {
+ slice_mask |= BIT(start_slice);
+ start_slice++;
+ }
+
+ return slice_mask;
+}
+
+static u8 skl_compute_dbuf_slices(const struct intel_crtc_state *crtc_state,
+ u8 active_pipes);
+
+static int
+skl_ddb_get_pipe_allocation_limits(struct drm_i915_private *dev_priv,
+ const struct intel_crtc_state *crtc_state,
+ const u64 total_data_rate,
struct skl_ddb_entry *alloc, /* out */
int *num_active /* out */)
{
- struct drm_atomic_state *state = cstate->base.state;
+ struct drm_atomic_state *state = crtc_state->uapi.state;
struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
- struct drm_i915_private *dev_priv = to_i915(dev);
- struct drm_crtc *for_crtc = cstate->base.crtc;
- unsigned int pipe_size, ddb_size;
- int nth_active_pipe;
+ struct drm_crtc *for_crtc = crtc_state->uapi.crtc;
+ const struct intel_crtc *crtc;
+ u32 pipe_width = 0, total_width_in_range = 0, width_before_pipe_in_range = 0;
+ enum pipe for_pipe = to_intel_crtc(for_crtc)->pipe;
+ struct intel_dbuf_state *new_dbuf_state =
+ intel_atomic_get_new_dbuf_state(intel_state);
+ const struct intel_dbuf_state *old_dbuf_state =
+ intel_atomic_get_old_dbuf_state(intel_state);
+ u8 active_pipes = new_dbuf_state->active_pipes;
+ u16 ddb_size;
+ u32 ddb_range_size;
+ u32 i;
+ u32 dbuf_slice_mask;
+ u32 offset;
+ u32 slice_size;
+ u32 total_slice_mask;
+ u32 start, end;
+ int ret;
- if (WARN_ON(!state) || !cstate->base.active) {
+ *num_active = hweight8(active_pipes);
+
+ if (!crtc_state->hw.active) {
alloc->start = 0;
alloc->end = 0;
- *num_active = hweight32(dev_priv->active_crtcs);
- return;
+ return 0;
}
- if (intel_state->active_pipe_changes)
- *num_active = hweight32(intel_state->active_crtcs);
- else
- *num_active = hweight32(dev_priv->active_crtcs);
+ ddb_size = intel_get_ddb_size(dev_priv);
- ddb_size = intel_get_ddb_size(dev_priv, cstate, total_data_rate,
- *num_active, ddb);
+ slice_size = ddb_size / INTEL_INFO(dev_priv)->num_supported_dbuf_slices;
/*
- * If the state doesn't change the active CRTC's, then there's
- * no need to recalculate; the existing pipe allocation limits
- * should remain unchanged. Note that we're safe from racing
- * commits since any racing commit that changes the active CRTC
- * list would need to grab _all_ crtc locks, including the one
- * we currently hold.
+ * If the state doesn't change the active CRTC's or there is no
+ * modeset request, then there's no need to recalculate;
+ * the existing pipe allocation limits should remain unchanged.
+ * Note that we're safe from racing commits since any racing commit
+ * that changes the active CRTC list or do modeset would need to
+ * grab _all_ crtc locks, including the one we currently hold.
*/
- if (!intel_state->active_pipe_changes) {
+ if (old_dbuf_state->active_pipes == new_dbuf_state->active_pipes &&
+ !dev_priv->wm.distrust_bios_wm) {
/*
* alloc may be cleared by clear_intel_crtc_state,
* copy from old state to be sure
+ *
+ * FIXME get rid of this mess
*/
*alloc = to_intel_crtc_state(for_crtc->state)->wm.skl.ddb;
- return;
+ return 0;
}
- nth_active_pipe = hweight32(intel_state->active_crtcs &
- (drm_crtc_mask(for_crtc) - 1));
- pipe_size = ddb_size / hweight32(intel_state->active_crtcs);
- alloc->start = nth_active_pipe * ddb_size / *num_active;
- alloc->end = alloc->start + pipe_size;
+ /*
+ * Get allowed DBuf slices for correspondent pipe and platform.
+ */
+ dbuf_slice_mask = skl_compute_dbuf_slices(crtc_state, active_pipes);
+
+ /*
+ * Figure out at which DBuf slice we start, i.e if we start at Dbuf S2
+ * and slice size is 1024, the offset would be 1024
+ */
+ offset = icl_get_first_dbuf_slice_offset(dbuf_slice_mask,
+ slice_size, ddb_size);
+
+ /*
+ * Figure out total size of allowed DBuf slices, which is basically
+ * a number of allowed slices for that pipe multiplied by slice size.
+ * Inside of this
+ * range ddb entries are still allocated in proportion to display width.
+ */
+ ddb_range_size = hweight8(dbuf_slice_mask) * slice_size;
+
+ /*
+ * Watermark/ddb requirement highly depends upon width of the
+ * framebuffer, So instead of allocating DDB equally among pipes
+ * distribute DDB based on resolution/width of the display.
+ */
+ total_slice_mask = dbuf_slice_mask;
+ for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) {
+ const struct drm_display_mode *adjusted_mode =
+ &crtc_state->hw.adjusted_mode;
+ enum pipe pipe = crtc->pipe;
+ int hdisplay, vdisplay;
+ u32 pipe_dbuf_slice_mask;
+
+ if (!crtc_state->hw.active)
+ continue;
+
+ pipe_dbuf_slice_mask = skl_compute_dbuf_slices(crtc_state,
+ active_pipes);
+
+ /*
+ * According to BSpec pipe can share one dbuf slice with another
+ * pipes or pipe can use multiple dbufs, in both cases we
+ * account for other pipes only if they have exactly same mask.
+ * However we need to account how many slices we should enable
+ * in total.
+ */
+ total_slice_mask |= pipe_dbuf_slice_mask;
+
+ /*
+ * Do not account pipes using other slice sets
+ * luckily as of current BSpec slice sets do not partially
+ * intersect(pipes share either same one slice or same slice set
+ * i.e no partial intersection), so it is enough to check for
+ * equality for now.
+ */
+ if (dbuf_slice_mask != pipe_dbuf_slice_mask)
+ continue;
+
+ drm_mode_get_hv_timing(adjusted_mode, &hdisplay, &vdisplay);
+
+ total_width_in_range += hdisplay;
+
+ if (pipe < for_pipe)
+ width_before_pipe_in_range += hdisplay;
+ else if (pipe == for_pipe)
+ pipe_width = hdisplay;
+ }
+
+ /*
+ * FIXME: For now we always enable slice S1 as per
+ * the Bspec display initialization sequence.
+ */
+ new_dbuf_state->enabled_slices = total_slice_mask | BIT(DBUF_S1);
+
+ if (old_dbuf_state->enabled_slices != new_dbuf_state->enabled_slices) {
+ ret = intel_atomic_serialize_global_state(&new_dbuf_state->base);
+ if (ret)
+ return ret;
+ }
+
+ start = ddb_range_size * width_before_pipe_in_range / total_width_in_range;
+ end = ddb_range_size *
+ (width_before_pipe_in_range + pipe_width) / total_width_in_range;
+
+ alloc->start = offset + start;
+ alloc->end = offset + end;
+
+ drm_dbg_kms(&dev_priv->drm,
+ "[CRTC:%d:%s] dbuf slices 0x%x, ddb (%d - %d), active pipes 0x%x\n",
+ for_crtc->base.id, for_crtc->name,
+ dbuf_slice_mask, alloc->start, alloc->end, active_pipes);
+
+ return 0;
}
-static unsigned int skl_cursor_allocation(int num_active)
-{
- if (num_active == 1)
- return 32;
+static int skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
+ int width, const struct drm_format_info *format,
+ u64 modifier, unsigned int rotation,
+ u32 plane_pixel_rate, struct skl_wm_params *wp,
+ int color_plane);
+static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
+ int level,
+ unsigned int latency,
+ const struct skl_wm_params *wp,
+ const struct skl_wm_level *result_prev,
+ struct skl_wm_level *result /* out */);
- return 8;
+static unsigned int
+skl_cursor_allocation(const struct intel_crtc_state *crtc_state,
+ int num_active)
+{
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+ int level, max_level = ilk_wm_max_level(dev_priv);
+ struct skl_wm_level wm = {};
+ int ret, min_ddb_alloc = 0;
+ struct skl_wm_params wp;
+
+ ret = skl_compute_wm_params(crtc_state, 256,
+ drm_format_info(DRM_FORMAT_ARGB8888),
+ DRM_FORMAT_MOD_LINEAR,
+ DRM_MODE_ROTATE_0,
+ crtc_state->pixel_rate, &wp, 0);
+ drm_WARN_ON(&dev_priv->drm, ret);
+
+ for (level = 0; level <= max_level; level++) {
+ unsigned int latency = dev_priv->wm.skl_latency[level];
+
+ skl_compute_plane_wm(crtc_state, level, latency, &wp, &wm, &wm);
+ if (wm.min_ddb_alloc == U16_MAX)
+ break;
+
+ min_ddb_alloc = wm.min_ddb_alloc;
+ }
+
+ return max(num_active == 1 ? 32 : 8, min_ddb_alloc);
}
static void skl_ddb_entry_init_from_hw(struct drm_i915_private *dev_priv,
struct skl_ddb_entry *entry, u32 reg)
{
- u16 mask;
- if (INTEL_GEN(dev_priv) >= 11)
- mask = ICL_DDB_ENTRY_MASK;
- else
- mask = SKL_DDB_ENTRY_MASK;
- entry->start = reg & mask;
- entry->end = (reg >> DDB_ENTRY_END_SHIFT) & mask;
+ entry->start = reg & DDB_ENTRY_MASK;
+ entry->end = (reg >> DDB_ENTRY_END_SHIFT) & DDB_ENTRY_MASK;
if (entry->end)
entry->end += 1;
@@ -3931,68 +4299,65 @@
skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv,
const enum pipe pipe,
const enum plane_id plane_id,
- struct skl_ddb_allocation *ddb /* out */)
+ struct skl_ddb_entry *ddb_y,
+ struct skl_ddb_entry *ddb_uv)
{
- u32 val, val2 = 0;
- int fourcc, pixel_format;
+ u32 val, val2;
+ u32 fourcc = 0;
/* Cursor doesn't support NV12/planar, so no extra calculation needed */
if (plane_id == PLANE_CURSOR) {
val = I915_READ(CUR_BUF_CFG(pipe));
- skl_ddb_entry_init_from_hw(dev_priv,
- &ddb->plane[pipe][plane_id], val);
+ skl_ddb_entry_init_from_hw(dev_priv, ddb_y, val);
return;
}
val = I915_READ(PLANE_CTL(pipe, plane_id));
/* No DDB allocated for disabled planes */
- if (!(val & PLANE_CTL_ENABLE))
- return;
+ if (val & PLANE_CTL_ENABLE)
+ fourcc = skl_format_to_fourcc(val & PLANE_CTL_FORMAT_MASK,
+ val & PLANE_CTL_ORDER_RGBX,
+ val & PLANE_CTL_ALPHA_MASK);
- pixel_format = val & PLANE_CTL_FORMAT_MASK;
- fourcc = skl_format_to_fourcc(pixel_format,
- val & PLANE_CTL_ORDER_RGBX,
- val & PLANE_CTL_ALPHA_MASK);
-
- val = I915_READ(PLANE_BUF_CFG(pipe, plane_id));
- val2 = I915_READ(PLANE_NV12_BUF_CFG(pipe, plane_id));
-
- if (fourcc == DRM_FORMAT_NV12) {
- skl_ddb_entry_init_from_hw(dev_priv,
- &ddb->plane[pipe][plane_id], val2);
- skl_ddb_entry_init_from_hw(dev_priv,
- &ddb->uv_plane[pipe][plane_id], val);
+ if (INTEL_GEN(dev_priv) >= 11) {
+ val = I915_READ(PLANE_BUF_CFG(pipe, plane_id));
+ skl_ddb_entry_init_from_hw(dev_priv, ddb_y, val);
} else {
- skl_ddb_entry_init_from_hw(dev_priv,
- &ddb->plane[pipe][plane_id], val);
+ val = I915_READ(PLANE_BUF_CFG(pipe, plane_id));
+ val2 = I915_READ(PLANE_NV12_BUF_CFG(pipe, plane_id));
+
+ if (fourcc &&
+ drm_format_info_is_yuv_semiplanar(drm_format_info(fourcc)))
+ swap(val, val2);
+
+ skl_ddb_entry_init_from_hw(dev_priv, ddb_y, val);
+ skl_ddb_entry_init_from_hw(dev_priv, ddb_uv, val2);
}
}
-void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
- struct skl_ddb_allocation *ddb /* out */)
+void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc,
+ struct skl_ddb_entry *ddb_y,
+ struct skl_ddb_entry *ddb_uv)
{
- struct intel_crtc *crtc;
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ enum intel_display_power_domain power_domain;
+ enum pipe pipe = crtc->pipe;
+ intel_wakeref_t wakeref;
+ enum plane_id plane_id;
- memset(ddb, 0, sizeof(*ddb));
+ power_domain = POWER_DOMAIN_PIPE(pipe);
+ wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+ if (!wakeref)
+ return;
- ddb->enabled_slices = intel_enabled_dbuf_slices_num(dev_priv);
+ for_each_plane_id_on_crtc(crtc, plane_id)
+ skl_ddb_get_hw_plane_state(dev_priv, pipe,
+ plane_id,
+ &ddb_y[plane_id],
+ &ddb_uv[plane_id]);
- for_each_intel_crtc(&dev_priv->drm, crtc) {
- enum intel_display_power_domain power_domain;
- enum plane_id plane_id;
- enum pipe pipe = crtc->pipe;
-
- power_domain = POWER_DOMAIN_PIPE(pipe);
- if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
- continue;
-
- for_each_plane_id_on_crtc(crtc, plane_id)
- skl_ddb_get_hw_plane_state(dev_priv, pipe,
- plane_id, ddb);
-
- intel_display_power_put(dev_priv, power_domain);
- }
+ intel_display_power_put(dev_priv, power_domain, wakeref);
}
/*
@@ -4012,38 +4377,29 @@
* Caller should take care of dividing & rounding off the value.
*/
static uint_fixed_16_16_t
-skl_plane_downscale_amount(const struct intel_crtc_state *cstate,
- const struct intel_plane_state *pstate)
+skl_plane_downscale_amount(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state)
{
- struct intel_plane *plane = to_intel_plane(pstate->base.plane);
- uint32_t src_w, src_h, dst_w, dst_h;
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+ u32 src_w, src_h, dst_w, dst_h;
uint_fixed_16_16_t fp_w_ratio, fp_h_ratio;
uint_fixed_16_16_t downscale_h, downscale_w;
- if (WARN_ON(!intel_wm_plane_visible(cstate, pstate)))
+ if (drm_WARN_ON(&dev_priv->drm,
+ !intel_wm_plane_visible(crtc_state, plane_state)))
return u32_to_fixed16(0);
- /* n.b., src is 16.16 fixed point, dst is whole integer */
- if (plane->id == PLANE_CURSOR) {
- /*
- * Cursors only support 0/180 degree rotation,
- * hence no need to account for rotation here.
- */
- src_w = pstate->base.src_w >> 16;
- src_h = pstate->base.src_h >> 16;
- dst_w = pstate->base.crtc_w;
- dst_h = pstate->base.crtc_h;
- } else {
- /*
- * Src coordinates are already rotated by 270 degrees for
- * the 90/270 degree plane rotation cases (to match the
- * GTT mapping), hence no need to account for rotation here.
- */
- src_w = drm_rect_width(&pstate->base.src) >> 16;
- src_h = drm_rect_height(&pstate->base.src) >> 16;
- dst_w = drm_rect_width(&pstate->base.dst);
- dst_h = drm_rect_height(&pstate->base.dst);
- }
+ /*
+ * Src coordinates are already rotated by 270 degrees for
+ * the 90/270 degree plane rotation cases (to match the
+ * GTT mapping), hence no need to account for rotation here.
+ *
+ * n.b., src is 16.16 fixed point, dst is whole integer.
+ */
+ src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+ src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
+ dst_w = drm_rect_width(&plane_state->uapi.dst);
+ dst_h = drm_rect_height(&plane_state->uapi.dst);
fp_w_ratio = div_fixed16(src_w, dst_w);
fp_h_ratio = div_fixed16(src_h, dst_h);
@@ -4053,120 +4409,274 @@
return mul_fixed16(downscale_w, downscale_h);
}
-static uint_fixed_16_16_t
-skl_pipe_downscale_amount(const struct intel_crtc_state *crtc_state)
+struct dbuf_slice_conf_entry {
+ u8 active_pipes;
+ u8 dbuf_mask[I915_MAX_PIPES];
+};
+
+/*
+ * Table taken from Bspec 12716
+ * Pipes do have some preferred DBuf slice affinity,
+ * plus there are some hardcoded requirements on how
+ * those should be distributed for multipipe scenarios.
+ * For more DBuf slices algorithm can get even more messy
+ * and less readable, so decided to use a table almost
+ * as is from BSpec itself - that way it is at least easier
+ * to compare, change and check.
+ */
+static const struct dbuf_slice_conf_entry icl_allowed_dbufs[] =
+/* Autogenerated with igt/tools/intel_dbuf_map tool: */
{
- uint_fixed_16_16_t pipe_downscale = u32_to_fixed16(1);
+ {
+ .active_pipes = BIT(PIPE_A),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_B),
+ .dbuf_mask = {
+ [PIPE_B] = BIT(DBUF_S1),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_A) | BIT(PIPE_B),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1),
+ [PIPE_B] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_C),
+ .dbuf_mask = {
+ [PIPE_C] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_A) | BIT(PIPE_C),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1),
+ [PIPE_C] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_B) | BIT(PIPE_C),
+ .dbuf_mask = {
+ [PIPE_B] = BIT(DBUF_S1),
+ [PIPE_C] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1),
+ [PIPE_B] = BIT(DBUF_S1),
+ [PIPE_C] = BIT(DBUF_S2),
+ },
+ },
+ {}
+};
- if (!crtc_state->base.enable)
- return pipe_downscale;
-
- if (crtc_state->pch_pfit.enabled) {
- uint32_t src_w, src_h, dst_w, dst_h;
- uint32_t pfit_size = crtc_state->pch_pfit.size;
- uint_fixed_16_16_t fp_w_ratio, fp_h_ratio;
- uint_fixed_16_16_t downscale_h, downscale_w;
-
- src_w = crtc_state->pipe_src_w;
- src_h = crtc_state->pipe_src_h;
- dst_w = pfit_size >> 16;
- dst_h = pfit_size & 0xffff;
-
- if (!dst_w || !dst_h)
- return pipe_downscale;
-
- fp_w_ratio = div_fixed16(src_w, dst_w);
- fp_h_ratio = div_fixed16(src_h, dst_h);
- downscale_w = max_fixed16(fp_w_ratio, u32_to_fixed16(1));
- downscale_h = max_fixed16(fp_h_ratio, u32_to_fixed16(1));
-
- pipe_downscale = mul_fixed16(downscale_w, downscale_h);
- }
-
- return pipe_downscale;
-}
-
-int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
- struct intel_crtc_state *cstate)
+/*
+ * Table taken from Bspec 49255
+ * Pipes do have some preferred DBuf slice affinity,
+ * plus there are some hardcoded requirements on how
+ * those should be distributed for multipipe scenarios.
+ * For more DBuf slices algorithm can get even more messy
+ * and less readable, so decided to use a table almost
+ * as is from BSpec itself - that way it is at least easier
+ * to compare, change and check.
+ */
+static const struct dbuf_slice_conf_entry tgl_allowed_dbufs[] =
+/* Autogenerated with igt/tools/intel_dbuf_map tool: */
{
- struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
- struct drm_crtc_state *crtc_state = &cstate->base;
- struct drm_atomic_state *state = crtc_state->state;
- struct drm_plane *plane;
- const struct drm_plane_state *pstate;
- struct intel_plane_state *intel_pstate;
- int crtc_clock, dotclk;
- uint32_t pipe_max_pixel_rate;
- uint_fixed_16_16_t pipe_downscale;
- uint_fixed_16_16_t max_downscale = u32_to_fixed16(1);
+ {
+ .active_pipes = BIT(PIPE_A),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_B),
+ .dbuf_mask = {
+ [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_A) | BIT(PIPE_B),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S2),
+ [PIPE_B] = BIT(DBUF_S1),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_C),
+ .dbuf_mask = {
+ [PIPE_C] = BIT(DBUF_S2) | BIT(DBUF_S1),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_A) | BIT(PIPE_C),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1),
+ [PIPE_C] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_B) | BIT(PIPE_C),
+ .dbuf_mask = {
+ [PIPE_B] = BIT(DBUF_S1),
+ [PIPE_C] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1),
+ [PIPE_B] = BIT(DBUF_S1),
+ [PIPE_C] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_D),
+ .dbuf_mask = {
+ [PIPE_D] = BIT(DBUF_S2) | BIT(DBUF_S1),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_A) | BIT(PIPE_D),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1),
+ [PIPE_D] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_B) | BIT(PIPE_D),
+ .dbuf_mask = {
+ [PIPE_B] = BIT(DBUF_S1),
+ [PIPE_D] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_D),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1),
+ [PIPE_B] = BIT(DBUF_S1),
+ [PIPE_D] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_C) | BIT(PIPE_D),
+ .dbuf_mask = {
+ [PIPE_C] = BIT(DBUF_S1),
+ [PIPE_D] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_A) | BIT(PIPE_C) | BIT(PIPE_D),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1),
+ [PIPE_C] = BIT(DBUF_S2),
+ [PIPE_D] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),
+ .dbuf_mask = {
+ [PIPE_B] = BIT(DBUF_S1),
+ [PIPE_C] = BIT(DBUF_S2),
+ [PIPE_D] = BIT(DBUF_S2),
+ },
+ },
+ {
+ .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),
+ .dbuf_mask = {
+ [PIPE_A] = BIT(DBUF_S1),
+ [PIPE_B] = BIT(DBUF_S1),
+ [PIPE_C] = BIT(DBUF_S2),
+ [PIPE_D] = BIT(DBUF_S2),
+ },
+ },
+ {}
+};
- if (!cstate->base.enable)
- return 0;
+static u8 compute_dbuf_slices(enum pipe pipe, u8 active_pipes,
+ const struct dbuf_slice_conf_entry *dbuf_slices)
+{
+ int i;
- drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) {
- uint_fixed_16_16_t plane_downscale;
- uint_fixed_16_16_t fp_9_div_8 = div_fixed16(9, 8);
- int bpp;
-
- if (!intel_wm_plane_visible(cstate,
- to_intel_plane_state(pstate)))
- continue;
-
- if (WARN_ON(!pstate->fb))
- return -EINVAL;
-
- intel_pstate = to_intel_plane_state(pstate);
- plane_downscale = skl_plane_downscale_amount(cstate,
- intel_pstate);
- bpp = pstate->fb->format->cpp[0] * 8;
- if (bpp == 64)
- plane_downscale = mul_fixed16(plane_downscale,
- fp_9_div_8);
-
- max_downscale = max_fixed16(plane_downscale, max_downscale);
+ for (i = 0; i < dbuf_slices[i].active_pipes; i++) {
+ if (dbuf_slices[i].active_pipes == active_pipes)
+ return dbuf_slices[i].dbuf_mask[pipe];
}
- pipe_downscale = skl_pipe_downscale_amount(cstate);
-
- pipe_downscale = mul_fixed16(pipe_downscale, max_downscale);
-
- crtc_clock = crtc_state->adjusted_mode.crtc_clock;
- dotclk = to_intel_atomic_state(state)->cdclk.logical.cdclk;
-
- if (IS_GEMINILAKE(dev_priv) || INTEL_GEN(dev_priv) >= 10)
- dotclk *= 2;
-
- pipe_max_pixel_rate = div_round_up_u32_fixed16(dotclk, pipe_downscale);
-
- if (pipe_max_pixel_rate < crtc_clock) {
- DRM_DEBUG_KMS("Max supported pixel clock with scaling exceeded\n");
- return -EINVAL;
- }
-
return 0;
}
-static unsigned int
-skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
- const struct drm_plane_state *pstate,
- const int plane)
+/*
+ * This function finds an entry with same enabled pipe configuration and
+ * returns correspondent DBuf slice mask as stated in BSpec for particular
+ * platform.
+ */
+static u8 icl_compute_dbuf_slices(enum pipe pipe, u8 active_pipes)
{
- struct intel_plane *intel_plane = to_intel_plane(pstate->plane);
- struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
- uint32_t data_rate;
- uint32_t width = 0, height = 0;
- struct drm_framebuffer *fb;
- u32 format;
+ /*
+ * FIXME: For ICL this is still a bit unclear as prev BSpec revision
+ * required calculating "pipe ratio" in order to determine
+ * if one or two slices can be used for single pipe configurations
+ * as additional constraint to the existing table.
+ * However based on recent info, it should be not "pipe ratio"
+ * but rather ratio between pixel_rate and cdclk with additional
+ * constants, so for now we are using only table until this is
+ * clarified. Also this is the reason why crtc_state param is
+ * still here - we will need it once those additional constraints
+ * pop up.
+ */
+ return compute_dbuf_slices(pipe, active_pipes, icl_allowed_dbufs);
+}
+
+static u8 tgl_compute_dbuf_slices(enum pipe pipe, u8 active_pipes)
+{
+ return compute_dbuf_slices(pipe, active_pipes, tgl_allowed_dbufs);
+}
+
+static u8 skl_compute_dbuf_slices(const struct intel_crtc_state *crtc_state,
+ u8 active_pipes)
+{
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ enum pipe pipe = crtc->pipe;
+
+ if (IS_GEN(dev_priv, 12))
+ return tgl_compute_dbuf_slices(pipe, active_pipes);
+ else if (IS_GEN(dev_priv, 11))
+ return icl_compute_dbuf_slices(pipe, active_pipes);
+ /*
+ * For anything else just return one slice yet.
+ * Should be extended for other platforms.
+ */
+ return active_pipes & BIT(pipe) ? BIT(DBUF_S1) : 0;
+}
+
+static u64
+skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ int color_plane)
+{
+ struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+ const struct drm_framebuffer *fb = plane_state->hw.fb;
+ u32 data_rate;
+ u32 width = 0, height = 0;
uint_fixed_16_16_t down_scale_amount;
+ u64 rate;
- if (!intel_pstate->base.visible)
+ if (!plane_state->uapi.visible)
return 0;
- fb = pstate->fb;
- format = fb->format->format;
-
- if (intel_plane->id == PLANE_CURSOR)
+ if (plane->id == PLANE_CURSOR)
return 0;
- if (plane == 1 && format != DRM_FORMAT_NV12)
+
+ if (color_plane == 1 &&
+ !intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier))
return 0;
/*
@@ -4174,265 +4684,352 @@
* the 90/270 degree plane rotation cases (to match the
* GTT mapping), hence no need to account for rotation here.
*/
- width = drm_rect_width(&intel_pstate->base.src) >> 16;
- height = drm_rect_height(&intel_pstate->base.src) >> 16;
+ width = drm_rect_width(&plane_state->uapi.src) >> 16;
+ height = drm_rect_height(&plane_state->uapi.src) >> 16;
/* UV plane does 1/2 pixel sub-sampling */
- if (plane == 1 && format == DRM_FORMAT_NV12) {
+ if (color_plane == 1) {
width /= 2;
height /= 2;
}
- data_rate = width * height * fb->format->cpp[plane];
+ data_rate = width * height;
- down_scale_amount = skl_plane_downscale_amount(cstate, intel_pstate);
+ down_scale_amount = skl_plane_downscale_amount(crtc_state, plane_state);
- return mul_round_up_u32_fixed16(data_rate, down_scale_amount);
+ rate = mul_round_up_u32_fixed16(data_rate, down_scale_amount);
+
+ rate *= fb->format->cpp[color_plane];
+ return rate;
}
-/*
- * We don't overflow 32 bits. Worst case is 3 planes enabled, each fetching
- * a 8192x4096@32bpp framebuffer:
- * 3 * 4096 * 8192 * 4 < 2^32
- */
-static unsigned int
-skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate,
- unsigned int *plane_data_rate,
- unsigned int *uv_plane_data_rate)
+static u64
+skl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
+ u64 *plane_data_rate,
+ u64 *uv_plane_data_rate)
{
- struct drm_crtc_state *cstate = &intel_cstate->base;
- struct drm_atomic_state *state = cstate->state;
- struct drm_plane *plane;
- const struct drm_plane_state *pstate;
- unsigned int total_data_rate = 0;
-
- if (WARN_ON(!state))
- return 0;
+ struct intel_plane *plane;
+ const struct intel_plane_state *plane_state;
+ u64 total_data_rate = 0;
/* Calculate and cache data rate for each plane */
- drm_atomic_crtc_state_for_each_plane_state(plane, pstate, cstate) {
- enum plane_id plane_id = to_intel_plane(plane)->id;
- unsigned int rate;
+ intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
+ enum plane_id plane_id = plane->id;
+ u64 rate;
/* packed/y */
- rate = skl_plane_relative_data_rate(intel_cstate,
- pstate, 0);
+ rate = skl_plane_relative_data_rate(crtc_state, plane_state, 0);
plane_data_rate[plane_id] = rate;
-
total_data_rate += rate;
/* uv-plane */
- rate = skl_plane_relative_data_rate(intel_cstate,
- pstate, 1);
+ rate = skl_plane_relative_data_rate(crtc_state, plane_state, 1);
uv_plane_data_rate[plane_id] = rate;
-
total_data_rate += rate;
}
return total_data_rate;
}
-static uint16_t
-skl_ddb_min_alloc(const struct drm_plane_state *pstate, const int plane)
+static u64
+icl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
+ u64 *plane_data_rate)
{
- struct drm_framebuffer *fb = pstate->fb;
- struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
- uint32_t src_w, src_h;
- uint32_t min_scanlines = 8;
- uint8_t plane_bpp;
+ struct intel_plane *plane;
+ const struct intel_plane_state *plane_state;
+ u64 total_data_rate = 0;
- if (WARN_ON(!fb))
- return 0;
+ /* Calculate and cache data rate for each plane */
+ intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
+ enum plane_id plane_id = plane->id;
+ u64 rate;
- /* For packed formats, and uv-plane, return 0 */
- if (plane == 1 && fb->format->format != DRM_FORMAT_NV12)
- return 0;
+ if (!plane_state->planar_linked_plane) {
+ rate = skl_plane_relative_data_rate(crtc_state, plane_state, 0);
+ plane_data_rate[plane_id] = rate;
+ total_data_rate += rate;
+ } else {
+ enum plane_id y_plane_id;
- /* For Non Y-tile return 8-blocks */
- if (fb->modifier != I915_FORMAT_MOD_Y_TILED &&
- fb->modifier != I915_FORMAT_MOD_Yf_TILED &&
- fb->modifier != I915_FORMAT_MOD_Y_TILED_CCS &&
- fb->modifier != I915_FORMAT_MOD_Yf_TILED_CCS)
- return 8;
+ /*
+ * The slave plane might not iterate in
+ * intel_atomic_crtc_state_for_each_plane_state(),
+ * and needs the master plane state which may be
+ * NULL if we try get_new_plane_state(), so we
+ * always calculate from the master.
