[PATCH] net: octeontx2: Make sure the buffer is 128 byte aligned

Subsystems: marvell octeontx2 physical function driver, networking drivers, the rest

STALE2030d LANDED

Landed in mainline as db2805150a0f on 2021-01-23.

6 messages, 5 authors, 2021-01-23 · open the first message on its own page

[PATCH] net: octeontx2: Make sure the buffer is 128 byte aligned

From: Kevin Hao <hidden>
Date: 2021-01-21 07:18:43

The octeontx2 hardware needs the buffer to be 128 byte aligned.
But in the current implementation of napi_alloc_frag(), it can't
guarantee the return address is 128 byte aligned even the request size
is a multiple of 128 bytes, so we have to request an extra 128 bytes and
use the PTR_ALIGN() to make sure that the buffer is aligned correctly.

Fixes: 7a36e4918e30 ("octeontx2-pf: Use the napi_alloc_frag() to alloc the pool buffers")
Reported-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Kevin Hao <redacted>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index bdfa2e293531..5ddedc3b754d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -488,10 +488,11 @@ dma_addr_t __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool)
 	dma_addr_t iova;
 	u8 *buf;
 
-	buf = napi_alloc_frag(pool->rbsize);
+	buf = napi_alloc_frag(pool->rbsize + OTX2_ALIGN);
 	if (unlikely(!buf))
 		return -ENOMEM;
 
+	buf = PTR_ALIGN(buf, OTX2_ALIGN);
 	iova = dma_map_single_attrs(pfvf->dev, buf, pool->rbsize,
 				    DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
 	if (unlikely(dma_mapping_error(pfvf->dev, iova))) {
-- 
2.29.2

Re: [PATCH] net: octeontx2: Make sure the buffer is 128 byte aligned

From: sundeep subbaraya <hidden>
Date: 2021-01-21 09:30:58

Hi Kevin,

Tested at my end and works fine. Thanks for the patch.

Tested-by: Subbaraya Sundeep <sbhatta@marvell.com>

Sundeep

On Thu, Jan 21, 2021 at 12:51 PM Kevin Hao [off-list ref] wrote:
quoted hunk
The octeontx2 hardware needs the buffer to be 128 byte aligned.
But in the current implementation of napi_alloc_frag(), it can't
guarantee the return address is 128 byte aligned even the request size
is a multiple of 128 bytes, so we have to request an extra 128 bytes and
use the PTR_ALIGN() to make sure that the buffer is aligned correctly.

Fixes: 7a36e4918e30 ("octeontx2-pf: Use the napi_alloc_frag() to alloc the pool buffers")
Reported-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Kevin Hao <redacted>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index bdfa2e293531..5ddedc3b754d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -488,10 +488,11 @@ dma_addr_t __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool)
        dma_addr_t iova;
        u8 *buf;

-       buf = napi_alloc_frag(pool->rbsize);
+       buf = napi_alloc_frag(pool->rbsize + OTX2_ALIGN);
        if (unlikely(!buf))
                return -ENOMEM;

+       buf = PTR_ALIGN(buf, OTX2_ALIGN);
        iova = dma_map_single_attrs(pfvf->dev, buf, pool->rbsize,
                                    DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
        if (unlikely(dma_mapping_error(pfvf->dev, iova))) {
--
2.29.2

RE: [PATCH] net: octeontx2: Make sure the buffer is 128 byte aligned

From: David Laight <hidden>
Date: 2021-01-21 10:01:25

From: Kevin Hao
quoted hunk
Sent: 21 January 2021 07:09

The octeontx2 hardware needs the buffer to be 128 byte aligned.
But in the current implementation of napi_alloc_frag(), it can't
guarantee the return address is 128 byte aligned even the request size
is a multiple of 128 bytes, so we have to request an extra 128 bytes and
use the PTR_ALIGN() to make sure that the buffer is aligned correctly.

Fixes: 7a36e4918e30 ("octeontx2-pf: Use the napi_alloc_frag() to alloc the pool buffers")
Reported-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Kevin Hao <redacted>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index bdfa2e293531..5ddedc3b754d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -488,10 +488,11 @@ dma_addr_t __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool)
 	dma_addr_t iova;
 	u8 *buf;

-	buf = napi_alloc_frag(pool->rbsize);
+	buf = napi_alloc_frag(pool->rbsize + OTX2_ALIGN);
 	if (unlikely(!buf))
 		return -ENOMEM;

+	buf = PTR_ALIGN(buf, OTX2_ALIGN);
 	iova = dma_map_single_attrs(pfvf->dev, buf, pool->rbsize,
 				    DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
 	if (unlikely(dma_mapping_error(pfvf->dev, iova))) {
--
2.29.2
Doesn't that break the 'free' code ?
Surely it needs the original pointer.

It isn't obvious that page_frag_free() it correct when the
allocator is napi_alloc_frag() either.
I'd have thought it ought to be returned to the pool.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH] net: octeontx2: Make sure the buffer is 128 byte aligned

From: Kevin Hao <hidden>
Date: 2021-01-21 11:53:07

On Thu, Jan 21, 2021 at 09:53:08AM +0000, David Laight wrote:
From: Kevin Hao
quoted
Sent: 21 January 2021 07:09

The octeontx2 hardware needs the buffer to be 128 byte aligned.
But in the current implementation of napi_alloc_frag(), it can't
guarantee the return address is 128 byte aligned even the request size
is a multiple of 128 bytes, so we have to request an extra 128 bytes and
use the PTR_ALIGN() to make sure that the buffer is aligned correctly.

Fixes: 7a36e4918e30 ("octeontx2-pf: Use the napi_alloc_frag() to alloc the pool buffers")
Reported-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Kevin Hao <redacted>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index bdfa2e293531..5ddedc3b754d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -488,10 +488,11 @@ dma_addr_t __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool)
 	dma_addr_t iova;
 	u8 *buf;

-	buf = napi_alloc_frag(pool->rbsize);
+	buf = napi_alloc_frag(pool->rbsize + OTX2_ALIGN);
 	if (unlikely(!buf))
 		return -ENOMEM;

+	buf = PTR_ALIGN(buf, OTX2_ALIGN);
 	iova = dma_map_single_attrs(pfvf->dev, buf, pool->rbsize,
 				    DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
 	if (unlikely(dma_mapping_error(pfvf->dev, iova))) {
--
2.29.2
Doesn't that break the 'free' code ?
Surely it needs the original pointer.
Why do we care about the original pointer? The free code should work with
the mangling poiner. Did I miss something?
It isn't obvious that page_frag_free() it correct when the
allocator is napi_alloc_frag() either.
I'd have thought it ought to be returned to the pool.
Sorry, I didn't get what you mean. Could you elaborate a bit more?

Thanks,
Kevin
	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH] net: octeontx2: Make sure the buffer is 128 byte aligned

From: Sunil Kovvuri <hidden>
Date: 2021-01-21 12:46:35

On Thu, Jan 21, 2021 at 5:26 PM Kevin Hao [off-list ref] wrote:
On Thu, Jan 21, 2021 at 09:53:08AM +0000, David Laight wrote:
quoted
From: Kevin Hao
quoted
Sent: 21 January 2021 07:09

The octeontx2 hardware needs the buffer to be 128 byte aligned.
But in the current implementation of napi_alloc_frag(), it can't
guarantee the return address is 128 byte aligned even the request size
is a multiple of 128 bytes, so we have to request an extra 128 bytes and
use the PTR_ALIGN() to make sure that the buffer is aligned correctly.

Fixes: 7a36e4918e30 ("octeontx2-pf: Use the napi_alloc_frag() to alloc the pool buffers")
Reported-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Kevin Hao <redacted>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index bdfa2e293531..5ddedc3b754d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -488,10 +488,11 @@ dma_addr_t __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool)
    dma_addr_t iova;
    u8 *buf;

-   buf = napi_alloc_frag(pool->rbsize);
+   buf = napi_alloc_frag(pool->rbsize + OTX2_ALIGN);
    if (unlikely(!buf))
            return -ENOMEM;

+   buf = PTR_ALIGN(buf, OTX2_ALIGN);
    iova = dma_map_single_attrs(pfvf->dev, buf, pool->rbsize,
                                DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
    if (unlikely(dma_mapping_error(pfvf->dev, iova))) {
--
2.29.2
Doesn't that break the 'free' code ?
Surely it needs the original pointer.
Why do we care about the original pointer? The free code should work with
the mangling poiner. Did I miss something?
quoted
I too agree, put_page(buf) or put_page(buf + OTX2_ALIGN) is same.

Re: [PATCH] net: octeontx2: Make sure the buffer is 128 byte aligned

From: patchwork-bot+netdevbpf@kernel.org
Date: 2021-01-23 02:11:35

Hello:

This patch was applied to netdev/net.git (refs/heads/master):

On Thu, 21 Jan 2021 15:09:06 +0800 you wrote:
The octeontx2 hardware needs the buffer to be 128 byte aligned.
But in the current implementation of napi_alloc_frag(), it can't
guarantee the return address is 128 byte aligned even the request size
is a multiple of 128 bytes, so we have to request an extra 128 bytes and
use the PTR_ALIGN() to make sure that the buffer is aligned correctly.

Fixes: 7a36e4918e30 ("octeontx2-pf: Use the napi_alloc_frag() to alloc the pool buffers")
Reported-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Kevin Hao <redacted>

[...]
Here is the summary with links:
  - net: octeontx2: Make sure the buffer is 128 byte aligned
    https://git.kernel.org/netdev/net/c/db2805150a0f

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html

Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help