* Re: [PATCH] ion_system_heap: support X86 archtecture
2019-09-29 7:28 [PATCH] ion_system_heap: support X86 archtecture jun.zhang
@ 2019-09-29 10:12 ` Greg KH
2019-10-01 5:28 ` Zhang, Jun
2019-09-29 20:57 ` Laura Abbott
2020-02-28 11:00 ` youling257
2 siblings, 1 reply; 5+ messages in thread
From: Greg KH @ 2019-09-29 10:12 UTC (permalink / raw)
To: jun.zhang
Cc: labbott, sumit.semwal, arve, tkjos, maco, joel, christian, devel,
Jie A, linux-kernel, dri-devel, linaro-mm-sig, he, Bai, bo
On Sun, Sep 29, 2019 at 03:28:41PM +0800, jun.zhang@intel.com wrote:
> From: zhang jun <jun.zhang@intel.com>
>
> we see tons of warning like:
> [ 45.846872] x86/PAT: NDK MediaCodec_:3753 map pfn RAM range req
> write-combining for [mem 0x1e7a80000-0x1e7a87fff], got write-back
> [ 45.848827] x86/PAT: .vorbis.decoder:4088 map pfn RAM range req
> write-combining for [mem 0x1e7a58000-0x1e7a58fff], got write-back
> [ 45.848875] x86/PAT: NDK MediaCodec_:3753 map pfn RAM range req
> write-combining for [mem 0x1e7a48000-0x1e7a4ffff], got write-back
> [ 45.849403] x86/PAT: .vorbis.decoder:4088 map pfn RAM range
> req write-combining for [mem 0x1e7a70000-0x1e7a70fff], got write-back
>
> check the kernel Documentation/x86/pat.txt, it says:
> A. Exporting pages to users with remap_pfn_range, io_remap_pfn_range,
> vm_insert_pfn
> Drivers wanting to export some pages to userspace do it by using
> mmap interface and a combination of
> 1) pgprot_noncached()
> 2) io_remap_pfn_range() or remap_pfn_range() or vm_insert_pfn()
> With PAT support, a new API pgprot_writecombine is being added.
> So, drivers can continue to use the above sequence, with either
> pgprot_noncached() or pgprot_writecombine() in step 1, followed by step 2.
>
> In addition, step 2 internally tracks the region as UC or WC in
> memtype list in order to ensure no conflicting mapping.
>
> Note that this set of APIs only works with IO (non RAM) regions.
> If driver ants to export a RAM region, it has to do set_memory_uc() or
> set_memory_wc() as step 0 above and also track the usage of those pages
> and use set_memory_wb() before the page is freed to free pool.
>
> the fix follow the pat document, do set_memory_wc() as step 0 and
> use the set_memory_wb() before the page is freed.
>
> Signed-off-by: he, bo <bo.he@intel.com>
> Signed-off-by: zhang jun <jun.zhang@intel.com>
> Signed-off-by: Bai, Jie A <jie.a.bai@intel.com>
> ---
> drivers/staging/android/ion/ion_system_heap.c | 28 ++++++++++++++++++-
> 1 file changed, 27 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c
> index b83a1d16bd89..d298b8194820 100644
> --- a/drivers/staging/android/ion/ion_system_heap.c
> +++ b/drivers/staging/android/ion/ion_system_heap.c
> @@ -13,6 +13,7 @@
> #include <linux/scatterlist.h>
> #include <linux/slab.h>
> #include <linux/vmalloc.h>
> +#include <asm/set_memory.h>
>
> #include "ion.h"
>
> @@ -134,6 +135,13 @@ static int ion_system_heap_allocate(struct ion_heap *heap,
> sg = table->sgl;
> list_for_each_entry_safe(page, tmp_page, &pages, lru) {
> sg_set_page(sg, page, page_size(page), 0);
> +
> +#ifdef CONFIG_X86
> + if (!(buffer->flags & ION_FLAG_CACHED))
> + set_memory_wc((unsigned long)page_address(sg_page(sg)),
> + PAGE_ALIGN(sg->length) >> PAGE_SHIFT);
> +#endif
There is no way to do this without these #ifdefs? That feels odd, why
can't you just always test for this?
