On Thu, 13 Oct 2011 16:08:51 -0700 Andi Kleen andi@firstfloor.org wrote:
From: Andi Kleen ak@linux.intel.com
With the tracing code in there they are far too big to inline.
.text savings compared to a non force inline kernel:
i915_restore_display 4393 12036 +7643 i915_save_display 4295 11459 +7164 i915_handle_error 2979 6666 +3687 i915_driver_irq_handler 2923 5086 +2163 i915_ringbuffer_info 458 1661 +1203 i915_save_vga - 1200 +1200 i915_driver_irq_uninstall 453 1624 +1171 i915_driver_irq_postinstall 913 2078 +1165 ironlake_enable_drps 719 1872 +1153 i915_restore_vga - 1142 +1142 intel_display_capture_error_state 784 2030 +1246 intel_init_emon 719 2016 +1297
and more ...
[AK: these are older numbers, with the new SNB forcewake checks it will be even worse]
Cc: keithp@keithp.com Signed-off-by: Andi Kleen ak@linux.intel.com
drivers/gpu/drm/i915/i915_drv.c | 40 +++++++++++++++++++++++++++++++++++++++ drivers/gpu/drm/i915/i915_drv.h | 22 ++------------------ 2 files changed, 43 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f07e425..c2de142 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -895,3 +895,43 @@ module_exit(i915_exit); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL and additional rights");
+/* We give fast paths for the really cool registers */ +#define NEEDS_FORCE_WAKE(dev_priv, reg) \
- (((dev_priv)->info->gen >= 6) && \
- ((reg) < 0x40000) && \
- ((reg) != FORCEWAKE))
+#define __i915_read(x, y) \ +u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
- u##x val = 0; \
- if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
gen6_gt_force_wake_get(dev_priv); \val = read##y(dev_priv->regs + reg); \gen6_gt_force_wake_put(dev_priv); \- } else { \
val = read##y(dev_priv->regs + reg); \- } \
- trace_i915_reg_rw(false, reg, val, sizeof(val)); \
- return val; \
+}
+__i915_read(8, b) +__i915_read(16, w) +__i915_read(32, l) +__i915_read(64, q) +#undef __i915_read
+#define __i915_write(x, y) \ +void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \
- trace_i915_reg_rw(true, reg, val, sizeof(val)); \
- if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
__gen6_gt_wait_for_fifo(dev_priv); \- } \
- write##y(val, dev_priv->regs + reg); \
+} +__i915_write(8, b) +__i915_write(16, w) +__i915_write(32, l) +__i915_write(64, q) +#undef __i915_write diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 7916bd9..7d171ea 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1354,18 +1354,7 @@ void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv); ((reg) != FORCEWAKE))
#define __i915_read(x, y) \ -static inline u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
- u##x val = 0; \
- if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
gen6_gt_force_wake_get(dev_priv); \val = read##y(dev_priv->regs + reg); \gen6_gt_force_wake_put(dev_priv); \- } else { \
val = read##y(dev_priv->regs + reg); \- } \
- trace_i915_reg_rw(false, reg, val, sizeof(val)); \
- return val; \
-}
- u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg);
__i915_read(8, b) __i915_read(16, w) @@ -1374,13 +1363,8 @@ __i915_read(64, q) #undef __i915_read
#define __i915_write(x, y) \ -static inline void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \
- trace_i915_reg_rw(true, reg, val, sizeof(val)); \
- if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
__gen6_gt_wait_for_fifo(dev_priv); \- } \
- write##y(val, dev_priv->regs + reg); \
-}
- void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val);
__i915_write(8, b) __i915_write(16, w) __i915_write(32, l)
Acked-by: Ben Widawsky ben@bwidawsk.net
The forcewake increased size should have been fixed a bit with the forcewake struct encapsulation patch I posted to intel-gfx mailing list. Keith, if you take this, could you also look into that patch? 1315951648-5380-1-git-send-email-ben@bwidawsk.net