Merge tag 'kvmarm-fixes-7.2-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 7.2, take #2

- Move locking for kvm_io_bus_get_dev() into the caller, ensuring
  race-free checks that the returned object is of the correct type

- Fix initialisation of the page-table walk level when relaxing
  permissions

- Correctly update the XN attribute when relaxing permissions

- Fix the sign extension of loads from emulated MMIO regions

- Assorted collection of fixes for pKVM's FFA proxy, together with a
  couple of FFA driver adjustments

9 files changed, 331 insertions, 43 deletions

diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index 1af722771178..a327c2bbb6b6 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -352,7 +352,7 @@ static u32 __ffa_host_share_ranges(struct ffa_mem_region_addr_range *ranges,
 		u64 sz = (u64)range->pg_cnt * FFA_PAGE_SIZE;
 		u64 pfn = hyp_phys_to_pfn(range->address);
 
-		if (!PAGE_ALIGNED(sz))
+		if (!PAGE_ALIGNED(sz | range->address))
 			break;
 
 		if (__pkvm_host_share_ffa(pfn, sz / PAGE_SIZE))
@@ -372,7 +372,7 @@ static u32 __ffa_host_unshare_ranges(struct ffa_mem_region_addr_range *ranges,
 		u64 sz = (u64)range->pg_cnt * FFA_PAGE_SIZE;
 		u64 pfn = hyp_phys_to_pfn(range->address);
 
-		if (!PAGE_ALIGNED(sz))
+		if (!PAGE_ALIGNED(sz | range->address))
 			break;
 
 		if (__pkvm_host_unshare_ffa(pfn, sz / PAGE_SIZE))
@@ -476,11 +476,12 @@ static void __do_ffa_mem_xfer(const u64 func_id,
 	DECLARE_REG(u32, fraglen, ctxt, 2);
 	DECLARE_REG(u64, addr_mbz, ctxt, 3);
 	DECLARE_REG(u32, npages_mbz, ctxt, 4);
+	u32 offset, nr_ranges, checked_offset, em_mem_access_off;
 	struct ffa_mem_region_attributes *ep_mem_access;
 	struct ffa_composite_mem_region *reg;
 	struct ffa_mem_region *buf;
-	u32 offset, nr_ranges, checked_offset;
 	int ret = 0;
+	size_t mem_region_len = FFA_MEM_REGION_SZ(hyp_ffa_version);
 
 	if (addr_mbz || npages_mbz || fraglen > len ||
 	    fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) {
@@ -488,8 +489,7 @@ static void __do_ffa_mem_xfer(const u64 func_id,
 		goto out;
 	}
 
-	if (fraglen < sizeof(struct ffa_mem_region) +
-		      sizeof(struct ffa_mem_region_attributes)) {
+	if (fraglen < mem_region_len + ffa_emad_size_get(hyp_ffa_version)) {
 		ret = FFA_RET_INVALID_PARAMETERS;
 		goto out;
 	}
@@ -508,8 +508,13 @@ static void __do_ffa_mem_xfer(const u64 func_id,
 	buf = hyp_buffers.tx;
 	memcpy(buf, host_buffers.tx, fraglen);
 
-	ep_mem_access = (void *)buf +
-			ffa_mem_desc_offset(buf, 0, hyp_ffa_version);
+	em_mem_access_off = ffa_mem_desc_offset(buf, 0, hyp_ffa_version);
+	if ((u64)em_mem_access_off + ffa_emad_size_get(hyp_ffa_version) > fraglen) {
+		ret = FFA_RET_INVALID_PARAMETERS;
+		goto out_unlock;
+	}
+
+	ep_mem_access = (void *)buf + em_mem_access_off;
 	offset = ep_mem_access->composite_off;
 	if (!offset || buf->ep_count != 1 || buf->sender_id != HOST_FFA_ID) {
 		ret = FFA_RET_INVALID_PARAMETERS;
@@ -574,9 +579,9 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res,
 	DECLARE_REG(u32, handle_lo, ctxt, 1);
 	DECLARE_REG(u32, handle_hi, ctxt, 2);
 	DECLARE_REG(u32, flags, ctxt, 3);
+	u32 offset, len, fraglen, fragoff, em_mem_access_off;
 	struct ffa_mem_region_attributes *ep_mem_access;
 	struct ffa_composite_mem_region *reg;
-	u32 offset, len, fraglen, fragoff;
 	struct ffa_mem_region *buf;
 	int ret = 0;
 	u64 handle;
@@ -599,16 +604,22 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res,
 	len = res->a1;
 	fraglen = res->a2;
 