thanks,
greg k-h
^ permalink raw reply [flat|nested] 5+ messages in thread* RE: [PATCH] ion_system_heap: support X86 archtecture
2019-09-29 10:12 ` Greg KH
@ 2019-10-01 5:28 ` Zhang, Jun
0 siblings, 0 replies; 5+ messages in thread
From: Zhang, Jun @ 2019-10-01 5:28 UTC (permalink / raw)
To: Greg KH
Cc: labbott@redhat.com, sumit.semwal@linaro.org, arve@android.com,
tkjos@android.com, maco@android.com, joel@joelfernandes.org,
christian@brauner.io, devel@driverdev.osuosl.org, Bai, Jie A,
linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org,
linaro-mm-sig@lists.linaro.org, he@osuosl.org, Bai@osuosl.org,
He, Bo
Hello, Greg
Sorry, I am newcomer, and I don't know why couldn't use #ifdefs? I only refer some kernel code(V4.19) in drivers/hwtracing/intel_th/msu.c.
Could you tell me why? And I tell my workmate to avoid the same case.
If I define a config in Kconfig, and static inline function in .h file, then call it? Could you accept it?
If not, Could you give me a sample?
Thanks,
Jun
-----Original Message-----
From: Greg KH <gregkh@linuxfoundation.org>
Sent: Sunday, September 29, 2019 6:13 PM
To: Zhang, Jun <jun.zhang@intel.com>
Cc: labbott@redhat.com; sumit.semwal@linaro.org; arve@android.com; tkjos@android.com; maco@android.com; joel@joelfernandes.org; christian@brauner.io; devel@driverdev.osuosl.org; Bai, Jie A <jie.a.bai@intel.com>; linux-kernel@vger.kernel.org; dri-devel@lists.freedesktop.org; linaro-mm-sig@lists.linaro.org; he@osuosl.org; Bai@osuosl.org; He, Bo <bo.he@intel.com>
Subject: Re: [PATCH] ion_system_heap: support X86 archtecture
On Sun, Sep 29, 2019 at 03:28:41PM +0800, jun.zhang@intel.com wrote:
> From: zhang jun <jun.zhang@intel.com>
>
> we see tons of warning like:
> [ 45.846872] x86/PAT: NDK MediaCodec_:3753 map pfn RAM range req
> write-combining for [mem 0x1e7a80000-0x1e7a87fff], got write-back
> [ 45.848827] x86/PAT: .vorbis.decoder:4088 map pfn RAM range req
> write-combining for [mem 0x1e7a58000-0x1e7a58fff], got write-back
> [ 45.848875] x86/PAT: NDK MediaCodec_:3753 map pfn RAM range req
> write-combining for [mem 0x1e7a48000-0x1e7a4ffff], got write-back
> [ 45.849403] x86/PAT: .vorbis.decoder:4088 map pfn RAM range
> req write-combining for [mem 0x1e7a70000-0x1e7a70fff], got write-back
>
> check the kernel Documentation/x86/pat.txt, it says:
> A. Exporting pages to users with remap_pfn_range, io_remap_pfn_range,
> vm_insert_pfn Drivers wanting to export some pages to userspace do it
> by using mmap interface and a combination of
> 1) pgprot_noncached()
> 2) io_remap_pfn_range() or remap_pfn_range() or vm_insert_pfn() With
> PAT support, a new API pgprot_writecombine is being added.
> So, drivers can continue to use the above sequence, with either
> pgprot_noncached() or pgprot_writecombine() in step 1, followed by step 2.
>
> In addition, step 2 internally tracks the region as UC or WC in
> memtype list in order to ensure no conflicting mapping.
>
> Note that this set of APIs only works with IO (non RAM) regions.
> If driver ants to export a RAM region, it has to do set_memory_uc() or
> set_memory_wc() as step 0 above and also track the usage of those
> pages and use set_memory_wb() before the page is freed to free pool.
>
> the fix follow the pat document, do set_memory_wc() as step 0 and use
> the set_memory_wb() before the page is freed.
>
> Signed-off-by: he, bo <bo.he@intel.com>
> Signed-off-by: zhang jun <jun.zhang@intel.com>
> Signed-off-by: Bai, Jie A <jie.a.bai@intel.com>
> ---
> drivers/staging/android/ion/ion_system_heap.c | 28
> ++++++++++++++++++-
> 1 file changed, 27 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/staging/android/ion/ion_system_heap.c
> b/drivers/staging/android/ion/ion_system_heap.c
> index b83a1d16bd89..d298b8194820 100644
> --- a/drivers/staging/android/ion/ion_system_heap.c
> +++ b/drivers/staging/android/ion/ion_system_heap.c
> @@ -13,6 +13,7 @@
> #include <linux/scatterlist.h>
> #include <linux/slab.h>
> #include <linux/vmalloc.h>
> +#include <asm/set_memory.h>
>
> #include "ion.h"
>
> @@ -134,6 +135,13 @@ static int ion_system_heap_allocate(struct ion_heap *heap,
> sg = table->sgl;
> list_for_each_entry_safe(page, tmp_page, &pages, lru) {
> sg_set_page(sg, page, page_size(page), 0);
> +
> +#ifdef CONFIG_X86
> + if (!(buffer->flags & ION_FLAG_CACHED))
> + set_memory_wc((unsigned long)page_address(sg_page(sg)),
> + PAGE_ALIGN(sg->length) >> PAGE_SHIFT); #endif
There is no way to do this without these #ifdefs? That feels odd, why can't you just always test for this?
thanks,
greg k-h
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] ion_system_heap: support X86 archtecture
2019-09-29 7:28 [PATCH] ion_system_heap: support X86 archtecture jun.zhang
2019-09-29 10:12 ` Greg KH
@ 2019-09-29 20:57 ` Laura Abbott
2020-02-28 11:00 ` youling257
2 siblings, 0 replies; 5+ messages in thread
From: Laura Abbott @ 2019-09-29 20:57 UTC (permalink / raw)
To: jun.zhang, sumit.semwal, gregkh, arve, tkjos, maco, joel,
christian
Cc: devel, dri-devel, linaro-mm-sig, linux-kernel, bo, Jie A
On 9/29/19 3:28 AM, jun.zhang@intel.com wrote:
> From: zhang jun <jun.zhang@intel.com>
>
> we see tons of warning like:
> [ 45.846872] x86/PAT: NDK MediaCodec_:3753 map pfn RAM range req
> write-combining for [mem 0x1e7a80000-0x1e7a87fff], got write-back
> [ 45.848827] x86/PAT: .vorbis.decoder:4088 map pfn RAM range req
> write-combining for [mem 0x1e7a58000-0x1e7a58fff], got write-back
> [ 45.848875] x86/PAT: NDK MediaCodec_:3753 map pfn RAM range req
> write-combining for [mem 0x1e7a48000-0x1e7a4ffff], got write-back
> [ 45.849403] x86/PAT: .vorbis.decoder:4088 map pfn RAM range
> req write-combining for [mem 0x1e7a70000-0x1e7a70fff], got write-back
>
> check the kernel Documentation/x86/pat.txt, it says:
> A. Exporting pages to users with remap_pfn_range, io_remap_pfn_range,
> vm_insert_pfn
> Drivers wanting to export some pages to userspace do it by using
> mmap interface and a combination of
> 1) pgprot_noncached()
> 2) io_remap_pfn_range() or remap_pfn_range() or vm_insert_pfn()
> With PAT support, a new API pgprot_writecombine is being added.
> So, drivers can continue to use the above sequence, with either
> pgprot_noncached() or pgprot_writecombine() in step 1, followed by step 2.
>
> In addition, step 2 internally tracks the region as UC or WC in
> memtype list in order to ensure no conflicting mapping.
>
> Note that this set of APIs only works with IO (non RAM) regions.
> If driver ants to export a RAM region, it has to do set_memory_uc() or
> set_memory_wc() as step 0 above and also track the usage of those pages
> and use set_memory_wb() before the page is freed to free pool.
>
> the fix follow the pat document, do set_memory_wc() as step 0 and
> use the set_memory_wb() before the page is freed.
