* [RFC PATCH 1/5] KVM: arm64: Make hyp symbol address conversion explicit
2026-07-16 14:09 [RFC PATCH 0/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings Aneesh Kumar K.V (Arm)
@ 2026-07-16 14:09 ` Aneesh Kumar K.V (Arm)
2026-07-16 14:09 ` [RFC PATCH 2/5] KVM: arm64: Split hyp mapping APIs by address type Aneesh Kumar K.V (Arm)
` (3 subsequent siblings)
4 siblings, 0 replies; 8+ messages in thread
From: Aneesh Kumar K.V (Arm) @ 2026-07-16 14:09 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel, kvmarm
Cc: Aneesh Kumar K.V (Arm), Marc Zyngier, Oliver Upton, Joey Gouly,
Steffen Eiden, Suzuki K Poulose, Zenghui Yu, Catalin Marinas,
Will Deacon
kvm_ksym_ref() and kvm_ksym_ref_nvhe() have confusing names which do not
clearly describe the address conversion they perform.
Replace them with kvm_hyp_kimg_kaddr() for selecting the kernel address
of a hyp symbol and kern_sym_hyp_va() for obtaining its hyp VA. Use
lm_alias() directly where a linear-map address is required.
This is a naming cleanup with no functional change.
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
arch/arm64/include/asm/kvm_asm.h | 10 ---------
arch/arm64/include/asm/kvm_mmu.h | 33 +++++++++++++++++++++++++++
arch/arm64/kvm/arm.c | 38 ++++++++++++++++----------------
arch/arm64/kvm/va_layout.c | 2 +-
4 files changed, 53 insertions(+), 30 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 043495f7fc78..6e0cc007bfe1 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -233,16 +233,6 @@ struct kvm_nvhe_stacktrace_info {
unsigned long pc;
};
-/* Translate a kernel address @ptr into its equivalent linear mapping */
-#define kvm_ksym_ref(ptr) \
- ({ \
- void *val = (ptr); \
- if (!is_kernel_in_hyp_mode()) \
- val = lm_alias((ptr)); \
- val; \
- })
-#define kvm_ksym_ref_nvhe(sym) kvm_ksym_ref(kvm_nvhe_sym(sym))
-
struct kvm;
struct kvm_vcpu;
struct kvm_s2_mmu;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 6eae7e7e2a68..6b708ff176fd 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -107,6 +107,28 @@ u32 kvm_hyp_va_bits(void);
void kvm_apply_hyp_relocations(void);
#define __hyp_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset)
+/**
+ * kvm_hyp_kimg_kaddr - Select the kernel address used for an EL2 mapping
+ * @ptr: Address within the kernel image
+ *
+ * Return @ptr when EL2 uses the kernel-image address directly, as with
+ * VHE. Otherwise return the corresponding linear-map alias used as input
+ * to the legacy nVHE VA conversion.
+ *
+ * Return: A kernel address suitable as the basis for an EL2 virtual address.
+ */
+static __always_inline void *kvm_hyp_kimg_kaddr(void *ptr)
+{
+ /*
+ * With VHE, the host runs at EL2 using the kernel mapping, so
+ * kernel-image VAs need no translation.
+ * Only legacy nVHE requires a linear-map alias.
+ */
+ if (is_kernel_in_hyp_mode())
+ return ptr;
+
+ return lm_alias(ptr);
+}
/*
* Convert a kernel VA into a HYP VA.
@@ -140,6 +162,17 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
#define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v))))
+/**
+ * kern_sym_hyp_va - Convert a kernel image symbol address to its runtime hyp VA
+ * @ptr: Address of a symbol in the kernel image
+ *
+ * Return: The runtime hyp virtual address corresponding to @ptr.
+ */
+static __always_inline void *kern_sym_hyp_va(void *ptr)
+{
+ return kern_hyp_va(kvm_hyp_kimg_kaddr(ptr));
+}
+
extern u32 __hyp_va_bits;
/*
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 50adfff75be8..e1613186efb0 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2105,10 +2105,10 @@ static int kvm_init_vector_slots(void)
int err;
void *base;
- base = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
+ base = kern_sym_hyp_va(__kvm_hyp_vector);
kvm_init_vector_slot(base, HYP_VECTOR_DIRECT);
- base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
+ base = kern_sym_hyp_va(__bp_harden_hyp_vecs);
kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT);
if (kvm_system_needs_idmapped_vectors() &&
@@ -2136,7 +2136,7 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
* Also drop the KASAN tag which gets in the way...
*/
params->tpidr_el2 = (unsigned long)kasan_reset_tag(per_cpu_ptr_nvhe_sym(__per_cpu_start, cpu)) -
- (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start));
+ (unsigned long)kvm_hyp_kimg_kaddr(CHOOSE_NVHE_SYM(__per_cpu_start));
params->mair_el2 = read_sysreg(mair_el1);
@@ -2532,13 +2532,13 @@ static void __init teardown_hyp_mode(void)
static int __init do_pkvm_init(u32 hyp_va_bits)
{
- void *per_cpu_base = kvm_ksym_ref(kvm_nvhe_sym(kvm_arm_hyp_percpu_base));
+ void *per_cpu_base = kvm_nvhe_sym(kvm_arm_hyp_percpu_base);
int ret;
preempt_disable();
cpu_hyp_init_context();
ret = kvm_call_hyp_nvhe(__pkvm_init, hyp_mem_base, hyp_mem_size,
- kern_hyp_va(per_cpu_base),
+ kern_sym_hyp_va(per_cpu_base),
hyp_va_bits);
cpu_hyp_init_features();
@@ -2611,8 +2611,8 @@ static void kvm_hyp_init_symbols(void)
* Flush entire BSS since part of its data containing init symbols is read
* while the MMU is off.
*/
- kvm_flush_dcache_to_poc(kvm_ksym_ref(__hyp_bss_start),
- kvm_ksym_ref(__hyp_bss_end) - kvm_ksym_ref(__hyp_bss_start));
+ kvm_flush_dcache_to_poc(lm_alias(__hyp_bss_start),
+ lm_alias(__hyp_bss_end) - lm_alias(__hyp_bss_start));
}
static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
@@ -2772,29 +2772,29 @@ static int __init init_hyp_mode(void)
/*
* Map the Hyp-code called directly from the host
*/
- err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start),
- kvm_ksym_ref(__hyp_text_end), PAGE_HYP_EXEC);
+ err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__hyp_text_start),
+ kvm_hyp_kimg_kaddr(__hyp_text_end), PAGE_HYP_EXEC);
if (err) {
kvm_err("Cannot map world-switch code\n");
goto out_err;
}
- err = create_hyp_mappings(kvm_ksym_ref(__hyp_data_start),
- kvm_ksym_ref(__hyp_data_end), PAGE_HYP);
+ err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__hyp_data_start),
+ kvm_hyp_kimg_kaddr(__hyp_data_end), PAGE_HYP);
if (err) {
kvm_err("Cannot map .hyp.data section\n");
goto out_err;
}
- err = create_hyp_mappings(kvm_ksym_ref(__hyp_rodata_start),
- kvm_ksym_ref(__hyp_rodata_end), PAGE_HYP_RO);
+ err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__hyp_rodata_start),
+ kvm_hyp_kimg_kaddr(__hyp_rodata_end), PAGE_HYP_RO);
if (err) {
kvm_err("Cannot map .hyp.rodata section\n");
goto out_err;
}
- err = create_hyp_mappings(kvm_ksym_ref(__start_rodata),
- kvm_ksym_ref(__end_rodata), PAGE_HYP_RO);
+ err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__start_rodata),
+ kvm_hyp_kimg_kaddr(__end_rodata), PAGE_HYP_RO);
if (err) {
kvm_err("Cannot map rodata section\n");
goto out_err;
@@ -2805,15 +2805,15 @@ static int __init init_hyp_mode(void)
* section thanks to an assertion in the linker script. Map it RW and
* the rest of .bss RO.
*/
- err = create_hyp_mappings(kvm_ksym_ref(__hyp_bss_start),
- kvm_ksym_ref(__hyp_bss_end), PAGE_HYP);
+ err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__hyp_bss_start),
+ kvm_hyp_kimg_kaddr(__hyp_bss_end), PAGE_HYP);
if (err) {
kvm_err("Cannot map hyp bss section: %d\n", err);
goto out_err;
}
- err = create_hyp_mappings(kvm_ksym_ref(__hyp_bss_end),
- kvm_ksym_ref(__bss_stop), PAGE_HYP_RO);
+ err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__hyp_bss_end),
+ kvm_hyp_kimg_kaddr(__bss_stop), PAGE_HYP_RO);
if (err) {
kvm_err("Cannot map bss section\n");
goto out_err;
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index 2346f9435a71..63bb58a7868a 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -223,7 +223,7 @@ void kvm_patch_vector_branch(struct alt_instr *alt,
/*
* Compute HYP VA by using the same computation as kern_hyp_va()
*/
- addr = __early_kern_hyp_va((u64)kvm_ksym_ref(__kvm_hyp_vector));
+ addr = __early_kern_hyp_va((u64)kvm_hyp_kimg_kaddr(__kvm_hyp_vector));
/* Use PC[10:7] to branch to the same vector in KVM */
addr |= ((u64)origptr & GENMASK_ULL(10, 7));
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* [RFC PATCH 2/5] KVM: arm64: Split hyp mapping APIs by address type
2026-07-16 14:09 [RFC PATCH 0/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings Aneesh Kumar K.V (Arm)
2026-07-16 14:09 ` [RFC PATCH 1/5] KVM: arm64: Make hyp symbol address conversion explicit Aneesh Kumar K.V (Arm)
@ 2026-07-16 14:09 ` Aneesh Kumar K.V (Arm)
2026-07-16 14:26 ` sashiko-bot
2026-07-16 14:09 ` [RFC PATCH 3/5] KVM: arm64: Split hyp VA-to-PA conversion " Aneesh Kumar K.V (Arm)
` (2 subsequent siblings)
4 siblings, 1 reply; 8+ messages in thread
From: Aneesh Kumar K.V (Arm) @ 2026-07-16 14:09 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel, kvmarm
Cc: Aneesh Kumar K.V (Arm), Marc Zyngier, Oliver Upton, Joey Gouly,
Steffen Eiden, Suzuki K Poulose, Zenghui Yu, Catalin Marinas,
Will Deacon
Kernel-image symbols and linear-map addresses may refer to the same
physical memory, but they are not interchangeable when constructing the
EL2 address space. A kernel-image symbol requires __pa_symbol() for its
physical address and kern_sym_hyp_va() for its runtime hyp VA, whereas a
linear-map address requires __pa() and kern_hyp_va().
The existing create_hyp_mappings() and pkvm_create_mappings() interfaces
do not express this distinction. Host callers prepare symbol addresses
before invoking create_hyp_mappings(), while the common implementation
attempts to infer the physical address from the resulting pointer. The
pKVM implementation similarly assumes that every input can be translated
using the linear hyp VA-to-PA offset.
This ambiguity works while hyp symbols and linear allocations share the
same fixed-offset translation. A later patch introduces an hVHE TTBR1
layout which retains kernel-image VAs for hyp symbols. That layout
requires symbol addresses to be distinguished from linear-map addresses.
Replace create_hyp_mappings() with explicit create_hyp_symbol_mappings()
and create_hyp_linear_mappings() interfaces. Resolve the appropriate hyp
VA and PA in each wrapper, then pass those values to a common mapping
helper. This also removes the need for the generic
kernel-address-to-physical-address classifier.
Apply the same separation to the pKVM mapping code. Introduce symbol and
linear-map wrappers around an internal helper which receives an already
resolved hyp VA range and starting PA. Retain a locked linear variant for
callers which already hold the hyp page-table lock.
Update all callers to use the interface matching the address type they
provide.
