[PATCH v1 00/11] KVM: arm64: Rework pKVM vCPU state synchronisation

[PATCH v1 00/11] KVM: arm64: Rework pKVM vCPU state synchronisation

[tabba]

Hi folks,

Building on Will's pKVM infrastructure series [1], this series reworks
how pKVM moves vCPU state between the host and EL2, and stops copying a
non-protected guest's state on every world switch.

EL2 gains proper primitives for the state it transfers: vCPU lookup
helpers, and VGIC flush/sync that reduces how much host state EL2
dereferences. The series also moves some preparatory code (such as sys
reg access and PSCI helpers) to shared headers and HYP, and implements
lazy copying of a non-protected guest's register state back to the host
until the host actually needs it, instead of on every exit.

This is the first of two series moving pKVM vCPU state management to
EL2. The follow-up completes the job for protected VMs: state
isolation, PSCI handling at EL2, and the resulting API behaviour.

The series is structured as follows:

  01-03:  Guard/scoped-resource support for hyp_spinlock and KVM locking
          (Marc asked for this to land as a prequel to a series that uses it).
  04-07:  Preparatory refactoring (MPIDR, sys reg access, vCPU reset, PSCI
          helpers) to shared headers and HYP.
  08:     Host and hypervisor vCPU lookup primitives.
  09-10:  VGIC: reduce EL2's exposure to host state, add flush/sync primitives.
  11:     Lazy state sync for non-protected guests.

Based on v7.1-rc7.

[1] https://lore.kernel.org/all/20260105154939.11041-1-will@kernel.org/

Cheers,
/fuad

Fuad Tabba (8):
  KVM: arm64: Add scoped resource management (guard) for hyp_spinlock
  KVM: arm64: Use guard(hyp_spinlock) in pKVM hypervisor code
  KVM: arm64: Use guard()/scoped_guard() in arm64 KVM EL1 code
  KVM: arm64: Extract MPIDR computation into a shared header
  KVM: arm64: Make vcpu_{read,write}_sys_reg available to HYP code
  KVM: arm64: Factor out reusable vCPU reset helpers
  KVM: arm64: Move PSCI helper functions to a shared header
  KVM: arm64: Implement lazy vCPU state sync for non-protected guests

Marc Zyngier (3):
  KVM: arm64: Add host and hypervisor vCPU lookup primitives
  KVM: arm64: Minimise EL2's exposure of host VGIC state during world
    switch
  KVM: arm64: Add primitives to flush/sync the VGIC state at EL2

 arch/arm64/include/asm/kvm_arm.h           |  12 +
 arch/arm64/include/asm/kvm_asm.h           |   1 +
 arch/arm64/include/asm/kvm_emulate.h       |  80 ++++++-
 arch/arm64/include/asm/kvm_host.h          |   2 +
 arch/arm64/kvm/arm.c                       |  21 +-
 arch/arm64/kvm/handle_exit.c               |  22 ++
 arch/arm64/kvm/hyp/include/nvhe/spinlock.h |   6 +
 arch/arm64/kvm/hyp/nvhe/ffa.c              | 154 +++++--------
 arch/arm64/kvm/hyp/nvhe/hyp-main.c         | 255 ++++++++++++++++++---
 arch/arm64/kvm/hyp/nvhe/mm.c               |  37 +--
 arch/arm64/kvm/hyp/nvhe/page_alloc.c       |  13 +-
 arch/arm64/kvm/hyp/nvhe/pkvm.c             |  86 +++----
 arch/arm64/kvm/mmu.c                       |  80 +++----
 arch/arm64/kvm/pkvm.c                      |  26 +--
 arch/arm64/kvm/psci.c                      |  47 +---
 arch/arm64/kvm/reset.c                     |  68 +-----
 arch/arm64/kvm/sys_regs.c                  |  14 +-
 arch/arm64/kvm/sys_regs.h                  |  19 ++
 include/kvm/arm_psci.h                     |  28 +++
 19 files changed, 562 insertions(+), 409 deletions(-)


base-commit: 4549871118cf616eecdd2d939f78e3b9e1dddc48
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 01/11] KVM: arm64: Add scoped resource management (guard) for hyp_spinlock

[tabba]

The nVHE hypervisor manages hyp_spinlock_t locks by hand across error
paths, where a missed unlock deadlocks the next CPU to take the lock.
Wire hyp_spinlock_t into <linux/cleanup.h> via DEFINE_LOCK_GUARD_1 so
callers can use guard(hyp_spinlock) and scoped_guard(hyp_spinlock),
letting later patches replace the manual lock/unlock pairs.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/kvm/hyp/include/nvhe/spinlock.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/spinlock.h b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h
index 7c7ea8c55405..63ba826d8e3d 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/spinlock.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h
@@ -13,6 +13,8 @@
 #ifndef __ARM64_KVM_NVHE_SPINLOCK_H__
 #define __ARM64_KVM_NVHE_SPINLOCK_H__
 
+#include <linux/cleanup.h>
+
 #include <asm/alternative.h>
 #include <asm/lse.h>
 #include <asm/rwonce.h>
@@ -98,6 +100,10 @@ static inline void hyp_spin_unlock(hyp_spinlock_t *lock)
 	: "memory");
 }
 
+DEFINE_LOCK_GUARD_1(hyp_spinlock, hyp_spinlock_t,
+		    hyp_spin_lock(_T->lock),
+		    hyp_spin_unlock(_T->lock))
+
 static inline bool hyp_spin_is_locked(hyp_spinlock_t *lock)
 {
 	hyp_spinlock_t lockval = READ_ONCE(*lock);
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 02/11] KVM: arm64: Use guard(hyp_spinlock) in pKVM hypervisor code

[tabba]

Convert the manual hyp_spin_lock()/hyp_spin_unlock() pairs in
arch/arm64/kvm/hyp/nvhe/{pkvm,mm,page_alloc,ffa}.c to
guard(hyp_spinlock) and scoped_guard(hyp_spinlock), dropping several
unlock-only goto labels in favour of direct returns.

hyp_fixblock_lock in mm.c is left as an explicit lock/unlock pair: it is
acquired in hyp_fixblock_map() and released in hyp_fixblock_unmap(), so
its critical section spans two functions and cannot be expressed as a
single lexical scope.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/kvm/hyp/nvhe/ffa.c        | 154 +++++++++++----------------
 arch/arm64/kvm/hyp/nvhe/mm.c         |  37 ++-----
 arch/arm64/kvm/hyp/nvhe/page_alloc.c |  13 +--
 arch/arm64/kvm/hyp/nvhe/pkvm.c       |  86 +++++----------
 4 files changed, 105 insertions(+), 185 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index 1af722771178..46cd4fa924be 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -313,17 +313,16 @@ static void do_ffa_rxtx_unmap(struct arm_smccc_1_2_regs *res,
 			      struct kvm_cpu_context *ctxt)
 {
 	DECLARE_REG(u32, id, ctxt, 1);
-	int ret = 0;
 
 	if (id != HOST_FFA_ID) {
-		ret = FFA_RET_INVALID_PARAMETERS;
-		goto out;
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
 	}
 
-	hyp_spin_lock(&host_buffers.lock);
+	guard(hyp_spinlock)(&host_buffers.lock);
 	if (!host_buffers.tx) {
-		ret = FFA_RET_INVALID_PARAMETERS;
-		goto out_unlock;
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
 	}
 
 	hyp_unpin_shared_mem(host_buffers.tx, host_buffers.tx + 1);
@@ -336,10 +335,7 @@ static void do_ffa_rxtx_unmap(struct arm_smccc_1_2_regs *res,
 
 	ffa_unmap_hyp_buffers();
 
-out_unlock:
-	hyp_spin_unlock(&host_buffers.lock);
-out:
-	ffa_to_smccc_res(res, ret);
+	ffa_to_smccc_res(res, 0);
 }
 
 static u32 __ffa_host_share_ranges(struct ffa_mem_region_addr_range *ranges,
@@ -418,18 +414,20 @@ static void do_ffa_mem_frag_tx(struct arm_smccc_1_2_regs *res,
 	DECLARE_REG(u32, fraglen, ctxt, 3);
 	DECLARE_REG(u32, endpoint_id, ctxt, 4);
 	struct ffa_mem_region_addr_range *buf;
-	int ret = FFA_RET_INVALID_PARAMETERS;
+	int ret;
 	u32 nr_ranges;
 
-	if (fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE)
-		goto out;
+	if (fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE ||
+	    fraglen % sizeof(*buf)) {
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
+	}
 
-	if (fraglen % sizeof(*buf))
-		goto out;
-
-	hyp_spin_lock(&host_buffers.lock);
-	if (!host_buffers.tx)
-		goto out_unlock;
+	guard(hyp_spinlock)(&host_buffers.lock);
+	if (!host_buffers.tx) {
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
+	}
 
 	buf = hyp_buffers.tx;
 	memcpy(buf, host_buffers.tx, fraglen);
@@ -444,19 +442,14 @@ static void do_ffa_mem_frag_tx(struct arm_smccc_1_2_regs *res,
 		 */
 		ffa_mem_reclaim(res, handle_lo, handle_hi, 0);
 		WARN_ON(res->a0 != FFA_SUCCESS);
-		goto out_unlock;
+		ffa_to_smccc_res(res, ret);
+		return;
 	}
 
 	ffa_mem_frag_tx(res, handle_lo, handle_hi, fraglen, endpoint_id);
 	if (res->a0 != FFA_SUCCESS && res->a0 != FFA_MEM_FRAG_RX)
 		WARN_ON(ffa_host_unshare_ranges(buf, nr_ranges));
 
-out_unlock:
-	hyp_spin_unlock(&host_buffers.lock);
-out:
-	if (ret)
-		ffa_to_smccc_res(res, ret);
-
 	/*
 	 * If for any reason this did not succeed, we're in trouble as we have
 	 * now lost the content of the previous fragments and we can't rollback
@@ -465,7 +458,6 @@ static void do_ffa_mem_frag_tx(struct arm_smccc_1_2_regs *res,
 	 * sharing/donating them again and may possibly lead to subsequent
 	 * failures, but this will not compromise confidentiality.
 	 */
-	return;
 }
 
 static void __do_ffa_mem_xfer(const u64 func_id,
@@ -480,29 +472,29 @@ static void __do_ffa_mem_xfer(const u64 func_id,
 	struct ffa_composite_mem_region *reg;
 	struct ffa_mem_region *buf;
 	u32 offset, nr_ranges, checked_offset;
-	int ret = 0;
+	int ret;
 
 	if (addr_mbz || npages_mbz || fraglen > len ||
 	    fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) {
-		ret = FFA_RET_INVALID_PARAMETERS;
-		goto out;
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
 	}
 
 	if (fraglen < sizeof(struct ffa_mem_region) +
 		      sizeof(struct ffa_mem_region_attributes)) {
-		ret = FFA_RET_INVALID_PARAMETERS;
-		goto out;
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
 	}
 
