HWCAP_AES
- Functionality implied by ID_AA64ISAR1_EL1.AES == 0b0001.
+ Functionality implied by ID_AA64ISAR0_EL1.AES == 0b0001.
HWCAP_PMULL
- Functionality implied by ID_AA64ISAR1_EL1.AES == 0b0010.
+ Functionality implied by ID_AA64ISAR0_EL1.AES == 0b0010.
HWCAP_SHA1
HWCAP_SHA512
- Functionality implied by ID_AA64ISAR0_EL1.SHA2 == 0b0002.
+ Functionality implied by ID_AA64ISAR0_EL1.SHA2 == 0b0010.
HWCAP_SVE
HWCAP_ILRCPC
- Functionality implied by ID_AA64ISR1_EL1.LRCPC == 0b0002.
+ Functionality implied by ID_AA64ISAR1_EL1.LRCPC == 0b0010.
HWCAP_FLAGM
Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0001.
+
+HWCAP_SSBS
+
+ Functionality implied by ID_AA64PFR1_EL1.SSBS == 0b0010.
--- /dev/null
+HugeTLBpage on ARM64
+====================
+
+Hugepage relies on making efficient use of TLBs to improve performance of
+address translations. The benefit depends on both -
+
+ - the size of hugepages
+ - size of entries supported by the TLBs
+
+The ARM64 port supports two flavours of hugepages.
+
+1) Block mappings at the pud/pmd level
+--------------------------------------
+
+These are regular hugepages where a pmd or a pud page table entry points to a
+block of memory. Regardless of the supported size of entries in TLB, block
+mappings reduce the depth of page table walk needed to translate hugepage
+addresses.
+
+2) Using the Contiguous bit
+---------------------------
+
+The architecture provides a contiguous bit in the translation table entries
+(D4.5.3, ARM DDI 0487C.a) that hints to the MMU to indicate that it is one of a
+contiguous set of entries that can be cached in a single TLB entry.
+
+The contiguous bit is used in Linux to increase the mapping size at the pmd and
+pte (last) level. The number of supported contiguous entries varies by page size
+and level of the page table.
+
+
+The following hugepage sizes are supported -
+
+ CONT PTE PMD CONT PMD PUD
+ -------- --- -------- ---
+ 4K: 64K 2M 32M 1G
+ 16K: 2M 32M 1G
+ 64K: 2M 512M 16G
| ARM | Cortex-A72 | #853709 | N/A |
| ARM | Cortex-A73 | #858921 | ARM64_ERRATUM_858921 |
| ARM | Cortex-A55 | #1024718 | ARM64_ERRATUM_1024718 |
+| ARM | Cortex-A76 | #1188873 | ARM64_ERRATUM_1188873 |
| ARM | MMU-500 | #841119,#826419 | N/A |
| | | | |
| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 |
F: arch/arm/boot/dts/mmp*
F: arch/arm/mach-mmp/
+MMU GATHER AND TLB INVALIDATION
+M: Will Deacon <will.deacon@arm.com>
+M: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
+M: Andrew Morton <akpm@linux-foundation.org>
+M: Nick Piggin <npiggin@gmail.com>
+M: Peter Zijlstra <peterz@infradead.org>
+L: linux-arch@vger.kernel.org
+L: linux-mm@kvack.org
+S: Maintained
+F: arch/*/include/asm/tlb.h
+F: include/asm-generic/tlb.h
+F: mm/mmu_gather.c
+
MN88472 MEDIA DRIVER
M: Antti Palosaari <crope@iki.fi>
L: linux-media@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/arm/firmware/sdei.txt
F: drivers/firmware/arm_sdei.c
-F: include/linux/sdei.h
-F: include/uapi/linux/sdei.h
+F: include/linux/arm_sdei.h
+F: include/uapi/linux/arm_sdei.h
SOFTWARE RAID (Multiple Disks) SUPPORT
M: Shaohua Li <shli@kernel.org>
#else
#define VTTBR_X (5 - KVM_T0SZ)
#endif
+#define VTTBR_CNP_BIT _AC(1, UL)
#define VTTBR_BADDR_MASK (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_X)
#define VTTBR_VMID_SHIFT _AC(48, ULL)
#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
#define kvm_phys_to_vttbr(addr) (addr)
+static inline bool kvm_cpu_has_cnp(void)
+{
+ return false;
+}
+
#endif /* !__ASSEMBLY__ */
#endif /* __ARM_KVM_MMU_H__ */
select CLONE_BACKWARDS
select COMMON_CLK
select CPU_PM if (SUSPEND || CPU_IDLE)
+ select CRC32
select DCACHE_WORD_ACCESS
select DMA_DIRECT_OPS
select EDAC_SUPPORT
select HAVE_PERF_USER_STACK_DUMP
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RCU_TABLE_FREE
+ select HAVE_RCU_TABLE_INVALIDATE
select HAVE_RSEQ
select HAVE_STACKPROTECTOR
select HAVE_SYSCALL_TRACEPOINTS
If unsure, say Y.
+config ARM64_ERRATUM_1188873
+ bool "Cortex-A76: MRC read following MRRC read of specific Generic Timer in AArch32 might give incorrect result"
+ default y
+ select ARM_ARCH_TIMER_OOL_WORKAROUND
+ help
+ This option adds work arounds for ARM Cortex-A76 erratum 1188873
+
+ Affected Cortex-A76 cores (r0p0, r1p0, r2p0) could cause
+ register corruption when accessing the timer registers from
+ AArch32 userspace.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
def_bool y
-config ARCH_HAS_HOLES_MEMORYMODEL
- def_bool y if SPARSEMEM
-
config ARCH_SPARSEMEM_ENABLE
def_bool y
select SPARSEMEM_VMEMMAP_ENABLE
def_bool !NUMA
config HAVE_ARCH_PFN_VALID
- def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
+ def_bool y
config HW_PERF_EVENTS
def_bool y
and access the new registers if the system supports the extension.
Platform RAS features may additionally depend on firmware support.
+config ARM64_CNP
+ bool "Enable support for Common Not Private (CNP) translations"
+ default y
+ depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN
+ help
+ Common Not Private (CNP) allows translation table entries to
+ be shared between different PEs in the same inner shareable
+ domain, so the hardware can use this fact to optimise the
+ caching of such entries in the TLB.
+
+ Selecting this option allows the CNP feature to be detected
+ at runtime, and does not affect PEs that do not implement
+ this feature.
+
endmenu
config ARM64_SVE
ldr \rd, [\rn, #MM_CONTEXT_ID]
.endm
/*
- * read_ctr - read CTR_EL0. If the system has mismatched
- * cache line sizes, provide the system wide safe value
- * from arm64_ftr_reg_ctrel0.sys_val
+ * read_ctr - read CTR_EL0. If the system has mismatched register fields,
+ * provide the system wide safe value from arm64_ftr_reg_ctrel0.sys_val
*/
.macro read_ctr, reg
-alternative_if_not ARM64_MISMATCHED_CACHE_LINE_SIZE
+alternative_if_not ARM64_MISMATCHED_CACHE_TYPE
mrs \reg, ctr_el0 // read CTR
nop
alternative_else
#define L1_CACHE_SHIFT (6)
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
+
+#define CLIDR_LOUU_SHIFT 27
+#define CLIDR_LOC_SHIFT 24
+#define CLIDR_LOUIS_SHIFT 21
+
+#define CLIDR_LOUU(clidr) (((clidr) >> CLIDR_LOUU_SHIFT) & 0x7)
+#define CLIDR_LOC(clidr) (((clidr) >> CLIDR_LOC_SHIFT) & 0x7)
+#define CLIDR_LOUIS(clidr) (((clidr) >> CLIDR_LOUIS_SHIFT) & 0x7)
+
/*
* Memory returned by kmalloc() may be used for DMA, so we must make
* sure that all such allocations are cache aligned. Otherwise,
return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
}
+/*
+ * Read the effective value of CTR_EL0.
+ *
+ * According to ARM ARM for ARMv8-A (ARM DDI 0487C.a),
+ * section D10.2.33 "CTR_EL0, Cache Type Register" :
+ *
+ * CTR_EL0.IDC reports the data cache clean requirements for
+ * instruction to data coherence.
+ *
+ * 0 - dcache clean to PoU is required unless :
+ * (CLIDR_EL1.LoC == 0) || (CLIDR_EL1.LoUIS == 0 && CLIDR_EL1.LoUU == 0)
+ * 1 - dcache clean to PoU is not required for i-to-d coherence.
+ *
+ * This routine provides the CTR_EL0 with the IDC field updated to the
+ * effective state.
+ */
+static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void)
+{
+ u32 ctr = read_cpuid_cachetype();
+
+ if (!(ctr & BIT(CTR_IDC_SHIFT))) {
+ u64 clidr = read_sysreg(clidr_el1);
+
+ if (CLIDR_LOC(clidr) == 0 ||
+ (CLIDR_LOUIS(clidr) == 0 && CLIDR_LOUU(clidr) == 0))
+ ctr |= BIT(CTR_IDC_SHIFT);
+ }
+
+ return ctr;
+}
+
#endif /* __ASSEMBLY__ */
#endif
}
#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
+#define COMPAT_MINSIGSTKSZ 2048
static inline void __user *arch_compat_alloc_user_space(long len)
{
+++ /dev/null
-/*
- * Based on arch/arm/include/asm/compiler.h
- *
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_COMPILER_H
-#define __ASM_COMPILER_H
-
-/*
- * This is used to ensure the compiler did actually allocate the register we
- * asked it for some inline assembly sequences. Apparently we can't trust the
- * compiler from one version to another so a bit of paranoia won't hurt. This
- * string is meant to be concatenated with the inline asm string and will
- * cause compilation to stop on mismatch. (for details, see gcc PR 15089)
- */
-#define __asmeq(x, y) ".ifnc " x "," y " ; .err ; .endif\n\t"
-
-#endif /* __ASM_COMPILER_H */
#define ARM64_WORKAROUND_CAVIUM_27456 12
#define ARM64_HAS_32BIT_EL0 13
#define ARM64_HARDEN_EL2_VECTORS 14
-#define ARM64_MISMATCHED_CACHE_LINE_SIZE 15
+#define ARM64_HAS_CNP 15
#define ARM64_HAS_NO_FPSIMD 16
#define ARM64_WORKAROUND_REPEAT_TLBI 17
#define ARM64_WORKAROUND_QCOM_FALKOR_E1003 18
#define ARM64_SSBD 30
#define ARM64_MISMATCHED_CACHE_TYPE 31
#define ARM64_HAS_STAGE2_FWB 32
+#define ARM64_HAS_CRC32 33
+#define ARM64_SSBS 34
+#define ARM64_WORKAROUND_1188873 35
-#define ARM64_NCAPS 33
+#define ARM64_NCAPS 36
#endif /* __ASM_CPUCAPS_H */
/*
* CPU feature detected at boot time based on system-wide value of a
* feature. It is safe for a late CPU to have this feature even though
- * the system hasn't enabled it, although the featuer will not be used
+ * the system hasn't enabled it, although the feature will not be used
* by Linux in this case. If the system has enabled this feature already,
* then every late CPU must have it.
*/
cpus_have_const_cap(ARM64_SVE);
}
+static inline bool system_supports_cnp(void)
+{
+ return IS_ENABLED(CONFIG_ARM64_CNP) &&
+ cpus_have_const_cap(ARM64_HAS_CNP);
+}
+
#define ARM64_SSBD_UNKNOWN -1
#define ARM64_SSBD_FORCE_DISABLE 0
#define ARM64_SSBD_KERNEL 1
static inline void arm64_set_ssbd_mitigation(bool state) {}
#endif
+extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
#endif /* __ASSEMBLY__ */
#endif
#define ARM_CPU_PART_CORTEX_A75 0xD0A
#define ARM_CPU_PART_CORTEX_A35 0xD04
#define ARM_CPU_PART_CORTEX_A55 0xD05
+#define ARM_CPU_PART_CORTEX_A76 0xD0B
#define APM_CPU_PART_POTENZA 0x000
#define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75)
#define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35)
#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55)
+#define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
#define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
{
unsigned long flags;
- asm volatile(
- "mrs %0, daif // local_daif_save\n"
- : "=r" (flags)
- :
- : "memory");
+ flags = arch_local_save_flags();
+
local_daif_mask();
return flags;
{
if (!arch_irqs_disabled_flags(flags))
trace_hardirqs_on();
- asm volatile(
- "msr daif, %0 // local_daif_restore"
- :
- : "r" (flags)
- : "memory");
+
+ arch_local_irq_restore(flags);
+
if (arch_irqs_disabled_flags(flags))
trace_hardirqs_off();
}
#define ESR_ELx_CV (UL(1) << 24)
#define ESR_ELx_COND_SHIFT (20)
#define ESR_ELx_COND_MASK (UL(0xF) << ESR_ELx_COND_SHIFT)
+#define ESR_ELx_WFx_ISS_TI (UL(1) << 0)
+#define ESR_ELx_WFx_ISS_WFI (UL(0) << 0)
#define ESR_ELx_WFx_ISS_WFE (UL(1) << 0)
#define ESR_ELx_xVC_IMM_MASK ((1UL << 16) - 1)
#define DISR_EL1_ESR_MASK (ESR_ELx_AET | ESR_ELx_EA | ESR_ELx_FSC)
/* ESR value templates for specific events */
+#define ESR_ELx_WFx_MASK (ESR_ELx_EC_MASK | ESR_ELx_WFx_ISS_TI)
+#define ESR_ELx_WFx_WFI_VAL ((ESR_ELx_EC_WFx << ESR_ELx_EC_SHIFT) | \
+ ESR_ELx_WFx_ISS_WFI)
/* BRK instruction trap from AArch64 state */
#define ESR_ELx_VAL_BRK64(imm) \
#define ESR_ELx_SYS64_ISS_SYS_OP_MASK (ESR_ELx_SYS64_ISS_SYS_MASK | \
ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_RT(esr) \
+ (((esr) & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT)
/*
* User space cache operations have the following sysreg encoding
* in System instructions.