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
arch/arm64/include/asm/kvm_mmu.h | 5 +-
arch/arm64/kvm/arm.c | 29 +++++------
arch/arm64/kvm/hyp/include/nvhe/mm.h | 8 ++-
arch/arm64/kvm/hyp/nvhe/mem_protect.c | 16 ++++--
arch/arm64/kvm/hyp/nvhe/mm.c | 46 ++++++++++++-----
arch/arm64/kvm/hyp/nvhe/setup.c | 18 ++++---
arch/arm64/kvm/hyp_trace.c | 2 +-
arch/arm64/kvm/mmu.c | 71 +++++++++++++++------------
8 files changed, 122 insertions(+), 73 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 6b708ff176fd..8c2972aa83b0 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -190,7 +190,10 @@ extern u32 __hyp_va_bits;
int kvm_share_hyp(void *from, void *to);
void kvm_unshare_hyp(void *from, void *to);
-int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot);
+int create_hyp_linear_mappings(void *from, void *to,
+ enum kvm_pgtable_prot prot);
+int create_hyp_symbol_mappings(void *from, void *to,
+ enum kvm_pgtable_prot prot);
int __create_hyp_mappings(unsigned long start, unsigned long size,
unsigned long phys, enum kvm_pgtable_prot prot);
int hyp_alloc_private_va_range(size_t size, unsigned long *haddr);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e1613186efb0..e498bb780382 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2620,7 +2620,7 @@ static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
void *addr = phys_to_virt(hyp_mem_base);
int ret;
- ret = create_hyp_mappings(addr, addr + hyp_mem_size, PAGE_HYP);
+ ret = create_hyp_linear_mappings(addr, addr + hyp_mem_size, PAGE_HYP);
if (ret)
return ret;
@@ -2772,29 +2772,29 @@ static int __init init_hyp_mode(void)
/*
* Map the Hyp-code called directly from the host
*/
- err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__hyp_text_start),
- kvm_hyp_kimg_kaddr(__hyp_text_end), PAGE_HYP_EXEC);
+ err = create_hyp_symbol_mappings(__hyp_text_start, __hyp_text_end,
+ PAGE_HYP_EXEC);
if (err) {
kvm_err("Cannot map world-switch code\n");
goto out_err;
}
- err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__hyp_data_start),
- kvm_hyp_kimg_kaddr(__hyp_data_end), PAGE_HYP);
+ err = create_hyp_symbol_mappings(__hyp_data_start, __hyp_data_end,
+ PAGE_HYP);
if (err) {
kvm_err("Cannot map .hyp.data section\n");
goto out_err;
}
- err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__hyp_rodata_start),
- kvm_hyp_kimg_kaddr(__hyp_rodata_end), PAGE_HYP_RO);
+ err = create_hyp_symbol_mappings(__hyp_rodata_start, __hyp_rodata_end,
+ PAGE_HYP_RO);
if (err) {
kvm_err("Cannot map .hyp.rodata section\n");
goto out_err;
}
- err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__start_rodata),
- kvm_hyp_kimg_kaddr(__end_rodata), PAGE_HYP_RO);
+ err = create_hyp_symbol_mappings(__start_rodata, __end_rodata,
+ PAGE_HYP_RO);
if (err) {
kvm_err("Cannot map rodata section\n");
goto out_err;
@@ -2805,15 +2805,15 @@ static int __init init_hyp_mode(void)
* section thanks to an assertion in the linker script. Map it RW and
* the rest of .bss RO.
*/
- err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__hyp_bss_start),
- kvm_hyp_kimg_kaddr(__hyp_bss_end), PAGE_HYP);
+ err = create_hyp_symbol_mappings(__hyp_bss_start, __hyp_bss_end,
+ PAGE_HYP);
if (err) {
kvm_err("Cannot map hyp bss section: %d\n", err);
goto out_err;
}
- err = create_hyp_mappings(kvm_hyp_kimg_kaddr(__hyp_bss_end),
- kvm_hyp_kimg_kaddr(__bss_stop), PAGE_HYP_RO);
+ err = create_hyp_symbol_mappings(__hyp_bss_end, __bss_stop,
+ PAGE_HYP_RO);
if (err) {
kvm_err("Cannot map bss section\n");
goto out_err;
@@ -2846,7 +2846,8 @@ static int __init init_hyp_mode(void)
char *percpu_end = percpu_begin + nvhe_percpu_size();
/* Map Hyp percpu pages */
- err = create_hyp_mappings(percpu_begin, percpu_end, PAGE_HYP);
+ err = create_hyp_linear_mappings(percpu_begin, percpu_end,
+ PAGE_HYP);
if (err) {
kvm_err("Cannot map hyp percpu region\n");
goto out_err;
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h
index 6e83ce35c2f2..c41152c84705 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h
@@ -23,8 +23,12 @@ int hyp_create_idmap(u32 hyp_va_bits);
int hyp_map_vectors(void);
int hyp_back_vmemmap(phys_addr_t back);
int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot);
-int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot);
-int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot);
+int pkvm_create_linear_mappings(void *from, void *to,
+ enum kvm_pgtable_prot prot);
+int pkvm_create_symbol_mappings(void *from, void *to,
+ enum kvm_pgtable_prot prot);
+int pkvm_create_linear_mappings_locked(void *from, void *to,
+ enum kvm_pgtable_prot prot);
int __pkvm_create_private_mapping(phys_addr_t phys, size_t size,
enum kvm_pgtable_prot prot,
unsigned long *haddr);
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 4e329e39a695..7f815345d6a5 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -1109,7 +1109,7 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
goto unlock;
__hyp_set_page_state_range(phys, size, PKVM_PAGE_OWNED);
- WARN_ON(pkvm_create_mappings_locked(virt, virt + size, PAGE_HYP));
+ WARN_ON(pkvm_create_linear_mappings_locked(virt, virt + size, PAGE_HYP));
WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HYP));
unlock:
@@ -1175,12 +1175,18 @@ int hyp_pin_shared_mem(void *from, void *to)
goto unlock;
for (cur = start; cur < end; cur += PAGE_SIZE) {
+ void *addr = (void *)cur;
+
p = hyp_virt_to_page(cur);
hyp_page_ref_inc(p);
- if (p->refcount == 1)
- WARN_ON(pkvm_create_mappings_locked((void *)cur,
- (void *)cur + PAGE_SIZE,
- PAGE_HYP));
+ if (p->refcount == 1) {
+ int err;
+
+ err = pkvm_create_linear_mappings_locked(addr,
+ addr + PAGE_SIZE,
+ PAGE_HYP);
+ WARN_ON(err);
+ }
}
unlock:
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 3b0bee496bff..9150ff94b01a 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -110,23 +110,21 @@ int __pkvm_create_private_mapping(phys_addr_t phys, size_t size,
return err;
}
-int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot)
+static int __pkvm_create_mappings_locked(unsigned long start,
+ unsigned long end,
+ phys_addr_t phys,
+ enum kvm_pgtable_prot prot)
{
- unsigned long start = (unsigned long)from;
- unsigned long end = (unsigned long)to;
- unsigned long virt_addr;
- phys_addr_t phys;
-
hyp_assert_lock_held(&pkvm_pgd_lock);
start = start & PAGE_MASK;
end = PAGE_ALIGN(end);
+ phys = ALIGN_DOWN(phys, PAGE_SIZE);
- for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) {
+ for (; start < end; start += PAGE_SIZE, phys += PAGE_SIZE) {
int err;
- phys = hyp_virt_to_phys((void *)virt_addr);
- err = kvm_pgtable_hyp_map(&pkvm_pgtable, virt_addr, PAGE_SIZE,
+ err = kvm_pgtable_hyp_map(&pkvm_pgtable, start, PAGE_SIZE,
phys, prot);
if (err)
return err;
@@ -135,12 +133,38 @@ int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot
return 0;
}
-int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
+int pkvm_create_linear_mappings_locked(void *from, void *to,
+ enum kvm_pgtable_prot prot)
+{
+ unsigned long start = (unsigned long)from & PAGE_MASK;
+ phys_addr_t phys = hyp_virt_to_phys((void *)start);
+
+ return __pkvm_create_mappings_locked(start, (unsigned long)to,
+ phys, prot);
+}
+
+int pkvm_create_linear_mappings(void *from, void *to,
+ enum kvm_pgtable_prot prot)
+{
+ int ret;
+
+ hyp_spin_lock(&pkvm_pgd_lock);
+ ret = pkvm_create_linear_mappings_locked(from, to, prot);
+ hyp_spin_unlock(&pkvm_pgd_lock);
+
+ return ret;
+}
+
+int pkvm_create_symbol_mappings(void *from, void *to,
+ enum kvm_pgtable_prot prot)
{
+ unsigned long start = (unsigned long)from & PAGE_MASK;
+ phys_addr_t phys = __hyp_pa(start);
int ret;
hyp_spin_lock(&pkvm_pgd_lock);
- ret = pkvm_create_mappings_locked(from, to, prot);
+ ret = __pkvm_create_mappings_locked(start, (unsigned long)to,
+ phys, prot);
hyp_spin_unlock(&pkvm_pgd_lock);
return ret;
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 75b00c323310..66a3d01cd79e 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -86,7 +86,7 @@ static int pkvm_create_host_sve_mappings(void)
start = kern_hyp_va(sve_regs);
end = start + PAGE_ALIGN(pkvm_host_sve_state_size());
- ret = pkvm_create_mappings(start, end, PAGE_HYP);
+ ret = pkvm_create_linear_mappings(start, end, PAGE_HYP);
if (ret)
return ret;
}
@@ -121,23 +121,27 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
if (ret)
return ret;
- ret = pkvm_create_mappings(__hyp_text_start, __hyp_text_end, PAGE_HYP_EXEC);
+ ret = pkvm_create_symbol_mappings(__hyp_text_start, __hyp_text_end,
+ PAGE_HYP_EXEC);
if (ret)
return ret;
- ret = pkvm_create_mappings(__hyp_data_start, __hyp_data_end, PAGE_HYP);
+ ret = pkvm_create_symbol_mappings(__hyp_data_start, __hyp_data_end,
+ PAGE_HYP);
if (ret)
return ret;
- ret = pkvm_create_mappings(__hyp_rodata_start, __hyp_rodata_end, PAGE_HYP_RO);
+ ret = pkvm_create_symbol_mappings(__hyp_rodata_start, __hyp_rodata_end,
+ PAGE_HYP_RO);
if (ret)
return ret;
- ret = pkvm_create_mappings(__hyp_bss_start, __hyp_bss_end, PAGE_HYP);
+ ret = pkvm_create_symbol_mappings(__hyp_bss_start, __hyp_bss_end,
+ PAGE_HYP);
if (ret)
return ret;
- ret = pkvm_create_mappings(virt, virt + size, PAGE_HYP);
+ ret = pkvm_create_linear_mappings(virt, virt + size, PAGE_HYP);
if (ret)
return ret;
@@ -146,7 +150,7 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
start = (void *)kern_hyp_va(per_cpu_base[i]);
end = start + PAGE_ALIGN(hyp_percpu_size);
- ret = pkvm_create_mappings(start, end, PAGE_HYP);
+ ret = pkvm_create_linear_mappings(start, end, PAGE_HYP);
if (ret)
return ret;
diff --git a/arch/arm64/kvm/hyp_trace.c b/arch/arm64/kvm/hyp_trace.c
index 2411b4c32932..0cf073682173 100644
--- a/arch/arm64/kvm/hyp_trace.c
+++ b/arch/arm64/kvm/hyp_trace.c
@@ -142,7 +142,7 @@ static int __map_hyp(void *start, size_t size)
if (is_protected_kvm_enabled())
return 0;
- return create_hyp_mappings(start, start + size, PAGE_HYP);
+ return create_hyp_linear_mappings(start, start + size, PAGE_HYP);
}
static int __share_page(unsigned long va)
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6c941aaa10c6..154d53dca619 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -436,17 +436,6 @@ int __create_hyp_mappings(unsigned long start, unsigned long size,
return err;
}
-static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
-{
- if (!is_vmalloc_addr(kaddr)) {
- BUG_ON(!virt_addr_valid(kaddr));
- return __pa(kaddr);
- } else {
- return page_to_phys(vmalloc_to_page(kaddr)) +
- offset_in_page(kaddr);
- }
-}
-
struct hyp_shared_pfn {
u64 pfn;
int count;
@@ -559,7 +548,7 @@ int kvm_share_hyp(void *from, void *to)
return -EINVAL;
if (kvm_host_owns_hyp_mappings())
- return create_hyp_mappings(from, to, PAGE_HYP);
+ return create_hyp_linear_mappings(from, to, PAGE_HYP);
start = ALIGN_DOWN(__pa(from), PAGE_SIZE);
end = PAGE_ALIGN(__pa(to));
@@ -608,23 +597,10 @@ void kvm_unshare_hyp(void *from, void *to)
}
}
-/**
- * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
- * @from: The virtual kernel start address of the range
- * @to: The virtual kernel end address of the range (exclusive)
- * @prot: The protection to be applied to this range
- *
- * The same virtual address as the kernel virtual address is also used
- * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying
- * physical pages.
- */
-int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
+static int __create_hyp_mapping_range(unsigned long start, unsigned long end,
+ phys_addr_t phys,
+ enum kvm_pgtable_prot prot)
{
- phys_addr_t phys_addr;
- unsigned long virt_addr;
- unsigned long start = kern_hyp_va((unsigned long)from);
- unsigned long end = kern_hyp_va((unsigned long)to);
-
if (is_kernel_in_hyp_mode())
return 0;
@@ -633,13 +609,12 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
start = start & PAGE_MASK;
end = PAGE_ALIGN(end);
+ phys = ALIGN_DOWN(phys, PAGE_SIZE);
- for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) {
+ for (; start < end; start += PAGE_SIZE, phys += PAGE_SIZE) {
int err;
- phys_addr = kvm_kaddr_to_phys(from + virt_addr - start);
- err = __create_hyp_mappings(virt_addr, PAGE_SIZE, phys_addr,
- prot);
+ err = __create_hyp_mappings(start, PAGE_SIZE, phys, prot);
if (err)
return err;
}
@@ -647,6 +622,38 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
return 0;
}
+/**
+ * create_hyp_linear_mappings - map a host linear-map range at EL2
+ * @from: The host linear-map start address
+ * @to: The host linear-map end address (exclusive)
+ * @prot: The protection to apply to the mapping
+ */
+int create_hyp_linear_mappings(void *from, void *to,
+ enum kvm_pgtable_prot prot)
+{
+ unsigned long start = kern_hyp_va((unsigned long)from);
+ unsigned long end = kern_hyp_va((unsigned long)to);
+ phys_addr_t phys = __pa((unsigned long)from & PAGE_MASK);
+
+ return __create_hyp_mapping_range(start, end, phys, prot);
+}
+
+/**
+ * create_hyp_symbol_mappings - map a kernel-image symbol range at EL2
+ * @from: The kernel-image symbol at the start of the range
+ * @to: The kernel-image symbol at the end of the range (exclusive)
+ * @prot: The protection to apply to the mapping
+ */
+int create_hyp_symbol_mappings(void *from, void *to,
+ enum kvm_pgtable_prot prot)
+{
+ unsigned long start = (unsigned long)kern_sym_hyp_va(from);
+ unsigned long end = (unsigned long)kern_sym_hyp_va(to);
+ phys_addr_t phys = __pa_symbol((unsigned long)from & PAGE_MASK);
+
+ return __create_hyp_mapping_range(start, end, phys, prot);
+}
+
static int __hyp_alloc_private_va_range(unsigned long base)
{
lockdep_assert_held(&kvm_hyp_pgd_mutex);
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* Re: [RFC PATCH 2/5] KVM: arm64: Split hyp mapping APIs by address type
2026-07-16 14:09 ` [RFC PATCH 2/5] KVM: arm64: Split hyp mapping APIs by address type Aneesh Kumar K.V (Arm)
@ 2026-07-16 14:26 ` sashiko-bot
0 siblings, 0 replies; 8+ messages in thread
From: sashiko-bot @ 2026-07-16 14:26 UTC (permalink / raw)
To: Aneesh Kumar K.V (Arm); +Cc: kvmarm, Oliver Upton, Marc Zyngier
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] This problem wasn't introduced by this patch, but it remains present: Treating EL2 page table allocation failure as fatal by wrapping `pkvm_create_linear_mappings_locked()` in `WARN_ON()`. This converts a recoverable `-ENOMEM` condition into a fatal hypervisor panic.
--
--- Patch [2]: [RFC PATCH 2/5] KVM: arm64: Split hyp mapping APIs by address type ---
commit 7eb3ee309a427de1a370d3d0ea72c38646079ff1
Author: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
KVM: arm64: Split hyp mapping APIs by address type
This commit replaces create_hyp_mappings() and pkvm_create_mappings()
with explicit symbol and linear-map interfaces to distinguish between
kernel-image symbols and linear-map addresses. It updates all callers
to use the appropriate interface for the address type they provide.
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index 4e329e39a695a..7f815345d6a56 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -1109,7 +1109,7 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
> goto unlock;
>
> __hyp_set_page_state_range(phys, size, PKVM_PAGE_OWNED);
> - WARN_ON(pkvm_create_mappings_locked(virt, virt + size, PAGE_HYP));
> + WARN_ON(pkvm_create_linear_mappings_locked(virt, virt + size, PAGE_HYP));
[Severity: High]
This is a pre-existing issue, but wrapping pkvm_create_linear_mappings_locked()
in a WARN_ON() in __pkvm_host_donate_hyp() converts a legitimate EL2 page table
allocation failure into a fatal hypervisor panic. At EL2, WARN_ON() expands to
BRK, taking down the host. Because userspace processes can exhaust the EL2
memory pool by triggering operations like host memory donation, could this
panic be used for a host denial-of-service attack?
[ ... ]
> @@ -1175,12 +1175,18 @@ int hyp_pin_shared_mem(void *from, void *to)
> goto unlock;
>
> for (cur = start; cur < end; cur += PAGE_SIZE) {
> + void *addr = (void *)cur;
> +
> p = hyp_virt_to_page(cur);
> hyp_page_ref_inc(p);
> - if (p->refcount == 1)
> - WARN_ON(pkvm_create_mappings_locked((void *)cur,
> - (void *)cur + PAGE_SIZE,
> - PAGE_HYP));
> + if (p->refcount == 1) {
> + int err;
> +
> + err = pkvm_create_linear_mappings_locked(addr,
> + addr + PAGE_SIZE,
> + PAGE_HYP);
> + WARN_ON(err);
[Severity: High]
This isn't a bug introduced by this patch, but similar to the above, wrapping
pkvm_create_linear_mappings_locked() in WARN_ON() in hyp_pin_shared_mem()
treats a legitimate -ENOMEM condition as fatal. If the EL2 buddy allocator
fails when allocating new page table pages, should this path instead return
the error and gracefully fail the hypercall rather than crashing the
hypervisor?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260716140936.4003182-1-aneesh.kumar@kernel.org?part=2
^ permalink raw reply [flat|nested] 8+ messages in thread
* [RFC PATCH 3/5] KVM: arm64: Split hyp VA-to-PA conversion by address type
2026-07-16 14:09 [RFC PATCH 0/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings Aneesh Kumar K.V (Arm)
2026-07-16 14:09 ` [RFC PATCH 1/5] KVM: arm64: Make hyp symbol address conversion explicit Aneesh Kumar K.V (Arm)
2026-07-16 14:09 ` [RFC PATCH 2/5] KVM: arm64: Split hyp mapping APIs by address type Aneesh Kumar K.V (Arm)
@ 2026-07-16 14:09 ` Aneesh Kumar K.V (Arm)
2026-07-16 14:09 ` [RFC PATCH 4/5] KVM: arm64: Rename the hyp private VA allocation base Aneesh Kumar K.V (Arm)
2026-07-16 14:09 ` [RFC PATCH 5/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings Aneesh Kumar K.V (Arm)
4 siblings, 0 replies; 8+ messages in thread
From: Aneesh Kumar K.V (Arm) @ 2026-07-16 14:09 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel, kvmarm
Cc: Aneesh Kumar K.V (Arm), Marc Zyngier, Oliver Upton, Joey Gouly,
Steffen Eiden, Suzuki K Poulose, Zenghui Yu, Catalin Marinas,
Will Deacon
The existing hyp VA-to-PA conversion uses one physvirt offset for both
kernel-image symbols and linear-map addresses. This only works while both
address types use the same EL2 VA transformation.
With hVHE TTBR1, hyp symbols retain their kernel-image VAs while pools,
per-CPU data and shared memory remain linear-map-derived. Introduce a
separate symbol physvirt offset and explicit symbol and linear conversion
helpers.
Update every caller according to its address type and remove the
ambiguous hyp_pa and __hyp_pa helpers. The offsets remain same as
hyp_physvirt_offset, making this preparatory for the TTBR1 layout.
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
arch/arm64/include/asm/kvm_host.h | 2 ++
arch/arm64/include/asm/kvm_mmu.h | 17 ++++++++++++-----
arch/arm64/kvm/arm.c | 2 +-
arch/arm64/kvm/hyp/include/nvhe/memory.h | 13 +++++++------
arch/arm64/kvm/hyp/nvhe/early_alloc.c | 1 +
arch/arm64/kvm/hyp/nvhe/events.c | 2 +-
arch/arm64/kvm/hyp/nvhe/host.S | 4 ++--
arch/arm64/kvm/hyp/nvhe/mem_protect.c | 14 +++++++-------
arch/arm64/kvm/hyp/nvhe/mm.c | 11 ++++++-----
arch/arm64/kvm/hyp/nvhe/psci-relay.c | 12 ++++++------
arch/arm64/kvm/hyp/nvhe/setup.c | 4 ++--
arch/arm64/kvm/va_layout.c | 2 ++
12 files changed, 49 insertions(+), 35 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index bae2c4f92ef5..d92e0d066de3 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -827,6 +827,8 @@ extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config);
extern s64 kvm_nvhe_sym(hyp_physvirt_offset);
#define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset)
+extern s64 kvm_nvhe_sym(hyp_symbol_physvirt_offset);
+#define hyp_symbol_physvirt_offset CHOOSE_NVHE_SYM(hyp_symbol_physvirt_offset)
extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS];
#define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 8c2972aa83b0..bcc8e28985f7 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -54,15 +54,21 @@
#include <asm/alternative.h>
/*
- * Convert a hypervisor VA to a PA
+ * Convert an address in the hypervisor linear map to a PA
* reg: hypervisor address to be converted in place
* tmp: temporary register
*/
-.macro hyp_pa reg, tmp
+.macro hyp_linear_pa reg, tmp
ldr_l \tmp, hyp_physvirt_offset
add \reg, \reg, \tmp
.endm
+/* Convert a hypervisor kernel-image VA to a PA. */
+.macro hyp_symbol_pa reg, tmp
+ ldr_l \tmp, hyp_symbol_physvirt_offset
+ add \reg, \reg, \tmp
+.endm
+
/*
* Convert a hypervisor VA to a kernel image address
* reg: hypervisor address to be converted in place
@@ -74,8 +80,8 @@
* specific registers encoded in the instructions).
*/
.macro hyp_kimg_va reg, tmp
- /* Convert hyp VA -> PA. */
- hyp_pa \reg, \tmp
+ /* Convert hyp kernel-image VA -> PA. */
+ hyp_symbol_pa \reg, \tmp
/* Load kimage_voffset. */
alternative_cb ARM64_ALWAYS_SYSTEM, kvm_get_kimage_voffset
@@ -106,7 +112,6 @@ void kvm_compute_layout(void);
u32 kvm_hyp_va_bits(void);
void kvm_apply_hyp_relocations(void);
-#define __hyp_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset)
/**
* kvm_hyp_kimg_kaddr - Select the kernel address used for an EL2 mapping
* @ptr: Address within the kernel image
@@ -130,6 +135,8 @@ static __always_inline void *kvm_hyp_kimg_kaddr(void *ptr)
return lm_alias(ptr);
}
+#define __hyp_linear_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset)
+#define __hyp_symbol_pa(x) (((phys_addr_t)(x)) + hyp_symbol_physvirt_offset)
/*
* Convert a kernel VA into a HYP VA.
*
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e498bb780382..924f33c1a9d4 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2835,7 +2835,7 @@ static int __init init_hyp_mode(void)
/*
* Save the stack PA in nvhe_init_params. This will be needed
* to recreate the stack mapping in protected nVHE mode.
- * __hyp_pa() won't do the right thing there, since the stack
+ * __hyp_linear_pa() won't do the right thing there, since the stack
* has been mapped in the flexible private VA space.
*/
params->stack_pa = __pa(stack_base);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
index b50712d47f6d..a7c3e70f7256 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
@@ -73,16 +73,17 @@ struct hyp_page {
extern u64 __hyp_vmemmap;
#define hyp_vmemmap ((struct hyp_page *)__hyp_vmemmap)
-#define __hyp_va(phys) ((void *)((phys_addr_t)(phys) - hyp_physvirt_offset))
+#define __hyp_linear_va(phys) \
+ ((void *)((phys_addr_t)(phys) - hyp_physvirt_offset))
static inline void *hyp_phys_to_virt(phys_addr_t phys)
{
- return __hyp_va(phys);
+ return __hyp_linear_va(phys);
}
static inline phys_addr_t hyp_virt_to_phys(void *addr)
{
- return __hyp_pa(addr);
+ return __hyp_linear_pa(addr);
}
#define hyp_phys_to_pfn(phys) ((phys) >> PAGE_SHIFT)
@@ -94,12 +95,12 @@ static inline struct hyp_page *hyp_phys_to_page(phys_addr_t phys)
return &hyp_vmemmap[hyp_phys_to_pfn(phys)];
}
-#define hyp_virt_to_page(virt) hyp_phys_to_page(__hyp_pa(virt))
-#define hyp_virt_to_pfn(virt) hyp_phys_to_pfn(__hyp_pa(virt))
+#define hyp_virt_to_page(virt) hyp_phys_to_page(__hyp_linear_pa(virt))
+#define hyp_virt_to_pfn(virt) hyp_phys_to_pfn(__hyp_linear_pa(virt))
#define hyp_page_to_pfn(page) ((struct hyp_page *)(page) - hyp_vmemmap)
#define hyp_page_to_phys(page) hyp_pfn_to_phys((hyp_page_to_pfn(page)))
-#define hyp_page_to_virt(page) __hyp_va(hyp_page_to_phys(page))
+#define hyp_page_to_virt(page) __hyp_linear_va(hyp_page_to_phys(page))
#define hyp_page_to_pool(page) (((struct hyp_page *)page)->pool)
static inline enum pkvm_page_state get_host_state(struct hyp_page *p)
diff --git a/arch/arm64/kvm/hyp/nvhe/early_alloc.c b/arch/arm64/kvm/hyp/nvhe/early_alloc.c
index 00de04153cc6..6002c61ae62c 100644
--- a/arch/arm64/kvm/hyp/nvhe/early_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/early_alloc.c
@@ -11,6 +11,7 @@
struct kvm_pgtable_mm_ops hyp_early_alloc_mm_ops;
s64 __ro_after_init hyp_physvirt_offset;
+s64 __ro_after_init hyp_symbol_physvirt_offset;
static unsigned long base;
static unsigned long end;
diff --git a/arch/arm64/kvm/hyp/nvhe/events.c b/arch/arm64/kvm/hyp/nvhe/events.c
index add9383aadb5..4204cf81f0e4 100644
--- a/arch/arm64/kvm/hyp/nvhe/events.c
+++ b/arch/arm64/kvm/hyp/nvhe/events.c
@@ -17,7 +17,7 @@ int __tracing_enable_event(unsigned short id, bool enable)
if (event_id >= __hyp_event_ids_end)
return -EINVAL;
- enabled = hyp_fixmap_map(__hyp_pa(&event_id->enabled));
+ enabled = hyp_fixmap_map(__hyp_symbol_pa(&event_id->enabled));
atomic_set(enabled, enable);
hyp_fixmap_unmap();
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 9393fe3ea6a1..079788f152d1 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -133,7 +133,7 @@ SYM_FUNC_START(__hyp_do_panic)
mrs x0, esr_el2
mov x4, x3
mov x3, x2
- hyp_pa x3, x6
+ hyp_symbol_pa x3, x6
get_vcpu_ptr x5, x6
mrs x6, far_el2
mrs x7, hpfar_el2
@@ -163,7 +163,7 @@ alternative_else_nop_endif
* Preserve x0-x4, which may contain stub parameters.
*/
adr_l x5, __kvm_handle_stub_hvc
- hyp_pa x5, x6
+ hyp_symbol_pa x5, x6
br x5
SYM_FUNC_END(__host_hvc)
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 7f815345d6a5..593359d04053 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -175,7 +175,7 @@ int kvm_host_prepare_stage2(void *pgt_pool_base)
if (ret)
return ret;
- mmu->pgd_phys = __hyp_pa(host_mmu.pgt.pgd);
+ mmu->pgd_phys = __hyp_linear_pa(host_mmu.pgt.pgd);
mmu->pgt = &host_mmu.pgt;
atomic64_set(&mmu->vmid.id, 0);
@@ -243,9 +243,9 @@ static void __apply_guest_page(void *va, size_t size,
void *map;
if (IS_ALIGNED((unsigned long)va, PMD_SIZE) && size >= PMD_SIZE)
- map = hyp_fixblock_map(__hyp_pa(va), &map_size);
+ map = hyp_fixblock_map(__hyp_linear_pa(va), &map_size);
else
- map = hyp_fixmap_map(__hyp_pa(va));
+ map = hyp_fixmap_map(__hyp_linear_pa(va));
func(map, map_size);
@@ -300,7 +300,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd)
if (ret)
return ret;
- vm->kvm.arch.mmu.pgd_phys = __hyp_pa(vm->pgt.pgd);
+ vm->kvm.arch.mmu.pgd_phys = __hyp_linear_pa(vm->pgt.pgd);
return 0;
}
@@ -1092,7 +1092,7 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
{
u64 phys = hyp_pfn_to_phys(pfn);
u64 size = PAGE_SIZE * nr_pages;
- void *virt = __hyp_va(phys);
+ void *virt = __hyp_linear_va(phys);
int ret;
if (!pfn_range_is_valid(pfn, nr_pages))
@@ -1123,7 +1123,7 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
{
u64 phys = hyp_pfn_to_phys(pfn);
u64 size = PAGE_SIZE * nr_pages;
- u64 virt = (u64)__hyp_va(phys);
+ u64 virt = (u64)__hyp_linear_va(phys);
int ret;
if (!pfn_range_is_valid(pfn, nr_pages))
@@ -1158,7 +1158,7 @@ int hyp_pin_shared_mem(void *from, void *to)
{
u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE);
u64 end = PAGE_ALIGN((u64)to);
- u64 phys = __hyp_pa(start);
+ u64 phys = __hyp_linear_pa(start);
u64 size = end - start;
struct hyp_page *p;
int ret;
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 9150ff94b01a..061fca95a78a 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -159,7 +159,7 @@ int pkvm_create_symbol_mappings(void *from, void *to,
enum kvm_pgtable_prot prot)
{
unsigned long start = (unsigned long)from & PAGE_MASK;
- phys_addr_t phys = __hyp_pa(start);
+ phys_addr_t phys = __hyp_symbol_pa(start);
int ret;
hyp_spin_lock(&pkvm_pgd_lock);
@@ -242,7 +242,7 @@ int hyp_map_vectors(void)
return 0;
}
- phys = __hyp_pa(__bp_harden_hyp_vecs);
+ phys = __hyp_symbol_pa(__bp_harden_hyp_vecs);
ret = __pkvm_create_private_mapping(phys, __BP_HARDEN_HYP_VECS_SZ,
PAGE_HYP_EXEC, &bp_base);
if (ret)
@@ -418,7 +418,8 @@ int hyp_create_fixmap(void)
return ret;
ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr, PAGE_SIZE,
- __hyp_pa(__hyp_bss_start), PAGE_HYP);
+ __hyp_symbol_pa(__hyp_bss_start),
+ PAGE_HYP);
if (ret)
return ret;
@@ -434,10 +435,10 @@ int hyp_create_idmap(u32 hyp_va_bits)
{
unsigned long start, end;
- start = hyp_virt_to_phys((void *)__hyp_idmap_text_start);
+ start = __hyp_symbol_pa(__hyp_idmap_text_start);
start = ALIGN_DOWN(start, PAGE_SIZE);
- end = hyp_virt_to_phys((void *)__hyp_idmap_text_end);
+ end = __hyp_symbol_pa(__hyp_idmap_text_end);
end = ALIGN(end, PAGE_SIZE);
/*
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index e20db999e328..91b658ac74ee 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -139,8 +139,8 @@ static int psci_cpu_on(u64 func_id, struct kvm_cpu_context *host_ctxt)
wmb();
ret = psci_call(func_id, mpidr,
- __hyp_pa(&kvm_hyp_cpu_entry),
- __hyp_pa(init_params));
+ __hyp_symbol_pa(&kvm_hyp_cpu_entry),
+ __hyp_linear_pa(init_params));
/* If successful, the lock will be released by the target CPU. */
if (ret != PSCI_RET_SUCCESS)
@@ -173,8 +173,8 @@ static int psci_cpu_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
* point if it is a deep sleep state.
*/
return psci_call(func_id, power_state,
- __hyp_pa(&kvm_hyp_cpu_resume),
- __hyp_pa(init_params));
+ __hyp_symbol_pa(&kvm_hyp_cpu_resume),
+ __hyp_linear_pa(init_params));
}
static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
@@ -197,8 +197,8 @@ static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
/* Will only return on error. */
return psci_call(func_id,
- __hyp_pa(&kvm_hyp_cpu_resume),
- __hyp_pa(init_params), 0);
+ __hyp_symbol_pa(&kvm_hyp_cpu_resume),
+ __hyp_linear_pa(init_params), 0);
}
static void __noreturn __kvm_host_psci_cpu_entry(unsigned long pc, unsigned long r0)
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 66a3d01cd79e..2ef1972cc3dd 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -169,7 +169,7 @@ static void update_nvhe_init_params(void)
for (i = 0; i < hyp_nr_cpus; i++) {
params = per_cpu_ptr(&kvm_init_params, i);
- params->pgd_pa = __hyp_pa(pkvm_pgtable.pgd);
+ params->pgd_pa = __hyp_linear_pa(pkvm_pgtable.pgd);
dcache_clean_inval_poc((unsigned long)params,
(unsigned long)params + sizeof(*params));
}
@@ -371,7 +371,7 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long *per_cpu_bas
/* Jump in the idmap page to switch to the new page-tables */
params = this_cpu_ptr(&kvm_init_params);
- fn = (typeof(fn))__hyp_pa(__pkvm_init_switch_pgd);
+ fn = (typeof(fn))__hyp_symbol_pa(__pkvm_init_switch_pgd);
fn(params->pgd_pa, params->stack_hyp_va, __pkvm_init_finalise);
unreachable();
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index 63bb58a7868a..75a89ad8fecf 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -44,6 +44,8 @@ static void init_hyp_physvirt_offset(void)
kern_va = (u64)lm_alias(__hyp_text_start);
hyp_va = __early_kern_hyp_va(kern_va);
hyp_physvirt_offset = (s64)__pa(kern_va) - (s64)hyp_va;
+
+ hyp_symbol_physvirt_offset = hyp_physvirt_offset;
}
/*
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* [RFC PATCH 4/5] KVM: arm64: Rename the hyp private VA allocation base
2026-07-16 14:09 [RFC PATCH 0/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings Aneesh Kumar K.V (Arm)
` (2 preceding siblings ...)
2026-07-16 14:09 ` [RFC PATCH 3/5] KVM: arm64: Split hyp VA-to-PA conversion " Aneesh Kumar K.V (Arm)
@ 2026-07-16 14:09 ` Aneesh Kumar K.V (Arm)
2026-07-16 14:09 ` [RFC PATCH 5/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings Aneesh Kumar K.V (Arm)
4 siblings, 0 replies; 8+ messages in thread
From: Aneesh Kumar K.V (Arm) @ 2026-07-16 14:09 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel, kvmarm
Cc: Aneesh Kumar K.V (Arm), Marc Zyngier, Oliver Upton, Joey Gouly,
Steffen Eiden, Suzuki K Poulose, Zenghui Yu, Catalin Marinas,
Will Deacon
io_map_base is not used for I/O mappings. It is the allocation base for
private hyp VAs used by stacks, fixmaps and others.
Rename it to __hyp_private_va_base in the hyp code
No functional change in this patch.
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
arch/arm64/kvm/hyp/nvhe/mm.c | 31 ++++++++++++++++---------------
1 file changed, 16 insertions(+), 15 deletions(-)
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 061fca95a78a..3233a7c70f7c 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -24,7 +24,7 @@ hyp_spinlock_t pkvm_pgd_lock;
struct memblock_region hyp_memory[HYP_MEMBLOCK_REGIONS];
unsigned int hyp_memblock_nr;
-static u64 __io_map_base;
+static u64 __hyp_private_va_base;
struct hyp_fixmap_slot {
u64 addr;
@@ -50,7 +50,7 @@ static int __pkvm_alloc_private_va_range(unsigned long start, size_t size)
hyp_assert_lock_held(&pkvm_pgd_lock);
- if (!start || start < __io_map_base)
+ if (!start || start < __hyp_private_va_base)
return -EINVAL;
/* The allocated size is always a multiple of PAGE_SIZE */
@@ -60,7 +60,7 @@ static int __pkvm_alloc_private_va_range(unsigned long start, size_t size)
if (cur > __hyp_vmemmap)
return -ENOMEM;
- __io_map_base = cur;
+ __hyp_private_va_base = cur;
return 0;
}
@@ -70,8 +70,8 @@ static int __pkvm_alloc_private_va_range(unsigned long start, size_t size)
* @size: The size of the VA range to reserve.
* @haddr: The hypervisor virtual start address of the allocation.
*
- * The private virtual address (VA) range is allocated above __io_map_base
- * and aligned based on the order of @size.
+ * The private virtual address (VA) range is allocated from
+ * __hyp_private_va_base and aligned based on the order of @size.
*
* Return: 0 on success or negative error code on failure.
*/
@@ -81,7 +81,7 @@ int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr)
int ret;
hyp_spin_lock(&pkvm_pgd_lock);
- addr = __io_map_base;
+ addr = __hyp_private_va_base;
ret = __pkvm_alloc_private_va_range(addr, size);
hyp_spin_unlock(&pkvm_pgd_lock);
@@ -365,7 +365,7 @@ static int create_fixblock(void)
return -EINVAL;
hyp_spin_lock(&pkvm_pgd_lock);
- addr = ALIGN(__io_map_base, PMD_SIZE);
+ addr = ALIGN(__hyp_private_va_base, PMD_SIZE);
ret = __pkvm_alloc_private_va_range(addr, PMD_SIZE);
if (ret)
goto unlock;
@@ -446,12 +446,13 @@ int hyp_create_idmap(u32 hyp_va_bits)
* memory -- see va_layout.c for more details. The other half of the VA
* space contains the trampoline page, and needs some care. Split that
* second half in two and find the quarter of VA space not conflicting
- * with the idmap to place the IOs and the vmemmap. IOs use the lower
- * half of the quarter and the vmemmap the upper half.
+ * with the idmap to place private mappings and the vmemmap. Private
+ * mappings use the lower half of the quarter and the vmemmap the upper
+ * half.
*/
- __io_map_base = start & BIT(hyp_va_bits - 2);
- __io_map_base ^= BIT(hyp_va_bits - 2);
- __hyp_vmemmap = __io_map_base | BIT(hyp_va_bits - 3);
+ __hyp_private_va_base = start & BIT(hyp_va_bits - 2);
+ __hyp_private_va_base ^= BIT(hyp_va_bits - 2);
+ __hyp_vmemmap = __hyp_private_va_base | BIT(hyp_va_bits - 3);
return __pkvm_create_mappings(start, end - start, start, PAGE_HYP_EXEC);
}
@@ -464,13 +465,13 @@ int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr)
hyp_spin_lock(&pkvm_pgd_lock);
- prev_base = __io_map_base;
+ prev_base = __hyp_private_va_base;
/*
* 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;
- addr = ALIGN(__io_map_base, size);
+ addr = ALIGN(__hyp_private_va_base, size);
ret = __pkvm_alloc_private_va_range(addr, size);
if (!ret) {
@@ -486,7 +487,7 @@ int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr)
ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr + NVHE_STACK_SIZE,
NVHE_STACK_SIZE, phys, PAGE_HYP);
if (ret)
- __io_map_base = prev_base;
+ __hyp_private_va_base = prev_base;
}
hyp_spin_unlock(&pkvm_pgd_lock);
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* [RFC PATCH 5/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings
2026-07-16 14:09 [RFC PATCH 0/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings Aneesh Kumar K.V (Arm)
` (3 preceding siblings ...)
2026-07-16 14:09 ` [RFC PATCH 4/5] KVM: arm64: Rename the hyp private VA allocation base Aneesh Kumar K.V (Arm)
@ 2026-07-16 14:09 ` Aneesh Kumar K.V (Arm)
2026-07-16 14:27 ` sashiko-bot
4 siblings, 1 reply; 8+ messages in thread
From: Aneesh Kumar K.V (Arm) @ 2026-07-16 14:09 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel, kvmarm
Cc: Aneesh Kumar K.V (Arm), Marc Zyngier, Oliver Upton, Joey Gouly,
Steffen Eiden, Suzuki K Poulose, Zenghui Yu, Catalin Marinas,
Will Deacon
hVHE currently disables TTBR1_EL2 and places both the identity mapping
and runtime hyp mappings in TTBR0_EL2. This unnecessarily retains the
legacy nVHE VA layout even though hVHE can use canonical kernel-image
addresses through the EL2&0 translation regime.
Place hVHE runtime mappings in TTBR1_EL2 and reserve TTBR0_EL2 for the
identity mapping used during MMU and page-table transitions. Select this
layout based on hVHE support independently of protected mode, while
retaining the existing TTBR0-only layout for nVHE and protected nVHE.
Keep hyp symbols at their linked kernel-image VAs, disable the legacy VA
relocations for hVHE, and configure TCR_EL2 for both translation ranges.
Allocate separate runtime and idmap page tables during initial setup and
pKVM finalization, pass both roots through the per-CPU initialization
parameters, and install both during page-table transitions.
Add support for walking canonical TTBR1 hyp page tables, including
handling the wrap at the top of the address space. Use this when fixing
page-table reference counts and destroying hyp page tables.
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
arch/arm64/include/asm/kvm_asm.h | 3 +-
arch/arm64/include/asm/kvm_hyp.h | 4 +-
arch/arm64/include/asm/kvm_mmu.h | 46 ++++++++++++++++++---
arch/arm64/include/asm/kvm_pgtable.h | 27 ++++++++++++
arch/arm64/include/asm/kvm_pkvm.h | 3 ++
arch/arm64/kernel/asm-offsets.c | 5 ++-
arch/arm64/kvm/arm.c | 47 +++++++++++++--------
arch/arm64/kvm/hyp/include/nvhe/mm.h | 1 +
arch/arm64/kvm/hyp/nvhe/hyp-init.S | 29 ++++++++++---
arch/arm64/kvm/hyp/nvhe/mm.c | 24 +++++++++++
arch/arm64/kvm/hyp/nvhe/setup.c | 35 ++++++++++++++--
arch/arm64/kvm/hyp/pgtable.c | 62 +++++++++++++++++++++++++---
arch/arm64/kvm/mmu.c | 57 +++++++++++++++++++++++--
arch/arm64/kvm/pkvm.c | 3 ++
arch/arm64/kvm/va_layout.c | 32 +++++++++++---
15 files changed, 328 insertions(+), 50 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 6e0cc007bfe1..e42baadf7990 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -210,7 +210,8 @@ struct kvm_nvhe_init_params {
unsigned long tpidr_el2;
unsigned long stack_hyp_va;
unsigned long stack_pa;
- phys_addr_t pgd_pa;
+ phys_addr_t ttbr0_pgd_pa;
+ phys_addr_t ttbr1_pgd_pa;
unsigned long hcr_el2;
unsigned long vttbr;
unsigned long vtcr;
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 4974492744cc..5cc196f84958 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -131,8 +131,8 @@ void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
#endif
#ifdef __KVM_NVHE_HYPERVISOR__
-void __pkvm_init_switch_pgd(phys_addr_t pgd, unsigned long sp,
- void (*fn)(void));
+void __pkvm_init_switch_pgd(phys_addr_t ttbr0, phys_addr_t ttbr1,
+ unsigned long sp, void (*fn)(void));
int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long *per_cpu_base, u32 hyp_va_bits);
void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);
#endif
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index bcc8e28985f7..30ac5cecaa93 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -105,6 +105,7 @@ alternative_cb_end
#include <asm/kvm_emulate.h>
#include <asm/kvm_host.h>
#include <asm/kvm_nested.h>
+#include <asm/virt.h>
void kvm_update_va_mask(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst);
@@ -112,13 +113,28 @@ void kvm_compute_layout(void);
u32 kvm_hyp_va_bits(void);
void kvm_apply_hyp_relocations(void);
+static __always_inline bool kvm_hyp_init_uses_ttbr1(void)
+{
+ BUILD_BUG_ON(__is_defined(__KVM_NVHE_HYPERVISOR__));
+
+ return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_HVHE);
+}
+
+static __always_inline bool kvm_hyp_uses_ttbr1(void)
+{
+ return cpus_have_final_cap(ARM64_KVM_HVHE);
+}
+
/**
* kvm_hyp_kimg_kaddr - Select the kernel address used for an EL2 mapping
* @ptr: Address within the kernel image
*
- * Return @ptr when EL2 uses the kernel-image address directly, as with
- * VHE. Otherwise return the corresponding linear-map alias used as input
- * to the legacy nVHE VA conversion.
+ * Return @ptr when EL2 uses the kernel-image address directly, as with VHE
+ * or hVHE TTBR1. Otherwise return the corresponding linear-map alias used
+ * as input to the legacy nVHE VA conversion.
+ *
+ * This helper relies on finalized CPU capabilities and must not be used from
+ * earlier boot stages.
*
* Return: A kernel address suitable as the basis for an EL2 virtual address.
*/
@@ -126,10 +142,11 @@ static __always_inline void *kvm_hyp_kimg_kaddr(void *ptr)
{
/*
* With VHE, the host runs at EL2 using the kernel mapping, so
- * kernel-image VAs need no translation.
- * Only legacy nVHE requires a linear-map alias.
+ * kernel-image VAs need no translation. hVHE similarly retains
+ * kernel-image VAs in its TTBR1 EL2 mapping. Only legacy nVHE
+ * requires a linear-map alias.
*/
- if (is_kernel_in_hyp_mode())
+ if (is_kernel_in_hyp_mode() || kvm_hyp_uses_ttbr1())
return ptr;
return lm_alias(ptr);
@@ -137,6 +154,22 @@ static __always_inline void *kvm_hyp_kimg_kaddr(void *ptr)
#define __hyp_linear_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset)
#define __hyp_symbol_pa(x) (((phys_addr_t)(x)) + hyp_symbol_physvirt_offset)
+
+static __always_inline unsigned long kvm_hyp_ttbr1_private_start(void)
+{
+ return PAGE_ALIGN((unsigned long)__hyp_bss_end);
+}
+
+static __always_inline unsigned long kvm_hyp_ttbr1_private_end(void)
+{
+ return VMALLOC_END;
+}
+
+static __always_inline unsigned long kvm_hyp_ttbr1_vmemmap_base(void)
+{
+ return kvm_hyp_ttbr1_private_start() + SZ_1G;
+}
+
/*
* Convert a kernel VA into a HYP VA.
*
@@ -228,6 +261,7 @@ int kvm_handle_guest_sea(struct kvm_vcpu *vcpu);
int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
phys_addr_t kvm_mmu_get_httbr(void);
+phys_addr_t kvm_mmu_get_hyp_ttbr1(void);
phys_addr_t kvm_get_idmap_vector(void);
int __init kvm_mmu_init(u32 hyp_va_bits);
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 41a8687938eb..1d51dcaaac0d 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -255,6 +255,14 @@ enum kvm_pgtable_stage2_flags {
KVM_PGTABLE_S2_AS_S1 = BIT(1),
};
+/**
+ * enum kvm_pgtable_hyp_flags - Hypervisor page-table flags.
+ * @KVM_PGTABLE_HYP_TTBR1: Walk TTBR1 canonical virtual addresses.
+ */
+enum kvm_pgtable_hyp_flags {
+ KVM_PGTABLE_HYP_TTBR1 = BIT(0),
+};
+
/**
* enum kvm_pgtable_prot - Page-table permissions and attributes.
* @KVM_PGTABLE_PROT_UX: Unprivileged execute permission.
@@ -443,6 +451,7 @@ static inline bool kvm_pgtable_walk_lock_held(void)
* @start_level: Level at which the page-table walk starts.
* @pgd: Pointer to the first top-level entry of the page-table.
* @mm_ops: Memory management callbacks.
+ * @hyp_flags: Hypervisor page-table flags.
* @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables.
* @flags: Stage-2 page-table flags.
* @force_pte_cb: Function that returns true if page level mappings must
@@ -457,6 +466,9 @@ struct kvm_pgtable {
kvm_pteref_t pgd;
struct kvm_pgtable_mm_ops *mm_ops;
+ /* Hyp only */
+ enum kvm_pgtable_hyp_flags hyp_flags;
+
/* Stage-2 only */
enum kvm_pgtable_stage2_flags flags;
kvm_pgtable_force_pte_cb_t force_pte_cb;
@@ -465,6 +477,11 @@ struct kvm_pgtable {
struct kvm_s2_mmu *mmu;
};
+static inline void kvm_pgtable_hyp_enable_ttbr1(struct kvm_pgtable *pgt)
+{
+ pgt->hyp_flags |= KVM_PGTABLE_HYP_TTBR1;
+}
+
/**
* kvm_pgtable_hyp_init() - Initialise a hypervisor stage-1 page-table.
* @pgt: Uninitialised page-table structure to initialise.
@@ -851,6 +868,16 @@ int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size,
int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
struct kvm_pgtable_walker *walker);
+/**
+ * kvm_pgtable_hyp_walk() - Walk the entire usable VA range of a hyp pgtable.
+ * @pgt: Page-table structure initialised by kvm_pgtable_hyp_init().
+ * @walker: Walker callback description.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_hyp_walk(struct kvm_pgtable *pgt,
+ struct kvm_pgtable_walker *walker);
+
/**
* kvm_pgtable_get_leaf() - Walk a page-table and retrieve the leaf entry
* with its level.
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index 74fedd9c5ff0..e632fe4ec43c 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -139,6 +139,9 @@ static inline unsigned long hyp_s1_pgtable_pages(void)
/* Allow 1 GiB for private mappings */
res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT);
+ /* Allow a separate TTBR0 idmap page-table. */
+ res += __hyp_pgtable_max_pages(1);
+
return res;
}
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index b6367ff3a49c..f95883771d34 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -120,7 +120,10 @@ int main(void)
DEFINE(NVHE_INIT_TCR_EL2, offsetof(struct kvm_nvhe_init_params, tcr_el2));
DEFINE(NVHE_INIT_TPIDR_EL2, offsetof(struct kvm_nvhe_init_params, tpidr_el2));
DEFINE(NVHE_INIT_STACK_HYP_VA, offsetof(struct kvm_nvhe_init_params, stack_hyp_va));
- DEFINE(NVHE_INIT_PGD_PA, offsetof(struct kvm_nvhe_init_params, pgd_pa));
+ DEFINE(NVHE_INIT_TTBR0_PGD_PA,
+ offsetof(struct kvm_nvhe_init_params, ttbr0_pgd_pa));
+ DEFINE(NVHE_INIT_TTBR1_PGD_PA,
+ offsetof(struct kvm_nvhe_init_params, ttbr1_pgd_pa));
DEFINE(NVHE_INIT_HCR_EL2, offsetof(struct kvm_nvhe_init_params, hcr_el2));
DEFINE(NVHE_INIT_VTTBR, offsetof(struct kvm_nvhe_init_params, vttbr));
DEFINE(NVHE_INIT_VTCR, offsetof(struct kvm_nvhe_init_params, vtcr));
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 924f33c1a9d4..f2ea75461c1f 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2124,38 +2124,51 @@ static int kvm_init_vector_slots(void)
return 0;
}
+static unsigned long __init kvm_compute_hyp_tcr(u32 hyp_va_bits)
+{
+ unsigned long tcr = read_sysreg(tcr_el1);
+
+ if (cpus_have_final_cap(ARM64_KVM_HVHE)) {
+ tcr &= ~(TCR_HD | TCR_HA | TCR_A1 | TCR_T0SZ_MASK |
+ TCR_T1SZ_MASK |
+ TCR_EPD0_MASK | TCR_EPD1_MASK);
+
+ if (kvm_hyp_uses_ttbr1())
+ tcr |= TCR_T1SZ(hyp_va_bits);
+ else
+ tcr |= TCR_EPD1_MASK;
+ } else {
+ unsigned long ips = FIELD_GET(TCR_IPS_MASK, tcr);
+
+ tcr &= TCR_EL2_MASK;
+ tcr |= TCR_EL2_RES1 | FIELD_PREP(TCR_EL2_PS_MASK, ips);
+ if (lpa2_is_enabled())
+ tcr |= TCR_EL2_DS;
+ }
+
+ return tcr | TCR_T0SZ(hyp_va_bits);
+}
+
static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
{
struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
- unsigned long tcr;
/*
* Calculate the raw per-cpu offset without a translation from the
* kernel's mapping to the linear mapping, and store it in tpidr_el2
* so that we can use adr_l to access per-cpu variables in EL2.
+ * In TTBR1 mode, this is the delta from the canonical hyp symbol to
+ * the linear-map VA at which the allocated per-cpu copy is mapped.
* Also drop the KASAN tag which gets in the way...
*/
params->tpidr_el2 = (unsigned long)kasan_reset_tag(per_cpu_ptr_nvhe_sym(__per_cpu_start, cpu)) -
(unsigned long)kvm_hyp_kimg_kaddr(CHOOSE_NVHE_SYM(__per_cpu_start));
params->mair_el2 = read_sysreg(mair_el1);
+ params->tcr_el2 = kvm_compute_hyp_tcr(hyp_va_bits);
- tcr = read_sysreg(tcr_el1);
- if (cpus_have_final_cap(ARM64_KVM_HVHE)) {
- tcr &= ~(TCR_HD | TCR_HA | TCR_A1 | TCR_T0SZ_MASK);
- tcr |= TCR_EPD1_MASK;
- } else {
- unsigned long ips = FIELD_GET(TCR_IPS_MASK, tcr);
-
- tcr &= TCR_EL2_MASK;
- tcr |= TCR_EL2_RES1 | FIELD_PREP(TCR_EL2_PS_MASK, ips);
- if (lpa2_is_enabled())
- tcr |= TCR_EL2_DS;
- }
- tcr |= TCR_T0SZ(hyp_va_bits);
- params->tcr_el2 = tcr;
-
- params->pgd_pa = kvm_mmu_get_httbr();
+ params->ttbr0_pgd_pa = kvm_mmu_get_httbr();
+ params->ttbr1_pgd_pa = kvm_mmu_get_hyp_ttbr1();
if (is_protected_kvm_enabled())
params->hcr_el2 = HCR_HOST_NVHE_PROTECTED_FLAGS;
else
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h
index c41152c84705..46f008ee6916 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h
@@ -11,6 +11,7 @@
#include <nvhe/spinlock.h>
extern struct kvm_pgtable pkvm_pgtable;
+extern struct kvm_pgtable pkvm_idmap_pgtable;
extern hyp_spinlock_t pkvm_pgd_lock;
int hyp_create_fixmap(void);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 89cb553be1e5..07fc29c34fb3 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -127,13 +127,22 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init)
ldr x1, [x0, #NVHE_INIT_VTCR]
msr vtcr_el2, x1
- ldr x1, [x0, #NVHE_INIT_PGD_PA]
+ ldr x1, [x0, #NVHE_INIT_TTBR0_PGD_PA]
phys_to_ttbr x2, x1
alternative_if ARM64_HAS_CNP
orr x2, x2, #TTBRx_EL1_CnP
alternative_else_nop_endif
msr ttbr0_el2, x2
+ ldr x1, [x0, #NVHE_INIT_TTBR1_PGD_PA]
+ cbz x1, 2f
+ phys_to_ttbr x2, x1
+alternative_if ARM64_HAS_CNP
+ orr x2, x2, #TTBRx_EL1_CnP
+alternative_else_nop_endif
+ msr_s SYS_TTBR1_EL2, x2
+2:
+
ldr x0, [x0, #NVHE_INIT_TCR_EL2]
msr tcr_el2, x0
@@ -261,13 +270,15 @@ reset:
SYM_CODE_END(__kvm_handle_stub_hvc)
/*
- * void __pkvm_init_switch_pgd(phys_addr_t pgd, unsigned long sp,
- * void (*fn)(void));
+ * void __pkvm_init_switch_pgd(phys_addr_t ttbr0, phys_addr_t ttbr1,
+ * unsigned long sp, void (*fn)(void));
*
* SYM_TYPED_FUNC_START() allows C to call this ID-mapped function indirectly
* using a physical pointer without triggering a kCFI failure.
*/
SYM_TYPED_FUNC_START(__pkvm_init_switch_pgd)
+ mov x6, x3
+
/* Turn the MMU off */
pre_disable_mmu_workaround
mrs x3, sctlr_el2
@@ -284,14 +295,22 @@ alternative_if ARM64_HAS_CNP
alternative_else_nop_endif
msr ttbr0_el2, x5
+ cbz x1, 1f
+ phys_to_ttbr x5, x1
+alternative_if ARM64_HAS_CNP
+ orr x5, x5, #TTBRx_EL1_CnP
+alternative_else_nop_endif
+ msr_s SYS_TTBR1_EL2, x5
+1:
+
/* Set the new stack pointer */
- mov sp, x1
+ mov sp, x2
/* And turn the MMU back on! */
dsb nsh
isb
set_sctlr_el2 x3
- ret x2
+ ret x6
SYM_FUNC_END(__pkvm_init_switch_pgd)
.popsection
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 3233a7c70f7c..c856b2399960 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -19,6 +19,7 @@
#include <nvhe/spinlock.h>
struct kvm_pgtable pkvm_pgtable;
+struct kvm_pgtable pkvm_idmap_pgtable;
hyp_spinlock_t pkvm_pgd_lock;
struct memblock_region hyp_memory[HYP_MEMBLOCK_REGIONS];
@@ -431,6 +432,22 @@ int hyp_create_fixmap(void)
return create_fixblock();
}
+static int pkvm_map_idmap_text(unsigned long start, unsigned long end)
+{
+ unsigned long idmap_start, idmap_end;
+
+ idmap_start = __hyp_symbol_pa(__hyp_idmap_text_start);
+ idmap_start = ALIGN_DOWN(idmap_start, PAGE_SIZE);
+ idmap_end = __hyp_symbol_pa(__hyp_idmap_text_end);
+ idmap_end = ALIGN(idmap_end, PAGE_SIZE);
+
+ if (WARN_ON(start != idmap_start || end != idmap_end))
+ return -EINVAL;
+
+ return kvm_pgtable_hyp_map(&pkvm_idmap_pgtable, start,
+ end - start, start, PAGE_HYP_EXEC);
+}
+
int hyp_create_idmap(u32 hyp_va_bits)
{
unsigned long start, end;
@@ -441,6 +458,13 @@ int hyp_create_idmap(u32 hyp_va_bits)
end = __hyp_symbol_pa(__hyp_idmap_text_end);
end = ALIGN(end, PAGE_SIZE);
+ if (kvm_hyp_uses_ttbr1()) {
+ __hyp_private_va_base = kvm_hyp_ttbr1_private_start();
+ __hyp_vmemmap = kvm_hyp_ttbr1_vmemmap_base();
+
+ return pkvm_map_idmap_text(start, end);
+ }
+
/*
* One half of the VA space is reserved to linearly map portions of
* memory -- see va_layout.c for more details. The other half of the VA
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 2ef1972cc3dd..45b8f7213e39 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -109,6 +109,15 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
if (ret)
return ret;
+ if (kvm_hyp_uses_ttbr1()) {
+ kvm_pgtable_hyp_enable_ttbr1(&pkvm_pgtable);
+
+ ret = kvm_pgtable_hyp_init(&pkvm_idmap_pgtable, hyp_va_bits,
+ &hyp_early_alloc_mm_ops);
+ if (ret)
+ return ret;
+ }
+
ret = hyp_create_idmap(hyp_va_bits);
if (ret)
return ret;
@@ -169,12 +178,27 @@ static void update_nvhe_init_params(void)
for (i = 0; i < hyp_nr_cpus; i++) {
params = per_cpu_ptr(&kvm_init_params, i);
- params->pgd_pa = __hyp_linear_pa(pkvm_pgtable.pgd);
+ params->ttbr0_pgd_pa = kvm_hyp_uses_ttbr1() ?
+ __hyp_linear_pa(pkvm_idmap_pgtable.pgd) :
+ __hyp_linear_pa(pkvm_pgtable.pgd);
+ params->ttbr1_pgd_pa = kvm_hyp_uses_ttbr1() ?
+ __hyp_linear_pa(pkvm_pgtable.pgd) : 0;
dcache_clean_inval_poc((unsigned long)params,
(unsigned long)params + sizeof(*params));
}
}
+static bool pkvm_init_ttbrs_valid(struct kvm_nvhe_init_params *params)
+{
+ if (!params->ttbr0_pgd_pa)
+ return false;
+
+ if (kvm_hyp_uses_ttbr1())
+ return params->ttbr1_pgd_pa;
+
+ return !params->ttbr1_pgd_pa;
+}
+
static void *hyp_zalloc_hyp_page(void *arg)
{
return hyp_alloc_pages(&hpool, 0);
@@ -284,8 +308,7 @@ static int fix_hyp_pgtable_refcnt(void)
.arg = pkvm_pgtable.mm_ops,
};
- return kvm_pgtable_walk(&pkvm_pgtable, 0, BIT(pkvm_pgtable.ia_bits),
- &walker);
+ return kvm_pgtable_hyp_walk(&pkvm_pgtable, &walker);
}
void __noreturn __pkvm_init_finalise(void)
@@ -371,8 +394,12 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long *per_cpu_bas
/* Jump in the idmap page to switch to the new page-tables */
params = this_cpu_ptr(&kvm_init_params);
+ if (WARN_ON(!pkvm_init_ttbrs_valid(params)))
+ return -EINVAL;
+
fn = (typeof(fn))__hyp_symbol_pa(__pkvm_init_switch_pgd);
- fn(params->pgd_pa, params->stack_hyp_va, __pkvm_init_finalise);
+ fn(params->ttbr0_pgd_pa, params->ttbr1_pgd_pa,
+ params->stack_hyp_va, __pkvm_init_finalise);
unreachable();
}
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 91a7dfad6686..ca07fc2a55ec 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -10,6 +10,7 @@
#include <linux/bitfield.h>
#include <asm/kvm_pgtable.h>
#include <asm/stage2_pgtable.h>
+#include <asm/kvm_mmu.h>
struct kvm_pgtable_walk_data {
struct kvm_pgtable_walker *walker;
@@ -71,6 +72,31 @@ static u32 kvm_pgd_pages(u32 ia_bits, s8 start_level)
return kvm_pgd_page_idx(&pgt, -1ULL) + 1;
}
+static bool kvm_pgtable_walk_range_valid(struct kvm_pgtable *pgt,
+ struct kvm_pgtable_walk_data *data)
+{
+ u64 limit = BIT(pgt->ia_bits);
+ u64 mask = limit - 1;
+ u64 last = data->end - 1;
+
+ if (data->addr > data->end)
+ return false;
+
+ if (!(pgt->hyp_flags & KVM_PGTABLE_HYP_TTBR1))
+ return data->addr <= limit && data->end <= limit;
+
+ /*
+ * TTBR1 hyp walks use canonical virtual addresses supplied by the
+ * caller. The index helpers extract the relevant bits for each level;
+ * the masked comparison here only rejects ranges that cross out of the
+ * single TTBR1 address window described by ia_bits.
+ */
+ if ((data->addr | mask) != ~0ULL || (last | mask) != ~0ULL)
+ return false;
+
+ return (data->addr & mask) <= (last & mask);
+}
+
static bool kvm_pte_table(kvm_pte_t pte, s8 level)
{
if (level == KVM_PGTABLE_LAST_LEVEL)
@@ -193,8 +219,13 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
goto out;
if (!table) {
- data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level));
- data->addr += kvm_granule_size(level);
+ u64 granule = kvm_granule_size(level);
+ u64 addr = ALIGN_DOWN(data->addr, granule);
+
+ if (granule > data->end - addr)
+ data->addr = data->end;
+ else
+ data->addr = addr + granule;
goto out;
}
@@ -241,9 +272,8 @@ static int _kvm_pgtable_walk(struct kvm_pgtable *pgt, struct kvm_pgtable_walk_da
{
u32 idx;
int ret = 0;
- u64 limit = BIT(pgt->ia_bits);
- if (data->addr > limit || data->end > limit)
+ if (!kvm_pgtable_walk_range_valid(pgt, data))
return -ERANGE;
if (!pgt->pgd)
@@ -281,6 +311,26 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
return r;
}
+int kvm_pgtable_hyp_walk(struct kvm_pgtable *pgt,
+ struct kvm_pgtable_walker *walker)
+{
+ u64 size = BIT(pgt->ia_bits);
+ u64 addr = 0;
+
+ if (pgt->hyp_flags & KVM_PGTABLE_HYP_TTBR1) {
+ addr = -size;
+
+ /*
+ * The exclusive end of the TTBR1 range cannot be represented in
+ * a u64. Exclude the last page, which cannot be mapped through
+ * kvm_pgtable_walk() for the same reason.
+ */
+ size -= PAGE_SIZE;
+ }
+
+ return kvm_pgtable_walk(pgt, addr, size, walker);
+}
+
struct leaf_walk_data {
kvm_pte_t pte;
s8 level;
@@ -539,6 +589,7 @@ int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
pgt->ia_bits = va_bits;
pgt->start_level = start_level;
pgt->mm_ops = mm_ops;
+ pgt->hyp_flags = 0;
pgt->mmu = NULL;
pgt->force_pte_cb = NULL;
@@ -568,7 +619,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt)
.flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST,
};
- WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker));
+ WARN_ON(kvm_pgtable_hyp_walk(pgt, &walker));
pgt->mm_ops->put_page(kvm_dereference_pteref(&walker, pgt->pgd));
pgt->pgd = NULL;
}
@@ -1589,6 +1640,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
pgt->start_level = start_level;
pgt->mm_ops = mm_ops;
pgt->mmu = mmu;
+ pgt->hyp_flags = 0;
pgt->flags = flags;
pgt->force_pte_cb = force_pte_cb;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 154d53dca619..46fd7040bca7 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -20,11 +20,13 @@
#include <asm/kvm_pkvm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
+#include <asm/sections.h>
#include <asm/virt.h>
#include "trace.h"
static struct kvm_pgtable *hyp_pgtable;
+static struct kvm_pgtable *hyp_idmap_pgtable;
static DEFINE_MUTEX(kvm_hyp_pgd_mutex);
static unsigned long __ro_after_init hyp_idmap_start;
@@ -392,6 +394,11 @@ static void stage2_flush_vm(struct kvm *kvm)
void __init free_hyp_pgds(void)
{
mutex_lock(&kvm_hyp_pgd_mutex);
+ if (hyp_idmap_pgtable) {
+ kvm_pgtable_hyp_destroy(hyp_idmap_pgtable);
+ kfree(hyp_idmap_pgtable);
+ hyp_idmap_pgtable = NULL;
+ }
if (hyp_pgtable) {
kvm_pgtable_hyp_destroy(hyp_pgtable);
kfree(hyp_pgtable);
@@ -2481,6 +2488,17 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
phys_addr_t kvm_mmu_get_httbr(void)
{
+ if (hyp_idmap_pgtable)
+ return __pa(hyp_idmap_pgtable->pgd);
+
+ return __pa(hyp_pgtable->pgd);
+}
+
+phys_addr_t kvm_mmu_get_hyp_ttbr1(void)
+{
+ if (!kvm_hyp_uses_ttbr1())
+ return 0;
+
return __pa(hyp_pgtable->pgd);
}
@@ -2491,9 +2509,15 @@ phys_addr_t kvm_get_idmap_vector(void)
static int kvm_map_idmap_text(void)
{
+ struct kvm_pgtable *pgt = hyp_idmap_pgtable ?: hyp_pgtable;
unsigned long size = hyp_idmap_end - hyp_idmap_start;
- int err = __create_hyp_mappings(hyp_idmap_start, size, hyp_idmap_start,
- PAGE_HYP_EXEC);
+ int err;
+
+ if (WARN_ON(kvm_hyp_uses_ttbr1() && !hyp_idmap_pgtable))
+ return -EINVAL;
+
+ err = kvm_pgtable_hyp_map(pgt, hyp_idmap_start, size, hyp_idmap_start,
+ PAGE_HYP_EXEC);
if (err)
kvm_err("Failed to idmap %lx-%lx\n",
hyp_idmap_start, hyp_idmap_end);
@@ -2559,14 +2583,39 @@ int __init kvm_mmu_init(u32 hyp_va_bits)
if (err)
goto out_free_pgtable;
+ if (kvm_hyp_uses_ttbr1()) {
+ kvm_pgtable_hyp_enable_ttbr1(hyp_pgtable);
+
+ hyp_idmap_pgtable = kzalloc_obj(*hyp_idmap_pgtable);
+ if (!hyp_idmap_pgtable) {
+ kvm_err("Hyp mode idmap page-table not allocated\n");
+ err = -ENOMEM;
+ goto out_destroy_pgtable;
+ }
+
+ err = kvm_pgtable_hyp_init(hyp_idmap_pgtable, hyp_va_bits,
+ &kvm_hyp_mm_ops);
+ if (err)
+ goto out_free_idmap_pgtable;
+ }
+
err = kvm_map_idmap_text();
if (err)
- goto out_destroy_pgtable;
+ goto out_destroy_idmap_pgtable;
- io_map_base = hyp_idmap_start;
+ if (kvm_hyp_uses_ttbr1())
+ io_map_base = kvm_hyp_ttbr1_private_end();
+ else
+ io_map_base = hyp_idmap_start;
__hyp_va_bits = hyp_va_bits;
return 0;
+out_destroy_idmap_pgtable:
+ if (hyp_idmap_pgtable)
+ kvm_pgtable_hyp_destroy(hyp_idmap_pgtable);
+out_free_idmap_pgtable:
+ kfree(hyp_idmap_pgtable);
+ hyp_idmap_pgtable = NULL;
out_destroy_pgtable:
kvm_pgtable_hyp_destroy(hyp_pgtable);
out_free_pgtable:
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 053e4f733e4b..1352c89d2bd8 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -292,6 +292,9 @@ static int __init finalize_pkvm(void)
ret = pkvm_drop_host_privileges();
if (ret)
pr_err("Failed to finalize Hyp protection: %d\n", ret);
+ else
+ kvm_info("pKVM finalized in %s mode\n",
+ kvm_hyp_uses_ttbr1() ? "hVHE" : "nVHE");
return ret;
}
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index 75a89ad8fecf..1e1816995fe4 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -33,19 +33,29 @@ static u64 __early_kern_hyp_va(u64 addr)
return addr;
}
+static u64 __early_kern_sym_hyp_va(void *ptr)
+{
+ if (is_kernel_in_hyp_mode() || kvm_hyp_init_uses_ttbr1())
+ return (u64)ptr;
+
+ return __early_kern_hyp_va((u64)lm_alias(ptr));
+}
+
/*
* Store a hyp VA <-> PA offset into a EL2-owned variable.
