[RFC V2 PATCH 00/12] x86/Hyper-V: Add Hyper-V Isolation VM support

[RFC V2 PATCH 00/12] x86/Hyper-V: Add Hyper-V Isolation VM support

[Tianyu Lan]

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


Hyper-V provides two kinds of Isolation VMs. VBS(Virtualization-based
security) and AMD SEV-SNP unenlightened Isolation VMs. This patchset
is to add support for these Isolation VM support in Linux.

The memory of these vms are encrypted and host can't access guest
memory directly. Hyper-V provides new host visibility hvcall and
the guest needs to call new hvcall to mark memory visible to host
before sharing memory with host. For security, all network/storage
stack memory should not be shared with host and so there is bounce
buffer requests.

Vmbus channel ring buffer already plays bounce buffer role because
all data from/to host needs to copy from/to between the ring buffer
and IO stack memory. So mark vmbus channel ring buffer visible to
host.

There are two exceptions - packets sent by vmbus_sendpacket_
pagebuffer() and vmbus_sendpacket_mpb_desc(). These packets
contains IO stack memory address and host will access these memory.
So add Hyper-V DMA Ops and use DMA API in the netvsc and storvsc
drivers to allocate bounce buffer via swiotlb interface.

For SNP isolation VM, guest needs to access the shared memory via
extra address space which is specified by Hyper-V CPUID HYPERV_CPUID_
ISOLATION_CONFIG. The access physical address of the shared memory
should be bounce buffer memory GPA plus with shared_gpa_boundary
reported by CPUID.

Change since v1:
       * Add DMA API support in the netvsc and storvsc driver.
       * Add Hyper-V DMA ops.
       * Add static branch for the check of isolation type snp.
       * Fix some code style comments.

Tianyu Lan (12):
  x86/HV: Initialize GHCB page in Isolation VM
  x86/HV: Initialize shared memory boundary in Isolation VM
  x86/Hyper-V: Add new hvcall guest address host visibility support
  HV: Add Write/Read MSR registers via ghcb
  HV: Add ghcb hvcall support for SNP VM
  HV/Vmbus: Add SNP support for VMbus channel initiate message
  HV/Vmbus: Initialize VMbus ring buffer for Isolation VM
  UIO/Hyper-V: Not load UIO HV driver in the isolation VM.
  swiotlb: Add bounce buffer remap address setting function
  HV/IOMMU: Add Hyper-V dma ops support
  HV/Netvsc: Add Isolation VM support for netvsc driver
  HV/Storvsc: Add Isolation VM support for storvsc driver

 arch/x86/hyperv/Makefile           |   2 +-
 arch/x86/hyperv/hv_init.c          |  70 +++++--
 arch/x86/hyperv/ivm.c              | 289 +++++++++++++++++++++++++++++
 arch/x86/include/asm/hyperv-tlfs.h |  22 +++
 arch/x86/include/asm/mshyperv.h    |  90 +++++++--
 arch/x86/kernel/cpu/mshyperv.c     |   5 +
 arch/x86/kernel/pci-swiotlb.c      |   3 +-
 drivers/hv/channel.c               |  44 ++++-
 drivers/hv/connection.c            |  68 ++++++-
 drivers/hv/hv.c                    |  73 ++++++--
 drivers/hv/hyperv_vmbus.h          |   3 +
 drivers/hv/ring_buffer.c           |  83 ++++++---
 drivers/hv/vmbus_drv.c             |   3 +
 drivers/iommu/hyperv-iommu.c       | 127 +++++++++++++
 drivers/net/hyperv/hyperv_net.h    |  11 ++
 drivers/net/hyperv/netvsc.c        | 137 +++++++++++++-
 drivers/net/hyperv/rndis_filter.c  |   3 +
 drivers/scsi/storvsc_drv.c         |  67 ++++++-
 drivers/uio/uio_hv_generic.c       |   5 +
 include/asm-generic/hyperv-tlfs.h  |   1 +
 include/asm-generic/mshyperv.h     |  18 +-
 include/linux/hyperv.h             |  12 +-
 include/linux/swiotlb.h            |   5 +
 kernel/dma/swiotlb.c               |  13 +-
 mm/ioremap.c                       |   1 +
 mm/vmalloc.c                       |   1 +
 26 files changed, 1068 insertions(+), 88 deletions(-)
 create mode 100644 arch/x86/hyperv/ivm.c

