* RE: [PATCH v5 rdma-next 1/6] RDMA/core: Create mmap database and cookie helper functions
From: Michal Kalderon @ 2019-07-09 10:29 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Ariel Elior, jgg@ziepe.ca, dledford@redhat.com,
galpress@amazon.com, linux-rdma@vger.kernel.org,
davem@davemloft.net, netdev@vger.kernel.org
In-Reply-To: <20190709070244.GH7034@mtr-leonro.mtl.com>
> From: linux-rdma-owner@vger.kernel.org <linux-rdma-
> owner@vger.kernel.org> On Behalf Of Leon Romanovsky
>
> On Mon, Jul 08, 2019 at 12:14:58PM +0300, Michal Kalderon wrote:
> > Create some common API's for adding entries to a xa_mmap.
> > Searching for an entry and freeing one.
> >
> > The code was copied from the efa driver almost as is, just renamed
> > function to be generic and not efa specific.
> >
> > Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
> > ---
> > drivers/infiniband/core/device.c | 1 +
> > drivers/infiniband/core/rdma_core.c | 1 +
> > drivers/infiniband/core/uverbs_cmd.c | 1 +
> > drivers/infiniband/core/uverbs_main.c | 105
> ++++++++++++++++++++++++++++++++++
> > include/rdma/ib_verbs.h | 32 +++++++++++
> > 5 files changed, 140 insertions(+)
> >
> > diff --git a/drivers/infiniband/core/device.c
> > b/drivers/infiniband/core/device.c
> > index 8a6ccb936dfe..a830c2c5d691 100644
> > --- a/drivers/infiniband/core/device.c
> > +++ b/drivers/infiniband/core/device.c
> > @@ -2521,6 +2521,7 @@ void ib_set_device_ops(struct ib_device *dev,
> const struct ib_device_ops *ops)
> > SET_DEVICE_OP(dev_ops, map_mr_sg_pi);
> > SET_DEVICE_OP(dev_ops, map_phys_fmr);
> > SET_DEVICE_OP(dev_ops, mmap);
> > + SET_DEVICE_OP(dev_ops, mmap_free);
> > SET_DEVICE_OP(dev_ops, modify_ah);
> > SET_DEVICE_OP(dev_ops, modify_cq);
> > SET_DEVICE_OP(dev_ops, modify_device); diff --git
> > a/drivers/infiniband/core/rdma_core.c
> > b/drivers/infiniband/core/rdma_core.c
> > index ccf4d069c25c..7166741834c8 100644
> > --- a/drivers/infiniband/core/rdma_core.c
> > +++ b/drivers/infiniband/core/rdma_core.c
> > @@ -817,6 +817,7 @@ static void ufile_destroy_ucontext(struct
> ib_uverbs_file *ufile,
> > rdma_restrack_del(&ucontext->res);
> >
> > ib_dev->ops.dealloc_ucontext(ucontext);
> > + rdma_user_mmap_entries_remove_free(ucontext);
> > kfree(ucontext);
> >
> > ufile->ucontext = NULL;
> > diff --git a/drivers/infiniband/core/uverbs_cmd.c
> > b/drivers/infiniband/core/uverbs_cmd.c
> > index 7ddd0e5bc6b3..44c0600245e4 100644
> > --- a/drivers/infiniband/core/uverbs_cmd.c
> > +++ b/drivers/infiniband/core/uverbs_cmd.c
> > @@ -254,6 +254,7 @@ static int ib_uverbs_get_context(struct
> > uverbs_attr_bundle *attrs)
> >
> > mutex_init(&ucontext->per_mm_list_lock);
> > INIT_LIST_HEAD(&ucontext->per_mm_list);
> > + xa_init(&ucontext->mmap_xa);
> >
> > ret = get_unused_fd_flags(O_CLOEXEC);
> > if (ret < 0)
> > diff --git a/drivers/infiniband/core/uverbs_main.c
> > b/drivers/infiniband/core/uverbs_main.c
> > index 11c13c1381cf..37507cc27e8c 100644
> > --- a/drivers/infiniband/core/uverbs_main.c
> > +++ b/drivers/infiniband/core/uverbs_main.c
> > @@ -965,6 +965,111 @@ int rdma_user_mmap_io(struct ib_ucontext
> > *ucontext, struct vm_area_struct *vma, }
> > EXPORT_SYMBOL(rdma_user_mmap_io);
> >
> > +static inline u64
> > +rdma_user_mmap_get_key(const struct rdma_user_mmap_entry
> *entry) {
> > + return (u64)entry->mmap_page << PAGE_SHIFT; }
> > +
> > +struct rdma_user_mmap_entry *
> > +rdma_user_mmap_entry_get(struct ib_ucontext *ucontext, u64 key, u64
> > +len) {
> > + struct rdma_user_mmap_entry *entry;
> > + u64 mmap_page;
> > +
> > + mmap_page = key >> PAGE_SHIFT;
> > + if (mmap_page > U32_MAX)
> > + return NULL;
> > +
> > + entry = xa_load(&ucontext->mmap_xa, mmap_page);
> > + if (!entry || rdma_user_mmap_get_key(entry) != key ||
> > + entry->length != len)
> > + return NULL;
> > +
> > + ibdev_dbg(ucontext->device,
> > + "mmap: obj[0x%p] key[%#llx] addr[%#llx] len[%#llx]
> removed\n",
> > + entry->obj, key, entry->address, entry->length);
> > +
> > + return entry;
> > +}
> > +EXPORT_SYMBOL(rdma_user_mmap_entry_get);
>
> Please add function description in kernel doc format for all newly
> EXPORT_SYMBOL() functions you introduced in RDMA/core.
Ok. Could you give me a reference to an example? Where should the
Documentation be added to?
>
> > +
> > +/*
> > + * Note this locking scheme cannot support removal of entries, except
> > +during
> > + * ucontext destruction when the core code guarentees no concurrency.
> > + */
> > +u64 rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext, void
> *obj,
> > + u64 address, u64 length, u8 mmap_flag) {
> > + struct rdma_user_mmap_entry *entry;
> > + u32 next_mmap_page;
> > + int err;
> > +
> > + entry = kmalloc(sizeof(*entry), GFP_KERNEL);
>
> It is worth to use kzalloc and not kmalloc.
>
> Thanks
^ permalink raw reply
* RE: [PATCH v5 rdma-next 1/6] RDMA/core: Create mmap database and cookie helper functions
From: Michal Kalderon @ 2019-07-09 10:26 UTC (permalink / raw)
To: Gal Pressman, Ariel Elior, jgg@ziepe.ca, dledford@redhat.com
Cc: linux-rdma@vger.kernel.org, davem@davemloft.net,
netdev@vger.kernel.org
In-Reply-To: <da67a821-1b26-c795-ff43-af17324f07e5@amazon.com>
> From: linux-rdma-owner@vger.kernel.org <linux-rdma-
> owner@vger.kernel.org> On Behalf Of Gal Pressman
>
> On 08/07/2019 12:14, Michal Kalderon wrote:
> > diff --git a/drivers/infiniband/core/device.c
> > b/drivers/infiniband/core/device.c
> > index 8a6ccb936dfe..a830c2c5d691 100644
> > --- a/drivers/infiniband/core/device.c
> > +++ b/drivers/infiniband/core/device.c
> > @@ -2521,6 +2521,7 @@ void ib_set_device_ops(struct ib_device *dev,
> const struct ib_device_ops *ops)
> > SET_DEVICE_OP(dev_ops, map_mr_sg_pi);
> > SET_DEVICE_OP(dev_ops, map_phys_fmr);
> > SET_DEVICE_OP(dev_ops, mmap);
> > + SET_DEVICE_OP(dev_ops, mmap_free);
> > SET_DEVICE_OP(dev_ops, modify_ah);
> > SET_DEVICE_OP(dev_ops, modify_cq);
> > SET_DEVICE_OP(dev_ops, modify_device); diff --git
> > a/drivers/infiniband/core/rdma_core.c
> > b/drivers/infiniband/core/rdma_core.c
> > index ccf4d069c25c..7166741834c8 100644
> > --- a/drivers/infiniband/core/rdma_core.c
> > +++ b/drivers/infiniband/core/rdma_core.c
> > @@ -817,6 +817,7 @@ static void ufile_destroy_ucontext(struct
> ib_uverbs_file *ufile,
> > rdma_restrack_del(&ucontext->res);
> >
> > ib_dev->ops.dealloc_ucontext(ucontext);
> > + rdma_user_mmap_entries_remove_free(ucontext);
>
> This should happen before dealloc_ucontext.
Right, will fix.
>
> > +struct rdma_user_mmap_entry *
> > +rdma_user_mmap_entry_get(struct ib_ucontext *ucontext, u64 key, u64
> > +len) {
> > + struct rdma_user_mmap_entry *entry;
> > + u64 mmap_page;
> > +
> > + mmap_page = key >> PAGE_SHIFT;
> > + if (mmap_page > U32_MAX)
> > + return NULL;
> > +
> > + entry = xa_load(&ucontext->mmap_xa, mmap_page);
> > + if (!entry || rdma_user_mmap_get_key(entry) != key ||
>
> I wonder if the 'rdma_user_mmap_get_key(entry) != key' check is still
> needed.
I guess it's not since the key is used to get the entry. I'll remove the check
>
> > +/*
> > + * This is only called when the ucontext is destroyed and there can
> > +be no
> > + * concurrent query via mmap or allocate on the xarray, thus we can
> > +be sure no
> > + * other thread is using the entry pointer. We also know that all the
> > +BAR
> > + * pages have either been zap'd or munmaped at this point. Normal
> > +pages are
> > + * refcounted and will be freed at the proper time.
> > + */
> > +void rdma_user_mmap_entries_remove_free(struct ib_ucontext
> *ucontext)
> > +{
> > + struct rdma_user_mmap_entry *entry;
> > + unsigned long mmap_page;
> > +
> > + xa_for_each(&ucontext->mmap_xa, mmap_page, entry) {
> > + xa_erase(&ucontext->mmap_xa, mmap_page);
> > +
> > + ibdev_dbg(ucontext->device,
> > + "mmap: obj[0x%p] key[%#llx] addr[%#llx] len[%#llx]
> removed\n",
> > + entry->obj, rdma_user_mmap_get_key(entry),
> > + entry->address, entry->length);
> > + if (ucontext->device->ops.mmap_free)
> > + ucontext->device->ops.mmap_free(entry->address,
> > + entry->length,
> > + entry->mmap_flag);
>
> Pass entry instead?
>
> > + kfree(entry);
> > + }
> > +}
> > +
> > void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) {
> > struct rdma_umap_priv *priv, *next_priv; diff --git
> > a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index
> > 26e9c2594913..54ce3fdae180 100644
> > --- a/include/rdma/ib_verbs.h
> > +++ b/include/rdma/ib_verbs.h
> > @@ -1425,6 +1425,8 @@ struct ib_ucontext {
> > * Implementation details of the RDMA core, don't use in drivers:
> > */
> > struct rdma_restrack_entry res;
> > + struct xarray mmap_xa;
> > + u32 mmap_xa_page;
> > };
> >
> > struct ib_uobject {
> > @@ -2311,6 +2313,7 @@ struct ib_device_ops {
> > struct ib_udata *udata);
> > void (*dealloc_ucontext)(struct ib_ucontext *context);
> > int (*mmap)(struct ib_ucontext *context, struct vm_area_struct
> > *vma);
> > + void (*mmap_free)(u64 address, u64 length, u8 mmap_flag);
>
> I feel like this callback needs some documentation.
>
> > void (*disassociate_ucontext)(struct ib_ucontext *ibcontext);
> > int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
> > void (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata); @@
> > -2706,9 +2709,23 @@ void ib_set_client_data(struct ib_device *device,
> > struct ib_client *client, void ib_set_device_ops(struct ib_device *device,
> > const struct ib_device_ops *ops);
> >
> > +#define RDMA_USER_MMAP_INVALID U64_MAX struct
> rdma_user_mmap_entry {
> > + void *obj;
>
> I know EFA is the culprit here, but please remove the extra space :).
>
> > + u64 address;
> > + u64 length;
> > + u32 mmap_page;
> > + u8 mmap_flag;
> > +};
> > +
^ permalink raw reply
* [PATCH v2 2/2] rtw88: pci: Use DMA sync instead of remapping in RX ISR
From: Jian-Hong Pan @ 2019-07-09 10:21 UTC (permalink / raw)
To: Yan-Hsuan Chuang, Kalle Valo, David S . Miller, Larry Finger,
David Laight
Cc: linux-wireless, netdev, linux-kernel, linux, Daniel Drake,
Jian-Hong Pan
In-Reply-To: <20190708063252.4756-1-jian-hong@endlessm.com>
Since each skb in RX ring is reused instead of new allocation, we can
treat the DMA in a more efficient way by DMA synchronization.
Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com>
---
drivers/net/wireless/realtek/rtw88/pci.c | 35 ++++++++++++++++++++++--
1 file changed, 32 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index e9fe3ad896c8..28ca76f71dfe 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -206,6 +206,35 @@ static int rtw_pci_reset_rx_desc(struct rtw_dev *rtwdev, struct sk_buff *skb,
return 0;
}
+static int rtw_pci_sync_rx_desc_cpu(struct rtw_dev *rtwdev, dma_addr_t dma)
+{
+ struct device *dev = rtwdev->dev;
+ int buf_sz = RTK_PCI_RX_BUF_SIZE;
+
+ dma_sync_single_for_cpu(dev, dma, buf_sz, PCI_DMA_FROMDEVICE);
+
+ return 0;
+}
+
+static int rtw_pci_sync_rx_desc_device(struct rtw_dev *rtwdev, dma_addr_t dma,
+ struct rtw_pci_rx_ring *rx_ring,
+ u32 idx, u32 desc_sz)
+{
+ struct device *dev = rtwdev->dev;
+ struct rtw_pci_rx_buffer_desc *buf_desc;
+ int buf_sz = RTK_PCI_RX_BUF_SIZE;
+
+ dma_sync_single_for_device(dev, dma, buf_sz, PCI_DMA_FROMDEVICE);
+
+ buf_desc = (struct rtw_pci_rx_buffer_desc *)(rx_ring->r.head +
+ idx * desc_sz);
+ memset(buf_desc, 0, sizeof(*buf_desc));
+ buf_desc->buf_size = cpu_to_le16(RTK_PCI_RX_BUF_SIZE);
+ buf_desc->dma = cpu_to_le32(dma);
+
+ return 0;
+}
+
static int rtw_pci_init_rx_ring(struct rtw_dev *rtwdev,
struct rtw_pci_rx_ring *rx_ring,
u8 desc_size, u32 len)
@@ -782,8 +811,7 @@ static void rtw_pci_rx_isr(struct rtw_dev *rtwdev, struct rtw_pci *rtwpci,
rtw_pci_dma_check(rtwdev, ring, cur_rp);
skb = ring->buf[cur_rp];
dma = *((dma_addr_t *)skb->cb);
- pci_unmap_single(rtwpci->pdev, dma, RTK_PCI_RX_BUF_SIZE,
- PCI_DMA_FROMDEVICE);
+ rtw_pci_sync_rx_desc_cpu(rtwdev, dma);
rx_desc = skb->data;
chip->ops->query_rx_desc(rtwdev, rx_desc, &pkt_stat, &rx_status);
@@ -818,7 +846,8 @@ static void rtw_pci_rx_isr(struct rtw_dev *rtwdev, struct rtw_pci *rtwpci,
next_rp:
/* new skb delivered to mac80211, re-enable original skb DMA */
- rtw_pci_reset_rx_desc(rtwdev, skb, ring, cur_rp, buf_desc_sz);
+ rtw_pci_sync_rx_desc_device(rtwdev, dma, ring, cur_rp,
+ buf_desc_sz);
/* host read next element in ring */
if (++cur_rp >= ring->r.len)
--
2.22.0
^ permalink raw reply related
* [PATCH v2 1/2] rtw88: pci: Rearrange the memory usage for skb in RX ISR
From: Jian-Hong Pan @ 2019-07-09 10:20 UTC (permalink / raw)
To: Yan-Hsuan Chuang, Kalle Valo, David S . Miller, Larry Finger,
David Laight
Cc: linux-wireless, netdev, linux-kernel, linux, Daniel Drake,
Jian-Hong Pan, stable
In-Reply-To: <20190708063252.4756-1-jian-hong@endlessm.com>
Testing with RTL8822BE hardware, when available memory is low, we
frequently see a kernel panic and system freeze.
First, rtw_pci_rx_isr encounters a memory allocation failure (trimmed):
rx routine starvation
WARNING: CPU: 7 PID: 9871 at drivers/net/wireless/realtek/rtw88/pci.c:822 rtw_pci_rx_isr.constprop.25+0x35a/0x370 [rtwpci]
[ 2356.580313] RIP: 0010:rtw_pci_rx_isr.constprop.25+0x35a/0x370 [rtwpci]
Then we see a variety of different error conditions and kernel panics,
such as this one (trimmed):
rtw_pci 0000:02:00.0: pci bus timeout, check dma status
skbuff: skb_over_panic: text:00000000091b6e66 len:415 put:415 head:00000000d2880c6f data:000000007a02b1ea tail:0x1df end:0xc0 dev:<NULL>
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:105!
invalid opcode: 0000 [#1] SMP NOPTI
RIP: 0010:skb_panic+0x43/0x45
When skb allocation fails and the "rx routine starvation" is hit, the
function returns immediately without updating the RX ring. At this
point, the RX ring may continue referencing an old skb which was already
handed off to ieee80211_rx_irqsafe(). When it comes to be used again,
bad things happen.
This patch allocates a new, data-sized skb first in RX ISR. After
copying the data in, we pass it to the upper layers. However, if skb
allocation fails, we effectively drop the frame. In both cases, the
original, full size ring skb is reused.
In addition, to fixing the kernel crash, the RX routine should now
generally behave better under low memory conditions.
