diff mbox series

[v11,4/4] kni: add IOVA=VA support in kernel module

Message ID 20191021080324.10659-5-vattunuru@marvell.com (mailing list archive)
State Superseded, archived
Delegated to: Ferruh Yigit
Headers
Series kni: add IOVA=VA mode support |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/Intel-compilation fail Compilation issues
ci/travis-robot success Travis build: passed

Commit Message

Vamsi Krishna Attunuru Oct. 21, 2019, 8:03 a.m. UTC 
  From: Vamsi Attunuru <vattunuru@marvell.com>

Patch adds support for kernel module to work in
IOVA = VA mode by providing address translation
routines to convert IOVA aka user space VA to
kernel virtual addresses.

Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
---
 kernel/linux/kni/compat.h   |  4 ++++
 kernel/linux/kni/kni_dev.h  | 31 ++++++++++++++++++++++++
 kernel/linux/kni/kni_misc.c | 39 +++++++++++++++++++++++-------
 kernel/linux/kni/kni_net.c  | 58 +++++++++++++++++++++++++++++++++++----------
 4 files changed, 110 insertions(+), 22 deletions(-)

Comments

Ferruh Yigit Oct. 21, 2019, 12:02 p.m. UTC | #1 
On 10/21/2019 9:03 AM, vattunuru@marvell.com wrote:
> From: Vamsi Attunuru <vattunuru@marvell.com>
> 
> Patch adds support for kernel module to work in
> IOVA = VA mode by providing address translation
> routines to convert IOVA aka user space VA to
> kernel virtual addresses.
> 
> Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
> Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>

<...>

> +static inline phys_addr_t iova_to_phys(struct task_struct *tsk,
> +				       unsigned long iova)
> +{
> +	unsigned int flags = FOLL_TOUCH;
> +	phys_addr_t offset, phys_addr;
> +	struct page *page = NULL;
> +	int ret;
> +
> +	offset = iova & (PAGE_SIZE - 1);
> +
> +	/* Read one page struct info */
> +	ret =  get_user_pages_remote(tsk, tsk->mm, iova, 1,
> +				     flags, &page, 0, 0);
> +	if (ret < 0)
> +		return 0;
> +
> +	phys_addr = page_to_phys(page) | offset;
> +	put_page(page);
> +
> +	return phys_addr;
> +}
> +
> +static inline void *iova_to_kva(struct task_struct *tsk, unsigned long iova)
> +{
> +	return phys_to_virt(iova_to_phys(tsk, iova));
> +}

Do you have any measurement for the performance affect of this change?

> +
>  void kni_net_release_fifo_phy(struct kni_dev *kni);
>  void kni_net_rx(struct kni_dev *kni);
>  void kni_net_init(struct net_device *dev);
> diff --git a/kernel/linux/kni/kni_misc.c b/kernel/linux/kni/kni_misc.c
> index 2b75502..7af7ab4 100644
> --- a/kernel/linux/kni/kni_misc.c
> +++ b/kernel/linux/kni/kni_misc.c
> @@ -348,15 +348,36 @@ kni_ioctl_create(struct net *net, uint32_t ioctl_num,
>  	strncpy(kni->name, dev_info.name, RTE_KNI_NAMESIZE);
>  
>  	/* Translate user space info into kernel space info */
> -	kni->tx_q = phys_to_virt(dev_info.tx_phys);
> -	kni->rx_q = phys_to_virt(dev_info.rx_phys);
> -	kni->alloc_q = phys_to_virt(dev_info.alloc_phys);
> -	kni->free_q = phys_to_virt(dev_info.free_phys);
> -
> -	kni->req_q = phys_to_virt(dev_info.req_phys);
> -	kni->resp_q = phys_to_virt(dev_info.resp_phys);
> -	kni->sync_va = dev_info.sync_va;
> -	kni->sync_kva = phys_to_virt(dev_info.sync_phys);
> +	if (dev_info.iova_mode) {
> +#ifdef HAVE_IOVA_TO_KVA_MAPPING_SUPPORT

Do you think is a runtime check required, for the case code has been compiled on
a box that has newer kernel but run in a box with older kernel?
Not sure about it myself either...

<...>

> @@ -62,6 +76,24 @@ kva2data_kva(struct rte_kni_mbuf *m)
>  	return phys_to_virt(m->buf_physaddr + m->data_off);
>  }
>  
> +static inline void *
> +get_kva(struct kni_dev *kni, void *pa)
> +{
> +	if (kni->iova_mode == 1)

This check done multiple times per packet, I wonder if this can be prevented,
again even with the original mode do you have any numbers related to the
performance affect of this check?

Thanks,
ferruh
diff mbox series

Patch

diff --git a/kernel/linux/kni/compat.h b/kernel/linux/kni/compat.h
index 562d8bf..b5e8914 100644
--- a/kernel/linux/kni/compat.h
+++ b/kernel/linux/kni/compat.h
@@ -121,3 +121,7 @@ 
 #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 11, 0)
 #define HAVE_SIGNAL_FUNCTIONS_OWN_HEADER
 #endif
+
+#if KERNEL_VERSION(4, 8, 0) <= LINUX_VERSION_CODE
+#define HAVE_IOVA_TO_KVA_MAPPING_SUPPORT
+#endif
diff --git a/kernel/linux/kni/kni_dev.h b/kernel/linux/kni/kni_dev.h
index c1ca678..abe9b14 100644
--- a/kernel/linux/kni/kni_dev.h
+++ b/kernel/linux/kni/kni_dev.h
@@ -41,6 +41,8 @@  struct kni_dev {
 	/* kni list */
 	struct list_head list;
 
+	uint8_t iova_mode;
+
 	uint32_t core_id;            /* Core ID to bind */
 	char name[RTE_KNI_NAMESIZE]; /* Network device name */
 	struct task_struct *pthread;
@@ -84,8 +86,37 @@  struct kni_dev {
 	void *va[MBUF_BURST_SZ];
 	void *alloc_pa[MBUF_BURST_SZ];
 	void *alloc_va[MBUF_BURST_SZ];
+
+	struct task_struct *usr_tsk;
 };
 
+static inline phys_addr_t iova_to_phys(struct task_struct *tsk,
+				       unsigned long iova)
+{
+	unsigned int flags = FOLL_TOUCH;
+	phys_addr_t offset, phys_addr;
+	struct page *page = NULL;
+	int ret;
+
+	offset = iova & (PAGE_SIZE - 1);
+
+	/* Read one page struct info */
+	ret =  get_user_pages_remote(tsk, tsk->mm, iova, 1,
+				     flags, &page, 0, 0);
+	if (ret < 0)
+		return 0;
+
+	phys_addr = page_to_phys(page) | offset;
+	put_page(page);
+
+	return phys_addr;
+}
+
+static inline void *iova_to_kva(struct task_struct *tsk, unsigned long iova)
+{
+	return phys_to_virt(iova_to_phys(tsk, iova));
+}
+
 void kni_net_release_fifo_phy(struct kni_dev *kni);
 void kni_net_rx(struct kni_dev *kni);
 void kni_net_init(struct net_device *dev);
diff --git a/kernel/linux/kni/kni_misc.c b/kernel/linux/kni/kni_misc.c
index 2b75502..7af7ab4 100644
--- a/kernel/linux/kni/kni_misc.c
+++ b/kernel/linux/kni/kni_misc.c
@@ -348,15 +348,36 @@  kni_ioctl_create(struct net *net, uint32_t ioctl_num,
 	strncpy(kni->name, dev_info.name, RTE_KNI_NAMESIZE);
 
 	/* Translate user space info into kernel space info */
-	kni->tx_q = phys_to_virt(dev_info.tx_phys);
-	kni->rx_q = phys_to_virt(dev_info.rx_phys);
-	kni->alloc_q = phys_to_virt(dev_info.alloc_phys);
-	kni->free_q = phys_to_virt(dev_info.free_phys);
-
-	kni->req_q = phys_to_virt(dev_info.req_phys);
-	kni->resp_q = phys_to_virt(dev_info.resp_phys);
-	kni->sync_va = dev_info.sync_va;
-	kni->sync_kva = phys_to_virt(dev_info.sync_phys);
+	if (dev_info.iova_mode) {
+#ifdef HAVE_IOVA_TO_KVA_MAPPING_SUPPORT
+		kni->tx_q = iova_to_kva(current, dev_info.tx_phys);
+		kni->rx_q = iova_to_kva(current, dev_info.rx_phys);
+		kni->alloc_q = iova_to_kva(current, dev_info.alloc_phys);
+		kni->free_q = iova_to_kva(current, dev_info.free_phys);
+
+		kni->req_q = iova_to_kva(current, dev_info.req_phys);
+		kni->resp_q = iova_to_kva(current, dev_info.resp_phys);
+		kni->sync_va = dev_info.sync_va;
+		kni->sync_kva = iova_to_kva(current, dev_info.sync_phys);
+		kni->usr_tsk = current;
+		kni->iova_mode = 1;
+#else
+		pr_err("KNI module does not support IOVA to VA translation\n");
+		return -EINVAL;
+#endif
+	} else {
+
+		kni->tx_q = phys_to_virt(dev_info.tx_phys);
+		kni->rx_q = phys_to_virt(dev_info.rx_phys);
+		kni->alloc_q = phys_to_virt(dev_info.alloc_phys);
+		kni->free_q = phys_to_virt(dev_info.free_phys);
+
+		kni->req_q = phys_to_virt(dev_info.req_phys);
+		kni->resp_q = phys_to_virt(dev_info.resp_phys);
+		kni->sync_va = dev_info.sync_va;
+		kni->sync_kva = phys_to_virt(dev_info.sync_phys);
+		kni->iova_mode = 0;
+	}
 
 	kni->mbuf_size = dev_info.mbuf_size;
 
diff --git a/kernel/linux/kni/kni_net.c b/kernel/linux/kni/kni_net.c
index f25b127..e95207b 100644
--- a/kernel/linux/kni/kni_net.c
+++ b/kernel/linux/kni/kni_net.c
@@ -36,6 +36,20 @@  static void kni_net_rx_normal(struct kni_dev *kni);
 /* kni rx function pointer, with default to normal rx */
 static kni_net_rx_t kni_net_rx_func = kni_net_rx_normal;
 
+/* iova to kernel virtual address */
+static inline void *
+iova2kva(struct kni_dev *kni, void *iova)
+{
+	return phys_to_virt(iova_to_phys(kni->usr_tsk, (unsigned long)iova));
+}
+
+static inline void *
+iova2data_kva(struct kni_dev *kni, struct rte_kni_mbuf *m)
+{
+	return phys_to_virt(iova_to_phys(kni->usr_tsk, m->buf_physaddr) +
+			    m->data_off);
+}
+
 /* physical address to kernel virtual address */
 static void *
 pa2kva(void *pa)
@@ -62,6 +76,24 @@  kva2data_kva(struct rte_kni_mbuf *m)
 	return phys_to_virt(m->buf_physaddr + m->data_off);
 }
 
+static inline void *
+get_kva(struct kni_dev *kni, void *pa)
+{
+	if (kni->iova_mode == 1)
+		return iova2kva(kni, pa);
+
+	return pa2kva(pa);
+}
+
+static inline void *
+get_data_kva(struct kni_dev *kni, void *pkt_kva)
+{
+	if (kni->iova_mode == 1)
+		return iova2data_kva(kni, pkt_kva);
+
+	return kva2data_kva(pkt_kva);
+}
+
 /*
  * It can be called to process the request.
  */
@@ -178,7 +210,7 @@  kni_fifo_trans_pa2va(struct kni_dev *kni,
 			return;
 
 		for (i = 0; i < num_rx; i++) {
-			kva = pa2kva(kni->pa[i]);
+			kva = get_kva(kni, kni->pa[i]);
 			kni->va[i] = pa2va(kni->pa[i], kva);
 
 			kva_nb_segs = kva->nb_segs;
@@ -266,8 +298,8 @@  kni_net_tx(struct sk_buff *skb, struct net_device *dev)
 	if (likely(ret == 1)) {
 		void *data_kva;
 
-		pkt_kva = pa2kva(pkt_pa);
-		data_kva = kva2data_kva(pkt_kva);
+		pkt_kva = get_kva(kni, pkt_pa);
+		data_kva = get_data_kva(kni, pkt_kva);
 		pkt_va = pa2va(pkt_pa, pkt_kva);
 
 		len = skb->len;
@@ -338,9 +370,9 @@  kni_net_rx_normal(struct kni_dev *kni)
 
 	/* Transfer received packets to netif */
 	for (i = 0; i < num_rx; i++) {
-		kva = pa2kva(kni->pa[i]);
+		kva = get_kva(kni, kni->pa[i]);
 		len = kva->pkt_len;
-		data_kva = kva2data_kva(kva);
+		data_kva = get_data_kva(kni, kva);
 		kni->va[i] = pa2va(kni->pa[i], kva);
 
 		skb = netdev_alloc_skb(dev, len);
@@ -437,9 +469,9 @@  kni_net_rx_lo_fifo(struct kni_dev *kni)
 		num = ret;
 		/* Copy mbufs */
 		for (i = 0; i < num; i++) {
-			kva = pa2kva(kni->pa[i]);
+			kva = get_kva(kni, kni->pa[i]);
 			len = kva->data_len;
-			data_kva = kva2data_kva(kva);
+			data_kva = get_data_kva(kni, kva);
 			kni->va[i] = pa2va(kni->pa[i], kva);
 
 			while (kva->next) {
@@ -449,8 +481,8 @@  kni_net_rx_lo_fifo(struct kni_dev *kni)
 				kva = next_kva;
 			}
 
-			alloc_kva = pa2kva(kni->alloc_pa[i]);
-			alloc_data_kva = kva2data_kva(alloc_kva);
+			alloc_kva = get_kva(kni, kni->alloc_pa[i]);
+			alloc_data_kva = get_data_kva(kni, alloc_kva);
 			kni->alloc_va[i] = pa2va(kni->alloc_pa[i], alloc_kva);
 
 			memcpy(alloc_data_kva, data_kva, len);
@@ -517,9 +549,9 @@  kni_net_rx_lo_fifo_skb(struct kni_dev *kni)
 
 	/* Copy mbufs to sk buffer and then call tx interface */
 	for (i = 0; i < num; i++) {
-		kva = pa2kva(kni->pa[i]);
+		kva = get_kva(kni, kni->pa[i]);
 		len = kva->pkt_len;
-		data_kva = kva2data_kva(kva);
+		data_kva = get_data_kva(kni, kva);
 		kni->va[i] = pa2va(kni->pa[i], kva);
 
 		skb = netdev_alloc_skb(dev, len);
@@ -550,8 +582,8 @@  kni_net_rx_lo_fifo_skb(struct kni_dev *kni)
 					break;
 
 				prev_kva = kva;
-				kva = pa2kva(kva->next);
-				data_kva = kva2data_kva(kva);
+				kva = get_kva(kni, kva->next);
+				data_kva = get_data_kva(kni, kva);
 				/* Convert physical address to virtual address */
 				prev_kva->next = pa2va(prev_kva->next, kva);
 			}