#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL \
(ESR_ELx_SYS64_ISS_SYS_VAL(1, 3, 1, 7, 0) | \
ESR_ELx_SYS64_ISS_DIR_WRITE)
+/*
+ * User space MRS operations which are supported for emulation
+ * have the following sysreg encoding in System instructions.
+ * op0 = 3, op1= 0, crn = 0, {crm = 0, 4-7}, READ (L = 1)
+ */
+#define ESR_ELx_SYS64_ISS_SYS_MRS_OP_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \
+ ESR_ELx_SYS64_ISS_OP1_MASK | \
+ ESR_ELx_SYS64_ISS_CRN_MASK | \
+ ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_SYS_MRS_OP_VAL \
+ (ESR_ELx_SYS64_ISS_SYS_VAL(3, 0, 0, 0, 0) | \
+ ESR_ELx_SYS64_ISS_DIR_READ)
#define ESR_ELx_SYS64_ISS_SYS_CTR ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 1, 0, 0)
#define ESR_ELx_SYS64_ISS_SYS_CTR_READ (ESR_ELx_SYS64_ISS_SYS_CTR | \
#define ESR_ELx_FP_EXC_TFV (UL(1) << 23)
+/*
+ * ISS field definitions for CP15 accesses
+ */
+#define ESR_ELx_CP15_32_ISS_DIR_MASK 0x1
+#define ESR_ELx_CP15_32_ISS_DIR_READ 0x1
+#define ESR_ELx_CP15_32_ISS_DIR_WRITE 0x0
+
+#define ESR_ELx_CP15_32_ISS_RT_SHIFT 5
+#define ESR_ELx_CP15_32_ISS_RT_MASK (UL(0x1f) << ESR_ELx_CP15_32_ISS_RT_SHIFT)
+#define ESR_ELx_CP15_32_ISS_CRM_SHIFT 1
+#define ESR_ELx_CP15_32_ISS_CRM_MASK (UL(0xf) << ESR_ELx_CP15_32_ISS_CRM_SHIFT)
+#define ESR_ELx_CP15_32_ISS_CRN_SHIFT 10
+#define ESR_ELx_CP15_32_ISS_CRN_MASK (UL(0xf) << ESR_ELx_CP15_32_ISS_CRN_SHIFT)
+#define ESR_ELx_CP15_32_ISS_OP1_SHIFT 14
+#define ESR_ELx_CP15_32_ISS_OP1_MASK (UL(0x7) << ESR_ELx_CP15_32_ISS_OP1_SHIFT)
+#define ESR_ELx_CP15_32_ISS_OP2_SHIFT 17
+#define ESR_ELx_CP15_32_ISS_OP2_MASK (UL(0x7) << ESR_ELx_CP15_32_ISS_OP2_SHIFT)
+
+#define ESR_ELx_CP15_32_ISS_SYS_MASK (ESR_ELx_CP15_32_ISS_OP1_MASK | \
+ ESR_ELx_CP15_32_ISS_OP2_MASK | \
+ ESR_ELx_CP15_32_ISS_CRN_MASK | \
+ ESR_ELx_CP15_32_ISS_CRM_MASK | \
+ ESR_ELx_CP15_32_ISS_DIR_MASK)
+#define ESR_ELx_CP15_32_ISS_SYS_VAL(op1, op2, crn, crm) \
+ (((op1) << ESR_ELx_CP15_32_ISS_OP1_SHIFT) | \
+ ((op2) << ESR_ELx_CP15_32_ISS_OP2_SHIFT) | \
+ ((crn) << ESR_ELx_CP15_32_ISS_CRN_SHIFT) | \
+ ((crm) << ESR_ELx_CP15_32_ISS_CRM_SHIFT))
+
+#define ESR_ELx_CP15_64_ISS_DIR_MASK 0x1
+#define ESR_ELx_CP15_64_ISS_DIR_READ 0x1
+#define ESR_ELx_CP15_64_ISS_DIR_WRITE 0x0
+
+#define ESR_ELx_CP15_64_ISS_RT_SHIFT 5
+#define ESR_ELx_CP15_64_ISS_RT_MASK (UL(0x1f) << ESR_ELx_CP15_64_ISS_RT_SHIFT)
+
+#define ESR_ELx_CP15_64_ISS_RT2_SHIFT 10
+#define ESR_ELx_CP15_64_ISS_RT2_MASK (UL(0x1f) << ESR_ELx_CP15_64_ISS_RT2_SHIFT)
+
+#define ESR_ELx_CP15_64_ISS_OP1_SHIFT 16
+#define ESR_ELx_CP15_64_ISS_OP1_MASK (UL(0xf) << ESR_ELx_CP15_64_ISS_OP1_SHIFT)
+#define ESR_ELx_CP15_64_ISS_CRM_SHIFT 1
+#define ESR_ELx_CP15_64_ISS_CRM_MASK (UL(0xf) << ESR_ELx_CP15_64_ISS_CRM_SHIFT)
+
+#define ESR_ELx_CP15_64_ISS_SYS_VAL(op1, crm) \
+ (((op1) << ESR_ELx_CP15_64_ISS_OP1_SHIFT) | \
+ ((crm) << ESR_ELx_CP15_64_ISS_CRM_SHIFT))
+
+#define ESR_ELx_CP15_64_ISS_SYS_MASK (ESR_ELx_CP15_64_ISS_OP1_MASK | \
+ ESR_ELx_CP15_64_ISS_CRM_MASK | \
+ ESR_ELx_CP15_64_ISS_DIR_MASK)
+
+#define ESR_ELx_CP15_64_ISS_SYS_CNTVCT (ESR_ELx_CP15_64_ISS_SYS_VAL(1, 14) | \
+ ESR_ELx_CP15_64_ISS_DIR_READ)
+
+#define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ (ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\
+ ESR_ELx_CP15_32_ISS_DIR_READ)
+
#ifndef __ASSEMBLY__
#include <asm/types.h>
+ EARLY_PGDS((vstart), (vend)) /* each PGDIR needs a next level page table */ \
+ EARLY_PUDS((vstart), (vend)) /* each PUD needs a next level page table */ \
+ EARLY_PMDS((vstart), (vend))) /* each PMD needs a next level page table */
-#define SWAPPER_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR + TEXT_OFFSET, _end))
+#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR + TEXT_OFFSET, _end))
#define IDMAP_DIR_SIZE (IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
#define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS)
#define VTTBR_X (VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA)
+#define VTTBR_CNP_BIT (UL(1))
#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X)
#define VTTBR_VMID_SHIFT (UL(48))
#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
{
u32 esr = kvm_vcpu_get_hsr(vcpu);
- return (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ return ESR_ELx_SYS64_ISS_RT(esr);
}
static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state);
+void __kvm_enable_ssbs(void);
+
static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
unsigned long hyp_stack_ptr,
unsigned long vector_ptr)
*/
BUG_ON(!static_branch_likely(&arm64_const_caps_ready));
__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2);
+
+ /*
+ * Disabling SSBD on a non-VHE system requires us to enable SSBS
+ * at EL2.
+ */
+ if (!has_vhe() && this_cpu_has_cap(ARM64_SSBS) &&
+ arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
+ kvm_call_hyp(__kvm_enable_ssbs);
+ }
}
static inline bool kvm_arch_check_sve_has_vhe(void)
#define kvm_phys_to_vttbr(addr) phys_to_ttbr(addr)
+static inline bool kvm_cpu_has_cnp(void)
+{
+ return system_supports_cnp();
+}
+
#endif /* __ASSEMBLY__ */
#endif /* __ARM64_KVM_MMU_H__ */
extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
extern void mark_linear_text_alias_ro(void);
+#define INIT_MM_CONTEXT(name) \
+ .pgd = init_pg_dir,
+
#endif /* !__ASSEMBLY__ */
#endif
extern ttbr_replace_func idmap_cpu_replace_ttbr1;
ttbr_replace_func *replace_phys;
- phys_addr_t pgd_phys = virt_to_phys(pgdp);
+ /* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
+ phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
+
+ if (system_supports_cnp() && !WARN_ON(pgdp != lm_alias(swapper_pg_dir))) {
+ /*
+ * cpu_replace_ttbr1() is used when there's a boot CPU
+ * up (i.e. cpufeature framework is not up yet) and
+ * latter only when we enable CNP via cpufeature's
+ * enable() callback.
+ * Also we rely on the cpu_hwcap bit being set before
+ * calling the enable() function.
+ */
+ ttbr1 |= TTBR_CNP_BIT;
+ }
replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
cpu_install_idmap();
- replace_phys(pgd_phys);
+ replace_phys(ttbr1);
cpu_uninstall_idmap();
}
typedef struct page *pgtable_t;
-#ifdef CONFIG_HAVE_ARCH_PFN_VALID
extern int pfn_valid(unsigned long);
-#endif
#include <asm/memory.h>
#define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS)
#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1)
+#define TTBR_CNP_BIT (UL(1) << 0)
+
/*
* TCR flags.
*/
#define pmd_present(pmd) pte_present(pmd_pte(pmd))
#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd))
#define pmd_young(pmd) pte_young(pmd_pte(pmd))
+#define pmd_valid(pmd) pte_valid(pmd_pte(pmd))
#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd)))
#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd)))
#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd)))
PUD_TYPE_TABLE)
#endif
+extern pgd_t init_pg_dir[PTRS_PER_PGD];
+extern pgd_t init_pg_end[];
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
+
+extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd);
+
+static inline bool in_swapper_pgdir(void *addr)
+{
+ return ((unsigned long)addr & PAGE_MASK) ==
+ ((unsigned long)swapper_pg_dir & PAGE_MASK);
+}
+
static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
{
+#ifdef __PAGETABLE_PMD_FOLDED
+ if (in_swapper_pgdir(pmdp)) {
+ set_swapper_pgd((pgd_t *)pmdp, __pgd(pmd_val(pmd)));
+ return;
+ }
+#endif /* __PAGETABLE_PMD_FOLDED */
+
WRITE_ONCE(*pmdp, pmd);
- dsb(ishst);
+
+ if (pmd_valid(pmd))
+ dsb(ishst);
}
static inline void pmd_clear(pmd_t *pmdp)
#define pud_none(pud) (!pud_val(pud))
#define pud_bad(pud) (!(pud_val(pud) & PUD_TABLE_BIT))
#define pud_present(pud) pte_present(pud_pte(pud))
+#define pud_valid(pud) pte_valid(pud_pte(pud))
static inline void set_pud(pud_t *pudp, pud_t pud)
{
+#ifdef __PAGETABLE_PUD_FOLDED
+ if (in_swapper_pgdir(pudp)) {
+ set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud)));
+ return;
+ }
+#endif /* __PAGETABLE_PUD_FOLDED */
+
WRITE_ONCE(*pudp, pud);
- dsb(ishst);
+
+ if (pud_valid(pud))
+ dsb(ishst);
}
static inline void pud_clear(pud_t *pudp)
static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
{
+ if (in_swapper_pgdir(pgdp)) {
+ set_swapper_pgd(pgdp, pgd);
+ return;
+ }
+
WRITE_ONCE(*pgdp, pgd);
dsb(ishst);
}
}
#endif
-extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-extern pgd_t swapper_pg_end[];
-extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
-extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
-
/*
* Encode and decode a swap entry:
* bits 0-1: present (must be zero)
{
start_thread_common(regs, pc);
regs->pstate = PSR_MODE_EL0t;
+
+ if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
+ regs->pstate |= PSR_SSBS_BIT;
+
regs->sp = sp;
}
regs->pstate |= PSR_AA32_E_BIT;
#endif
+ if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
+ regs->pstate |= PSR_AA32_SSBS_BIT;
+
regs->compat_sp = sp;
}
#endif
#endif
-void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused);
-void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused);
-void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused);
-
extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */
extern void __init minsigstksz_setup(void);
#define PSR_AA32_I_BIT 0x00000080
#define PSR_AA32_A_BIT 0x00000100
#define PSR_AA32_E_BIT 0x00000200
+#define PSR_AA32_SSBS_BIT 0x00800000
#define PSR_AA32_DIT_BIT 0x01000000
#define PSR_AA32_Q_BIT 0x08000000
#define PSR_AA32_V_BIT 0x10000000
#ifndef __ASM_SYSREG_H
#define __ASM_SYSREG_H
-#include <asm/compiler.h>
#include <linux/stringify.h>
/*
#endif /* CONFIG_BROKEN_GAS_INST */
-#define REG_PSTATE_PAN_IMM sys_reg(0, 0, 4, 0, 4)
-#define REG_PSTATE_UAO_IMM sys_reg(0, 0, 4, 0, 3)
+/*
+ * Instructions for modifying PSTATE fields.
+ * As per Arm ARM for v8-A, Section "C.5.1.3 op0 == 0b00, architectural hints,
+ * barriers and CLREX, and PSTATE access", ARM DDI 0487 C.a, system instructions
+ * for accessing PSTATE fields have the following encoding:
+ * Op0 = 0, CRn = 4
+ * Op1, Op2 encodes the PSTATE field modified and defines the constraints.
+ * CRm = Imm4 for the instruction.
+ * Rt = 0x1f
+ */
+#define pstate_field(op1, op2) ((op1) << Op1_shift | (op2) << Op2_shift)
+#define PSTATE_Imm_shift CRm_shift
+
+#define PSTATE_PAN pstate_field(0, 4)
+#define PSTATE_UAO pstate_field(0, 3)
+#define PSTATE_SSBS pstate_field(3, 1)
-#define SET_PSTATE_PAN(x) __emit_inst(0xd5000000 | REG_PSTATE_PAN_IMM | \
- (!!x)<<8 | 0x1f)
-#define SET_PSTATE_UAO(x) __emit_inst(0xd5000000 | REG_PSTATE_UAO_IMM | \
- (!!x)<<8 | 0x1f)
+#define SET_PSTATE_PAN(x) __emit_inst(0xd500401f | PSTATE_PAN | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_UAO(x) __emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_SSBS(x) __emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift))
#define SYS_DC_ISW sys_insn(1, 0, 7, 6, 2)
#define SYS_DC_CSW sys_insn(1, 0, 7, 10, 2)
#define SYS_ICH_LR15_EL2 __SYS__LR8_EL2(7)
/* Common SCTLR_ELx flags. */
+#define SCTLR_ELx_DSSBS (1UL << 44)
#define SCTLR_ELx_EE (1 << 25)
#define SCTLR_ELx_IESB (1 << 21)
#define SCTLR_ELx_WXN (1 << 19)
(1 << 10) | (1 << 13) | (1 << 14) | (1 << 15) | \
(1 << 17) | (1 << 20) | (1 << 24) | (1 << 26) | \
(1 << 27) | (1 << 30) | (1 << 31) | \
- (0xffffffffUL << 32))
+ (0xffffefffUL << 32))
#ifdef CONFIG_CPU_BIG_ENDIAN
#define ENDIAN_SET_EL2 SCTLR_ELx_EE
#define SCTLR_EL2_SET (SCTLR_ELx_IESB | ENDIAN_SET_EL2 | SCTLR_EL2_RES1)
#define SCTLR_EL2_CLEAR (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_WXN | \
- ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0)
+ SCTLR_ELx_DSSBS | ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0)
#if (SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != 0xffffffffffffffff
#error "Inconsistent SCTLR_EL2 set/clear bits"
(1 << 29))
#define SCTLR_EL1_RES0 ((1 << 6) | (1 << 10) | (1 << 13) | (1 << 17) | \
(1 << 27) | (1 << 30) | (1 << 31) | \
- (0xffffffffUL << 32))
+ (0xffffefffUL << 32))
#ifdef CONFIG_CPU_BIG_ENDIAN
#define ENDIAN_SET_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE)
#define SCTLR_EL1_SET (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA |\
SCTLR_EL1_SA0 | SCTLR_EL1_SED | SCTLR_ELx_I |\
- SCTLR_EL1_DZE | SCTLR_EL1_UCT | SCTLR_EL1_NTWI |\
+ SCTLR_EL1_DZE | SCTLR_EL1_UCT |\
SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN |\
ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_RES1)
#define SCTLR_EL1_CLEAR (SCTLR_ELx_A | SCTLR_EL1_CP15BEN | SCTLR_EL1_ITD |\
SCTLR_EL1_UMA | SCTLR_ELx_WXN | ENDIAN_CLEAR_EL1 |\
- SCTLR_EL1_RES0)
+ SCTLR_ELx_DSSBS | SCTLR_EL1_NTWI | SCTLR_EL1_RES0)
#if (SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != 0xffffffffffffffff
#error "Inconsistent SCTLR_EL1 set/clear bits"
#define ID_AA64PFR0_EL0_64BIT_ONLY 0x1
#define ID_AA64PFR0_EL0_32BIT_64BIT 0x2
+/* id_aa64pfr1 */
+#define ID_AA64PFR1_SSBS_SHIFT 4
+
+#define ID_AA64PFR1_SSBS_PSTATE_NI 0
+#define ID_AA64PFR1_SSBS_PSTATE_ONLY 1
+#define ID_AA64PFR1_SSBS_PSTATE_INSNS 2
+
/* id_aa64mmfr0 */
#define ID_AA64MMFR0_TGRAN4_SHIFT 28
#define ID_AA64MMFR0_TGRAN64_SHIFT 24
#include <linux/pagemap.h>
#include <linux/swap.h>
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-
-#define tlb_remove_entry(tlb, entry) tlb_remove_table(tlb, entry)
static inline void __tlb_remove_table(void *_table)
{
free_page_and_swap_cache((struct page *)_table);
}
-#else
-#define tlb_remove_entry(tlb, entry) tlb_remove_page(tlb, entry)
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
static void tlb_flush(struct mmu_gather *tlb);
static inline void tlb_flush(struct mmu_gather *tlb)
{
struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
+ bool last_level = !tlb->freed_tables;
+ unsigned long stride = tlb_get_unmap_size(tlb);
/*
- * The ASID allocator will either invalidate the ASID or mark
- * it as used.
+ * If we're tearing down the address space then we only care about
+ * invalidating the walk-cache, since the ASID allocator won't
+ * reallocate our ASID without invalidating the entire TLB.
*/
- if (tlb->fullmm)
+ if (tlb->fullmm) {
+ if (!last_level)
+ flush_tlb_mm(tlb->mm);
return;
+ }
- /*
- * The intermediate page table levels are already handled by
- * the __(pte|pmd|pud)_free_tlb() functions, so last level
- * TLBI is sufficient here.
- */
- __flush_tlb_range(&vma, tlb->start, tlb->end, true);
+ __flush_tlb_range(&vma, tlb->start, tlb->end, stride, last_level);
}
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
unsigned long addr)
{
- __flush_tlb_pgtable(tlb->mm, addr);
pgtable_page_dtor(pte);
- tlb_remove_entry(tlb, pte);
+ tlb_remove_table(tlb, pte);
}
#if CONFIG_PGTABLE_LEVELS > 2
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
unsigned long addr)
{
- __flush_tlb_pgtable(tlb->mm, addr);
- tlb_remove_entry(tlb, virt_to_page(pmdp));
+ tlb_remove_table(tlb, virt_to_page(pmdp));
}
#endif
static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
unsigned long addr)
{
- __flush_tlb_pgtable(tlb->mm, addr);
- tlb_remove_entry(tlb, virt_to_page(pudp));
+ tlb_remove_table(tlb, virt_to_page(pudp));
}
#endif
})
/*
- * TLB Management
- * ==============
+ * TLB Invalidation
+ * ================
*
- * The TLB specific code is expected to perform whatever tests it needs
- * to determine if it should invalidate the TLB for each call. Start
- * addresses are inclusive and end addresses are exclusive; it is safe to
- * round these addresses down.
+ * This header file implements the low-level TLB invalidation routines
+ * (sometimes referred to as "flushing" in the kernel) for arm64.
*
- * flush_tlb_all()
+ * Every invalidation operation uses the following template:
+ *
+ * DSB ISHST // Ensure prior page-table updates have completed
+ * TLBI ... // Invalidate the TLB
+ * DSB ISH // Ensure the TLB invalidation has completed
+ * if (invalidated kernel mappings)
+ * ISB // Discard any instructions fetched from the old mapping
+ *
+ *
+ * The following functions form part of the "core" TLB invalidation API,
+ * as documented in Documentation/core-api/cachetlb.rst:
*
- * Invalidate the entire TLB.
+ * flush_tlb_all()
+ * Invalidate the entire TLB (kernel + user) on all CPUs
*
* flush_tlb_mm(mm)
+ * Invalidate an entire user address space on all CPUs.
+ * The 'mm' argument identifies the ASID to invalidate.
+ *
+ * flush_tlb_range(vma, start, end)
+ * Invalidate the virtual-address range '[start, end)' on all
+ * CPUs for the user address space corresponding to 'vma->mm'.
+ * Note that this operation also invalidates any walk-cache
+ * entries associated with translations for the specified address
+ * range.
+ *
+ * flush_tlb_kernel_range(start, end)
+ * Same as flush_tlb_range(..., start, end), but applies to
+ * kernel mappings rather than a particular user address space.
+ * Whilst not explicitly documented, this function is used when
+ * unmapping pages from vmalloc/io space.
+ *
+ * flush_tlb_page(vma, addr)
+ * Invalidate a single user mapping for address 'addr' in the
+ * address space corresponding to 'vma->mm'. Note that this
+ * operation only invalidates a single, last-level page-table
+ * entry and therefore does not affect any walk-caches.
*
- * Invalidate all TLB entries in a particular address space.
- * - mm - mm_struct describing address space
*
- * flush_tlb_range(mm,start,end)
+ * Next, we have some undocumented invalidation routines that you probably
+ * don't want to call unless you know what you're doing:
*
- * Invalidate a range of TLB entries in the specified address
- * space.
- * - mm - mm_struct describing address space
- * - start - start address (may not be aligned)
- * - end - end address (exclusive, may not be aligned)
+ * local_flush_tlb_all()
+ * Same as flush_tlb_all(), but only applies to the calling CPU.
*
- * flush_tlb_page(vaddr,vma)
+ * __flush_tlb_kernel_pgtable(addr)
+ * Invalidate a single kernel mapping for address 'addr' on all
+ * CPUs, ensuring that any walk-cache entries associated with the
+ * translation are also invalidated.
*
- * Invalidate the specified page in the specified address range.
- * - vaddr - virtual address (may not be aligned)
- * - vma - vma_struct describing address range
+ * __flush_tlb_range(vma, start, end, stride, last_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.
*
- * flush_kern_tlb_page(kaddr)
*
- * Invalidate the TLB entry for the specified page. The address
- * will be in the kernels virtual memory space. Current uses
- * only require the D-TLB to be invalidated.
- * - kaddr - Kernel virtual memory address
+ * Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented
+ * on top of these routines, since that is our interface to the mmu_gather
+ * API as used by munmap() and friends.
*/
static inline void local_flush_tlb_all(void)
{
* This is meant to avoid soft lock-ups on large TLB flushing ranges and not
* necessarily a performance improvement.
*/
-#define MAX_TLB_RANGE (1024UL << PAGE_SHIFT)
+#define MAX_TLBI_OPS 1024UL
static inline void __flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
- bool last_level)
+ unsigned long stride, bool last_level)
{
unsigned long asid = ASID(vma->vm_mm);
unsigned long addr;
- if ((end - start) > MAX_TLB_RANGE) {
+ if ((end - start) > (MAX_TLBI_OPS * stride)) {
flush_tlb_mm(vma->vm_mm);
return;
}
+ /* Convert the stride into units of 4k */
+ stride >>= 12;
+
start = __TLBI_VADDR(start, asid);
end = __TLBI_VADDR(end, asid);
dsb(ishst);
- for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
+ for (addr = start; addr < end; addr += stride) {
if (last_level) {
__tlbi(vale1is, addr);
__tlbi_user(vale1is, addr);
static inline void flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- __flush_tlb_range(vma, start, end, false);
+ /*
+ * We cannot use leaf-only invalidation here, since we may be invalidating
+ * table entries as part of collapsing hugepages or moving page tables.
+ */
+ __flush_tlb_range(vma, start, end, PAGE_SIZE, false);
}
static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
unsigned long addr;
- if ((end - start) > MAX_TLB_RANGE) {
+ if ((end - start) > (MAX_TLBI_OPS * PAGE_SIZE)) {
flush_tlb_all();
return;
}
dsb(ishst);
for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
- __tlbi(vaae1is, addr);
+ __tlbi(vaale1is, addr);
dsb(ish);
isb();
}
* Used to invalidate the TLB (walk caches) corresponding to intermediate page
* table levels (pgd/pud/pmd).
