From: Tianyu Lan <ltyker...@gmail.com>
Sent: Tuesday, December 7, 2021 2:56 AM
To: KY Srinivasan <k...@microsoft.com>; Haiyang Zhang <haiya...@microsoft.com>;
Stephen
Hemminger <sthem...@microsoft.com>; wei....@kernel.org; Dexuan Cui
<de...@microsoft.com>;
t...@linutronix.de; mi...@redhat.com; b...@alien8.de;
dave.han...@linux.intel.com;
x...@kernel.org; h...@zytor.com; da...@davemloft.net; k...@kernel.org;
j...@linux.ibm.com;
martin.peter...@oracle.com; a...@arndb.de; h...@infradead.org;
m.szyprow...@samsung.com;
robin.mur...@arm.com; Tianyu Lan <tianyu....@microsoft.com>;
thomas.lenda...@amd.com;
Michael Kelley (LINUX) <mikel...@microsoft.com>
Cc: iommu@lists.linux-foundation.org; linux-a...@vger.kernel.org; linux-
hyp...@vger.kernel.org; linux-ker...@vger.kernel.org;
linux-s...@vger.kernel.org;
net...@vger.kernel.org; vkuznets <vkuzn...@redhat.com>; brijesh.si...@amd.com;
konrad.w...@oracle.com; h...@lst.de; j...@8bytes.org; parri.and...@gmail.com;
dave.han...@intel.com
Subject: [PATCH V6 5/5] net: netvsc: Add Isolation VM support for netvsc driver
From: Tianyu Lan <tianyu....@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() stills need to be handled. Use DMA API to map/umap
these memory during sending/receiving packet and Hyper-V swiotlb
bounce buffer dma address will be returned. The swiotlb bounce buffer
has been masked to be visible to host during boot up.
rx/tx ring buffer is allocated via vzalloc() and they need to be
mapped into unencrypted address space(above vTOM) before sharing
with host and accessing. Add hv_map/unmap_memory() to map/umap rx
/tx ring buffer.
Signed-off-by: Tianyu Lan <tianyu....@microsoft.com>
---
Change since v3:
* Replace HV_HYP_PAGE_SIZE with PAGE_SIZE and virt_to_hvpfn()
with vmalloc_to_pfn() in the hv_map_memory()
Change since v2:
* Add hv_map/unmap_memory() to map/umap rx/tx ring buffer.
---
arch/x86/hyperv/ivm.c | 28 ++++++
drivers/hv/hv_common.c | 11 +++
drivers/net/hyperv/hyperv_net.h | 5 ++
drivers/net/hyperv/netvsc.c | 136 +++++++++++++++++++++++++++++-
drivers/net/hyperv/netvsc_drv.c | 1 +
drivers/net/hyperv/rndis_filter.c | 2 +
include/asm-generic/mshyperv.h | 2 +
include/linux/hyperv.h | 5 ++
8 files changed, 187 insertions(+), 3 deletions(-)
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 69c7a57f3307..2b994117581e 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -287,3 +287,31 @@ int hv_set_mem_host_visibility(unsigned long kbuffer, int
pagecount,
bool visibl
kfree(pfn_array);
return ret;
}
+
+/*
+ * hv_map_memory - map memory to extra space in the AMD SEV-SNP Isolation VM.
+ */
+void *hv_map_memory(void *addr, unsigned long size)
+{
+ unsigned long *pfns = kcalloc(size / PAGE_SIZE,
+ sizeof(unsigned long), GFP_KERNEL);
+ void *vaddr;
+ int i;
+
+ if (!pfns)
+ return NULL;
+
+ for (i = 0; i < size / PAGE_SIZE; i++)
+ pfns[i] = vmalloc_to_pfn(addr + i * PAGE_SIZE) +
+ (ms_hyperv.shared_gpa_boundary >> PAGE_SHIFT);
+
+ vaddr = vmap_pfn(pfns, size / PAGE_SIZE, PAGE_KERNEL_IO);
+ kfree(pfns);
+
+ return vaddr;
+}
+
+void hv_unmap_memory(void *addr)
+{
+ vunmap(addr);
+}
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index 7be173a99f27..3c5cb1f70319 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -295,3 +295,14 @@ u64 __weak hv_ghcb_hypercall(u64 control, void *input,
void *output,
u32 input_s
return HV_STATUS_INVALID_PARAMETER;
}
EXPORT_SYMBOL_GPL(hv_ghcb_hypercall);
+
+void __weak *hv_map_memory(void *addr, unsigned long size)
+{
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(hv_map_memory);
+
+void __weak hv_unmap_memory(void *addr)
+{
+}
+EXPORT_SYMBOL_GPL(hv_unmap_memory);
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 315278a7cf88..cf69da0e296c 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 */
struct vmbus_gpadl recv_buf_gpadl_handle;
u32 recv_section_cnt;
@@ -1082,6 +1084,7 @@ struct netvsc_device {
/* Send buffer allocated by us */
void *send_buf;
+ void *send_original_buf;
u32 send_buf_size;
struct vmbus_gpadl send_buf_gpadl_handle;
u32 send_section_cnt;
@@ -1731,4 +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 396bc1c204e6..b7ade735a806 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) {
+ hv_unmap_memory(nvdev->recv_buf);
+ vfree(nvdev->recv_original_buf);
+ } else {
+ vfree(nvdev->recv_buf);
+ }
+
+ if (nvdev->send_original_buf) {
+ hv_unmap_memory(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++) {
@@ -338,6 +351,7 @@ 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;
@@ -373,6 +387,17 @@ static int netvsc_init_buf(struct hv_device *device,
goto cleanup;
}
+ if (hv_isolation_type_snp()) {
+ vaddr = hv_map_memory(net_device->recv_buf, buf_size);
+ if (!vaddr) {
+ ret = -ENOMEM;
+ 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));
@@ -476,6 +501,17 @@ static int netvsc_init_buf(struct hv_device *device,
goto cleanup;
}
+ if (hv_isolation_type_snp()) {
+ vaddr = hv_map_memory(net_device->send_buf, buf_size);
+ if (!vaddr) {
+ ret = -ENOMEM;
+ 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));
@@ -766,7 +802,7 @@ 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;
@@ -782,6 +818,7 @@ 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);
}
@@ -946,6 +983,88 @@ 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 because the
+ * entries in the page buffer array are not necessarily full
+ * pages of data. Each entry in the array has a separate offset and
+ * len that may be non-zero, even for entries in the middle of the
+ * array. And the entries are not physically contiguous. So each
+ * entry must be individually mapped rather than as a contiguous unit.
+ * 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;
+ }
+
+ /* pb[].offset and pb[].len are not changed during dma mapping
+ * and so not reassign.
+ */
+ packet->dma_range[i].dma = dma;
+ packet->dma_range[i].mapping_size = len;
+ pb[i].pfn = dma >> HV_HYP_PAGE_SHIFT;
+ }
+
+ return 0;
+}
+
static inline int netvsc_send_pkt(
struct hv_device *device,
struct hv_netvsc_packet *packet,
@@ -986,14 +1105,24 @@ 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) {
+ ret = -EAGAIN;
+ goto exit;
+ }