+ */
+ if (plane_state->planar_slave)
+ continue;
- /*
- * Src coordinates are already rotated by 270 degrees for
- * the 90/270 degree plane rotation cases (to match the
- * GTT mapping), hence no need to account for rotation here.
- */
- src_w = drm_rect_width(&intel_pstate->base.src) >> 16;
- src_h = drm_rect_height(&intel_pstate->base.src) >> 16;
+ /* Y plane rate is calculated on the slave */
+ rate = skl_plane_relative_data_rate(crtc_state, plane_state, 0);
+ y_plane_id = plane_state->planar_linked_plane->id;
+ plane_data_rate[y_plane_id] = rate;
+ total_data_rate += rate;
- /* Halve UV plane width and height for NV12 */
- if (plane == 1) {
- src_w /= 2;
- src_h /= 2;
- }
-
- plane_bpp = fb->format->cpp[plane];
-
- if (drm_rotation_90_or_270(pstate->rotation)) {
- switch (plane_bpp) {
- case 1:
- min_scanlines = 32;
- break;
- case 2:
- min_scanlines = 16;
- break;
- case 4:
- min_scanlines = 8;
- break;
- case 8:
- min_scanlines = 4;
- break;
- default:
- WARN(1, "Unsupported pixel depth %u for rotation",
- plane_bpp);
- min_scanlines = 32;
+ rate = skl_plane_relative_data_rate(crtc_state, plane_state, 1);
+ plane_data_rate[plane_id] = rate;
+ total_data_rate += rate;
}
}
- return DIV_ROUND_UP((4 * src_w * plane_bpp), 512) * min_scanlines/4 + 3;
+ return total_data_rate;
}
-static void
-skl_ddb_calc_min(const struct intel_crtc_state *cstate, int num_active,
- uint16_t *minimum, uint16_t *uv_minimum)
+static const struct skl_wm_level *
+skl_plane_wm_level(const struct intel_crtc_state *crtc_state,
+ enum plane_id plane_id,
+ int level)
{
- const struct drm_plane_state *pstate;
- struct drm_plane *plane;
+ const struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
+ const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id];
- drm_atomic_crtc_state_for_each_plane_state(plane, pstate, &cstate->base) {
- enum plane_id plane_id = to_intel_plane(plane)->id;
+ if (level == 0 && pipe_wm->use_sagv_wm)
+ return &wm->sagv_wm0;
- if (plane_id == PLANE_CURSOR)
- continue;
-
- if (!pstate->visible)
- continue;
-
- minimum[plane_id] = skl_ddb_min_alloc(pstate, 0);
- uv_minimum[plane_id] = skl_ddb_min_alloc(pstate, 1);
- }
-
- minimum[PLANE_CURSOR] = skl_cursor_allocation(num_active);
+ return &wm->wm[level];
}
static int
-skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
- struct skl_ddb_allocation *ddb /* out */)
+skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state)
{
- struct drm_atomic_state *state = cstate->base.state;
- struct drm_crtc *crtc = cstate->base.crtc;
- struct drm_device *dev = crtc->dev;
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- enum pipe pipe = intel_crtc->pipe;
- struct skl_ddb_entry *alloc = &cstate->wm.skl.ddb;
- uint16_t alloc_size, start;
- uint16_t minimum[I915_MAX_PLANES] = {};
- uint16_t uv_minimum[I915_MAX_PLANES] = {};
- unsigned int total_data_rate;
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ struct skl_ddb_entry *alloc = &crtc_state->wm.skl.ddb;
+ u16 alloc_size, start = 0;
+ u16 total[I915_MAX_PLANES] = {};
+ u16 uv_total[I915_MAX_PLANES] = {};
+ u64 total_data_rate;
enum plane_id plane_id;
int num_active;
- unsigned int plane_data_rate[I915_MAX_PLANES] = {};
- unsigned int uv_plane_data_rate[I915_MAX_PLANES] = {};
- uint16_t total_min_blocks = 0;
+ u64 plane_data_rate[I915_MAX_PLANES] = {};
+ u64 uv_plane_data_rate[I915_MAX_PLANES] = {};
+ u32 blocks;
+ int level;
+ int ret;
/* Clear the partitioning for disabled planes. */
- memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
- memset(ddb->uv_plane[pipe], 0, sizeof(ddb->uv_plane[pipe]));
+ memset(crtc_state->wm.skl.plane_ddb_y, 0, sizeof(crtc_state->wm.skl.plane_ddb_y));
+ memset(crtc_state->wm.skl.plane_ddb_uv, 0, sizeof(crtc_state->wm.skl.plane_ddb_uv));
- if (WARN_ON(!state))
- return 0;
+ if (!crtc_state->hw.active) {
+ struct intel_atomic_state *state =
+ to_intel_atomic_state(crtc_state->uapi.state);
+ struct intel_dbuf_state *new_dbuf_state =
+ intel_atomic_get_new_dbuf_state(state);
+ const struct intel_dbuf_state *old_dbuf_state =
+ intel_atomic_get_old_dbuf_state(state);
- if (!cstate->base.active) {
+ /*
+ * FIXME hack to make sure we compute this sensibly when
+ * turning off all the pipes. Otherwise we leave it at
+ * whatever we had previously, and then runtime PM will
+ * mess it up by turning off all but S1. Remove this
+ * once the dbuf state computation flow becomes sane.
+ */
+ if (new_dbuf_state->active_pipes == 0) {
+ new_dbuf_state->enabled_slices = BIT(DBUF_S1);
+
+ if (old_dbuf_state->enabled_slices != new_dbuf_state->enabled_slices) {
+ ret = intel_atomic_serialize_global_state(&new_dbuf_state->base);
+ if (ret)
+ return ret;
+ }
+ }
+
alloc->start = alloc->end = 0;
return 0;
}
- total_data_rate = skl_get_total_relative_data_rate(cstate,
- plane_data_rate,
- uv_plane_data_rate);
- skl_ddb_get_pipe_allocation_limits(dev, cstate, total_data_rate, ddb,
- alloc, &num_active);
+ if (INTEL_GEN(dev_priv) >= 11)
+ total_data_rate =
+ icl_get_total_relative_data_rate(crtc_state,
+ plane_data_rate);
+ else
+ total_data_rate =
+ skl_get_total_relative_data_rate(crtc_state,
+ plane_data_rate,
+ uv_plane_data_rate);
+
+ ret = skl_ddb_get_pipe_allocation_limits(dev_priv, crtc_state,
+ total_data_rate,
+ alloc, &num_active);
+ if (ret)
+ return ret;
+
alloc_size = skl_ddb_entry_size(alloc);
if (alloc_size == 0)
return 0;
- skl_ddb_calc_min(cstate, num_active, minimum, uv_minimum);
+ /* Allocate fixed number of blocks for cursor. */
+ total[PLANE_CURSOR] = skl_cursor_allocation(crtc_state, num_active);
+ alloc_size -= total[PLANE_CURSOR];
+ crtc_state->wm.skl.plane_ddb_y[PLANE_CURSOR].start =
+ alloc->end - total[PLANE_CURSOR];
+ crtc_state->wm.skl.plane_ddb_y[PLANE_CURSOR].end = alloc->end;
- /*
- * 1. Allocate the mininum required blocks for each active plane
- * and allocate the cursor, it doesn't require extra allocation
- * proportional to the data rate.
- */
-
- for_each_plane_id_on_crtc(intel_crtc, plane_id) {
- total_min_blocks += minimum[plane_id];
- total_min_blocks += uv_minimum[plane_id];
- }
-
- if (total_min_blocks > alloc_size) {
- DRM_DEBUG_KMS("Requested display configuration exceeds system DDB limitations");
- DRM_DEBUG_KMS("minimum required %d/%d\n", total_min_blocks,
- alloc_size);
- return -EINVAL;
- }
-
- alloc_size -= total_min_blocks;
- ddb->plane[pipe][PLANE_CURSOR].start = alloc->end - minimum[PLANE_CURSOR];
- ddb->plane[pipe][PLANE_CURSOR].end = alloc->end;
-
- /*
- * 2. Distribute the remaining space in proportion to the amount of
- * data each plane needs to fetch from memory.
- *
- * FIXME: we may not allocate every single block here.
- */
if (total_data_rate == 0)
return 0;
- start = alloc->start;
- for_each_plane_id_on_crtc(intel_crtc, plane_id) {
- unsigned int data_rate, uv_data_rate;
- uint16_t plane_blocks, uv_plane_blocks;
+ /*
+ * Find the highest watermark level for which we can satisfy the block
+ * requirement of active planes.
+ */
+ for (level = ilk_wm_max_level(dev_priv); level >= 0; level--) {
+ blocks = 0;
+ for_each_plane_id_on_crtc(crtc, plane_id) {
+ const struct skl_plane_wm *wm =
+ &crtc_state->wm.skl.optimal.planes[plane_id];
+
+ if (plane_id == PLANE_CURSOR) {
+ if (wm->wm[level].min_ddb_alloc > total[PLANE_CURSOR]) {
+ drm_WARN_ON(&dev_priv->drm,
+ wm->wm[level].min_ddb_alloc != U16_MAX);
+ blocks = U32_MAX;
+ break;
+ }
+ continue;
+ }
+
+ blocks += wm->wm[level].min_ddb_alloc;
+ blocks += wm->uv_wm[level].min_ddb_alloc;
+ }
+
+ if (blocks <= alloc_size) {
+ alloc_size -= blocks;
+ break;
+ }
+ }
+
+ if (level < 0) {
+ drm_dbg_kms(&dev_priv->drm,
+ "Requested display configuration exceeds system DDB limitations");
+ drm_dbg_kms(&dev_priv->drm, "minimum required %d/%d\n",
+ blocks, alloc_size);
+ return -EINVAL;
+ }
+
+ /*
+ * Grant each plane the blocks it requires at the highest achievable
+ * watermark level, plus an extra share of the leftover blocks
+ * proportional to its relative data rate.
+ */
+ for_each_plane_id_on_crtc(crtc, plane_id) {
+ const struct skl_plane_wm *wm =
+ &crtc_state->wm.skl.optimal.planes[plane_id];
+ u64 rate;
+ u16 extra;
if (plane_id == PLANE_CURSOR)
continue;
- data_rate = plane_data_rate[plane_id];
-
/*
- * allocation for (packed formats) or (uv-plane part of planar format):
- * promote the expression to 64 bits to avoid overflowing, the
- * result is < available as data_rate / total_data_rate < 1
+ * We've accounted for all active planes; remaining planes are
+ * all disabled.
*/
- plane_blocks = minimum[plane_id];
- plane_blocks += div_u64((uint64_t)alloc_size * data_rate,
- total_data_rate);
+ if (total_data_rate == 0)
+ break;
+
+ rate = plane_data_rate[plane_id];
+ extra = min_t(u16, alloc_size,
+ DIV64_U64_ROUND_UP(alloc_size * rate,
+ total_data_rate));
+ total[plane_id] = wm->wm[level].min_ddb_alloc + extra;
+ alloc_size -= extra;
+ total_data_rate -= rate;
+
+ if (total_data_rate == 0)
+ break;
+
+ rate = uv_plane_data_rate[plane_id];
+ extra = min_t(u16, alloc_size,
+ DIV64_U64_ROUND_UP(alloc_size * rate,
+ total_data_rate));
+ uv_total[plane_id] = wm->uv_wm[level].min_ddb_alloc + extra;
+ alloc_size -= extra;
+ total_data_rate -= rate;
+ }
+ drm_WARN_ON(&dev_priv->drm, alloc_size != 0 || total_data_rate != 0);
+
+ /* Set the actual DDB start/end points for each plane */
+ start = alloc->start;
+ for_each_plane_id_on_crtc(crtc, plane_id) {
+ struct skl_ddb_entry *plane_alloc =
+ &crtc_state->wm.skl.plane_ddb_y[plane_id];
+ struct skl_ddb_entry *uv_plane_alloc =
+ &crtc_state->wm.skl.plane_ddb_uv[plane_id];
+
+ if (plane_id == PLANE_CURSOR)
+ continue;
+
+ /* Gen11+ uses a separate plane for UV watermarks */
+ drm_WARN_ON(&dev_priv->drm,
+ INTEL_GEN(dev_priv) >= 11 && uv_total[plane_id]);
/* Leave disabled planes at (0,0) */
- if (data_rate) {
- ddb->plane[pipe][plane_id].start = start;
- ddb->plane[pipe][plane_id].end = start + plane_blocks;
+ if (total[plane_id]) {
+ plane_alloc->start = start;
+ start += total[plane_id];
+ plane_alloc->end = start;
}
- start += plane_blocks;
-
- /* Allocate DDB for UV plane for planar format/NV12 */
- uv_data_rate = uv_plane_data_rate[plane_id];
-
- uv_plane_blocks = uv_minimum[plane_id];
- uv_plane_blocks += div_u64((uint64_t)alloc_size * uv_data_rate,
- total_data_rate);
-
- if (uv_data_rate) {
- ddb->uv_plane[pipe][plane_id].start = start;
- ddb->uv_plane[pipe][plane_id].end =
- start + uv_plane_blocks;
+ if (uv_total[plane_id]) {
+ uv_plane_alloc->start = start;
+ start += uv_total[plane_id];
+ uv_plane_alloc->end = start;
}
+ }
- start += uv_plane_blocks;
+ /*
+ * When we calculated watermark values we didn't know how high
+ * of a level we'd actually be able to hit, so we just marked
+ * all levels as "enabled." Go back now and disable the ones
+ * that aren't actually possible.
+ */
+ for (level++; level <= ilk_wm_max_level(dev_priv); level++) {
+ for_each_plane_id_on_crtc(crtc, plane_id) {
+ struct skl_plane_wm *wm =
+ &crtc_state->wm.skl.optimal.planes[plane_id];
+
+ /*
+ * We only disable the watermarks for each plane if
+ * they exceed the ddb allocation of said plane. This
+ * is done so that we don't end up touching cursor
+ * watermarks needlessly when some other plane reduces
+ * our max possible watermark level.
+ *
+ * Bspec has this to say about the PLANE_WM enable bit:
+ * "All the watermarks at this level for all enabled
+ * planes must be enabled before the level will be used."
+ * So this is actually safe to do.
+ */
+ if (wm->wm[level].min_ddb_alloc > total[plane_id] ||
+ wm->uv_wm[level].min_ddb_alloc > uv_total[plane_id])
+ memset(&wm->wm[level], 0, sizeof(wm->wm[level]));
+
+ /*
+ * Wa_1408961008:icl, ehl
+ * Underruns with WM1+ disabled
+ */
+ if (IS_GEN(dev_priv, 11) &&
+ level == 1 && wm->wm[0].plane_en) {
+ wm->wm[level].plane_res_b = wm->wm[0].plane_res_b;
+ wm->wm[level].plane_res_l = wm->wm[0].plane_res_l;
+ wm->wm[level].ignore_lines = wm->wm[0].ignore_lines;
+ }
+ }
+ }
+
+ /*
+ * Go back and disable the transition watermark if it turns out we
+ * don't have enough DDB blocks for it.
+ */
+ for_each_plane_id_on_crtc(crtc, plane_id) {
+ struct skl_plane_wm *wm =
+ &crtc_state->wm.skl.optimal.planes[plane_id];
+
+ if (wm->trans_wm.plane_res_b >= total[plane_id])
+ memset(&wm->trans_wm, 0, sizeof(wm->trans_wm));
}
return 0;
@@ -4445,10 +5042,10 @@
* 2xcdclk is 1350 MHz and the pixel rate should never exceed that.
*/
static uint_fixed_16_16_t
-skl_wm_method1(const struct drm_i915_private *dev_priv, uint32_t pixel_rate,
- uint8_t cpp, uint32_t latency, uint32_t dbuf_block_size)
+skl_wm_method1(const struct drm_i915_private *dev_priv, u32 pixel_rate,
+ u8 cpp, u32 latency, u32 dbuf_block_size)
{
- uint32_t wm_intermediate_val;
+ u32 wm_intermediate_val;
uint_fixed_16_16_t ret;
if (latency == 0)
@@ -4457,18 +5054,17 @@
wm_intermediate_val = latency * pixel_rate * cpp;
ret = div_fixed16(wm_intermediate_val, 1000 * dbuf_block_size);
- if (INTEL_GEN(dev_priv) >= 10)
+ if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
ret = add_fixed16_u32(ret, 1);
return ret;
}
-static uint_fixed_16_16_t skl_wm_method2(uint32_t pixel_rate,
- uint32_t pipe_htotal,
- uint32_t latency,
- uint_fixed_16_16_t plane_blocks_per_line)
+static uint_fixed_16_16_t
+skl_wm_method2(u32 pixel_rate, u32 pipe_htotal, u32 latency,
+ uint_fixed_16_16_t plane_blocks_per_line)
{
- uint32_t wm_intermediate_val;
+ u32 wm_intermediate_val;
uint_fixed_16_16_t ret;
if (latency == 0)
@@ -4482,106 +5078,97 @@
}
static uint_fixed_16_16_t
-intel_get_linetime_us(struct intel_crtc_state *cstate)
+intel_get_linetime_us(const struct intel_crtc_state *crtc_state)
{
- uint32_t pixel_rate;
- uint32_t crtc_htotal;
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+ u32 pixel_rate;
+ u32 crtc_htotal;
uint_fixed_16_16_t linetime_us;
- if (!cstate->base.active)
+ if (!crtc_state->hw.active)
return u32_to_fixed16(0);
- pixel_rate = cstate->pixel_rate;
+ pixel_rate = crtc_state->pixel_rate;
- if (WARN_ON(pixel_rate == 0))
+ if (drm_WARN_ON(&dev_priv->drm, pixel_rate == 0))
return u32_to_fixed16(0);
- crtc_htotal = cstate->base.adjusted_mode.crtc_htotal;
+ crtc_htotal = crtc_state->hw.adjusted_mode.crtc_htotal;
linetime_us = div_fixed16(crtc_htotal * 1000, pixel_rate);
return linetime_us;
}
-static uint32_t
-skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *cstate,
- const struct intel_plane_state *pstate)
+static u32
+skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state)
{
- uint64_t adjusted_pixel_rate;
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+ u64 adjusted_pixel_rate;
uint_fixed_16_16_t downscale_amount;
/* Shouldn't reach here on disabled planes... */
- if (WARN_ON(!intel_wm_plane_visible(cstate, pstate)))
+ if (drm_WARN_ON(&dev_priv->drm,
+ !intel_wm_plane_visible(crtc_state, plane_state)))
return 0;
/*
* Adjusted plane pixel rate is just the pipe's adjusted pixel rate
* with additional adjustments for plane-specific scaling.
*/
- adjusted_pixel_rate = cstate->pixel_rate;
- downscale_amount = skl_plane_downscale_amount(cstate, pstate);
+ adjusted_pixel_rate = crtc_state->pixel_rate;
+ downscale_amount = skl_plane_downscale_amount(crtc_state, plane_state);
return mul_round_up_u32_fixed16(adjusted_pixel_rate,
downscale_amount);
}
static int
-skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv,
- struct intel_crtc_state *cstate,
- const struct intel_plane_state *intel_pstate,
- struct skl_wm_params *wp, int plane_id)
+skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
+ int width, const struct drm_format_info *format,
+ u64 modifier, unsigned int rotation,
+ u32 plane_pixel_rate, struct skl_wm_params *wp,
+ int color_plane)
{
- struct intel_plane *plane = to_intel_plane(intel_pstate->base.plane);
- const struct drm_plane_state *pstate = &intel_pstate->base;
- const struct drm_framebuffer *fb = pstate->fb;
- uint32_t interm_pbpl;
- struct intel_atomic_state *state =
- to_intel_atomic_state(cstate->base.state);
- bool apply_memory_bw_wa = skl_needs_memory_bw_wa(state);
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ u32 interm_pbpl;
- if (!intel_wm_plane_visible(cstate, intel_pstate))
- return 0;
-
- /* only NV12 format has two planes */
- if (plane_id == 1 && fb->format->format != DRM_FORMAT_NV12) {
- DRM_DEBUG_KMS("Non NV12 format have single plane\n");
+ /* only planar format has two planes */
+ if (color_plane == 1 &&
+ !intel_format_info_is_yuv_semiplanar(format, modifier)) {
+ drm_dbg_kms(&dev_priv->drm,
+ "Non planar format have single plane\n");
return -EINVAL;
}
- wp->y_tiled = fb->modifier == I915_FORMAT_MOD_Y_TILED ||
- fb->modifier == I915_FORMAT_MOD_Yf_TILED ||
- fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
- fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
- wp->x_tiled = fb->modifier == I915_FORMAT_MOD_X_TILED;
- wp->rc_surface = fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
- fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
- wp->is_planar = fb->format->format == DRM_FORMAT_NV12;
+ wp->y_tiled = modifier == I915_FORMAT_MOD_Y_TILED ||
+ modifier == I915_FORMAT_MOD_Yf_TILED ||
+ modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+ modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
+ modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+ modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS;
+ wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED;
+ wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+ modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
+ modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+ modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS;
+ wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);
- if (plane->id == PLANE_CURSOR) {
- wp->width = intel_pstate->base.crtc_w;
- } else {
- /*
- * Src coordinates are already rotated by 270 degrees for
- * the 90/270 degree plane rotation cases (to match the
- * GTT mapping), hence no need to account for rotation here.
- */
- wp->width = drm_rect_width(&intel_pstate->base.src) >> 16;
- }
-
- if (plane_id == 1 && wp->is_planar)
+ wp->width = width;
+ if (color_plane == 1 && wp->is_planar)
wp->width /= 2;
- wp->cpp = fb->format->cpp[plane_id];
- wp->plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate,
- intel_pstate);
+ wp->cpp = format->cpp[color_plane];
+ wp->plane_pixel_rate = plane_pixel_rate;
if (INTEL_GEN(dev_priv) >= 11 &&
- fb->modifier == I915_FORMAT_MOD_Yf_TILED && wp->cpp == 8)
+ modifier == I915_FORMAT_MOD_Yf_TILED && wp->cpp == 1)
wp->dbuf_block_size = 256;
else
wp->dbuf_block_size = 512;
- if (drm_rotation_90_or_270(pstate->rotation)) {
-
+ if (drm_rotation_90_or_270(rotation)) {
switch (wp->cpp) {
case 1:
wp->y_min_scanlines = 16;
@@ -4600,7 +5187,7 @@
wp->y_min_scanlines = 4;
}
- if (apply_memory_bw_wa)
+ if (skl_needs_memory_bw_wa(dev_priv))
wp->y_min_scanlines *= 2;
wp->plane_bytes_per_line = wp->width * wp->cpp;
@@ -4609,320 +5196,403 @@
wp->y_min_scanlines,
wp->dbuf_block_size);
- if (INTEL_GEN(dev_priv) >= 10)
+ if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
interm_pbpl++;
wp->plane_blocks_per_line = div_fixed16(interm_pbpl,
wp->y_min_scanlines);
- } else if (wp->x_tiled && IS_GEN9(dev_priv)) {
- interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line,
- wp->dbuf_block_size);
- wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
} else {
interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line,
- wp->dbuf_block_size) + 1;
+ wp->dbuf_block_size);
+
+ if (!wp->x_tiled ||
+ INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+ interm_pbpl++;
+
wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
}
wp->y_tile_minimum = mul_u32_fixed16(wp->y_min_scanlines,
wp->plane_blocks_per_line);
+
wp->linetime_us = fixed16_to_u32_round_up(
- intel_get_linetime_us(cstate));
+ intel_get_linetime_us(crtc_state));
return 0;
}
-static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
- struct intel_crtc_state *cstate,
- const struct intel_plane_state *intel_pstate,
- uint16_t ddb_allocation,
- int level,
- const struct skl_wm_params *wp,
- const struct skl_wm_level *result_prev,
- struct skl_wm_level *result /* out */)
+static int
+skl_compute_plane_wm_params(const struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ struct skl_wm_params *wp, int color_plane)
{
- const struct drm_plane_state *pstate = &intel_pstate->base;
- uint32_t latency = dev_priv->wm.skl_latency[level];
+ const struct drm_framebuffer *fb = plane_state->hw.fb;
+ int width;
+
+ /*
+ * Src coordinates are already rotated by 270 degrees for
+ * the 90/270 degree plane rotation cases (to match the
+ * GTT mapping), hence no need to account for rotation here.
+ */
+ width = drm_rect_width(&plane_state->uapi.src) >> 16;
+
+ return skl_compute_wm_params(crtc_state, width,
+ fb->format, fb->modifier,
+ plane_state->hw.rotation,
+ skl_adjusted_plane_pixel_rate(crtc_state, plane_state),
+ wp, color_plane);
+}
+
+static bool skl_wm_has_lines(struct drm_i915_private *dev_priv, int level)
+{
+ if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+ return true;
+
+ /* The number of lines are ignored for the level 0 watermark. */
+ return level > 0;
+}
+
+static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
+ int level,
+ unsigned int latency,
+ const struct skl_wm_params *wp,
+ const struct skl_wm_level *result_prev,
+ struct skl_wm_level *result /* out */)
+{
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
uint_fixed_16_16_t method1, method2;
uint_fixed_16_16_t selected_result;
- uint32_t res_blocks, res_lines;
- struct intel_atomic_state *state =
- to_intel_atomic_state(cstate->base.state);
- bool apply_memory_bw_wa = skl_needs_memory_bw_wa(state);
- uint32_t min_disp_buf_needed;
+ u32 res_blocks, res_lines, min_ddb_alloc = 0;
- if (latency == 0 ||
- !intel_wm_plane_visible(cstate, intel_pstate)) {
- result->plane_en = false;
- return 0;
+ if (latency == 0) {
+ /* reject it */
+ result->min_ddb_alloc = U16_MAX;
+ return;
}
- /* Display WA #1141: kbl,cfl */
- if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv) ||
- IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_B0)) &&
+ /*
+ * WaIncreaseLatencyIPCEnabled: kbl,cfl
+ * Display WA #1141: kbl,cfl
+ */
+ if ((IS_KABYLAKE(dev_priv) ||
+ IS_COFFEELAKE(dev_priv) ||
+ IS_COMETLAKE(dev_priv)) &&
dev_priv->ipc_enabled)
latency += 4;
- if (apply_memory_bw_wa && wp->x_tiled)
+ if (skl_needs_memory_bw_wa(dev_priv) && wp->x_tiled)
latency += 15;
method1 = skl_wm_method1(dev_priv, wp->plane_pixel_rate,
wp->cpp, latency, wp->dbuf_block_size);
method2 = skl_wm_method2(wp->plane_pixel_rate,
- cstate->base.adjusted_mode.crtc_htotal,
+ crtc_state->hw.adjusted_mode.crtc_htotal,
latency,
wp->plane_blocks_per_line);
if (wp->y_tiled) {
selected_result = max_fixed16(method2, wp->y_tile_minimum);
} else {
- if ((wp->cpp * cstate->base.adjusted_mode.crtc_htotal /
+ if ((wp->cpp * crtc_state->hw.adjusted_mode.crtc_htotal /
wp->dbuf_block_size < 1) &&
- (wp->plane_bytes_per_line / wp->dbuf_block_size < 1))
+ (wp->plane_bytes_per_line / wp->dbuf_block_size < 1)) {
selected_result = method2;
- else if (ddb_allocation >=
- fixed16_to_u32_round_up(wp->plane_blocks_per_line))
- selected_result = min_fixed16(method1, method2);
- else if (latency >= wp->linetime_us)
- selected_result = min_fixed16(method1, method2);
- else
+ } else if (latency >= wp->linetime_us) {
+ if (IS_GEN(dev_priv, 9) &&
+ !IS_GEMINILAKE(dev_priv))
+ selected_result = min_fixed16(method1, method2);
+ else
+ selected_result = method2;
+ } else {
selected_result = method1;
+ }
}
res_blocks = fixed16_to_u32_round_up(selected_result) + 1;
res_lines = div_round_up_fixed16(selected_result,
wp->plane_blocks_per_line);
- /* Display WA #1125: skl,bxt,kbl,glk */
- if (level == 0 && wp->rc_surface)
- res_blocks += fixed16_to_u32_round_up(wp->y_tile_minimum);
+ if (IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) {
+ /* Display WA #1125: skl,bxt,kbl */
+ if (level == 0 && wp->rc_surface)
+ res_blocks +=
+ fixed16_to_u32_round_up(wp->y_tile_minimum);
- /* Display WA #1126: skl,bxt,kbl,glk */
- if (level >= 1 && level <= 7) {
- if (wp->y_tiled) {
- res_blocks += fixed16_to_u32_round_up(
- wp->y_tile_minimum);
- res_lines += wp->y_min_scanlines;
- } else {
- res_blocks++;
+ /* Display WA #1126: skl,bxt,kbl */
+ if (level >= 1 && level <= 7) {
+ if (wp->y_tiled) {
+ res_blocks +=
+ fixed16_to_u32_round_up(wp->y_tile_minimum);
+ res_lines += wp->y_min_scanlines;
+ } else {
+ res_blocks++;
+ }
+
+ /*
+ * Make sure result blocks for higher latency levels are
+ * atleast as high as level below the current level.
+ * Assumption in DDB algorithm optimization for special
+ * cases. Also covers Display WA #1125 for RC.
+ */
+ if (result_prev->plane_res_b > res_blocks)
+ res_blocks = result_prev->plane_res_b;
}
-
- /*
- * Make sure result blocks for higher latency levels are atleast
- * as high as level below the current level.
- * Assumption in DDB algorithm optimization for special cases.
- * Also covers Display WA #1125 for RC.
- */
- if (result_prev->plane_res_b > res_blocks)
- res_blocks = result_prev->plane_res_b;
}
if (INTEL_GEN(dev_priv) >= 11) {
if (wp->y_tiled) {
- uint32_t extra_lines;
- uint_fixed_16_16_t fp_min_disp_buf_needed;
+ int extra_lines;
if (res_lines % wp->y_min_scanlines == 0)
extra_lines = wp->y_min_scanlines;
else
extra_lines = wp->y_min_scanlines * 2 -
- res_lines % wp->y_min_scanlines;
+ res_lines % wp->y_min_scanlines;
- fp_min_disp_buf_needed = mul_u32_fixed16(res_lines +
- extra_lines,
- wp->plane_blocks_per_line);
- min_disp_buf_needed = fixed16_to_u32_round_up(
- fp_min_disp_buf_needed);
+ min_ddb_alloc = mul_round_up_u32_fixed16(res_lines + extra_lines,
+ wp->plane_blocks_per_line);
} else {
- min_disp_buf_needed = DIV_ROUND_UP(res_blocks * 11, 10);
+ min_ddb_alloc = res_blocks +
+ DIV_ROUND_UP(res_blocks, 10);
}
- } else {
- min_disp_buf_needed = res_blocks;
}
- if ((level > 0 && res_lines > 31) ||
- res_blocks >= ddb_allocation ||
- min_disp_buf_needed >= ddb_allocation) {
- result->plane_en = false;
+ if (!skl_wm_has_lines(dev_priv, level))
+ res_lines = 0;
- /*
- * If there are no valid level 0 watermarks, then we can't
- * support this display configuration.
