From: "Luis R. Rodriguez" <[email protected]>
Ingo,
This is my pending series of patches for both write-combining and moving
Linux' use of MTRR into the grave. It combines three set of straggler patch
series which have been pending integration for a while now. The rename patches
do not depend in any way with the MTRR patches but I've combined them here as
they are all pending and relating to write-combining. I explain why integration
of such patches has been delayed but also provide reasoning for why I believe
its time to merge them.
1) The DMA API rename for write-combining goes with the old naming convention
defines added as suggested by you for any possible stragglers which may come
up as this goes through and gets merged. We can remove the old define
mappings after a release once this gets sucked in and things settle. These
patches have been in Boris tree for a while but I keep having to refresh
them as the kernel moves on, the addition of the old mapping should allow
us to merge this without any collateral.
2) The PCI driver changes go with Tomi Valkeinen's Acks as well as
Arnd Bergmann's own Acks for the PCI and asm-generic changes. This series
was technically acknowledged by Bjorn to be correct and acceptable but his
preference was for this to not use EXPORT_SYMBOL_GPL() as not *all*
write-combine APIs are using EXPORT_SYMBOL_GPL(). Our goal on x86 though
is to not deal with bug reports for new PAT APIs [0] and since its now clear
through documentation that its up to the maintainers / developers if they
decide to use EXPORT_SYMBOL_GPL() for new *features* [1] I keep that
practice in alignment with our own x86 goals to avoid bug reports and
issues with proprietary drivers on new PAT interfaces. Bjorn was happy for
this to go through someone else's tree, in particular Arnd's. Arnd Acked
the series [2] but is unable to take these patches in at this time as he's
out on paternal leave so sending these through you with the respective Acks.
Boris has been hugely instrumental on helping review all MTRR related
series, these were sitting on his queue for a while, but he's also
unavailable now as he's on vacation.
3) Unexporting direct MTRR access. This is last patch, I had posted this first
on March 2015 when [3] I originally had meshed up all the MTRR work into one
giant series. I ending up splitting up all the work into *over* 12 series.
Now that all the work is merged except these few patches I've combined that
patch as the last part of this series. I've amended an obituary note for
MTRR regarding platform firmware access to MTRR based on recent discussions
[4] and updated the documentation to reflect the status quo for Linux.
All of these patches have been tested by the 0-day bot machine. The only thing
*new* here is just my obituary amended documentation note for platform firmware
access to MTRRs on the last patch based hugely on review with Toshi.
[0] http://lkml.kernel.org/r/[email protected]
[1] https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=582ed8d51e2b6cb8a168c94852bca482685c2509
[2] http://lkml.kernel.org/r/2962702.QXZzP3RbKY@wuerfel
[3] http://lkml.kernel.org/r/[email protected]
[4] http://lkml.kernel.org/r/[email protected]
Luis R. Rodriguez (11):
PCI: Add pci_ioremap_wc_bar()
drivers/video/fbdev/i740fb: Use arch_phys_wc_add() and
pci_ioremap_wc_bar()
drivers/video/fbdev/kyrofb: Use arch_phys_wc_add() and
pci_ioremap_wc_bar()
drivers/video/fbdev/gxt4500: Use pci_ioremap_wc_bar() to map
framebuffer
PCI: Add pci_iomap_wc() variants
drivers/video/fbdev/arkfb.c: Use arch_phys_wc_add() and pci_iomap_wc()
drivers/video/fbdev/s3fb: Use arch_phys_wc_add() and pci_iomap_wc()
drivers/video/fbdev/vt8623fb: Use arch_phys_wc_add() and
pci_iomap_wc()
drivers/dma/iop-adma: Use dma_alloc_writecombine() kernel-style
dma: rename dma_*_writecombine() to dma_*_wc()
mtrr: bury MTRR - unexport mtrr_add() and mtrr_del()
Documentation/x86/mtrr.txt | 20 ++++++++--
arch/arm/mach-lpc32xx/phy3250.c | 13 +++---
arch/arm/mach-netx/fb.c | 14 +++----
arch/arm/mach-nspire/clcd.c | 13 +++---
arch/avr32/include/asm/dma-mapping.h | 20 +++++-----
arch/avr32/mm/dma-coherent.c | 12 +++---
arch/metag/include/asm/dma-mapping.h | 4 +-
arch/metag/kernel/dma.c | 6 +--
arch/x86/kernel/cpu/mtrr/main.c | 2 -
drivers/dma/iop-adma.c | 9 +++--
drivers/dma/mv_xor.c | 4 +-
drivers/dma/qcom_bam_dma.c | 14 +++----
drivers/gpu/drm/drm_gem_cma_helper.c | 13 +++---
drivers/gpu/drm/omapdrm/omap_dmm_tiler.c | 13 +++---
drivers/gpu/drm/omapdrm/omap_gem.c | 8 ++--
drivers/gpu/drm/sti/sti_cursor.c | 13 +++---
drivers/gpu/drm/sti/sti_gdp.c | 3 +-
drivers/gpu/drm/sti/sti_hqvdp.c | 6 +--
drivers/gpu/drm/tegra/gem.c | 11 +++---
drivers/gpu/host1x/cdma.c | 8 ++--
drivers/gpu/host1x/job.c | 10 ++---
drivers/media/platform/coda/coda-bit.c | 10 ++---
drivers/pci/pci.c | 14 +++++++
drivers/video/fbdev/acornfb.c | 4 +-
drivers/video/fbdev/amba-clcd-versatile.c | 14 +++----
drivers/video/fbdev/amba-clcd.c | 4 +-
drivers/video/fbdev/arkfb.c | 36 +++--------------
drivers/video/fbdev/atmel_lcdfb.c | 9 +++--
drivers/video/fbdev/ep93xx-fb.c | 9 ++---
drivers/video/fbdev/gbefb.c | 8 ++--
drivers/video/fbdev/gxt4500.c | 2 +-
drivers/video/fbdev/i740fb.c | 35 +++-------------
drivers/video/fbdev/imxfb.c | 12 +++---
drivers/video/fbdev/kyro/fbdev.c | 33 ++++++----------
drivers/video/fbdev/mx3fb.c | 9 ++---
drivers/video/fbdev/nuc900fb.c | 8 ++--
drivers/video/fbdev/omap/lcdc.c | 16 ++++----
drivers/video/fbdev/pxa168fb.c | 8 ++--
drivers/video/fbdev/pxafb.c | 4 +-
drivers/video/fbdev/s3c-fb.c | 7 ++--
drivers/video/fbdev/s3c2410fb.c | 8 ++--
drivers/video/fbdev/s3fb.c | 35 +++-------------
drivers/video/fbdev/sa1100fb.c | 8 ++--
drivers/video/fbdev/vt8623fb.c | 31 +++------------
include/asm-generic/pci_iomap.h | 14 +++++++
include/linux/dma-mapping.h | 16 ++++----
include/linux/pci.h | 1 +
include/video/kyro.h | 4 +-
lib/pci_iomap.c | 66 +++++++++++++++++++++++++++++++
sound/arm/pxa2xx-pcm-lib.c | 20 ++++------
sound/soc/fsl/imx-pcm-fiq.c | 10 ++---
sound/soc/nuc900/nuc900-pcm.c | 6 +--
sound/soc/omap/omap-pcm.c | 12 ++----
53 files changed, 331 insertions(+), 358 deletions(-)
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
This lets drivers take advantage of PAT when available. It should help
with the transition of converting video drivers over to ioremap_wc()
to help with the goal of eventually using _PAGE_CACHE_UC over
_PAGE_CACHE_UC_MINUS on x86 on ioremap_nocache(), see:
de33c442ed2a ("x86 PAT: fix performance drop for glx, use UC minus for ioremap(),
ioremap_nocache() and pci_mmap_page_range()")
Signed-off-by: Luis R. Rodriguez <[email protected]>
Acked-by: Arnd Bergmann <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: [email protected]
Cc: Bjorn Helgaas <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: Mel Gorman <[email protected]>
Cc: [email protected]
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tomi Valkeinen <[email protected]>
Cc: Toshi Kani <[email protected]>
Cc: Ville Syrjälä <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Borislav Petkov <[email protected]>
---
drivers/pci/pci.c | 14 ++++++++++++++
include/linux/pci.h | 1 +
2 files changed, 15 insertions(+)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 8037c27beb05..33867b8a4bc9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -138,6 +138,20 @@ void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar)
return ioremap_nocache(res->start, resource_size(res));
}
EXPORT_SYMBOL_GPL(pci_ioremap_bar);
+
+void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar)
+{
+ /*
+ * Make sure the BAR is actually a memory resource, not an IO resource
+ */
+ if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) {
+ WARN_ON(1);
+ return NULL;
+ }
+ return ioremap_wc(pci_resource_start(pdev, bar),
+ pci_resource_len(pdev, bar));
+}
+EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar);
#endif
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 88bee285b93d..2b2d7d44c21a 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1701,6 +1701,7 @@ static inline void pci_mmcfg_late_init(void) { }
int pci_ext_cfg_avail(void);
void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar);
+void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar);
#ifdef CONFIG_PCI_IOV
int pci_iov_virtfn_bus(struct pci_dev *dev, int id);
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
Convert the driver from using the x86-specific MTRR code to the
architecture-agnostic arch_phys_wc_add(). It will avoid MTRR if
write-combining is available, in order to take advantage of that also
ensure the ioremapped 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 it is being 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
ifdeffery 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);
Signed-off-by: Luis R. Rodriguez <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: [email protected]
Cc: Benoit Taine <[email protected]>
Cc: Bjorn Helgaas <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Jingoo Han <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: Rob Clark <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Borislav Petkov <[email protected]>
---
drivers/video/fbdev/i740fb.c | 35 ++++++-----------------------------
1 file changed, 6 insertions(+), 29 deletions(-)
diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c
index a2b4204b42bb..452e1163ad02 100644
--- a/drivers/video/fbdev/i740fb.c
+++ b/drivers/video/fbdev/i740fb.c
@@ -27,24 +27,15 @@
#include <linux/console.h>
#include <video/vga.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
#include "i740_reg.h"
static char *mode_option;
-
-#ifdef CONFIG_MTRR
static int mtrr = 1;
-#endif
struct i740fb_par {
unsigned char __iomem *regs;
bool has_sgram;
-#ifdef CONFIG_MTRR
- int mtrr_reg;
-#endif
+ int wc_cookie;
bool ddc_registered;
struct i2c_adapter ddc_adapter;
struct i2c_algo_bit_data ddc_algo;
@@ -1040,7 +1031,7 @@ static int i740fb_probe(struct pci_dev *dev, const struct pci_device_id *ent)
goto err_request_regions;
}
- info->screen_base = pci_ioremap_bar(dev, 0);
+ info->screen_base = pci_ioremap_wc_bar(dev, 0);
if (!info->screen_base) {
dev_err(info->device, "error remapping base\n");
ret = -ENOMEM;
@@ -1144,13 +1135,9 @@ static int i740fb_probe(struct pci_dev *dev, const struct pci_device_id *ent)
fb_info(info, "%s frame buffer device\n", info->fix.id);
pci_set_drvdata(dev, info);
-#ifdef CONFIG_MTRR
- if (mtrr) {
- par->mtrr_reg = -1;
- par->mtrr_reg = mtrr_add(info->fix.smem_start,
- info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
- }
-#endif
+ if (mtrr)
+ par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+ info->fix.smem_len);
return 0;
err_reg_framebuffer:
@@ -1177,13 +1164,7 @@ static void i740fb_remove(struct pci_dev *dev)
if (info) {
struct i740fb_par *par = info->par;
-
-#ifdef CONFIG_MTRR
- if (par->mtrr_reg >= 0) {
- mtrr_del(par->mtrr_reg, 0, 0);
- par->mtrr_reg = -1;
- }
-#endif
+ arch_phys_wc_del(par->wc_cookie);
unregister_framebuffer(info);
fb_dealloc_cmap(&info->cmap);
if (par->ddc_registered)
@@ -1287,10 +1268,8 @@ static int __init i740fb_setup(char *options)
while ((opt = strsep(&options, ",")) != NULL) {
if (!*opt)
continue;
-#ifdef CONFIG_MTRR
else if (!strncmp(opt, "mtrr:", 5))
mtrr = simple_strtoul(opt + 5, NULL, 0);
-#endif
else
mode_option = opt;
}
@@ -1327,7 +1306,5 @@ MODULE_DESCRIPTION("fbdev driver for Intel740");
module_param(mode_option, charp, 0444);
MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
-#ifdef CONFIG_MTRR
module_param(mtrr, int, 0444);
MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
Convert the driver from using the x86-specific MTRR code to the
architecture-agnostic arch_phys_wc_add(). It will avoid MTRR if
write-combining is available, in order to take advantage of that
also ensure the ioremapped 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 it is being 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
ifdeffery 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);
Signed-off-by: Luis R. Rodriguez <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Jingoo Han <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Laurent Pinchart <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Borislav Petkov <[email protected]>
---
drivers/video/fbdev/kyro/fbdev.c | 33 +++++++++++----------------------
include/video/kyro.h | 4 +---
2 files changed, 12 insertions(+), 25 deletions(-)
diff --git a/drivers/video/fbdev/kyro/fbdev.c b/drivers/video/fbdev/kyro/fbdev.c
index 65041e15fd59..5bb01533271e 100644
--- a/drivers/video/fbdev/kyro/fbdev.c
+++ b/drivers/video/fbdev/kyro/fbdev.c
@@ -22,9 +22,6 @@
#include <linux/pci.h>
#include <asm/io.h>
#include <linux/uaccess.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
#include <video/kyro.h>
@@ -84,9 +81,7 @@ static device_info_t deviceInfo;
static char *mode_option = NULL;
static int nopan = 0;
static int nowrap = 1;
-#ifdef CONFIG_MTRR
static int nomtrr = 0;
-#endif
/* PCI driver prototypes */
static int kyrofb_probe(struct pci_dev *pdev, const struct pci_device_id *ent);
@@ -570,10 +565,8 @@ static int __init kyrofb_setup(char *options)
nopan = 1;
} else if (strcmp(this_opt, "nowrap") == 0) {
nowrap = 1;
-#ifdef CONFIG_MTRR
} else if (strcmp(this_opt, "nomtrr") == 0) {
nomtrr = 1;
-#endif
} else {
mode_option = this_opt;
}
@@ -691,17 +684,16 @@ static int kyrofb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
currentpar->regbase = deviceInfo.pSTGReg =
ioremap_nocache(kyro_fix.mmio_start, kyro_fix.mmio_len);
+ if (!currentpar->regbase)
+ goto out_free_fb;
- info->screen_base = ioremap_nocache(kyro_fix.smem_start,
- kyro_fix.smem_len);
+ info->screen_base = pci_ioremap_wc_bar(pdev, 0);
+ if (!info->screen_base)
+ goto out_unmap_regs;
-#ifdef CONFIG_MTRR
if (!nomtrr)
- currentpar->mtrr_handle =
- mtrr_add(kyro_fix.smem_start,
- kyro_fix.smem_len,
- MTRR_TYPE_WRCOMB, 1);
-#endif
+ currentpar->wc_cookie = arch_phys_wc_add(kyro_fix.smem_start,
+ kyro_fix.smem_len);
kyro_fix.ypanstep = nopan ? 0 : 1;
kyro_fix.ywrapstep = nowrap ? 0 : 1;
@@ -745,8 +737,10 @@ static int kyrofb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
return 0;
out_unmap:
- iounmap(currentpar->regbase);
iounmap(info->screen_base);
+out_unmap_regs:
+ iounmap(currentpar->regbase);
+out_free_fb:
framebuffer_release(info);
return -EINVAL;
@@ -770,12 +764,7 @@ static void kyrofb_remove(struct pci_dev *pdev)
iounmap(info->screen_base);
iounmap(par->regbase);
-#ifdef CONFIG_MTRR
- if (par->mtrr_handle)
- mtrr_del(par->mtrr_handle,
- info->fix.smem_start,
- info->fix.smem_len);
-#endif
+ arch_phys_wc_del(par->wc_cookie);
unregister_framebuffer(info);
framebuffer_release(info);
diff --git a/include/video/kyro.h b/include/video/kyro.h
index c563968e926c..b958c2e9c915 100644
--- a/include/video/kyro.h
+++ b/include/video/kyro.h
@@ -35,9 +35,7 @@ struct kyrofb_info {
/* Useful to hold depth here for Linux */
u8 PIXDEPTH;
-#ifdef CONFIG_MTRR
- int mtrr_handle;
-#endif
+ int wc_cookie;
};
extern int kyro_dev_init(void);
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
The driver doesn't use mtrr_add() or arch_phys_wc_add() but since we
know the framebuffer is isolated already on an ioremap() we can take
advantage of write combining for performance where possible.
In this case there are a few motivations for this:
a) Take advantage of PAT when available.
b) 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()").
Signed-off-by: Luis R. Rodriguez <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Laurent Pinchart <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: Rob Clark <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Borislav Petkov <[email protected]>
---
drivers/video/fbdev/gxt4500.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/video/fbdev/gxt4500.c b/drivers/video/fbdev/gxt4500.c
index 135d78a02588..f19133a80e8c 100644
--- a/drivers/video/fbdev/gxt4500.c
+++ b/drivers/video/fbdev/gxt4500.c
@@ -662,7 +662,7 @@ static int gxt4500_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
info->fix.smem_start = fb_phys;
info->fix.smem_len = pci_resource_len(pdev, 1);
- info->screen_base = pci_ioremap_bar(pdev, 1);
+ info->screen_base = pci_ioremap_wc_bar(pdev, 1);
if (!info->screen_base) {
dev_err(&pdev->dev, "gxt4500: cannot map framebuffer\n");
goto err_unmap_regs;
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
PCI BARs tell us whether prefetching is safe, but they don't say
anything about write combining (WC). WC changes ordering rules and
allows writes to be collapsed, so it's not safe in general to use it on
a prefetchable region.
Add pci_iomap_wc() and pci_iomap_wc_range() so drivers can take advantage
of write combining when they know it's safe.
On architectures that don't fully support WC, e.g., x86 without PAT,
drivers for legacy framebuffers may get some of the benefit by using
arch_phys_wc_add() in addition to pci_iomap_wc(). But arch_phys_wc_add()
is unreliable and should be avoided in general. On x86, it uses MTRRs,
which are limited in number and size, so the results will vary based on
driver loading order.
The goals of adding pci_iomap_wc() are to:
- Give drivers an architecture-independent way to use WC so they can stop
using interfaces like mtrr_add() (on x86, pci_iomap_wc() uses
PAT when available).
- Move toward using _PAGE_CACHE_MODE_UC, not _PAGE_CACHE_MODE_UC_MINUS,
on x86 on ioremap_nocache() (see de33c442ed2a ("x86 PAT: fix
performance drop for glx, use UC minus for ioremap(), ioremap_nocache()
and pci_mmap_page_range()").
Signed-off-by: Luis R. Rodriguez <[email protected]>
Acked-by: Arnd Bergmann <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: Bjorn Helgaas <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: [email protected]
Cc: H. Peter Anvin <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: [email protected]
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: Mel Gorman <[email protected]>
Cc: "Michael S. Tsirkin" <[email protected]>
Cc: Roger Pau Monné <[email protected]>
Cc: Rusty Russell <[email protected]>
Cc: Stefan Bader <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tomi Valkeinen <[email protected]>
Cc: Toshi Kani <[email protected]>
Cc: [email protected]
Cc: Ville Syrjälä <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
[ Move IORESOURCE_IO check up, space out statements for better readability. ]
Signed-off-by: Borislav Petkov <[email protected]>
---
include/asm-generic/pci_iomap.h | 14 +++++++++
lib/pci_iomap.c | 66 +++++++++++++++++++++++++++++++++++++++++
2 files changed, 80 insertions(+)
diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h
index 7389c87116a0..b1e17fcee2d0 100644
--- a/include/asm-generic/pci_iomap.h
+++ b/include/asm-generic/pci_iomap.h
@@ -15,9 +15,13 @@ struct pci_dev;
#ifdef CONFIG_PCI
/* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+extern void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long max);
extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
unsigned long offset,
unsigned long maxlen);
+extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
+ unsigned long offset,
+ unsigned long maxlen);
/* Create a virtual mapping cookie for a port on a given PCI device.
* Do not call this directly, it exists to make it easier for architectures
* to override */
@@ -34,12 +38,22 @@ static inline void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned lon
return NULL;
}
+static inline void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long max)
+{
+ return NULL;
+}
static inline void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
unsigned long offset,
unsigned long maxlen)
{
return NULL;
}
+static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
+ unsigned long offset,
+ unsigned long maxlen)
+{
+ return NULL;
+}
#endif
#endif /* __ASM_GENERIC_IO_H */
diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c
index e1930dbab2da..c10fba461454 100644
--- a/lib/pci_iomap.c
+++ b/lib/pci_iomap.c
@@ -49,6 +49,51 @@ void __iomem *pci_iomap_range(struct pci_dev *dev,
EXPORT_SYMBOL(pci_iomap_range);
/**
+ * pci_iomap_wc_range - create a virtual WC mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @offset: map memory at the given offset in BAR
+ * @maxlen: max length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way. When possible write combining
+ * is used.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR from offset to the end, pass %0 here.
+ * */
+void __iomem *pci_iomap_wc_range(struct pci_dev *dev,
+ int bar,
+ unsigned long offset,
+ unsigned long maxlen)
+{
+ resource_size_t start = pci_resource_start(dev, bar);
+ resource_size_t len = pci_resource_len(dev, bar);
+ unsigned long flags = pci_resource_flags(dev, bar);
+
+
+ if (flags & IORESOURCE_IO)
+ return NULL;
+
+ if (len <= offset || !start)
+ return NULL;
+
+ len -= offset;
+ start += offset;
+ if (maxlen && len > maxlen)
+ len = maxlen;
+
+ if (flags & IORESOURCE_MEM)
+ return ioremap_wc(start, len);
+
+ /* What? */
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(pci_iomap_wc_range);
+
+/**
* pci_iomap - create a virtual mapping cookie for a PCI BAR
* @dev: PCI device that owns the BAR
* @bar: BAR number
@@ -67,4 +112,25 @@ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
return pci_iomap_range(dev, bar, 0, maxlen);
}
EXPORT_SYMBOL(pci_iomap);
+
+/**
+ * pci_iomap_wc - create a virtual WC mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @maxlen: length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way. When possible write combining
+ * is used.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR without checking for its length first, pass %0 here.