*/
-static inline void __flush_tlb_pgtable(struct mm_struct *mm,
- unsigned long uaddr)
-{
- unsigned long addr = __TLBI_VADDR(uaddr, ASID(mm));
-
- __tlbi(vae1is, addr);
- __tlbi_user(vae1is, addr);
- dsb(ish);
-}
-
static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
{
unsigned long addr = __TLBI_VADDR(kaddr, 0);
+ dsb(ishst);
__tlbi(vaae1is, addr);
dsb(ish);
}
#include <asm/cpufeature.h>
#include <asm/ptrace.h>
#include <asm/memory.h>
-#include <asm/compiler.h>
#include <asm/extable.h>
#define get_ds() (KERNEL_DS)
static inline int xen_irqs_disabled(struct pt_regs *regs)
{
- return raw_irqs_disabled_flags((unsigned long) regs->pstate);
+ return !interrupts_enabled(regs);
}
#define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
#define HWCAP_USCAT (1 << 25)
#define HWCAP_ILRCPC (1 << 26)
#define HWCAP_FLAGM (1 << 27)
+#define HWCAP_SSBS (1 << 28)
#endif /* _UAPI__ASM_HWCAP_H */
#define PSR_I_BIT 0x00000080
#define PSR_A_BIT 0x00000100
#define PSR_D_BIT 0x00000200
+#define PSR_SSBS_BIT 0x00001000
#define PSR_PAN_BIT 0x00400000
#define PSR_UAO_BIT 0x00800000
#define PSR_V_BIT 0x10000000
has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
int scope)
{
- u64 mask = CTR_CACHE_MINLINE_MASK;
-
- /* Skip matching the min line sizes for cache type check */
- if (entry->capability == ARM64_MISMATCHED_CACHE_TYPE)
- mask ^= arm64_ftr_reg_ctrel0.strict_mask;
+ u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+ u64 sys = arm64_ftr_reg_ctrel0.sys_val & mask;
+ u64 ctr_raw, ctr_real;
WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
- return (read_cpuid_cachetype() & mask) !=
- (arm64_ftr_reg_ctrel0.sys_val & mask);
+
+ /*
+ * We want to make sure that all the CPUs in the system expose
+ * a consistent CTR_EL0 to make sure that applications behaves
+ * correctly with migration.
+ *
+ * If a CPU has CTR_EL0.IDC but does not advertise it via CTR_EL0 :
+ *
+ * 1) It is safe if the system doesn't support IDC, as CPU anyway
+ * reports IDC = 0, consistent with the rest.
+ *
+ * 2) If the system has IDC, it is still safe as we trap CTR_EL0
+ * access on this CPU via the ARM64_HAS_CACHE_IDC capability.
+ *
+ * So, we need to make sure either the raw CTR_EL0 or the effective
+ * CTR_EL0 matches the system's copy to allow a secondary CPU to boot.
+ */
+ ctr_raw = read_cpuid_cachetype() & mask;
+ ctr_real = read_cpuid_effective_cachetype() & mask;
+
+ return (ctr_real != sys) && (ctr_raw != sys);
}
static void
cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
{
- sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
+ u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+
+ /* Trap CTR_EL0 access on this CPU, only if it has a mismatch */
+ if ((read_cpuid_cachetype() & mask) !=
+ (arm64_ftr_reg_ctrel0.sys_val & mask))
+ sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
}
atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
static DEFINE_SPINLOCK(bp_lock);
int cpu, slot = -1;
+ /*
+ * enable_smccc_arch_workaround_1() passes NULL for the hyp_vecs
+ * start/end if we're a guest. Skip the hyp-vectors work.
+ */
+ if (!hyp_vecs_start) {
+ __this_cpu_write(bp_hardening_data.fn, fn);
+ return;
+ }
+
spin_lock(&bp_lock);
for_each_possible_cpu(cpu) {
if (per_cpu(bp_hardening_data.fn, cpu) == fn) {
void arm64_set_ssbd_mitigation(bool state)
{
+ if (this_cpu_has_cap(ARM64_SSBS)) {
+ if (state)
+ asm volatile(SET_PSTATE_SSBS(0));
+ else
+ asm volatile(SET_PSTATE_SSBS(1));
+ return;
+ }
+
switch (psci_ops.conduit) {
case PSCI_CONDUIT_HVC:
arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+ if (this_cpu_has_cap(ARM64_SSBS)) {
+ required = false;
+ goto out_printmsg;
+ }
+
if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
ssbd_state = ARM64_SSBD_UNKNOWN;
return false;
switch (ssbd_state) {
case ARM64_SSBD_FORCE_DISABLE:
- pr_info_once("%s disabled from command-line\n", entry->desc);
arm64_set_ssbd_mitigation(false);
required = false;
break;
break;
case ARM64_SSBD_FORCE_ENABLE:
- pr_info_once("%s forced from command-line\n", entry->desc);
arm64_set_ssbd_mitigation(true);
required = true;
break;
break;
}
+out_printmsg:
+ switch (ssbd_state) {
+ case ARM64_SSBD_FORCE_DISABLE:
+ pr_info_once("%s disabled from command-line\n", entry->desc);
+ break;
+
+ case ARM64_SSBD_FORCE_ENABLE:
+ pr_info_once("%s forced from command-line\n", entry->desc);
+ break;
+ }
+
return required;
}
#endif /* CONFIG_ARM64_SSBD */
+static void __maybe_unused
+cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
+{
+ sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0);
+}
+
#define CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max) \
.matches = is_affected_midr_range, \
.midr_range = MIDR_RANGE(model, v_min, r_min, v_max, r_max)
},
#endif
{
- .desc = "Mismatched cache line size",
- .capability = ARM64_MISMATCHED_CACHE_LINE_SIZE,
- .matches = has_mismatched_cache_type,
- .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
- .cpu_enable = cpu_enable_trap_ctr_access,
- },
- {
- .desc = "Mismatched cache type",
+ .desc = "Mismatched cache type (CTR_EL0)",
.capability = ARM64_MISMATCHED_CACHE_TYPE,
.matches = has_mismatched_cache_type,
.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
.matches = has_ssbd_mitigation,
},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1188873
+ {
+ /* Cortex-A76 r0p0 to r2p0 */
+ .desc = "ARM erratum 1188873",
+ .capability = ARM64_WORKAROUND_1188873,
+ ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+ },
#endif
{
}
#include <linux/bsearch.h>
#include <linux/cpumask.h>
+#include <linux/crash_dump.h>
#include <linux/sort.h>
#include <linux/stop_machine.h>
#include <linux/types.h>
static bool __maybe_unused
cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused);
+static void cpu_enable_cnp(struct arm64_cpu_capabilities const *cap);
/*
* NOTE: Any changes to the visibility of features should be kept in
ARM64_FTR_END,
};
+static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI),
+ ARM64_FTR_END,
+};
+
static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
/* Op1 = 0, CRn = 0, CRm = 4 */
ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
- ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_raz),
+ ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1),
ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz),
/* Op1 = 0, CRn = 0, CRm = 5 */
/*
* EL3 is not our concern.
- * ID_AA64PFR1 is currently RES0.
*/
taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu,
info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0);
}
static bool has_cache_idc(const struct arm64_cpu_capabilities *entry,
- int __unused)
+ int scope)
{
- return read_sanitised_ftr_reg(SYS_CTR_EL0) & BIT(CTR_IDC_SHIFT);
+ u64 ctr;
+
+ if (scope == SCOPE_SYSTEM)
+ ctr = arm64_ftr_reg_ctrel0.sys_val;
+ else
+ ctr = read_cpuid_effective_cachetype();
+
+ return ctr & BIT(CTR_IDC_SHIFT);
+}
+
+static void cpu_emulate_effective_ctr(const struct arm64_cpu_capabilities *__unused)
+{
+ /*
+ * If the CPU exposes raw CTR_EL0.IDC = 0, while effectively
+ * CTR_EL0.IDC = 1 (from CLIDR values), we need to trap accesses
+ * to the CTR_EL0 on this CPU and emulate it with the real/safe
+ * value.
+ */
+ if (!(read_cpuid_cachetype() & BIT(CTR_IDC_SHIFT)))
+ sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
}
static bool has_cache_dic(const struct arm64_cpu_capabilities *entry,
- int __unused)
+ int scope)
{
- return read_sanitised_ftr_reg(SYS_CTR_EL0) & BIT(CTR_DIC_SHIFT);
+ u64 ctr;
+
+ if (scope == SCOPE_SYSTEM)
+ ctr = arm64_ftr_reg_ctrel0.sys_val;
+ else
+ ctr = read_cpuid_cachetype();
+
+ return ctr & BIT(CTR_DIC_SHIFT);
+}
+
+static bool __maybe_unused
+has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope)
+{
+ /*
+ * Kdump isn't guaranteed to power-off all secondary CPUs, CNP
+ * may share TLB entries with a CPU stuck in the crashed
+ * kernel.
+ */
+ if (is_kdump_kernel())
+ return false;
+
+ return has_cpuid_feature(entry, scope);
}
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
WARN_ON(val & (7 << 27 | 7 << 21));
}
+#ifdef CONFIG_ARM64_SSBD
+static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr)
+{
+ if (user_mode(regs))
+ return 1;
+
+ if (instr & BIT(PSTATE_Imm_shift))
+ regs->pstate |= PSR_SSBS_BIT;
+ else
+ regs->pstate &= ~PSR_SSBS_BIT;
+
+ arm64_skip_faulting_instruction(regs, 4);
+ return 0;
+}
+
+static struct undef_hook ssbs_emulation_hook = {
+ .instr_mask = ~(1U << PSTATE_Imm_shift),
+ .instr_val = 0xd500401f | PSTATE_SSBS,
+ .fn = ssbs_emulation_handler,
+};
+
+static void cpu_enable_ssbs(const struct arm64_cpu_capabilities *__unused)
+{
+ static bool undef_hook_registered = false;
+ static DEFINE_SPINLOCK(hook_lock);
+
+ spin_lock(&hook_lock);
+ if (!undef_hook_registered) {
+ register_undef_hook(&ssbs_emulation_hook);
+ undef_hook_registered = true;
+ }
+ spin_unlock(&hook_lock);
+
+ if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
+ sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS);
+ arm64_set_ssbd_mitigation(false);
+ } else {
+ arm64_set_ssbd_mitigation(true);
+ }
+}
+#endif /* CONFIG_ARM64_SSBD */
+
+#ifdef CONFIG_ARM64_PAN
+static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
+{
+ /*
+ * We modify PSTATE. This won't work from irq context as the PSTATE
+ * is discarded once we return from the exception.
+ */
+ WARN_ON_ONCE(in_interrupt());
+
+ sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0);
+ asm(SET_PSTATE_PAN(1));
+}
+#endif /* CONFIG_ARM64_PAN */
+
+#ifdef CONFIG_ARM64_RAS_EXTN
+static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
+{
+ /* Firmware may have left a deferred SError in this register. */
+ write_sysreg_s(0, SYS_DISR_EL1);
+}
+#endif /* CONFIG_ARM64_RAS_EXTN */
+
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
.capability = ARM64_HAS_CACHE_IDC,
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.matches = has_cache_idc,
+ .cpu_enable = cpu_emulate_effective_ctr,
},
{
.desc = "Instruction cache invalidation not required for I/D coherence",
.matches = has_hw_dbm,
.cpu_enable = cpu_enable_hw_dbm,
},
+#endif
+#ifdef CONFIG_ARM64_SSBD
+ {
+ .desc = "CRC32 instructions",
+ .capability = ARM64_HAS_CRC32,
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64ISAR0_EL1,
+ .field_pos = ID_AA64ISAR0_CRC32_SHIFT,
+ .min_field_value = 1,
+ },
+ {
+ .desc = "Speculative Store Bypassing Safe (SSBS)",
+ .capability = ARM64_SSBS,
+ .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64PFR1_EL1,
+ .field_pos = ID_AA64PFR1_SSBS_SHIFT,
+ .sign = FTR_UNSIGNED,
+ .min_field_value = ID_AA64PFR1_SSBS_PSTATE_ONLY,
+ .cpu_enable = cpu_enable_ssbs,
+ },
+#endif
+#ifdef CONFIG_ARM64_CNP
+ {
+ .desc = "Common not Private translations",
+ .capability = ARM64_HAS_CNP,
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .matches = has_useable_cnp,
+ .sys_reg = SYS_ID_AA64MMFR2_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64MMFR2_CNP_SHIFT,
+ .min_field_value = 1,
+ .cpu_enable = cpu_enable_cnp,
+ },
#endif
{},
};
#ifdef CONFIG_ARM64_SVE
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE),
#endif
+ HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, HWCAP_SSBS),
{},
};
return (cpus_have_const_cap(ARM64_HAS_PAN) && !cpus_have_const_cap(ARM64_HAS_UAO));
}
+static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap)
+{
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+}
+
/*
* We emulate only the following system register space.
* Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 4 - 7]
return 0;
}
-static int emulate_mrs(struct pt_regs *regs, u32 insn)
+int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt)
{
int rc;
- u32 sys_reg, dst;
u64 val;
- /*
- * sys_reg values are defined as used in mrs/msr instruction.
- * shift the imm value to get the encoding.
- */
- sys_reg = (u32)aarch64_insn_decode_immediate(AARCH64_INSN_IMM_16, insn) << 5;
rc = emulate_sys_reg(sys_reg, &val);
if (!rc) {
- dst = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
- pt_regs_write_reg(regs, dst, val);
+ pt_regs_write_reg(regs, rt, val);
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
}
-
return rc;
}
+static int emulate_mrs(struct pt_regs *regs, u32 insn)
+{
+ u32 sys_reg, rt;
+
+ /*
+ * sys_reg values are defined as used in mrs/msr instruction.
+ * shift the imm value to get the encoding.
+ */
+ sys_reg = (u32)aarch64_insn_decode_immediate(AARCH64_INSN_IMM_16, insn) << 5;
+ rt = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
+ return do_emulate_mrs(regs, sys_reg, rt);
+}
+
static struct undef_hook mrs_hook = {
.instr_mask = 0xfff00000,
.instr_val = 0xd5300000,
}
core_initcall(enable_mrs_emulation);
-
-void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
-{
- /* Firmware may have left a deferred SError in this register. */
- write_sysreg_s(0, SYS_DISR_EL1);
-}
"uscat",
"ilrcpc",
"flagm",
+ "ssbs",
NULL
};
static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
{
info->reg_cntfrq = arch_timer_get_cntfrq();
- info->reg_ctr = read_cpuid_cachetype();
+ /*
+ * Use the effective value of the CTR_EL0 than the raw value
+ * exposed by the CPU. CTR_E0.IDC field value must be interpreted
+ * with the CLIDR_EL1 fields to avoid triggering false warnings
+ * when there is a mismatch across the CPUs. Keep track of the
+ * effective value of the CTR_EL0 in our internal records for
+ * acurate sanity check and feature enablement.
+ */
+ info->reg_ctr = read_cpuid_effective_cachetype();
info->reg_dczid = read_cpuid(DCZID_EL0);
info->reg_midr = read_cpuid_id();
info->reg_revidr = read_cpuid(REVIDR_EL1);
inherit_daif pstate=x23, tmp=x2
mov x0, sp
bl do_undefinstr
- ASM_BUG()
+ kernel_exit 1
el1_dbg:
/*
* Debug exception handling
cmp x24, #ESR_ELx_EC_FP_EXC64 // FP/ASIMD exception
b.eq el0_fpsimd_exc
cmp x24, #ESR_ELx_EC_SYS64 // configurable trap
+ ccmp x24, #ESR_ELx_EC_WFx, #4, ne
b.eq el0_sys
cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception
b.eq el0_sp_pc
cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0
b.eq el0_undef
cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap
- b.eq el0_undef
+ b.eq el0_cp15
cmp x24, #ESR_ELx_EC_CP15_64 // CP15 MRRC/MCRR trap
- b.eq el0_undef
+ b.eq el0_cp15
cmp x24, #ESR_ELx_EC_CP14_MR // CP14 MRC/MCR trap
b.eq el0_undef
cmp x24, #ESR_ELx_EC_CP14_LS // CP14 LDC/STC trap
el0_error_compat:
kernel_entry 0, 32
b el0_error_naked
+
+el0_cp15:
+ /*
+ * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions
+ */
+ enable_daif
+ ct_user_exit
+ mov x0, x25
+ mov x1, sp
+ bl do_cp15instr
+ b ret_to_user
#endif
el0_da:
mov x28, lr
/*
- * Invalidate the idmap and swapper page tables to avoid potential
- * dirty cache lines being evicted.
+ * Invalidate the init page tables to avoid potential dirty cache lines
+ * being evicted. Other page tables are allocated in rodata as part of
+ * the kernel image, and thus are clean to the PoC per the boot
+ * protocol.
*/
- adrp x0, idmap_pg_dir
- adrp x1, swapper_pg_end
+ adrp x0, init_pg_dir
+ adrp x1, init_pg_end
sub x1, x1, x0
bl __inval_dcache_area
/*
- * Clear the idmap and swapper page tables.
+ * Clear the init page tables.
*/
- adrp x0, idmap_pg_dir
- adrp x1, swapper_pg_end
+ adrp x0, init_pg_dir
+ adrp x1, init_pg_end
sub x1, x1, x0
1: stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
/*
* Map the kernel image (starting with PHYS_OFFSET).
*/
- adrp x0, swapper_pg_dir
+ adrp x0, init_pg_dir
mov_q x5, KIMAGE_VADDR + TEXT_OFFSET // compile time __va(_text)
add x5, x5, x23 // add KASLR displacement
mov x4, PTRS_PER_PGD
* tables again to remove any speculatively loaded cache lines.
*/
adrp x0, idmap_pg_dir
- adrp x1, swapper_pg_end
+ adrp x1, init_pg_end
sub x1, x1, x0
dmb sy
bl __inval_dcache_area
* Common entry point for secondary CPUs.
*/
bl __cpu_setup // initialise processor
+ adrp x1, swapper_pg_dir
bl __enable_mmu
ldr x8, =__secondary_switched
br x8
* Enable the MMU.
*
* x0 = SCTLR_EL1 value for turning on the MMU.
+ * x1 = TTBR1_EL1 value
*
* Returns to the caller via x30/lr. This requires the caller to be covered
* by the .idmap.text section.
* If it isn't, park the CPU
*/
ENTRY(__enable_mmu)
- mrs x1, ID_AA64MMFR0_EL1
- ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
+ mrs x2, ID_AA64MMFR0_EL1
+ ubfx x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4
cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
b.ne __no_granule_support
- update_early_cpu_boot_status 0, x1, x2
- adrp x1, idmap_pg_dir
- adrp x2, swapper_pg_dir
- phys_to_ttbr x3, x1
- phys_to_ttbr x4, x2
- msr ttbr0_el1, x3 // load TTBR0
- msr ttbr1_el1, x4 // load TTBR1
+ update_early_cpu_boot_status 0, x2, x3
+ adrp x2, idmap_pg_dir
+ phys_to_ttbr x1, x1
+ phys_to_ttbr x2, x2
+ msr ttbr0_el1, x2 // load TTBR0
+ msr ttbr1_el1, x1 // load TTBR1
isb
msr sctlr_el1, x0
isb
mrs x20, sctlr_el1 // preserve old SCTLR_EL1 value
#endif
+ adrp x1, init_pg_dir
bl __enable_mmu
#ifdef CONFIG_RELOCATABLE
bl __relocate_kernel
if (!p->ainsn.api.insn)
return -ENOMEM;
break;
- };
+ }
/* prepare the instruction */
if (p->ainsn.api.insn)
if (IS_ENABLED(CONFIG_ARM64_UAO) &&
cpus_have_const_cap(ARM64_HAS_UAO))
childregs->pstate |= PSR_UAO_BIT;
+
+ if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
+ childregs->pstate |= PSR_SSBS_BIT;
+
p->thread.cpu_context.x19 = stack_start;
p->thread.cpu_context.x20 = stk_sz;
}
#include <uapi/linux/psci.h>
-#include <asm/compiler.h>
#include <asm/cpu_ops.h>
#include <asm/errno.h>
#include <asm/smp_plat.h>
#endif
#ifdef CONFIG_VT
-#if defined(CONFIG_VGA_CONSOLE)
- conswitchp = &vga_con;
-#elif defined(CONFIG_DUMMY_CONSOLE)
conswitchp = &dummy_con;
-#endif
#endif
if (boot_args[1] || boot_args[2] || boot_args[3]) {
pr_err("WARNING: x1-x3 nonzero in violation of boot protocol:\n"
bl el2_setup // if in EL2 drop to EL1 cleanly
bl __cpu_setup
/* enable the MMU early - so we can access sleep_save_stash by va */
+ adrp x1, swapper_pg_dir
bl __enable_mmu
ldr x8, =_cpu_resume
br x8
* Copyright (C) 2018 ARM Ltd, All Rights Reserved.
*/
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
#include <linux/thread_info.h>
#include <asm/cpufeature.h>
+static void ssbd_ssbs_enable(struct task_struct *task)
+{
+ u64 val = is_compat_thread(task_thread_info(task)) ?
+ PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
+
+ task_pt_regs(task)->pstate |= val;
+}
+
+static void ssbd_ssbs_disable(struct task_struct *task)
+{
+ u64 val = is_compat_thread(task_thread_info(task)) ?
+ PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
+
+ task_pt_regs(task)->pstate &= ~val;
+}
+
/*
* prctl interface for SSBD
- * FIXME: Drop the below ifdefery once merged in 4.18.
*/
-#ifdef PR_SPEC_STORE_BYPASS
static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
{
int state = arm64_get_ssbd_state();
return -EPERM;
task_clear_spec_ssb_disable(task);
clear_tsk_thread_flag(task, TIF_SSBD);
+ ssbd_ssbs_enable(task);
break;
case PR_SPEC_DISABLE:
if (state == ARM64_SSBD_FORCE_DISABLE)
return -EPERM;
task_set_spec_ssb_disable(task);
set_tsk_thread_flag(task, TIF_SSBD);
+ ssbd_ssbs_disable(task);
break;
case PR_SPEC_FORCE_DISABLE:
if (state == ARM64_SSBD_FORCE_DISABLE)
task_set_spec_ssb_disable(task);
task_set_spec_ssb_force_disable(task);
set_tsk_thread_flag(task, TIF_SSBD);
+ ssbd_ssbs_disable(task);
break;
default:
return -ERANGE;
return -ENODEV;
}
}
-#endif /* PR_SPEC_STORE_BYPASS */
*/
cpu_uninstall_idmap();
+ /* Restore CnP bit in TTBR1_EL1 */
+ if (system_supports_cnp())
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+
/*
* PSTATE was not saved over suspend/resume, re-enable any detected
* features that might not have been set correctly.
int (*fn)(struct pt_regs *regs, u32 instr) = NULL;
void __user *pc = (void __user *)instruction_pointer(regs);
- if (!user_mode(regs))
- return 1;
-
- if (compat_thumb_mode(regs)) {
+ if (!user_mode(regs)) {
+ __le32 instr_le;
+ if (probe_kernel_address((__force __le32 *)pc, instr_le))
+ goto exit;
+ instr = le32_to_cpu(instr_le);
+ } else if (compat_thumb_mode(regs)) {
/* 16-bit Thumb instruction */
__le16 instr_le;
if (get_user(instr_le, (__le16 __user *)pc))
const char *desc;
struct pt_regs *regs = current_pt_regs();
+ if (WARN_ON(!user_mode(regs)))
+ return;
+
clear_siginfo(&info);
switch (signal) {
if (call_undef_hook(regs) == 0)
return;
+ BUG_ON(!user_mode(regs));
force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
}
-void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
-{
- sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0);
-}
-
#define __user_cache_maint(insn, address, res) \
if (address >= user_addr_max()) { \
res = -EFAULT; \
static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
{
unsigned long address;
- int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ int rt = ESR_ELx_SYS64_ISS_RT(esr);
int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
int ret = 0;
static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
{
- int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ int rt = ESR_ELx_SYS64_ISS_RT(esr);
unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
pt_regs_write_reg(regs, rt, val);
static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
{
- int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ int rt = ESR_ELx_SYS64_ISS_RT(esr);
pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
{
- int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ int rt = ESR_ELx_SYS64_ISS_RT(esr);
pt_regs_write_reg(regs, rt, arch_timer_get_rate());
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
}
+static void mrs_handler(unsigned int esr, struct pt_regs *regs)
+{
+ u32 sysreg, rt;
+
+ rt = ESR_ELx_SYS64_ISS_RT(esr);
+ sysreg = esr_sys64_to_sysreg(esr);
+
+ if (do_emulate_mrs(regs, sysreg, rt) != 0)
+ force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+}
+
+static void wfi_handler(unsigned int esr, struct pt_regs *regs)
+{
+ arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
+}
+
struct sys64_hook {
unsigned int esr_mask;
unsigned int esr_val;
.esr_val = ESR_ELx_SYS64_ISS_SYS_CNTFRQ,
.handler = cntfrq_read_handler,
},
+ {
+ /* Trap read access to CPUID registers */
+ .esr_mask = ESR_ELx_SYS64_ISS_SYS_MRS_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_SYS_MRS_OP_VAL,
+ .handler = mrs_handler,
+ },
+ {
+ /* Trap WFI instructions executed in userspace */
+ .esr_mask = ESR_ELx_WFx_MASK,
+ .esr_val = ESR_ELx_WFx_WFI_VAL,
+ .handler = wfi_handler,
+ },
{},
};
+
+#ifdef CONFIG_COMPAT
+#define PSTATE_IT_1_0_SHIFT 25
+#define PSTATE_IT_1_0_MASK (0x3 << PSTATE_IT_1_0_SHIFT)
+#define PSTATE_IT_7_2_SHIFT 10
+#define PSTATE_IT_7_2_MASK (0x3f << PSTATE_IT_7_2_SHIFT)
+
+static u32 compat_get_it_state(struct pt_regs *regs)
+{
+ u32 it, pstate = regs->pstate;
+
+ it = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT;
+ it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2;
+
+ return it;
+}
+
+static void compat_set_it_state(struct pt_regs *regs, u32 it)
+{
+ u32 pstate_it;
+
+ pstate_it = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK;
+ pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK;
+
+ regs->pstate &= ~PSR_AA32_IT_MASK;
+ regs->pstate |= pstate_it;
+}
+
+static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
+{
+ int cond;
+
+ /* Only a T32 instruction can trap without CV being set */
+ if (!(esr & ESR_ELx_CV)) {
+ u32 it;
+
+ it = compat_get_it_state(regs);
+ if (!it)
+ return true;
+
+ cond = it >> 4;
+ } else {
+ cond = (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT;
+ }
+
+ return aarch32_opcode_cond_checks[cond](regs->pstate);
+}
+
+static void advance_itstate(struct pt_regs *regs)
+{
+ u32 it;
+
+ /* ARM mode */
+ if (!(regs->pstate & PSR_AA32_T_BIT) ||
+ !(regs->pstate & PSR_AA32_IT_MASK))
+ return;
+
+ it = compat_get_it_state(regs);
+
+ /*
+ * If this is the last instruction of the block, wipe the IT
+ * state. Otherwise advance it.
