From: Yuanhan Liu <yuanhan.liu@linux.intel.com>
To: dev@dpdk.org
Cc: Maxime Coquelin <maxime.coquelin@redhat.com>,
Yuanhan Liu <yuanhan.liu@linux.intel.com>
Subject: [dpdk-dev] [PATCH v2 2/7] vhost: get guest/host physical address mappings
Date: Fri, 23 Sep 2016 12:13:22 +0800 [thread overview]
Message-ID: <1474604007-5221-3-git-send-email-yuanhan.liu@linux.intel.com> (raw)
In-Reply-To: <1474604007-5221-1-git-send-email-yuanhan.liu@linux.intel.com>
So that we can convert a guest physical address to host physical
address, which will be used in later Tx zero copy implementation.
MAP_POPULATE is set while mmaping guest memory regions, to make
sure the page tables are setup and then rte_mem_virt2phy() could
yield proper physical address.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
---
v2: - use MAP_POPULATE option to make sure the page table will
be already setup while getting the phys address
- do a simple merge if the last 2 pages are continuous
- dump guest pages only in debug mode
---
lib/librte_vhost/vhost.h | 30 +++++++++++++
lib/librte_vhost/vhost_user.c | 100 +++++++++++++++++++++++++++++++++++++++++-
2 files changed, 128 insertions(+), 2 deletions(-)
diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index df2107b..2d52987 100644
--- a/lib/librte_vhost/vhost.h
+++ b/lib/librte_vhost/vhost.h
@@ -114,6 +114,12 @@ struct vhost_virtqueue {
#define VIRTIO_F_VERSION_1 32
#endif
+struct guest_page {
+ uint64_t guest_phys_addr;
+ uint64_t host_phys_addr;
+ uint64_t size;
+};
+
/**
* Device structure contains all configuration information relating
* to the device.
@@ -137,6 +143,10 @@ struct virtio_net {
uint64_t log_addr;
struct ether_addr mac;
+ uint32_t nr_guest_pages;
+ uint32_t max_guest_pages;
+ struct guest_page *guest_pages;
+
} __rte_cache_aligned;
/**
@@ -217,6 +227,26 @@ gpa_to_vva(struct virtio_net *dev, uint64_t gpa)
return 0;
}
+/* Convert guest physical address to host physical address */
+static inline phys_addr_t __attribute__((always_inline))
+gpa_to_hpa(struct virtio_net *dev, uint64_t gpa, uint64_t size)
+{
+ uint32_t i;
+ struct guest_page *page;
+
+ for (i = 0; i < dev->nr_guest_pages; i++) {
+ page = &dev->guest_pages[i];
+
+ if (gpa >= page->guest_phys_addr &&
+ gpa + size < page->guest_phys_addr + page->size) {
+ return gpa - page->guest_phys_addr +
+ page->host_phys_addr;
+ }
+ }
+
+ return 0;
+}
+
struct virtio_net_device_ops const *notify_ops;
struct virtio_net *get_device(int vid);
diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index 49585b8..e651912 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -372,6 +372,91 @@ vhost_user_set_vring_base(struct virtio_net *dev,
return 0;
}
+static void
+add_one_guest_page(struct virtio_net *dev, uint64_t guest_phys_addr,
+ uint64_t host_phys_addr, uint64_t size)
+{
+ struct guest_page *page, *last_page;
+
+ if (dev->nr_guest_pages == dev->max_guest_pages) {
+ dev->max_guest_pages *= 2;
+ dev->guest_pages = realloc(dev->guest_pages,
+ dev->max_guest_pages * sizeof(*page));
+ }
+
+ if (dev->nr_guest_pages > 0) {
+ last_page = &dev->guest_pages[dev->nr_guest_pages - 1];
+ /* merge if the two pages are continuous */
+ if (host_phys_addr == last_page->host_phys_addr +
+ last_page->size) {
+ last_page->size += size;
+ return;
+ }
+ }
+
+ page = &dev->guest_pages[dev->nr_guest_pages++];
+ page->guest_phys_addr = guest_phys_addr;
+ page->host_phys_addr = host_phys_addr;
+ page->size = size;
+}
+
+static void
+add_guest_pages(struct virtio_net *dev, struct virtio_memory_region *reg,
+ uint64_t page_size)
+{
+ uint64_t reg_size = reg->size;
+ uint64_t host_user_addr = reg->host_user_addr;
+ uint64_t guest_phys_addr = reg->guest_phys_addr;
+ uint64_t host_phys_addr;
+ uint64_t size;
+
+ host_phys_addr = rte_mem_virt2phy((void *)(uintptr_t)host_user_addr);
+ size = page_size - (guest_phys_addr & (page_size - 1));
+ size = RTE_MIN(size, reg_size);
+
+ add_one_guest_page(dev, guest_phys_addr, host_phys_addr, size);
+ host_user_addr += size;
+ guest_phys_addr += size;
+ reg_size -= size;
+
+ while (reg_size > 0) {
+ host_phys_addr = rte_mem_virt2phy((void *)(uintptr_t)
+ host_user_addr);
+ add_one_guest_page(dev, guest_phys_addr, host_phys_addr,
+ page_size);
+
+ host_user_addr += page_size;
+ guest_phys_addr += page_size;
+ reg_size -= page_size;
+ }
+}
+
+#ifdef RTE_LIBRTE_VHOST_DEBUG
+/* TODO: enable it only in debug mode? */
+static void
+dump_guest_pages(struct virtio_net *dev)
+{
+ uint32_t i;
+ struct guest_page *page;
+
+ for (i = 0; i < dev->nr_guest_pages; i++) {
+ page = &dev->guest_pages[i];
+
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "guest physical page region %u\n"
+ "\t guest_phys_addr: %" PRIx64 "\n"
+ "\t host_phys_addr : %" PRIx64 "\n"
+ "\t size : %" PRIx64 "\n",
+ i,
+ page->guest_phys_addr,
+ page->host_phys_addr,
+ page->size);
+ }
+}
+#else
+#define dump_guest_pages(dev)
+#endif
+
static int
vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg)
{
@@ -396,6 +481,13 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg)
dev->mem = NULL;
}
+ dev->nr_guest_pages = 0;
+ if (!dev->guest_pages) {
+ dev->max_guest_pages = 8;
+ dev->guest_pages = malloc(dev->max_guest_pages *
+ sizeof(struct guest_page));
+ }
+
dev->mem = rte_zmalloc("vhost-mem-table", sizeof(struct virtio_memory) +
sizeof(struct virtio_memory_region) * memory.nregions, 0);
if (dev->mem == NULL) {
@@ -434,8 +526,8 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg)
}
mmap_size = RTE_ALIGN_CEIL(mmap_size, alignment);
- mmap_addr = mmap(NULL, mmap_size,
- PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ mmap_addr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE, fd, 0);
if (mmap_addr == MAP_FAILED) {
RTE_LOG(ERR, VHOST_CONFIG,
@@ -448,6 +540,8 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg)
reg->host_user_addr = (uint64_t)(uintptr_t)mmap_addr +
mmap_offset;
+ add_guest_pages(dev, reg, alignment);
+
RTE_LOG(INFO, VHOST_CONFIG,
"guest memory region %u, size: 0x%" PRIx64 "\n"
"\t guest physical addr: 0x%" PRIx64 "\n"
@@ -467,6 +561,8 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg)
mmap_offset);
}
+ dump_guest_pages(dev);
+
return 0;
err_mmap:
--
1.9.0
next prev parent reply other threads:[~2016-09-23 4:13 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-08-23 8:10 [dpdk-dev] [PATCH 0/6] vhost: add Tx zero copy support Yuanhan Liu
2016-08-23 8:10 ` [dpdk-dev] [PATCH 1/6] vhost: simplify memory regions handling Yuanhan Liu
2016-08-23 9:17 ` Maxime Coquelin
2016-08-24 7:26 ` Xu, Qian Q
2016-08-24 7:40 ` Yuanhan Liu
2016-08-24 7:36 ` Xu, Qian Q
2016-08-23 8:10 ` [dpdk-dev] [PATCH 2/6] vhost: get guest/host physical address mappings Yuanhan Liu
2016-08-23 9:58 ` Maxime Coquelin
2016-08-23 12:32 ` Yuanhan Liu
2016-08-23 13:25 ` Maxime Coquelin
2016-08-23 13:49 ` Yuanhan Liu
2016-08-23 14:05 ` Maxime Coquelin
2016-08-23 8:10 ` [dpdk-dev] [PATCH 3/6] vhost: introduce last avail idx for Tx Yuanhan Liu
2016-08-23 12:27 ` Maxime Coquelin
2016-08-23 8:10 ` [dpdk-dev] [PATCH 4/6] vhost: add Tx zero copy Yuanhan Liu
2016-08-23 14:04 ` Maxime Coquelin
2016-08-23 14:31 ` Yuanhan Liu
2016-08-23 15:40 ` Maxime Coquelin
2016-08-23 8:10 ` [dpdk-dev] [PATCH 5/6] vhost: add a flag to enable " Yuanhan Liu
2016-09-06 9:00 ` Xu, Qian Q
2016-09-06 9:42 ` Xu, Qian Q
2016-09-06 10:02 ` Yuanhan Liu
2016-09-07 2:43 ` Xu, Qian Q
2016-09-06 9:55 ` Yuanhan Liu
2016-09-07 16:00 ` Thomas Monjalon
2016-09-08 7:21 ` Yuanhan Liu
2016-09-08 7:57 ` Thomas Monjalon
2016-08-23 8:10 ` [dpdk-dev] [PATCH 6/6] examples/vhost: add an option " Yuanhan Liu
2016-08-23 9:31 ` Thomas Monjalon
2016-08-23 12:33 ` Yuanhan Liu
2016-08-23 14:14 ` Maxime Coquelin
2016-08-23 14:45 ` Yuanhan Liu
2016-08-23 14:18 ` [dpdk-dev] [PATCH 0/6] vhost: add Tx zero copy support Maxime Coquelin
2016-08-23 14:42 ` Yuanhan Liu
2016-08-23 14:53 ` Yuanhan Liu
2016-08-23 16:41 ` Maxime Coquelin
2016-08-29 8:32 ` Xu, Qian Q
2016-08-29 8:57 ` Xu, Qian Q
2016-09-23 4:11 ` Yuanhan Liu
2016-10-09 15:20 ` Yuanhan Liu
2016-09-23 4:13 ` [dpdk-dev] [PATCH v2 0/7] vhost: add dequeue " Yuanhan Liu
2016-09-23 4:13 ` [dpdk-dev] [PATCH v2 1/7] vhost: simplify memory regions handling Yuanhan Liu
2016-09-23 4:13 ` Yuanhan Liu [this message]
2016-09-26 20:17 ` [dpdk-dev] [PATCH v2 2/7] vhost: get guest/host physical address mappings Maxime Coquelin
2016-09-23 4:13 ` [dpdk-dev] [PATCH v2 3/7] vhost: introduce last avail idx for dequeue Yuanhan Liu
2016-09-23 4:13 ` [dpdk-dev] [PATCH v2 4/7] vhost: add dequeue zero copy Yuanhan Liu
2016-09-26 20:45 ` Maxime Coquelin
2016-10-06 14:37 ` Xu, Qian Q
2016-10-09 2:03 ` Yuanhan Liu
2016-10-10 10:12 ` Xu, Qian Q
2016-10-10 10:14 ` Maxime Coquelin
2016-10-10 10:22 ` Xu, Qian Q
2016-10-10 10:40 ` Xu, Qian Q
2016-10-10 11:48 ` Maxime Coquelin
2016-09-23 4:13 ` [dpdk-dev] [PATCH v2 5/7] vhost: add a flag to enable " Yuanhan Liu
2016-09-26 20:57 ` Maxime Coquelin
2016-09-23 4:13 ` [dpdk-dev] [PATCH v2 6/7] examples/vhost: add an option " Yuanhan Liu
2016-09-26 21:05 ` Maxime Coquelin
2016-09-23 4:13 ` [dpdk-dev] [PATCH v2 7/7] net/vhost: " Yuanhan Liu
2016-09-26 21:05 ` Maxime Coquelin
2016-10-09 7:27 ` [dpdk-dev] [PATCH v3 0/7] vhost: add dequeue zero copy support Yuanhan Liu
2016-10-09 7:27 ` [dpdk-dev] [PATCH v3 1/7] vhost: simplify memory regions handling Yuanhan Liu
2016-10-09 7:27 ` [dpdk-dev] [PATCH v3 2/7] vhost: get guest/host physical address mappings Yuanhan Liu
2016-11-29 3:10 ` linhaifeng
2016-11-29 13:14 ` linhaifeng
2016-10-09 7:27 ` [dpdk-dev] [PATCH v3 3/7] vhost: introduce last avail idx for dequeue Yuanhan Liu
2016-10-09 7:27 ` [dpdk-dev] [PATCH v3 4/7] vhost: add dequeue zero copy Yuanhan Liu
2016-10-09 7:27 ` [dpdk-dev] [PATCH v3 5/7] vhost: add a flag to enable " Yuanhan Liu
2016-10-09 7:27 ` [dpdk-dev] [PATCH v3 6/7] examples/vhost: add an option " Yuanhan Liu
2016-10-09 7:28 ` [dpdk-dev] [PATCH v3 7/7] net/vhost: " Yuanhan Liu
2016-10-11 13:04 ` [dpdk-dev] [PATCH v3 0/7] vhost: add dequeue zero copy support Xu, Qian Q
2016-10-12 7:48 ` Yuanhan Liu
2016-10-09 10:46 ` [dpdk-dev] [PATCH 0/6] vhost: add Tx " linhaifeng
2016-10-10 8:03 ` Yuanhan Liu
2016-10-14 7:30 ` linhaifeng
Reply instructions:
You may reply publicly 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=1474604007-5221-3-git-send-email-yuanhan.liu@linux.intel.com \
--to=yuanhan.liu@linux.intel.com \
--cc=dev@dpdk.org \
--cc=maxime.coquelin@redhat.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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).