+ * */
+void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+ return pci_iomap_wc_range(dev, bar, 0, maxlen);
+}
+EXPORT_SYMBOL_GPL(pci_iomap_wc);
#endif /* CONFIG_PCI */
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
Convert the driver from using the x86-specific MTRR code to the
architecture-agnostic arch_phys_wc_add(). It will avoid MTRRs if
write-combining is available. In order to take advantage of that also
ensure the ioremapped 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 it is being 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 ifdeffery 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);
Signed-off-by: Luis R. Rodriguez <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: "Lad, Prabhakar" <[email protected]>
Cc: Laurent Pinchart <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Borislav Petkov <[email protected]>
---
drivers/video/fbdev/arkfb.c | 36 +++++-------------------------------
1 file changed, 5 insertions(+), 31 deletions(-)
diff --git a/drivers/video/fbdev/arkfb.c b/drivers/video/fbdev/arkfb.c
index b305a1e7cc76..6a317de7082c 100644
--- a/drivers/video/fbdev/arkfb.c
+++ b/drivers/video/fbdev/arkfb.c
@@ -26,13 +26,9 @@
#include <linux/console.h> /* Why should fb driver call console functions? because console_lock() */
#include <video/vga.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
struct arkfb_info {
int mclk_freq;
- int mtrr_reg;
+ int wc_cookie;
struct dac_info *dac;
struct vgastate state;
@@ -102,10 +98,6 @@ static const struct svga_timing_regs ark_timing_regs = {
static char *mode_option = "640x480-8@60";
-#ifdef CONFIG_MTRR
-static int mtrr = 1;
-#endif
-
MODULE_AUTHOR("(c) 2007 Ondrej Zajicek <[email protected]>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("fbdev driver for ARK 2000PV");
@@ -115,11 +107,6 @@ MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
module_param_named(mode, mode_option, charp, 0444);
MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc) (deprecated)");
-#ifdef CONFIG_MTRR
-module_param(mtrr, int, 0444);
-MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
-
static int threshold = 4;
module_param(threshold, int, 0644);
@@ -1002,7 +989,7 @@ static int ark_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
info->fix.smem_len = pci_resource_len(dev, 0);
/* Map physical IO memory address into kernel space */
- info->screen_base = pci_iomap(dev, 0, 0);
+ info->screen_base = pci_iomap_wc(dev, 0, 0);
if (! info->screen_base) {
rc = -ENOMEM;
dev_err(info->device, "iomap for framebuffer failed\n");
@@ -1057,14 +1044,8 @@ static int ark_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
/* Record a reference to the driver data */
pci_set_drvdata(dev, info);
-
-#ifdef CONFIG_MTRR
- if (mtrr) {
- par->mtrr_reg = -1;
- par->mtrr_reg = mtrr_add(info->fix.smem_start, info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
- }
-#endif
-
+ par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+ info->fix.smem_len);
return 0;
/* Error handling */
@@ -1092,14 +1073,7 @@ static void ark_pci_remove(struct pci_dev *dev)
if (info) {
struct arkfb_info *par = info->par;
-
-#ifdef CONFIG_MTRR
- if (par->mtrr_reg >= 0) {
- mtrr_del(par->mtrr_reg, 0, 0);
- par->mtrr_reg = -1;
- }
-#endif
-
+ arch_phys_wc_del(par->wc_cookie);
dac_release(par->dac);
unregister_framebuffer(info);
fb_dealloc_cmap(&info->cmap);
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
This driver uses the same area for MTRR as for the ioremap().
Convert the driver from using the x86-specific MTRR code to the
architecture-agnostic arch_phys_wc_add(). It will avoid MTRRs if
write-combining is available. In order to take advantage of that
also ensure the ioremapped 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 it is being 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 ifdeffery 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);
Signed-off-by: Luis R. Rodriguez <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Jingoo Han <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: "Lad, Prabhakar" <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: Rickard Strandqvist <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Borislav Petkov <[email protected]>
---
drivers/video/fbdev/s3fb.c | 35 ++++++-----------------------------
1 file changed, 6 insertions(+), 29 deletions(-)
diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c
index f0ae61a37f04..13b109073c63 100644
--- a/drivers/video/fbdev/s3fb.c
+++ b/drivers/video/fbdev/s3fb.c
@@ -28,13 +28,9 @@
#include <linux/i2c.h>
#include <linux/i2c-algo-bit.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
struct s3fb_info {
int chip, rev, mclk_freq;
- int mtrr_reg;
+ int wc_cookie;
struct vgastate state;
struct mutex open_lock;
unsigned int ref_count;
@@ -154,11 +150,7 @@ static const struct svga_timing_regs s3_timing_regs = {
static char *mode_option;
-
-#ifdef CONFIG_MTRR
static int mtrr = 1;
-#endif
-
static int fasttext = 1;
@@ -170,11 +162,8 @@ module_param(mode_option, charp, 0444);
MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
module_param_named(mode, mode_option, charp, 0444);
MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc) (deprecated)");
-
-#ifdef CONFIG_MTRR
module_param(mtrr, int, 0444);
MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
module_param(fasttext, int, 0644);
MODULE_PARM_DESC(fasttext, "Enable S3 fast text mode (1=enable, 0=disable, default=1)");
@@ -1168,7 +1157,7 @@ static int s3_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
info->fix.smem_len = pci_resource_len(dev, 0);
/* Map physical IO memory address into kernel space */
- info->screen_base = pci_iomap(dev, 0, 0);
+ info->screen_base = pci_iomap_wc(dev, 0, 0);
if (! info->screen_base) {
rc = -ENOMEM;
dev_err(info->device, "iomap for framebuffer failed\n");
@@ -1365,12 +1354,9 @@ static int s3_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
/* Record a reference to the driver data */
pci_set_drvdata(dev, info);
-#ifdef CONFIG_MTRR
- if (mtrr) {
- par->mtrr_reg = -1;
- par->mtrr_reg = mtrr_add(info->fix.smem_start, info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
- }
-#endif
+ if (mtrr)
+ par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+ info->fix.smem_len);
return 0;
@@ -1405,14 +1391,7 @@ static void s3_pci_remove(struct pci_dev *dev)
if (info) {
par = info->par;
-
-#ifdef CONFIG_MTRR
- if (par->mtrr_reg >= 0) {
- mtrr_del(par->mtrr_reg, 0, 0);
- par->mtrr_reg = -1;
- }
-#endif
-
+ arch_phys_wc_del(par->wc_cookie);
unregister_framebuffer(info);
fb_dealloc_cmap(&info->cmap);
@@ -1551,10 +1530,8 @@ static int __init s3fb_setup(char *options)
if (!*opt)
continue;
-#ifdef CONFIG_MTRR
else if (!strncmp(opt, "mtrr:", 5))
mtrr = simple_strtoul(opt + 5, NULL, 0);
-#endif
else if (!strncmp(opt, "fasttext:", 9))
fasttext = simple_strtoul(opt + 9, NULL, 0);
else
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
This driver uses the same area for MTRR as for the ioremap().
Convert the driver from using the x86-specific MTRR code to the
architecture-agnostic arch_phys_wc_add(). It will avoid MTRRs if
write-combining is available. In order to take advantage of that
also ensure the ioremapped 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 it is being 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 ifdeffery 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);
Signed-off-by: Luis R. Rodriguez <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Jingoo Han <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: "Lad, Prabhakar" <[email protected]>
Cc: Laurent Pinchart <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: Rob Clark <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Borislav Petkov <[email protected]>
---
drivers/video/fbdev/vt8623fb.c | 31 ++++++-------------------------
1 file changed, 6 insertions(+), 25 deletions(-)
diff --git a/drivers/video/fbdev/vt8623fb.c b/drivers/video/fbdev/vt8623fb.c
index 8bac309c24b9..dd0f18e42d3e 100644
--- a/drivers/video/fbdev/vt8623fb.c
+++ b/drivers/video/fbdev/vt8623fb.c
@@ -26,13 +26,9 @@
#include <linux/console.h> /* Why should fb driver call console functions? because console_lock() */
#include <video/vga.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
struct vt8623fb_info {
char __iomem *mmio_base;
- int mtrr_reg;
+ int wc_cookie;
struct vgastate state;
struct mutex open_lock;
unsigned int ref_count;
@@ -99,10 +95,7 @@ static struct svga_timing_regs vt8623_timing_regs = {
/* Module parameters */
static char *mode_option = "640x480-8@60";
-
-#ifdef CONFIG_MTRR
static int mtrr = 1;
-#endif
MODULE_AUTHOR("(c) 2006 Ondrej Zajicek <[email protected]>");
MODULE_LICENSE("GPL");
@@ -112,11 +105,8 @@ module_param(mode_option, charp, 0644);
MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
module_param_named(mode, mode_option, charp, 0);
MODULE_PARM_DESC(mode, "Default video mode e.g. '648x480-8@60' (deprecated)");
-
-#ifdef CONFIG_MTRR
module_param(mtrr, int, 0444);
MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
/* ------------------------------------------------------------------------- */
@@ -710,7 +700,7 @@ static int vt8623_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
info->fix.mmio_len = pci_resource_len(dev, 1);
/* Map physical IO memory address into kernel space */
- info->screen_base = pci_iomap(dev, 0, 0);
+ info->screen_base = pci_iomap_wc(dev, 0, 0);
if (! info->screen_base) {
rc = -ENOMEM;
dev_err(info->device, "iomap for framebuffer failed\n");
@@ -781,12 +771,9 @@ static int vt8623_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
/* Record a reference to the driver data */
pci_set_drvdata(dev, info);
-#ifdef CONFIG_MTRR
- if (mtrr) {
- par->mtrr_reg = -1;
- par->mtrr_reg = mtrr_add(info->fix.smem_start, info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
- }
-#endif
+ if (mtrr)
+ par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+ info->fix.smem_len);
return 0;
@@ -816,13 +803,7 @@ static void vt8623_pci_remove(struct pci_dev *dev)
if (info) {
struct vt8623fb_info *par = info->par;
-#ifdef CONFIG_MTRR
- if (par->mtrr_reg >= 0) {
- mtrr_del(par->mtrr_reg, 0, 0);
- par->mtrr_reg = -1;
- }
-#endif
-
+ arch_phys_wc_del(par->wc_cookie);
unregister_framebuffer(info);
fb_dealloc_cmap(&info->cmap);
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
dma_alloc_writecombine()'s call and return value check is tangled in all
in one call. Untangle both calls according to kernel coding style.
Signed-off-by: Luis R. Rodriguez <[email protected]>
Acked-by: Vinod Koul <[email protected]>
Cc: Vinod Koul <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Borislav Petkov <[email protected]>
---
drivers/dma/iop-adma.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index 998826854fdd..e4f43125e0fb 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -1300,10 +1300,11 @@ static int iop_adma_probe(struct platform_device *pdev)
* note: writecombine gives slightly better performance, but
* requires that we explicitly flush the writes
*/
- if ((adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
- plat_data->pool_size,
- &adev->dma_desc_pool,
- GFP_KERNEL)) == NULL) {
+ adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
+ plat_data->pool_size,
+ &adev->dma_desc_pool,
+ GFP_KERNEL);
+ if (!adev->dma_desc_pool_virt) {
ret = -ENOMEM;
goto err_free_adev;
}
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
Rename dma_*_writecombine() to dma_*_wc(), so that the naming
is coherent across the various write-combining APIs.
The following Coccinelle SmPL patch was used for this simple
transformation:
@ rename_dma_alloc_writecombine @
expression dev, size, dma_addr, gfp;
@@
-dma_alloc_writecombine(dev, size, dma_addr, gfp)
+dma_alloc_wc(dev, size, dma_addr, gfp)
@ rename_dma_free_writecombine @
expression dev, size, cpu_addr, dma_addr;
@@
-dma_free_writecombine(dev, size, cpu_addr, dma_addr)
+dma_free_wc(dev, size, cpu_addr, dma_addr)
@ rename_dma_mmap_writecombine @
expression dev, vma, cpu_addr, dma_addr, size;
@@
-dma_mmap_writecombine(dev, vma, cpu_addr, dma_addr, size)
+dma_mmap_wc(dev, vma, cpu_addr, dma_addr, size)
Generated-by: Coccinelle SmPL
Suggested-by: Ingo Molnar <[email protected]>
Signed-off-by: Luis R. Rodriguez <[email protected]>
---
arch/arm/mach-lpc32xx/phy3250.c | 13 ++++++-------
arch/arm/mach-netx/fb.c | 14 ++++++--------
arch/arm/mach-nspire/clcd.c | 13 ++++++-------
arch/avr32/include/asm/dma-mapping.h | 20 ++++++++++----------
arch/avr32/mm/dma-coherent.c | 12 ++++++------
arch/metag/include/asm/dma-mapping.h | 4 ++--
arch/metag/kernel/dma.c | 6 +++---
drivers/dma/iop-adma.c | 8 ++++----
drivers/dma/mv_xor.c | 4 ++--
drivers/dma/qcom_bam_dma.c | 14 +++++++-------
drivers/gpu/drm/drm_gem_cma_helper.c | 13 ++++++-------
drivers/gpu/drm/omapdrm/omap_dmm_tiler.c | 13 ++++++-------
drivers/gpu/drm/omapdrm/omap_gem.c | 8 ++++----
drivers/gpu/drm/sti/sti_cursor.c | 13 ++++++-------
drivers/gpu/drm/sti/sti_gdp.c | 3 +--
drivers/gpu/drm/sti/sti_hqvdp.c | 6 +++---
drivers/gpu/drm/tegra/gem.c | 11 +++++------
drivers/gpu/host1x/cdma.c | 8 ++++----
drivers/gpu/host1x/job.c | 10 ++++------
drivers/media/platform/coda/coda-bit.c | 10 +++++-----
drivers/video/fbdev/acornfb.c | 4 ++--
drivers/video/fbdev/amba-clcd-versatile.c | 14 ++++++--------
drivers/video/fbdev/amba-clcd.c | 4 ++--
drivers/video/fbdev/atmel_lcdfb.c | 9 +++++----
drivers/video/fbdev/ep93xx-fb.c | 9 +++------
drivers/video/fbdev/gbefb.c | 8 ++++----
drivers/video/fbdev/imxfb.c | 12 ++++++------
drivers/video/fbdev/mx3fb.c | 9 ++++-----
drivers/video/fbdev/nuc900fb.c | 8 ++++----
drivers/video/fbdev/omap/lcdc.c | 16 ++++++++--------
drivers/video/fbdev/pxa168fb.c | 8 ++++----
drivers/video/fbdev/pxafb.c | 4 ++--
drivers/video/fbdev/s3c-fb.c | 7 +++----
drivers/video/fbdev/s3c2410fb.c | 8 ++++----
drivers/video/fbdev/sa1100fb.c | 8 ++++----
include/linux/dma-mapping.h | 16 ++++++++--------
sound/arm/pxa2xx-pcm-lib.c | 20 ++++++++------------
sound/soc/fsl/imx-pcm-fiq.c | 10 ++++------
sound/soc/nuc900/nuc900-pcm.c | 6 ++----
sound/soc/omap/omap-pcm.c | 12 ++++--------
40 files changed, 183 insertions(+), 212 deletions(-)
diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c
index 77d6b1bab278..ee06fabdf60e 100644
--- a/arch/arm/mach-lpc32xx/phy3250.c
+++ b/arch/arm/mach-lpc32xx/phy3250.c
@@ -86,8 +86,8 @@ static int lpc32xx_clcd_setup(struct clcd_fb *fb)
{
dma_addr_t dma;
- fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev,
- PANEL_SIZE, &dma, GFP_KERNEL);
+ fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, PANEL_SIZE, &dma,
+ GFP_KERNEL);
if (!fb->fb.screen_base) {
printk(KERN_ERR "CLCD: unable to map framebuffer\n");
return -ENOMEM;
@@ -116,15 +116,14 @@ static int lpc32xx_clcd_setup(struct clcd_fb *fb)
static int lpc32xx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
{
- return dma_mmap_writecombine(&fb->dev->dev, vma,
- fb->fb.screen_base, fb->fb.fix.smem_start,
- fb->fb.fix.smem_len);
+ return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+ fb->fb.fix.smem_start, fb->fb.fix.smem_len);
}
static void lpc32xx_clcd_remove(struct clcd_fb *fb)
{
- dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
- fb->fb.screen_base, fb->fb.fix.smem_start);
+ dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+ fb->fb.fix.smem_start);
}
/*
diff --git a/arch/arm/mach-netx/fb.c b/arch/arm/mach-netx/fb.c
index d122ee6ab991..8814ee5e98fd 100644
--- a/arch/arm/mach-netx/fb.c
+++ b/arch/arm/mach-netx/fb.c
@@ -42,8 +42,8 @@ int netx_clcd_setup(struct clcd_fb *fb)
fb->panel = netx_panel;
- fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, 1024*1024,
- &dma, GFP_KERNEL);
+ fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, 1024 * 1024, &dma,
+ GFP_KERNEL);
if (!fb->fb.screen_base) {
printk(KERN_ERR "CLCD: unable to map framebuffer\n");
return -ENOMEM;
@@ -57,16 +57,14 @@ int netx_clcd_setup(struct clcd_fb *fb)
int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
{
- return dma_mmap_writecombine(&fb->dev->dev, vma,
- fb->fb.screen_base,
- fb->fb.fix.smem_start,
- fb->fb.fix.smem_len);
+ return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+ fb->fb.fix.smem_start, fb->fb.fix.smem_len);
}
void netx_clcd_remove(struct clcd_fb *fb)
{
- dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
- fb->fb.screen_base, fb->fb.fix.smem_start);
+ dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+ fb->fb.fix.smem_start);
}
static AMBA_AHB_DEVICE(fb, "fb", 0, 0x00104000, { NETX_IRQ_LCD }, NULL);
diff --git a/arch/arm/mach-nspire/clcd.c b/arch/arm/mach-nspire/clcd.c
index abea12617b17..ea0e5b2ca1cd 100644
--- a/arch/arm/mach-nspire/clcd.c
+++ b/arch/arm/mach-nspire/clcd.c
@@ -90,8 +90,8 @@ int nspire_clcd_setup(struct clcd_fb *fb)
panel_size = ((panel->mode.xres * panel->mode.yres) * panel->bpp) / 8;
panel_size = ALIGN(panel_size, PAGE_SIZE);
- fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev,
- panel_size, &dma, GFP_KERNEL);
+ fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, panel_size, &dma,
+ GFP_KERNEL);
if (!fb->fb.screen_base) {
pr_err("CLCD: unable to map framebuffer\n");
@@ -107,13 +107,12 @@ int nspire_clcd_setup(struct clcd_fb *fb)
int nspire_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
{
- return dma_mmap_writecombine(&fb->dev->dev, vma,
- fb->fb.screen_base, fb->fb.fix.smem_start,
- fb->fb.fix.smem_len);
+ return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+ fb->fb.fix.smem_start, fb->fb.fix.smem_len);
}
void nspire_clcd_remove(struct clcd_fb *fb)
{
- dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
- fb->fb.screen_base, fb->fb.fix.smem_start);
+ dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+ fb->fb.fix.smem_start);
}
diff --git a/arch/avr32/include/asm/dma-mapping.h b/arch/avr32/include/asm/dma-mapping.h
index ae7ac9205d20..b43b11d1c7c0 100644
--- a/arch/avr32/include/asm/dma-mapping.h
+++ b/arch/avr32/include/asm/dma-mapping.h
@@ -71,7 +71,7 @@ extern void dma_free_coherent(struct device *dev, size_t size,
void *cpu_addr, dma_addr_t handle);
/**
- * dma_alloc_writecombine - allocate write-combining memory for DMA
+ * dma_alloc_wc - allocate write-combining memory for DMA
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
* @size: required memory size
* @handle: bus-specific DMA address
@@ -81,24 +81,24 @@ extern void dma_free_coherent(struct device *dev, size_t size,
* return the CPU-viewed address, and sets @handle to be the
* device-viewed address.
*/
-extern void *dma_alloc_writecombine(struct device *dev, size_t size,
- dma_addr_t *handle, gfp_t gfp);
+extern void *dma_alloc_wc(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp);
/**
- * dma_free_coherent - free memory allocated by dma_alloc_writecombine
+ * dma_free_coherent - free memory allocated by dma_alloc_wc
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @size: size of memory originally requested in dma_alloc_writecombine
- * @cpu_addr: CPU-view address returned from dma_alloc_writecombine
- * @handle: device-view address returned from dma_alloc_writecombine
+ * @size: size of memory originally requested in dma_alloc_wc
+ * @cpu_addr: CPU-view address returned from dma_alloc_wc
+ * @handle: device-view address returned from dma_alloc_wc
*
* Free (and unmap) a DMA buffer previously allocated by
- * dma_alloc_writecombine().
+ * dma_alloc_wc().
*
* References to memory and mappings associated with cpu_addr/handle
* during and after this call executing are illegal.
*/
-extern void dma_free_writecombine(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t handle);
+extern void dma_free_wc(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t handle);
/**
* dma_map_single - map a single buffer for streaming DMA
diff --git a/arch/avr32/mm/dma-coherent.c b/arch/avr32/mm/dma-coherent.c
index 50cdb5b10f0f..5d029d202a2a 100644
--- a/arch/avr32/mm/dma-coherent.c
+++ b/arch/avr32/mm/dma-coherent.c
@@ -121,8 +121,8 @@ void dma_free_coherent(struct device *dev, size_t size,
}
EXPORT_SYMBOL(dma_free_coherent);
-void *dma_alloc_writecombine(struct device *dev, size_t size,
- dma_addr_t *handle, gfp_t gfp)
+void *dma_alloc_wc(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp)
{
struct page *page;
dma_addr_t phys;
@@ -137,10 +137,10 @@ void *dma_alloc_writecombine(struct device *dev, size_t size,
/* Now, map the page into P3 with write-combining turned on */
return __ioremap(phys, size, _PAGE_BUFFER);
}
-EXPORT_SYMBOL(dma_alloc_writecombine);
+EXPORT_SYMBOL(dma_alloc_wc);
-void dma_free_writecombine(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t handle)
+void dma_free_wc(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t handle)
{
struct page *page;
@@ -149,4 +149,4 @@ void dma_free_writecombine(struct device *dev, size_t size,
page = phys_to_page(handle);
__dma_free(dev, size, page, handle);
}
-EXPORT_SYMBOL(dma_free_writecombine);
+EXPORT_SYMBOL(dma_free_wc);
diff --git a/arch/metag/include/asm/dma-mapping.h b/arch/metag/include/asm/dma-mapping.h
index eb5cdec94be0..d727deae083a 100644
--- a/arch/metag/include/asm/dma-mapping.h
+++ b/arch/metag/include/asm/dma-mapping.h
@@ -23,8 +23,8 @@ void dma_sync_for_cpu(void *vaddr, size_t size, int dma_direction);
int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size);
-int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size);
+int dma_mmap_wc(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size);
static inline dma_addr_t
dma_map_single(struct device *dev, void *ptr, size_t size,
diff --git a/arch/metag/kernel/dma.c b/arch/metag/kernel/dma.c
index c700d625067a..89138b4f717a 100644
--- a/arch/metag/kernel/dma.c
+++ b/arch/metag/kernel/dma.c
@@ -372,13 +372,13 @@ int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
}
EXPORT_SYMBOL(dma_mmap_coherent);
-int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size)
+int dma_mmap_wc(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size)
{
vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
}
-EXPORT_SYMBOL(dma_mmap_writecombine);
+EXPORT_SYMBOL(dma_mmap_wc);
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index e4f43125e0fb..f039cfadf17b 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -1300,10 +1300,10 @@ static int iop_adma_probe(struct platform_device *pdev)
* note: writecombine gives slightly better performance, but
* requires that we explicitly flush the writes
*/
- adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
- plat_data->pool_size,
- &adev->dma_desc_pool,
- GFP_KERNEL);
+ adev->dma_desc_pool_virt = dma_alloc_wc(&pdev->dev,
+ plat_data->pool_size,
+ &adev->dma_desc_pool,
+ GFP_KERNEL);
if (!adev->dma_desc_pool_virt) {
ret = -ENOMEM;
goto err_free_adev;
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 1c2de9a834a9..c277b9af3c2d 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1000,8 +1000,8 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
* requires that we explicitly flush the writes
*/
mv_chan->dma_desc_pool_virt =
- dma_alloc_writecombine(&pdev->dev, MV_XOR_POOL_SIZE,
- &mv_chan->dma_desc_pool, GFP_KERNEL);
+ dma_alloc_wc(&pdev->dev, MV_XOR_POOL_SIZE, &mv_chan->dma_desc_pool,
+ GFP_KERNEL);
if (!mv_chan->dma_desc_pool_virt)
return ERR_PTR(-ENOMEM);
diff --git a/drivers/dma/qcom_bam_dma.c b/drivers/dma/qcom_bam_dma.c
index 5a250cdc8376..d34aef7a101b 100644
--- a/drivers/dma/qcom_bam_dma.c
+++ b/drivers/dma/qcom_bam_dma.c
@@ -502,8 +502,8 @@ static int bam_alloc_chan(struct dma_chan *chan)
return 0;
/* allocate FIFO descriptor space, but only if necessary */
- bchan->fifo_virt = dma_alloc_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE,
- &bchan->fifo_phys, GFP_KERNEL);
+ bchan->fifo_virt = dma_alloc_wc(bdev->dev, BAM_DESC_FIFO_SIZE,
+ &bchan->fifo_phys, GFP_KERNEL);
if (!bchan->fifo_virt) {
dev_err(bdev->dev, "Failed to allocate desc fifo\n");
@@ -538,8 +538,8 @@ static void bam_free_chan(struct dma_chan *chan)
bam_reset_channel(bchan);
spin_unlock_irqrestore(&bchan->vc.lock, flags);
- dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE, bchan->fifo_virt,
- bchan->fifo_phys);
+ dma_free_wc(bdev->dev, BAM_DESC_FIFO_SIZE, bchan->fifo_virt,
+ bchan->fifo_phys);
bchan->fifo_virt = NULL;
/* mask irq for pipe/channel */
@@ -1231,9 +1231,9 @@ static int bam_dma_remove(struct platform_device *pdev)
bam_dma_terminate_all(&bdev->channels[i].vc.chan);
tasklet_kill(&bdev->channels[i].vc.task);
- dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE,
- bdev->channels[i].fifo_virt,
- bdev->channels[i].fifo_phys);
+ dma_free_wc(bdev->dev, BAM_DESC_FIFO_SIZE,
+ bdev->channels[i].fifo_virt,
+ bdev->channels[i].fifo_phys);
}
tasklet_kill(&bdev->task);
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index 86cc793cdf79..07b571d70a8d 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -107,8 +107,8 @@ struct drm_gem_cma_object *drm_gem_cma_create(struct drm_device *drm,
if (IS_ERR(cma_obj))
return cma_obj;
- cma_obj->vaddr = dma_alloc_writecombine(drm->dev, size,
- &cma_obj->paddr, GFP_KERNEL | __GFP_NOWARN);
+ cma_obj->vaddr = dma_alloc_wc(drm->dev, size, &cma_obj->paddr,
+ GFP_KERNEL | __GFP_NOWARN);
if (!cma_obj->vaddr) {
dev_err(drm->dev, "failed to allocate buffer with size %zu\n",
size);
@@ -190,8 +190,8 @@ void drm_gem_cma_free_object(struct drm_gem_object *gem_obj)
cma_obj = to_drm_gem_cma_obj(gem_obj);
if (cma_obj->vaddr) {
- dma_free_writecombine(gem_obj->dev->dev, cma_obj->base.size,
- cma_obj->vaddr, cma_obj->paddr);
+ dma_free_wc(gem_obj->dev->dev, cma_obj->base.size,
+ cma_obj->vaddr, cma_obj->paddr);
} else if (gem_obj->import_attach) {
drm_prime_gem_destroy(gem_obj, cma_obj->sgt);
}
@@ -322,9 +322,8 @@ static int drm_gem_cma_mmap_obj(struct drm_gem_cma_object *cma_obj,
vma->vm_flags &= ~VM_PFNMAP;
vma->vm_pgoff = 0;
- ret = dma_mmap_writecombine(cma_obj->base.dev->dev, vma,
- cma_obj->vaddr, cma_obj->paddr,
- vma->vm_end - vma->vm_start);
+ ret = dma_mmap_wc(cma_obj->base.dev->dev, vma, cma_obj->vaddr,
+ cma_obj->paddr, vma->vm_end - vma->vm_start);
if (ret)
drm_gem_vm_close(vma);
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index 7841970de48d..43f0697ce752 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -570,10 +570,9 @@ static int omap_dmm_remove(struct platform_device *dev)
kfree(omap_dmm->engines);
if (omap_dmm->refill_va)
- dma_free_writecombine(omap_dmm->dev,
- REFILL_BUFFER_SIZE * omap_dmm->num_engines,
- omap_dmm->refill_va,
- omap_dmm->refill_pa);
+ dma_free_wc(omap_dmm->dev,
+ REFILL_BUFFER_SIZE * omap_dmm->num_engines,
+ omap_dmm->refill_va, omap_dmm->refill_pa);
if (omap_dmm->dummy_page)
__free_page(omap_dmm->dummy_page);
@@ -698,9 +697,9 @@ static int omap_dmm_probe(struct platform_device *dev)
omap_dmm->dummy_pa = page_to_phys(omap_dmm->dummy_page);
/* alloc refill memory */
- omap_dmm->refill_va = dma_alloc_writecombine(&dev->dev,
- REFILL_BUFFER_SIZE * omap_dmm->num_engines,
- &omap_dmm->refill_pa, GFP_KERNEL);
+ omap_dmm->refill_va = dma_alloc_wc(&dev->dev,
+ REFILL_BUFFER_SIZE * omap_dmm->num_engines,
+ &omap_dmm->refill_pa, GFP_KERNEL);
if (!omap_dmm->refill_va) {
dev_err(&dev->dev, "could not allocate refill memory\n");
goto fail;
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 7ed08fdc4c42..b20909a78775 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -1295,8 +1295,8 @@ void omap_gem_free_object(struct drm_gem_object *obj)
omap_gem_detach_pages(obj);
if (!is_shmem(obj)) {
- dma_free_writecombine(dev->dev, obj->size,
- omap_obj->vaddr, omap_obj->paddr);
+ dma_free_wc(dev->dev, obj->size, omap_obj->vaddr,
+ omap_obj->paddr);
} else if (omap_obj->vaddr) {
vunmap(omap_obj->vaddr);
}
@@ -1384,8 +1384,8 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev,
/* attempt to allocate contiguous memory if we don't
* have DMM for remappign discontiguous buffers
*/
- omap_obj->vaddr = dma_alloc_writecombine(dev->dev, size,
- &omap_obj->paddr, GFP_KERNEL);
+ omap_obj->vaddr = dma_alloc_wc(dev->dev, size,
+ &omap_obj->paddr, GFP_KERNEL);
if (!omap_obj->vaddr) {
kfree(omap_obj);
diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c
index dd1032195051..3a190957c200 100644
--- a/drivers/gpu/drm/sti/sti_cursor.c
+++ b/drivers/gpu/drm/sti/sti_cursor.c
@@ -164,10 +164,10 @@ static void sti_cursor_atomic_update(struct drm_plane *drm_plane,
cursor->pixmap.size = cursor->width * cursor->height;
- cursor->pixmap.base = dma_alloc_writecombine(cursor->dev,
- cursor->pixmap.size,
- &cursor->pixmap.paddr,
- GFP_KERNEL | GFP_DMA);
+ cursor->pixmap.base = dma_alloc_wc(cursor->dev,
+ cursor->pixmap.size,
+ &cursor->pixmap.paddr,
+ GFP_KERNEL | GFP_DMA);
if (!cursor->pixmap.base) {
DRM_ERROR("Failed to allocate memory for pixmap\n");
return;
@@ -252,9 +252,8 @@ struct drm_plane *sti_cursor_create(struct drm_device *drm_dev,
/* Allocate clut buffer */
size = 0x100 * sizeof(unsigned short);
- cursor->clut = dma_alloc_writecombine(dev, size, &cursor->clut_paddr,
- GFP_KERNEL | GFP_DMA);
-
+ cursor->clut = dma_alloc_wc(dev, size, &cursor->clut_paddr,
+ GFP_KERNEL | GFP_DMA);
if (!cursor->clut) {
DRM_ERROR("Failed to allocate memory for cursor clut\n");
goto err_clut;
diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c
index 9365670427ad..539889992bb0 100644
--- a/drivers/gpu/drm/sti/sti_gdp.c
+++ b/drivers/gpu/drm/sti/sti_gdp.c
@@ -312,8 +312,7 @@ static void sti_gdp_init(struct sti_gdp *gdp)
/* Allocate all the nodes within a single memory page */
size = sizeof(struct sti_gdp_node) *
GDP_NODE_PER_FIELD * GDP_NODE_NB_BANK;
- base = dma_alloc_writecombine(gdp->dev,
- size, &dma_addr, GFP_KERNEL | GFP_DMA);
+ base = dma_alloc_wc(gdp->dev, size, &dma_addr, GFP_KERNEL | GFP_DMA);
if (!base) {
DRM_ERROR("Failed to allocate memory for GDP node\n");
diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c
index 7c8f9b8bfae1..2d32e87190c2 100644
--- a/drivers/gpu/drm/sti/sti_hqvdp.c
+++ b/drivers/gpu/drm/sti/sti_hqvdp.c
@@ -617,9 +617,9 @@ static void sti_hqvdp_init(struct sti_hqvdp *hqvdp)
/* Allocate memory for the VDP commands */
size = NB_VDP_CMD * sizeof(struct sti_hqvdp_cmd);
- hqvdp->hqvdp_cmd = dma_alloc_writecombine(hqvdp->dev, size,
- &hqvdp->hqvdp_cmd_paddr,
- GFP_KERNEL | GFP_DMA);
+ hqvdp->hqvdp_cmd = dma_alloc_wc(hqvdp->dev, size,
+ &hqvdp->hqvdp_cmd_paddr,
+ GFP_KERNEL | GFP_DMA);
if (!hqvdp->hqvdp_cmd) {
DRM_ERROR("Failed to allocate memory for VDP cmd\n");
return;
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 01e16e146bfe..82777d424f23 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -181,8 +181,7 @@ static void tegra_bo_free(struct drm_device *drm, struct tegra_bo *bo)
sg_free_table(bo->sgt);
kfree(bo->sgt);
} else if (bo->vaddr) {
- dma_free_writecombine(drm->dev, bo->gem.size, bo->vaddr,
- bo->paddr);
+ dma_free_wc(drm->dev, bo->gem.size, bo->vaddr, bo->paddr);
}
}
@@ -239,8 +238,8 @@ static int tegra_bo_alloc(struct drm_device *drm, struct tegra_bo *bo)
} else {
size_t size = bo->gem.size;
- bo->vaddr = dma_alloc_writecombine(drm->dev, size, &bo->paddr,
- GFP_KERNEL | __GFP_NOWARN);
+ bo->vaddr = dma_alloc_wc(drm->dev, size, &bo->paddr,
+ GFP_KERNEL | __GFP_NOWARN);
if (!bo->vaddr) {
dev_err(drm->dev,
"failed to allocate buffer of size %zu\n",
@@ -483,8 +482,8 @@ int tegra_drm_mmap(struct file *file, struct vm_area_struct *vma)
vma->vm_flags &= ~VM_PFNMAP;
vma->vm_pgoff = 0;
- ret = dma_mmap_writecombine(gem->dev->dev, vma, bo->vaddr,
- bo->paddr, gem->size);
+ ret = dma_mmap_wc(gem->dev->dev, vma, bo->vaddr, bo->paddr,
+ gem->size);
if (ret) {
drm_gem_vm_close(vma);
return ret;
diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
index 5a8c8d55317a..a18db4d5347c 100644
--- a/drivers/gpu/host1x/cdma.c
+++ b/drivers/gpu/host1x/cdma.c
@@ -52,8 +52,8 @@ static void host1x_pushbuffer_destroy(struct push_buffer *pb)
struct host1x *host1x = cdma_to_host1x(cdma);
if (pb->phys != 0)
- dma_free_writecombine(host1x->dev, pb->size_bytes + 4,
- pb->mapped, pb->phys);
+ dma_free_wc(host1x->dev, pb->size_bytes + 4, pb->mapped,
+ pb->phys);
pb->mapped = NULL;
pb->phys = 0;
@@ -76,8 +76,8 @@ static int host1x_pushbuffer_init(struct push_buffer *pb)
pb->pos = 0;
/* allocate and map pushbuffer memory */
- pb->mapped = dma_alloc_writecombine(host1x->dev, pb->size_bytes + 4,
- &pb->phys, GFP_KERNEL);
+ pb->mapped = dma_alloc_wc(host1x->dev, pb->size_bytes + 4, &pb->phys,
+ GFP_KERNEL);
if (!pb->mapped)
goto fail;
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index 63bd63f3c7df..defa7995f213 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -467,9 +467,8 @@ static inline int copy_gathers(struct host1x_job *job, struct device *dev)
size += g->words * sizeof(u32);
}
- job->gather_copy_mapped = dma_alloc_writecombine(dev, size,
- &job->gather_copy,
- GFP_KERNEL);
+ job->gather_copy_mapped = dma_alloc_wc(dev, size, &job->gather_copy,
+ GFP_KERNEL);
if (!job->gather_copy_mapped) {
job->gather_copy_mapped = NULL;
return -ENOMEM;
@@ -578,9 +577,8 @@ void host1x_job_unpin(struct host1x_job *job)
job->num_unpins = 0;
if (job->gather_copy_size)
- dma_free_writecombine(job->channel->dev, job->gather_copy_size,
- job->gather_copy_mapped,
- job->gather_copy);
+ dma_free_wc(job->channel->dev, job->gather_copy_size,
+ job->gather_copy_mapped, job->gather_copy);
}
EXPORT_SYMBOL(host1x_job_unpin);
diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index fd7819d8922d..152293a81e88 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -1452,9 +1452,9 @@ static int coda_alloc_bitstream_buffer(struct coda_ctx *ctx,
return 0;
ctx->bitstream.size = roundup_pow_of_two(q_data->sizeimage * 2);
- ctx->bitstream.vaddr = dma_alloc_writecombine(
- &ctx->dev->plat_dev->dev, ctx->bitstream.size,
- &ctx->bitstream.paddr, GFP_KERNEL);
+ ctx->bitstream.vaddr = dma_alloc_wc(&ctx->dev->plat_dev->dev,
+ ctx->bitstream.size,
+ &ctx->bitstream.paddr, GFP_KERNEL);
if (!ctx->bitstream.vaddr) {
v4l2_err(&ctx->dev->v4l2_dev,
"failed to allocate bitstream ringbuffer");
@@ -1471,8 +1471,8 @@ static void coda_free_bitstream_buffer(struct coda_ctx *ctx)
if (ctx->bitstream.vaddr == NULL)
return;
- dma_free_writecombine(&ctx->dev->plat_dev->dev, ctx->bitstream.size,
- ctx->bitstream.vaddr, ctx->bitstream.paddr);
+ dma_free_wc(&ctx->dev->plat_dev->dev, ctx->bitstream.size,
+ ctx->bitstream.vaddr, ctx->bitstream.paddr);
ctx->bitstream.vaddr = NULL;
kfifo_init(&ctx->bitstream_fifo, NULL, 0);
}
diff --git a/drivers/video/fbdev/acornfb.c b/drivers/video/fbdev/acornfb.c
index a305caea58ee..fb75b7e5a19a 100644
--- a/drivers/video/fbdev/acornfb.c
+++ b/drivers/video/fbdev/acornfb.c
@@ -1040,8 +1040,8 @@ static int acornfb_probe(struct platform_device *dev)
* for the framebuffer if we are not using
* VRAM.
*/
- base = dma_alloc_writecombine(current_par.dev, size, &handle,
- GFP_KERNEL);
+ base = dma_alloc_wc(current_par.dev, size, &handle,
+ GFP_KERNEL);
if (base == NULL) {
printk(KERN_ERR "acornfb: unable to allocate screen "
"memory\n");
diff --git a/drivers/video/fbdev/amba-clcd-versatile.c b/drivers/video/fbdev/amba-clcd-versatile.c
index 7a8afcd4573e..a8a22daa3f9d 100644
--- a/drivers/video/fbdev/amba-clcd-versatile.c
+++ b/drivers/video/fbdev/amba-clcd-versatile.c
@@ -154,8 +154,8 @@ int versatile_clcd_setup_dma(struct clcd_fb *fb, unsigned long framesize)
{
dma_addr_t dma;
- fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, framesize,
- &dma, GFP_KERNEL);
+ fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, framesize, &dma,
+ GFP_KERNEL);
if (!fb->fb.screen_base) {
pr_err("CLCD: unable to map framebuffer\n");
return -ENOMEM;
@@ -169,14 +169,12 @@ int versatile_clcd_setup_dma(struct clcd_fb *fb, unsigned long framesize)
int versatile_clcd_mmap_dma(struct clcd_fb *fb, struct vm_area_struct *vma)
{
- return dma_mmap_writecombine(&fb->dev->dev, vma,
- fb->fb.screen_base,
- fb->fb.fix.smem_start,
- fb->fb.fix.smem_len);
+ return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+ fb->fb.fix.smem_start, fb->fb.fix.smem_len);
}
void versatile_clcd_remove_dma(struct clcd_fb *fb)
{
- dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
- fb->fb.screen_base, fb->fb.fix.smem_start);
+ dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+ fb->fb.fix.smem_start);
}
diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c
index 9362424c2340..fe274b5851c7 100644
--- a/drivers/video/fbdev/amba-clcd.c
+++ b/drivers/video/fbdev/amba-clcd.c
@@ -774,8 +774,8 @@ static int clcdfb_of_dma_setup(struct clcd_fb *fb)
static int clcdfb_of_dma_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
{
- return dma_mmap_writecombine(&fb->dev->dev, vma, fb->fb.screen_base,
- fb->fb.fix.smem_start, fb->fb.fix.smem_len);
+ return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+ fb->fb.fix.smem_start, fb->fb.fix.smem_len);
}
static void clcdfb_of_dma_remove(struct clcd_fb *fb)
diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c
index 016cae1425a4..da7fa7858589 100644
--- a/drivers/video/fbdev/atmel_lcdfb.c
+++ b/drivers/video/fbdev/atmel_lcdfb.c
@@ -415,8 +415,8 @@ static inline void atmel_lcdfb_free_video_memory(struct atmel_lcdfb_info *sinfo)
{
struct fb_info *info = sinfo->info;
- dma_free_writecombine(info->device, info->fix.smem_len,
- info->screen_base, info->fix.smem_start);
+ dma_free_wc(info->device, info->fix.smem_len, info->screen_base,
+ info->fix.smem_start);
}
/**
@@ -436,8 +436,9 @@ static int atmel_lcdfb_alloc_video_memory(struct atmel_lcdfb_info *sinfo)
* ((var->bits_per_pixel + 7) / 8));
info->fix.smem_len = max(smem_len, sinfo->smem_len);
- info->screen_base = dma_alloc_writecombine(info->device, info->fix.smem_len,
- (dma_addr_t *)&info->fix.smem_start, GFP_KERNEL);
+ info->screen_base = dma_alloc_wc(info->device, info->fix.smem_len,
+ (dma_addr_t *)&info->fix.smem_start,
+ GFP_KERNEL);
if (!info->screen_base) {
return -ENOMEM;
diff --git a/drivers/video/fbdev/ep93xx-fb.c b/drivers/video/fbdev/ep93xx-fb.c
index 5b1081030cbb..78ec79d84f3f 100644
--- a/drivers/video/fbdev/ep93xx-fb.c
+++ b/drivers/video/fbdev/ep93xx-fb.c
@@ -316,9 +316,8 @@ static int ep93xxfb_mmap(struct fb_info *info, struct vm_area_struct *vma)
unsigned int offset = vma->vm_pgoff << PAGE_SHIFT;
if (offset < info->fix.smem_len) {
- return dma_mmap_writecombine(info->dev, vma, info->screen_base,
- info->fix.smem_start,
- info->fix.smem_len);
+ return dma_mmap_wc(info->dev, vma, info->screen_base,
+ info->fix.smem_start, info->fix.smem_len);
}
return -EINVAL;
@@ -427,9 +426,7 @@ static int ep93xxfb_alloc_videomem(struct fb_info *info)
/* Maximum 16bpp -> used memory is maximum x*y*2 bytes */
fb_size = EP93XXFB_MAX_XRES * EP93XXFB_MAX_YRES * 2;
-
- virt_addr = dma_alloc_writecombine(info->dev, fb_size,
- &phys_addr, GFP_KERNEL);
+ virt_addr = dma_alloc_wc(info->dev, fb_size, &phys_addr, GFP_KERNEL);
if (!virt_addr)
return -ENOMEM;
diff --git a/drivers/video/fbdev/gbefb.c b/drivers/video/fbdev/gbefb.c
index b63d55f481fa..1a242b1338e9 100644
--- a/drivers/video/fbdev/gbefb.c
+++ b/drivers/video/fbdev/gbefb.c
@@ -1185,8 +1185,8 @@ static int gbefb_probe(struct platform_device *p_dev)
} else {
/* try to allocate memory with the classical allocator
* this has high chance to fail on low memory machines */
- gbe_mem = dma_alloc_writecombine(NULL, gbe_mem_size,
- &gbe_dma_addr, GFP_KERNEL);
+ gbe_mem = dma_alloc_wc(NULL, gbe_mem_size, &gbe_dma_addr,
+ GFP_KERNEL);
if (!gbe_mem) {
printk(KERN_ERR "gbefb: couldn't allocate framebuffer memory\n");
ret = -ENOMEM;
@@ -1238,7 +1238,7 @@ static int gbefb_probe(struct platform_device *p_dev)
out_gbe_unmap:
arch_phys_wc_del(par->wc_cookie);
if (gbe_dma_addr)
- dma_free_writecombine(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
+ dma_free_wc(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
out_tiles_free:
dma_free_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t),
(void *)gbe_tiles.cpu, gbe_tiles.dma);
@@ -1259,7 +1259,7 @@ static int gbefb_remove(struct platform_device* p_dev)
gbe_turn_off();
arch_phys_wc_del(par->wc_cookie);
if (gbe_dma_addr)
- dma_free_writecombine(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
+ dma_free_wc(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
dma_free_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t),
(void *)gbe_tiles.cpu, gbe_tiles.dma);
release_mem_region(GBE_BASE, sizeof(struct sgi_gbe));
diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c
index cee88603efc9..465b3387c549 100644
--- a/drivers/video/fbdev/imxfb.c
+++ b/drivers/video/fbdev/imxfb.c
@@ -922,8 +922,8 @@ static int imxfb_probe(struct platform_device *pdev)
}
fbi->map_size = PAGE_ALIGN(info->fix.smem_len);
- info->screen_base = dma_alloc_writecombine(&pdev->dev, fbi->map_size,
- &fbi->map_dma, GFP_KERNEL);
+ info->screen_base = dma_alloc_wc(&pdev->dev, fbi->map_size,
+ &fbi->map_dma, GFP_KERNEL);
if (!info->screen_base) {
dev_err(&pdev->dev, "Failed to allocate video RAM: %d\n", ret);
@@ -990,8 +990,8 @@ failed_cmap:
if (pdata && pdata->exit)
pdata->exit(fbi->pdev);
failed_platform_init:
- dma_free_writecombine(&pdev->dev, fbi->map_size, info->screen_base,
