DPDK-dev Archive on lore.kernel.org
 help / color / Atom feed
From: <vattunuru@marvell.com>
To: <dev@dpdk.org>
Cc: <ferruh.yigit@intel.com>, <olivier.matz@6wind.com>,
	<arybchenko@solarflare.com>,
	Kiran Kumar K <kirankumark@marvell.com>,
	"Vamsi Attunuru" <vattunuru@marvell.com>
Subject: [dpdk-dev] [PATCH v6 4/4] kernel/linux/kni: add IOVA support in kni module
Date: Tue, 25 Jun 2019 09:27:00 +0530
Message-ID: <20190625035700.2953-5-vattunuru@marvell.com> (raw)
In-Reply-To: <20190625035700.2953-1-vattunuru@marvell.com>

From: Kiran Kumar K <kirankumark@marvell.com>

Patch adds support for kernel module to work in IOVA = VA mode,
the idea is to get physical address from iova address using
iommu_iova_to_phys API and later use phys_to_virt API to
convert the physical address to kernel virtual address.

When compared with IOVA = PA mode, there is no performance
drop with this approach.

This approach does not work with the kernel versions less
than 4.4.0 because of API compatibility issues.

Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
---
 kernel/linux/kni/kni_dev.h  |  3 ++
 kernel/linux/kni/kni_misc.c | 62 ++++++++++++++++++++++++++++++------
 kernel/linux/kni/kni_net.c  | 76 +++++++++++++++++++++++++++++++++++++--------
 3 files changed, 119 insertions(+), 22 deletions(-)

diff --git a/kernel/linux/kni/kni_dev.h b/kernel/linux/kni/kni_dev.h
index d57bce6..6ad53c7 100644
--- a/kernel/linux/kni/kni_dev.h
+++ b/kernel/linux/kni/kni_dev.h
@@ -23,6 +23,7 @@
 #include <linux/netdevice.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/iommu.h>
 
 #include <rte_kni_common.h>
 #define KNI_KTHREAD_RESCHEDULE_INTERVAL 5 /* us */
@@ -39,6 +40,8 @@ struct kni_dev {
 	/* kni list */
 	struct list_head list;
 
+	uint8_t iova_mode;
+	struct iommu_domain *domain;
 	struct net_device_stats stats;
 	int status;
 	uint16_t group_id;           /* Group ID of a group of KNI devices */
diff --git a/kernel/linux/kni/kni_misc.c b/kernel/linux/kni/kni_misc.c
index 1fc5eeb..b70c827 100644
--- a/kernel/linux/kni/kni_misc.c
+++ b/kernel/linux/kni/kni_misc.c
@@ -294,6 +294,9 @@ kni_ioctl_create(struct net *net, uint32_t ioctl_num,
 	struct rte_kni_device_info dev_info;
 	struct net_device *net_dev = NULL;
 	struct kni_dev *kni, *dev, *n;
+	struct pci_dev *pci = NULL;
+	struct iommu_domain *domain = NULL;
+	phys_addr_t phys_addr;
 
 	pr_info("Creating kni...\n");
 	/* Check the buffer size, to avoid warning */
@@ -351,15 +354,56 @@ 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) {
+#if KERNEL_VERSION(4, 4, 0) > LINUX_VERSION_CODE
+		(void)pci;
+		pr_err("Kernel version is not supported\n");
+		return -EINVAL;
+#else
+		pci = pci_get_device(dev_info.vendor_id,
+				     dev_info.device_id, NULL);
+		while (pci) {
+			if ((pci->bus->number == dev_info.bus) &&
+			    (PCI_SLOT(pci->devfn) == dev_info.devid) &&
+			    (PCI_FUNC(pci->devfn) == dev_info.function)) {
+				domain = iommu_get_domain_for_dev(&pci->dev);
+				break;
+			}
+			pci = pci_get_device(dev_info.vendor_id,
+					     dev_info.device_id, pci);
+		}
+#endif
+		kni->domain = domain;
+		phys_addr = iommu_iova_to_phys(domain, dev_info.tx_phys);
+		kni->tx_q = phys_to_virt(phys_addr);
+		phys_addr = iommu_iova_to_phys(domain, dev_info.rx_phys);
+		kni->rx_q = phys_to_virt(phys_addr);
+		phys_addr = iommu_iova_to_phys(domain, dev_info.alloc_phys);
+		kni->alloc_q = phys_to_virt(phys_addr);
+		phys_addr = iommu_iova_to_phys(domain, dev_info.free_phys);
+		kni->free_q = phys_to_virt(phys_addr);
+		phys_addr = iommu_iova_to_phys(domain, dev_info.req_phys);
+		kni->req_q = phys_to_virt(phys_addr);
+		phys_addr = iommu_iova_to_phys(domain, dev_info.resp_phys);
+		kni->resp_q = phys_to_virt(phys_addr);
+		kni->sync_va = dev_info.sync_va;
+		phys_addr = iommu_iova_to_phys(domain, dev_info.sync_phys);
+		kni->sync_kva = phys_to_virt(phys_addr);
+		kni->iova_mode = 1;
+
+	} 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 ad83658..92d5991 100644
--- a/kernel/linux/kni/kni_net.c
+++ b/kernel/linux/kni/kni_net.c
@@ -35,6 +35,22 @@ 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 void *
+iova2kva(struct kni_dev *kni, void *pa)
+{
+	return phys_to_virt(iommu_iova_to_phys(kni->domain,
+				(uintptr_t)pa));
+}
+
+static void *
+iova2data_kva(struct kni_dev *kni, struct rte_kni_mbuf *m)
+{
+	return phys_to_virt((iommu_iova_to_phys(kni->domain,
+					(uintptr_t)m->buf_physaddr) +
+			     m->data_off));
+}
+
 /* physical address to kernel virtual address */
 static void *
 pa2kva(void *pa)
@@ -186,7 +202,10 @@ kni_fifo_trans_pa2va(struct kni_dev *kni,
 			return;
 
 		for (i = 0; i < num_rx; i++) {
-			kva = pa2kva(kni->pa[i]);
+			if (likely(kni->iova_mode == 1))
+				kva = iova2kva(kni, kni->pa[i]);
+			else
+				kva = pa2kva(kni->pa[i]);
 			kni->va[i] = pa2va(kni->pa[i], kva);
 		}
 
@@ -263,8 +282,13 @@ 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);
+		if (likely(kni->iova_mode == 1)) {
+			pkt_kva = iova2kva(kni, pkt_pa);
+			data_kva = iova2data_kva(kni, pkt_kva);
+		} else {
+			pkt_kva = pa2kva(pkt_pa);
+			data_kva = kva2data_kva(pkt_kva);
+		}
 		pkt_va = pa2va(pkt_pa, pkt_kva);
 
 		len = skb->len;
@@ -335,9 +359,14 @@ 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]);
+		if (likely(kni->iova_mode == 1)) {
+			kva = iova2kva(kni, kni->pa[i]);
+			data_kva = iova2data_kva(kni, kva);
+		} else {
+			kva = pa2kva(kni->pa[i]);
+			data_kva = kva2data_kva(kva);
+		}
 		len = kva->pkt_len;
-		data_kva = kva2data_kva(kva);
 		kni->va[i] = pa2va(kni->pa[i], kva);
 
 		skb = dev_alloc_skb(len + 2);
@@ -434,13 +463,21 @@ kni_net_rx_lo_fifo(struct kni_dev *kni)
 		num = ret;
 		/* Copy mbufs */
 		for (i = 0; i < num; i++) {
-			kva = pa2kva(kni->pa[i]);
+
+			if (likely(kni->iova_mode == 1)) {
+				kva = iova2kva(kni, kni->pa[i]);
+				data_kva = iova2data_kva(kni, kva);
+				alloc_kva = iova2kva(kni, kni->alloc_pa[i]);
+				alloc_data_kva = iova2data_kva(kni, alloc_kva);
+			} else {
+				kva = pa2kva(kni->pa[i]);
+				data_kva = kva2data_kva(kva);
+				alloc_kva = pa2kva(kni->alloc_pa[i]);
+				alloc_data_kva = kva2data_kva(alloc_kva);
+			}
 			len = kva->pkt_len;
-			data_kva = kva2data_kva(kva);
 			kni->va[i] = pa2va(kni->pa[i], kva);
 
-			alloc_kva = pa2kva(kni->alloc_pa[i]);
-			alloc_data_kva = kva2data_kva(alloc_kva);
 			kni->alloc_va[i] = pa2va(kni->alloc_pa[i], alloc_kva);
 
 			memcpy(alloc_data_kva, data_kva, len);
@@ -507,9 +544,16 @@ 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]);
+
+		if (likely(kni->iova_mode == 1)) {
+			kva = iova2kva(kni, kni->pa[i]);
+			data_kva = iova2data_kva(kni, kva);
+		} else {
+			kva = pa2kva(kni->pa[i]);
+			data_kva = kva2data_kva(kva);
+		}
+
 		len = kva->pkt_len;
-		data_kva = kva2data_kva(kva);
 		kni->va[i] = pa2va(kni->pa[i], kva);
 
 		skb = dev_alloc_skb(len + 2);
@@ -545,8 +589,14 @@ kni_net_rx_lo_fifo_skb(struct kni_dev *kni)
 				if (!kva->next)
 					break;
 
-				kva = pa2kva(va2pa(kva->next, kva));
-				data_kva = kva2data_kva(kva);
+				if (likely(kni->iova_mode == 1)) {
+					kva = iova2kva(kni,
+						       va2pa(kva->next, kva));
+					data_kva = iova2data_kva(kni, kva);
+				} else {
+					kva = pa2kva(va2pa(kva->next, kva));
+					data_kva = kva2data_kva(kva);
+				}
 			}
 		}
 
-- 
2.8.4


  parent reply index

Thread overview: 103+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-27 10:49 [PATCH] kni: add IOVA va support for kni Kiran Kumar
2018-09-27 10:58 ` Burakov, Anatoly
2018-10-02 17:05 ` Ferruh Yigit
2019-04-01 17:30   ` Jerin Jacob Kollanukkaran
2019-04-01 18:20     ` Ferruh Yigit
2019-04-01  9:51 ` [PATCH v2] " Kiran Kumar Kokkilagadda
2019-04-03 16:29   ` Ferruh Yigit
2019-04-04  5:03     ` [dpdk-dev] [EXT] " Kiran Kumar Kokkilagadda
2019-04-04 11:20       ` Ferruh Yigit
2019-04-04 13:29         ` Burakov, Anatoly
2019-04-04  9:57     ` Burakov, Anatoly
2019-04-04 11:21       ` Ferruh Yigit
2019-04-16  4:55   ` [dpdk-dev] [PATCH v3] " kirankumark
2019-04-19 10:38     ` Thomas Monjalon
2019-04-22  4:39     ` [dpdk-dev] [PATCH v4] " kirankumark
2019-04-22  6:15       ` [dpdk-dev] [PATCH v5] " kirankumark
2019-04-26  9:11         ` Burakov, Anatoly
2019-06-25  3:56         ` [dpdk-dev] [PATCH v6 0/4] add IOVA = VA support in KNI vattunuru
2019-06-25  3:56           ` [dpdk-dev] [PATCH v6 1/4] lib/mempool: skip populating mempool objs that falls on page boundaries vattunuru
2019-06-25  3:56           ` [dpdk-dev] [PATCH v6 2/4] lib/kni: add PCI related information vattunuru
2019-06-25 17:41             ` Stephen Hemminger
2019-06-26  3:48               ` [dpdk-dev] [EXT] " Vamsi Krishna Attunuru
2019-06-26 14:58                 ` Stephen Hemminger
2019-06-27  9:43                   ` Vamsi Krishna Attunuru
2019-07-11 16:22             ` [dpdk-dev] " Ferruh Yigit
2019-07-12 11:02               ` [dpdk-dev] [EXT] " Vamsi Krishna Attunuru
2019-07-12 11:11                 ` Ferruh Yigit
2019-06-25  3:56           ` [dpdk-dev] [PATCH v6 3/4] example/kni: add IOVA support for kni application vattunuru
2019-07-11 16:23             ` Ferruh Yigit
2019-06-25  3:57           ` vattunuru [this message]
2019-07-11 16:30             ` [dpdk-dev] [PATCH v6 4/4] kernel/linux/kni: add IOVA support in kni module Ferruh Yigit
2019-07-12 10:38               ` [dpdk-dev] [EXT] " Vamsi Krishna Attunuru
2019-07-12 11:10                 ` Ferruh Yigit
2019-07-12 12:27                   ` Vamsi Krishna Attunuru
2019-07-12 16:29                   ` Vamsi Krishna Attunuru
2019-07-15 11:26                     ` Ferruh Yigit
2019-07-15 13:06                       ` Vamsi Krishna Attunuru
2019-07-11 16:43             ` [dpdk-dev] " Stephen Hemminger
2019-06-25 10:00           ` [dpdk-dev] [PATCH v6 0/4] add IOVA = VA support in KNI Burakov, Anatoly
2019-06-25 11:15             ` Jerin Jacob Kollanukkaran
2019-06-25 11:30               ` Burakov, Anatoly
2019-06-25 13:38                 ` Burakov, Anatoly
2019-06-27  9:34                   ` Jerin Jacob Kollanukkaran
2019-07-01 13:51                     ` Vamsi Krishna Attunuru
2019-07-04  6:42                       ` Vamsi Krishna Attunuru
2019-07-04  9:48                         ` Jerin Jacob Kollanukkaran
2019-07-11 16:21                           ` Ferruh Yigit
2019-07-17  9:04           ` [dpdk-dev] [PATCH v7 0/4] kni: add IOVA=VA support vattunuru
2019-07-17  9:04             ` [dpdk-dev] [PATCH v7 1/4] mempool: modify mempool populate() to skip objects from page boundaries vattunuru
2019-07-17 13:36               ` Andrew Rybchenko
2019-07-17 13:47                 ` Olivier Matz
2019-07-17 17:31                 ` Vamsi Krishna Attunuru
2019-07-18  9:28                   ` Andrew Rybchenko
2019-07-18 14:16                     ` Vamsi Krishna Attunuru
2019-07-19 13:38                       ` [dpdk-dev] [RFC 0/4] mempool: avoid objects allocations across pages Olivier Matz
2019-07-19 13:38                         ` [dpdk-dev] [RFC 1/4] mempool: clarify default populate function Olivier Matz
2019-07-19 15:42                           ` Andrew Rybchenko
2019-07-19 13:38                         ` [dpdk-dev] [RFC 2/4] mempool: unalign size when calculating required mem amount Olivier Matz
2019-08-07 15:21                           ` [dpdk-dev] ***Spam*** " Andrew Rybchenko
2019-07-19 13:38                         ` [dpdk-dev] [RFC 3/4] mempool: introduce function to get mempool page size Olivier Matz
2019-08-07 15:21                           ` Andrew Rybchenko
2019-07-19 13:38                         ` [dpdk-dev] [RFC 4/4] mempool: prevent objects from being across pages Olivier Matz
2019-07-19 14:03                           ` Burakov, Anatoly
2019-07-19 14:11                           ` Burakov, Anatoly
2019-08-07 15:21                           ` Andrew Rybchenko
2019-07-23  5:37                         ` [dpdk-dev] [RFC 0/4] mempool: avoid objects allocations " Vamsi Krishna Attunuru
2019-08-07 15:21                         ` [dpdk-dev] ***Spam*** " Andrew Rybchenko
2019-07-17  9:04             ` [dpdk-dev] [PATCH v7 2/4] kni: add IOVA = VA support in KNI lib vattunuru
2019-07-17  9:04             ` [dpdk-dev] [PATCH v7 3/4] kni: add IOVA=VA support in KNI module vattunuru
2019-07-17  9:04             ` [dpdk-dev] [PATCH v7 4/4] kni: modify IOVA mode checks to support VA vattunuru
2019-07-23  5:38             ` [dpdk-dev] [PATCH v8 0/5] kni: add IOVA=VA support vattunuru
2019-07-23  5:38               ` [dpdk-dev] [PATCH v8 1/5] mempool: populate mempool with page sized chunks of memory vattunuru
2019-07-23 11:08                 ` Andrew Rybchenko
2019-07-23 12:28                   ` Vamsi Krishna Attunuru
2019-07-23 19:33                     ` Andrew Rybchenko
2019-07-24  7:09                       ` Vamsi Krishna Attunuru
2019-07-24  7:27                         ` Andrew Rybchenko
2019-07-29  6:25                           ` Vamsi Krishna Attunuru
2019-07-23  5:38               ` [dpdk-dev] [PATCH v8 2/5] add IOVA -VA support in KNI lib vattunuru
2019-07-23 10:54                 ` Andrew Rybchenko
2019-07-23  5:38               ` [dpdk-dev] [PATCH v8 3/5] kni: add app specific mempool create & free routine vattunuru
2019-07-23 10:50                 ` Andrew Rybchenko
2019-07-23 11:01                   ` Vamsi Krishna Attunuru
2019-07-23  5:38               ` [dpdk-dev] [PATCH v8 4/5] kni: add IOVA=VA support in KNI module vattunuru
2019-07-23  5:38               ` [dpdk-dev] [PATCH v8 5/5] kni: modify IOVA mode checks to support VA vattunuru
2019-07-24  7:14               ` [dpdk-dev] [PATCH v8 0/5] kni: add IOVA=VA support Vamsi Krishna Attunuru
2019-07-29 12:13               ` [dpdk-dev] [PATCH v9 " vattunuru
2019-07-29 12:13                 ` [dpdk-dev] [PATCH v9 1/5] mempool: populate mempool with the page sized chunks of memory vattunuru
2019-07-29 12:41                   ` Andrew Rybchenko
2019-07-29 13:33                     ` [dpdk-dev] [EXT] " Vamsi Krishna Attunuru
2019-08-16  6:12                   ` [dpdk-dev] [PATCH v10 0/5] kni: add IOVA=VA support vattunuru
2019-08-16  6:12                     ` [dpdk-dev] [PATCH v10 1/5] mempool: populate mempool with the page sized chunks vattunuru
2019-08-16  6:12                     ` [dpdk-dev] [PATCH v10 2/5] kni: add IOVA=VA support in KNI lib vattunuru
2019-08-16  6:12                     ` [dpdk-dev] [PATCH v10 3/5] kni: add app specific mempool create and free routines vattunuru
2019-08-16  6:12                     ` [dpdk-dev] [PATCH v10 4/5] kni: add IOVA=VA support in KNI module vattunuru
2019-08-16  6:12                     ` [dpdk-dev] [PATCH v10 5/5] kni: modify IOVA mode checks to support VA vattunuru
2019-07-29 12:13                 ` [dpdk-dev] [PATCH v9 2/5] kni: add IOVA=VA support in KNI lib vattunuru
2019-07-29 12:24                   ` Igor Ryzhov
2019-07-29 13:22                     ` [dpdk-dev] [EXT] " Vamsi Krishna Attunuru
2019-07-29 12:13                 ` [dpdk-dev] [PATCH v9 3/5] kni: add app specific mempool create & free routine vattunuru
2019-07-29 12:13                 ` [dpdk-dev] [PATCH v9 4/5] kni: add IOVA=VA support in KNI module vattunuru
2019-07-29 12:13                 ` [dpdk-dev] [PATCH v9 5/5] kni: modify IOVA mode checks to support VA vattunuru
2019-04-23  8:56       ` [dpdk-dev] [PATCH v4] kni: add IOVA va support for kni Burakov, Anatoly

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190625035700.2953-5-vattunuru@marvell.com \
    --to=vattunuru@marvell.com \
    --cc=arybchenko@solarflare.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=kirankumark@marvell.com \
    --cc=olivier.matz@6wind.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

DPDK-dev Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/dpdk-dev/0 dpdk-dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dpdk-dev dpdk-dev/ https://lore.kernel.org/dpdk-dev \
		dev@dpdk.org dpdk-dev@archiver.kernel.org
	public-inbox-index dpdk-dev


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/ public-inbox