- */
- if (level) {
- return 0;
- } else {
- struct drm_plane *plane = pstate->plane;
-
- DRM_DEBUG_KMS("Requested display configuration exceeds system watermark limitations\n");
- DRM_DEBUG_KMS("[PLANE:%d:%s] blocks required = %u/%u, lines required = %u/31\n",
- plane->base.id, plane->name,
- res_blocks, ddb_allocation, res_lines);
- return -EINVAL;
- }
+ if (res_lines > 31) {
+ /* reject it */
+ result->min_ddb_alloc = U16_MAX;
+ return;
}
/*
- * Display WA #826 (SKL:ALL, BXT:ALL) & #1059 (CNL:A)
- * disable wm level 1-7 on NV12 planes
+ * If res_lines is valid, assume we can use this watermark level
+ * for now. We'll come back and disable it after we calculate the
+ * DDB allocation if it turns out we don't actually have enough
+ * blocks to satisfy it.
*/
- if (wp->is_planar && level >= 1 &&
- (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv) ||
- IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_A0))) {
- result->plane_en = false;
- return 0;
- }
-
- /* The number of lines are ignored for the level 0 watermark. */
result->plane_res_b = res_blocks;
result->plane_res_l = res_lines;
+ /* Bspec says: value >= plane ddb allocation -> invalid, hence the +1 here */
+ result->min_ddb_alloc = max(min_ddb_alloc, res_blocks) + 1;
result->plane_en = true;
+}
+
+static void
+skl_compute_wm_levels(const struct intel_crtc_state *crtc_state,
+ const struct skl_wm_params *wm_params,
+ struct skl_wm_level *levels)
+{
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+ int level, max_level = ilk_wm_max_level(dev_priv);
+ struct skl_wm_level *result_prev = &levels[0];
+
+ for (level = 0; level <= max_level; level++) {
+ struct skl_wm_level *result = &levels[level];
+ unsigned int latency = dev_priv->wm.skl_latency[level];
+
+ skl_compute_plane_wm(crtc_state, level, latency,
+ wm_params, result_prev, result);
+
+ result_prev = result;
+ }
+}
+
+static void tgl_compute_sagv_wm(const struct intel_crtc_state *crtc_state,
+ const struct skl_wm_params *wm_params,
+ struct skl_plane_wm *plane_wm)
+{
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+ struct skl_wm_level *sagv_wm = &plane_wm->sagv_wm0;
+ struct skl_wm_level *levels = plane_wm->wm;
+ unsigned int latency = dev_priv->wm.skl_latency[0] + dev_priv->sagv_block_time_us;
+
+ skl_compute_plane_wm(crtc_state, 0, latency,
+ wm_params, &levels[0],
+ sagv_wm);
+}
+
+static void skl_compute_transition_wm(const struct intel_crtc_state *crtc_state,
+ const struct skl_wm_params *wp,
+ struct skl_plane_wm *wm)
+{
+ struct drm_device *dev = crtc_state->uapi.crtc->dev;
+ const struct drm_i915_private *dev_priv = to_i915(dev);
+ u16 trans_min, trans_amount, trans_y_tile_min;
+ u16 wm0_sel_res_b, trans_offset_b, res_blocks;
+
+ /* Transition WM don't make any sense if ipc is disabled */
+ if (!dev_priv->ipc_enabled)
+ return;
+
+ /*
+ * WaDisableTWM:skl,kbl,cfl,bxt
+ * Transition WM are not recommended by HW team for GEN9
+ */
+ if (IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv))
+ return;
+
+ if (INTEL_GEN(dev_priv) >= 11)
+ trans_min = 4;
+ else
+ trans_min = 14;
+
+ /* Display WA #1140: glk,cnl */
+ if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+ trans_amount = 0;
+ else
+ trans_amount = 10; /* This is configurable amount */
+
+ trans_offset_b = trans_min + trans_amount;
+
+ /*
+ * The spec asks for Selected Result Blocks for wm0 (the real value),
+ * not Result Blocks (the integer value). Pay attention to the capital
+ * letters. The value wm_l0->plane_res_b is actually Result Blocks, but
+ * since Result Blocks is the ceiling of Selected Result Blocks plus 1,
+ * and since we later will have to get the ceiling of the sum in the
+ * transition watermarks calculation, we can just pretend Selected
+ * Result Blocks is Result Blocks minus 1 and it should work for the
+ * current platforms.
+ */
+ wm0_sel_res_b = wm->wm[0].plane_res_b - 1;
+
+ if (wp->y_tiled) {
+ trans_y_tile_min =
+ (u16)mul_round_up_u32_fixed16(2, wp->y_tile_minimum);
+ res_blocks = max(wm0_sel_res_b, trans_y_tile_min) +
+ trans_offset_b;
+ } else {
+ res_blocks = wm0_sel_res_b + trans_offset_b;
+ }
+
+ /*
+ * Just assume we can enable the transition watermark. After
+ * computing the DDB we'll come back and disable it if that
+ * assumption turns out to be false.
+ */
+ wm->trans_wm.plane_res_b = res_blocks + 1;
+ wm->trans_wm.plane_en = true;
+}
+
+static int skl_build_plane_wm_single(struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ enum plane_id plane_id, int color_plane)
+{
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ struct skl_plane_wm *wm = &crtc_state->wm.skl.optimal.planes[plane_id];
+ struct skl_wm_params wm_params;
+ int ret;
+
+ ret = skl_compute_plane_wm_params(crtc_state, plane_state,
+ &wm_params, color_plane);
+ if (ret)
+ return ret;
+
+ skl_compute_wm_levels(crtc_state, &wm_params, wm->wm);
+
+ if (INTEL_GEN(dev_priv) >= 12)
+ tgl_compute_sagv_wm(crtc_state, &wm_params, wm);
+
+ skl_compute_transition_wm(crtc_state, &wm_params, wm);
return 0;
}
-static int
-skl_compute_wm_levels(const struct drm_i915_private *dev_priv,
- struct skl_ddb_allocation *ddb,
- struct intel_crtc_state *cstate,
- const struct intel_plane_state *intel_pstate,
- const struct skl_wm_params *wm_params,
- struct skl_plane_wm *wm,
- int plane_id)
+static int skl_build_plane_wm_uv(struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state,
+ enum plane_id plane_id)
{
- struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
- struct drm_plane *plane = intel_pstate->base.plane;
- struct intel_plane *intel_plane = to_intel_plane(plane);
- uint16_t ddb_blocks;
- enum pipe pipe = intel_crtc->pipe;
- int level, max_level = ilk_wm_max_level(dev_priv);
- enum plane_id intel_plane_id = intel_plane->id;
+ struct skl_plane_wm *wm = &crtc_state->wm.skl.optimal.planes[plane_id];
+ struct skl_wm_params wm_params;
int ret;
- if (WARN_ON(!intel_pstate->base.fb))
- return -EINVAL;
+ wm->is_planar = true;
- ddb_blocks = plane_id ?
- skl_ddb_entry_size(&ddb->uv_plane[pipe][intel_plane_id]) :
- skl_ddb_entry_size(&ddb->plane[pipe][intel_plane_id]);
+ /* uv plane watermarks must also be validated for NV12/Planar */
+ ret = skl_compute_plane_wm_params(crtc_state, plane_state,
+ &wm_params, 1);
+ if (ret)
+ return ret;
- for (level = 0; level <= max_level; level++) {
- struct skl_wm_level *result = plane_id ? &wm->uv_wm[level] :
- &wm->wm[level];
- struct skl_wm_level *result_prev;
+ skl_compute_wm_levels(crtc_state, &wm_params, wm->uv_wm);
- if (level)
- result_prev = plane_id ? &wm->uv_wm[level - 1] :
- &wm->wm[level - 1];
- else
- result_prev = plane_id ? &wm->uv_wm[0] : &wm->wm[0];
+ return 0;
+}
- ret = skl_compute_plane_wm(dev_priv,
- cstate,
- intel_pstate,
- ddb_blocks,
- level,
- wm_params,
- result_prev,
- result);
+static int skl_build_plane_wm(struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state)
+{
+ struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+ const struct drm_framebuffer *fb = plane_state->hw.fb;
+ enum plane_id plane_id = plane->id;
+ int ret;
+
+ if (!intel_wm_plane_visible(crtc_state, plane_state))
+ return 0;
+
+ ret = skl_build_plane_wm_single(crtc_state, plane_state,
+ plane_id, 0);
+ if (ret)
+ return ret;
+
+ if (fb->format->is_yuv && fb->format->num_planes > 1) {
+ ret = skl_build_plane_wm_uv(crtc_state, plane_state,
+ plane_id);
if (ret)
return ret;
}
- if (intel_pstate->base.fb->format->format == DRM_FORMAT_NV12)
- wm->is_planar = true;
+ return 0;
+}
+
+static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
+ const struct intel_plane_state *plane_state)
+{
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+ enum plane_id plane_id = to_intel_plane(plane_state->uapi.plane)->id;
+ int ret;
+
+ /* Watermarks calculated in master */
+ if (plane_state->planar_slave)
+ return 0;
+
+ if (plane_state->planar_linked_plane) {
+ const struct drm_framebuffer *fb = plane_state->hw.fb;
+ enum plane_id y_plane_id = plane_state->planar_linked_plane->id;
+
+ drm_WARN_ON(&dev_priv->drm,
+ !intel_wm_plane_visible(crtc_state, plane_state));
+ drm_WARN_ON(&dev_priv->drm, !fb->format->is_yuv ||
+ fb->format->num_planes == 1);
+
+ ret = skl_build_plane_wm_single(crtc_state, plane_state,
+ y_plane_id, 0);
+ if (ret)
+ return ret;
+
+ ret = skl_build_plane_wm_single(crtc_state, plane_state,
+ plane_id, 1);
+ if (ret)
+ return ret;
+ } else if (intel_wm_plane_visible(crtc_state, plane_state)) {
+ ret = skl_build_plane_wm_single(crtc_state, plane_state,
+ plane_id, 0);
+ if (ret)
+ return ret;
+ }
return 0;
}
-static uint32_t
-skl_compute_linetime_wm(struct intel_crtc_state *cstate)
+static int skl_build_pipe_wm(struct intel_crtc_state *crtc_state)
{
- struct drm_atomic_state *state = cstate->base.state;
- struct drm_i915_private *dev_priv = to_i915(state->dev);
- uint_fixed_16_16_t linetime_us;
- uint32_t linetime_wm;
-
- linetime_us = intel_get_linetime_us(cstate);
-
- if (is_fixed16_zero(linetime_us))
- return 0;
-
- linetime_wm = fixed16_to_u32_round_up(mul_u32_fixed16(8, linetime_us));
-
- /* Display WA #1135: bxt:ALL GLK:ALL */
- if ((IS_BROXTON(dev_priv) || IS_GEMINILAKE(dev_priv)) &&
- dev_priv->ipc_enabled)
- linetime_wm /= 2;
-
- return linetime_wm;
-}
-
-static void skl_compute_transition_wm(struct intel_crtc_state *cstate,
- struct skl_wm_params *wp,
- struct skl_wm_level *wm_l0,
- uint16_t ddb_allocation,
- struct skl_wm_level *trans_wm /* out */)
-{
- struct drm_device *dev = cstate->base.crtc->dev;
- const struct drm_i915_private *dev_priv = to_i915(dev);
- uint16_t trans_min, trans_y_tile_min;
- const uint16_t trans_amount = 10; /* This is configurable amount */
- uint16_t trans_offset_b, res_blocks;
-
- if (!cstate->base.active)
- goto exit;
-
- /* Transition WM are not recommended by HW team for GEN9 */
- if (INTEL_GEN(dev_priv) <= 9)
- goto exit;
-
- /* Transition WM don't make any sense if ipc is disabled */
- if (!dev_priv->ipc_enabled)
- goto exit;
-
- trans_min = 0;
- if (INTEL_GEN(dev_priv) >= 10)
- trans_min = 4;
-
- trans_offset_b = trans_min + trans_amount;
-
- if (wp->y_tiled) {
- trans_y_tile_min = (uint16_t) mul_round_up_u32_fixed16(2,
- wp->y_tile_minimum);
- res_blocks = max(wm_l0->plane_res_b, trans_y_tile_min) +
- trans_offset_b;
- } else {
- res_blocks = wm_l0->plane_res_b + trans_offset_b;
-
- /* WA BUG:1938466 add one block for non y-tile planes */
- if (IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_A0))
- res_blocks += 1;
-
- }
-
- res_blocks += 1;
-
- if (res_blocks < ddb_allocation) {
- trans_wm->plane_res_b = res_blocks;
- trans_wm->plane_en = true;
- return;
- }
-
-exit:
- trans_wm->plane_en = false;
-}
-
-static int skl_build_pipe_wm(struct intel_crtc_state *cstate,
- struct skl_ddb_allocation *ddb,
- struct skl_pipe_wm *pipe_wm)
-{
- struct drm_device *dev = cstate->base.crtc->dev;
- struct drm_crtc_state *crtc_state = &cstate->base;
- const struct drm_i915_private *dev_priv = to_i915(dev);
- struct drm_plane *plane;
- const struct drm_plane_state *pstate;
- struct skl_plane_wm *wm;
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+ struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
+ struct intel_plane *plane;
+ const struct intel_plane_state *plane_state;
int ret;
/*
@@ -4931,50 +5601,16 @@
*/
memset(pipe_wm->planes, 0, sizeof(pipe_wm->planes));
- drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) {
- const struct intel_plane_state *intel_pstate =
- to_intel_plane_state(pstate);
- enum plane_id plane_id = to_intel_plane(plane)->id;
- struct skl_wm_params wm_params;
- enum pipe pipe = to_intel_crtc(cstate->base.crtc)->pipe;
- uint16_t ddb_blocks;
+ intel_atomic_crtc_state_for_each_plane_state(plane, plane_state,
+ crtc_state) {
- wm = &pipe_wm->planes[plane_id];
- ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][plane_id]);
-
- ret = skl_compute_plane_wm_params(dev_priv, cstate,
- intel_pstate, &wm_params, 0);
+ if (INTEL_GEN(dev_priv) >= 11)
+ ret = icl_build_plane_wm(crtc_state, plane_state);
+ else
+ ret = skl_build_plane_wm(crtc_state, plane_state);
if (ret)
return ret;
-
- ret = skl_compute_wm_levels(dev_priv, ddb, cstate,
- intel_pstate, &wm_params, wm, 0);
- if (ret)
- return ret;
-
- skl_compute_transition_wm(cstate, &wm_params, &wm->wm[0],
- ddb_blocks, &wm->trans_wm);
-
- /* uv plane watermarks must also be validated for NV12/Planar */
- if (wm_params.is_planar) {
- memset(&wm_params, 0, sizeof(struct skl_wm_params));
- wm->is_planar = true;
-
- ret = skl_compute_plane_wm_params(dev_priv, cstate,
- intel_pstate,
- &wm_params, 1);
- if (ret)
- return ret;
-
- ret = skl_compute_wm_levels(dev_priv, ddb, cstate,
- intel_pstate, &wm_params,
- wm, 1);
- if (ret)
- return ret;
- }
}
-
- pipe_wm->linetime = skl_compute_linetime_wm(cstate);
return 0;
}
@@ -4984,400 +5620,519 @@
const struct skl_ddb_entry *entry)
{
if (entry->end)
- I915_WRITE(reg, (entry->end - 1) << 16 | entry->start);
+ intel_de_write_fw(dev_priv, reg,
+ (entry->end - 1) << 16 | entry->start);
else
- I915_WRITE(reg, 0);
+ intel_de_write_fw(dev_priv, reg, 0);
}
static void skl_write_wm_level(struct drm_i915_private *dev_priv,
i915_reg_t reg,
const struct skl_wm_level *level)
{
- uint32_t val = 0;
+ u32 val = 0;
- if (level->plane_en) {
+ if (level->plane_en)
val |= PLANE_WM_EN;
- val |= level->plane_res_b;
- val |= level->plane_res_l << PLANE_WM_LINES_SHIFT;
- }
+ if (level->ignore_lines)
+ val |= PLANE_WM_IGNORE_LINES;
+ val |= level->plane_res_b;
+ val |= level->plane_res_l << PLANE_WM_LINES_SHIFT;
- I915_WRITE(reg, val);
+ intel_de_write_fw(dev_priv, reg, val);
}
-static void skl_write_plane_wm(struct intel_crtc *intel_crtc,
- const struct skl_plane_wm *wm,
- const struct skl_ddb_allocation *ddb,
- enum plane_id plane_id)
+void skl_write_plane_wm(struct intel_plane *plane,
+ const struct intel_crtc_state *crtc_state)
{
- struct drm_crtc *crtc = &intel_crtc->base;
- struct drm_device *dev = crtc->dev;
- struct drm_i915_private *dev_priv = to_i915(dev);
+ struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
int level, max_level = ilk_wm_max_level(dev_priv);
- enum pipe pipe = intel_crtc->pipe;
+ enum plane_id plane_id = plane->id;
+ enum pipe pipe = plane->pipe;
+ const struct skl_plane_wm *wm =
+ &crtc_state->wm.skl.optimal.planes[plane_id];
+ const struct skl_ddb_entry *ddb_y =
+ &crtc_state->wm.skl.plane_ddb_y[plane_id];
+ const struct skl_ddb_entry *ddb_uv =
+ &crtc_state->wm.skl.plane_ddb_uv[plane_id];
for (level = 0; level <= max_level; level++) {
+ const struct skl_wm_level *wm_level;
+
+ wm_level = skl_plane_wm_level(crtc_state, plane_id, level);
+
skl_write_wm_level(dev_priv, PLANE_WM(pipe, plane_id, level),
- &wm->wm[level]);
+ wm_level);
}
skl_write_wm_level(dev_priv, PLANE_WM_TRANS(pipe, plane_id),
&wm->trans_wm);
- skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
- &ddb->plane[pipe][plane_id]);
- if (INTEL_GEN(dev_priv) >= 11)
- return skl_ddb_entry_write(dev_priv,
- PLANE_BUF_CFG(pipe, plane_id),
- &ddb->plane[pipe][plane_id]);
- if (wm->is_planar) {
- skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
- &ddb->uv_plane[pipe][plane_id]);
+ if (INTEL_GEN(dev_priv) >= 11) {
skl_ddb_entry_write(dev_priv,
- PLANE_NV12_BUF_CFG(pipe, plane_id),
- &ddb->plane[pipe][plane_id]);
- } else {
- skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
- &ddb->plane[pipe][plane_id]);
- I915_WRITE(PLANE_NV12_BUF_CFG(pipe, plane_id), 0x0);
+ PLANE_BUF_CFG(pipe, plane_id), ddb_y);
+ return;
}
+
+ if (wm->is_planar)
+ swap(ddb_y, ddb_uv);
+
+ skl_ddb_entry_write(dev_priv,
+ PLANE_BUF_CFG(pipe, plane_id), ddb_y);
+ skl_ddb_entry_write(dev_priv,
+ PLANE_NV12_BUF_CFG(pipe, plane_id), ddb_uv);
}
-static void skl_write_cursor_wm(struct intel_crtc *intel_crtc,
- const struct skl_plane_wm *wm,
- const struct skl_ddb_allocation *ddb)
+void skl_write_cursor_wm(struct intel_plane *plane,
+ const struct intel_crtc_state *crtc_state)
{
- struct drm_crtc *crtc = &intel_crtc->base;
- struct drm_device *dev = crtc->dev;
- struct drm_i915_private *dev_priv = to_i915(dev);
+ struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
int level, max_level = ilk_wm_max_level(dev_priv);
- enum pipe pipe = intel_crtc->pipe;
+ enum plane_id plane_id = plane->id;
+ enum pipe pipe = plane->pipe;
+ const struct skl_plane_wm *wm =
+ &crtc_state->wm.skl.optimal.planes[plane_id];
+ const struct skl_ddb_entry *ddb =
+ &crtc_state->wm.skl.plane_ddb_y[plane_id];
for (level = 0; level <= max_level; level++) {
+ const struct skl_wm_level *wm_level;
+
+ wm_level = skl_plane_wm_level(crtc_state, plane_id, level);
+
skl_write_wm_level(dev_priv, CUR_WM(pipe, level),
- &wm->wm[level]);
+ wm_level);
}
skl_write_wm_level(dev_priv, CUR_WM_TRANS(pipe), &wm->trans_wm);
- skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe),
- &ddb->plane[pipe][PLANE_CURSOR]);
+ skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe), ddb);
}
bool skl_wm_level_equals(const struct skl_wm_level *l1,
const struct skl_wm_level *l2)
{
- if (l1->plane_en != l2->plane_en)
- return false;
-
- /* If both planes aren't enabled, the rest shouldn't matter */
- if (!l1->plane_en)
- return true;
-
- return (l1->plane_res_l == l2->plane_res_l &&
- l1->plane_res_b == l2->plane_res_b);
+ return l1->plane_en == l2->plane_en &&
+ l1->ignore_lines == l2->ignore_lines &&
+ l1->plane_res_l == l2->plane_res_l &&
+ l1->plane_res_b == l2->plane_res_b;
}
-static inline bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a,
- const struct skl_ddb_entry *b)
+static bool skl_plane_wm_equals(struct drm_i915_private *dev_priv,
+ const struct skl_plane_wm *wm1,
+ const struct skl_plane_wm *wm2)
+{
+ int level, max_level = ilk_wm_max_level(dev_priv);
+
+ for (level = 0; level <= max_level; level++) {
+ /*
+ * We don't check uv_wm as the hardware doesn't actually
+ * use it. It only gets used for calculating the required
+ * ddb allocation.
+ */
+ if (!skl_wm_level_equals(&wm1->wm[level], &wm2->wm[level]))
+ return false;
+ }
+
+ return skl_wm_level_equals(&wm1->trans_wm, &wm2->trans_wm);
+}
+
+static bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a,
+ const struct skl_ddb_entry *b)
{
return a->start < b->end && b->start < a->end;
}
-bool skl_ddb_allocation_overlaps(struct drm_i915_private *dev_priv,
- const struct skl_ddb_entry **entries,
- const struct skl_ddb_entry *ddb,
- int ignore)
+bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb,
+ const struct skl_ddb_entry *entries,
+ int num_entries, int ignore_idx)
{
- enum pipe pipe;
+ int i;
- for_each_pipe(dev_priv, pipe) {
- if (pipe != ignore && entries[pipe] &&
- skl_ddb_entries_overlap(ddb, entries[pipe]))
+ for (i = 0; i < num_entries; i++) {
+ if (i != ignore_idx &&
+ skl_ddb_entries_overlap(ddb, &entries[i]))
return true;
}
return false;
}
-static int skl_update_pipe_wm(struct drm_crtc_state *cstate,
- const struct skl_pipe_wm *old_pipe_wm,
- struct skl_pipe_wm *pipe_wm, /* out */
- struct skl_ddb_allocation *ddb, /* out */
- bool *changed /* out */)
-{
- struct intel_crtc_state *intel_cstate = to_intel_crtc_state(cstate);
- int ret;
-
- ret = skl_build_pipe_wm(intel_cstate, ddb, pipe_wm);
- if (ret)
- return ret;
-
- if (!memcmp(old_pipe_wm, pipe_wm, sizeof(*pipe_wm)))
- *changed = false;
- else
- *changed = true;
-
- return 0;
-}
-
-static uint32_t
-pipes_modified(struct drm_atomic_state *state)
-{
- struct drm_crtc *crtc;
- struct drm_crtc_state *cstate;
- uint32_t i, ret = 0;
-
- for_each_new_crtc_in_state(state, crtc, cstate, i)
- ret |= drm_crtc_mask(crtc);
-
- return ret;
-}
-
static int
-skl_ddb_add_affected_planes(struct intel_crtc_state *cstate)
+skl_ddb_add_affected_planes(const struct intel_crtc_state *old_crtc_state,
+ struct intel_crtc_state *new_crtc_state)
{
- struct drm_atomic_state *state = cstate->base.state;
- struct drm_device *dev = state->dev;
- struct drm_crtc *crtc = cstate->base.crtc;
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- struct drm_i915_private *dev_priv = to_i915(dev);
- struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
- struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb;
- struct skl_ddb_allocation *cur_ddb = &dev_priv->wm.skl_hw.ddb;
- struct drm_plane_state *plane_state;
- struct drm_plane *plane;
- enum pipe pipe = intel_crtc->pipe;
+ struct intel_atomic_state *state = to_intel_atomic_state(new_crtc_state->uapi.state);
+ struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ struct intel_plane *plane;
- drm_for_each_plane_mask(plane, dev, cstate->base.plane_mask) {
- enum plane_id plane_id = to_intel_plane(plane)->id;
+ for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
+ struct intel_plane_state *plane_state;
+ enum plane_id plane_id = plane->id;
- if (skl_ddb_entry_equal(&cur_ddb->plane[pipe][plane_id],
- &new_ddb->plane[pipe][plane_id]) &&
- skl_ddb_entry_equal(&cur_ddb->uv_plane[pipe][plane_id],
- &new_ddb->uv_plane[pipe][plane_id]))
+ if (skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb_y[plane_id],
+ &new_crtc_state->wm.skl.plane_ddb_y[plane_id]) &&
+ skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb_uv[plane_id],
+ &new_crtc_state->wm.skl.plane_ddb_uv[plane_id]))
continue;
- plane_state = drm_atomic_get_plane_state(state, plane);
+ plane_state = intel_atomic_get_plane_state(state, plane);
if (IS_ERR(plane_state))
return PTR_ERR(plane_state);
+
+ new_crtc_state->update_planes |= BIT(plane_id);
}
return 0;
}
static int
-skl_compute_ddb(struct drm_atomic_state *state)
+skl_compute_ddb(struct intel_atomic_state *state)
{
- const struct drm_i915_private *dev_priv = to_i915(state->dev);
- struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
- struct skl_ddb_allocation *ddb = &intel_state->wm_results.ddb;
+ struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+ const struct intel_dbuf_state *old_dbuf_state;
+ const struct intel_dbuf_state *new_dbuf_state;
+ const struct intel_crtc_state *old_crtc_state;
+ struct intel_crtc_state *new_crtc_state;
struct intel_crtc *crtc;
- struct intel_crtc_state *cstate;
int ret, i;
- memcpy(ddb, &dev_priv->wm.skl_hw.ddb, sizeof(*ddb));
-
- for_each_new_intel_crtc_in_state(intel_state, crtc, cstate, i) {
- ret = skl_allocate_pipe_ddb(cstate, ddb);
+ for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+ new_crtc_state, i) {
+ ret = skl_allocate_pipe_ddb(new_crtc_state);
if (ret)
return ret;
- ret = skl_ddb_add_affected_planes(cstate);
+ ret = skl_ddb_add_affected_planes(old_crtc_state,
+ new_crtc_state);
if (ret)
return ret;
}
+ old_dbuf_state = intel_atomic_get_old_dbuf_state(state);
+ new_dbuf_state = intel_atomic_get_new_dbuf_state(state);
+
+ if (new_dbuf_state &&
+ new_dbuf_state->enabled_slices != old_dbuf_state->enabled_slices)
+ drm_dbg_kms(&dev_priv->drm,
+ "Enabled dbuf slices 0x%x -> 0x%x (out of %d dbuf slices)\n",
+ old_dbuf_state->enabled_slices,
+ new_dbuf_state->enabled_slices,
+ INTEL_INFO(dev_priv)->num_supported_dbuf_slices);
+
return 0;
}
-static void
-skl_copy_ddb_for_pipe(struct skl_ddb_values *dst,
- struct skl_ddb_values *src,
- enum pipe pipe)
+static char enast(bool enable)
{
- memcpy(dst->ddb.uv_plane[pipe], src->ddb.uv_plane[pipe],
- sizeof(dst->ddb.uv_plane[pipe]));
- memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe],
- sizeof(dst->ddb.plane[pipe]));
+ return enable ? '*' : ' ';
}
static void
-skl_print_wm_changes(const struct drm_atomic_state *state)
+skl_print_wm_changes(struct intel_atomic_state *state)
{
- const struct drm_device *dev = state->dev;
- const struct drm_i915_private *dev_priv = to_i915(dev);
- const struct intel_atomic_state *intel_state =
- to_intel_atomic_state(state);
- const struct drm_crtc *crtc;
- const struct drm_crtc_state *cstate;
- const struct intel_plane *intel_plane;
- const struct skl_ddb_allocation *old_ddb = &dev_priv->wm.skl_hw.ddb;
- const struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb;
+ struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+ const struct intel_crtc_state *old_crtc_state;
+ const struct intel_crtc_state *new_crtc_state;
+ struct intel_plane *plane;
+ struct intel_crtc *crtc;
int i;
- for_each_new_crtc_in_state(state, crtc, cstate, i) {
- const struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- enum pipe pipe = intel_crtc->pipe;
+ if (!drm_debug_enabled(DRM_UT_KMS))
+ return;
- for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
- enum plane_id plane_id = intel_plane->id;
+ for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+ new_crtc_state, i) {
+ const struct skl_pipe_wm *old_pipe_wm, *new_pipe_wm;
+
+ old_pipe_wm = &old_crtc_state->wm.skl.optimal;
+ new_pipe_wm = &new_crtc_state->wm.skl.optimal;
+
+ for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
+ enum plane_id plane_id = plane->id;
const struct skl_ddb_entry *old, *new;
- old = &old_ddb->plane[pipe][plane_id];
- new = &new_ddb->plane[pipe][plane_id];
+ old = &old_crtc_state->wm.skl.plane_ddb_y[plane_id];
+ new = &new_crtc_state->wm.skl.plane_ddb_y[plane_id];
if (skl_ddb_entry_equal(old, new))
continue;
- DRM_DEBUG_ATOMIC("[PLANE:%d:%s] ddb (%d - %d) -> (%d - %d)\n",
- intel_plane->base.base.id,
- intel_plane->base.name,
- old->start, old->end,
- new->start, new->end);
+ drm_dbg_kms(&dev_priv->drm,
+ "[PLANE:%d:%s] ddb (%4d - %4d) -> (%4d - %4d), size %4d -> %4d\n",
+ plane->base.base.id, plane->base.name,
+ old->start, old->end, new->start, new->end,
+ skl_ddb_entry_size(old), skl_ddb_entry_size(new));
+ }
+
+ for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
+ enum plane_id plane_id = plane->id;
+ const struct skl_plane_wm *old_wm, *new_wm;
+
+ old_wm = &old_pipe_wm->planes[plane_id];
+ new_wm = &new_pipe_wm->planes[plane_id];
+
+ if (skl_plane_wm_equals(dev_priv, old_wm, new_wm))
+ continue;
+
+ drm_dbg_kms(&dev_priv->drm,
+ "[PLANE:%d:%s] level %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm,%cswm"
+ " -> %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm,%cswm\n",
+ plane->base.base.id, plane->base.name,
+ enast(old_wm->wm[0].plane_en), enast(old_wm->wm[1].plane_en),
+ enast(old_wm->wm[2].plane_en), enast(old_wm->wm[3].plane_en),
+ enast(old_wm->wm[4].plane_en), enast(old_wm->wm[5].plane_en),
+ enast(old_wm->wm[6].plane_en), enast(old_wm->wm[7].plane_en),
+ enast(old_wm->trans_wm.plane_en),
+ enast(old_wm->sagv_wm0.plane_en),
+ enast(new_wm->wm[0].plane_en), enast(new_wm->wm[1].plane_en),
+ enast(new_wm->wm[2].plane_en), enast(new_wm->wm[3].plane_en),
+ enast(new_wm->wm[4].plane_en), enast(new_wm->wm[5].plane_en),
+ enast(new_wm->wm[6].plane_en), enast(new_wm->wm[7].plane_en),
+ enast(new_wm->trans_wm.plane_en),
+ enast(new_wm->sagv_wm0.plane_en));
+
+ drm_dbg_kms(&dev_priv->drm,
+ "[PLANE:%d:%s] lines %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d"
+ " -> %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d\n",
+ plane->base.base.id, plane->base.name,
+ enast(old_wm->wm[0].ignore_lines), old_wm->wm[0].plane_res_l,
+ enast(old_wm->wm[1].ignore_lines), old_wm->wm[1].plane_res_l,
+ enast(old_wm->wm[2].ignore_lines), old_wm->wm[2].plane_res_l,
+ enast(old_wm->wm[3].ignore_lines), old_wm->wm[3].plane_res_l,
+ enast(old_wm->wm[4].ignore_lines), old_wm->wm[4].plane_res_l,
+ enast(old_wm->wm[5].ignore_lines), old_wm->wm[5].plane_res_l,
+ enast(old_wm->wm[6].ignore_lines), old_wm->wm[6].plane_res_l,
+ enast(old_wm->wm[7].ignore_lines), old_wm->wm[7].plane_res_l,
+ enast(old_wm->trans_wm.ignore_lines), old_wm->trans_wm.plane_res_l,
+ enast(old_wm->sagv_wm0.ignore_lines), old_wm->sagv_wm0.plane_res_l,
+
+ enast(new_wm->wm[0].ignore_lines), new_wm->wm[0].plane_res_l,
+ enast(new_wm->wm[1].ignore_lines), new_wm->wm[1].plane_res_l,
+ enast(new_wm->wm[2].ignore_lines), new_wm->wm[2].plane_res_l,
+ enast(new_wm->wm[3].ignore_lines), new_wm->wm[3].plane_res_l,
+ enast(new_wm->wm[4].ignore_lines), new_wm->wm[4].plane_res_l,
+ enast(new_wm->wm[5].ignore_lines), new_wm->wm[5].plane_res_l,
+ enast(new_wm->wm[6].ignore_lines), new_wm->wm[6].plane_res_l,
+ enast(new_wm->wm[7].ignore_lines), new_wm->wm[7].plane_res_l,
+ enast(new_wm->trans_wm.ignore_lines), new_wm->trans_wm.plane_res_l,
+ enast(new_wm->sagv_wm0.ignore_lines), new_wm->sagv_wm0.plane_res_l);
+
+ drm_dbg_kms(&dev_priv->drm,
+ "[PLANE:%d:%s] blocks %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
+ " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
+ plane->base.base.id, plane->base.name,
+ old_wm->wm[0].plane_res_b, old_wm->wm[1].plane_res_b,
+ old_wm->wm[2].plane_res_b, old_wm->wm[3].plane_res_b,
+ old_wm->wm[4].plane_res_b, old_wm->wm[5].plane_res_b,
+ old_wm->wm[6].plane_res_b, old_wm->wm[7].plane_res_b,
+ old_wm->trans_wm.plane_res_b,
+ old_wm->sagv_wm0.plane_res_b,
+ new_wm->wm[0].plane_res_b, new_wm->wm[1].plane_res_b,
+ new_wm->wm[2].plane_res_b, new_wm->wm[3].plane_res_b,
+ new_wm->wm[4].plane_res_b, new_wm->wm[5].plane_res_b,
+ new_wm->wm[6].plane_res_b, new_wm->wm[7].plane_res_b,
+ new_wm->trans_wm.plane_res_b,
+ new_wm->sagv_wm0.plane_res_b);
+
+ drm_dbg_kms(&dev_priv->drm,
+ "[PLANE:%d:%s] min_ddb %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
+ " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
+ plane->base.base.id, plane->base.name,
+ old_wm->wm[0].min_ddb_alloc, old_wm->wm[1].min_ddb_alloc,
+ old_wm->wm[2].min_ddb_alloc, old_wm->wm[3].min_ddb_alloc,
+ old_wm->wm[4].min_ddb_alloc, old_wm->wm[5].min_ddb_alloc,
+ old_wm->wm[6].min_ddb_alloc, old_wm->wm[7].min_ddb_alloc,
+ old_wm->trans_wm.min_ddb_alloc,
+ old_wm->sagv_wm0.min_ddb_alloc,
+ new_wm->wm[0].min_ddb_alloc, new_wm->wm[1].min_ddb_alloc,
+ new_wm->wm[2].min_ddb_alloc, new_wm->wm[3].min_ddb_alloc,
+ new_wm->wm[4].min_ddb_alloc, new_wm->wm[5].min_ddb_alloc,
+ new_wm->wm[6].min_ddb_alloc, new_wm->wm[7].min_ddb_alloc,
+ new_wm->trans_wm.min_ddb_alloc,
+ new_wm->sagv_wm0.min_ddb_alloc);
}
}
}
-static int
-skl_ddb_add_affected_pipes(struct drm_atomic_state *state, bool *changed)
+static int intel_add_affected_pipes(struct intel_atomic_state *state,
+ u8 pipe_mask)
{
- struct drm_device *dev = state->dev;
- const struct drm_i915_private *dev_priv = to_i915(dev);
- const struct drm_crtc *crtc;
- const struct drm_crtc_state *cstate;
- struct intel_crtc *intel_crtc;
- struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
- uint32_t realloc_pipes = pipes_modified(state);
- int ret, i;
+ struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+ struct intel_crtc *crtc;
- /*
- * When we distrust bios wm we always need to recompute to set the
- * expected DDB allocations for each CRTC.