- fbi->map_dma);
+ dma_free_wc(&pdev->dev, fbi->map_size, info->screen_base,
+ fbi->map_dma);
failed_map:
iounmap(fbi->regs);
failed_ioremap:
@@ -1026,8 +1026,8 @@ static int imxfb_remove(struct platform_device *pdev)
kfree(info->pseudo_palette);
framebuffer_release(info);
- dma_free_writecombine(&pdev->dev, fbi->map_size, info->screen_base,
- fbi->map_dma);
+ dma_free_wc(&pdev->dev, fbi->map_size, info->screen_base,
+ fbi->map_dma);
iounmap(fbi->regs);
release_mem_region(res->start, resource_size(res));
diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c
index 7947634ee6b0..f91b1db262b0 100644
--- a/drivers/video/fbdev/mx3fb.c
+++ b/drivers/video/fbdev/mx3fb.c
@@ -1336,9 +1336,8 @@ static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len,
int retval = 0;
dma_addr_t addr;
- fbi->screen_base = dma_alloc_writecombine(fbi->device,
- mem_len,
- &addr, GFP_DMA | GFP_KERNEL);
+ fbi->screen_base = dma_alloc_wc(fbi->device, mem_len, &addr,
+ GFP_DMA | GFP_KERNEL);
if (!fbi->screen_base) {
dev_err(fbi->device, "Cannot allocate %u bytes framebuffer memory\n",
@@ -1378,8 +1377,8 @@ err0:
*/
static int mx3fb_unmap_video_memory(struct fb_info *fbi)
{
- dma_free_writecombine(fbi->device, fbi->fix.smem_len,
- fbi->screen_base, fbi->fix.smem_start);
+ dma_free_wc(fbi->device, fbi->fix.smem_len, fbi->screen_base,
+ fbi->fix.smem_start);
fbi->screen_base = NULL;
mutex_lock(&fbi->mm_lock);
diff --git a/drivers/video/fbdev/nuc900fb.c b/drivers/video/fbdev/nuc900fb.c
index 389fa2cbb713..6680edae4696 100644
--- a/drivers/video/fbdev/nuc900fb.c
+++ b/drivers/video/fbdev/nuc900fb.c
@@ -396,8 +396,8 @@ static int nuc900fb_map_video_memory(struct fb_info *info)
dev_dbg(fbi->dev, "nuc900fb_map_video_memory(fbi=%p) map_size %lu\n",
fbi, map_size);
- info->screen_base = dma_alloc_writecombine(fbi->dev, map_size,
- &map_dma, GFP_KERNEL);
+ info->screen_base = dma_alloc_wc(fbi->dev, map_size, &map_dma,
+ GFP_KERNEL);
if (!info->screen_base)
return -ENOMEM;
@@ -411,8 +411,8 @@ static int nuc900fb_map_video_memory(struct fb_info *info)
static inline void nuc900fb_unmap_video_memory(struct fb_info *info)
{
struct nuc900fb_info *fbi = info->par;
- dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
- info->screen_base, info->fix.smem_start);
+ dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+ info->screen_base, info->fix.smem_start);
}
static irqreturn_t nuc900fb_irqhandler(int irq, void *dev_id)
diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c
index 6efa2591eaa8..e3d9b9ea5498 100644
--- a/drivers/video/fbdev/omap/lcdc.c
+++ b/drivers/video/fbdev/omap/lcdc.c
@@ -612,8 +612,8 @@ static void lcdc_dma_handler(u16 status, void *data)
static int alloc_palette_ram(void)
{
- lcdc.palette_virt = dma_alloc_writecombine(lcdc.fbdev->dev,
- MAX_PALETTE_SIZE, &lcdc.palette_phys, GFP_KERNEL);
+ lcdc.palette_virt = dma_alloc_wc(lcdc.fbdev->dev, MAX_PALETTE_SIZE,
+ &lcdc.palette_phys, GFP_KERNEL);
if (lcdc.palette_virt == NULL) {
dev_err(lcdc.fbdev->dev, "failed to alloc palette memory\n");
return -ENOMEM;
@@ -625,8 +625,8 @@ static int alloc_palette_ram(void)
static void free_palette_ram(void)
{
- dma_free_writecombine(lcdc.fbdev->dev, MAX_PALETTE_SIZE,
- lcdc.palette_virt, lcdc.palette_phys);
+ dma_free_wc(lcdc.fbdev->dev, MAX_PALETTE_SIZE, lcdc.palette_virt,
+ lcdc.palette_phys);
}
static int alloc_fbmem(struct omapfb_mem_region *region)
@@ -642,8 +642,8 @@ static int alloc_fbmem(struct omapfb_mem_region *region)
if (region->size > frame_size)
frame_size = region->size;
lcdc.vram_size = frame_size;
- lcdc.vram_virt = dma_alloc_writecombine(lcdc.fbdev->dev,
- lcdc.vram_size, &lcdc.vram_phys, GFP_KERNEL);
+ lcdc.vram_virt = dma_alloc_wc(lcdc.fbdev->dev, lcdc.vram_size,
+ &lcdc.vram_phys, GFP_KERNEL);
if (lcdc.vram_virt == NULL) {
dev_err(lcdc.fbdev->dev, "unable to allocate FB DMA memory\n");
return -ENOMEM;
@@ -660,8 +660,8 @@ static int alloc_fbmem(struct omapfb_mem_region *region)
static void free_fbmem(void)
{
- dma_free_writecombine(lcdc.fbdev->dev, lcdc.vram_size,
- lcdc.vram_virt, lcdc.vram_phys);
+ dma_free_wc(lcdc.fbdev->dev, lcdc.vram_size, lcdc.vram_virt,
+ lcdc.vram_phys);
}
static int setup_fbmem(struct omapfb_mem_desc *req_md)
diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c
index e209b039f553..04bd7237da6f 100644
--- a/drivers/video/fbdev/pxa168fb.c
+++ b/drivers/video/fbdev/pxa168fb.c
@@ -683,8 +683,8 @@ static int pxa168fb_probe(struct platform_device *pdev)
*/
info->fix.smem_len = PAGE_ALIGN(DEFAULT_FB_SIZE);
- info->screen_base = dma_alloc_writecombine(fbi->dev, info->fix.smem_len,
- &fbi->fb_start_dma, GFP_KERNEL);
+ info->screen_base = dma_alloc_wc(fbi->dev, info->fix.smem_len,
+ &fbi->fb_start_dma, GFP_KERNEL);
if (info->screen_base == NULL) {
ret = -ENOMEM;
goto failed_free_info;
@@ -809,8 +809,8 @@ static int pxa168fb_remove(struct platform_device *pdev)
irq = platform_get_irq(pdev, 0);
- dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
- info->screen_base, info->fix.smem_start);
+ dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+ info->screen_base, info->fix.smem_start);
clk_disable(fbi->clk);
clk_put(fbi->clk);
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index 7245611ec963..6a5b9801396a 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -2286,8 +2286,8 @@ static int pxafb_remove(struct platform_device *dev)
free_pages_exact(fbi->video_mem, fbi->video_mem_size);
- dma_free_writecombine(&dev->dev, fbi->dma_buff_size,
- fbi->dma_buff, fbi->dma_buff_phys);
+ dma_free_wc(&dev->dev, fbi->dma_buff_size, fbi->dma_buff,
+ fbi->dma_buff_phys);
iounmap(fbi->mmio_base);
diff --git a/drivers/video/fbdev/s3c-fb.c b/drivers/video/fbdev/s3c-fb.c
index f72dd12456f9..5f4f696c2ecf 100644
--- a/drivers/video/fbdev/s3c-fb.c
+++ b/drivers/video/fbdev/s3c-fb.c
@@ -1105,8 +1105,7 @@ static int s3c_fb_alloc_memory(struct s3c_fb *sfb, struct s3c_fb_win *win)
dev_dbg(sfb->dev, "want %u bytes for window\n", size);
- fbi->screen_base = dma_alloc_writecombine(sfb->dev, size,
- &map_dma, GFP_KERNEL);
+ fbi->screen_base = dma_alloc_wc(sfb->dev, size, &map_dma, GFP_KERNEL);
if (!fbi->screen_base)
return -ENOMEM;
@@ -1131,8 +1130,8 @@ static void s3c_fb_free_memory(struct s3c_fb *sfb, struct s3c_fb_win *win)
struct fb_info *fbi = win->fbinfo;
if (fbi->screen_base)
- dma_free_writecombine(sfb->dev, PAGE_ALIGN(fbi->fix.smem_len),
- fbi->screen_base, fbi->fix.smem_start);
+ dma_free_wc(sfb->dev, PAGE_ALIGN(fbi->fix.smem_len),
+ fbi->screen_base, fbi->fix.smem_start);
}
/**
diff --git a/drivers/video/fbdev/s3c2410fb.c b/drivers/video/fbdev/s3c2410fb.c
index d6704add1601..0dd86be36afb 100644
--- a/drivers/video/fbdev/s3c2410fb.c
+++ b/drivers/video/fbdev/s3c2410fb.c
@@ -645,8 +645,8 @@ static int s3c2410fb_map_video_memory(struct fb_info *info)
dprintk("map_video_memory(fbi=%p) map_size %u\n", fbi, map_size);
- info->screen_base = dma_alloc_writecombine(fbi->dev, map_size,
- &map_dma, GFP_KERNEL);
+ info->screen_base = dma_alloc_wc(fbi->dev, map_size, &map_dma,
+ GFP_KERNEL);
if (info->screen_base) {
/* prevent initial garbage on screen */
@@ -667,8 +667,8 @@ static inline void s3c2410fb_unmap_video_memory(struct fb_info *info)
{
struct s3c2410fb_info *fbi = info->par;
- dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
- info->screen_base, info->fix.smem_start);
+ dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+ info->screen_base, info->fix.smem_start);
}
static inline void modify_gpio(void __iomem *reg,
diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c
index 89dd7e02197f..66467eb190b2 100644
--- a/drivers/video/fbdev/sa1100fb.c
+++ b/drivers/video/fbdev/sa1100fb.c
@@ -567,8 +567,8 @@ static int sa1100fb_mmap(struct fb_info *info,
if (off < info->fix.smem_len) {
vma->vm_pgoff += 1; /* skip over the palette */
- return dma_mmap_writecombine(fbi->dev, vma, fbi->map_cpu,
- fbi->map_dma, fbi->map_size);
+ return dma_mmap_wc(fbi->dev, vma, fbi->map_cpu, fbi->map_dma,
+ fbi->map_size);
}
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
@@ -1100,8 +1100,8 @@ static int sa1100fb_map_video_memory(struct sa1100fb_info *fbi)
* of the framebuffer.
*/
fbi->map_size = PAGE_ALIGN(fbi->fb.fix.smem_len + PAGE_SIZE);
- fbi->map_cpu = dma_alloc_writecombine(fbi->dev, fbi->map_size,
- &fbi->map_dma, GFP_KERNEL);
+ fbi->map_cpu = dma_alloc_wc(fbi->dev, fbi->map_size, &fbi->map_dma,
+ GFP_KERNEL);
if (fbi->map_cpu) {
fbi->fb.screen_base = fbi->map_cpu + PAGE_SIZE;
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index ac07ff090919..1f54e9bd6b34 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -271,26 +271,26 @@ struct dma_attrs;
dma_unmap_sg(dev, sgl, nents, dir)
#else
-static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
- dma_addr_t *dma_addr, gfp_t gfp)
+static inline void *dma_alloc_wc(struct device *dev, size_t size,
+ dma_addr_t *dma_addr, gfp_t gfp)
{
DEFINE_DMA_ATTRS(attrs);
dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
return dma_alloc_attrs(dev, size, dma_addr, gfp, &attrs);
}
-static inline void dma_free_writecombine(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t dma_addr)
+static inline void dma_free_wc(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t dma_addr)
{
DEFINE_DMA_ATTRS(attrs);
dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
return dma_free_attrs(dev, size, cpu_addr, dma_addr, &attrs);
}
-static inline int dma_mmap_writecombine(struct device *dev,
- struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr,
- size_t size)
+static inline int dma_mmap_wc(struct device *dev,
+ struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr,
+ size_t size)
{
DEFINE_DMA_ATTRS(attrs);
dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index 01f8fdc42b1b..5596f7cc8e73 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -238,8 +238,8 @@ int __pxa2xx_pcm_open(struct snd_pcm_substream *substream)
if (!rtd)
goto out;
rtd->dma_desc_array =
- dma_alloc_writecombine(substream->pcm->card->dev, PAGE_SIZE,
- &rtd->dma_desc_array_phys, GFP_KERNEL);
+ dma_alloc_wc(substream->pcm->card->dev, PAGE_SIZE,
+ &rtd->dma_desc_array_phys, GFP_KERNEL);
if (!rtd->dma_desc_array)
goto err1;
@@ -259,8 +259,8 @@ int __pxa2xx_pcm_close(struct snd_pcm_substream *substream)
struct snd_pcm_runtime *runtime = substream->runtime;
struct pxa2xx_runtime_data *rtd = runtime->private_data;
- dma_free_writecombine(substream->pcm->card->dev, PAGE_SIZE,
- rtd->dma_desc_array, rtd->dma_desc_array_phys);
+ dma_free_wc(substream->pcm->card->dev, PAGE_SIZE,
+ rtd->dma_desc_array, rtd->dma_desc_array_phys);
kfree(rtd);
return 0;
}
@@ -270,10 +270,8 @@ int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream,
struct vm_area_struct *vma)
{
struct snd_pcm_runtime *runtime = substream->runtime;
- return dma_mmap_writecombine(substream->pcm->card->dev, vma,
- runtime->dma_area,
- runtime->dma_addr,
- runtime->dma_bytes);
+ return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+ runtime->dma_addr, runtime->dma_bytes);
}
EXPORT_SYMBOL(pxa2xx_pcm_mmap);
@@ -285,8 +283,7 @@ int pxa2xx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
buf->dev.type = SNDRV_DMA_TYPE_DEV;
buf->dev.dev = pcm->card->dev;
buf->private_data = NULL;
- buf->area = dma_alloc_writecombine(pcm->card->dev, size,
- &buf->addr, GFP_KERNEL);
+ buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
if (!buf->area)
return -ENOMEM;
buf->bytes = size;
@@ -307,8 +304,7 @@ void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm)
buf = &substream->dma_buffer;
if (!buf->area)
continue;
- dma_free_writecombine(pcm->card->dev, buf->bytes,
- buf->area, buf->addr);
+ dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
buf->area = NULL;
}
}
diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c
index 7abf6a079574..ccdc4380d86a 100644
--- a/sound/soc/fsl/imx-pcm-fiq.c
+++ b/sound/soc/fsl/imx-pcm-fiq.c
@@ -217,8 +217,8 @@ static int snd_imx_pcm_mmap(struct snd_pcm_substream *substream,
struct snd_pcm_runtime *runtime = substream->runtime;
int ret;
- ret = dma_mmap_writecombine(substream->pcm->card->dev, vma,
- runtime->dma_area, runtime->dma_addr, runtime->dma_bytes);
+ ret = dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+ runtime->dma_addr, runtime->dma_bytes);
pr_debug("%s: ret: %d %p 0x%08x 0x%08x\n", __func__, ret,
runtime->dma_area,
@@ -247,8 +247,7 @@ static int imx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
buf->dev.type = SNDRV_DMA_TYPE_DEV;
buf->dev.dev = pcm->card->dev;
buf->private_data = NULL;
- buf->area = dma_alloc_writecombine(pcm->card->dev, size,
- &buf->addr, GFP_KERNEL);
+ buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
if (!buf->area)
return -ENOMEM;
buf->bytes = size;
@@ -330,8 +329,7 @@ static void imx_pcm_free(struct snd_pcm *pcm)
if (!buf->area)
continue;
- dma_free_writecombine(pcm->card->dev, buf->bytes,
- buf->area, buf->addr);
+ dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
buf->area = NULL;
}
}
diff --git a/sound/soc/nuc900/nuc900-pcm.c b/sound/soc/nuc900/nuc900-pcm.c
index 5ae5ca15b6d6..cd8175afa900 100644
--- a/sound/soc/nuc900/nuc900-pcm.c
+++ b/sound/soc/nuc900/nuc900-pcm.c
@@ -267,10 +267,8 @@ static int nuc900_dma_mmap(struct snd_pcm_substream *substream,
{
struct snd_pcm_runtime *runtime = substream->runtime;
- return dma_mmap_writecombine(substream->pcm->card->dev, vma,
- runtime->dma_area,
- runtime->dma_addr,
- runtime->dma_bytes);
+ return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+ runtime->dma_addr, runtime->dma_bytes);
}
static struct snd_pcm_ops nuc900_dma_ops = {
diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c
index 6bb623a2a4df..99381a27295b 100644
--- a/sound/soc/omap/omap-pcm.c
+++ b/sound/soc/omap/omap-pcm.c
@@ -156,10 +156,8 @@ static int omap_pcm_mmap(struct snd_pcm_substream *substream,
{
struct snd_pcm_runtime *runtime = substream->runtime;
- return dma_mmap_writecombine(substream->pcm->card->dev, vma,
- runtime->dma_area,
- runtime->dma_addr,
- runtime->dma_bytes);
+ return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+ runtime->dma_addr, runtime->dma_bytes);
}
static struct snd_pcm_ops omap_pcm_ops = {
@@ -183,8 +181,7 @@ static int omap_pcm_preallocate_dma_buffer(struct snd_pcm *pcm,
buf->dev.type = SNDRV_DMA_TYPE_DEV;
buf->dev.dev = pcm->card->dev;
buf->private_data = NULL;
- buf->area = dma_alloc_writecombine(pcm->card->dev, size,
- &buf->addr, GFP_KERNEL);
+ buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
if (!buf->area)
return -ENOMEM;
@@ -207,8 +204,7 @@ static void omap_pcm_free_dma_buffers(struct snd_pcm *pcm)
if (!buf->area)
continue;
- dma_free_writecombine(pcm->card->dev, buf->bytes,
- buf->area, buf->addr);
+ dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
buf->area = NULL;
}
}
--
2.4.3
From: "Luis R. Rodriguez" <[email protected]>
The crusade to replace mtrr_add() with architecture agnostic
arch_phys_wc_add() is complete, this will ensure write-combining
implementations (PAT on x86) is taken advantage instead of using
MTRR. With the crusade done now, hide direct MTRR access for
drivers.
Update x86 documentation on MTRR to reflect the completion of the
phasing out of direct access to MTRR, also add a note on platform
firmware code use of MTRRs based on the obituary discussion of
MTRRs on Linux [0].
[0] http://lkml.kernel.org/r/[email protected]
Cc: Toshi Kani <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Ingo Molnar <[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: Ville Syrjälä <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: Doug Ledford <[email protected]>
Cc: Andy Walls <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Signed-off-by: Luis R. Rodriguez <[email protected]>
---
Documentation/x86/mtrr.txt | 20 ++++++++++++++++----
arch/x86/kernel/cpu/mtrr/main.c | 2 --
2 files changed, 16 insertions(+), 6 deletions(-)
diff --git a/Documentation/x86/mtrr.txt b/Documentation/x86/mtrr.txt
index 860bc3adc223..8a0bdb6e7370 100644
--- a/Documentation/x86/mtrr.txt
+++ b/Documentation/x86/mtrr.txt
@@ -6,10 +6,22 @@ Luis R. Rodriguez <[email protected]> - April 9, 2015
===============================================================================
Phasing out MTRR use
-MTRR use is replaced on modern x86 hardware with PAT. Over time the only type
-of effective MTRR that is expected to be supported will be for write-combining.
-As MTRR use is phased out device drivers should use arch_phys_wc_add() to make
-MTRR effective on non-PAT systems while a no-op on PAT enabled systems.
+MTRR use is replaced on modern x86 hardware with PAT. Direct MTRR use by
+drivers on Linux is now completely phased out, device drivers should use
+arch_phys_wc_add() in combination with ioremap_wc() to make MTRR effective on
+non-PAT systems while a no-op but equally effective on PAT enabled systems.
+
+Even if Linux does not use MTRR directly some x86 platform firmware may still
+set up MTRRs early before booting the OS, they do this as some platform
+firmware may still have implemented access to MTRRs which would be controlled
+and handled by the platform firmware directly. An example of platform use of
+MTRR is through the use of SMI handlers, one case could be for fan control,
+the platform code would need uncachable access to some of its fan control
+registers. Such platform access does not need any Operating System MTRR code in
+place other than mtrr_type_lookup() to ensure any OS specific mapping requests
+are aligned with platform MTRR setup. If MTRRs are only set up by the platform
+firmware code though and the OS does not make any specific MTRR mapping
+requests mtrr_type_lookup() should always return MTRR_TYPE_INVALID.
For details refer to Documentation/x86/pat.txt.
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index e7ed0d8ebacb..f891b4750f04 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -448,7 +448,6 @@ int mtrr_add(unsigned long base, unsigned long size, unsigned int type,
return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
increment);
}
-EXPORT_SYMBOL(mtrr_add);
/**
* mtrr_del_page - delete a memory type region
@@ -537,7 +536,6 @@ int mtrr_del(int reg, unsigned long base, unsigned long size)
return -EINVAL;
return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
}
-EXPORT_SYMBOL(mtrr_del);
/**
* arch_phys_wc_add - add a WC MTRR and handle errors if PAT is unavailable
--
2.4.3
* Luis R. Rodriguez <[email protected]> wrote:
> From: "Luis R. Rodriguez" <[email protected]>
>
> Rename dma_*_writecombine() to dma_*_wc(), so that the naming
> is coherent across the various write-combining APIs.
>
> The following Coccinelle SmPL patch was used for this simple
> transformation:
>
> @ rename_dma_alloc_writecombine @
> expression dev, size, dma_addr, gfp;
> @@
>
> -dma_alloc_writecombine(dev, size, dma_addr, gfp)
> +dma_alloc_wc(dev, size, dma_addr, gfp)
>
> @ rename_dma_free_writecombine @
> expression dev, size, cpu_addr, dma_addr;
> @@
>
> -dma_free_writecombine(dev, size, cpu_addr, dma_addr)
> +dma_free_wc(dev, size, cpu_addr, dma_addr)
>
> @ rename_dma_mmap_writecombine @
> expression dev, vma, cpu_addr, dma_addr, size;
> @@
>
> -dma_mmap_writecombine(dev, vma, cpu_addr, dma_addr, size)
> +dma_mmap_wc(dev, vma, cpu_addr, dma_addr, size)
>
> Generated-by: Coccinelle SmPL
> Suggested-by: Ingo Molnar <[email protected]>
> Signed-off-by: Luis R. Rodriguez <[email protected]>
> ---
> arch/arm/mach-lpc32xx/phy3250.c | 13 ++++++-------
> arch/arm/mach-netx/fb.c | 14 ++++++--------
> arch/arm/mach-nspire/clcd.c | 13 ++++++-------
> arch/avr32/include/asm/dma-mapping.h | 20 ++++++++++----------
> arch/avr32/mm/dma-coherent.c | 12 ++++++------
> arch/metag/include/asm/dma-mapping.h | 4 ++--
> arch/metag/kernel/dma.c | 6 +++---
> drivers/dma/iop-adma.c | 8 ++++----
> drivers/dma/mv_xor.c | 4 ++--
> drivers/dma/qcom_bam_dma.c | 14 +++++++-------
> drivers/gpu/drm/drm_gem_cma_helper.c | 13 ++++++-------
> drivers/gpu/drm/omapdrm/omap_dmm_tiler.c | 13 ++++++-------
> drivers/gpu/drm/omapdrm/omap_gem.c | 8 ++++----
> drivers/gpu/drm/sti/sti_cursor.c | 13 ++++++-------
> drivers/gpu/drm/sti/sti_gdp.c | 3 +--
> drivers/gpu/drm/sti/sti_hqvdp.c | 6 +++---
> drivers/gpu/drm/tegra/gem.c | 11 +++++------
> drivers/gpu/host1x/cdma.c | 8 ++++----
> drivers/gpu/host1x/job.c | 10 ++++------
> drivers/media/platform/coda/coda-bit.c | 10 +++++-----
> drivers/video/fbdev/acornfb.c | 4 ++--
> drivers/video/fbdev/amba-clcd-versatile.c | 14 ++++++--------
> drivers/video/fbdev/amba-clcd.c | 4 ++--
> drivers/video/fbdev/atmel_lcdfb.c | 9 +++++----
> drivers/video/fbdev/ep93xx-fb.c | 9 +++------
> drivers/video/fbdev/gbefb.c | 8 ++++----
> drivers/video/fbdev/imxfb.c | 12 ++++++------
> drivers/video/fbdev/mx3fb.c | 9 ++++-----
> drivers/video/fbdev/nuc900fb.c | 8 ++++----
> drivers/video/fbdev/omap/lcdc.c | 16 ++++++++--------
> drivers/video/fbdev/pxa168fb.c | 8 ++++----
> drivers/video/fbdev/pxafb.c | 4 ++--
> drivers/video/fbdev/s3c-fb.c | 7 +++----
> drivers/video/fbdev/s3c2410fb.c | 8 ++++----
> drivers/video/fbdev/sa1100fb.c | 8 ++++----
> include/linux/dma-mapping.h | 16 ++++++++--------
> sound/arm/pxa2xx-pcm-lib.c | 20 ++++++++------------
> sound/soc/fsl/imx-pcm-fiq.c | 10 ++++------
> sound/soc/nuc900/nuc900-pcm.c | 6 ++----
> sound/soc/omap/omap-pcm.c | 12 ++++--------
> 40 files changed, 183 insertions(+), 212 deletions(-)
Which kernel is this against? It has conflicts in 3 files with Linus's latest:
v4.2-rc8.
