[PATCH v2 0/6] arm64: hyperv: Add Realm support for Hyper-V

[PATCH v2 0/6] arm64: hyperv: Add Realm support for Hyper-V

[Kameron Carr]

Realms (CoCo VMs on ARM) require host calls to be routed through the RMM
(Realm Management Monitor) via the RSI (Realm Service Interface). This
series implements most of the necessary changes to support Realms on
Hyper-V.

One required change is not included in this series. The two buffers
allocated via vzalloc() in netvsc_init_buf() cannot be decrypted in
vmbus_establish_gpadl(). Currently only linearly mapped memory can be
decrypted. See my RFC patch [1]. I will implement the accompanying netvsc
changes based on the feedback I receive on that patch.

This patch series was tested by booting a Realm on Cobalt 200 running
Windows. I decreased the buffer size and used kzalloc() in
netvsc_init_buf() in my testing as a workaround for the issue mentioned
above.


Changes since v1 [2]:
  Patch 1: Add explicit padding to the RSI host call structure
  Patch 3: Change from a per-cpu pointer lazily allocated to an array
             of host call structs indexed by cpu id
  Patch 4: Align input_page + output_page allocation to PAGE_SIZE since
              that is the smallest unit of memory that can be decrypted
           Remove KSAN tags before passing address to set_memory_decrypted()
             since __is_lm_address() does pointer arithmetic.
  Patch 5: Add a helper function to reduce repetition
           Check for NULL before indexing into host call array

[1] https://lore.kernel.org/all/20260521205834.1012925-1-kameroncarr@linux.microsoft.com/
[2] https://lore.kernel.org/all/20260609181030.2378391-1-kameroncarr@linux.microsoft.com/

Kameron Carr (6):
  arm64: rsi: Add RSI host call structure and helper function
  firmware: smccc: Detect hypervisor via RSI host call in CCA Realms
  arm64: hyperv: Add per-CPU RSI host call infrastructure for CCA Realms
  Drivers: hv: Mark shared memory as decrypted for CCA Realms
  arm64: hyperv: Route hypercalls through RSI host call in CCA Realms
  arm64: hyperv: Implement hv_is_isolation_supported() for CCA Realms

 arch/arm64/hyperv/hv_core.c       | 155 +++++++++++++++++++++++-------
 arch/arm64/hyperv/mshyperv.c      |  42 +++++++-
 arch/arm64/include/asm/mshyperv.h |   4 +
 arch/arm64/include/asm/rsi_cmds.h |  22 +++++
 arch/arm64/include/asm/rsi_smc.h  |   7 ++
 drivers/firmware/smccc/smccc.c    |  41 +++++++-
 drivers/hv/hv_common.c            |  17 +++-
 include/asm-generic/mshyperv.h    |   1 +
 8 files changed, 249 insertions(+), 40 deletions(-)


base-commit: a4ffc59238be84dd1c26bf1c001543e832674fc6
-- 
2.45.4

[PATCH v2 1/6] arm64: rsi: Add RSI host call structure and helper function

[Kameron Carr]

Add struct rsi_host_call to rsi_smc.h, which represents the host call
data structure used by the Realm Management Monitor (RMM) for the
RSI_HOST_CALL interface. The structure contains a 16-bit immediate field
and 31 general-purpose register values, aligned to 256 bytes as required
by the CCA RMM specification.

Add rsi_host_call() static inline wrapper in rsi_cmds.h that invokes
SMC_RSI_HOST_CALL with the physical address of the host call structure.
This will be used by Hyper-V guest code to route hypercalls through the
RSI interface when running inside an Arm CCA Realm.

Signed-off-by: Kameron Carr <kameroncarr@linux.microsoft.com>
---
 arch/arm64/include/asm/rsi_cmds.h | 22 ++++++++++++++++++++++
 arch/arm64/include/asm/rsi_smc.h  |  7 +++++++
 2 files changed, 29 insertions(+)

diff --git a/arch/arm64/include/asm/rsi_cmds.h b/arch/arm64/include/asm/rsi_cmds.h
index 2c8763876dfb7..9daf8008e5da2 100644
--- a/arch/arm64/include/asm/rsi_cmds.h
+++ b/arch/arm64/include/asm/rsi_cmds.h
@@ -88,6 +88,28 @@ static inline long rsi_set_addr_range_state(phys_addr_t start,
 	return res.a0;
 }
 
+/**
+ * rsi_host_call - Make a Host call.
+ * @host_call_struct: IPA of host call structure
+ *
+ * This call will fail if the IPA of the host call structure:
+ * * is not aligned to 256 bytes,
+ * * is not protected / encrypted,
+ * * is RIPAS_EMPTY
+ *
+ * Returns:
+ *  On success, returns RSI_SUCCESS.
+ *  Otherwise, returns an error code.
+ */
+static inline unsigned long rsi_host_call(phys_addr_t host_call_struct)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_smc(SMC_RSI_HOST_CALL, host_call_struct, 0, 0, 0, 0, 0, 0,
+		      &res);
+	return res.a0;
+}
+
 /**
  * rsi_attestation_token_init - Initialise the operation to retrieve an
  * attestation token.
diff --git a/arch/arm64/include/asm/rsi_smc.h b/arch/arm64/include/asm/rsi_smc.h
index e19253f96c940..9cc57b5be0c02 100644
--- a/arch/arm64/include/asm/rsi_smc.h
+++ b/arch/arm64/include/asm/rsi_smc.h
@@ -142,6 +142,13 @@ struct realm_config {
 	 */
 } __aligned(0x1000);
 
