dri-devel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Lauri Kasanen <cand@gmx.com>
To: dri-devel@lists.freedesktop.org
Subject: [PATCH] drm/radeon: Inline r100_mm_rreg, -wreg, v3
Date: Sun, 20 Apr 2014 20:29:33 +0300	[thread overview]
Message-ID: <20140420202933.78b3e355.cand@gmx.com> (raw)

This was originally un-inlined by Andi Kleen in 2011 citing size concerns.
Indeed, a first attempt at inlining it grew radeon.ko by 7%.

However, 2% of cpu is spent in this function. Simply inlining it gave 1% more fps
in Urban Terror.

v2: We know the minimum MMIO size. Adding it to the if allows the compiler to
optimize the branch out, improving both performance and size.

The v2 patch decreases radeon.ko size by 2%. I didn't re-benchmark, but common sense
says perf is now more than 1% better.

v3: Also change _wreg, make the threshold a define.

Inlining _wreg increased the size a bit compared to v2, so now radeon.ko
is only 1% smaller.

Signed-off-by: Lauri Kasanen <cand@gmx.com>
---
 drivers/gpu/drm/radeon/r100.c   | 33 ---------------------------------
 drivers/gpu/drm/radeon/radeon.h | 40 ++++++++++++++++++++++++++++++++++++----
 2 files changed, 36 insertions(+), 37 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index b6c3264..a4e7871 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -4086,39 +4086,6 @@ int r100_init(struct radeon_device *rdev)
 	return 0;
 }
 
-uint32_t r100_mm_rreg(struct radeon_device *rdev, uint32_t reg,
-		      bool always_indirect)
-{
-	if (reg < rdev->rmmio_size && !always_indirect)
-		return readl(((void __iomem *)rdev->rmmio) + reg);
-	else {
-		unsigned long flags;
-		uint32_t ret;
-
-		spin_lock_irqsave(&rdev->mmio_idx_lock, flags);
-		writel(reg, ((void __iomem *)rdev->rmmio) + RADEON_MM_INDEX);
-		ret = readl(((void __iomem *)rdev->rmmio) + RADEON_MM_DATA);
-		spin_unlock_irqrestore(&rdev->mmio_idx_lock, flags);
-
-		return ret;
-	}
-}
-
-void r100_mm_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v,
-		  bool always_indirect)
-{
-	if (reg < rdev->rmmio_size && !always_indirect)
-		writel(v, ((void __iomem *)rdev->rmmio) + reg);
-	else {
-		unsigned long flags;
-
-		spin_lock_irqsave(&rdev->mmio_idx_lock, flags);
-		writel(reg, ((void __iomem *)rdev->rmmio) + RADEON_MM_INDEX);
-		writel(v, ((void __iomem *)rdev->rmmio) + RADEON_MM_DATA);
-		spin_unlock_irqrestore(&rdev->mmio_idx_lock, flags);
-	}
-}
-
 u32 r100_io_rreg(struct radeon_device *rdev, u32 reg)
 {
 	if (reg < rdev->rio_mem_size)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index f21db7a..a749b6c 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2328,10 +2328,42 @@ int radeon_device_init(struct radeon_device *rdev,
 void radeon_device_fini(struct radeon_device *rdev);
 int radeon_gpu_wait_for_idle(struct radeon_device *rdev);
 
-uint32_t r100_mm_rreg(struct radeon_device *rdev, uint32_t reg,
-		      bool always_indirect);
-void r100_mm_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v,
-		  bool always_indirect);
+#define RADEON_MIN_MMIO_SIZE 0x10000
+
+static inline uint32_t r100_mm_rreg(struct radeon_device *rdev, uint32_t reg,
+				    bool always_indirect)
+{
+	/* The mmio size is 64kb at minimum. Allows the if to be optimized out. */
+	if ((reg < rdev->rmmio_size || reg < RADEON_MIN_MMIO_SIZE) && !always_indirect)
+		return readl(((void __iomem *)rdev->rmmio) + reg);
+	else {
+		unsigned long flags;
+		uint32_t ret;
+
+		spin_lock_irqsave(&rdev->mmio_idx_lock, flags);
+		writel(reg, ((void __iomem *)rdev->rmmio) + RADEON_MM_INDEX);
+		ret = readl(((void __iomem *)rdev->rmmio) + RADEON_MM_DATA);
+		spin_unlock_irqrestore(&rdev->mmio_idx_lock, flags);
+
+		return ret;
+	}
+}
+
+static inline void r100_mm_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v,
+				bool always_indirect)
+{
+	if ((reg < rdev->rmmio_size || reg < RADEON_MIN_MMIO_SIZE) && !always_indirect)
+		writel(v, ((void __iomem *)rdev->rmmio) + reg);
+	else {
+		unsigned long flags;
+
+		spin_lock_irqsave(&rdev->mmio_idx_lock, flags);
+		writel(reg, ((void __iomem *)rdev->rmmio) + RADEON_MM_INDEX);
+		writel(v, ((void __iomem *)rdev->rmmio) + RADEON_MM_DATA);
+		spin_unlock_irqrestore(&rdev->mmio_idx_lock, flags);
+	}
+}
+
 u32 r100_io_rreg(struct radeon_device *rdev, u32 reg);
 void r100_io_wreg(struct radeon_device *rdev, u32 reg, u32 v);
 
-- 
1.8.3.1

             reply	other threads:[~2014-04-20 17:28 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-04-20 17:29 Lauri Kasanen [this message]
2014-04-20 17:41 ` [PATCH] drm/radeon: Inline r100_mm_rreg, -wreg, v3 Christian König
2014-07-10  8:48   ` Lauri Kasanen
2014-07-10  8:55     ` Christian König
2014-07-10 17:17       ` Alex Deucher

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20140420202933.78b3e355.cand@gmx.com \
    --to=cand@gmx.com \
    --cc=dri-devel@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox