From: "Luis R. Rodriguez" <[email protected]>
The same area used for ioremap() is used for the MTRR area.
Convert the driver from using the x86 specific MTRR code to
the architecture agnostic arch_phys_wc_add(). arch_phys_wc_add()
will avoid MTRR if write-combining is available, in order to
take advantage of that also ensure the ioremap'd area is requested
as write-combining.
There are a few motivations for this:
a) Take advantage of PAT when available
b) Help bury MTRR code away, MTRR is architecture specific and on
x86 its replaced by PAT
c) Help with the goal of eventually using _PAGE_CACHE_UC over
_PAGE_CACHE_UC_MINUS on x86 on ioremap_nocache() (see commit
de33c442e titled "x86 PAT: fix performance drop for glx,
use UC minus for ioremap(), ioremap_nocache() and
pci_mmap_page_range()")
The conversion done is expressed by the following Coccinelle
SmPL patch, it additionally required manual intervention to
address all the #ifdery and removal of redundant things which
arch_phys_wc_add() already addresses such as verbose message
about when MTRR fails and doing nothing when we didn't get
an MTRR.
@ mtrr_found @
expression index, base, size;
@@
-index = mtrr_add(base, size, MTRR_TYPE_WRCOMB, 1);
+index = arch_phys_wc_add(base, size);
@ mtrr_rm depends on mtrr_found @
expression mtrr_found.index, mtrr_found.base, mtrr_found.size;
@@
-mtrr_del(index, base, size);
+arch_phys_wc_del(index);
@ mtrr_rm_zero_arg depends on mtrr_found @
expression mtrr_found.index;
@@
-mtrr_del(index, 0, 0);
+arch_phys_wc_del(index);
@ mtrr_rm_fb_info depends on mtrr_found @
struct fb_info *info;
expression mtrr_found.index;
@@
-mtrr_del(index, info->fix.smem_start, info->fix.smem_len);
+arch_phys_wc_del(index);
@ ioremap_replace_nocache depends on mtrr_found @
struct fb_info *info;
expression base, size;
@@
-info->screen_base = ioremap_nocache(base, size);
+info->screen_base = ioremap_wc(base, size);
@ ioremap_replace_default depends on mtrr_found @
struct fb_info *info;
expression base, size;
@@
-info->screen_base = ioremap(base, size);
+info->screen_base = ioremap_wc(base, size);
Generated-by: Coccinelle SmPL
Cc: Sudip Mukherjee <[email protected]>
Cc: Teddy Wang <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Tomi Valkeinen <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Signed-off-by: Luis R. Rodriguez <[email protected]>
---
drivers/staging/sm750fb/sm750.c | 36 ++++--------------------------------
drivers/staging/sm750fb/sm750.h | 3 ---
drivers/staging/sm750fb/sm750_hw.c | 3 +--
3 files changed, 5 insertions(+), 37 deletions(-)
diff --git a/drivers/staging/sm750fb/sm750.c b/drivers/staging/sm750fb/sm750.c
index 3c7ea95..cf57e3e 100644
--- a/drivers/staging/sm750fb/sm750.c
+++ b/drivers/staging/sm750fb/sm750.c
@@ -16,9 +16,6 @@
#include<linux/vmalloc.h>
#include<linux/pagemap.h>
#include <linux/console.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
#include <asm/fb.h>
#include "sm750.h"
#include "sm750_hw.h"
@@ -47,9 +44,7 @@ typedef int (*PROC_SPEC_INITHW)(struct lynx_share*, struct pci_dev*);
/* common var for all device */
static int g_hwcursor = 1;
static int g_noaccel;
-#ifdef CONFIG_MTRR
static int g_nomtrr;
-#endif
static const char *g_fbmode[] = {NULL, NULL};
static const char *g_def_fbmode = "800x600-16@60";
static char *g_settings = NULL;
@@ -1126,11 +1121,8 @@ static int lynxfb_pci_probe(struct pci_dev *pdev,
pr_info("share->revid = %02x\n", share->revid);
share->pdev = pdev;
-#ifdef CONFIG_MTRR
share->mtrr_off = g_nomtrr;
share->mtrr.vram = 0;
- share->mtrr.vram_added = 0;
-#endif
share->accel_off = g_noaccel;
share->dual = g_dualview;
spin_lock_init(&share->slock);
@@ -1158,22 +1150,9 @@ static int lynxfb_pci_probe(struct pci_dev *pdev,
goto err_map;
}
-#ifdef CONFIG_MTRR
- if (!share->mtrr_off) {
- pr_info("enable mtrr\n");
- share->mtrr.vram = mtrr_add(share->vidmem_start,
- share->vidmem_size,
- MTRR_TYPE_WRCOMB, 1);
-
- if (share->mtrr.vram < 0) {
- /* don't block driver with the failure of MTRR */
- pr_err("Unable to setup MTRR.\n");
- } else {
- share->mtrr.vram_added = 1;
- pr_info("MTRR added succesfully\n");
- }
- }
-#endif
+ if (!share->mtrr_off)
+ share->mtrr.vram = arch_phys_wc_add(share->vidmem_start,
+ share->vidmem_size);
memset_io(share->pvMem, 0, share->vidmem_size);
@@ -1274,12 +1253,7 @@ static void __exit lynxfb_pci_remove(struct pci_dev *pdev)
/* release frame buffer */
framebuffer_release(info);
}
-#ifdef CONFIG_MTRR
- if (share->mtrr.vram_added)
- mtrr_del(share->mtrr.vram,
- share->vidmem_start,
- share->vidmem_size);
-#endif
+ arch_phys_wc_del(share->mtrr.vram);
iounmap(share->pvReg);
iounmap(share->pvMem);
@@ -1321,10 +1295,8 @@ static int __init lynxfb_setup(char *options)
/* options that mean for any lynx chips are configured here */
if (!strncmp(opt, "noaccel", strlen("noaccel")))
g_noaccel = 1;
-#ifdef CONFIG_MTRR
else if (!strncmp(opt, "nomtrr", strlen("nomtrr")))
g_nomtrr = 1;
-#endif
else if (!strncmp(opt, "dual", strlen("dual")))
g_dualview = 1;
else {
diff --git a/drivers/staging/sm750fb/sm750.h b/drivers/staging/sm750fb/sm750.h
index 0847d2b..5528912 100644
--- a/drivers/staging/sm750fb/sm750.h
+++ b/drivers/staging/sm750fb/sm750.h
@@ -51,13 +51,10 @@ struct lynx_share{
struct lynx_accel accel;
int accel_off;
int dual;
-#ifdef CONFIG_MTRR
int mtrr_off;
struct{
int vram;
- int vram_added;
}mtrr;
-#endif
/* all smi graphic adaptor got below attributes */
unsigned long vidmem_start;
unsigned long vidreg_start;
diff --git a/drivers/staging/sm750fb/sm750_hw.c b/drivers/staging/sm750fb/sm750_hw.c
index 9f0d06d..4b77eb1 100644
--- a/drivers/staging/sm750fb/sm750_hw.c
+++ b/drivers/staging/sm750fb/sm750_hw.c
@@ -85,8 +85,7 @@ int hw_sm750_map(struct lynx_share* share, struct pci_dev* pdev)
}
#endif
- share->pvMem = ioremap(share->vidmem_start,
- share->vidmem_size);
+ share->pvMem = ioremap_wc(share->vidmem_start, share->vidmem_size);
if(!share->pvMem){
pr_err("Map video memory failed\n");
--
2.3.2.209.gd67f9d5.dirty
On Tue, Apr 21, 2015 at 1:13 PM, Luis R. Rodriguez
<[email protected]> wrote:
> From: "Luis R. Rodriguez" <[email protected]>
>
> The same area used for ioremap() is used for the MTRR area.
> Convert the driver from using the x86 specific MTRR code to
> the architecture agnostic arch_phys_wc_add(). arch_phys_wc_add()
> will avoid MTRR if write-combining is available, in order to
> take advantage of that also ensure the ioremap'd area is requested
> as write-combining.
>
> There are a few motivations for this:
>
> a) Take advantage of PAT when available
>
> b) Help bury MTRR code away, MTRR is architecture specific and on
> x86 its replaced by PAT
>
> c) Help with the goal of eventually using _PAGE_CACHE_UC over
> _PAGE_CACHE_UC_MINUS on x86 on ioremap_nocache() (see commit
> de33c442e titled "x86 PAT: fix performance drop for glx,
> use UC minus for ioremap(), ioremap_nocache() and
> pci_mmap_page_range()")
>
> The conversion done is expressed by the following Coccinelle
> SmPL patch, it additionally required manual intervention to
> address all the #ifdery and removal of redundant things which
> arch_phys_wc_add() already addresses such as verbose message
> about when MTRR fails and doing nothing when we didn't get
> an MTRR.
>
> @ mtrr_found @
> expression index, base, size;
> @@
>
> -index = mtrr_add(base, size, MTRR_TYPE_WRCOMB, 1);
> +index = arch_phys_wc_add(base, size);
>
> @ mtrr_rm depends on mtrr_found @
> expression mtrr_found.index, mtrr_found.base, mtrr_found.size;
> @@
>
> -mtrr_del(index, base, size);
> +arch_phys_wc_del(index);
>
> @ mtrr_rm_zero_arg depends on mtrr_found @
> expression mtrr_found.index;
> @@
>
> -mtrr_del(index, 0, 0);
> +arch_phys_wc_del(index);
>
> @ mtrr_rm_fb_info depends on mtrr_found @
> struct fb_info *info;
> expression mtrr_found.index;
> @@
>
> -mtrr_del(index, info->fix.smem_start, info->fix.smem_len);
> +arch_phys_wc_del(index);
>
> @ ioremap_replace_nocache depends on mtrr_found @
> struct fb_info *info;
> expression base, size;
> @@
>
> -info->screen_base = ioremap_nocache(base, size);
> +info->screen_base = ioremap_wc(base, size);
>
> @ ioremap_replace_default depends on mtrr_found @
> struct fb_info *info;
> expression base, size;
> @@
>
> -info->screen_base = ioremap(base, size);
> +info->screen_base = ioremap_wc(base, size);
>
> Generated-by: Coccinelle SmPL
> Cc: Sudip Mukherjee <[email protected]>
> Cc: Teddy Wang <[email protected]>
> Cc: Greg Kroah-Hartman <[email protected]>
> Cc: Suresh Siddha <[email protected]>
> Cc: Ingo Molnar <[email protected]>
> Cc: Thomas Gleixner <[email protected]>
> Cc: Juergen Gross <[email protected]>
> Cc: Daniel Vetter <[email protected]>
> Cc: Andy Lutomirski <[email protected]>
> Cc: Dave Airlie <[email protected]>
> Cc: Antonino Daplas <[email protected]>
> Cc: Jean-Christophe Plagniol-Villard <[email protected]>
> Cc: Tomi Valkeinen <[email protected]>
> Cc: [email protected]
> Cc: [email protected]
> Cc: [email protected]
> Signed-off-by: Luis R. Rodriguez <[email protected]>
Hey folks, just a follow up. Can this be considered to be merged?
Luis
On Thu, Apr 30, 2015 at 10:38:27AM -0700, Luis R. Rodriguez wrote:
> On Tue, Apr 21, 2015 at 1:13 PM, Luis R. Rodriguez
> <[email protected]> wrote:
> > From: "Luis R. Rodriguez" <[email protected]>
> >
> > The same area used for ioremap() is used for the MTRR area.
> > Convert the driver from using the x86 specific MTRR code to
> > the architecture agnostic arch_phys_wc_add(). arch_phys_wc_add()
> > will avoid MTRR if write-combining is available, in order to
> > take advantage of that also ensure the ioremap'd area is requested
> > as write-combining.
> >
> > There are a few motivations for this:
> >
> > a) Take advantage of PAT when available
> >
> > b) Help bury MTRR code away, MTRR is architecture specific and on
> > x86 its replaced by PAT
> >
> > c) Help with the goal of eventually using _PAGE_CACHE_UC over
> > _PAGE_CACHE_UC_MINUS on x86 on ioremap_nocache() (see commit
> > de33c442e titled "x86 PAT: fix performance drop for glx,
> > use UC minus for ioremap(), ioremap_nocache() and
> > pci_mmap_page_range()")
> >
> > The conversion done is expressed by the following Coccinelle
> > SmPL patch, it additionally required manual intervention to
> > address all the #ifdery and removal of redundant things which
> > arch_phys_wc_add() already addresses such as verbose message
> > about when MTRR fails and doing nothing when we didn't get
> > an MTRR.
> >
> > @ mtrr_found @
> > expression index, base, size;
> > @@
> >
> > -index = mtrr_add(base, size, MTRR_TYPE_WRCOMB, 1);
> > +index = arch_phys_wc_add(base, size);
> >
> > @ mtrr_rm depends on mtrr_found @
> > expression mtrr_found.index, mtrr_found.base, mtrr_found.size;
> > @@
> >
> > -mtrr_del(index, base, size);
> > +arch_phys_wc_del(index);
> >
> > @ mtrr_rm_zero_arg depends on mtrr_found @
> > expression mtrr_found.index;
> > @@
> >
> > -mtrr_del(index, 0, 0);
> > +arch_phys_wc_del(index);
> >
> > @ mtrr_rm_fb_info depends on mtrr_found @
> > struct fb_info *info;
> > expression mtrr_found.index;
> > @@
> >
> > -mtrr_del(index, info->fix.smem_start, info->fix.smem_len);
> > +arch_phys_wc_del(index);
> >
> > @ ioremap_replace_nocache depends on mtrr_found @
> > struct fb_info *info;
> > expression base, size;
> > @@
> >
> > -info->screen_base = ioremap_nocache(base, size);
> > +info->screen_base = ioremap_wc(base, size);
> >
> > @ ioremap_replace_default depends on mtrr_found @
> > struct fb_info *info;
> > expression base, size;
> > @@
> >
> > -info->screen_base = ioremap(base, size);
> > +info->screen_base = ioremap_wc(base, size);
> >
> > Generated-by: Coccinelle SmPL
> > Cc: Sudip Mukherjee <[email protected]>
> > Cc: Teddy Wang <[email protected]>
> > Cc: Greg Kroah-Hartman <[email protected]>
> > Cc: Suresh Siddha <[email protected]>
> > Cc: Ingo Molnar <[email protected]>
> > Cc: Thomas Gleixner <[email protected]>
> > Cc: Juergen Gross <[email protected]>
> > Cc: Daniel Vetter <[email protected]>
> > Cc: Andy Lutomirski <[email protected]>
> > Cc: Dave Airlie <[email protected]>
> > Cc: Antonino Daplas <[email protected]>
> > Cc: Jean-Christophe Plagniol-Villard <[email protected]>
> > Cc: Tomi Valkeinen <[email protected]>
> > Cc: [email protected]
> > Cc: [email protected]
> > Cc: [email protected]
> > Signed-off-by: Luis R. Rodriguez <[email protected]>
>
> Hey folks, just a follow up. Can this be considered to be merged?
>
> Luis
I'm just starting to get to staging tree patches after the -rc1 window
was over. Give me a week or so, they are at the bottom of my list.
thanks,
greg k-h