summaryrefslogtreecommitdiffstats
path: root/arch/arm64/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/include')
-rw-r--r--arch/arm64/include/asm/assembler.h27
-rw-r--r--arch/arm64/include/asm/cache.h6
-rw-r--r--arch/arm64/include/asm/cpu.h1
-rw-r--r--arch/arm64/include/asm/cpufeature.h8
-rw-r--r--arch/arm64/include/asm/esr.h15
-rw-r--r--arch/arm64/include/asm/fpsimdmacros.h8
-rw-r--r--arch/arm64/include/asm/irq.h2
-rw-r--r--arch/arm64/include/asm/kasan.h22
-rw-r--r--arch/arm64/include/asm/kernel-pgtable.h27
-rw-r--r--arch/arm64/include/asm/kvm_arm.h63
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h34
-rw-r--r--arch/arm64/include/asm/kvm_host.h140
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h7
-rw-r--r--arch/arm64/include/asm/kvm_nested.h56
-rw-r--r--arch/arm64/include/asm/kvm_pgtable.h80
-rw-r--r--arch/arm64/include/asm/kvm_pkvm.h5
-rw-r--r--arch/arm64/include/asm/memory.h45
-rw-r--r--arch/arm64/include/asm/pgtable-prot.h2
-rw-r--r--arch/arm64/include/asm/processor.h3
-rw-r--r--arch/arm64/include/asm/simd.h11
-rw-r--r--arch/arm64/include/asm/sparsemem.h2
-rw-r--r--arch/arm64/include/asm/spectre.h4
-rw-r--r--arch/arm64/include/asm/stacktrace/common.h19
-rw-r--r--arch/arm64/include/asm/stacktrace/nvhe.h2
-rw-r--r--arch/arm64/include/asm/sysreg.h25
-rw-r--r--arch/arm64/include/asm/thread_info.h1
-rw-r--r--arch/arm64/include/asm/tlb.h15
-rw-r--r--arch/arm64/include/asm/tlbflush.h118
-rw-r--r--arch/arm64/include/asm/topology.h1
-rw-r--r--arch/arm64/include/asm/unistd.h2
-rw-r--r--arch/arm64/include/asm/unistd32.h10
-rw-r--r--arch/arm64/include/asm/vdso.h3
-rw-r--r--arch/arm64/include/asm/vncr_mapping.h103
33 files changed, 565 insertions, 302 deletions
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 376a980f2b..513787e433 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -12,7 +12,7 @@
#ifndef __ASM_ASSEMBLER_H
#define __ASM_ASSEMBLER_H
-#include <asm-generic/export.h>
+#include <linux/export.h>
#include <asm/alternative.h>
#include <asm/asm-bug.h>
@@ -760,32 +760,25 @@ alternative_endif
.endm
/*
- * Check whether preempt/bh-disabled asm code should yield as soon as
- * it is able. This is the case if we are currently running in task
- * context, and either a softirq is pending, or the TIF_NEED_RESCHED
- * flag is set and re-enabling preemption a single time would result in
- * a preempt count of zero. (Note that the TIF_NEED_RESCHED flag is
- * stored negated in the top word of the thread_info::preempt_count
+ * Check whether asm code should yield as soon as it is able. This is
+ * the case if we are currently running in task context, and the
+ * TIF_NEED_RESCHED flag is set. (Note that the TIF_NEED_RESCHED flag
+ * is stored negated in the top word of the thread_info::preempt_count
* field)
*/
- .macro cond_yield, lbl:req, tmp:req, tmp2:req
+ .macro cond_yield, lbl:req, tmp:req, tmp2
+#ifdef CONFIG_PREEMPT_VOLUNTARY
get_current_task \tmp
ldr \tmp, [\tmp, #TSK_TI_PREEMPT]
/*
* If we are serving a softirq, there is no point in yielding: the
* softirq will not be preempted no matter what we do, so we should
- * run to completion as quickly as we can.
+ * run to completion as quickly as we can. The preempt_count field will
+ * have BIT(SOFTIRQ_SHIFT) set in this case, so the zero check will
+ * catch this case too.
*/
- tbnz \tmp, #SOFTIRQ_SHIFT, .Lnoyield_\@
-#ifdef CONFIG_PREEMPTION
- sub \tmp, \tmp, #PREEMPT_DISABLE_OFFSET
cbz \tmp, \lbl
#endif
- adr_l \tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING
- get_this_cpu_offset \tmp2
- ldr w\tmp, [\tmp, \tmp2]
- cbnz w\tmp, \lbl // yield on pending softirq in task context
-.Lnoyield_\@:
.endm
/*
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index ceb368d33b..06a4670bdb 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -58,7 +58,6 @@ static inline unsigned int arch_slab_minalign(void)
#define CTR_L1IP(ctr) SYS_FIELD_GET(CTR_EL0, L1Ip, ctr)
#define ICACHEF_ALIASING 0
-#define ICACHEF_VPIPT 1
extern unsigned long __icache_flags;
/*
@@ -70,11 +69,6 @@ static inline int icache_is_aliasing(void)
return test_bit(ICACHEF_ALIASING, &__icache_flags);
}
-static __always_inline int icache_is_vpipt(void)
-{
- return test_bit(ICACHEF_VPIPT, &__icache_flags);
-}
-
static inline u32 cache_type_cwg(void)
{
return SYS_FIELD_GET(CTR_EL0, CWG, read_cpuid_cachetype());
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index f3034099fd..b1e43f56ee 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -38,7 +38,6 @@ struct cpuinfo_32bit {
};
struct cpuinfo_arm64 {
- struct cpu cpu;
struct kobject kobj;
u64 reg_ctr;
u64 reg_cntfrq;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index f6d416fe49..bd8d4ca81a 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -83,7 +83,7 @@ struct arm64_ftr_bits {
* to full-0 denotes that this field has no override
*
* A @mask field set to full-0 with the corresponding @val field set
- * to full-1 denotes thath this field has an invalid override.
+ * to full-1 denotes that this field has an invalid override.
*/
struct arm64_ftr_override {
u64 val;
@@ -617,6 +617,7 @@ static inline bool id_aa64pfr1_mte(u64 pfr1)
return val >= ID_AA64PFR1_EL1_MTE_MTE2;
}
+void __init setup_boot_cpu_features(void);
void __init setup_system_features(void);
void __init setup_user_features(void);
@@ -819,6 +820,11 @@ static inline bool system_supports_tlb_range(void)
return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE);
}
+static inline bool system_supports_lpa2(void)
+{
+ return cpus_have_final_cap(ARM64_HAS_LPA2);
+}
+
int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index ae35939f39..353fe08546 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -392,6 +392,21 @@ static inline bool esr_is_data_abort(unsigned long esr)
return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR;
}
+static inline bool esr_fsc_is_translation_fault(unsigned long esr)
+{
+ return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT;
+}
+
+static inline bool esr_fsc_is_permission_fault(unsigned long esr)
+{
+ return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM;
+}
+
+static inline bool esr_fsc_is_access_flag_fault(unsigned long esr)
+{
+ return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_ACCESS;
+}
+
const char *esr_get_class_string(unsigned long esr);
#endif /* __ASSEMBLY */
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index cdf6a35e39..cda81d009c 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -242,14 +242,6 @@
| (\nx << 5)
.endm
-/*
- * Zero the entire ZA array
- * ZERO ZA
- */
-.macro zero_za
- .inst 0xc00800ff
-.endm
-
.macro __for from:req, to:req
.if (\from) == (\to)
_for__body %\from
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 50ce8b697f..e93548914c 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -4,6 +4,8 @@
#ifndef __ASSEMBLER__
+#include <linux/cpumask.h>
+
#include <asm-generic/irq.h>
void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu);
diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h
index 12d5f47f7d..7eefc525a9 100644
--- a/arch/arm64/include/asm/kasan.h
+++ b/arch/arm64/include/asm/kasan.h
@@ -15,29 +15,9 @@
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+asmlinkage void kasan_early_init(void);
void kasan_init(void);
-
-/*
- * KASAN_SHADOW_START: beginning of the kernel virtual addresses.
- * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses,
- * where N = (1 << KASAN_SHADOW_SCALE_SHIFT).
- *
- * KASAN_SHADOW_OFFSET:
- * This value is used to map an address to the corresponding shadow
- * address by the following formula:
- * shadow_addr = (address >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET
- *
- * (1 << (64 - KASAN_SHADOW_SCALE_SHIFT)) shadow addresses that lie in range
- * [KASAN_SHADOW_OFFSET, KASAN_SHADOW_END) cover all 64-bits of virtual
- * addresses. So KASAN_SHADOW_OFFSET should satisfy the following equation:
- * KASAN_SHADOW_OFFSET = KASAN_SHADOW_END -
- * (1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT))
- */
-#define _KASAN_SHADOW_START(va) (KASAN_SHADOW_END - (1UL << ((va) - KASAN_SHADOW_SCALE_SHIFT)))
-#define KASAN_SHADOW_START _KASAN_SHADOW_START(vabits_actual)
-
void kasan_copy_shadow(pgd_t *pgdir);
-asmlinkage void kasan_early_init(void);
#else
static inline void kasan_init(void) { }
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 85d26143fa..83ddb14b95 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -37,27 +37,12 @@
/*
- * If KASLR is enabled, then an offset K is added to the kernel address
- * space. The bottom 21 bits of this offset are zero to guarantee 2MB
- * alignment for PA and VA.
- *
- * For each pagetable level of the swapper, we know that the shift will
- * be larger than 21 (for the 4KB granule case we use section maps thus
- * the smallest shift is actually 30) thus there is the possibility that
- * KASLR can increase the number of pagetable entries by 1, so we make
- * room for this extra entry.
- *
- * Note KASLR cannot increase the number of required entries for a level
- * by more than one because it increments both the virtual start and end
- * addresses equally (the extra entry comes from the case where the end
- * address is just pushed over a boundary and the start address isn't).
+ * A relocatable kernel may execute from an address that differs from the one at
+ * which it was linked. In the worst case, its runtime placement may intersect
+ * with two adjacent PGDIR entries, which means that an additional page table
+ * may be needed at each subordinate level.
*/
-
-#ifdef CONFIG_RANDOMIZE_BASE
-#define EARLY_KASLR (1)
-#else
-#define EARLY_KASLR (0)
-#endif
+#define EXTRA_PAGE __is_defined(CONFIG_RELOCATABLE)
#define SPAN_NR_ENTRIES(vstart, vend, shift) \
((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1)
@@ -83,7 +68,7 @@
+ EARLY_PGDS((vstart), (vend), add) /* each PGDIR needs a next level page table */ \
+ EARLY_PUDS((vstart), (vend), add) /* each PUD needs a next level page table */ \
+ EARLY_PMDS((vstart), (vend), add)) /* each PMD needs a next level page table */
-#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EARLY_KASLR))
+#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EXTRA_PAGE))
/* the initial ID map may need two extra pages if it needs to be extended */
#if VA_BITS < 48
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index b85f46a73e..3c6f8ba1e4 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -108,6 +108,7 @@
#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En)
/* TCR_EL2 Registers bits */
+#define TCR_EL2_DS (1UL << 32)
#define TCR_EL2_RES1 ((1U << 31) | (1 << 23))
#define TCR_EL2_TBI (1 << 20)
#define TCR_EL2_PS_SHIFT 16
@@ -122,6 +123,7 @@
TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
/* VTCR_EL2 Registers bits */
+#define VTCR_EL2_DS TCR_EL2_DS
#define VTCR_EL2_RES1 (1U << 31)
#define VTCR_EL2_HD (1 << 22)
#define VTCR_EL2_HA (1 << 21)
@@ -344,36 +346,47 @@
* Once we get to a point where the two describe the same thing, we'll
* merge the definitions. One day.
*/
-#define __HFGRTR_EL2_RES0 (GENMASK(63, 56) | GENMASK(53, 51))
+#define __HFGRTR_EL2_RES0 HFGxTR_EL2_RES0
#define __HFGRTR_EL2_MASK GENMASK(49, 0)
-#define __HFGRTR_EL2_nMASK (GENMASK(58, 57) | GENMASK(55, 54) | BIT(50))
+#define __HFGRTR_EL2_nMASK ~(__HFGRTR_EL2_RES0 | __HFGRTR_EL2_MASK)
-#define __HFGWTR_EL2_RES0 (GENMASK(63, 56) | GENMASK(53, 51) | \
- BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
- GENMASK(26, 25) | BIT(21) | BIT(18) | \
+/*
+ * The HFGWTR bits are a subset of HFGRTR bits. To ensure we don't miss any
+ * future additions, define __HFGWTR* macros relative to __HFGRTR* ones.
+ */
+#define __HFGRTR_ONLY_MASK (BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
+ GENMASK(26, 25) | BIT(21) | BIT(18) | \
GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
-#define __HFGWTR_EL2_MASK GENMASK(49, 0)
-#define __HFGWTR_EL2_nMASK (GENMASK(58, 57) | GENMASK(55, 54) | BIT(50))
-
-#define __HFGITR_EL2_RES0 GENMASK(63, 57)
-#define __HFGITR_EL2_MASK GENMASK(54, 0)
-#define __HFGITR_EL2_nMASK GENMASK(56, 55)
-
-#define __HDFGRTR_EL2_RES0 (BIT(49) | BIT(42) | GENMASK(39, 38) | \
- GENMASK(21, 20) | BIT(8))
-#define __HDFGRTR_EL2_MASK ~__HDFGRTR_EL2_nMASK
-#define __HDFGRTR_EL2_nMASK GENMASK(62, 59)
-
-#define __HDFGWTR_EL2_RES0 (BIT(63) | GENMASK(59, 58) | BIT(51) | BIT(47) | \
- BIT(43) | GENMASK(40, 38) | BIT(34) | BIT(30) | \
- BIT(22) | BIT(9) | BIT(6))
-#define __HDFGWTR_EL2_MASK ~__HDFGWTR_EL2_nMASK
-#define __HDFGWTR_EL2_nMASK GENMASK(62, 60)
+#define __HFGWTR_EL2_RES0 (__HFGRTR_EL2_RES0 | __HFGRTR_ONLY_MASK)
+#define __HFGWTR_EL2_MASK (__HFGRTR_EL2_MASK & ~__HFGRTR_ONLY_MASK)
+#define __HFGWTR_EL2_nMASK ~(__HFGWTR_EL2_RES0 | __HFGWTR_EL2_MASK)
+
+#define __HFGITR_EL2_RES0 HFGITR_EL2_RES0
+#define __HFGITR_EL2_MASK (BIT(62) | BIT(60) | GENMASK(54, 0))
+#define __HFGITR_EL2_nMASK ~(__HFGITR_EL2_RES0 | __HFGITR_EL2_MASK)
+
+#define __HDFGRTR_EL2_RES0 HDFGRTR_EL2_RES0
+#define __HDFGRTR_EL2_MASK (BIT(63) | GENMASK(58, 50) | GENMASK(48, 43) | \
+ GENMASK(41, 40) | GENMASK(37, 22) | \
+ GENMASK(19, 9) | GENMASK(7, 0))
+#define __HDFGRTR_EL2_nMASK ~(__HDFGRTR_EL2_RES0 | __HDFGRTR_EL2_MASK)
+
+#define __HDFGWTR_EL2_RES0 HDFGWTR_EL2_RES0
+#define __HDFGWTR_EL2_MASK (GENMASK(57, 52) | GENMASK(50, 48) | \
+ GENMASK(46, 44) | GENMASK(42, 41) | \
+ GENMASK(37, 35) | GENMASK(33, 31) | \
+ GENMASK(29, 23) | GENMASK(21, 10) | \
+ GENMASK(8, 7) | GENMASK(5, 0))
+#define __HDFGWTR_EL2_nMASK ~(__HDFGWTR_EL2_RES0 | __HDFGWTR_EL2_MASK)
+
+#define __HAFGRTR_EL2_RES0 HAFGRTR_EL2_RES0
+#define __HAFGRTR_EL2_MASK (GENMASK(49, 17) | GENMASK(4, 0))
+#define __HAFGRTR_EL2_nMASK ~(__HAFGRTR_EL2_RES0 | __HAFGRTR_EL2_MASK)
/* Similar definitions for HCRX_EL2 */
-#define __HCRX_EL2_RES0 (GENMASK(63, 16) | GENMASK(13, 12))
-#define __HCRX_EL2_MASK (0)
-#define __HCRX_EL2_nMASK (GENMASK(15, 14) | GENMASK(4, 0))
+#define __HCRX_EL2_RES0 HCRX_EL2_RES0
+#define __HCRX_EL2_MASK (BIT(6))
+#define __HCRX_EL2_nMASK ~(__HCRX_EL2_RES0 | __HCRX_EL2_MASK)
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~UL(0xf))
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 78a550537b..b804fe8321 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -17,6 +17,7 @@
#include <asm/esr.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_hyp.h>
+#include <asm/kvm_nested.h>
#include <asm/ptrace.h>
#include <asm/cputype.h>
#include <asm/virt.h>
@@ -54,11 +55,6 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu);
int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2);
int kvm_inject_nested_irq(struct kvm_vcpu *vcpu);
-static inline bool vcpu_has_feature(const struct kvm_vcpu *vcpu, int feature)
-{
- return test_bit(feature, vcpu->kvm->arch.vcpu_features);
-}
-
#if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
{
@@ -248,7 +244,7 @@ static inline bool __is_hyp_ctxt(const struct kvm_cpu_context *ctxt)
static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
{
- return __is_hyp_ctxt(&vcpu->arch.ctxt);
+ return vcpu_has_nv(vcpu) && __is_hyp_ctxt(&vcpu->arch.ctxt);
}
/*
@@ -404,14 +400,25 @@ static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
}
-static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
+static inline
+bool kvm_vcpu_trap_is_permission_fault(const struct kvm_vcpu *vcpu)
{
- return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
+ return esr_fsc_is_permission_fault(kvm_vcpu_get_esr(vcpu));
}
-static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
+static inline
+bool kvm_vcpu_trap_is_translation_fault(const struct kvm_vcpu *vcpu)
{
- return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL;
+ return esr_fsc_is_translation_fault(kvm_vcpu_get_esr(vcpu));
+}
+
+static inline
+u64 kvm_vcpu_trap_get_perm_fault_granule(const struct kvm_vcpu *vcpu)
+{
+ unsigned long esr = kvm_vcpu_get_esr(vcpu);
+
+ BUG_ON(!esr_fsc_is_permission_fault(esr));
+ return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(esr & ESR_ELx_FSC_LEVEL));
}
static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
@@ -454,12 +461,7 @@ static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
* first), then a permission fault to allow the flags
* to be set.
