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

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

[Tianyu Lan]

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

"Resend all patches because someone in CC list didn't receive all
patchset. Sorry for nosy."

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.

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 allocation bounce buffer support in vmbus for these packets.

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.

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

[Resend RFC PATCH V2 01/12] x86/HV: Initialize GHCB page in Isolation VM

[Tianyu Lan]

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

Hyper-V exposes GHCB page via SEV ES GHCB MSR for SNP guest
to communicate with hypervisor. Map GHCB page for all
cpus to read/write MSR register and submit hvcall request
via GHCB.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 arch/x86/hyperv/hv_init.c      | 52 +++++++++++++++++++++++++++++++---
 include/asm-generic/mshyperv.h |  1 +
 2 files changed, 49 insertions(+), 4 deletions(-)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 0db5137d5b81..90e65fbf4c58 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -82,6 +82,9 @@ static int hv_cpu_init(unsigned int cpu)
 	struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
 	void **input_arg;
 	struct page *pg;
+	u64 ghcb_gpa;
+	void *ghcb_va;
+	void **ghcb_base;
 
 	/* hv_cpu_init() can be called with IRQs disabled from hv_resume() */
 	pg = alloc_pages(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL, hv_root_partition ? 1 : 0);
@@ -128,6 +131,17 @@ static int hv_cpu_init(unsigned int cpu)
 		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, val);
 	}
 
+	if (ms_hyperv.ghcb_base) {
+		rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
+
+		ghcb_va = ioremap_cache(ghcb_gpa, HV_HYP_PAGE_SIZE);
+		if (!ghcb_va)
+			return -ENOMEM;
+
+		ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+		*ghcb_base = ghcb_va;
+	}
+
 	return 0;
 }
 
@@ -223,6 +237,7 @@ static int hv_cpu_die(unsigned int cpu)
 	unsigned long flags;
 	void **input_arg;
 	void *pg;
+	void **ghcb_va = NULL;
 
 	local_irq_save(flags);
 	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
@@ -236,6 +251,13 @@ static int hv_cpu_die(unsigned int cpu)
 		*output_arg = NULL;
 	}
 
+	if (ms_hyperv.ghcb_base) {
+		ghcb_va = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+		if (*ghcb_va)
+			iounmap(*ghcb_va);
+		*ghcb_va = NULL;
+	}
+
 	local_irq_restore(flags);
 
 	free_pages((unsigned long)pg, hv_root_partition ? 1 : 0);
@@ -372,6 +394,9 @@ void __init hyperv_init(void)
 	u64 guest_id, required_msrs;
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 	int cpuhp, i;
+	u64 ghcb_gpa;
+	void *ghcb_va;
+	void **ghcb_base;
 
 	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
 		return;
@@ -432,9 +457,24 @@ void __init hyperv_init(void)
 			VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX,
 			VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
 			__builtin_return_address(0));
-	if (hv_hypercall_pg == NULL) {
-		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
-		goto remove_cpuhp_state;
+	if (hv_hypercall_pg == NULL)
+		goto clean_guest_os_id;
+
+	if (hv_isolation_type_snp()) {
+		ms_hyperv.ghcb_base = alloc_percpu(void *);
+		if (!ms_hyperv.ghcb_base)
+			goto clean_guest_os_id;
+
+		rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
+		ghcb_va = ioremap_cache(ghcb_gpa, HV_HYP_PAGE_SIZE);
+		if (!ghcb_va) {
+			free_percpu(ms_hyperv.ghcb_base);
+			ms_hyperv.ghcb_base = NULL;
+			goto clean_guest_os_id;
+		}
+
+		ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+		*ghcb_base = ghcb_va;
 	}
 
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
@@ -499,7 +539,8 @@ void __init hyperv_init(void)
 
 	return;
 
-remove_cpuhp_state:
+clean_guest_os_id:
+	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 	cpuhp_remove_state(cpuhp);
 free_vp_assist_page:
 	kfree(hv_vp_assist_page);
@@ -528,6 +569,9 @@ void hyperv_cleanup(void)
 	 */
 	hv_hypercall_pg = NULL;
 
+	if (ms_hyperv.ghcb_base)
+		free_percpu(ms_hyperv.ghcb_base);
+
 	/* Reset the hypercall page */
 	hypercall_msr.as_uint64 = 0;
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index dff58a3db5d5..c6f4c5c20fb8 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -35,6 +35,7 @@ struct ms_hyperv_info {
 	u32 max_lp_index;
 	u32 isolation_config_a;
 	u32 isolation_config_b;
+	void  __percpu **ghcb_base;
 };
 extern struct ms_hyperv_info ms_hyperv;
 
-- 
2.25.1

[Resend RFC PATCH V2 02/12] x86/HV: Initialize shared memory boundary in Isolation VM

[Tianyu Lan]

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

Hyper-V exposes shared memory boundary via cpuid HYPERV_
CPUID_ISOLATION_CONFIG and store it in the shared_gpa_
boundary of ms_hyperv struct. This prepares to share
memory with host for AMD SEV SNP guest.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 arch/x86/kernel/cpu/mshyperv.c |  2 ++
 include/asm-generic/mshyperv.h | 13 ++++++++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index e88bc296afca..aeafd4017c89 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -328,6 +328,8 @@ static void __init ms_hyperv_init_platform(void)
 	if (ms_hyperv.features_b & HV_ISOLATION) {
 		ms_hyperv.isolation_config_a = cpuid_eax(HYPERV_CPUID_ISOLATION_CONFIG);
 		ms_hyperv.isolation_config_b = cpuid_ebx(HYPERV_CPUID_ISOLATION_CONFIG);
+		ms_hyperv.shared_gpa_boundary =
+			(u64)1 << ms_hyperv.shared_gpa_boundary_bits;
 
 		pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n",
 			ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b);
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index c6f4c5c20fb8..b73e201abc70 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -34,8 +34,19 @@ struct ms_hyperv_info {
 	u32 max_vp_index;
 	u32 max_lp_index;
 	u32 isolation_config_a;
-	u32 isolation_config_b;
+	union
+	{
+		u32 isolation_config_b;
+		struct {
+			u32 cvm_type : 4;
+			u32 Reserved11 : 1;
+			u32 shared_gpa_boundary_active : 1;
+			u32 shared_gpa_boundary_bits : 6;
+			u32 Reserved12 : 20;
+		};
+	};
 	void  __percpu **ghcb_base;
+	u64 shared_gpa_boundary;
 };
 extern struct ms_hyperv_info ms_hyperv;
 
-- 
2.25.1

[Resend RFC PATCH V2 03/12] x86/Hyper-V: Add new hvcall guest address host visibility support

[Tianyu Lan]

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

Add new hvcall guest address host visibility support. Mark vmbus
ring buffer visible to host when create gpadl buffer and mark back
to not visible when tear down gpadl buffer.

Co-Developed-by: Sunil Muthuswamy <sunilmut@microsoft.com>
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 arch/x86/hyperv/Makefile           |  2 +-
 arch/x86/hyperv/ivm.c              | 90 ++++++++++++++++++++++++++++++
 arch/x86/include/asm/hyperv-tlfs.h | 22 ++++++++
 arch/x86/include/asm/mshyperv.h    |  2 +
 drivers/hv/channel.c               | 34 ++++++++++-
 include/asm-generic/hyperv-tlfs.h  |  1 +
 include/linux/hyperv.h             | 12 +++-
 7 files changed, 159 insertions(+), 4 deletions(-)
 create mode 100644 arch/x86/hyperv/ivm.c

diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index 48e2c51464e8..5d2de10809ae 100644
--- a/arch/x86/hyperv/Makefile
+++ b/arch/x86/hyperv/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y			:= hv_init.o mmu.o nested.o irqdomain.o
+obj-y			:= hv_init.o mmu.o nested.o irqdomain.o ivm.o
 obj-$(CONFIG_X86_64)	+= hv_apic.o hv_proc.o
 
 ifdef CONFIG_X86_64
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
new file mode 100644
index 000000000000..a5950b7a9214
--- /dev/null
+++ b/arch/x86/hyperv/ivm.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hyper-V Isolation VM interface with paravisor and hypervisor
+ *
+ * Author:
+ *  Tianyu Lan <Tianyu.Lan@microsoft.com>
+ */
+
+#include <linux/hyperv.h>
+#include <linux/types.h>
+#include <linux/bitfield.h>
+#include <asm/io.h>
+#include <asm/mshyperv.h>
+
+/*
+ * hv_set_mem_host_visibility - Set host visibility for specified memory.
+ */
+int hv_set_mem_host_visibility(void *kbuffer, u32 size, u32 visibility)
+{
+	int i, pfn;
+	int pagecount = size >> HV_HYP_PAGE_SHIFT;
+	u64 *pfn_array;
+	int ret = 0;
+
+	pfn_array = vzalloc(HV_HYP_PAGE_SIZE);
+	if (!pfn_array)
+		return -ENOMEM;
+
+	for (i = 0, pfn = 0; i < pagecount; i++) {
+		pfn_array[pfn] = virt_to_hvpfn(kbuffer + i * HV_HYP_PAGE_SIZE);
+		pfn++;
+
+		if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
+			ret = hv_mark_gpa_visibility(pfn, pfn_array, visibility);
+			pfn = 0;
+
+			if (ret)
+				goto err_free_pfn_array;
+		}
+	}
+
+ err_free_pfn_array:
+	vfree(pfn_array);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hv_set_mem_host_visibility);
+
+int hv_mark_gpa_visibility(u16 count, const u64 pfn[], u32 visibility)
+{
+	struct hv_input_modify_sparse_gpa_page_host_visibility **input_pcpu;
+	struct hv_input_modify_sparse_gpa_page_host_visibility *input;
+	u16 pages_processed;
+	u64 hv_status;
+	unsigned long flags;
+
+	/* no-op if partition isolation is not enabled */
+	if (!hv_is_isolation_supported())
+		return 0;
+
+	if (count > HV_MAX_MODIFY_GPA_REP_COUNT) {
+		pr_err("Hyper-V: GPA count:%d exceeds supported:%lu\n", count,
+			HV_MAX_MODIFY_GPA_REP_COUNT);
+		return -EINVAL;
+	}
+
+	local_irq_save(flags);
+	input_pcpu = (struct hv_input_modify_sparse_gpa_page_host_visibility **)
+			this_cpu_ptr(hyperv_pcpu_input_arg);
+	input = *input_pcpu;
+	if (unlikely(!input)) {
+		local_irq_restore(flags);
+		return -1;
+	}
+
+	input->partition_id = HV_PARTITION_ID_SELF;
+	input->host_visibility = visibility;
+	input->reserved0 = 0;
+	input->reserved1 = 0;
+	memcpy((void *)input->gpa_page_list, pfn, count * sizeof(*pfn));
+	hv_status = hv_do_rep_hypercall(
+			HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY, count,
+			0, input, &pages_processed);
+	local_irq_restore(flags);
+
+	if (!(hv_status & HV_HYPERCALL_RESULT_MASK))
+		return 0;
+
+	return hv_status & HV_HYPERCALL_RESULT_MASK;
+}
+EXPORT_SYMBOL(hv_mark_gpa_visibility);
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index e6cd3fee562b..1f1ce9afb6f1 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -236,6 +236,15 @@ enum hv_isolation_type {
 /* TSC invariant control */
 #define HV_X64_MSR_TSC_INVARIANT_CONTROL	0x40000118
 
+/* Hyper-V GPA map flags */
+#define HV_MAP_GPA_PERMISSIONS_NONE            0x0
+#define HV_MAP_GPA_READABLE                    0x1
+#define HV_MAP_GPA_WRITABLE                    0x2
+
+#define VMBUS_PAGE_VISIBLE_READ_ONLY HV_MAP_GPA_READABLE
+#define VMBUS_PAGE_VISIBLE_READ_WRITE (HV_MAP_GPA_READABLE|HV_MAP_GPA_WRITABLE)
+#define VMBUS_PAGE_NOT_VISIBLE HV_MAP_GPA_PERMISSIONS_NONE
+
 /*
  * Declare the MSR used to setup pages used to communicate with the hypervisor.
  */
@@ -564,4 +573,17 @@ enum hv_interrupt_type {
 
 #include <asm-generic/hyperv-tlfs.h>
 
+/* All input parameters should be in single page. */
+#define HV_MAX_MODIFY_GPA_REP_COUNT		\
+	((PAGE_SIZE / sizeof(u64)) - 2)
+
+/* HvCallModifySparseGpaPageHostVisibility hypercall */
+struct hv_input_modify_sparse_gpa_page_host_visibility {
+	u64 partition_id;
+	u32 host_visibility:2;
+	u32 reserved0:30;
+	u32 reserved1;
+	u64 gpa_page_list[HV_MAX_MODIFY_GPA_REP_COUNT];
+} __packed;
+
 #endif
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index ccf60a809a17..d9437f096ce5 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -269,6 +269,8 @@ int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
 		struct hv_interrupt_entry *entry);
 int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
 
+int hv_set_mem_host_visibility(void *kbuffer, u32 size, u32 visibility);
+int hv_mark_gpa_visibility(u16 count, const u64 pfn[], u32 visibility);
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 0bd202de7960..407b74d72f3f 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -400,7 +400,7 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 	struct list_head *curr;
 	u32 next_gpadl_handle;
 	unsigned long flags;
-	int ret = 0;
+	int ret = 0, index;
 
 	next_gpadl_handle =
 		(atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1);
@@ -409,6 +409,13 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 	if (ret)
 		return ret;
 
+	ret = hv_set_mem_host_visibility(kbuffer, size,
+					 VMBUS_PAGE_VISIBLE_READ_WRITE);
+	if (ret) {
+		pr_warn("Failed to set host visibility.\n");
+		return ret;
+	}
+
 	init_completion(&msginfo->waitevent);
 	msginfo->waiting_channel = channel;
 
@@ -484,6 +491,16 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 	}
 
 	kfree(msginfo);
+
+	if (type == HV_GPADL_BUFFER)
+		index = 0;
+	else
+		index = channel->gpadl_range[1].gpadlhandle ? 2 : 1;
+
+	channel->gpadl_range[index].size = size;
+	channel->gpadl_range[index].buffer = kbuffer;
+	channel->gpadl_range[index].gpadlhandle = *gpadl_handle;
+
 	return ret;
 }
 
@@ -743,7 +760,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	struct vmbus_channel_gpadl_teardown *msg;
 	struct vmbus_channel_msginfo *info;
 	unsigned long flags;
-	int ret;
+	int ret, i;
 
 	info = kzalloc(sizeof(*info) +
 		       sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL);
@@ -791,6 +808,19 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
 	kfree(info);
+
+	/* Find gpadl buffer virtual address and size. */
+	for (i = 0; i < VMBUS_GPADL_RANGE_COUNT; i++)
+		if (channel->gpadl_range[i].gpadlhandle == gpadl_handle)
+			break;
+
+	if (hv_set_mem_host_visibility(channel->gpadl_range[i].buffer,
+				       channel->gpadl_range[i].size,
+				       VMBUS_PAGE_NOT_VISIBLE))
+		pr_warn("Fail to set mem host visibility.\n");
+
+	channel->gpadl_range[i].gpadlhandle = 0;
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl);
diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h
index 83448e837ded..ad19f4199f90 100644
--- a/include/asm-generic/hyperv-tlfs.h
+++ b/include/asm-generic/hyperv-tlfs.h
@@ -158,6 +158,7 @@ struct ms_hyperv_tsc_page {
 #define HVCALL_RETARGET_INTERRUPT		0x007e
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
+#define HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db
 
 #define HV_FLUSH_ALL_PROCESSORS			BIT(0)
 #define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES	BIT(1)
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index f1d74dcf0353..b877a68f326c 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -788,6 +788,14 @@ struct vmbus_device {
 	bool allowed_in_isolated;
 };
 
+struct vmbus_gpadl_range {
+	u32 gpadlhandle;
+	u32 size;
+	void *buffer;
+};
+
+#define VMBUS_GPADL_RANGE_COUNT		3
+
 struct vmbus_channel {
 	struct list_head listentry;
 
@@ -808,6 +816,8 @@ struct vmbus_channel {
 	struct completion rescind_event;
 
 	u32 ringbuffer_gpadlhandle;
+	/* GPADL_RING and Send/Receive GPADL_BUFFER. */
+	struct vmbus_gpadl_range gpadl_range[VMBUS_GPADL_RANGE_COUNT];
 
 	/* Allocated memory for ring buffer */
 	struct page *ringbuffer_page;
@@ -1182,7 +1192,7 @@ extern int vmbus_establish_gpadl(struct vmbus_channel *channel,
 				      u32 *gpadl_handle);
 
 extern int vmbus_teardown_gpadl(struct vmbus_channel *channel,
-				     u32 gpadl_handle);
+				u32 gpadl_handle);
 
 void vmbus_reset_channel_cb(struct vmbus_channel *channel);
 
-- 
2.25.1

Re: [Resend RFC PATCH V2 03/12] x86/Hyper-V: Add new hvcall guest address host visibility support

[Christoph Hellwig]

> +/*
> + * hv_set_mem_host_visibility - Set host visibility for specified memory.
> + */

I don't think this comment really clarifies anything over the function
name.  What is 'host visibility'

> +int hv_set_mem_host_visibility(void *kbuffer, u32 size, u32 visibility)

Should size be a size_t?
Should visibility be an enum of some kind?

> +int hv_mark_gpa_visibility(u16 count, const u64 pfn[], u32 visibility)

Not sure what this does either.

> +	local_irq_save(flags);
> +	input_pcpu = (struct hv_input_modify_sparse_gpa_page_host_visibility **)

Is there a chance we could find a shorter but still descriptive
name for this variable?  Why do we need the cast?

> +#define VMBUS_PAGE_VISIBLE_READ_ONLY HV_MAP_GPA_READABLE
> +#define VMBUS_PAGE_VISIBLE_READ_WRITE (HV_MAP_GPA_READABLE|HV_MAP_GPA_WRITABLE)

pointlessly overlong line.

Re: [Resend RFC PATCH V2 03/12] x86/Hyper-V: Add new hvcall guest address host visibility support

[Tianyu Lan]

Hi Christoph:
	Thanks for your review.

On 4/14/2021 11:40 PM, Christoph Hellwig wrote:
>> +/*
>> + * hv_set_mem_host_visibility - Set host visibility for specified memory.
>> + */
> 
> I don't think this comment really clarifies anything over the function
> name.  What is 'host visibility'

OK. Will update the comment.

> 
>> +int hv_set_mem_host_visibility(void *kbuffer, u32 size, u32 visibility)
> 
> Should size be a size_t?
> Should visibility be an enum of some kind?
> 

Will update.

>> +int hv_mark_gpa_visibility(u16 count, const u64 pfn[], u32 visibility)
> 
> Not sure what this does either.

Will add a comment.

> 
>> +	local_irq_save(flags);
>> +	input_pcpu = (struct hv_input_modify_sparse_gpa_page_host_visibility **)
> 
> Is there a chance we could find a shorter but still descriptive
> name for this variable?  Why do we need the cast?

Sure. The cast is to avoid build error due to "incompatible-pointer-types"
> 
>> +#define VMBUS_PAGE_VISIBLE_READ_ONLY HV_MAP_GPA_READABLE
>> +#define VMBUS_PAGE_VISIBLE_READ_WRITE (HV_MAP_GPA_READABLE|HV_MAP_GPA_WRITABLE)
> 
> pointlessly overlong line.
> 

[Resend RFC PATCH V2 04/12] HV: Add Write/Read MSR registers via ghcb

[Tianyu Lan]

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

Hyper-V provides GHCB protocol to write Synthetic Interrupt
Controller MSR registers and these registers are emulated by
Hypervisor rather than paravisor.

Hyper-V requests to write SINTx MSR registers twice(once via
GHCB and once via wrmsr instruction including the proxy bit 21)
Guest OS ID MSR also needs to be set via GHCB.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 arch/x86/hyperv/hv_init.c       |  18 +----
 arch/x86/hyperv/ivm.c           | 130 ++++++++++++++++++++++++++++++++
 arch/x86/include/asm/mshyperv.h |  87 +++++++++++++++++----
 arch/x86/kernel/cpu/mshyperv.c  |   3 +
 drivers/hv/hv.c                 |  65 +++++++++++-----
 include/asm-generic/mshyperv.h  |   4 +-
 6 files changed, 261 insertions(+), 46 deletions(-)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 90e65fbf4c58..87b1dd9c84d6 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -475,6 +475,9 @@ void __init hyperv_init(void)
 
 		ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
 		*ghcb_base = ghcb_va;
+
+		/* Hyper-V requires to write guest os id via ghcb in SNP IVM. */
+		hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);
 	}
 
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
@@ -561,6 +564,7 @@ void hyperv_cleanup(void)
 
 	/* Reset our OS id */
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+	hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
 
 	/*
 	 * Reset hypercall page reference before reset the page,
@@ -668,17 +672,3 @@ bool hv_is_hibernation_supported(void)
 	return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4);
 }
 EXPORT_SYMBOL_GPL(hv_is_hibernation_supported);
-
-enum hv_isolation_type hv_get_isolation_type(void)
-{
-	if (!(ms_hyperv.features_b & HV_ISOLATION))
-		return HV_ISOLATION_TYPE_NONE;
-	return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b);
-}
-EXPORT_SYMBOL_GPL(hv_get_isolation_type);
-
-bool hv_is_isolation_supported(void)
-{
-	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
-}
-EXPORT_SYMBOL_GPL(hv_is_isolation_supported);
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index a5950b7a9214..2ec64b367aaf 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -6,12 +6,139 @@
  *  Tianyu Lan <Tianyu.Lan@microsoft.com>
  */
 
+#include <linux/types.h>
+#include <linux/bitfield.h>
 #include <linux/hyperv.h>
 #include <linux/types.h>
 #include <linux/bitfield.h>
 #include <asm/io.h>
+#include <asm/svm.h>
+#include <asm/sev-es.h>
 #include <asm/mshyperv.h>
 
+union hv_ghcb {
+	struct ghcb ghcb;
+} __packed __aligned(PAGE_SIZE);
+
+void hv_ghcb_msr_write(u64 msr, u64 value)
+{
+	union hv_ghcb *hv_ghcb;
+	void **ghcb_base;
+	unsigned long flags;
+
+	if (!ms_hyperv.ghcb_base)
+		return;
+
+	local_irq_save(flags);
+	ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+	hv_ghcb = (union hv_ghcb *)*ghcb_base;
+	if (!hv_ghcb) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	memset(hv_ghcb, 0x00, HV_HYP_PAGE_SIZE);
+
+	hv_ghcb->ghcb.protocol_version = 1;
+	hv_ghcb->ghcb.ghcb_usage = 0;
+
+	ghcb_set_sw_exit_code(&hv_ghcb->ghcb, SVM_EXIT_MSR);
+	ghcb_set_rcx(&hv_ghcb->ghcb, msr);
+	ghcb_set_rax(&hv_ghcb->ghcb, lower_32_bits(value));
+	ghcb_set_rdx(&hv_ghcb->ghcb, value >> 32);
+	ghcb_set_sw_exit_info_1(&hv_ghcb->ghcb, 1);
+	ghcb_set_sw_exit_info_2(&hv_ghcb->ghcb, 0);
+
+	VMGEXIT();
+
+	if ((hv_ghcb->ghcb.save.sw_exit_info_1 & 0xffffffff) == 1)
+		pr_warn("Fail to write msr via ghcb.\n.");
+
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(hv_ghcb_msr_write);
+
+void hv_ghcb_msr_read(u64 msr, u64 *value)
+{
+	union hv_ghcb *hv_ghcb;
+	void **ghcb_base;
+	unsigned long flags;
+
+	if (!ms_hyperv.ghcb_base)
+		return;
+
+	local_irq_save(flags);
+	ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+	hv_ghcb = (union hv_ghcb *)*ghcb_base;
+	if (!hv_ghcb) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	memset(hv_ghcb, 0x00, PAGE_SIZE);
+	hv_ghcb->ghcb.protocol_version = 1;
+	hv_ghcb->ghcb.ghcb_usage = 0;
+
+	ghcb_set_sw_exit_code(&hv_ghcb->ghcb, SVM_EXIT_MSR);
+	ghcb_set_rcx(&hv_ghcb->ghcb, msr);
+	ghcb_set_sw_exit_info_1(&hv_ghcb->ghcb, 0);
+	ghcb_set_sw_exit_info_2(&hv_ghcb->ghcb, 0);
+
+	VMGEXIT();
+
+	if ((hv_ghcb->ghcb.save.sw_exit_info_1 & 0xffffffff) == 1)
+		pr_warn("Fail to write msr via ghcb.\n.");
+	else
+		*value = (u64)lower_32_bits(hv_ghcb->ghcb.save.rax)
+			| ((u64)lower_32_bits(hv_ghcb->ghcb.save.rdx) << 32);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(hv_ghcb_msr_read);
+
+void hv_sint_rdmsrl_ghcb(u64 msr, u64 *value)
+{
+	hv_ghcb_msr_read(msr, value);
+}
+EXPORT_SYMBOL_GPL(hv_sint_rdmsrl_ghcb);
+
+void hv_sint_wrmsrl_ghcb(u64 msr, u64 value)
+{
+	hv_ghcb_msr_write(msr, value);
+
+	/* Write proxy bit vua wrmsrl instruction. */
+	if (msr >= HV_X64_MSR_SINT0 && msr <= HV_X64_MSR_SINT15)
+		wrmsrl(msr, value | 1 << 20);
+}
+EXPORT_SYMBOL_GPL(hv_sint_wrmsrl_ghcb);
+
+inline void hv_signal_eom_ghcb(void)
+{
+	hv_sint_wrmsrl_ghcb(HV_X64_MSR_EOM, 0);
+}
+EXPORT_SYMBOL_GPL(hv_signal_eom_ghcb);
+
+enum hv_isolation_type hv_get_isolation_type(void)
+{
+	if (!(ms_hyperv.features_b & HV_ISOLATION))
+		return HV_ISOLATION_TYPE_NONE;
+	return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b);
+}
+EXPORT_SYMBOL_GPL(hv_get_isolation_type);
+
+bool hv_is_isolation_supported(void)
+{
+	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
+}
+EXPORT_SYMBOL_GPL(hv_is_isolation_supported);
+
+DEFINE_STATIC_KEY_FALSE(isolation_type_snp);
+
+bool hv_isolation_type_snp(void)
+{
+	return static_branch_unlikely(&isolation_type_snp);
+}
+EXPORT_SYMBOL_GPL(hv_isolation_type_snp);
+
 /*
  * hv_set_mem_host_visibility - Set host visibility for specified memory.
  */
@@ -22,6 +149,9 @@ int hv_set_mem_host_visibility(void *kbuffer, u32 size, u32 visibility)
 	u64 *pfn_array;
 	int ret = 0;
 
+	if (!hv_is_isolation_supported())
+		return 0;
+
 	pfn_array = vzalloc(HV_HYP_PAGE_SIZE);
 	if (!pfn_array)
 		return -ENOMEM;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index d9437f096ce5..73501dbbc240 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -10,6 +10,8 @@
 #include <asm/nospec-branch.h>
 #include <asm/paravirt.h>
 
+DECLARE_STATIC_KEY_FALSE(isolation_type_snp);
+
 typedef int (*hyperv_fill_flush_list_func)(
 		struct hv_guest_mapping_flush_list *flush,
 		void *data);
@@ -19,24 +21,64 @@ typedef int (*hyperv_fill_flush_list_func)(
 #define hv_init_timer_config(timer, val) \
 	wrmsrl(HV_X64_MSR_STIMER0_CONFIG + (2*timer), val)
 
-#define hv_get_simp(val) rdmsrl(HV_X64_MSR_SIMP, val)
-#define hv_set_simp(val) wrmsrl(HV_X64_MSR_SIMP, val)
+#define hv_get_sint_reg(val, reg) {		\
+	if (hv_isolation_type_snp())		\
+		hv_get_##reg##_ghcb(&val);		\
+	else					\
+		rdmsrl(HV_X64_MSR_##reg, val);	\
+	}
+
+#define hv_set_sint_reg(val, reg) {		\
+	if (hv_isolation_type_snp())		\
+		hv_set_##reg##_ghcb(val);		\
+	else					\
+		wrmsrl(HV_X64_MSR_##reg, val);	\
+	}
+
 
-#define hv_get_siefp(val) rdmsrl(HV_X64_MSR_SIEFP, val)
-#define hv_set_siefp(val) wrmsrl(HV_X64_MSR_SIEFP, val)
+#define hv_get_simp(val) hv_get_sint_reg(val, SIMP)
+#define hv_get_siefp(val) hv_get_sint_reg(val, SIEFP)
 
-#define hv_get_synic_state(val) rdmsrl(HV_X64_MSR_SCONTROL, val)
-#define hv_set_synic_state(val) wrmsrl(HV_X64_MSR_SCONTROL, val)
+#define hv_set_simp(val) hv_set_sint_reg(val, SIMP)
+#define hv_set_siefp(val) hv_set_sint_reg(val, SIEFP)
+
+#define hv_get_synic_state(val) {			\
+	if (hv_isolation_type_snp())			\
+		hv_get_synic_state_ghcb(&val);		\
+	else						\
+		rdmsrl(HV_X64_MSR_SCONTROL, val);	\
+	}
+#define hv_set_synic_state(val) {			\
+	if (hv_isolation_type_snp())			\
+		hv_set_synic_state_ghcb(val);		\
+	else						\
+		wrmsrl(HV_X64_MSR_SCONTROL, val);	\
+	}
 
 #define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index)
 
-#define hv_signal_eom() wrmsrl(HV_X64_MSR_EOM, 0)
+#define hv_signal_eom() {			 \
+	if (hv_isolation_type_snp() &&		 \
+	    old_msg_type != HVMSG_TIMER_EXPIRED) \
+		hv_signal_eom_ghcb();		 \
+	else					 \
+		wrmsrl(HV_X64_MSR_EOM, 0);	 \
+	}
 
-#define hv_get_synint_state(int_num, val) \
-	rdmsrl(HV_X64_MSR_SINT0 + int_num, val)
-#define hv_set_synint_state(int_num, val) \
-	wrmsrl(HV_X64_MSR_SINT0 + int_num, val)
-#define hv_recommend_using_aeoi() \
+#define hv_get_synint_state(int_num, val) {		\
+	if (hv_isolation_type_snp())			\
+		hv_get_synint_state_ghcb(int_num, &val);\
+	else						\
+		rdmsrl(HV_X64_MSR_SINT0 + int_num, val);\
+	}
+#define hv_set_synint_state(int_num, val) {		\
+	if (hv_isolation_type_snp())			\
+		hv_set_synint_state_ghcb(int_num, val);	\
+	else						\
+		wrmsrl(HV_X64_MSR_SINT0 + int_num, val);\
+	}
+
+#define hv_recommend_using_aeoi()				\
 	(!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED))
 
 #define hv_get_crash_ctl(val) \
@@ -271,6 +313,25 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
 
 int hv_set_mem_host_visibility(void *kbuffer, u32 size, u32 visibility);
 int hv_mark_gpa_visibility(u16 count, const u64 pfn[], u32 visibility);
+void hv_sint_wrmsrl_ghcb(u64 msr, u64 value);
+void hv_sint_rdmsrl_ghcb(u64 msr, u64 *value);
+void hv_signal_eom_ghcb(void);
+void hv_ghcb_msr_write(u64 msr, u64 value);
+void hv_ghcb_msr_read(u64 msr, u64 *value);
+
+#define hv_get_synint_state_ghcb(int_num, val)			\
+	hv_sint_rdmsrl_ghcb(HV_X64_MSR_SINT0 + int_num, val)
+#define hv_set_synint_state_ghcb(int_num, val) \
+	hv_sint_wrmsrl_ghcb(HV_X64_MSR_SINT0 + int_num, val)
+
+#define hv_get_SIMP_ghcb(val) hv_sint_rdmsrl_ghcb(HV_X64_MSR_SIMP, val)
+#define hv_set_SIMP_ghcb(val) hv_sint_wrmsrl_ghcb(HV_X64_MSR_SIMP, val)
+
+#define hv_get_SIEFP_ghcb(val) hv_sint_rdmsrl_ghcb(HV_X64_MSR_SIEFP, val)
+#define hv_set_SIEFP_ghcb(val) hv_sint_wrmsrl_ghcb(HV_X64_MSR_SIEFP, val)
+
+#define hv_get_synic_state_ghcb(val) hv_sint_rdmsrl_ghcb(HV_X64_MSR_SCONTROL, val)
+#define hv_set_synic_state_ghcb(val) hv_sint_wrmsrl_ghcb(HV_X64_MSR_SCONTROL, val)
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}
@@ -289,9 +350,9 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
 {
 	return -1;
 }
+static inline void hv_signal_eom_ghcb(void) { };
 #endif /* CONFIG_HYPERV */
 
-
 #include <asm-generic/mshyperv.h>
 
 #endif
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index aeafd4017c89..6eaa0891c0f7 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -333,6 +333,9 @@ static void __init ms_hyperv_init_platform(void)
 
 		pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n",
 			ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b);
+
+		if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP)
+			static_branch_enable(&isolation_type_snp);
 	}
 
 	if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) {
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index f202ac7f4b3d..069530eeb7c6 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -99,17 +99,24 @@ int hv_synic_alloc(void)
 		tasklet_init(&hv_cpu->msg_dpc,
 			     vmbus_on_msg_dpc, (unsigned long) hv_cpu);
 
-		hv_cpu->synic_message_page =
-			(void *)get_zeroed_page(GFP_ATOMIC);
-		if (hv_cpu->synic_message_page == NULL) {
-			pr_err("Unable to allocate SYNIC message page\n");
-			goto err;
-		}
+		/*
+		 * Synic message and event pages are allocated by paravisor.
+		 * Skip these pages allocation here.
+		 */
+		if (!hv_isolation_type_snp()) {
+			hv_cpu->synic_message_page =
+				(void *)get_zeroed_page(GFP_ATOMIC);
+			if (hv_cpu->synic_message_page == NULL) {
+				pr_err("Unable to allocate SYNIC message page\n");
+				goto err;
+			}
 
-		hv_cpu->synic_event_page = (void *)get_zeroed_page(GFP_ATOMIC);
-		if (hv_cpu->synic_event_page == NULL) {
-			pr_err("Unable to allocate SYNIC event page\n");
-			goto err;
+			hv_cpu->synic_event_page =
+				(void *)get_zeroed_page(GFP_ATOMIC);
+			if (hv_cpu->synic_event_page == NULL) {
+				pr_err("Unable to allocate SYNIC event page\n");
+				goto err;
+			}
 		}
 
 		hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC);
@@ -136,10 +143,17 @@ void hv_synic_free(void)
 	for_each_present_cpu(cpu) {
 		struct hv_per_cpu_context *hv_cpu
 			= per_cpu_ptr(hv_context.cpu_context, cpu);
+		free_page((unsigned long)hv_cpu->post_msg_page);
+
+		/*
+		 * Synic message and event pages are allocated by paravisor.
+		 * Skip free these pages here.
+		 */
+		if (hv_isolation_type_snp())
+			continue;
 
 		free_page((unsigned long)hv_cpu->synic_event_page);
 		free_page((unsigned long)hv_cpu->synic_message_page);
-		free_page((unsigned long)hv_cpu->post_msg_page);
 	}
 
 	kfree(hv_context.hv_numa_map);
@@ -161,20 +175,36 @@ void hv_synic_enable_regs(unsigned int cpu)
 	union hv_synic_sint shared_sint;
 	union hv_synic_scontrol sctrl;
 
-	/* Setup the Synic's message page */
+
+	/* Setup the Synic's message. */
 	hv_get_simp(simp.as_uint64);
 	simp.simp_enabled = 1;
-	simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
-		>> HV_HYP_PAGE_SHIFT;
+
+	if (hv_isolation_type_snp()) {
+		hv_cpu->synic_message_page
+			= ioremap_cache(simp.base_simp_gpa << HV_HYP_PAGE_SHIFT,
+					HV_HYP_PAGE_SIZE);
+		if (!hv_cpu->synic_message_page)
+			pr_err("Fail to map syinc message page.\n");
+	} else {
+		simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
+			>> HV_HYP_PAGE_SHIFT;
+	}
 
 	hv_set_simp(simp.as_uint64);
 
 	/* Setup the Synic's event page */
 	hv_get_siefp(siefp.as_uint64);
 	siefp.siefp_enabled = 1;
-	siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
-		>> HV_HYP_PAGE_SHIFT;
-
+	if (hv_isolation_type_snp()) {
+		hv_cpu->synic_event_page = ioremap_cache(
+			 siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT, HV_HYP_PAGE_SIZE);
+		if (!hv_cpu->synic_event_page)
+			pr_err("Fail to map syinc event page.\n");
+	} else {
+		siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
+			>> HV_HYP_PAGE_SHIFT;
+	}
 	hv_set_siefp(siefp.as_uint64);
 
 	/* Setup the shared SINT. */
@@ -188,7 +218,6 @@ void hv_synic_enable_regs(unsigned int cpu)
 	/* Enable the global synic bit */
 	hv_get_synic_state(sctrl.as_uint64);
 	sctrl.enable = 1;
-
 	hv_set_synic_state(sctrl.as_uint64);
 }
 
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index b73e201abc70..59777377e641 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -23,6 +23,7 @@
 #include <linux/bitops.h>
 #include <linux/cpumask.h>
 #include <asm/ptrace.h>
+#include <asm/mshyperv.h>
 #include <asm/hyperv-tlfs.h>
 
 struct ms_hyperv_info {
@@ -52,7 +53,7 @@ extern struct ms_hyperv_info ms_hyperv;
 
 extern u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr);
 extern u64 hv_do_fast_hypercall8(u16 control, u64 input8);
-
+extern bool hv_isolation_type_snp(void);
 
 /* Generate the guest OS identifier as described in the Hyper-V TLFS */
 static inline  __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version,
@@ -186,6 +187,7 @@ bool hv_is_hyperv_initialized(void);
 bool hv_is_hibernation_supported(void);
 enum hv_isolation_type hv_get_isolation_type(void);
 bool hv_is_isolation_supported(void);
+bool hv_isolation_type_snp(void);
 void hyperv_cleanup(void);
 #else /* CONFIG_HYPERV */
 static inline bool hv_is_hyperv_initialized(void) { return false; }
-- 
2.25.1

Re: [Resend RFC PATCH V2 04/12] HV: Add Write/Read MSR registers via ghcb

[Christoph Hellwig]

> +EXPORT_SYMBOL_GPL(hv_ghcb_msr_write);

Just curious, who is going to use all these exports?  These seems like
extremely low-level functionality.  Isn't there a way to build a more
useful higher level API?

Re: [Resend RFC PATCH V2 04/12] HV: Add Write/Read MSR registers via ghcb

[Tianyu Lan]

On 4/14/2021 11:41 PM, Christoph Hellwig wrote:
>> +EXPORT_SYMBOL_GPL(hv_ghcb_msr_write);
> 
> Just curious, who is going to use all these exports?  These seems like
> extremely low-level functionality.  Isn't there a way to build a more
> useful higher level API?
>

Yes, will remove it.

Re: [Resend RFC PATCH V2 04/12] HV: Add Write/Read MSR registers via ghcb

[Konrad Rzeszutek Wilk]

On Wed, Apr 14, 2021 at 10:49:37AM -0400, Tianyu Lan wrote:
> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
> 
> Hyper-V provides GHCB protocol to write Synthetic Interrupt
> Controller MSR registers and these registers are emulated by
> Hypervisor rather than paravisor.

What is paravisor? Is that the VMPL0 to borrow AMD speak from
https://www.amd.com/system/files/TechDocs/SEV-SNP-strengthening-vm-isolation-with-integrity-protection-and-more.pdf
 
> 
> Hyper-V requests to write SINTx MSR registers twice(once via
> GHCB and once via wrmsr instruction including the proxy bit 21)

Why? And what does 'proxy bit 21' mean? Isn't it just setting a bit
on the MSR?

Oh. Are you writting to it twice because you need to let the hypervisor
know (Hyper-V) which is done via the WRMSR. And then the inner
hypervisor (VMPL0) via the SINITx MSR?


> Guest OS ID MSR also needs to be set via GHCB.
> 
> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> ---
>  arch/x86/hyperv/hv_init.c       |  18 +----
>  arch/x86/hyperv/ivm.c           | 130 ++++++++++++++++++++++++++++++++
>  arch/x86/include/asm/mshyperv.h |  87 +++++++++++++++++----
>  arch/x86/kernel/cpu/mshyperv.c  |   3 +
>  drivers/hv/hv.c                 |  65 +++++++++++-----
>  include/asm-generic/mshyperv.h  |   4 +-
>  6 files changed, 261 insertions(+), 46 deletions(-)
> 
> diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
> index 90e65fbf4c58..87b1dd9c84d6 100644
> --- a/arch/x86/hyperv/hv_init.c
> +++ b/arch/x86/hyperv/hv_init.c
> @@ -475,6 +475,9 @@ void __init hyperv_init(void)
>  
>  		ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
>  		*ghcb_base = ghcb_va;
> +
> +		/* Hyper-V requires to write guest os id via ghcb in SNP IVM. */
> +		hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);
>  	}
>  
>  	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
> @@ -561,6 +564,7 @@ void hyperv_cleanup(void)
>  
>  	/* Reset our OS id */
>  	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
> +	hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
>  
>  	/*
>  	 * Reset hypercall page reference before reset the page,
> @@ -668,17 +672,3 @@ bool hv_is_hibernation_supported(void)
>  	return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4);
>  }
>  EXPORT_SYMBOL_GPL(hv_is_hibernation_supported);
> -
> -enum hv_isolation_type hv_get_isolation_type(void)
> -{
> -	if (!(ms_hyperv.features_b & HV_ISOLATION))
> -		return HV_ISOLATION_TYPE_NONE;
> -	return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b);
> -}
> -EXPORT_SYMBOL_GPL(hv_get_isolation_type);
> -
> -bool hv_is_isolation_supported(void)
> -{
> -	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
> -}
> -EXPORT_SYMBOL_GPL(hv_is_isolation_supported);
> diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
> index a5950b7a9214..2ec64b367aaf 100644
> --- a/arch/x86/hyperv/ivm.c
> +++ b/arch/x86/hyperv/ivm.c
> @@ -6,12 +6,139 @@
>   *  Tianyu Lan <Tianyu.Lan@microsoft.com>
>   */
>  
> +#include <linux/types.h>
> +#include <linux/bitfield.h>
>  #include <linux/hyperv.h>
>  #include <linux/types.h>
>  #include <linux/bitfield.h>
>  #include <asm/io.h>
> +#include <asm/svm.h>
> +#include <asm/sev-es.h>
>  #include <asm/mshyperv.h>
>  
> +union hv_ghcb {
> +	struct ghcb ghcb;
> +} __packed __aligned(PAGE_SIZE);
> +
> +void hv_ghcb_msr_write(u64 msr, u64 value)
> +{
> +	union hv_ghcb *hv_ghcb;
> +	void **ghcb_base;
> +	unsigned long flags;
> +
> +	if (!ms_hyperv.ghcb_base)
> +		return;
> +
> +	local_irq_save(flags);
> +	ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
> +	hv_ghcb = (union hv_ghcb *)*ghcb_base;
> +	if (!hv_ghcb) {
> +		local_irq_restore(flags);
> +		return;
> +	}
> +
> +	memset(hv_ghcb, 0x00, HV_HYP_PAGE_SIZE);
> +
> +	hv_ghcb->ghcb.protocol_version = 1;
> +	hv_ghcb->ghcb.ghcb_usage = 0;
> +
> +	ghcb_set_sw_exit_code(&hv_ghcb->ghcb, SVM_EXIT_MSR);
> +	ghcb_set_rcx(&hv_ghcb->ghcb, msr);
> +	ghcb_set_rax(&hv_ghcb->ghcb, lower_32_bits(value));
> +	ghcb_set_rdx(&hv_ghcb->ghcb, value >> 32);
> +	ghcb_set_sw_exit_info_1(&hv_ghcb->ghcb, 1);
> +	ghcb_set_sw_exit_info_2(&hv_ghcb->ghcb, 0);
> +
> +	VMGEXIT();
> +
> +	if ((hv_ghcb->ghcb.save.sw_exit_info_1 & 0xffffffff) == 1)
> +		pr_warn("Fail to write msr via ghcb.\n.");
> +
> +	local_irq_restore(flags);
> +}
> +EXPORT_SYMBOL_GPL(hv_ghcb_msr_write);
> +
> +void hv_ghcb_msr_read(u64 msr, u64 *value)
> +{
> +	union hv_ghcb *hv_ghcb;
> +	void **ghcb_base;
> +	unsigned long flags;
> +
> +	if (!ms_hyperv.ghcb_base)
> +		return;
> +
> +	local_irq_save(flags);
> +	ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
> +	hv_ghcb = (union hv_ghcb *)*ghcb_base;
> +	if (!hv_ghcb) {
> +		local_irq_restore(flags);
> +		return;
> +	}
> +
> +	memset(hv_ghcb, 0x00, PAGE_SIZE);
> +	hv_ghcb->ghcb.protocol_version = 1;
> +	hv_ghcb->ghcb.ghcb_usage = 0;
> +
> +	ghcb_set_sw_exit_code(&hv_ghcb->ghcb, SVM_EXIT_MSR);
> +	ghcb_set_rcx(&hv_ghcb->ghcb, msr);
> +	ghcb_set_sw_exit_info_1(&hv_ghcb->ghcb, 0);
> +	ghcb_set_sw_exit_info_2(&hv_ghcb->ghcb, 0);
> +
> +	VMGEXIT();
> +
> +	if ((hv_ghcb->ghcb.save.sw_exit_info_1 & 0xffffffff) == 1)
> +		pr_warn("Fail to write msr via ghcb.\n.");
> +	else
> +		*value = (u64)lower_32_bits(hv_ghcb->ghcb.save.rax)
> +			| ((u64)lower_32_bits(hv_ghcb->ghcb.save.rdx) << 32);
> +	local_irq_restore(flags);
> +}
> +EXPORT_SYMBOL_GPL(hv_ghcb_msr_read);
> +
> +void hv_sint_rdmsrl_ghcb(u64 msr, u64 *value)
> +{
> +	hv_ghcb_msr_read(msr, value);
> +}
> +EXPORT_SYMBOL_GPL(hv_sint_rdmsrl_ghcb);
> +
> +void hv_sint_wrmsrl_ghcb(u64 msr, u64 value)
> +{
> +	hv_ghcb_msr_write(msr, value);
> +
> +	/* Write proxy bit vua wrmsrl instruction. */
> +	if (msr >= HV_X64_MSR_SINT0 && msr <= HV_X64_MSR_SINT15)
> +		wrmsrl(msr, value | 1 << 20);
> +}
> +EXPORT_SYMBOL_GPL(hv_sint_wrmsrl_ghcb);
> +
> +inline void hv_signal_eom_ghcb(void)
> +{
> +	hv_sint_wrmsrl_ghcb(HV_X64_MSR_EOM, 0);
> +}
> +EXPORT_SYMBOL_GPL(hv_signal_eom_ghcb);
> +
> +enum hv_isolation_type hv_get_isolation_type(void)
> +{
> +	if (!(ms_hyperv.features_b & HV_ISOLATION))
> +		return HV_ISOLATION_TYPE_NONE;
> +	return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b);
> +}
> +EXPORT_SYMBOL_GPL(hv_get_isolation_type);
> +
> +bool hv_is_isolation_supported(void)
> +{
> +	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
> +}
> +EXPORT_SYMBOL_GPL(hv_is_isolation_supported);
> +
> +DEFINE_STATIC_KEY_FALSE(isolation_type_snp);
> +
> +bool hv_isolation_type_snp(void)
> +{
> +	return static_branch_unlikely(&isolation_type_snp);
> +}
> +EXPORT_SYMBOL_GPL(hv_isolation_type_snp);
> +
>  /*
>   * hv_set_mem_host_visibility - Set host visibility for specified memory.
>   */
> @@ -22,6 +149,9 @@ int hv_set_mem_host_visibility(void *kbuffer, u32 size, u32 visibility)
>  	u64 *pfn_array;
>  	int ret = 0;
>  
> +	if (!hv_is_isolation_supported())
> +		return 0;
> +
>  	pfn_array = vzalloc(HV_HYP_PAGE_SIZE);
>  	if (!pfn_array)
>  		return -ENOMEM;
> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> index d9437f096ce5..73501dbbc240 100644
> --- a/arch/x86/include/asm/mshyperv.h
> +++ b/arch/x86/include/asm/mshyperv.h
> @@ -10,6 +10,8 @@
>  #include <asm/nospec-branch.h>
>  #include <asm/paravirt.h>
>  
> +DECLARE_STATIC_KEY_FALSE(isolation_type_snp);
> +
>  typedef int (*hyperv_fill_flush_list_func)(
>  		struct hv_guest_mapping_flush_list *flush,
>  		void *data);
> @@ -19,24 +21,64 @@ typedef int (*hyperv_fill_flush_list_func)(
>  #define hv_init_timer_config(timer, val) \
>  	wrmsrl(HV_X64_MSR_STIMER0_CONFIG + (2*timer), val)
>  
> -#define hv_get_simp(val) rdmsrl(HV_X64_MSR_SIMP, val)
> -#define hv_set_simp(val) wrmsrl(HV_X64_MSR_SIMP, val)
> +#define hv_get_sint_reg(val, reg) {		\
> +	if (hv_isolation_type_snp())		\
> +		hv_get_##reg##_ghcb(&val);		\
> +	else					\
> +		rdmsrl(HV_X64_MSR_##reg, val);	\
> +	}
> +
> +#define hv_set_sint_reg(val, reg) {		\
> +	if (hv_isolation_type_snp())		\
> +		hv_set_##reg##_ghcb(val);		\
> +	else					\
> +		wrmsrl(HV_X64_MSR_##reg, val);	\
> +	}
> +
>  
> -#define hv_get_siefp(val) rdmsrl(HV_X64_MSR_SIEFP, val)
> -#define hv_set_siefp(val) wrmsrl(HV_X64_MSR_SIEFP, val)
> +#define hv_get_simp(val) hv_get_sint_reg(val, SIMP)
> +#define hv_get_siefp(val) hv_get_sint_reg(val, SIEFP)
>  
> -#define hv_get_synic_state(val) rdmsrl(HV_X64_MSR_SCONTROL, val)
> -#define hv_set_synic_state(val) wrmsrl(HV_X64_MSR_SCONTROL, val)
> +#define hv_set_simp(val) hv_set_sint_reg(val, SIMP)
> +#define hv_set_siefp(val) hv_set_sint_reg(val, SIEFP)
> +
> +#define hv_get_synic_state(val) {			\
> +	if (hv_isolation_type_snp())			\
> +		hv_get_synic_state_ghcb(&val);		\
> +	else						\
> +		rdmsrl(HV_X64_MSR_SCONTROL, val);	\
> +	}
> +#define hv_set_synic_state(val) {			\
> +	if (hv_isolation_type_snp())			\
> +		hv_set_synic_state_ghcb(val);		\
> +	else						\
> +		wrmsrl(HV_X64_MSR_SCONTROL, val);	\
> +	}
>  
>  #define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index)
>  
> -#define hv_signal_eom() wrmsrl(HV_X64_MSR_EOM, 0)
> +#define hv_signal_eom() {			 \
> +	if (hv_isolation_type_snp() &&		 \
> +	    old_msg_type != HVMSG_TIMER_EXPIRED) \
> +		hv_signal_eom_ghcb();		 \
> +	else					 \
> +		wrmsrl(HV_X64_MSR_EOM, 0);	 \
> +	}
>  
> -#define hv_get_synint_state(int_num, val) \
> -	rdmsrl(HV_X64_MSR_SINT0 + int_num, val)
> -#define hv_set_synint_state(int_num, val) \
> -	wrmsrl(HV_X64_MSR_SINT0 + int_num, val)
> -#define hv_recommend_using_aeoi() \
> +#define hv_get_synint_state(int_num, val) {		\
> +	if (hv_isolation_type_snp())			\
> +		hv_get_synint_state_ghcb(int_num, &val);\
> +	else						\
> +		rdmsrl(HV_X64_MSR_SINT0 + int_num, val);\
> +	}
> +#define hv_set_synint_state(int_num, val) {		\
> +	if (hv_isolation_type_snp())			\
> +		hv_set_synint_state_ghcb(int_num, val);	\
> +	else						\
> +		wrmsrl(HV_X64_MSR_SINT0 + int_num, val);\
> +	}
> +
> +#define hv_recommend_using_aeoi()				\
>  	(!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED))
>  
>  #define hv_get_crash_ctl(val) \
> @@ -271,6 +313,25 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
>  
>  int hv_set_mem_host_visibility(void *kbuffer, u32 size, u32 visibility);
>  int hv_mark_gpa_visibility(u16 count, const u64 pfn[], u32 visibility);
> +void hv_sint_wrmsrl_ghcb(u64 msr, u64 value);
> +void hv_sint_rdmsrl_ghcb(u64 msr, u64 *value);
> +void hv_signal_eom_ghcb(void);
> +void hv_ghcb_msr_write(u64 msr, u64 value);
> +void hv_ghcb_msr_read(u64 msr, u64 *value);
> +
> +#define hv_get_synint_state_ghcb(int_num, val)			\
> +	hv_sint_rdmsrl_ghcb(HV_X64_MSR_SINT0 + int_num, val)
> +#define hv_set_synint_state_ghcb(int_num, val) \
> +	hv_sint_wrmsrl_ghcb(HV_X64_MSR_SINT0 + int_num, val)
> +
> +#define hv_get_SIMP_ghcb(val) hv_sint_rdmsrl_ghcb(HV_X64_MSR_SIMP, val)
> +#define hv_set_SIMP_ghcb(val) hv_sint_wrmsrl_ghcb(HV_X64_MSR_SIMP, val)
> +
> +#define hv_get_SIEFP_ghcb(val) hv_sint_rdmsrl_ghcb(HV_X64_MSR_SIEFP, val)
> +#define hv_set_SIEFP_ghcb(val) hv_sint_wrmsrl_ghcb(HV_X64_MSR_SIEFP, val)
> +
> +#define hv_get_synic_state_ghcb(val) hv_sint_rdmsrl_ghcb(HV_X64_MSR_SCONTROL, val)
> +#define hv_set_synic_state_ghcb(val) hv_sint_wrmsrl_ghcb(HV_X64_MSR_SCONTROL, val)
>  #else /* CONFIG_HYPERV */
>  static inline void hyperv_init(void) {}
>  static inline void hyperv_setup_mmu_ops(void) {}
> @@ -289,9 +350,9 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
>  {
>  	return -1;
>  }
> +static inline void hv_signal_eom_ghcb(void) { };
>  #endif /* CONFIG_HYPERV */
>  
> -
>  #include <asm-generic/mshyperv.h>
>  
>  #endif
> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
> index aeafd4017c89..6eaa0891c0f7 100644
> --- a/arch/x86/kernel/cpu/mshyperv.c
> +++ b/arch/x86/kernel/cpu/mshyperv.c
> @@ -333,6 +333,9 @@ static void __init ms_hyperv_init_platform(void)
>  
>  		pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n",
>  			ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b);
> +
> +		if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP)
> +			static_branch_enable(&isolation_type_snp);
>  	}
>  
>  	if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) {
> diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
> index f202ac7f4b3d..069530eeb7c6 100644
> --- a/drivers/hv/hv.c
> +++ b/drivers/hv/hv.c
> @@ -99,17 +99,24 @@ int hv_synic_alloc(void)
>  		tasklet_init(&hv_cpu->msg_dpc,
>  			     vmbus_on_msg_dpc, (unsigned long) hv_cpu);
>  
> -		hv_cpu->synic_message_page =
> -			(void *)get_zeroed_page(GFP_ATOMIC);
> -		if (hv_cpu->synic_message_page == NULL) {
> -			pr_err("Unable to allocate SYNIC message page\n");
> -			goto err;
> -		}
> +		/*
> +		 * Synic message and event pages are allocated by paravisor.
> +		 * Skip these pages allocation here.
> +		 */
> +		if (!hv_isolation_type_snp()) {
> +			hv_cpu->synic_message_page =
> +				(void *)get_zeroed_page(GFP_ATOMIC);
> +			if (hv_cpu->synic_message_page == NULL) {
> +				pr_err("Unable to allocate SYNIC message page\n");
> +				goto err;
> +			}
>  
> -		hv_cpu->synic_event_page = (void *)get_zeroed_page(GFP_ATOMIC);
> -		if (hv_cpu->synic_event_page == NULL) {
> -			pr_err("Unable to allocate SYNIC event page\n");
> -			goto err;
> +			hv_cpu->synic_event_page =
> +				(void *)get_zeroed_page(GFP_ATOMIC);
> +			if (hv_cpu->synic_event_page == NULL) {
> +				pr_err("Unable to allocate SYNIC event page\n");
> +				goto err;
> +			}
>  		}
>  
>  		hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC);
> @@ -136,10 +143,17 @@ void hv_synic_free(void)
>  	for_each_present_cpu(cpu) {
>  		struct hv_per_cpu_context *hv_cpu
>  			= per_cpu_ptr(hv_context.cpu_context, cpu);
> +		free_page((unsigned long)hv_cpu->post_msg_page);
> +
> +		/*
> +		 * Synic message and event pages are allocated by paravisor.
> +		 * Skip free these pages here.
> +		 */
> +		if (hv_isolation_type_snp())
> +			continue;
>  
>  		free_page((unsigned long)hv_cpu->synic_event_page);
>  		free_page((unsigned long)hv_cpu->synic_message_page);
> -		free_page((unsigned long)hv_cpu->post_msg_page);
>  	}
>  
>  	kfree(hv_context.hv_numa_map);
> @@ -161,20 +175,36 @@ void hv_synic_enable_regs(unsigned int cpu)
>  	union hv_synic_sint shared_sint;
>  	union hv_synic_scontrol sctrl;
>  
> -	/* Setup the Synic's message page */
> +
> +	/* Setup the Synic's message. */
>  	hv_get_simp(simp.as_uint64);
>  	simp.simp_enabled = 1;
> -	simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
> -		>> HV_HYP_PAGE_SHIFT;
> +
> +	if (hv_isolation_type_snp()) {
> +		hv_cpu->synic_message_page
> +			= ioremap_cache(simp.base_simp_gpa << HV_HYP_PAGE_SHIFT,
> +					HV_HYP_PAGE_SIZE);
> +		if (!hv_cpu->synic_message_page)
> +			pr_err("Fail to map syinc message page.\n");
> +	} else {
> +		simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
> +			>> HV_HYP_PAGE_SHIFT;
> +	}
>  
>  	hv_set_simp(simp.as_uint64);
>  
>  	/* Setup the Synic's event page */
>  	hv_get_siefp(siefp.as_uint64);
>  	siefp.siefp_enabled = 1;
> -	siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
> -		>> HV_HYP_PAGE_SHIFT;
> -
> +	if (hv_isolation_type_snp()) {
> +		hv_cpu->synic_event_page = ioremap_cache(
> +			 siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT, HV_HYP_PAGE_SIZE);
> +		if (!hv_cpu->synic_event_page)
> +			pr_err("Fail to map syinc event page.\n");
> +	} else {
> +		siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
> +			>> HV_HYP_PAGE_SHIFT;
> +	}
>  	hv_set_siefp(siefp.as_uint64);
>  
>  	/* Setup the shared SINT. */
> @@ -188,7 +218,6 @@ void hv_synic_enable_regs(unsigned int cpu)
>  	/* Enable the global synic bit */
>  	hv_get_synic_state(sctrl.as_uint64);
>  	sctrl.enable = 1;
> -
>  	hv_set_synic_state(sctrl.as_uint64);
>  }
>  
> diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
> index b73e201abc70..59777377e641 100644
> --- a/include/asm-generic/mshyperv.h
> +++ b/include/asm-generic/mshyperv.h
> @@ -23,6 +23,7 @@
>  #include <linux/bitops.h>
>  #include <linux/cpumask.h>
>  #include <asm/ptrace.h>
> +#include <asm/mshyperv.h>
>  #include <asm/hyperv-tlfs.h>
>  
>  struct ms_hyperv_info {
> @@ -52,7 +53,7 @@ extern struct ms_hyperv_info ms_hyperv;
>  
>  extern u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr);
>  extern u64 hv_do_fast_hypercall8(u16 control, u64 input8);
> -
> +extern bool hv_isolation_type_snp(void);
>  
>  /* Generate the guest OS identifier as described in the Hyper-V TLFS */
>  static inline  __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version,
> @@ -186,6 +187,7 @@ bool hv_is_hyperv_initialized(void);
>  bool hv_is_hibernation_supported(void);
>  enum hv_isolation_type hv_get_isolation_type(void);
>  bool hv_is_isolation_supported(void);
> +bool hv_isolation_type_snp(void);
>  void hyperv_cleanup(void);
>  #else /* CONFIG_HYPERV */
>  static inline bool hv_is_hyperv_initialized(void) { return false; }
> -- 
> 2.25.1
> 

[Resend RFC PATCH V2 05/12] HV: Add ghcb hvcall support for SNP VM

[Tianyu Lan]

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

Hyper-V provides ghcb hvcall to handle VMBus
HVCALL_SIGNAL_EVENT and HVCALL_POST_MESSAGE
msg in SNP Isolation VM. Add such support.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 arch/x86/hyperv/ivm.c           | 69 +++++++++++++++++++++++++++++++++
 arch/x86/include/asm/mshyperv.h |  1 +
 drivers/hv/connection.c         |  6 ++-
 drivers/hv/hv.c                 |  8 +++-
 4 files changed, 82 insertions(+), 2 deletions(-)

diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 2ec64b367aaf..0ad73ea60c8f 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -18,8 +18,77 @@
 
 union hv_ghcb {
 	struct ghcb ghcb;
+	struct {
+		u64 hypercalldata[509];
+		u64 outputgpa;
+		union {
+			union {
+				struct {
+					u32 callcode        : 16;
+					u32 isfast          : 1;
+					u32 reserved1       : 14;
+					u32 isnested        : 1;
+					u32 countofelements : 12;
+					u32 reserved2       : 4;
+					u32 repstartindex   : 12;
+					u32 reserved3       : 4;
+				};
+				u64 asuint64;
+			} hypercallinput;
+			union {
+				struct {
+					u16 callstatus;
+					u16 reserved1;
+					u32 elementsprocessed : 12;
+					u32 reserved2         : 20;
+				};
+				u64 asunit64;
+			} hypercalloutput;
+		};
+		u64 reserved2;
+	} hypercall;
 } __packed __aligned(PAGE_SIZE);
 
+u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size)
+{
+	union hv_ghcb *hv_ghcb;
+	void **ghcb_base;
+	unsigned long flags;
+
+	if (!ms_hyperv.ghcb_base)
+		return -EFAULT;
+
+	local_irq_save(flags);
+	ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+	hv_ghcb = (union hv_ghcb *)*ghcb_base;
+	if (!hv_ghcb) {
+		local_irq_restore(flags);
+		return -EFAULT;
+	}
+
+	memset(hv_ghcb, 0x00, HV_HYP_PAGE_SIZE);
+	hv_ghcb->ghcb.protocol_version = 1;
+	hv_ghcb->ghcb.ghcb_usage = 1;
+
+	hv_ghcb->hypercall.outputgpa = (u64)output;
+	hv_ghcb->hypercall.hypercallinput.asuint64 = 0;
+	hv_ghcb->hypercall.hypercallinput.callcode = control;
+
+	if (input_size)
+		memcpy(hv_ghcb->hypercall.hypercalldata, input, input_size);
+
+	VMGEXIT();
+
+	hv_ghcb->ghcb.ghcb_usage = 0xffffffff;
+	memset(hv_ghcb->ghcb.save.valid_bitmap, 0,
+	       sizeof(hv_ghcb->ghcb.save.valid_bitmap));
+
+	local_irq_restore(flags);
+
+	return hv_ghcb->hypercall.hypercalloutput.callstatus;
+}
+EXPORT_SYMBOL_GPL(hv_ghcb_hypercall);
+
 void hv_ghcb_msr_write(u64 msr, u64 value)
 {
 	union hv_ghcb *hv_ghcb;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 73501dbbc240..929504fe8654 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -318,6 +318,7 @@ void hv_sint_rdmsrl_ghcb(u64 msr, u64 *value);
 void hv_signal_eom_ghcb(void);
 void hv_ghcb_msr_write(u64 msr, u64 value);
 void hv_ghcb_msr_read(u64 msr, u64 *value);
+u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size);
 
 #define hv_get_synint_state_ghcb(int_num, val)			\
 	hv_sint_rdmsrl_ghcb(HV_X64_MSR_SINT0 + int_num, val)
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index c83612cddb99..79bca653dce9 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -442,6 +442,10 @@ void vmbus_set_event(struct vmbus_channel *channel)
 
 	++channel->sig_events;
 
-	hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event);
+	if (hv_isolation_type_snp())
+		hv_ghcb_hypercall(HVCALL_SIGNAL_EVENT, &channel->sig_event,
+				NULL, sizeof(u64));
+	else
+		hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event);
 }
 EXPORT_SYMBOL_GPL(vmbus_set_event);
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 069530eeb7c6..bff7c9049ffb 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -60,7 +60,13 @@ int hv_post_message(union hv_connection_id connection_id,
 	aligned_msg->payload_size = payload_size;
 	memcpy((void *)aligned_msg->payload, payload, payload_size);
 
-	status = hv_do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL);
+	if (hv_isolation_type_snp())
+		status = hv_ghcb_hypercall(HVCALL_POST_MESSAGE,
+				(void *)aligned_msg, NULL,
+				sizeof(struct hv_input_post_message));
+	else
+		status = hv_do_hypercall(HVCALL_POST_MESSAGE,
+				aligned_msg, NULL);
 
 	/* Preemption must remain disabled until after the hypercall
 	 * so some other thread can't get scheduled onto this cpu and
-- 
2.25.1

[Resend RFC PATCH V2 06/12] HV/Vmbus: Add SNP support for VMbus channel initiate message

[Tianyu Lan]

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

The physical address of monitor pages in the CHANNELMSG_INITIATE_CONTACT
msg should be in the extra address space for SNP support and these
pages also should be accessed via the extra address space inside Linux
guest and remap the extra address by ioremap function.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 drivers/hv/connection.c   | 62 +++++++++++++++++++++++++++++++++++++++
 drivers/hv/hyperv_vmbus.h |  1 +
 2 files changed, 63 insertions(+)

diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 79bca653dce9..a0be9c11d737 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -101,6 +101,12 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 
 	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
 	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
+
+	if (hv_isolation_type_snp()) {
+		msg->monitor_page1 += ms_hyperv.shared_gpa_boundary;
+		msg->monitor_page2 += ms_hyperv.shared_gpa_boundary;
+	}
+
 	msg->target_vcpu = hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU);
 
 	/*
@@ -145,6 +151,29 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 		return -ECONNREFUSED;
 	}
 
+	if (hv_isolation_type_snp()) {
+		vmbus_connection.monitor_pages_va[0]
+			= vmbus_connection.monitor_pages[0];
+		vmbus_connection.monitor_pages[0]
+			= ioremap_cache(msg->monitor_page1, HV_HYP_PAGE_SIZE);
+		if (!vmbus_connection.monitor_pages[0])
+			return -ENOMEM;
+
+		vmbus_connection.monitor_pages_va[1]
+			= vmbus_connection.monitor_pages[1];
+		vmbus_connection.monitor_pages[1]
+			= ioremap_cache(msg->monitor_page2, HV_HYP_PAGE_SIZE);
+		if (!vmbus_connection.monitor_pages[1]) {
+			vunmap(vmbus_connection.monitor_pages[0]);
+			return -ENOMEM;
+		}
+
+		memset(vmbus_connection.monitor_pages[0], 0x00,
+		       HV_HYP_PAGE_SIZE);
+		memset(vmbus_connection.monitor_pages[1], 0x00,
+		       HV_HYP_PAGE_SIZE);
+	}
+
 	return ret;
 }
 
@@ -156,6 +185,7 @@ int vmbus_connect(void)
 	struct vmbus_channel_msginfo *msginfo = NULL;
 	int i, ret = 0;
 	__u32 version;
+	u64 pfn[2];
 
 	/* Initialize the vmbus connection */
 	vmbus_connection.conn_state = CONNECTING;
@@ -213,6 +243,16 @@ int vmbus_connect(void)
 		goto cleanup;
 	}
 
+	if (hv_isolation_type_snp()) {
+		pfn[0] = virt_to_hvpfn(vmbus_connection.monitor_pages[0]);
+		pfn[1] = virt_to_hvpfn(vmbus_connection.monitor_pages[1]);
+		if (hv_mark_gpa_visibility(2, pfn,
+				VMBUS_PAGE_VISIBLE_READ_WRITE)) {
+			ret = -EFAULT;
+			goto cleanup;
+		}
+	}
+
 	msginfo = kzalloc(sizeof(*msginfo) +
 			  sizeof(struct vmbus_channel_initiate_contact),
 			  GFP_KERNEL);
@@ -279,6 +319,8 @@ int vmbus_connect(void)
 
 void vmbus_disconnect(void)
 {
+	u64 pfn[2];
+
 	/*
 	 * First send the unload request to the host.
 	 */
@@ -298,6 +340,26 @@ void vmbus_disconnect(void)
 		vmbus_connection.int_page = NULL;
 	}
 
+	if (hv_isolation_type_snp()) {
+		if (vmbus_connection.monitor_pages_va[0]) {
+			vunmap(vmbus_connection.monitor_pages[0]);
+			vmbus_connection.monitor_pages[0]
+				= vmbus_connection.monitor_pages_va[0];
+			vmbus_connection.monitor_pages_va[0] = NULL;
+		}
+
+		if (vmbus_connection.monitor_pages_va[1]) {
+			vunmap(vmbus_connection.monitor_pages[1]);
+			vmbus_connection.monitor_pages[1]
+				= vmbus_connection.monitor_pages_va[1];
+			vmbus_connection.monitor_pages_va[1] = NULL;
+		}
+
+		pfn[0] = virt_to_hvpfn(vmbus_connection.monitor_pages[0]);
+		pfn[1] = virt_to_hvpfn(vmbus_connection.monitor_pages[1]);
+		hv_mark_gpa_visibility(2, pfn, VMBUS_PAGE_NOT_VISIBLE);
+	}
+
 	hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[0]);
 	hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[1]);
 	vmbus_connection.monitor_pages[0] = NULL;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 9416e09ebd58..0778add21a9c 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -240,6 +240,7 @@ struct vmbus_connection {
 	 * is child->parent notification
 	 */
 	struct hv_monitor_page *monitor_pages[2];
+	void *monitor_pages_va[2];
 	struct list_head chn_msg_list;
 	spinlock_t channelmsg_lock;
 
-- 
2.25.1

Re: [Resend RFC PATCH V2 06/12] HV/Vmbus: Add SNP support for VMbus channel initiate message

[Konrad Rzeszutek Wilk]

On Wed, Apr 14, 2021 at 10:49:39AM -0400, Tianyu Lan wrote:
> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
> 
> The physical address of monitor pages in the CHANNELMSG_INITIATE_CONTACT
> msg should be in the extra address space for SNP support and these

What is this 'extra address space'? Is that just normal virtual address
space of the Linux kernel?

> pages also should be accessed via the extra address space inside Linux
> guest and remap the extra address by ioremap function.

OK, why do you need to use ioremap on them? Why not use vmap for
example? What is it that makes ioremap the right candidate?





> 
> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> ---
>  drivers/hv/connection.c   | 62 +++++++++++++++++++++++++++++++++++++++
>  drivers/hv/hyperv_vmbus.h |  1 +
>  2 files changed, 63 insertions(+)
> 
> diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
> index 79bca653dce9..a0be9c11d737 100644
> --- a/drivers/hv/connection.c
> +++ b/drivers/hv/connection.c
> @@ -101,6 +101,12 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
>  
>  	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
>  	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
> +
> +	if (hv_isolation_type_snp()) {
> +		msg->monitor_page1 += ms_hyperv.shared_gpa_boundary;
> +		msg->monitor_page2 += ms_hyperv.shared_gpa_boundary;
> +	}
> +
>  	msg->target_vcpu = hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU);
>  
>  	/*
> @@ -145,6 +151,29 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
>  		return -ECONNREFUSED;
>  	}
>  
> +	if (hv_isolation_type_snp()) {
> +		vmbus_connection.monitor_pages_va[0]
> +			= vmbus_connection.monitor_pages[0];
> +		vmbus_connection.monitor_pages[0]
> +			= ioremap_cache(msg->monitor_page1, HV_HYP_PAGE_SIZE);
> +		if (!vmbus_connection.monitor_pages[0])
> +			return -ENOMEM;
> +
> +		vmbus_connection.monitor_pages_va[1]
> +			= vmbus_connection.monitor_pages[1];
> +		vmbus_connection.monitor_pages[1]
> +			= ioremap_cache(msg->monitor_page2, HV_HYP_PAGE_SIZE);
> +		if (!vmbus_connection.monitor_pages[1]) {
> +			vunmap(vmbus_connection.monitor_pages[0]);
> +			return -ENOMEM;
> +		}
> +
> +		memset(vmbus_connection.monitor_pages[0], 0x00,
> +		       HV_HYP_PAGE_SIZE);
> +		memset(vmbus_connection.monitor_pages[1], 0x00,
> +		       HV_HYP_PAGE_SIZE);
> +	}
> +
>  	return ret;
>  }
>  
> @@ -156,6 +185,7 @@ int vmbus_connect(void)
>  	struct vmbus_channel_msginfo *msginfo = NULL;
>  	int i, ret = 0;
>  	__u32 version;
> +	u64 pfn[2];
>  
>  	/* Initialize the vmbus connection */
>  	vmbus_connection.conn_state = CONNECTING;
> @@ -213,6 +243,16 @@ int vmbus_connect(void)
>  		goto cleanup;
>  	}
>  
> +	if (hv_isolation_type_snp()) {
> +		pfn[0] = virt_to_hvpfn(vmbus_connection.monitor_pages[0]);
> +		pfn[1] = virt_to_hvpfn(vmbus_connection.monitor_pages[1]);
> +		if (hv_mark_gpa_visibility(2, pfn,
> +				VMBUS_PAGE_VISIBLE_READ_WRITE)) {
> +			ret = -EFAULT;
> +			goto cleanup;
> +		}
> +	}
> +
>  	msginfo = kzalloc(sizeof(*msginfo) +
>  			  sizeof(struct vmbus_channel_initiate_contact),
>  			  GFP_KERNEL);
> @@ -279,6 +319,8 @@ int vmbus_connect(void)
>  
>  void vmbus_disconnect(void)
>  {
> +	u64 pfn[2];
> +
>  	/*
>  	 * First send the unload request to the host.
>  	 */
> @@ -298,6 +340,26 @@ void vmbus_disconnect(void)
>  		vmbus_connection.int_page = NULL;
>  	}
>  
> +	if (hv_isolation_type_snp()) {
> +		if (vmbus_connection.monitor_pages_va[0]) {
> +			vunmap(vmbus_connection.monitor_pages[0]);
> +			vmbus_connection.monitor_pages[0]
> +				= vmbus_connection.monitor_pages_va[0];
> +			vmbus_connection.monitor_pages_va[0] = NULL;
> +		}
> +
> +		if (vmbus_connection.monitor_pages_va[1]) {
> +			vunmap(vmbus_connection.monitor_pages[1]);
> +			vmbus_connection.monitor_pages[1]
> +				= vmbus_connection.monitor_pages_va[1];
> +			vmbus_connection.monitor_pages_va[1] = NULL;
> +		}
> +
> +		pfn[0] = virt_to_hvpfn(vmbus_connection.monitor_pages[0]);
> +		pfn[1] = virt_to_hvpfn(vmbus_connection.monitor_pages[1]);
> +		hv_mark_gpa_visibility(2, pfn, VMBUS_PAGE_NOT_VISIBLE);
> +	}
> +
>  	hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[0]);
>  	hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[1]);
>  	vmbus_connection.monitor_pages[0] = NULL;
> diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
> index 9416e09ebd58..0778add21a9c 100644
> --- a/drivers/hv/hyperv_vmbus.h
> +++ b/drivers/hv/hyperv_vmbus.h
> @@ -240,6 +240,7 @@ struct vmbus_connection {
>  	 * is child->parent notification
>  	 */
>  	struct hv_monitor_page *monitor_pages[2];
> +	void *monitor_pages_va[2];
>  	struct list_head chn_msg_list;
>  	spinlock_t channelmsg_lock;
>  
> -- 
> 2.25.1
> 

[Resend RFC PATCH V2 07/12] HV/Vmbus: Initialize VMbus ring buffer for Isolation VM

[Tianyu Lan]

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

VMbus ring buffer are shared with host and it's need to
be accessed via extra address space of Isolation VM with
SNP support. This patch is to map the ring buffer
address in extra address space via ioremap(). HV host
visibility hvcall smears data in the ring buffer and
so reset the ring buffer memory to zero after calling
visibility hvcall.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 drivers/hv/channel.c      | 10 +++++
 drivers/hv/hyperv_vmbus.h |  2 +
 drivers/hv/ring_buffer.c  | 83 +++++++++++++++++++++++++++++----------
 mm/ioremap.c              |  1 +
 mm/vmalloc.c              |  1 +
 5 files changed, 76 insertions(+), 21 deletions(-)

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 407b74d72f3f..4a9fb7ad4c72 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -634,6 +634,16 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	if (err)
 		goto error_clean_ring;
 
+	err = hv_ringbuffer_post_init(&newchannel->outbound,
+				      page, send_pages);
+	if (err)
+		goto error_free_gpadl;
+
+	err = hv_ringbuffer_post_init(&newchannel->inbound,
+				      &page[send_pages], recv_pages);
+	if (err)
+		goto error_free_gpadl;
+
 	/* Create and init the channel open message */
 	open_info = kzalloc(sizeof(*open_info) +
 			   sizeof(struct vmbus_channel_open_channel),
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 0778add21a9c..d78a04ad5490 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -172,6 +172,8 @@ extern int hv_synic_cleanup(unsigned int cpu);
 /* Interface */
 
 void hv_ringbuffer_pre_init(struct vmbus_channel *channel);
+int hv_ringbuffer_post_init(struct hv_ring_buffer_info *ring_info,
+		struct page *pages, u32 page_cnt);
 
 int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
 		       struct page *pages, u32 pagecnt);
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 35833d4d1a1d..c8b0f7b45158 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -17,6 +17,8 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/prefetch.h>
+#include <linux/io.h>
+#include <asm/mshyperv.h>
 
 #include "hyperv_vmbus.h"
 
@@ -188,6 +190,44 @@ void hv_ringbuffer_pre_init(struct vmbus_channel *channel)
 	mutex_init(&channel->outbound.ring_buffer_mutex);
 }
 
+int hv_ringbuffer_post_init(struct hv_ring_buffer_info *ring_info,
+		       struct page *pages, u32 page_cnt)
+{
+	struct vm_struct *area;
+	u64 physic_addr = page_to_pfn(pages) << PAGE_SHIFT;
+	unsigned long vaddr;
+	int err = 0;
+
+	if (!hv_isolation_type_snp())
+		return 0;
+
+	physic_addr += ms_hyperv.shared_gpa_boundary;
+	area = get_vm_area((2 * page_cnt - 1) * PAGE_SIZE, VM_IOREMAP);
+	if (!area || !area->addr)
+		return -EFAULT;
+
+	vaddr = (unsigned long)area->addr;
+	err = ioremap_page_range(vaddr, vaddr + page_cnt * PAGE_SIZE,
+			   physic_addr, PAGE_KERNEL_IO);
+	err |= ioremap_page_range(vaddr + page_cnt * PAGE_SIZE,
+				  vaddr + (2 * page_cnt - 1) * PAGE_SIZE,
+				  physic_addr + PAGE_SIZE, PAGE_KERNEL_IO);
+	if (err) {
+		vunmap((void *)vaddr);
+		return -EFAULT;
+	}
+
+	/* Clean memory after setting host visibility. */
+	memset((void *)vaddr, 0x00, page_cnt * PAGE_SIZE);
+
+	ring_info->ring_buffer = (struct hv_ring_buffer *)vaddr;
+	ring_info->ring_buffer->read_index = 0;
+	ring_info->ring_buffer->write_index = 0;
+	ring_info->ring_buffer->feature_bits.value = 1;
+
+	return 0;
+}
+
 /* Initialize the ring buffer. */
 int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
 		       struct page *pages, u32 page_cnt)
@@ -197,33 +237,34 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
 
 	BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE));
 
-	/*
-	 * First page holds struct hv_ring_buffer, do wraparound mapping for
-	 * the rest.
-	 */
-	pages_wraparound = kcalloc(page_cnt * 2 - 1, sizeof(struct page *),
-				   GFP_KERNEL);
-	if (!pages_wraparound)
-		return -ENOMEM;
-
-	pages_wraparound[0] = pages;
-	for (i = 0; i < 2 * (page_cnt - 1); i++)
-		pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1];
+	if (!hv_isolation_type_snp()) {
+		/*
+		 * First page holds struct hv_ring_buffer, do wraparound mapping for
+		 * the rest.
+		 */
+		pages_wraparound = kcalloc(page_cnt * 2 - 1, sizeof(struct page *),
+					   GFP_KERNEL);
+		if (!pages_wraparound)
+			return -ENOMEM;
 
-	ring_info->ring_buffer = (struct hv_ring_buffer *)
-		vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, PAGE_KERNEL);
+		pages_wraparound[0] = pages;
+		for (i = 0; i < 2 * (page_cnt - 1); i++)
+			pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1];
 
-	kfree(pages_wraparound);
+		ring_info->ring_buffer = (struct hv_ring_buffer *)
+			vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, PAGE_KERNEL);
 
+		kfree(pages_wraparound);
 
-	if (!ring_info->ring_buffer)
-		return -ENOMEM;
+		if (!ring_info->ring_buffer)
+			return -ENOMEM;
 
-	ring_info->ring_buffer->read_index =
-		ring_info->ring_buffer->write_index = 0;
+		ring_info->ring_buffer->read_index =
+			ring_info->ring_buffer->write_index = 0;
 
-	/* Set the feature bit for enabling flow control. */
-	ring_info->ring_buffer->feature_bits.value = 1;
+		/* Set the feature bit for enabling flow control. */
+		ring_info->ring_buffer->feature_bits.value = 1;
+	}
 
 	ring_info->ring_size = page_cnt << PAGE_SHIFT;
 	ring_info->ring_size_div10_reciprocal =
diff --git a/mm/ioremap.c b/mm/ioremap.c
index 5fa1ab41d152..d63c4ba067f9 100644
--- a/mm/ioremap.c
+++ b/mm/ioremap.c
@@ -248,6 +248,7 @@ int ioremap_page_range(unsigned long addr,
 
 	return err;
 }
+EXPORT_SYMBOL_GPL(ioremap_page_range);
 
 #ifdef CONFIG_GENERIC_IOREMAP
 void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e6f352bf0498..19724a8ebcb7 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2131,6 +2131,7 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
 				  NUMA_NO_NODE, GFP_KERNEL,
 				  __builtin_return_address(0));
 }
+EXPORT_SYMBOL_GPL(get_vm_area);
 
 struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
 				const void *caller)
-- 
2.25.1

Re: [Resend RFC PATCH V2 07/12] HV/Vmbus: Initialize VMbus ring buffer for Isolation VM

[Konrad Rzeszutek Wilk]

On Wed, Apr 14, 2021 at 10:49:40AM -0400, Tianyu Lan wrote:
> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
> 
> VMbus ring buffer are shared with host and it's need to
> be accessed via extra address space of Isolation VM with
> SNP support. This patch is to map the ring buffer
> address in extra address space via ioremap(). HV host

Why do you need to use ioremap()? Why not just use vmap?


> visibility hvcall smears data in the ring buffer and
> so reset the ring buffer memory to zero after calling
> visibility hvcall.

So you are exposing these two:
 EXPORT_SYMBOL_GPL(get_vm_area);
 EXPORT_SYMBOL_GPL(ioremap_page_range);

But if you used vmap wouldn't you get the same thing for free?

> 
> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> ---
>  drivers/hv/channel.c      | 10 +++++
>  drivers/hv/hyperv_vmbus.h |  2 +
>  drivers/hv/ring_buffer.c  | 83 +++++++++++++++++++++++++++++----------
>  mm/ioremap.c              |  1 +
>  mm/vmalloc.c              |  1 +
>  5 files changed, 76 insertions(+), 21 deletions(-)
> 
> diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
> index 407b74d72f3f..4a9fb7ad4c72 100644
> --- a/drivers/hv/channel.c
> +++ b/drivers/hv/channel.c
> @@ -634,6 +634,16 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
>  	if (err)
>  		goto error_clean_ring;
>  
> +	err = hv_ringbuffer_post_init(&newchannel->outbound,
> +				      page, send_pages);
> +	if (err)
> +		goto error_free_gpadl;
> +
> +	err = hv_ringbuffer_post_init(&newchannel->inbound,
> +				      &page[send_pages], recv_pages);
> +	if (err)
> +		goto error_free_gpadl;
> +
>  	/* Create and init the channel open message */
>  	open_info = kzalloc(sizeof(*open_info) +
>  			   sizeof(struct vmbus_channel_open_channel),
> diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
> index 0778add21a9c..d78a04ad5490 100644
> --- a/drivers/hv/hyperv_vmbus.h
> +++ b/drivers/hv/hyperv_vmbus.h
> @@ -172,6 +172,8 @@ extern int hv_synic_cleanup(unsigned int cpu);
>  /* Interface */
>  
>  void hv_ringbuffer_pre_init(struct vmbus_channel *channel);
> +int hv_ringbuffer_post_init(struct hv_ring_buffer_info *ring_info,
> +		struct page *pages, u32 page_cnt);
>  
>  int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
>  		       struct page *pages, u32 pagecnt);
> diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
> index 35833d4d1a1d..c8b0f7b45158 100644
> --- a/drivers/hv/ring_buffer.c
> +++ b/drivers/hv/ring_buffer.c
> @@ -17,6 +17,8 @@
>  #include <linux/vmalloc.h>
>  #include <linux/slab.h>
>  #include <linux/prefetch.h>
> +#include <linux/io.h>
> +#include <asm/mshyperv.h>
>  
>  #include "hyperv_vmbus.h"
>  
> @@ -188,6 +190,44 @@ void hv_ringbuffer_pre_init(struct vmbus_channel *channel)
>  	mutex_init(&channel->outbound.ring_buffer_mutex);
>  }
>  
> +int hv_ringbuffer_post_init(struct hv_ring_buffer_info *ring_info,
> +		       struct page *pages, u32 page_cnt)
> +{
> +	struct vm_struct *area;
> +	u64 physic_addr = page_to_pfn(pages) << PAGE_SHIFT;
> +	unsigned long vaddr;
> +	int err = 0;
> +
> +	if (!hv_isolation_type_snp())
> +		return 0;
> +
> +	physic_addr += ms_hyperv.shared_gpa_boundary;
> +	area = get_vm_area((2 * page_cnt - 1) * PAGE_SIZE, VM_IOREMAP);
> +	if (!area || !area->addr)
> +		return -EFAULT;
> +
> +	vaddr = (unsigned long)area->addr;
> +	err = ioremap_page_range(vaddr, vaddr + page_cnt * PAGE_SIZE,
> +			   physic_addr, PAGE_KERNEL_IO);
> +	err |= ioremap_page_range(vaddr + page_cnt * PAGE_SIZE,
> +				  vaddr + (2 * page_cnt - 1) * PAGE_SIZE,
> +				  physic_addr + PAGE_SIZE, PAGE_KERNEL_IO);
> +	if (err) {
> +		vunmap((void *)vaddr);
> +		return -EFAULT;
> +	}
> +
> +	/* Clean memory after setting host visibility. */
> +	memset((void *)vaddr, 0x00, page_cnt * PAGE_SIZE);
> +
> +	ring_info->ring_buffer = (struct hv_ring_buffer *)vaddr;
> +	ring_info->ring_buffer->read_index = 0;
> +	ring_info->ring_buffer->write_index = 0;
> +	ring_info->ring_buffer->feature_bits.value = 1;
> +
> +	return 0;
> +}
> +
>  /* Initialize the ring buffer. */
>  int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
>  		       struct page *pages, u32 page_cnt)
> @@ -197,33 +237,34 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
>  
>  	BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE));
>  
> -	/*
> -	 * First page holds struct hv_ring_buffer, do wraparound mapping for
> -	 * the rest.
> -	 */
> -	pages_wraparound = kcalloc(page_cnt * 2 - 1, sizeof(struct page *),
> -				   GFP_KERNEL);
> -	if (!pages_wraparound)
> -		return -ENOMEM;
> -
> -	pages_wraparound[0] = pages;
> -	for (i = 0; i < 2 * (page_cnt - 1); i++)
> -		pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1];
> +	if (!hv_isolation_type_snp()) {
> +		/*
> +		 * First page holds struct hv_ring_buffer, do wraparound mapping for
> +		 * the rest.
> +		 */
> +		pages_wraparound = kcalloc(page_cnt * 2 - 1, sizeof(struct page *),
> +					   GFP_KERNEL);
> +		if (!pages_wraparound)
> +			return -ENOMEM;
>  
> -	ring_info->ring_buffer = (struct hv_ring_buffer *)
> -		vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, PAGE_KERNEL);
> +		pages_wraparound[0] = pages;
> +		for (i = 0; i < 2 * (page_cnt - 1); i++)
> +			pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1];
>  
> -	kfree(pages_wraparound);
> +		ring_info->ring_buffer = (struct hv_ring_buffer *)
> +			vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, PAGE_KERNEL);
>  
> +		kfree(pages_wraparound);
>  
> -	if (!ring_info->ring_buffer)
> -		return -ENOMEM;
> +		if (!ring_info->ring_buffer)
> +			return -ENOMEM;
>  
> -	ring_info->ring_buffer->read_index =
> -		ring_info->ring_buffer->write_index = 0;
> +		ring_info->ring_buffer->read_index =
> +			ring_info->ring_buffer->write_index = 0;
>  
> -	/* Set the feature bit for enabling flow control. */
> -	ring_info->ring_buffer->feature_bits.value = 1;
> +		/* Set the feature bit for enabling flow control. */
> +		ring_info->ring_buffer->feature_bits.value = 1;
> +	}
>  
>  	ring_info->ring_size = page_cnt << PAGE_SHIFT;
>  	ring_info->ring_size_div10_reciprocal =
> diff --git a/mm/ioremap.c b/mm/ioremap.c
> index 5fa1ab41d152..d63c4ba067f9 100644
> --- a/mm/ioremap.c
> +++ b/mm/ioremap.c
> @@ -248,6 +248,7 @@ int ioremap_page_range(unsigned long addr,
>  
>  	return err;
>  }
> +EXPORT_SYMBOL_GPL(ioremap_page_range);
>  
>  #ifdef CONFIG_GENERIC_IOREMAP
>  void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot)
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index e6f352bf0498..19724a8ebcb7 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -2131,6 +2131,7 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
>  				  NUMA_NO_NODE, GFP_KERNEL,
>  				  __builtin_return_address(0));
>  }
> +EXPORT_SYMBOL_GPL(get_vm_area);
>  
>  struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
>  				const void *caller)
> -- 
> 2.25.1
> 

Re: [Resend RFC PATCH V2 07/12] HV/Vmbus: Initialize VMbus ring buffer for Isolation VM

[Christoph Hellwig]

On Thu, Apr 15, 2021 at 04:24:15PM -0400, Konrad Rzeszutek Wilk wrote:
> So you are exposing these two:
>  EXPORT_SYMBOL_GPL(get_vm_area);
>  EXPORT_SYMBOL_GPL(ioremap_page_range);
> 
> But if you used vmap wouldn't you get the same thing for free?

Yes, this needs to go into some vmap version, preferably reusing the
existing code in kernel/dma/remap.c.

Exporting get_vm_area is a complete dealbreaker and not going to happen.
We worked hard on not exposing it to modules.

[Resend RFC PATCH V2 08/12] UIO/Hyper-V: Not load UIO HV driver in the isolation VM.

[Tianyu Lan]

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

UIO HV driver should not load in the isolation VM for security reason.
Return ENOTSUPP in the hv_uio_probe() in the isolation VM.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 drivers/uio/uio_hv_generic.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index 0330ba99730e..678b021d66f8 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -29,6 +29,7 @@
 #include <linux/hyperv.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
+#include <asm/mshyperv.h>
 
 #include "../hv/hyperv_vmbus.h"
 
@@ -241,6 +242,10 @@ hv_uio_probe(struct hv_device *dev,
 	void *ring_buffer;
 	int ret;
 
+	/* UIO driver should not be loaded in the isolation VM.*/
+	if (hv_is_isolation_supported())
+		return -ENOTSUPP;
+		
 	/* Communicating with host has to be via shared memory not hypercall */
 	if (!channel->offermsg.monitor_allocated) {
 		dev_err(&dev->device, "vmbus channel requires hypercall\n");
-- 
2.25.1

Re: [Resend RFC PATCH V2 08/12] UIO/Hyper-V: Not load UIO HV driver in the isolation VM.

[Christoph Hellwig]

On Wed, Apr 14, 2021 at 10:49:41AM -0400, Tianyu Lan wrote:
> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
> 
> UIO HV driver should not load in the isolation VM for security reason.
> Return ENOTSUPP in the hv_uio_probe() in the isolation VM.

What is the "security reason"?  After all a user can simply patch the
code and just load it anyway..

Re: [Resend RFC PATCH V2 08/12] UIO/Hyper-V: Not load UIO HV driver in the isolation VM.

[Greg KH]

On Wed, Apr 14, 2021 at 10:49:41AM -0400, Tianyu Lan wrote:
> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
> 
> UIO HV driver should not load in the isolation VM for security reason.
> Return ENOTSUPP in the hv_uio_probe() in the isolation VM.
> 
> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> ---
>  drivers/uio/uio_hv_generic.c | 5 +++++
>  1 file changed, 5 insertions(+)
> 
> diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
> index 0330ba99730e..678b021d66f8 100644
> --- a/drivers/uio/uio_hv_generic.c
> +++ b/drivers/uio/uio_hv_generic.c
> @@ -29,6 +29,7 @@
>  #include <linux/hyperv.h>
>  #include <linux/vmalloc.h>
>  #include <linux/slab.h>
> +#include <asm/mshyperv.h>
>  
>  #include "../hv/hyperv_vmbus.h"
>  
> @@ -241,6 +242,10 @@ hv_uio_probe(struct hv_device *dev,
>  	void *ring_buffer;
>  	int ret;
>  
> +	/* UIO driver should not be loaded in the isolation VM.*/
> +	if (hv_is_isolation_supported())
> +		return -ENOTSUPP;
> +		
>  	/* Communicating with host has to be via shared memory not hypercall */
>  	if (!channel->offermsg.monitor_allocated) {
>  		dev_err(&dev->device, "vmbus channel requires hypercall\n");
> -- 
> 2.25.1
> 

Again you send out known-wrong patches?

:(

Re: [Resend RFC PATCH V2 08/12] UIO/Hyper-V: Not load UIO HV driver in the isolation VM.

[Stephen Hemminger]

On Wed, 14 Apr 2021 17:45:51 +0200
Greg KH <gregkh@linuxfoundation.org> wrote:

> On Wed, Apr 14, 2021 at 10:49:41AM -0400, Tianyu Lan wrote:
> > From: Tianyu Lan <Tianyu.Lan@microsoft.com>
> > 
> > UIO HV driver should not load in the isolation VM for security reason.
> > Return ENOTSUPP in the hv_uio_probe() in the isolation VM.
> > 
> > Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>

This is debatable, in isolation VM's shouldn't userspace take responsibility
to validate host communication. If that is an issue please participate with
the DPDK community (main user of this) to make sure netvsc userspace driver
has the required checks.

Re: [Resend RFC PATCH V2 08/12] UIO/Hyper-V: Not load UIO HV driver in the isolation VM.

[Tianyu Lan]

Hi Stephen:
	Thanks for your review.


On 4/15/2021 12:17 AM, Stephen Hemminger wrote:
> On Wed, 14 Apr 2021 17:45:51 +0200
> Greg KH <gregkh@linuxfoundation.org> wrote:
> 
>> On Wed, Apr 14, 2021 at 10:49:41AM -0400, Tianyu Lan wrote:
>>> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
>>>
>>> UIO HV driver should not load in the isolation VM for security reason.
>>> Return ENOTSUPP in the hv_uio_probe() in the isolation VM.
>>>
>>> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> 
> This is debatable, in isolation VM's shouldn't userspace take responsibility
> to validate host communication. If that is an issue please participate with
> the DPDK community (main user of this) to make sure netvsc userspace driver
> has the required checks.
> 

Agree. Will report back to secure team and apply request to add change 
in userspace netvsc driver. Thanks for advise.

Re: [Resend RFC PATCH V2 08/12] UIO/Hyper-V: Not load UIO HV driver in the isolation VM.

[Tianyu Lan]

On 4/14/2021 11:45 PM, Greg KH wrote:
> On Wed, Apr 14, 2021 at 10:49:41AM -0400, Tianyu Lan wrote:
>> From: Tianyu Lan <Tianyu.Lan@microsoft.com>
>>
>> UIO HV driver should not load in the isolation VM for security reason.
>> Return ENOTSUPP in the hv_uio_probe() in the isolation VM.
>>
>> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
>> ---
>>   drivers/uio/uio_hv_generic.c | 5 +++++
>>   1 file changed, 5 insertions(+)
>>
>> diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
>> index 0330ba99730e..678b021d66f8 100644
>> --- a/drivers/uio/uio_hv_generic.c
>> +++ b/drivers/uio/uio_hv_generic.c
>> @@ -29,6 +29,7 @@
>>   #include <linux/hyperv.h>
>>   #include <linux/vmalloc.h>
>>   #include <linux/slab.h>
>> +#include <asm/mshyperv.h>
>>   
>>   #include "../hv/hyperv_vmbus.h"
>>   
>> @@ -241,6 +242,10 @@ hv_uio_probe(struct hv_device *dev,
>>   	void *ring_buffer;
>>   	int ret;
>>   
>> +	/* UIO driver should not be loaded in the isolation VM.*/
>> +	if (hv_is_isolation_supported())
>> +		return -ENOTSUPP;
>> +		
>>   	/* Communicating with host has to be via shared memory not hypercall */
>>   	if (!channel->offermsg.monitor_allocated) {
>>   		dev_err(&dev->device, "vmbus channel requires hypercall\n");
>> -- 
>> 2.25.1
>>
> 
> Again you send out known-wrong patches?
> 
> :(
> 
Sorry for noise. Will fix this next version and I think we should make 
sure user space driver to check data from host. This patch will be removed.

[Resend RFC PATCH V2 09/12] 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

Re: [Resend RFC PATCH V2 09/12] swiotlb: Add bounce buffer remap address setting function

[Konrad Rzeszutek Wilk]

On Wed, Apr 14, 2021 at 10:49:42AM -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()

May? Isn't this a MUST in this case?

> needs to use remap virtual address to copy data from/to bounce buffer. Add
> new interface swiotlb_set_bounce_remap() to do that.

I am bit lost - why can't you use the swiotlb_init and pass in your
DMA pool that is already above bit 39?

> 
> 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
> 

[Resend RFC PATCH V2 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

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

[Christoph Hellwig]

> +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;
> +}

This largerly duplicates what dma-direct + swiotlb does.  Please use
force_dma_unencrypted to force bounce buffering and just use the generic
code.

> +	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);

And this really needs to go into a common hook where we currently just
call set_memory_decrypted so that all the different schemes for these
trusted VMs (we have about half a dozen now) can share code rather than
reinventing it.

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

[Tianyu Lan]

Hi Christoph and Konrad:
      Current Swiotlb bounce buffer uses a pool for all devices. There
is a high overhead to get or free bounce buffer during performance test.
Swiotlb code now use a global spin lock to protect bounce buffer data.
Several device queues try to acquire the spin lock and this introduce
additional overhead.

For performance and security perspective, each devices should have a
separate swiotlb bounce buffer pool and so this part needs to rework.
I want to check this is right way to resolve performance issues with 
swiotlb bounce buffer. If you have some other suggestions,welcome.

Thanks.

On 4/14/2021 11:47 PM, Christoph Hellwig wrote:
>> +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;
>> +}
> 
> This largerly duplicates what dma-direct + swiotlb does.  Please use
> force_dma_unencrypted to force bounce buffering and just use the generic
> code.
> 
>> +	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);
> 
> And this really needs to go into a common hook where we currently just
> call set_memory_decrypted so that all the different schemes for these
> trusted VMs (we have about half a dozen now) can share code rather than
> reinventing it.
> 

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

[Robin Murphy]

On 2021-05-12 17:01, Tianyu Lan wrote:
> Hi Christoph and Konrad:
>       Current Swiotlb bounce buffer uses a pool for all devices. There
> is a high overhead to get or free bounce buffer during performance test.
> Swiotlb code now use a global spin lock to protect bounce buffer data.
> Several device queues try to acquire the spin lock and this introduce
> additional overhead.
> 
> For performance and security perspective, each devices should have a
> separate swiotlb bounce buffer pool and so this part needs to rework.
> I want to check this is right way to resolve performance issues with 
> swiotlb bounce buffer. If you have some other suggestions,welcome.

We're already well on the way to factoring out SWIOTLB to allow for just 
this sort of more flexible usage like per-device bounce pools - see here:

https://lore.kernel.org/linux-iommu/20210510095026.3477496-1-tientzu@chromium.org/T/#t

FWIW this looks to have an awful lot in common with what's going to be 
needed for Android's protected KVM and Arm's Confidential Compute 
Architecture, so we'll all be better off by doing it right. I'm getting 
the feeling that set_memory_decrypted() wants to grow into a more 
general abstraction that can return an alias at a different GPA if 
necessary.

Robin.

> 
> Thanks.
> 
> On 4/14/2021 11:47 PM, Christoph Hellwig wrote:
>>> +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;
>>> +}
>>
>> This largerly duplicates what dma-direct + swiotlb does.  Please use
>> force_dma_unencrypted to force bounce buffering and just use the generic
>> code.
>>
>>> +    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);
>>
>> And this really needs to go into a common hook where we currently just
>> call set_memory_decrypted so that all the different schemes for these
>> trusted VMs (we have about half a dozen now) can share code rather than
>> reinventing it.
>>

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

[Lu Baolu]

On 5/13/21 12:01 AM, Tianyu Lan wrote:
> Hi Christoph and Konrad:
>       Current Swiotlb bounce buffer uses a pool for all devices. There
> is a high overhead to get or free bounce buffer during performance test.
> Swiotlb code now use a global spin lock to protect bounce buffer data.
> Several device queues try to acquire the spin lock and this introduce
> additional overhead.
> 
> For performance and security perspective, each devices should have a
> separate swiotlb bounce buffer pool and so this part needs to rework.
> I want to check this is right way to resolve performance issues with 
> swiotlb bounce buffer. If you have some other suggestions,welcome.

Is this what you want?

https://lore.kernel.org/linux-iommu/20210510095026.3477496-1-tientzu@chromium.org/

Best regards,
baolu

[Resend RFC PATCH V2 11/12] HV/Netvsc: Add Isolation VM support for netvsc driver

[Tianyu Lan]

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 fucntion 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   |  11 +++
 drivers/net/hyperv/netvsc.c       | 137 ++++++++++++++++++++++++++++--
 drivers/net/hyperv/rndis_filter.c |   3 +
 3 files changed, 144 insertions(+), 7 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 2a87cfa27ac0..d85f811238c7 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -130,6 +130,7 @@ struct hv_netvsc_packet {
 	u32 total_bytes;
 	u32 send_buf_index;
 	u32 total_data_buflen;
+	struct dma_range *dma_range;
 };
 
 #define NETVSC_HASH_KEYLEN 40
@@ -1026,6 +1027,7 @@ 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;
@@ -1034,6 +1036,8 @@ 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;
@@ -1715,4 +1719,11 @@ struct rndis_message {
 #define TRANSPORT_INFO_IPV6_TCP 0x10
 #define TRANSPORT_INFO_IPV6_UDP 0x20
 
+struct dma_range {
+	dma_addr_t dma;
+	u32 mapping_size;
+};
+
+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 2353623259f3..1a5f5be4eeea 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -26,6 +26,7 @@
 
 #include "hyperv_net.h"
 #include "netvsc_trace.h"
+#include "../../hv/hyperv_vmbus.h"
 
 /*
  * Switch the data path from the synthetic interface to the VF
@@ -119,8 +120,21 @@ 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) {
+		iounmap(nvdev->recv_buf);
+		vfree(nvdev->recv_original_buf);
+	} else {
+		vfree(nvdev->recv_buf);
+	}
+
+	if (nvdev->send_original_buf) {
+		iounmap(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++) {
@@ -302,9 +316,12 @@ static int netvsc_init_buf(struct hv_device *device,
 	struct nvsp_1_message_send_receive_buffer_complete *resp;
 	struct net_device *ndev = hv_get_drvdata(device);
 	struct nvsp_message *init_packet;
+	struct vm_struct *area;
+	u64 extra_phys;
 	unsigned int buf_size;
+	unsigned long vaddr;
 	size_t map_words;
-	int ret = 0;
+	int ret = 0, i;
 
 	/* Get receive buffer area. */
 	buf_size = device_info->recv_sections * device_info->recv_section_size;
@@ -340,6 +357,27 @@ static int netvsc_init_buf(struct hv_device *device,
 		goto cleanup;
 	}
 
+	if (hv_isolation_type_snp()) {
+		area = get_vm_area(buf_size, VM_IOREMAP);
+		if (!area)
+			goto cleanup;
+
+		vaddr = (unsigned long)area->addr;
+		for (i = 0; i < buf_size / HV_HYP_PAGE_SIZE; i++) {
+			extra_phys = (virt_to_hvpfn(net_device->recv_buf + i * HV_HYP_PAGE_SIZE)
+				<< HV_HYP_PAGE_SHIFT) + ms_hyperv.shared_gpa_boundary;
+			ret |= ioremap_page_range(vaddr + i * HV_HYP_PAGE_SIZE,
+					   vaddr + (i + 1) * HV_HYP_PAGE_SIZE,
+					   extra_phys, PAGE_KERNEL_IO);
+		}
+
+		if (ret)
+			goto cleanup;
+
+		net_device->recv_original_buf = net_device->recv_buf;
+		net_device->recv_buf = (void *)vaddr;
+	}
+
 	/* Notify the NetVsp of the gpadl handle */
 	init_packet = &net_device->channel_init_pkt;
 	memset(init_packet, 0, sizeof(struct nvsp_message));
@@ -432,6 +470,28 @@ static int netvsc_init_buf(struct hv_device *device,
 		goto cleanup;
 	}
 
+	if (hv_isolation_type_snp()) {
+		area = get_vm_area(buf_size, VM_IOREMAP);
+		if (!area)
+			goto cleanup;
+
+		vaddr = (unsigned long)area->addr;
+
+		for (i = 0; i < buf_size / HV_HYP_PAGE_SIZE; i++) {
+			extra_phys = (virt_to_hvpfn(net_device->send_buf + i * HV_HYP_PAGE_SIZE)
+				<< HV_HYP_PAGE_SHIFT) + ms_hyperv.shared_gpa_boundary;
+			ret |= ioremap_page_range(vaddr + i * HV_HYP_PAGE_SIZE,
+					   vaddr + (i + 1) * HV_HYP_PAGE_SIZE,
+					   extra_phys, PAGE_KERNEL_IO);
+		}
+
+		if (ret)
+			goto cleanup;
+
+		net_device->send_original_buf = net_device->send_buf;
+		net_device->send_buf = (void *)vaddr;
+	}
+
 	/* Notify the NetVsp of the gpadl handle */
 	init_packet = &net_device->channel_init_pkt;
 	memset(init_packet, 0, sizeof(struct nvsp_message));
@@ -722,7 +782,7 @@ 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;
@@ -738,6 +798,7 @@ 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);
 	}
 
@@ -878,6 +939,60 @@ 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 (!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);
+}
+
+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;
+
+	packet->dma_range = kzalloc(sizeof(struct dma_range) * page_count,
+			      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))
+			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,
@@ -917,14 +1032,22 @@ 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);
+					  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 598713c0d5a8..b19243f5874c 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -263,6 +263,8 @@ static void rndis_filter_receive_response(struct net_device *ndev,
 {
 	struct rndis_device *dev = nvdev->extension;
 	struct rndis_request *request = NULL;
+	struct hv_device *hv_dev = ((struct net_device_context *)
+			netdev_priv(ndev))->device_ctx;
 	bool found = false;
 	unsigned long flags;
 
@@ -327,6 +329,7 @@ static void rndis_filter_receive_response(struct net_device *ndev,
 			}
 		}
 
+		netvsc_dma_unmap(hv_dev, &request->pkt);
 		complete(&request->wait_event);
 	} else {
 		netdev_err(ndev,
-- 
2.25.1

Re: [Resend RFC PATCH V2 11/12] HV/Netvsc: Add Isolation VM support for netvsc driver

[Christoph Hellwig]

> +struct dma_range {
> +	dma_addr_t dma;
> +	u32 mapping_size;
> +};

That's a rather generic name that is bound to create a conflict sooner
or later.

>  #include "hyperv_net.h"
>  #include "netvsc_trace.h"
> +#include "../../hv/hyperv_vmbus.h"

Please move public interfaces out of the private header rather than doing
this.

> +	if (hv_isolation_type_snp()) {
> +		area = get_vm_area(buf_size, VM_IOREMAP);

Err, no.  get_vm_area is private a for a reason.

> +		if (!area)
> +			goto cleanup;
> +
> +		vaddr = (unsigned long)area->addr;
> +		for (i = 0; i < buf_size / HV_HYP_PAGE_SIZE; i++) {
> +			extra_phys = (virt_to_hvpfn(net_device->recv_buf + i * HV_HYP_PAGE_SIZE)
> +				<< HV_HYP_PAGE_SHIFT) + ms_hyperv.shared_gpa_boundary;
> +			ret |= ioremap_page_range(vaddr + i * HV_HYP_PAGE_SIZE,
> +					   vaddr + (i + 1) * HV_HYP_PAGE_SIZE,
> +					   extra_phys, PAGE_KERNEL_IO);
> +		}
> +
> +		if (ret)
> +			goto cleanup;

And this is not something a driver should ever do.  I think you are badly
reimplementing functionality that should be in the dma coherent allocator
here.

Re: [Resend RFC PATCH V2 11/12] HV/Netvsc: Add Isolation VM support for netvsc driver

[Tianyu Lan]

On 4/14/2021 11:50 PM, Christoph Hellwig wrote:
>> +struct dma_range {
>> +	dma_addr_t dma;
>> +	u32 mapping_size;
>> +};
> 
> That's a rather generic name that is bound to create a conflict sooner
> or later.

Good point. Will update.

> 
>>   #include "hyperv_net.h"
>>   #include "netvsc_trace.h"
>> +#include "../../hv/hyperv_vmbus.h"
> 
> Please move public interfaces out of the private header rather than doing
> this.

OK. Will update.

> 
>> +	if (hv_isolation_type_snp()) {
>> +		area = get_vm_area(buf_size, VM_IOREMAP);
> 
> Err, no.  get_vm_area is private a for a reason.
> 
>> +		if (!area)
>> +			goto cleanup;
>> +
>> +		vaddr = (unsigned long)area->addr;
>> +		for (i = 0; i < buf_size / HV_HYP_PAGE_SIZE; i++) {
>> +			extra_phys = (virt_to_hvpfn(net_device->recv_buf + i * HV_HYP_PAGE_SIZE)
>> +				<< HV_HYP_PAGE_SHIFT) + ms_hyperv.shared_gpa_boundary;
>> +			ret |= ioremap_page_range(vaddr + i * HV_HYP_PAGE_SIZE,
>> +					   vaddr + (i + 1) * HV_HYP_PAGE_SIZE,
>> +					   extra_phys, PAGE_KERNEL_IO);
>> +		}
>> +
>> +		if (ret)
>> +			goto cleanup;
> 
> And this is not something a driver should ever do.  I think you are badly
> reimplementing functionality that should be in the dma coherent allocator
> here.
>
OK. I will try hiding these in the Hyper-V dma ops callback. Thanks.

[Resend RFC PATCH V2 12/12] HV/Storvsc: Add Isolation VM support for storvsc driver

[Tianyu Lan]

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_
mpb_desc() 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 fucntion to allocate bounce buffer and copy data
from/to bounce buffer.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 drivers/scsi/storvsc_drv.c | 67 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 66 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 2e4fa77445fd..d271578b1811 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -21,6 +21,8 @@
 #include <linux/device.h>
 #include <linux/hyperv.h>
 #include <linux/blkdev.h>
+#include <linux/io.h>
+#include <linux/dma-mapping.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_host.h>
@@ -414,6 +416,11 @@ static void storvsc_on_channel_callback(void *context);
 #define STORVSC_IDE_MAX_TARGETS				1
 #define STORVSC_IDE_MAX_CHANNELS			1
 
+struct dma_range {
+	dma_addr_t dma;
+	u32 mapping_size;
+};
+
 struct storvsc_cmd_request {
 	struct scsi_cmnd *cmd;
 
@@ -427,6 +434,8 @@ struct storvsc_cmd_request {
 	u32 payload_sz;
 
 	struct vstor_packet vstor_packet;
+	u32 hvpg_count;
+	struct dma_range *dma_range;
 };
 
 
@@ -1236,6 +1245,7 @@ static void storvsc_on_channel_callback(void *context)
 	const struct vmpacket_descriptor *desc;
 	struct hv_device *device;
 	struct storvsc_device *stor_device;
+	int i;
 
 	if (channel->primary_channel != NULL)
 		device = channel->primary_channel->device_obj;
@@ -1249,6 +1259,8 @@ static void storvsc_on_channel_callback(void *context)
 	foreach_vmbus_pkt(desc, channel) {
 		void *packet = hv_pkt_data(desc);
 		struct storvsc_cmd_request *request;
+		enum dma_data_direction dir;
+		u32 attrs;
 		u64 cmd_rqst;
 
 		cmd_rqst = vmbus_request_addr(&channel->requestor,
@@ -1261,6 +1273,22 @@ static void storvsc_on_channel_callback(void *context)
 
 		request = (struct storvsc_cmd_request *)(unsigned long)cmd_rqst;
 
+		if (request->vstor_packet.vm_srb.data_in == READ_TYPE)
+			dir = DMA_FROM_DEVICE;
+		 else
+			dir = DMA_TO_DEVICE;
+
+		if (request->dma_range) {
+			for (i = 0; i < request->hvpg_count; i++)
+				dma_unmap_page_attrs(&device->device,
+						request->dma_range[i].dma,
+						request->dma_range[i].mapping_size,
+						request->vstor_packet.vm_srb.data_in
+						     == READ_TYPE ?
+						DMA_FROM_DEVICE : DMA_TO_DEVICE, attrs);
+			kfree(request->dma_range);
+		}
+
 		if (request == &stor_device->init_request ||
 		    request == &stor_device->reset_request) {
 			memcpy(&request->vstor_packet, packet,
@@ -1682,8 +1710,10 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	struct vmscsi_request *vm_srb;
 	struct scatterlist *cur_sgl;
 	struct vmbus_packet_mpb_array  *payload;
+	enum dma_data_direction dir;
 	u32 payload_sz;
 	u32 length;
+	u32 attrs;
 
 	if (vmstor_proto_version <= VMSTOR_PROTO_VERSION_WIN8) {
 		/*
@@ -1722,14 +1752,17 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	case DMA_TO_DEVICE:
 		vm_srb->data_in = WRITE_TYPE;
 		vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_OUT;
+		dir = DMA_TO_DEVICE;
 		break;
 	case DMA_FROM_DEVICE:
 		vm_srb->data_in = READ_TYPE;
 		vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_IN;
+		dir = DMA_FROM_DEVICE;
 		break;
 	case DMA_NONE:
 		vm_srb->data_in = UNKNOWN_TYPE;
 		vm_srb->win8_extension.srb_flags |= SRB_FLAGS_NO_DATA_TRANSFER;
+		dir = DMA_NONE;
 		break;
 	default:
 		/*
@@ -1786,6 +1819,12 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 		hvpgoff = sgl->offset >> HV_HYP_PAGE_SHIFT;
 
 		cur_sgl = sgl;
+
+		cmd_request->dma_range = kzalloc(sizeof(struct dma_range) * hvpg_count,
+			      GFP_ATOMIC);
+		if (!cmd_request->dma_range)
+			return -ENOMEM;
+
 		for (i = 0; i < hvpg_count; i++) {
 			/*
 			 * 'i' is the index of hv pages in the payload and
@@ -1805,6 +1844,8 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 			 */
 			unsigned int hvpgoff_in_page =
 				(i + hvpgoff) % NR_HV_HYP_PAGES_IN_PAGE;
+			dma_addr_t dma;
+			u32 size;
 
 			/*
 			 * Two cases that we need to fetch a page:
@@ -1817,8 +1858,28 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 				cur_sgl = sg_next(cur_sgl);
 			}
 
-			payload->range.pfn_array[i] = hvpfn + hvpgoff_in_page;
+			size = min(HV_HYP_PAGE_SIZE - offset_in_hvpg, (unsigned long)length);
+			dma = dma_map_page_attrs(&dev->device,
+						 pfn_to_page(hvpfn),
+						 offset_in_hvpg, size,
+						 scmnd->sc_data_direction, attrs);
+			if (dma_mapping_error(&dev->device, dma)) {
+				pr_warn("dma map error.\n");
+				ret = -ENOMEM;
+				goto free_dma_range;
+			}
+
+			if (offset_in_hvpg) {
+				payload->range.offset = dma & ~HV_HYP_PAGE_MASK;
+				offset_in_hvpg = 0;
+			}
+
+			cmd_request->dma_range[i].dma = dma;
+			cmd_request->dma_range[i].mapping_size = size;
+			payload->range.pfn_array[i] = dma >> HV_HYP_PAGE_SHIFT;
+			length -= size;
 		}
+		cmd_request->hvpg_count = hvpg_count;
 	}
 
 	cmd_request->payload = payload;
@@ -1836,6 +1897,10 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	}
 
 	return 0;
+
+free_dma_range:
+	kfree(cmd_request->dma_range);
+	return ret;
 }
 
 static struct scsi_host_template scsi_driver = {
-- 
2.25.1

Re: [Resend RFC PATCH V2 12/12] HV/Storvsc: Add Isolation VM support for storvsc driver

[Christoph Hellwig]

Same comments as for the net driver.  In addition to all the poking
into kernel internals the fact that this is duplicated in the two main
drivers should have been a huge red flag.