- */
- if (dev_priv->wm.distrust_bios_wm)
- (*changed) = true;
+ for_each_intel_crtc(&dev_priv->drm, crtc) {
+ struct intel_crtc_state *crtc_state;
- /*
- * If this transaction isn't actually touching any CRTC's, don't
- * bother with watermark calculation. Note that if we pass this
- * test, we're guaranteed to hold at least one CRTC state mutex,
- * which means we can safely use values like dev_priv->active_crtcs
- * since any racing commits that want to update them would need to
- * hold _all_ CRTC state mutexes.
- */
- for_each_new_crtc_in_state(state, crtc, cstate, i)
- (*changed) = true;
+ if ((pipe_mask & BIT(crtc->pipe)) == 0)
+ continue;
- if (!*changed)
- return 0;
-
- /*
- * If this is our first atomic update following hardware readout,
- * we can't trust the DDB that the BIOS programmed for us. Let's
- * pretend that all pipes switched active status so that we'll
- * ensure a full DDB recompute.
- */
- if (dev_priv->wm.distrust_bios_wm) {
- ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
- state->acquire_ctx);
- if (ret)
- return ret;
-
- intel_state->active_pipe_changes = ~0;
-
- /*
- * We usually only initialize intel_state->active_crtcs if we
- * we're doing a modeset; make sure this field is always
- * initialized during the sanitization process that happens
- * on the first commit too.
- */
- if (!intel_state->modeset)
- intel_state->active_crtcs = dev_priv->active_crtcs;
- }
-
- /*
- * If the modeset changes which CRTC's are active, we need to
- * recompute the DDB allocation for *all* active pipes, even
- * those that weren't otherwise being modified in any way by this
- * atomic commit. Due to the shrinking of the per-pipe allocations
- * when new active CRTC's are added, it's possible for a pipe that
- * we were already using and aren't changing at all here to suddenly
- * become invalid if its DDB needs exceeds its new allocation.
- *
- * Note that if we wind up doing a full DDB recompute, we can't let
- * any other display updates race with this transaction, so we need
- * to grab the lock on *all* CRTC's.
- */
- if (intel_state->active_pipe_changes) {
- realloc_pipes = ~0;
- intel_state->wm_results.dirty_pipes = ~0;
- }
-
- /*
- * We're not recomputing for the pipes not included in the commit, so
- * make sure we start with the current state.
- */
- for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) {
- struct intel_crtc_state *cstate;
-
- cstate = intel_atomic_get_crtc_state(state, intel_crtc);
- if (IS_ERR(cstate))
- return PTR_ERR(cstate);
+ crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+ if (IS_ERR(crtc_state))
+ return PTR_ERR(crtc_state);
}
return 0;
}
static int
-skl_compute_wm(struct drm_atomic_state *state)
+skl_ddb_add_affected_pipes(struct intel_atomic_state *state)
{
- struct drm_crtc *crtc;
- struct drm_crtc_state *cstate;
- struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
- struct skl_ddb_values *results = &intel_state->wm_results;
- struct skl_pipe_wm *pipe_wm;
- bool changed = false;
+ struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+ struct intel_crtc_state *crtc_state;
+ struct intel_crtc *crtc;
+ int i, ret;
+
+ if (dev_priv->wm.distrust_bios_wm) {
+ /*
+ * skl_ddb_get_pipe_allocation_limits() currently requires
+ * all active pipes to be included in the state so that
+ * it can redistribute the dbuf among them, and it really
+ * wants to recompute things when distrust_bios_wm is set
+ * so we add all the pipes to the state.
+ */
+ ret = intel_add_affected_pipes(state, ~0);
+ if (ret)
+ return ret;
+ }
+
+ for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
+ struct intel_dbuf_state *new_dbuf_state;
+ const struct intel_dbuf_state *old_dbuf_state;
+
+ new_dbuf_state = intel_atomic_get_dbuf_state(state);
+ if (IS_ERR(new_dbuf_state))
+ return PTR_ERR(new_dbuf_state);
+
+ old_dbuf_state = intel_atomic_get_old_dbuf_state(state);
+
+ new_dbuf_state->active_pipes =
+ intel_calc_active_pipes(state, old_dbuf_state->active_pipes);
+
+ if (old_dbuf_state->active_pipes == new_dbuf_state->active_pipes)
+ break;
+
+ ret = intel_atomic_lock_global_state(&new_dbuf_state->base);
+ if (ret)
+ return ret;
+
+ /*
+ * skl_ddb_get_pipe_allocation_limits() currently requires
+ * all active pipes to be included in the state so that
+ * it can redistribute the dbuf among them.
+ */
+ ret = intel_add_affected_pipes(state,
+ new_dbuf_state->active_pipes);
+ if (ret)
+ return ret;
+
+ break;
+ }
+
+ return 0;
+}
+
+/*
+ * To make sure the cursor watermark registers are always consistent
+ * with our computed state the following scenario needs special
+ * treatment:
+ *
+ * 1. enable cursor
+ * 2. move cursor entirely offscreen
+ * 3. disable cursor
+ *
+ * Step 2. does call .disable_plane() but does not zero the watermarks
+ * (since we consider an offscreen cursor still active for the purposes
+ * of watermarks). Step 3. would not normally call .disable_plane()
+ * because the actual plane visibility isn't changing, and we don't
+ * deallocate the cursor ddb until the pipe gets disabled. So we must
+ * force step 3. to call .disable_plane() to update the watermark
+ * registers properly.
+ *
+ * Other planes do not suffer from this issues as their watermarks are
+ * calculated based on the actual plane visibility. The only time this
+ * can trigger for the other planes is during the initial readout as the
+ * default value of the watermarks registers is not zero.
+ */
+static int skl_wm_add_affected_planes(struct intel_atomic_state *state,
+ struct intel_crtc *crtc)
+{
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ const struct intel_crtc_state *old_crtc_state =
+ intel_atomic_get_old_crtc_state(state, crtc);
+ struct intel_crtc_state *new_crtc_state =
+ intel_atomic_get_new_crtc_state(state, crtc);
+ struct intel_plane *plane;
+
+ for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
+ struct intel_plane_state *plane_state;
+ enum plane_id plane_id = plane->id;
+
+ /*
+ * Force a full wm update for every plane on modeset.
+ * Required because the reset value of the wm registers
+ * is non-zero, whereas we want all disabled planes to
+ * have zero watermarks. So if we turn off the relevant
+ * power well the hardware state will go out of sync
+ * with the software state.
+ */
+ if (!drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi) &&
+ skl_plane_wm_equals(dev_priv,
+ &old_crtc_state->wm.skl.optimal.planes[plane_id],
+ &new_crtc_state->wm.skl.optimal.planes[plane_id]))
+ continue;
+
+ plane_state = intel_atomic_get_plane_state(state, plane);
+ if (IS_ERR(plane_state))
+ return PTR_ERR(plane_state);
+
+ new_crtc_state->update_planes |= BIT(plane_id);
+ }
+
+ return 0;
+}
+
+static int
+skl_compute_wm(struct intel_atomic_state *state)
+{
+ struct intel_crtc *crtc;
+ struct intel_crtc_state *new_crtc_state;
+ struct intel_crtc_state *old_crtc_state;
int ret, i;
- /* Clear all dirty flags */
- results->dirty_pipes = 0;
-
- ret = skl_ddb_add_affected_pipes(state, &changed);
- if (ret || !changed)
- return ret;
-
- ret = skl_compute_ddb(state);
+ ret = skl_ddb_add_affected_pipes(state);
if (ret)
return ret;
/*
* Calculate WM's for all pipes that are part of this transaction.
- * Note that the DDB allocation above may have added more CRTC's that
- * weren't otherwise being modified (and set bits in dirty_pipes) if
- * pipe allocations had to change.
- *
- * FIXME: Now that we're doing this in the atomic check phase, we
- * should allow skl_update_pipe_wm() to return failure in cases where
- * no suitable watermark values can be found.
+ * Note that skl_ddb_add_affected_pipes may have added more CRTC's that
+ * weren't otherwise being modified if pipe allocations had to change.
*/
- for_each_new_crtc_in_state(state, crtc, cstate, i) {
- struct intel_crtc_state *intel_cstate =
- to_intel_crtc_state(cstate);
- const struct skl_pipe_wm *old_pipe_wm =
- &to_intel_crtc_state(crtc->state)->wm.skl.optimal;
-
- pipe_wm = &intel_cstate->wm.skl.optimal;
- ret = skl_update_pipe_wm(cstate, old_pipe_wm, pipe_wm,
- &results->ddb, &changed);
+ for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+ new_crtc_state, i) {
+ ret = skl_build_pipe_wm(new_crtc_state);
if (ret)
return ret;
+ }
- if (changed)
- results->dirty_pipes |= drm_crtc_mask(crtc);
+ ret = skl_compute_ddb(state);
+ if (ret)
+ return ret;
- if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0)
- /* This pipe's WM's did not change */
- continue;
+ ret = intel_compute_sagv_mask(state);
+ if (ret)
+ return ret;
- intel_cstate->update_wm_pre = true;
+ /*
+ * skl_compute_ddb() will have adjusted the final watermarks
+ * based on how much ddb is available. Now we can actually
+ * check if the final watermarks changed.
+ */
+ for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+ new_crtc_state, i) {
+ ret = skl_wm_add_affected_planes(state, crtc);
+ if (ret)
+ return ret;
}
skl_print_wm_changes(state);
@@ -5385,61 +6140,13 @@
return 0;
}
-static void skl_atomic_update_crtc_wm(struct intel_atomic_state *state,
- struct intel_crtc_state *cstate)
-{
- struct intel_crtc *crtc = to_intel_crtc(cstate->base.crtc);
- struct drm_i915_private *dev_priv = to_i915(state->base.dev);
- struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal;
- const struct skl_ddb_allocation *ddb = &state->wm_results.ddb;
- enum pipe pipe = crtc->pipe;
- enum plane_id plane_id;
-
- if (!(state->wm_results.dirty_pipes & drm_crtc_mask(&crtc->base)))
- return;
-
- I915_WRITE(PIPE_WM_LINETIME(pipe), pipe_wm->linetime);
-
- for_each_plane_id_on_crtc(crtc, plane_id) {
- if (plane_id != PLANE_CURSOR)
- skl_write_plane_wm(crtc, &pipe_wm->planes[plane_id],
- ddb, plane_id);
- else
- skl_write_cursor_wm(crtc, &pipe_wm->planes[plane_id],
- ddb);
- }
-}
-
-static void skl_initial_wm(struct intel_atomic_state *state,
- struct intel_crtc_state *cstate)
-{
- struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
- struct drm_device *dev = intel_crtc->base.dev;
- struct drm_i915_private *dev_priv = to_i915(dev);
- struct skl_ddb_values *results = &state->wm_results;
- struct skl_ddb_values *hw_vals = &dev_priv->wm.skl_hw;
- enum pipe pipe = intel_crtc->pipe;
-
- if ((results->dirty_pipes & drm_crtc_mask(&intel_crtc->base)) == 0)
- return;
-
- mutex_lock(&dev_priv->wm.wm_mutex);
-
- if (cstate->base.active_changed)
- skl_atomic_update_crtc_wm(state, cstate);
-
- skl_copy_ddb_for_pipe(hw_vals, results, pipe);
-
- mutex_unlock(&dev_priv->wm.wm_mutex);
-}
-
-static void ilk_compute_wm_config(struct drm_device *dev,
+static void ilk_compute_wm_config(struct drm_i915_private *dev_priv,
struct intel_wm_config *config)
{
struct intel_crtc *crtc;
/* Compute the currently _active_ config */
- for_each_intel_crtc(dev, crtc) {
+ for_each_intel_crtc(&dev_priv->drm, crtc) {
const struct intel_pipe_wm *wm = &crtc->wm.active.ilk;
if (!wm->pipe_enabled)
@@ -5453,25 +6160,24 @@
static void ilk_program_watermarks(struct drm_i915_private *dev_priv)
{
- struct drm_device *dev = &dev_priv->drm;
struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm;
struct ilk_wm_maximums max;
struct intel_wm_config config = {};
struct ilk_wm_values results = {};
enum intel_ddb_partitioning partitioning;
- ilk_compute_wm_config(dev, &config);
+ ilk_compute_wm_config(dev_priv, &config);
- ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_1_2, &max);
- ilk_wm_merge(dev, &config, &max, &lp_wm_1_2);
+ ilk_compute_wm_maximums(dev_priv, 1, &config, INTEL_DDB_PART_1_2, &max);
+ ilk_wm_merge(dev_priv, &config, &max, &lp_wm_1_2);
/* 5/6 split only in single pipe config on IVB+ */
if (INTEL_GEN(dev_priv) >= 7 &&
config.num_pipes_active == 1 && config.sprites_enabled) {
- ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_5_6, &max);
- ilk_wm_merge(dev, &config, &max, &lp_wm_5_6);
+ ilk_compute_wm_maximums(dev_priv, 1, &config, INTEL_DDB_PART_5_6, &max);
+ ilk_wm_merge(dev_priv, &config, &max, &lp_wm_5_6);
- best_lp_wm = ilk_find_best_result(dev, &lp_wm_1_2, &lp_wm_5_6);
+ best_lp_wm = ilk_find_best_result(dev_priv, &lp_wm_1_2, &lp_wm_5_6);
} else {
best_lp_wm = &lp_wm_1_2;
}
@@ -5479,59 +6185,61 @@
partitioning = (best_lp_wm == &lp_wm_1_2) ?
INTEL_DDB_PART_1_2 : INTEL_DDB_PART_5_6;
- ilk_compute_wm_results(dev, best_lp_wm, partitioning, &results);
+ ilk_compute_wm_results(dev_priv, best_lp_wm, partitioning, &results);
ilk_write_wm_values(dev_priv, &results);
}
static void ilk_initial_watermarks(struct intel_atomic_state *state,
- struct intel_crtc_state *cstate)
+ struct intel_crtc *crtc)
{
- struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
- struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ const struct intel_crtc_state *crtc_state =
+ intel_atomic_get_new_crtc_state(state, crtc);
mutex_lock(&dev_priv->wm.wm_mutex);
- intel_crtc->wm.active.ilk = cstate->wm.ilk.intermediate;
+ crtc->wm.active.ilk = crtc_state->wm.ilk.intermediate;
ilk_program_watermarks(dev_priv);
mutex_unlock(&dev_priv->wm.wm_mutex);
}
static void ilk_optimize_watermarks(struct intel_atomic_state *state,
- struct intel_crtc_state *cstate)
+ struct intel_crtc *crtc)
{
- struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
- struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ const struct intel_crtc_state *crtc_state =
+ intel_atomic_get_new_crtc_state(state, crtc);
+
+ if (!crtc_state->wm.need_postvbl_update)
+ return;
mutex_lock(&dev_priv->wm.wm_mutex);
- if (cstate->wm.need_postvbl_update) {
- intel_crtc->wm.active.ilk = cstate->wm.ilk.optimal;
- ilk_program_watermarks(dev_priv);
- }
+ crtc->wm.active.ilk = crtc_state->wm.ilk.optimal;
+ ilk_program_watermarks(dev_priv);
mutex_unlock(&dev_priv->wm.wm_mutex);
}
-static inline void skl_wm_level_from_reg_val(uint32_t val,
- struct skl_wm_level *level)
+static void skl_wm_level_from_reg_val(u32 val, struct skl_wm_level *level)
{
level->plane_en = val & PLANE_WM_EN;
+ level->ignore_lines = val & PLANE_WM_IGNORE_LINES;
level->plane_res_b = val & PLANE_WM_BLOCKS_MASK;
level->plane_res_l = (val >> PLANE_WM_LINES_SHIFT) &
PLANE_WM_LINES_MASK;
}
-void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc,
+void skl_pipe_wm_get_hw_state(struct intel_crtc *crtc,
struct skl_pipe_wm *out)
{
- struct drm_i915_private *dev_priv = to_i915(crtc->dev);
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- enum pipe pipe = intel_crtc->pipe;
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ enum pipe pipe = crtc->pipe;
int level, max_level;
enum plane_id plane_id;
- uint32_t val;
+ u32 val;
max_level = ilk_wm_max_level(dev_priv);
- for_each_plane_id_on_crtc(intel_crtc, plane_id) {
+ for_each_plane_id_on_crtc(crtc, plane_id) {
struct skl_plane_wm *wm = &out->planes[plane_id];
for (level = 0; level <= max_level; level++) {
@@ -5543,6 +6251,9 @@
skl_wm_level_from_reg_val(val, &wm->wm[level]);
}
+ if (INTEL_GEN(dev_priv) >= 12)
+ wm->sagv_wm0 = wm->wm[0];
+
if (plane_id != PLANE_CURSOR)
val = I915_READ(PLANE_WM_TRANS(pipe, plane_id));
else
@@ -5551,54 +6262,35 @@
skl_wm_level_from_reg_val(val, &wm->trans_wm);
}
- if (!intel_crtc->active)
+ if (!crtc->active)
return;
-
- out->linetime = I915_READ(PIPE_WM_LINETIME(pipe));
}
-void skl_wm_get_hw_state(struct drm_device *dev)
+void skl_wm_get_hw_state(struct drm_i915_private *dev_priv)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
- struct skl_ddb_values *hw = &dev_priv->wm.skl_hw;
- struct skl_ddb_allocation *ddb = &dev_priv->wm.skl_hw.ddb;
- struct drm_crtc *crtc;
- struct intel_crtc *intel_crtc;
- struct intel_crtc_state *cstate;
+ struct intel_crtc *crtc;
+ struct intel_crtc_state *crtc_state;
- skl_ddb_get_hw_state(dev_priv, ddb);
- list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
- intel_crtc = to_intel_crtc(crtc);
- cstate = to_intel_crtc_state(crtc->state);
+ for_each_intel_crtc(&dev_priv->drm, crtc) {
+ crtc_state = to_intel_crtc_state(crtc->base.state);
- skl_pipe_wm_get_hw_state(crtc, &cstate->wm.skl.optimal);
-
- if (intel_crtc->active)
- hw->dirty_pipes |= drm_crtc_mask(crtc);
+ skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal);
}
- if (dev_priv->active_crtcs) {
+ if (dev_priv->active_pipes) {
/* Fully recompute DDB on first atomic commit */
dev_priv->wm.distrust_bios_wm = true;
- } else {
- /*
- * Easy/common case; just sanitize DDB now if everything off
- * Keep dbuf slice info intact
- */
- memset(ddb->plane, 0, sizeof(ddb->plane));
- memset(ddb->uv_plane, 0, sizeof(ddb->uv_plane));
}
}
-static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
+static void ilk_pipe_wm_get_hw_state(struct intel_crtc *crtc)
{
- struct drm_device *dev = crtc->dev;
+ struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = to_i915(dev);
struct ilk_wm_values *hw = &dev_priv->wm.hw;
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
- struct intel_pipe_wm *active = &cstate->wm.ilk.optimal;
- enum pipe pipe = intel_crtc->pipe;
+ struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state);
+ struct intel_pipe_wm *active = &crtc_state->wm.ilk.optimal;
+ enum pipe pipe = crtc->pipe;
static const i915_reg_t wm0_pipe_reg[] = {
[PIPE_A] = WM0_PIPEA_ILK,
[PIPE_B] = WM0_PIPEB_ILK,
@@ -5606,12 +6298,10 @@
};
hw->wm_pipe[pipe] = I915_READ(wm0_pipe_reg[pipe]);
- if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
- hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe));
memset(active, 0, sizeof(*active));
- active->pipe_enabled = intel_crtc->active;
+ active->pipe_enabled = crtc->active;
if (active->pipe_enabled) {
u32 tmp = hw->wm_pipe[pipe];
@@ -5626,7 +6316,6 @@
active->wm[0].pri_val = (tmp & WM0_PIPE_PLANE_MASK) >> WM0_PIPE_PLANE_SHIFT;
active->wm[0].spr_val = (tmp & WM0_PIPE_SPRITE_MASK) >> WM0_PIPE_SPRITE_SHIFT;
active->wm[0].cur_val = tmp & WM0_PIPE_CURSOR_MASK;
- active->linetime = hw->wm_linetime[pipe];
} else {
int level, max_level = ilk_wm_max_level(dev_priv);
@@ -5639,7 +6328,7 @@
active->wm[level].enable = true;
}
- intel_crtc->wm.active.ilk = *active;
+ crtc->wm.active.ilk = *active;
}
#define _FW_WM(value, plane) \
@@ -5650,7 +6339,7 @@
static void g4x_read_wm_values(struct drm_i915_private *dev_priv,
struct g4x_wm_values *wm)
{
- uint32_t tmp;
+ u32 tmp;
tmp = I915_READ(DSPFW1);
wm->sr.plane = _FW_WM(tmp, SR);
@@ -5677,7 +6366,7 @@
struct vlv_wm_values *wm)
{
enum pipe pipe;
- uint32_t tmp;
+ u32 tmp;
for_each_pipe(dev_priv, pipe) {
tmp = I915_READ(VLV_DDL(pipe));
@@ -5749,9 +6438,8 @@
#undef _FW_WM
#undef _FW_WM_VLV
-void g4x_wm_get_hw_state(struct drm_device *dev)
+void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
struct g4x_wm_values *wm = &dev_priv->wm.g4x;
struct intel_crtc *crtc;
@@ -5759,7 +6447,7 @@
wm->cxsr = I915_READ(FW_BLC_SELF) & FW_BLC_SELF_EN;
- for_each_intel_crtc(dev, crtc) {
+ for_each_intel_crtc(&dev_priv->drm, crtc) {
struct intel_crtc_state *crtc_state =
to_intel_crtc_state(crtc->base.state);
struct g4x_wm_state *active = &crtc->wm.active.g4x;
@@ -5819,19 +6507,22 @@
crtc_state->wm.g4x.optimal = *active;
crtc_state->wm.g4x.intermediate = *active;
- DRM_DEBUG_KMS("Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite=%d\n",
- pipe_name(pipe),
- wm->pipe[pipe].plane[PLANE_PRIMARY],
- wm->pipe[pipe].plane[PLANE_CURSOR],
- wm->pipe[pipe].plane[PLANE_SPRITE0]);
+ drm_dbg_kms(&dev_priv->drm,
+ "Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite=%d\n",
+ pipe_name(pipe),
+ wm->pipe[pipe].plane[PLANE_PRIMARY],
+ wm->pipe[pipe].plane[PLANE_CURSOR],
+ wm->pipe[pipe].plane[PLANE_SPRITE0]);
}
- DRM_DEBUG_KMS("Initial SR watermarks: plane=%d, cursor=%d fbc=%d\n",
- wm->sr.plane, wm->sr.cursor, wm->sr.fbc);
- DRM_DEBUG_KMS("Initial HPLL watermarks: plane=%d, SR cursor=%d fbc=%d\n",
- wm->hpll.plane, wm->hpll.cursor, wm->hpll.fbc);
- DRM_DEBUG_KMS("Initial SR=%s HPLL=%s FBC=%s\n",
- yesno(wm->cxsr), yesno(wm->hpll_en), yesno(wm->fbc_en));
+ drm_dbg_kms(&dev_priv->drm,
+ "Initial SR watermarks: plane=%d, cursor=%d fbc=%d\n",
+ wm->sr.plane, wm->sr.cursor, wm->sr.fbc);
+ drm_dbg_kms(&dev_priv->drm,
+ "Initial HPLL watermarks: plane=%d, SR cursor=%d fbc=%d\n",
+ wm->hpll.plane, wm->hpll.cursor, wm->hpll.fbc);
+ drm_dbg_kms(&dev_priv->drm, "Initial SR=%s HPLL=%s FBC=%s\n",
+ yesno(wm->cxsr), yesno(wm->hpll_en), yesno(wm->fbc_en));
}
void g4x_wm_sanitize(struct drm_i915_private *dev_priv)
@@ -5852,7 +6543,7 @@
enum plane_id plane_id = plane->id;
int level;
- if (plane_state->base.visible)
+ if (plane_state->uapi.visible)
continue;
for (level = 0; level < 3; level++) {
@@ -5890,9 +6581,8 @@
mutex_unlock(&dev_priv->wm.wm_mutex);
}
-void vlv_wm_get_hw_state(struct drm_device *dev)
+void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
struct vlv_wm_values *wm = &dev_priv->wm.vlv;
struct intel_crtc *crtc;
u32 val;
@@ -5903,9 +6593,9 @@
wm->level = VLV_WM_LEVEL_PM2;
if (IS_CHERRYVIEW(dev_priv)) {
- mutex_lock(&dev_priv->pcu_lock);
+ vlv_punit_get(dev_priv);
- val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
+ val = vlv_punit_read(dev_priv, PUNIT_REG_DSPSSPM);
if (val & DSP_MAXFIFO_PM5_ENABLE)
wm->level = VLV_WM_LEVEL_PM5;
@@ -5924,8 +6614,9 @@
if (wait_for((vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2) &
FORCE_DDR_FREQ_REQ_ACK) == 0, 3)) {
- DRM_DEBUG_KMS("Punit not acking DDR DVFS request, "
- "assuming DDR DVFS is disabled\n");
+ drm_dbg_kms(&dev_priv->drm,
+ "Punit not acking DDR DVFS request, "
+ "assuming DDR DVFS is disabled\n");
dev_priv->wm.max_level = VLV_WM_LEVEL_PM5;
} else {
val = vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2);
@@ -5933,10 +6624,10 @@
wm->level = VLV_WM_LEVEL_DDR_DVFS;
}
- mutex_unlock(&dev_priv->pcu_lock);
+ vlv_punit_put(dev_priv);
}
- for_each_intel_crtc(dev, crtc) {
+ for_each_intel_crtc(&dev_priv->drm, crtc) {
struct intel_crtc_state *crtc_state =
to_intel_crtc_state(crtc->base.state);
struct vlv_wm_state *active = &crtc->wm.active.vlv;
@@ -5976,16 +6667,18 @@
crtc_state->wm.vlv.optimal = *active;
crtc_state->wm.vlv.intermediate = *active;
- DRM_DEBUG_KMS("Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite0=%d, sprite1=%d\n",
- pipe_name(pipe),
- wm->pipe[pipe].plane[PLANE_PRIMARY],
- wm->pipe[pipe].plane[PLANE_CURSOR],
- wm->pipe[pipe].plane[PLANE_SPRITE0],
- wm->pipe[pipe].plane[PLANE_SPRITE1]);
+ drm_dbg_kms(&dev_priv->drm,
+ "Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite0=%d, sprite1=%d\n",
+ pipe_name(pipe),
+ wm->pipe[pipe].plane[PLANE_PRIMARY],
+ wm->pipe[pipe].plane[PLANE_CURSOR],
+ wm->pipe[pipe].plane[PLANE_SPRITE0],
+ wm->pipe[pipe].plane[PLANE_SPRITE1]);
}
- DRM_DEBUG_KMS("Initial watermarks: SR plane=%d, SR cursor=%d level=%d cxsr=%d\n",
- wm->sr.plane, wm->sr.cursor, wm->level, wm->cxsr);
+ drm_dbg_kms(&dev_priv->drm,
+ "Initial watermarks: SR plane=%d, SR cursor=%d level=%d cxsr=%d\n",
+ wm->sr.plane, wm->sr.cursor, wm->level, wm->cxsr);
}
void vlv_wm_sanitize(struct drm_i915_private *dev_priv)
@@ -6008,7 +6701,7 @@
enum plane_id plane_id = plane->id;
int level;
- if (plane_state->base.visible)
+ if (plane_state->uapi.visible)
continue;
for (level = 0; level < wm_state->num_levels; level++) {
@@ -6053,15 +6746,14 @@
*/
}
-void ilk_wm_get_hw_state(struct drm_device *dev)
+void ilk_wm_get_hw_state(struct drm_i915_private *dev_priv)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
struct ilk_wm_values *hw = &dev_priv->wm.hw;
- struct drm_crtc *crtc;
+ struct intel_crtc *crtc;
ilk_init_lp_watermarks(dev_priv);
- for_each_crtc(dev, crtc)
+ for_each_intel_crtc(&dev_priv->drm, crtc)
ilk_pipe_wm_get_hw_state(crtc);
hw->wm_lp[0] = I915_READ(WM1_LP_ILK);
@@ -6130,11 +6822,8 @@
{
u32 val;
- /* Display WA #0477 WaDisableIPC: skl */
- if (IS_SKYLAKE(dev_priv)) {
- dev_priv->ipc_enabled = false;
+ if (!HAS_IPC(dev_priv))
return;
- }
val = I915_READ(DISP_ARB_CTL2);
@@ -6146,2397 +6835,29 @@
I915_WRITE(DISP_ARB_CTL2, val);
}
+static bool intel_can_enable_ipc(struct drm_i915_private *dev_priv)
+{
+ /* Display WA #0477 WaDisableIPC: skl */
+ if (IS_SKYLAKE(dev_priv))
+ return false;
+
+ /* Display WA #1141: SKL:all KBL:all CFL */
+ if (IS_KABYLAKE(dev_priv) ||
+ IS_COFFEELAKE(dev_priv) ||
+ IS_COMETLAKE(dev_priv))
+ return dev_priv->dram_info.symmetric_memory;
+
+ return true;
+}
+
void intel_init_ipc(struct drm_i915_private *dev_priv)
{
- dev_priv->ipc_enabled = false;
if (!HAS_IPC(dev_priv))
return;
- dev_priv->ipc_enabled = true;
+ dev_priv->ipc_enabled = intel_can_enable_ipc(dev_priv);
+
intel_enable_ipc(dev_priv);
-}
-
-/*
- * Lock protecting IPS related data structures
- */
-DEFINE_SPINLOCK(mchdev_lock);
-
-/* Global for IPS driver to get at the current i915 device. Protected by
- * mchdev_lock. */
-static struct drm_i915_private *i915_mch_dev;
-
-bool ironlake_set_drps(struct drm_i915_private *dev_priv, u8 val)
-{
- u16 rgvswctl;
-
- lockdep_assert_held(&mchdev_lock);
-
- rgvswctl = I915_READ16(MEMSWCTL);
- if (rgvswctl & MEMCTL_CMD_STS) {
- DRM_DEBUG("gpu busy, RCS change rejected\n");
- return false; /* still busy with another command */
- }
-
- rgvswctl = (MEMCTL_CMD_CHFREQ << MEMCTL_CMD_SHIFT) |
- (val << MEMCTL_FREQ_SHIFT) | MEMCTL_SFCAVM;
- I915_WRITE16(MEMSWCTL, rgvswctl);
- POSTING_READ16(MEMSWCTL);
-
- rgvswctl |= MEMCTL_CMD_STS;
- I915_WRITE16(MEMSWCTL, rgvswctl);
-
- return true;
-}
-
-static void ironlake_enable_drps(struct drm_i915_private *dev_priv)
-{
- u32 rgvmodectl;
- u8 fmax, fmin, fstart, vstart;
-
- spin_lock_irq(&mchdev_lock);
-
- rgvmodectl = I915_READ(MEMMODECTL);
-
- /* Enable temp reporting */
- I915_WRITE16(PMMISC, I915_READ(PMMISC) | MCPPCE_EN);
- I915_WRITE16(TSC1, I915_READ(TSC1) | TSE);
-
- /* 100ms RC evaluation intervals */
- I915_WRITE(RCUPEI, 100000);
- I915_WRITE(RCDNEI, 100000);
-
- /* Set max/min thresholds to 90ms and 80ms respectively */
- I915_WRITE(RCBMAXAVG, 90000);
- I915_WRITE(RCBMINAVG, 80000);
-
- I915_WRITE(MEMIHYST, 1);
-
- /* Set up min, max, and cur for interrupt handling */
- fmax = (rgvmodectl & MEMMODE_FMAX_MASK) >> MEMMODE_FMAX_SHIFT;
- fmin = (rgvmodectl & MEMMODE_FMIN_MASK);
- fstart = (rgvmodectl & MEMMODE_FSTART_MASK) >>
- MEMMODE_FSTART_SHIFT;
-
- vstart = (I915_READ(PXVFREQ(fstart)) & PXVFREQ_PX_MASK) >>
- PXVFREQ_PX_SHIFT;
-
- dev_priv->ips.fmax = fmax; /* IPS callback will increase this */
- dev_priv->ips.fstart = fstart;
-
- dev_priv->ips.max_delay = fstart;
- dev_priv->ips.min_delay = fmin;
- dev_priv->ips.cur_delay = fstart;
-
- DRM_DEBUG_DRIVER("fmax: %d, fmin: %d, fstart: %d\n",
- fmax, fmin, fstart);
-
- I915_WRITE(MEMINTREN, MEMINT_CX_SUPR_EN | MEMINT_EVAL_CHG_EN);
-
- /*
- * Interrupts will be enabled in ironlake_irq_postinstall
- */
-
- I915_WRITE(VIDSTART, vstart);
- POSTING_READ(VIDSTART);
-
- rgvmodectl |= MEMMODE_SWMODE_EN;
- I915_WRITE(MEMMODECTL, rgvmodectl);
-
- if (wait_for_atomic((I915_READ(MEMSWCTL) & MEMCTL_CMD_STS) == 0, 10))
- DRM_ERROR("stuck trying to change perf mode\n");
- mdelay(1);
-
- ironlake_set_drps(dev_priv, fstart);
-
- dev_priv->ips.last_count1 = I915_READ(DMIEC) +
- I915_READ(DDREC) + I915_READ(CSIEC);
- dev_priv->ips.last_time1 = jiffies_to_msecs(jiffies);
- dev_priv->ips.last_count2 = I915_READ(GFXEC);
- dev_priv->ips.last_time2 = ktime_get_raw_ns();
-
- spin_unlock_irq(&mchdev_lock);
-}
-
-static void ironlake_disable_drps(struct drm_i915_private *dev_priv)
-{
- u16 rgvswctl;
-
- spin_lock_irq(&mchdev_lock);
-
- rgvswctl = I915_READ16(MEMSWCTL);
-
- /* Ack interrupts, disable EFC interrupt */
- I915_WRITE(MEMINTREN, I915_READ(MEMINTREN) & ~MEMINT_EVAL_CHG_EN);
- I915_WRITE(MEMINTRSTS, MEMINT_EVAL_CHG);
- I915_WRITE(DEIER, I915_READ(DEIER) & ~DE_PCU_EVENT);
- I915_WRITE(DEIIR, DE_PCU_EVENT);
- I915_WRITE(DEIMR, I915_READ(DEIMR) | DE_PCU_EVENT);
-
- /* Go back to the starting frequency */
- ironlake_set_drps(dev_priv, dev_priv->ips.fstart);
- mdelay(1);
- rgvswctl |= MEMCTL_CMD_STS;
- I915_WRITE(MEMSWCTL, rgvswctl);
- mdelay(1);
-
- spin_unlock_irq(&mchdev_lock);
-}
-
-/* There's a funny hw issue where the hw returns all 0 when reading from
- * GEN6_RP_INTERRUPT_LIMITS. Hence we always need to compute the desired value
- * ourselves, instead of doing a rmw cycle (which might result in us clearing
- * all limits and the gpu stuck at whatever frequency it is at atm).