*/
- switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
- case ESR_ELx_FSC_PERM:
- return true;
- default:
- return false;
- }
+ return kvm_vcpu_trap_is_permission_fault(vcpu);
}
if (kvm_vcpu_trap_is_iabt(vcpu))
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 824f29f049..21c57b8125 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -27,6 +27,7 @@
#include <asm/fpsimd.h>
#include <asm/kvm.h>
#include <asm/kvm_asm.h>
+#include <asm/vncr_mapping.h>
#define __KVM_HAVE_ARCH_INTC_INITIALIZED
@@ -306,6 +307,7 @@ struct kvm_arch {
* Atomic access to multiple idregs are guarded by kvm_arch.config_lock.
*/
#define IDREG_IDX(id) (((sys_reg_CRm(id) - 1) << 3) | sys_reg_Op2(id))
+#define IDX_IDREG(idx) sys_reg(3, 0, 0, ((idx) >> 3) + 1, (idx) & Op2_mask)
#define IDREG(kvm, id) ((kvm)->arch.id_regs[IDREG_IDX(id)])
#define KVM_ARM_ID_REG_NUM (IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1)
u64 id_regs[KVM_ARM_ID_REG_NUM];
@@ -324,33 +326,33 @@ struct kvm_vcpu_fault_info {
u64 disr_el1; /* Deferred [SError] Status Register */
};
+/*
+ * VNCR() just places the VNCR_capable registers in the enum after
+ * __VNCR_START__, and the value (after correction) to be an 8-byte offset
+ * from the VNCR base. As we don't require the enum to be otherwise ordered,
+ * we need the terrible hack below to ensure that we correctly size the
+ * sys_regs array, no matter what.
+ *
+ * The __MAX__ macro has been lifted from Sean Eron Anderson's wonderful
+ * treasure trove of bit hacks:
+ * https://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ */
+#define __MAX__(x,y) ((x) ^ (((x) ^ (y)) & -((x) < (y))))
+#define VNCR(r) \
+ __before_##r, \
+ r = __VNCR_START__ + ((VNCR_ ## r) / 8), \
+ __after_##r = __MAX__(__before_##r - 1, r)
+
enum vcpu_sysreg {
__INVALID_SYSREG__, /* 0 is reserved as an invalid value */
MPIDR_EL1, /* MultiProcessor Affinity Register */
CLIDR_EL1, /* Cache Level ID Register */
CSSELR_EL1, /* Cache Size Selection Register */
- SCTLR_EL1, /* System Control Register */
- ACTLR_EL1, /* Auxiliary Control Register */
- CPACR_EL1, /* Coprocessor Access Control */
- ZCR_EL1, /* SVE Control */
- TTBR0_EL1, /* Translation Table Base Register 0 */
- TTBR1_EL1, /* Translation Table Base Register 1 */
- TCR_EL1, /* Translation Control Register */
- TCR2_EL1, /* Extended Translation Control Register */
- ESR_EL1, /* Exception Syndrome Register */
- AFSR0_EL1, /* Auxiliary Fault Status Register 0 */
- AFSR1_EL1, /* Auxiliary Fault Status Register 1 */
- FAR_EL1, /* Fault Address Register */
- MAIR_EL1, /* Memory Attribute Indirection Register */
- VBAR_EL1, /* Vector Base Address Register */
- CONTEXTIDR_EL1, /* Context ID Register */
TPIDR_EL0, /* Thread ID, User R/W */
TPIDRRO_EL0, /* Thread ID, User R/O */
TPIDR_EL1, /* Thread ID, Privileged */
- AMAIR_EL1, /* Aux Memory Attribute Indirection Register */
CNTKCTL_EL1, /* Timer Control Register (EL1) */
PAR_EL1, /* Physical Address Register */
- MDSCR_EL1, /* Monitor Debug System Control Register */
MDCCINT_EL1, /* Monitor Debug Comms Channel Interrupt Enable Reg */
OSLSR_EL1, /* OS Lock Status Register */
DISR_EL1, /* Deferred Interrupt Status Register */
@@ -381,26 +383,11 @@ enum vcpu_sysreg {
APGAKEYLO_EL1,
APGAKEYHI_EL1,
- ELR_EL1,
- SP_EL1,
- SPSR_EL1,
-
- CNTVOFF_EL2,
- CNTV_CVAL_EL0,
- CNTV_CTL_EL0,
- CNTP_CVAL_EL0,
- CNTP_CTL_EL0,
-
/* Memory Tagging Extension registers */
RGSR_EL1, /* Random Allocation Tag Seed Register */
GCR_EL1, /* Tag Control Register */
- TFSR_EL1, /* Tag Fault Status Register (EL1) */
TFSRE0_EL1, /* Tag Fault Status Register (EL0) */
- /* Permission Indirection Extension registers */
- PIR_EL1, /* Permission Indirection Register 1 (EL1) */
- PIRE0_EL1, /* Permission Indirection Register 0 (EL1) */
-
/* 32bit specific registers. */
DACR32_EL2, /* Domain Access Control Register */
IFSR32_EL2, /* Instruction Fault Status Register */
@@ -408,21 +395,14 @@ enum vcpu_sysreg {
DBGVCR32_EL2, /* Debug Vector Catch Register */
/* EL2 registers */
- VPIDR_EL2, /* Virtualization Processor ID Register */
- VMPIDR_EL2, /* Virtualization Multiprocessor ID Register */
SCTLR_EL2, /* System Control Register (EL2) */
ACTLR_EL2, /* Auxiliary Control Register (EL2) */
- HCR_EL2, /* Hypervisor Configuration Register */
MDCR_EL2, /* Monitor Debug Configuration Register (EL2) */
CPTR_EL2, /* Architectural Feature Trap Register (EL2) */
- HSTR_EL2, /* Hypervisor System Trap Register */
HACR_EL2, /* Hypervisor Auxiliary Control Register */
- HCRX_EL2, /* Extended Hypervisor Configuration Register */
TTBR0_EL2, /* Translation Table Base Register 0 (EL2) */
TTBR1_EL2, /* Translation Table Base Register 1 (EL2) */
TCR_EL2, /* Translation Control Register (EL2) */
- VTTBR_EL2, /* Virtualization Translation Table Base Register */
- VTCR_EL2, /* Virtualization Translation Control Register */
SPSR_EL2, /* EL2 saved program status register */
ELR_EL2, /* EL2 exception link register */
AFSR0_EL2, /* Auxiliary Fault Status Register 0 (EL2) */
@@ -435,19 +415,62 @@ enum vcpu_sysreg {
VBAR_EL2, /* Vector Base Address Register (EL2) */
RVBAR_EL2, /* Reset Vector Base Address Register */
CONTEXTIDR_EL2, /* Context ID Register (EL2) */
- TPIDR_EL2, /* EL2 Software Thread ID Register */
CNTHCTL_EL2, /* Counter-timer Hypervisor Control register */
SP_EL2, /* EL2 Stack Pointer */
- HFGRTR_EL2,
- HFGWTR_EL2,
- HFGITR_EL2,
- HDFGRTR_EL2,
- HDFGWTR_EL2,
CNTHP_CTL_EL2,
CNTHP_CVAL_EL2,
CNTHV_CTL_EL2,
CNTHV_CVAL_EL2,
+ __VNCR_START__, /* Any VNCR-capable reg goes after this point */
+
+ VNCR(SCTLR_EL1),/* System Control Register */
+ VNCR(ACTLR_EL1),/* Auxiliary Control Register */
+ VNCR(CPACR_EL1),/* Coprocessor Access Control */
+ VNCR(ZCR_EL1), /* SVE Control */
+ VNCR(TTBR0_EL1),/* Translation Table Base Register 0 */
+ VNCR(TTBR1_EL1),/* Translation Table Base Register 1 */
+ VNCR(TCR_EL1), /* Translation Control Register */
+ VNCR(TCR2_EL1), /* Extended Translation Control Register */
+ VNCR(ESR_EL1), /* Exception Syndrome Register */
+ VNCR(AFSR0_EL1),/* Auxiliary Fault Status Register 0 */
+ VNCR(AFSR1_EL1),/* Auxiliary Fault Status Register 1 */
+ VNCR(FAR_EL1), /* Fault Address Register */
+ VNCR(MAIR_EL1), /* Memory Attribute Indirection Register */
+ VNCR(VBAR_EL1), /* Vector Base Address Register */
+ VNCR(CONTEXTIDR_EL1), /* Context ID Register */
+ VNCR(AMAIR_EL1),/* Aux Memory Attribute Indirection Register */
+ VNCR(MDSCR_EL1),/* Monitor Debug System Control Register */
+ VNCR(ELR_EL1),
+ VNCR(SP_EL1),
+ VNCR(SPSR_EL1),
+ VNCR(TFSR_EL1), /* Tag Fault Status Register (EL1) */
+ VNCR(VPIDR_EL2),/* Virtualization Processor ID Register */
+ VNCR(VMPIDR_EL2),/* Virtualization Multiprocessor ID Register */
+ VNCR(HCR_EL2), /* Hypervisor Configuration Register */
+ VNCR(HSTR_EL2), /* Hypervisor System Trap Register */
+ VNCR(VTTBR_EL2),/* Virtualization Translation Table Base Register */
+ VNCR(VTCR_EL2), /* Virtualization Translation Control Register */
+ VNCR(TPIDR_EL2),/* EL2 Software Thread ID Register */
+ VNCR(HCRX_EL2), /* Extended Hypervisor Configuration Register */
+
+ /* Permission Indirection Extension registers */
+ VNCR(PIR_EL1), /* Permission Indirection Register 1 (EL1) */
+ VNCR(PIRE0_EL1), /* Permission Indirection Register 0 (EL1) */
+
+ VNCR(HFGRTR_EL2),
+ VNCR(HFGWTR_EL2),
+ VNCR(HFGITR_EL2),
+ VNCR(HDFGRTR_EL2),
+ VNCR(HDFGWTR_EL2),
+ VNCR(HAFGRTR_EL2),
+
+ VNCR(CNTVOFF_EL2),
+ VNCR(CNTV_CVAL_EL0),
+ VNCR(CNTV_CTL_EL0),
+ VNCR(CNTP_CVAL_EL0),
+ VNCR(CNTP_CTL_EL0),
+
NR_SYS_REGS /* Nothing after this line! */
};
@@ -464,6 +487,9 @@ struct kvm_cpu_context {
u64 sys_regs[NR_SYS_REGS];
struct kvm_vcpu *__hyp_running_vcpu;
+
+ /* This pointer has to be 4kB aligned. */
+ u64 *vncr_array;
};
struct kvm_host_data {
@@ -826,8 +852,19 @@ struct kvm_vcpu_arch {
* accessed by a running VCPU. For example, for userspace access or
* for system registers that are never context switched, but only
* emulated.