>
All this work needs to be done on the new dma-buf heap rework and I
don't think it makes sense to put it on the staging version
https://lore.kernel.org/lkml/20190906184712.91980-1-john.stultz@linaro.org/
(I also continue to question the value of uncached buffers, especially on
x86)
> Signed-off-by: he, bo <bo.he@intel.com>
> Signed-off-by: zhang jun <jun.zhang@intel.com>
> Signed-off-by: Bai, Jie A <jie.a.bai@intel.com>
> ---
> drivers/staging/android/ion/ion_system_heap.c | 28 ++++++++++++++++++-
> 1 file changed, 27 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c
> index b83a1d16bd89..d298b8194820 100644
> --- a/drivers/staging/android/ion/ion_system_heap.c
> +++ b/drivers/staging/android/ion/ion_system_heap.c
> @@ -13,6 +13,7 @@
> #include <linux/scatterlist.h>
> #include <linux/slab.h>
> #include <linux/vmalloc.h>
> +#include <asm/set_memory.h>
>
> #include "ion.h"
>
> @@ -134,6 +135,13 @@ static int ion_system_heap_allocate(struct ion_heap *heap,
> sg = table->sgl;
> list_for_each_entry_safe(page, tmp_page, &pages, lru) {
> sg_set_page(sg, page, page_size(page), 0);
> +
> +#ifdef CONFIG_X86
> + if (!(buffer->flags & ION_FLAG_CACHED))
> + set_memory_wc((unsigned long)page_address(sg_page(sg)),
> + PAGE_ALIGN(sg->length) >> PAGE_SHIFT);
> +#endif
> +
> sg = sg_next(sg);
> list_del(&page->lru);
> }
> @@ -162,8 +170,15 @@ static void ion_system_heap_free(struct ion_buffer *buffer)
> if (!(buffer->private_flags & ION_PRIV_FLAG_SHRINKER_FREE))
> ion_heap_buffer_zero(buffer);
>
> - for_each_sg(table->sgl, sg, table->nents, i)
> + for_each_sg(table->sgl, sg, table->nents, i) {
> +#ifdef CONFIG_X86
> + if (!(buffer->flags & ION_FLAG_CACHED))
> + set_memory_wb((unsigned long)page_address(sg_page(sg)),
> + PAGE_ALIGN(sg->length) >> PAGE_SHIFT);
> +#endif
> +
> free_buffer_page(sys_heap, buffer, sg_page(sg));
> + }
> sg_free_table(table);
> kfree(table);
> }
> @@ -316,6 +331,12 @@ static int ion_system_contig_heap_allocate(struct ion_heap *heap,
>
> buffer->sg_table = table;
>
> +#ifdef CONFIG_X86
> + if (!(buffer->flags & ION_FLAG_CACHED))
> + set_memory_wc((unsigned long)page_address(page),
> + PAGE_ALIGN(len) >> PAGE_SHIFT);
> +#endif
> +
> return 0;
>
> free_table:
> @@ -334,6 +355,11 @@ static void ion_system_contig_heap_free(struct ion_buffer *buffer)
> unsigned long pages = PAGE_ALIGN(buffer->size) >> PAGE_SHIFT;
> unsigned long i;
>
> +#ifdef CONFIG_X86
> + if (!(buffer->flags & ION_FLAG_CACHED))
> + set_memory_wb((unsigned long)page_address(page), pages);
> +#endif
> +
> for (i = 0; i < pages; i++)
> __free_page(page + i);
> sg_free_table(table);
>
^ permalink raw reply [flat|nested] 5+ messages in thread* Re: [PATCH] ion_system_heap: support X86 archtecture
2019-09-29 7:28 [PATCH] ion_system_heap: support X86 archtecture jun.zhang
2019-09-29 10:12 ` Greg KH
2019-09-29 20:57 ` Laura Abbott
@ 2020-02-28 11:00 ` youling257
2 siblings, 0 replies; 5+ messages in thread
From: youling257 @ 2020-02-28 11:00 UTC (permalink / raw)
To: jun.zhang
Cc: labbott, sumit.semwal, gregkh, arve, tkjos, joel, christian, maco,
devel, dri-devel, linux-kernel, he, linaro-mm-sig, bo.he, Bai,
jie.a.bai, youling257
this patch no help for x86.
i have same problem on Androidx86 10.
[ 846.089339] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c00000-0x77c07fff], got write-back
[ 846.089756] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c08000-0x77c0ffff], got write-back
[ 846.090062] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c10000-0x77c17fff], got write-back
[ 846.090311] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c18000-0x77c1ffff], got write-back
[ 846.091353] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c20000-0x77c27fff], got write-back
[ 846.094230] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c00000-0x77c07fff], got write-back
[ 846.095464] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c28000-0x77c2ffff], got write-back
[ 846.099184] x86/PAT: .vorbis.decoder:11142 map pfn RAM range req write-combining for [mem 0x77c08000-0x77c08fff], got write-back
[ 846.100383] x86/PAT: .vorbis.decoder:11142 map pfn RAM range req write-combining for [mem 0x77c10000-0x77c10fff], got write-back
[ 846.103239] x86/PAT: .vorbis.decoder:11142 map pfn RAM range req write-combining for [mem 0x77c18000-0x77c18fff], got write-back
[ 846.104483] x86/PAT: .vorbis.decoder:11142 map pfn RAM range req write-combining for [mem 0x77c30000-0x77c33fff], got write-back
[ 846.104906] x86/PAT: .vorbis.decoder:11142 map pfn RAM range req write-combining for [mem 0x77c20000-0x77c20fff], got write-back
[ 846.104987] x86/PAT: .vorbis.decoder:11142 map pfn RAM range req write-combining for [mem 0x77c30000-0x77c33fff], got write-back
[ 846.109349] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c08000-0x77c0ffff], got write-back
[ 846.109491] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c10000-0x77c17fff], got write-back
[ 846.109965] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c38000-0x77c3ffff], got write-back
[ 846.110136] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c40000-0x77c47fff], got write-back
[ 846.111691] x86/PAT: .vorbis.decoder:11142 map pfn RAM range req write-combining for [mem 0x77c00000-0x77c00fff], got write-back
[ 846.112631] x86/PAT: NPDecoder-CL:11141 map pfn RAM range req write-combining for [mem 0x77c30000-0x77c30fff], got write-back
[ 846.114647] x86/PAT: .vorbis.decoder:11142 map pfn RAM range req write-combining for [mem 0x77c34000-0x77c37fff], got write-back
[ 848.562022] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c00000-0x77c01fff], got write-back
[ 848.562208] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c02000-0x77c03fff], got write-back
[ 848.562587] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c04000-0x77c05fff], got write-back
[ 848.562887] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c06000-0x77c07fff], got write-back
[ 848.564765] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c08000-0x77c09fff], got write-back
[ 848.567498] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c02000-0x77c02fff], got write-back
[ 848.568559] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c00000-0x77c01fff], got write-back
[ 848.569570] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0a000-0x77c0bfff], got write-back
[ 848.571470] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c04000-0x77c04fff], got write-back
[ 848.573627] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c06000-0x77c06fff], got write-back
[ 848.575635] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c08000-0x77c08fff], got write-back
[ 848.576566] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.579950] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c00000-0x77c00fff], got write-back
[ 848.581189] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0d000-0x77c0dfff], got write-back
[ 848.582210] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.582821] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0d000-0x77c0dfff], got write-back
[ 848.584509] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0a000-0x77c0afff], got write-back
[ 848.585061] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.585725] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.586834] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c04000-0x77c04fff], got write-back
[ 848.587474] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.588119] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.589486] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c06000-0x77c06fff], got write-back
[ 848.590083] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.591243] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.592301] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c08000-0x77c08fff], got write-back
[ 848.592891] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.596420] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c00000-0x77c00fff], got write-back
[ 848.596961] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0d000-0x77c0dfff], got write-back
[ 848.598486] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0a000-0x77c0afff], got write-back
[ 848.598598] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.599180] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.603080] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c04000-0x77c04fff], got write-back
[ 848.604500] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0e000-0x77c0efff], got write-back
[ 848.604969] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c06000-0x77c06fff], got write-back
[ 848.606555] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c0f000-0x77c0ffff], got write-back
[ 848.607668] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c08000-0x77c08fff], got write-back
[ 848.611666] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c10000-0x77c10fff], got write-back
[ 848.612810] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c00000-0x77c00fff], got write-back
[ 848.613929] x86/PAT: oid.aac.decoder:11197 map pfn RAM range req write-combining for [mem 0x77c11000-0x77c11fff], got write-back
[ 848.683124] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0d000-0x77c0dfff], got write-back
[ 848.683259] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0c000-0x77c0cfff], got write-back
[ 848.683420] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0e000-0x77c0efff], got write-back
[ 848.683508] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c0f000-0x77c0ffff], got write-back
[ 848.683583] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c10000-0x77c10fff], got write-back
[ 848.683664] x86/PAT: MediaCodec_loop:11196 map pfn RAM range req write-combining for [mem 0x77c11000-0x77c11fff], got write-back
^ permalink raw reply [flat|nested] 5+ messages in thread