- */
-static u32 intel_rps_limits(struct drm_i915_private *dev_priv, u8 val)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
- u32 limits;
-
- /* Only set the down limit when we've reached the lowest level to avoid
- * getting more interrupts, otherwise leave this clear. This prevents a
- * race in the hw when coming out of rc6: There's a tiny window where
- * the hw runs at the minimal clock before selecting the desired
- * frequency, if the down threshold expires in that window we will not
- * receive a down interrupt. */
- if (INTEL_GEN(dev_priv) >= 9) {
- limits = (rps->max_freq_softlimit) << 23;
- if (val <= rps->min_freq_softlimit)
- limits |= (rps->min_freq_softlimit) << 14;
- } else {
- limits = rps->max_freq_softlimit << 24;
- if (val <= rps->min_freq_softlimit)
- limits |= rps->min_freq_softlimit << 16;
- }
-
- return limits;
-}
-
-static void rps_set_power(struct drm_i915_private *dev_priv, int new_power)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
- u32 threshold_up = 0, threshold_down = 0; /* in % */
- u32 ei_up = 0, ei_down = 0;
-
- lockdep_assert_held(&rps->power.mutex);
-
- if (new_power == rps->power.mode)
- return;
-
- /* Note the units here are not exactly 1us, but 1280ns. */
- switch (new_power) {
- case LOW_POWER:
- /* Upclock if more than 95% busy over 16ms */
- ei_up = 16000;
- threshold_up = 95;
-
- /* Downclock if less than 85% busy over 32ms */
- ei_down = 32000;
- threshold_down = 85;
- break;
-
- case BETWEEN:
- /* Upclock if more than 90% busy over 13ms */
- ei_up = 13000;
- threshold_up = 90;
-
- /* Downclock if less than 75% busy over 32ms */
- ei_down = 32000;
- threshold_down = 75;
- break;
-
- case HIGH_POWER:
- /* Upclock if more than 85% busy over 10ms */
- ei_up = 10000;
- threshold_up = 85;
-
- /* Downclock if less than 60% busy over 32ms */
- ei_down = 32000;
- threshold_down = 60;
- break;
- }
-
- /* When byt can survive without system hang with dynamic
- * sw freq adjustments, this restriction can be lifted.
- */
- if (IS_VALLEYVIEW(dev_priv))
- goto skip_hw_write;
-
- I915_WRITE(GEN6_RP_UP_EI,
- GT_INTERVAL_FROM_US(dev_priv, ei_up));
- I915_WRITE(GEN6_RP_UP_THRESHOLD,
- GT_INTERVAL_FROM_US(dev_priv,
- ei_up * threshold_up / 100));
-
- I915_WRITE(GEN6_RP_DOWN_EI,
- GT_INTERVAL_FROM_US(dev_priv, ei_down));
- I915_WRITE(GEN6_RP_DOWN_THRESHOLD,
- GT_INTERVAL_FROM_US(dev_priv,
- ei_down * threshold_down / 100));
-
- I915_WRITE(GEN6_RP_CONTROL,
- GEN6_RP_MEDIA_TURBO |
- GEN6_RP_MEDIA_HW_NORMAL_MODE |
- GEN6_RP_MEDIA_IS_GFX |
- GEN6_RP_ENABLE |
- GEN6_RP_UP_BUSY_AVG |
- GEN6_RP_DOWN_IDLE_AVG);
-
-skip_hw_write:
- rps->power.mode = new_power;
- rps->power.up_threshold = threshold_up;
- rps->power.down_threshold = threshold_down;
-}
-
-static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
- int new_power;
-
- new_power = rps->power.mode;
- switch (rps->power.mode) {
- case LOW_POWER:
- if (val > rps->efficient_freq + 1 &&
- val > rps->cur_freq)
- new_power = BETWEEN;
- break;
-
- case BETWEEN:
- if (val <= rps->efficient_freq &&
- val < rps->cur_freq)
- new_power = LOW_POWER;
- else if (val >= rps->rp0_freq &&
- val > rps->cur_freq)
- new_power = HIGH_POWER;
- break;
-
- case HIGH_POWER:
- if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 &&
- val < rps->cur_freq)
- new_power = BETWEEN;
- break;
- }
- /* Max/min bins are special */
- if (val <= rps->min_freq_softlimit)
- new_power = LOW_POWER;
- if (val >= rps->max_freq_softlimit)
- new_power = HIGH_POWER;
-
- mutex_lock(&rps->power.mutex);
- if (rps->power.interactive)
- new_power = HIGH_POWER;
- rps_set_power(dev_priv, new_power);
- mutex_unlock(&rps->power.mutex);
- rps->last_adj = 0;
-}
-
-void intel_rps_mark_interactive(struct drm_i915_private *i915, bool interactive)
-{
- struct intel_rps *rps = &i915->gt_pm.rps;
-
- if (INTEL_GEN(i915) < 6)
- return;
-
- mutex_lock(&rps->power.mutex);
- if (interactive) {
- if (!rps->power.interactive++ && READ_ONCE(i915->gt.awake))
- rps_set_power(i915, HIGH_POWER);
- } else {
- GEM_BUG_ON(!rps->power.interactive);
- rps->power.interactive--;
- }
- mutex_unlock(&rps->power.mutex);
-}
-
-static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
- u32 mask = 0;
-
- /* We use UP_EI_EXPIRED interupts for both up/down in manual mode */
- if (val > rps->min_freq_softlimit)
- mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
- if (val < rps->max_freq_softlimit)
- mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD;
-
- mask &= dev_priv->pm_rps_events;
-
- return gen6_sanitize_rps_pm_mask(dev_priv, ~mask);
-}
-
-/* gen6_set_rps is called to update the frequency request, but should also be
- * called when the range (min_delay and max_delay) is modified so that we can
- * update the GEN6_RP_INTERRUPT_LIMITS register accordingly. */
-static int gen6_set_rps(struct drm_i915_private *dev_priv, u8 val)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- /* min/max delay may still have been modified so be sure to
- * write the limits value.
- */
- if (val != rps->cur_freq) {
- gen6_set_rps_thresholds(dev_priv, val);
-
- if (INTEL_GEN(dev_priv) >= 9)
- I915_WRITE(GEN6_RPNSWREQ,
- GEN9_FREQUENCY(val));
- else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
- I915_WRITE(GEN6_RPNSWREQ,
- HSW_FREQUENCY(val));
- else
- I915_WRITE(GEN6_RPNSWREQ,
- GEN6_FREQUENCY(val) |
- GEN6_OFFSET(0) |
- GEN6_AGGRESSIVE_TURBO);
- }
-
- /* Make sure we continue to get interrupts
- * until we hit the minimum or maximum frequencies.
- */
- I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, intel_rps_limits(dev_priv, val));
- I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
-
- rps->cur_freq = val;
- trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
-
- return 0;
-}
-
-static int valleyview_set_rps(struct drm_i915_private *dev_priv, u8 val)
-{
- int err;
-
- if (WARN_ONCE(IS_CHERRYVIEW(dev_priv) && (val & 1),
- "Odd GPU freq value\n"))
- val &= ~1;
-
- I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
-
- if (val != dev_priv->gt_pm.rps.cur_freq) {
- err = vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
- if (err)
- return err;
-
- gen6_set_rps_thresholds(dev_priv, val);
- }
-
- dev_priv->gt_pm.rps.cur_freq = val;
- trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
-
- return 0;
-}
-
-/* vlv_set_rps_idle: Set the frequency to idle, if Gfx clocks are down
- *
- * * If Gfx is Idle, then
- * 1. Forcewake Media well.
- * 2. Request idle freq.
- * 3. Release Forcewake of Media well.
-*/
-static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
- u32 val = rps->idle_freq;
- int err;
-
- if (rps->cur_freq <= val)
- return;
-
- /* The punit delays the write of the frequency and voltage until it
- * determines the GPU is awake. During normal usage we don't want to
- * waste power changing the frequency if the GPU is sleeping (rc6).
- * However, the GPU and driver is now idle and we do not want to delay
- * switching to minimum voltage (reducing power whilst idle) as we do
- * not expect to be woken in the near future and so must flush the
- * change by waking the device.
- *
- * We choose to take the media powerwell (either would do to trick the
- * punit into committing the voltage change) as that takes a lot less
- * power than the render powerwell.
- */
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_MEDIA);
- err = valleyview_set_rps(dev_priv, val);
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_MEDIA);
-
- if (err)
- DRM_ERROR("Failed to set RPS for idle\n");
-}
-
-void gen6_rps_busy(struct drm_i915_private *dev_priv)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- mutex_lock(&dev_priv->pcu_lock);
- if (rps->enabled) {
- u8 freq;
-
- if (dev_priv->pm_rps_events & GEN6_PM_RP_UP_EI_EXPIRED)
- gen6_rps_reset_ei(dev_priv);
- I915_WRITE(GEN6_PMINTRMSK,
- gen6_rps_pm_mask(dev_priv, rps->cur_freq));
-
- gen6_enable_rps_interrupts(dev_priv);
-
- /* Use the user's desired frequency as a guide, but for better
- * performance, jump directly to RPe as our starting frequency.
- */
- freq = max(rps->cur_freq,
- rps->efficient_freq);
-
- if (intel_set_rps(dev_priv,
- clamp(freq,
- rps->min_freq_softlimit,
- rps->max_freq_softlimit)))
- DRM_DEBUG_DRIVER("Failed to set idle frequency\n");
- }
- mutex_unlock(&dev_priv->pcu_lock);
-}
-
-void gen6_rps_idle(struct drm_i915_private *dev_priv)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- /* Flush our bottom-half so that it does not race with us
- * setting the idle frequency and so that it is bounded by
- * our rpm wakeref. And then disable the interrupts to stop any
- * futher RPS reclocking whilst we are asleep.
- */
- gen6_disable_rps_interrupts(dev_priv);
-
- mutex_lock(&dev_priv->pcu_lock);
- if (rps->enabled) {
- if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
- vlv_set_rps_idle(dev_priv);
- else
- gen6_set_rps(dev_priv, rps->idle_freq);
- rps->last_adj = 0;
- I915_WRITE(GEN6_PMINTRMSK,
- gen6_sanitize_rps_pm_mask(dev_priv, ~0));
- }
- mutex_unlock(&dev_priv->pcu_lock);
-}
-
-void gen6_rps_boost(struct i915_request *rq,
- struct intel_rps_client *rps_client)
-{
- struct intel_rps *rps = &rq->i915->gt_pm.rps;
- unsigned long flags;
- bool boost;
-
- /* This is intentionally racy! We peek at the state here, then
- * validate inside the RPS worker.
- */
- if (!rps->enabled)
- return;
-
- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags))
- return;
-
- /* Serializes with i915_request_retire() */
- boost = false;
- spin_lock_irqsave(&rq->lock, flags);
- if (!rq->waitboost && !dma_fence_is_signaled_locked(&rq->fence)) {
- boost = !atomic_fetch_inc(&rps->num_waiters);
- rq->waitboost = true;
- }
- spin_unlock_irqrestore(&rq->lock, flags);
- if (!boost)
- return;
-
- if (READ_ONCE(rps->cur_freq) < rps->boost_freq)
- schedule_work(&rps->work);
-
- atomic_inc(rps_client ? &rps_client->boosts : &rps->boosts);
-}
-
-int intel_set_rps(struct drm_i915_private *dev_priv, u8 val)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
- int err;
-
- lockdep_assert_held(&dev_priv->pcu_lock);
- GEM_BUG_ON(val > rps->max_freq);
- GEM_BUG_ON(val < rps->min_freq);
-
- if (!rps->enabled) {
- rps->cur_freq = val;
- return 0;
- }
-
- if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
- err = valleyview_set_rps(dev_priv, val);
- else
- err = gen6_set_rps(dev_priv, val);
-
- return err;
-}
-
-static void gen9_disable_rc6(struct drm_i915_private *dev_priv)
-{
- I915_WRITE(GEN6_RC_CONTROL, 0);
- I915_WRITE(GEN9_PG_ENABLE, 0);
-}
-
-static void gen9_disable_rps(struct drm_i915_private *dev_priv)
-{
- I915_WRITE(GEN6_RP_CONTROL, 0);
-}
-
-static void gen6_disable_rc6(struct drm_i915_private *dev_priv)
-{
- I915_WRITE(GEN6_RC_CONTROL, 0);
-}
-
-static void gen6_disable_rps(struct drm_i915_private *dev_priv)
-{
- I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
- I915_WRITE(GEN6_RP_CONTROL, 0);
-}
-
-static void cherryview_disable_rc6(struct drm_i915_private *dev_priv)
-{
- I915_WRITE(GEN6_RC_CONTROL, 0);
-}
-
-static void cherryview_disable_rps(struct drm_i915_private *dev_priv)
-{
- I915_WRITE(GEN6_RP_CONTROL, 0);
-}
-
-static void valleyview_disable_rc6(struct drm_i915_private *dev_priv)
-{
- /* We're doing forcewake before Disabling RC6,
- * This what the BIOS expects when going into suspend */
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- I915_WRITE(GEN6_RC_CONTROL, 0);
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static void valleyview_disable_rps(struct drm_i915_private *dev_priv)
-{
- I915_WRITE(GEN6_RP_CONTROL, 0);
-}
-
-static bool bxt_check_bios_rc6_setup(struct drm_i915_private *dev_priv)
-{
- bool enable_rc6 = true;
- unsigned long rc6_ctx_base;
- u32 rc_ctl;
- int rc_sw_target;
-
- rc_ctl = I915_READ(GEN6_RC_CONTROL);
- rc_sw_target = (I915_READ(GEN6_RC_STATE) & RC_SW_TARGET_STATE_MASK) >>
- RC_SW_TARGET_STATE_SHIFT;
- DRM_DEBUG_DRIVER("BIOS enabled RC states: "
- "HW_CTRL %s HW_RC6 %s SW_TARGET_STATE %x\n",
- onoff(rc_ctl & GEN6_RC_CTL_HW_ENABLE),
- onoff(rc_ctl & GEN6_RC_CTL_RC6_ENABLE),
- rc_sw_target);
-
- if (!(I915_READ(RC6_LOCATION) & RC6_CTX_IN_DRAM)) {
- DRM_DEBUG_DRIVER("RC6 Base location not set properly.\n");
- enable_rc6 = false;
- }
-
- /*
- * The exact context size is not known for BXT, so assume a page size
- * for this check.
- */
- rc6_ctx_base = I915_READ(RC6_CTX_BASE) & RC6_CTX_BASE_MASK;
- if (!((rc6_ctx_base >= dev_priv->dsm_reserved.start) &&
- (rc6_ctx_base + PAGE_SIZE < dev_priv->dsm_reserved.end))) {
- DRM_DEBUG_DRIVER("RC6 Base address not as expected.\n");
- enable_rc6 = false;
- }
-
- if (!(((I915_READ(PWRCTX_MAXCNT_RCSUNIT) & IDLE_TIME_MASK) > 1) &&
- ((I915_READ(PWRCTX_MAXCNT_VCSUNIT0) & IDLE_TIME_MASK) > 1) &&
- ((I915_READ(PWRCTX_MAXCNT_BCSUNIT) & IDLE_TIME_MASK) > 1) &&
- ((I915_READ(PWRCTX_MAXCNT_VECSUNIT) & IDLE_TIME_MASK) > 1))) {
- DRM_DEBUG_DRIVER("Engine Idle wait time not set properly.\n");
- enable_rc6 = false;
- }
-
- if (!I915_READ(GEN8_PUSHBUS_CONTROL) ||
- !I915_READ(GEN8_PUSHBUS_ENABLE) ||
- !I915_READ(GEN8_PUSHBUS_SHIFT)) {
- DRM_DEBUG_DRIVER("Pushbus not setup properly.\n");
- enable_rc6 = false;
- }
-
- if (!I915_READ(GEN6_GFXPAUSE)) {
- DRM_DEBUG_DRIVER("GFX pause not setup properly.\n");
- enable_rc6 = false;
- }
-
- if (!I915_READ(GEN8_MISC_CTRL0)) {
- DRM_DEBUG_DRIVER("GPM control not setup properly.\n");
- enable_rc6 = false;
- }
-
- return enable_rc6;
-}
-
-static bool sanitize_rc6(struct drm_i915_private *i915)
-{
- struct intel_device_info *info = mkwrite_device_info(i915);
-
- /* Powersaving is controlled by the host when inside a VM */
- if (intel_vgpu_active(i915))
- info->has_rc6 = 0;
-
- if (info->has_rc6 &&
- IS_GEN9_LP(i915) && !bxt_check_bios_rc6_setup(i915)) {
- DRM_INFO("RC6 disabled by BIOS\n");
- info->has_rc6 = 0;
- }
-
- /*
- * We assume that we do not have any deep rc6 levels if we don't have
- * have the previous rc6 level supported, i.e. we use HAS_RC6()
- * as the initial coarse check for rc6 in general, moving on to
- * progressively finer/deeper levels.
- */
- if (!info->has_rc6 && info->has_rc6p)
- info->has_rc6p = 0;
-
- return info->has_rc6;
-}
-
-static void gen6_init_rps_frequencies(struct drm_i915_private *dev_priv)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- /* All of these values are in units of 50MHz */
-
- /* static values from HW: RP0 > RP1 > RPn (min_freq) */
- if (IS_GEN9_LP(dev_priv)) {
- u32 rp_state_cap = I915_READ(BXT_RP_STATE_CAP);
- rps->rp0_freq = (rp_state_cap >> 16) & 0xff;
- rps->rp1_freq = (rp_state_cap >> 8) & 0xff;
- rps->min_freq = (rp_state_cap >> 0) & 0xff;
- } else {
- u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
- rps->rp0_freq = (rp_state_cap >> 0) & 0xff;
- rps->rp1_freq = (rp_state_cap >> 8) & 0xff;
- rps->min_freq = (rp_state_cap >> 16) & 0xff;
- }
- /* hw_max = RP0 until we check for overclocking */
- rps->max_freq = rps->rp0_freq;
-
- rps->efficient_freq = rps->rp1_freq;
- if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv) ||
- IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
- u32 ddcc_status = 0;
-
- if (sandybridge_pcode_read(dev_priv,
- HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL,
- &ddcc_status) == 0)
- rps->efficient_freq =
- clamp_t(u8,
- ((ddcc_status >> 8) & 0xff),
- rps->min_freq,
- rps->max_freq);
- }
-
- if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
- /* Store the frequency values in 16.66 MHZ units, which is
- * the natural hardware unit for SKL
- */
- rps->rp0_freq *= GEN9_FREQ_SCALER;
- rps->rp1_freq *= GEN9_FREQ_SCALER;
- rps->min_freq *= GEN9_FREQ_SCALER;
- rps->max_freq *= GEN9_FREQ_SCALER;
- rps->efficient_freq *= GEN9_FREQ_SCALER;
- }
-}
-
-static void reset_rps(struct drm_i915_private *dev_priv,
- int (*set)(struct drm_i915_private *, u8))
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
- u8 freq = rps->cur_freq;
-
- /* force a reset */
- rps->power.mode = -1;
- rps->cur_freq = -1;
-
- if (set(dev_priv, freq))
- DRM_ERROR("Failed to reset RPS to initial values\n");
-}
-
-/* See the Gen9_GT_PM_Programming_Guide doc for the below */
-static void gen9_enable_rps(struct drm_i915_private *dev_priv)
-{
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- /* Program defaults and thresholds for RPS */
- if (IS_GEN9(dev_priv))
- I915_WRITE(GEN6_RC_VIDEO_FREQ,
- GEN9_FREQUENCY(dev_priv->gt_pm.rps.rp1_freq));
-
- /* 1 second timeout*/
- I915_WRITE(GEN6_RP_DOWN_TIMEOUT,
- GT_INTERVAL_FROM_US(dev_priv, 1000000));
-
- I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 0xa);
-
- /* Leaning on the below call to gen6_set_rps to program/setup the
- * Up/Down EI & threshold registers, as well as the RP_CONTROL,
- * RP_INTERRUPT_LIMITS & RPNSWREQ registers */
- reset_rps(dev_priv, gen6_set_rps);
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
-{
- struct intel_engine_cs *engine;
- enum intel_engine_id id;
- u32 rc6_mode;
-
- /* 1a: Software RC state - RC0 */
- I915_WRITE(GEN6_RC_STATE, 0);
-
- /* 1b: Get forcewake during program sequence. Although the driver
- * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- /* 2a: Disable RC states. */
- I915_WRITE(GEN6_RC_CONTROL, 0);
-
- /* 2b: Program RC6 thresholds.*/
- if (INTEL_GEN(dev_priv) >= 10) {
- I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
- I915_WRITE(GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
- } else if (IS_SKYLAKE(dev_priv)) {
- /*
- * WaRsDoubleRc6WrlWithCoarsePowerGating:skl Doubling WRL only
- * when CPG is enabled
- */
- I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 108 << 16);
- } else {
- I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
- }
-
- I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
- I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
- for_each_engine(engine, dev_priv, id)
- I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
-
- if (HAS_GUC(dev_priv))
- I915_WRITE(GUC_MAX_IDLE_COUNT, 0xA);
-
- I915_WRITE(GEN6_RC_SLEEP, 0);
-
- /*
- * 2c: Program Coarse Power Gating Policies.
- *
- * Bspec's guidance is to use 25us (really 25 * 1280ns) here. What we
- * use instead is a more conservative estimate for the maximum time
- * it takes us to service a CS interrupt and submit a new ELSP - that
- * is the time which the GPU is idle waiting for the CPU to select the
- * next request to execute. If the idle hysteresis is less than that
- * interrupt service latency, the hardware will automatically gate
- * the power well and we will then incur the wake up cost on top of
- * the service latency. A similar guide from intel_pstate is that we
- * do not want the enable hysteresis to less than the wakeup latency.
- *
- * igt/gem_exec_nop/sequential provides a rough estimate for the
- * service latency, and puts it around 10us for Broadwell (and other
- * big core) and around 40us for Broxton (and other low power cores).
- * [Note that for legacy ringbuffer submission, this is less than 1us!]