+ */
+ if (!(it & 7))
+ it = 0;
+ else
+ it = (it & 0xe0) | ((it << 1) & 0x1f);
+
+ compat_set_it_state(regs, it);
+}
+
+static void arm64_compat_skip_faulting_instruction(struct pt_regs *regs,
+ unsigned int sz)
+{
+ advance_itstate(regs);
+ arm64_skip_faulting_instruction(regs, sz);
+}
+
+static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT;
+
+ pt_regs_write_reg(regs, reg, arch_timer_get_rate());
+ arm64_compat_skip_faulting_instruction(regs, 4);
+}
+
+static struct sys64_hook cp15_32_hooks[] = {
+ {
+ .esr_mask = ESR_ELx_CP15_32_ISS_SYS_MASK,
+ .esr_val = ESR_ELx_CP15_32_ISS_SYS_CNTFRQ,
+ .handler = compat_cntfrq_read_handler,
+ },
+ {},
+};
+
+static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int rt = (esr & ESR_ELx_CP15_64_ISS_RT_MASK) >> ESR_ELx_CP15_64_ISS_RT_SHIFT;
+ int rt2 = (esr & ESR_ELx_CP15_64_ISS_RT2_MASK) >> ESR_ELx_CP15_64_ISS_RT2_SHIFT;
+ u64 val = arch_counter_get_cntvct();
+
+ pt_regs_write_reg(regs, rt, lower_32_bits(val));
+ pt_regs_write_reg(regs, rt2, upper_32_bits(val));
+ arm64_compat_skip_faulting_instruction(regs, 4);
+}
+
+static struct sys64_hook cp15_64_hooks[] = {
+ {
+ .esr_mask = ESR_ELx_CP15_64_ISS_SYS_MASK,
+ .esr_val = ESR_ELx_CP15_64_ISS_SYS_CNTVCT,
+ .handler = compat_cntvct_read_handler,
+ },
+ {},
+};
+
+asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
+{
+ struct sys64_hook *hook, *hook_base;
+
+ if (!cp15_cond_valid(esr, regs)) {
+ /*
+ * There is no T16 variant of a CP access, so we
+ * always advance PC by 4 bytes.
+ */
+ arm64_compat_skip_faulting_instruction(regs, 4);
+ return;
+ }
+
+ switch (ESR_ELx_EC(esr)) {
+ case ESR_ELx_EC_CP15_32:
+ hook_base = cp15_32_hooks;
+ break;
+ case ESR_ELx_EC_CP15_64:
+ hook_base = cp15_64_hooks;
+ break;
+ default:
+ do_undefinstr(regs);
+ return;
+ }
+
+ for (hook = hook_base; hook->handler; hook++)
+ if ((hook->esr_mask & esr) == hook->esr_val) {
+ hook->handler(esr, regs);
+ return;
+ }
+
+ /*
+ * New cp15 instructions may previously have been undefined at
+ * EL0. Fall back to our usual undefined instruction handler
+ * so that we handle these consistently.
+ */
+ do_undefinstr(regs);
+}
+#endif
+
asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
{
struct sys64_hook *hook;
handler[reason], smp_processor_id(), esr,
esr_get_class_string(esr));
- die("Oops - bad mode", regs, 0);
local_daif_mask();
panic("bad mode");
}
EXCEPTION_TABLE(8) /* __init_begin will be marked RO NX */
NOTES
+ . = ALIGN(PAGE_SIZE);
+ idmap_pg_dir = .;
+ . += IDMAP_DIR_SIZE;
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ tramp_pg_dir = .;
+ . += PAGE_SIZE;
+#endif
+
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ reserved_ttbr0 = .;
+ . += RESERVED_TTBR0_SIZE;
+#endif
+ swapper_pg_dir = .;
+ . += PAGE_SIZE;
+ swapper_pg_end = .;
+
. = ALIGN(SEGMENT_ALIGN);
__init_begin = .;
__inittext_begin = .;
BSS_SECTION(0, 0, 0)
. = ALIGN(PAGE_SIZE);
- idmap_pg_dir = .;
- . += IDMAP_DIR_SIZE;
-
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
- tramp_pg_dir = .;
- . += PAGE_SIZE;
-#endif
-
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
- reserved_ttbr0 = .;
- . += RESERVED_TTBR0_SIZE;
-#endif
- swapper_pg_dir = .;
- . += SWAPPER_DIR_SIZE;
- swapper_pg_end = .;
+ init_pg_dir = .;
+ . += INIT_DIR_SIZE;
+ init_pg_end = .;
__pecoff_data_size = ABSOLUTE(. - __initdata_begin);
_end = .;
b.lo __kvm_handle_stub_hvc
phys_to_ttbr x4, x0
+alternative_if ARM64_HAS_CNP
+ orr x4, x4, #TTBR_CNP_BIT
+alternative_else_nop_endif
msr ttbr0_el2, x4
mrs x4, tcr_el1
vcpu->arch.sysregs_loaded_on_cpu = false;
}
+
+void __hyp_text __kvm_enable_ssbs(void)
+{
+ u64 tmp;
+
+ asm volatile(
+ "mrs %0, sctlr_el2\n"
+ "orr %0, %0, %1\n"
+ "msr sctlr_el2, %0"
+ : "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
+}
# when supported by the CPU. Result and argument registers are handled
# correctly, based on the function prototype.
lib-$(CONFIG_ARM64_LSE_ATOMICS) += atomic_ll_sc.o
-CFLAGS_atomic_ll_sc.o := -fcall-used-x0 -ffixed-x1 -ffixed-x2 \
+CFLAGS_atomic_ll_sc.o := -ffixed-x1 -ffixed-x2 \
-ffixed-x3 -ffixed-x4 -ffixed-x5 -ffixed-x6 \
-ffixed-x7 -fcall-saved-x8 -fcall-saved-x9 \
-fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12 \
UBSAN_SANITIZE_atomic_ll_sc.o := n
lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
+
+obj-$(CONFIG_CRC32) += crc32.o
--- /dev/null
+/*
+ * Accelerated CRC32(C) using AArch64 CRC instructions
+ *
+ * Copyright (C) 2016 - 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/alternative.h>
+#include <asm/assembler.h>
+
+ .cpu generic+crc
+
+ .macro __crc32, c
+0: subs x2, x2, #16
+ b.mi 8f
+ ldp x3, x4, [x1], #16
+CPU_BE( rev x3, x3 )
+CPU_BE( rev x4, x4 )
+ crc32\c\()x w0, w0, x3
+ crc32\c\()x w0, w0, x4
+ b.ne 0b
+ ret
+
+8: tbz x2, #3, 4f
+ ldr x3, [x1], #8
+CPU_BE( rev x3, x3 )
+ crc32\c\()x w0, w0, x3
+4: tbz x2, #2, 2f
+ ldr w3, [x1], #4
+CPU_BE( rev w3, w3 )
+ crc32\c\()w w0, w0, w3
+2: tbz x2, #1, 1f
+ ldrh w3, [x1], #2
+CPU_BE( rev16 w3, w3 )
+ crc32\c\()h w0, w0, w3
+1: tbz x2, #0, 0f
+ ldrb w3, [x1]
+ crc32\c\()b w0, w0, w3
+0: ret
+ .endm
+
+ .align 5
+ENTRY(crc32_le)
+alternative_if_not ARM64_HAS_CRC32
+ b crc32_le_base
+alternative_else_nop_endif
+ __crc32
+ENDPROC(crc32_le)
+
+ .align 5
+ENTRY(__crc32c_le)
+alternative_if_not ARM64_HAS_CRC32
+ b __crc32c_le_base
+alternative_else_nop_endif
+ __crc32 c
+ENDPROC(__crc32c_le)
}
}
-static void flush_context(unsigned int cpu)
+static void flush_context(void)
{
int i;
u64 asid;
return hit;
}
-static u64 new_context(struct mm_struct *mm, unsigned int cpu)
+static u64 new_context(struct mm_struct *mm)
{
static u32 cur_idx = 1;
u64 asid = atomic64_read(&mm->context.id);
/* We're out of ASIDs, so increment the global generation count */
generation = atomic64_add_return_relaxed(ASID_FIRST_VERSION,
&asid_generation);
- flush_context(cpu);
+ flush_context();
/* We have more ASIDs than CPUs, so this will always succeed */
asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
unsigned long flags;
u64 asid, old_active_asid;
+ if (system_supports_cnp())
+ cpu_set_reserved_ttbr0();
+
asid = atomic64_read(&mm->context.id);
/*
/* Check that our ASID belongs to the current generation. */
asid = atomic64_read(&mm->context.id);
if ((asid ^ atomic64_read(&asid_generation)) >> asid_bits) {
- asid = new_context(mm, cpu);
+ asid = new_context(mm);
atomic64_set(&mm->context.id, asid);
}
#endif
{ MODULES_VADDR, "Modules start" },
{ MODULES_END, "Modules end" },
- { VMALLOC_START, "vmalloc() Area" },
- { VMALLOC_END, "vmalloc() End" },
+ { VMALLOC_START, "vmalloc() area" },
+ { VMALLOC_END, "vmalloc() end" },
{ FIXADDR_START, "Fixmap start" },
{ FIXADDR_TOP, "Fixmap end" },
{ PCI_IO_START, "PCI I/O start" },
{ VMEMMAP_START, "vmemmap start" },
{ VMEMMAP_START + VMEMMAP_SIZE, "vmemmap end" },
#endif
- { PAGE_OFFSET, "Linear Mapping" },
+ { PAGE_OFFSET, "Linear mapping" },
{ -1, NULL },
};
#include <asm/cmpxchg.h>
#include <asm/cpufeature.h>
#include <asm/exception.h>
+#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
#include <asm/sysreg.h>
};
static const struct fault_info fault_info[];
+static struct fault_info debug_fault_info[];
static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
{
- return fault_info + (esr & 63);
+ return fault_info + (esr & ESR_ELx_FSC);
+}
+
+static inline const struct fault_info *esr_to_debug_fault_info(unsigned int esr)
+{
+ return debug_fault_info + DBG_ESR_EVT(esr);
}
#ifdef CONFIG_KPROBES
return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
}
-static inline bool is_el1_permission_fault(unsigned int esr,
- struct pt_regs *regs,
- unsigned long addr)
+static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs)
{
unsigned int ec = ESR_ELx_EC(esr);
unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
return;
- if (is_el1_permission_fault(esr, regs, addr)) {
+ if (is_el1_permission_fault(addr, esr, regs)) {
if (esr & ESR_ELx_WNR)
msg = "write to read-only memory";
else
mm_flags |= FAULT_FLAG_WRITE;
}
- if (addr < TASK_SIZE && is_el1_permission_fault(esr, regs, addr)) {
+ if (addr < TASK_SIZE && is_el1_permission_fault(addr, esr, regs)) {
/* regs->orig_addr_limit may be 0 if we entered from EL0 */
if (regs->orig_addr_limit == KERNEL_DS)
die_kernel_fault("access to user memory with fs=KERNEL_DS",
if (addr > TASK_SIZE)
arm64_apply_bp_hardening();
- local_irq_enable();
+ local_daif_restore(DAIF_PROCCTX);
do_mem_abort(addr, esr, regs);
}
if (user_mode(regs)) {
if (instruction_pointer(regs) > TASK_SIZE)
arm64_apply_bp_hardening();
- local_irq_enable();
+ local_daif_restore(DAIF_PROCCTX);
}
clear_siginfo(&info);
unsigned int esr,
struct pt_regs *regs)
{
- const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
+ const struct fault_info *inf = esr_to_debug_fault_info(esr);
int rv;
/*
return rv;
}
NOKPROBE_SYMBOL(do_debug_exception);
-
-#ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
-{
- /*
- * We modify PSTATE. This won't work from irq context as the PSTATE
- * is discarded once we return from the exception.
- */
- WARN_ON_ONCE(in_interrupt());
-
- sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0);
- asm(SET_PSTATE_PAN(1));
-}
-#endif /* CONFIG_ARM64_PAN */
#endif /* CONFIG_NUMA */
-#ifdef CONFIG_HAVE_ARCH_PFN_VALID
int pfn_valid(unsigned long pfn)
{
phys_addr_t addr = pfn << PAGE_SHIFT;
return memblock_is_map_memory(addr);
}
EXPORT_SYMBOL(pfn_valid);
-#endif
#ifndef CONFIG_SPARSEMEM
static void __init arm64_memory_present(void)
/*
* We are going to perform proper setup of shadow memory.
- * At first we should unmap early shadow (clear_pgds() call bellow).
+ * At first we should unmap early shadow (clear_pgds() call below).
* However, instrumented code couldn't execute without shadow memory.
* tmp_pg_dir used to keep early shadow mapped until full shadow
* setup will be finished.
static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
+static DEFINE_SPINLOCK(swapper_pgdir_lock);
+
+void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ pgd_t *fixmap_pgdp;
+
+ spin_lock(&swapper_pgdir_lock);
+ fixmap_pgdp = pgd_set_fixmap(__pa_symbol(pgdp));
+ WRITE_ONCE(*fixmap_pgdp, pgd);
+ /*
+ * We need dsb(ishst) here to ensure the page-table-walker sees
+ * our new entry before set_p?d() returns. The fixmap's
+ * flush_tlb_kernel_range() via clear_fixmap() does this for us.
+ */
+ pgd_clear_fixmap();
+ spin_unlock(&swapper_pgdir_lock);
+}
+
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
{
*/
void __init paging_init(void)
{
- phys_addr_t pgd_phys = early_pgtable_alloc();
- pgd_t *pgdp = pgd_set_fixmap(pgd_phys);
+ pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir));
map_kernel(pgdp);
map_mem(pgdp);
- /*
- * We want to reuse the original swapper_pg_dir so we don't have to
- * communicate the new address to non-coherent secondaries in
- * secondary_entry, and so cpu_switch_mm can generate the address with
- * adrp+add rather than a load from some global variable.
- *
- * To do this we need to go via a temporary pgd.
- */
- cpu_replace_ttbr1(__va(pgd_phys));
- memcpy(swapper_pg_dir, pgdp, PGD_SIZE);
- cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
-
pgd_clear_fixmap();
- memblock_free(pgd_phys, PAGE_SIZE);
- /*
- * We only reuse the PGD from the swapper_pg_dir, not the pud + pmd
- * allocated with it.
- */
- memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
- __pa_symbol(swapper_pg_end) - __pa_symbol(swapper_pg_dir)
- - PAGE_SIZE);
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+ init_mm.pgd = swapper_pg_dir;
+
+ memblock_free(__pa_symbol(init_pg_dir),
+ __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir));
}
/*
nodes_clear(numa_nodes_parsed);
nodes_clear(node_possible_map);
nodes_clear(node_online_map);
- numa_free_distance();
ret = numa_alloc_distance();
if (ret < 0)
ret = init_func();
if (ret < 0)
- return ret;
+ goto out_free_distance;
if (nodes_empty(numa_nodes_parsed)) {
pr_info("No NUMA configuration found\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_free_distance;
}
ret = numa_register_nodes();
if (ret < 0)
- return ret;
+ goto out_free_distance;
setup_node_to_cpumask_map();
return 0;
+out_free_distance:
+ numa_free_distance();
+ return ret;
}
/**
if (numa_off)
pr_info("NUMA disabled\n"); /* Forced off on command line. */
pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n",
- 0LLU, PFN_PHYS(max_pfn) - 1);
+ memblock_start_of_DRAM(), memblock_end_of_DRAM() - 1);
for_each_memblock(memory, mblk) {
ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
mrs x2, ttbr1_el1
mmid x1, x1 // get mm->context.id
phys_to_ttbr x3, x0
+
+alternative_if ARM64_HAS_CNP
+ cbz x1, 1f // skip CNP for reserved ASID
+ orr x3, x3, #TTBR_CNP_BIT
+1:
+alternative_else_nop_endif
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
bfi x3, x1, #48, #16 // set the ASID field in TTBR0
#endif
.endm
/*
- * void idmap_cpu_replace_ttbr1(phys_addr_t new_pgd)
+ * void idmap_cpu_replace_ttbr1(phys_addr_t ttbr1)
*
* This is the low-level counterpart to cpu_replace_ttbr1, and should not be
* called by anything else. It can only be executed from a TTBR0 mapping.
__idmap_cpu_set_reserved_ttbr1 x1, x3
- phys_to_ttbr x3, x0
- msr ttbr1_el1, x3
+ msr ttbr1_el1, x0
isb
restore_daif x2
}
#endif
+#ifdef CONFIG_ARM64_ERRATUM_1188873
+static u64 notrace arm64_1188873_read_cntvct_el0(void)
+{
+ return read_sysreg(cntvct_el0);
+}
+#endif
+
#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
DEFINE_PER_CPU(const struct arch_timer_erratum_workaround *, timer_unstable_counter_workaround);
EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
.read_cntvct_el0 = arm64_858921_read_cntvct_el0,
},
#endif
+#ifdef CONFIG_ARM64_ERRATUM_1188873
+ {
+ .match_type = ate_match_local_cap_id,
+ .id = (void *)ARM64_WORKAROUND_1188873,
+ .desc = "ARM erratum 1188873",
+ .read_cntvct_el0 = arm64_1188873_read_cntvct_el0,
+ },
+#endif
};
typedef bool (*ate_match_fn_t)(const struct arch_timer_erratum_workaround *,
dn = of_parse_phandle(node, "interrupt-affinity", i);
if (!dn) {
- pr_warn("failed to parse interrupt-affinity[%d] for %s\n",
- i, node->name);
+ pr_warn("failed to parse interrupt-affinity[%d] for %pOFn\n",
+ i, node);
return -EINVAL;
}
cpu = of_cpu_node_to_id(dn);
if (cpu < 0) {
- pr_warn("failed to find logical CPU for %s\n", dn->name);
+ pr_warn("failed to find logical CPU for %pOFn\n", dn);
cpu = nr_cpu_ids;
}
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
+#ifdef CONFIG_MMU
+
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
/*
* Semi RCU freeing of the page directories.
#endif
unsigned long start;
unsigned long end;
- /* we are in the middle of an operation to clear
- * a full mm and can make some optimizations */
- unsigned int fullmm : 1,
- /* we have performed an operation which
- * requires a complete flush of the tlb */
- need_flush_all : 1;
+ /*
+ * we are in the middle of an operation to clear
+ * a full mm and can make some optimizations
+ */
+ unsigned int fullmm : 1;
+
+ /*
+ * we have performed an operation which
+ * requires a complete flush of the tlb
+ */
+ unsigned int need_flush_all : 1;
+
+ /*
+ * we have removed page directories
+ */
+ unsigned int freed_tables : 1;
+
+ /*
+ * at which levels have we cleared entries?
+ */
+ unsigned int cleared_ptes : 1;
+ unsigned int cleared_pmds : 1;
+ unsigned int cleared_puds : 1;
+ unsigned int cleared_p4ds : 1;
struct mmu_gather_batch *active;
struct mmu_gather_batch local;
void tlb_flush_mmu(struct mmu_gather *tlb);
void arch_tlb_finish_mmu(struct mmu_gather *tlb,
unsigned long start, unsigned long end, bool force);
+void tlb_flush_mmu_free(struct mmu_gather *tlb);
extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
int page_size);
tlb->start = TASK_SIZE;
tlb->end = 0;
}
+ tlb->freed_tables = 0;
+ tlb->cleared_ptes = 0;
+ tlb->cleared_pmds = 0;
+ tlb->cleared_puds = 0;
+ tlb->cleared_p4ds = 0;
}
static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
}
#endif
+static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb)
+{
+ if (tlb->cleared_ptes)
+ return PAGE_SHIFT;
+ if (tlb->cleared_pmds)
+ return PMD_SHIFT;
+ if (tlb->cleared_puds)
+ return PUD_SHIFT;
+ if (tlb->cleared_p4ds)
+ return P4D_SHIFT;
+
+ return PAGE_SHIFT;
+}
+
+static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
+{
+ return 1UL << tlb_get_unmap_shift(tlb);
+}
+
/*
* In the case of tlb vma handling, we can optimise these away in the
* case where we're doing a full MM flush. When we're doing a munmap,
#define tlb_remove_tlb_entry(tlb, ptep, address) \
do { \
__tlb_adjust_range(tlb, address, PAGE_SIZE); \
+ tlb->cleared_ptes = 1; \
__tlb_remove_tlb_entry(tlb, ptep, address); \
} while (0)
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
- do { \
- __tlb_adjust_range(tlb, address, huge_page_size(h)); \
- __tlb_remove_tlb_entry(tlb, ptep, address); \
+#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
+ do { \
+ unsigned long _sz = huge_page_size(h); \
+ __tlb_adjust_range(tlb, address, _sz); \
+ if (_sz == PMD_SIZE) \
+ tlb->cleared_pmds = 1; \
+ else if (_sz == PUD_SIZE) \
+ tlb->cleared_puds = 1; \
+ __tlb_remove_tlb_entry(tlb, ptep, address); \
} while (0)
/**
#define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \
do { \
__tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE); \
+ tlb->cleared_pmds = 1; \
__tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \
} while (0)
#define tlb_remove_pud_tlb_entry(tlb, pudp, address) \
do { \
__tlb_adjust_range(tlb, address, HPAGE_PUD_SIZE); \
+ tlb->cleared_puds = 1; \
__tlb_remove_pud_tlb_entry(tlb, pudp, address); \
} while (0)
#define pte_free_tlb(tlb, ptep, address) \
do { \
__tlb_adjust_range(tlb, address, PAGE_SIZE); \
+ tlb->freed_tables = 1; \
+ tlb->cleared_pmds = 1; \
__pte_free_tlb(tlb, ptep, address); \
} while (0)
#endif
#ifndef pmd_free_tlb
#define pmd_free_tlb(tlb, pmdp, address) \
do { \
- __tlb_adjust_range(tlb, address, PAGE_SIZE); \
+ __tlb_adjust_range(tlb, address, PAGE_SIZE); \
+ tlb->freed_tables = 1; \
+ tlb->cleared_puds = 1; \
__pmd_free_tlb(tlb, pmdp, address); \
} while (0)
#endif
#define pud_free_tlb(tlb, pudp, address) \
do { \
__tlb_adjust_range(tlb, address, PAGE_SIZE); \
+ tlb->freed_tables = 1; \
+ tlb->cleared_p4ds = 1; \
__pud_free_tlb(tlb, pudp, address); \
} while (0)
#endif
#ifndef p4d_free_tlb
#define p4d_free_tlb(tlb, pudp, address) \
do { \
- __tlb_adjust_range(tlb, address, PAGE_SIZE); \
+ __tlb_adjust_range(tlb, address, PAGE_SIZE); \
+ tlb->freed_tables = 1; \
__p4d_free_tlb(tlb, pudp, address); \
} while (0)
#endif
#endif
+#endif /* CONFIG_MMU */
+
#define tlb_migrate_finish(mm) do {} while (0)
#endif /* _ASM_GENERIC__TLB_H */
compat_size_t ss_size;
} compat_stack_t;
#endif
+#ifndef COMPAT_MINSIGSTKSZ
+#define COMPAT_MINSIGSTKSZ MINSIGSTKSZ
+#endif
#define compat_jiffies_to_clock_t(x) \
(((unsigned long)(x) * COMPAT_USER_HZ) / HZ)
}
static int
-do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp)
+do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp,
+ size_t min_ss_size)
{
struct task_struct *t = current;
ss_size = 0;
ss_sp = NULL;
} else {
- if (unlikely(ss_size < MINSIGSTKSZ))
+ if (unlikely(ss_size < min_ss_size))
return -ENOMEM;
}
if (uss && copy_from_user(&new, uss, sizeof(stack_t)))
return -EFAULT;
err = do_sigaltstack(uss ? &new : NULL, uoss ? &old : NULL,
- current_user_stack_pointer());
+ current_user_stack_pointer(),
+ MINSIGSTKSZ);
if (!err && uoss && copy_to_user(uoss, &old, sizeof(stack_t)))
err = -EFAULT;
return err;
stack_t new;
if (copy_from_user(&new, uss, sizeof(stack_t)))
return -EFAULT;
- (void)do_sigaltstack(&new, NULL, current_user_stack_pointer());
+ (void)do_sigaltstack(&new, NULL, current_user_stack_pointer(),
+ MINSIGSTKSZ);
/* squash all but EFAULT for now */
return 0;
}
uss.ss_size = uss32.ss_size;
}
ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss,
- compat_user_stack_pointer());
+ compat_user_stack_pointer(),
+ COMPAT_MINSIGSTKSZ);
if (ret >= 0 && uoss_ptr) {
compat_stack_t old;
memset(&old, 0, sizeof(old));
}
#if CRC_LE_BITS == 1
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len)
{
return crc32_le_generic(crc, p, len, NULL, CRC32_POLY_LE);
}
-u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len)
{
return crc32_le_generic(crc, p, len, NULL, CRC32C_POLY_LE);
}
#else
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len)
{
return crc32_le_generic(crc, p, len,
(const u32 (*)[256])crc32table_le, CRC32_POLY_LE);
}
-u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len)
{
return crc32_le_generic(crc, p, len,
(const u32 (*)[256])crc32ctable_le, CRC32C_POLY_LE);
EXPORT_SYMBOL(crc32_le);
EXPORT_SYMBOL(__crc32c_le);
+u32 crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le);
+u32 __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le);
+
/*
* This multiplies the polynomials x and y modulo the given modulus.
* This follows the "little-endian" CRC convention that the lsbit
mmu-y := nommu.o
mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \
- mlock.o mmap.o mprotect.o mremap.o msync.o \
- page_vma_mapped.o pagewalk.o pgtable-generic.o \
- rmap.o vmalloc.o
+ mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \
+ msync.o page_vma_mapped.o pagewalk.o \
+ pgtable-generic.o rmap.o vmalloc.o
ifdef CONFIG_CROSS_MEMORY_ATTACH
#endif /* SPLIT_RSS_COUNTING */
-#ifdef HAVE_GENERIC_MMU_GATHER
-
-static bool tlb_next_batch(struct mmu_gather *tlb)
-{
- struct mmu_gather_batch *batch;
-
- batch = tlb->active;
- if (batch->next) {
- tlb->active = batch->next;
- return true;
- }
-
- if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
- return false;
-
- batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
- if (!batch)
- return false;
-
- tlb->batch_count++;
- batch->next = NULL;
- batch->nr = 0;
- batch->max = MAX_GATHER_BATCH;
-
- tlb->active->next = batch;
- tlb->active = batch;
-
- return true;
-}
-
-void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- tlb->mm = mm;
-
- /* Is it from 0 to ~0? */
- tlb->fullmm = !(start | (end+1));
- tlb->need_flush_all = 0;
- tlb->local.next = NULL;
- tlb->local.nr = 0;
- tlb->local.max = ARRAY_SIZE(tlb->__pages);
- tlb->active = &tlb->local;
- tlb->batch_count = 0;
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
- tlb->batch = NULL;
-#endif
- tlb->page_size = 0;
-
- __tlb_reset_range(tlb);
-}
-
-static void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
- struct mmu_gather_batch *batch;
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
- tlb_table_flush(tlb);
-#endif
- for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
- free_pages_and_swap_cache(batch->pages, batch->nr);
- batch->nr = 0;
- }
- tlb->active = &tlb->local;
-}
-
-void tlb_flush_mmu(struct mmu_gather *tlb)
-{
- tlb_flush_mmu_tlbonly(tlb);
- tlb_flush_mmu_free(tlb);
-}
-
-/* tlb_finish_mmu
- * Called at the end of the shootdown operation to free up any resources
- * that were required.
- */
-void arch_tlb_finish_mmu(struct mmu_gather *tlb,
- unsigned long start, unsigned long end, bool force)
-{
- struct mmu_gather_batch *batch, *next;
-
- if (force)
- __tlb_adjust_range(tlb, start, end - start);
-
- tlb_flush_mmu(tlb);
-
- /* keep the page table cache within bounds */
- check_pgt_cache();
-
- for (batch = tlb->local.next; batch; batch = next) {
- next = batch->next;
- free_pages((unsigned long)batch, 0);
- }
- tlb->local.next = NULL;
-}
-
-/* __tlb_remove_page
- * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
- * handling the additional races in SMP caused by other CPUs caching valid
- * mappings in their TLBs. Returns the number of free page slots left.
- * When out of page slots we must call tlb_flush_mmu().
- *returns true if the caller should flush.
- */
-bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
-{
- struct mmu_gather_batch *batch;
-
- VM_BUG_ON(!tlb->end);
- VM_WARN_ON(tlb->page_size != page_size);
-
- batch = tlb->active;
- /*
- * Add the page and check if we are full. If so
- * force a flush.
- */
- batch->pages[batch->nr++] = page;
- if (batch->nr == batch->max) {
- if (!tlb_next_batch(tlb))
- return true;
- batch = tlb->active;
- }
- VM_BUG_ON_PAGE(batch->nr > batch->max, page);
-
- return false;
-}
-
-#endif /* HAVE_GENERIC_MMU_GATHER */
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-
-/*
- * See the comment near struct mmu_table_batch.
- */
-
-/*
- * If we want tlb_remove_table() to imply TLB invalidates.
- */
-static inline void tlb_table_invalidate(struct mmu_gather *tlb)
-{
-#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
- /*
- * Invalidate page-table caches used by hardware walkers. Then we still
- * need to RCU-sched wait while freeing the pages because software
- * walkers can still be in-flight.
- */
- tlb_flush_mmu_tlbonly(tlb);
-#endif
-}
-
-static void tlb_remove_table_smp_sync(void *arg)
-{
- /* Simply deliver the interrupt */
-}
-
-static void tlb_remove_table_one(void *table)
-{
- /*
- * This isn't an RCU grace period and hence the page-tables cannot be
- * assumed to be actually RCU-freed.
- *
- * It is however sufficient for software page-table walkers that rely on
- * IRQ disabling. See the comment near struct mmu_table_batch.
- */
- smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
- __tlb_remove_table(table);
-}
-
-static void tlb_remove_table_rcu(struct rcu_head *head)
-{
- struct mmu_table_batch *batch;
- int i;
-
- batch = container_of(head, struct mmu_table_batch, rcu);
-
- for (i = 0; i < batch->nr; i++)
- __tlb_remove_table(batch->tables[i]);
-
- free_page((unsigned long)batch);
-}
-
-void tlb_table_flush(struct mmu_gather *tlb)
-{
- struct mmu_table_batch **batch = &tlb->batch;
-
- if (*batch) {
- tlb_table_invalidate(tlb);
- call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
- *batch = NULL;
- }
-}
-
-void tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
- struct mmu_table_batch **batch = &tlb->batch;
-
- if (*batch == NULL) {
- *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
- if (*batch == NULL) {
- tlb_table_invalidate(tlb);
- tlb_remove_table_one(table);
- return;
- }
- (*batch)->nr = 0;
- }
-
- (*batch)->tables[(*batch)->nr++] = table;
- if ((*batch)->nr == MAX_TABLE_BATCH)
- tlb_table_flush(tlb);
-}
-
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
-
-/**
- * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
- * @tlb: the mmu_gather structure to initialize
- * @mm: the mm_struct of the target address space
- * @start: start of the region that will be removed from the page-table
- * @end: end of the region that will be removed from the page-table
- *
- * Called to initialize an (on-stack) mmu_gather structure for page-table
- * tear-down from @mm. The @start and @end are set to 0 and -1
- * respectively when @mm is without users and we're going to destroy
- * the full address space (exit/execve).
- */
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- arch_tlb_gather_mmu(tlb, mm, start, end);
- inc_tlb_flush_pending(tlb->mm);
-}
-
-void tlb_finish_mmu(struct mmu_gather *tlb,
- unsigned long start, unsigned long end)
-{
- /*
- * If there are parallel threads are doing PTE changes on same range
- * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB
- * flush by batching, a thread has stable TLB entry can fail to flush
- * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
- * forcefully if we detect parallel PTE batching threads.
- */
- bool force = mm_tlb_flush_nested(tlb->mm);
-
- arch_tlb_finish_mmu(tlb, start, end, force);
- dec_tlb_flush_pending(tlb->mm);
-}
-
/*
* Note: this doesn't free the actual pages themselves. That
* has been handled earlier when unmapping all the memory regions.
--- /dev/null
+#include <linux/gfp.h>
+#include <linux/highmem.h>
+#include <linux/kernel.h>
+#include <linux/mmdebug.h>
+#include <linux/mm_types.h>
+#include <linux/pagemap.h>
+#include <linux/rcupdate.h>
+#include <linux/smp.h>
+#include <linux/swap.h>
+
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+
+#ifdef HAVE_GENERIC_MMU_GATHER
+
+static bool tlb_next_batch(struct mmu_gather *tlb)
+{
+ struct mmu_gather_batch *batch;
+
+ batch = tlb->active;
+ if (batch->next) {
+ tlb->active = batch->next;
+ return true;
+ }
+
+ if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
+ return false;
+
+ batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
+ if (!batch)
+ return false;
+
+ tlb->batch_count++;
+ batch->next = NULL;
+ batch->nr = 0;
+ batch->max = MAX_GATHER_BATCH;
+
+ tlb->active->next = batch;
+ tlb->active = batch;
+
+ return true;
+}
+
+void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ tlb->mm = mm;
+
+ /* Is it from 0 to ~0? */
+ tlb->fullmm = !(start | (end+1));
+ tlb->need_flush_all = 0;
+ tlb->local.next = NULL;
+ tlb->local.nr = 0;
+ tlb->local.max = ARRAY_SIZE(tlb->__pages);
+ tlb->active = &tlb->local;
+ tlb->batch_count = 0;
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+ tlb->batch = NULL;
+#endif
+ tlb->page_size = 0;
+
+ __tlb_reset_range(tlb);
+}
+
+void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+ struct mmu_gather_batch *batch;
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+ tlb_table_flush(tlb);
+#endif
+ for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
+ free_pages_and_swap_cache(batch->pages, batch->nr);
+ batch->nr = 0;
+ }
+ tlb->active = &tlb->local;
+}
+
+void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+ tlb_flush_mmu_tlbonly(tlb);
+ tlb_flush_mmu_free(tlb);
+}
+
+/* tlb_finish_mmu
+ * Called at the end of the shootdown operation to free up any resources
+ * that were required.
+ */
+void arch_tlb_finish_mmu(struct mmu_gather *tlb,
+ unsigned long start, unsigned long end, bool force)
+{
+ struct mmu_gather_batch *batch, *next;
+
+ if (force) {
+ __tlb_reset_range(tlb);
+ __tlb_adjust_range(tlb, start, end - start);
+ }
+
+ tlb_flush_mmu(tlb);
+
+ /* keep the page table cache within bounds */
+ check_pgt_cache();
+
+ for (batch = tlb->local.next; batch; batch = next) {
+ next = batch->next;
+ free_pages((unsigned long)batch, 0);
+ }
+ tlb->local.next = NULL;
+}
+
+/* __tlb_remove_page
+ * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
+ * handling the additional races in SMP caused by other CPUs caching valid
+ * mappings in their TLBs. Returns the number of free page slots left.
+ * When out of page slots we must call tlb_flush_mmu().
+ *returns true if the caller should flush.
+ */
+bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
+{
+ struct mmu_gather_batch *batch;
+
+ VM_BUG_ON(!tlb->end);
+ VM_WARN_ON(tlb->page_size != page_size);
+
+ batch = tlb->active;
+ /*
+ * Add the page and check if we are full. If so
+ * force a flush.
+ */
+ batch->pages[batch->nr++] = page;
+ if (batch->nr == batch->max) {
+ if (!tlb_next_batch(tlb))
+ return true;
+ batch = tlb->active;
+ }
+ VM_BUG_ON_PAGE(batch->nr > batch->max, page);
+
+ return false;
+}
+
+#endif /* HAVE_GENERIC_MMU_GATHER */
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+
+/*
+ * See the comment near struct mmu_table_batch.
+ */
+
+/*
+ * If we want tlb_remove_table() to imply TLB invalidates.
+ */
+static inline void tlb_table_invalidate(struct mmu_gather *tlb)
+{
+#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
+ /*
+ * Invalidate page-table caches used by hardware walkers. Then we still
+ * need to RCU-sched wait while freeing the pages because software
+ * walkers can still be in-flight.
+ */
+ tlb_flush_mmu_tlbonly(tlb);
+#endif
+}
+
+static void tlb_remove_table_smp_sync(void *arg)
+{
+ /* Simply deliver the interrupt */
+}
+
+static void tlb_remove_table_one(void *table)
+{
+ /*
+ * This isn't an RCU grace period and hence the page-tables cannot be
+ * assumed to be actually RCU-freed.
+ *
+ * It is however sufficient for software page-table walkers that rely on
+ * IRQ disabling. See the comment near struct mmu_table_batch.
+ */
+ smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+ __tlb_remove_table(table);
+}
+
+static void tlb_remove_table_rcu(struct rcu_head *head)
+{
+ struct mmu_table_batch *batch;
+ int i;
+
+ batch = container_of(head, struct mmu_table_batch, rcu);
+
+ for (i = 0; i < batch->nr; i++)
+ __tlb_remove_table(batch->tables[i]);
+
+ free_page((unsigned long)batch);
+}
+
+void tlb_table_flush(struct mmu_gather *tlb)
+{
+ struct mmu_table_batch **batch = &tlb->batch;
+
+ if (*batch) {
+ tlb_table_invalidate(tlb);
+ call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
+ *batch = NULL;
+ }
+}
+
+void tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+ struct mmu_table_batch **batch = &tlb->batch;
+
+ if (*batch == NULL) {
+ *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+ if (*batch == NULL) {
+ tlb_table_invalidate(tlb);
+ tlb_remove_table_one(table);
+ return;
+ }
+ (*batch)->nr = 0;
+ }
+
+ (*batch)->tables[(*batch)->nr++] = table;
+ if ((*batch)->nr == MAX_TABLE_BATCH)
+ tlb_table_flush(tlb);
+}
+
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
+/**
+ * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
+ * @tlb: the mmu_gather structure to initialize
+ * @mm: the mm_struct of the target address space
+ * @start: start of the region that will be removed from the page-table
+ * @end: end of the region that will be removed from the page-table
+ *
+ * Called to initialize an (on-stack) mmu_gather structure for page-table
+ * tear-down from @mm. The @start and @end are set to 0 and -1
+ * respectively when @mm is without users and we're going to destroy
+ * the full address space (exit/execve).
+ */
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ arch_tlb_gather_mmu(tlb, mm, start, end);
+ inc_tlb_flush_pending(tlb->mm);
+}
+
+void tlb_finish_mmu(struct mmu_gather *tlb,
+ unsigned long start, unsigned long end)
+{
+ /*
+ * If there are parallel threads are doing PTE changes on same range
+ * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB
+ * flush by batching, a thread has stable TLB entry can fail to flush
+ * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
+ * forcefully if we detect parallel PTE batching threads.
+ */
+ bool force = mm_tlb_flush_nested(tlb->mm);
+
+ arch_tlb_finish_mmu(tlb, start, end, force);
+ dec_tlb_flush_pending(tlb->mm);
+}
static void update_vttbr(struct kvm *kvm)
{
phys_addr_t pgd_phys;
- u64 vmid;
+ u64 vmid, cnp = kvm_cpu_has_cnp() ? VTTBR_CNP_BIT : 0;
bool new_gen;
read_lock(&kvm_vmid_lock);
pgd_phys = virt_to_phys(kvm->arch.pgd);
BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
- kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid;
+ kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid | cnp;
write_unlock(&kvm_vmid_lock);
}