+struct rsi_host_call {
+	u16 immediate;
+	u8 _padding[6];
+	u64 gprs[31];
+} __aligned(256);
+static_assert(sizeof(struct rsi_host_call) == 256);
+
 #endif /* __ASSEMBLER__ */
 
 /*
-- 
2.45.4

[PATCH v2 2/6] firmware: smccc: Detect hypervisor via RSI host call in CCA Realms

[Kameron Carr]

Modify arm_smccc_hypervisor_has_uuid() to check is_realm_world() and
use rsi_host_call() to query the hypervisor vendor UUID when inside a
Realm. The realm path is factored into a helper,
arm_smccc_realm_get_hypervisor_uuid(), that owns a file-static
rsi_host_call buffer (uuid_hc) serialized by a spinlock.

The RSI-specific includes, file-static state and helper are guarded
with CONFIG_ARM64 because <asm/rsi.h> does not exist on 32-bit ARM.

For non-Realm environments, the existing arm_smccc_1_1_invoke() path
is unchanged.

Signed-off-by: Kameron Carr <kameroncarr@linux.microsoft.com>
---
 drivers/firmware/smccc/smccc.c | 41 +++++++++++++++++++++++++++++++++-
 1 file changed, 40 insertions(+), 1 deletion(-)

diff --git a/drivers/firmware/smccc/smccc.c b/drivers/firmware/smccc/smccc.c
index bdee057db2fd3..a876b7aa2dc99 100644
--- a/drivers/firmware/smccc/smccc.c
+++ b/drivers/firmware/smccc/smccc.c
@@ -12,6 +12,12 @@
 #include <linux/platform_device.h>
 #include <asm/archrandom.h>
 
+#ifdef CONFIG_ARM64
+#include <linux/cleanup.h>
+#include <linux/spinlock.h>
+#include <asm/rsi.h>
+#endif
+
 static u32 smccc_version = ARM_SMCCC_VERSION_1_0;
 static enum arm_smccc_conduit smccc_conduit = SMCCC_CONDUIT_NONE;
 
@@ -67,12 +73,45 @@ s32 arm_smccc_get_soc_id_revision(void)
 }
 EXPORT_SYMBOL_GPL(arm_smccc_get_soc_id_revision);
 
+#ifdef CONFIG_ARM64
+static struct rsi_host_call uuid_hc;
+static DEFINE_SPINLOCK(uuid_hc_lock);
+
+/*
+ * Helper function to get the hypervisor UUID via an RsiHostCall.
+ */
+static void arm_smccc_realm_get_hypervisor_uuid(struct arm_smccc_res *res)
+{
+	guard(spinlock_irqsave)(&uuid_hc_lock);
+
+	memset(&uuid_hc, 0, sizeof(uuid_hc));
+	uuid_hc.gprs[0] = ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID;
+
+	if (rsi_host_call(__pa_symbol(&uuid_hc)) != RSI_SUCCESS) {
+		res->a0 = SMCCC_RET_NOT_SUPPORTED;
+		return;
+	}
+
+	res->a0 = uuid_hc.gprs[0];
+	res->a1 = uuid_hc.gprs[1];
+	res->a2 = uuid_hc.gprs[2];
+	res->a3 = uuid_hc.gprs[3];
+}
+#endif
+
 bool arm_smccc_hypervisor_has_uuid(const uuid_t *hyp_uuid)
 {
 	struct arm_smccc_res res = {};
 	uuid_t uuid;
 
-	arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, &res);
+#ifdef CONFIG_ARM64
+	if (is_realm_world())
+		arm_smccc_realm_get_hypervisor_uuid(&res);
+	else
+#endif
+		arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID,
+				     &res);
+
 	if (res.a0 == SMCCC_RET_NOT_SUPPORTED)
 		return false;
 
-- 
2.45.4

[PATCH v2 3/6] arm64: hyperv: Add per-CPU RSI host call infrastructure for CCA Realms

[Kameron Carr]

Arm CCA Realms cannot issue Hyper-V hypercalls via HVC; the guest must
route them through the RSI_HOST_CALL interface, which takes the IPA of a
per-CPU rsi_host_call structure as its argument.

Add hv_hostcall_array as a per-CPU struct array and allocate it during
hyperv_init(). The allocation is gated on is_realm_world() so non-Realm
arm64 Hyper-V guests pay no memory cost.

Signed-off-by: Kameron Carr <kameroncarr@linux.microsoft.com>
---
 arch/arm64/hyperv/mshyperv.c      | 32 ++++++++++++++++++++++++++++++-
 arch/arm64/include/asm/mshyperv.h |  4 ++++
 2 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c
index 4fdc26ade1d74..7d536d7fb557e 100644
--- a/arch/arm64/hyperv/mshyperv.c
+++ b/arch/arm64/hyperv/mshyperv.c
@@ -15,10 +15,15 @@
 #include <linux/errno.h>
 #include <linux/version.h>
 #include <linux/cpuhotplug.h>
+#include <linux/slab.h>
 #include <asm/mshyperv.h>
+#include <asm/rsi.h>
 
 static bool hyperv_initialized;
 
+struct rsi_host_call *hv_hostcall_array;
+EXPORT_SYMBOL_GPL(hv_hostcall_array);
+
 int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
 {
 	hv_get_vpreg_128(HV_REGISTER_HYPERVISOR_VERSION,
@@ -60,6 +65,12 @@ static bool __init hyperv_detect_via_acpi(void)
 
 #endif
 
+static void hv_hostcall_free(void)
+{
+	kfree(hv_hostcall_array);
+	hv_hostcall_array = NULL;
+}
+
 static bool __init hyperv_detect_via_smccc(void)
 {
 	uuid_t hyperv_uuid = UUID_INIT(
@@ -85,6 +96,20 @@ static int __init hyperv_init(void)
 	if (!hyperv_detect_via_acpi() && !hyperv_detect_via_smccc())
 		return 0;
 
+	/*
+	 * The RSI host-call buffers are only ever used when
+	 * is_realm_world() is true. Skip the allocation on non-Realm
+	 * guests. A single contiguous array of nr_cpu_ids entries is
+	 * allocated; each CPU indexes into it by its processor ID.
+	 */
+	if (is_realm_world()) {
+		hv_hostcall_array = kcalloc(nr_cpu_ids,
+					    sizeof(struct rsi_host_call),
+					    GFP_KERNEL);
+		if (!hv_hostcall_array)
+			return -ENOMEM;
+	}
+
 	/* Setup the guest ID */
 	guest_id = hv_generate_guest_id(LINUX_VERSION_CODE);
 	hv_set_vpreg(HV_REGISTER_GUEST_OS_ID, guest_id);
@@ -106,12 +131,13 @@ static int __init hyperv_init(void)
 
 	ret = hv_common_init();
 	if (ret)
-		return ret;
+		goto free_hostcall_mem;
 
 	ret = cpuhp_setup_state(CPUHP_AP_HYPERV_ONLINE, "arm64/hyperv_init:online",
 				hv_common_cpu_init, hv_common_cpu_die);
 	if (ret < 0) {
 		hv_common_free();
+		hv_hostcall_free();
 		return ret;
 	}
 
@@ -125,6 +151,10 @@ static int __init hyperv_init(void)
 
 	hyperv_initialized = true;
 	return 0;
+
+free_hostcall_mem:
+	hv_hostcall_free();
+	return ret;
 }
 
 early_initcall(hyperv_init);
diff --git a/arch/arm64/include/asm/mshyperv.h b/arch/arm64/include/asm/mshyperv.h
index b721d3134ab66..c207a3f79b99b 100644
--- a/arch/arm64/include/asm/mshyperv.h
+++ b/arch/arm64/include/asm/mshyperv.h
@@ -63,4 +63,8 @@ static inline u64 hv_get_non_nested_msr(unsigned int reg)
 
 #include <asm-generic/mshyperv.h>
 
+/* Per-CPU-indexed RSI host call structures for CCA Realms */
+struct rsi_host_call;
+extern struct rsi_host_call *hv_hostcall_array;
+
 #endif
-- 
2.45.4

[PATCH v2 4/6] Drivers: hv: Mark shared memory as decrypted for CCA Realms

[Kameron Carr]

In hv_common_cpu_init(), the per-CPU hypercall input/output pages need
to be marked as decrypted (shared) for confidential VM isolation types.
This is already done for SNP and TDX isolation; extend the same handling
to Arm CCA Realm guests so that the host hypervisor can access the
shared hypercall buffers.

We need to round up the memory allocated for the input/output pages to
the nearest PAGE_SIZE, since set_memory_decrypted() requires the size to
be a multiple of PAGE_SIZE. This only has an effect on ARM VMs that are
using PAGE_SIZE larger than 4K.

is_realm_world() is only declared in arch/arm64/include/asm/rsi.h, so
using it directly in the arch-neutral drivers/hv/hv_common.c would
break the x86 build. Introduce a Hyper-V-specific helper following the
established hv_isolation_type_snp() / hv_isolation_type_tdx() pattern.

On architectures other than arm64 the weak default keeps the existing
behaviour.

Signed-off-by: Kameron Carr <kameroncarr@linux.microsoft.com>
---
 arch/arm64/hyperv/mshyperv.c   |  5 +++++
 drivers/hv/hv_common.c         | 17 +++++++++++++----
 include/asm-generic/mshyperv.h |  1 +
 3 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c
index 7d536d7fb557e..8e8148b723d9c 100644
--- a/arch/arm64/hyperv/mshyperv.c
+++ b/arch/arm64/hyperv/mshyperv.c
@@ -164,3 +164,8 @@ bool hv_is_hyperv_initialized(void)
 	return hyperv_initialized;
 }
 EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
+
+bool hv_isolation_type_cca(void)
+{
+	return is_realm_world();
+}
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index 6b67ac6167891..17048a0a18729 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -476,6 +476,7 @@ int hv_common_cpu_init(unsigned int cpu)
 	u64 msr_vp_index;
 	gfp_t flags;
 	const int pgcount = hv_output_page_exists() ? 2 : 1;
+	const size_t alloc_size = ALIGN((size_t)pgcount * HV_HYP_PAGE_SIZE, PAGE_SIZE);
 	void *mem;
 	int ret = 0;
 
@@ -489,7 +490,7 @@ int hv_common_cpu_init(unsigned int cpu)
 	 * online and then taken offline
 	 */
 	if (!*inputarg) {
-		mem = kmalloc_array(pgcount, HV_HYP_PAGE_SIZE, flags);
+		mem = kmalloc(alloc_size, flags);
 		if (!mem)
 			return -ENOMEM;
 