Thanks,
Ingo
Commit-ID: c43996f4001de629af4a4d6713782e883677e5b9
Gitweb: http://git.kernel.org/tip/c43996f4001de629af4a4d6713782e883677e5b9
Author: Luis R. Rodriguez <[email protected]>
AuthorDate: Mon, 24 Aug 2015 12:13:23 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 25 Aug 2015 09:59:43 +0200
PCI: Add pci_ioremap_wc_bar()
This lets drivers take advantage of PAT when available. It
should help with the transition of converting video drivers over
to ioremap_wc() to help with the goal of eventually using
_PAGE_CACHE_UC over _PAGE_CACHE_UC_MINUS on x86 on
ioremap_nocache(), see:
de33c442ed2a ("x86 PAT: fix performance drop for glx, use UC minus for ioremap(), ioremap_nocache() and pci_mmap_page_range()")
Signed-off-by: Luis R. Rodriguez <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Acked-by: Arnd Bergmann <[email protected]>
Cc: <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Bjorn Helgaas <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tomi Valkeinen <[email protected]>
Cc: Toshi Kani <[email protected]>
Cc: Ville Syrjälä <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
drivers/pci/pci.c | 14 ++++++++++++++
include/linux/pci.h | 1 +
2 files changed, 15 insertions(+)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 0008c95..fdae37b 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -138,6 +138,20 @@ void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar)
return ioremap_nocache(res->start, resource_size(res));
}
EXPORT_SYMBOL_GPL(pci_ioremap_bar);
+
+void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar)
+{
+ /*
+ * Make sure the BAR is actually a memory resource, not an IO resource
+ */
+ if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) {
+ WARN_ON(1);
+ return NULL;
+ }
+ return ioremap_wc(pci_resource_start(pdev, bar),
+ pci_resource_len(pdev, bar));
+}
+EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar);
#endif
#define PCI_FIND_CAP_TTL 48
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 8a0321a..985dd39 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1661,6 +1661,7 @@ static inline void pci_mmcfg_late_init(void) { }
int pci_ext_cfg_avail(void);
void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar);
+void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar);
#ifdef CONFIG_PCI_IOV
int pci_iov_virtfn_bus(struct pci_dev *dev, int id);
Commit-ID: c112709809b2ca1e8ff2841a1958503e548b81e4
Gitweb: http://git.kernel.org/tip/c112709809b2ca1e8ff2841a1958503e548b81e4
Author: Luis R. Rodriguez <[email protected]>
AuthorDate: Mon, 24 Aug 2015 12:13:24 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 25 Aug 2015 09:59:44 +0200
drivers/video/fbdev/i740fb: Use arch_phys_wc_add() and pci_ioremap_wc_bar()
Convert the driver from using the x86-specific MTRR code to the
architecture-agnostic arch_phys_wc_add(). It will avoid MTRR if
write-combining is available, in order to take advantage of that
also ensure the ioremapped 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 it is being 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 ifdeffery 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);
Signed-off-by: Luis R. Rodriguez <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Benoit Taine <[email protected]>
Cc: Bjorn Helgaas <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Jingoo Han <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Rob Clark <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
drivers/video/fbdev/i740fb.c | 35 ++++++-----------------------------
1 file changed, 6 insertions(+), 29 deletions(-)
diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c
index a2b4204..452e116 100644
--- a/drivers/video/fbdev/i740fb.c
+++ b/drivers/video/fbdev/i740fb.c
@@ -27,24 +27,15 @@
#include <linux/console.h>
#include <video/vga.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
#include "i740_reg.h"
static char *mode_option;
-
-#ifdef CONFIG_MTRR
static int mtrr = 1;
-#endif
struct i740fb_par {
unsigned char __iomem *regs;
bool has_sgram;
-#ifdef CONFIG_MTRR
- int mtrr_reg;
-#endif
+ int wc_cookie;
bool ddc_registered;
struct i2c_adapter ddc_adapter;
struct i2c_algo_bit_data ddc_algo;
@@ -1040,7 +1031,7 @@ static int i740fb_probe(struct pci_dev *dev, const struct pci_device_id *ent)
goto err_request_regions;
}
- info->screen_base = pci_ioremap_bar(dev, 0);
+ info->screen_base = pci_ioremap_wc_bar(dev, 0);
if (!info->screen_base) {
dev_err(info->device, "error remapping base\n");
ret = -ENOMEM;
@@ -1144,13 +1135,9 @@ static int i740fb_probe(struct pci_dev *dev, const struct pci_device_id *ent)
fb_info(info, "%s frame buffer device\n", info->fix.id);
pci_set_drvdata(dev, info);
-#ifdef CONFIG_MTRR
- if (mtrr) {
- par->mtrr_reg = -1;
- par->mtrr_reg = mtrr_add(info->fix.smem_start,
- info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
- }
-#endif
+ if (mtrr)
+ par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+ info->fix.smem_len);
return 0;
err_reg_framebuffer:
@@ -1177,13 +1164,7 @@ static void i740fb_remove(struct pci_dev *dev)
if (info) {
struct i740fb_par *par = info->par;
-
-#ifdef CONFIG_MTRR
- if (par->mtrr_reg >= 0) {
- mtrr_del(par->mtrr_reg, 0, 0);
- par->mtrr_reg = -1;
- }
-#endif
+ arch_phys_wc_del(par->wc_cookie);
unregister_framebuffer(info);
fb_dealloc_cmap(&info->cmap);
if (par->ddc_registered)
@@ -1287,10 +1268,8 @@ static int __init i740fb_setup(char *options)
while ((opt = strsep(&options, ",")) != NULL) {
if (!*opt)
continue;
-#ifdef CONFIG_MTRR
else if (!strncmp(opt, "mtrr:", 5))
mtrr = simple_strtoul(opt + 5, NULL, 0);
-#endif
else
mode_option = opt;
}
@@ -1327,7 +1306,5 @@ MODULE_DESCRIPTION("fbdev driver for Intel740");
module_param(mode_option, charp, 0444);
MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
-#ifdef CONFIG_MTRR
module_param(mtrr, int, 0444);
MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
Commit-ID: 9e517ac88b2443bebc0499c0b477b155d63648a7
Gitweb: http://git.kernel.org/tip/9e517ac88b2443bebc0499c0b477b155d63648a7
Author: Luis R. Rodriguez <[email protected]>
AuthorDate: Mon, 24 Aug 2015 12:13:25 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 25 Aug 2015 09:59:44 +0200
drivers/video/fbdev/kyrofb: Use arch_phys_wc_add() and pci_ioremap_wc_bar()
Convert the driver from using the x86-specific MTRR code to the
architecture-agnostic arch_phys_wc_add(). It will avoid MTRR if
write-combining is available, in order to take advantage of that
also ensure the ioremapped 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 it is being 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 ifdeffery 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);
Signed-off-by: Luis R. Rodriguez <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Jingoo Han <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Laurent Pinchart <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
drivers/video/fbdev/kyro/fbdev.c | 33 +++++++++++----------------------
include/video/kyro.h | 4 +---
2 files changed, 12 insertions(+), 25 deletions(-)
diff --git a/drivers/video/fbdev/kyro/fbdev.c b/drivers/video/fbdev/kyro/fbdev.c
index 65041e1..5bb0153 100644
--- a/drivers/video/fbdev/kyro/fbdev.c
+++ b/drivers/video/fbdev/kyro/fbdev.c
@@ -22,9 +22,6 @@
#include <linux/pci.h>
#include <asm/io.h>
#include <linux/uaccess.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
#include <video/kyro.h>
@@ -84,9 +81,7 @@ static device_info_t deviceInfo;
static char *mode_option = NULL;
static int nopan = 0;
static int nowrap = 1;
-#ifdef CONFIG_MTRR
static int nomtrr = 0;
-#endif
/* PCI driver prototypes */
static int kyrofb_probe(struct pci_dev *pdev, const struct pci_device_id *ent);
@@ -570,10 +565,8 @@ static int __init kyrofb_setup(char *options)
nopan = 1;
} else if (strcmp(this_opt, "nowrap") == 0) {
nowrap = 1;
-#ifdef CONFIG_MTRR
} else if (strcmp(this_opt, "nomtrr") == 0) {
nomtrr = 1;
-#endif
} else {
mode_option = this_opt;
}
@@ -691,17 +684,16 @@ static int kyrofb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
currentpar->regbase = deviceInfo.pSTGReg =
ioremap_nocache(kyro_fix.mmio_start, kyro_fix.mmio_len);
+ if (!currentpar->regbase)
+ goto out_free_fb;
- info->screen_base = ioremap_nocache(kyro_fix.smem_start,
- kyro_fix.smem_len);
+ info->screen_base = pci_ioremap_wc_bar(pdev, 0);
+ if (!info->screen_base)
+ goto out_unmap_regs;
-#ifdef CONFIG_MTRR
if (!nomtrr)
- currentpar->mtrr_handle =
- mtrr_add(kyro_fix.smem_start,
- kyro_fix.smem_len,
- MTRR_TYPE_WRCOMB, 1);
-#endif
+ currentpar->wc_cookie = arch_phys_wc_add(kyro_fix.smem_start,
+ kyro_fix.smem_len);
kyro_fix.ypanstep = nopan ? 0 : 1;
kyro_fix.ywrapstep = nowrap ? 0 : 1;
@@ -745,8 +737,10 @@ static int kyrofb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
return 0;
out_unmap:
- iounmap(currentpar->regbase);
iounmap(info->screen_base);
+out_unmap_regs:
+ iounmap(currentpar->regbase);
+out_free_fb:
framebuffer_release(info);
return -EINVAL;
@@ -770,12 +764,7 @@ static void kyrofb_remove(struct pci_dev *pdev)
iounmap(info->screen_base);
iounmap(par->regbase);
-#ifdef CONFIG_MTRR
- if (par->mtrr_handle)
- mtrr_del(par->mtrr_handle,
- info->fix.smem_start,
- info->fix.smem_len);
-#endif
+ arch_phys_wc_del(par->wc_cookie);
unregister_framebuffer(info);
framebuffer_release(info);
diff --git a/include/video/kyro.h b/include/video/kyro.h
index c563968..b958c2e 100644
--- a/include/video/kyro.h
+++ b/include/video/kyro.h
@@ -35,9 +35,7 @@ struct kyrofb_info {
/* Useful to hold depth here for Linux */
u8 PIXDEPTH;
-#ifdef CONFIG_MTRR
- int mtrr_handle;
-#endif
+ int wc_cookie;
};
extern int kyro_dev_init(void);
Commit-ID: f3adccbd75831f3651ca6e2cbb83f27cd68a27c9
Gitweb: http://git.kernel.org/tip/f3adccbd75831f3651ca6e2cbb83f27cd68a27c9
Author: Luis R. Rodriguez <[email protected]>
AuthorDate: Mon, 24 Aug 2015 12:13:26 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 25 Aug 2015 09:59:44 +0200
drivers/video/fbdev/gxt4500: Use pci_ioremap_wc_bar() to map framebuffer
The driver doesn't use mtrr_add() or arch_phys_wc_add() but
since we know the framebuffer is isolated already on an
ioremap() we can take advantage of write combining for
performance where possible.
In this case there are a few motivations for this:
a) Take advantage of PAT when available.
b) 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()").
Signed-off-by: Luis R. Rodriguez <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Laurent Pinchart <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Rob Clark <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
drivers/video/fbdev/gxt4500.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/video/fbdev/gxt4500.c b/drivers/video/fbdev/gxt4500.c
index 135d78a..f19133a 100644
--- a/drivers/video/fbdev/gxt4500.c
+++ b/drivers/video/fbdev/gxt4500.c
@@ -662,7 +662,7 @@ static int gxt4500_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
info->fix.smem_start = fb_phys;
info->fix.smem_len = pci_resource_len(pdev, 1);
- info->screen_base = pci_ioremap_bar(pdev, 1);
+ info->screen_base = pci_ioremap_wc_bar(pdev, 1);
if (!info->screen_base) {
dev_err(&pdev->dev, "gxt4500: cannot map framebuffer\n");
goto err_unmap_regs;
Commit-ID: 1b3d4200c1e00a3fb5e0aea428de5b07079a37e3
Gitweb: http://git.kernel.org/tip/1b3d4200c1e00a3fb5e0aea428de5b07079a37e3
Author: Luis R. Rodriguez <[email protected]>
AuthorDate: Mon, 24 Aug 2015 12:13:27 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 25 Aug 2015 09:59:45 +0200
PCI: Add pci_iomap_wc() variants
PCI BARs tell us whether prefetching is safe, but they don't say
anything about write combining (WC). WC changes ordering rules
and allows writes to be collapsed, so it's not safe in general
to use it on a prefetchable region.
Add pci_iomap_wc() and pci_iomap_wc_range() so drivers can take
advantage of write combining when they know it's safe.
On architectures that don't fully support WC, e.g., x86 without
PAT, drivers for legacy framebuffers may get some of the benefit
by using arch_phys_wc_add() in addition to pci_iomap_wc(). But
arch_phys_wc_add() is unreliable and should be avoided in
general. On x86, it uses MTRRs, which are limited in number and
size, so the results will vary based on driver loading order.
The goals of adding pci_iomap_wc() are to:
- Give drivers an architecture-independent way to use WC so they can stop
using interfaces like mtrr_add() (on x86, pci_iomap_wc() uses
PAT when available).
- Move toward using _PAGE_CACHE_MODE_UC, not _PAGE_CACHE_MODE_UC_MINUS,
on x86 on ioremap_nocache() (see de33c442ed2a ("x86 PAT: fix
performance drop for glx, use UC minus for ioremap(), ioremap_nocache()
and pci_mmap_page_range()").
Signed-off-by: Luis R. Rodriguez <[email protected]>
[ Move IORESOURCE_IO check up, space out statements for better readability. ]
Signed-off-by: Borislav Petkov <[email protected]>
Acked-by: Arnd Bergmann <[email protected]>
Cc: <[email protected]>
Cc: <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Bjorn Helgaas <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Michael S. Tsirkin <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Roger Pau Monné <[email protected]>
Cc: Rusty Russell <[email protected]>
Cc: Stefan Bader <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tomi Valkeinen <[email protected]>
Cc: Toshi Kani <[email protected]>
Cc: Ville Syrjälä <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
include/asm-generic/pci_iomap.h | 14 +++++++++
lib/pci_iomap.c | 66 +++++++++++++++++++++++++++++++++++++++++
2 files changed, 80 insertions(+)
diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h
index 7389c87..b1e17fc 100644
--- a/include/asm-generic/pci_iomap.h
+++ b/include/asm-generic/pci_iomap.h
@@ -15,9 +15,13 @@ struct pci_dev;
#ifdef CONFIG_PCI
/* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+extern void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long max);
extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
unsigned long offset,
unsigned long maxlen);
+extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
+ unsigned long offset,
+ unsigned long maxlen);
/* Create a virtual mapping cookie for a port on a given PCI device.
* Do not call this directly, it exists to make it easier for architectures
* to override */
@@ -34,12 +38,22 @@ static inline void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned lon
return NULL;
}
+static inline void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long max)
+{
+ return NULL;
+}
static inline void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
unsigned long offset,
unsigned long maxlen)
{
return NULL;
}
+static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
+ unsigned long offset,
+ unsigned long maxlen)
+{
+ return NULL;
+}
#endif
#endif /* __ASM_GENERIC_IO_H */
diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c
index bcce5f1..5f5d24d 100644
--- a/lib/pci_iomap.c
+++ b/lib/pci_iomap.c
@@ -52,6 +52,51 @@ void __iomem *pci_iomap_range(struct pci_dev *dev,
EXPORT_SYMBOL(pci_iomap_range);
/**
+ * pci_iomap_wc_range - create a virtual WC mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @offset: map memory at the given offset in BAR
+ * @maxlen: max length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way. When possible write combining
+ * is used.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR from offset to the end, pass %0 here.
+ * */
+void __iomem *pci_iomap_wc_range(struct pci_dev *dev,
+ int bar,
+ unsigned long offset,
+ unsigned long maxlen)
+{
+ resource_size_t start = pci_resource_start(dev, bar);
+ resource_size_t len = pci_resource_len(dev, bar);
+ unsigned long flags = pci_resource_flags(dev, bar);
+
+
+ if (flags & IORESOURCE_IO)
+ return NULL;
+
+ if (len <= offset || !start)
+ return NULL;
+
+ len -= offset;
+ start += offset;
+ if (maxlen && len > maxlen)
+ len = maxlen;
+
+ if (flags & IORESOURCE_MEM)
+ return ioremap_wc(start, len);
+
+ /* What? */
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(pci_iomap_wc_range);
+
+/**
* pci_iomap - create a virtual mapping cookie for a PCI BAR
* @dev: PCI device that owns the BAR
* @bar: BAR number
@@ -70,4 +115,25 @@ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
return pci_iomap_range(dev, bar, 0, maxlen);
}
EXPORT_SYMBOL(pci_iomap);
+
+/**
+ * pci_iomap_wc - create a virtual WC mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @maxlen: length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way. When possible write combining
+ * is used.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR without checking for its length first, pass %0 here.
+ * */
+void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+ return pci_iomap_wc_range(dev, bar, 0, maxlen);
+}
+EXPORT_SYMBOL_GPL(pci_iomap_wc);
#endif /* CONFIG_PCI */
Commit-ID: c823a48ac47f8e0274fa7c8a3befae4bfa8412e3
Gitweb: http://git.kernel.org/tip/c823a48ac47f8e0274fa7c8a3befae4bfa8412e3
Author: Luis R. Rodriguez <[email protected]>
AuthorDate: Mon, 24 Aug 2015 12:13:28 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 25 Aug 2015 09:59:45 +0200
drivers/video/fbdev/arkfb.c: Use arch_phys_wc_add() and pci_iomap_wc()
Convert the driver from using the x86-specific MTRR code to the
architecture-agnostic arch_phys_wc_add(). It will avoid MTRRs if
write-combining is available. In order to take advantage of that
also ensure the ioremapped 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 it is being 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 ifdeffery 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);
Signed-off-by: Luis R. Rodriguez <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Lad, Prabhakar <[email protected]>
Cc: Laurent Pinchart <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
drivers/video/fbdev/arkfb.c | 36 +++++-------------------------------
1 file changed, 5 insertions(+), 31 deletions(-)
diff --git a/drivers/video/fbdev/arkfb.c b/drivers/video/fbdev/arkfb.c
index b305a1e..6a317de 100644
--- a/drivers/video/fbdev/arkfb.c
+++ b/drivers/video/fbdev/arkfb.c
@@ -26,13 +26,9 @@
#include <linux/console.h> /* Why should fb driver call console functions? because console_lock() */
#include <video/vga.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
struct arkfb_info {
int mclk_freq;
- int mtrr_reg;
+ int wc_cookie;
struct dac_info *dac;
struct vgastate state;
@@ -102,10 +98,6 @@ static const struct svga_timing_regs ark_timing_regs = {
static char *mode_option = "640x480-8@60";
-#ifdef CONFIG_MTRR
-static int mtrr = 1;
-#endif
-
MODULE_AUTHOR("(c) 2007 Ondrej Zajicek <[email protected]>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("fbdev driver for ARK 2000PV");
@@ -115,11 +107,6 @@ MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
module_param_named(mode, mode_option, charp, 0444);
MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc) (deprecated)");
-#ifdef CONFIG_MTRR
-module_param(mtrr, int, 0444);
-MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
-
static int threshold = 4;
module_param(threshold, int, 0644);
@@ -1002,7 +989,7 @@ static int ark_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
info->fix.smem_len = pci_resource_len(dev, 0);
/* Map physical IO memory address into kernel space */
- info->screen_base = pci_iomap(dev, 0, 0);
+ info->screen_base = pci_iomap_wc(dev, 0, 0);
if (! info->screen_base) {
rc = -ENOMEM;
dev_err(info->device, "iomap for framebuffer failed\n");
@@ -1057,14 +1044,8 @@ static int ark_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
/* Record a reference to the driver data */
pci_set_drvdata(dev, info);
-
-#ifdef CONFIG_MTRR
- if (mtrr) {
- par->mtrr_reg = -1;
- par->mtrr_reg = mtrr_add(info->fix.smem_start, info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
- }
-#endif
-
+ par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+ info->fix.smem_len);
return 0;
/* Error handling */
@@ -1092,14 +1073,7 @@ static void ark_pci_remove(struct pci_dev *dev)
if (info) {
struct arkfb_info *par = info->par;
-
-#ifdef CONFIG_MTRR
- if (par->mtrr_reg >= 0) {
- mtrr_del(par->mtrr_reg, 0, 0);
- par->mtrr_reg = -1;
- }
-#endif
-
+ arch_phys_wc_del(par->wc_cookie);
dac_release(par->dac);
unregister_framebuffer(info);
fb_dealloc_cmap(&info->cmap);
Commit-ID: 4edcd2ab125506516c7de038f6e0a6d19dcc411d
Gitweb: http://git.kernel.org/tip/4edcd2ab125506516c7de038f6e0a6d19dcc411d
Author: Luis R. Rodriguez <[email protected]>
AuthorDate: Mon, 24 Aug 2015 12:13:29 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 25 Aug 2015 09:59:45 +0200
drivers/video/fbdev/s3fb: Use arch_phys_wc_add() and pci_iomap_wc()
This driver uses the same area for MTRR as for the ioremap().
