| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <AANLkTilyGz86DlwOvtVolthE66VzkSwj9jDv0s138Egi@mail.gmail.com>
Date: Tue, 18 May 2010 19:34:01 +1000
From: Dave Airlie <airlied@...il.com>
To: Pauli Nieminen <suokkos@...il.com>,
LKML <linux-kernel@...r.kernel.org>, Ingo Molnar <mingo@...e.hu>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@...il.com>,
Suresh Siddha <suresh.b.siddha@...el.com>
Subject: Re: [PATCH 5/7] arch/x86: Add array variants for setting memory to wc
caching.
On Thu, Apr 1, 2010 at 10:45 PM, Pauli Nieminen <suokkos@...il.com> wrote:
> Setting single memory pages at a time to wc takes a lot time in cache flush. To
> reduce number of cache flush set_pages_array_wc and set_memory_array_wc can be
> used to set multiple pages to WC with single cache flush.
>
> This improves allocation performance for wc cached pages in drm/ttm.
>
I've got this in drm-next for quite a while and almost forgot about
it, I'm meant to be on holidays and I'd really like to just have Linus
pull my tree,
I had only one issue with this as we had some problems with doing it
before but it looks like they've since been fixed in the x86 pat code
a kernel or two ago so this patch should be fine now.
its been well tested in drm-next on AGP machines by the author,
any objections to this?
Dave.
> CC: Suresh Siddha <suresh.b.siddha@...el.com>
> CC: Venkatesh Pallipadi <venkatesh.pallipadi@...il.com>
> Signed-off-by: Pauli Nieminen <suokkos@...il.com>
> ---
> arch/x86/include/asm/cacheflush.h | 2 +
> arch/x86/mm/pageattr.c | 53 +++++++++++++++++++++++++++++++-----
> 2 files changed, 47 insertions(+), 8 deletions(-)
>
> diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
> index 634c40a..d92d63a 100644
> --- a/arch/x86/include/asm/cacheflush.h
> +++ b/arch/x86/include/asm/cacheflush.h
> @@ -139,9 +139,11 @@ int set_memory_np(unsigned long addr, int numpages);
> int set_memory_4k(unsigned long addr, int numpages);
>
> int set_memory_array_uc(unsigned long *addr, int addrinarray);
> +int set_memory_array_wc(unsigned long *addr, int addrinarray);
> int set_memory_array_wb(unsigned long *addr, int addrinarray);
>
> int set_pages_array_uc(struct page **pages, int addrinarray);
> +int set_pages_array_wc(struct page **pages, int addrinarray);
> int set_pages_array_wb(struct page **pages, int addrinarray);
>
> /*
> diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
> index cf07c26..0c98a75 100644
> --- a/arch/x86/mm/pageattr.c
> +++ b/arch/x86/mm/pageattr.c
> @@ -997,7 +997,8 @@ out_err:
> }
> EXPORT_SYMBOL(set_memory_uc);
>
> -int set_memory_array_uc(unsigned long *addr, int addrinarray)
> +int _set_memory_array(unsigned long *addr, int addrinarray,
> + unsigned long new_type)
> {
> int i, j;
> int ret;
> @@ -1007,13 +1008,19 @@ int set_memory_array_uc(unsigned long *addr, int addrinarray)
> */
> for (i = 0; i < addrinarray; i++) {
> ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
> - _PAGE_CACHE_UC_MINUS, NULL);
> + new_type, NULL);
> if (ret)
> goto out_free;
> }
>
> ret = change_page_attr_set(addr, addrinarray,
> __pgprot(_PAGE_CACHE_UC_MINUS), 1);
> +
> + if (!ret && new_type == _PAGE_CACHE_WC)
> + ret = change_page_attr_set_clr(addr, addrinarray,
> + __pgprot(_PAGE_CACHE_WC),
> + __pgprot(_PAGE_CACHE_MASK),
> + 0, CPA_ARRAY, NULL);
> if (ret)
> goto out_free;
>
> @@ -1025,8 +1032,19 @@ out_free:
>
> return ret;
> }
> +
> +int set_memory_array_uc(unsigned long *addr, int addrinarray)
> +{
> + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_UC_MINUS);
> +}
> EXPORT_SYMBOL(set_memory_array_uc);
>
> +int set_memory_array_wc(unsigned long *addr, int addrinarray)
> +{
> + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_WC);
> +}
> +EXPORT_SYMBOL(set_memory_array_wc);
> +
> int _set_memory_wc(unsigned long addr, int numpages)
> {
> int ret;
> @@ -1153,26 +1171,34 @@ int set_pages_uc(struct page *page, int numpages)
> }
> EXPORT_SYMBOL(set_pages_uc);
>
> -int set_pages_array_uc(struct page **pages, int addrinarray)
> +static int _set_pages_array(struct page **pages, int addrinarray,
> + unsigned long new_type)
> {
> unsigned long start;
> unsigned long end;
> int i;
> int free_idx;
> + int ret;
>
> for (i = 0; i < addrinarray; i++) {
> if (PageHighMem(pages[i]))
> continue;
> start = page_to_pfn(pages[i]) << PAGE_SHIFT;
> end = start + PAGE_SIZE;
> - if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
> + if (reserve_memtype(start, end, new_type, NULL))
> goto err_out;
> }
>
> - if (cpa_set_pages_array(pages, addrinarray,
> - __pgprot(_PAGE_CACHE_UC_MINUS)) == 0) {
> - return 0; /* Success */
> - }
> + ret = cpa_set_pages_array(pages, addrinarray,
> + __pgprot(_PAGE_CACHE_UC_MINUS));
> + if (!ret && new_type == _PAGE_CACHE_WC)
> + ret = change_page_attr_set_clr(NULL, addrinarray,
> + __pgprot(_PAGE_CACHE_WC),
> + __pgprot(_PAGE_CACHE_MASK),
> + 0, CPA_PAGES_ARRAY, pages);
> + if (ret)
> + goto err_out;
> + return 0; /* Success */
> err_out:
> free_idx = i;
> for (i = 0; i < free_idx; i++) {
> @@ -1184,8 +1210,19 @@ err_out:
> }
> return -EINVAL;
> }
> +
> +int set_pages_array_uc(struct page **pages, int addrinarray)
> +{
> + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_UC_MINUS);
> +}
> EXPORT_SYMBOL(set_pages_array_uc);
>
> +int set_pages_array_wc(struct page **pages, int addrinarray)
> +{
> + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_WC);
> +}
> +EXPORT_SYMBOL(set_pages_array_wc);
> +
> int set_pages_wb(struct page *page, int numpages)
> {
> unsigned long addr = (unsigned long)page_address(page);
> --
> 1.7.0
>
>
> ------------------------------------------------------------------------------
> Download Intel® Parallel Studio Eval
> Try the new software tools for yourself. Speed compiling, find bugs
> proactively, and fine-tune applications for parallel performance.
> See why Intel Parallel Studio got high marks during beta.
> http://p.sf.net/sfu/intel-sw-dev
> --
> _______________________________________________
> Dri-devel mailing list
> Dri-devel@...ts.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/dri-devel
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists