summaryrefslogtreecommitdiff
path: root/arch/arm64/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/include')
-rw-r--r--arch/arm64/include/asm/assembler.h2
-rw-r--r--arch/arm64/include/asm/cache.h6
-rw-r--r--arch/arm64/include/asm/cpufeature.h6
-rw-r--r--arch/arm64/include/asm/fpsimdmacros.h8
-rw-r--r--arch/arm64/include/asm/kernel-pgtable.h27
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h7
-rw-r--r--arch/arm64/include/asm/kvm_pgtable.h2
-rw-r--r--arch/arm64/include/asm/memory.h7
-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/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.h100
-rw-r--r--arch/arm64/include/asm/unistd.h2
-rw-r--r--arch/arm64/include/asm/unistd32.h4
19 files changed, 129 insertions, 120 deletions
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 376a980f2bad..7b1975bf4b90 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>
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index ceb368d33bf4..06a4670bdb0b 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/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index f6d416fe49b0..21c824edf8ce 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -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/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index cdf6a35e3994..cda81d009c9b 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/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 85d26143faa5..83ddb14b95a5 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_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 49e0d4b36bd0..e3e793d0ec30 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_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index d3e354bb8351..10068500d601 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -25,6 +25,8 @@
#define KVM_PGTABLE_MIN_BLOCK_LEVEL 2U
#endif
+#define kvm_lpa2_is_enabled() false
+
static inline u64 kvm_get_parange(u64 mmfr0)
{
u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index fde4186cc387..56d1e6f14861 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -182,6 +182,7 @@
#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 +194,12 @@ 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 +405,5 @@ 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 e9624f6326dd..483dbfa39c4c 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 e5bc54522e71..5b0a04810b23 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 6a75d7ecdcaa..8e86c9e70e48 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/stacktrace/common.h b/arch/arm64/include/asm/stacktrace/common.h
index 508f734de46e..f63dc654e545 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 25ab83a315a7..44759281d0d4 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 5e65f51c10d2..c3b19b376c86 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 553d1bc559c6..e72a3bf9e563 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 846c563689a8..0150deb332af 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 bb2c2833a987..1deb5d789c2e 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. */
@@ -216,12 +225,16 @@ 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 +358,44 @@ 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. 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.
*
- * 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.
+ * 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.
*
* 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.
*/
#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 +407,20 @@ 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 +450,11 @@ 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 +466,10 @@ 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/unistd.h b/arch/arm64/include/asm/unistd.h
index 531effca5f1f..b63f870debaf 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 459
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 9f7c1bf99526..8a191423c316 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -919,6 +919,10 @@ __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)
/*
* Please add new compat syscalls above this comment and update
generated by cgit (git 2.34.1) at 2024-06-09 10:40:56 +0000