- * However, the wakeup latency on Broxton is closer to 100us. To be
- * conservative, we have to factor in a context switch on top (due
- * to ksoftirqd).
- */
- I915_WRITE(GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
- I915_WRITE(GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);
-
- /* 3a: Enable RC6 */
- I915_WRITE(GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */
-
- /* WaRsUseTimeoutMode:cnl (pre-prod) */
- if (IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_C0))
- rc6_mode = GEN7_RC_CTL_TO_MODE;
- else
- rc6_mode = GEN6_RC_CTL_EI_MODE(1);
-
- I915_WRITE(GEN6_RC_CONTROL,
- GEN6_RC_CTL_HW_ENABLE |
- GEN6_RC_CTL_RC6_ENABLE |
- rc6_mode);
-
- /*
- * 3b: Enable Coarse Power Gating only when RC6 is enabled.
- * WaRsDisableCoarsePowerGating:skl,cnl - Render/Media PG need to be disabled with RC6.
- */
- if (NEEDS_WaRsDisableCoarsePowerGating(dev_priv))
- I915_WRITE(GEN9_PG_ENABLE, 0);
- else
- I915_WRITE(GEN9_PG_ENABLE,
- GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE);
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static void gen8_enable_rc6(struct drm_i915_private *dev_priv)
-{
- struct intel_engine_cs *engine;
- enum intel_engine_id id;
-
- /* 1a: Software RC state - RC0 */
- I915_WRITE(GEN6_RC_STATE, 0);
-
- /* 1b: Get forcewake during program sequence. Although the driver
- * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- /* 2a: Disable RC states. */
- I915_WRITE(GEN6_RC_CONTROL, 0);
-
- /* 2b: Program RC6 thresholds.*/
- I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
- I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
- I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
- for_each_engine(engine, dev_priv, id)
- I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
- I915_WRITE(GEN6_RC_SLEEP, 0);
- I915_WRITE(GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
-
- /* 3: Enable RC6 */
-
- I915_WRITE(GEN6_RC_CONTROL,
- GEN6_RC_CTL_HW_ENABLE |
- GEN7_RC_CTL_TO_MODE |
- GEN6_RC_CTL_RC6_ENABLE);
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static void gen8_enable_rps(struct drm_i915_private *dev_priv)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- /* 1 Program defaults and thresholds for RPS*/
- I915_WRITE(GEN6_RPNSWREQ,
- HSW_FREQUENCY(rps->rp1_freq));
- I915_WRITE(GEN6_RC_VIDEO_FREQ,
- HSW_FREQUENCY(rps->rp1_freq));
- /* NB: Docs say 1s, and 1000000 - which aren't equivalent */
- I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 100000000 / 128); /* 1 second timeout */
-
- /* Docs recommend 900MHz, and 300 MHz respectively */
- I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
- rps->max_freq_softlimit << 24 |
- rps->min_freq_softlimit << 16);
-
- I915_WRITE(GEN6_RP_UP_THRESHOLD, 7600000 / 128); /* 76ms busyness per EI, 90% */
- I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 31300000 / 128); /* 313ms busyness per EI, 70%*/
- I915_WRITE(GEN6_RP_UP_EI, 66000); /* 84.48ms, XXX: random? */
- I915_WRITE(GEN6_RP_DOWN_EI, 350000); /* 448ms, XXX: random? */
-
- I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-
- /* 2: Enable RPS */
- I915_WRITE(GEN6_RP_CONTROL,
- GEN6_RP_MEDIA_TURBO |
- GEN6_RP_MEDIA_HW_NORMAL_MODE |
- GEN6_RP_MEDIA_IS_GFX |
- GEN6_RP_ENABLE |
- GEN6_RP_UP_BUSY_AVG |
- GEN6_RP_DOWN_IDLE_AVG);
-
- reset_rps(dev_priv, gen6_set_rps);
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static void gen6_enable_rc6(struct drm_i915_private *dev_priv)
-{
- struct intel_engine_cs *engine;
- enum intel_engine_id id;
- u32 rc6vids, rc6_mask;
- u32 gtfifodbg;
- int ret;
-
- I915_WRITE(GEN6_RC_STATE, 0);
-
- /* Clear the DBG now so we don't confuse earlier errors */
- gtfifodbg = I915_READ(GTFIFODBG);
- if (gtfifodbg) {
- DRM_ERROR("GT fifo had a previous error %x\n", gtfifodbg);
- I915_WRITE(GTFIFODBG, gtfifodbg);
- }
-
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- /* disable the counters and set deterministic thresholds */
- I915_WRITE(GEN6_RC_CONTROL, 0);
-
- I915_WRITE(GEN6_RC1_WAKE_RATE_LIMIT, 1000 << 16);
- I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16 | 30);
- I915_WRITE(GEN6_RC6pp_WAKE_RATE_LIMIT, 30);
- I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
- I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
-
- for_each_engine(engine, dev_priv, id)
- I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
-
- I915_WRITE(GEN6_RC_SLEEP, 0);
- I915_WRITE(GEN6_RC1e_THRESHOLD, 1000);
- if (IS_IVYBRIDGE(dev_priv))
- I915_WRITE(GEN6_RC6_THRESHOLD, 125000);
- else
- I915_WRITE(GEN6_RC6_THRESHOLD, 50000);
- I915_WRITE(GEN6_RC6p_THRESHOLD, 150000);
- I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
-
- /* We don't use those on Haswell */
- rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
- if (HAS_RC6p(dev_priv))
- rc6_mask |= GEN6_RC_CTL_RC6p_ENABLE;
- if (HAS_RC6pp(dev_priv))
- rc6_mask |= GEN6_RC_CTL_RC6pp_ENABLE;
- I915_WRITE(GEN6_RC_CONTROL,
- rc6_mask |
- GEN6_RC_CTL_EI_MODE(1) |
- GEN6_RC_CTL_HW_ENABLE);
-
- rc6vids = 0;
- ret = sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS, &rc6vids);
- if (IS_GEN6(dev_priv) && ret) {
- DRM_DEBUG_DRIVER("Couldn't check for BIOS workaround\n");
- } else if (IS_GEN6(dev_priv) && (GEN6_DECODE_RC6_VID(rc6vids & 0xff) < 450)) {
- DRM_DEBUG_DRIVER("You should update your BIOS. Correcting minimum rc6 voltage (%dmV->%dmV)\n",
- GEN6_DECODE_RC6_VID(rc6vids & 0xff), 450);
- rc6vids &= 0xffff00;
- rc6vids |= GEN6_ENCODE_RC6_VID(450);
- ret = sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_RC6VIDS, rc6vids);
- if (ret)
- DRM_ERROR("Couldn't fix incorrect rc6 voltage\n");
- }
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static void gen6_enable_rps(struct drm_i915_private *dev_priv)
-{
- /* Here begins a magic sequence of register writes to enable
- * auto-downclocking.
- *
- * Perhaps there might be some value in exposing these to
- * userspace...
- */
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- /* Power down if completely idle for over 50ms */
- I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 50000);
- I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-
- reset_rps(dev_priv, gen6_set_rps);
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
- const int min_freq = 15;
- const int scaling_factor = 180;
- unsigned int gpu_freq;
- unsigned int max_ia_freq, min_ring_freq;
- unsigned int max_gpu_freq, min_gpu_freq;
- struct cpufreq_policy *policy;
-
- WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
-
- if (rps->max_freq <= rps->min_freq)
- return;
-
- policy = cpufreq_cpu_get(0);
- if (policy) {
- max_ia_freq = policy->cpuinfo.max_freq;
- cpufreq_cpu_put(policy);
- } else {
- /*
- * Default to measured freq if none found, PCU will ensure we
- * don't go over
- */
- max_ia_freq = tsc_khz;
- }
-
- /* Convert from kHz to MHz */
- max_ia_freq /= 1000;
-
- min_ring_freq = I915_READ(DCLK) & 0xf;
- /* convert DDR frequency from units of 266.6MHz to bandwidth */
- min_ring_freq = mult_frac(min_ring_freq, 8, 3);
-
- min_gpu_freq = rps->min_freq;
- max_gpu_freq = rps->max_freq;
- if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
- /* Convert GT frequency to 50 HZ units */
- min_gpu_freq /= GEN9_FREQ_SCALER;
- max_gpu_freq /= GEN9_FREQ_SCALER;
- }
-
- /*
- * For each potential GPU frequency, load a ring frequency we'd like
- * to use for memory access. We do this by specifying the IA frequency
- * the PCU should use as a reference to determine the ring frequency.
- */
- for (gpu_freq = max_gpu_freq; gpu_freq >= min_gpu_freq; gpu_freq--) {
- const int diff = max_gpu_freq - gpu_freq;
- unsigned int ia_freq = 0, ring_freq = 0;
-
- if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
- /*
- * ring_freq = 2 * GT. ring_freq is in 100MHz units
- * No floor required for ring frequency on SKL.
- */
- ring_freq = gpu_freq;
- } else if (INTEL_GEN(dev_priv) >= 8) {
- /* max(2 * GT, DDR). NB: GT is 50MHz units */
- ring_freq = max(min_ring_freq, gpu_freq);
- } else if (IS_HASWELL(dev_priv)) {
- ring_freq = mult_frac(gpu_freq, 5, 4);
- ring_freq = max(min_ring_freq, ring_freq);
- /* leave ia_freq as the default, chosen by cpufreq */
- } else {
- /* On older processors, there is no separate ring
- * clock domain, so in order to boost the bandwidth
- * of the ring, we need to upclock the CPU (ia_freq).
- *
- * For GPU frequencies less than 750MHz,
- * just use the lowest ring freq.
- */
- if (gpu_freq < min_freq)
- ia_freq = 800;
- else
- ia_freq = max_ia_freq - ((diff * scaling_factor) / 2);
- ia_freq = DIV_ROUND_CLOSEST(ia_freq, 100);
- }
-
- sandybridge_pcode_write(dev_priv,
- GEN6_PCODE_WRITE_MIN_FREQ_TABLE,
- ia_freq << GEN6_PCODE_FREQ_IA_RATIO_SHIFT |
- ring_freq << GEN6_PCODE_FREQ_RING_RATIO_SHIFT |
- gpu_freq);
- }
-}
-
-static int cherryview_rps_max_freq(struct drm_i915_private *dev_priv)
-{
- u32 val, rp0;
-
- val = vlv_punit_read(dev_priv, FB_GFX_FMAX_AT_VMAX_FUSE);
-
- switch (INTEL_INFO(dev_priv)->sseu.eu_total) {
- case 8:
- /* (2 * 4) config */
- rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS4EU_FUSE_SHIFT);
- break;
- case 12:
- /* (2 * 6) config */
- rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS6EU_FUSE_SHIFT);
- break;
- case 16:
- /* (2 * 8) config */
- default:
- /* Setting (2 * 8) Min RP0 for any other combination */
- rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS8EU_FUSE_SHIFT);
- break;
- }
-
- rp0 = (rp0 & FB_GFX_FREQ_FUSE_MASK);
-
- return rp0;
-}
-
-static int cherryview_rps_rpe_freq(struct drm_i915_private *dev_priv)
-{
- u32 val, rpe;
-
- val = vlv_punit_read(dev_priv, PUNIT_GPU_DUTYCYCLE_REG);
- rpe = (val >> PUNIT_GPU_DUTYCYCLE_RPE_FREQ_SHIFT) & PUNIT_GPU_DUTYCYCLE_RPE_FREQ_MASK;
-
- return rpe;
-}
-
-static int cherryview_rps_guar_freq(struct drm_i915_private *dev_priv)
-{
- u32 val, rp1;
-
- val = vlv_punit_read(dev_priv, FB_GFX_FMAX_AT_VMAX_FUSE);
- rp1 = (val & FB_GFX_FREQ_FUSE_MASK);
-
- return rp1;
-}
-
-static u32 cherryview_rps_min_freq(struct drm_i915_private *dev_priv)
-{
- u32 val, rpn;
-
- val = vlv_punit_read(dev_priv, FB_GFX_FMIN_AT_VMIN_FUSE);
- rpn = ((val >> FB_GFX_FMIN_AT_VMIN_FUSE_SHIFT) &
- FB_GFX_FREQ_FUSE_MASK);
-
- return rpn;
-}
-
-static int valleyview_rps_guar_freq(struct drm_i915_private *dev_priv)
-{
- u32 val, rp1;
-
- val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FREQ_FUSE);
-
- rp1 = (val & FB_GFX_FGUARANTEED_FREQ_FUSE_MASK) >> FB_GFX_FGUARANTEED_FREQ_FUSE_SHIFT;
-
- return rp1;
-}
-
-static int valleyview_rps_max_freq(struct drm_i915_private *dev_priv)
-{
- u32 val, rp0;
-
- val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FREQ_FUSE);
-
- rp0 = (val & FB_GFX_MAX_FREQ_FUSE_MASK) >> FB_GFX_MAX_FREQ_FUSE_SHIFT;
- /* Clamp to max */
- rp0 = min_t(u32, rp0, 0xea);
-
- return rp0;
-}
-
-static int valleyview_rps_rpe_freq(struct drm_i915_private *dev_priv)
-{
- u32 val, rpe;
-
- val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_LO);
- rpe = (val & FB_FMAX_VMIN_FREQ_LO_MASK) >> FB_FMAX_VMIN_FREQ_LO_SHIFT;
- val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_HI);
- rpe |= (val & FB_FMAX_VMIN_FREQ_HI_MASK) << 5;
-
- return rpe;
-}
-
-static int valleyview_rps_min_freq(struct drm_i915_private *dev_priv)
-{
- u32 val;
-
- val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_LFM) & 0xff;
- /*
- * According to the BYT Punit GPU turbo HAS 1.1.6.3 the minimum value
- * for the minimum frequency in GPLL mode is 0xc1. Contrary to this on
- * a BYT-M B0 the above register contains 0xbf. Moreover when setting
- * a frequency Punit will not allow values below 0xc0. Clamp it 0xc0
- * to make sure it matches what Punit accepts.
- */
- return max_t(u32, val, 0xc0);
-}
-
-/* Check that the pctx buffer wasn't move under us. */
-static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
-{
- unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
-
- WARN_ON(pctx_addr != dev_priv->dsm.start +
- dev_priv->vlv_pctx->stolen->start);
-}
-
-
-/* Check that the pcbr address is not empty. */
-static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
-{
- unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
-
- WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
-}
-
-static void cherryview_setup_pctx(struct drm_i915_private *dev_priv)
-{
- resource_size_t pctx_paddr, paddr;
- resource_size_t pctx_size = 32*1024;
- u32 pcbr;
-
- pcbr = I915_READ(VLV_PCBR);
- if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
- DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");
- paddr = dev_priv->dsm.end + 1 - pctx_size;
- GEM_BUG_ON(paddr > U32_MAX);
-
- pctx_paddr = (paddr & (~4095));
- I915_WRITE(VLV_PCBR, pctx_paddr);
- }
-
- DRM_DEBUG_DRIVER("PCBR: 0x%08x\n", I915_READ(VLV_PCBR));
-}
-
-static void valleyview_setup_pctx(struct drm_i915_private *dev_priv)
-{
- struct drm_i915_gem_object *pctx;
- resource_size_t pctx_paddr;
- resource_size_t pctx_size = 24*1024;
- u32 pcbr;
-
- pcbr = I915_READ(VLV_PCBR);
- if (pcbr) {
- /* BIOS set it up already, grab the pre-alloc'd space */
- resource_size_t pcbr_offset;
-
- pcbr_offset = (pcbr & (~4095)) - dev_priv->dsm.start;
- pctx = i915_gem_object_create_stolen_for_preallocated(dev_priv,
- pcbr_offset,
- I915_GTT_OFFSET_NONE,
- pctx_size);
- goto out;
- }
-
- DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");
-
- /*
- * From the Gunit register HAS:
- * The Gfx driver is expected to program this register and ensure
- * proper allocation within Gfx stolen memory. For example, this
- * register should be programmed such than the PCBR range does not
- * overlap with other ranges, such as the frame buffer, protected
- * memory, or any other relevant ranges.
- */
- pctx = i915_gem_object_create_stolen(dev_priv, pctx_size);
- if (!pctx) {
- DRM_DEBUG("not enough stolen space for PCTX, disabling\n");
- goto out;
- }
-
- GEM_BUG_ON(range_overflows_t(u64,
- dev_priv->dsm.start,
- pctx->stolen->start,
- U32_MAX));
- pctx_paddr = dev_priv->dsm.start + pctx->stolen->start;
- I915_WRITE(VLV_PCBR, pctx_paddr);
-
-out:
- DRM_DEBUG_DRIVER("PCBR: 0x%08x\n", I915_READ(VLV_PCBR));
- dev_priv->vlv_pctx = pctx;
-}
-
-static void valleyview_cleanup_pctx(struct drm_i915_private *dev_priv)
-{
- struct drm_i915_gem_object *pctx;
-
- pctx = fetch_and_zero(&dev_priv->vlv_pctx);
- if (pctx)
- i915_gem_object_put(pctx);
-}
-
-static void vlv_init_gpll_ref_freq(struct drm_i915_private *dev_priv)
-{
- dev_priv->gt_pm.rps.gpll_ref_freq =
- vlv_get_cck_clock(dev_priv, "GPLL ref",
- CCK_GPLL_CLOCK_CONTROL,
- dev_priv->czclk_freq);
-
- DRM_DEBUG_DRIVER("GPLL reference freq: %d kHz\n",
- dev_priv->gt_pm.rps.gpll_ref_freq);
-}
-
-static void valleyview_init_gt_powersave(struct drm_i915_private *dev_priv)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
- u32 val;
-
- valleyview_setup_pctx(dev_priv);
-
- vlv_init_gpll_ref_freq(dev_priv);
-
- val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
- switch ((val >> 6) & 3) {
- case 0:
- case 1:
- dev_priv->mem_freq = 800;
- break;
- case 2:
- dev_priv->mem_freq = 1066;
- break;
- case 3:
- dev_priv->mem_freq = 1333;
- break;
- }
- DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", dev_priv->mem_freq);
-
- rps->max_freq = valleyview_rps_max_freq(dev_priv);
- rps->rp0_freq = rps->max_freq;
- DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
- intel_gpu_freq(dev_priv, rps->max_freq),
- rps->max_freq);
-
- rps->efficient_freq = valleyview_rps_rpe_freq(dev_priv);
- DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
- intel_gpu_freq(dev_priv, rps->efficient_freq),
- rps->efficient_freq);
-
- rps->rp1_freq = valleyview_rps_guar_freq(dev_priv);
- DRM_DEBUG_DRIVER("RP1(Guar Freq) GPU freq: %d MHz (%u)\n",
- intel_gpu_freq(dev_priv, rps->rp1_freq),
- rps->rp1_freq);
-
- rps->min_freq = valleyview_rps_min_freq(dev_priv);
- DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
- intel_gpu_freq(dev_priv, rps->min_freq),
- rps->min_freq);
-}
-
-static void cherryview_init_gt_powersave(struct drm_i915_private *dev_priv)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
- u32 val;
-
- cherryview_setup_pctx(dev_priv);
-
- vlv_init_gpll_ref_freq(dev_priv);
-
- mutex_lock(&dev_priv->sb_lock);
- val = vlv_cck_read(dev_priv, CCK_FUSE_REG);
- mutex_unlock(&dev_priv->sb_lock);
-
- switch ((val >> 2) & 0x7) {
- case 3:
- dev_priv->mem_freq = 2000;
- break;
- default:
- dev_priv->mem_freq = 1600;
- break;
- }
- DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", dev_priv->mem_freq);
-
- rps->max_freq = cherryview_rps_max_freq(dev_priv);
- rps->rp0_freq = rps->max_freq;
- DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
- intel_gpu_freq(dev_priv, rps->max_freq),
- rps->max_freq);
-
- rps->efficient_freq = cherryview_rps_rpe_freq(dev_priv);
- DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
- intel_gpu_freq(dev_priv, rps->efficient_freq),
- rps->efficient_freq);
-
- rps->rp1_freq = cherryview_rps_guar_freq(dev_priv);
- DRM_DEBUG_DRIVER("RP1(Guar) GPU freq: %d MHz (%u)\n",
- intel_gpu_freq(dev_priv, rps->rp1_freq),
- rps->rp1_freq);
-
- rps->min_freq = cherryview_rps_min_freq(dev_priv);
- DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
- intel_gpu_freq(dev_priv, rps->min_freq),
- rps->min_freq);
-
- WARN_ONCE((rps->max_freq | rps->efficient_freq | rps->rp1_freq |
- rps->min_freq) & 1,
- "Odd GPU freq values\n");
-}
-
-static void valleyview_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
-{
- valleyview_cleanup_pctx(dev_priv);
-}
-
-static void cherryview_enable_rc6(struct drm_i915_private *dev_priv)
-{
- struct intel_engine_cs *engine;
- enum intel_engine_id id;
- u32 gtfifodbg, rc6_mode, pcbr;
-
- gtfifodbg = I915_READ(GTFIFODBG) & ~(GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV |
- GT_FIFO_FREE_ENTRIES_CHV);
- if (gtfifodbg) {
- DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
- gtfifodbg);
- I915_WRITE(GTFIFODBG, gtfifodbg);
- }
-
- cherryview_check_pctx(dev_priv);
-
- /* 1a & 1b: Get forcewake during program sequence. Although the driver
- * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- /* Disable RC states. */
- I915_WRITE(GEN6_RC_CONTROL, 0);
-
- /* 2a: Program RC6 thresholds.*/
- I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
- I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
- I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-
- for_each_engine(engine, dev_priv, id)
- I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
- I915_WRITE(GEN6_RC_SLEEP, 0);
-
- /* TO threshold set to 500 us ( 0x186 * 1.28 us) */
- I915_WRITE(GEN6_RC6_THRESHOLD, 0x186);
-
- /* Allows RC6 residency counter to work */
- I915_WRITE(VLV_COUNTER_CONTROL,
- _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
- VLV_MEDIA_RC6_COUNT_EN |
- VLV_RENDER_RC6_COUNT_EN));
-
- /* For now we assume BIOS is allocating and populating the PCBR */
- pcbr = I915_READ(VLV_PCBR);
-
- /* 3: Enable RC6 */
- rc6_mode = 0;
- if (pcbr >> VLV_PCBR_ADDR_SHIFT)
- rc6_mode = GEN7_RC_CTL_TO_MODE;
- I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
-{
- u32 val;
-
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- /* 1: Program defaults and thresholds for RPS*/
- I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 1000000);
- I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
- I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
- I915_WRITE(GEN6_RP_UP_EI, 66000);
- I915_WRITE(GEN6_RP_DOWN_EI, 350000);
-
- I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-
- /* 2: Enable RPS */
- I915_WRITE(GEN6_RP_CONTROL,
- GEN6_RP_MEDIA_HW_NORMAL_MODE |
- GEN6_RP_MEDIA_IS_GFX |
- GEN6_RP_ENABLE |
- GEN6_RP_UP_BUSY_AVG |
- GEN6_RP_DOWN_IDLE_AVG);
-
- /* Setting Fixed Bias */
- val = VLV_OVERRIDE_EN |
- VLV_SOC_TDP_EN |
- CHV_BIAS_CPU_50_SOC_50;
- vlv_punit_write(dev_priv, VLV_TURBO_SOC_OVERRIDE, val);
-
- val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-
- /* RPS code assumes GPLL is used */
- WARN_ONCE((val & GPLLENABLE) == 0, "GPLL not enabled\n");
-
- DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE));
- DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
-
- reset_rps(dev_priv, valleyview_set_rps);
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static void valleyview_enable_rc6(struct drm_i915_private *dev_priv)
-{
- struct intel_engine_cs *engine;
- enum intel_engine_id id;
- u32 gtfifodbg;
-
- valleyview_check_pctx(dev_priv);
-
- gtfifodbg = I915_READ(GTFIFODBG);
- if (gtfifodbg) {
- DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
- gtfifodbg);
- I915_WRITE(GTFIFODBG, gtfifodbg);
- }
-
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- /* Disable RC states. */
- I915_WRITE(GEN6_RC_CONTROL, 0);
-
- I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 0x00280000);
- I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
- I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
-
- for_each_engine(engine, dev_priv, id)
- I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
-
- I915_WRITE(GEN6_RC6_THRESHOLD, 0x557);
-
- /* Allows RC6 residency counter to work */
- I915_WRITE(VLV_COUNTER_CONTROL,
- _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
- VLV_MEDIA_RC0_COUNT_EN |
- VLV_RENDER_RC0_COUNT_EN |
- VLV_MEDIA_RC6_COUNT_EN |
- VLV_RENDER_RC6_COUNT_EN));
-
- I915_WRITE(GEN6_RC_CONTROL,
- GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL);
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
-{
- u32 val;
-
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-
- I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 1000000);
- I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
- I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
- I915_WRITE(GEN6_RP_UP_EI, 66000);
- I915_WRITE(GEN6_RP_DOWN_EI, 350000);
-
- I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-
- I915_WRITE(GEN6_RP_CONTROL,
- GEN6_RP_MEDIA_TURBO |
- GEN6_RP_MEDIA_HW_NORMAL_MODE |
- GEN6_RP_MEDIA_IS_GFX |
- GEN6_RP_ENABLE |
- GEN6_RP_UP_BUSY_AVG |
- GEN6_RP_DOWN_IDLE_CONT);
-
- /* Setting Fixed Bias */
- val = VLV_OVERRIDE_EN |
- VLV_SOC_TDP_EN |
- VLV_BIAS_CPU_125_SOC_875;
- vlv_punit_write(dev_priv, VLV_TURBO_SOC_OVERRIDE, val);
-
- val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-
- /* RPS code assumes GPLL is used */
- WARN_ONCE((val & GPLLENABLE) == 0, "GPLL not enabled\n");
-
- DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE));
- DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
-
- reset_rps(dev_priv, valleyview_set_rps);
-
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-}
-
-static unsigned long intel_pxfreq(u32 vidfreq)
-{
- unsigned long freq;
- int div = (vidfreq & 0x3f0000) >> 16;
- int post = (vidfreq & 0x3000) >> 12;
- int pre = (vidfreq & 0x7);
-
- if (!pre)
- return 0;
-
- freq = ((div * 133333) / ((1<<post) * pre));
-
- return freq;
-}
-
-static const struct cparams {
- u16 i;
- u16 t;
- u16 m;
- u16 c;
-} cparams[] = {
- { 1, 1333, 301, 28664 },
- { 1, 1066, 294, 24460 },
- { 1, 800, 294, 25192 },
- { 0, 1333, 276, 27605 },
- { 0, 1066, 276, 27605 },
- { 0, 800, 231, 23784 },
-};
-
-static unsigned long __i915_chipset_val(struct drm_i915_private *dev_priv)
-{
- u64 total_count, diff, ret;
- u32 count1, count2, count3, m = 0, c = 0;
- unsigned long now = jiffies_to_msecs(jiffies), diff1;
- int i;
-
- lockdep_assert_held(&mchdev_lock);
-
- diff1 = now - dev_priv->ips.last_time1;
-
- /* Prevent division-by-zero if we are asking too fast.
- * Also, we don't get interesting results if we are polling
- * faster than once in 10ms, so just return the saved value
- * in such cases.
- */
- if (diff1 <= 10)
- return dev_priv->ips.chipset_power;
-
- count1 = I915_READ(DMIEC);
- count2 = I915_READ(DDREC);
- count3 = I915_READ(CSIEC);
-
- total_count = count1 + count2 + count3;
-
- /* FIXME: handle per-counter overflow */
- if (total_count < dev_priv->ips.last_count1) {
- diff = ~0UL - dev_priv->ips.last_count1;
- diff += total_count;
- } else {
- diff = total_count - dev_priv->ips.last_count1;
- }
-
- for (i = 0; i < ARRAY_SIZE(cparams); i++) {
- if (cparams[i].i == dev_priv->ips.c_m &&
- cparams[i].t == dev_priv->ips.r_t) {
- m = cparams[i].m;
- c = cparams[i].c;
- break;
- }
- }
-
- diff = div_u64(diff, diff1);
- ret = ((m * diff) + c);
- ret = div_u64(ret, 10);
-
- dev_priv->ips.last_count1 = total_count;
- dev_priv->ips.last_time1 = now;
-
- dev_priv->ips.chipset_power = ret;
-
- return ret;
-}
-
-unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
-{
- unsigned long val;
-
- if (!IS_GEN5(dev_priv))
- return 0;
-
- spin_lock_irq(&mchdev_lock);
-
- val = __i915_chipset_val(dev_priv);
-
- spin_unlock_irq(&mchdev_lock);
-
- return val;
-}
-
-unsigned long i915_mch_val(struct drm_i915_private *dev_priv)
-{
- unsigned long m, x, b;
- u32 tsfs;
-
- tsfs = I915_READ(TSFS);
-
- m = ((tsfs & TSFS_SLOPE_MASK) >> TSFS_SLOPE_SHIFT);
- x = I915_READ8(TR1);
-
- b = tsfs & TSFS_INTR_MASK;
-
- return ((m * x) / 127) - b;
-}
-
-static int _pxvid_to_vd(u8 pxvid)
-{
- if (pxvid == 0)
- return 0;
-
- if (pxvid >= 8 && pxvid < 31)
- pxvid = 31;
-
- return (pxvid + 2) * 125;
-}
-
-static u32 pvid_to_extvid(struct drm_i915_private *dev_priv, u8 pxvid)
-{
- const int vd = _pxvid_to_vd(pxvid);
- const int vm = vd - 1125;
-
- if (INTEL_INFO(dev_priv)->is_mobile)
- return vm > 0 ? vm : 0;
-
- return vd;
-}
-
-static void __i915_update_gfx_val(struct drm_i915_private *dev_priv)
-{
- u64 now, diff, diffms;
- u32 count;
-
- lockdep_assert_held(&mchdev_lock);
-
- now = ktime_get_raw_ns();
- diffms = now - dev_priv->ips.last_time2;
- do_div(diffms, NSEC_PER_MSEC);
-
- /* Don't divide by 0 */
- if (!diffms)
- return;
-
- count = I915_READ(GFXEC);
-
- if (count < dev_priv->ips.last_count2) {
- diff = ~0UL - dev_priv->ips.last_count2;
- diff += count;
- } else {
- diff = count - dev_priv->ips.last_count2;
- }
-
- dev_priv->ips.last_count2 = count;
- dev_priv->ips.last_time2 = now;
-
- /* More magic constants... */
- diff = diff * 1181;
- diff = div_u64(diff, diffms * 10);
- dev_priv->ips.gfx_power = diff;
-}
-
-void i915_update_gfx_val(struct drm_i915_private *dev_priv)
-{
- if (!IS_GEN5(dev_priv))
- return;
-
- spin_lock_irq(&mchdev_lock);
-
- __i915_update_gfx_val(dev_priv);
-
- spin_unlock_irq(&mchdev_lock);
-}
-
-static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv)
-{
- unsigned long t, corr, state1, corr2, state2;
- u32 pxvid, ext_v;
-
- lockdep_assert_held(&mchdev_lock);
-
- pxvid = I915_READ(PXVFREQ(dev_priv->gt_pm.rps.cur_freq));
- pxvid = (pxvid >> 24) & 0x7f;
- ext_v = pvid_to_extvid(dev_priv, pxvid);
-
- state1 = ext_v;
-
- t = i915_mch_val(dev_priv);
-
- /* Revel in the empirically derived constants */
-
- /* Correction factor in 1/100000 units */
- if (t > 80)
- corr = ((t * 2349) + 135940);
- else if (t >= 50)
- corr = ((t * 964) + 29317);
- else /* < 50 */
- corr = ((t * 301) + 1004);
-
- corr = corr * ((150142 * state1) / 10000 - 78642);
- corr /= 100000;
- corr2 = (corr * dev_priv->ips.corr);
-
- state2 = (corr2 * state1) / 10000;
- state2 /= 100; /* convert to mW */
-
- __i915_update_gfx_val(dev_priv);
-
- return dev_priv->ips.gfx_power + state2;
-}
-
-unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
-{
- unsigned long val;
-
- if (!IS_GEN5(dev_priv))
- return 0;
-
- spin_lock_irq(&mchdev_lock);
-
- val = __i915_gfx_val(dev_priv);
-
- spin_unlock_irq(&mchdev_lock);
-
- return val;
-}
-
-/**
- * i915_read_mch_val - return value for IPS use
- *
- * Calculate and return a value for the IPS driver to use when deciding whether
- * we have thermal and power headroom to increase CPU or GPU power budget.
- */
-unsigned long i915_read_mch_val(void)
-{
- struct drm_i915_private *dev_priv;
- unsigned long chipset_val, graphics_val, ret = 0;
-
- spin_lock_irq(&mchdev_lock);
- if (!i915_mch_dev)
- goto out_unlock;
- dev_priv = i915_mch_dev;
-
- chipset_val = __i915_chipset_val(dev_priv);
- graphics_val = __i915_gfx_val(dev_priv);
-
- ret = chipset_val + graphics_val;
-
-out_unlock:
- spin_unlock_irq(&mchdev_lock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(i915_read_mch_val);
-
-/**
- * i915_gpu_raise - raise GPU frequency limit
- *
- * Raise the limit; IPS indicates we have thermal headroom.
- */
-bool i915_gpu_raise(void)
-{
- struct drm_i915_private *dev_priv;
- bool ret = true;
-
- spin_lock_irq(&mchdev_lock);
- if (!i915_mch_dev) {
- ret = false;
- goto out_unlock;
- }
- dev_priv = i915_mch_dev;
-
- if (dev_priv->ips.max_delay > dev_priv->ips.fmax)
- dev_priv->ips.max_delay--;
-
-out_unlock:
- spin_unlock_irq(&mchdev_lock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(i915_gpu_raise);
-
-/**
- * i915_gpu_lower - lower GPU frequency limit
- *
- * IPS indicates we're close to a thermal limit, so throttle back the GPU
- * frequency maximum.
- */
-bool i915_gpu_lower(void)
-{
- struct drm_i915_private *dev_priv;
- bool ret = true;
-
- spin_lock_irq(&mchdev_lock);
- if (!i915_mch_dev) {
- ret = false;
- goto out_unlock;
- }
- dev_priv = i915_mch_dev;
-
- if (dev_priv->ips.max_delay < dev_priv->ips.min_delay)
- dev_priv->ips.max_delay++;
-
-out_unlock:
- spin_unlock_irq(&mchdev_lock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(i915_gpu_lower);
-
-/**
- * i915_gpu_busy - indicate GPU business to IPS
- *
- * Tell the IPS driver whether or not the GPU is busy.
- */
-bool i915_gpu_busy(void)
-{
- bool ret = false;
-
- spin_lock_irq(&mchdev_lock);
- if (i915_mch_dev)
- ret = i915_mch_dev->gt.awake;
- spin_unlock_irq(&mchdev_lock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(i915_gpu_busy);
-
-/**
- * i915_gpu_turbo_disable - disable graphics turbo
- *
- * Disable graphics turbo by resetting the max frequency and setting the
- * current frequency to the default.
- */
-bool i915_gpu_turbo_disable(void)
-{
- struct drm_i915_private *dev_priv;
- bool ret = true;
-
- spin_lock_irq(&mchdev_lock);
- if (!i915_mch_dev) {
- ret = false;
- goto out_unlock;
- }
- dev_priv = i915_mch_dev;
-
- dev_priv->ips.max_delay = dev_priv->ips.fstart;
-
- if (!ironlake_set_drps(dev_priv, dev_priv->ips.fstart))
- ret = false;
-
-out_unlock:
- spin_unlock_irq(&mchdev_lock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(i915_gpu_turbo_disable);
-
-/**
- * Tells the intel_ips driver that the i915 driver is now loaded, if
- * IPS got loaded first.
- *
- * This awkward dance is so that neither module has to depend on the
- * other in order for IPS to do the appropriate communication of
- * GPU turbo limits to i915.
- */
-static void
-ips_ping_for_i915_load(void)
-{
- void (*link)(void);
-
- link = symbol_get(ips_link_to_i915_driver);
- if (link) {
- link();
- symbol_put(ips_link_to_i915_driver);
- }
-}
-
-void intel_gpu_ips_init(struct drm_i915_private *dev_priv)
-{
- /* We only register the i915 ips part with intel-ips once everything is
- * set up, to avoid intel-ips sneaking in and reading bogus values. */
- spin_lock_irq(&mchdev_lock);
- i915_mch_dev = dev_priv;
- spin_unlock_irq(&mchdev_lock);
-
- ips_ping_for_i915_load();
-}
-
-void intel_gpu_ips_teardown(void)
-{
- spin_lock_irq(&mchdev_lock);
- i915_mch_dev = NULL;
- spin_unlock_irq(&mchdev_lock);
-}
-
-static void intel_init_emon(struct drm_i915_private *dev_priv)
-{
- u32 lcfuse;
- u8 pxw[16];
- int i;
-
- /* Disable to program */
- I915_WRITE(ECR, 0);
- POSTING_READ(ECR);
-
- /* Program energy weights for various events */
- I915_WRITE(SDEW, 0x15040d00);
- I915_WRITE(CSIEW0, 0x007f0000);
- I915_WRITE(CSIEW1, 0x1e220004);
- I915_WRITE(CSIEW2, 0x04000004);
-
- for (i = 0; i < 5; i++)
- I915_WRITE(PEW(i), 0);
- for (i = 0; i < 3; i++)
- I915_WRITE(DEW(i), 0);
-
- /* Program P-state weights to account for frequency power adjustment */
- for (i = 0; i < 16; i++) {
- u32 pxvidfreq = I915_READ(PXVFREQ(i));
- unsigned long freq = intel_pxfreq(pxvidfreq);
- unsigned long vid = (pxvidfreq & PXVFREQ_PX_MASK) >>
- PXVFREQ_PX_SHIFT;
- unsigned long val;
-
- val = vid * vid;
- val *= (freq / 1000);
- val *= 255;
- val /= (127*127*900);
- if (val > 0xff)
- DRM_ERROR("bad pxval: %ld\n", val);
- pxw[i] = val;
- }
- /* Render standby states get 0 weight */
- pxw[14] = 0;
- pxw[15] = 0;
-
- for (i = 0; i < 4; i++) {
- u32 val = (pxw[i*4] << 24) | (pxw[(i*4)+1] << 16) |
- (pxw[(i*4)+2] << 8) | (pxw[(i*4)+3]);
- I915_WRITE(PXW(i), val);
- }
-
- /* Adjust magic regs to magic values (more experimental results) */
- I915_WRITE(OGW0, 0);
- I915_WRITE(OGW1, 0);
- I915_WRITE(EG0, 0x00007f00);
- I915_WRITE(EG1, 0x0000000e);
- I915_WRITE(EG2, 0x000e0000);
- I915_WRITE(EG3, 0x68000300);
- I915_WRITE(EG4, 0x42000000);
- I915_WRITE(EG5, 0x00140031);
- I915_WRITE(EG6, 0);
- I915_WRITE(EG7, 0);
-
- for (i = 0; i < 8; i++)
- I915_WRITE(PXWL(i), 0);
-
- /* Enable PMON + select events */
- I915_WRITE(ECR, 0x80000019);
-
- lcfuse = I915_READ(LCFUSE02);
-
- dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK);
-}
-
-static bool i915_rc6_ctx_corrupted(struct drm_i915_private *dev_priv)
-{
- return !I915_READ(GEN8_RC6_CTX_INFO);
-}
-
-static void i915_rc6_ctx_wa_init(struct drm_i915_private *i915)
-{
- if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
- return;
-
- if (i915_rc6_ctx_corrupted(i915)) {
- DRM_INFO("RC6 context corrupted, disabling runtime power management\n");
- i915->gt_pm.rc6.ctx_corrupted = true;
- intel_runtime_pm_get(i915);
- }
-}
-
-static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915)
-{
- if (i915->gt_pm.rc6.ctx_corrupted) {
- intel_runtime_pm_put(i915);
- i915->gt_pm.rc6.ctx_corrupted = false;
- }
-}
-
-/**
- * i915_rc6_ctx_wa_suspend - system suspend sequence for the RC6 CTX WA
- * @i915: i915 device
- *
- * Perform any steps needed to clean up the RC6 CTX WA before system suspend.
- */
-void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915)
-{
- if (i915->gt_pm.rc6.ctx_corrupted)
- intel_runtime_pm_put(i915);
-}
-
-/**
- * i915_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA
- * @i915: i915 device
- *
- * Perform any steps needed to re-init the RC6 CTX WA after system resume.
- */
-void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915)
-{
- if (!i915->gt_pm.rc6.ctx_corrupted)
- return;
-
- if (i915_rc6_ctx_corrupted(i915)) {
- intel_runtime_pm_get(i915);
- return;
- }
-
- DRM_INFO("RC6 context restored, re-enabling runtime power management\n");
- i915->gt_pm.rc6.ctx_corrupted = false;
-}
-
-static void intel_disable_rc6(struct drm_i915_private *dev_priv);
-
-/**
- * i915_rc6_ctx_wa_check - check for a new RC6 CTX corruption
- * @i915: i915 device
- *
- * Check if an RC6 CTX corruption has happened since the last check and if so
- * disable RC6 and runtime power management.
- *
- * Return false if no context corruption has happened since the last call of
- * this function, true otherwise.
-*/
-bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915)
-{
- if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
- return false;
-
- if (i915->gt_pm.rc6.ctx_corrupted)
- return false;
-
- if (!i915_rc6_ctx_corrupted(i915))
- return false;
-
- DRM_NOTE("RC6 context corruption, disabling runtime power management\n");
-
- intel_disable_rc6(i915);
- i915->gt_pm.rc6.ctx_corrupted = true;
- intel_runtime_pm_get_noresume(i915);
-
- return true;
-}
-
-void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- /*
- * RPM depends on RC6 to save restore the GT HW context, so make RC6 a
- * requirement.
- */
- if (!sanitize_rc6(dev_priv)) {
- DRM_INFO("RC6 disabled, disabling runtime PM support\n");
- intel_runtime_pm_get(dev_priv);
- }
-
- mutex_lock(&dev_priv->pcu_lock);
-
- i915_rc6_ctx_wa_init(dev_priv);
-
- /* Initialize RPS limits (for userspace) */
- if (IS_CHERRYVIEW(dev_priv))
- cherryview_init_gt_powersave(dev_priv);
- else if (IS_VALLEYVIEW(dev_priv))
- valleyview_init_gt_powersave(dev_priv);
- else if (INTEL_GEN(dev_priv) >= 6)
- gen6_init_rps_frequencies(dev_priv);
-
- /* Derive initial user preferences/limits from the hardware limits */
- rps->idle_freq = rps->min_freq;
- rps->cur_freq = rps->idle_freq;
-
- rps->max_freq_softlimit = rps->max_freq;
- rps->min_freq_softlimit = rps->min_freq;
-
- if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
- rps->min_freq_softlimit =
- max_t(int,
- rps->efficient_freq,
- intel_freq_opcode(dev_priv, 450));
-
- /* After setting max-softlimit, find the overclock max freq */
- if (IS_GEN6(dev_priv) ||
- IS_IVYBRIDGE(dev_priv) || IS_HASWELL(dev_priv)) {
- u32 params = 0;
-
- sandybridge_pcode_read(dev_priv, GEN6_READ_OC_PARAMS, ¶ms);
- if (params & BIT(31)) { /* OC supported */
- DRM_DEBUG_DRIVER("Overclocking supported, max: %dMHz, overclock: %dMHz\n",
- (rps->max_freq & 0xff) * 50,
- (params & 0xff) * 50);
- rps->max_freq = params & 0xff;
- }
- }
-
- /* Finally allow us to boost to max by default */
- rps->boost_freq = rps->max_freq;
-
- mutex_unlock(&dev_priv->pcu_lock);
-}
-
-void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
-{
- if (IS_VALLEYVIEW(dev_priv))
- valleyview_cleanup_gt_powersave(dev_priv);
-
- i915_rc6_ctx_wa_cleanup(dev_priv);
-
- if (!HAS_RC6(dev_priv))
- intel_runtime_pm_put(dev_priv);
-}
-
-/**
- * intel_suspend_gt_powersave - suspend PM work and helper threads
- * @dev_priv: i915 device
- *
- * We don't want to disable RC6 or other features here, we just want
- * to make sure any work we've queued has finished and won't bother
- * us while we're suspended.
- */
-void intel_suspend_gt_powersave(struct drm_i915_private *dev_priv)
-{
- if (INTEL_GEN(dev_priv) < 6)
- return;
-
- /* gen6_rps_idle() will be called later to disable interrupts */
-}
-
-void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv)
-{
- dev_priv->gt_pm.rps.enabled = true; /* force RPS disabling */
- dev_priv->gt_pm.rc6.enabled = true; /* force RC6 disabling */
- intel_disable_gt_powersave(dev_priv);
-
- if (INTEL_GEN(dev_priv) >= 11)
- gen11_reset_rps_interrupts(dev_priv);
- else
- gen6_reset_rps_interrupts(dev_priv);
-}
-
-static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
-{
- lockdep_assert_held(&i915->pcu_lock);
-
- if (!i915->gt_pm.llc_pstate.enabled)
- return;
-
- /* Currently there is no HW configuration to be done to disable. */
-
- i915->gt_pm.llc_pstate.enabled = false;
-}
-
-static void __intel_disable_rc6(struct drm_i915_private *dev_priv)
-{
- lockdep_assert_held(&dev_priv->pcu_lock);
-
- if (!dev_priv->gt_pm.rc6.enabled)
- return;
-
- if (INTEL_GEN(dev_priv) >= 9)
- gen9_disable_rc6(dev_priv);
- else if (IS_CHERRYVIEW(dev_priv))
- cherryview_disable_rc6(dev_priv);
- else if (IS_VALLEYVIEW(dev_priv))
- valleyview_disable_rc6(dev_priv);
- else if (INTEL_GEN(dev_priv) >= 6)
- gen6_disable_rc6(dev_priv);
-
- dev_priv->gt_pm.rc6.enabled = false;
-}
-
-static void intel_disable_rc6(struct drm_i915_private *dev_priv)
-{
- mutex_lock(&dev_priv->pcu_lock);
- __intel_disable_rc6(dev_priv);
- mutex_unlock(&dev_priv->pcu_lock);
-}
-
-static void intel_disable_rps(struct drm_i915_private *dev_priv)
-{
- lockdep_assert_held(&dev_priv->pcu_lock);
-
- if (!dev_priv->gt_pm.rps.enabled)
- return;
-
- if (INTEL_GEN(dev_priv) >= 9)
- gen9_disable_rps(dev_priv);
- else if (IS_CHERRYVIEW(dev_priv))
- cherryview_disable_rps(dev_priv);
- else if (IS_VALLEYVIEW(dev_priv))
- valleyview_disable_rps(dev_priv);
- else if (INTEL_GEN(dev_priv) >= 6)
- gen6_disable_rps(dev_priv);
- else if (IS_IRONLAKE_M(dev_priv))
- ironlake_disable_drps(dev_priv);
-
- dev_priv->gt_pm.rps.enabled = false;
-}
-
-void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
-{
- mutex_lock(&dev_priv->pcu_lock);
-
- __intel_disable_rc6(dev_priv);
- intel_disable_rps(dev_priv);
- if (HAS_LLC(dev_priv))
- intel_disable_llc_pstate(dev_priv);
-
- mutex_unlock(&dev_priv->pcu_lock);
-}
-
-static inline void intel_enable_llc_pstate(struct drm_i915_private *i915)
-{
- lockdep_assert_held(&i915->pcu_lock);
-
- if (i915->gt_pm.llc_pstate.enabled)
- return;
-
- gen6_update_ring_freq(i915);
-
- i915->gt_pm.llc_pstate.enabled = true;
-}
-
-static void intel_enable_rc6(struct drm_i915_private *dev_priv)
-{
- lockdep_assert_held(&dev_priv->pcu_lock);
-
- if (dev_priv->gt_pm.rc6.enabled)
- return;
-
- if (dev_priv->gt_pm.rc6.ctx_corrupted)
- return;
-
- if (IS_CHERRYVIEW(dev_priv))
- cherryview_enable_rc6(dev_priv);
- else if (IS_VALLEYVIEW(dev_priv))
- valleyview_enable_rc6(dev_priv);
- else if (INTEL_GEN(dev_priv) >= 9)
- gen9_enable_rc6(dev_priv);
- else if (IS_BROADWELL(dev_priv))
- gen8_enable_rc6(dev_priv);
- else if (INTEL_GEN(dev_priv) >= 6)
- gen6_enable_rc6(dev_priv);
-
- dev_priv->gt_pm.rc6.enabled = true;
-}
-
-static void intel_enable_rps(struct drm_i915_private *dev_priv)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- lockdep_assert_held(&dev_priv->pcu_lock);
-
- if (rps->enabled)
- return;
-
- if (IS_CHERRYVIEW(dev_priv)) {
- cherryview_enable_rps(dev_priv);
- } else if (IS_VALLEYVIEW(dev_priv)) {
- valleyview_enable_rps(dev_priv);
- } else if (INTEL_GEN(dev_priv) >= 9) {
- gen9_enable_rps(dev_priv);
- } else if (IS_BROADWELL(dev_priv)) {
- gen8_enable_rps(dev_priv);
- } else if (INTEL_GEN(dev_priv) >= 6) {
- gen6_enable_rps(dev_priv);
- } else if (IS_IRONLAKE_M(dev_priv)) {
- ironlake_enable_drps(dev_priv);
- intel_init_emon(dev_priv);
- }
-
- WARN_ON(rps->max_freq < rps->min_freq);
- WARN_ON(rps->idle_freq > rps->max_freq);
-
- WARN_ON(rps->efficient_freq < rps->min_freq);
- WARN_ON(rps->efficient_freq > rps->max_freq);
-
- rps->enabled = true;
-}
-
-void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
-{
- /* Powersaving is controlled by the host when inside a VM */
- if (intel_vgpu_active(dev_priv))
- return;
-
- mutex_lock(&dev_priv->pcu_lock);
-
- if (HAS_RC6(dev_priv))
- intel_enable_rc6(dev_priv);
- intel_enable_rps(dev_priv);
- if (HAS_LLC(dev_priv))
- intel_enable_llc_pstate(dev_priv);
-
- mutex_unlock(&dev_priv->pcu_lock);
}
static void ibx_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -8565,7 +6886,7 @@
static void ilk_init_clock_gating(struct drm_i915_private *dev_priv)
{
- uint32_t dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE;
+ u32 dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE;
/*
* Required for FBC
@@ -8618,16 +6939,6 @@
I915_WRITE(ILK_DISPLAY_CHICKEN2,
I915_READ(ILK_DISPLAY_CHICKEN2) |
ILK_ELPIN_409_SELECT);
- I915_WRITE(_3D_CHICKEN2,
- _3D_CHICKEN2_WM_READ_PIPELINED << 16 |
- _3D_CHICKEN2_WM_READ_PIPELINED);
-
- /* WaDisableRenderCachePipelinedFlush:ilk */
- I915_WRITE(CACHE_MODE_0,
- _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
-
- /* WaDisable_RenderCache_OperationalFlush:ilk */
- I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
g4x_disable_trickle_feed(dev_priv);
@@ -8636,8 +6947,8 @@
static void cpt_init_clock_gating(struct drm_i915_private *dev_priv)
{
- int pipe;
- uint32_t val;
+ enum pipe pipe;
+ u32 val;
/*
* On Ibex Peak and Cougar Point, we need to disable clock
@@ -8658,7 +6969,6 @@
val &= ~TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
if (dev_priv->vbt.fdi_rx_polarity_inverted)
val |= TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
- val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK;
val &= ~TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER;
val &= ~TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH;
I915_WRITE(TRANS_CHICKEN2(pipe), val);
@@ -8672,44 +6982,24 @@
static void gen6_check_mch_setup(struct drm_i915_private *dev_priv)
{
- uint32_t tmp;
+ u32 tmp;
tmp = I915_READ(MCH_SSKPD);
if ((tmp & MCH_SSKPD_WM0_MASK) != MCH_SSKPD_WM0_VAL)
- DRM_DEBUG_KMS("Wrong MCH_SSKPD value: 0x%08x This can cause underruns.\n",
- tmp);
+ drm_dbg_kms(&dev_priv->drm,
+ "Wrong MCH_SSKPD value: 0x%08x This can cause underruns.\n",
+ tmp);
}
static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
{
- uint32_t dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE;
+ u32 dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE;
I915_WRITE(ILK_DSPCLK_GATE_D, dspclk_gate);
I915_WRITE(ILK_DISPLAY_CHICKEN2,
I915_READ(ILK_DISPLAY_CHICKEN2) |
ILK_ELPIN_409_SELECT);
-
- /* WaDisableHiZPlanesWhenMSAAEnabled:snb */
- I915_WRITE(_3D_CHICKEN,
- _MASKED_BIT_ENABLE(_3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB));
-
- /* WaDisable_RenderCache_OperationalFlush:snb */
- I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
- /*
- * BSpec recoomends 8x4 when MSAA is used,
- * however in practice 16x4 seems fastest.
- *
- * Note that PS/WM thread counts depend on the WIZ hashing
- * disable bit, which we don't touch here, but it's good
- * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
- */
- I915_WRITE(GEN6_GT_MODE,
- _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
- I915_WRITE(CACHE_MODE_0,
- _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
I915_WRITE(GEN6_UCGCTL1,
I915_READ(GEN6_UCGCTL1) |
@@ -8732,18 +7022,6 @@
I915_WRITE(GEN6_UCGCTL2,
GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
-
- /* WaStripsFansDisableFastClipPerformanceFix:snb */
- I915_WRITE(_3D_CHICKEN3,
- _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL));
-
- /*
- * Bspec says:
- * "This bit must be set if 3DSTATE_CLIP clip mode is set to normal and
- * 3DSTATE_SF number of SF output attributes is more than 16."
- */
- I915_WRITE(_3D_CHICKEN3,
- _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH));
/*
* According to the spec the following bits should be
@@ -8774,24 +7052,6 @@
gen6_check_mch_setup(dev_priv);
}
-static void gen7_setup_fixed_func_scheduler(struct drm_i915_private *dev_priv)
-{
- uint32_t reg = I915_READ(GEN7_FF_THREAD_MODE);
-
- /*
- * WaVSThreadDispatchOverride:ivb,vlv
- *
- * This actually overrides the dispatch
- * mode for all thread types.
- */
- reg &= ~GEN7_FF_SCHED_MASK;
- reg |= GEN7_FF_TS_SCHED_HW;
- reg |= GEN7_FF_VS_SCHED_HW;
- reg |= GEN7_FF_DS_SCHED_HW;
-
- I915_WRITE(GEN7_FF_THREAD_MODE, reg);
-}
-
static void lpt_init_clock_gating(struct drm_i915_private *dev_priv)
{
/*
@@ -8812,7 +7072,7 @@
static void lpt_suspend_hw(struct drm_i915_private *dev_priv)
{
if (HAS_PCH_LPT_LP(dev_priv)) {
- uint32_t val = I915_READ(SOUTH_DSPCLK_GATE_D);
+ u32 val = I915_READ(SOUTH_DSPCLK_GATE_D);
val &= ~PCH_LP_PARTITION_LEVEL_DISABLE;
I915_WRITE(SOUTH_DSPCLK_GATE_D, val);
@@ -8847,9 +7107,33 @@
static void icl_init_clock_gating(struct drm_i915_private *dev_priv)
{
+ /* Wa_1409120013:icl,ehl */
+ I915_WRITE(ILK_DPFC_CHICKEN,
+ ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL);
+
/* This is not an Wa. Enable to reduce Sampler power */
I915_WRITE(GEN10_DFR_RATIO_EN_AND_CHICKEN,
I915_READ(GEN10_DFR_RATIO_EN_AND_CHICKEN) & ~DFR_DISABLE);
+
+ /*Wa_14010594013:icl, ehl */
+ intel_uncore_rmw(&dev_priv->uncore, GEN8_CHICKEN_DCPR_1,
+ 0, CNL_DELAY_PMRSP);
+}
+
+static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
+{
+ /* Wa_1409120013:tgl */
+ I915_WRITE(ILK_DPFC_CHICKEN,
+ ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL);
+
+ /* Wa_1409825376:tgl (pre-prod)*/
+ if (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B1))
+ I915_WRITE(GEN9_CLKGATE_DIS_3, I915_READ(GEN9_CLKGATE_DIS_3) |
+ TGL_VRH_GATING_DIS);
+
+ /* Wa_14011059788:tgl */
+ intel_uncore_rmw(&dev_priv->uncore, GEN10_DFR_RATIO_EN_AND_CHICKEN,
+ 0, DFR_DISABLE);
}
static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -8875,16 +7159,16 @@
I915_WRITE(GEN8_CHICKEN_DCPR_1,
I915_READ(GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM);
- /* WaFbcWakeMemOn:cnl */
+ /*
+ * WaFbcWakeMemOn:cnl
+ * Display WA #0859: cnl
+ */
I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
DISP_FBC_MEMORY_WAKE);
val = I915_READ(SLICE_UNIT_LEVEL_CLKGATE);
/* ReadHitWriteOnlyDisable:cnl */
val |= RCCUNIT_CLKGATE_DIS;
- /* WaSarbUnitClockGatingDisable:cnl (pre-prod) */
- if (IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_B0))
- val |= SARBUNIT_CLKGATE_DIS;
I915_WRITE(SLICE_UNIT_LEVEL_CLKGATE, val);
/* Wa_2201832410:cnl */
@@ -8904,7 +7188,17 @@
cnp_init_clock_gating(dev_priv);
gen9_init_clock_gating(dev_priv);
- /* WaFbcNukeOnHostModify:cfl */
+ /*
+ * WaFbcTurnOffFbcWatermark:cfl
+ * Display WA #0562: cfl
+ */
+ I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
+ DISP_FBC_WM_DIS);
+
+ /*
+ * WaFbcNukeOnHostModify:cfl
+ * Display WA #0873: cfl
+ */
I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
}
@@ -8914,16 +7208,26 @@
gen9_init_clock_gating(dev_priv);
/* WaDisableSDEUnitClockGating:kbl */
- if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+ if (IS_KBL_GT_REVID(dev_priv, 0, KBL_REVID_B0))
I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
/* WaDisableGamClockGating:kbl */
- if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+ if (IS_KBL_GT_REVID(dev_priv, 0, KBL_REVID_B0))
I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
GEN6_GAMUNIT_CLOCK_GATE_DISABLE);
- /* WaFbcNukeOnHostModify:kbl */
+ /*
+ * WaFbcTurnOffFbcWatermark:kbl
+ * Display WA #0562: kbl
+ */
+ I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
+ DISP_FBC_WM_DIS);
+
+ /*
+ * WaFbcNukeOnHostModify:kbl
+ * Display WA #0873: kbl
+ */
I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
}
@@ -8932,21 +7236,44 @@
{
gen9_init_clock_gating(dev_priv);
+ /* WaDisableDopClockGating:skl */
+ I915_WRITE(GEN7_MISCCPCTL, I915_READ(GEN7_MISCCPCTL) &
+ ~GEN7_DOP_CLOCK_GATE_ENABLE);
+
/* WAC6entrylatency:skl */
I915_WRITE(FBC_LLC_READ_CTRL, I915_READ(FBC_LLC_READ_CTRL) |
FBC_LLC_FULLY_OPEN);
- /* WaFbcNukeOnHostModify:skl */
+ /*
+ * WaFbcTurnOffFbcWatermark:skl
+ * Display WA #0562: skl
+ */
+ I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
+ DISP_FBC_WM_DIS);
+
+ /*
+ * WaFbcNukeOnHostModify:skl
+ * Display WA #0873: skl
+ */
I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
+
+ /*
+ * WaFbcHighMemBwCorruptionAvoidance:skl
+ * Display WA #0883: skl
+ */
+ I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
+ ILK_DPFC_DISABLE_DUMMY0);
}
static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
{
- /* The GTT cache must be disabled if the system is using 2M pages. */
- bool can_use_gtt_cache = !HAS_PAGE_SIZES(dev_priv,
- I915_GTT_PAGE_SIZE_2M);
enum pipe pipe;
+
+ /* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
+ I915_WRITE(CHICKEN_PIPESL_1(PIPE_A),
+ I915_READ(CHICKEN_PIPESL_1(PIPE_A)) |
+ HSW_FBCQ_DIS);
/* WaSwitchSolVfFArbitrationPriority:bdw */
I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
@@ -8978,9 +7305,6 @@
/* WaProgramL3SqcReg1Default:bdw */
gen8_set_l3sqc_credits(dev_priv, 30, 2);
- /* WaGttCachingOffByDefault:bdw */
- I915_WRITE(HSW_GTT_CACHE_EN, can_use_gtt_cache ? GTT_CACHE_EN_ALL : 0);
-
/* WaKVMNotificationOnConfigChange:bdw */
I915_WRITE(CHICKEN_PAR2_1, I915_READ(CHICKEN_PAR2_1)
| KVM_CONFIG_CHANGE_NOTIFICATION_SELECT);
@@ -8998,45 +7322,15 @@
static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
{
- /* L3 caching of data atomics doesn't work -- disable it. */
- I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
- I915_WRITE(HSW_ROW_CHICKEN3,
- _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE));
+ /* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
+ I915_WRITE(CHICKEN_PIPESL_1(PIPE_A),
+ I915_READ(CHICKEN_PIPESL_1(PIPE_A)) |
+ HSW_FBCQ_DIS);
/* This is required by WaCatErrorRejectionIssue:hsw */
I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
- I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
- GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
-
- /* WaVSRefCountFullforceMissDisable:hsw */
- I915_WRITE(GEN7_FF_THREAD_MODE,
- I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME);
-
- /* WaDisable_RenderCache_OperationalFlush:hsw */
- I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
- /* enable HiZ Raw Stall Optimization */
- I915_WRITE(CACHE_MODE_0_GEN7,
- _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
-
- /* WaDisable4x2SubspanOptimization:hsw */
- I915_WRITE(CACHE_MODE_1,
- _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
-
- /*
- * BSpec recommends 8x4 when MSAA is used,
- * however in practice 16x4 seems fastest.