-- 
2.25.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[RFC V2 PATCH 9/12] swiotlb: Add bounce buffer remap address setting function

[Tianyu Lan]

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

For Hyper-V isolation VM with AMD SEV SNP, the bounce buffer(shared memory)
needs to be accessed via extra address space(e.g address above bit39).
Hyper-V code may remap extra address space outside of swiotlb. swiotlb_bounce()
needs to use remap virtual address to copy data from/to bounce buffer. Add
new interface swiotlb_set_bounce_remap() to do that.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 include/linux/swiotlb.h |  5 +++++
 kernel/dma/swiotlb.c    | 13 ++++++++++++-
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index d9c9fc9ca5d2..3ccd08116683 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -82,8 +82,13 @@ unsigned int swiotlb_max_segment(void);
 size_t swiotlb_max_mapping_size(struct device *dev);
 bool is_swiotlb_active(void);
 void __init swiotlb_adjust_size(unsigned long new_size);
+void swiotlb_set_bounce_remap(unsigned char *vaddr);
 #else
 #define swiotlb_force SWIOTLB_NO_FORCE
+static inline void swiotlb_set_bounce_remap(unsigned char *vaddr)
+{
+}
+
 static inline bool is_swiotlb_buffer(phys_addr_t paddr)
 {
 	return false;
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 7c42df6e6100..5fd2db6aa149 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -94,6 +94,7 @@ static unsigned int io_tlb_index;
  * not be bounced (unless SWIOTLB_FORCE is set).
  */
 static unsigned int max_segment;
+static unsigned char *swiotlb_bounce_remap_addr;
 
 /*
  * We need to save away the original address corresponding to a mapped entry
@@ -421,6 +422,11 @@ void __init swiotlb_exit(void)
 	swiotlb_cleanup();
 }
 
+void swiotlb_set_bounce_remap(unsigned char *vaddr)
+{
+	swiotlb_bounce_remap_addr = vaddr;
+}
+
 /*
  * Bounce: copy the swiotlb buffer from or back to the original dma location
  */
@@ -428,7 +434,12 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
 			   size_t size, enum dma_data_direction dir)
 {
 	unsigned long pfn = PFN_DOWN(orig_addr);
-	unsigned char *vaddr = phys_to_virt(tlb_addr);
+	unsigned char *vaddr;
+
+	if (swiotlb_bounce_remap_addr)
+		vaddr = swiotlb_bounce_remap_addr + tlb_addr - io_tlb_start;
+	else
+		vaddr = phys_to_virt(tlb_addr);
 
 	if (PageHighMem(pfn_to_page(pfn))) {
 		/* The buffer does not have a mapping.  Map it in and copy */
-- 
2.25.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [RFC V2 PATCH 9/12] swiotlb: Add bounce buffer remap address setting function

[Christoph Hellwig]

On Tue, Apr 13, 2021 at 11:22:14AM -0400, Tianyu Lan wrote:
> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
> 
> For Hyper-V isolation VM with AMD SEV SNP, the bounce buffer(shared memory)
> needs to be accessed via extra address space(e.g address above bit39).
> Hyper-V code may remap extra address space outside of swiotlb. swiotlb_bounce()
> needs to use remap virtual address to copy data from/to bounce buffer. Add
> new interface swiotlb_set_bounce_remap() to do that.

I have no way to review what this actually doing when you only Cc me
on a single patch.  Please make sure everyone is Cced on the whole
series to enable proper review.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [RFC V2 PATCH 9/12] swiotlb: Add bounce buffer remap address setting function

[Tianyu Lan]

On 4/14/2021 2:43 PM, Christoph Hellwig wrote:
> On Tue, Apr 13, 2021 at 11:22:14AM -0400, Tianyu Lan wrote:
>> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
>>
>> For Hyper-V isolation VM with AMD SEV SNP, the bounce buffer(shared memory)
>> needs to be accessed via extra address space(e.g address above bit39).
>> Hyper-V code may remap extra address space outside of swiotlb. swiotlb_bounce()
>> needs to use remap virtual address to copy data from/to bounce buffer. Add
>> new interface swiotlb_set_bounce_remap() to do that.
> 
> I have no way to review what this actually doing when you only Cc me
> on a single patch.  Please make sure everyone is Cced on the whole
> series to enable proper review.
> 

Sure. I will resend all patches. Thanks for reminder.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[RFC V2 PATCH 10/12] HV/IOMMU: Add Hyper-V dma ops support

[Tianyu Lan]

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

Hyper-V Isolation VM requires bounce buffer support. To use swiotlb
bounce buffer, add Hyper-V dma ops and use swiotlb functions in the
map and unmap callback.