+ *
+ * Don't bother with VNCR-based accesses in the nVHE code, it has no
+ * business dealing with NV.
*/
-#define __ctxt_sys_reg(c,r) (&(c)->sys_regs[(r)])
+static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
+{
+#if !defined (__KVM_NVHE_HYPERVISOR__)
+ if (unlikely(cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) &&
+ r >= __VNCR_START__ && ctxt->vncr_array))
+ return &ctxt->vncr_array[r - __VNCR_START__];
+#endif
+ return (u64 *)&ctxt->sys_regs[r];
+}
#define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r))
@@ -871,6 +908,7 @@ static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
case AMAIR_EL1: *val = read_sysreg_s(SYS_AMAIR_EL12); break;
case CNTKCTL_EL1: *val = read_sysreg_s(SYS_CNTKCTL_EL12); break;
case ELR_EL1: *val = read_sysreg_s(SYS_ELR_EL12); break;
+ case SPSR_EL1: *val = read_sysreg_s(SYS_SPSR_EL12); break;
case PAR_EL1: *val = read_sysreg_par(); break;
case DACR32_EL2: *val = read_sysreg_s(SYS_DACR32_EL2); break;
case IFSR32_EL2: *val = read_sysreg_s(SYS_IFSR32_EL2); break;
@@ -915,6 +953,7 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); break;
case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); break;
case ELR_EL1: write_sysreg_s(val, SYS_ELR_EL12); break;
+ case SPSR_EL1: write_sysreg_s(val, SYS_SPSR_EL12); break;
case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); break;
case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); break;
case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); break;
@@ -954,8 +993,6 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events);
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
void kvm_arm_halt_guest(struct kvm *kvm);
void kvm_arm_resume_guest(struct kvm *kvm);
@@ -1177,6 +1214,13 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
#define kvm_vm_has_ran_once(kvm) \
(test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &(kvm)->arch.flags))
+static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature)
+{
+ return test_bit(feature, ka->vcpu_features);
+}
+
+#define vcpu_has_feature(v, f) __vcpu_has_feature(&(v)->kvm->arch, (f))
+
int kvm_trng_call(struct kvm_vcpu *vcpu);
#ifdef CONFIG_KVM
extern phys_addr_t hyp_mem_base;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 49e0d4b36b..e3e793d0ec 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -244,13 +244,6 @@ static inline size_t __invalidate_icache_max_range(void)
static inline void __invalidate_icache_guest_page(void *va, size_t size)
{
/*
- * VPIPT I-cache maintenance must be done from EL2. See comment in the
- * nVHE flavor of __kvm_tlb_flush_vmid_ipa().
- */
- if (icache_is_vpipt() && read_sysreg(CurrentEL) != CurrentEL_EL2)
- return;
-
- /*
* Blow the whole I-cache if it is aliasing (i.e. VIPT) or the
* invalidation range exceeds our arbitrary limit on invadations by
* cache line.
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 6cec8e9c6c..4882905357 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -2,8 +2,9 @@
#ifndef __ARM64_KVM_NESTED_H
#define __ARM64_KVM_NESTED_H
-#include <asm/kvm_emulate.h>
+#include <linux/bitfield.h>
#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
{
@@ -12,12 +13,55 @@ static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
vcpu_has_feature(vcpu, KVM_ARM_VCPU_HAS_EL2));
}
-extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
+/* Translation helpers from non-VHE EL2 to EL1 */
+static inline u64 tcr_el2_ps_to_tcr_el1_ips(u64 tcr_el2)
+{
+ return (u64)FIELD_GET(TCR_EL2_PS_MASK, tcr_el2) << TCR_IPS_SHIFT;
+}
+
+static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr)
+{
+ return TCR_EPD1_MASK | /* disable TTBR1_EL1 */
+ ((tcr & TCR_EL2_TBI) ? TCR_TBI0 : 0) |
+ tcr_el2_ps_to_tcr_el1_ips(tcr) |
+ (tcr & TCR_EL2_TG0_MASK) |
+ (tcr & TCR_EL2_ORGN0_MASK) |
+ (tcr & TCR_EL2_IRGN0_MASK) |
+ (tcr & TCR_EL2_T0SZ_MASK);
+}
+
+static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2)
+{
+ u64 cpacr_el1 = 0;
+
+ if (cptr_el2 & CPTR_EL2_TTA)
+ cpacr_el1 |= CPACR_ELx_TTA;
+ if (!(cptr_el2 & CPTR_EL2_TFP))
+ cpacr_el1 |= CPACR_ELx_FPEN;
+ if (!(cptr_el2 & CPTR_EL2_TZ))
+ cpacr_el1 |= CPACR_ELx_ZEN;
-struct sys_reg_params;
-struct sys_reg_desc;
+ return cpacr_el1;
+}
+
+static inline u64 translate_sctlr_el2_to_sctlr_el1(u64 val)
+{
+ /* Only preserve the minimal set of bits we support */
+ val &= (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | SCTLR_ELx_SA |
+ SCTLR_ELx_I | SCTLR_ELx_IESB | SCTLR_ELx_WXN | SCTLR_ELx_EE);
+ val |= SCTLR_EL1_RES1;
+
+ return val;
+}
+
+static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
+{
+ /* Clear the ASID field */
+ return ttbr0 & ~GENMASK_ULL(63, 48);
+}
+
+extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
-void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
- const struct sys_reg_desc *r);
+int kvm_init_nv_sysregs(struct kvm *kvm);
#endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index d3e354bb83..cfdf40f734 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -11,7 +11,8 @@
#include <linux/kvm_host.h>
#include <linux/types.h>
-#define KVM_PGTABLE_MAX_LEVELS 4U
+#define KVM_PGTABLE_FIRST_LEVEL -1
+#define KVM_PGTABLE_LAST_LEVEL 3
/*
* The largest supported block sizes for KVM (no 52-bit PA support):
@@ -20,17 +21,29 @@
* - 64K (level 2): 512MB
*/
#ifdef CONFIG_ARM64_4K_PAGES
-#define KVM_PGTABLE_MIN_BLOCK_LEVEL 1U
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL 1
#else
-#define KVM_PGTABLE_MIN_BLOCK_LEVEL 2U
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL 2
#endif
+#define kvm_lpa2_is_enabled() system_supports_lpa2()
+
+static inline u64 kvm_get_parange_max(void)
+{
+ if (kvm_lpa2_is_enabled() ||
+ (IS_ENABLED(CONFIG_ARM64_PA_BITS_52) && PAGE_SHIFT == 16))
+ return ID_AA64MMFR0_EL1_PARANGE_52;
+ else
+ return ID_AA64MMFR0_EL1_PARANGE_48;
+}
+
static inline u64 kvm_get_parange(u64 mmfr0)
{
+ u64 parange_max = kvm_get_parange_max();
u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_EL1_PARANGE_SHIFT);
- if (parange > ID_AA64MMFR0_EL1_PARANGE_MAX)
- parange = ID_AA64MMFR0_EL1_PARANGE_MAX;
+ if (parange > parange_max)
+ parange = parange_max;
return parange;
}
@@ -41,6 +54,8 @@ typedef u64 kvm_pte_t;
#define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT)
#define KVM_PTE_ADDR_51_48 GENMASK(15, 12)
+#define KVM_PTE_ADDR_MASK_LPA2 GENMASK(49, PAGE_SHIFT)
+#define KVM_PTE_ADDR_51_50_LPA2 GENMASK(9, 8)
#define KVM_PHYS_INVALID (-1ULL)
@@ -51,21 +66,34 @@ static inline bool kvm_pte_valid(kvm_pte_t pte)
static inline u64 kvm_pte_to_phys(kvm_pte_t pte)
{
- u64 pa = pte & KVM_PTE_ADDR_MASK;
-
- if (PAGE_SHIFT == 16)
- pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48;
+ u64 pa;
+
+ if (kvm_lpa2_is_enabled()) {
+ pa = pte & KVM_PTE_ADDR_MASK_LPA2;
+ pa |= FIELD_GET(KVM_PTE_ADDR_51_50_LPA2, pte) << 50;
+ } else {
+ pa = pte & KVM_PTE_ADDR_MASK;
+ if (PAGE_SHIFT == 16)
+ pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48;
+ }
return pa;
}
static inline kvm_pte_t kvm_phys_to_pte(u64 pa)
{
- kvm_pte_t pte = pa & KVM_PTE_ADDR_MASK;
-
- if (PAGE_SHIFT == 16) {
- pa &= GENMASK(51, 48);
- pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48);
+ kvm_pte_t pte;
+
+ if (kvm_lpa2_is_enabled()) {
+ pte = pa & KVM_PTE_ADDR_MASK_LPA2;
+ pa &= GENMASK(51, 50);
+ pte |= FIELD_PREP(KVM_PTE_ADDR_51_50_LPA2, pa >> 50);
+ } else {
+ pte = pa & KVM_PTE_ADDR_MASK;
+ if (PAGE_SHIFT == 16) {
+ pa &= GENMASK(51, 48);
+ pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48);
+ }
}
return pte;
@@ -76,28 +104,28 @@ static inline kvm_pfn_t kvm_pte_to_pfn(kvm_pte_t pte)
return __phys_to_pfn(kvm_pte_to_phys(pte));
}
-static inline u64 kvm_granule_shift(u32 level)
+static inline u64 kvm_granule_shift(s8 level)
{
- /* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */
+ /* Assumes KVM_PGTABLE_LAST_LEVEL is 3 */
return ARM64_HW_PGTABLE_LEVEL_SHIFT(level);
}
-static inline u64 kvm_granule_size(u32 level)
+static inline u64 kvm_granule_size(s8 level)
{
return BIT(kvm_granule_shift(level));
}
-static inline bool kvm_level_supports_block_mapping(u32 level)
+static inline bool kvm_level_supports_block_mapping(s8 level)
{
return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
}
static inline u32 kvm_supported_block_sizes(void)
{
- u32 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
+ s8 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
u32 r = 0;
- for (; level < KVM_PGTABLE_MAX_LEVELS; level++)
+ for (; level <= KVM_PGTABLE_LAST_LEVEL; level++)
r |= BIT(kvm_granule_shift(level));
return r;
@@ -142,7 +170,7 @@ struct kvm_pgtable_mm_ops {
void* (*zalloc_page)(void *arg);
void* (*zalloc_pages_exact)(size_t size);
void (*free_pages_exact)(void *addr, size_t size);
- void (*free_unlinked_table)(void *addr, u32 level);
+ void (*free_unlinked_table)(void *addr, s8 level);
void (*get_page)(void *addr);
void (*put_page)(void *addr);
int (*page_count)(void *addr);
@@ -238,7 +266,7 @@ struct kvm_pgtable_visit_ctx {
u64 start;
u64 addr;
u64 end;
- u32 level;
+ s8 level;
enum kvm_pgtable_walk_flags flags;
};
@@ -341,7 +369,7 @@ static inline bool kvm_pgtable_walk_lock_held(void)
*/
struct kvm_pgtable {
u32 ia_bits;
- u32 start_level;
+ s8 start_level;
kvm_pteref_t pgd;
struct kvm_pgtable_mm_ops *mm_ops;
@@ -475,7 +503,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
* The page-table is assumed to be unreachable by any hardware walkers prior to
* freeing and therefore no TLB invalidation is performed.
*/
-void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level);
/**
* kvm_pgtable_stage2_create_unlinked() - Create an unlinked stage-2 paging structure.
@@ -499,7 +527,7 @@ void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *p
* an ERR_PTR(error) on failure.
*/
kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
- u64 phys, u32 level,
+ u64 phys, s8 level,
enum kvm_pgtable_prot prot,
void *mc, bool force_pte);
@@ -725,7 +753,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
- kvm_pte_t *ptep, u32 *level);
+ kvm_pte_t *ptep, s8 *level);
/**
* kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index e46250a020..ad9cfb5c1f 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -56,10 +56,11 @@ static inline unsigned long hyp_vm_table_pages(void)
static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages)
{
- unsigned long total = 0, i;
+ unsigned long total = 0;
+ int i;
/* Provision the worst case scenario */
- for (i = 0; i < KVM_PGTABLE_MAX_LEVELS; i++) {
+ for (i = KVM_PGTABLE_FIRST_LEVEL; i <= KVM_PGTABLE_LAST_LEVEL; i++) {
nr_pages = DIV_ROUND_UP(nr_pages, PTRS_PER_PTE);
total += nr_pages;
}
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index fde4186cc3..d82305ab42 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -65,15 +65,41 @@
#define KERNEL_END _end
/*
- * Generic and tag-based KASAN require 1/8th and 1/16th of the kernel virtual
- * address space for the shadow region respectively. They can bloat the stack
- * significantly, so double the (minimum) stack size when they are in use.
+ * Generic and Software Tag-Based KASAN modes require 1/8th and 1/16th of the
+ * kernel virtual address space for storing the shadow memory respectively.
+ *
+ * The mapping between a virtual memory address and its corresponding shadow
+ * memory address is defined based on the formula:
+ *
+ * shadow_addr = (addr >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET
+ *
+ * where KASAN_SHADOW_SCALE_SHIFT is the order of the number of bits that map
+ * to a single shadow byte and KASAN_SHADOW_OFFSET is a constant that offsets
+ * the mapping. Note that KASAN_SHADOW_OFFSET does not point to the start of
+ * the shadow memory region.
+ *
+ * Based on this mapping, we define two constants:
+ *
+ * KASAN_SHADOW_START: the start of the shadow memory region;
+ * KASAN_SHADOW_END: the end of the shadow memory region.
+ *
+ * KASAN_SHADOW_END is defined first as the shadow address that corresponds to
+ * the upper bound of possible virtual kernel memory addresses UL(1) << 64
+ * according to the mapping formula.
+ *
+ * KASAN_SHADOW_START is defined second based on KASAN_SHADOW_END. The shadow
+ * memory start must map to the lowest possible kernel virtual memory address
+ * and thus it depends on the actual bitness of the address space.
+ *
+ * As KASAN inserts redzones between stack variables, this increases the stack
+ * memory usage significantly. Thus, we double the (minimum) stack size.
*/
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
-#define KASAN_SHADOW_END ((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) \
- + KASAN_SHADOW_OFFSET)
-#define PAGE_END (KASAN_SHADOW_END - (1UL << (vabits_actual - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_SHADOW_END ((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) + KASAN_SHADOW_OFFSET)
+#define _KASAN_SHADOW_START(va) (KASAN_SHADOW_END - (UL(1) << ((va) - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_SHADOW_START _KASAN_SHADOW_START(vabits_actual)
+#define PAGE_END KASAN_SHADOW_START
#define KASAN_THREAD_SHIFT 1
#else
#define KASAN_THREAD_SHIFT 0
@@ -182,6 +208,7 @@
#include <linux/types.h>
#include <asm/boot.h>
#include <asm/bug.h>
+#include <asm/sections.h>
#if VA_BITS > 48
extern u64 vabits_actual;
@@ -193,15 +220,12 @@ extern s64 memstart_addr;
/* PHYS_OFFSET - the physical address of the start of memory. */
#define PHYS_OFFSET ({ VM_BUG_ON(memstart_addr & 1); memstart_addr; })
-/* the virtual base of the kernel image */
-extern u64 kimage_vaddr;
-
/* the offset between the kernel virtual and physical mappings */
extern u64 kimage_voffset;
static inline unsigned long kaslr_offset(void)
{
- return kimage_vaddr - KIMAGE_VADDR;
+ return (u64)&_text - KIMAGE_VADDR;
}
#ifdef CONFIG_RANDOMIZE_BASE
@@ -407,6 +431,5 @@ void dump_mem_limit(void);
#define INIT_MEMBLOCK_MEMORY_REGIONS (INIT_MEMBLOCK_REGIONS * 8)
#endif
-#include <asm-generic/memory_model.h>
#endif /* __ASM_MEMORY_H */
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index e9624f6326..483dbfa39c 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -71,6 +71,8 @@ extern bool arm64_use_ng_mappings;
#define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0)
#define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0)
+#define lpa2_is_enabled() false
+
/*
* If we have userspace only BTI we don't want to mark kernel pages
* guarded even if the system does support BTI.
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index e5bc54522e..5b0a04810b 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -167,6 +167,9 @@ struct thread_struct {
unsigned long fault_address; /* fault info */
unsigned long fault_code; /* ESR_EL1 value */
struct debug_info debug; /* debugging */
+
+ struct user_fpsimd_state kernel_fpsimd_state;
+ unsigned int kernel_fpsimd_cpu;
#ifdef CONFIG_ARM64_PTR_AUTH
struct ptrauth_keys_user keys_user;
#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h
index 6a75d7ecdc..8e86c9e70e 100644
--- a/arch/arm64/include/asm/simd.h
+++ b/arch/arm64/include/asm/simd.h
@@ -12,8 +12,6 @@
#include <linux/preempt.h>
#include <linux/types.h>
-DECLARE_PER_CPU(bool, fpsimd_context_busy);
-
#ifdef CONFIG_KERNEL_MODE_NEON
/*
@@ -28,17 +26,10 @@ static __must_check inline bool may_use_simd(void)
/*
* We must make sure that the SVE has been initialized properly
* before using the SIMD in kernel.
- * fpsimd_context_busy is only set while preemption is disabled,
- * and is clear whenever preemption is enabled. Since
- * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy
- * cannot change under our feet -- if it's set we cannot be
- * migrated, and if it's clear we cannot be migrated to a CPU
- * where it is set.
*/
return !WARN_ON(!system_capabilities_finalized()) &&
system_supports_fpsimd() &&
- !in_hardirq() && !irqs_disabled() && !in_nmi() &&
- !this_cpu_read(fpsimd_context_busy);
+ !in_hardirq() && !irqs_disabled() && !in_nmi();
}
#else /* ! CONFIG_KERNEL_MODE_NEON */
diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h
index 5f54376210..8a8acc2203 100644
--- a/arch/arm64/include/asm/sparsemem.h
+++ b/arch/arm64/include/asm/sparsemem.h
@@ -10,7 +10,7 @@
/*
* Section size must be at least 512MB for 64K base
* page size config. Otherwise it will be less than
- * MAX_ORDER and the build process will fail.
+ * MAX_PAGE_ORDER and the build process will fail.
*/
#ifdef CONFIG_ARM64_64K_PAGES
#define SECTION_SIZE_BITS 29
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index 06c357d83b..0c4d9045c3 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -13,8 +13,8 @@
#define __BP_HARDEN_HYP_VECS_SZ ((BP_HARDEN_EL2_SLOTS - 1) * SZ_2K)
#ifndef __ASSEMBLY__
-
-#include <linux/percpu.h>
+#include <linux/smp.h>
+#include <asm/percpu.h>
#include <asm/cpufeature.h>
#include <asm/virt.h>
diff --git a/arch/arm64/include/asm/stacktrace/common.h b/arch/arm64/include/asm/stacktrace/common.h
index 508f734de4..f63dc654e5 100644
--- a/arch/arm64/include/asm/stacktrace/common.h
+++ b/arch/arm64/include/asm/stacktrace/common.h
@@ -9,7 +9,6 @@
#ifndef __ASM_STACKTRACE_COMMON_H
#define __ASM_STACKTRACE_COMMON_H
-#include <linux/kprobes.h>
#include <linux/types.h>
struct stack_info {
@@ -23,12 +22,6 @@ struct stack_info {
* @fp: The fp value in the frame record (or the real fp)
* @pc: The lr value in the frame record (or the real lr)
*
- * @kr_cur: When KRETPROBES is selected, holds the kretprobe instance
- * associated with the most recently encountered replacement lr
- * value.
- *
- * @task: The task being unwound.
- *
* @stack: The stack currently being unwound.
* @stacks: An array of stacks which can be unwound.
* @nr_stacks: The number of stacks in @stacks.
@@ -36,10 +29,6 @@ struct stack_info {
struct unwind_state {
unsigned long fp;
unsigned long pc;
-#ifdef CONFIG_KRETPROBES
- struct llist_node *kr_cur;
-#endif
- struct task_struct *task;
struct stack_info stack;
struct stack_info *stacks;
@@ -66,14 +55,8 @@ static inline bool stackinfo_on_stack(const struct stack_info *info,
return true;
}
-static inline void unwind_init_common(struct unwind_state *state,
- struct task_struct *task)
+static inline void unwind_init_common(struct unwind_state *state)
{
- state->task = task;
-#ifdef CONFIG_KRETPROBES
- state->kr_cur = NULL;
-#endif
-
state->stack = stackinfo_get_unknown();
}
diff --git a/arch/arm64/include/asm/stacktrace/nvhe.h b/arch/arm64/include/asm/stacktrace/nvhe.h
index 25ab83a315..44759281d0 100644
--- a/arch/arm64/include/asm/stacktrace/nvhe.h
+++ b/arch/arm64/include/asm/stacktrace/nvhe.h
@@ -31,7 +31,7 @@ static inline void kvm_nvhe_unwind_init(struct unwind_state *state,
unsigned long fp,
unsigned long pc)
{
- unwind_init_common(state, NULL);
+ unwind_init_common(state);
state->fp = fp;
state->pc = pc;
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 5e65f51c10..c3b19b376c 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -645,6 +645,7 @@
#define OP_AT_S1E0W sys_insn(AT_Op0, 0, AT_CRn, 8, 3)
#define OP_AT_S1E1RP sys_insn(AT_Op0, 0, AT_CRn, 9, 0)
#define OP_AT_S1E1WP sys_insn(AT_Op0, 0, AT_CRn, 9, 1)
+#define OP_AT_S1E1A sys_insn(AT_Op0, 0, AT_CRn, 9, 2)
#define OP_AT_S1E2R sys_insn(AT_Op0, 4, AT_CRn, 8, 0)
#define OP_AT_S1E2W sys_insn(AT_Op0, 4, AT_CRn, 8, 1)
#define OP_AT_S12E1R sys_insn(AT_Op0, 4, AT_CRn, 8, 4)
@@ -781,10 +782,16 @@
#define OP_TLBI_VMALLS12E1NXS sys_insn(1, 4, 9, 7, 6)
/* Misc instructions */
+#define OP_GCSPUSHX sys_insn(1, 0, 7, 7, 4)
+#define OP_GCSPOPCX sys_insn(1, 0, 7, 7, 5)
+#define OP_GCSPOPX sys_insn(1, 0, 7, 7, 6)
+#define OP_GCSPUSHM sys_insn(1, 3, 7, 7, 0)
+
#define OP_BRB_IALL sys_insn(1, 1, 7, 2, 4)
#define OP_BRB_INJ sys_insn(1, 1, 7, 2, 5)
#define OP_CFP_RCTX sys_insn(1, 3, 7, 3, 4)
#define OP_DVP_RCTX sys_insn(1, 3, 7, 3, 5)
+#define OP_COSP_RCTX sys_insn(1, 3, 7, 3, 6)
#define OP_CPP_RCTX sys_insn(1, 3, 7, 3, 7)
/* Common SCTLR_ELx flags. */
@@ -871,10 +878,12 @@
/* id_aa64mmfr0 */
#define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN 0x0
+#define ID_AA64MMFR0_EL1_TGRAN4_LPA2 ID_AA64MMFR0_EL1_TGRAN4_52_BIT
#define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX 0x7
#define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN 0x0
#define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX 0x7
#define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN 0x1
+#define ID_AA64MMFR0_EL1_TGRAN16_LPA2 ID_AA64MMFR0_EL1_TGRAN16_52_BIT
#define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX 0xf
#define ARM64_MIN_PARANGE_BITS 32
@@ -882,6 +891,7 @@
#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT 0x0
#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE 0x1
#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN 0x2
+#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2 0x3
#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX 0x7
#ifdef CONFIG_ARM64_PA_BITS_52
@@ -892,11 +902,13 @@
#if defined(CONFIG_ARM64_4K_PAGES)
#define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN4_SHIFT
+#define ID_AA64MMFR0_EL1_TGRAN_LPA2 ID_AA64MMFR0_EL1_TGRAN4_52_BIT
#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN
#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX
#define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT
#elif defined(CONFIG_ARM64_16K_PAGES)
#define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN16_SHIFT
+#define ID_AA64MMFR0_EL1_TGRAN_LPA2 ID_AA64MMFR0_EL1_TGRAN16_52_BIT
#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN
#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX
#define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN16_2_SHIFT
@@ -1039,6 +1051,19 @@
#define PIRx_ELx_PERM(idx, perm) ((perm) << ((idx) * 4))
+/*
+ * Permission Overlay Extension (POE) permission encodings.
+ */
+#define POE_NONE UL(0x0)
+#define POE_R UL(0x1)
+#define POE_X UL(0x2)
+#define POE_RX UL(0x3)
+#define POE_W UL(0x4)
+#define POE_RW UL(0x5)
+#define POE_XW UL(0x6)
+#define POE_RXW UL(0x7)
+#define POE_MASK UL(0xf)
+
#define ARM64_FEATURE_FIELD_BITS 4
/* Defined for compatibility only, do not add new users. */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 553d1bc559..e72a3bf9e5 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -80,6 +80,7 @@ void arch_setup_new_exec(void);
#define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */
#define TIF_SME 27 /* SME in use */
#define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */
+#define TIF_KERNEL_FPSTATE 29 /* Task is in a kernel mode FPSIMD section */
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 846c563689..0150deb332 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -22,15 +22,15 @@ static void tlb_flush(struct mmu_gather *tlb);
#include <asm-generic/tlb.h>
/*
- * get the tlbi levels in arm64. Default value is 0 if more than one
- * of cleared_* is set or neither is set.
- * Arm64 doesn't support p4ds now.
+ * get the tlbi levels in arm64. Default value is TLBI_TTL_UNKNOWN if more than
+ * one of cleared_* is set or neither is set - this elides the level hinting to
+ * the hardware.
*/
static inline int tlb_get_level(struct mmu_gather *tlb)
{
/* The TTL field is only valid for the leaf entry. */
if (tlb->freed_tables)
- return 0;
+ return TLBI_TTL_UNKNOWN;
if (tlb->cleared_ptes && !(tlb->cleared_pmds ||
tlb->cleared_puds ||
@@ -47,7 +47,12 @@ static inline int tlb_get_level(struct mmu_gather *tlb)
tlb->cleared_p4ds))
return 1;
- return 0;
+ if (tlb->cleared_p4ds && !(tlb->cleared_ptes ||
+ tlb->cleared_pmds ||
+ tlb->cleared_puds))
+ return 0;
+
+ return TLBI_TTL_UNKNOWN;
}
static inline void tlb_flush(struct mmu_gather *tlb)
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index bb2c2833a9..bfeb54f3a9 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -94,19 +94,22 @@ static inline unsigned long get_trans_granule(void)
* When ARMv8.4-TTL exists, TLBI operations take an additional hint for
* the level at which the invalidation must take place. If the level is
* wrong, no invalidation may take place. In the case where the level
- * cannot be easily determined, a 0 value for the level parameter will
- * perform a non-hinted invalidation.
+ * cannot be easily determined, the value TLBI_TTL_UNKNOWN will perform
+ * a non-hinted invalidation. Any provided level outside the hint range
+ * will also cause fall-back to non-hinted invalidation.
*
* For Stage-2 invalidation, use the level values provided to that effect
* in asm/stage2_pgtable.h.
*/
#define TLBI_TTL_MASK GENMASK_ULL(47, 44)
+#define TLBI_TTL_UNKNOWN INT_MAX
+
#define __tlbi_level(op, addr, level) do { \
u64 arg = addr; \
\
if (alternative_has_cap_unlikely(ARM64_HAS_ARMv8_4_TTL) && \
- level) { \
+ level >= 0 && level <= 3) { \
u64 ttl = level & 3; \
ttl |= get_trans_granule() << 2; \
arg &= ~TLBI_TTL_MASK; \
@@ -122,28 +125,34 @@ static inline unsigned long get_trans_granule(void)
} while (0)
/*
- * This macro creates a properly formatted VA operand for the TLB RANGE.
- * The value bit assignments are:
+ * This macro creates a properly formatted VA operand for the TLB RANGE. The
+ * value bit assignments are:
*
* +----------+------+-------+-------+-------+----------------------+
* | ASID | TG | SCALE | NUM | TTL | BADDR |
* +-----------------+-------+-------+-------+----------------------+
* |63 48|47 46|45 44|43 39|38 37|36 0|
*
- * The address range is determined by below formula:
- * [BADDR, BADDR + (NUM + 1) * 2^(5*SCALE + 1) * PAGESIZE)
+ * The address range is determined by below formula: [BADDR, BADDR + (NUM + 1) *
+ * 2^(5*SCALE + 1) * PAGESIZE)
+ *
+ * Note that the first argument, baddr, is pre-shifted; If LPA2 is in use, BADDR
+ * holds addr[52:16]. Else BADDR holds page number. See for example ARM DDI
+ * 0487J.a section C5.5.60 "TLBI VAE1IS, TLBI VAE1ISNXS, TLB Invalidate by VA,
+ * EL1, Inner Shareable".
*
*/
-#define __TLBI_VADDR_RANGE(addr, asid, scale, num, ttl) \
- ({ \
- unsigned long __ta = (addr) >> PAGE_SHIFT; \
- __ta &= GENMASK_ULL(36, 0); \
- __ta |= (unsigned long)(ttl) << 37; \
- __ta |= (unsigned long)(num) << 39; \
- __ta |= (unsigned long)(scale) << 44; \
- __ta |= get_trans_granule() << 46; \
- __ta |= (unsigned long)(asid) << 48; \
- __ta; \
+#define __TLBI_VADDR_RANGE(baddr, asid, scale, num, ttl) \
+ ({ \
+ unsigned long __ta = (baddr); \
+ unsigned long __ttl = (ttl >= 1 && ttl <= 3) ? ttl : 0; \
+ __ta &= GENMASK_ULL(36, 0); \
+ __ta |= __ttl << 37; \
+ __ta |= (unsigned long)(num) << 39; \
+ __ta |= (unsigned long)(scale) << 44; \
+ __ta |= get_trans_granule() << 46; \
+ __ta |= (unsigned long)(asid) << 48; \
+ __ta; \
})
/* These macros are used by the TLBI RANGE feature. */
@@ -152,12 +161,18 @@ static inline unsigned long get_trans_granule(void)
#define MAX_TLBI_RANGE_PAGES __TLBI_RANGE_PAGES(31, 3)
/*
- * Generate 'num' values from -1 to 30 with -1 rejected by the
- * __flush_tlb_range() loop below.
+ * Generate 'num' values from -1 to 31 with -1 rejected by the
+ * __flush_tlb_range() loop below. Its return value is only
+ * significant for a maximum of MAX_TLBI_RANGE_PAGES pages. If
+ * 'pages' is more than that, you must iterate over the overall
+ * range.
*/
-#define TLBI_RANGE_MASK GENMASK_ULL(4, 0)
-#define __TLBI_RANGE_NUM(pages, scale) \
- ((((pages) >> (5 * (scale) + 1)) & TLBI_RANGE_MASK) - 1)
+#define __TLBI_RANGE_NUM(pages, scale) \
+ ({ \
+ int __pages = min((pages), \
+ __TLBI_RANGE_PAGES(31, (scale))); \
+ (__pages >> (5 * (scale) + 1)) - 1; \
+ })
/*
* TLB Invalidation
@@ -216,12 +231,16 @@ static inline unsigned long get_trans_granule(void)
* CPUs, ensuring that any walk-cache entries associated with the
* translation are also invalidated.
*
- * __flush_tlb_range(vma, start, end, stride, last_level)
+ * __flush_tlb_range(vma, start, end, stride, last_level, tlb_level)
* Invalidate the virtual-address range '[start, end)' on all
* CPUs for the user address space corresponding to 'vma->mm'.
* The invalidation operations are issued at a granularity
* determined by 'stride' and only affect any walk-cache entries
- * if 'last_level' is equal to false.
+ * if 'last_level' is equal to false. tlb_level is the level at
+ * which the invalidation must take place. If the level is wrong,
+ * no invalidation may take place. In the case where the level
+ * cannot be easily determined, the value TLBI_TTL_UNKNOWN will
+ * perform a non-hinted invalidation.
*
*
* Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented
@@ -345,34 +364,40 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
* @tlb_level: Translation Table level hint, if known
* @tlbi_user: If 'true', call an additional __tlbi_user()
* (typically for user ASIDs). 'flase' for IPA instructions
+ * @lpa2: If 'true', the lpa2 scheme is used as set out below
*
* When the CPU does not support TLB range operations, flush the TLB
* entries one by one at the granularity of 'stride'. If the TLB
* range ops are supported, then:
*
- * 1. If 'pages' is odd, flush the first page through non-range
- * operations;
+ * 1. If FEAT_LPA2 is in use, the start address of a range operation must be
+ * 64KB aligned, so flush pages one by one until the alignment is reached
+ * using the non-range operations. This step is skipped if LPA2 is not in
+ * use.
*
- * 2. For remaining pages: the minimum range granularity is decided
- * by 'scale', so multiple range TLBI operations may be required.
- * Start from scale = 0, flush the corresponding number of pages
- * ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
- * until no pages left.
+ * 2. The minimum range granularity is decided by 'scale', so multiple range
+ * TLBI operations may be required. Start from scale = 3, flush the largest
+ * possible number of pages ((num+1)*2^(5*scale+1)) that fit into the
+ * requested range, then decrement scale and continue until one or zero pages
+ * are left. We must start from highest scale to ensure 64KB start alignment
+ * is maintained in the LPA2 case.
*
- * Note that certain ranges can be represented by either num = 31 and
- * scale or num = 0 and scale + 1. The loop below favours the latter
- * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
+ * 3. If there is 1 page remaining, flush it through non-range operations. Range
+ * operations can only span an even number of pages. We save this for last to
+ * ensure 64KB start alignment is maintained for the LPA2 case.