Convert the driver from using the x86-specific MTRR code to the
architecture-agnostic arch_phys_wc_add(). It will avoid MTRRs if
write-combining is available. In order to take advantage of that
also ensure the ioremapped 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 it is being 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 ifdeffery 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);
Signed-off-by: Luis R. Rodriguez <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Jingoo Han <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Lad, Prabhakar <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Rickard Strandqvist <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
drivers/video/fbdev/s3fb.c | 35 ++++++-----------------------------
1 file changed, 6 insertions(+), 29 deletions(-)
diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c
index f0ae61a..13b1090 100644
--- a/drivers/video/fbdev/s3fb.c
+++ b/drivers/video/fbdev/s3fb.c
@@ -28,13 +28,9 @@
#include <linux/i2c.h>
#include <linux/i2c-algo-bit.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
struct s3fb_info {
int chip, rev, mclk_freq;
- int mtrr_reg;
+ int wc_cookie;
struct vgastate state;
struct mutex open_lock;
unsigned int ref_count;
@@ -154,11 +150,7 @@ static const struct svga_timing_regs s3_timing_regs = {
static char *mode_option;
-
-#ifdef CONFIG_MTRR
static int mtrr = 1;
-#endif
-
static int fasttext = 1;
@@ -170,11 +162,8 @@ module_param(mode_option, charp, 0444);
MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
module_param_named(mode, mode_option, charp, 0444);
MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc) (deprecated)");
-
-#ifdef CONFIG_MTRR
module_param(mtrr, int, 0444);
MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
module_param(fasttext, int, 0644);
MODULE_PARM_DESC(fasttext, "Enable S3 fast text mode (1=enable, 0=disable, default=1)");
@@ -1168,7 +1157,7 @@ static int s3_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
info->fix.smem_len = pci_resource_len(dev, 0);
/* Map physical IO memory address into kernel space */
- info->screen_base = pci_iomap(dev, 0, 0);
+ info->screen_base = pci_iomap_wc(dev, 0, 0);
if (! info->screen_base) {
rc = -ENOMEM;
dev_err(info->device, "iomap for framebuffer failed\n");
@@ -1365,12 +1354,9 @@ static int s3_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
/* Record a reference to the driver data */
pci_set_drvdata(dev, info);
-#ifdef CONFIG_MTRR
- if (mtrr) {
- par->mtrr_reg = -1;
- par->mtrr_reg = mtrr_add(info->fix.smem_start, info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
- }
-#endif
+ if (mtrr)
+ par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+ info->fix.smem_len);
return 0;
@@ -1405,14 +1391,7 @@ static void s3_pci_remove(struct pci_dev *dev)
if (info) {
par = info->par;
-
-#ifdef CONFIG_MTRR
- if (par->mtrr_reg >= 0) {
- mtrr_del(par->mtrr_reg, 0, 0);
- par->mtrr_reg = -1;
- }
-#endif
-
+ arch_phys_wc_del(par->wc_cookie);
unregister_framebuffer(info);
fb_dealloc_cmap(&info->cmap);
@@ -1551,10 +1530,8 @@ static int __init s3fb_setup(char *options)
if (!*opt)
continue;
-#ifdef CONFIG_MTRR
else if (!strncmp(opt, "mtrr:", 5))
mtrr = simple_strtoul(opt + 5, NULL, 0);
-#endif
else if (!strncmp(opt, "fasttext:", 9))
fasttext = simple_strtoul(opt + 9, NULL, 0);
else
Commit-ID: 81bdef04d3bc76fc516ca613fa96061ff27bced9
Gitweb: http://git.kernel.org/tip/81bdef04d3bc76fc516ca613fa96061ff27bced9
Author: Luis R. Rodriguez <[email protected]>
AuthorDate: Mon, 24 Aug 2015 12:13:30 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 25 Aug 2015 09:59:45 +0200
drivers/video/fbdev/vt8623fb: Use arch_phys_wc_add() and pci_iomap_wc()
This driver uses the same area for MTRR as for the ioremap().
Convert the driver from using the x86-specific MTRR code to the
architecture-agnostic arch_phys_wc_add(). It will avoid MTRRs if
write-combining is available. In order to take advantage of that
also ensure the ioremapped 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 it is being 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 ifdeffery 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);
Signed-off-by: Luis R. Rodriguez <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Acked-by: Tomi Valkeinen <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Jingoo Han <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Lad, Prabhakar <[email protected]>
Cc: Laurent Pinchart <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Rob Clark <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
drivers/video/fbdev/vt8623fb.c | 31 ++++++-------------------------
1 file changed, 6 insertions(+), 25 deletions(-)
diff --git a/drivers/video/fbdev/vt8623fb.c b/drivers/video/fbdev/vt8623fb.c
index 8bac309..dd0f18e 100644
--- a/drivers/video/fbdev/vt8623fb.c
+++ b/drivers/video/fbdev/vt8623fb.c
@@ -26,13 +26,9 @@
#include <linux/console.h> /* Why should fb driver call console functions? because console_lock() */
#include <video/vga.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
struct vt8623fb_info {
char __iomem *mmio_base;
- int mtrr_reg;
+ int wc_cookie;
struct vgastate state;
struct mutex open_lock;
unsigned int ref_count;
@@ -99,10 +95,7 @@ static struct svga_timing_regs vt8623_timing_regs = {
/* Module parameters */
static char *mode_option = "640x480-8@60";
-
-#ifdef CONFIG_MTRR
static int mtrr = 1;
-#endif
MODULE_AUTHOR("(c) 2006 Ondrej Zajicek <[email protected]>");
MODULE_LICENSE("GPL");
@@ -112,11 +105,8 @@ module_param(mode_option, charp, 0644);
MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
module_param_named(mode, mode_option, charp, 0);
MODULE_PARM_DESC(mode, "Default video mode e.g. '648x480-8@60' (deprecated)");
-
-#ifdef CONFIG_MTRR
module_param(mtrr, int, 0444);
MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
/* ------------------------------------------------------------------------- */
@@ -710,7 +700,7 @@ static int vt8623_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
info->fix.mmio_len = pci_resource_len(dev, 1);
/* Map physical IO memory address into kernel space */
- info->screen_base = pci_iomap(dev, 0, 0);
+ info->screen_base = pci_iomap_wc(dev, 0, 0);
if (! info->screen_base) {
rc = -ENOMEM;
dev_err(info->device, "iomap for framebuffer failed\n");
@@ -781,12 +771,9 @@ static int vt8623_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
/* Record a reference to the driver data */
pci_set_drvdata(dev, info);
-#ifdef CONFIG_MTRR
- if (mtrr) {
- par->mtrr_reg = -1;
- par->mtrr_reg = mtrr_add(info->fix.smem_start, info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
- }
-#endif
+ if (mtrr)
+ par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+ info->fix.smem_len);
return 0;
@@ -816,13 +803,7 @@ static void vt8623_pci_remove(struct pci_dev *dev)
if (info) {
struct vt8623fb_info *par = info->par;
-#ifdef CONFIG_MTRR
- if (par->mtrr_reg >= 0) {
- mtrr_del(par->mtrr_reg, 0, 0);
- par->mtrr_reg = -1;
- }
-#endif
-
+ arch_phys_wc_del(par->wc_cookie);
unregister_framebuffer(info);
fb_dealloc_cmap(&info->cmap);
Commit-ID: 39c33704420b147fb7e193a9f406cc8420a1d610
Gitweb: http://git.kernel.org/tip/39c33704420b147fb7e193a9f406cc8420a1d610
Author: Luis R. Rodriguez <[email protected]>
AuthorDate: Mon, 24 Aug 2015 12:13:31 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 25 Aug 2015 09:59:46 +0200
drivers/dma/iop-adma: Use dma_alloc_writecombine() kernel-style
dma_alloc_writecombine()'s call and return value check is
tangled in all in one call. Untangle both calls according to
kernel coding style.
Signed-off-by: Luis R. Rodriguez <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Acked-by: Vinod Koul <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
drivers/dma/iop-adma.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index 9988268..e4f4312 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -1300,10 +1300,11 @@ static int iop_adma_probe(struct platform_device *pdev)
* note: writecombine gives slightly better performance, but
* requires that we explicitly flush the writes
*/
- if ((adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
- plat_data->pool_size,
- &adev->dma_desc_pool,
- GFP_KERNEL)) == NULL) {
+ adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
+ plat_data->pool_size,
+ &adev->dma_desc_pool,
+ GFP_KERNEL);
+ if (!adev->dma_desc_pool_virt) {
ret = -ENOMEM;
goto err_free_adev;
}
On Tue, Aug 25, 2015 at 09:53:18AM +0200, Ingo Molnar wrote:
> Which kernel is this against? It has conflicts in 3 files with Linus's latest:
> v4.2-rc8.
Sorry I based it on linux-next, will respin the rename patch onto tip/auto-latest
Luis
From: "Luis R. Rodriguez" <[email protected]>
Rename dma_*_writecombine() to dma_*_wc(), so that the naming
is coherent across the various write-combining APIs.
The following Coccinelle SmPL patch was used for this simple
transformation:
@ rename_dma_alloc_writecombine @
expression dev, size, dma_addr, gfp;
@@
-dma_alloc_writecombine(dev, size, dma_addr, gfp)
+dma_alloc_wc(dev, size, dma_addr, gfp)
@ rename_dma_free_writecombine @
expression dev, size, cpu_addr, dma_addr;
@@
-dma_free_writecombine(dev, size, cpu_addr, dma_addr)
+dma_free_wc(dev, size, cpu_addr, dma_addr)
@ rename_dma_mmap_writecombine @
expression dev, vma, cpu_addr, dma_addr, size;
@@
-dma_mmap_writecombine(dev, vma, cpu_addr, dma_addr, size)
+dma_mmap_wc(dev, vma, cpu_addr, dma_addr, size)
Generated-by: Coccinelle SmPL
Suggested-by: Ingo Molnar <[email protected]>
Signed-off-by: Luis R. Rodriguez <[email protected]>
---
arch/arm/mach-lpc32xx/phy3250.c | 13 ++++++-------
arch/arm/mach-netx/fb.c | 14 ++++++--------
arch/arm/mach-nspire/clcd.c | 13 ++++++-------
arch/avr32/include/asm/dma-mapping.h | 20 ++++++++++----------
arch/avr32/mm/dma-coherent.c | 12 ++++++------
arch/metag/include/asm/dma-mapping.h | 4 ++--
arch/metag/kernel/dma.c | 6 +++---
drivers/dma/iop-adma.c | 8 ++++----
drivers/dma/mv_xor.c | 4 ++--
drivers/dma/qcom_bam_dma.c | 14 +++++++-------
drivers/gpu/drm/drm_gem_cma_helper.c | 13 ++++++-------
drivers/gpu/drm/omapdrm/omap_dmm_tiler.c | 13 ++++++-------
drivers/gpu/drm/omapdrm/omap_gem.c | 8 ++++----
drivers/gpu/drm/sti/sti_cursor.c | 20 ++++++++------------
drivers/gpu/drm/sti/sti_gdp.c | 3 +--
drivers/gpu/drm/sti/sti_hqvdp.c | 6 +++---
drivers/gpu/drm/tegra/gem.c | 11 +++++------
drivers/gpu/host1x/cdma.c | 8 ++++----
drivers/gpu/host1x/job.c | 10 ++++------
drivers/media/platform/coda/coda-bit.c | 10 +++++-----
drivers/video/fbdev/acornfb.c | 4 ++--
drivers/video/fbdev/amba-clcd-versatile.c | 14 ++++++--------
drivers/video/fbdev/amba-clcd.c | 4 ++--
drivers/video/fbdev/atmel_lcdfb.c | 9 +++++----
drivers/video/fbdev/ep93xx-fb.c | 8 +++-----
drivers/video/fbdev/gbefb.c | 8 ++++----
drivers/video/fbdev/imxfb.c | 12 ++++++------
drivers/video/fbdev/mx3fb.c | 9 ++++-----
drivers/video/fbdev/nuc900fb.c | 8 ++++----
drivers/video/fbdev/omap/lcdc.c | 16 ++++++++--------
drivers/video/fbdev/pxa168fb.c | 8 ++++----
drivers/video/fbdev/pxafb.c | 4 ++--
drivers/video/fbdev/s3c-fb.c | 7 +++----
drivers/video/fbdev/s3c2410fb.c | 8 ++++----
drivers/video/fbdev/sa1100fb.c | 8 ++++----
include/linux/dma-mapping.h | 16 ++++++++--------
sound/arm/pxa2xx-pcm-lib.c | 20 ++++++++------------
sound/soc/fsl/imx-pcm-fiq.c | 10 ++++------
sound/soc/nuc900/nuc900-pcm.c | 6 ++----
sound/soc/omap/omap-pcm.c | 12 ++++--------
40 files changed, 185 insertions(+), 216 deletions(-)
diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c
index 7858d5b6f6ce..43ff56c2a7a9 100644
--- a/arch/arm/mach-lpc32xx/phy3250.c
+++ b/arch/arm/mach-lpc32xx/phy3250.c
@@ -86,8 +86,8 @@ static int lpc32xx_clcd_setup(struct clcd_fb *fb)
{
dma_addr_t dma;
- fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev,
- PANEL_SIZE, &dma, GFP_KERNEL);
+ fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, PANEL_SIZE, &dma,
+ GFP_KERNEL);
if (!fb->fb.screen_base) {
printk(KERN_ERR "CLCD: unable to map framebuffer\n");
return -ENOMEM;
@@ -116,15 +116,14 @@ static int lpc32xx_clcd_setup(struct clcd_fb *fb)
static int lpc32xx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
{
- return dma_mmap_writecombine(&fb->dev->dev, vma,
- fb->fb.screen_base, fb->fb.fix.smem_start,
- fb->fb.fix.smem_len);
+ return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+ fb->fb.fix.smem_start, fb->fb.fix.smem_len);
}
static void lpc32xx_clcd_remove(struct clcd_fb *fb)
{
- dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
- fb->fb.screen_base, fb->fb.fix.smem_start);
+ dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+ fb->fb.fix.smem_start);
}
/*
diff --git a/arch/arm/mach-netx/fb.c b/arch/arm/mach-netx/fb.c
index d122ee6ab991..8814ee5e98fd 100644
--- a/arch/arm/mach-netx/fb.c
+++ b/arch/arm/mach-netx/fb.c
@@ -42,8 +42,8 @@ int netx_clcd_setup(struct clcd_fb *fb)
fb->panel = netx_panel;
- fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, 1024*1024,
- &dma, GFP_KERNEL);
+ fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, 1024 * 1024, &dma,
+ GFP_KERNEL);
if (!fb->fb.screen_base) {
printk(KERN_ERR "CLCD: unable to map framebuffer\n");
return -ENOMEM;
@@ -57,16 +57,14 @@ int netx_clcd_setup(struct clcd_fb *fb)
int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
{
- return dma_mmap_writecombine(&fb->dev->dev, vma,
- fb->fb.screen_base,
- fb->fb.fix.smem_start,
- fb->fb.fix.smem_len);
+ return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+ fb->fb.fix.smem_start, fb->fb.fix.smem_len);
}
void netx_clcd_remove(struct clcd_fb *fb)
{
- dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
- fb->fb.screen_base, fb->fb.fix.smem_start);
+ dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+ fb->fb.fix.smem_start);
}
static AMBA_AHB_DEVICE(fb, "fb", 0, 0x00104000, { NETX_IRQ_LCD }, NULL);
diff --git a/arch/arm/mach-nspire/clcd.c b/arch/arm/mach-nspire/clcd.c
index abea12617b17..ea0e5b2ca1cd 100644
--- a/arch/arm/mach-nspire/clcd.c
+++ b/arch/arm/mach-nspire/clcd.c
@@ -90,8 +90,8 @@ int nspire_clcd_setup(struct clcd_fb *fb)
panel_size = ((panel->mode.xres * panel->mode.yres) * panel->bpp) / 8;
panel_size = ALIGN(panel_size, PAGE_SIZE);
- fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev,
- panel_size, &dma, GFP_KERNEL);
+ fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, panel_size, &dma,
+ GFP_KERNEL);
if (!fb->fb.screen_base) {
pr_err("CLCD: unable to map framebuffer\n");
@@ -107,13 +107,12 @@ int nspire_clcd_setup(struct clcd_fb *fb)
int nspire_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
{
- return dma_mmap_writecombine(&fb->dev->dev, vma,
- fb->fb.screen_base, fb->fb.fix.smem_start,
- fb->fb.fix.smem_len);
+ return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+ fb->fb.fix.smem_start, fb->fb.fix.smem_len);
}
void nspire_clcd_remove(struct clcd_fb *fb)
{
- dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
- fb->fb.screen_base, fb->fb.fix.smem_start);
+ dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+ fb->fb.fix.smem_start);
}
diff --git a/arch/avr32/include/asm/dma-mapping.h b/arch/avr32/include/asm/dma-mapping.h
index ae7ac9205d20..b43b11d1c7c0 100644
--- a/arch/avr32/include/asm/dma-mapping.h
+++ b/arch/avr32/include/asm/dma-mapping.h
@@ -71,7 +71,7 @@ extern void dma_free_coherent(struct device *dev, size_t size,
void *cpu_addr, dma_addr_t handle);
/**
- * dma_alloc_writecombine - allocate write-combining memory for DMA
+ * dma_alloc_wc - allocate write-combining memory for DMA
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
* @size: required memory size
* @handle: bus-specific DMA address
@@ -81,24 +81,24 @@ extern void dma_free_coherent(struct device *dev, size_t size,
* return the CPU-viewed address, and sets @handle to be the
* device-viewed address.
*/
-extern void *dma_alloc_writecombine(struct device *dev, size_t size,
- dma_addr_t *handle, gfp_t gfp);
+extern void *dma_alloc_wc(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp);
/**
- * dma_free_coherent - free memory allocated by dma_alloc_writecombine
+ * dma_free_coherent - free memory allocated by dma_alloc_wc
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @size: size of memory originally requested in dma_alloc_writecombine
- * @cpu_addr: CPU-view address returned from dma_alloc_writecombine
- * @handle: device-view address returned from dma_alloc_writecombine
+ * @size: size of memory originally requested in dma_alloc_wc
+ * @cpu_addr: CPU-view address returned from dma_alloc_wc
+ * @handle: device-view address returned from dma_alloc_wc
*
* Free (and unmap) a DMA buffer previously allocated by
- * dma_alloc_writecombine().
+ * dma_alloc_wc().
*
* References to memory and mappings associated with cpu_addr/handle
* during and after this call executing are illegal.
*/
-extern void dma_free_writecombine(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t handle);
+extern void dma_free_wc(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t handle);
/**
* dma_map_single - map a single buffer for streaming DMA
diff --git a/arch/avr32/mm/dma-coherent.c b/arch/avr32/mm/dma-coherent.c
index 50cdb5b10f0f..5d029d202a2a 100644
--- a/arch/avr32/mm/dma-coherent.c
+++ b/arch/avr32/mm/dma-coherent.c
@@ -121,8 +121,8 @@ void dma_free_coherent(struct device *dev, size_t size,
}
EXPORT_SYMBOL(dma_free_coherent);
-void *dma_alloc_writecombine(struct device *dev, size_t size,
- dma_addr_t *handle, gfp_t gfp)
+void *dma_alloc_wc(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp)
{
struct page *page;
dma_addr_t phys;
@@ -137,10 +137,10 @@ void *dma_alloc_writecombine(struct device *dev, size_t size,
/* Now, map the page into P3 with write-combining turned on */
return __ioremap(phys, size, _PAGE_BUFFER);
}
-EXPORT_SYMBOL(dma_alloc_writecombine);
+EXPORT_SYMBOL(dma_alloc_wc);
-void dma_free_writecombine(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t handle)
+void dma_free_wc(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t handle)
{
struct page *page;
@@ -149,4 +149,4 @@ void dma_free_writecombine(struct device *dev, size_t size,
page = phys_to_page(handle);
__dma_free(dev, size, page, handle);
}
-EXPORT_SYMBOL(dma_free_writecombine);
+EXPORT_SYMBOL(dma_free_wc);
diff --git a/arch/metag/include/asm/dma-mapping.h b/arch/metag/include/asm/dma-mapping.h
index eb5cdec94be0..d727deae083a 100644
--- a/arch/metag/include/asm/dma-mapping.h
+++ b/arch/metag/include/asm/dma-mapping.h
@@ -23,8 +23,8 @@ void dma_sync_for_cpu(void *vaddr, size_t size, int dma_direction);
int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size);
-int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size);
+int dma_mmap_wc(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size);
static inline dma_addr_t
dma_map_single(struct device *dev, void *ptr, size_t size,
diff --git a/arch/metag/kernel/dma.c b/arch/metag/kernel/dma.c
index c700d625067a..89138b4f717a 100644
--- a/arch/metag/kernel/dma.c
+++ b/arch/metag/kernel/dma.c
@@ -372,13 +372,13 @@ int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
}
EXPORT_SYMBOL(dma_mmap_coherent);
-int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size)
+int dma_mmap_wc(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size)
{
vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
}
-EXPORT_SYMBOL(dma_mmap_writecombine);
+EXPORT_SYMBOL(dma_mmap_wc);
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index e4f43125e0fb..f039cfadf17b 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -1300,10 +1300,10 @@ static int iop_adma_probe(struct platform_device *pdev)
* note: writecombine gives slightly better performance, but
* requires that we explicitly flush the writes
*/
- adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
- plat_data->pool_size,
- &adev->dma_desc_pool,
- GFP_KERNEL);
+ adev->dma_desc_pool_virt = dma_alloc_wc(&pdev->dev,
+ plat_data->pool_size,
+ &adev->dma_desc_pool,
+ GFP_KERNEL);
if (!adev->dma_desc_pool_virt) {
ret = -ENOMEM;
goto err_free_adev;
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index f1325f62563e..872a385a66fe 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1000,8 +1000,8 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
* requires that we explicitly flush the writes
*/
mv_chan->dma_desc_pool_virt =
- dma_alloc_writecombine(&pdev->dev, MV_XOR_POOL_SIZE,
- &mv_chan->dma_desc_pool, GFP_KERNEL);
+ dma_alloc_wc(&pdev->dev, MV_XOR_POOL_SIZE, &mv_chan->dma_desc_pool,
+ GFP_KERNEL);
if (!mv_chan->dma_desc_pool_virt)
return ERR_PTR(-ENOMEM);
diff --git a/drivers/dma/qcom_bam_dma.c b/drivers/dma/qcom_bam_dma.c
index 5a250cdc8376..d34aef7a101b 100644
--- a/drivers/dma/qcom_bam_dma.c
+++ b/drivers/dma/qcom_bam_dma.c
@@ -502,8 +502,8 @@ static int bam_alloc_chan(struct dma_chan *chan)
return 0;
/* allocate FIFO descriptor space, but only if necessary */
- bchan->fifo_virt = dma_alloc_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE,
- &bchan->fifo_phys, GFP_KERNEL);
+ bchan->fifo_virt = dma_alloc_wc(bdev->dev, BAM_DESC_FIFO_SIZE,
+ &bchan->fifo_phys, GFP_KERNEL);
if (!bchan->fifo_virt) {
dev_err(bdev->dev, "Failed to allocate desc fifo\n");
@@ -538,8 +538,8 @@ static void bam_free_chan(struct dma_chan *chan)
bam_reset_channel(bchan);
spin_unlock_irqrestore(&bchan->vc.lock, flags);
- dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE, bchan->fifo_virt,
- bchan->fifo_phys);
+ dma_free_wc(bdev->dev, BAM_DESC_FIFO_SIZE, bchan->fifo_virt,
+ bchan->fifo_phys);
bchan->fifo_virt = NULL;
/* mask irq for pipe/channel */
@@ -1231,9 +1231,9 @@ static int bam_dma_remove(struct platform_device *pdev)
bam_dma_terminate_all(&bdev->channels[i].vc.chan);
tasklet_kill(&bdev->channels[i].vc.task);
- dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE,
- bdev->channels[i].fifo_virt,
- bdev->channels[i].fifo_phys);
+ dma_free_wc(bdev->dev, BAM_DESC_FIFO_SIZE,
+ bdev->channels[i].fifo_virt,
+ bdev->channels[i].fifo_phys);
}
tasklet_kill(&bdev->task);
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index bd75f303da63..138142fcaf75 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -107,8 +107,8 @@ struct drm_gem_cma_object *drm_gem_cma_create(struct drm_device *drm,
if (IS_ERR(cma_obj))
return cma_obj;
- cma_obj->vaddr = dma_alloc_writecombine(drm->dev, size,
- &cma_obj->paddr, GFP_KERNEL | __GFP_NOWARN);
+ cma_obj->vaddr = dma_alloc_wc(drm->dev, size, &cma_obj->paddr,
+ GFP_KERNEL | __GFP_NOWARN);
if (!cma_obj->vaddr) {
dev_err(drm->dev, "failed to allocate buffer with size %zu\n",
size);
@@ -190,8 +190,8 @@ void drm_gem_cma_free_object(struct drm_gem_object *gem_obj)
cma_obj = to_drm_gem_cma_obj(gem_obj);
if (cma_obj->vaddr) {
- dma_free_writecombine(gem_obj->dev->dev, cma_obj->base.size,
- cma_obj->vaddr, cma_obj->paddr);
+ dma_free_wc(gem_obj->dev->dev, cma_obj->base.size,
+ cma_obj->vaddr, cma_obj->paddr);
} else if (gem_obj->import_attach) {
drm_prime_gem_destroy(gem_obj, cma_obj->sgt);
}
@@ -327,9 +327,8 @@ static int drm_gem_cma_mmap_obj(struct drm_gem_cma_object *cma_obj,
vma->vm_flags &= ~VM_PFNMAP;
vma->vm_pgoff = 0;
- ret = dma_mmap_writecombine(cma_obj->base.dev->dev, vma,
- cma_obj->vaddr, cma_obj->paddr,
- vma->vm_end - vma->vm_start);
+ ret = dma_mmap_wc(cma_obj->base.dev->dev, vma, cma_obj->vaddr,
+ cma_obj->paddr, vma->vm_end - vma->vm_start);
if (ret)
drm_gem_vm_close(vma);
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index 7841970de48d..43f0697ce752 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -570,10 +570,9 @@ static int omap_dmm_remove(struct platform_device *dev)
kfree(omap_dmm->engines);
if (omap_dmm->refill_va)
- dma_free_writecombine(omap_dmm->dev,
- REFILL_BUFFER_SIZE * omap_dmm->num_engines,
- omap_dmm->refill_va,
- omap_dmm->refill_pa);
+ dma_free_wc(omap_dmm->dev,
+ REFILL_BUFFER_SIZE * omap_dmm->num_engines,
+ omap_dmm->refill_va, omap_dmm->refill_pa);
if (omap_dmm->dummy_page)
__free_page(omap_dmm->dummy_page);
@@ -698,9 +697,9 @@ static int omap_dmm_probe(struct platform_device *dev)
omap_dmm->dummy_pa = page_to_phys(omap_dmm->dummy_page);
/* alloc refill memory */
- omap_dmm->refill_va = dma_alloc_writecombine(&dev->dev,
- REFILL_BUFFER_SIZE * omap_dmm->num_engines,
- &omap_dmm->refill_pa, GFP_KERNEL);
+ omap_dmm->refill_va = dma_alloc_wc(&dev->dev,
+ REFILL_BUFFER_SIZE * omap_dmm->num_engines,
+ &omap_dmm->refill_pa, GFP_KERNEL);
if (!omap_dmm->refill_va) {
dev_err(&dev->dev, "could not allocate refill memory\n");
goto fail;
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 7ed08fdc4c42..be3635b93527 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -1295,8 +1295,8 @@ void omap_gem_free_object(struct drm_gem_object *obj)
omap_gem_detach_pages(obj);
if (!is_shmem(obj)) {
- dma_free_writecombine(dev->dev, obj->size,
- omap_obj->vaddr, omap_obj->paddr);
+ dma_free_wc(dev->dev, obj->size, omap_obj->vaddr,
+ omap_obj->paddr);
} else if (omap_obj->vaddr) {
vunmap(omap_obj->vaddr);
}
@@ -1384,8 +1384,8 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev,
/* attempt to allocate contiguous memory if we don't
* have DMM for remappign discontiguous buffers
*/
- omap_obj->vaddr = dma_alloc_writecombine(dev->dev, size,
- &omap_obj->paddr, GFP_KERNEL);
+ omap_obj->vaddr = dma_alloc_wc(dev->dev, size,
+ &omap_obj->paddr, GFP_KERNEL);
if (!omap_obj->vaddr) {
kfree(omap_obj);
diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c
index 010eaee60bf7..75bdbf140fb0 100644
--- a/drivers/gpu/drm/sti/sti_cursor.c
+++ b/drivers/gpu/drm/sti/sti_cursor.c
@@ -124,17 +124,15 @@ static int sti_cursor_prepare_layer(struct sti_layer *layer, bool first_prepare)
cursor->height = layer->src_h;
if (cursor->pixmap.base)
- dma_free_writecombine(layer->dev,
- cursor->pixmap.size,
- cursor->pixmap.base,
- cursor->pixmap.paddr);
+ dma_free_wc(layer->dev, cursor->pixmap.size,
+ cursor->pixmap.base, cursor->pixmap.paddr);
cursor->pixmap.size = cursor->width * cursor->height;
- cursor->pixmap.base = dma_alloc_writecombine(layer->dev,
- cursor->pixmap.size,
- &cursor->pixmap.paddr,
- GFP_KERNEL | GFP_DMA);
+ cursor->pixmap.base = dma_alloc_wc(layer->dev,
+ cursor->pixmap.size,
+ &cursor->pixmap.paddr,
+ GFP_KERNEL | GFP_DMA);
if (!cursor->pixmap.base) {
DRM_ERROR("Failed to allocate memory for pixmap\n");
return -ENOMEM;
@@ -225,10 +223,8 @@ struct sti_layer *sti_cursor_create(struct device *dev)
}
/* Allocate clut buffer */
- cursor->clut = dma_alloc_writecombine(dev,
- 0x100 * sizeof(unsigned short),
- &cursor->clut_paddr,
- GFP_KERNEL | GFP_DMA);
+ cursor->clut = dma_alloc_wc(dev, 0x100 * sizeof(unsigned short),
+ &cursor->clut_paddr, GFP_KERNEL | GFP_DMA);
if (!cursor->clut) {
DRM_ERROR("Failed to allocate memory for cursor clut\n");
diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c
index 087906fd8846..9bf293ee3bc3 100644
--- a/drivers/gpu/drm/sti/sti_gdp.c
+++ b/drivers/gpu/drm/sti/sti_gdp.c
@@ -490,8 +490,7 @@ static void sti_gdp_init(struct sti_layer *layer)
/* Allocate all the nodes within a single memory page */
size = sizeof(struct sti_gdp_node) *
GDP_NODE_PER_FIELD * GDP_NODE_NB_BANK;
- base = dma_alloc_writecombine(layer->dev,
- size, &dma_addr, GFP_KERNEL | GFP_DMA);
+ base = dma_alloc_wc(layer->dev, size, &dma_addr, GFP_KERNEL | GFP_DMA);
if (!base) {
DRM_ERROR("Failed to allocate memory for GDP node\n");
diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c
index b0eb62de1b2e..025f48795b9c 100644
--- a/drivers/gpu/drm/sti/sti_hqvdp.c
+++ b/drivers/gpu/drm/sti/sti_hqvdp.c
@@ -788,9 +788,9 @@ static void sti_hqvd_init(struct sti_layer *layer)
/* Allocate memory for the VDP commands */
size = NB_VDP_CMD * sizeof(struct sti_hqvdp_cmd);
- hqvdp->hqvdp_cmd = dma_alloc_writecombine(hqvdp->dev, size,
- &hqvdp->hqvdp_cmd_paddr,
- GFP_KERNEL | GFP_DMA);
+ hqvdp->hqvdp_cmd = dma_alloc_wc(hqvdp->dev, size,
+ &hqvdp->hqvdp_cmd_paddr,
+ GFP_KERNEL | GFP_DMA);
if (!hqvdp->hqvdp_cmd) {
DRM_ERROR("Failed to allocate memory for VDP cmd\n");
return;
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 01e16e146bfe..82777d424f23 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -181,8 +181,7 @@ static void tegra_bo_free(struct drm_device *drm, struct tegra_bo *bo)
sg_free_table(bo->sgt);
kfree(bo->sgt);
} else if (bo->vaddr) {
- dma_free_writecombine(drm->dev, bo->gem.size, bo->vaddr,
- bo->paddr);
+ dma_free_wc(drm->dev, bo->gem.size, bo->vaddr, bo->paddr);
}
}
@@ -239,8 +238,8 @@ static int tegra_bo_alloc(struct drm_device *drm, struct tegra_bo *bo)
} else {
size_t size = bo->gem.size;
- bo->vaddr = dma_alloc_writecombine(drm->dev, size, &bo->paddr,
- GFP_KERNEL | __GFP_NOWARN);
+ bo->vaddr = dma_alloc_wc(drm->dev, size, &bo->paddr,
+ GFP_KERNEL | __GFP_NOWARN);
if (!bo->vaddr) {
dev_err(drm->dev,
"failed to allocate buffer of size %zu\n",
@@ -483,8 +482,8 @@ int tegra_drm_mmap(struct file *file, struct vm_area_struct *vma)
vma->vm_flags &= ~VM_PFNMAP;
vma->vm_pgoff = 0;
- ret = dma_mmap_writecombine(gem->dev->dev, vma, bo->vaddr,
- bo->paddr, gem->size);
+ ret = dma_mmap_wc(gem->dev->dev, vma, bo->vaddr, bo->paddr,
+ gem->size);
if (ret) {
drm_gem_vm_close(vma);
return ret;
diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
index 5a8c8d55317a..a18db4d5347c 100644
--- a/drivers/gpu/host1x/cdma.c
+++ b/drivers/gpu/host1x/cdma.c
@@ -52,8 +52,8 @@ static void host1x_pushbuffer_destroy(struct push_buffer *pb)
struct host1x *host1x = cdma_to_host1x(cdma);
if (pb->phys != 0)
- dma_free_writecombine(host1x->dev, pb->size_bytes + 4,
- pb->mapped, pb->phys);
+ dma_free_wc(host1x->dev, pb->size_bytes + 4, pb->mapped,
+ pb->phys);
pb->mapped = NULL;
pb->phys = 0;
@@ -76,8 +76,8 @@ static int host1x_pushbuffer_init(struct push_buffer *pb)
pb->pos = 0;
/* allocate and map pushbuffer memory */
- pb->mapped = dma_alloc_writecombine(host1x->dev, pb->size_bytes + 4,
- &pb->phys, GFP_KERNEL);
+ pb->mapped = dma_alloc_wc(host1x->dev, pb->size_bytes + 4, &pb->phys,
+ GFP_KERNEL);
if (!pb->mapped)
goto fail;
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index 63bd63f3c7df..defa7995f213 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -467,9 +467,8 @@ static inline int copy_gathers(struct host1x_job *job, struct device *dev)
size += g->words * sizeof(u32);
}
- job->gather_copy_mapped = dma_alloc_writecombine(dev, size,
- &job->gather_copy,
- GFP_KERNEL);
+ job->gather_copy_mapped = dma_alloc_wc(dev, size, &job->gather_copy,
+ GFP_KERNEL);
if (!job->gather_copy_mapped) {
job->gather_copy_mapped = NULL;
return -ENOMEM;
@@ -578,9 +577,8 @@ void host1x_job_unpin(struct host1x_job *job)
job->num_unpins = 0;
if (job->gather_copy_size)
- dma_free_writecombine(job->channel->dev, job->gather_copy_size,
- job->gather_copy_mapped,
- job->gather_copy);
+ dma_free_wc(job->channel->dev, job->gather_copy_size,
+ job->gather_copy_mapped, job->gather_copy);
}
EXPORT_SYMBOL(host1x_job_unpin);
diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 109797bb8fbb..d1e1658a4f35 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -1373,9 +1373,9 @@ static int coda_alloc_bitstream_buffer(struct coda_ctx *ctx,
return 0;
ctx->bitstream.size = roundup_pow_of_two(q_data->sizeimage * 2);
- ctx->bitstream.vaddr = dma_alloc_writecombine(
- &ctx->dev->plat_dev->dev, ctx->bitstream.size,
- &ctx->bitstream.paddr, GFP_KERNEL);
+ ctx->bitstream.vaddr = dma_alloc_wc(&ctx->dev->plat_dev->dev,
+ ctx->bitstream.size,
+ &ctx->bitstream.paddr, GFP_KERNEL);
if (!ctx->bitstream.vaddr) {
v4l2_err(&ctx->dev->v4l2_dev,
"failed to allocate bitstream ringbuffer");
@@ -1392,8 +1392,8 @@ static void coda_free_bitstream_buffer(struct coda_ctx *ctx)
if (ctx->bitstream.vaddr == NULL)
return;
- dma_free_writecombine(&ctx->dev->plat_dev->dev, ctx->bitstream.size,
- ctx->bitstream.vaddr, ctx->bitstream.paddr);
+ dma_free_wc(&ctx->dev->plat_dev->dev, ctx->bitstream.size,
+ ctx->bitstream.vaddr, ctx->bitstream.paddr);
ctx->bitstream.vaddr = NULL;
kfifo_init(&ctx->bitstream_fifo, NULL, 0);
}
diff --git a/drivers/video/fbdev/acornfb.c b/drivers/video/fbdev/acornfb.c
index a305caea58ee..fb75b7e5a19a 100644
--- a/drivers/video/fbdev/acornfb.c
+++ b/drivers/video/fbdev/acornfb.c
@@ -1040,8 +1040,8 @@ static int acornfb_probe(struct platform_device *dev)
* for the framebuffer if we are not using
* VRAM.
*/
- base = dma_alloc_writecombine(current_par.dev, size, &handle,
- GFP_KERNEL);
+ base = dma_alloc_wc(current_par.dev, size, &handle,
+ GFP_KERNEL);
if (base == NULL) {
printk(KERN_ERR "acornfb: unable to allocate screen "
"memory\n");
diff --git a/drivers/video/fbdev/amba-clcd-versatile.c b/drivers/video/fbdev/amba-clcd-versatile.c
index 7a8afcd4573e..a8a22daa3f9d 100644
--- a/drivers/video/fbdev/amba-clcd-versatile.c
+++ b/drivers/video/fbdev/amba-clcd-versatile.c
@@ -154,8 +154,8 @@ int versatile_clcd_setup_dma(struct clcd_fb *fb, unsigned long framesize)
{
dma_addr_t dma;
- fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, framesize,
- &dma, GFP_KERNEL);
+ fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, framesize, &dma,
+ GFP_KERNEL);
if (!fb->fb.screen_base) {
pr_err("CLCD: unable to map framebuffer\n");
return -ENOMEM;
@@ -169,14 +169,12 @@ int versatile_clcd_setup_dma(struct clcd_fb *fb, unsigned long framesize)
int versatile_clcd_mmap_dma(struct clcd_fb *fb, struct vm_area_struct *vma)
{
- return dma_mmap_writecombine(&fb->dev->dev, vma,
- fb->fb.screen_base,
- fb->fb.fix.smem_start,
- fb->fb.fix.smem_len);
+ return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+ fb->fb.fix.smem_start, fb->fb.fix.smem_len);
}
void versatile_clcd_remove_dma(struct clcd_fb *fb)
{
- dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
- fb->fb.screen_base, fb->fb.fix.smem_start);
+ dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+ fb->fb.fix.smem_start);
}
diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c
index 9362424c2340..fe274b5851c7 100644
--- a/drivers/video/fbdev/amba-clcd.c
+++ b/drivers/video/fbdev/amba-clcd.c
@@ -774,8 +774,8 @@ static int clcdfb_of_dma_setup(struct clcd_fb *fb)
static int clcdfb_of_dma_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
{
- return dma_mmap_writecombine(&fb->dev->dev, vma, fb->fb.screen_base,
- fb->fb.fix.smem_start, fb->fb.fix.smem_len);
+ return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+ fb->fb.fix.smem_start, fb->fb.fix.smem_len);
}
static void clcdfb_of_dma_remove(struct clcd_fb *fb)
diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c
index abadc490fa1f..689fb9d99988 100644
--- a/drivers/video/fbdev/atmel_lcdfb.c
+++ b/drivers/video/fbdev/atmel_lcdfb.c
@@ -415,8 +415,8 @@ static inline void atmel_lcdfb_free_video_memory(struct atmel_lcdfb_info *sinfo)
{
struct fb_info *info = sinfo->info;
- dma_free_writecombine(info->device, info->fix.smem_len,
- info->screen_base, info->fix.smem_start);
+ dma_free_wc(info->device, info->fix.smem_len, info->screen_base,
+ info->fix.smem_start);
}
/**
@@ -436,8 +436,9 @@ static int atmel_lcdfb_alloc_video_memory(struct atmel_lcdfb_info *sinfo)
* ((var->bits_per_pixel + 7) / 8));
info->fix.smem_len = max(smem_len, sinfo->smem_len);
- info->screen_base = dma_alloc_writecombine(info->device, info->fix.smem_len,
- (dma_addr_t *)&info->fix.smem_start, GFP_KERNEL);
+ info->screen_base = dma_alloc_wc(info->device, info->fix.smem_len,
+ (dma_addr_t *)&info->fix.smem_start,
+ GFP_KERNEL);
if (!info->screen_base) {
return -ENOMEM;
diff --git a/drivers/video/fbdev/ep93xx-fb.c b/drivers/video/fbdev/ep93xx-fb.c
index 7ec251cc9c03..e876b83e4600 100644
--- a/drivers/video/fbdev/ep93xx-fb.c
+++ b/drivers/video/fbdev/ep93xx-fb.c
@@ -316,9 +316,8 @@ static int ep93xxfb_mmap(struct fb_info *info, struct vm_area_struct *vma)
unsigned int offset = vma->vm_pgoff << PAGE_SHIFT;
if (offset < info->fix.smem_len) {
- return dma_mmap_writecombine(info->dev, vma, info->screen_base,
- info->fix.smem_start,
- info->fix.smem_len);
+ return dma_mmap_wc(info->dev, vma, info->screen_base,
+ info->fix.smem_start, info->fix.smem_len);
}
return -EINVAL;
@@ -449,8 +448,7 @@ static int ep93xxfb_alloc_videomem(struct fb_info *info)
unsigned int fb_size;
fb_size = ep93xxfb_calc_fbsize(fbi->mach_info);
- virt_addr = dma_alloc_writecombine(info->dev, fb_size,
- &phys_addr, GFP_KERNEL);
+ virt_addr = dma_alloc_wc(info->dev, fb_size, &phys_addr, GFP_KERNEL);
if (!virt_addr)
return -ENOMEM;
diff --git a/drivers/video/fbdev/gbefb.c b/drivers/video/fbdev/gbefb.c
index b63d55f481fa..1a242b1338e9 100644
--- a/drivers/video/fbdev/gbefb.c
+++ b/drivers/video/fbdev/gbefb.c
@@ -1185,8 +1185,8 @@ static int gbefb_probe(struct platform_device *p_dev)
} else {
/* try to allocate memory with the classical allocator
* this has high chance to fail on low memory machines */
- gbe_mem = dma_alloc_writecombine(NULL, gbe_mem_size,
- &gbe_dma_addr, GFP_KERNEL);
+ gbe_mem = dma_alloc_wc(NULL, gbe_mem_size, &gbe_dma_addr,
+ GFP_KERNEL);
if (!gbe_mem) {
printk(KERN_ERR "gbefb: couldn't allocate framebuffer memory\n");
ret = -ENOMEM;
@@ -1238,7 +1238,7 @@ static int gbefb_probe(struct platform_device *p_dev)
out_gbe_unmap:
arch_phys_wc_del(par->wc_cookie);
if (gbe_dma_addr)
- dma_free_writecombine(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
+ dma_free_wc(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
out_tiles_free:
dma_free_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t),
(void *)gbe_tiles.cpu, gbe_tiles.dma);
@@ -1259,7 +1259,7 @@ static int gbefb_remove(struct platform_device* p_dev)
gbe_turn_off();
arch_phys_wc_del(par->wc_cookie);
if (gbe_dma_addr)
- dma_free_writecombine(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
+ dma_free_wc(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
dma_free_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t),
(void *)gbe_tiles.cpu, gbe_tiles.dma);
release_mem_region(GBE_BASE, sizeof(struct sgi_gbe));
diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c
index cee88603efc9..465b3387c549 100644
--- a/drivers/video/fbdev/imxfb.c
+++ b/drivers/video/fbdev/imxfb.c
@@ -922,8 +922,8 @@ static int imxfb_probe(struct platform_device *pdev)
}
fbi->map_size = PAGE_ALIGN(info->fix.smem_len);
- info->screen_base = dma_alloc_writecombine(&pdev->dev, fbi->map_size,
- &fbi->map_dma, GFP_KERNEL);
+ info->screen_base = dma_alloc_wc(&pdev->dev, fbi->map_size,
+ &fbi->map_dma, GFP_KERNEL);
if (!info->screen_base) {
dev_err(&pdev->dev, "Failed to allocate video RAM: %d\n", ret);
@@ -990,8 +990,8 @@ failed_cmap:
if (pdata && pdata->exit)
pdata->exit(fbi->pdev);
failed_platform_init:
- dma_free_writecombine(&pdev->dev, fbi->map_size, info->screen_base,
- fbi->map_dma);
+ dma_free_wc(&pdev->dev, fbi->map_size, info->screen_base,
+ fbi->map_dma);
failed_map:
iounmap(fbi->regs);
failed_ioremap:
@@ -1026,8 +1026,8 @@ static int imxfb_remove(struct platform_device *pdev)
kfree(info->pseudo_palette);
framebuffer_release(info);
- dma_free_writecombine(&pdev->dev, fbi->map_size, info->screen_base,
- fbi->map_dma);
+ dma_free_wc(&pdev->dev, fbi->map_size, info->screen_base,
+ fbi->map_dma);
iounmap(fbi->regs);
release_mem_region(res->start, resource_size(res));
diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c
index 7947634ee6b0..f91b1db262b0 100644
--- a/drivers/video/fbdev/mx3fb.c
+++ b/drivers/video/fbdev/mx3fb.c
@@ -1336,9 +1336,8 @@ static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len,
int retval = 0;
dma_addr_t addr;
- fbi->screen_base = dma_alloc_writecombine(fbi->device,
- mem_len,
- &addr, GFP_DMA | GFP_KERNEL);
+ fbi->screen_base = dma_alloc_wc(fbi->device, mem_len, &addr,
+ GFP_DMA | GFP_KERNEL);
if (!fbi->screen_base) {
dev_err(fbi->device, "Cannot allocate %u bytes framebuffer memory\n",