@@ -499,14 +500,16 @@ int hv_common_cpu_init(unsigned int cpu)
 		}
 
 		if (!ms_hyperv.paravisor_present &&
-		    (hv_isolation_type_snp() || hv_isolation_type_tdx())) {
-			ret = set_memory_decrypted((unsigned long)mem, pgcount);
+		    (hv_isolation_type_snp() || hv_isolation_type_tdx() ||
+		     hv_isolation_type_cca())) {
+			ret = set_memory_decrypted((unsigned long)kasan_reset_tag(mem),
+				alloc_size >> PAGE_SHIFT);
 			if (ret) {
 				/* It may be unsafe to free 'mem' */
 				return ret;
 			}
 
-			memset(mem, 0x00, pgcount * HV_HYP_PAGE_SIZE);
+			memset(mem, 0x00, alloc_size);
 		}
 
 		/*
@@ -666,6 +669,12 @@ bool __weak hv_isolation_type_tdx(void)
 }
 EXPORT_SYMBOL_GPL(hv_isolation_type_tdx);
 
+bool __weak hv_isolation_type_cca(void)
+{
+	return false;
+}
+EXPORT_SYMBOL_GPL(hv_isolation_type_cca);
+
 void __weak hv_setup_vmbus_handler(void (*handler)(void))
 {
 }
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index bf601d67cecb9..1fa79abce743c 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -79,6 +79,7 @@ u64 hv_do_fast_hypercall16(u16 control, u64 input1, u64 input2);
 
 bool hv_isolation_type_snp(void);
 bool hv_isolation_type_tdx(void);
+bool hv_isolation_type_cca(void);
 
 /*
  * On architectures where Hyper-V doesn't support AEOI (e.g., ARM64),
-- 
2.45.4

[PATCH v2 5/6] arm64: hyperv: Route hypercalls through RSI host call in CCA Realms

[Kameron Carr]

Modify the five hypercall wrapper functions to check is_realm_world()
and use the per-CPU rsi_host_call structure when inside a Realm.

Signed-off-by: Kameron Carr <kameroncarr@linux.microsoft.com>
---
 arch/arm64/hyperv/hv_core.c | 155 ++++++++++++++++++++++++++++--------
 1 file changed, 121 insertions(+), 34 deletions(-)

diff --git a/arch/arm64/hyperv/hv_core.c b/arch/arm64/hyperv/hv_core.c
index e33a9e3c366a1..77cba08fca132 100644
--- a/arch/arm64/hyperv/hv_core.c
+++ b/arch/arm64/hyperv/hv_core.c
@@ -13,9 +13,41 @@
 #include <linux/mm.h>
 #include <linux/arm-smccc.h>
 #include <linux/module.h>
+#include <linux/smp.h>
 #include <asm-generic/bug.h>
 #include <hyperv/hvhdk.h>
 #include <asm/mshyperv.h>
+#include <asm/rsi.h>
+
+/*
+ * hv_do_rsi_hypercall - Helper function to invoke a hypercall from a
+ * Realm world using the RSI interface.
+ */
+static u64 hv_do_rsi_hypercall(u64 control, u64 input1, u64 input2)
+{
+	struct rsi_host_call *hostcall;
+	unsigned long flags;
+	u64 ret;
+
+	if (!hv_hostcall_array)
+		return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+	local_irq_save(flags);
+	hostcall = &hv_hostcall_array[smp_processor_id()];
+	memset(hostcall, 0, sizeof(*hostcall));
+	hostcall->gprs[0] = HV_FUNC_ID;
+	hostcall->gprs[1] = control;
+	hostcall->gprs[2] = input1;
+	hostcall->gprs[3] = input2;
+
+	if (rsi_host_call(virt_to_phys(hostcall)) == RSI_SUCCESS)
+		ret = hostcall->gprs[0];
+	else
+		ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+	local_irq_restore(flags);
+	return ret;
+}
 
 /*
  * hv_do_hypercall- Invoke the specified hypercall
@@ -29,8 +61,11 @@ u64 hv_do_hypercall(u64 control, void *input, void *output)
 	input_address = input ? virt_to_phys(input) : 0;
 	output_address = output ? virt_to_phys(output) : 0;
 
-	arm_smccc_1_1_hvc(HV_FUNC_ID, control,
-			  input_address, output_address, &res);
+	if (is_realm_world())
+		return hv_do_rsi_hypercall(control, input_address, output_address);
+
+	arm_smccc_1_1_hvc(HV_FUNC_ID, control, input_address,
+			  output_address, &res);
 	return res.a0;
 }
 EXPORT_SYMBOL_GPL(hv_do_hypercall);
@@ -48,6 +83,9 @@ u64 hv_do_fast_hypercall8(u16 code, u64 input)
 
 	control = (u64)code | HV_HYPERCALL_FAST_BIT;
 
+	if (is_realm_world())
+		return hv_do_rsi_hypercall(control, input, 0);
+
 	arm_smccc_1_1_hvc(HV_FUNC_ID, control, input, &res);
 	return res.a0;
 }
@@ -65,6 +103,9 @@ u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
 
 	control = (u64)code | HV_HYPERCALL_FAST_BIT;
 
+	if (is_realm_world())
+		return hv_do_rsi_hypercall(control, input1, input2);
+
 	arm_smccc_1_1_hvc(HV_FUNC_ID, control, input1, input2, &res);
 	return res.a0;
 }
@@ -76,24 +117,44 @@ EXPORT_SYMBOL_GPL(hv_do_fast_hypercall16);
 void hv_set_vpreg(u32 msr, u64 value)
 {
 	struct arm_smccc_res res;
+	struct rsi_host_call *hostcall;
+	unsigned long flags;
+	u64 status;
 
-	arm_smccc_1_1_hvc(HV_FUNC_ID,
-		HVCALL_SET_VP_REGISTERS | HV_HYPERCALL_FAST_BIT |
-			HV_HYPERCALL_REP_COMP_1,
-		HV_PARTITION_ID_SELF,
-		HV_VP_INDEX_SELF,
-		msr,
-		0,
-		value,
-		0,
-		&res);
+	if (is_realm_world()) {
+		local_irq_save(flags);
+		hostcall = &hv_hostcall_array[smp_processor_id()];
+		memset(hostcall, 0, sizeof(*hostcall));
+		hostcall->gprs[0] = HV_FUNC_ID;
+		hostcall->gprs[1] = HVCALL_SET_VP_REGISTERS |
+				    HV_HYPERCALL_FAST_BIT |
+				    HV_HYPERCALL_REP_COMP_1;
+		hostcall->gprs[2] = HV_PARTITION_ID_SELF;
+		hostcall->gprs[3] = HV_VP_INDEX_SELF;
+		hostcall->gprs[4] = msr;
+		hostcall->gprs[6] = value;
+
+		if (rsi_host_call(virt_to_phys(hostcall)) == RSI_SUCCESS)
+			status = hostcall->gprs[0];
+		else
+			status = HV_STATUS_INVALID_HYPERCALL_INPUT;
+		local_irq_restore(flags);
+	} else {
+		arm_smccc_1_1_hvc(HV_FUNC_ID,
+				  HVCALL_SET_VP_REGISTERS |
+					  HV_HYPERCALL_FAST_BIT |
+					  HV_HYPERCALL_REP_COMP_1,
+				  HV_PARTITION_ID_SELF, HV_VP_INDEX_SELF, msr,
+				  0, value, 0, &res);
+		status = res.a0;
+	}
 
 	/*
-	 * Something is fundamentally broken in the hypervisor if
-	 * setting a VP register fails. There's really no way to
-	 * continue as a guest VM, so panic.
+	 * Something is fundamentally broken in the hypervisor (or, in a
+	 * Realm, the RMM denied the host call) if setting a VP register
+	 * fails. There's really no way to continue as a guest VM, so panic.
 	 */
-	BUG_ON(!hv_result_success(res.a0));
+	BUG_ON(!hv_result_success(status));
 }
 EXPORT_SYMBOL_GPL(hv_set_vpreg);
 
@@ -108,29 +169,55 @@ void hv_get_vpreg_128(u32 msr, struct hv_get_vp_registers_output *result)
 {
 	struct arm_smccc_1_2_regs args;
 	struct arm_smccc_1_2_regs res;
+	struct rsi_host_call *hostcall;
+	unsigned long flags;
+	u64 status;
 
-	args.a0 = HV_FUNC_ID;
-	args.a1 = HVCALL_GET_VP_REGISTERS | HV_HYPERCALL_FAST_BIT |
-			HV_HYPERCALL_REP_COMP_1;
-	args.a2 = HV_PARTITION_ID_SELF;
-	args.a3 = HV_VP_INDEX_SELF;
-	args.a4 = msr;
+	if (is_realm_world()) {
+		local_irq_save(flags);
+		hostcall = &hv_hostcall_array[smp_processor_id()];
+		memset(hostcall, 0, sizeof(*hostcall));
 
-	/*
-	 * Use the SMCCC 1.2 interface because the results are in registers
-	 * beyond X0-X3.
-	 */
-	arm_smccc_1_2_hvc(&args, &res);
+		hostcall->gprs[0] = HV_FUNC_ID;
+		hostcall->gprs[1] = HVCALL_GET_VP_REGISTERS |
+				    HV_HYPERCALL_FAST_BIT |
+				    HV_HYPERCALL_REP_COMP_1;
+		hostcall->gprs[2] = HV_PARTITION_ID_SELF;
+		hostcall->gprs[3] = HV_VP_INDEX_SELF;
+		hostcall->gprs[4] = msr;
+
+		if (rsi_host_call(virt_to_phys(hostcall)) == RSI_SUCCESS) {
+			status = hostcall->gprs[0];
+			result->as64.low = hostcall->gprs[6];
+			result->as64.high = hostcall->gprs[7];
+		} else {
+			status = HV_STATUS_INVALID_HYPERCALL_INPUT;
+		}
+		local_irq_restore(flags);
+	} else {
+		args.a0 = HV_FUNC_ID;
+		args.a1 = HVCALL_GET_VP_REGISTERS | HV_HYPERCALL_FAST_BIT |
+			  HV_HYPERCALL_REP_COMP_1;
+		args.a2 = HV_PARTITION_ID_SELF;
+		args.a3 = HV_VP_INDEX_SELF;
+		args.a4 = msr;
+
+		/*
+		 * Use the SMCCC 1.2 interface because the results are in
+		 * registers beyond X0-X3.
+		 */
+		arm_smccc_1_2_hvc(&args, &res);
+		status = res.a0;
+		result->as64.low = res.a6;
+		result->as64.high = res.a7;
+	}
 
 	/*
-	 * Something is fundamentally broken in the hypervisor if
-	 * getting a VP register fails. There's really no way to
-	 * continue as a guest VM, so panic.
+	 * Something is fundamentally broken in the hypervisor (or, in a
+	 * Realm, the RMM denied the host call) if getting a VP register
+	 * fails. There's really no way to continue as a guest VM, so panic.
 	 */
-	BUG_ON(!hv_result_success(res.a0));
-
-	result->as64.low = res.a6;
-	result->as64.high = res.a7;
+	BUG_ON(!hv_result_success(status));
 }
 EXPORT_SYMBOL_GPL(hv_get_vpreg_128);
 
-- 
2.45.4

[PATCH v2 6/6] arm64: hyperv: Implement hv_is_isolation_supported() for CCA Realms

[Kameron Carr]

Provide an arm64 implementation of hv_is_isolation_supported() that
overrides the __weak default in drivers/hv/hv_common.c.

The implementation deliberately does not depend on
hv_is_hyperv_initialized() because hv_common_init() consults
hv_is_isolation_supported() before hyperv_initialized is set.

Signed-off-by: Kameron Carr <kameroncarr@linux.microsoft.com>
---
 arch/arm64/hyperv/mshyperv.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c
index 8e8148b723d9c..62995b6133f6f 100644
--- a/arch/arm64/hyperv/mshyperv.c
+++ b/arch/arm64/hyperv/mshyperv.c
@@ -169,3 +169,8 @@ bool hv_isolation_type_cca(void)
 {
 	return is_realm_world();
 }
+
+bool hv_is_isolation_supported(void)
+{
+	return is_realm_world();
+}
-- 
2.45.4

Re: [PATCH v2 3/6] arm64: hyperv: Add per-CPU RSI host call infrastructure for CCA Realms

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [High] The `hv_hostcall_array` is allocated with `kcalloc()`, which does not guarantee the strict 256-byte alignment required by the RMM for `SMC_RSI_HOST_CALL`.
- [High] If `hyperv_init()` fails, `hv_hostcall_array` is freed but panic notifiers are left registered, causing a fatal NULL pointer dereference during a subsequent panic.
- [Low] The early boot initialization function `hyperv_init()` contains unnecessary memory allocation failure handling and cleanup logic for `hv_hostcall_array`.
--

commit 906cd2b30d2ff5884265fe39d28d07e982c9f874
Author: Kameron Carr <kameroncarr@linux.microsoft.com>

arm64: hyperv: Add per-CPU RSI host call infrastructure for CCA Realms

This commit adds a per-CPU rsi_host_call array allocation for Arm CCA
Realms. It routes Hyper-V hypercalls through the RSI_HOST_CALL interface
instead of HVC.

> diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c
> index 4fdc26ade1d74..7d536d7fb557e 100644
> --- a/arch/arm64/hyperv/mshyperv.c
> +++ b/arch/arm64/hyperv/mshyperv.c

[ ... ]

> @@ -85,6 +96,20 @@ static int __init hyperv_init(void)
>  	if (!hyperv_detect_via_acpi() && !hyperv_detect_via_smccc())
>  		return 0;
>  
> +	/*
> +	 * The RSI host-call buffers are only ever used when
> +	 * is_realm_world() is true. Skip the allocation on non-Realm
> +	 * guests. A single contiguous array of nr_cpu_ids entries is
> +	 * allocated; each CPU indexes into it by its processor ID.
> +	 */
> +	if (is_realm_world()) {
> +		hv_hostcall_array = kcalloc(nr_cpu_ids,
> +					    sizeof(struct rsi_host_call),
> +					    GFP_KERNEL);

[Severity: High]
The RMM requires the IPA of the host call structure to be strictly 256-byte
aligned for SMC_RSI_HOST_CALL. Since standard slab allocators like kcalloc()
do not guarantee alignment beyond ARCH_KMALLOC_MINALIGN, could this result
in an unaligned physical address being passed to rsi_host_call() in
hv_set_vpreg()?

> +		if (!hv_hostcall_array)
> +			return -ENOMEM;

[Severity: Low]
This isn't a bug, but since hyperv_init() is an early_initcall executed
early in the boot process, is it necessary to handle this allocation failure
gracefully? Early boot memory allocations typically do not need complex
failure paths, as a failure at this stage implies the system cannot boot.

> +	}
> +
>  	/* Setup the guest ID */

[ ... ]

> @@ -125,6 +151,10 @@ static int __init hyperv_init(void)
>  
>  	hyperv_initialized = true;
>  	return 0;
> +
> +free_hostcall_mem:
> +	hv_hostcall_free();
> +	return ret;

[Severity: High]
If hyperv_init() fails here, hv_hostcall_array is freed and set to NULL.
Since the panic notifiers registered earlier in hv_common_init() are not
unregistered on this error path, will this cause a newly introduced NULL
pointer dereference during a later panic?

When the leaked notifier invokes hyperv_report_panic(), it calls
hv_set_vpreg(), which unconditionally accesses the array:

hv_set_vpreg() {
    ...
    hostcall = &hv_hostcall_array[smp_processor_id()];
    memset(hostcall, 0, sizeof(*hostcall));
    ...
}

>  }

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260625173500.1995481-1-kameroncarr@linux.microsoft.com?part=3

Re: [PATCH v2 5/6] arm64: hyperv: Route hypercalls through RSI host call in CCA Realms

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [Critical] Missing Unprotected IPA Translation
- [High] Alignment Constraint Violation / Boot Failure
- [High] Missing NULL Pointer Check / NULL Dereference
--

commit a71c2edcad24708c7ea03f518e33fcef346f68d6
Author: Kameron Carr <kameroncarr@linux.microsoft.com>

arm64: hyperv: Route hypercalls through RSI host call in CCA Realms
    
Modify the five hypercall wrapper functions to check is_realm_world()
and use the per-CPU rsi_host_call structure when inside a Realm.

> diff --git a/arch/arm64/hyperv/hv_core.c b/arch/arm64/hyperv/hv_core.c
> index e33a9e3c366a1..77cba08fca132 100644
> --- a/arch/arm64/hyperv/hv_core.c
> +++ b/arch/arm64/hyperv/hv_core.c
> @@ -13,9 +13,41 @@

[ ... ]

> +static u64 hv_do_rsi_hypercall(u64 control, u64 input1, u64 input2)
> +{
> +	struct rsi_host_call *hostcall;
> +	unsigned long flags;
> +	u64 ret;
> +
> +	if (!hv_hostcall_array)
> +		return HV_STATUS_INVALID_HYPERCALL_INPUT;
> +
> +	local_irq_save(flags);
> +	hostcall = &hv_hostcall_array[smp_processor_id()];
> +	memset(hostcall, 0, sizeof(*hostcall));
> +	hostcall->gprs[0] = HV_FUNC_ID;
> +	hostcall->gprs[1] = control;
> +	hostcall->gprs[2] = input1;
> +	hostcall->gprs[3] = input2;
> +
> +	if (rsi_host_call(virt_to_phys(hostcall)) == RSI_SUCCESS)

[Severity: High]
Does this allocation guarantee the 256-byte alignment required by the Arm CCA
RMM specification for the hostcall structure IPA?

If hv_hostcall_array is allocated with kcalloc(), which does not guarantee
type alignment, SLUB debugging or KASAN redzones could shift the object
offset.

Will calling rsi_host_call() with a misaligned pointer cause the RMM to
reject the command with RSI_ERROR_INPUT, ultimately triggering a fatal
BUG_ON(!hv_result_success(status)) in the wrapper?

> +		ret = hostcall->gprs[0];
> +	else
> +		ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
> +
> +	local_irq_restore(flags);
> +	return ret;
> +}

[ ... ]

> @@ -29,8 +61,11 @@ u64 hv_do_hypercall(u64 control, void *input, void *output)
>  	input_address = input ? virt_to_phys(input) : 0;
>  	output_address = output ? virt_to_phys(output) : 0;
>  
> -	arm_smccc_1_1_hvc(HV_FUNC_ID, control,
> -			  input_address, output_address, &res);
> +	if (is_realm_world())
> +		return hv_do_rsi_hypercall(control, input_address, output_address);

[Severity: Critical]
Will this translate the virtual address into a protected IPA without applying
the PROT_NS_SHARED bit required for host access?

In an Arm CCA Realm, memory shared with the host must be accessed via the
unprotected IPA space. The virt_to_phys() call only calculates the canonical
protected IPA.

When the untrusted host attempts to read or write the hypercall buffer using
these protected IPAs, won't the RMM block the access and generate a stage-2
fault?

> +
> +	arm_smccc_1_1_hvc(HV_FUNC_ID, control, input_address,
> +			  output_address, &res);
>  	return res.a0;
>  }

[ ... ]

> @@ -76,24 +117,44 @@ EXPORT_SYMBOL_GPL(hv_do_fast_hypercall16);
>  void hv_set_vpreg(u32 msr, u64 value)
>  {
>  	struct arm_smccc_res res;
> +	struct rsi_host_call *hostcall;
> +	unsigned long flags;
> +	u64 status;
>  
> +	if (is_realm_world()) {
> +		local_irq_save(flags);
> +		hostcall = &hv_hostcall_array[smp_processor_id()];
> +		memset(hostcall, 0, sizeof(*hostcall));

[Severity: High]
What happens if this is called early during a kernel panic before
hv_hostcall_array is initialized?

If an early kernel panic occurs or allocation fails, the crash handler
hyperv_report_panic() will invoke hv_set_vpreg(). Because this lacks the NULL
check present in hv_do_rsi_hypercall(), calculating the offset from NULL and
passing it to memset() might cause a double fault.

Could this prevent the panic from being reported to the hypervisor and
hang the system?

> +		hostcall->gprs[0] = HV_FUNC_ID;
> +		hostcall->gprs[1] = HVCALL_SET_VP_REGISTERS |

[ ... ]

> @@ -108,29 +169,55 @@ void hv_get_vpreg_128(u32 msr, struct hv_get_vp_registers_output *result)
>  {
>  	struct arm_smccc_1_2_regs args;
>  	struct arm_smccc_1_2_regs res;
> +	struct rsi_host_call *hostcall;
> +	unsigned long flags;
> +	u64 status;
>  
> +	if (is_realm_world()) {
> +		local_irq_save(flags);
> +		hostcall = &hv_hostcall_array[smp_processor_id()];
> +		memset(hostcall, 0, sizeof(*hostcall));

[Severity: High]
Similar to hv_set_vpreg(), does this need a check for hv_hostcall_array
being NULL to avoid a NULL pointer dereference if invoked before the array
is properly allocated?

