From: Ben Widawsky <benjamin.widawsky@intel.com>
To: keithp@keithp.com
Cc: Andi Kleen <andi@firstfloor.org>,
linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org,
akpm@linux-foundation.org, Andi Kleen <ak@linux.intel.com>,
intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 11/12] i915: Move i915_read/write out of line
Date: Mon, 17 Oct 2011 22:47:29 -0700 [thread overview]
Message-ID: <20111017224729.54e2dbc0@intel.com> (raw)
In-Reply-To: <1318547332-23155-11-git-send-email-andi@firstfloor.org>
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>
next prev parent reply other threads:[~2011-10-18 5:48 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-10-13 23:08 [PATCH 01/12] RADEON: Drop inlines from evergreen_cs.c / r600_cs.c Andi Kleen
2011-10-13 23:08 ` [PATCH 02/12] RADEON: Move r100_*_*reg out of line Andi Kleen
2011-10-13 23:08 ` [PATCH 03/12] RADEON: drop inlines in r600_blit.c Andi Kleen
2011-10-13 23:08 ` [PATCH 04/12] RADEON: Remove now unused functions in radeon driver Andi Kleen
2011-10-13 23:08 ` [PATCH 05/12] FB_ATY: Move register accesses out of line Andi Kleen
2011-10-13 23:08 ` [PATCH 06/12] RADEON: Remove more bogus inlines in the radeon driver Andi Kleen
2011-10-13 23:08 ` [PATCH 07/12] RADEON: Move more code out of line Andi Kleen
2011-10-13 23:08 ` [PATCH 08/12] X86: Move alloc_intr_gate " Andi Kleen
2011-10-13 23:08 ` [PATCH 09/12] Don't use inline node_page_state for sysfs output functions Andi Kleen
2011-10-13 23:08 ` [PATCH 10/12] REISERFS: reiserfs drop unnecessary inlines Andi Kleen
2011-10-13 23:08 ` [PATCH 11/12] i915: Move i915_read/write out of line Andi Kleen
2011-10-15 13:49 ` Daniel Vetter
2011-10-18 5:47 ` Ben Widawsky [this message]
2011-10-13 23:08 ` [PATCH 12/12] Force always inline for gcc 4.5 when optimizing for size Andi Kleen
2011-10-18 8:59 ` [PATCH 01/12] RADEON: Drop inlines from evergreen_cs.c / r600_cs.c David Airlie
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=20111017224729.54e2dbc0@intel.com \
--to=benjamin.widawsky@intel.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
--cc=keithp@keithp.com \
--cc=linux-kernel@vger.kernel.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