RE: [PATCH V3 03/13] x86/HV: Add new hvcall guest address host visibility support

From: Michael Kelley
Date: Thu Aug 12 2021 - 15:36:17 EST


From: Tianyu Lan <ltykernel@xxxxxxxxx> Sent: Monday, August 9, 2021 10:56 AM
> Subject: [PATCH V3 03/13] x86/HV: Add new hvcall guest address host visibility support

Use "x86/hyperv:" tag in the Subject line.

>
> From: Tianyu Lan <Tianyu.Lan@xxxxxxxxxxxxx>
>
> Add new hvcall guest address host visibility support to mark
> memory visible to host. Call it inside set_memory_decrypted
> /encrypted(). Add HYPERVISOR feature check in the
> hv_is_isolation_supported() to optimize in non-virtualization
> environment.
>
> Signed-off-by: Tianyu Lan <Tianyu.Lan@xxxxxxxxxxxxx>
> ---
> Change since v2:
> * Rework __set_memory_enc_dec() and call Hyper-V and AMD function
> according to platform check.
>
> Change since v1:
> * Use new staic call x86_set_memory_enc to avoid add Hyper-V
> specific check in the set_memory code.
> ---
> arch/x86/hyperv/Makefile | 2 +-
> arch/x86/hyperv/hv_init.c | 6 ++
> arch/x86/hyperv/ivm.c | 114 +++++++++++++++++++++++++++++
> arch/x86/include/asm/hyperv-tlfs.h | 20 +++++
> arch/x86/include/asm/mshyperv.h | 4 +-
> arch/x86/mm/pat/set_memory.c | 19 +++--
> include/asm-generic/hyperv-tlfs.h | 1 +
> include/asm-generic/mshyperv.h | 1 +
> 8 files changed, 160 insertions(+), 7 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/hv_init.c b/arch/x86/hyperv/hv_init.c
> index 0bb4d9ca7a55..b3683083208a 100644
> --- a/arch/x86/hyperv/hv_init.c
> +++ b/arch/x86/hyperv/hv_init.c
> @@ -607,6 +607,12 @@ EXPORT_SYMBOL_GPL(hv_get_isolation_type);
>
> bool hv_is_isolation_supported(void)
> {
> + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
> + return 0;
> +
> + if (!hypervisor_is_type(X86_HYPER_MS_HYPERV))
> + return 0;
> +
> return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;

Could all of the tests in this function be run at initialization time, and
a single Boolean value pre-computed that this function returns? I don't
think any of tests would change during the lifetime of the Linux instance,
so running the tests every time is slower than it needs to be.

> }
>
> diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
> new file mode 100644
> index 000000000000..8c905ffdba7f
> --- /dev/null
> +++ b/arch/x86/hyperv/ivm.c
> @@ -0,0 +1,114 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Hyper-V Isolation VM interface with paravisor and hypervisor
> + *
> + * Author:
> + * Tianyu Lan <Tianyu.Lan@xxxxxxxxxxxxx>
> + */
> +
> +#include <linux/hyperv.h>
> +#include <linux/types.h>
> +#include <linux/bitfield.h>
> +#include <linux/slab.h>
> +#include <asm/io.h>
> +#include <asm/mshyperv.h>
> +
> +/*
> + * hv_mark_gpa_visibility - Set pages visible to host via hvcall.
> + *
> + * In Isolation VM, all guest memory is encripted from host and guest
> + * needs to set memory visible to host via hvcall before sharing memory
> + * with host.
> + */
> +int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
> + enum hv_mem_host_visibility visibility)
> +{
> + struct hv_gpa_range_for_visibility **input_pcpu, *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_gpa_range_for_visibility **)
> + this_cpu_ptr(hyperv_pcpu_input_arg);
> + input = *input_pcpu;
> + if (unlikely(!input)) {
> + local_irq_restore(flags);
> + return -EINVAL;
> + }
> +
> + 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;

pages_processed should also be checked to ensure that it equals count.
If not, something has gone wrong in the hypercall.

> +
> + return hv_status & HV_HYPERCALL_RESULT_MASK;
> +}
> +EXPORT_SYMBOL(hv_mark_gpa_visibility);
> +
> +static int __hv_set_mem_host_visibility(void *kbuffer, int pagecount,
> + enum hv_mem_host_visibility visibility)
> +{
> + u64 *pfn_array;
> + int ret = 0;
> + int i, pfn;
> +
> + if (!hv_is_isolation_supported() || !ms_hyperv.ghcb_base)
> + return 0;
> +
> + pfn_array = kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);

Does the page need to be zero'ed? All bytes that are used will
be explicitly written in the loop below.

> + 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);

I don't see why value of "ret" is OR'ed. If the result of hv_mark_gpa_visibility()
is ever non-zero, we'll exit immediately. There's no need to accumulate the
results of multiple calls to hv_mark_gpa_visibility().

> + pfn = 0;
> +
> + if (ret)
> + goto err_free_pfn_array;
> + }
> + }
> +
> + err_free_pfn_array:
> + kfree(pfn_array);
> + return ret;
> +}
> +
> +/*
> + * hv_set_mem_host_visibility - Set specified memory visible to host.
> + *
> + * In Isolation VM, all guest memory is encrypted from host and guest
> + * needs to set memory visible to host via hvcall before sharing memory
> + * with host. This function works as wrap of hv_mark_gpa_visibility()
> + * with memory base and size.
> + */
> +int hv_set_mem_host_visibility(unsigned long addr, int numpages, bool visible)
> +{
> + enum hv_mem_host_visibility visibility = visible ?
> + VMBUS_PAGE_VISIBLE_READ_WRITE : VMBUS_PAGE_NOT_VISIBLE;
> +
> + return __hv_set_mem_host_visibility((void *)addr, numpages, visibility);
> +}
> diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
> index 2322d6bd5883..1691d2bce0b7 100644
> --- a/arch/x86/include/asm/hyperv-tlfs.h
> +++ b/arch/x86/include/asm/hyperv-tlfs.h
> @@ -276,6 +276,13 @@ enum hv_isolation_type {
> #define HV_X64_MSR_TIME_REF_COUNT HV_REGISTER_TIME_REF_COUNT
> #define HV_X64_MSR_REFERENCE_TSC HV_REGISTER_REFERENCE_TSC
>
> +/* Hyper-V memory host visibility */
> +enum hv_mem_host_visibility {
> + VMBUS_PAGE_NOT_VISIBLE = 0,
> + VMBUS_PAGE_VISIBLE_READ_ONLY = 1,
> + VMBUS_PAGE_VISIBLE_READ_WRITE = 3
> +};
> +
> /*
> * Declare the MSR used to setup pages used to communicate with the hypervisor.
> */
> @@ -587,4 +594,17 @@ 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_gpa_range_for_visibility {
> + u64 partition_id;
> + u32 host_visibility:2;
> + u32 reserved0:30;
> + u32 reserved1;
> + u64 gpa_page_list[HV_MAX_MODIFY_GPA_REP_COUNT];
> +} __packed;
> +

We should avoid adding definitions *after* the #include of
<asm-generic/hyperv-tlfs.h>. That #include should be last. Any
reason these can't go earlier? And they really go together with
enum hv_mem_host_visibility.

Separately, take a look at how the structure hv_memory_hint
and HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES is handled.
It's a close parallel to what you are doing above, and is a slightly
cleaner approach.

> #endif
> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> index 6627cfd2bfba..87a386fa97f7 100644
> --- a/arch/x86/include/asm/mshyperv.h
> +++ b/arch/x86/include/asm/mshyperv.h
> @@ -190,7 +190,9 @@ struct irq_domain *hv_create_pci_msi_domain(void);
> 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_mark_gpa_visibility(u16 count, const u64 pfn[],
> + enum hv_mem_host_visibility visibility);
> +int hv_set_mem_host_visibility(unsigned long addr, int numpages, bool visible);
> #else /* CONFIG_HYPERV */
> static inline void hyperv_init(void) {}
> static inline void hyperv_setup_mmu_ops(void) {}
> diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
> index ad8a5c586a35..1e4a0882820a 100644
> --- a/arch/x86/mm/pat/set_memory.c
> +++ b/arch/x86/mm/pat/set_memory.c
> @@ -29,6 +29,8 @@
> #include <asm/proto.h>
> #include <asm/memtype.h>
> #include <asm/set_memory.h>
> +#include <asm/hyperv-tlfs.h>
> +#include <asm/mshyperv.h>
>
> #include "../mm_internal.h"
>
> @@ -1980,15 +1982,11 @@ int set_memory_global(unsigned long addr, int numpages)
> __pgprot(_PAGE_GLOBAL), 0);
> }
>
> -static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
> +static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
> {
> struct cpa_data cpa;
> int ret;
>
> - /* Nothing to do if memory encryption is not active */
> - if (!mem_encrypt_active())
> - return 0;
> -
> /* Should not be working on unaligned addresses */
> if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr))
> addr &= PAGE_MASK;
> @@ -2023,6 +2021,17 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
> return ret;
> }
>
> +static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
> +{
> + if (hv_is_isolation_supported())
> + return hv_set_mem_host_visibility(addr, numpages, !enc);
> +
> + if (mem_encrypt_active())
> + return __set_memory_enc_pgtable(addr, numpages, enc);
> +
> + return 0;
> +}
> +
> int set_memory_encrypted(unsigned long addr, int numpages)
> {
> return __set_memory_enc_dec(addr, numpages, true);
> diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h
> index 56348a541c50..8ed6733d5146 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
>
> /* Extended hypercalls */
> #define HV_EXT_CALL_QUERY_CAPABILITIES 0x8001
> diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
> index aa26d24a5ca9..079988ed45b9 100644
> --- a/include/asm-generic/mshyperv.h
> +++ b/include/asm-generic/mshyperv.h
> @@ -255,6 +255,7 @@ bool hv_query_ext_cap(u64 cap_query);
> static inline bool hv_is_hyperv_initialized(void) { return false; }
> static inline bool hv_is_hibernation_supported(void) { return false; }
> static inline void hyperv_cleanup(void) {}
> +static inline hv_is_isolation_supported(void);
> #endif /* CONFIG_HYPERV */
>
> #endif
> --
> 2.25.1