-	hyp_spin_lock(&host_buffers.lock);
+	guard(hyp_spinlock)(&host_buffers.lock);
 	if (!host_buffers.tx) {
-		ret = FFA_RET_INVALID_PARAMETERS;
-		goto out_unlock;
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
 	}
 
 	if (len > ffa_desc_buf.len) {
-		ret = FFA_RET_NO_MEMORY;
-		goto out_unlock;
+		ffa_to_smccc_res(res, FFA_RET_NO_MEMORY);
+		return;
 	}
 
 	buf = hyp_buffers.tx;
@@ -512,53 +504,41 @@ static void __do_ffa_mem_xfer(const u64 func_id,
 			ffa_mem_desc_offset(buf, 0, hyp_ffa_version);
 	offset = ep_mem_access->composite_off;
 	if (!offset || buf->ep_count != 1 || buf->sender_id != HOST_FFA_ID) {
-		ret = FFA_RET_INVALID_PARAMETERS;
-		goto out_unlock;
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
 	}
 
 	if (check_add_overflow(offset, sizeof(struct ffa_composite_mem_region), &checked_offset)) {
-		ret = FFA_RET_INVALID_PARAMETERS;
-		goto out_unlock;
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
 	}
 
 	if (fraglen < checked_offset) {
-		ret = FFA_RET_INVALID_PARAMETERS;
-		goto out_unlock;
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
 	}
 
 	reg = (void *)buf + offset;
 	nr_ranges = ((void *)buf + fraglen) - (void *)reg->constituents;
 	if (nr_ranges % sizeof(reg->constituents[0])) {
-		ret = FFA_RET_INVALID_PARAMETERS;
-		goto out_unlock;
+		ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+		return;
 	}
 
 	nr_ranges /= sizeof(reg->constituents[0]);
 	ret = ffa_host_share_ranges(reg->constituents, nr_ranges);
-	if (ret)
-		goto out_unlock;
+	if (ret) {
+		ffa_to_smccc_res(res, ret);
+		return;
+	}
 
 	ffa_mem_xfer(res, func_id, len, fraglen);
 	if (fraglen != len) {
-		if (res->a0 != FFA_MEM_FRAG_RX)
-			goto err_unshare;
-
-		if (res->a3 != fraglen)
-			goto err_unshare;
+		if (res->a0 != FFA_MEM_FRAG_RX || res->a3 != fraglen)
+			WARN_ON(ffa_host_unshare_ranges(reg->constituents, nr_ranges));
 	} else if (res->a0 != FFA_SUCCESS) {
-		goto err_unshare;
+		WARN_ON(ffa_host_unshare_ranges(reg->constituents, nr_ranges));
 	}
-
-out_unlock:
-	hyp_spin_unlock(&host_buffers.lock);
-out:
-	if (ret)
-		ffa_to_smccc_res(res, ret);
-	return;
-
-err_unshare:
-	WARN_ON(ffa_host_unshare_ranges(reg->constituents, nr_ranges));
-	goto out_unlock;
 }
 
 #define do_ffa_mem_xfer(fid, res, ctxt)				\
@@ -578,12 +558,11 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res,
 	struct ffa_composite_mem_region *reg;
 	u32 offset, len, fraglen, fragoff;
 	struct ffa_mem_region *buf;
-	int ret = 0;
 	u64 handle;
 
 	handle = PACK_HANDLE(handle_lo, handle_hi);
 
-	hyp_spin_lock(&host_buffers.lock);
+	guard(hyp_spinlock)(&host_buffers.lock);
 
 	buf = hyp_buffers.tx;
 	*buf = (struct ffa_mem_region) {
@@ -594,7 +573,7 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res,
 	ffa_retrieve_req(res, sizeof(*buf));
 	buf = hyp_buffers.rx;
 	if (res->a0 != FFA_MEM_RETRIEVE_RESP)
-		goto out_unlock;
+		return;
 
 	len = res->a1;
 	fraglen = res->a2;
@@ -609,15 +588,15 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res,
 	 */
 	if (WARN_ON(offset > len ||
 		    fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE)) {
-		ret = FFA_RET_ABORTED;
 		ffa_rx_release(res);
-		goto out_unlock;
+		ffa_to_smccc_res(res, FFA_RET_ABORTED);
+		return;
 	}
 
 	if (len > ffa_desc_buf.len) {
-		ret = FFA_RET_NO_MEMORY;
 		ffa_rx_release(res);
-		goto out_unlock;
+		ffa_to_smccc_res(res, FFA_RET_NO_MEMORY);
+		return;
 	}
 
 	buf = ffa_desc_buf.buf;
@@ -627,8 +606,8 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res,
 	for (fragoff = fraglen; fragoff < len; fragoff += fraglen) {
 		ffa_mem_frag_rx(res, handle_lo, handle_hi, fragoff);
 		if (res->a0 != FFA_MEM_FRAG_TX) {
-			ret = FFA_RET_INVALID_PARAMETERS;
-			goto out_unlock;
+			ffa_to_smccc_res(res, FFA_RET_INVALID_PARAMETERS);
+			return;
 		}
 
 		fraglen = res->a3;
@@ -638,17 +617,12 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res,
 
 	ffa_mem_reclaim(res, handle_lo, handle_hi, flags);
 	if (res->a0 != FFA_SUCCESS)
-		goto out_unlock;
+		return;
 
 	reg = (void *)buf + offset;
 	/* If the SPMD was happy, then we should be too. */
 	WARN_ON(ffa_host_unshare_ranges(reg->constituents,
 					reg->addr_range_cnt));
-out_unlock:
-	hyp_spin_unlock(&host_buffers.lock);
-
-	if (ret)
-		ffa_to_smccc_res(res, ret);
 }
 
 /*
@@ -774,13 +748,13 @@ static void do_ffa_version(struct arm_smccc_1_2_regs *res,
 		return;
 	}
 
-	hyp_spin_lock(&version_lock);
+	guard(hyp_spinlock)(&version_lock);
 	if (has_version_negotiated) {
 		if (FFA_MINOR_VERSION(ffa_req_version) < FFA_MINOR_VERSION(hyp_ffa_version))
 			res->a0 = FFA_RET_NOT_SUPPORTED;
 		else
 			res->a0 = hyp_ffa_version;
-		goto unlock;
+		return;
 	}
 
 	/*
@@ -793,7 +767,7 @@ static void do_ffa_version(struct arm_smccc_1_2_regs *res,
 			.a1 = ffa_req_version,
 		}, res);
 		if ((s32)res->a0 == FFA_RET_NOT_SUPPORTED)
-			goto unlock;
+			return;
 
 		hyp_ffa_version = ffa_req_version;
 	}
@@ -804,8 +778,6 @@ static void do_ffa_version(struct arm_smccc_1_2_regs *res,
 		smp_store_release(&has_version_negotiated, true);
 		res->a0 = hyp_ffa_version;
 	}
-unlock:
-	hyp_spin_unlock(&version_lock);
 }
 
 static void do_ffa_part_get(struct arm_smccc_1_2_regs *res,
@@ -818,10 +790,10 @@ static void do_ffa_part_get(struct arm_smccc_1_2_regs *res,
 	DECLARE_REG(u32, flags, ctxt, 5);
 	u32 count, partition_sz, copy_sz;
 
-	hyp_spin_lock(&host_buffers.lock);
+	guard(hyp_spinlock)(&host_buffers.lock);
 	if (!host_buffers.rx) {
 		ffa_to_smccc_res(res, FFA_RET_BUSY);
-		goto out_unlock;
+		return;
 	}
 
 	hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) {
@@ -834,16 +806,16 @@ static void do_ffa_part_get(struct arm_smccc_1_2_regs *res,
 	}, res);
 
 	if (res->a0 != FFA_SUCCESS)
-		goto out_unlock;
+		return;
 
 	count = res->a2;
 	if (!count)
-		goto out_unlock;
+		return;
 
 	if (hyp_ffa_version > FFA_VERSION_1_0) {
 		/* Get the number of partitions deployed in the system */
 		if (flags & 0x1)
-			goto out_unlock;
+			return;
 
 		partition_sz  = res->a3;
 	} else {
@@ -854,12 +826,10 @@ static void do_ffa_part_get(struct arm_smccc_1_2_regs *res,
 	copy_sz = partition_sz * count;
 	if (copy_sz > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) {
 		ffa_to_smccc_res(res, FFA_RET_ABORTED);
-		goto out_unlock;
+		return;
 	}
 
 	memcpy(host_buffers.rx, hyp_buffers.rx, copy_sz);
-out_unlock:
-	hyp_spin_unlock(&host_buffers.lock);
 }
 
 bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 3b0bee496bff..56c3eb4a2251 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -35,13 +35,8 @@ static DEFINE_PER_CPU(struct hyp_fixmap_slot, fixmap_slots);
 static int __pkvm_create_mappings(unsigned long start, unsigned long size,
 				  unsigned long phys, enum kvm_pgtable_prot prot)
 {
-	int err;
-
-	hyp_spin_lock(&pkvm_pgd_lock);
-	err = kvm_pgtable_hyp_map(&pkvm_pgtable, start, size, phys, prot);
-	hyp_spin_unlock(&pkvm_pgd_lock);
-
-	return err;
+	guard(hyp_spinlock)(&pkvm_pgd_lock);
+	return kvm_pgtable_hyp_map(&pkvm_pgtable, start, size, phys, prot);
 }
 
 static int __pkvm_alloc_private_va_range(unsigned long start, size_t size)
@@ -80,10 +75,9 @@ int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr)
 	unsigned long addr;
 	int ret;
 
-	hyp_spin_lock(&pkvm_pgd_lock);
+	guard(hyp_spinlock)(&pkvm_pgd_lock);
 	addr = __io_map_base;
 	ret = __pkvm_alloc_private_va_range(addr, size);
-	hyp_spin_unlock(&pkvm_pgd_lock);
 
 	*haddr = addr;
 
@@ -137,13 +131,8 @@ int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot
 
 int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
 {
-	int ret;
-
-	hyp_spin_lock(&pkvm_pgd_lock);
-	ret = pkvm_create_mappings_locked(from, to, prot);
-	hyp_spin_unlock(&pkvm_pgd_lock);
-
-	return ret;
+	guard(hyp_spinlock)(&pkvm_pgd_lock);
+	return pkvm_create_mappings_locked(from, to, prot);
 }
 
 int hyp_back_vmemmap(phys_addr_t back)
@@ -340,22 +329,17 @@ static int create_fixblock(void)
 	if (i >= hyp_memblock_nr)
 		return -EINVAL;
 
-	hyp_spin_lock(&pkvm_pgd_lock);
+	guard(hyp_spinlock)(&pkvm_pgd_lock);
 	addr = ALIGN(__io_map_base, PMD_SIZE);
 	ret = __pkvm_alloc_private_va_range(addr, PMD_SIZE);
 	if (ret)
-		goto unlock;
+		return ret;
 
 	ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr, PMD_SIZE, phys, PAGE_HYP);
 	if (ret)
-		goto unlock;
+		return ret;
 
-	ret = kvm_pgtable_walk(&pkvm_pgtable, addr, PMD_SIZE, &walker);
-
-unlock:
-	hyp_spin_unlock(&pkvm_pgd_lock);
-
-	return ret;
+	return kvm_pgtable_walk(&pkvm_pgtable, addr, PMD_SIZE, &walker);
 #else
 	return 0;
 #endif
@@ -437,7 +421,7 @@ int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr)
 	size_t size;
 	int ret;
 
-	hyp_spin_lock(&pkvm_pgd_lock);
+	guard(hyp_spinlock)(&pkvm_pgd_lock);
 
 	prev_base = __io_map_base;
 	/*
@@ -463,7 +447,6 @@ int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr)
 		if (ret)
 			__io_map_base = prev_base;
 	}
-	hyp_spin_unlock(&pkvm_pgd_lock);
 
 	*haddr = addr + size;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index a1eb27a1a747..f43d8ad507e9 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -167,18 +167,16 @@ void hyp_put_page(struct hyp_pool *pool, void *addr)
 {
 	struct hyp_page *p = hyp_virt_to_page(addr);
 
-	hyp_spin_lock(&pool->lock);
+	guard(hyp_spinlock)(&pool->lock);
 	__hyp_put_page(pool, p);
-	hyp_spin_unlock(&pool->lock);
 }
 
 void hyp_get_page(struct hyp_pool *pool, void *addr)
 {
 	struct hyp_page *p = hyp_virt_to_page(addr);
 
-	hyp_spin_lock(&pool->lock);
+	guard(hyp_spinlock)(&pool->lock);
 	hyp_page_ref_inc(p);
-	hyp_spin_unlock(&pool->lock);
 }
 
 void hyp_split_page(struct hyp_page *p)
@@ -200,22 +198,19 @@ void *hyp_alloc_pages(struct hyp_pool *pool, u8 order)
 	struct hyp_page *p;
 	u8 i = order;
 
-	hyp_spin_lock(&pool->lock);
+	guard(hyp_spinlock)(&pool->lock);
 
 	/* Look for a high-enough-order page */
 	while (i <= pool->max_order && list_empty(&pool->free_area[i]))
 		i++;
-	if (i > pool->max_order) {
-		hyp_spin_unlock(&pool->lock);
+	if (i > pool->max_order)
 		return NULL;
-	}
 
 	/* Extract it from the tree at the right order */
 	p = node_to_page(pool->free_area[i].next);
 	p = __hyp_extract_page(pool, p, order);
 
 	hyp_set_page_refcounted(p);
-	hyp_spin_unlock(&pool->lock);
 
 	return hyp_page_to_virt(p);
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index eb1c10120f9f..7d843afd8c0a 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -258,32 +258,27 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 	if (__this_cpu_read(loaded_hyp_vcpu))
 		return NULL;
 
-	hyp_spin_lock(&vm_table_lock);
+	guard(hyp_spinlock)(&vm_table_lock);
 	hyp_vm = get_vm_by_handle(handle);
 	if (!hyp_vm || hyp_vm->kvm.arch.pkvm.is_dying)
-		goto unlock;
+		return NULL;
 
 	if (hyp_vm->kvm.created_vcpus <= vcpu_idx)
-		goto unlock;
+		return NULL;
 
 	/* Pairs with smp_store_release() in register_hyp_vcpu(). */
 	hyp_vcpu = smp_load_acquire(&hyp_vm->vcpus[vcpu_idx]);
 	if (!hyp_vcpu)
-		goto unlock;
+		return NULL;
 
 	/* Ensure vcpu isn't loaded on more than one cpu simultaneously. */
-	if (unlikely(hyp_vcpu->loaded_hyp_vcpu)) {
-		hyp_vcpu = NULL;
-		goto unlock;
-	}
+	if (unlikely(hyp_vcpu->loaded_hyp_vcpu))
+		return NULL;
 
 	hyp_vcpu->loaded_hyp_vcpu = this_cpu_ptr(&loaded_hyp_vcpu);
 	hyp_page_ref_inc(hyp_virt_to_page(hyp_vm));
-unlock:
-	hyp_spin_unlock(&vm_table_lock);
 
-	if (hyp_vcpu)
-		__this_cpu_write(loaded_hyp_vcpu, hyp_vcpu);
+	__this_cpu_write(loaded_hyp_vcpu, hyp_vcpu);
 	return hyp_vcpu;
 }
 
@@ -291,11 +286,10 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
 	struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
 
-	hyp_spin_lock(&vm_table_lock);
+	guard(hyp_spinlock)(&vm_table_lock);
 	hyp_vcpu->loaded_hyp_vcpu = NULL;
 	__this_cpu_write(loaded_hyp_vcpu, NULL);
 	hyp_page_ref_dec(hyp_virt_to_page(hyp_vm));
-	hyp_spin_unlock(&vm_table_lock);
 }
 
 struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void)
@@ -308,20 +302,18 @@ struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle)
 {
 	struct pkvm_hyp_vm *hyp_vm;
 
-	hyp_spin_lock(&vm_table_lock);
+	guard(hyp_spinlock)(&vm_table_lock);
 	hyp_vm = get_vm_by_handle(handle);
 	if (hyp_vm)
 		hyp_page_ref_inc(hyp_virt_to_page(hyp_vm));
-	hyp_spin_unlock(&vm_table_lock);
 
 	return hyp_vm;
 }
 
 void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm)
 {
-	hyp_spin_lock(&vm_table_lock);
+	guard(hyp_spinlock)(&vm_table_lock);
 	hyp_page_ref_dec(hyp_virt_to_page(hyp_vm));
-	hyp_spin_unlock(&vm_table_lock);
 }
 
 struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle)
@@ -620,13 +612,8 @@ static int __insert_vm_table_entry(pkvm_handle_t handle,
 static int insert_vm_table_entry(pkvm_handle_t handle,
 				 struct pkvm_hyp_vm *hyp_vm)
 {
-	int ret;
-
-	hyp_spin_lock(&vm_table_lock);
-	ret = __insert_vm_table_entry(handle, hyp_vm);
-	hyp_spin_unlock(&vm_table_lock);
-
-	return ret;
+	guard(hyp_spinlock)(&vm_table_lock);
+	return __insert_vm_table_entry(handle, hyp_vm);
 }
 
 /*
@@ -701,9 +688,8 @@ int __pkvm_reserve_vm(void)
 {
 	int ret;
 
-	hyp_spin_lock(&vm_table_lock);
+	guard(hyp_spinlock)(&vm_table_lock);
 	ret = allocate_vm_table_entry();
-	hyp_spin_unlock(&vm_table_lock);
 
 	if (ret < 0)
 		return ret;
@@ -722,10 +708,9 @@ void __pkvm_unreserve_vm(pkvm_handle_t handle)
 	if (unlikely(!vm_table))
 		return;
 
-	hyp_spin_lock(&vm_table_lock);
+	guard(hyp_spinlock)(&vm_table_lock);
 	if (likely(idx < KVM_MAX_PVMS && vm_table[idx] == RESERVED_ENTRY))
 		remove_vm_table_entry(handle);
-	hyp_spin_unlock(&vm_table_lock);
 }
 
 #ifdef CONFIG_NVHE_EL2_DEBUG
@@ -785,9 +770,8 @@ struct pkvm_hyp_vcpu *init_selftest_vm(void *virt)
 
 void teardown_selftest_vm(void)
 {
-	hyp_spin_lock(&vm_table_lock);
+	guard(hyp_spinlock)(&vm_table_lock);
 	remove_vm_table_entry(selftest_vm.kvm.arch.pkvm.handle);
-	hyp_spin_unlock(&vm_table_lock);
 }
 #endif /* CONFIG_NVHE_EL2_DEBUG */
 
@@ -973,20 +957,15 @@ static struct pkvm_hyp_vm *get_pkvm_unref_hyp_vm_locked(pkvm_handle_t handle)
 int __pkvm_start_teardown_vm(pkvm_handle_t handle)
 {
 	struct pkvm_hyp_vm *hyp_vm;
-	int ret = 0;
 
-	hyp_spin_lock(&vm_table_lock);
+	guard(hyp_spinlock)(&vm_table_lock);
 	hyp_vm = get_pkvm_unref_hyp_vm_locked(handle);
-	if (!hyp_vm || hyp_vm->kvm.arch.pkvm.is_dying) {
-		ret = -EINVAL;
-		goto unlock;
-	}
+	if (!hyp_vm || hyp_vm->kvm.arch.pkvm.is_dying)
+		return -EINVAL;
 
 	hyp_vm->kvm.arch.pkvm.is_dying = true;
-unlock:
-	hyp_spin_unlock(&vm_table_lock);
 
-	return ret;
+	return 0;
 }
 
 int __pkvm_finalize_teardown_vm(pkvm_handle_t handle)
@@ -996,22 +975,19 @@ int __pkvm_finalize_teardown_vm(pkvm_handle_t handle)
 	struct kvm *host_kvm;
 	unsigned int idx;
 	size_t vm_size;
-	int err;
 
-	hyp_spin_lock(&vm_table_lock);
-	hyp_vm = get_pkvm_unref_hyp_vm_locked(handle);
-	if (!hyp_vm || !hyp_vm->kvm.arch.pkvm.is_dying) {
-		err = -EINVAL;
-		goto err_unlock;
+	scoped_guard(hyp_spinlock, &vm_table_lock) {
+		hyp_vm = get_pkvm_unref_hyp_vm_locked(handle);
+		if (!hyp_vm || !hyp_vm->kvm.arch.pkvm.is_dying)
+			return -EINVAL;
+
+		host_kvm = hyp_vm->host_kvm;
+
+		/* Ensure the VMID is clean before it can be reallocated */
+		__kvm_tlb_flush_vmid(&hyp_vm->kvm.arch.mmu);
+		remove_vm_table_entry(handle);
 	}
 
-	host_kvm = hyp_vm->host_kvm;
-
-	/* Ensure the VMID is clean before it can be reallocated */
-	__kvm_tlb_flush_vmid(&hyp_vm->kvm.arch.mmu);
-	remove_vm_table_entry(handle);
-	hyp_spin_unlock(&vm_table_lock);
-
 	/* Reclaim guest pages (including page-table pages) */
 	mc = &host_kvm->arch.pkvm.teardown_mc;
 	stage2_mc = &host_kvm->arch.pkvm.stage2_teardown_mc;
@@ -1042,10 +1018,6 @@ int __pkvm_finalize_teardown_vm(pkvm_handle_t handle)
 	teardown_donated_memory(mc, hyp_vm, vm_size);
 	hyp_unpin_shared_mem(host_kvm, host_kvm + 1);
 	return 0;
-
-err_unlock:
-	hyp_spin_unlock(&vm_table_lock);
-	return err;
 }
 
 static u64 __pkvm_memshare_page_req(struct kvm_vcpu *vcpu, u64 ipa)
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 03/11] KVM: arm64: Use guard()/scoped_guard() in arm64 KVM EL1 code

[tabba]

Convert the manual mutex_lock()/spin_lock() pairs in
arch/arm64/kvm/{pkvm,arm,mmu,reset,psci}.c to guard(mutex),
guard(spinlock) and scoped_guard(), dropping unlock-only goto labels in
favour of direct returns. Centralised cleanup gotos that still serve
other resources are preserved.

reset.c uses scoped_guard() rather than guard() so the lock covers only
the small read/update window inside kvm_reset_vcpu(), leaving the rest
of the function outside the critical section.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/kvm/arm.c   | 14 +++-----
 arch/arm64/kvm/mmu.c   | 80 +++++++++++++++---------------------------
 arch/arm64/kvm/pkvm.c  | 26 ++++++--------
 arch/arm64/kvm/psci.c  | 17 ++++-----
 arch/arm64/kvm/reset.c |  8 ++---
 5 files changed, 53 insertions(+), 92 deletions(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 9453321ef8c6..c9f36932c980 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -793,9 +793,7 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	int ret = 0;
-
-	spin_lock(&vcpu->arch.mp_state_lock);
+	guard(spinlock)(&vcpu->arch.mp_state_lock);
 
 	switch (mp_state->mp_state) {
 	case KVM_MP_STATE_RUNNABLE:
@@ -808,12 +806,10 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 		kvm_arm_vcpu_suspend(vcpu);
 		break;
 	default:
-		ret = -EINVAL;
+		return -EINVAL;
 	}
 
-	spin_unlock(&vcpu->arch.mp_state_lock);
-
-	return ret;
+	return 0;
 }
 
 /**
@@ -1726,15 +1722,13 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	/*
 	 * Handle the "start in power-off" case.
 	 */
-	spin_lock(&vcpu->arch.mp_state_lock);
+	guard(spinlock)(&vcpu->arch.mp_state_lock);
 
 	if (power_off)
 		__kvm_arm_vcpu_power_off(vcpu);
 	else
 		WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE);
 
-	spin_unlock(&vcpu->arch.mp_state_lock);
-
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 4da9281312eb..d18f4ce7ceae 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -391,13 +391,13 @@ static void stage2_flush_vm(struct kvm *kvm)
  */
 void __init free_hyp_pgds(void)
 {
-	mutex_lock(&kvm_hyp_pgd_mutex);
-	if (hyp_pgtable) {
-		kvm_pgtable_hyp_destroy(hyp_pgtable);
-		kfree(hyp_pgtable);
-		hyp_pgtable = NULL;
-	}
-	mutex_unlock(&kvm_hyp_pgd_mutex);
+	guard(mutex)(&kvm_hyp_pgd_mutex);
+	if (!hyp_pgtable)
+		return;
+
+	kvm_pgtable_hyp_destroy(hyp_pgtable);
+	kfree(hyp_pgtable);
+	hyp_pgtable = NULL;
 }
 
 static bool kvm_host_owns_hyp_mappings(void)
@@ -424,16 +424,11 @@ static bool kvm_host_owns_hyp_mappings(void)
 int __create_hyp_mappings(unsigned long start, unsigned long size,
 			  unsigned long phys, enum kvm_pgtable_prot prot)
 {
-	int err;
-
 	if (WARN_ON(!kvm_host_owns_hyp_mappings()))
 		return -EINVAL;
 
-	mutex_lock(&kvm_hyp_pgd_mutex);
-	err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
-	mutex_unlock(&kvm_hyp_pgd_mutex);
-
-	return err;
+	guard(mutex)(&kvm_hyp_pgd_mutex);
+	return kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
 }
 
 static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
@@ -481,56 +476,42 @@ static int share_pfn_hyp(u64 pfn)
 {
 	struct rb_node **node, *parent;
 	struct hyp_shared_pfn *this;
-	int ret = 0;
 
-	mutex_lock(&hyp_shared_pfns_lock);
+	guard(mutex)(&hyp_shared_pfns_lock);
 	this = find_shared_pfn(pfn, &node, &parent);
 	if (this) {
 		this->count++;
-		goto unlock;
+		return 0;
 	}
 
 	this = kzalloc_obj(*this);
-	if (!this) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	if (!this)
+		return -ENOMEM;
 
 	this->pfn = pfn;
 	this->count = 1;
 	rb_link_node(&this->node, parent, node);
 	rb_insert_color(&this->node, &hyp_shared_pfns);
-	ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn);
-unlock:
-	mutex_unlock(&hyp_shared_pfns_lock);
-
-	return ret;
+	return kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn);
 }
 
 static int unshare_pfn_hyp(u64 pfn)
 {
 	struct rb_node **node, *parent;
 	struct hyp_shared_pfn *this;
-	int ret = 0;
 
-	mutex_lock(&hyp_shared_pfns_lock);
+	guard(mutex)(&hyp_shared_pfns_lock);
 	this = find_shared_pfn(pfn, &node, &parent);
-	if (WARN_ON(!this)) {
-		ret = -ENOENT;
-		goto unlock;
-	}
+	if (WARN_ON(!this))
+		return -ENOENT;
 
 	this->count--;
 	if (this->count)
-		goto unlock;
+		return 0;
 
 	rb_erase(&this->node, &hyp_shared_pfns);
 	kfree(this);
-	ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn);
-unlock:
-	mutex_unlock(&hyp_shared_pfns_lock);
-
-	return ret;
+	return kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn);
 }
 
 int kvm_share_hyp(void *from, void *to)
@@ -655,7 +636,7 @@ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr)
 	unsigned long base;
 	int ret = 0;
 
-	mutex_lock(&kvm_hyp_pgd_mutex);
+	guard(mutex)(&kvm_hyp_pgd_mutex);
 
 	/*
 	 * This assumes that we have enough space below the idmap
@@ -670,8 +651,6 @@ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr)
 	base = io_map_base - size;
 	ret = __hyp_alloc_private_va_range(base);
 
-	mutex_unlock(&kvm_hyp_pgd_mutex);
-
 	if (!ret)
 		*haddr = base;
 
@@ -714,17 +693,16 @@ int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr)
 	size_t size;
 	int ret;
 
-	mutex_lock(&kvm_hyp_pgd_mutex);
-	/*
-	 * Efficient stack verification using the NVHE_STACK_SHIFT bit implies
-	 * an alignment of our allocation on the order of the size.
-	 */
-	size = NVHE_STACK_SIZE * 2;
-	base = ALIGN_DOWN(io_map_base - size, size);
+	scoped_guard(mutex, &kvm_hyp_pgd_mutex) {
+		/*
+		 * Efficient stack verification using the NVHE_STACK_SHIFT bit implies
+		 * an alignment of our allocation on the order of the size.
+		 */
+		size = NVHE_STACK_SIZE * 2;
+		base = ALIGN_DOWN(io_map_base - size, size);
 
-	ret = __hyp_alloc_private_va_range(base);
-
-	mutex_unlock(&kvm_hyp_pgd_mutex);
+		ret = __hyp_alloc_private_va_range(base);
+	}
 
 	if (ret) {
 		kvm_err("Cannot allocate hyp stack guard page\n");
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 053e4f733e4b..a39111b70f9f 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -190,39 +190,33 @@ bool pkvm_hyp_vm_is_created(struct kvm *kvm)
 
 int pkvm_create_hyp_vm(struct kvm *kvm)
 {
-	int ret = 0;
-
 	/*
 	 * Synchronise with kvm_arch_prepare_memory_region(), as we
 	 * prevent memslot modifications on a pVM that has been run.
 	 */
-	mutex_lock(&kvm->slots_lock);
-	mutex_lock(&kvm->arch.config_lock);
-	if (!pkvm_hyp_vm_is_created(kvm))
-		ret = __pkvm_create_hyp_vm(kvm);
-	mutex_unlock(&kvm->arch.config_lock);
-	mutex_unlock(&kvm->slots_lock);
+	guard(mutex)(&kvm->slots_lock);
+	guard(mutex)(&kvm->arch.config_lock);
 
-	return ret;
+	if (!pkvm_hyp_vm_is_created(kvm))
+		return __pkvm_create_hyp_vm(kvm);
+
+	return 0;
 }
 
 int pkvm_create_hyp_vcpu(struct kvm_vcpu *vcpu)
 {
-	int ret = 0;
+	guard(mutex)(&vcpu->kvm->arch.config_lock);
 
-	mutex_lock(&vcpu->kvm->arch.config_lock);
 	if (!vcpu_get_flag(vcpu, VCPU_PKVM_FINALIZED))
-		ret = __pkvm_create_hyp_vcpu(vcpu);
-	mutex_unlock(&vcpu->kvm->arch.config_lock);
+		return __pkvm_create_hyp_vcpu(vcpu);
 
-	return ret;
+	return 0;
 }
 
 void pkvm_destroy_hyp_vm(struct kvm *kvm)
 {
-	mutex_lock(&kvm->arch.config_lock);
+	guard(mutex)(&kvm->arch.config_lock);
 	__pkvm_destroy_hyp_vm(kvm);
-	mutex_unlock(&kvm->arch.config_lock);
 }
 
 int pkvm_init_host_vm(struct kvm *kvm, unsigned long type)
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index 3b5dbe9a0a0e..e1389c525e9d 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -62,7 +62,6 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	struct vcpu_reset_state *reset_state;
 	struct kvm *kvm = source_vcpu->kvm;
 	struct kvm_vcpu *vcpu = NULL;
-	int ret = PSCI_RET_SUCCESS;
 	unsigned long cpu_id;
 
 	cpu_id = smccc_get_arg1(source_vcpu);
@@ -78,14 +77,13 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	if (!vcpu)
 		return PSCI_RET_INVALID_PARAMS;
 
-	spin_lock(&vcpu->arch.mp_state_lock);
+	guard(spinlock)(&vcpu->arch.mp_state_lock);
+
 	if (!kvm_arm_vcpu_stopped(vcpu)) {
 		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
-			ret = PSCI_RET_ALREADY_ON;
+			return PSCI_RET_ALREADY_ON;
 		else
-			ret = PSCI_RET_INVALID_PARAMS;
-
-		goto out_unlock;
+			return PSCI_RET_INVALID_PARAMS;
 	}
 
 	reset_state = &vcpu->arch.reset_state;
@@ -113,9 +111,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE);
 	kvm_vcpu_wake_up(vcpu);
 
-out_unlock:
-	spin_unlock(&vcpu->arch.mp_state_lock);
-	return ret;
+	return PSCI_RET_SUCCESS;
 }
 
 static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
@@ -176,9 +172,8 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags)
 	 * re-initialized.
 	 */
 	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
-		spin_lock(&tmp->arch.mp_state_lock);
+		guard(spinlock)(&tmp->arch.mp_state_lock);
 		WRITE_ONCE(tmp->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED);
-		spin_unlock(&tmp->arch.mp_state_lock);
 	}
 	kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP);
 
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index b963fd975aac..60969d90bdd3 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -193,10 +193,10 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	bool loaded;
 	u32 pstate;
 
-	spin_lock(&vcpu->arch.mp_state_lock);
-	reset_state = vcpu->arch.reset_state;
-	vcpu->arch.reset_state.reset = false;
-	spin_unlock(&vcpu->arch.mp_state_lock);
+	scoped_guard(spinlock, &vcpu->arch.mp_state_lock) {
+		reset_state = vcpu->arch.reset_state;
+		vcpu->arch.reset_state.reset = false;
+	}
 
 	preempt_disable();
 	loaded = (vcpu->cpu != -1);
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 04/11] KVM: arm64: Extract MPIDR computation into a shared header

[tabba]

Extract the vCPU MPIDR computation embedded in reset_mpidr() into a
kvm_calculate_mpidr() inline in sys_regs.h, so it can be computed
without duplicating the logic. A follow-up series reuses it to reset
protected vCPUs at EL2.

No functional change intended.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/kvm/sys_regs.c | 14 +-------------
 arch/arm64/kvm/sys_regs.h | 19 +++++++++++++++++++
 2 files changed, 20 insertions(+), 13 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index fa5c93c7a135..869a4bac96d6 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -979,21 +979,9 @@ static u64 reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 
 static u64 reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	u64 mpidr;
+	u64 mpidr = kvm_calculate_mpidr(vcpu);
 
-	/*
-	 * Map the vcpu_id into the first three affinity level fields of
-	 * the MPIDR. We limit the number of VCPUs in level 0 due to a
-	 * limitation to 16 CPUs in that level in the ICC_SGIxR registers
-	 * of the GICv3 to be able to address each CPU directly when
-	 * sending IPIs.
-	 */
-	mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
-	mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
-	mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
-	mpidr |= (1ULL << 31);
 	vcpu_write_sys_reg(vcpu, mpidr, MPIDR_EL1);
-
 	return mpidr;
 }
 
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 2a983664220c..bd56a45abbf9 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -222,6 +222,25 @@ find_reg(const struct sys_reg_params *params, const struct sys_reg_desc table[],
 	return __inline_bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg);
 }
 
+static inline u64 kvm_calculate_mpidr(const struct kvm_vcpu *vcpu)
+{
+	u64 mpidr;
+
+	/*
+	 * Map the vcpu_id into the first three affinity level fields of
+	 * the MPIDR. We limit the number of VCPUs in level 0 due to a
+	 * limitation to 16 CPUs in that level in the ICC_SGIxR registers
+	 * of the GICv3 to be able to address each CPU directly when
+	 * sending IPIs.
+	 */
+	mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
+	mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
+	mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
+	mpidr |= (1ULL << 31);
+
+	return mpidr;
+}
+
 const struct sys_reg_desc *get_reg_by_id(u64 id,
 					 const struct sys_reg_desc table[],
 					 unsigned int num);
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 05/11] KVM: arm64: Make vcpu_{read,write}_sys_reg available to HYP code

[tabba]

The vcpu_{read,write}_sys_reg() accessors are host-only, so helpers
built on them such as kvm_vcpu_set_be()/kvm_vcpu_is_be() cannot be
shared with hyp code. Add _vcpu_read_sys_reg()/_vcpu_write_sys_reg()
inlines in kvm_emulate.h that dispatch on is_nvhe_hyp_code() to the
host- or hyp-side accessor. A follow-up series uses this to share that
emulation code at EL2.

No functional change intended.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/include/asm/kvm_emulate.h | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5bf3d7e1d92c..aed9fc0b717b 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -506,6 +506,22 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 	return __vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
 }
 
+static inline u64 _vcpu_read_sys_reg(struct kvm_vcpu *vcpu, enum vcpu_sysreg reg)
+{
+	if (!is_nvhe_hyp_code())
+		return vcpu_read_sys_reg(vcpu, reg);
+
+	return __vcpu_sys_reg(vcpu, reg);
+}
+
+static inline void _vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, enum vcpu_sysreg reg)
+{
+	if (!is_nvhe_hyp_code())
+		vcpu_write_sys_reg(vcpu, val, reg);
+	else
+		__vcpu_assign_sys_reg(vcpu, reg, val);
+}
+
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu)) {
@@ -516,9 +532,9 @@ static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 
 		r = vcpu_has_nv(vcpu) ? SCTLR_EL2 : SCTLR_EL1;
 
-		sctlr = vcpu_read_sys_reg(vcpu, r);
+		sctlr = _vcpu_read_sys_reg(vcpu, r);
 		sctlr |= SCTLR_ELx_EE;
-		vcpu_write_sys_reg(vcpu, sctlr, r);
+		_vcpu_write_sys_reg(vcpu, sctlr, r);
 	}
 }
 
@@ -533,7 +549,7 @@ static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
 	r = is_hyp_ctxt(vcpu) ? SCTLR_EL2 : SCTLR_EL1;
 	bit = vcpu_mode_priv(vcpu) ? SCTLR_ELx_EE : SCTLR_EL1_E0E;
 
-	return vcpu_read_sys_reg(vcpu, r) & bit;
+	return _vcpu_read_sys_reg(vcpu, r) & bit;
 }
 
 static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 06/11] KVM: arm64: Factor out reusable vCPU reset helpers

[tabba]

Pull the reusable pieces out of kvm_reset_vcpu(): expose the reset
PSTATE values in kvm_arm.h, and split the core register reset and the
PSCI-driven reset into kvm_reset_vcpu_core() and kvm_reset_vcpu_psci().
A follow-up series reuses these to reset protected vCPUs at EL2.

No functional change intended.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/include/asm/kvm_arm.h     | 12 ++++++
 arch/arm64/include/asm/kvm_emulate.h | 58 +++++++++++++++++++++++++++
 arch/arm64/kvm/reset.c               | 60 ++--------------------------
 3 files changed, 73 insertions(+), 57 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 3f9233b5a130..aba4ec09acd2 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -348,4 +348,16 @@
 	{ PSR_AA32_MODE_UND,	"32-bit UND" },	\
 	{ PSR_AA32_MODE_SYS,	"32-bit SYS" }
 
+/*
+ * ARMv8 Reset Values
+ */
+#define VCPU_RESET_PSTATE_EL1	(PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \
+				 PSR_F_BIT | PSR_D_BIT)
+
+#define VCPU_RESET_PSTATE_EL2	(PSR_MODE_EL2h | PSR_A_BIT | PSR_I_BIT | \
+				 PSR_F_BIT | PSR_D_BIT)
+
+#define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
+				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)
+
 #endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index aed9fc0b717b..8436e71c402d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -704,4 +704,62 @@ static inline void vcpu_set_hcrx(struct kvm_vcpu *vcpu)
 			vcpu->arch.hcrx_el2 |= HCRX_EL2_EnASR;
 	}
 }
+
+/* Reset a vcpu's core registers. */
+static inline void kvm_reset_vcpu_core(struct kvm_vcpu *vcpu)
+{
+	u32 pstate;
+
+	if (vcpu_el1_is_32bit(vcpu)) {
+		pstate = VCPU_RESET_PSTATE_SVC;
+	} else if (vcpu_has_nv(vcpu)) {
+		pstate = VCPU_RESET_PSTATE_EL2;
+	} else {
+		pstate = VCPU_RESET_PSTATE_EL1;
+	}
+
+	/* Reset core registers */
+	memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
+	memset(&vcpu->arch.ctxt.fp_regs, 0, sizeof(vcpu->arch.ctxt.fp_regs));
+	vcpu->arch.ctxt.spsr_abt = 0;
+	vcpu->arch.ctxt.spsr_und = 0;
+	vcpu->arch.ctxt.spsr_irq = 0;
+	vcpu->arch.ctxt.spsr_fiq = 0;
+	vcpu_gp_regs(vcpu)->pstate = pstate;
+}
+
+/* PSCI reset handling for a vcpu. */
+static inline void kvm_reset_vcpu_psci(struct kvm_vcpu *vcpu,
+				       struct vcpu_reset_state *reset_state)
+{
+	unsigned long target_pc = reset_state->pc;
+
+	/* Gracefully handle Thumb2 entry point */
+	if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
+		target_pc &= ~1UL;
+		vcpu_set_thumb(vcpu);
+	}
+
+	/* Propagate caller endianness */
+	if (reset_state->be)
+		kvm_vcpu_set_be(vcpu);
+
+	*vcpu_pc(vcpu) = target_pc;
+
+	/*
+	 * We may come from a state where either a PC update was
+	 * pending (SMC call resulting in PC being increpented to
+	 * skip the SMC) or a pending exception. Make sure we get
+	 * rid of all that, as this cannot be valid out of reset.
+	 *
+	 * Note that clearing the exception mask also clears PC
+	 * updates, but that's an implementation detail, and we
+	 * really want to make it explicit.
+	 */
+	vcpu_clear_flag(vcpu, PENDING_EXCEPTION);
+	vcpu_clear_flag(vcpu, EXCEPT_MASK);
+	vcpu_clear_flag(vcpu, INCREMENT_PC);
+	vcpu_set_reg(vcpu, 0, reset_state->r0);
+}
+
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 60969d90bdd3..e22d0be9e57c 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -34,18 +34,6 @@
 static u32 __ro_after_init kvm_ipa_limit;
 unsigned int __ro_after_init kvm_host_sve_max_vl;
 
-/*
- * ARMv8 Reset Values
- */
-#define VCPU_RESET_PSTATE_EL1	(PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \
-				 PSR_F_BIT | PSR_D_BIT)
-
-#define VCPU_RESET_PSTATE_EL2	(PSR_MODE_EL2h | PSR_A_BIT | PSR_I_BIT | \
-				 PSR_F_BIT | PSR_D_BIT)
-
-#define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
-				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)
-
 unsigned int __ro_after_init kvm_sve_max_vl;
 
 int __init kvm_arm_init_sve(void)
@@ -191,7 +179,6 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_reset_state reset_state;
 	bool loaded;
-	u32 pstate;
 
 	scoped_guard(spinlock, &vcpu->arch.mp_state_lock) {
 		reset_state = vcpu->arch.reset_state;
@@ -210,21 +197,8 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		kvm_vcpu_reset_sve(vcpu);
 	}
 
-	if (vcpu_el1_is_32bit(vcpu))
-		pstate = VCPU_RESET_PSTATE_SVC;
-	else if (vcpu_has_nv(vcpu))
-		pstate = VCPU_RESET_PSTATE_EL2;
-	else
-		pstate = VCPU_RESET_PSTATE_EL1;
-
 	/* Reset core registers */
-	memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
-	memset(&vcpu->arch.ctxt.fp_regs, 0, sizeof(vcpu->arch.ctxt.fp_regs));
-	vcpu->arch.ctxt.spsr_abt = 0;
-	vcpu->arch.ctxt.spsr_und = 0;
-	vcpu->arch.ctxt.spsr_irq = 0;
-	vcpu->arch.ctxt.spsr_fiq = 0;
-	vcpu_gp_regs(vcpu)->pstate = pstate;
+	kvm_reset_vcpu_core(vcpu);
 
 	/* Reset system registers */
 	kvm_reset_sys_regs(vcpu);
@@ -233,36 +207,8 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	 * Additional reset state handling that PSCI may have imposed on us.
 	 * Must be done after all the sys_reg reset.
 	 */
-	if (reset_state.reset) {
-		unsigned long target_pc = reset_state.pc;
-
-		/* Gracefully handle Thumb2 entry point */
-		if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
-			target_pc &= ~1UL;
-			vcpu_set_thumb(vcpu);
-		}
-
-		/* Propagate caller endianness */
-		if (reset_state.be)
-			kvm_vcpu_set_be(vcpu);
-
-		*vcpu_pc(vcpu) = target_pc;
-
-		/*
-		 * We may come from a state where either a PC update was
-		 * pending (SMC call resulting in PC being increpented to
-		 * skip the SMC) or a pending exception. Make sure we get
-		 * rid of all that, as this cannot be valid out of reset.
-		 *
-		 * Note that clearing the exception mask also clears PC
-		 * updates, but that's an implementation detail, and we
-		 * really want to make it explicit.
-		 */
-		vcpu_clear_flag(vcpu, PENDING_EXCEPTION);
-		vcpu_clear_flag(vcpu, EXCEPT_MASK);
-		vcpu_clear_flag(vcpu, INCREMENT_PC);
-		vcpu_set_reg(vcpu, 0, reset_state.r0);
-	}
+	if (reset_state.reset)
+		kvm_reset_vcpu_psci(vcpu, &reset_state);
 
 	/* Reset timer */
 	kvm_timer_vcpu_reset(vcpu);
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 07/11] KVM: arm64: Move PSCI helper functions to a shared header

[tabba]

Move kvm_psci_valid_affinity() and kvm_psci_narrow_to_32bit() from
psci.c to include/kvm/arm_psci.h, and move psci_affinity_mask() there
too, renaming it kvm_psci_affinity_mask() now that it is no longer
file-local. A follow-up series handles some protected-guest PSCI calls
at EL2 using these helpers.

No functional change intended.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/kvm/psci.c  | 30 +-----------------------------
 include/kvm/arm_psci.h | 28 ++++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index e1389c525e9d..228e5040c379 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -21,16 +21,6 @@
  * as described in ARM document number ARM DEN 0022A.
  */
 
-#define AFFINITY_MASK(level)	~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
-
-static unsigned long psci_affinity_mask(unsigned long affinity_level)
-{
-	if (affinity_level <= 3)
-		return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level);
-
-	return 0;
-}
-
 static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
 {
 	/*
@@ -51,12 +41,6 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
 	return PSCI_RET_SUCCESS;
 }
 
-static inline bool kvm_psci_valid_affinity(struct kvm_vcpu *vcpu,
-					   unsigned long affinity)
-{
-	return !(affinity & ~MPIDR_HWID_BITMASK);
-}
-
 static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
 	struct vcpu_reset_state *reset_state;
@@ -131,7 +115,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 		return PSCI_RET_INVALID_PARAMS;
 
 	/* Determine target affinity mask */
-	target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
+	target_affinity_mask = kvm_psci_affinity_mask(lowest_affinity_level);
 	if (!target_affinity_mask)
 		return PSCI_RET_INVALID_PARAMS;
 
@@ -215,18 +199,6 @@ static void kvm_psci_system_suspend(struct kvm_vcpu *vcpu)
 	run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
 }
 
-static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu)
-{
-	int i;
-
-	/*
-	 * Zero the input registers' upper 32 bits. They will be fully
-	 * zeroed on exit, so we're fine changing them in place.
-	 */
-	for (i = 1; i < 4; i++)
-		vcpu_set_reg(vcpu, i, lower_32_bits(vcpu_get_reg(vcpu, i)));
-}
-
 static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn)
 {
 	/*
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index cbaec804eb83..f12b74a4b176 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -38,6 +38,34 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu)
 	return KVM_ARM_PSCI_0_1;
 }
 
+/* Narrow the PSCI register arguments (r1 to r3) to 32 bits. */
+static inline void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu)
+{
+	int i;
+
+	/*
+	 * Zero the input registers' upper 32 bits. They will be fully
+	 * zeroed on exit, so we're fine changing them in place.
+	 */
+	for (i = 1; i < 4; i++)
+		vcpu_set_reg(vcpu, i, lower_32_bits(vcpu_get_reg(vcpu, i)));
+}
+
+static inline bool kvm_psci_valid_affinity(struct kvm_vcpu *vcpu,
+					   unsigned long affinity)
+{
+	return !(affinity & ~MPIDR_HWID_BITMASK);
+}
+
+
+static inline unsigned long kvm_psci_affinity_mask(unsigned long affinity_level)
+{
+	if (affinity_level <= 3)
+		return MPIDR_HWID_BITMASK &
+			~((0x1UL << (affinity_level * MPIDR_LEVEL_BITS)) - 1);
+
+	return 0;
+}
 
 int kvm_psci_call(struct kvm_vcpu *vcpu);
 
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 08/11] KVM: arm64: Add host and hypervisor vCPU lookup primitives

[tabba]

From: Marc Zyngier <maz@kernel.org>

The nVHE hypervisor repeatedly resolves a host vCPU into the EL2
address space and validates that the loaded hyp vCPU matches it, with
that logic open-coded in each handler.

Add __get_host_hyp_vcpus() and the get_host_hyp_vcpus() macro, which
translate the host vCPU into the hypervisor's address space and, when
pKVM is enabled, also return the loaded hyp vCPU if it matches. If pKVM
is enabled but the loaded hyp vCPU does not correspond to the requested
host vCPU, both the host and hyp vCPU are returned as NULL. Convert
handle___kvm_vcpu_run() to use it.

No functional change intended.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Co-developed-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 52 ++++++++++++++++++++++--------
 1 file changed, 38 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 06db299c37a8..420fb19a6476 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -195,14 +195,45 @@ static void handle___pkvm_vcpu_put(struct kvm_cpu_context *host_ctxt)
 		pkvm_put_hyp_vcpu(hyp_vcpu);
 }
 
-static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
+static struct kvm_vcpu *__get_host_hyp_vcpus(struct kvm_vcpu *arg,
+					     struct pkvm_hyp_vcpu **hyp_vcpup)
 {
-	DECLARE_REG(struct kvm_vcpu *, host_vcpu, host_ctxt, 1);
-	int ret;
+	struct kvm_vcpu *host_vcpu = kern_hyp_va(arg);
+	struct pkvm_hyp_vcpu *hyp_vcpu = NULL;
 
 	if (unlikely(is_protected_kvm_enabled())) {
-		struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+		hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
 
+		if (!hyp_vcpu || hyp_vcpu->host_vcpu != host_vcpu) {
+			hyp_vcpu = NULL;
+			host_vcpu = NULL;
+		}
+	}
+
+	*hyp_vcpup = hyp_vcpu;
+	return host_vcpu;
+}
+
+#define get_host_hyp_vcpus(ctxt, regnr, hyp_vcpup)			\
+	({								\
+		DECLARE_REG(struct kvm_vcpu *, __vcpu, ctxt, regnr);	\
+		__get_host_hyp_vcpus(__vcpu, hyp_vcpup);		\
+	})
+
+static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
+{
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	struct kvm_vcpu *host_vcpu;
+	int ret;
+
+	host_vcpu = get_host_hyp_vcpus(host_ctxt, 1, &hyp_vcpu);
+
+	if (!host_vcpu) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (unlikely(hyp_vcpu)) {
 		/*
 		 * KVM (and pKVM) doesn't support SME guests for now, and
 		 * ensures that SME features aren't enabled in pstate when
@@ -214,23 +245,16 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 			goto out;
 		}
 
-		if (!hyp_vcpu) {
-			ret = -EINVAL;
-			goto out;
-		}
-
 		flush_hyp_vcpu(hyp_vcpu);
 
 		ret = __kvm_vcpu_run(&hyp_vcpu->vcpu);
 
 		sync_hyp_vcpu(hyp_vcpu);
 	} else {
-		struct kvm_vcpu *vcpu = kern_hyp_va(host_vcpu);
-
 		/* The host is fully trusted, run its vCPU directly. */
-		fpsimd_lazy_switch_to_guest(vcpu);
-		ret = __kvm_vcpu_run(vcpu);
-		fpsimd_lazy_switch_to_host(vcpu);
+		fpsimd_lazy_switch_to_guest(host_vcpu);
+		ret = __kvm_vcpu_run(host_vcpu);
+		fpsimd_lazy_switch_to_host(host_vcpu);
 	}
 out:
 	cpu_reg(host_ctxt, 1) =  ret;
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 09/11] KVM: arm64: Minimise EL2's exposure of host VGIC state during world switch

[tabba]

From: Marc Zyngier <maz@kernel.org>

The host passes a vgic_v3_cpu_if pointer to the __vgic_v3_save_aprs and
__vgic_v3_restore_vmcr_aprs hypercalls, which EL2 dereferences
wholesale. That exposes the host's full VGIC emulation state to the
hypervisor, against pKVM's isolation goals.

Recover the host vCPU from the supplied cpu_if via container_of() and
copy only vgic_vmcr and the active priority registers between EL2's
hyp-side state and the host vCPU, so EL2 no longer dereferences the
host's vgic_v3_cpu_if directly.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Co-developed-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 67 ++++++++++++++++++++++++++++--
 1 file changed, 63 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 420fb19a6476..2f165b6c7b07 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -7,6 +7,8 @@
 #include <hyp/adjust_pc.h>
 #include <hyp/switch.h>
 
+#include <linux/irqchip/arm-gic-v3.h>
+
 #include <asm/pgtable-types.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
@@ -220,6 +222,16 @@ static struct kvm_vcpu *__get_host_hyp_vcpus(struct kvm_vcpu *arg,
 		__get_host_hyp_vcpus(__vcpu, hyp_vcpup);		\
 	})
 
+#define get_host_hyp_vcpus_from_vgic_v3_cpu_if(ctxt, regnr, hyp_vcpup)		\
+	({									\
+		DECLARE_REG(struct vgic_v3_cpu_if *, cif, ctxt, regnr);\
+		struct kvm_vcpu *__vcpu = container_of(cif,			\
+						       struct kvm_vcpu,		\
+						       arch.vgic_cpu.vgic_v3);	\
+										\
+		__get_host_hyp_vcpus(__vcpu, hyp_vcpup);			\
+	})
+
 static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 {
 	struct pkvm_hyp_vcpu *hyp_vcpu;
@@ -489,16 +501,63 @@ static void handle___vgic_v3_init_lrs(struct kvm_cpu_context *host_ctxt)
 
 static void handle___vgic_v3_save_aprs(struct kvm_cpu_context *host_ctxt)
 {
-	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	struct kvm_vcpu *host_vcpu;
 
-	__vgic_v3_save_aprs(kern_hyp_va(cpu_if));
+	host_vcpu = get_host_hyp_vcpus_from_vgic_v3_cpu_if(host_ctxt, 1,
+							   &hyp_vcpu);
+	if (!host_vcpu)
+		return;
+
+	if (unlikely(hyp_vcpu)) {
+		struct vgic_v3_cpu_if *hyp_cpu_if, *host_cpu_if;
+		int i;
+
+		hyp_cpu_if = &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3;
+		__vgic_v3_save_aprs(hyp_cpu_if);
+
+		host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3;
+		host_cpu_if->vgic_vmcr = hyp_cpu_if->vgic_vmcr;
+		for (i = 0; i < ARRAY_SIZE(host_cpu_if->vgic_ap0r); i++) {
+			host_cpu_if->vgic_ap0r[i] = hyp_cpu_if->vgic_ap0r[i];
+			host_cpu_if->vgic_ap1r[i] = hyp_cpu_if->vgic_ap1r[i];
+		}
+	} else {
+		__vgic_v3_save_aprs(&host_vcpu->arch.vgic_cpu.vgic_v3);
+	}
 }
 
 static void handle___vgic_v3_restore_vmcr_aprs(struct kvm_cpu_context *host_ctxt)
 {
-	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	struct kvm_vcpu *host_vcpu;
 
-	__vgic_v3_restore_vmcr_aprs(kern_hyp_va(cpu_if));
+	host_vcpu = get_host_hyp_vcpus_from_vgic_v3_cpu_if(host_ctxt, 1,
+							   &hyp_vcpu);
+	if (!host_vcpu)
+		return;
+
+	if (unlikely(hyp_vcpu)) {
+		struct vgic_v3_cpu_if *hyp_cpu_if, *host_cpu_if;
+		int i;
+
+		hyp_cpu_if = &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3;
+		host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3;
+
+		hyp_cpu_if->vgic_vmcr = host_cpu_if->vgic_vmcr;
+		/* Should be a one-off */
+		hyp_cpu_if->vgic_sre = (ICC_SRE_EL1_DIB |
+					ICC_SRE_EL1_DFB |
+					ICC_SRE_EL1_SRE);
+		for (i = 0; i < ARRAY_SIZE(host_cpu_if->vgic_ap0r); i++) {
+			hyp_cpu_if->vgic_ap0r[i] = host_cpu_if->vgic_ap0r[i];
+			hyp_cpu_if->vgic_ap1r[i] = host_cpu_if->vgic_ap1r[i];
+		}
+
+		__vgic_v3_restore_vmcr_aprs(hyp_cpu_if);
+	} else {
+		__vgic_v3_restore_vmcr_aprs(&host_vcpu->arch.vgic_cpu.vgic_v3);
+	}
 }
 
 static void handle___pkvm_init(struct kvm_cpu_context *host_ctxt)
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 10/11] KVM: arm64: Add primitives to flush/sync the VGIC state at EL2

[tabba]

From: Marc Zyngier <maz@kernel.org>

pKVM performs its own world switch for protected VMs but has no
primitives to move the per-vCPU VGIC state between the host and
hypervisor vCPU contexts.

Add flush_hyp_vgic_state() and sync_hyp_vgic_state(). Flush copies
vgic_hcr, the in-use list registers and used_lrs from the host into the
hyp vCPU and pins vgic_sre to a fixed value; sync copies vgic_hcr,
vgic_vmcr and the in-use list registers back. The active priority
registers are handled separately by the save/restore-aprs path.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Co-developed-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 50 +++++++++++++++++++++++++-----
 1 file changed, 42 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 2f165b6c7b07..23e644c24a03 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -99,6 +99,46 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
 	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
 }
 
+static void flush_hyp_vgic_state(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+	struct vgic_v3_cpu_if *host_cpu_if, *hyp_cpu_if;
+	unsigned int used_lrs, max_lrs, i;
+
+	host_cpu_if	= &host_vcpu->arch.vgic_cpu.vgic_v3;
+	hyp_cpu_if	= &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3;
+
+	max_lrs		= (read_gicreg(ICH_VTR_EL2) & ICH_VTR_EL2_ListRegs) + 1;
+	used_lrs	= host_cpu_if->used_lrs;
+	used_lrs	= min(used_lrs, max_lrs);
+
+	hyp_cpu_if->vgic_hcr	= host_cpu_if->vgic_hcr;
+	/* Should be a one-off */
+	hyp_cpu_if->vgic_sre	= (ICC_SRE_EL1_DIB |
+				   ICC_SRE_EL1_DFB |
+				   ICC_SRE_EL1_SRE);
+	hyp_cpu_if->used_lrs	= used_lrs;
+
+	for (i = 0; i < used_lrs; i++)
+		hyp_cpu_if->vgic_lr[i] = host_cpu_if->vgic_lr[i];
+}
+
+static void sync_hyp_vgic_state(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+	struct vgic_v3_cpu_if *host_cpu_if, *hyp_cpu_if;
+	unsigned int i;
+
+	host_cpu_if	= &host_vcpu->arch.vgic_cpu.vgic_v3;
+	hyp_cpu_if	= &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3;
+
+	host_cpu_if->vgic_hcr = hyp_cpu_if->vgic_hcr;
+	host_cpu_if->vgic_vmcr = hyp_cpu_if->vgic_vmcr;
+
+	for (i = 0; i < hyp_cpu_if->used_lrs; i++)
+		host_cpu_if->vgic_lr[i] = hyp_cpu_if->vgic_lr[i];
+}
+
 static void flush_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
 	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
@@ -139,7 +179,7 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 
 	hyp_vcpu->vcpu.arch.vsesr_el2	= host_vcpu->arch.vsesr_el2;
 
-	hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3 = host_vcpu->arch.vgic_cpu.vgic_v3;
+	flush_hyp_vgic_state(hyp_vcpu);
 
 	hyp_vcpu->vcpu.arch.pid = host_vcpu->arch.pid;
 }
@@ -147,9 +187,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
 	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
-	struct vgic_v3_cpu_if *hyp_cpu_if = &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3;
-	struct vgic_v3_cpu_if *host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3;
-	unsigned int i;
 
 	fpsimd_sve_sync(&hyp_vcpu->vcpu);
 	sync_debug_state(hyp_vcpu);
@@ -162,10 +199,7 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 
 	host_vcpu->arch.iflags		= hyp_vcpu->vcpu.arch.iflags;
 
-	host_cpu_if->vgic_hcr		= hyp_cpu_if->vgic_hcr;
-	host_cpu_if->vgic_vmcr		= hyp_cpu_if->vgic_vmcr;
-	for (i = 0; i < hyp_cpu_if->used_lrs; ++i)
-		host_cpu_if->vgic_lr[i] = hyp_cpu_if->vgic_lr[i];
+	sync_hyp_vgic_state(hyp_vcpu);
 }
 
 static void handle___pkvm_vcpu_load(struct kvm_cpu_context *host_ctxt)
-- 
2.54.0.1136.gdb2ca164c4-goog

[PATCH v1 11/11] KVM: arm64: Implement lazy vCPU state sync for non-protected guests

[tabba]

pKVM copies a non-protected guest's register context between the host
and the hypervisor on every world switch, even when the host never
inspects it. Defer the copy: on entry, flush the host context into the
hyp vCPU only when the host marked it dirty (PKVM_HOST_STATE_DIRTY); on
exit, leave it in the hyp vCPU and copy it back only when the host needs
it, via a __pkvm_vcpu_sync_state hypercall on trap handling or at vcpu
put. A protected guest's context is copied as before, since lazy sync
only helps where the host is trusted to see the guest's registers.

The PC is the exception: it is copied back on every exit so the
kvm_exit tracepoint reports the guest's real exit PC rather than the
value left by the previous sync.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/include/asm/kvm_asm.h   |  1 +
 arch/arm64/include/asm/kvm_host.h  |  2 +
 arch/arm64/kvm/arm.c               |  7 +++
 arch/arm64/kvm/handle_exit.c       | 22 ++++++++
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 88 ++++++++++++++++++++++++++++--
 5 files changed, 115 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 043495f7fc78..6e1135b3ded4 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -113,6 +113,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_finalize_teardown_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load,
 	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put,
+	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_sync_state,
 	__KVM_HOST_SMCCC_FUNC___pkvm_tlb_flush_vmid,
 
 	MARKER(__KVM_HOST_SMCCC_FUNC_MAX)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index a49042bfa801..1ef660774adc 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1113,6 +1113,8 @@ struct kvm_vcpu_arch {
 /* SError pending for nested guest */
 #define NESTED_SERROR_PENDING	__vcpu_single_flag(sflags, BIT(8))
 
+/* pKVM host vcpu state is dirty, needs resync (nVHE-only) */
+#define PKVM_HOST_STATE_DIRTY	__vcpu_single_flag(iflags, BIT(4))
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
 #define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) +	\
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index c9f36932c980..a5c54e37778b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -734,6 +734,10 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	if (is_protected_kvm_enabled()) {
 		kvm_call_hyp(__vgic_v3_save_aprs, &vcpu->arch.vgic_cpu.vgic_v3);
 		kvm_call_hyp_nvhe(__pkvm_vcpu_put);
+
+		/* __pkvm_vcpu_put implies a sync of the state */
+		if (!kvm_vm_is_protected(vcpu->kvm))
+			vcpu_set_flag(vcpu, PKVM_HOST_STATE_DIRTY);
 	}
 
 	kvm_vcpu_put_debug(vcpu);
@@ -961,6 +965,9 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 		return ret;
 
 	if (is_protected_kvm_enabled()) {
+		/* Start with the vcpu in a dirty state */
+		if (!kvm_vm_is_protected(vcpu->kvm))
+			vcpu_set_flag(vcpu, PKVM_HOST_STATE_DIRTY);
 		ret = pkvm_create_hyp_vm(kvm);
 		if (ret)
 			return ret;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 54aedf93c78b..dccc3786548b 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -422,6 +422,21 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu)
 {
 	int handled;
 
+	/*
+	 * If we run a non-protected VM when protection is enabled
+	 * system-wide, resync the state from the hypervisor and mark
+	 * it as dirty on the host side if it wasn't dirty already
+	 * (which could happen if preemption has taken place).
+	 */
+	if (is_protected_kvm_enabled() && !kvm_vm_is_protected(vcpu->kvm)) {
+		preempt_disable();
+		if (!(vcpu_get_flag(vcpu, PKVM_HOST_STATE_DIRTY))) {
+			kvm_call_hyp_nvhe(__pkvm_vcpu_sync_state);
+			vcpu_set_flag(vcpu, PKVM_HOST_STATE_DIRTY);
+		}
+		preempt_enable();
+	}
+
 	/*
 	 * See ARM ARM B1.14.1: "Hyp traps on instructions
 	 * that fail their condition code check"
@@ -489,6 +504,13 @@ int handle_exit(struct kvm_vcpu *vcpu, int exception_index)
 /* For exit types that need handling before we can be preempted */
 void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index)
 {
+	/*
+	 * We just exited, so the state is clean from a hypervisor
+	 * perspective.
+	 */
+	if (is_protected_kvm_enabled())
+		vcpu_clear_flag(vcpu, PKVM_HOST_STATE_DIRTY);
+
 	if (ARM_SERROR_PENDING(exception_index)) {
 		if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN)) {
 			u64 disr = kvm_vcpu_get_disr(vcpu);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 23e644c24a03..02383b372258 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -139,6 +139,49 @@ static void sync_hyp_vgic_state(struct pkvm_hyp_vcpu *hyp_vcpu)
 		host_cpu_if->vgic_lr[i] = hyp_cpu_if->vgic_lr[i];
 }
 
+
+static void __copy_vcpu_state(const struct kvm_vcpu *from_vcpu,
+			      struct kvm_vcpu *to_vcpu)
+{
+	int i;
+
+	to_vcpu->arch.ctxt.regs		= from_vcpu->arch.ctxt.regs;
+	to_vcpu->arch.ctxt.spsr_abt	= from_vcpu->arch.ctxt.spsr_abt;
+	to_vcpu->arch.ctxt.spsr_und	= from_vcpu->arch.ctxt.spsr_und;
+	to_vcpu->arch.ctxt.spsr_irq	= from_vcpu->arch.ctxt.spsr_irq;
+	to_vcpu->arch.ctxt.spsr_fiq	= from_vcpu->arch.ctxt.spsr_fiq;
+	to_vcpu->arch.ctxt.fp_regs	= from_vcpu->arch.ctxt.fp_regs;
+
+	/*
+	 * Copy the sysregs, but don't mess with the timer state which
+	 * is directly handled by EL1 and is expected to be preserved.
+	 * enum vcpu_sysreg is sparse: VNCR-mapped registers take values
+	 * derived from their VNCR page offset, so the timer registers do
+	 * not form a contiguous numeric range and must be skipped by name.
+	 */
+	for (i = 1; i < NR_SYS_REGS; i++) {
+		switch (i) {
+		case CNTVOFF_EL2:
+		case CNTV_CVAL_EL0:
+		case CNTV_CTL_EL0:
+		case CNTP_CVAL_EL0:
+		case CNTP_CTL_EL0:
+			continue;
+		}
+		to_vcpu->arch.ctxt.sys_regs[i] = from_vcpu->arch.ctxt.sys_regs[i];
+	}
+}
+
+static void __sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	__copy_vcpu_state(&hyp_vcpu->vcpu, hyp_vcpu->host_vcpu);
+}
+
+static void __flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	__copy_vcpu_state(hyp_vcpu->host_vcpu, &hyp_vcpu->vcpu);
+}
+
 static void flush_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
 	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
@@ -168,7 +211,17 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	fpsimd_sve_flush();
 	flush_debug_state(hyp_vcpu);
 
-	hyp_vcpu->vcpu.arch.ctxt	= host_vcpu->arch.ctxt;
+	/*
+	 * If we deal with a non-protected guest and the state is potentially
+	 * dirty (from a host perspective), copy the state back into the hyp
+	 * vcpu.
+	 */
+	if (!pkvm_hyp_vcpu_is_protected(hyp_vcpu)) {
+		if (vcpu_get_flag(host_vcpu, PKVM_HOST_STATE_DIRTY))
+			__flush_hyp_vcpu(hyp_vcpu);
+	} else {
+		hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt;
+	}
 
 	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
 	hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE);
@@ -191,9 +244,11 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	fpsimd_sve_sync(&hyp_vcpu->vcpu);
 	sync_debug_state(hyp_vcpu);
 
-	host_vcpu->arch.ctxt		= hyp_vcpu->vcpu.arch.ctxt;
-
-	host_vcpu->arch.hcr_el2		= hyp_vcpu->vcpu.arch.hcr_el2;
+	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		host_vcpu->arch.ctxt = hyp_vcpu->vcpu.arch.ctxt;
+	else
+		/* Keep the PC current for the kvm_exit tracepoint (lazy ctxt sync). */
+		host_vcpu->arch.ctxt.regs.pc = hyp_vcpu->vcpu.arch.ctxt.regs.pc;
 
 	host_vcpu->arch.fault		= hyp_vcpu->vcpu.arch.fault;
 
@@ -227,8 +282,30 @@ static void handle___pkvm_vcpu_put(struct kvm_cpu_context *host_ctxt)
 {
 	struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
 
-	if (hyp_vcpu)
+	if (hyp_vcpu) {
+		struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+
+		if (!pkvm_hyp_vcpu_is_protected(hyp_vcpu) &&
+		    !vcpu_get_flag(host_vcpu, PKVM_HOST_STATE_DIRTY)) {
+			__sync_hyp_vcpu(hyp_vcpu);
+		}
+
 		pkvm_put_hyp_vcpu(hyp_vcpu);
+	}
+}
+
+static void handle___pkvm_vcpu_sync_state(struct kvm_cpu_context *host_ctxt)
+{
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+
+	if (!is_protected_kvm_enabled())
+		return;
+
+	hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+	if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		return;
+
+	__sync_hyp_vcpu(hyp_vcpu);
 }
 
 static struct kvm_vcpu *__get_host_hyp_vcpus(struct kvm_vcpu *arg,
@@ -859,6 +936,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_finalize_teardown_vm),
 	HANDLE_FUNC(__pkvm_vcpu_load),
 	HANDLE_FUNC(__pkvm_vcpu_put),
+	HANDLE_FUNC(__pkvm_vcpu_sync_state),
 	HANDLE_FUNC(__pkvm_tlb_flush_vmid),
 };
 
-- 
2.54.0.1136.gdb2ca164c4-goog