Il 29/01/24 09:32, Yi-De Wu ha scritto:
From: "Yingshiuan Pan" <yingshiuan.pan@xxxxxxxxxxxx>
Direct use of physical memory from VMs is forbidden and designed to be
dictated to the privilege models managed by GenieZone hypervisor for
security reason. With the help of gzvm-ko, the hypervisor would be able
to manipulate memory as objects. And the memory management is highly
integrated with ARM 2-stage translation tables to convert VA to IPA to
PA under proper security measures required by protected VMs.
Signed-off-by: Yingshiuan Pan <yingshiuan.pan@xxxxxxxxxxxx>
Signed-off-by: Jerry Wang <ze-yu.wang@xxxxxxxxxxxx>
Signed-off-by: Liju Chen <liju-clr.chen@xxxxxxxxxxxx>
Signed-off-by: Yi-De Wu <yi-de.wu@xxxxxxxxxxxx>
---
arch/arm64/geniezone/gzvm_arch_common.h | 2 +
arch/arm64/geniezone/vm.c | 9 ++
drivers/virt/geniezone/Makefile | 1 -
drivers/virt/geniezone/gzvm_vm.c | 110 ++++++++++++++++++++++++
include/linux/gzvm_drv.h | 40 +++++++++
include/uapi/linux/gzvm.h | 26 ++++++
6 files changed, 187 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/geniezone/gzvm_arch_common.h b/arch/arm64/geniezone/gzvm_arch_common.h
index fdaa7849353d..2f66e496dfae 100644
--- a/arch/arm64/geniezone/gzvm_arch_common.h
+++ b/arch/arm64/geniezone/gzvm_arch_common.h
@@ -11,6 +11,7 @@
enum {
GZVM_FUNC_CREATE_VM = 0,
GZVM_FUNC_DESTROY_VM = 1,
+ GZVM_FUNC_SET_MEMREGION = 4,
GZVM_FUNC_PROBE = 12,
NR_GZVM_FUNC,
};
@@ -23,6 +24,7 @@ enum {
#define MT_HVC_GZVM_CREATE_VM GZVM_HCALL_ID(GZVM_FUNC_CREATE_VM)
#define MT_HVC_GZVM_DESTROY_VM GZVM_HCALL_ID(GZVM_FUNC_DESTROY_VM)
+#define MT_HVC_GZVM_SET_MEMREGION GZVM_HCALL_ID(GZVM_FUNC_SET_MEMREGION)
#define MT_HVC_GZVM_PROBE GZVM_HCALL_ID(GZVM_FUNC_PROBE)
/**
diff --git a/arch/arm64/geniezone/vm.c b/arch/arm64/geniezone/vm.c
index a15bad13c2ee..998d6498ac5e 100644
--- a/arch/arm64/geniezone/vm.c
+++ b/arch/arm64/geniezone/vm.c
@@ -49,6 +49,15 @@ int gzvm_arch_probe(void)
return 0;
}
+int gzvm_arch_set_memregion(u16 vm_id, size_t buf_size,
+ phys_addr_t region)
+{
+ struct arm_smccc_res res;
+
+ return gzvm_hypcall_wrapper(MT_HVC_GZVM_SET_MEMREGION, vm_id,
+ buf_size, region, 0, 0, 0, 0, &res);
+}
+
/**
* gzvm_arch_create_vm() - create vm
* @vm_type: VM type. Only supports Linux VM now.
diff --git a/drivers/virt/geniezone/Makefile b/drivers/virt/geniezone/Makefile
index 066efddc0b9c..25614ea3dea2 100644
--- a/drivers/virt/geniezone/Makefile
+++ b/drivers/virt/geniezone/Makefile
@@ -7,4 +7,3 @@
GZVM_DIR ?= ../../../drivers/virt/geniezone
gzvm-y := $(GZVM_DIR)/gzvm_main.o $(GZVM_DIR)/gzvm_vm.o
-
Don't remove this line here - actually, don't introduce it in the first place...
diff --git a/drivers/virt/geniezone/gzvm_vm.c b/drivers/virt/geniezone/gzvm_vm.c
index d5e850af924a..326cc9e93d92 100644
--- a/drivers/virt/geniezone/gzvm_vm.c
+++ b/drivers/virt/geniezone/gzvm_vm.c
@@ -15,6 +15,115 @@
static DEFINE_MUTEX(gzvm_list_lock);
static LIST_HEAD(gzvm_list);
+u64 gzvm_gfn_to_hva_memslot(struct gzvm_memslot *memslot, u64 gfn)
+{
+ u64 offset = gfn - memslot->base_gfn;
I'd check if `gfn` is less than `memslot->base_gfn` - that's a potential security
issue.
This means that this function should be
int gzvm_gfn_to_hva_memslot(struct gzvm_memslot *memslot, u64 gfn, u64 *hva_memslot)
if (gfn < memslot->base_gfn)
return -EINVAL
offset = gfn - memslot->base_gfn;
*hva_memslot = memslot->userspace_addr + offset * PAGE_SIZE:
return 0;
+
+ return memslot->userspace_addr + offset * PAGE_SIZE;
+}
+
+/**
+ * register_memslot_addr_range() - Register memory region to GenieZone
+ * @gzvm: Pointer to struct gzvm
+ * @memslot: Pointer to struct gzvm_memslot
+ *
+ * Return: 0 for success, negative number for error
+ */
+static int
+register_memslot_addr_range(struct gzvm *gzvm, struct gzvm_memslot *memslot)
+{
+ struct gzvm_memory_region_ranges *region;
+ u32 buf_size = PAGE_SIZE * 2;
+ u64 gfn;
+
+ region = alloc_pages_exact(buf_size, GFP_KERNEL);
+ if (!region)
+ return -ENOMEM;
+
+ region->slot = memslot->slot_id;
+ region->total_pages = memslot->npages;
+ gfn = memslot->base_gfn;
+ region->gpa = PFN_PHYS(gfn);
+
+ if (gzvm_arch_set_memregion(gzvm->vm_id, buf_size,
+ virt_to_phys(region))) {
+ pr_err("Failed to register memregion to hypervisor\n");
+ free_pages_exact(region, buf_size);
+ return -EFAULT;
+ }
+
+ free_pages_exact(region, buf_size);
+ return 0;
+}
+
+/**
+ * gzvm_vm_ioctl_set_memory_region() - Set memory region of guest
+ * @gzvm: Pointer to struct gzvm.
+ * @mem: Input memory region from user.
+ *
+ * Return: 0 for success, negative number for error
+ *
+ * -EXIO - The memslot is out-of-range
+ * -EFAULT - Cannot find corresponding vma
+ * -EINVAL - Region size and VMA size mismatch
+ */
+static int
+gzvm_vm_ioctl_set_memory_region(struct gzvm *gzvm,
+ struct gzvm_userspace_memory_region *mem)
+{
+ struct vm_area_struct *vma;
+ struct gzvm_memslot *memslot;
+ unsigned long size;
+ __u32 slot;
+
Remove __u32 slot.....
if (mem->slot >= GZVM_MAX_MEM_REGION)
return -ENXIO;
memslot = &gzvm->memslot[mem->slot];
+ slot = mem->slot;
+ if (slot >= GZVM_MAX_MEM_REGION)
+ return -ENXIO;
+ memslot = &gzvm->memslot[slot];
+ > + vma = vma_lookup(gzvm->mm, mem->userspace_addr);
+ if (!vma)
+ return -EFAULT;
+
+ size = vma->vm_end - vma->vm_start;
+ if (size != mem->memory_size)
+ return -EINVAL;
+
+ memslot->base_gfn = __phys_to_pfn(mem->guest_phys_addr);
+ memslot->npages = size >> PAGE_SHIFT;
+ memslot->userspace_addr = mem->userspace_addr;
+ memslot->vma = vma;
+ memslot->flags = mem->flags;
+ memslot->slot_id = mem->slot;
+ return register_memslot_addr_range(gzvm, memslot);
+}
+
+/* gzvm_vm_ioctl() - Ioctl handler of VM FD */
+static long gzvm_vm_ioctl(struct file *filp, unsigned int ioctl,
+ unsigned long arg)
+{
+ long ret;
+ void __user *argp = (void __user *)arg;
+ struct gzvm *gzvm = filp->private_data;
+
+ switch (ioctl) {
+ case GZVM_SET_USER_MEMORY_REGION: {
+ struct gzvm_userspace_memory_region userspace_mem;
+
+ if (copy_from_user(&userspace_mem, argp, sizeof(userspace_mem))) {
return -EFAULT;
+ ret = -EFAULT;
+ goto out;
+ }
+ ret = gzvm_vm_ioctl_set_memory_region(gzvm, &userspace_mem);
+ break;
+ }
+ default:
+ ret = -ENOTTY;
+ }
+out:
+ return ret;
+}
+
static void gzvm_destroy_vm(struct gzvm *gzvm)
{
pr_debug("VM-%u is going to be destroyed\n", gzvm->vm_id);
@@ -42,6 +151,7 @@ static int gzvm_vm_release(struct inode *inode, struct file *filp)
static const struct file_operations gzvm_vm_fops = {
.release = gzvm_vm_release,
+ .unlocked_ioctl = gzvm_vm_ioctl,
.llseek = noop_llseek,
};
diff --git a/include/linux/gzvm_drv.h b/include/linux/gzvm_drv.h
index f1dce23838e4..81696b7b67cc 100644
--- a/include/linux/gzvm_drv.h
+++ b/include/linux/gzvm_drv.h
@@ -7,9 +7,16 @@
#define __GZVM_DRV_H__
#include <linux/list.h>
+#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/gzvm.h>
+/*
+ * For the normal physical address, the highest 12 bits should be zero, so we
+ * can mask bit 62 ~ bit 52 to indicate the error physical address
+ */
+#define GZVM_PA_ERR_BAD (0x7ffULL << 52)
+
#define INVALID_VM_ID 0xffff
/*
@@ -27,10 +34,39 @@
* The following data structures are for data transferring between driver and
* hypervisor, and they're aligned with hypervisor definitions
*/
+#define GZVM_MAX_MEM_REGION 10
+
+/* struct mem_region_addr_range - Identical to ffa memory constituent */
+struct mem_region_addr_range {
+ /* the base IPA of the constituent memory region, aligned to 4 kiB */
+ __u64 address;
+ /* the number of 4 kiB pages in the constituent memory region. */
+ __u32 pg_cnt;
+ __u32 reserved;
+};
+
+struct gzvm_memory_region_ranges {
+ __u32 slot;
+ __u32 constituent_cnt;
+ __u64 total_pages;
+ __u64 gpa;
+ struct mem_region_addr_range constituents[];
+};
+
+/* struct gzvm_memslot - VM's memory slot descriptor */
+struct gzvm_memslot {
+ u64 base_gfn; /* begin of guest page frame */
+ unsigned long npages; /* number of pages this slot covers */
+ unsigned long userspace_addr; /* corresponding userspace va */
+ struct vm_area_struct *vma; /* vma related to this userspace addr */
kerneldoc please
+ u32 flags;
+ u32 slot_id;
+};
Regards,
Angelo