Allocate bounce buffer in the Hyper-V code because bounce buffer
needs to be accessed via extra address space(e.g, address above 39bit)
in the AMD SEV SNP based Isolation VM.

ioremap_cache() can't use in the hyperv_iommu_swiotlb_init() which
is too early place and remap bounce buffer in the hyperv_iommu_swiotlb_
later_init().

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 arch/x86/kernel/pci-swiotlb.c |   3 +-
 drivers/hv/vmbus_drv.c        |   3 +
 drivers/iommu/hyperv-iommu.c  | 127 ++++++++++++++++++++++++++++++++++
 3 files changed, 132 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index c2cfa5e7c152..caaf68c06f24 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -15,6 +15,7 @@
 #include <asm/iommu_table.h>
 
 int swiotlb __read_mostly;
+extern int hyperv_swiotlb;
 
 /*
  * pci_swiotlb_detect_override - set swiotlb to 1 if necessary
@@ -68,7 +69,7 @@ void __init pci_swiotlb_init(void)
 void __init pci_swiotlb_late_init(void)
 {
 	/* An IOMMU turned us off. */
-	if (!swiotlb)
+	if (!swiotlb && !hyperv_swiotlb)
 		swiotlb_exit();
 	else {
 		printk(KERN_INFO "PCI-DMA: "
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 10dce9f91216..0ee6ec3a5de6 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -23,6 +23,7 @@
 #include <linux/cpu.h>
 #include <linux/sched/task_stack.h>
 
+#include <linux/dma-map-ops.h>
 #include <linux/delay.h>
 #include <linux/notifier.h>
 #include <linux/ptrace.h>
@@ -2030,6 +2031,7 @@ struct hv_device *vmbus_device_create(const guid_t *type,
 	return child_device_obj;
 }
 
+static u64 vmbus_dma_mask = DMA_BIT_MASK(64);
 /*
  * vmbus_device_register - Register the child device
  */
@@ -2070,6 +2072,7 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 	}
 	hv_debug_add_dev_dir(child_device_obj);
 
+	child_device_obj->device.dma_mask = &vmbus_dma_mask;
 	return 0;
 
 err_kset_unregister:
diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c
index e285a220c913..588ba847f0cc 100644
--- a/drivers/iommu/hyperv-iommu.c
+++ b/drivers/iommu/hyperv-iommu.c
@@ -13,19 +13,28 @@
 #include <linux/irq.h>
 #include <linux/iommu.h>
 #include <linux/module.h>
+#include <linux/hyperv.h>
 
+#include <asm/io.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
 #include <asm/hw_irq.h>
 #include <asm/io_apic.h>
+#include <asm/iommu.h>
+#include <asm/iommu_table.h>
 #include <asm/irq_remapping.h>
 #include <asm/hypervisor.h>
 #include <asm/mshyperv.h>
+#include <asm/swiotlb.h>
+#include <linux/dma-map-ops.h>
+#include <linux/dma-direct.h>
 
 #include "irq_remapping.h"
 
 #ifdef CONFIG_IRQ_REMAP
 
+int hyperv_swiotlb __read_mostly;
+
 /*
  * According 82093AA IO-APIC spec , IO APIC has a 24-entry Interrupt
  * Redirection Table. Hyper-V exposes one single IO-APIC and so define
@@ -36,6 +45,10 @@
 static cpumask_t ioapic_max_cpumask = { CPU_BITS_NONE };
 static struct irq_domain *ioapic_ir_domain;
 
+static unsigned long hyperv_io_tlb_start, *hyperv_io_tlb_end; 
+static unsigned long hyperv_io_tlb_nslabs, hyperv_io_tlb_size;
+static void *hyperv_io_tlb_remap;
+
 static int hyperv_ir_set_affinity(struct irq_data *data,
 		const struct cpumask *mask, bool force)
 {
@@ -337,4 +350,118 @@ static const struct irq_domain_ops hyperv_root_ir_domain_ops = {
 	.free = hyperv_root_irq_remapping_free,
 };
 
+static dma_addr_t hyperv_map_page(struct device *dev, struct page *page,
+				  unsigned long offset, size_t size,
+				  enum dma_data_direction dir,
+				  unsigned long attrs)
+{
+	phys_addr_t map, phys = (page_to_pfn(page) << PAGE_SHIFT) + offset;
+
+	if (!hv_is_isolation_supported())
+		return phys;
+
+	map = swiotlb_tbl_map_single(dev, phys, size, HV_HYP_PAGE_SIZE, dir,
+				     attrs);
+	if (map == (phys_addr_t)DMA_MAPPING_ERROR)
+		return DMA_MAPPING_ERROR;
+
+	return map;
+}
+
+static void hyperv_unmap_page(struct device *dev, dma_addr_t dev_addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	if (!hv_is_isolation_supported())
+		return;
+
+	swiotlb_tbl_unmap_single(dev, dev_addr, size, HV_HYP_PAGE_SIZE, dir,
+				attrs);
+}
+
+int __init hyperv_swiotlb_init(void)
+{
+	unsigned long bytes;
+	void *vstart = 0;
+
+	bytes = 200 * 1024 * 1024;
+	vstart = memblock_alloc_low(PAGE_ALIGN(bytes), PAGE_SIZE);
+	hyperv_io_tlb_nslabs = bytes >> IO_TLB_SHIFT;
+	hyperv_io_tlb_size = bytes;
+
+	if (!vstart) {
+		pr_warn("Fail to allocate swiotlb.\n");
+		return -ENOMEM;
+	}
+
+	hyperv_io_tlb_start = virt_to_phys(vstart);
+	if (!hyperv_io_tlb_start)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx.\n",
+		      __func__, PAGE_ALIGN(bytes), PAGE_SIZE);
+
+	if (swiotlb_init_with_tbl(vstart, hyperv_io_tlb_nslabs, 1))
+		panic("%s: Cannot allocate SWIOTLB buffer.\n", __func__);
+
+	swiotlb_set_max_segment(PAGE_SIZE);
+	hyperv_io_tlb_end = hyperv_io_tlb_start + bytes;
+	return 0;
+}
+
+const struct dma_map_ops hyperv_dma_ops = {
+	.map_page = hyperv_map_page,
+	.unmap_page = hyperv_unmap_page,
+};
+
+int __init hyperv_swiotlb_detect(void)
+{
+	dma_ops = &hyperv_dma_ops;
+
+	if (hypervisor_is_type(X86_HYPER_MS_HYPERV)
+	    && hv_is_isolation_supported()) {
+		/*
+		 * Disable generic swiotlb and allocate Hyper-v swiotlb
+		 * in the hyperv_iommu_swiotlb_init().
+		 */
+		swiotlb = 0;
+		hyperv_swiotlb = 1;
+
+		return 1;
+	}
+
+	return 0;
+}
+
+void __init hyperv_iommu_swiotlb_init(void)
+{
+	hyperv_swiotlb_init();
+}
+
+void __init hyperv_iommu_swiotlb_later_init(void)
+{
+	int ret;
+
+	/* Mask bounce buffer visible to host and remap extra address. */
+	if (hv_isolation_type_snp()) {
+		ret = hv_set_mem_host_visibility(
+				phys_to_virt(hyperv_io_tlb_start),
+				hyperv_io_tlb_size,
+				VMBUS_PAGE_VISIBLE_READ_WRITE);
+		if (ret)
+			panic("%s: Fail to mark Hyper-v swiotlb buffer visible to host. err=%d\n",
+			      __func__, ret);
+
+		hyperv_io_tlb_remap = ioremap_cache(hyperv_io_tlb_start
+					    + ms_hyperv.shared_gpa_boundary,
+						    hyperv_io_tlb_size);
+		if (!hyperv_io_tlb_remap)
+			panic("%s: Fail to remap io tlb.\n", __func__);
+
+		memset(hyperv_io_tlb_remap, 0x00, hyperv_io_tlb_size);
+		swiotlb_set_bounce_remap(hyperv_io_tlb_remap);
+	}
+}
+
+IOMMU_INIT_FINISH(hyperv_swiotlb_detect,
+		  NULL, hyperv_iommu_swiotlb_init,
+		  hyperv_iommu_swiotlb_later_init);
+
 #endif
-- 
2.25.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu