lkml.org 
[lkml]   [2011]   [Oct]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 05/12] FB_ATY: Move register accesses out of line
Date
From: Andi Kleen <ak@linux.intel.com>

This fixes size regressions like

radeon_set_suspend 1724 7873 +6149
radeon_reinitialize_M10 3974 9285 +5311
radeon_pm_disable_dynamic_mode 868 6125 +5257
radeon_pm_enable_dynamic_mode 985 6065 +5080
radeon_pm_start_mclk_sclk - 4614 +4614
radeon_write_mode 1252 5377 +4125

among others compared to a non force inline kernel.

Cc: David Airlie <airlied@linux.ie>
Cc: benh@kernel.crashing.org
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
drivers/video/aty/radeon_accel.c | 88 ++++++++++++++++++++++++++++++++++
drivers/video/aty/radeonfb.h | 96 +++-----------------------------------
2 files changed, 95 insertions(+), 89 deletions(-)

diff --git a/drivers/video/aty/radeon_accel.c b/drivers/video/aty/radeon_accel.c
index a469a3d..0f1e367 100644
--- a/drivers/video/aty/radeon_accel.c
+++ b/drivers/video/aty/radeon_accel.c
@@ -326,3 +326,91 @@ void radeonfb_engine_init (struct radeonfb_info *rinfo)

radeon_engine_idle ();
}
+
+
+void _OUTREGP(struct radeonfb_info *rinfo, u32 addr, u32 val, u32 mask)
+{
+ unsigned long flags;
+ unsigned int tmp;
+
+ spin_lock_irqsave(&rinfo->reg_lock, flags);
+ tmp = INREG(addr);
+ tmp &= (mask);
+ tmp |= (val);
+ OUTREG(addr, tmp);
+ spin_unlock_irqrestore(&rinfo->reg_lock, flags);
+}
+
+
+/*
+ * Note about PLL register accesses:
+ *
+ * I have removed the spinlock on them on purpose. The driver now
+ * expects that it will only manipulate the PLL registers in normal
+ * task environment, where radeon_msleep() will be called, protected
+ * by a semaphore (currently the console semaphore) so that no conflict
+ * will happen on the PLL register index.
+ *
+ * With the latest changes to the VT layer, this is guaranteed for all
+ * calls except the actual drawing/blits which aren't supposed to use
+ * the PLL registers anyway
+ *
+ * This is very important for the workarounds to work properly. The only
+ * possible exception to this rule is the call to unblank(), which may
+ * be done at irq time if an oops is in progress.
+ */
+void radeon_pll_errata_after_index(struct radeonfb_info *rinfo)
+{
+ if (!(rinfo->errata & CHIP_ERRATA_PLL_DUMMYREADS))
+ return;
+
+ (void)INREG(CLOCK_CNTL_DATA);
+ (void)INREG(CRTC_GEN_CNTL);
+}
+
+void radeon_pll_errata_after_data(struct radeonfb_info *rinfo)
+{
+ if (rinfo->errata & CHIP_ERRATA_PLL_DELAY) {
+ /* we can't deal with posted writes here ... */
+ _radeon_msleep(rinfo, 5);
+ }
+ if (rinfo->errata & CHIP_ERRATA_R300_CG) {
+ u32 save, tmp;
+ save = INREG(CLOCK_CNTL_INDEX);
+ tmp = save & ~(0x3f | PLL_WR_EN);
+ OUTREG(CLOCK_CNTL_INDEX, tmp);
+ tmp = INREG(CLOCK_CNTL_DATA);
+ OUTREG(CLOCK_CNTL_INDEX, save);
+ }
+}
+
+u32 __INPLL(struct radeonfb_info *rinfo, u32 addr)
+{
+ u32 data;
+
+ OUTREG8(CLOCK_CNTL_INDEX, addr & 0x0000003f);
+ radeon_pll_errata_after_index(rinfo);
+ data = INREG(CLOCK_CNTL_DATA);
+ radeon_pll_errata_after_data(rinfo);
+ return data;
+}
+
+void __OUTPLL(struct radeonfb_info *rinfo, unsigned int index, u32 val)
+{
+
+ OUTREG8(CLOCK_CNTL_INDEX, (index & 0x0000003f) | 0x00000080);
+ radeon_pll_errata_after_index(rinfo);
+ OUTREG(CLOCK_CNTL_DATA, val);
+ radeon_pll_errata_after_data(rinfo);
+}
+
+void __OUTPLLP(struct radeonfb_info *rinfo, unsigned int index, u32 val, u32 mask)
+{
+ unsigned int tmp;
+
+ tmp = __INPLL(rinfo, index);
+ tmp &= (mask);
+ tmp |= (val);
+ __OUTPLL(rinfo, index, tmp);
+}
+
diff --git a/drivers/video/aty/radeonfb.h b/drivers/video/aty/radeonfb.h
index 7351e66..cde9c2e 100644
--- a/drivers/video/aty/radeonfb.h
+++ b/drivers/video/aty/radeonfb.h
@@ -393,98 +393,16 @@ static inline void _radeon_msleep(struct radeonfb_info *rinfo, unsigned long ms)
#define INREG(addr) readl((rinfo->mmio_base)+addr)
#define OUTREG(addr,val) writel(val, (rinfo->mmio_base)+addr)

-static inline void _OUTREGP(struct radeonfb_info *rinfo, u32 addr,
- u32 val, u32 mask)
-{
- unsigned long flags;
- unsigned int tmp;
-
- spin_lock_irqsave(&rinfo->reg_lock, flags);
- tmp = INREG(addr);
- tmp &= (mask);
- tmp |= (val);
- OUTREG(addr, tmp);
- spin_unlock_irqrestore(&rinfo->reg_lock, flags);
-}
+void _OUTREGP(struct radeonfb_info *rinfo, u32 addr, u32 val, u32 mask);
+void __OUTPLLP(struct radeonfb_info *rinfo, unsigned int index,
+ u32 val, u32 mask);
+void __OUTPLL(struct radeonfb_info *rinfo, unsigned int index, u32 val);
+u32 __INPLL(struct radeonfb_info *rinfo, u32 addr);
+void radeon_pll_errata_after_data(struct radeonfb_info *rinfo);
+void radeon_pll_errata_after_index(struct radeonfb_info *rinfo);

#define OUTREGP(addr,val,mask) _OUTREGP(rinfo, addr, val,mask)

-/*
- * Note about PLL register accesses:
- *
- * I have removed the spinlock on them on purpose. The driver now
- * expects that it will only manipulate the PLL registers in normal
- * task environment, where radeon_msleep() will be called, protected
- * by a semaphore (currently the console semaphore) so that no conflict
- * will happen on the PLL register index.
- *
- * With the latest changes to the VT layer, this is guaranteed for all
- * calls except the actual drawing/blits which aren't supposed to use
- * the PLL registers anyway
- *
- * This is very important for the workarounds to work properly. The only
- * possible exception to this rule is the call to unblank(), which may
- * be done at irq time if an oops is in progress.
- */
-static inline void radeon_pll_errata_after_index(struct radeonfb_info *rinfo)
-{
- if (!(rinfo->errata & CHIP_ERRATA_PLL_DUMMYREADS))
- return;
-
- (void)INREG(CLOCK_CNTL_DATA);
- (void)INREG(CRTC_GEN_CNTL);
-}
-
-static inline void radeon_pll_errata_after_data(struct radeonfb_info *rinfo)
-{
- if (rinfo->errata & CHIP_ERRATA_PLL_DELAY) {
- /* we can't deal with posted writes here ... */
- _radeon_msleep(rinfo, 5);
- }
- if (rinfo->errata & CHIP_ERRATA_R300_CG) {
- u32 save, tmp;
- save = INREG(CLOCK_CNTL_INDEX);
- tmp = save & ~(0x3f | PLL_WR_EN);
- OUTREG(CLOCK_CNTL_INDEX, tmp);
- tmp = INREG(CLOCK_CNTL_DATA);
- OUTREG(CLOCK_CNTL_INDEX, save);
- }
-}
-
-static inline u32 __INPLL(struct radeonfb_info *rinfo, u32 addr)
-{
- u32 data;
-
- OUTREG8(CLOCK_CNTL_INDEX, addr & 0x0000003f);
- radeon_pll_errata_after_index(rinfo);
- data = INREG(CLOCK_CNTL_DATA);
- radeon_pll_errata_after_data(rinfo);
- return data;
-}
-
-static inline void __OUTPLL(struct radeonfb_info *rinfo, unsigned int index,
- u32 val)
-{
-
- OUTREG8(CLOCK_CNTL_INDEX, (index & 0x0000003f) | 0x00000080);
- radeon_pll_errata_after_index(rinfo);
- OUTREG(CLOCK_CNTL_DATA, val);
- radeon_pll_errata_after_data(rinfo);
-}
-
-
-static inline void __OUTPLLP(struct radeonfb_info *rinfo, unsigned int index,
- u32 val, u32 mask)
-{
- unsigned int tmp;
-
- tmp = __INPLL(rinfo, index);
- tmp &= (mask);
- tmp |= (val);
- __OUTPLL(rinfo, index, tmp);
-}
-
-
#define INPLL(addr) __INPLL(rinfo, addr)
#define OUTPLL(index, val) __OUTPLL(rinfo, index, val)
#define OUTPLLP(index, val, mask) __OUTPLLP(rinfo, index, val, mask)
--
1.7.4.4


\
 
 \ /
  Last update: 2011-10-14 01:13    [W:0.066 / U:0.556 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site