@@ -1378,8 +1377,8 @@ err0:
*/
static int mx3fb_unmap_video_memory(struct fb_info *fbi)
{
- dma_free_writecombine(fbi->device, fbi->fix.smem_len,
- fbi->screen_base, fbi->fix.smem_start);
+ dma_free_wc(fbi->device, fbi->fix.smem_len, fbi->screen_base,
+ fbi->fix.smem_start);
fbi->screen_base = NULL;
mutex_lock(&fbi->mm_lock);
diff --git a/drivers/video/fbdev/nuc900fb.c b/drivers/video/fbdev/nuc900fb.c
index 389fa2cbb713..6680edae4696 100644
--- a/drivers/video/fbdev/nuc900fb.c
+++ b/drivers/video/fbdev/nuc900fb.c
@@ -396,8 +396,8 @@ static int nuc900fb_map_video_memory(struct fb_info *info)
dev_dbg(fbi->dev, "nuc900fb_map_video_memory(fbi=%p) map_size %lu\n",
fbi, map_size);
- info->screen_base = dma_alloc_writecombine(fbi->dev, map_size,
- &map_dma, GFP_KERNEL);
+ info->screen_base = dma_alloc_wc(fbi->dev, map_size, &map_dma,
+ GFP_KERNEL);
if (!info->screen_base)
return -ENOMEM;
@@ -411,8 +411,8 @@ static int nuc900fb_map_video_memory(struct fb_info *info)
static inline void nuc900fb_unmap_video_memory(struct fb_info *info)
{
struct nuc900fb_info *fbi = info->par;
- dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
- info->screen_base, info->fix.smem_start);
+ dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+ info->screen_base, info->fix.smem_start);
}
static irqreturn_t nuc900fb_irqhandler(int irq, void *dev_id)
diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c
index 6efa2591eaa8..e3d9b9ea5498 100644
--- a/drivers/video/fbdev/omap/lcdc.c
+++ b/drivers/video/fbdev/omap/lcdc.c
@@ -612,8 +612,8 @@ static void lcdc_dma_handler(u16 status, void *data)
static int alloc_palette_ram(void)
{
- lcdc.palette_virt = dma_alloc_writecombine(lcdc.fbdev->dev,
- MAX_PALETTE_SIZE, &lcdc.palette_phys, GFP_KERNEL);
+ lcdc.palette_virt = dma_alloc_wc(lcdc.fbdev->dev, MAX_PALETTE_SIZE,
+ &lcdc.palette_phys, GFP_KERNEL);
if (lcdc.palette_virt == NULL) {
dev_err(lcdc.fbdev->dev, "failed to alloc palette memory\n");
return -ENOMEM;
@@ -625,8 +625,8 @@ static int alloc_palette_ram(void)
static void free_palette_ram(void)
{
- dma_free_writecombine(lcdc.fbdev->dev, MAX_PALETTE_SIZE,
- lcdc.palette_virt, lcdc.palette_phys);
+ dma_free_wc(lcdc.fbdev->dev, MAX_PALETTE_SIZE, lcdc.palette_virt,
+ lcdc.palette_phys);
}
static int alloc_fbmem(struct omapfb_mem_region *region)
@@ -642,8 +642,8 @@ static int alloc_fbmem(struct omapfb_mem_region *region)
if (region->size > frame_size)
frame_size = region->size;
lcdc.vram_size = frame_size;
- lcdc.vram_virt = dma_alloc_writecombine(lcdc.fbdev->dev,
- lcdc.vram_size, &lcdc.vram_phys, GFP_KERNEL);
+ lcdc.vram_virt = dma_alloc_wc(lcdc.fbdev->dev, lcdc.vram_size,
+ &lcdc.vram_phys, GFP_KERNEL);
if (lcdc.vram_virt == NULL) {
dev_err(lcdc.fbdev->dev, "unable to allocate FB DMA memory\n");
return -ENOMEM;
@@ -660,8 +660,8 @@ static int alloc_fbmem(struct omapfb_mem_region *region)
static void free_fbmem(void)
{
- dma_free_writecombine(lcdc.fbdev->dev, lcdc.vram_size,
- lcdc.vram_virt, lcdc.vram_phys);
+ dma_free_wc(lcdc.fbdev->dev, lcdc.vram_size, lcdc.vram_virt,
+ lcdc.vram_phys);
}
static int setup_fbmem(struct omapfb_mem_desc *req_md)
diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c
index e209b039f553..04bd7237da6f 100644
--- a/drivers/video/fbdev/pxa168fb.c
+++ b/drivers/video/fbdev/pxa168fb.c
@@ -683,8 +683,8 @@ static int pxa168fb_probe(struct platform_device *pdev)
*/
info->fix.smem_len = PAGE_ALIGN(DEFAULT_FB_SIZE);
- info->screen_base = dma_alloc_writecombine(fbi->dev, info->fix.smem_len,
- &fbi->fb_start_dma, GFP_KERNEL);
+ info->screen_base = dma_alloc_wc(fbi->dev, info->fix.smem_len,
+ &fbi->fb_start_dma, GFP_KERNEL);
if (info->screen_base == NULL) {
ret = -ENOMEM;
goto failed_free_info;
@@ -809,8 +809,8 @@ static int pxa168fb_remove(struct platform_device *pdev)
irq = platform_get_irq(pdev, 0);
- dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
- info->screen_base, info->fix.smem_start);
+ dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+ info->screen_base, info->fix.smem_start);
clk_disable(fbi->clk);
clk_put(fbi->clk);
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index 7245611ec963..6a5b9801396a 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -2286,8 +2286,8 @@ static int pxafb_remove(struct platform_device *dev)
free_pages_exact(fbi->video_mem, fbi->video_mem_size);
- dma_free_writecombine(&dev->dev, fbi->dma_buff_size,
- fbi->dma_buff, fbi->dma_buff_phys);
+ dma_free_wc(&dev->dev, fbi->dma_buff_size, fbi->dma_buff,
+ fbi->dma_buff_phys);
iounmap(fbi->mmio_base);
diff --git a/drivers/video/fbdev/s3c-fb.c b/drivers/video/fbdev/s3c-fb.c
index 7e3a05fc47aa..b7e3571c396f 100644
--- a/drivers/video/fbdev/s3c-fb.c
+++ b/drivers/video/fbdev/s3c-fb.c
@@ -1105,8 +1105,7 @@ static int s3c_fb_alloc_memory(struct s3c_fb *sfb, struct s3c_fb_win *win)
dev_dbg(sfb->dev, "want %u bytes for window\n", size);
- fbi->screen_base = dma_alloc_writecombine(sfb->dev, size,
- &map_dma, GFP_KERNEL);
+ fbi->screen_base = dma_alloc_wc(sfb->dev, size, &map_dma, GFP_KERNEL);
if (!fbi->screen_base)
return -ENOMEM;
@@ -1131,8 +1130,8 @@ static void s3c_fb_free_memory(struct s3c_fb *sfb, struct s3c_fb_win *win)
struct fb_info *fbi = win->fbinfo;
if (fbi->screen_base)
- dma_free_writecombine(sfb->dev, PAGE_ALIGN(fbi->fix.smem_len),
- fbi->screen_base, fbi->fix.smem_start);
+ dma_free_wc(sfb->dev, PAGE_ALIGN(fbi->fix.smem_len),
+ fbi->screen_base, fbi->fix.smem_start);
}
/**
diff --git a/drivers/video/fbdev/s3c2410fb.c b/drivers/video/fbdev/s3c2410fb.c
index d6704add1601..0dd86be36afb 100644
--- a/drivers/video/fbdev/s3c2410fb.c
+++ b/drivers/video/fbdev/s3c2410fb.c
@@ -645,8 +645,8 @@ static int s3c2410fb_map_video_memory(struct fb_info *info)
dprintk("map_video_memory(fbi=%p) map_size %u\n", fbi, map_size);
- info->screen_base = dma_alloc_writecombine(fbi->dev, map_size,
- &map_dma, GFP_KERNEL);
+ info->screen_base = dma_alloc_wc(fbi->dev, map_size, &map_dma,
+ GFP_KERNEL);
if (info->screen_base) {
/* prevent initial garbage on screen */
@@ -667,8 +667,8 @@ static inline void s3c2410fb_unmap_video_memory(struct fb_info *info)
{
struct s3c2410fb_info *fbi = info->par;
- dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
- info->screen_base, info->fix.smem_start);
+ dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+ info->screen_base, info->fix.smem_start);
}
static inline void modify_gpio(void __iomem *reg,
diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c
index 89dd7e02197f..66467eb190b2 100644
--- a/drivers/video/fbdev/sa1100fb.c
+++ b/drivers/video/fbdev/sa1100fb.c
@@ -567,8 +567,8 @@ static int sa1100fb_mmap(struct fb_info *info,
if (off < info->fix.smem_len) {
vma->vm_pgoff += 1; /* skip over the palette */
- return dma_mmap_writecombine(fbi->dev, vma, fbi->map_cpu,
- fbi->map_dma, fbi->map_size);
+ return dma_mmap_wc(fbi->dev, vma, fbi->map_cpu, fbi->map_dma,
+ fbi->map_size);
}
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
@@ -1100,8 +1100,8 @@ static int sa1100fb_map_video_memory(struct sa1100fb_info *fbi)
* of the framebuffer.
*/
fbi->map_size = PAGE_ALIGN(fbi->fb.fix.smem_len + PAGE_SIZE);
- fbi->map_cpu = dma_alloc_writecombine(fbi->dev, fbi->map_size,
- &fbi->map_dma, GFP_KERNEL);
+ fbi->map_cpu = dma_alloc_wc(fbi->dev, fbi->map_size, &fbi->map_dma,
+ GFP_KERNEL);
if (fbi->map_cpu) {
fbi->fb.screen_base = fbi->map_cpu + PAGE_SIZE;
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index ac07ff090919..1f54e9bd6b34 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -271,26 +271,26 @@ struct dma_attrs;
dma_unmap_sg(dev, sgl, nents, dir)
#else
-static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
- dma_addr_t *dma_addr, gfp_t gfp)
+static inline void *dma_alloc_wc(struct device *dev, size_t size,
+ dma_addr_t *dma_addr, gfp_t gfp)
{
DEFINE_DMA_ATTRS(attrs);
dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
return dma_alloc_attrs(dev, size, dma_addr, gfp, &attrs);
}
-static inline void dma_free_writecombine(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t dma_addr)
+static inline void dma_free_wc(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t dma_addr)
{
DEFINE_DMA_ATTRS(attrs);
dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
return dma_free_attrs(dev, size, cpu_addr, dma_addr, &attrs);
}
-static inline int dma_mmap_writecombine(struct device *dev,
- struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr,
- size_t size)
+static inline int dma_mmap_wc(struct device *dev,
+ struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr,
+ size_t size)
{
DEFINE_DMA_ATTRS(attrs);
dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index 01f8fdc42b1b..5596f7cc8e73 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -238,8 +238,8 @@ int __pxa2xx_pcm_open(struct snd_pcm_substream *substream)
if (!rtd)
goto out;
rtd->dma_desc_array =
- dma_alloc_writecombine(substream->pcm->card->dev, PAGE_SIZE,
- &rtd->dma_desc_array_phys, GFP_KERNEL);
+ dma_alloc_wc(substream->pcm->card->dev, PAGE_SIZE,
+ &rtd->dma_desc_array_phys, GFP_KERNEL);
if (!rtd->dma_desc_array)
goto err1;
@@ -259,8 +259,8 @@ int __pxa2xx_pcm_close(struct snd_pcm_substream *substream)
struct snd_pcm_runtime *runtime = substream->runtime;
struct pxa2xx_runtime_data *rtd = runtime->private_data;
- dma_free_writecombine(substream->pcm->card->dev, PAGE_SIZE,
- rtd->dma_desc_array, rtd->dma_desc_array_phys);
+ dma_free_wc(substream->pcm->card->dev, PAGE_SIZE,
+ rtd->dma_desc_array, rtd->dma_desc_array_phys);
kfree(rtd);
return 0;
}
@@ -270,10 +270,8 @@ int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream,
struct vm_area_struct *vma)
{
struct snd_pcm_runtime *runtime = substream->runtime;
- return dma_mmap_writecombine(substream->pcm->card->dev, vma,
- runtime->dma_area,
- runtime->dma_addr,
- runtime->dma_bytes);
+ return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+ runtime->dma_addr, runtime->dma_bytes);
}
EXPORT_SYMBOL(pxa2xx_pcm_mmap);
@@ -285,8 +283,7 @@ int pxa2xx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
buf->dev.type = SNDRV_DMA_TYPE_DEV;
buf->dev.dev = pcm->card->dev;
buf->private_data = NULL;
- buf->area = dma_alloc_writecombine(pcm->card->dev, size,
- &buf->addr, GFP_KERNEL);
+ buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
if (!buf->area)
return -ENOMEM;
buf->bytes = size;
@@ -307,8 +304,7 @@ void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm)
buf = &substream->dma_buffer;
if (!buf->area)
continue;
- dma_free_writecombine(pcm->card->dev, buf->bytes,
- buf->area, buf->addr);
+ dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
buf->area = NULL;
}
}
diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c
index 7abf6a079574..ccdc4380d86a 100644
--- a/sound/soc/fsl/imx-pcm-fiq.c
+++ b/sound/soc/fsl/imx-pcm-fiq.c
@@ -217,8 +217,8 @@ static int snd_imx_pcm_mmap(struct snd_pcm_substream *substream,
struct snd_pcm_runtime *runtime = substream->runtime;
int ret;
- ret = dma_mmap_writecombine(substream->pcm->card->dev, vma,
- runtime->dma_area, runtime->dma_addr, runtime->dma_bytes);
+ ret = dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+ runtime->dma_addr, runtime->dma_bytes);
pr_debug("%s: ret: %d %p 0x%08x 0x%08x\n", __func__, ret,
runtime->dma_area,
@@ -247,8 +247,7 @@ static int imx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
buf->dev.type = SNDRV_DMA_TYPE_DEV;
buf->dev.dev = pcm->card->dev;
buf->private_data = NULL;
- buf->area = dma_alloc_writecombine(pcm->card->dev, size,
- &buf->addr, GFP_KERNEL);
+ buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
if (!buf->area)
return -ENOMEM;
buf->bytes = size;
@@ -330,8 +329,7 @@ static void imx_pcm_free(struct snd_pcm *pcm)
if (!buf->area)
continue;
- dma_free_writecombine(pcm->card->dev, buf->bytes,
- buf->area, buf->addr);
+ dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
buf->area = NULL;
}
}
diff --git a/sound/soc/nuc900/nuc900-pcm.c b/sound/soc/nuc900/nuc900-pcm.c
index 5ae5ca15b6d6..cd8175afa900 100644
--- a/sound/soc/nuc900/nuc900-pcm.c
+++ b/sound/soc/nuc900/nuc900-pcm.c
@@ -267,10 +267,8 @@ static int nuc900_dma_mmap(struct snd_pcm_substream *substream,
{
struct snd_pcm_runtime *runtime = substream->runtime;
- return dma_mmap_writecombine(substream->pcm->card->dev, vma,
- runtime->dma_area,
- runtime->dma_addr,
- runtime->dma_bytes);
+ return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+ runtime->dma_addr, runtime->dma_bytes);
}
static struct snd_pcm_ops nuc900_dma_ops = {
diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c
index 6bb623a2a4df..99381a27295b 100644
--- a/sound/soc/omap/omap-pcm.c
+++ b/sound/soc/omap/omap-pcm.c
@@ -156,10 +156,8 @@ static int omap_pcm_mmap(struct snd_pcm_substream *substream,
{
struct snd_pcm_runtime *runtime = substream->runtime;
- return dma_mmap_writecombine(substream->pcm->card->dev, vma,
- runtime->dma_area,
- runtime->dma_addr,
- runtime->dma_bytes);
+ return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+ runtime->dma_addr, runtime->dma_bytes);
}
static struct snd_pcm_ops omap_pcm_ops = {
@@ -183,8 +181,7 @@ static int omap_pcm_preallocate_dma_buffer(struct snd_pcm *pcm,
buf->dev.type = SNDRV_DMA_TYPE_DEV;
buf->dev.dev = pcm->card->dev;
buf->private_data = NULL;
- buf->area = dma_alloc_writecombine(pcm->card->dev, size,
- &buf->addr, GFP_KERNEL);
+ buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
if (!buf->area)
return -ENOMEM;
@@ -207,8 +204,7 @@ static void omap_pcm_free_dma_buffers(struct snd_pcm *pcm)
if (!buf->area)
continue;
- dma_free_writecombine(pcm->card->dev, buf->bytes,
- buf->area, buf->addr);
+ dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
buf->area = NULL;
}
}
--
2.4.3
On Tue, 25 Aug 2015 17:48:37 +0200 "Luis R. Rodriguez" <[email protected]> wrote:
> On Tue, Aug 25, 2015 at 09:53:18AM +0200, Ingo Molnar wrote:
> > Which kernel is this against? It has conflicts in 3 files with Linus's latest:
> > v4.2-rc8.
>
> Sorry I based it on linux-next, will respin the rename patch onto tip/auto-latest
>
Doing that will make the patch kinda useless, because then the patch
will trash more mature work which is pending in linux-next, one week
before the merge window opens.
A better plan would be to base the patches on linux-next then wait for
4.3-rc1.
On Tue, Aug 25, 2015 at 01:43:58PM -0700, Andrew Morton wrote:
> On Tue, 25 Aug 2015 17:48:37 +0200 "Luis R. Rodriguez" <[email protected]> wrote:
>
> > On Tue, Aug 25, 2015 at 09:53:18AM +0200, Ingo Molnar wrote:
> > > Which kernel is this against? It has conflicts in 3 files with Linus's latest:
> > > v4.2-rc8.
> >
> > Sorry I based it on linux-next, will respin the rename patch onto tip/auto-latest
> >
>
> Doing that will make the patch kinda useless, because then the patch
> will trash more mature work which is pending in linux-next, one week
> before the merge window opens.
>
> A better plan would be to base the patches on linux-next then wait for
> 4.3-rc1.
There's a catch-22 issue here either way, for instance this rename
patch has been being baked for probably 2 releases already but the
difficulty has been trying to find the appropriate time to merge it
without conflict.
If you do it in the beginning of the merge window, you have to ask
yourself in what tree it will be done. Since subsystems are topic
specific that means that subsystem will end up having a conflict
at the end of the merge window.
If you do it at the end you run into the issue you describe.
So unless I'm missing something, perhaps metrics to argue one way is better
than another, it seems today this is up up to a subsystem's maintainer's
preference?
There are more subtle issues with this though, I've identified similar problems
before and proposed one solution to it could be a linux-oven [0], in that
thread I describe other issues and why I think a linux-oven might help.
Perhaps the biggest change that comes to mind that could have caused
tons of collateral was the UAPI change David Howells did years ago,
when did that go in, at the end of early? In retrospect what would have
helped?
Anyway, both version of the patch are now available, up to you guys :)
[0] http://lkml.kernel.org/r/[email protected]
Luis
On Wed, 26 Aug 2015 01:19:13 +0200 "Luis R. Rodriguez" <[email protected]> wrote:
> On Tue, Aug 25, 2015 at 01:43:58PM -0700, Andrew Morton wrote:
> > On Tue, 25 Aug 2015 17:48:37 +0200 "Luis R. Rodriguez" <[email protected]> wrote:
> >
> > > On Tue, Aug 25, 2015 at 09:53:18AM +0200, Ingo Molnar wrote:
> > > > Which kernel is this against? It has conflicts in 3 files with Linus's latest:
> > > > v4.2-rc8.
> > >
> > > Sorry I based it on linux-next, will respin the rename patch onto tip/auto-latest
> > >
> >
> > Doing that will make the patch kinda useless, because then the patch
> > will trash more mature work which is pending in linux-next, one week
> > before the merge window opens.
> >
> > A better plan would be to base the patches on linux-next then wait for
> > 4.3-rc1.
>
> There's a catch-22 issue here either way, for instance this rename
> patch has been being baked for probably 2 releases already but the
> difficulty has been trying to find the appropriate time to merge it
> without conflict.
>
> If you do it in the beginning of the merge window, you have to ask
> yourself in what tree it will be done. Since subsystems are topic
> specific that means that subsystem will end up having a conflict
> at the end of the merge window.
Yes it's a special case. I think the best way of handling such things
is to get them in to Linus either right at the end of the merge window
or the day after he releases -rc1. This is when most people's trees
are mostly empty.
* Andrew Morton <[email protected]> wrote:
> > There's a catch-22 issue here either way, for instance this rename patch has
> > been being baked for probably 2 releases already but the difficulty has been
> > trying to find the appropriate time to merge it without conflict.
> >
> > If you do it in the beginning of the merge window, you have to ask yourself in
> > what tree it will be done. Since subsystems are topic specific that means that
> > subsystem will end up having a conflict at the end of the merge window.
>
> Yes it's a special case. I think the best way of handling such things is to get
> them in to Linus either right at the end of the merge window or the day after he
> releases -rc1. This is when most people's trees are mostly empty.
Yes, that was the plan last time around as well - but the end of the merge window
is when we have the least maintainer bandwidth as well ...
Anyway, I applied most of the patches (sans the rename), so the rename patch
should be a lot simpler to execute at the right moment this time around.
Thanks,
Ingo
Commit-ID: 2baa891e42d84159b693eadd44f6fe1486285bdc
Gitweb: http://git.kernel.org/tip/2baa891e42d84159b693eadd44f6fe1486285bdc
Author: Luis R. Rodriguez <[email protected]>
AuthorDate: Mon, 24 Aug 2015 12:13:33 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Fri, 28 Aug 2015 10:09:28 +0200
x86/mm/mtrr: Remove kernel internal MTRR interfaces: unexport mtrr_add() and mtrr_del()
The effort to replace mtrr_add() with architecture agnostic
arch_phys_wc_add() is complete, this will ensure write-combining
implementations (PAT on x86) is taken advantage instead of using
MTRR. With the effort done now, hide direct MTRR access for
drivers.
The legacy user-space /proc/mtrr ABI is not affected.
Update x86 documentation on MTRR to reflect the completion of
the phasing out of direct access to MTRR, also add a note on
platform firmware code use of MTRRs based on the obituary
discussion of MTRRs on Linux [0].
[0] http://lkml.kernel.org/r/[email protected]
Signed-off-by: Luis R. Rodriguez <[email protected]>
Cc: <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Andy Walls <[email protected]>
Cc: Antonino Daplas <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: Doug Ledford <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Jean-Christophe Plagniol-Villard <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tomi Valkeinen <[email protected]>
Cc: Toshi Kani <[email protected]>
Cc: Ville Syrjälä <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
Documentation/x86/mtrr.txt | 20 ++++++++++++++++----
arch/x86/kernel/cpu/mtrr/main.c | 2 --
2 files changed, 16 insertions(+), 6 deletions(-)
diff --git a/Documentation/x86/mtrr.txt b/Documentation/x86/mtrr.txt
index 860bc3a..dc3e703 100644
--- a/Documentation/x86/mtrr.txt
+++ b/Documentation/x86/mtrr.txt
@@ -6,10 +6,22 @@ Luis R. Rodriguez <[email protected]> - April 9, 2015
===============================================================================
Phasing out MTRR use
-MTRR use is replaced on modern x86 hardware with PAT. Over time the only type
-of effective MTRR that is expected to be supported will be for write-combining.
-As MTRR use is phased out device drivers should use arch_phys_wc_add() to make
-MTRR effective on non-PAT systems while a no-op on PAT enabled systems.
+MTRR use is replaced on modern x86 hardware with PAT. Direct MTRR use by
+drivers on Linux is now completely phased out, device drivers should use
+arch_phys_wc_add() in combination with ioremap_wc() to make MTRR effective on
+non-PAT systems while a no-op but equally effective on PAT enabled systems.
+
+Even if Linux does not use MTRRs directly, some x86 platform firmware may still
+set up MTRRs early before booting the OS. They do this as some platform
+firmware may still have implemented access to MTRRs which would be controlled
+and handled by the platform firmware directly. An example of platform use of
+MTRRs is through the use of SMI handlers, one case could be for fan control,
+the platform code would need uncachable access to some of its fan control
+registers. Such platform access does not need any Operating System MTRR code in
+place other than mtrr_type_lookup() to ensure any OS specific mapping requests
+are aligned with platform MTRR setup. If MTRRs are only set up by the platform
+firmware code though and the OS does not make any specific MTRR mapping
+requests mtrr_type_lookup() should always return MTRR_TYPE_INVALID.
For details refer to Documentation/x86/pat.txt.
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index e7ed0d8..f891b47 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -448,7 +448,6 @@ int mtrr_add(unsigned long base, unsigned long size, unsigned int type,
return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
increment);
}
-EXPORT_SYMBOL(mtrr_add);
/**
* mtrr_del_page - delete a memory type region
@@ -537,7 +536,6 @@ int mtrr_del(int reg, unsigned long base, unsigned long size)
return -EINVAL;
return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
}
-EXPORT_SYMBOL(mtrr_del);
/**
* arch_phys_wc_add - add a WC MTRR and handle errors if PAT is unavailable