- *
- * Note that PS/WM thread counts depend on the WIZ hashing
- * disable bit, which we don't touch here, but it's good
- * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
- */
- I915_WRITE(GEN7_GT_MODE,
- _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
- /* WaSampleCChickenBitEnable:hsw */
- I915_WRITE(HALF_SLICE_CHICKEN3,
- _MASKED_BIT_ENABLE(HSW_SAMPLE_C_PERFORMANCE));
+ I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
+ GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
/* WaSwitchSolVfFArbitrationPriority:hsw */
I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
@@ -9046,36 +7340,20 @@
static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
{
- uint32_t snpcr;
+ u32 snpcr;
I915_WRITE(ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE);
- /* WaDisableEarlyCull:ivb */
- I915_WRITE(_3D_CHICKEN3,
- _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_DISABLE_OBJEND_CULL));
+ /* WaFbcAsynchFlipDisableFbcQueue:ivb */
+ I915_WRITE(ILK_DISPLAY_CHICKEN1,
+ I915_READ(ILK_DISPLAY_CHICKEN1) |
+ ILK_FBCQ_DIS);
/* WaDisableBackToBackFlipFix:ivb */
I915_WRITE(IVB_CHICKEN3,
CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
CHICKEN3_DGMG_DONE_FIX_DISABLE);
- /* WaDisablePSDDualDispatchEnable:ivb */
- if (IS_IVB_GT1(dev_priv))
- I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
- _MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
-
- /* WaDisable_RenderCache_OperationalFlush:ivb */
- I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
- /* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
- I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1,
- GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
-
- /* WaApplyL3ControlAndL3ChickenMode:ivb */
- I915_WRITE(GEN7_L3CNTLREG1,
- GEN7_WA_FOR_GEN7_L3_CONTROL);
- I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER,
- GEN7_WA_L3_CHICKEN_MODE);
if (IS_IVB_GT1(dev_priv))
I915_WRITE(GEN7_ROW_CHICKEN2,
_MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
@@ -9086,10 +7364,6 @@
I915_WRITE(GEN7_ROW_CHICKEN2_GT2,
_MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
}
-
- /* WaForceL3Serialization:ivb */
- I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
- ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
/*
* According to the spec, bit 13 (RCZUNIT) must be set on IVB.
@@ -9105,29 +7379,6 @@
g4x_disable_trickle_feed(dev_priv);
- gen7_setup_fixed_func_scheduler(dev_priv);
-
- if (0) { /* causes HiZ corruption on ivb:gt1 */
- /* enable HiZ Raw Stall Optimization */
- I915_WRITE(CACHE_MODE_0_GEN7,
- _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
- }
-
- /* WaDisable4x2SubspanOptimization:ivb */
- I915_WRITE(CACHE_MODE_1,
- _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
-
- /*
- * BSpec recommends 8x4 when MSAA is used,
- * however in practice 16x4 seems fastest.
- *
- * Note that PS/WM thread counts depend on the WIZ hashing
- * disable bit, which we don't touch here, but it's good
- * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
- */
- I915_WRITE(GEN7_GT_MODE,
- _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
snpcr &= ~GEN6_MBC_SNPCR_MASK;
snpcr |= GEN6_MBC_SNPCR_MED;
@@ -9141,27 +7392,10 @@
static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
{
- /* WaDisableEarlyCull:vlv */
- I915_WRITE(_3D_CHICKEN3,
- _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_DISABLE_OBJEND_CULL));
-
/* WaDisableBackToBackFlipFix:vlv */
I915_WRITE(IVB_CHICKEN3,
CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
CHICKEN3_DGMG_DONE_FIX_DISABLE);
-
- /* WaPsdDispatchEnable:vlv */
- /* WaDisablePSDDualDispatchEnable:vlv */
- I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
- _MASKED_BIT_ENABLE(GEN7_MAX_PS_THREAD_DEP |
- GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
-
- /* WaDisable_RenderCache_OperationalFlush:vlv */
- I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
- /* WaForceL3Serialization:vlv */
- I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
- ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
/* WaDisableDopClockGating:vlv */
I915_WRITE(GEN7_ROW_CHICKEN2,
@@ -9171,8 +7405,6 @@
I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
-
- gen7_setup_fixed_func_scheduler(dev_priv);
/*
* According to the spec, bit 13 (RCZUNIT) must be set on IVB.
@@ -9186,30 +7418,6 @@
* Set bit 25, to disable L3_BANK_2x_CLK_GATING */
I915_WRITE(GEN7_UCGCTL4,
I915_READ(GEN7_UCGCTL4) | GEN7_L3BANK2X_CLOCK_GATE_DISABLE);
-
- /*
- * BSpec says this must be set, even though
- * WaDisable4x2SubspanOptimization isn't listed for VLV.
- */
- I915_WRITE(CACHE_MODE_1,
- _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
-
- /*
- * BSpec recommends 8x4 when MSAA is used,
- * however in practice 16x4 seems fastest.
- *
- * Note that PS/WM thread counts depend on the WIZ hashing
- * disable bit, which we don't touch here, but it's good
- * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
- */
- I915_WRITE(GEN7_GT_MODE,
- _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
- /*
- * WaIncreaseL3CreditsForVLVB0:vlv
- * This is the hardware default actually.
- */
- I915_WRITE(GEN7_L3SQCREG1, VLV_B0_WA_L3SQCREG1_VALUE);
/*
* WaDisableVLVClockGating_VBIIssue:vlv
@@ -9245,17 +7453,11 @@
* LSQC Setting Recommendations.
*/
gen8_set_l3sqc_credits(dev_priv, 38, 2);
-
- /*
- * GTT cache may not work with big pages, so if those
- * are ever enabled GTT cache may need to be disabled.
- */
- I915_WRITE(HSW_GTT_CACHE_EN, GTT_CACHE_EN_ALL);
}
static void g4x_init_clock_gating(struct drm_i915_private *dev_priv)
{
- uint32_t dspclk_gate;
+ u32 dspclk_gate;
I915_WRITE(RENCLK_GATE_D1, 0);
I915_WRITE(RENCLK_GATE_D2, VF_UNIT_CLOCK_GATE_DISABLE |
@@ -9269,28 +7471,21 @@
dspclk_gate |= DSSUNIT_CLOCK_GATE_DISABLE;
I915_WRITE(DSPCLK_GATE_D, dspclk_gate);
- /* WaDisableRenderCachePipelinedFlush */
- I915_WRITE(CACHE_MODE_0,
- _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
-
- /* WaDisable_RenderCache_OperationalFlush:g4x */
- I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
g4x_disable_trickle_feed(dev_priv);
}
static void i965gm_init_clock_gating(struct drm_i915_private *dev_priv)
{
- I915_WRITE(RENCLK_GATE_D1, I965_RCC_CLOCK_GATE_DISABLE);
- I915_WRITE(RENCLK_GATE_D2, 0);
- I915_WRITE(DSPCLK_GATE_D, 0);
- I915_WRITE(RAMCLK_GATE_D, 0);
- I915_WRITE16(DEUC, 0);
- I915_WRITE(MI_ARB_STATE,
- _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
+ struct intel_uncore *uncore = &dev_priv->uncore;
- /* WaDisable_RenderCache_OperationalFlush:gen4 */
- I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+ intel_uncore_write(uncore, RENCLK_GATE_D1, I965_RCC_CLOCK_GATE_DISABLE);
+ intel_uncore_write(uncore, RENCLK_GATE_D2, 0);
+ intel_uncore_write(uncore, DSPCLK_GATE_D, 0);
+ intel_uncore_write(uncore, RAMCLK_GATE_D, 0);
+ intel_uncore_write16(uncore, DEUC, 0);
+ intel_uncore_write(uncore,
+ MI_ARB_STATE,
+ _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
}
static void i965g_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -9303,9 +7498,6 @@
I915_WRITE(RENCLK_GATE_D2, 0);
I915_WRITE(MI_ARB_STATE,
_MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
-
- /* WaDisable_RenderCache_OperationalFlush:gen4 */
- I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
}
static void gen3_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -9342,6 +7534,16 @@
I915_WRITE(MEM_MODE,
_MASKED_BIT_ENABLE(MEM_DISPLAY_TRICKLE_FEED_DISABLE));
+
+ /*
+ * Have FBC ignore 3D activity since we use software
+ * render tracking, and otherwise a pure 3D workload
+ * (even if it just renders a single frame and then does
+ * abosultely nothing) would not allow FBC to recompress
+ * until a 2D blit occurs.
+ */
+ I915_WRITE(SCPD0,
+ _MASKED_BIT_ENABLE(SCPD_FBC_IGNORE_3D));
}
static void i830_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -9364,7 +7566,8 @@
static void nop_init_clock_gating(struct drm_i915_private *dev_priv)
{
- DRM_DEBUG_KMS("No clock gating settings or workarounds applied.\n");
+ drm_dbg_kms(&dev_priv->drm,
+ "No clock gating settings or workarounds applied.\n");
}
/**
@@ -9378,11 +7581,13 @@
*/
void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
{
- if (IS_ICELAKE(dev_priv))
+ if (IS_GEN(dev_priv, 12))
+ dev_priv->display.init_clock_gating = tgl_init_clock_gating;
+ else if (IS_GEN(dev_priv, 11))
dev_priv->display.init_clock_gating = icl_init_clock_gating;
else if (IS_CANNONLAKE(dev_priv))
dev_priv->display.init_clock_gating = cnl_init_clock_gating;
- else if (IS_COFFEELAKE(dev_priv))
+ else if (IS_COFFEELAKE(dev_priv) || IS_COMETLAKE(dev_priv))
dev_priv->display.init_clock_gating = cfl_init_clock_gating;
else if (IS_SKYLAKE(dev_priv))
dev_priv->display.init_clock_gating = skl_init_clock_gating;
@@ -9402,9 +7607,9 @@
dev_priv->display.init_clock_gating = ivb_init_clock_gating;
else if (IS_VALLEYVIEW(dev_priv))
dev_priv->display.init_clock_gating = vlv_init_clock_gating;
- else if (IS_GEN6(dev_priv))
+ else if (IS_GEN(dev_priv, 6))
dev_priv->display.init_clock_gating = gen6_init_clock_gating;
- else if (IS_GEN5(dev_priv))
+ else if (IS_GEN(dev_priv, 5))
dev_priv->display.init_clock_gating = ilk_init_clock_gating;
else if (IS_G4X(dev_priv))
dev_priv->display.init_clock_gating = g4x_init_clock_gating;
@@ -9412,11 +7617,11 @@
dev_priv->display.init_clock_gating = i965gm_init_clock_gating;
else if (IS_I965G(dev_priv))
dev_priv->display.init_clock_gating = i965g_init_clock_gating;
- else if (IS_GEN3(dev_priv))
+ else if (IS_GEN(dev_priv, 3))
dev_priv->display.init_clock_gating = gen3_init_clock_gating;
else if (IS_I85X(dev_priv) || IS_I865G(dev_priv))
dev_priv->display.init_clock_gating = i85x_init_clock_gating;
- else if (IS_GEN2(dev_priv))
+ else if (IS_GEN(dev_priv, 2))
dev_priv->display.init_clock_gating = i830_init_clock_gating;
else {
MISSING_CASE(INTEL_DEVID(dev_priv));
@@ -9427,26 +7632,25 @@
/* Set up chip specific power management-related functions */
void intel_init_pm(struct drm_i915_private *dev_priv)
{
- intel_fbc_init(dev_priv);
-
/* For cxsr */
if (IS_PINEVIEW(dev_priv))
- i915_pineview_get_mem_freq(dev_priv);
- else if (IS_GEN5(dev_priv))
- i915_ironlake_get_mem_freq(dev_priv);
+ pnv_get_mem_freq(dev_priv);
+ else if (IS_GEN(dev_priv, 5))
+ ilk_get_mem_freq(dev_priv);
+
+ if (intel_has_sagv(dev_priv))
+ skl_setup_sagv_block_time(dev_priv);
/* For FIFO watermark updates */
if (INTEL_GEN(dev_priv) >= 9) {
skl_setup_wm_latency(dev_priv);
- dev_priv->display.initial_watermarks = skl_initial_wm;
- dev_priv->display.atomic_update_watermarks = skl_atomic_update_crtc_wm;
dev_priv->display.compute_global_watermarks = skl_compute_wm;
} else if (HAS_PCH_SPLIT(dev_priv)) {
ilk_setup_wm_latency(dev_priv);
- if ((IS_GEN5(dev_priv) && dev_priv->wm.pri_latency[1] &&
+ if ((IS_GEN(dev_priv, 5) && dev_priv->wm.pri_latency[1] &&
dev_priv->wm.spr_latency[1] && dev_priv->wm.cur_latency[1]) ||
- (!IS_GEN5(dev_priv) && dev_priv->wm.pri_latency[0] &&
+ (!IS_GEN(dev_priv, 5) && dev_priv->wm.pri_latency[0] &&
dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) {
dev_priv->display.compute_pipe_wm = ilk_compute_pipe_wm;
dev_priv->display.compute_intermediate_wm =
@@ -9456,8 +7660,9 @@
dev_priv->display.optimize_watermarks =
ilk_optimize_watermarks;
} else {
- DRM_DEBUG_KMS("Failed to read display plane latency. "
- "Disable CxSR\n");
+ drm_dbg_kms(&dev_priv->drm,
+ "Failed to read display plane latency. "
+ "Disable CxSR\n");
}
} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
vlv_setup_wm_latency(dev_priv);
@@ -9473,11 +7678,12 @@
dev_priv->display.initial_watermarks = g4x_initial_watermarks;
dev_priv->display.optimize_watermarks = g4x_optimize_watermarks;
} else if (IS_PINEVIEW(dev_priv)) {
- if (!intel_get_cxsr_latency(IS_PINEVIEW_G(dev_priv),
+ if (!intel_get_cxsr_latency(!IS_MOBILE(dev_priv),
dev_priv->is_ddr3,
dev_priv->fsb_freq,
dev_priv->mem_freq)) {
- DRM_INFO("failed to find known CxSR latency "
+ drm_info(&dev_priv->drm,
+ "failed to find known CxSR latency "
"(found ddr%s fsb freq %d, mem freq %d), "
"disabling CxSR\n",
(dev_priv->is_ddr3 == 1) ? "3" : "2",
@@ -9486,14 +7692,14 @@
intel_set_memory_cxsr(dev_priv, false);
dev_priv->display.update_wm = NULL;
} else
- dev_priv->display.update_wm = pineview_update_wm;
- } else if (IS_GEN4(dev_priv)) {
+ dev_priv->display.update_wm = pnv_update_wm;
+ } else if (IS_GEN(dev_priv, 4)) {
dev_priv->display.update_wm = i965_update_wm;
- } else if (IS_GEN3(dev_priv)) {
+ } else if (IS_GEN(dev_priv, 3)) {
dev_priv->display.update_wm = i9xx_update_wm;
dev_priv->display.get_fifo_size = i9xx_get_fifo_size;
- } else if (IS_GEN2(dev_priv)) {
- if (INTEL_INFO(dev_priv)->num_pipes == 1) {
+ } else if (IS_GEN(dev_priv, 2)) {
+ if (INTEL_NUM_PIPES(dev_priv) == 1) {
dev_priv->display.update_wm = i845_update_wm;
dev_priv->display.get_fifo_size = i845_get_fifo_size;
} else {
@@ -9501,429 +7707,99 @@
dev_priv->display.get_fifo_size = i830_get_fifo_size;
}
} else {
- DRM_ERROR("unexpected fall-through in intel_init_pm\n");
+ drm_err(&dev_priv->drm,
+ "unexpected fall-through in %s\n", __func__);
}
-}
-
-static inline int gen6_check_mailbox_status(struct drm_i915_private *dev_priv)
-{
- uint32_t flags =
- I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK;
-
- switch (flags) {
- case GEN6_PCODE_SUCCESS:
- return 0;
- case GEN6_PCODE_UNIMPLEMENTED_CMD:
- return -ENODEV;
- case GEN6_PCODE_ILLEGAL_CMD:
- return -ENXIO;
- case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
- case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
- return -EOVERFLOW;
- case GEN6_PCODE_TIMEOUT:
- return -ETIMEDOUT;
- default:
- MISSING_CASE(flags);
- return 0;
- }
-}
-
-static inline int gen7_check_mailbox_status(struct drm_i915_private *dev_priv)
-{
- uint32_t flags =
- I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK;
-
- switch (flags) {
- case GEN6_PCODE_SUCCESS:
- return 0;
- case GEN6_PCODE_ILLEGAL_CMD:
- return -ENXIO;
- case GEN7_PCODE_TIMEOUT:
- return -ETIMEDOUT;
- case GEN7_PCODE_ILLEGAL_DATA:
- return -EINVAL;
- case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
- return -EOVERFLOW;
- default:
- MISSING_CASE(flags);
- return 0;
- }
-}
-
-int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val)
-{
- int status;
-
- WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
-
- /* GEN6_PCODE_* are outside of the forcewake domain, we can
- * use te fw I915_READ variants to reduce the amount of work
- * required when reading/writing.
- */
-
- if (I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) {
- DRM_DEBUG_DRIVER("warning: pcode (read from mbox %x) mailbox access failed for %ps\n",
- mbox, __builtin_return_address(0));
- return -EAGAIN;
- }
-
- I915_WRITE_FW(GEN6_PCODE_DATA, *val);
- I915_WRITE_FW(GEN6_PCODE_DATA1, 0);
- I915_WRITE_FW(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY | mbox);
-
- if (__intel_wait_for_register_fw(dev_priv,
- GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0,
- 500, 0, NULL)) {
- DRM_ERROR("timeout waiting for pcode read (from mbox %x) to finish for %ps\n",
- mbox, __builtin_return_address(0));
- return -ETIMEDOUT;
- }
-
- *val = I915_READ_FW(GEN6_PCODE_DATA);
- I915_WRITE_FW(GEN6_PCODE_DATA, 0);
-
- if (INTEL_GEN(dev_priv) > 6)
- status = gen7_check_mailbox_status(dev_priv);
- else
- status = gen6_check_mailbox_status(dev_priv);
-
- if (status) {
- DRM_DEBUG_DRIVER("warning: pcode (read from mbox %x) mailbox access failed for %ps: %d\n",
- mbox, __builtin_return_address(0), status);
- return status;
- }
-
- return 0;
-}
-
-int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv,
- u32 mbox, u32 val,
- int fast_timeout_us, int slow_timeout_ms)
-{
- int status;
-
- WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
-
- /* GEN6_PCODE_* are outside of the forcewake domain, we can
- * use te fw I915_READ variants to reduce the amount of work
- * required when reading/writing.
- */
-
- if (I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) {
- DRM_DEBUG_DRIVER("warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps\n",
- val, mbox, __builtin_return_address(0));
- return -EAGAIN;
- }
-
- I915_WRITE_FW(GEN6_PCODE_DATA, val);
- I915_WRITE_FW(GEN6_PCODE_DATA1, 0);
- I915_WRITE_FW(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY | mbox);
-
- if (__intel_wait_for_register_fw(dev_priv,
- GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0,
- fast_timeout_us, slow_timeout_ms,
- NULL)) {
- DRM_ERROR("timeout waiting for pcode write of 0x%08x to mbox %x to finish for %ps\n",
- val, mbox, __builtin_return_address(0));
- return -ETIMEDOUT;
- }
-
- I915_WRITE_FW(GEN6_PCODE_DATA, 0);
-
- if (INTEL_GEN(dev_priv) > 6)
- status = gen7_check_mailbox_status(dev_priv);
- else
- status = gen6_check_mailbox_status(dev_priv);
-
- if (status) {
- DRM_DEBUG_DRIVER("warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps: %d\n",
- val, mbox, __builtin_return_address(0), status);
- return status;
- }
-
- return 0;
-}
-
-static bool skl_pcode_try_request(struct drm_i915_private *dev_priv, u32 mbox,
- u32 request, u32 reply_mask, u32 reply,
- u32 *status)
-{
- u32 val = request;
-
- *status = sandybridge_pcode_read(dev_priv, mbox, &val);
-
- return *status || ((val & reply_mask) == reply);
-}
-
-/**
- * skl_pcode_request - send PCODE request until acknowledgment
- * @dev_priv: device private
- * @mbox: PCODE mailbox ID the request is targeted for
- * @request: request ID
- * @reply_mask: mask used to check for request acknowledgment
- * @reply: value used to check for request acknowledgment
- * @timeout_base_ms: timeout for polling with preemption enabled
- *
- * Keep resending the @request to @mbox until PCODE acknowledges it, PCODE
- * reports an error or an overall timeout of @timeout_base_ms+50 ms expires.
- * The request is acknowledged once the PCODE reply dword equals @reply after
- * applying @reply_mask. Polling is first attempted with preemption enabled
- * for @timeout_base_ms and if this times out for another 50 ms with
- * preemption disabled.
- *
- * Returns 0 on success, %-ETIMEDOUT in case of a timeout, <0 in case of some
- * other error as reported by PCODE.
- */
-int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
- u32 reply_mask, u32 reply, int timeout_base_ms)
-{
- u32 status;
- int ret;
-
- WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
-
-#define COND skl_pcode_try_request(dev_priv, mbox, request, reply_mask, reply, \
- &status)
-
- /*
- * Prime the PCODE by doing a request first. Normally it guarantees
- * that a subsequent request, at most @timeout_base_ms later, succeeds.
- * _wait_for() doesn't guarantee when its passed condition is evaluated
- * first, so send the first request explicitly.
- */
- if (COND) {
- ret = 0;
- goto out;
- }
- ret = _wait_for(COND, timeout_base_ms * 1000, 10, 10);
- if (!ret)
- goto out;
-
- /*
- * The above can time out if the number of requests was low (2 in the
- * worst case) _and_ PCODE was busy for some reason even after a
- * (queued) request and @timeout_base_ms delay. As a workaround retry
- * the poll with preemption disabled to maximize the number of
- * requests. Increase the timeout from @timeout_base_ms to 50ms to
- * account for interrupts that could reduce the number of these
- * requests, and for any quirks of the PCODE firmware that delays
- * the request completion.
- */
- DRM_DEBUG_KMS("PCODE timeout, retrying with preemption disabled\n");
- WARN_ON_ONCE(timeout_base_ms > 3);
- preempt_disable();
- ret = wait_for_atomic(COND, 50);
- preempt_enable();
-
-out:
- return ret ? ret : status;
-#undef COND
-}
-
-static int byt_gpu_freq(struct drm_i915_private *dev_priv, int val)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- /*
- * N = val - 0xb7
- * Slow = Fast = GPLL ref * N
- */
- return DIV_ROUND_CLOSEST(rps->gpll_ref_freq * (val - 0xb7), 1000);
-}
-
-static int byt_freq_opcode(struct drm_i915_private *dev_priv, int val)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- return DIV_ROUND_CLOSEST(1000 * val, rps->gpll_ref_freq) + 0xb7;
-}
-
-static int chv_gpu_freq(struct drm_i915_private *dev_priv, int val)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- /*
- * N = val / 2
- * CU (slow) = CU2x (fast) / 2 = GPLL ref * N / 2
- */
- return DIV_ROUND_CLOSEST(rps->gpll_ref_freq * val, 2 * 2 * 1000);
-}
-
-static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val)
-{
- struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
- /* CHV needs even values */
- return DIV_ROUND_CLOSEST(2 * 1000 * val, rps->gpll_ref_freq) * 2;
-}
-
-int intel_gpu_freq(struct drm_i915_private *dev_priv, int val)
-{
- if (INTEL_GEN(dev_priv) >= 9)
- return DIV_ROUND_CLOSEST(val * GT_FREQUENCY_MULTIPLIER,
- GEN9_FREQ_SCALER);
- else if (IS_CHERRYVIEW(dev_priv))
- return chv_gpu_freq(dev_priv, val);
- else if (IS_VALLEYVIEW(dev_priv))
- return byt_gpu_freq(dev_priv, val);
- else
- return val * GT_FREQUENCY_MULTIPLIER;
-}
-
-int intel_freq_opcode(struct drm_i915_private *dev_priv, int val)
-{
- if (INTEL_GEN(dev_priv) >= 9)
- return DIV_ROUND_CLOSEST(val * GEN9_FREQ_SCALER,
- GT_FREQUENCY_MULTIPLIER);
- else if (IS_CHERRYVIEW(dev_priv))
- return chv_freq_opcode(dev_priv, val);
- else if (IS_VALLEYVIEW(dev_priv))
- return byt_freq_opcode(dev_priv, val);
- else
- return DIV_ROUND_CLOSEST(val, GT_FREQUENCY_MULTIPLIER);
}
void intel_pm_setup(struct drm_i915_private *dev_priv)
{
- mutex_init(&dev_priv->pcu_lock);
- mutex_init(&dev_priv->gt_pm.rps.power.mutex);
-
- atomic_set(&dev_priv->gt_pm.rps.num_waiters, 0);
-
dev_priv->runtime_pm.suspended = false;
atomic_set(&dev_priv->runtime_pm.wakeref_count, 0);
}
-static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
- const i915_reg_t reg)
+static struct intel_global_state *intel_dbuf_duplicate_state(struct intel_global_obj *obj)
{
- u32 lower, upper, tmp;
- int loop = 2;
+ struct intel_dbuf_state *dbuf_state;
- /*
- * The register accessed do not need forcewake. We borrow
- * uncore lock to prevent concurrent access to range reg.
- */
- lockdep_assert_held(&dev_priv->uncore.lock);
+ dbuf_state = kmemdup(obj->state, sizeof(*dbuf_state), GFP_KERNEL);
+ if (!dbuf_state)
+ return NULL;
- /*
- * vlv and chv residency counters are 40 bits in width.
- * With a control bit, we can choose between upper or lower
- * 32bit window into this counter.
- *
- * Although we always use the counter in high-range mode elsewhere,
- * userspace may attempt to read the value before rc6 is initialised,
- * before we have set the default VLV_COUNTER_CONTROL value. So always
- * set the high bit to be safe.
- */
- I915_WRITE_FW(VLV_COUNTER_CONTROL,
- _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
- upper = I915_READ_FW(reg);
- do {
- tmp = upper;
-
- I915_WRITE_FW(VLV_COUNTER_CONTROL,
- _MASKED_BIT_DISABLE(VLV_COUNT_RANGE_HIGH));
- lower = I915_READ_FW(reg);
-
- I915_WRITE_FW(VLV_COUNTER_CONTROL,
- _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
- upper = I915_READ_FW(reg);
- } while (upper != tmp && --loop);
-
- /*
- * Everywhere else we always use VLV_COUNTER_CONTROL with the
- * VLV_COUNT_RANGE_HIGH bit set - so it is safe to leave it set
- * now.
- */
-
- return lower | (u64)upper << 8;
+ return &dbuf_state->base;
}
-u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
- const i915_reg_t reg)
+static void intel_dbuf_destroy_state(struct intel_global_obj *obj,
+ struct intel_global_state *state)
{
- u64 time_hw, prev_hw, overflow_hw;
- unsigned int fw_domains;
- unsigned long flags;
- unsigned int i;
- u32 mul, div;
-
- if (!HAS_RC6(dev_priv))
- return 0;
-
- /*
- * Store previous hw counter values for counter wrap-around handling.
- *
- * There are only four interesting registers and they live next to each
- * other so we can use the relative address, compared to the smallest
- * one as the index into driver storage.
- */
- i = (i915_mmio_reg_offset(reg) -
- i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32);
- if (WARN_ON_ONCE(i >= ARRAY_SIZE(dev_priv->gt_pm.rc6.cur_residency)))
- return 0;
-
- fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ);
-
- spin_lock_irqsave(&dev_priv->uncore.lock, flags);
- intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
-
- /* On VLV and CHV, residency time is in CZ units rather than 1.28us */
- if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
- mul = 1000000;
- div = dev_priv->czclk_freq;
- overflow_hw = BIT_ULL(40);
- time_hw = vlv_residency_raw(dev_priv, reg);
- } else {
- /* 833.33ns units on Gen9LP, 1.28us elsewhere. */
- if (IS_GEN9_LP(dev_priv)) {
- mul = 10000;
- div = 12;
- } else {
- mul = 1280;
- div = 1;
- }
-
- overflow_hw = BIT_ULL(32);
- time_hw = I915_READ_FW(reg);
- }
-
- /*
- * Counter wrap handling.
- *
- * But relying on a sufficient frequency of queries otherwise counters
- * can still wrap.
- */
- prev_hw = dev_priv->gt_pm.rc6.prev_hw_residency[i];
- dev_priv->gt_pm.rc6.prev_hw_residency[i] = time_hw;
-
- /* RC6 delta from last sample. */
- if (time_hw >= prev_hw)
- time_hw -= prev_hw;
- else
- time_hw += overflow_hw - prev_hw;
-
- /* Add delta to RC6 extended raw driver copy. */
- time_hw += dev_priv->gt_pm.rc6.cur_residency[i];
- dev_priv->gt_pm.rc6.cur_residency[i] = time_hw;
-
- intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
- spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
-
- return mul_u64_u32_div(time_hw, mul, div);
+ kfree(state);
}
-u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat)
+static const struct intel_global_state_funcs intel_dbuf_funcs = {
+ .atomic_duplicate_state = intel_dbuf_duplicate_state,
+ .atomic_destroy_state = intel_dbuf_destroy_state,
+};
+
+struct intel_dbuf_state *
+intel_atomic_get_dbuf_state(struct intel_atomic_state *state)
{
- u32 cagf;
+ struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+ struct intel_global_state *dbuf_state;
- if (INTEL_GEN(dev_priv) >= 9)
- cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
- else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
- cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
- else
- cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
+ dbuf_state = intel_atomic_get_global_obj_state(state, &dev_priv->dbuf.obj);
+ if (IS_ERR(dbuf_state))
+ return ERR_CAST(dbuf_state);
- return cagf;
+ return to_intel_dbuf_state(dbuf_state);
+}
+
+int intel_dbuf_init(struct drm_i915_private *dev_priv)
+{
+ struct intel_dbuf_state *dbuf_state;
+
+ dbuf_state = kzalloc(sizeof(*dbuf_state), GFP_KERNEL);
+ if (!dbuf_state)
+ return -ENOMEM;
+
+ intel_atomic_global_obj_init(dev_priv, &dev_priv->dbuf.obj,
+ &dbuf_state->base, &intel_dbuf_funcs);
+
+ return 0;
+}
+
+void intel_dbuf_pre_plane_update(struct intel_atomic_state *state)
+{
+ struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+ const struct intel_dbuf_state *new_dbuf_state =
+ intel_atomic_get_new_dbuf_state(state);
+ const struct intel_dbuf_state *old_dbuf_state =
+ intel_atomic_get_old_dbuf_state(state);
+
+ if (!new_dbuf_state ||
+ new_dbuf_state->enabled_slices == old_dbuf_state->enabled_slices)
+ return;
+
+ WARN_ON(!new_dbuf_state->base.changed);
+
+ gen9_dbuf_slices_update(dev_priv,
+ old_dbuf_state->enabled_slices |
+ new_dbuf_state->enabled_slices);
+}
+
+void intel_dbuf_post_plane_update(struct intel_atomic_state *state)
+{
+ struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+ const struct intel_dbuf_state *new_dbuf_state =
+ intel_atomic_get_new_dbuf_state(state);
+ const struct intel_dbuf_state *old_dbuf_state =
+ intel_atomic_get_old_dbuf_state(state);
+
+ if (!new_dbuf_state ||
+ new_dbuf_state->enabled_slices == old_dbuf_state->enabled_slices)
+ return;
+
+ WARN_ON(!new_dbuf_state->base.changed);
+
+ gen9_dbuf_slices_update(dev_priv,
+ new_dbuf_state->enabled_slices);
}
--
Gitblit v1.6.2