-	ep_mem_access = (void *)buf +
-			ffa_mem_desc_offset(buf, 0, hyp_ffa_version);
+	em_mem_access_off = ffa_mem_desc_offset(buf, 0, hyp_ffa_version);
+	if ((u64)em_mem_access_off + ffa_emad_size_get(hyp_ffa_version) > fraglen) {
+		ret = FFA_RET_INVALID_PARAMETERS;
+		ffa_rx_release(res);
+		goto out_unlock;
+	}
+
+	ep_mem_access = (void *)buf + em_mem_access_off;
 	offset = ep_mem_access->composite_off;
 	/*
 	 * We can trust the SPMD to get this right, but let's at least
 	 * check that we end up with something that doesn't look _completely_
 	 * bogus.
 	 */
-	if (WARN_ON(offset > len ||
-		    fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE)) {
+	if (offset + CONSTITUENTS_OFFSET(0) > len ||
+	    fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) {
 		ret = FFA_RET_ABORTED;
 		ffa_rx_release(res);
 		goto out_unlock;
@@ -636,11 +647,16 @@ static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res,
 		ffa_rx_release(res);
 	}
 
+	reg = (void *)buf + offset;
+	if (offset + CONSTITUENTS_OFFSET(reg->addr_range_cnt) > len) {
+		ret = FFA_RET_ABORTED;
+		goto out_unlock;
+	}
+
 	ffa_mem_reclaim(res, handle_lo, handle_hi, flags);
 	if (res->a0 != FFA_SUCCESS)
 		goto out_unlock;
 
-	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));
@@ -864,7 +880,7 @@ out_unlock:
 
 bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 {
-	struct arm_smccc_1_2_regs res;
+	struct arm_smccc_1_2_regs res = {0};
 
 	/*
 	 * There's no way we can tell what a non-standard SMC call might
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 91a7dfad6686..b74dd5ce1efd 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1370,16 +1370,19 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 	if (prot & KVM_PGTABLE_PROT_W)
 		set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W;
 
-	ret = stage2_set_xn_attr(prot, &xn);
-	if (ret)
-		return ret;
+	if (prot & KVM_PGTABLE_PROT_X) {
+		ret = stage2_set_xn_attr(prot, &xn);
+		if (ret)
+			return ret;
 
-	set |= xn & KVM_PTE_LEAF_ATTR_HI_S2_XN;
-	clr |= ~xn & KVM_PTE_LEAF_ATTR_HI_S2_XN;
+		set |= xn & KVM_PTE_LEAF_ATTR_HI_S2_XN;
+		clr |= ~xn & KVM_PTE_LEAF_ATTR_HI_S2_XN;
+	}
 
 	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, flags);
 	if (!ret || ret == -EAGAIN)
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level);
+		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr,
+			     (ret == -EAGAIN) ? TLBI_TTL_UNKNOWN : level);
 	return ret;
 }
 
diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c
index e2285ed8c91d..d1c3a352d5a2 100644
--- a/arch/arm64/kvm/mmio.c
+++ b/arch/arm64/kvm/mmio.c
@@ -126,6 +126,10 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu)
 		len = kvm_vcpu_dabt_get_as(vcpu);
 		data = kvm_mmio_read_buf(run->mmio.data, len);
 
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
+			       &data);
+		data = vcpu_data_host_to_guest(vcpu, data, len);
+
 		if (kvm_vcpu_dabt_issext(vcpu) &&
 		    len < sizeof(unsigned long)) {
 			mask = 1U << ((len * 8) - 1);
@@ -135,9 +139,6 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu)
 		if (!kvm_vcpu_dabt_issf(vcpu))
 			data = data & 0xffffffff;
 
-		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
-			       &data);
-		data = vcpu_data_host_to_guest(vcpu, data, len);
 		vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu), data);
 	}
 
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 4477f870c7b3..740b39875728 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -508,6 +508,8 @@ static struct vgic_its *__vgic_doorbell_to_its(struct kvm *kvm, gpa_t db)
 	struct kvm_io_device *kvm_io_dev;
 	struct vgic_io_device *iodev;
 
+	guard(srcu)(&kvm->srcu);
+
 	kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, db);
 	if (!kvm_io_dev)
 		return ERR_PTR(-EINVAL);
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 0f468362c288..7c1b747797b4 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -713,30 +713,39 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize,
 	struct ffa_composite_mem_region *composite;
 	struct ffa_mem_region_addr_range *constituents;
 	struct ffa_mem_region_attributes *ep_mem_access;
-	u32 idx, frag_len, length, buf_sz = 0, num_entries = sg_nents(args->sg);
+	u32 idx, frag_len, length, buf_sz = 0, num_entries = sg_nents(args->sg), ep_offset;
+	u32 emad_end, emad_size = ffa_emad_size_get(drv_info->version);
 
 	mem_region->tag = args->tag;
 	mem_region->flags = args->flags;
 	mem_region->sender_id = drv_info->vm_id;
 	mem_region->attributes = ffa_memory_attributes_get(func_id);
+
+	ffa_mem_region_additional_setup(drv_info->version, mem_region);
 	composite_offset = ffa_mem_desc_offset(buffer, args->nattrs,
 					       drv_info->version);
+	if (composite_offset + sizeof(*composite) > max_fragsize)
+		return -ENXIO;
 
 	for (idx = 0; idx < args->nattrs; idx++) {
-		ep_mem_access = buffer +
-			ffa_mem_desc_offset(buffer, idx, drv_info->version);
+		ep_offset = ffa_mem_desc_offset(buffer, idx, drv_info->version);
+		if (check_add_overflow(ep_offset, emad_size, &emad_end))
+			return -ENXIO;
+
+		if (emad_end > max_fragsize)
+			return -ENXIO;
+
+		ep_mem_access = buffer + ep_offset;
+		memset(ep_mem_access, 0, emad_size);
 		ep_mem_access->receiver = args->attrs[idx].receiver;
 		ep_mem_access->attrs = args->attrs[idx].attrs;
 		ep_mem_access->composite_off = composite_offset;
-		ep_mem_access->flag = 0;
-		ep_mem_access->reserved = 0;
 		ffa_emad_impdef_value_init(drv_info->version,
 					   ep_mem_access->impdef_val,
 					   args->attrs[idx].impdef_val);
 	}
 	mem_region->handle = 0;
 	mem_region->ep_count = args->nattrs;
-	ffa_mem_region_additional_setup(drv_info->version, mem_region);
 
 	composite = buffer + composite_offset;
 	composite->total_pg_cnt = ffa_get_num_pages_sg(args->sg);
@@ -769,7 +778,7 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize,
 			constituents = buffer;
 		}
 
-		if ((void *)constituents - buffer > max_fragsize) {
+		if ((void *)constituents + sizeof(*constituents) - buffer > max_fragsize) {
 			pr_err("Memory Region Fragment > Tx Buffer size\n");
 			return -EFAULT;
 		}
@@ -778,7 +787,7 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize,
 		constituents->pg_cnt = args->sg->length / FFA_PAGE_SIZE;
 		constituents->reserved = 0;
 		constituents++;
-		frag_len += sizeof(struct ffa_mem_region_addr_range);
+		frag_len += sizeof(*constituents);
 	} while ((args->sg = sg_next(args->sg)));
 
 	return ffa_transmit_fragment(func_id, addr, buf_sz, frag_len,
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 17eca3dfc59e..e71d83ee0aef 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -421,6 +421,13 @@ struct ffa_mem_region {
 #define FFA_EMAD_HAS_IMPDEF_FIELD(version)	((version) >= FFA_VERSION_1_2)
 #define FFA_MEM_REGION_HAS_EP_MEM_OFFSET(version) ((version) > FFA_VERSION_1_0)
 
+/* The layout changed from FFA_VERSION_1_0 and the region includes an
+ * ep_mem_offset.
+ */
+#define FFA_MEM_REGION_SZ(version)		(!FFA_MEM_REGION_HAS_EP_MEM_OFFSET((version)) ?\
+						 offsetof(struct ffa_mem_region, ep_mem_offset) :\
+						 sizeof(struct ffa_mem_region))
+
 static inline u32 ffa_emad_size_get(u32 ffa_version)
 {
 	u32 sz;
@@ -445,7 +452,7 @@ ffa_mem_desc_offset(struct ffa_mem_region *buf, int count, u32 ffa_version)
 	if (!FFA_MEM_REGION_HAS_EP_MEM_OFFSET(ffa_version))
 		offset += offsetof(struct ffa_mem_region, ep_mem_offset);
 	else
-		offset += sizeof(struct ffa_mem_region);
+		offset += buf->ep_mem_offset;
 
 	return offset;
 }
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index d28a057fa6c2..6fc34e9bf8e1 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -174,6 +174,7 @@ TEST_GEN_PROGS_arm64 += arm64/hello_el2
 TEST_GEN_PROGS_arm64 += arm64/host_sve
 TEST_GEN_PROGS_arm64 += arm64/hypercalls
 TEST_GEN_PROGS_arm64 += arm64/external_aborts
+TEST_GEN_PROGS_arm64 += arm64/mmio_sign_ext
 TEST_GEN_PROGS_arm64 += arm64/page_fault_test
 TEST_GEN_PROGS_arm64 += arm64/psci_test
 TEST_GEN_PROGS_arm64 += arm64/sea_to_user
diff --git a/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c b/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c
new file mode 100644
index 000000000000..25196f1e6322
--- /dev/null
+++ b/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c
@@ -0,0 +1,255 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * mmio_sign_ext - Test sign-extending MMIO load emulation (LDRSB/LDRSH/LDRSW)
+ *
+ * Copyright (c) 2026 Google LLC
+ * Author: Fuad Tabba <fuad.tabba@linux.dev>
+ */
+
+#include <asm/ptrace.h>
+
+#include "processor.h"
+#include "test_util.h"
+
+#define MMIO_ADDR	0x8000000ULL
+
+/* AP[1]: allow unprivileged (EL0) access to a mapping. */
+#define PTE_USER	BIT(6)
+
+/* SPSR for ERET to EL0t with DAIF masked. */
+#define SPSR_EL0	(PSR_MODE_EL0t | PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
+
+struct mmio_test {
+	const char *name;
+	uint64_t data;		/* access-width value, host byte order */
+	uint8_t len;
+	uint64_t expected;	/* sign-extended result; same for LE and BE */
+};
+
+/* Paired 1:1, in order, with the loads in guest_loads_le() and el0_be_loads. */
+static const struct mmio_test tests[] = {
+	/* LDRSB Xt: byte sign-extended to 64 bits */
+	{ "LDRSB Xt 0xFF",	0xFF,		1, 0xFFFFFFFFFFFFFFFFULL },
+	{ "LDRSB Xt 0x7F",	0x7F,		1, 0x7FULL },
+
+	/* LDRSB Wt: byte sign-extended to 32 bits, upper 32 bits zeroed */
+	{ "LDRSB Wt 0xFF",	0xFF,		1, 0xFFFFFFFFULL },
+	{ "LDRSB Wt 0x7F",	0x7F,		1, 0x7FULL },
+
+	/* LDRSH Xt: halfword sign-extended to 64 bits */
+	{ "LDRSH Xt 0x8001",	0x8001,		2, 0xFFFFFFFFFFFF8001ULL },
+	{ "LDRSH Xt 0x7FFF",	0x7FFF,		2, 0x7FFFULL },
+
+	/* LDRSH Wt: halfword sign-extended to 32 bits, upper 32 bits zeroed */
+	{ "LDRSH Wt 0x8001",	0x8001,		2, 0xFFFF8001ULL },
+	{ "LDRSH Wt 0x7FFF",	0x7FFF,		2, 0x7FFFULL },
+
+	/* LDRSW Xt: word sign-extended to 64 bits (no Wt form) */
+	{ "LDRSW Xt 0x80000001", 0x80000001,	4, 0xFFFFFFFF80000001ULL },
+	{ "LDRSW Xt 0x7FFFFFFF", 0x7FFFFFFF,	4, 0x7FFFFFFFULL },
+};
+
+/* Issue one sign-extending load from MMIO and report the result. */
+#define GUEST_LDRS(load) do {						\
+	uint64_t val;							\
+									\
+	asm volatile(load : "=r"(val) : "r"(MMIO_ADDR) : "memory");	\
+	GUEST_SYNC(val);						\
+} while (0)
+
+/* Little-endian pass: loads issued at EL1. */
+static void guest_loads_le(void)
+{
+	GUEST_LDRS("ldrsb %0, [%1]");
+	GUEST_LDRS("ldrsb %0, [%1]");
+	GUEST_LDRS("ldrsb %w0, [%1]");
+	GUEST_LDRS("ldrsb %w0, [%1]");
+	GUEST_LDRS("ldrsh %0, [%1]");
+	GUEST_LDRS("ldrsh %0, [%1]");
+	GUEST_LDRS("ldrsh %w0, [%1]");
+	GUEST_LDRS("ldrsh %w0, [%1]");
+	GUEST_LDRS("ldrsw %0, [%1]");
+	GUEST_LDRS("ldrsw %0, [%1]");
+}
+
+/*
+ * Run the big-endian loads at EL0, where SCTLR_EL1.E0E flips only the data
+ * endianness; at EL1, SCTLR_EL1.EE would also flip the page-table walk and
+ * fault on the little-endian tables. x0 holds MMIO_ADDR; results return in
+ * x19..x28 (tests[] order) via a single SVC.
+ */
+extern char el0_be_loads[];
+asm(
+"	.pushsection .text, \"ax\"\n"
+"	.global el0_be_loads\n"
+"el0_be_loads:\n"
+"	ldrsb	x19, [x0]\n"
+"	ldrsb	x20, [x0]\n"
+"	ldrsb	w21, [x0]\n"
+"	ldrsb	w22, [x0]\n"
+"	ldrsh	x23, [x0]\n"
+"	ldrsh	x24, [x0]\n"
+"	ldrsh	w25, [x0]\n"
+"	ldrsh	w26, [x0]\n"
+"	ldrsw	x27, [x0]\n"
+"	ldrsw	x28, [x0]\n"
+"	svc	#0\n"
+"	.popsection\n"
+);
+
+/* EL1 handler for the EL0 SVC: report the results, then finish. */
+static void el0_svc_handler(struct ex_regs *regs)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++)
+		GUEST_SYNC(regs->regs[19 + i]);
+
+	GUEST_DONE();
+}
+
+static bool guest_mixed_endian_el0(void)
+{
+	uint64_t mmfr0 = read_sysreg(id_aa64mmfr0_el1);
+
+	return SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGEND, mmfr0) ||
+	       SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGENDEL0, mmfr0);
+}
+
+static void guest_code(void)
+{
+	guest_loads_le();
+
+	if (guest_mixed_endian_el0()) {
+		write_sysreg(read_sysreg(sctlr_el1) | SCTLR_EL1_E0E, sctlr_el1);
+		isb();
+
+		asm volatile(
+		"	msr	elr_el1, %[pc]\n"
+		"	msr	spsr_el1, %[spsr]\n"
+		"	mov	x0, %[mmio]\n"
+		"	isb\n"
+		"	eret\n"
+		:
+		: [pc] "r"(el0_be_loads),
+		  [spsr] "r"((uint64_t)SPSR_EL0),
+		  [mmio] "r"(MMIO_ADDR)
+		: "x0", "memory");
+		__builtin_unreachable();	/* el0_svc_handler ends the test */
+	}
+
+	GUEST_DONE();
+}
+
+static void handle_mmio(struct kvm_run *run, const struct mmio_test *t, bool be)
+{
+	int i;
+
+	TEST_ASSERT_EQ(run->mmio.phys_addr, MMIO_ADDR);
+	TEST_ASSERT(!run->mmio.is_write, "Expected MMIO read for %s", t->name);
+	TEST_ASSERT_EQ(run->mmio.len, t->len);
+
+	memset(run->mmio.data, 0, sizeof(run->mmio.data));
+	if (be) {
+		/* The guest reads the device bytes most-significant first. */
+		for (i = 0; i < t->len; i++)
+			run->mmio.data[i] = t->data >> (8 * (t->len - 1 - i));
+	} else {
+		/* Works because arm64 KVM hosts are always little-endian. */
+		memcpy(run->mmio.data, &t->data, t->len);
+	}
+}
+
+static void expect_sync(struct kvm_vcpu *vcpu, struct ucall *uc,
+			const struct mmio_test *t)
+{
+	switch (get_ucall(vcpu, uc)) {
+	case UCALL_SYNC:
+		TEST_ASSERT(uc->args[1] == t->expected,
+			    "%s: got %#lx, want %#lx", t->name,
+			    (unsigned long)uc->args[1], (unsigned long)t->expected);
+		break;
+	case UCALL_ABORT:
+		REPORT_GUEST_ASSERT(*uc);
+		break;
+	default:
+		TEST_FAIL("Unexpected ucall for %s", t->name);
+	}
+}
+
+/* OR PTE_USER into the leaf descriptors covering [gva, gva + len). */
+static void make_el0_accessible(struct kvm_vm *vm, uint64_t gva, uint64_t len)
+{
+	uint64_t addr;
+
+	for (addr = gva & ~((uint64_t)vm->page_size - 1); addr < gva + len;
+	     addr += vm->page_size)
+		*virt_get_pte_hva(vm, addr) |= PTE_USER;
+}
+
+static bool vcpu_mixed_endian_el0(struct kvm_vcpu *vcpu)
+{
+	uint64_t mmfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1));
+
+	return SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGEND, mmfr0) ||
+	       SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGENDEL0, mmfr0);
+}
+
+int main(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct ucall uc;
+	unsigned int i;
+	bool be;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+	virt_map(vm, MMIO_ADDR, MMIO_ADDR, 1);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vcpu);
+	vm_install_sync_handler(vm, VECTOR_SYNC_LOWER_64, ESR_ELx_EC_SVC64,
+				el0_svc_handler);
+
+	be = vcpu_mixed_endian_el0(vcpu);
+	if (be)
+		make_el0_accessible(vm, MMIO_ADDR, vm->page_size);
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests) * (be ? 2 : 1));
+
+	/* Little-endian pass: one load and one result per iteration. */
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		const struct mmio_test *t = &tests[i];
+
+		vcpu_run(vcpu);
+		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_MMIO);
+		handle_mmio(vcpu->run, t, false);
+
+		vcpu_run(vcpu);
+		expect_sync(vcpu, &uc, t);
+
+		ksft_test_result_pass("%s\n", t->name);
+	}
+
+	if (be) {
+		/* The EL0 stub issues all the loads, then reports the results. */
+		for (i = 0; i < ARRAY_SIZE(tests); i++) {
+			vcpu_run(vcpu);
+			TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_MMIO);
+			handle_mmio(vcpu->run, &tests[i], true);
+		}
+		for (i = 0; i < ARRAY_SIZE(tests); i++) {
+			vcpu_run(vcpu);
+			expect_sync(vcpu, &uc, &tests[i]);
+			ksft_test_result_pass("BE %s\n", tests[i].name);
+		}
+	}
+
+	vcpu_run(vcpu);
+	TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE, "Expected UCALL_DONE");
+
+	kvm_vm_free(vm);
+
+	ksft_finished();
+}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e44c20c04961..45e784462ec6 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -6069,25 +6069,19 @@ struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 					 gpa_t addr)
 {
 	struct kvm_io_bus *bus;
-	int dev_idx, srcu_idx;
-	struct kvm_io_device *iodev = NULL;
+	int dev_idx;
 
-	srcu_idx = srcu_read_lock(&kvm->srcu);
+	lockdep_assert_held(&kvm->srcu);
 
 	bus = kvm_get_bus_srcu(kvm, bus_idx);
 	if (!bus)
-		goto out_unlock;
+		return NULL;
 
 	dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1);
 	if (dev_idx < 0)
-		goto out_unlock;
-
-	iodev = bus->range[dev_idx].dev;
-
-out_unlock:
-	srcu_read_unlock(&kvm->srcu, srcu_idx);
+		return NULL;
 
-	return iodev;
+	return bus->range[dev_idx].dev;
 }
 EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_io_bus_get_dev);