>  
> -	/*
> -	 * Use the SMCCC 1.2 interface because the results are in registers
> -	 * beyond X0-X3.
> -	 */
> -	arm_smccc_1_2_hvc(&args, &res);
> +		hostcall->gprs[0] = HV_FUNC_ID;
> +		hostcall->gprs[1] = HVCALL_GET_VP_REGISTERS |

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260625173500.1995481-1-kameroncarr@linux.microsoft.com?part=5

Re: [PATCH v2 4/6] Drivers: hv: Mark shared memory as decrypted for CCA Realms

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Using `kmalloc()` to allocate hypercall input/output pages violates the strict page-alignment requirements of `set_memory_decrypted()`, causing silent failures on ARM64 and exposing slab metadata to the untrusted host on x86.
--

commit 02dd1b4271844f489855c82e06efdec7e95897e3
Author: Kameron Carr <kameroncarr@linux.microsoft.com>

Drivers: hv: Mark shared memory as decrypted for CCA Realms

This commit extends the confidential VM shared memory decryption handling
for hypercall input/output pages to support Arm CCA Realm guests. It also
updates the memory allocation to round up to the nearest page size to satisfy
decryption requirements.

> diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
> index 6b67ac6167891..17048a0a18729 100644
> --- a/drivers/hv/hv_common.c
> +++ b/drivers/hv/hv_common.c

[ ... ]

> @@ -489,7 +490,7 @@ int hv_common_cpu_init(unsigned int cpu)
>  	 * online and then taken offline
>  	 */
>  	if (!*inputarg) {
> -		mem = kmalloc_array(pgcount, HV_HYP_PAGE_SIZE, flags);
> +		mem = kmalloc(alloc_size, flags);
>  		if (!mem)
>  			return -ENOMEM;
>  
> @@ -499,14 +500,16 @@ int hv_common_cpu_init(unsigned int cpu)
>  		}
>  
>  		if (!ms_hyperv.paravisor_present &&
> -		    (hv_isolation_type_snp() || hv_isolation_type_tdx())) {
> -			ret = set_memory_decrypted((unsigned long)mem, pgcount);
> +		    (hv_isolation_type_snp() || hv_isolation_type_tdx() ||
> +		     hv_isolation_type_cca())) {
> +			ret = set_memory_decrypted((unsigned long)kasan_reset_tag(mem),
> +				alloc_size >> PAGE_SHIFT);

[Severity: High]
This is a pre-existing issue, but does using kmalloc() here guarantee the
required page alignment for set_memory_decrypted()?

When slub debugging (like redzoning) is enabled, kmalloc() can return an
unaligned address due to prepended metadata.

On arm64, set_memory_decrypted() requires a page-aligned address. If
given an unaligned address, it warns and returns 0 without decrypting.
This leaves the hypercall pages encrypted, which breaks guest-hypervisor
communication for CCA Realms.

On x86, set_memory_decrypted() masks the address to the page boundary.
Because this memory is from a slab cache, decrypting the entire underlying
physical page could expose other unrelated kernel slab objects on the same
page to the untrusted hypervisor.

>  			if (ret) {
>  				/* It may be unsafe to free 'mem' */
>  				return ret;
>  			}
>  
> -			memset(mem, 0x00, pgcount * HV_HYP_PAGE_SIZE);
> +			memset(mem, 0x00, alloc_size);
>  		}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260625173500.1995481-1-kameroncarr@linux.microsoft.com?part=4

Re: [PATCH v2 2/6] firmware: smccc: Detect hypervisor via RSI host call in CCA Realms

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] Initialization order bug causes `arm_smccc_hypervisor_has_uuid()` to incorrectly fall back to standard SMC during early boot in a CCA Realm.
--

commit 8e27a5d40fac36e0edcb6814624362e892694ac4
Author: Kameron Carr <kameroncarr@linux.microsoft.com>

firmware: smccc: Detect hypervisor via RSI host call in CCA Realms

This commit modifies arm_smccc_hypervisor_has_uuid() to check is_realm_world()
and use an RSI host call to query the hypervisor UUID inside a Realm. It adds
a file-static RSI host call buffer serialized by a spinlock for ARM64.

> diff --git a/drivers/firmware/smccc/smccc.c b/drivers/firmware/smccc/smccc.c
> index bdee057db2fd3..a876b7aa2dc99 100644
> --- a/drivers/firmware/smccc/smccc.c
> +++ b/drivers/firmware/smccc/smccc.c
[ ... ]
> @@ -67,12 +73,45 @@ s32 arm_smccc_get_soc_id_revision(void)
>  }
>  EXPORT_SYMBOL_GPL(arm_smccc_get_soc_id_revision);
>  
[ ... ]
>  bool arm_smccc_hypervisor_has_uuid(const uuid_t *hyp_uuid)
>  {
>  	struct arm_smccc_res res = {};
>  	uuid_t uuid;
>  
> -	arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, &res);
> +#ifdef CONFIG_ARM64
> +	if (is_realm_world())
> +		arm_smccc_realm_get_hypervisor_uuid(&res);
> +	else
> +#endif

[Severity: Medium]
Will this check evaluate to false during early boot, causing the detection to
incorrectly fall back to the standard SMC conduit?

Looking at setup_arch(), psci_dt_init() executes before arm64_rsi_init() is
called to set up the rsi_present static key used by is_realm_world():

setup_arch() {
    ...
    if (acpi_disabled)
        psci_dt_init();
    else
        psci_acpi_init();

    arm64_rsi_init();
    ...
}

Because psci_dt_init() calls psci_probe(), which calls kvm_init_hyp_services(),
this eventually reaches arm_smccc_hypervisor_has_uuid() before the static key
is initialized. 

Does this sequence cause a silent failure to detect the KVM hypervisor inside
an Arm CCA Realm?

> +		arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID,
> +				     &res);
> +
>  	if (res.a0 == SMCCC_RET_NOT_SUPPORTED)
>  		return false;

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260625173500.1995481-1-kameroncarr@linux.microsoft.com?part=2