*/
static void init_hyp_physvirt_offset(void)
{
- u64 kern_va, hyp_va;
+ u64 kern_va, hyp_va, sym_va;
/* Compute the offset from the hyp VA and PA of a random symbol. */
kern_va = (u64)lm_alias(__hyp_text_start);
hyp_va = __early_kern_hyp_va(kern_va);
hyp_physvirt_offset = (s64)__pa(kern_va) - (s64)hyp_va;
- hyp_symbol_physvirt_offset = hyp_physvirt_offset;
+ sym_va = __early_kern_sym_hyp_va(__hyp_text_start);
+ hyp_symbol_physvirt_offset = (s64)__pa_symbol(__hyp_text_start) -
+ (s64)sym_va;
}
/*
@@ -87,6 +97,14 @@ __init void kvm_compute_layout(void)
u64 hyp_va_msb;
u32 hyp_va_bits = kvm_hyp_va_bits();
+ if (kvm_hyp_init_uses_ttbr1()) {
+ tag_lsb = 0;
+ tag_val = 0;
+ va_mask = ~0ULL;
+ init_hyp_physvirt_offset();
+ return;
+ }
+
/* Where is my RAM region? */
hyp_va_msb = idmap_addr & BIT(hyp_va_bits - 1);
hyp_va_msb ^= BIT(hyp_va_bits - 1);
@@ -117,6 +135,9 @@ __init void kvm_apply_hyp_relocations(void)
int32_t *begin = (int32_t *)__hyp_reloc_begin;
int32_t *end = (int32_t *)__hyp_reloc_end;
+ if (kvm_hyp_init_uses_ttbr1())
+ return;
+
for (rel = begin; rel < end; ++rel) {
uintptr_t *ptr, kimg_va;
@@ -187,14 +208,15 @@ void __init kvm_update_va_mask(struct alt_instr *alt,
u32 rd, rn, insn, oinsn;
/*
- * VHE doesn't need any address translation, let's NOP
+ * VHE/hVHE doesn't need any address translation, let's NOP
* everything.
*
* Alternatively, if the tag is zero (because the layout
* dictates it and we don't have any spare bits in the
* address), NOP everything after masking the kernel VA.
*/
- if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN) || (!tag_val && i > 0)) {
+ if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN) ||
+ kvm_hyp_init_uses_ttbr1() || (!tag_val && i > 0)) {
updptr[i] = cpu_to_le32(aarch64_insn_gen_nop());
continue;
}
@@ -225,7 +247,7 @@ void kvm_patch_vector_branch(struct alt_instr *alt,
/*
* Compute HYP VA by using the same computation as kern_hyp_va()
*/
- addr = __early_kern_hyp_va((u64)kvm_hyp_kimg_kaddr(__kvm_hyp_vector));
+ addr = __early_kern_sym_hyp_va(__kvm_hyp_vector);
/* Use PC[10:7] to branch to the same vector in KVM */
addr |= ((u64)origptr & GENMASK_ULL(10, 7));
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* Re: [RFC PATCH 5/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings
2026-07-16 14:09 ` [RFC PATCH 5/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings Aneesh Kumar K.V (Arm)
@ 2026-07-16 14:27 ` sashiko-bot
0 siblings, 0 replies; 8+ messages in thread
From: sashiko-bot @ 2026-07-16 14:27 UTC (permalink / raw)
To: Aneesh Kumar K.V (Arm); +Cc: kvmarm, Oliver Upton, Marc Zyngier
Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:
- [High] Spectre V3A vector hardening branch synthesis truncates TTBR1 canonical addresses, leading to a fatal EL2 Instruction Abort.
- [High] Writes to control-plane system registers (`SYS_TTBR1_EL2`) are not immediately followed by an `isb()` instruction.
- [Medium] The error-handling branches following `WARN_ON` at EL2 are dead code, as `WARN_ON` expands to a fatal `BRK` instruction.
- [Medium] Unvalidated software feature override leads to fatal hVHE layout mismatch on unsupported hardware.
--
--- Patch [5]: [RFC PATCH 5/5] KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings ---
commit c5a5f8a98b4a3d3fc85945a12a0935f8530f85d7
Author: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
KVM: arm64: Use TTBR1_EL2 for hVHE runtime mappings
This patch updates hVHE to place runtime mappings in TTBR1_EL2 and reserves
TTBR0_EL2 for the identity mapping used during MMU transitions. It introduces
support for walking canonical TTBR1 hyp page tables while retaining the
existing TTBR0-only layout for nVHE.
> diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
> index bcc8e28985f70..30ac5cecaa93b 100644
> --- a/arch/arm64/include/asm/kvm_mmu.h
> +++ b/arch/arm64/include/asm/kvm_mmu.h
> @@ -112,13 +113,28 @@ void kvm_compute_layout(void);
> u32 kvm_hyp_va_bits(void);
> void kvm_apply_hyp_relocations(void);
>
> +static __always_inline bool kvm_hyp_init_uses_ttbr1(void)
> +{
> + BUILD_BUG_ON(__is_defined(__KVM_NVHE_HYPERVISOR__));
> +
> + return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_HVHE);
> +}
[Severity: Medium]
Will this lead to a fatal hVHE layout mismatch on hardware that does not
support VHE?
If a user specifies the arm64.sw_feature_override=hvhe command-line parameter
on an unsupported CPU, early initialization will use the TTBR1 layout based on
this override. However, the final CPU capabilities check in
kvm_hyp_uses_ttbr1() evaluates to false, causing a desynchronization between
early-boot and runtime page table layouts.
[ ... ]
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
> index 89cb553be1e55..07fc29c34fb36 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
> @@ -127,13 +127,22 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init)
> ldr x1, [x0, #NVHE_INIT_VTCR]
> msr vtcr_el2, x1
>
> - ldr x1, [x0, #NVHE_INIT_PGD_PA]
> + ldr x1, [x0, #NVHE_INIT_TTBR0_PGD_PA]
> phys_to_ttbr x2, x1
> alternative_if ARM64_HAS_CNP
> orr x2, x2, #TTBRx_EL1_CnP
> alternative_else_nop_endif
> msr ttbr0_el2, x2
>
> + ldr x1, [x0, #NVHE_INIT_TTBR1_PGD_PA]
> + cbz x1, 2f
> + phys_to_ttbr x2, x1
> +alternative_if ARM64_HAS_CNP
> + orr x2, x2, #TTBRx_EL1_CnP
> +alternative_else_nop_endif
> + msr_s SYS_TTBR1_EL2, x2
> +2:
> +
> ldr x0, [x0, #NVHE_INIT_TCR_EL2]
> msr tcr_el2, x0
[Severity: High]
Does the write to SYS_TTBR1_EL2 require an immediate isb?
Subsystem architectural invariants require every write to a control-plane
system register to be followed by an isb as the very next instruction. Since
it is delayed here behind register loads and another msr, intervening
instructions might execute against an undefined pipeline state.
[ ... ]
> @@ -284,14 +295,22 @@ alternative_if ARM64_HAS_CNP
> alternative_else_nop_endif
> msr ttbr0_el2, x5
>
> + cbz x1, 1f
> + phys_to_ttbr x5, x1
> +alternative_if ARM64_HAS_CNP
> + orr x5, x5, #TTBRx_EL1_CnP
> +alternative_else_nop_endif
> + msr_s SYS_TTBR1_EL2, x5
> +1:
> +
> /* Set the new stack pointer */
> - mov sp, x1
> + mov sp, x2
>
> /* And turn the MMU back on! */
> dsb nsh
> isb
[Severity: High]
Could the lack of an immediate isb after msr_s SYS_TTBR1_EL2 cause
unpredictable behavior here as well?
The isb is placed after the stack pointer assignment and dsb, which leaves a
window where instructions execute against an undefined pipeline state.
[ ... ]
> diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
> index 3233a7c70f7ca..c856b2399960c 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mm.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mm.c
> @@ -431,6 +432,22 @@ int hyp_create_fixmap(void)
> return create_fixblock();
> }
>
> +static int pkvm_map_idmap_text(unsigned long start, unsigned long end)
> +{
> + unsigned long idmap_start, idmap_end;
> +
> + idmap_start = __hyp_symbol_pa(__hyp_idmap_text_start);
> + idmap_start = ALIGN_DOWN(idmap_start, PAGE_SIZE);
> + idmap_end = __hyp_symbol_pa(__hyp_idmap_text_end);
> + idmap_end = ALIGN(idmap_end, PAGE_SIZE);
> +
> + if (WARN_ON(start != idmap_start || end != idmap_end))
> + return -EINVAL;
[Severity: Medium]
Is the error-handling branch following this WARN_ON dead code?
At EL2 in nVHE/pKVM, WARN_ON expands to a fatal BRK instruction which is
caught by the hypervisor panic handler. The subsystem does not support
warn-and-return semantics, meaning the return -EINVAL will never execute.
[ ... ]
> diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
> index 2ef1972cc3ddc..45b8f7213e396 100644
> --- a/arch/arm64/kvm/hyp/nvhe/setup.c
> +++ b/arch/arm64/kvm/hyp/nvhe/setup.c
> @@ -371,8 +394,12 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long *per_cpu_bas
>
> /* Jump in the idmap page to switch to the new page-tables */
> params = this_cpu_ptr(&kvm_init_params);
> + if (WARN_ON(!pkvm_init_ttbrs_valid(params)))
> + return -EINVAL;
> +
[Severity: Medium]
Similarly here, is this return -EINVAL unreachable?
The WARN_ON will trigger a hypervisor panic, so the recovery path cannot be
executed.
[ ... ]
> diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
> index 75a89ad8fecfe..1e1816995fe4f 100644
> --- a/arch/arm64/kvm/va_layout.c
> +++ b/arch/arm64/kvm/va_layout.c
> @@ -225,7 +247,7 @@ void kvm_patch_vector_branch(struct alt_instr *alt,
> /*
> * Compute HYP VA by using the same computation as kern_hyp_va()
> */
> - addr = __early_kern_hyp_va((u64)kvm_hyp_kimg_kaddr(__kvm_hyp_vector));
> + addr = __early_kern_sym_hyp_va(__kvm_hyp_vector);
>
> /* Use PC[10:7] to branch to the same vector in KVM */
> addr |= ((u64)origptr & GENMASK_ULL(10, 7));
[Severity: High]
Does the Spectre V3A vector hardening branch synthesis truncate TTBR1
canonical addresses?
The AARCH64_INSN_MOVEWIDE_ZERO instruction generated below clears bits 16-63
to zero:
insn = aarch64_insn_gen_movewide(AARCH64_INSN_REG_0,
(u16)addr,
0,
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_MOVEWIDE_ZERO);
*updptr++ = cpu_to_le32(insn);
This branch synthesis relies on a TTBR0 address format. Since a TTBR1 address
requires bits 48-63 to be set to 1, the address becomes corrupted. When the
hypervisor exits to the host, this truncated address could lead to a fatal EL2
Instruction Abort.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260716140936.4003182-1-aneesh.kumar@kernel.org?part=5
^ permalink raw reply [flat|nested] 8+ messages in thread