*/
#define __flush_tlb_range_op(op, start, pages, stride, \
- asid, tlb_level, tlbi_user) \
+ asid, tlb_level, tlbi_user, lpa2) \
do { \
int num = 0; \
- int scale = 0; \
+ int scale = 3; \
+ int shift = lpa2 ? 16 : PAGE_SHIFT; \
unsigned long addr; \
\
while (pages > 0) { \
if (!system_supports_tlb_range() || \
- pages % 2 == 1) { \
+ pages == 1 || \
+ (lpa2 && start != ALIGN(start, SZ_64K))) { \
addr = __TLBI_VADDR(start, asid); \
__tlbi_level(op, addr, tlb_level); \
if (tlbi_user) \
@@ -384,20 +409,20 @@ do { \
\
num = __TLBI_RANGE_NUM(pages, scale); \
if (num >= 0) { \
- addr = __TLBI_VADDR_RANGE(start, asid, scale, \
- num, tlb_level); \
+ addr = __TLBI_VADDR_RANGE(start >> shift, asid, \
+ scale, num, tlb_level); \
__tlbi(r##op, addr); \
if (tlbi_user) \
__tlbi_user(r##op, addr); \
start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
pages -= __TLBI_RANGE_PAGES(num, scale); \
} \
- scale++; \
+ scale--; \
} \
} while (0)
#define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
- __flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false)
+ __flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false, kvm_lpa2_is_enabled());
static inline void __flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
@@ -427,9 +452,11 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
asid = ASID(vma->vm_mm);
if (last_level)
- __flush_tlb_range_op(vale1is, start, pages, stride, asid, tlb_level, true);
+ __flush_tlb_range_op(vale1is, start, pages, stride, asid,
+ tlb_level, true, lpa2_is_enabled());
else
- __flush_tlb_range_op(vae1is, start, pages, stride, asid, tlb_level, true);
+ __flush_tlb_range_op(vae1is, start, pages, stride, asid,
+ tlb_level, true, lpa2_is_enabled());
dsb(ish);
mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end);
@@ -441,9 +468,10 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
/*
* We cannot use leaf-only invalidation here, since we may be invalidating
* table entries as part of collapsing hugepages or moving page tables.
- * Set the tlb_level to 0 because we can not get enough information here.
+ * Set the tlb_level to TLBI_TTL_UNKNOWN because we can not get enough
+ * information here.
*/
- __flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
+ __flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
}
static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 9fab663dd2..a323b109b9 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -23,6 +23,7 @@ void update_freq_counters_refs(void);
#define arch_set_freq_scale topology_set_freq_scale
#define arch_scale_freq_capacity topology_get_freq_scale
#define arch_scale_freq_invariant topology_scale_freq_invariant
+#define arch_scale_freq_ref topology_get_freq_ref
#ifdef CONFIG_ACPI_CPPC_LIB
#define arch_init_invariance_cppc topology_init_cpu_capacity_cppc
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 531effca5f..491b2b9bd5 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -39,7 +39,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 457
+#define __NR_compat_syscalls 462
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 9f7c1bf995..7118282d1c 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -919,6 +919,16 @@ __SYSCALL(__NR_futex_wake, sys_futex_wake)
__SYSCALL(__NR_futex_wait, sys_futex_wait)
#define __NR_futex_requeue 456
__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
+#define __NR_statmount 457
+__SYSCALL(__NR_statmount, sys_statmount)
+#define __NR_listmount 458
+__SYSCALL(__NR_listmount, sys_listmount)
+#define __NR_lsm_get_self_attr 459
+__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr)
+#define __NR_lsm_set_self_attr 460
+__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
+#define __NR_lsm_list_modules 461
+__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h
index b4ae321099..4305995c8f 100644
--- a/arch/arm64/include/asm/vdso.h
+++ b/arch/arm64/include/asm/vdso.h
@@ -17,9 +17,6 @@
#ifndef __ASSEMBLY__
#include <generated/vdso-offsets.h>
-#ifdef CONFIG_COMPAT_VDSO
-#include <generated/vdso32-offsets.h>
-#endif
#define VDSO_SYMBOL(base, name) \
({ \
diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h
new file mode 100644
index 0000000000..df2c47c559
--- /dev/null
+++ b/arch/arm64/include/asm/vncr_mapping.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * System register offsets in the VNCR page
+ * All offsets are *byte* displacements!
+ */
+
+#ifndef __ARM64_VNCR_MAPPING_H__
+#define __ARM64_VNCR_MAPPING_H__
+
+#define VNCR_VTTBR_EL2 0x020
+#define VNCR_VTCR_EL2 0x040
+#define VNCR_VMPIDR_EL2 0x050
+#define VNCR_CNTVOFF_EL2 0x060
+#define VNCR_HCR_EL2 0x078
+#define VNCR_HSTR_EL2 0x080
+#define VNCR_VPIDR_EL2 0x088
+#define VNCR_TPIDR_EL2 0x090
+#define VNCR_HCRX_EL2 0x0A0
+#define VNCR_VNCR_EL2 0x0B0
+#define VNCR_CPACR_EL1 0x100
+#define VNCR_CONTEXTIDR_EL1 0x108
+#define VNCR_SCTLR_EL1 0x110
+#define VNCR_ACTLR_EL1 0x118
+#define VNCR_TCR_EL1 0x120
+#define VNCR_AFSR0_EL1 0x128
+#define VNCR_AFSR1_EL1 0x130
+#define VNCR_ESR_EL1 0x138
+#define VNCR_MAIR_EL1 0x140
+#define VNCR_AMAIR_EL1 0x148
+#define VNCR_MDSCR_EL1 0x158
+#define VNCR_SPSR_EL1 0x160
+#define VNCR_CNTV_CVAL_EL0 0x168
+#define VNCR_CNTV_CTL_EL0 0x170
+#define VNCR_CNTP_CVAL_EL0 0x178
+#define VNCR_CNTP_CTL_EL0 0x180
+#define VNCR_SCXTNUM_EL1 0x188
+#define VNCR_TFSR_EL1 0x190
+#define VNCR_HFGRTR_EL2 0x1B8
+#define VNCR_HFGWTR_EL2 0x1C0
+#define VNCR_HFGITR_EL2 0x1C8
+#define VNCR_HDFGRTR_EL2 0x1D0
+#define VNCR_HDFGWTR_EL2 0x1D8
+#define VNCR_ZCR_EL1 0x1E0
+#define VNCR_HAFGRTR_EL2 0x1E8
+#define VNCR_TTBR0_EL1 0x200
+#define VNCR_TTBR1_EL1 0x210
+#define VNCR_FAR_EL1 0x220
+#define VNCR_ELR_EL1 0x230
+#define VNCR_SP_EL1 0x240
+#define VNCR_VBAR_EL1 0x250
+#define VNCR_TCR2_EL1 0x270
+#define VNCR_PIRE0_EL1 0x290
+#define VNCR_PIRE0_EL2 0x298
+#define VNCR_PIR_EL1 0x2A0
+#define VNCR_ICH_LR0_EL2 0x400
+#define VNCR_ICH_LR1_EL2 0x408
+#define VNCR_ICH_LR2_EL2 0x410
+#define VNCR_ICH_LR3_EL2 0x418
+#define VNCR_ICH_LR4_EL2 0x420
+#define VNCR_ICH_LR5_EL2 0x428
+#define VNCR_ICH_LR6_EL2 0x430
+#define VNCR_ICH_LR7_EL2 0x438
+#define VNCR_ICH_LR8_EL2 0x440
+#define VNCR_ICH_LR9_EL2 0x448
+#define VNCR_ICH_LR10_EL2 0x450
+#define VNCR_ICH_LR11_EL2 0x458
+#define VNCR_ICH_LR12_EL2 0x460
+#define VNCR_ICH_LR13_EL2 0x468
+#define VNCR_ICH_LR14_EL2 0x470
+#define VNCR_ICH_LR15_EL2 0x478
+#define VNCR_ICH_AP0R0_EL2 0x480
+#define VNCR_ICH_AP0R1_EL2 0x488
+#define VNCR_ICH_AP0R2_EL2 0x490
+#define VNCR_ICH_AP0R3_EL2 0x498
+#define VNCR_ICH_AP1R0_EL2 0x4A0
+#define VNCR_ICH_AP1R1_EL2 0x4A8
+#define VNCR_ICH_AP1R2_EL2 0x4B0
+#define VNCR_ICH_AP1R3_EL2 0x4B8
+#define VNCR_ICH_HCR_EL2 0x4C0
+#define VNCR_ICH_VMCR_EL2 0x4C8
+#define VNCR_VDISR_EL2 0x500
+#define VNCR_PMBLIMITR_EL1 0x800
+#define VNCR_PMBPTR_EL1 0x810
+#define VNCR_PMBSR_EL1 0x820
+#define VNCR_PMSCR_EL1 0x828
+#define VNCR_PMSEVFR_EL1 0x830
+#define VNCR_PMSICR_EL1 0x838
+#define VNCR_PMSIRR_EL1 0x840
+#define VNCR_PMSLATFR_EL1 0x848
+#define VNCR_TRFCR_EL1 0x880
+#define VNCR_MPAM1_EL1 0x900
+#define VNCR_MPAMHCR_EL2 0x930
+#define VNCR_MPAMVPMV_EL2 0x938
+#define VNCR_MPAMVPM0_EL2 0x940
+#define VNCR_MPAMVPM1_EL2 0x948
+#define VNCR_MPAMVPM2_EL2 0x950
+#define VNCR_MPAMVPM3_EL2 0x958
+#define VNCR_MPAMVPM4_EL2 0x960
+#define VNCR_MPAMVPM5_EL2 0x968
+#define VNCR_MPAMVPM6_EL2 0x970
+#define VNCR_MPAMVPM7_EL2 0x978
+
+#endif /* __ARM64_VNCR_MAPPING_H__ */