Buglink: https://bugzilla.kernel.org/show_bug.cgi?id=204053
Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com>
Cc: <stable@vger.kernel.org>
---
drivers/net/wireless/realtek/rtw88/pci.c | 49 +++++++++++-------------
1 file changed, 22 insertions(+), 27 deletions(-)
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index cfe05ba7280d..e9fe3ad896c8 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -763,6 +763,7 @@ static void rtw_pci_rx_isr(struct rtw_dev *rtwdev, struct rtw_pci *rtwpci,
u32 pkt_offset;
u32 pkt_desc_sz = chip->rx_pkt_desc_sz;
u32 buf_desc_sz = chip->rx_buf_desc_sz;
+ u32 new_len;
u8 *rx_desc;
dma_addr_t dma;
@@ -790,40 +791,34 @@ static void rtw_pci_rx_isr(struct rtw_dev *rtwdev, struct rtw_pci *rtwpci,
pkt_offset = pkt_desc_sz + pkt_stat.drv_info_sz +
pkt_stat.shift;
- if (pkt_stat.is_c2h) {
- /* keep rx_desc, halmac needs it */
- skb_put(skb, pkt_stat.pkt_len + pkt_offset);
+ /* discard current skb if the new skb cannot be allocated as a
+ * new one in rx ring later
+ */
+ new_len = pkt_stat.pkt_len + pkt_offset;
+ new = dev_alloc_skb(new_len);
+ if (WARN_ONCE(!new, "rx routine starvation\n"))
+ goto next_rp;
+
+ /* put the DMA data including rx_desc from phy to new skb */
+ skb_put_data(new, skb->data, new_len);
- /* pass offset for further operation */
- *((u32 *)skb->cb) = pkt_offset;
- skb_queue_tail(&rtwdev->c2h_queue, skb);
+ if (pkt_stat.is_c2h) {
+ /* pass rx_desc & offset for further operation */
+ *((u32 *)new->cb) = pkt_offset;
+ skb_queue_tail(&rtwdev->c2h_queue, new);
ieee80211_queue_work(rtwdev->hw, &rtwdev->c2h_work);
} else {
- /* remove rx_desc, maybe use skb_pull? */
- skb_put(skb, pkt_stat.pkt_len);
- skb_reserve(skb, pkt_offset);
-
- /* alloc a smaller skb to mac80211 */
- new = dev_alloc_skb(pkt_stat.pkt_len);
- if (!new) {
- new = skb;
- } else {
- skb_put_data(new, skb->data, skb->len);
- dev_kfree_skb_any(skb);
- }
- /* TODO: merge into rx.c */
- rtw_rx_stats(rtwdev, pkt_stat.vif, skb);
+ /* remove rx_desc */
+ skb_pull(new, pkt_offset);
+
+ rtw_rx_stats(rtwdev, pkt_stat.vif, new);
memcpy(new->cb, &rx_status, sizeof(rx_status));
ieee80211_rx_irqsafe(rtwdev->hw, new);
}
- /* skb delivered to mac80211, alloc a new one in rx ring */
- new = dev_alloc_skb(RTK_PCI_RX_BUF_SIZE);
- if (WARN(!new, "rx routine starvation\n"))
- return;
-
- ring->buf[cur_rp] = new;
- rtw_pci_reset_rx_desc(rtwdev, new, ring, cur_rp, buf_desc_sz);
+next_rp:
+ /* new skb delivered to mac80211, re-enable original skb DMA */
+ rtw_pci_reset_rx_desc(rtwdev, skb, ring, cur_rp, buf_desc_sz);
/* host read next element in ring */
if (++cur_rp >= ring->r.len)
--
2.22.0
^ permalink raw reply related
* Re: [PATCH v2 05/10] net: hisilicon: HI13X1_GMAX need dreq reset at first
From: Sergei Shtylyov @ 2019-07-09 9:35 UTC (permalink / raw)
To: Jiangfeng Xiao, davem, robh+dt, yisen.zhuang, salil.mehta,
mark.rutland, dingtianhong
Cc: netdev, devicetree, linux-kernel, leeyou.li, nixiaoming,
jianping.liu, xiekunxun
In-Reply-To: <1562643071-46811-6-git-send-email-xiaojiangfeng@huawei.com>
Hello!
On 09.07.2019 6:31, Jiangfeng Xiao wrote:
> HI13X1_GMAC delete request for soft reset at first,
> otherwise, the subsequent initialization will not
> take effect.
>
> Signed-off-by: Jiangfeng Xiao <xiaojiangfeng@huawei.com>
> ---
> drivers/net/ethernet/hisilicon/hip04_eth.c | 24 ++++++++++++++++++++++++
> 1 file changed, 24 insertions(+)
>
> diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
> index fe61b01..19d8cfd 100644
> --- a/drivers/net/ethernet/hisilicon/hip04_eth.c
> +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
[...]
> @@ -853,6 +867,15 @@ static int hip04_mac_probe(struct platform_device *pdev)
> goto init_fail;
> }
>
> +#if defined(CONFIG_HI13X1_GMAC)
> + res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
> + priv->sysctrl_base = devm_ioremap_resource(d, res);
There's devm_platform_ioremap_resource() now.
> + if (IS_ERR(priv->sysctrl_base)) {
> + ret = PTR_ERR(priv->sysctrl_base);
> + goto init_fail;
> + }
> +#endif
> +
> ret = of_parse_phandle_with_fixed_args(node, "port-handle", 2, 0, &arg);
> if (ret < 0) {
> dev_warn(d, "no port-handle\n");
[...]
MBR, Sergei
^ permalink raw reply
* Re: [PATCH v5 rdma-next 2/6] RDMA/efa: Use the common mmap_xa helpers
From: Gal Pressman @ 2019-07-09 9:02 UTC (permalink / raw)
To: Michal Kalderon, ariel.elior, jgg, dledford, galpress
Cc: linux-rdma, davem, netdev
In-Reply-To: <20190708091503.14723-3-michal.kalderon@marvell.com>
On 08/07/2019 12:14, Michal Kalderon wrote:
Hi, a few nits:
> Remove the functions related to managing the mmap_xa database.
> This code was copied to the ib_core. Use the common API's instead.
>
> Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
> ---
> drivers/infiniband/hw/efa/efa.h | 3 +-
> drivers/infiniband/hw/efa/efa_main.c | 1 +
> drivers/infiniband/hw/efa/efa_verbs.c | 183 ++++++++--------------------------
> 3 files changed, 42 insertions(+), 145 deletions(-)
> diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
> index df77bc312a25..5dff892da161 100644
> --- a/drivers/infiniband/hw/efa/efa_verbs.c
> +++ b/drivers/infiniband/hw/efa/efa_verbs.c
> @@ -13,34 +13,15 @@
>
> #include "efa.h"
>
> -#define EFA_MMAP_FLAG_SHIFT 56
> -#define EFA_MMAP_PAGE_MASK GENMASK(EFA_MMAP_FLAG_SHIFT - 1, 0)
> -#define EFA_MMAP_INVALID U64_MAX
> -
Don't delete the blank line please.
> enum {
> EFA_MMAP_DMA_PAGE = 0,
> EFA_MMAP_IO_WC,
> EFA_MMAP_IO_NC,
> };
> -
> #define EFA_AENQ_ENABLED_GROUPS \
> (BIT(EFA_ADMIN_FATAL_ERROR) | BIT(EFA_ADMIN_WARNING) | \
> BIT(EFA_ADMIN_NOTIFICATION) | BIT(EFA_ADMIN_KEEP_ALIVE))
>
> -struct efa_mmap_entry {
> - void *obj;
> - u64 address;
> - u64 length;
> - u32 mmap_page;
> - u8 mmap_flag;
> -};
> -
> -static inline u64 get_mmap_key(const struct efa_mmap_entry *efa)
> -{
> - return ((u64)efa->mmap_flag << EFA_MMAP_FLAG_SHIFT) |
> - ((u64)efa->mmap_page << PAGE_SHIFT);
> -}
> -
> #define EFA_CHUNK_PAYLOAD_SHIFT 12
> #define EFA_CHUNK_PAYLOAD_SIZE BIT(EFA_CHUNK_PAYLOAD_SHIFT)
> #define EFA_CHUNK_PAYLOAD_PTR_SIZE 8
> @@ -145,105 +126,7 @@ static void *efa_zalloc_mapped(struct efa_dev *dev, dma_addr_t *dma_addr,
> return addr;
> }
>
> -/*
> - * This is only called when the ucontext is destroyed and there can be no
> - * concurrent query via mmap or allocate on the xarray, thus we can be sure no
> - * other thread is using the entry pointer. We also know that all the BAR
> - * pages have either been zap'd or munmaped at this point. Normal pages are
> - * refcounted and will be freed at the proper time.
> - */
> -static void mmap_entries_remove_free(struct efa_dev *dev,
> - struct efa_ucontext *ucontext)
> -{
> - struct efa_mmap_entry *entry;
> - unsigned long mmap_page;
>
> - xa_for_each(&ucontext->mmap_xa, mmap_page, entry) {
> - xa_erase(&ucontext->mmap_xa, mmap_page);
> -
> - ibdev_dbg(
> - &dev->ibdev,
> - "mmap: obj[0x%p] key[%#llx] addr[%#llx] len[%#llx] removed\n",
> - entry->obj, get_mmap_key(entry), entry->address,
> - entry->length);
> - if (entry->mmap_flag == EFA_MMAP_DMA_PAGE)
> - /* DMA mapping is already gone, now free the pages */
> - free_pages_exact(phys_to_virt(entry->address),
> - entry->length);
> - kfree(entry);
> - }
> -}
> -
> -static struct efa_mmap_entry *mmap_entry_get(struct efa_dev *dev,
> - struct efa_ucontext *ucontext,
> - u64 key, u64 len)
> -{
> - struct efa_mmap_entry *entry;
> - u64 mmap_page;
> -
> - mmap_page = (key & EFA_MMAP_PAGE_MASK) >> PAGE_SHIFT;
> - if (mmap_page > U32_MAX)
> - return NULL;
> -
> - entry = xa_load(&ucontext->mmap_xa, mmap_page);
> - if (!entry || get_mmap_key(entry) != key || entry->length != len)
> - return NULL;
> -
> - ibdev_dbg(&dev->ibdev,
> - "mmap: obj[0x%p] key[%#llx] addr[%#llx] len[%#llx] removed\n",
> - entry->obj, key, entry->address, entry->length);
> -
> - return entry;
> -}
> -
> -/*
> - * Note this locking scheme cannot support removal of entries, except during
> - * ucontext destruction when the core code guarentees no concurrency.
> - */
> -static u64 mmap_entry_insert(struct efa_dev *dev, struct efa_ucontext *ucontext,
> - void *obj, u64 address, u64 length, u8 mmap_flag)
> -{
> - struct efa_mmap_entry *entry;
> - u32 next_mmap_page;
> - int err;
> -
> - entry = kmalloc(sizeof(*entry), GFP_KERNEL);
> - if (!entry)
> - return EFA_MMAP_INVALID;
> -
> - entry->obj = obj;
> - entry->address = address;
> - entry->length = length;
> - entry->mmap_flag = mmap_flag;
> -
> - xa_lock(&ucontext->mmap_xa);
> - if (check_add_overflow(ucontext->mmap_xa_page,
> - (u32)(length >> PAGE_SHIFT),
> - &next_mmap_page))
> - goto err_unlock;
> -
> - entry->mmap_page = ucontext->mmap_xa_page;
> - ucontext->mmap_xa_page = next_mmap_page;
> - err = __xa_insert(&ucontext->mmap_xa, entry->mmap_page, entry,
> - GFP_KERNEL);
> - if (err)
> - goto err_unlock;
> -
> - xa_unlock(&ucontext->mmap_xa);
> -
> - ibdev_dbg(
> - &dev->ibdev,
> - "mmap: obj[0x%p] addr[%#llx], len[%#llx], key[%#llx] inserted\n",
> - entry->obj, entry->address, entry->length, get_mmap_key(entry));
> -
> - return get_mmap_key(entry);
> -
> -err_unlock:
> - xa_unlock(&ucontext->mmap_xa);
> - kfree(entry);
> - return EFA_MMAP_INVALID;
> -
> -}
>
You left two extra blank lines between efa_zalloc_mapped and efa_query_device.
> int efa_query_device(struct ib_device *ibdev,
> struct ib_device_attr *props,
> @@ -488,45 +371,52 @@ static int qp_mmap_entries_setup(struct efa_qp *qp,
> struct efa_com_create_qp_params *params,
> struct efa_ibv_create_qp_resp *resp)
> {
> + u64 address;
> + u64 length;
Line break.
> /*
> * Once an entry is inserted it might be mmapped, hence cannot be
> * cleaned up until dealloc_ucontext.
> */
> resp->sq_db_mmap_key =
> - mmap_entry_insert(dev, ucontext, qp,
> - dev->db_bar_addr + resp->sq_db_offset,
> - PAGE_SIZE, EFA_MMAP_IO_NC);
> - if (resp->sq_db_mmap_key == EFA_MMAP_INVALID)
> + rdma_user_mmap_entry_insert(&ucontext->ibucontext, qp,
> + dev->db_bar_addr +
> + resp->sq_db_offset,
> + PAGE_SIZE, EFA_MMAP_IO_NC);
> + if (resp->sq_db_mmap_key == RDMA_USER_MMAP_INVALID)
> return -ENOMEM;
>
> resp->sq_db_offset &= ~PAGE_MASK;
>
> + address = dev->mem_bar_addr + resp->llq_desc_offset;
> + length = PAGE_ALIGN(params->sq_ring_size_in_bytes +
> + (resp->llq_desc_offset & ~PAGE_MASK));
> resp->llq_desc_mmap_key =
> - mmap_entry_insert(dev, ucontext, qp,
> - dev->mem_bar_addr + resp->llq_desc_offset,
> - PAGE_ALIGN(params->sq_ring_size_in_bytes +
> - (resp->llq_desc_offset & ~PAGE_MASK)),
> - EFA_MMAP_IO_WC);
> - if (resp->llq_desc_mmap_key == EFA_MMAP_INVALID)
> + rdma_user_mmap_entry_insert(&ucontext->ibucontext, qp,
> + address,
> + length,
> + EFA_MMAP_IO_WC);
> + if (resp->llq_desc_mmap_key == RDMA_USER_MMAP_INVALID)
> return -ENOMEM;
>
> resp->llq_desc_offset &= ~PAGE_MASK;
>
> if (qp->rq_size) {
> + address = dev->db_bar_addr + resp->rq_db_offset;
> resp->rq_db_mmap_key =
> - mmap_entry_insert(dev, ucontext, qp,
> - dev->db_bar_addr + resp->rq_db_offset,
> - PAGE_SIZE, EFA_MMAP_IO_NC);
> - if (resp->rq_db_mmap_key == EFA_MMAP_INVALID)
> + rdma_user_mmap_entry_insert(&ucontext->ibucontext, qp,
> + address, PAGE_SIZE,
> + EFA_MMAP_IO_NC);
> + if (resp->rq_db_mmap_key == RDMA_USER_MMAP_INVALID)
> return -ENOMEM;
>
> resp->rq_db_offset &= ~PAGE_MASK;
>
> + address = virt_to_phys(qp->rq_cpu_addr);
> resp->rq_mmap_key =
> - mmap_entry_insert(dev, ucontext, qp,
> - virt_to_phys(qp->rq_cpu_addr),
> - qp->rq_size, EFA_MMAP_DMA_PAGE);
> - if (resp->rq_mmap_key == EFA_MMAP_INVALID)
> + rdma_user_mmap_entry_insert(&ucontext->ibucontext, qp,
> + address, qp->rq_size,
> + EFA_MMAP_DMA_PAGE);
> + if (resp->rq_mmap_key == RDMA_USER_MMAP_INVALID)
> return -ENOMEM;
>
> resp->rq_mmap_size = qp->rq_size;
> @@ -875,11 +765,13 @@ void efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
> static int cq_mmap_entries_setup(struct efa_dev *dev, struct efa_cq *cq,
> struct efa_ibv_create_cq_resp *resp)
> {
> + struct efa_ucontext *ucontext = cq->ucontext;
Line break.
> resp->q_mmap_size = cq->size;
> - resp->q_mmap_key = mmap_entry_insert(dev, cq->ucontext, cq,
> - virt_to_phys(cq->cpu_addr),
> - cq->size, EFA_MMAP_DMA_PAGE);
> - if (resp->q_mmap_key == EFA_MMAP_INVALID)
> + resp->q_mmap_key =
> + rdma_user_mmap_entry_insert(&ucontext->ibucontext, cq,
> + virt_to_phys(cq->cpu_addr),
> + cq->size, EFA_MMAP_DMA_PAGE);
> + if (resp->q_mmap_key == RDMA_USER_MMAP_INVALID)
> return -ENOMEM;
>
> return 0;
> @@ -1531,7 +1423,6 @@ int efa_alloc_ucontext(struct ib_ucontext *ibucontext, struct ib_udata *udata)
> goto err_out;
>
> ucontext->uarn = result.uarn;
> - xa_init(&ucontext->mmap_xa);
>
> resp.cmds_supp_udata_mask |= EFA_USER_CMDS_SUPP_UDATA_QUERY_DEVICE;
> resp.cmds_supp_udata_mask |= EFA_USER_CMDS_SUPP_UDATA_CREATE_AH;
> @@ -1560,19 +1451,25 @@ void efa_dealloc_ucontext(struct ib_ucontext *ibucontext)
> struct efa_ucontext *ucontext = to_eucontext(ibucontext);
> struct efa_dev *dev = to_edev(ibucontext->device);
>
> - mmap_entries_remove_free(dev, ucontext);
> efa_dealloc_uar(dev, ucontext->uarn);
> }
>
> +void efa_mmap_free(u64 address, u64 length, u8 mmap_flag)
> +{
> + /* DMA mapping is already gone, now free the pages */
> + if (mmap_flag == EFA_MMAP_DMA_PAGE)
> + free_pages_exact(phys_to_virt(address), length);
> +}
> +
> static int __efa_mmap(struct efa_dev *dev, struct efa_ucontext *ucontext,
> struct vm_area_struct *vma, u64 key, u64 length)
> {
> - struct efa_mmap_entry *entry;
> + struct rdma_user_mmap_entry *entry;
> unsigned long va;
> u64 pfn;
> int err;
>
> - entry = mmap_entry_get(dev, ucontext, key, length);
> + entry = rdma_user_mmap_entry_get(&ucontext->ibucontext, key, length);
> if (!entry) {
> ibdev_dbg(&dev->ibdev, "key[%#llx] does not have valid entry\n",
> key);
>
^ permalink raw reply
* Re: Re: linux-next: build failure after merge of the net-next tree
From: Bernard Metzler @ 2019-07-09 9:00 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Stephen Rothwell, Doug Ledford, Jason Gunthorpe, David Miller,
Networking, Linux Next Mailing List, Linux Kernel Mailing List
In-Reply-To: <20190709064346.GF7034@mtr-leonro.mtl.com>
-----"Leon Romanovsky" <leon@kernel.org> wrote: -----
>To: "Stephen Rothwell" <sfr@canb.auug.org.au>
>From: "Leon Romanovsky" <leon@kernel.org>
>Date: 07/09/2019 08:43AM
>Cc: "Doug Ledford" <dledford@redhat.com>, "Jason Gunthorpe"
><jgg@mellanox.com>, "David Miller" <davem@davemloft.net>,
>"Networking" <netdev@vger.kernel.org>, "Linux Next Mailing List"
><linux-next@vger.kernel.org>, "Linux Kernel Mailing List"
><linux-kernel@vger.kernel.org>, "Bernard Metzler"
><bmt@zurich.ibm.com>
>Subject: [EXTERNAL] Re: linux-next: build failure after merge of the
>net-next tree
>
>On Tue, Jul 09, 2019 at 01:56:36PM +1000, Stephen Rothwell wrote:
>> Hi all,
>>
>> After merging the net-next tree, today's linux-next build (x86_64
>> allmodconfig) failed like this:
>>
>> drivers/infiniband/sw/siw/siw_cm.c: In function
>'siw_create_listen':
>> drivers/infiniband/sw/siw/siw_cm.c:1978:3: error: implicit
>declaration of function 'for_ifa'; did you mean 'fork_idle'?
>[-Werror=implicit-function-declaration]
>> for_ifa(in_dev)
>> ^~~~~~~
>> fork_idle
>> drivers/infiniband/sw/siw/siw_cm.c:1978:18: error: expected ';'
>before '{' token
>> for_ifa(in_dev)
>> ^
>> ;
>> {
>> ~
>>
>> Caused by commit
>>
>> 6c52fdc244b5 ("rdma/siw: connection management")
>>
>> from the rdma tree. I don't know why this didn't fail after I
>mereged
>> that tree.
>
>I had the same question, because I have this fix for a couple of days
>already.
>
>From 56c9e15ec670af580daa8c3ffde9503af3042d67 Mon Sep 17 00:00:00
>2001
>From: Leon Romanovsky <leonro@mellanox.com>
>Date: Sun, 7 Jul 2019 10:43:42 +0300
>Subject: [PATCH] Fixup to build SIW issue
>
>Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
>---
> drivers/infiniband/sw/siw/siw_cm.c | 5 ++---
> 1 file changed, 2 insertions(+), 3 deletions(-)
>
>diff --git a/drivers/infiniband/sw/siw/siw_cm.c
>b/drivers/infiniband/sw/siw/siw_cm.c
>index 8e618cb7261f..c883bf514341 100644
>--- a/drivers/infiniband/sw/siw/siw_cm.c
>+++ b/drivers/infiniband/sw/siw/siw_cm.c
>@@ -1954,6 +1954,7 @@ static void siw_drop_listeners(struct iw_cm_id
>*id)
> int siw_create_listen(struct iw_cm_id *id, int backlog)
> {
> struct net_device *dev = to_siw_dev(id->device)->netdev;
>+ const struct in_ifaddr *ifa;
> int rv = 0, listeners = 0;
>
> siw_dbg(id->device, "id 0x%p: backlog %d\n", id, backlog);
>@@ -1975,8 +1976,7 @@ int siw_create_listen(struct iw_cm_id *id, int
>backlog)
> id, &s_laddr.sin_addr, ntohs(s_laddr.sin_port),
> &s_raddr->sin_addr, ntohs(s_raddr->sin_port));
>
>- for_ifa(in_dev)
>- {
>+ in_dev_for_each_ifa_rcu(ifa, in_dev) {
> if (ipv4_is_zeronet(s_laddr.sin_addr.s_addr) ||
> s_laddr.sin_addr.s_addr == ifa->ifa_address) {
> s_laddr.sin_addr.s_addr = ifa->ifa_address;
>@@ -1988,7 +1988,6 @@ int siw_create_listen(struct iw_cm_id *id, int
>backlog)
> listeners++;
> }
> }
>- endfor_ifa(in_dev);
> in_dev_put(in_dev);
> } else if (id->local_addr.ss_family == AF_INET6) {
> struct inet6_dev *in6_dev = in6_dev_get(dev);
>--
>2.21.0
>
>
>>
>> I have marked that driver as depending on BROKEN for today.
>>
>> --
>> Cheers,
>> Stephen Rothwell
>
>
>
I am very sorry for that issues. Things are moving fast, and I
didn't realize 'for_ifa' recently went away. I agree with Leon,
his patch fixes the issue. So, please, let's apply that one.
Leon, many thanks for providing the fix.
Thanks very much,
Bernard.
^ permalink raw reply
* Re: [PATCH 0/2] forcedeth: recv cache support
From: Yanjun Zhu @ 2019-07-09 8:28 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20190708.152352.710464914281100209.davem@davemloft.net>
On 2019/7/9 6:23, David Miller wrote:
> From: Zhu Yanjun <yanjun.zhu@oracle.com>
> Date: Fri, 5 Jul 2019 02:19:26 -0400
>
>> This recv cache is to make NIC work steadily when the system memory is
>> not enough.
> The system is supposed to hold onto enough atomic memory to absorb all
> reasonable situations like this.
>
> If anything a solution to this problem belongs generically somewhere,
> not in a driver. And furthermore looping over an allocation attempt
> with a delay is strongly discouraged.
Thanks a lot for your suggestions. Now a user is testing this patch in
LAB and production hosts.
After this patch can pass tests, I will send V2 based on your suggestions.
Thanks,
Zhu Yanjun
^ permalink raw reply
* [PATCH net-next v4 1/3] net: stmmac: Implement RX Coalesce Frames setting
From: Jose Abreu @ 2019-07-09 8:02 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel, Jakub Kicinski
In-Reply-To: <cover.1562659012.git.joabreu@synopsys.com>
Add support for coalescing RX path by specifying number of frames which
don't need to have interrupt on completion bit set.
This is only available when RX Watchdog is enabled.
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
---
drivers/net/ethernet/stmicro/stmmac/common.h | 1 +
drivers/net/ethernet/stmicro/stmmac/stmmac.h | 2 ++
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 7 +++++--
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 18 ++++++++++++------
4 files changed, 20 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 2403a65167b2..dfd47fdfa447 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -252,6 +252,7 @@ struct stmmac_safety_stats {
#define STMMAC_MAX_COAL_TX_TICK 100000
#define STMMAC_TX_MAX_FRAMES 256
#define STMMAC_TX_FRAMES 1
+#define STMMAC_RX_FRAMES 25
/* Packets types */
enum packets_types {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 123898235cb0..513f4e2df5f6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -55,6 +55,7 @@ struct stmmac_tx_queue {
};
struct stmmac_rx_queue {
+ u32 rx_count_frames;
u32 queue_index;
struct stmmac_priv *priv_data;
struct dma_extended_desc *dma_erx;
@@ -110,6 +111,7 @@ struct stmmac_priv {
/* Frequently used values are kept adjacent for cache effect */
u32 tx_coal_frames;
u32 tx_coal_timer;
+ u32 rx_coal_frames;
int tx_coalesce;
int hwts_tx_en;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index cfd93eefb50e..6efb66820d4c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -701,8 +701,10 @@ static int stmmac_get_coalesce(struct net_device *dev,
ec->tx_coalesce_usecs = priv->tx_coal_timer;
ec->tx_max_coalesced_frames = priv->tx_coal_frames;
- if (priv->use_riwt)
+ if (priv->use_riwt) {
+ ec->rx_max_coalesced_frames = priv->rx_coal_frames;
ec->rx_coalesce_usecs = stmmac_riwt2usec(priv->rx_riwt, priv);
+ }
return 0;
}
@@ -715,7 +717,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
unsigned int rx_riwt;
/* Check not supported parameters */
- if ((ec->rx_max_coalesced_frames) || (ec->rx_coalesce_usecs_irq) ||
+ if ((ec->rx_coalesce_usecs_irq) ||
(ec->rx_max_coalesced_frames_irq) || (ec->tx_coalesce_usecs_irq) ||
(ec->use_adaptive_rx_coalesce) || (ec->use_adaptive_tx_coalesce) ||
(ec->pkt_rate_low) || (ec->rx_coalesce_usecs_low) ||
@@ -749,6 +751,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
/* Only copy relevant parameters, ignore all others. */
priv->tx_coal_frames = ec->tx_max_coalesced_frames;
priv->tx_coal_timer = ec->tx_coalesce_usecs;
+ priv->rx_coal_frames = ec->rx_max_coalesced_frames;
priv->rx_riwt = rx_riwt;
stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index bdedde99148a..c142e9367a68 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2268,20 +2268,21 @@ static void stmmac_tx_timer(struct timer_list *t)
}
/**
- * stmmac_init_tx_coalesce - init tx mitigation options.
+ * stmmac_init_coalesce - init mitigation options.
* @priv: driver private structure
* Description:
- * This inits the transmit coalesce parameters: i.e. timer rate,
+ * This inits the coalesce parameters: i.e. timer rate,
* timer handler and default threshold used for enabling the
* interrupt on completion bit.
*/
-static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
+static void stmmac_init_coalesce(struct stmmac_priv *priv)
{
u32 tx_channel_count = priv->plat->tx_queues_to_use;
u32 chan;
priv->tx_coal_frames = STMMAC_TX_FRAMES;
priv->tx_coal_timer = STMMAC_COAL_TX_TIMER;
+ priv->rx_coal_frames = STMMAC_RX_FRAMES;
for (chan = 0; chan < tx_channel_count; chan++) {
struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
@@ -2651,7 +2652,7 @@ static int stmmac_open(struct net_device *dev)
goto init_error;
}
- stmmac_init_tx_coalesce(priv);
+ stmmac_init_coalesce(priv);
phylink_start(priv->phylink);
@@ -3289,6 +3290,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
while (dirty-- > 0) {
struct dma_desc *p;
+ bool use_rx_wd;
if (priv->extend_desc)
p = (struct dma_desc *)(rx_q->dma_erx + entry);
@@ -3331,7 +3333,11 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
}
dma_wmb();
- stmmac_set_rx_owner(priv, p, priv->use_riwt);
+ rx_q->rx_count_frames++;
+ rx_q->rx_count_frames %= priv->rx_coal_frames;
+ use_rx_wd = priv->use_riwt && rx_q->rx_count_frames;
+
+ stmmac_set_rx_owner(priv, p, use_rx_wd);
dma_wmb();
@@ -4631,7 +4637,7 @@ int stmmac_resume(struct device *dev)
stmmac_clear_descriptors(priv);
stmmac_hw_setup(ndev, false);
- stmmac_init_tx_coalesce(priv);
+ stmmac_init_coalesce(priv);
stmmac_set_rx_mode(ndev);
stmmac_enable_all_queues(priv);
--
2.7.4
^ permalink raw reply related
* [PATCH net-next v4 2/3] net: stmmac: Fix descriptors address being in > 32 bits address space
From: Jose Abreu @ 2019-07-09 8:02 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, Maxime Ripard, Chen-Yu Tsai,
linux-stm32, linux-arm-kernel, linux-kernel
In-Reply-To: <cover.1562659012.git.joabreu@synopsys.com>
Commit a993db88d17d ("net: stmmac: Enable support for > 32 Bits
addressing in XGMAC"), introduced support for > 32 bits addressing in
XGMAC but the conversion of descriptors to dma_addr_t was left out.
As some devices assing coherent memory in regions > 32 bits we need to
set lower and upper value of descriptors address when initializing DMA
channels.
Luckly, this was working for me because I was assigning CMA to < 4GB
address space for performance reasons.
Fixes: a993db88d17d ("net: stmmac: Enable support for > 32 Bits addressing in XGMAC")
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: Maxime Ripard <maxime.ripard@bootlin.com>
Cc: Chen-Yu Tsai <wens@csie.org>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 8 ++++----
drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 8 ++++----
drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c | 8 ++++----
drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c | 8 ++++----
drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h | 2 ++
drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 10 ++++++----
drivers/net/ethernet/stmicro/stmmac/hwif.h | 4 ++--
7 files changed, 26 insertions(+), 22 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 6d5cba4075eb..2856f3fe5266 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -289,18 +289,18 @@ static void sun8i_dwmac_dma_init(void __iomem *ioaddr,
static void sun8i_dwmac_dma_init_rx(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_rx_phy, u32 chan)
+ dma_addr_t dma_rx_phy, u32 chan)
{
/* Write RX descriptors address */
- writel(dma_rx_phy, ioaddr + EMAC_RX_DESC_LIST);
+ writel(lower_32_bits(dma_rx_phy), ioaddr + EMAC_RX_DESC_LIST);
}
static void sun8i_dwmac_dma_init_tx(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx_phy, u32 chan)
+ dma_addr_t dma_tx_phy, u32 chan)
{
/* Write TX descriptors address */
- writel(dma_tx_phy, ioaddr + EMAC_TX_DESC_LIST);
+ writel(lower_32_bits(dma_tx_phy), ioaddr + EMAC_TX_DESC_LIST);
}
/* sun8i_dwmac_dump_regs() - Dump EMAC address space
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index 1fdedf77678f..2bac49b49f73 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -112,18 +112,18 @@ static void dwmac1000_dma_init(void __iomem *ioaddr,
static void dwmac1000_dma_init_rx(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_rx_phy, u32 chan)
+ dma_addr_t dma_rx_phy, u32 chan)
{
/* RX descriptor base address list must be written into DMA CSR3 */
- writel(dma_rx_phy, ioaddr + DMA_RCV_BASE_ADDR);
+ writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_RCV_BASE_ADDR);
}
static void dwmac1000_dma_init_tx(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx_phy, u32 chan)
+ dma_addr_t dma_tx_phy, u32 chan)
{
/* TX descriptor base address list must be written into DMA CSR4 */
- writel(dma_tx_phy, ioaddr + DMA_TX_BASE_ADDR);
+ writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_TX_BASE_ADDR);
}
static u32 dwmac1000_configure_fc(u32 csr6, int rxfifosz)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
index c980cc7360a4..8f0d9bc7cab5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
@@ -31,18 +31,18 @@ static void dwmac100_dma_init(void __iomem *ioaddr,
static void dwmac100_dma_init_rx(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_rx_phy, u32 chan)
+ dma_addr_t dma_rx_phy, u32 chan)
{
/* RX descriptor base addr lists must be written into DMA CSR3 */
- writel(dma_rx_phy, ioaddr + DMA_RCV_BASE_ADDR);
+ writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_RCV_BASE_ADDR);
}
static void dwmac100_dma_init_tx(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx_phy, u32 chan)
+ dma_addr_t dma_tx_phy, u32 chan)
{
/* TX descriptor base addr lists must be written into DMA CSR4 */
- writel(dma_tx_phy, ioaddr + DMA_TX_BASE_ADDR);
+ writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_TX_BASE_ADDR);
}
/* Store and Forward capability is not used at all.
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index 0f208e13da9f..6cbcdaea55f6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -70,7 +70,7 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
static void dwmac4_dma_init_rx_chan(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_rx_phy, u32 chan)
+ dma_addr_t dma_rx_phy, u32 chan)
{
u32 value;
u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
@@ -79,12 +79,12 @@ static void dwmac4_dma_init_rx_chan(void __iomem *ioaddr,
value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
- writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(chan));
+ writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_CHAN_RX_BASE_ADDR(chan));
}
static void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx_phy, u32 chan)
+ dma_addr_t dma_tx_phy, u32 chan)
{
u32 value;
u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
@@ -97,7 +97,7 @@ static void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
- writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
+ writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
}
static void dwmac4_dma_init_channel(void __iomem *ioaddr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 9a9792527530..7f86dffb264d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -199,7 +199,9 @@
#define XGMAC_RxPBL GENMASK(21, 16)
#define XGMAC_RxPBL_SHIFT 16
#define XGMAC_RXST BIT(0)
+#define XGMAC_DMA_CH_TxDESC_HADDR(x) (0x00003110 + (0x80 * (x)))
#define XGMAC_DMA_CH_TxDESC_LADDR(x) (0x00003114 + (0x80 * (x)))
+#define XGMAC_DMA_CH_RxDESC_HADDR(x) (0x00003118 + (0x80 * (x)))
#define XGMAC_DMA_CH_RxDESC_LADDR(x) (0x0000311c + (0x80 * (x)))
#define XGMAC_DMA_CH_TxDESC_TAIL_LPTR(x) (0x00003124 + (0x80 * (x)))
#define XGMAC_DMA_CH_RxDESC_TAIL_LPTR(x) (0x0000312c + (0x80 * (x)))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 229c58758cbd..a4f236e3593e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -44,7 +44,7 @@ static void dwxgmac2_dma_init_chan(void __iomem *ioaddr,
static void dwxgmac2_dma_init_rx_chan(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_rx_phy, u32 chan)
+ dma_addr_t phy, u32 chan)
{
u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
u32 value;
@@ -54,12 +54,13 @@ static void dwxgmac2_dma_init_rx_chan(void __iomem *ioaddr,
value |= (rxpbl << XGMAC_RxPBL_SHIFT) & XGMAC_RxPBL;
writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
- writel(dma_rx_phy, ioaddr + XGMAC_DMA_CH_RxDESC_LADDR(chan));
+ writel(upper_32_bits(phy), ioaddr + XGMAC_DMA_CH_RxDESC_HADDR(chan));
+ writel(lower_32_bits(phy), ioaddr + XGMAC_DMA_CH_RxDESC_LADDR(chan));
}
static void dwxgmac2_dma_init_tx_chan(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx_phy, u32 chan)
+ dma_addr_t phy, u32 chan)
{
u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
u32 value;
@@ -70,7 +71,8 @@ static void dwxgmac2_dma_init_tx_chan(void __iomem *ioaddr,
value |= XGMAC_OSP;
writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
- writel(dma_tx_phy, ioaddr + XGMAC_DMA_CH_TxDESC_LADDR(chan));
+ writel(upper_32_bits(phy), ioaddr + XGMAC_DMA_CH_TxDESC_HADDR(chan));
+ writel(lower_32_bits(phy), ioaddr + XGMAC_DMA_CH_TxDESC_LADDR(chan));
}
static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 2acfbc70e3c8..278c0dbec9d9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -150,10 +150,10 @@ struct stmmac_dma_ops {
struct stmmac_dma_cfg *dma_cfg, u32 chan);
void (*init_rx_chan)(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_rx_phy, u32 chan);
+ dma_addr_t phy, u32 chan);
void (*init_tx_chan)(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx_phy, u32 chan);
+ dma_addr_t phy, u32 chan);
/* Configure the AXI Bus Mode Register */
void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi);
/* Dump DMA registers */
--
2.7.4
^ permalink raw reply related
* [PATCH net-next v4 0/3] net: stmmac: Some improvements and a fix
From: Jose Abreu @ 2019-07-09 8:02 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, Maxime Ripard, Chen-Yu Tsai,
linux-stm32, linux-arm-kernel, linux-kernel
Some performace improvements (01/03 and 03/03) and a fix (02/03), all for -next.
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: Maxime Ripard <maxime.ripard@bootlin.com>
Cc: Chen-Yu Tsai <wens@csie.org>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
Jose Abreu (3):
net: stmmac: Implement RX Coalesce Frames setting
net: stmmac: Fix descriptors address being in > 32 bits address space
net: stmmac: Introducing support for Page Pool
drivers/net/ethernet/stmicro/stmmac/Kconfig | 1 +
drivers/net/ethernet/stmicro/stmmac/common.h | 1 +
drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 8 +-
.../net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 8 +-
drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c | 8 +-
drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c | 8 +-
drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h | 2 +
drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 10 +-
drivers/net/ethernet/stmicro/stmmac/hwif.h | 4 +-
drivers/net/ethernet/stmicro/stmmac/stmmac.h | 12 +-
.../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 7 +-
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 217 +++++++--------------
12 files changed, 114 insertions(+), 172 deletions(-)
--
2.7.4
^ permalink raw reply
* [PATCH net-next v4 3/3] net: stmmac: Introducing support for Page Pool
From: Jose Abreu @ 2019-07-09 8:03 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel, Ilias Apalodimas, Jesper Dangaard Brouer,
Arnd Bergmann
In-Reply-To: <cover.1562659012.git.joabreu@synopsys.com>
Mapping and unmapping DMA region is an high bottleneck in stmmac driver,
specially in the RX path.
This commit introduces support for Page Pool API and uses it in all RX
queues. With this change, we get more stable troughput and some increase
of banwidth with iperf:
- MAC1000 - 950 Mbps
- XGMAC: 9.22 Gbps
Changes from v3:
- Use page_pool_destroy() (Ilias)
Changes from v2:
- Uncoditionally call page_pool_free() (Jesper)
Changes from v1:
- Use page_pool_get_dma_addr() (Jesper)
- Add a comment (Jesper)
- Add page_pool_free() call (Jesper)
- Reintroduce sync_single_for_device (Arnd / Ilias)
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
---
drivers/net/ethernet/stmicro/stmmac/Kconfig | 1 +
drivers/net/ethernet/stmicro/stmmac/stmmac.h | 10 +-
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 203 +++++++---------------
3 files changed, 70 insertions(+), 144 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 943189dcccb1..2325b40dff6e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -3,6 +3,7 @@ config STMMAC_ETH
tristate "STMicroelectronics Multi-Gigabit Ethernet driver"
depends on HAS_IOMEM && HAS_DMA
select MII
+ select PAGE_POOL
select PHYLINK
select CRC32
imply PTP_1588_CLOCK
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 513f4e2df5f6..5cd966c154f3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -20,6 +20,7 @@
#include <linux/ptp_clock_kernel.h>
#include <linux/net_tstamp.h>
#include <linux/reset.h>
+#include <net/page_pool.h>
struct stmmac_resources {
void __iomem *addr;
@@ -54,14 +55,19 @@ struct stmmac_tx_queue {
u32 mss;
};
+struct stmmac_rx_buffer {
+ struct page *page;
+ dma_addr_t addr;
+};
+
struct stmmac_rx_queue {
u32 rx_count_frames;
u32 queue_index;
+ struct page_pool *page_pool;
+ struct stmmac_rx_buffer *buf_pool;
struct stmmac_priv *priv_data;
struct dma_extended_desc *dma_erx;
struct dma_desc *dma_rx ____cacheline_aligned_in_smp;
- struct sk_buff **rx_skbuff;
- dma_addr_t *rx_skbuff_dma;
unsigned int cur_rx;
unsigned int dirty_rx;
u32 rx_zeroc_thresh;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c142e9367a68..00f2df304e28 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1197,26 +1197,14 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
int i, gfp_t flags, u32 queue)
{
struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
- struct sk_buff *skb;
+ struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
- skb = __netdev_alloc_skb_ip_align(priv->dev, priv->dma_buf_sz, flags);
- if (!skb) {
- netdev_err(priv->dev,
- "%s: Rx init fails; skb is NULL\n", __func__);
+ buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+ if (!buf->page)
return -ENOMEM;
- }
- rx_q->rx_skbuff[i] = skb;
- rx_q->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
- priv->dma_buf_sz,
- DMA_FROM_DEVICE);
- if (dma_mapping_error(priv->device, rx_q->rx_skbuff_dma[i])) {
- netdev_err(priv->dev, "%s: DMA mapping error\n", __func__);
- dev_kfree_skb_any(skb);
- return -EINVAL;
- }
-
- stmmac_set_desc_addr(priv, p, rx_q->rx_skbuff_dma[i]);
+ buf->addr = page_pool_get_dma_addr(buf->page);
+ stmmac_set_desc_addr(priv, p, buf->addr);
if (priv->dma_buf_sz == BUF_SIZE_16KiB)
stmmac_init_desc3(priv, p);
@@ -1232,13 +1220,11 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
static void stmmac_free_rx_buffer(struct stmmac_priv *priv, u32 queue, int i)
{
struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+ struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
- if (rx_q->rx_skbuff[i]) {
- dma_unmap_single(priv->device, rx_q->rx_skbuff_dma[i],
- priv->dma_buf_sz, DMA_FROM_DEVICE);
- dev_kfree_skb_any(rx_q->rx_skbuff[i]);
- }
- rx_q->rx_skbuff[i] = NULL;
+ if (buf->page)
+ page_pool_put_page(rx_q->page_pool, buf->page, false);
+ buf->page = NULL;
}
/**
@@ -1321,10 +1307,6 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags)
queue);
if (ret)
goto err_init_rx_buffers;
-
- netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n",
- rx_q->rx_skbuff[i], rx_q->rx_skbuff[i]->data,
- (unsigned int)rx_q->rx_skbuff_dma[i]);
}
rx_q->cur_rx = 0;
@@ -1498,8 +1480,11 @@ static void free_dma_rx_desc_resources(struct stmmac_priv *priv)
sizeof(struct dma_extended_desc),
rx_q->dma_erx, rx_q->dma_rx_phy);
- kfree(rx_q->rx_skbuff_dma);
- kfree(rx_q->rx_skbuff);
+ kfree(rx_q->buf_pool);
+ if (rx_q->page_pool) {
+ page_pool_request_shutdown(rx_q->page_pool);
+ page_pool_destroy(rx_q->page_pool);
+ }
}
}
@@ -1551,20 +1536,29 @@ static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv)
/* RX queues buffers and DMA */
for (queue = 0; queue < rx_count; queue++) {
struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+ struct page_pool_params pp_params = { 0 };
rx_q->queue_index = queue;
rx_q->priv_data = priv;
- rx_q->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE,
- sizeof(dma_addr_t),
- GFP_KERNEL);
- if (!rx_q->rx_skbuff_dma)
+ pp_params.flags = PP_FLAG_DMA_MAP;
+ pp_params.pool_size = DMA_RX_SIZE;
+ pp_params.order = DIV_ROUND_UP(priv->dma_buf_sz, PAGE_SIZE);
+ pp_params.nid = dev_to_node(priv->device);
+ pp_params.dev = priv->device;
+ pp_params.dma_dir = DMA_FROM_DEVICE;
+
+ rx_q->page_pool = page_pool_create(&pp_params);
+ if (IS_ERR(rx_q->page_pool)) {
+ ret = PTR_ERR(rx_q->page_pool);
+ rx_q->page_pool = NULL;
goto err_dma;
+ }
- rx_q->rx_skbuff = kmalloc_array(DMA_RX_SIZE,
- sizeof(struct sk_buff *),
- GFP_KERNEL);
- if (!rx_q->rx_skbuff)
+ rx_q->buf_pool = kmalloc_array(DMA_RX_SIZE,
+ sizeof(*rx_q->buf_pool),
+ GFP_KERNEL);
+ if (!rx_q->buf_pool)
goto err_dma;
if (priv->extend_desc) {
@@ -3286,9 +3280,8 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
int dirty = stmmac_rx_dirty(priv, queue);
unsigned int entry = rx_q->dirty_rx;
- int bfsize = priv->dma_buf_sz;
-
while (dirty-- > 0) {
+ struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry];
struct dma_desc *p;
bool use_rx_wd;
@@ -3297,49 +3290,22 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
else
p = rx_q->dma_rx + entry;
- if (likely(!rx_q->rx_skbuff[entry])) {
- struct sk_buff *skb;
-
- skb = netdev_alloc_skb_ip_align(priv->dev, bfsize);
- if (unlikely(!skb)) {
- /* so for a while no zero-copy! */
- rx_q->rx_zeroc_thresh = STMMAC_RX_THRESH;
- if (unlikely(net_ratelimit()))
- dev_err(priv->device,
- "fail to alloc skb entry %d\n",
- entry);
- break;
- }
-
- rx_q->rx_skbuff[entry] = skb;
- rx_q->rx_skbuff_dma[entry] =
- dma_map_single(priv->device, skb->data, bfsize,
- DMA_FROM_DEVICE);
- if (dma_mapping_error(priv->device,
- rx_q->rx_skbuff_dma[entry])) {
- netdev_err(priv->dev, "Rx DMA map failed\n");
- dev_kfree_skb(skb);
+ if (!buf->page) {
+ buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+ if (!buf->page)
break;
- }
-
- stmmac_set_desc_addr(priv, p, rx_q->rx_skbuff_dma[entry]);
- stmmac_refill_desc3(priv, rx_q, p);
-
- if (rx_q->rx_zeroc_thresh > 0)
- rx_q->rx_zeroc_thresh--;
-
- netif_dbg(priv, rx_status, priv->dev,
- "refill entry #%d\n", entry);
}
- dma_wmb();
+
+ buf->addr = page_pool_get_dma_addr(buf->page);
+ stmmac_set_desc_addr(priv, p, buf->addr);
+ stmmac_refill_desc3(priv, rx_q, p);
rx_q->rx_count_frames++;
rx_q->rx_count_frames %= priv->rx_coal_frames;
use_rx_wd = priv->use_riwt && rx_q->rx_count_frames;
- stmmac_set_rx_owner(priv, p, use_rx_wd);
-
dma_wmb();
+ stmmac_set_rx_owner(priv, p, use_rx_wd);
entry = STMMAC_GET_ENTRY(entry, DMA_RX_SIZE);
}
@@ -3364,9 +3330,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
unsigned int next_entry = rx_q->cur_rx;
int coe = priv->hw->rx_csum;
unsigned int count = 0;
- bool xmac;
-
- xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
if (netif_msg_rx_status(priv)) {
void *rx_head;
@@ -3380,11 +3343,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true);
}
while (count < limit) {
+ struct stmmac_rx_buffer *buf;
+ struct dma_desc *np, *p;
int entry, status;
- struct dma_desc *p;
- struct dma_desc *np;
entry = next_entry;
+ buf = &rx_q->buf_pool[entry];
if (priv->extend_desc)
p = (struct dma_desc *)(rx_q->dma_erx + entry);
@@ -3414,20 +3378,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
stmmac_rx_extended_status(priv, &priv->dev->stats,
&priv->xstats, rx_q->dma_erx + entry);
if (unlikely(status == discard_frame)) {
+ page_pool_recycle_direct(rx_q->page_pool, buf->page);
priv->dev->stats.rx_errors++;
- if (priv->hwts_rx_en && !priv->extend_desc) {
- /* DESC2 & DESC3 will be overwritten by device
- * with timestamp value, hence reinitialize
- * them in stmmac_rx_refill() function so that
- * device can reuse it.
- */
- dev_kfree_skb_any(rx_q->rx_skbuff[entry]);
- rx_q->rx_skbuff[entry] = NULL;
- dma_unmap_single(priv->device,
- rx_q->rx_skbuff_dma[entry],
- priv->dma_buf_sz,
- DMA_FROM_DEVICE);
- }
+ buf->page = NULL;
} else {
struct sk_buff *skb;
int frame_len;
@@ -3467,58 +3420,20 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
frame_len, status);
}
- /* The zero-copy is always used for all the sizes
- * in case of GMAC4 because it needs
- * to refill the used descriptors, always.
- */
- if (unlikely(!xmac &&
- ((frame_len < priv->rx_copybreak) ||
- stmmac_rx_threshold_count(rx_q)))) {
- skb = netdev_alloc_skb_ip_align(priv->dev,
- frame_len);
- if (unlikely(!skb)) {
- if (net_ratelimit())
- dev_warn(priv->device,
- "packet dropped\n");
- priv->dev->stats.rx_dropped++;
- continue;
- }
-
- dma_sync_single_for_cpu(priv->device,
- rx_q->rx_skbuff_dma
- [entry], frame_len,
- DMA_FROM_DEVICE);
- skb_copy_to_linear_data(skb,
- rx_q->
- rx_skbuff[entry]->data,
- frame_len);
-
- skb_put(skb, frame_len);
- dma_sync_single_for_device(priv->device,
- rx_q->rx_skbuff_dma
- [entry], frame_len,
- DMA_FROM_DEVICE);
- } else {
- skb = rx_q->rx_skbuff[entry];
- if (unlikely(!skb)) {
- if (net_ratelimit())
- netdev_err(priv->dev,
- "%s: Inconsistent Rx chain\n",
- priv->dev->name);
- priv->dev->stats.rx_dropped++;
- continue;
- }
- prefetch(skb->data - NET_IP_ALIGN);
- rx_q->rx_skbuff[entry] = NULL;
- rx_q->rx_zeroc_thresh++;
-
- skb_put(skb, frame_len);
- dma_unmap_single(priv->device,
- rx_q->rx_skbuff_dma[entry],
- priv->dma_buf_sz,
- DMA_FROM_DEVICE);
+ skb = netdev_alloc_skb_ip_align(priv->dev, frame_len);
+ if (unlikely(!skb)) {
+ priv->dev->stats.rx_dropped++;
+ continue;
}
+ dma_sync_single_for_cpu(priv->device, buf->addr,
+ frame_len, DMA_FROM_DEVICE);
+ skb_copy_to_linear_data(skb, page_address(buf->page),
+ frame_len);
+ skb_put(skb, frame_len);
+ dma_sync_single_for_device(priv->device, buf->addr,
+ frame_len, DMA_FROM_DEVICE);
+
if (netif_msg_pktdata(priv)) {
netdev_dbg(priv->dev, "frame received (%dbytes)",
frame_len);
@@ -3538,6 +3453,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
napi_gro_receive(&ch->rx_napi, skb);
+ /* Data payload copied into SKB, page ready for recycle */
+ page_pool_recycle_direct(rx_q->page_pool, buf->page);
+ buf->page = NULL;
+
priv->dev->stats.rx_packets++;
priv->dev->stats.rx_bytes += frame_len;
}
--
2.7.4
^ permalink raw reply related
* [PATCH net-next] bnxt_en: Add page_pool_destroy() during RX ring cleanup.
From: Michael Chan @ 2019-07-09 7:50 UTC (permalink / raw)
To: davem; +Cc: netdev, Ilias Apalodimas, Andy Gospodarek
Add page_pool_destroy() in bnxt_free_rx_rings() during normal RX ring
cleanup, as Ilias has informed us that the following commit has been
merged:
1da4bbeffe41 ("net: core: page_pool: add user refcnt and reintroduce page_pool_destroy")
The special error handling code to call page_pool_free() can now be
removed. bnxt_free_rx_rings() will always be called during normal
shutdown or any error paths.
Fixes: 322b87ca55f2 ("bnxt_en: add page_pool support")
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: Andy Gospodarek <gospo@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e9d3bd8..2b5b0ab 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2500,6 +2500,7 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
if (xdp_rxq_info_is_reg(&rxr->xdp_rxq))
xdp_rxq_info_unreg(&rxr->xdp_rxq);
+ page_pool_destroy(rxr->page_pool);
rxr->page_pool = NULL;
kfree(rxr->rx_tpa);
@@ -2560,19 +2561,14 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
return rc;
rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i);
- if (rc < 0) {
- page_pool_free(rxr->page_pool);
- rxr->page_pool = NULL;
+ if (rc < 0)
return rc;
- }
rc = xdp_rxq_info_reg_mem_model(&rxr->xdp_rxq,
MEM_TYPE_PAGE_POOL,
rxr->page_pool);
if (rc) {
xdp_rxq_info_unreg(&rxr->xdp_rxq);
- page_pool_free(rxr->page_pool);
- rxr->page_pool = NULL;
return rc;
}
--
2.5.1
^ permalink raw reply related
* Re: [PATCH 1/2] forcedeth: add recv cache make nic work steadily
From: Yanjun Zhu @ 2019-07-09 7:38 UTC (permalink / raw)
To: Jakub Kicinski; +Cc: netdev, davem
In-Reply-To: <20190708135257.18200316@cakuba.netronome.com>
On 2019/7/9 4:52, Jakub Kicinski wrote:
> On Fri, 5 Jul 2019 02:19:27 -0400, Zhu Yanjun wrote:
>> A recv cache is added. The size of recv cache is 1000Mb / skb_length.
>> When the system memory is not enough, this recv cache can make nic work
>> steadily.
>> When nic is up, this recv cache and work queue are created. When nic
>> is down, this recv cache will be destroyed and delayed workqueue is
>> canceled.
>> When nic is polled or rx interrupt is triggerred, rx handler will
>> get a skb from recv cache. Then the state of recv cache is checked.
>> If recv cache is not in filling up state, a work is queued to fill
>> up recv cache.
>> When skb size is changed, the old recv cache is destroyed and new recv
>> cache is created.
>> When the system memory is not enough, the allocation of skb failed.
>> recv cache will continue allocate skb until the recv cache is filled up.
>> When the system memory is not enough, this can make nic work steadily.
>> Becase of recv cache, the performance of nic is enhanced.
>>
>> CC: Joe Jin <joe.jin@oracle.com>
>> CC: Junxiao Bi <junxiao.bi@oracle.com>
>> Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
> Could you tell us a little more about the use case and the system
> condition?
When the host run for long time, there are a lot of memory fragments in
hosts.
In this condition, this patch can help us a lot.
>
>> diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
>> index b327b29..a673005 100644
>> --- a/drivers/net/ethernet/nvidia/forcedeth.c
>> +++ b/drivers/net/ethernet/nvidia/forcedeth.c
>> @@ -674,6 +674,11 @@ struct nv_ethtool_stats {
>> u64 tx_broadcast;
>> };
>>
>> +/* 1000Mb is 125M bytes, 125 * 1024 * 1024 bytes
>> + * The length of recv cache is 125M / skb_length
>> + */
>> +#define RECV_CACHE_LIST_LENGTH (125 * 1024 * 1024 / np->rx_buf_sz)
>> +
>> #define NV_DEV_STATISTICS_V3_COUNT (sizeof(struct nv_ethtool_stats)/sizeof(u64))
>> #define NV_DEV_STATISTICS_V2_COUNT (NV_DEV_STATISTICS_V3_COUNT - 3)
>> #define NV_DEV_STATISTICS_V1_COUNT (NV_DEV_STATISTICS_V2_COUNT - 6)
>> @@ -844,8 +849,18 @@ struct fe_priv {
>> char name_rx[IFNAMSIZ + 3]; /* -rx */
>> char name_tx[IFNAMSIZ + 3]; /* -tx */
>> char name_other[IFNAMSIZ + 6]; /* -other */
>> +
>> + /* This is to schedule work */
>> + struct delayed_work recv_cache_work;
>> + /* This list is to store skb queue for recv */
>> + struct sk_buff_head recv_list;
>> + unsigned long nv_recv_list_state;
>> };
>>
>> +/* This is recv list state to fill up recv cache */
>> +enum recv_list_state {
>> + RECV_LIST_ALLOCATE
>> +};
>> /*
>> * Maximum number of loops until we assume that a bit in the irq mask
>> * is stuck. Overridable with module param.
>> @@ -1804,7 +1819,11 @@ static int nv_alloc_rx(struct net_device *dev)
>> less_rx = np->last_rx.orig;
>>
>> while (np->put_rx.orig != less_rx) {
>> - struct sk_buff *skb = netdev_alloc_skb(dev, np->rx_buf_sz + NV_RX_ALLOC_PAD);
>> + struct sk_buff *skb = skb_dequeue(&np->recv_list);
>> +
>> + if (!test_bit(RECV_LIST_ALLOCATE, &np->nv_recv_list_state))
>> + schedule_delayed_work(&np->recv_cache_work, 0);
> Interesting, this seems to be coming up in multiple places recently..
>
> Could you explain why you have your own RECV_LIST_ALLOCATE bit here?
> Workqueue implementation itself uses an atomic bit to avoid scheduling
> work mutliple times:
This can avoid function call overhead to optimize the recv process.
Thanks
Zhu Yanjun
>
> bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
> struct delayed_work *dwork, unsigned long delay)
> {
> struct work_struct *work = &dwork->work;
> bool ret = false;
> unsigned long flags;
>
> /* read the comment in __queue_work() */
> local_irq_save(flags);
>
> if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
> __queue_delayed_work(cpu, wq, dwork, delay);
> ret = true;
> }
>
> local_irq_restore(flags);
> return ret;
> }
> EXPORT_SYMBOL(queue_delayed_work_on);
>
>> if (likely(skb)) {
>> np->put_rx_ctx->skb = skb;
>> np->put_rx_ctx->dma = dma_map_single(&np->pci_dev->dev,
>> @@ -1845,7 +1864,11 @@ static int nv_alloc_rx_optimized(struct net_device *dev)
>> less_rx = np->last_rx.ex;
>>
>> while (np->put_rx.ex != less_rx) {
>> - struct sk_buff *skb = netdev_alloc_skb(dev, np->rx_buf_sz + NV_RX_ALLOC_PAD);
>> + struct sk_buff *skb = skb_dequeue(&np->recv_list);
>> +
>> + if (!test_bit(RECV_LIST_ALLOCATE, &np->nv_recv_list_state))
>> + schedule_delayed_work(&np->recv_cache_work, 0);
> It seems a little heavy to schedule this work on every packet, would it
> make sense to add this in nv_napi_poll() instead?
>
>> if (likely(skb)) {
>> np->put_rx_ctx->skb = skb;
>> np->put_rx_ctx->dma = dma_map_single(&np->pci_dev->dev,
>> @@ -1957,6 +1980,40 @@ static void nv_init_tx(struct net_device *dev)
>> }
>> }
>>
>> +static void nv_init_recv_cache(struct net_device *dev)
>> +{
>> + struct fe_priv *np = netdev_priv(dev);
>> +
>> + skb_queue_head_init(&np->recv_list);
>> + while (skb_queue_len(&np->recv_list) < RECV_CACHE_LIST_LENGTH) {
>> + struct sk_buff *skb = netdev_alloc_skb(dev,
>> + np->rx_buf_sz + NV_RX_ALLOC_PAD);
>> + /* skb is null. This indicates that memory is not
>> + * enough.
>> + */
>> + if (unlikely(!skb)) {
>> + ndelay(3);
>> + continue;
> Does this path ever hit? Seems like doing an ndelay() and retrying
> allocation is not the best idea for non-preempt kernel.
>
> Also perhaps you should consider using __netdev_alloc_skb() and passing
> GFP_KERNEL, that way the system has a chance to go into memory reclaim
> (I presume this function can sleep).
>
>> + }
>> +
>> + skb_queue_tail(&np->recv_list, skb);
>> + }
>> +}
>> +
>> +static void nv_destroy_recv_cache(struct net_device *dev)
>> +{
>> + struct sk_buff *skb;
>> + struct fe_priv *np = netdev_priv(dev);
>> +
>> + cancel_delayed_work_sync(&np->recv_cache_work);
>> + WARN_ON(delayed_work_pending(&np->recv_cache_work));
>> +
>> + while ((skb = skb_dequeue(&np->recv_list)))
>> + kfree_skb(skb);
> skb_queue_purge()
>
>> + WARN_ON(skb_queue_len(&np->recv_list));
>> +}
>> +
>> static int nv_init_ring(struct net_device *dev)
>> {
>> struct fe_priv *np = netdev_priv(dev);
>> @@ -3047,6 +3104,8 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu)
>> nv_drain_rxtx(dev);
>> /* reinit driver view of the rx queue */
>> set_bufsize(dev);
>> + nv_destroy_recv_cache(dev);
>> + nv_init_recv_cache(dev);
>> if (nv_init_ring(dev)) {
>> if (!np->in_shutdown)
>> mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
>> @@ -4074,6 +4133,32 @@ static void nv_free_irq(struct net_device *dev)
>> }
>> }
>>
>> +static void nv_recv_cache_worker(struct work_struct *work)
>> +{
>> + struct fe_priv *np = container_of(work, struct fe_priv,
>> + recv_cache_work.work);
>> +
>> + set_bit(RECV_LIST_ALLOCATE, &np->nv_recv_list_state);
>> + while (skb_queue_len(&np->recv_list) < RECV_CACHE_LIST_LENGTH) {
>> + struct sk_buff *skb = netdev_alloc_skb(np->dev,
>> + np->rx_buf_sz + NV_RX_ALLOC_PAD);
>> + /* skb is null. This indicates that memory is not
>> + * enough.
>> + * When the system memory is not enough, the kernel
>> + * will compact memory or drop caches. At that time,
>> + * if memory allocation fails, it had better wait some
>> + * time for memory.
>> + */
>> + if (unlikely(!skb)) {
>> + ndelay(3);
>> + continue;
> Same comments as for the init function.
>
>> + }
>> +
>> + skb_queue_tail(&np->recv_list, skb);
>> + }
>> + clear_bit(RECV_LIST_ALLOCATE, &np->nv_recv_list_state);
>> +}
>> +
>> static void nv_do_nic_poll(struct timer_list *t)
>> {
>> struct fe_priv *np = from_timer(np, t, nic_poll);
>> @@ -4129,6 +4214,8 @@ static void nv_do_nic_poll(struct timer_list *t)
>> nv_drain_rxtx(dev);
>> /* reinit driver view of the rx queue */
>> set_bufsize(dev);
>> + nv_destroy_recv_cache(dev);
>> + nv_init_recv_cache(dev);
>> if (nv_init_ring(dev)) {
>> if (!np->in_shutdown)
>> mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
^ permalink raw reply
* RE: [PATCH net-next v3 3/3] net: stmmac: Introducing support for Page Pool
From: Jose Abreu @ 2019-07-09 7:38 UTC (permalink / raw)
To: Ilias Apalodimas, David Miller
Cc: Jose.Abreu@synopsys.com, linux-kernel@vger.kernel.org,
netdev@vger.kernel.org, linux-stm32@st-md-mailman.stormreply.com,
linux-arm-kernel@lists.infradead.org, Joao.Pinto@synopsys.com,
peppe.cavallaro@st.com, alexandre.torgue@st.com,
brouer@redhat.com, arnd@arndb.de
In-Reply-To: <20190709072356.GA4599@apalos>
From: Ilias Apalodimas <ilias.apalodimas@linaro.org> | Date: Tue, Jul 09, 2019 at 08:23:56
> The patch from Ivan did get merged, can you change the free call to
> page_pool_destroy and re-spin? You can add my acked-by
Yes, I will re-spin then. Thanks!
---
Thanks,
Jose Miguel Abreu
^ permalink raw reply
* [PATCH net-next v6 4/4] tc-tests: Add tc action ct tests
From: Paul Blakey @ 2019-07-09 7:30 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit,
Marcelo Ricardo Leitner
In-Reply-To: <1562657451-20819-1-git-send-email-paulb@mellanox.com>
Add 13 tests ensuring the command line is doing what is supposed to do.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
---
.../selftests/tc-testing/tc-tests/actions/ct.json | 314 +++++++++++++++++++++
1 file changed, 314 insertions(+)
create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
new file mode 100644
index 0000000..62b82fe
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
@@ -0,0 +1,314 @@
+[
+ {
+ "id": "696a",
+ "name": "Add simple ct action",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct zone 0 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "9f20",
+ "name": "Add ct clear action",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct clear index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct clear pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "5bea",
+ "name": "Try ct with zone",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct zone 404 index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct zone 404 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "d5d6",
+ "name": "Try ct with zone, commit",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct zone 404 commit index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit zone 404 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "029f",
+ "name": "Try ct with zone, commit, mark",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct zone 404 commit mark 0x42 index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit mark 66 zone 404 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "a58d",
+ "name": "Try ct with zone, commit, mark, nat",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct zone 404 commit mark 0x42 nat src addr 5.5.5.7 index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit mark 66 zone 404 nat src addr 5.5.5.7 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "901b",
+ "name": "Try ct with full nat ipv4 range syntax",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct commit nat src addr 5.5.5.7-5.5.6.0 port 1000-2000 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit zone 0 nat src addr 5.5.5.7-5.5.6.0 port 1000-2000 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "072b",
+ "name": "Try ct with full nat ipv6 syntax",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct commit nat src addr 2001::1 port 1000-2000 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit zone 0 nat src addr 2001::1 port 1000-2000 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "3420",
+ "name": "Try ct with full nat ipv6 range syntax",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct commit nat src addr 2001::1-2001::10 port 1000-2000 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit zone 0 nat src addr 2001::1-2001::10 port 1000-2000 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "4470",
+ "name": "Try ct with full nat ipv6 range syntax + force",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct commit force nat src addr 2001::1-2001::10 port 1000-2000 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit force zone 0 nat src addr 2001::1-2001::10 port 1000-2000 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "5d88",
+ "name": "Try ct with label",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct label 123123 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct zone 0 label 12312300000000000000000000000000 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "04d4",
+ "name": "Try ct with label with mask",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct label 12312300000000000000000000000001/ffffffff000000000000000000000001 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct zone 0 label 12312300000000000000000000000001/ffffffff000000000000000000000001 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "9751",
+ "name": "Try ct with mark + mask",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct mark 0x42/0xf0 index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct mark 66/0xf0 zone 0 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ }
+]
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v6 1/4] net/sched: Introduce action ct
From: Paul Blakey @ 2019-07-09 7:30 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
In-Reply-To: <1562657451-20819-1-git-send-email-paulb@mellanox.com>
Allow sending a packet to conntrack module for connection tracking.
The packet will be marked with conntrack connection's state, and
any metadata such as conntrack mark and label. This state metadata
can later be matched against with tc classifers, for example with the
flower classifier as below.
In addition to committing new connections the user can optionally
specific a zone to track within, set a mark/label and configure nat
with an address range and port range.
Usage is as follows:
$ tc qdisc add dev ens1f0_0 ingress
$ tc qdisc add dev ens1f0_1 ingress
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 0 proto ip \
flower ip_proto tcp ct_state -trk \
action ct zone 2 pipe \
action goto chain 2
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 2 proto ip \
flower ct_state +trk+new \
action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 2 proto ip \
flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
action ct nat pipe \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_1 ingress \
prio 1 chain 0 proto ip \
flower ip_proto tcp ct_state -trk \
action ct zone 2 pipe \
action goto chain 1
$ tc filter add dev ens1f0_1 ingress \
prio 1 chain 1 proto ip \
flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
action ct nat pipe \
action mirred egress redirect dev ens1f0_0
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Changelog:
V5->V6:
Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case
V4->V5:
Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached()
V3->V4:
Added strict_start_type for act_ct policy
V2->V3:
Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c
V1->V2:
Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max
Refactored NAT_PORT_MIN_MAX range handling as well
Added ipv4/ipv6 defragmentation
Removed extra skb pull push of nw offset in exectute nat
Refactored tcf_ct_skb_network_trim after pull
Removed TCA_ACT_CT define
---
include/net/flow_offload.h | 5 +
include/net/tc_act/tc_ct.h | 63 +++
include/uapi/linux/pkt_cls.h | 1 +
include/uapi/linux/tc_act/tc_ct.h | 41 ++
net/sched/Kconfig | 11 +
net/sched/Makefile | 1 +
net/sched/act_ct.c | 984 ++++++++++++++++++++++++++++++++++++++
net/sched/cls_api.c | 5 +
8 files changed, 1111 insertions(+)
create mode 100644 include/net/tc_act/tc_ct.h
create mode 100644 include/uapi/linux/tc_act/tc_ct.h
create mode 100644 net/sched/act_ct.c
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 36127c1..a09e256 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -129,6 +129,7 @@ enum flow_action_id {
FLOW_ACTION_QUEUE,
FLOW_ACTION_SAMPLE,
FLOW_ACTION_POLICE,
+ FLOW_ACTION_CT,
};
/* This is mirroring enum pedit_header_type definition for easy mapping between
@@ -178,6 +179,10 @@ struct flow_action_entry {
s64 burst;
u64 rate_bytes_ps;
} police;
+ struct { /* FLOW_ACTION_CT */
+ int action;
+ u16 zone;
+ } ct;
};
};
diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h
new file mode 100644
index 0000000..bdc20ab
--- /dev/null
+++ b/include/net/tc_act/tc_ct.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_TC_CT_H
+#define __NET_TC_CT_H
+
+#include <net/act_api.h>
+#include <uapi/linux/tc_act/tc_ct.h>
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_conntrack_labels.h>
+
+struct tcf_ct_params {
+ struct nf_conn *tmpl;
+ u16 zone;
+
+ u32 mark;
+ u32 mark_mask;
+
+ u32 labels[NF_CT_LABELS_MAX_SIZE / sizeof(u32)];
+ u32 labels_mask[NF_CT_LABELS_MAX_SIZE / sizeof(u32)];
+
+ struct nf_nat_range2 range;
+ bool ipv4_range;
+
+ u16 ct_action;
+
+ struct rcu_head rcu;
+};
+
+struct tcf_ct {
+ struct tc_action common;
+ struct tcf_ct_params __rcu *params;
+};
+
+#define to_ct(a) ((struct tcf_ct *)a)
+#define to_ct_params(a) ((struct tcf_ct_params *) \
+ rtnl_dereference((to_ct(a)->params)))
+
+static inline uint16_t tcf_ct_zone(const struct tc_action *a)
+{
+ return to_ct_params(a)->zone;
+}
+
+static inline int tcf_ct_action(const struct tc_action *a)
+{
+ return to_ct_params(a)->ct_action;
+}
+
+#else
+static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; }
+static inline int tcf_ct_action(const struct tc_action *a) { return 0; }
+#endif /* CONFIG_NF_CONNTRACK */
+
+static inline bool is_tcf_ct(const struct tc_action *a)
+{
+#if defined(CONFIG_NET_CLS_ACT) && IS_ENABLED(CONFIG_NF_CONNTRACK)
+ if (a->ops && a->ops->id == TCA_ID_CT)
+ return true;
+#endif
+ return false;
+}
+
+#endif /* __NET_TC_CT_H */
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 8cc6b67..7c9d701 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -106,6 +106,7 @@ enum tca_id {
TCA_ID_SAMPLE = TCA_ACT_SAMPLE,
/* other actions go here */
TCA_ID_CTINFO,
+ TCA_ID_CT,
__TCA_ID_MAX = 255
};
diff --git a/include/uapi/linux/tc_act/tc_ct.h b/include/uapi/linux/tc_act/tc_ct.h
new file mode 100644
index 0000000..5fb1d7a
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_ct.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __UAPI_TC_CT_H
+#define __UAPI_TC_CT_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+enum {
+ TCA_CT_UNSPEC,
+ TCA_CT_PARMS,
+ TCA_CT_TM,
+ TCA_CT_ACTION, /* u16 */
+ TCA_CT_ZONE, /* u16 */
+ TCA_CT_MARK, /* u32 */
+ TCA_CT_MARK_MASK, /* u32 */
+ TCA_CT_LABELS, /* u128 */
+ TCA_CT_LABELS_MASK, /* u128 */
+ TCA_CT_NAT_IPV4_MIN, /* be32 */
+ TCA_CT_NAT_IPV4_MAX, /* be32 */
+ TCA_CT_NAT_IPV6_MIN, /* struct in6_addr */
+ TCA_CT_NAT_IPV6_MAX, /* struct in6_addr */
+ TCA_CT_NAT_PORT_MIN, /* be16 */
+ TCA_CT_NAT_PORT_MAX, /* be16 */
+ TCA_CT_PAD,
+ __TCA_CT_MAX
+};
+
+#define TCA_CT_MAX (__TCA_CT_MAX - 1)
+
+#define TCA_CT_ACT_COMMIT (1 << 0)
+#define TCA_CT_ACT_FORCE (1 << 1)
+#define TCA_CT_ACT_CLEAR (1 << 2)
+#define TCA_CT_ACT_NAT (1 << 3)
+#define TCA_CT_ACT_NAT_SRC (1 << 4)
+#define TCA_CT_ACT_NAT_DST (1 << 5)
+
+struct tc_ct {
+ tc_gen;
+};
+
+#endif /* __UAPI_TC_CT_H */
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 360fdd3..ff90a71 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -929,6 +929,17 @@ config NET_ACT_TUNNEL_KEY
To compile this code as a module, choose M here: the
module will be called act_tunnel_key.
+config NET_ACT_CT
+ tristate "connection tracking tc action"
+ depends on NET_CLS_ACT && NF_CONNTRACK
+ help
+ Say Y here to allow sending the packets to conntrack module.
+
+ If unsure, say N.
+
+ To compile this code as a module, choose M here: the
+ module will be called act_ct.
+
config NET_IFE_SKBMARK
tristate "Support to encoding decoding skb mark on IFE action"
depends on NET_ACT_IFE
diff --git a/net/sched/Makefile b/net/sched/Makefile
index d54bfcb..23d2202 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o
obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o
obj-$(CONFIG_NET_IFE_SKBTCINDEX) += act_meta_skbtcindex.o
obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o
+obj-$(CONFIG_NET_ACT_CT) += act_ct.o
obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o
obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o
obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
new file mode 100644
index 0000000..b501ce0
--- /dev/null
+++ b/net/sched/act_ct.c
@@ -0,0 +1,984 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* -
+ * net/sched/act_ct.c Connection Tracking action
+ *
+ * Authors: Paul Blakey <paulb@mellanox.com>
+ * Yossi Kuperman <yossiku@mellanox.com>
+ * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/pkt_cls.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+#include <net/act_api.h>
+#include <net/ip.h>
+#include <net/ipv6_frag.h>
+#include <uapi/linux/tc_act/tc_ct.h>
+#include <net/tc_act/tc_ct.h>
+
+#include <linux/netfilter/nf_nat.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+
+static struct tc_action_ops act_ct_ops;
+static unsigned int ct_net_id;
+
+struct tc_ct_action_net {
+ struct tc_action_net tn; /* Must be first */
+ bool labels;
+};
+
+/* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
+static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
+ u16 zone_id, bool force)
+{
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct)
+ return false;
+ if (!net_eq(net, read_pnet(&ct->ct_net)))
+ return false;
+ if (nf_ct_zone(ct)->id != zone_id)
+ return false;
+
+ /* Force conntrack entry direction. */
+ if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
+ if (nf_ct_is_confirmed(ct))
+ nf_ct_kill(ct);
+
+ nf_conntrack_put(&ct->ct_general);
+ nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
+
+ return false;
+ }
+
+ return true;
+}
+
+/* Trim the skb to the length specified by the IP/IPv6 header,
+ * removing any trailing lower-layer padding. This prepares the skb
+ * for higher-layer processing that assumes skb->len excludes padding
+ * (such as nf_ip_checksum). The caller needs to pull the skb to the
+ * network header, and ensure ip_hdr/ipv6_hdr points to valid data.
+ */
+static int tcf_ct_skb_network_trim(struct sk_buff *skb, int family)
+{
+ unsigned int len;
+ int err;
+
+ switch (family) {
+ case NFPROTO_IPV4:
+ len = ntohs(ip_hdr(skb)->tot_len);
+ break;
+ case NFPROTO_IPV6:
+ len = sizeof(struct ipv6hdr)
+ + ntohs(ipv6_hdr(skb)->payload_len);
+ break;
+ default:
+ len = skb->len;
+ }
+
+ err = pskb_trim_rcsum(skb, len);
+
+ return err;
+}
+
+static u8 tcf_ct_skb_nf_family(struct sk_buff *skb)
+{
+ u8 family = NFPROTO_UNSPEC;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ family = NFPROTO_IPV4;
+ break;
+ case htons(ETH_P_IPV6):
+ family = NFPROTO_IPV6;
+ break;
+ default:
+ break;
+ }
+
+ return family;
+}
+
+static int tcf_ct_ipv4_is_fragment(struct sk_buff *skb, bool *frag)
+{
+ unsigned int len;
+
+ len = skb_network_offset(skb) + sizeof(struct iphdr);
+ if (unlikely(skb->len < len))
+ return -EINVAL;
+ if (unlikely(!pskb_may_pull(skb, len)))
+ return -ENOMEM;
+
+ *frag = ip_is_fragment(ip_hdr(skb));
+ return 0;
+}
+
+static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag)
+{
+ unsigned int flags = 0, len, payload_ofs = 0;
+ unsigned short frag_off;
+ int nexthdr;
+
+ len = skb_network_offset(skb) + sizeof(struct ipv6hdr);
+ if (unlikely(skb->len < len))
+ return -EINVAL;
+ if (unlikely(!pskb_may_pull(skb, len)))
+ return -ENOMEM;
+
+ nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags);
+ if (unlikely(nexthdr < 0))
+ return -EPROTO;
+
+ *frag = flags & IP6_FH_F_FRAG;
+ return 0;
+}
+
+static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
+ u8 family, u16 zone)
+{
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+ int err = 0;
+ bool frag;
+
+ /* Previously seen (loopback)? Ignore. */
+ ct = nf_ct_get(skb, &ctinfo);
+ if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED)
+ return 0;
+
+ if (family == NFPROTO_IPV4)
+ err = tcf_ct_ipv4_is_fragment(skb, &frag);
+ else
+ err = tcf_ct_ipv6_is_fragment(skb, &frag);
+ if (err || !frag)
+ return err;
+
+ skb_get(skb);
+
+ if (family == NFPROTO_IPV4) {
+ enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
+
+ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+ local_bh_disable();
+ err = ip_defrag(net, skb, user);
+ local_bh_enable();
+ if (err && err != -EINPROGRESS)
+ goto out_free;
+ } else { /* NFPROTO_IPV6 */
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
+ enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
+
+ memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
+ err = nf_ct_frag6_gather(net, skb, user);
+ if (err && err != -EINPROGRESS)
+ goto out_free;
+#else
+ err = -EOPNOTSUPP;
+ goto out_free;
+#endif
+ }
+
+ skb_clear_hash(skb);
+ skb->ignore_df = 1;
+ return err;
+
+out_free:
+ kfree_skb(skb);
+ return err;
+}
+
+static void tcf_ct_params_free(struct rcu_head *head)
+{
+ struct tcf_ct_params *params = container_of(head,
+ struct tcf_ct_params, rcu);
+
+ if (params->tmpl)
+ nf_conntrack_put(¶ms->tmpl->ct_general);
+ kfree(params);
+}
+
+#if IS_ENABLED(CONFIG_NF_NAT)
+/* Modelled after nf_nat_ipv[46]_fn().
+ * range is only used for new, uninitialized NAT state.
+ * Returns either NF_ACCEPT or NF_DROP.
+ */
+static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo,
+ const struct nf_nat_range2 *range,
+ enum nf_nat_manip_type maniptype)
+{
+ int hooknum, err = NF_ACCEPT;
+
+ /* See HOOK2MANIP(). */
+ if (maniptype == NF_NAT_MANIP_SRC)
+ hooknum = NF_INET_LOCAL_IN; /* Source NAT */
+ else
+ hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */
+
+ switch (ctinfo) {
+ case IP_CT_RELATED:
+ case IP_CT_RELATED_REPLY:
+ if (skb->protocol == htons(ETH_P_IP) &&
+ ip_hdr(skb)->protocol == IPPROTO_ICMP) {
+ if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
+ hooknum))
+ err = NF_DROP;
+ goto out;
+ } else if (IS_ENABLED(CONFIG_IPV6) &&
+ skb->protocol == htons(ETH_P_IPV6)) {
+ __be16 frag_off;
+ u8 nexthdr = ipv6_hdr(skb)->nexthdr;
+ int hdrlen = ipv6_skip_exthdr(skb,
+ sizeof(struct ipv6hdr),
+ &nexthdr, &frag_off);
+
+ if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
+ if (!nf_nat_icmpv6_reply_translation(skb, ct,
+ ctinfo,
+ hooknum,
+ hdrlen))
+ err = NF_DROP;
+ goto out;
+ }
+ }
+ /* Non-ICMP, fall thru to initialize if needed. */
+ /* fall through */
+ case IP_CT_NEW:
+ /* Seen it before? This can happen for loopback, retrans,
+ * or local packets.
+ */
+ if (!nf_nat_initialized(ct, maniptype)) {
+ /* Initialize according to the NAT action. */
+ err = (range && range->flags & NF_NAT_RANGE_MAP_IPS)
+ /* Action is set up to establish a new
+ * mapping.
+ */
+ ? nf_nat_setup_info(ct, range, maniptype)
+ : nf_nat_alloc_null_binding(ct, hooknum);
+ if (err != NF_ACCEPT)
+ goto out;
+ }
+ break;
+
+ case IP_CT_ESTABLISHED:
+ case IP_CT_ESTABLISHED_REPLY:
+ break;
+
+ default:
+ err = NF_DROP;
+ goto out;
+ }
+
+ err = nf_nat_packet(ct, ctinfo, hooknum, skb);
+out:
+ return err;
+}
+#endif /* CONFIG_NF_NAT */
+
+static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
+ u32 new_mark;
+
+ if (!mask)
+ return;
+
+ new_mark = mark | (ct->mark & ~(mask));
+ if (ct->mark != new_mark) {
+ ct->mark = new_mark;
+ if (nf_ct_is_confirmed(ct))
+ nf_conntrack_event_cache(IPCT_MARK, ct);
+ }
+#endif
+}
+
+static void tcf_ct_act_set_labels(struct nf_conn *ct,
+ u32 *labels,
+ u32 *labels_m)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)
+ size_t labels_sz = FIELD_SIZEOF(struct tcf_ct_params, labels);
+
+ if (!memchr_inv(labels_m, 0, labels_sz))
+ return;
+
+ nf_connlabels_replace(ct, labels, labels_m, 4);
+#endif
+}
+
+static int tcf_ct_act_nat(struct sk_buff *skb,
+ struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo,
+ int ct_action,
+ struct nf_nat_range2 *range,
+ bool commit)
+{
+#if IS_ENABLED(CONFIG_NF_NAT)
+ enum nf_nat_manip_type maniptype;
+
+ if (!(ct_action & TCA_CT_ACT_NAT))
+ return NF_ACCEPT;
+
+ /* Add NAT extension if not confirmed yet. */
+ if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
+ return NF_DROP; /* Can't NAT. */
+
+ if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) &&
+ (ctinfo != IP_CT_RELATED || commit)) {
+ /* NAT an established or related connection like before. */
+ if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY)
+ /* This is the REPLY direction for a connection
+ * for which NAT was applied in the forward
+ * direction. Do the reverse NAT.
+ */
+ maniptype = ct->status & IPS_SRC_NAT
+ ? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC;
+ else
+ maniptype = ct->status & IPS_SRC_NAT
+ ? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST;
+ } else if (ct_action & TCA_CT_ACT_NAT_SRC) {
+ maniptype = NF_NAT_MANIP_SRC;
+ } else if (ct_action & TCA_CT_ACT_NAT_DST) {
+ maniptype = NF_NAT_MANIP_DST;
+ } else {
+ return NF_ACCEPT;
+ }
+
+ return ct_nat_execute(skb, ct, ctinfo, range, maniptype);
+#else
+ return NF_ACCEPT;
+#endif
+}
+
+static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
+ struct tcf_result *res)
+{
+ struct net *net = dev_net(skb->dev);
+ bool cached, commit, clear, force;
+ enum ip_conntrack_info ctinfo;
+ struct tcf_ct *c = to_ct(a);
+ struct nf_conn *tmpl = NULL;
+ struct nf_hook_state state;
+ int nh_ofs, err, retval;
+ struct tcf_ct_params *p;
+ struct nf_conn *ct;
+ u8 family;
+
+ p = rcu_dereference_bh(c->params);
+
+ retval = READ_ONCE(c->tcf_action);
+ commit = p->ct_action & TCA_CT_ACT_COMMIT;
+ clear = p->ct_action & TCA_CT_ACT_CLEAR;
+ force = p->ct_action & TCA_CT_ACT_FORCE;
+ tmpl = p->tmpl;
+
+ if (clear) {
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct) {
+ nf_conntrack_put(&ct->ct_general);
+ nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
+ }
+
+ goto out;
+ }
+
+ family = tcf_ct_skb_nf_family(skb);
+ if (family == NFPROTO_UNSPEC)
+ goto drop;
+
+ /* The conntrack module expects to be working at L3.
+ * We also try to pull the IPv4/6 header to linear area
+ */
+ nh_ofs = skb_network_offset(skb);
+ skb_pull_rcsum(skb, nh_ofs);
+ err = tcf_ct_handle_fragments(net, skb, family, p->zone);
+ if (err == -EINPROGRESS) {
+ retval = TC_ACT_STOLEN;
+ goto out;
+ }
+ if (err)
+ goto drop;
+
+ err = tcf_ct_skb_network_trim(skb, family);
+ if (err)
+ goto drop;
+
+ /* If we are recirculating packets to match on ct fields and
+ * committing with a separate ct action, then we don't need to
+ * actually run the packet through conntrack twice unless it's for a
+ * different zone.
+ */
+ cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force);
+ if (!cached) {
+ /* Associate skb with specified zone. */
+ if (tmpl) {
+ ct = nf_ct_get(skb, &ctinfo);
+ if (skb_nfct(skb))
+ nf_conntrack_put(skb_nfct(skb));
+ nf_conntrack_get(&tmpl->ct_general);
+ nf_ct_set(skb, tmpl, IP_CT_NEW);
+ }
+
+ state.hook = NF_INET_PRE_ROUTING;
+ state.net = net;
+ state.pf = family;
+ err = nf_conntrack_in(skb, &state);
+ if (err != NF_ACCEPT)
+ goto out_push;
+ }
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct)
+ goto out_push;
+ nf_ct_deliver_cached_events(ct);
+
+ err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit);
+ if (err != NF_ACCEPT)
+ goto drop;
+
+ if (commit) {
+ tcf_ct_act_set_mark(ct, p->mark, p->mark_mask);
+ tcf_ct_act_set_labels(ct, p->labels, p->labels_mask);
+
+ /* This will take care of sending queued events
+ * even if the connection is already confirmed.
+ */
+ nf_conntrack_confirm(skb);
+ }
+
+out_push:
+ skb_push_rcsum(skb, nh_ofs);
+
+out:
+ bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb);
+ return retval;
+
+drop:
+ qstats_drop_inc(this_cpu_ptr(a->cpu_qstats));
+ return TC_ACT_SHOT;
+}
+
+static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
+ [TCA_CT_UNSPEC] = { .strict_start_type = TCA_CT_UNSPEC + 1 },
+ [TCA_CT_ACTION] = { .type = NLA_U16 },
+ [TCA_CT_PARMS] = { .type = NLA_EXACT_LEN, .len = sizeof(struct tc_ct) },
+ [TCA_CT_ZONE] = { .type = NLA_U16 },
+ [TCA_CT_MARK] = { .type = NLA_U32 },
+ [TCA_CT_MARK_MASK] = { .type = NLA_U32 },
+ [TCA_CT_LABELS] = { .type = NLA_BINARY,
+ .len = 128 / BITS_PER_BYTE },
+ [TCA_CT_LABELS_MASK] = { .type = NLA_BINARY,
+ .len = 128 / BITS_PER_BYTE },
+ [TCA_CT_NAT_IPV4_MIN] = { .type = NLA_U32 },
+ [TCA_CT_NAT_IPV4_MAX] = { .type = NLA_U32 },
+ [TCA_CT_NAT_IPV6_MIN] = { .type = NLA_EXACT_LEN,
+ .len = sizeof(struct in6_addr) },
+ [TCA_CT_NAT_IPV6_MAX] = { .type = NLA_EXACT_LEN,
+ .len = sizeof(struct in6_addr) },
+ [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 },
+ [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 },
+};
+
+static int tcf_ct_fill_params_nat(struct tcf_ct_params *p,
+ struct tc_ct *parm,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ struct nf_nat_range2 *range;
+
+ if (!(p->ct_action & TCA_CT_ACT_NAT))
+ return 0;
+
+ if (!IS_ENABLED(CONFIG_NF_NAT)) {
+ NL_SET_ERR_MSG_MOD(extack, "Netfilter nat isn't enabled in kernel");
+ return -EOPNOTSUPP;
+ }
+
+ if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST)))
+ return 0;
+
+ if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
+ (p->ct_action & TCA_CT_ACT_NAT_DST)) {
+ NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
+ return -EOPNOTSUPP;
+ }
+
+ range = &p->range;
+ if (tb[TCA_CT_NAT_IPV4_MIN]) {
+ struct nlattr *max_attr = tb[TCA_CT_NAT_IPV4_MAX];
+
+ p->ipv4_range = true;
+ range->flags |= NF_NAT_RANGE_MAP_IPS;
+ range->min_addr.ip =
+ nla_get_in_addr(tb[TCA_CT_NAT_IPV4_MIN]);
+
+ range->max_addr.ip = max_attr ?
+ nla_get_in_addr(max_attr) :
+ range->min_addr.ip;
+ } else if (tb[TCA_CT_NAT_IPV6_MIN]) {
+ struct nlattr *max_attr = tb[TCA_CT_NAT_IPV6_MAX];
+
+ p->ipv4_range = false;
+ range->flags |= NF_NAT_RANGE_MAP_IPS;
+ range->min_addr.in6 =
+ nla_get_in6_addr(tb[TCA_CT_NAT_IPV6_MIN]);
+
+ range->max_addr.in6 = max_attr ?
+ nla_get_in6_addr(max_attr) :
+ range->min_addr.in6;
+ }
+
+ if (tb[TCA_CT_NAT_PORT_MIN]) {
+ range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+ range->min_proto.all = nla_get_be16(tb[TCA_CT_NAT_PORT_MIN]);
+
+ range->max_proto.all = tb[TCA_CT_NAT_PORT_MAX] ?
+ nla_get_be16(tb[TCA_CT_NAT_PORT_MAX]) :
+ range->min_proto.all;
+ }
+
+ return 0;
+}
+
+static void tcf_ct_set_key_val(struct nlattr **tb,
+ void *val, int val_type,
+ void *mask, int mask_type,
+ int len)
+{
+ if (!tb[val_type])
+ return;
+ nla_memcpy(val, tb[val_type], len);
+
+ if (!mask)
+ return;
+
+ if (mask_type == TCA_CT_UNSPEC || !tb[mask_type])
+ memset(mask, 0xff, len);
+ else
+ nla_memcpy(mask, tb[mask_type], len);
+}
+
+static int tcf_ct_fill_params(struct net *net,
+ struct tcf_ct_params *p,
+ struct tc_ct *parm,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ struct tc_ct_action_net *tn = net_generic(net, ct_net_id);
+ struct nf_conntrack_zone zone;
+ struct nf_conn *tmpl;
+ int err;
+
+ p->zone = NF_CT_DEFAULT_ZONE_ID;
+
+ tcf_ct_set_key_val(tb,
+ &p->ct_action, TCA_CT_ACTION,
+ NULL, TCA_CT_UNSPEC,
+ sizeof(p->ct_action));
+
+ if (p->ct_action & TCA_CT_ACT_CLEAR)
+ return 0;
+
+ err = tcf_ct_fill_params_nat(p, parm, tb, extack);
+ if (err)
+ return err;
+
+ if (tb[TCA_CT_MARK]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) {
+ NL_SET_ERR_MSG_MOD(extack, "Conntrack mark isn't enabled.");
+ return -EOPNOTSUPP;
+ }
+ tcf_ct_set_key_val(tb,
+ &p->mark, TCA_CT_MARK,
+ &p->mark_mask, TCA_CT_MARK_MASK,
+ sizeof(p->mark));
+ }
+
+ if (tb[TCA_CT_LABELS]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) {
+ NL_SET_ERR_MSG_MOD(extack, "Conntrack labels isn't enabled.");
+ return -EOPNOTSUPP;
+ }
+
+ if (!tn->labels) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to set connlabel length");
+ return -EOPNOTSUPP;
+ }
+ tcf_ct_set_key_val(tb,
+ p->labels, TCA_CT_LABELS,
+ p->labels_mask, TCA_CT_LABELS_MASK,
+ sizeof(p->labels));
+ }
+
+ if (tb[TCA_CT_ZONE]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) {
+ NL_SET_ERR_MSG_MOD(extack, "Conntrack zones isn't enabled.");
+ return -EOPNOTSUPP;
+ }
+
+ tcf_ct_set_key_val(tb,
+ &p->zone, TCA_CT_ZONE,
+ NULL, TCA_CT_UNSPEC,
+ sizeof(p->zone));
+ }
+
+ if (p->zone == NF_CT_DEFAULT_ZONE_ID)
+ return 0;
+
+ nf_ct_zone_init(&zone, p->zone, NF_CT_DEFAULT_ZONE_DIR, 0);
+ tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL);
+ if (!tmpl) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template");
+ return -ENOMEM;
+ }
+ __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+ nf_conntrack_get(&tmpl->ct_general);
+ p->tmpl = tmpl;
+
+ return 0;
+}
+
+static int tcf_ct_init(struct net *net, struct nlattr *nla,
+ struct nlattr *est, struct tc_action **a,
+ int replace, int bind, bool rtnl_held,
+ struct tcf_proto *tp,
+ struct netlink_ext_ack *extack)
+{
+ struct tc_action_net *tn = net_generic(net, ct_net_id);
+ struct tcf_ct_params *params = NULL;
+ struct nlattr *tb[TCA_CT_MAX + 1];
+ struct tcf_chain *goto_ch = NULL;
+ struct tc_ct *parm;
+ struct tcf_ct *c;
+ int err, res = 0;
+
+ if (!nla) {
+ NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed");
+ return -EINVAL;
+ }
+
+ err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!tb[TCA_CT_PARMS]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing required ct parameters");
+ return -EINVAL;
+ }
+ parm = nla_data(tb[TCA_CT_PARMS]);
+
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+
+ if (!err) {
+ err = tcf_idr_create(tn, parm->index, est, a,
+ &act_ct_ops, bind, true);
+ if (err) {
+ tcf_idr_cleanup(tn, parm->index);
+ return err;
+ }
+ res = ACT_P_CREATED;
+ } else {
+ if (bind)
+ return 0;
+
+ if (!replace) {
+ tcf_idr_release(*a, bind);
+ return -EEXIST;
+ }
+ }
+ err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+ if (err < 0)
+ goto cleanup;
+
+ c = to_ct(*a);
+
+ params = kzalloc(sizeof(*params), GFP_KERNEL);
+ if (unlikely(!params)) {
+ err = -ENOMEM;
+ goto cleanup;
+ }
+
+ err = tcf_ct_fill_params(net, params, parm, tb, extack);
+ if (err)
+ goto cleanup;
+
+ spin_lock_bh(&c->tcf_lock);
+ goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
+ rcu_swap_protected(c->params, params, lockdep_is_held(&c->tcf_lock));
+ spin_unlock_bh(&c->tcf_lock);
+
+ if (goto_ch)
+ tcf_chain_put_by_act(goto_ch);
+ if (params)
+ kfree_rcu(params, rcu);
+ if (res == ACT_P_CREATED)
+ tcf_idr_insert(tn, *a);
+
+ return res;
+
+cleanup:
+ if (goto_ch)
+ tcf_chain_put_by_act(goto_ch);
+ kfree(params);
+ tcf_idr_release(*a, bind);
+ return err;
+}
+
+static void tcf_ct_cleanup(struct tc_action *a)
+{
+ struct tcf_ct_params *params;
+ struct tcf_ct *c = to_ct(a);
+
+ params = rcu_dereference_protected(c->params, 1);
+ if (params)
+ call_rcu(¶ms->rcu, tcf_ct_params_free);
+}
+
+static int tcf_ct_dump_key_val(struct sk_buff *skb,
+ void *val, int val_type,
+ void *mask, int mask_type,
+ int len)
+{
+ int err;
+
+ if (mask && !memchr_inv(mask, 0, len))
+ return 0;
+
+ err = nla_put(skb, val_type, len, val);
+ if (err)
+ return err;
+
+ if (mask_type != TCA_CT_UNSPEC) {
+ err = nla_put(skb, mask_type, len, mask);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p)
+{
+ struct nf_nat_range2 *range = &p->range;
+
+ if (!(p->ct_action & TCA_CT_ACT_NAT))
+ return 0;
+
+ if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST)))
+ return 0;
+
+ if (range->flags & NF_NAT_RANGE_MAP_IPS) {
+ if (p->ipv4_range) {
+ if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MIN,
+ range->min_addr.ip))
+ return -1;
+ if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MAX,
+ range->max_addr.ip))
+ return -1;
+ } else {
+ if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MIN,
+ &range->min_addr.in6))
+ return -1;
+ if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MAX,
+ &range->max_addr.in6))
+ return -1;
+ }
+ }
+
+ if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
+ if (nla_put_be16(skb, TCA_CT_NAT_PORT_MIN,
+ range->min_proto.all))
+ return -1;
+ if (nla_put_be16(skb, TCA_CT_NAT_PORT_MAX,
+ range->max_proto.all))
+ return -1;
+ }
+
+ return 0;
+}
+
+static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
+ int bind, int ref)
+{
+ unsigned char *b = skb_tail_pointer(skb);
+ struct tcf_ct *c = to_ct(a);
+ struct tcf_ct_params *p;
+
+ struct tc_ct opt = {
+ .index = c->tcf_index,
+ .refcnt = refcount_read(&c->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&c->tcf_bindcnt) - bind,
+ };
+ struct tcf_t t;
+
+ spin_lock_bh(&c->tcf_lock);
+ p = rcu_dereference_protected(c->params,
+ lockdep_is_held(&c->tcf_lock));
+ opt.action = c->tcf_action;
+
+ if (tcf_ct_dump_key_val(skb,
+ &p->ct_action, TCA_CT_ACTION,
+ NULL, TCA_CT_UNSPEC,
+ sizeof(p->ct_action)))
+ goto nla_put_failure;
+
+ if (p->ct_action & TCA_CT_ACT_CLEAR)
+ goto skip_dump;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
+ tcf_ct_dump_key_val(skb,
+ &p->mark, TCA_CT_MARK,
+ &p->mark_mask, TCA_CT_MARK_MASK,
+ sizeof(p->mark)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
+ tcf_ct_dump_key_val(skb,
+ p->labels, TCA_CT_LABELS,
+ p->labels_mask, TCA_CT_LABELS_MASK,
+ sizeof(p->labels)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
+ tcf_ct_dump_key_val(skb,
+ &p->zone, TCA_CT_ZONE,
+ NULL, TCA_CT_UNSPEC,
+ sizeof(p->zone)))
+ goto nla_put_failure;
+
+ if (tcf_ct_dump_nat(skb, p))
+ goto nla_put_failure;
+
+skip_dump:
+ if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt))
+ goto nla_put_failure;
+
+ tcf_tm_dump(&t, &c->tcf_tm);
+ if (nla_put_64bit(skb, TCA_CT_TM, sizeof(t), &t, TCA_CT_PAD))
+ goto nla_put_failure;
+ spin_unlock_bh(&c->tcf_lock);
+
+ return skb->len;
+nla_put_failure:
+ spin_unlock_bh(&c->tcf_lock);
+ nlmsg_trim(skb, b);
+ return -1;
+}
+
+static int tcf_ct_walker(struct net *net, struct sk_buff *skb,
+ struct netlink_callback *cb, int type,
+ const struct tc_action_ops *ops,
+ struct netlink_ext_ack *extack)
+{
+ struct tc_action_net *tn = net_generic(net, ct_net_id);
+
+ return tcf_generic_walker(tn, skb, cb, type, ops, extack);
+}
+
+static int tcf_ct_search(struct net *net, struct tc_action **a, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, ct_net_id);
+
+ return tcf_idr_search(tn, a, index);
+}
+
+static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
+ u64 lastuse, bool hw)
+{
+ struct tcf_ct *c = to_ct(a);
+
+ _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
+
+ if (hw)
+ _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
+ bytes, packets);
+ c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse);
+}
+
+static struct tc_action_ops act_ct_ops = {
+ .kind = "ct",
+ .id = TCA_ID_CT,
+ .owner = THIS_MODULE,
+ .act = tcf_ct_act,
+ .dump = tcf_ct_dump,
+ .init = tcf_ct_init,
+ .cleanup = tcf_ct_cleanup,
+ .walk = tcf_ct_walker,
+ .lookup = tcf_ct_search,
+ .stats_update = tcf_stats_update,
+ .size = sizeof(struct tcf_ct),
+};
+
+static __net_init int ct_init_net(struct net *net)
+{
+ unsigned int n_bits = FIELD_SIZEOF(struct tcf_ct_params, labels) * 8;
+ struct tc_ct_action_net *tn = net_generic(net, ct_net_id);
+
+ if (nf_connlabels_get(net, n_bits - 1)) {
+ tn->labels = false;
+ pr_err("act_ct: Failed to set connlabels length");
+ } else {
+ tn->labels = true;
+ }
+
+ return tc_action_net_init(&tn->tn, &act_ct_ops);
+}
+
+static void __net_exit ct_exit_net(struct list_head *net_list)
+{
+ struct net *net;
+
+ rtnl_lock();
+ list_for_each_entry(net, net_list, exit_list) {
+ struct tc_ct_action_net *tn = net_generic(net, ct_net_id);
+
+ if (tn->labels)
+ nf_connlabels_put(net);
+ }
+ rtnl_unlock();
+
+ tc_action_net_exit(net_list, ct_net_id);
+}
+
+static struct pernet_operations ct_net_ops = {
+ .init = ct_init_net,
+ .exit_batch = ct_exit_net,
+ .id = &ct_net_id,
+ .size = sizeof(struct tc_ct_action_net),
+};
+
+static int __init ct_init_module(void)
+{
+ return tcf_register_action(&act_ct_ops, &ct_net_ops);
+}
+
+static void __exit ct_cleanup_module(void)
+{
+ tcf_unregister_action(&act_ct_ops, &ct_net_ops);
+}
+
+module_init(ct_init_module);
+module_exit(ct_cleanup_module);
+MODULE_AUTHOR("Paul Blakey <paulb@mellanox.com>");
+MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>");
+MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>");
+MODULE_DESCRIPTION("Connection tracking action");
+MODULE_LICENSE("GPL v2");
+
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ad36bbc..4a7331c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -35,6 +35,7 @@
#include <net/tc_act/tc_police.h>
#include <net/tc_act/tc_sample.h>
#include <net/tc_act/tc_skbedit.h>
+#include <net/tc_act/tc_ct.h>
extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
@@ -3266,6 +3267,10 @@ int tc_setup_flow_action(struct flow_action *flow_action,
entry->police.burst = tcf_police_tcfp_burst(act);
entry->police.rate_bytes_ps =
tcf_police_rate_bytes_ps(act);
+ } else if (is_tcf_ct(act)) {
+ entry->id = FLOW_ACTION_CT;
+ entry->ct.action = tcf_ct_action(act);
+ entry->ct.zone = tcf_ct_zone(act);
} else {
goto err_out;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v6 3/4] net/sched: cls_flower: Add matching on conntrack info
From: Paul Blakey @ 2019-07-09 7:30 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
In-Reply-To: <1562657451-20819-1-git-send-email-paulb@mellanox.com>
New matches for conntrack mark, label, zone, and state.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/uapi/linux/pkt_cls.h | 16 ++++++
net/sched/cls_flower.c | 127 +++++++++++++++++++++++++++++++++++++++++--
2 files changed, 138 insertions(+), 5 deletions(-)
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 7c9d701..6992df1 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -536,12 +536,28 @@ enum {
TCA_FLOWER_KEY_PORT_DST_MIN, /* be16 */
TCA_FLOWER_KEY_PORT_DST_MAX, /* be16 */
+ TCA_FLOWER_KEY_CT_STATE, /* u16 */
+ TCA_FLOWER_KEY_CT_STATE_MASK, /* u16 */
+ TCA_FLOWER_KEY_CT_ZONE, /* u16 */
+ TCA_FLOWER_KEY_CT_ZONE_MASK, /* u16 */
+ TCA_FLOWER_KEY_CT_MARK, /* u32 */
+ TCA_FLOWER_KEY_CT_MARK_MASK, /* u32 */
+ TCA_FLOWER_KEY_CT_LABELS, /* u128 */
+ TCA_FLOWER_KEY_CT_LABELS_MASK, /* u128 */
+
__TCA_FLOWER_MAX,
};
#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
enum {
+ TCA_FLOWER_KEY_CT_FLAGS_NEW = 1 << 0, /* Beginning of a new connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */
+};
+
+enum {
TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
* TCA_FLOWER_KEY_ENC_OPT_GENEVE_
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index ce2e9b1..d90ec2c 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -26,6 +26,8 @@
#include <net/dst.h>
#include <net/dst_metadata.h>
+#include <uapi/linux/netfilter/nf_conntrack_common.h>
+
struct fl_flow_key {
struct flow_dissector_key_meta meta;
struct flow_dissector_key_control control;
@@ -54,6 +56,7 @@ struct fl_flow_key {
struct flow_dissector_key_enc_opts enc_opts;
struct flow_dissector_key_ports tp_min;
struct flow_dissector_key_ports tp_max;
+ struct flow_dissector_key_ct ct;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct fl_flow_mask_range {
@@ -272,14 +275,27 @@ static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask,
return __fl_lookup(mask, mkey);
}
+static u16 fl_ct_info_to_flower_map[] = {
+ [IP_CT_ESTABLISHED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED,
+ [IP_CT_RELATED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_RELATED,
+ [IP_CT_ESTABLISHED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED,
+ [IP_CT_RELATED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_RELATED,
+ [IP_CT_NEW] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_NEW,
+};
+
static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct cls_fl_head *head = rcu_dereference_bh(tp->root);
- struct cls_fl_filter *f;
- struct fl_flow_mask *mask;
- struct fl_flow_key skb_key;
struct fl_flow_key skb_mkey;
+ struct fl_flow_key skb_key;
+ struct fl_flow_mask *mask;
+ struct cls_fl_filter *f;
list_for_each_entry_rcu(mask, &head->masks, list) {
fl_clear_masked_range(&skb_key, mask);
@@ -290,6 +306,9 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
*/
skb_key.basic.n_proto = skb->protocol;
skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key);
+ skb_flow_dissect_ct(skb, &mask->dissector, &skb_key,
+ fl_ct_info_to_flower_map,
+ ARRAY_SIZE(fl_ct_info_to_flower_map));
skb_flow_dissect(skb, &mask->dissector, &skb_key, 0);
fl_set_masked_key(&skb_mkey, &skb_key, mask);
@@ -704,6 +723,16 @@ static void *fl_get(struct tcf_proto *tp, u32 handle)
[TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_ENC_OPTS] = { .type = NLA_NESTED },
[TCA_FLOWER_KEY_ENC_OPTS_MASK] = { .type = NLA_NESTED },
+ [TCA_FLOWER_KEY_CT_STATE] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CT_STATE_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CT_ZONE] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CT_ZONE_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CT_MARK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_CT_MARK_MASK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_CT_LABELS] = { .type = NLA_BINARY,
+ .len = 128 / BITS_PER_BYTE },
+ [TCA_FLOWER_KEY_CT_LABELS_MASK] = { .type = NLA_BINARY,
+ .len = 128 / BITS_PER_BYTE },
};
static const struct nla_policy
@@ -725,11 +754,11 @@ static void fl_set_key_val(struct nlattr **tb,
{
if (!tb[val_type])
return;
- memcpy(val, nla_data(tb[val_type]), len);
+ nla_memcpy(val, tb[val_type], len);
if (mask_type == TCA_FLOWER_UNSPEC || !tb[mask_type])
memset(mask, 0xff, len);
else
- memcpy(mask, nla_data(tb[mask_type]), len);
+ nla_memcpy(mask, tb[mask_type], len);
}
static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key,
@@ -1015,6 +1044,51 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
return 0;
}
+static int fl_set_key_ct(struct nlattr **tb,
+ struct flow_dissector_key_ct *key,
+ struct flow_dissector_key_ct *mask,
+ struct netlink_ext_ack *extack)
+{
+ if (tb[TCA_FLOWER_KEY_CT_STATE]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK)) {
+ NL_SET_ERR_MSG(extack, "Conntrack isn't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, &key->ct_state, TCA_FLOWER_KEY_CT_STATE,
+ &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK,
+ sizeof(key->ct_state));
+ }
+ if (tb[TCA_FLOWER_KEY_CT_ZONE]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) {
+ NL_SET_ERR_MSG(extack, "Conntrack zones isn't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, &key->ct_zone, TCA_FLOWER_KEY_CT_ZONE,
+ &mask->ct_zone, TCA_FLOWER_KEY_CT_ZONE_MASK,
+ sizeof(key->ct_zone));
+ }
+ if (tb[TCA_FLOWER_KEY_CT_MARK]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) {
+ NL_SET_ERR_MSG(extack, "Conntrack mark isn't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, &key->ct_mark, TCA_FLOWER_KEY_CT_MARK,
+ &mask->ct_mark, TCA_FLOWER_KEY_CT_MARK_MASK,
+ sizeof(key->ct_mark));
+ }
+ if (tb[TCA_FLOWER_KEY_CT_LABELS]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) {
+ NL_SET_ERR_MSG(extack, "Conntrack labels aren't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, key->ct_labels, TCA_FLOWER_KEY_CT_LABELS,
+ mask->ct_labels, TCA_FLOWER_KEY_CT_LABELS_MASK,
+ sizeof(key->ct_labels));
+ }
+
+ return 0;
+}
+
static int fl_set_key(struct net *net, struct nlattr **tb,
struct fl_flow_key *key, struct fl_flow_key *mask,
struct netlink_ext_ack *extack)
@@ -1224,6 +1298,10 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
return ret;
}
+ ret = fl_set_key_ct(tb, &key->ct, &mask->ct, extack);
+ if (ret)
+ return ret;
+
if (tb[TCA_FLOWER_KEY_FLAGS])
ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
@@ -1324,6 +1402,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
FLOW_DISSECTOR_KEY_ENC_IP, enc_ip);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_OPTS, enc_opts);
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_CT, ct);
skb_flow_dissector_init(dissector, keys, cnt);
}
@@ -2078,6 +2158,40 @@ static int fl_dump_key_geneve_opt(struct sk_buff *skb,
return -EMSGSIZE;
}
+static int fl_dump_key_ct(struct sk_buff *skb,
+ struct flow_dissector_key_ct *key,
+ struct flow_dissector_key_ct *mask)
+{
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK) &&
+ fl_dump_key_val(skb, &key->ct_state, TCA_FLOWER_KEY_CT_STATE,
+ &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK,
+ sizeof(key->ct_state)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
+ fl_dump_key_val(skb, &key->ct_zone, TCA_FLOWER_KEY_CT_ZONE,
+ &mask->ct_zone, TCA_FLOWER_KEY_CT_ZONE_MASK,
+ sizeof(key->ct_zone)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
+ fl_dump_key_val(skb, &key->ct_mark, TCA_FLOWER_KEY_CT_MARK,
+ &mask->ct_mark, TCA_FLOWER_KEY_CT_MARK_MASK,
+ sizeof(key->ct_mark)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
+ fl_dump_key_val(skb, &key->ct_labels, TCA_FLOWER_KEY_CT_LABELS,
+ &mask->ct_labels, TCA_FLOWER_KEY_CT_LABELS_MASK,
+ sizeof(key->ct_labels)))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
struct flow_dissector_key_enc_opts *enc_opts)
{
@@ -2311,6 +2425,9 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
fl_dump_key_enc_opt(skb, &key->enc_opts, &mask->enc_opts))
goto nla_put_failure;
+ if (fl_dump_key_ct(skb, &key->ct, &mask->ct))
+ goto nla_put_failure;
+
if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
goto nla_put_failure;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v6 2/4] net/flow_dissector: add connection tracking dissection
From: Paul Blakey @ 2019-07-09 7:30 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
In-Reply-To: <1562657451-20819-1-git-send-email-paulb@mellanox.com>
Retreives connection tracking zone, mark, label, and state from
a SKB.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/linux/skbuff.h | 10 ++++++++++
include/net/flow_dissector.h | 15 +++++++++++++++
net/core/flow_dissector.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 69 insertions(+)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b5d427b..1dcb674 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1324,6 +1324,16 @@ void skb_flow_dissect_meta(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container);
+/* Gets a skb connection tracking info, ctinfo map should be a
+ * a map of mapsize to translate enum ip_conntrack_info states
+ * to user states.
+ */
+void
+skb_flow_dissect_ct(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container,
+ u16 *ctinfo_map,
+ size_t mapsize);
void
skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 02478e4..90bd210 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -208,6 +208,20 @@ struct flow_dissector_key_meta {
int ingress_ifindex;
};
+/**
+ * struct flow_dissector_key_ct:
+ * @ct_state: conntrack state after converting with map
+ * @ct_mark: conttrack mark
+ * @ct_zone: conntrack zone
+ * @ct_labels: conntrack labels
+ */
+struct flow_dissector_key_ct {
+ u16 ct_state;
+ u16 ct_zone;
+ u32 ct_mark;
+ u32 ct_labels[4];
+};
+
enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */
FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
@@ -234,6 +248,7 @@ enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */
FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */
FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */
+ FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */
FLOW_DISSECTOR_KEY_MAX,
};
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 01ad60b..3e6fedb 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -27,6 +27,10 @@
#include <scsi/fc/fc_fcoe.h>
#include <uapi/linux/batadv_packet.h>
#include <linux/bpf.h>
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_labels.h>
+#endif
static DEFINE_MUTEX(flow_dissector_mutex);
@@ -232,6 +236,46 @@ void skb_flow_dissect_meta(const struct sk_buff *skb,
}
void
+skb_flow_dissect_ct(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container,
+ u16 *ctinfo_map,
+ size_t mapsize)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ struct flow_dissector_key_ct *key;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn_labels *cl;
+ struct nf_conn *ct;
+
+ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CT))
+ return;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct)
+ return;
+
+ key = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_CT,
+ target_container);
+
+ if (ctinfo < mapsize)
+ key->ct_state = ctinfo_map[ctinfo];
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)
+ key->ct_zone = ct->zone.id;
+#endif
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
+ key->ct_mark = ct->mark;
+#endif
+
+ cl = nf_ct_labels_find(ct);
+ if (cl)
+ memcpy(key->ct_labels, cl->bits, sizeof(key->ct_labels));
+#endif /* CONFIG_NF_CONNTRACK */
+}
+EXPORT_SYMBOL(skb_flow_dissect_ct);
+
+void
skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v6 0/4] net/sched: Introduce tc connection tracking
From: Paul Blakey @ 2019-07-09 7:30 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
Hi,
This patch series add connection tracking capabilities in tc sw datapath.
It does so via a new tc action, called act_ct, and new tc flower classifier matching
on conntrack state, mark and label.
Usage is as follows:
$ tc qdisc add dev ens1f0_0 ingress
$ tc qdisc add dev ens1f0_1 ingress
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 0 proto ip \
flower ip_proto tcp ct_state -trk \
action ct zone 2 pipe \
action goto chain 2
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 2 proto ip \
flower ct_state +trk+new \
action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 2 proto ip \
flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
action ct nat pipe \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_1 ingress \
prio 1 chain 0 proto ip \
flower ip_proto tcp ct_state -trk \
action ct zone 2 pipe \
action goto chain 1
$ tc filter add dev ens1f0_1 ingress \
prio 1 chain 1 proto ip \
flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
action ct nat pipe \
action mirred egress redirect dev ens1f0_0
The pattern used in the design here closely resembles OvS, as the plan is to also offload
OvS conntrack rules to tc. OvS datapath rules uses it's recirculation mechanism to send
specific packets to conntrack, and return with the new conntrack state (ct_state) on some other recirc_id
to be matched again (we use goto chain for this).
This results in the following OvS datapath rules:
recirc_id(0),in_port(ens1f0_0),ct_state(-trk),... actions:ct(zone=2),recirc(2)
recirc_id(2),in_port(ens1f0_0),ct_state(+new+trk),ct_mark(0xbb),... actions:ct(commit,zone=2,nat(src=5.5.5.7),mark=0xbb),ens1f0_1
recirc_id(2),in_port(ens1f0_0),ct_state(+est+trk),ct_mark(0xbb),... actions:ct(zone=2,nat),ens1f0_1
recirc_id(1),in_port(ens1f0_1),ct_state(-trk),... actions:ct(zone=2),recirc(1)
recirc_id(1),in_port(ens1f0_1),ct_state(+est+trk),... actions:ct(zone=2,nat),ens1f0_0
Changelog:
See individual patches.
Paul Blakey (4):
net/sched: Introduce action ct
net/flow_dissector: add connection tracking dissection
net/sched: cls_flower: Add matching on conntrack info
tc-tests: Add tc action ct tests
include/linux/skbuff.h | 10 +
include/net/flow_dissector.h | 15 +
include/net/flow_offload.h | 5 +
include/net/tc_act/tc_ct.h | 63 ++
include/uapi/linux/pkt_cls.h | 17 +
include/uapi/linux/tc_act/tc_ct.h | 41 +
net/core/flow_dissector.c | 44 +
net/sched/Kconfig | 11 +
net/sched/Makefile | 1 +
net/sched/act_ct.c | 984 +++++++++++++++++++++
net/sched/cls_api.c | 5 +
net/sched/cls_flower.c | 127 ++-
.../selftests/tc-testing/tc-tests/actions/ct.json | 314 +++++++
13 files changed, 1632 insertions(+), 5 deletions(-)
create mode 100644 include/net/tc_act/tc_ct.h
create mode 100644 include/uapi/linux/tc_act/tc_ct.h
create mode 100644 net/sched/act_ct.c
create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
--
1.8.3.1
^ permalink raw reply
* Re: [PATCH] tipc: ensure skb->lock is initialised
From: Eric Dumazet @ 2019-07-09 7:30 UTC (permalink / raw)
To: Chris Packham, Eric Dumazet, jon.maloy@ericsson.com,
ying.xue@windriver.com, davem@davemloft.net
Cc: netdev@vger.kernel.org, tipc-discussion@lists.sourceforge.net,
linux-kernel@vger.kernel.org
In-Reply-To: <87fd2150548041219fc42bce80b63c9c@svr-chch-ex1.atlnz.lc>
On 7/8/19 11:13 PM, Chris Packham wrote:
> On 9/07/19 8:43 AM, Chris Packham wrote:
>> On 8/07/19 8:18 PM, Eric Dumazet wrote:
>>>
>>>
>>> On 7/8/19 12:53 AM, Chris Packham wrote:
>>>> tipc_named_node_up() creates a skb list. It passes the list to
>>>> tipc_node_xmit() which has some code paths that can call
>>>> skb_queue_purge() which relies on the list->lock being initialised.
>>>> Ensure tipc_named_node_up() uses skb_queue_head_init() so that the lock
>>>> is explicitly initialised.
>>>>
>>>> Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
>>>
>>> I would rather change the faulty skb_queue_purge() to __skb_queue_purge()
>>>
>>
>> Makes sense. I'll look at that for v2.
>>
>
> Actually maybe not. tipc_rcast_xmit(), tipc_node_xmit_skb(),
> tipc_send_group_msg(), __tipc_sendmsg(), __tipc_sendstream(), and
> tipc_sk_timeout() all use skb_queue_head_init(). So my original change
> brings tipc_named_node_up() into line with them.
>
> I think it should be safe for tipc_node_xmit() to use
> __skb_queue_purge() since all the callers seem to have exclusive access
> to the list of skbs. It still seems that the callers should all use
> skb_queue_head_init() for consistency.
>
No, tipc does not use the list lock (it relies on the socket lock)
and therefore should consistently use __skb_queue_head_init()
instead of skb_queue_head_init()
Using a spinlock to protect a local list makes no sense really,
it spreads false sense of correctness.
tipc_link_xmit() for example never acquires the spinlock,
yet uses skb_peek() and __skb_dequeue()
It is time to clean all this mess.
^ permalink raw reply
* Re: [PATCH net-next v3 3/3] net: stmmac: Introducing support for Page Pool
From: Ilias Apalodimas @ 2019-07-09 7:23 UTC (permalink / raw)
To: David Miller
Cc: Jose.Abreu, linux-kernel, netdev, linux-stm32, linux-arm-kernel,
Joao.Pinto, peppe.cavallaro, alexandre.torgue, brouer, arnd
In-Reply-To: <20190708.141515.1767939731073284700.davem@davemloft.net>
Hello,
> From: Jose Abreu <Jose.Abreu@synopsys.com>
> Date: Mon, 8 Jul 2019 16:08:07 +0000
>
> > From: Ilias Apalodimas <ilias.apalodimas@linaro.org> | Date: Fri, Jul
> > 05, 2019 at 16:24:53
> >
> >> Well ideally we'd like to get the change in before the merge window ourselves,
> >> since we dont want to remove->re-add the same function in stable kernels. If
> >> that doesn't go in i am fine fixing it in the next merge window i guess, since
> >> it offers substantial speedups
> >
> > I think the series is marked as "Changes Requested" in patchwork. What's
> > the status of this ?
>
> That means I expect a respin based upon feedback or similar. If Ilias and
> you agreed to put this series in as-is, my apologies and just resend the
> series with appropriate ACK and Review tags added.
The patch from Ivan did get merged, can you change the free call to
page_pool_destroy and re-spin? You can add my acked-by
Thanks
/Ilias
^ permalink raw reply
* Re: [PATCH net-next 12/16] net/mlx5e: Split open/close ICOSQ into stages
From: Jiri Pirko @ 2019-07-09 7:23 UTC (permalink / raw)
To: Tariq Toukan
Cc: David S. Miller, netdev, Eran Ben Elisha, ayal, jiri,
Saeed Mahameed, moshe
In-Reply-To: <1562500388-16847-13-git-send-email-tariqt@mellanox.com>
Sun, Jul 07, 2019 at 01:53:04PM CEST, tariqt@mellanox.com wrote:
>From: Aya Levin <ayal@mellanox.com>
>
>Align ICOSQ open/close behaviour with RQ and SQ. Split open flow into
>open and activate where open handles creation and activate enables the
>queue. Do a symmetric thing in close flow: split into close and
>deactivate.
>
>Signed-off-by: Aya Levin <ayal@mellanox.com>
>Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
^ permalink raw reply
* Re: [PATCH nf-next 1/3] netfilter: nf_nat_proto: add nf_nat_bridge_ops support
From: kbuild test robot @ 2019-07-09 7:04 UTC (permalink / raw)
To: wenxu; +Cc: kbuild-all, pablo, fw, netfilter-devel, netdev
In-Reply-To: <1562574567-8293-1-git-send-email-wenxu@ucloud.cn>
[-- Attachment #1: Type: text/plain, Size: 2475 bytes --]
Hi,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on nf-next/master]
url: https://github.com/0day-ci/linux/commits/wenxu-ucloud-cn/netfilter-nf_nat_proto-add-nf_nat_bridge_ops-support/20190709-070304
base: https://kernel.googlesource.com/pub/scm/linux/kernel/git/pablo/nf-next.git master
config: x86_64-randconfig-s1-07091425 (attached as .config)
compiler: gcc-7 (Debian 7.4.0-9) 7.4.0
reproduce:
# save the attached .config to linux build tree
make ARCH=x86_64
If you fix the issue, kindly add following tag
Reported-by: kbuild test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
net/netfilter/nf_nat_proto.c: In function 'nf_nat_bridge_in':
>> net/netfilter/nf_nat_proto.c:1048:10: error: implicit declaration of function 'nf_nat_ipv6_in'; did you mean 'nf_nat_ipv4_in'? [-Werror=implicit-function-declaration]
return nf_nat_ipv6_in(priv, skb, state);
^~~~~~~~~~~~~~
nf_nat_ipv4_in
net/netfilter/nf_nat_proto.c: In function 'nf_nat_bridge_out':
>> net/netfilter/nf_nat_proto.c:1062:10: error: implicit declaration of function 'nf_nat_ipv6_out'; did you mean 'nf_nat_ipv4_out'? [-Werror=implicit-function-declaration]
return nf_nat_ipv6_out(priv, skb, state);
^~~~~~~~~~~~~~~
nf_nat_ipv4_out
cc1: some warnings being treated as errors
vim +1048 net/netfilter/nf_nat_proto.c
1038
1039 #if defined(CONFIG_NF_TABLES_BRIDGE) && IS_ENABLED(CONFIG_NFT_NAT)
1040 static unsigned int
1041 nf_nat_bridge_in(void *priv, struct sk_buff *skb,
1042 const struct nf_hook_state *state)
1043 {
1044 switch (skb->protocol) {
1045 case htons(ETH_P_IP):
1046 return nf_nat_ipv4_in(priv, skb, state);
1047 case htons(ETH_P_IPV6):
> 1048 return nf_nat_ipv6_in(priv, skb, state);
1049 default:
1050 return NF_ACCEPT;
1051 }
1052 }
1053
1054 static unsigned int
1055 nf_nat_bridge_out(void *priv, struct sk_buff *skb,
1056 const struct nf_hook_state *state)
1057 {
1058 switch (skb->protocol) {
1059 case htons(ETH_P_IP):
1060 return nf_nat_ipv4_out(priv, skb, state);
1061 case htons(ETH_P_IPV6):
> 1062 return nf_nat_ipv6_out(priv, skb, state);
1063 default:
1064 return NF_ACCEPT;
1065 }
1066 }
1067
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 34307 bytes --]
^ permalink raw reply
* Re: [PATCH v5 rdma-next 1/6] RDMA/core: Create mmap database and cookie helper functions
From: Leon Romanovsky @ 2019-07-09 7:02 UTC (permalink / raw)
To: Michal Kalderon
Cc: ariel.elior, jgg, dledford, galpress, linux-rdma, davem, netdev
In-Reply-To: <20190708091503.14723-2-michal.kalderon@marvell.com>
On Mon, Jul 08, 2019 at 12:14:58PM +0300, Michal Kalderon wrote:
> Create some common API's for adding entries to a xa_mmap.
> Searching for an entry and freeing one.
>
> The code was copied from the efa driver almost as is, just renamed
> function to be generic and not efa specific.
>
> Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
> ---
> drivers/infiniband/core/device.c | 1 +
> drivers/infiniband/core/rdma_core.c | 1 +
> drivers/infiniband/core/uverbs_cmd.c | 1 +
> drivers/infiniband/core/uverbs_main.c | 105 ++++++++++++++++++++++++++++++++++
> include/rdma/ib_verbs.h | 32 +++++++++++
> 5 files changed, 140 insertions(+)
>
> diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
> index 8a6ccb936dfe..a830c2c5d691 100644
> --- a/drivers/infiniband/core/device.c
> +++ b/drivers/infiniband/core/device.c
> @@ -2521,6 +2521,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
> SET_DEVICE_OP(dev_ops, map_mr_sg_pi);
> SET_DEVICE_OP(dev_ops, map_phys_fmr);
> SET_DEVICE_OP(dev_ops, mmap);
> + SET_DEVICE_OP(dev_ops, mmap_free);
> SET_DEVICE_OP(dev_ops, modify_ah);
> SET_DEVICE_OP(dev_ops, modify_cq);
> SET_DEVICE_OP(dev_ops, modify_device);
> diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
> index ccf4d069c25c..7166741834c8 100644
> --- a/drivers/infiniband/core/rdma_core.c
> +++ b/drivers/infiniband/core/rdma_core.c
> @@ -817,6 +817,7 @@ static void ufile_destroy_ucontext(struct ib_uverbs_file *ufile,
> rdma_restrack_del(&ucontext->res);
>
> ib_dev->ops.dealloc_ucontext(ucontext);
> + rdma_user_mmap_entries_remove_free(ucontext);
> kfree(ucontext);
>
> ufile->ucontext = NULL;
> diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
> index 7ddd0e5bc6b3..44c0600245e4 100644
> --- a/drivers/infiniband/core/uverbs_cmd.c
> +++ b/drivers/infiniband/core/uverbs_cmd.c
> @@ -254,6 +254,7 @@ static int ib_uverbs_get_context(struct uverbs_attr_bundle *attrs)
>
> mutex_init(&ucontext->per_mm_list_lock);
> INIT_LIST_HEAD(&ucontext->per_mm_list);
> + xa_init(&ucontext->mmap_xa);
>
> ret = get_unused_fd_flags(O_CLOEXEC);
> if (ret < 0)
> diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
> index 11c13c1381cf..37507cc27e8c 100644
> --- a/drivers/infiniband/core/uverbs_main.c
> +++ b/drivers/infiniband/core/uverbs_main.c
> @@ -965,6 +965,111 @@ int rdma_user_mmap_io(struct ib_ucontext *ucontext, struct vm_area_struct *vma,
> }
> EXPORT_SYMBOL(rdma_user_mmap_io);
>
> +static inline u64
> +rdma_user_mmap_get_key(const struct rdma_user_mmap_entry *entry)
> +{
> + return (u64)entry->mmap_page << PAGE_SHIFT;
> +}
> +
> +struct rdma_user_mmap_entry *
> +rdma_user_mmap_entry_get(struct ib_ucontext *ucontext, u64 key, u64 len)
> +{
> + struct rdma_user_mmap_entry *entry;
> + u64 mmap_page;
> +
> + mmap_page = key >> PAGE_SHIFT;
> + if (mmap_page > U32_MAX)
> + return NULL;
> +
> + entry = xa_load(&ucontext->mmap_xa, mmap_page);
> + if (!entry || rdma_user_mmap_get_key(entry) != key ||
> + entry->length != len)
> + return NULL;
> +
> + ibdev_dbg(ucontext->device,
> + "mmap: obj[0x%p] key[%#llx] addr[%#llx] len[%#llx] removed\n",
> + entry->obj, key, entry->address, entry->length);
> +
> + return entry;
> +}
> +EXPORT_SYMBOL(rdma_user_mmap_entry_get);
Please add function description in kernel doc format for all newly EXPORT_SYMBOL()
functions you introduced in RDMA/core.
> +
> +/*
> + * Note this locking scheme cannot support removal of entries, except during
> + * ucontext destruction when the core code guarentees no concurrency.
> + */
> +u64 rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext, void *obj,
> + u64 address, u64 length, u8 mmap_flag)
> +{
> + struct rdma_user_mmap_entry *entry;
> + u32 next_mmap_page;
> + int err;
> +
> + entry = kmalloc(sizeof(*entry), GFP_KERNEL);
It is worth to use kzalloc and not kmalloc.
Thanks
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox