* [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
@ 2015-03-23 7:27 ` Tomasz Figa
0 siblings, 0 replies; 14+ messages in thread
From: Tomasz Figa @ 2015-03-23 7:27 UTC (permalink / raw)
To: linux-arm-kernel
IOMMU should be able to use single pages as well as bigger blocks, so if
higher order allocations fail, we should not affect state of the system,
with events such as OOM killer, but rather fall back to order 0
allocations.
This patch changes the behavior of ARM IOMMU DMA allocator to use
__GFP_NORETRY, which bypasses OOM invocation, for orders higher than
zero and, only if that fails, fall back to normal order 0 allocation
which might invoke OOM killer.
Signed-off-by: Tomasz Figa <tfiga@chromium.org>
---
arch/arm/mm/dma-mapping.c | 27 +++++++++++++++++++++------
1 file changed, 21 insertions(+), 6 deletions(-)
Changes since v1:
(https://patchwork.kernel.org/patch/6015921/)
- do not clear __GFP_NORETRY, as it might come from the caller,
- s/positive order/order higher than 0/.
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 83cd5ac..3f1ac51 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1150,13 +1150,28 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
while (count) {
- int j, order = __fls(count);
+ int j, order;
+
+ for (order = __fls(count); order > 0; --order) {
+ /*
+ * We do not want OOM killer to be invoked as long
+ * as we can fall back to single pages, so we force
+ * __GFP_NORETRY for orders higher than zero.
+ */
+ pages[i] = alloc_pages(gfp | __GFP_NORETRY, order);
+ if (pages[i])
+ break;
+ }
- pages[i] = alloc_pages(gfp, order);
- while (!pages[i] && order)
- pages[i] = alloc_pages(gfp, --order);
- if (!pages[i])
- goto error;
+ if (!pages[i]) {
+ /*
+ * Fall back to single page allocation.
+ * Might invoke OOM killer as last resort.
+ */
+ pages[i] = alloc_pages(gfp, 0);
+ if (!pages[i])
+ goto error;
+ }
if (order) {
split_page(pages[i], order);
--
2.2.0.rc0.207.ga3a616c
^ permalink raw reply related [flat|nested] 14+ messages in thread* Re: [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
2015-03-23 7:27 ` Tomasz Figa
@ 2015-03-23 16:30 ` Doug Anderson
-1 siblings, 0 replies; 14+ messages in thread
From: Doug Anderson @ 2015-03-23 16:30 UTC (permalink / raw)
To: Tomasz Figa
Cc: linux-arm-kernel, linux-kernel, Russell King, Marek Szyprowski,
Will Deacon, Andrew Morton, Laura Abbott, Ritesh Harjani,
Carlo Caione, Laurent Pinchart, Sonny Rao, David Rientjes
Tomasz,
On Mon, Mar 23, 2015 at 12:27 AM, Tomasz Figa <tfiga@chromium.org> wrote:
> IOMMU should be able to use single pages as well as bigger blocks, so if
> higher order allocations fail, we should not affect state of the system,
> with events such as OOM killer, but rather fall back to order 0
> allocations.
>
> This patch changes the behavior of ARM IOMMU DMA allocator to use
> __GFP_NORETRY, which bypasses OOM invocation, for orders higher than
> zero and, only if that fails, fall back to normal order 0 allocation
> which might invoke OOM killer.
>
> Signed-off-by: Tomasz Figa <tfiga@chromium.org>
> ---
> arch/arm/mm/dma-mapping.c | 27 +++++++++++++++++++++------
> 1 file changed, 21 insertions(+), 6 deletions(-)
FWIW:
Reviewed-by: Doug Anderson <dianders@chromium.org>
^ permalink raw reply [flat|nested] 14+ messages in thread
* [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
@ 2015-03-23 16:30 ` Doug Anderson
0 siblings, 0 replies; 14+ messages in thread
From: Doug Anderson @ 2015-03-23 16:30 UTC (permalink / raw)
To: linux-arm-kernel
Tomasz,
On Mon, Mar 23, 2015 at 12:27 AM, Tomasz Figa <tfiga@chromium.org> wrote:
> IOMMU should be able to use single pages as well as bigger blocks, so if
> higher order allocations fail, we should not affect state of the system,
> with events such as OOM killer, but rather fall back to order 0
> allocations.
>
> This patch changes the behavior of ARM IOMMU DMA allocator to use
> __GFP_NORETRY, which bypasses OOM invocation, for orders higher than
> zero and, only if that fails, fall back to normal order 0 allocation
> which might invoke OOM killer.
>
> Signed-off-by: Tomasz Figa <tfiga@chromium.org>
> ---
> arch/arm/mm/dma-mapping.c | 27 +++++++++++++++++++++------
> 1 file changed, 21 insertions(+), 6 deletions(-)
FWIW:
Reviewed-by: Doug Anderson <dianders@chromium.org>
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
2015-03-23 7:27 ` Tomasz Figa
@ 2015-03-23 23:07 ` David Rientjes
-1 siblings, 0 replies; 14+ messages in thread
From: David Rientjes @ 2015-03-23 23:07 UTC (permalink / raw)
To: Tomasz Figa
Cc: linux-arm-kernel, linux-kernel, Russell King, Marek Szyprowski,
Will Deacon, Andrew Morton, Laura Abbott, Ritesh Harjani,
Carlo Caione, Laurent Pinchart, Douglas Anderson, Sonny Rao
On Mon, 23 Mar 2015, Tomasz Figa wrote:
> IOMMU should be able to use single pages as well as bigger blocks, so if
> higher order allocations fail, we should not affect state of the system,
> with events such as OOM killer, but rather fall back to order 0
> allocations.
>
> This patch changes the behavior of ARM IOMMU DMA allocator to use
> __GFP_NORETRY, which bypasses OOM invocation, for orders higher than
> zero and, only if that fails, fall back to normal order 0 allocation
> which might invoke OOM killer.
>
> Signed-off-by: Tomasz Figa <tfiga@chromium.org>
Acked-by: David Rientjes <rientjes@google.com>
^ permalink raw reply [flat|nested] 14+ messages in thread
* [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
@ 2015-03-23 23:07 ` David Rientjes
0 siblings, 0 replies; 14+ messages in thread
From: David Rientjes @ 2015-03-23 23:07 UTC (permalink / raw)
To: linux-arm-kernel
On Mon, 23 Mar 2015, Tomasz Figa wrote:
> IOMMU should be able to use single pages as well as bigger blocks, so if
> higher order allocations fail, we should not affect state of the system,
> with events such as OOM killer, but rather fall back to order 0
> allocations.
>
> This patch changes the behavior of ARM IOMMU DMA allocator to use
> __GFP_NORETRY, which bypasses OOM invocation, for orders higher than
> zero and, only if that fails, fall back to normal order 0 allocation
> which might invoke OOM killer.
>
> Signed-off-by: Tomasz Figa <tfiga@chromium.org>
Acked-by: David Rientjes <rientjes@google.com>
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
2015-03-23 7:27 ` Tomasz Figa
@ 2015-03-24 9:02 ` Marek Szyprowski
-1 siblings, 0 replies; 14+ messages in thread
From: Marek Szyprowski @ 2015-03-24 9:02 UTC (permalink / raw)
To: Tomasz Figa, linux-arm-kernel
Cc: linux-kernel, Russell King, Will Deacon, Andrew Morton,
Laura Abbott, Ritesh Harjani, Carlo Caione, Laurent Pinchart,
Douglas Anderson, Sonny Rao, David Rientjes
Hello,
On 2015-03-23 08:27, Tomasz Figa wrote:
> IOMMU should be able to use single pages as well as bigger blocks, so if
> higher order allocations fail, we should not affect state of the system,
> with events such as OOM killer, but rather fall back to order 0
> allocations.
>
> This patch changes the behavior of ARM IOMMU DMA allocator to use
> __GFP_NORETRY, which bypasses OOM invocation, for orders higher than
> zero and, only if that fails, fall back to normal order 0 allocation
> which might invoke OOM killer.
>
> Signed-off-by: Tomasz Figa <tfiga@chromium.org>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
> ---
> arch/arm/mm/dma-mapping.c | 27 +++++++++++++++++++++------
> 1 file changed, 21 insertions(+), 6 deletions(-)
>
> Changes since v1:
> (https://patchwork.kernel.org/patch/6015921/)
> - do not clear __GFP_NORETRY, as it might come from the caller,
> - s/positive order/order higher than 0/.
>
> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index 83cd5ac..3f1ac51 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -1150,13 +1150,28 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
> gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
>
> while (count) {
> - int j, order = __fls(count);
> + int j, order;
> +
> + for (order = __fls(count); order > 0; --order) {
> + /*
> + * We do not want OOM killer to be invoked as long
> + * as we can fall back to single pages, so we force
> + * __GFP_NORETRY for orders higher than zero.
> + */
> + pages[i] = alloc_pages(gfp | __GFP_NORETRY, order);
> + if (pages[i])
> + break;
> + }
>
> - pages[i] = alloc_pages(gfp, order);
> - while (!pages[i] && order)
> - pages[i] = alloc_pages(gfp, --order);
> - if (!pages[i])
> - goto error;
> + if (!pages[i]) {
> + /*
> + * Fall back to single page allocation.
> + * Might invoke OOM killer as last resort.
> + */
> + pages[i] = alloc_pages(gfp, 0);
> + if (!pages[i])
> + goto error;
> + }
>
> if (order) {
> split_page(pages[i], order);
Best regards
--
Marek Szyprowski, PhD
Samsung R&D Institute Poland
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
@ 2015-03-24 9:02 ` Marek Szyprowski
0 siblings, 0 replies; 14+ messages in thread
From: Marek Szyprowski @ 2015-03-24 9:02 UTC (permalink / raw)
To: linux-arm-kernel
Hello,
On 2015-03-23 08:27, Tomasz Figa wrote:
> IOMMU should be able to use single pages as well as bigger blocks, so if
> higher order allocations fail, we should not affect state of the system,
> with events such as OOM killer, but rather fall back to order 0
> allocations.
>
> This patch changes the behavior of ARM IOMMU DMA allocator to use
> __GFP_NORETRY, which bypasses OOM invocation, for orders higher than
> zero and, only if that fails, fall back to normal order 0 allocation
> which might invoke OOM killer.
>
> Signed-off-by: Tomasz Figa <tfiga@chromium.org>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
> ---
> arch/arm/mm/dma-mapping.c | 27 +++++++++++++++++++++------
> 1 file changed, 21 insertions(+), 6 deletions(-)
>
> Changes since v1:
> (https://patchwork.kernel.org/patch/6015921/)
> - do not clear __GFP_NORETRY, as it might come from the caller,
> - s/positive order/order higher than 0/.
>
> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index 83cd5ac..3f1ac51 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -1150,13 +1150,28 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
> gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
>
> while (count) {
> - int j, order = __fls(count);
> + int j, order;
> +
> + for (order = __fls(count); order > 0; --order) {
> + /*
> + * We do not want OOM killer to be invoked as long
> + * as we can fall back to single pages, so we force
> + * __GFP_NORETRY for orders higher than zero.
> + */
> + pages[i] = alloc_pages(gfp | __GFP_NORETRY, order);
> + if (pages[i])
> + break;
> + }
>
> - pages[i] = alloc_pages(gfp, order);
> - while (!pages[i] && order)
> - pages[i] = alloc_pages(gfp, --order);
> - if (!pages[i])
> - goto error;
> + if (!pages[i]) {
> + /*
> + * Fall back to single page allocation.
> + * Might invoke OOM killer as last resort.
> + */
> + pages[i] = alloc_pages(gfp, 0);
> + if (!pages[i])
> + goto error;
> + }
>
> if (order) {
> split_page(pages[i], order);
Best regards
--
Marek Szyprowski, PhD
Samsung R&D Institute Poland
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
2015-03-23 7:27 ` Tomasz Figa
@ 2015-03-25 18:39 ` Ritesh Harjani
-1 siblings, 0 replies; 14+ messages in thread
From: Ritesh Harjani @ 2015-03-25 18:39 UTC (permalink / raw)
To: Tomasz Figa
Cc: linux-arm-kernel, Laurent Pinchart, Laura Abbott, David Rientjes,
Will Deacon, LKML, Douglas Anderson, Carlo Caione, Russell King,
Andrew Morton, Sonny Rao, Marek Szyprowski, Ritesh Harjani
Hi
On Mon, Mar 23, 2015 at 12:57 PM, Tomasz Figa <tfiga@chromium.org> wrote:
> IOMMU should be able to use single pages as well as bigger blocks, so if
> higher order allocations fail, we should not affect state of the system,
> with events such as OOM killer, but rather fall back to order 0
> allocations.
>
> This patch changes the behavior of ARM IOMMU DMA allocator to use
> __GFP_NORETRY, which bypasses OOM invocation, for orders higher than
> zero and, only if that fails, fall back to normal order 0 allocation
> which might invoke OOM killer.
Logical thing to do in IOMMU case :)
>
> Signed-off-by: Tomasz Figa <tfiga@chromium.org>
> ---
> arch/arm/mm/dma-mapping.c | 27 +++++++++++++++++++++------
> 1 file changed, 21 insertions(+), 6 deletions(-)
>
> Changes since v1:
> (https://patchwork.kernel.org/patch/6015921/)
> - do not clear __GFP_NORETRY, as it might come from the caller,
> - s/positive order/order higher than 0/.
>
> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index 83cd5ac..3f1ac51 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -1150,13 +1150,28 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
> gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
>
> while (count) {
> - int j, order = __fls(count);
> + int j, order;
> +
> + for (order = __fls(count); order > 0; --order) {
> + /*
> + * We do not want OOM killer to be invoked as long
> + * as we can fall back to single pages, so we force
> + * __GFP_NORETRY for orders higher than zero.
> + */
> + pages[i] = alloc_pages(gfp | __GFP_NORETRY, order);
> + if (pages[i])
> + break;
> + }
>
> - pages[i] = alloc_pages(gfp, order);
> - while (!pages[i] && order)
> - pages[i] = alloc_pages(gfp, --order);
> - if (!pages[i])
> - goto error;
> + if (!pages[i]) {
> + /*
> + * Fall back to single page allocation.
> + * Might invoke OOM killer as last resort.
> + */
> + pages[i] = alloc_pages(gfp, 0);
I think down the code in this while loop, i & count is being
calculated based on the "order" of allocation in the current
iteration.
Since value of order will be automatically 0 here if (!pages[i]) is
true then, why hard code order to value of 0 here.
Comment clearly says what this code is doing right?
I know it is just a minor thing. Don't know if it is relevant.
> + if (!pages[i])
> + goto error;
> + }
>
> if (order) {
> split_page(pages[i], order);
> --
> 2.2.0.rc0.207.ga3a616c
>
>
> _______________________________________________
> linux-arm-kernel mailing list
> linux-arm-kernel@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Thanks
Ritesh
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
@ 2015-03-25 18:39 ` Ritesh Harjani
0 siblings, 0 replies; 14+ messages in thread
From: Ritesh Harjani @ 2015-03-25 18:39 UTC (permalink / raw)
To: linux-arm-kernel
Hi
On Mon, Mar 23, 2015 at 12:57 PM, Tomasz Figa <tfiga@chromium.org> wrote:
> IOMMU should be able to use single pages as well as bigger blocks, so if
> higher order allocations fail, we should not affect state of the system,
> with events such as OOM killer, but rather fall back to order 0
> allocations.
>
> This patch changes the behavior of ARM IOMMU DMA allocator to use
> __GFP_NORETRY, which bypasses OOM invocation, for orders higher than
> zero and, only if that fails, fall back to normal order 0 allocation
> which might invoke OOM killer.
Logical thing to do in IOMMU case :)
>
> Signed-off-by: Tomasz Figa <tfiga@chromium.org>
> ---
> arch/arm/mm/dma-mapping.c | 27 +++++++++++++++++++++------
> 1 file changed, 21 insertions(+), 6 deletions(-)
>
> Changes since v1:
> (https://patchwork.kernel.org/patch/6015921/)
> - do not clear __GFP_NORETRY, as it might come from the caller,
> - s/positive order/order higher than 0/.
>
> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index 83cd5ac..3f1ac51 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -1150,13 +1150,28 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
> gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
>
> while (count) {
> - int j, order = __fls(count);
> + int j, order;
> +
> + for (order = __fls(count); order > 0; --order) {
> + /*
> + * We do not want OOM killer to be invoked as long
> + * as we can fall back to single pages, so we force
> + * __GFP_NORETRY for orders higher than zero.
> + */
> + pages[i] = alloc_pages(gfp | __GFP_NORETRY, order);
> + if (pages[i])
> + break;
> + }
>
> - pages[i] = alloc_pages(gfp, order);
> - while (!pages[i] && order)
> - pages[i] = alloc_pages(gfp, --order);
> - if (!pages[i])
> - goto error;
> + if (!pages[i]) {
> + /*
> + * Fall back to single page allocation.
> + * Might invoke OOM killer as last resort.
> + */
> + pages[i] = alloc_pages(gfp, 0);
I think down the code in this while loop, i & count is being
calculated based on the "order" of allocation in the current
iteration.
Since value of order will be automatically 0 here if (!pages[i]) is
true then, why hard code order to value of 0 here.
Comment clearly says what this code is doing right?
I know it is just a minor thing. Don't know if it is relevant.
> + if (!pages[i])
> + goto error;
> + }
>
> if (order) {
> split_page(pages[i], order);
> --
> 2.2.0.rc0.207.ga3a616c
>
>
> _______________________________________________
> linux-arm-kernel mailing list
> linux-arm-kernel at lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Thanks
Ritesh
^ permalink raw reply [flat|nested] 14+ messages in thread* Re: [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
2015-03-25 18:39 ` Ritesh Harjani
@ 2015-03-26 0:34 ` David Rientjes
-1 siblings, 0 replies; 14+ messages in thread
From: David Rientjes @ 2015-03-26 0:34 UTC (permalink / raw)
To: Ritesh Harjani
Cc: Tomasz Figa, linux-arm-kernel, Laurent Pinchart, Laura Abbott,
Will Deacon, LKML, Douglas Anderson, Carlo Caione, Russell King,
Andrew Morton, Sonny Rao, Marek Szyprowski, Ritesh Harjani
On Thu, 26 Mar 2015, Ritesh Harjani wrote:
> > diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> > index 83cd5ac..3f1ac51 100644
> > --- a/arch/arm/mm/dma-mapping.c
> > +++ b/arch/arm/mm/dma-mapping.c
> > @@ -1150,13 +1150,28 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
> > gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
> >
> > while (count) {
> > - int j, order = __fls(count);
> > + int j, order;
> > +
> > + for (order = __fls(count); order > 0; --order) {
> > + /*
> > + * We do not want OOM killer to be invoked as long
> > + * as we can fall back to single pages, so we force
> > + * __GFP_NORETRY for orders higher than zero.
> > + */
> > + pages[i] = alloc_pages(gfp | __GFP_NORETRY, order);
> > + if (pages[i])
> > + break;
> > + }
> >
> > - pages[i] = alloc_pages(gfp, order);
> > - while (!pages[i] && order)
> > - pages[i] = alloc_pages(gfp, --order);
> > - if (!pages[i])
> > - goto error;
> > + if (!pages[i]) {
> > + /*
> > + * Fall back to single page allocation.
> > + * Might invoke OOM killer as last resort.
> > + */
> > + pages[i] = alloc_pages(gfp, 0);
> I think down the code in this while loop, i & count is being
> calculated based on the "order" of allocation in the current
> iteration.
> Since value of order will be automatically 0 here if (!pages[i]) is
> true then, why hard code order to value of 0 here.
> Comment clearly says what this code is doing right?
>
Gcc is smart enough to know that order == 0 here, the code generation on
arm will be the same, so this is only a matter of how the source looks.
To me, it doesn't make a lot of sense to write it as alloc_pages(gfp,
order) when order is always equal to 0. I think it's clearer the way that
Tomasz wrote it.
> I know it is just a minor thing. Don't know if it is relevant.
>
> > + if (!pages[i])
> > + goto error;
> > + }
> >
> > if (order) {
> > split_page(pages[i], order);
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
@ 2015-03-26 0:34 ` David Rientjes
0 siblings, 0 replies; 14+ messages in thread
From: David Rientjes @ 2015-03-26 0:34 UTC (permalink / raw)
To: linux-arm-kernel
On Thu, 26 Mar 2015, Ritesh Harjani wrote:
> > diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> > index 83cd5ac..3f1ac51 100644
> > --- a/arch/arm/mm/dma-mapping.c
> > +++ b/arch/arm/mm/dma-mapping.c
> > @@ -1150,13 +1150,28 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
> > gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
> >
> > while (count) {
> > - int j, order = __fls(count);
> > + int j, order;
> > +
> > + for (order = __fls(count); order > 0; --order) {
> > + /*
> > + * We do not want OOM killer to be invoked as long
> > + * as we can fall back to single pages, so we force
> > + * __GFP_NORETRY for orders higher than zero.
> > + */
> > + pages[i] = alloc_pages(gfp | __GFP_NORETRY, order);
> > + if (pages[i])
> > + break;
> > + }
> >
> > - pages[i] = alloc_pages(gfp, order);
> > - while (!pages[i] && order)
> > - pages[i] = alloc_pages(gfp, --order);
> > - if (!pages[i])
> > - goto error;
> > + if (!pages[i]) {
> > + /*
> > + * Fall back to single page allocation.
> > + * Might invoke OOM killer as last resort.
> > + */
> > + pages[i] = alloc_pages(gfp, 0);
> I think down the code in this while loop, i & count is being
> calculated based on the "order" of allocation in the current
> iteration.
> Since value of order will be automatically 0 here if (!pages[i]) is
> true then, why hard code order to value of 0 here.
> Comment clearly says what this code is doing right?
>
Gcc is smart enough to know that order == 0 here, the code generation on
arm will be the same, so this is only a matter of how the source looks.
To me, it doesn't make a lot of sense to write it as alloc_pages(gfp,
order) when order is always equal to 0. I think it's clearer the way that
Tomasz wrote it.
> I know it is just a minor thing. Don't know if it is relevant.
>
> > + if (!pages[i])
> > + goto error;
> > + }
> >
> > if (order) {
> > split_page(pages[i], order);
^ permalink raw reply [flat|nested] 14+ messages in thread* Re: [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
2015-03-26 0:34 ` David Rientjes
@ 2015-03-26 4:31 ` Ritesh Harjani
-1 siblings, 0 replies; 14+ messages in thread
From: Ritesh Harjani @ 2015-03-26 4:31 UTC (permalink / raw)
To: David Rientjes
Cc: Tomasz Figa, linux-arm-kernel, Laurent Pinchart, Laura Abbott,
Will Deacon, LKML, Douglas Anderson, Carlo Caione, Russell King,
Andrew Morton, Sonny Rao, Marek Szyprowski
On Thu, Mar 26, 2015 at 6:04 AM, David Rientjes <rientjes@google.com> wrote:
> On Thu, 26 Mar 2015, Ritesh Harjani wrote:
>
>> > diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
>> > index 83cd5ac..3f1ac51 100644
>> > --- a/arch/arm/mm/dma-mapping.c
>> > +++ b/arch/arm/mm/dma-mapping.c
>> > @@ -1150,13 +1150,28 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
>> > gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
>> >
>> > while (count) {
>> > - int j, order = __fls(count);
>> > + int j, order;
>> > +
>> > + for (order = __fls(count); order > 0; --order) {
>> > + /*
>> > + * We do not want OOM killer to be invoked as long
>> > + * as we can fall back to single pages, so we force
>> > + * __GFP_NORETRY for orders higher than zero.
>> > + */
>> > + pages[i] = alloc_pages(gfp | __GFP_NORETRY, order);
>> > + if (pages[i])
>> > + break;
>> > + }
>> >
>> > - pages[i] = alloc_pages(gfp, order);
>> > - while (!pages[i] && order)
>> > - pages[i] = alloc_pages(gfp, --order);
>> > - if (!pages[i])
>> > - goto error;
>> > + if (!pages[i]) {
>> > + /*
>> > + * Fall back to single page allocation.
>> > + * Might invoke OOM killer as last resort.
>> > + */
>> > + pages[i] = alloc_pages(gfp, 0);
>> I think down the code in this while loop, i & count is being
>> calculated based on the "order" of allocation in the current
>> iteration.
>> Since value of order will be automatically 0 here if (!pages[i]) is
>> true then, why hard code order to value of 0 here.
>> Comment clearly says what this code is doing right?
>>
>
> Gcc is smart enough to know that order == 0 here, the code generation on
> arm will be the same, so this is only a matter of how the source looks.
Agreed.
> To me, it doesn't make a lot of sense to write it as alloc_pages(gfp,
> order) when order is always equal to 0. I think it's clearer the way that
> Tomasz wrote it.
Ok
>
>> I know it is just a minor thing. Don't know if it is relevant.
>>
>> > + if (!pages[i])
>> > + goto error;
>> > + }
>> >
>> > if (order) {
>> > split_page(pages[i], order);
Thanks
Ritesh
^ permalink raw reply [flat|nested] 14+ messages in thread* [PATCH v2] ARM: mm: Do not invoke OOM for higher order IOMMU DMA allocations
@ 2015-03-26 4:31 ` Ritesh Harjani
0 siblings, 0 replies; 14+ messages in thread
From: Ritesh Harjani @ 2015-03-26 4:31 UTC (permalink / raw)
To: linux-arm-kernel
On Thu, Mar 26, 2015 at 6:04 AM, David Rientjes <rientjes@google.com> wrote:
> On Thu, 26 Mar 2015, Ritesh Harjani wrote:
>
>> > diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
>> > index 83cd5ac..3f1ac51 100644
>> > --- a/arch/arm/mm/dma-mapping.c
>> > +++ b/arch/arm/mm/dma-mapping.c
>> > @@ -1150,13 +1150,28 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
>> > gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
>> >
>> > while (count) {
>> > - int j, order = __fls(count);
>> > + int j, order;
>> > +
>> > + for (order = __fls(count); order > 0; --order) {
>> > + /*
>> > + * We do not want OOM killer to be invoked as long
>> > + * as we can fall back to single pages, so we force
>> > + * __GFP_NORETRY for orders higher than zero.
>> > + */
>> > + pages[i] = alloc_pages(gfp | __GFP_NORETRY, order);
>> > + if (pages[i])
>> > + break;
>> > + }
>> >
>> > - pages[i] = alloc_pages(gfp, order);
>> > - while (!pages[i] && order)
>> > - pages[i] = alloc_pages(gfp, --order);
>> > - if (!pages[i])
>> > - goto error;
>> > + if (!pages[i]) {
>> > + /*
>> > + * Fall back to single page allocation.
>> > + * Might invoke OOM killer as last resort.
>> > + */
>> > + pages[i] = alloc_pages(gfp, 0);
>> I think down the code in this while loop, i & count is being
>> calculated based on the "order" of allocation in the current
>> iteration.
>> Since value of order will be automatically 0 here if (!pages[i]) is
>> true then, why hard code order to value of 0 here.
>> Comment clearly says what this code is doing right?
>>
>
> Gcc is smart enough to know that order == 0 here, the code generation on
> arm will be the same, so this is only a matter of how the source looks.
Agreed.
> To me, it doesn't make a lot of sense to write it as alloc_pages(gfp,
> order) when order is always equal to 0. I think it's clearer the way that
> Tomasz wrote it.
Ok
>
>> I know it is just a minor thing. Don't know if it is relevant.
>>
>> > + if (!pages[i])
>> > + goto error;
>> > + }
>> >
>> > if (order) {
>> > split_page(pages[i], order);
Thanks
Ritesh
^ permalink raw reply [flat|nested] 14+ messages in thread