linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tianyu Lan <ltykernel@gmail.com>
To: kys@microsoft.com, haiyangz@microsoft.com,
	sthemmin@microsoft.com, wei.liu@kernel.org, decui@microsoft.com,
	tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
	x86@kernel.org, hpa@zytor.com, dave.hansen@linux.intel.com,
	luto@kernel.org, peterz@infradead.org, konrad.wilk@oracle.com,
	boris.ostrovsky@oracle.com, jgross@suse.com,
	sstabellini@kernel.org, joro@8bytes.org, will@kernel.org,
	davem@davemloft.net, kuba@kernel.org, jejb@linux.ibm.com,
	martin.petersen@oracle.com, arnd@arndb.de, hch@lst.de,
	m.szyprowski@samsung.com, robin.murphy@arm.com,
	thomas.lendacky@amd.com, brijesh.singh@amd.com, ardb@kernel.org,
	Tianyu.Lan@microsoft.com, rientjes@google.com,
	martin.b.radev@gmail.com, akpm@linux-foundation.org,
	rppt@kernel.org, kirill.shutemov@linux.intel.com,
	aneesh.kumar@linux.ibm.com, krish.sadhukhan@oracle.com,
	saravanand@fb.com, xen-devel@lists.xenproject.org,
	pgonda@google.com, david@redhat.com, keescook@chromium.org,
	hannes@cmpxchg.org, sfr@canb.auug.org.au,
	michael.h.kelley@microsoft.com
Cc: iommu@lists.linux-foundation.org, linux-arch@vger.kernel.org,
	linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-scsi@vger.kernel.org, netdev@vger.kernel.org,
	vkuznets@redhat.com, anparri@microsoft.com
Subject: [PATCH 12/13] HV/Netvsc: Add Isolation VM support for netvsc driver
Date: Wed, 28 Jul 2021 10:52:27 -0400	[thread overview]
Message-ID: <20210728145232.285861-13-ltykernel@gmail.com> (raw)
In-Reply-To: <20210728145232.285861-1-ltykernel@gmail.com>

From: Tianyu Lan <Tianyu.Lan@microsoft.com>

In Isolation VM, all shared memory with host needs to mark visible
to host via hvcall. vmbus_establish_gpadl() has already done it for
netvsc rx/tx ring buffer. The page buffer used by vmbus_sendpacket_
pagebuffer() still need to handle. Use DMA API to map/umap these
memory during sending/receiving packet and Hyper-V DMA ops callback
will use swiotlb function to allocate bounce buffer and copy data
from/to bounce buffer.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 drivers/net/hyperv/hyperv_net.h   |   6 ++
 drivers/net/hyperv/netvsc.c       | 144 +++++++++++++++++++++++++++++-
 drivers/net/hyperv/rndis_filter.c |   2 +
 include/linux/hyperv.h            |   5 ++
 4 files changed, 154 insertions(+), 3 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index bc48855dff10..862419912bfb 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -164,6 +164,7 @@ struct hv_netvsc_packet {
 	u32 total_bytes;
 	u32 send_buf_index;
 	u32 total_data_buflen;
+	struct hv_dma_range *dma_range;
 };
 
 #define NETVSC_HASH_KEYLEN 40
@@ -1074,6 +1075,7 @@ struct netvsc_device {
 
 	/* Receive buffer allocated by us but manages by NetVSP */
 	void *recv_buf;
+	void *recv_original_buf;
 	u32 recv_buf_size; /* allocated bytes */
 	u32 recv_buf_gpadl_handle;
 	u32 recv_section_cnt;
@@ -1082,6 +1084,8 @@ struct netvsc_device {
 
 	/* Send buffer allocated by us */
 	void *send_buf;
+	void *send_original_buf;
+	u32 send_buf_size;
 	u32 send_buf_gpadl_handle;
 	u32 send_section_cnt;
 	u32 send_section_size;
@@ -1730,4 +1734,6 @@ struct rndis_message {
 #define RETRY_US_HI	10000
 #define RETRY_MAX	2000	/* >10 sec */
 
+void netvsc_dma_unmap(struct hv_device *hv_dev,
+		      struct hv_netvsc_packet *packet);
 #endif /* _HYPERV_NET_H */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 7bd935412853..fc312e5db4d5 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -153,8 +153,21 @@ static void free_netvsc_device(struct rcu_head *head)
 	int i;
 
 	kfree(nvdev->extension);
-	vfree(nvdev->recv_buf);
-	vfree(nvdev->send_buf);
+
+	if (nvdev->recv_original_buf) {
+		vunmap(nvdev->recv_buf);
+		vfree(nvdev->recv_original_buf);
+	} else {
+		vfree(nvdev->recv_buf);
+	}
+
+	if (nvdev->send_original_buf) {
+		vunmap(nvdev->send_buf);
+		vfree(nvdev->send_original_buf);
+	} else {
+		vfree(nvdev->send_buf);
+	}
+
 	kfree(nvdev->send_section_map);
 
 	for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
@@ -330,6 +343,27 @@ int netvsc_alloc_recv_comp_ring(struct netvsc_device *net_device, u32 q_idx)
 	return nvchan->mrc.slots ? 0 : -ENOMEM;
 }
 
+static void *netvsc_remap_buf(void *buf, unsigned long size)
+{
+	unsigned long *pfns;
+	void *vaddr;
+	int i;
+
+	pfns = kcalloc(size / HV_HYP_PAGE_SIZE, sizeof(unsigned long),
+		       GFP_KERNEL);
+	if (!pfns)
+		return NULL;
+
+	for (i = 0; i < size / HV_HYP_PAGE_SIZE; i++)
+		pfns[i] = virt_to_hvpfn(buf + i * HV_HYP_PAGE_SIZE)
+			+ (ms_hyperv.shared_gpa_boundary >> HV_HYP_PAGE_SHIFT);
+
+	vaddr = vmap_pfn(pfns, size / HV_HYP_PAGE_SIZE, PAGE_KERNEL_IO);
+	kfree(pfns);
+
+	return vaddr;
+}
+
 static int netvsc_init_buf(struct hv_device *device,
 			   struct netvsc_device *net_device,
 			   const struct netvsc_device_info *device_info)
@@ -340,6 +374,7 @@ static int netvsc_init_buf(struct hv_device *device,
 	unsigned int buf_size;
 	size_t map_words;
 	int i, ret = 0;
+	void *vaddr;
 
 	/* Get receive buffer area. */
 	buf_size = device_info->recv_sections * device_info->recv_section_size;
@@ -375,6 +410,15 @@ static int netvsc_init_buf(struct hv_device *device,
 		goto cleanup;
 	}
 
+	if (hv_isolation_type_snp()) {
+		vaddr = netvsc_remap_buf(net_device->recv_buf, buf_size);
+		if (!vaddr)
+			goto cleanup;
+
+		net_device->recv_original_buf = net_device->recv_buf;
+		net_device->recv_buf = vaddr;
+	}
+
 	/* Notify the NetVsp of the gpadl handle */
 	init_packet = &net_device->channel_init_pkt;
 	memset(init_packet, 0, sizeof(struct nvsp_message));
@@ -477,6 +521,15 @@ static int netvsc_init_buf(struct hv_device *device,
 		goto cleanup;
 	}
 
+	if (hv_isolation_type_snp()) {
+		vaddr = netvsc_remap_buf(net_device->send_buf, buf_size);
+		if (!vaddr)
+			goto cleanup;
+
+		net_device->send_original_buf = net_device->send_buf;
+		net_device->send_buf = vaddr;
+	}
+
 	/* Notify the NetVsp of the gpadl handle */
 	init_packet = &net_device->channel_init_pkt;
 	memset(init_packet, 0, sizeof(struct nvsp_message));
@@ -767,7 +820,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 
 	/* Notify the layer above us */
 	if (likely(skb)) {
-		const struct hv_netvsc_packet *packet
+		struct hv_netvsc_packet *packet
 			= (struct hv_netvsc_packet *)skb->cb;
 		u32 send_index = packet->send_buf_index;
 		struct netvsc_stats *tx_stats;
@@ -783,6 +836,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 		tx_stats->bytes += packet->total_bytes;
 		u64_stats_update_end(&tx_stats->syncp);
 
+		netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
 		napi_consume_skb(skb, budget);
 	}
 
@@ -947,6 +1001,82 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		memset(dest, 0, padding);
 }
 
+void netvsc_dma_unmap(struct hv_device *hv_dev,
+		      struct hv_netvsc_packet *packet)
+{
+	u32 page_count = packet->cp_partial ?
+		packet->page_buf_cnt - packet->rmsg_pgcnt :
+		packet->page_buf_cnt;
+	int i;
+
+	if (!hv_is_isolation_supported())
+		return;
+
+	if (!packet->dma_range)
+		return;
+
+	for (i = 0; i < page_count; i++)
+		dma_unmap_single(&hv_dev->device, packet->dma_range[i].dma,
+				 packet->dma_range[i].mapping_size,
+				 DMA_TO_DEVICE);
+
+	kfree(packet->dma_range);
+}
+
+/* netvsc_dma_map - Map swiotlb bounce buffer with data page of
+ * packet sent by vmbus_sendpacket_pagebuffer() in the Isolation
+ * VM.
+ *
+ * In isolation VM, netvsc send buffer has been marked visible to
+ * host and so the data copied to send buffer doesn't need to use
+ * bounce buffer. The data pages handled by vmbus_sendpacket_pagebuffer()
+ * may not be copied to send buffer and so these pages need to be
+ * mapped with swiotlb bounce buffer. netvsc_dma_map() is to do
+ * that. The pfns in the struct hv_page_buffer need to be converted
+ * to bounce buffer's pfn. The loop here is necessary and so not
+ * use dma_map_sg() here.
+ */
+int netvsc_dma_map(struct hv_device *hv_dev,
+		   struct hv_netvsc_packet *packet,
+		   struct hv_page_buffer *pb)
+{
+	u32 page_count =  packet->cp_partial ?
+		packet->page_buf_cnt - packet->rmsg_pgcnt :
+		packet->page_buf_cnt;
+	dma_addr_t dma;
+	int i;
+
+	if (!hv_is_isolation_supported())
+		return 0;
+
+	packet->dma_range = kcalloc(page_count,
+				    sizeof(*packet->dma_range),
+				    GFP_KERNEL);
+	if (!packet->dma_range)
+		return -ENOMEM;
+
+	for (i = 0; i < page_count; i++) {
+		char *src = phys_to_virt((pb[i].pfn << HV_HYP_PAGE_SHIFT)
+					 + pb[i].offset);
+		u32 len = pb[i].len;
+
+		dma = dma_map_single(&hv_dev->device, src, len,
+				     DMA_TO_DEVICE);
+		if (dma_mapping_error(&hv_dev->device, dma)) {
+			kfree(packet->dma_range);
+			return -ENOMEM;
+		}
+
+		packet->dma_range[i].dma = dma;
+		packet->dma_range[i].mapping_size = len;
+		pb[i].pfn = dma >> HV_HYP_PAGE_SHIFT;
+		pb[i].offset = offset_in_hvpage(dma);
+		pb[i].len = len;
+	}
+
+	return 0;
+}
+
 static inline int netvsc_send_pkt(
 	struct hv_device *device,
 	struct hv_netvsc_packet *packet,
@@ -987,14 +1117,22 @@ static inline int netvsc_send_pkt(
 
 	trace_nvsp_send_pkt(ndev, out_channel, rpkt);
 
+	packet->dma_range = NULL;
 	if (packet->page_buf_cnt) {
 		if (packet->cp_partial)
 			pb += packet->rmsg_pgcnt;
 
+		ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb);
+		if (ret)
+			return ret;
+
 		ret = vmbus_sendpacket_pagebuffer(out_channel,
 						  pb, packet->page_buf_cnt,
 						  &nvmsg, sizeof(nvmsg),
 						  req_id);
+
+		if (ret)
+			netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
 	} else {
 		ret = vmbus_sendpacket(out_channel,
 				       &nvmsg, sizeof(nvmsg),
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index f6c9c2a670f9..448fcc325ed7 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -361,6 +361,8 @@ static void rndis_filter_receive_response(struct net_device *ndev,
 			}
 		}
 
+		netvsc_dma_unmap(((struct net_device_context *)
+			netdev_priv(ndev))->device_ctx, &request->pkt);
 		complete(&request->wait_event);
 	} else {
 		netdev_err(ndev,
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index babbe19f57e2..90abff664495 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1616,6 +1616,11 @@ struct hyperv_service_callback {
 	void (*callback)(void *context);
 };
 
+struct hv_dma_range {
+	dma_addr_t dma;
+	u32 mapping_size;
+};
+
 #define MAX_SRV_VER	0x7ffffff
 extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, u32 buflen,
 				const int *fw_version, int fw_vercnt,
-- 
2.25.1


  parent reply	other threads:[~2021-07-28 14:54 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-28 14:52 [PATCH 00/13] x86/Hyper-V: Add Hyper-V Isolation VM support Tianyu Lan
2021-07-28 14:52 ` [PATCH 01/13] x86/HV: Initialize GHCB page in Isolation VM Tianyu Lan
2021-08-02 11:53   ` Joerg Roedel
2021-08-02 12:35     ` Tianyu Lan
2021-07-28 14:52 ` [PATCH 02/13] x86/HV: Initialize shared memory boundary in the " Tianyu Lan
2021-07-28 14:52 ` [PATCH 03/13] x86/HV: Add new hvcall guest address host visibility support Tianyu Lan
2021-07-28 15:29   ` Dave Hansen
2021-07-29 12:49     ` Tianyu Lan
2021-08-02 12:01     ` Joerg Roedel
2021-08-02 12:59       ` Tianyu Lan
2021-08-02 13:11       ` Juergen Gross
2021-08-02 13:30         ` Joerg Roedel
2021-07-28 17:06   ` Dave Hansen
2021-07-29 13:01     ` Tianyu Lan
2021-07-29 14:09       ` Dave Hansen
2021-07-29 15:02         ` Tianyu Lan
2021-07-29 16:05           ` Dave Hansen
2021-07-30  2:52             ` Tianyu Lan
2021-07-28 14:52 ` [PATCH 04/13] HV: Mark vmbus ring buffer visible to host in Isolation VM Tianyu Lan
2021-08-02 12:07   ` Joerg Roedel
2021-08-02 12:56     ` Tianyu Lan
2021-08-02 12:59       ` Joerg Roedel
2021-08-02 13:08         ` Tianyu Lan
2021-07-28 14:52 ` [PATCH 05/13] HV: Add Write/Read MSR registers via ghcb page Tianyu Lan
2021-08-02 12:28   ` Joerg Roedel
2021-08-02 13:18     ` Tianyu Lan
2021-07-28 14:52 ` [PATCH 06/13] HV: Add ghcb hvcall support for SNP VM Tianyu Lan
2021-08-02 12:39   ` Joerg Roedel
2021-08-02 13:32     ` Tianyu Lan
2021-07-28 14:52 ` [PATCH 07/13] HV/Vmbus: Add SNP support for VMbus channel initiate message Tianyu Lan
2021-08-02 12:58   ` Joerg Roedel
2021-07-28 14:52 ` [PATCH 08/13] HV/Vmbus: Initialize VMbus ring buffer for Isolation VM Tianyu Lan
2021-07-28 14:52 ` [PATCH 09/13] DMA: Add dma_map_decrypted/dma_unmap_encrypted() function Tianyu Lan
2021-07-29 15:13   ` Tianyu Lan
2021-07-28 14:52 ` [PATCH 10/13] x86/Swiotlb: Add Swiotlb bounce buffer remap function for HV IVM Tianyu Lan
2021-07-29 16:29   ` Konrad Rzeszutek Wilk
2021-07-30  4:10     ` Tianyu Lan
2021-07-28 14:52 ` [PATCH 11/13] HV/IOMMU: Enable swiotlb bounce buffer for Isolation VM Tianyu Lan
2021-07-28 14:52 ` Tianyu Lan [this message]
2021-07-28 14:52 ` [PATCH 13/13] HV/Storvsc: Add Isolation VM support for storvsc driver Tianyu Lan
2021-08-02 13:20   ` Joerg Roedel
2021-08-02 14:08     ` Tianyu Lan

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=20210728145232.285861-13-ltykernel@gmail.com \
    --to=ltykernel@gmail.com \
    --cc=Tianyu.Lan@microsoft.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.ibm.com \
    --cc=anparri@microsoft.com \
    --cc=ardb@kernel.org \
    --cc=arnd@arndb.de \
    --cc=boris.ostrovsky@oracle.com \
    --cc=bp@alien8.de \
    --cc=brijesh.singh@amd.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=davem@davemloft.net \
    --cc=david@redhat.com \
    --cc=decui@microsoft.com \
    --cc=haiyangz@microsoft.com \
    --cc=hannes@cmpxchg.org \
    --cc=hch@lst.de \
    --cc=hpa@zytor.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jejb@linux.ibm.com \
    --cc=jgross@suse.com \
    --cc=joro@8bytes.org \
    --cc=keescook@chromium.org \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=konrad.wilk@oracle.com \
    --cc=krish.sadhukhan@oracle.com \
    --cc=kuba@kernel.org \
    --cc=kys@microsoft.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-hyperv@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=m.szyprowski@samsung.com \
    --cc=martin.b.radev@gmail.com \
    --cc=martin.petersen@oracle.com \
    --cc=michael.h.kelley@microsoft.com \
    --cc=mingo@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=pgonda@google.com \
    --cc=rientjes@google.com \
    --cc=robin.murphy@arm.com \
    --cc=rppt@kernel.org \
    --cc=saravanand@fb.com \
    --cc=sfr@canb.auug.org.au \
    --cc=sstabellini@kernel.org \
    --cc=sthemmin@microsoft.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=vkuznets@redhat.com \
    --cc=wei.liu@kernel.org \
    --cc=will@kernel.org \
    --cc=x86@kernel.org \
    --cc=xen-devel@lists.xenproject.org \
    --subject='Re: [PATCH 12/13] HV/Netvsc: Add Isolation VM support for netvsc driver' \
    /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

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).